diff --git a/Documentation/DocBook/media/v4l/media-types.xml b/Documentation/DocBook/media/v4l/media-types.xml index 1af3842509105..0ee0f3386cdf3 100644 --- a/Documentation/DocBook/media/v4l/media-types.xml +++ b/Documentation/DocBook/media/v4l/media-types.xml @@ -56,10 +56,6 @@ MEDIA_ENT_F_CONN_COMPOSITE Connector for a RGB composite signal. - - MEDIA_ENT_F_CONN_TEST - Connector for a test generator. - MEDIA_ENT_F_CAM_SENSOR Camera video sensor entity. diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt index a2bd593881cab..66422d6631841 100644 --- a/Documentation/devicetree/bindings/arm/omap/omap.txt +++ b/Documentation/devicetree/bindings/arm/omap/omap.txt @@ -23,6 +23,7 @@ Optional properties: during suspend. - ti,no-reset-on-init: When present, the module should not be reset at init - ti,no-idle-on-init: When present, the module should not be idled at init +- ti,no-idle: When present, the module is never allowed to idle. Example: diff --git a/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt new file mode 100644 index 0000000000000..f6f1c14bf99bd --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt @@ -0,0 +1,26 @@ +Alpine MSIX controller + +See arm,gic-v3.txt for SPI and MSI definitions. + +Required properties: + +- compatible: should be "al,alpine-msix" +- reg: physical base address and size of the registers +- interrupt-parent: specifies the parent interrupt controller. +- interrupt-controller: identifies the node as an interrupt controller +- msi-controller: identifies the node as an PCI Message Signaled Interrupt + controller +- al,msi-base-spi: SPI base of the MSI frame +- al,msi-num-spis: number of SPIs assigned to the MSI frame, relative to SPI0 + +Example: + +msix: msix { + compatible = "al,alpine-msix"; + reg = <0x0 0xfbe00000 0x0 0x100000>; + interrupt-parent = <&gic>; + interrupt-controller; + msi-controller; + al,msi-base-spi = <160>; + al,msi-num-spis = <160>; +}; diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt index 5a1cb4bc3dfe8..793c20ff8fccc 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt @@ -16,6 +16,7 @@ Main node required properties: "arm,cortex-a15-gic" "arm,cortex-a7-gic" "arm,cortex-a9-gic" + "arm,eb11mp-gic" "arm,gic-400" "arm,pl390" "arm,tc11mp-gic" diff --git a/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt new file mode 100644 index 0000000000000..8af0a8e613abe --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt @@ -0,0 +1,44 @@ + +* Marvell ODMI for MSI support + +Some Marvell SoCs have an On-Die Message Interrupt (ODMI) controller +which can be used by on-board peripheral for MSI interrupts. + +Required properties: + +- compatible : The value here should contain: + + "marvell,ap806-odmi-controller", "marvell,odmi-controller". + +- interrupt,controller : Identifies the node as an interrupt controller. + +- msi-controller : Identifies the node as an MSI controller. + +- marvell,odmi-frames : Number of ODMI frames available. Each frame + provides a number of events. + +- reg : List of register definitions, one for each + ODMI frame. + +- marvell,spi-base : List of GIC base SPI interrupts, one for each + ODMI frame. Those SPI interrupts are 0-based, + i.e marvell,spi-base = <128> will use SPI #96. + See Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt + for details about the GIC Device Tree binding. + +- interrupt-parent : Reference to the parent interrupt controller. + +Example: + + odmi: odmi@300000 { + compatible = "marvell,ap806-odm-controller", + "marvell,odmi-controller"; + interrupt-controller; + msi-controller; + marvell,odmi-frames = <4>; + reg = <0x300000 0x4000>, + <0x304000 0x4000>, + <0x308000 0x4000>, + <0x30C000 0x4000>; + marvell,spi-base = <128>, <136>, <144>, <152>; + }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt b/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt index aae4c384ee1f2..173595305e266 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt @@ -23,6 +23,12 @@ Optional properties: - mti,reserved-cpu-vectors : Specifies the list of CPU interrupt vectors to which the GIC may not route interrupts. Valid values are 2 - 7. This property is ignored if the CPU is started in EIC mode. +- mti,reserved-ipi-vectors : Specifies the range of GIC interrupts that are + reserved for IPIs. + It accepts 2 values, the 1st is the starting interrupt and the 2nd is the size + of the reserved range. + If not specified, the driver will allocate the last 2 * number of VPEs in the + system. Required properties for timer sub-node: - compatible : Should be "mti,gic-timer". @@ -44,6 +50,7 @@ Example: #interrupt-cells = <3>; mti,reserved-cpu-vectors = <7>; + mti,reserved-ipi-vectors = <40 8>; timer { compatible = "mti,gic-timer"; diff --git a/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt new file mode 100644 index 0000000000000..1f441fa0ad401 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt @@ -0,0 +1,49 @@ +Sigma Designs SMP86xx/SMP87xx secondary interrupt controller + +Required properties: +- compatible: should be "sigma,smp8642-intc" +- reg: physical address of MMIO region +- ranges: address space mapping of child nodes +- interrupt-parent: phandle of parent interrupt controller +- interrupt-controller: boolean +- #address-cells: should be <1> +- #size-cells: should be <1> + +One child node per control block with properties: +- reg: address of registers for this control block +- interrupt-controller: boolean +- #interrupt-cells: should be <2>, interrupt index and flags per interrupts.txt +- interrupts: interrupt spec of primary interrupt controller + +Example: + +interrupt-controller@6e000 { + compatible = "sigma,smp8642-intc"; + reg = <0x6e000 0x400>; + ranges = <0x0 0x6e000 0x400>; + interrupt-parent = <&gic>; + interrupt-controller; + #address-cells = <1>; + #size-cells = <1>; + + irq0: interrupt-controller@0 { + reg = <0x000 0x100>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + + irq1: interrupt-controller@100 { + reg = <0x100 0x100>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + + irq2: interrupt-controller@300 { + reg = <0x300 0x100>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; +}; diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9a53c929f017d..4d9ca7d92a20a 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -666,7 +666,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. clearcpuid=BITNUM [X86] Disable CPUID feature X for the kernel. See - arch/x86/include/asm/cpufeature.h for the valid bit + arch/x86/include/asm/cpufeatures.h for the valid bit numbers. Note the Linux specific bits are not necessarily stable over kernel options, but the vendor specific ones should be. @@ -1687,6 +1687,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. ip= [IP_PNP] See Documentation/filesystems/nfs/nfsroot.txt. + irqaffinity= [SMP] Set the default irq affinity mask + Format: + ,..., + or + - + (must be a positive range in ascending order) + or a mixture + ,...,- + irqfixup [HW] When an interrupt is not handled search all handlers for it. Intended to get systems with badly broken @@ -2566,6 +2575,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nointroute [IA-64] + noinvpcid [X86] Disable the INVPCID cpu feature. + nojitter [IA-64] Disables jitter checking for ITC timers. no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver @@ -3491,6 +3502,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. ro [KNL] Mount root device read-only on boot + rodata= [KNL] + on Mark read-only kernel memory as read-only (default). + off Leave read-only kernel memory writable for debugging. + root= [KNL] Root filesystem See name_to_dev_t comment in init/do_mounts.c. @@ -3528,6 +3543,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. sched_debug [KNL] Enables verbose scheduler debug messages. + schedstats= [KNL,X86] Enable or disable scheduled statistics. + Allowed values are enable and disable. This feature + incurs a small amount of overhead in the scheduler + but is useful for debugging and performance tuning. + skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate xtime_lock contention on larger systems, and/or RCU lock contention on all systems with CONFIG_MAXSMP set. diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c index 6c6247aaa7b93..d99012f41602a 100644 --- a/Documentation/ptp/testptp.c +++ b/Documentation/ptp/testptp.c @@ -277,13 +277,15 @@ int main(int argc, char *argv[]) " %d external time stamp channels\n" " %d programmable periodic signals\n" " %d pulse per second\n" - " %d programmable pins\n", + " %d programmable pins\n" + " %d cross timestamping\n", caps.max_adj, caps.n_alarm, caps.n_ext_ts, caps.n_per_out, caps.pps, - caps.n_pins); + caps.n_pins, + caps.cross_timestamping); } } diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index a93b414672a71..f4444c94ff285 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -58,6 +58,8 @@ show up in /proc/sys/kernel: - panic_on_stackoverflow - panic_on_unrecovered_nmi - panic_on_warn +- perf_cpu_time_max_percent +- perf_event_paranoid - pid_max - powersave-nap [ PPC only ] - printk @@ -639,6 +641,17 @@ allowed to execute. ============================================================== +perf_event_paranoid: + +Controls use of the performance events system by unprivileged +users (without CAP_SYS_ADMIN). The default value is 1. + + -1: Allow use of (almost) all events by all users +>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK +>=1: Disallow CPU event access by users without CAP_SYS_ADMIN +>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN + +============================================================== pid_max: @@ -760,6 +773,14 @@ rtsig-nr shows the number of RT signals currently queued. ============================================================== +sched_schedstats: + +Enables/disables scheduler statistics. Enabling this feature +incurs a small amount of overhead in the scheduler but is +useful for debugging and performance tuning. + +============================================================== + sg-big-buff: This file shows the size of the generic SCSI (sg) buffer. diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index daf9c0f742d22..c81731096a433 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -358,7 +358,8 @@ In the first case there are two additional complications: - if CR4.SMEP is enabled: since we've turned the page into a kernel page, the kernel may now execute it. We handle this by also setting spte.nx. If we get a user fetch or read fault, we'll change spte.u=1 and - spte.nx=gpte.nx back. + spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when + shadow paging is in use. - if CR4.SMAP is disabled: since the page has been changed to a kernel page, it can not be reused when CR4.SMAP is enabled. We set CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note, diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt index 9f9ec9f760394..4e4b6f10d8410 100644 --- a/Documentation/watchdog/watchdog-parameters.txt +++ b/Documentation/watchdog/watchdog-parameters.txt @@ -400,3 +400,7 @@ wm8350_wdt: nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) ------------------------------------------------- +sun4v_wdt: +timeout_ms: Watchdog timeout in milliseconds 1..180000, default=60000) +nowayout: Watchdog cannot be stopped once started +------------------------------------------------- diff --git a/Documentation/x86/early-microcode.txt b/Documentation/x86/early-microcode.txt index d62bea6796dad..c956d99cf1de4 100644 --- a/Documentation/x86/early-microcode.txt +++ b/Documentation/x86/early-microcode.txt @@ -40,3 +40,28 @@ cp ../microcode.bin kernel/x86/microcode/GenuineIntel.bin (or AuthenticAMD.bin) find . | cpio -o -H newc >../ucode.cpio cd .. cat ucode.cpio /boot/initrd-3.5.0.img >/boot/initrd-3.5.0.ucode.img + +Builtin microcode +================= + +We can also load builtin microcode supplied through the regular firmware +builtin method CONFIG_FIRMWARE_IN_KERNEL. Here's an example: + +CONFIG_FIRMWARE_IN_KERNEL=y +CONFIG_EXTRA_FIRMWARE="intel-ucode/06-3a-09 amd-ucode/microcode_amd_fam15h.bin" +CONFIG_EXTRA_FIRMWARE_DIR="/lib/firmware" + +This basically means, you have the following tree structure locally: + +/lib/firmware/ +|-- amd-ucode +... +| |-- microcode_amd_fam15h.bin +... +|-- intel-ucode +... +| |-- 06-3a-09 +... + +so that the build system can find those files and integrate them into +the final kernel image. The early loader finds them and applies them. diff --git a/Documentation/x86/exception-tables.txt b/Documentation/x86/exception-tables.txt index 32901aa36f0a9..e396bcd8d8304 100644 --- a/Documentation/x86/exception-tables.txt +++ b/Documentation/x86/exception-tables.txt @@ -290,3 +290,38 @@ Due to the way that the exception table is built and needs to be ordered, only use exceptions for code in the .text section. Any other section will cause the exception table to not be sorted correctly, and the exceptions will fail. + +Things changed when 64-bit support was added to x86 Linux. Rather than +double the size of the exception table by expanding the two entries +from 32-bits to 64 bits, a clever trick was used to store addresses +as relative offsets from the table itself. The assembly code changed +from: + .long 1b,3b +to: + .long (from) - . + .long (to) - . + +and the C-code that uses these values converts back to absolute addresses +like this: + + ex_insn_addr(const struct exception_table_entry *x) + { + return (unsigned long)&x->insn + x->insn; + } + +In v4.6 the exception table entry was expanded with a new field "handler". +This is also 32-bits wide and contains a third relative function +pointer which points to one of: + +1) int ex_handler_default(const struct exception_table_entry *fixup) + This is legacy case that just jumps to the fixup code +2) int ex_handler_fault(const struct exception_table_entry *fixup) + This case provides the fault number of the trap that occurred at + entry->insn. It is used to distinguish page faults from machine + check. +3) int ex_handler_ext(const struct exception_table_entry *fixup) + This case is used for uaccess_err ... we need to set a flag + in the task structure. Before the handler functions existed this + case was handled by adding a large offset to the fixup to tag + it as special. +More functions can easily be added. diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index 68ed3114c363b..0965a71f99424 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt @@ -60,6 +60,8 @@ Machine check threshold to 1. Enabling this may make memory predictive failure analysis less effective if the bios sets thresholds for memory errors since we will not see details for all errors. + mce=recovery + Force-enable recoverable machine check code paths nomce (for compatibility with i386): same as mce=off diff --git a/MAINTAINERS b/MAINTAINERS index da3e4d8016d0f..57adf395a61f9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2422,6 +2422,7 @@ F: arch/mips/bmips/* F: arch/mips/include/asm/mach-bmips/* F: arch/mips/kernel/*bmips* F: arch/mips/boot/dts/brcm/bcm*.dts* +F: drivers/irqchip/irq-bcm63* F: drivers/irqchip/irq-bcm7* F: drivers/irqchip/irq-brcmstb* F: include/linux/bcm963xx_nvram.h @@ -4518,6 +4519,12 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/dma/fsldma.* +FREESCALE GPMI NAND DRIVER +M: Han Xu +L: linux-mtd@lists.infradead.org +S: Maintained +F: drivers/mtd/nand/gpmi-nand/* + FREESCALE I2C CPM DRIVER M: Jochen Friedrich L: linuxppc-dev@lists.ozlabs.org @@ -4534,7 +4541,7 @@ F: include/linux/platform_data/video-imxfb.h F: drivers/video/fbdev/imxfb.c FREESCALE QUAD SPI DRIVER -M: Han Xu +M: Han Xu L: linux-mtd@lists.infradead.org S: Maintained F: drivers/mtd/spi-nor/fsl-quadspi.c @@ -4548,6 +4555,15 @@ S: Maintained F: drivers/net/ethernet/freescale/fs_enet/ F: include/linux/fs_enet_pd.h +FREESCALE IMX / MXC FEC DRIVER +M: Fugang Duan +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/fec_main.c +F: drivers/net/ethernet/freescale/fec_ptp.c +F: drivers/net/ethernet/freescale/fec.h +F: Documentation/devicetree/bindings/net/fsl-fec.txt + FREESCALE QUICC ENGINE LIBRARY L: linuxppc-dev@lists.ozlabs.org S: Orphan @@ -6764,6 +6780,7 @@ S: Maintained F: Documentation/networking/mac80211-injection.txt F: include/net/mac80211.h F: net/mac80211/ +F: drivers/net/wireless/mac80211_hwsim.[ch] MACVLAN DRIVER M: Patrick McHardy @@ -7383,6 +7400,17 @@ W: https://www.myricom.com/support/downloads/myri10ge.html S: Supported F: drivers/net/ethernet/myricom/myri10ge/ +NAND FLASH SUBSYSTEM +M: Boris Brezillon +R: Richard Weinberger +L: linux-mtd@lists.infradead.org +W: http://www.linux-mtd.infradead.org/ +Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ +T: git git://github.com/linux-nand/linux.git +S: Maintained +F: drivers/mtd/nand/ +F: include/linux/mtd/nand*.h + NATSEMI ETHERNET DRIVER (DP8381x) S: Orphan F: drivers/net/ethernet/natsemi/natsemi.c @@ -8448,6 +8476,7 @@ PERFORMANCE EVENTS SUBSYSTEM M: Peter Zijlstra M: Ingo Molnar M: Arnaldo Carvalho de Melo +R: Alexander Shishkin L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core S: Supported diff --git a/Makefile b/Makefile index af6e5f893d56e..7b3ecdcdc6c18 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 2f24447fef920..46bf263c31531 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -168,7 +168,7 @@ smp_callin(void) cpuid, current, current->active_mm)); preempt_disable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } /* Wait until hwrpb->txrdy is clear for cpu. Return -1 on timeout. */ diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 424e937da5c89..4cb3add77c75c 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -142,7 +142,7 @@ void start_kernel_secondary(void) local_irq_enable(); preempt_disable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } /* diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 7a6a58ef8aaf8..43788b1a1ac5e 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -195,5 +195,7 @@ CFLAGS_font.o := -Dstatic= $(obj)/font.c: $(FONTC) $(call cmd,shipped) +AFLAGS_hyp-stub.o := -Wa,-march=armv7-a + $(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S $(call cmd,shipped) diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts index 23fc670c04277..5c21b236721fc 100644 --- a/arch/arm/boot/dts/armada-xp-axpwifiap.dts +++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts @@ -70,8 +70,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index f774101416a55..ebe1d267406df 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -76,8 +76,8 @@ ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 4878d7353069f..5730b875c4f51 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -95,8 +95,8 @@ ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts index fb9e1bbf23385..8af463f26ea1e 100644 --- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts +++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts @@ -65,8 +65,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index 6e9820e141f8d..b89e6cf1271a1 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -70,8 +70,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts index 6ab33837a2b6d..6522b04f4a8e7 100644 --- a/arch/arm/boot/dts/armada-xp-matrix.dts +++ b/arch/arm/boot/dts/armada-xp-matrix.dts @@ -68,8 +68,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; internal-regs { serial@12000 { diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index 62175a8848bc2..d19f44c709257 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -64,8 +64,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index a5db17782e085..853bd392a4fe2 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -65,9 +65,9 @@ soc { ranges = ; + MBUS_ID(0x01, 0x2f) 0 0 0xe8000000 0x8000000 + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-synology-ds414.dts b/arch/arm/boot/dts/armada-xp-synology-ds414.dts index 2391b11dc546b..d17dab0a6f513 100644 --- a/arch/arm/boot/dts/armada-xp-synology-ds414.dts +++ b/arch/arm/boot/dts/armada-xp-synology-ds414.dts @@ -78,8 +78,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index c4d9175b90dce..f82aa44c3ceed 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1500,6 +1500,16 @@ 0x48485200 0x2E00>; #address-cells = <1>; #size-cells = <1>; + + /* + * Do not allow gating of cpsw clock as workaround + * for errata i877. Keeping internal clock disabled + * causes the device switching characteristics + * to degrade over time and eventually fail to meet + * the data manual delay time/skew specs. + */ + ti,no-idle; + /* * rx_thresh_pend * rx_pend diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts index 6713b1ea732b0..01d239c3eaaaa 100644 --- a/arch/arm/boot/dts/r8a7791-porter.dts +++ b/arch/arm/boot/dts/r8a7791-porter.dts @@ -283,7 +283,6 @@ pinctrl-names = "default"; status = "okay"; - renesas,enable-gpio = <&gpio5 31 GPIO_ACTIVE_HIGH>; }; &usbphy { diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index d5525bfc7e3e6..9156fc303afd8 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -491,7 +491,6 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif #ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); void set_kernel_text_rw(void); void set_kernel_text_ro(void); #else diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 2c5f160be65e4..ad325a8c7e1e5 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -88,6 +88,7 @@ obj-$(CONFIG_DEBUG_LL) += debug.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o +AFLAGS_hyp-stub.o :=-Wa,-march=armv7-a ifeq ($(CONFIG_ARM_PSCI),y) obj-$(CONFIG_SMP) += psci_smp.o endif diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 7d0cba6f1cc5e..139791ed473d5 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -176,13 +176,13 @@ static struct resource mem_res[] = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM }, { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM } }; @@ -851,7 +851,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) res->name = "System RAM"; res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 37312f6749f3d..baee70267f293 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -409,7 +409,7 @@ asmlinkage void secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index dda1959f0ddeb..08e49c423c241 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -506,18 +506,18 @@ static void kvm_arm_resume_guest(struct kvm *kvm) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); vcpu->arch.pause = false; - wake_up_interruptible(wq); + swake_up(wq); } } static void vcpu_sleep(struct kvm_vcpu *vcpu) { - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - wait_event_interruptible(*wq, ((!vcpu->arch.power_off) && + swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && (!vcpu->arch.pause))); } diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 5fa69d7bae58a..99361f11354a0 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -161,7 +161,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_core_regs(void) diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index a9b3b905e661d..c2b131527a643 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -70,7 +70,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) { struct kvm *kvm = source_vcpu->kvm; struct kvm_vcpu *vcpu = NULL; - wait_queue_head_t *wq; + struct swait_queue_head *wq; unsigned long cpu_id; unsigned long context_id; phys_addr_t target_pc; @@ -119,7 +119,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) smp_mb(); /* Make sure the above is visible */ wq = kvm_arch_vcpu_wq(vcpu); - wake_up_interruptible(wq); + swake_up(wq); return PSCI_RET_SUCCESS; } diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c index 77d6b1bab2782..ee06fabdf60e6 100644 --- a/arch/arm/mach-lpc32xx/phy3250.c +++ b/arch/arm/mach-lpc32xx/phy3250.c @@ -86,8 +86,8 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb) { dma_addr_t dma; - fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, - PANEL_SIZE, &dma, GFP_KERNEL); + fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, PANEL_SIZE, &dma, + GFP_KERNEL); if (!fb->fb.screen_base) { printk(KERN_ERR "CLCD: unable to map framebuffer\n"); return -ENOMEM; @@ -116,15 +116,14 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb) static int lpc32xx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, - fb->fb.screen_base, fb->fb.fix.smem_start, - fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } static void lpc32xx_clcd_remove(struct clcd_fb *fb) { - dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, - fb->fb.screen_base, fb->fb.fix.smem_start); + dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, + fb->fb.fix.smem_start); } /* diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig index 64e3d2ce9a076..b003e3afd6930 100644 --- a/arch/arm/mach-mvebu/Kconfig +++ b/arch/arm/mach-mvebu/Kconfig @@ -3,7 +3,6 @@ menuconfig ARCH_MVEBU depends on ARCH_MULTI_V7 || ARCH_MULTI_V5 select ARCH_SUPPORTS_BIG_ENDIAN select CLKSRC_MMIO - select GENERIC_IRQ_CHIP select PINCTRL select PLAT_ORION select SOC_BUS @@ -29,6 +28,7 @@ config MACH_ARMADA_370 bool "Marvell Armada 370 boards" depends on ARCH_MULTI_V7 select ARMADA_370_CLK + select ARMADA_370_XP_IRQ select CPU_PJ4B select MACH_MVEBU_V7 select PINCTRL_ARMADA_370 @@ -39,6 +39,7 @@ config MACH_ARMADA_370 config MACH_ARMADA_375 bool "Marvell Armada 375 boards" depends on ARCH_MULTI_V7 + select ARMADA_370_XP_IRQ select ARM_ERRATA_720789 select ARM_ERRATA_753970 select ARM_GIC @@ -58,6 +59,7 @@ config MACH_ARMADA_38X select ARM_ERRATA_720789 select ARM_ERRATA_753970 select ARM_GIC + select ARMADA_370_XP_IRQ select ARMADA_38X_CLK select HAVE_ARM_SCU select HAVE_ARM_TWD if SMP @@ -72,6 +74,7 @@ config MACH_ARMADA_39X bool "Marvell Armada 39x boards" depends on ARCH_MULTI_V7 select ARM_GIC + select ARMADA_370_XP_IRQ select ARMADA_39X_CLK select CACHE_L2X0 select HAVE_ARM_SCU @@ -86,6 +89,7 @@ config MACH_ARMADA_39X config MACH_ARMADA_XP bool "Marvell Armada XP boards" depends on ARCH_MULTI_V7 + select ARMADA_370_XP_IRQ select ARMADA_XP_CLK select CPU_PJ4B select MACH_MVEBU_V7 diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c index d122ee6ab9913..8814ee5e98fd5 100644 --- a/arch/arm/mach-netx/fb.c +++ b/arch/arm/mach-netx/fb.c @@ -42,8 +42,8 @@ int netx_clcd_setup(struct clcd_fb *fb) fb->panel = netx_panel; - fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, 1024*1024, - &dma, GFP_KERNEL); + fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma, + GFP_KERNEL); if (!fb->fb.screen_base) { printk(KERN_ERR "CLCD: unable to map framebuffer\n"); return -ENOMEM; @@ -57,16 +57,14 @@ int netx_clcd_setup(struct clcd_fb *fb) int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, - fb->fb.screen_base, - fb->fb.fix.smem_start, - fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } void netx_clcd_remove(struct clcd_fb *fb) { - dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, - fb->fb.screen_base, fb->fb.fix.smem_start); + dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, + fb->fb.fix.smem_start); } static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL); diff --git a/arch/arm/mach-nspire/clcd.c b/arch/arm/mach-nspire/clcd.c index abea12617b173..ea0e5b2ca1cd4 100644 --- a/arch/arm/mach-nspire/clcd.c +++ b/arch/arm/mach-nspire/clcd.c @@ -90,8 +90,8 @@ int nspire_clcd_setup(struct clcd_fb *fb) panel_size = ((panel->mode.xres * panel->mode.yres) * panel->bpp) / 8; panel_size = ALIGN(panel_size, PAGE_SIZE); - fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, - panel_size, &dma, GFP_KERNEL); + fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, panel_size, &dma, + GFP_KERNEL); if (!fb->fb.screen_base) { pr_err("CLCD: unable to map framebuffer\n"); @@ -107,13 +107,12 @@ int nspire_clcd_setup(struct clcd_fb *fb) int nspire_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, - fb->fb.screen_base, fb->fb.fix.smem_start, - fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } void nspire_clcd_remove(struct clcd_fb *fb) { - dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, - fb->fb.screen_base, fb->fb.fix.smem_start); + dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, + fb->fb.fix.smem_start); } diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index e9f65fec55c0b..b6d62e4cdfdda 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2200,6 +2200,11 @@ static int _enable(struct omap_hwmod *oh) */ static int _idle(struct omap_hwmod *oh) { + if (oh->flags & HWMOD_NO_IDLE) { + oh->_int_flags |= _HWMOD_SKIP_ENABLE; + return 0; + } + pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { @@ -2504,6 +2509,8 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + if (of_find_property(np, "ti,no-idle", NULL)) + oh->flags |= HWMOD_NO_IDLE; } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -2630,7 +2637,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh) * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data - * it should be set by the core code as a runtime flag during startup */ - if ((oh->flags & HWMOD_INIT_NO_IDLE) && + if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) && (postsetup_state == _HWMOD_STATE_IDLE)) { oh->_int_flags |= _HWMOD_SKIP_ENABLE; postsetup_state = _HWMOD_STATE_ENABLED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 76bce11c85a40..7c7a31169475b 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -525,6 +525,8 @@ struct omap_hwmod_omap4_prcm { * or idled. * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to * operate and they need to be handled at the same time as the main_clk. + * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain + * IPs like CPSW on DRA7, where clocks to this module cannot be disabled. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -541,6 +543,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) #define HWMOD_OPT_CLKS_NEEDED (1 << 14) +#define HWMOD_NO_IDLE (1 << 15) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c index cf30daff89325..d19b1ad29b075 100644 --- a/arch/arm/mm/pageattr.c +++ b/arch/arm/mm/pageattr.c @@ -49,6 +49,9 @@ static int change_memory_common(unsigned long addr, int numpages, WARN_ON_ONCE(1); } + if (!numpages) + return 0; + if (start < MODULES_VADDR || start >= MODULES_END) return -EINVAL; diff --git a/arch/arm/plat-samsung/pm-check.c b/arch/arm/plat-samsung/pm-check.c index 04aff2c31b460..70f2f699bed3e 100644 --- a/arch/arm/plat-samsung/pm-check.c +++ b/arch/arm/plat-samsung/pm-check.c @@ -53,8 +53,8 @@ static void s3c_pm_run_res(struct resource *ptr, run_fn_t fn, u32 *arg) if (ptr->child != NULL) s3c_pm_run_res(ptr->child, fn, arg); - if ((ptr->flags & IORESOURCE_MEM) && - strcmp(ptr->name, "System RAM") == 0) { + if ((ptr->flags & IORESOURCE_SYSTEM_RAM) + == IORESOURCE_SYSTEM_RAM) { S3C_PMDBG("Found system RAM at %08lx..%08lx\n", (unsigned long)ptr->start, (unsigned long)ptr->end); diff --git a/arch/arm/vdso/vdso.S b/arch/arm/vdso/vdso.S index b2b97e3e7babb..a62a7b64f49c5 100644 --- a/arch/arm/vdso/vdso.S +++ b/arch/arm/vdso/vdso.S @@ -23,9 +23,8 @@ #include #include - __PAGE_ALIGNED_DATA - .globl vdso_start, vdso_end + .section .data..ro_after_init .balign PAGE_SIZE vdso_start: .incbin "arch/arm/vdso/vdso.so" diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 7fc294c3bc5ba..22dda613f9c91 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -156,8 +156,4 @@ int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); -#endif - #endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bf464de33f52f..819aff5d593f7 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,7 +34,7 @@ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. * - * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). * VMALLOC_START: beginning of the kernel VA space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, @@ -51,7 +51,9 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 8119479147db1..450987d99b9b9 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -73,13 +73,13 @@ static struct resource mem_res[] = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM }, { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM } }; @@ -210,7 +210,7 @@ static void __init request_standard_resources(void) res->name = "System RAM"; res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index e33fe33876ab3..fd10eb6638689 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -145,6 +145,10 @@ ENTRY(cpu_resume_mmu) ENDPROC(cpu_resume_mmu) .popsection cpu_resume_after_mmu: +#ifdef CONFIG_KASAN + mov x0, sp + bl kasan_unpoison_remaining_stack +#endif mov x0, #0 // return zero on success ldp x19, x20, [sp, #16] ldp x21, x22, [sp, #32] diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index b1adc51b2c2e7..460765799c642 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -195,7 +195,7 @@ asmlinkage void secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index fcb778899a380..9e54ad7c240ac 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -194,7 +194,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } /** diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 82d607c3614ed..da30529bb1f65 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -306,10 +306,6 @@ static __init int setup_hugepagesz(char *opt) hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); - } else if (ps == (PAGE_SIZE * CONT_PTES)) { - hugetlb_add_hstate(CONT_PTE_SHIFT); - } else if (ps == (PMD_SIZE * CONT_PMDS)) { - hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); return 0; @@ -317,13 +313,3 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); - -#ifdef CONFIG_ARM64_64K_PAGES -static __init int add_default_hugepagesz(void) -{ - if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) - hugetlb_add_hstate(CONT_PMD_SHIFT); - return 0; -} -arch_initcall(add_default_hugepagesz); -#endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index f3b061e67bfe0..7802f216a67a5 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -319,8 +319,8 @@ void __init mem_init(void) #endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG((unsigned long)vmemmap, - (unsigned long)vmemmap + VMEMMAP_SIZE), + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), MLM((unsigned long)virt_to_page(PAGE_OFFSET), (unsigned long)virt_to_page(high_memory)), #endif diff --git a/arch/avr32/kernel/setup.c b/arch/avr32/kernel/setup.c index 209ae5ad34958..e6928896da2a4 100644 --- a/arch/avr32/kernel/setup.c +++ b/arch/avr32/kernel/setup.c @@ -49,13 +49,13 @@ static struct resource __initdata kernel_data = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM, + .flags = IORESOURCE_SYSTEM_RAM, }; static struct resource __initdata kernel_code = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM, + .flags = IORESOURCE_SYSTEM_RAM, .sibling = &kernel_data, }; @@ -134,7 +134,7 @@ add_physical_memory(resource_size_t start, resource_size_t end) new->start = start; new->end = end; new->name = "System RAM"; - new->flags = IORESOURCE_MEM; + new->flags = IORESOURCE_SYSTEM_RAM; *pprev = new; } diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 0030e21cfceb3..23c4ef5f8bdce 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -333,7 +333,7 @@ void secondary_start_kernel(void) /* We are done with local CPU inits, unblock the boot CPU. */ set_cpu_online(cpu, true); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void __init smp_prepare_boot_cpu(void) diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c index 72e17f7ebd6ff..786e36e2f61de 100644 --- a/arch/c6x/kernel/setup.c +++ b/arch/c6x/kernel/setup.c @@ -281,8 +281,6 @@ notrace void __init machine_init(unsigned long dt_ptr) */ set_ist(_vectors_start); - lockdep_init(); - /* * dtb is passed in from bootloader. * fdt is linked in blob. diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index ff759f26b96ae..983bae7d2665c 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -180,7 +180,7 @@ void start_secondary(void) local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index caae3f4e4341a..300dac3702f11 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -1178,7 +1178,7 @@ efi_initialize_iomem_resources(struct resource *code_resource, efi_memory_desc_t *md; u64 efi_desc_size; char *name; - unsigned long flags; + unsigned long flags, desc; efi_map_start = __va(ia64_boot_param->efi_memmap); efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size; @@ -1193,6 +1193,8 @@ efi_initialize_iomem_resources(struct resource *code_resource, continue; flags = IORESOURCE_MEM | IORESOURCE_BUSY; + desc = IORES_DESC_NONE; + switch (md->type) { case EFI_MEMORY_MAPPED_IO: @@ -1207,14 +1209,17 @@ efi_initialize_iomem_resources(struct resource *code_resource, if (md->attribute & EFI_MEMORY_WP) { name = "System ROM"; flags |= IORESOURCE_READONLY; - } else if (md->attribute == EFI_MEMORY_UC) + } else if (md->attribute == EFI_MEMORY_UC) { name = "Uncached RAM"; - else + } else { name = "System RAM"; + flags |= IORESOURCE_SYSRAM; + } break; case EFI_ACPI_MEMORY_NVS: name = "ACPI Non-volatile Storage"; + desc = IORES_DESC_ACPI_NV_STORAGE; break; case EFI_UNUSABLE_MEMORY: @@ -1224,6 +1229,7 @@ efi_initialize_iomem_resources(struct resource *code_resource, case EFI_PERSISTENT_MEMORY: name = "Persistent Memory"; + desc = IORES_DESC_PERSISTENT_MEMORY; break; case EFI_RESERVED_TYPE: @@ -1246,6 +1252,7 @@ efi_initialize_iomem_resources(struct resource *code_resource, res->start = md->phys_addr; res->end = md->phys_addr + efi_md_size(md) - 1; res->flags = flags; + res->desc = desc; if (insert_resource(&iomem_resource, res) < 0) kfree(res); diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 4f118b0d30915..2029a38a72aee 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -80,17 +80,17 @@ unsigned long vga_console_membase; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; unsigned long ia64_max_cacheline_size; diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 0e76fad27975d..74fe317477e62 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -454,7 +454,7 @@ start_secondary (void *unused) preempt_disable(); smp_callin(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); return 0; } diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index a5ecef7188baa..136c69f1fb8ab 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -70,14 +70,14 @@ static struct resource data_resource = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; unsigned long memory_start; diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c index a468467542f45..f98d2f6519d63 100644 --- a/arch/m32r/kernel/smpboot.c +++ b/arch/m32r/kernel/smpboot.c @@ -432,7 +432,7 @@ int __init start_secondary(void *unused) */ local_flush_tlb_all(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); return 0; } diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c index c3c6f08648816..bad13232de518 100644 --- a/arch/metag/kernel/smp.c +++ b/arch/metag/kernel/smp.c @@ -396,7 +396,7 @@ asmlinkage void secondary_start_kernel(void) /* * OK, it's off to the idle thread for us */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index 89a2a93949274..f31ebb5dc26c2 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -130,8 +130,6 @@ void __init machine_early_init(const char *cmdline, unsigned int ram, memset(__bss_start, 0, __bss_stop-__bss_start); memset(_ssbss, 0, _esbss-_ssbss); - lockdep_init(); - /* initialize device tree for usage in early_printk */ early_init_devtree(_fdt_start); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 74a3db92da1b5..a65eacf59918e 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -151,6 +151,7 @@ config BMIPS_GENERIC select CSRC_R4K select SYNC_R4K select COMMON_CLK + select BCM6345_L1_IRQ select BCM7038_L1_IRQ select BCM7120_L2_IRQ select BRCMSTB_L2_IRQ @@ -2169,7 +2170,6 @@ config MIPS_MT_SMP select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select SYNC_R4K - select MIPS_GIC_IPI select MIPS_MT select SMP select SMP_UP @@ -2267,7 +2267,6 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select MIPS_GIC_IPI select SMP select SYNC_R4K select SYS_SUPPORTS_SMP @@ -2287,7 +2286,6 @@ config MIPS_CPS select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU - select MIPS_GIC_IPI select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU @@ -2305,9 +2303,6 @@ config MIPS_CPS_PM select MIPS_CPC bool -config MIPS_GIC_IPI - bool - config MIPS_CM bool diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c index 511c06560dc1f..2dfff1f190043 100644 --- a/arch/mips/ath79/irq.c +++ b/arch/mips/ath79/irq.c @@ -26,90 +26,6 @@ #include "common.h" #include "machtypes.h" -static void __init ath79_misc_intc_domain_init( - struct device_node *node, int irq); - -static void ath79_misc_irq_handler(struct irq_desc *desc) -{ - struct irq_domain *domain = irq_desc_get_handler_data(desc); - void __iomem *base = domain->host_data; - u32 pending; - - pending = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS) & - __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); - - if (!pending) { - spurious_interrupt(); - return; - } - - while (pending) { - int bit = __ffs(pending); - - generic_handle_irq(irq_linear_revmap(domain, bit)); - pending &= ~BIT(bit); - } -} - -static void ar71xx_misc_irq_unmask(struct irq_data *d) -{ - void __iomem *base = irq_data_get_irq_chip_data(d); - unsigned int irq = d->hwirq; - u32 t; - - t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); - __raw_writel(t | (1 << irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE); - - /* flush write */ - __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); -} - -static void ar71xx_misc_irq_mask(struct irq_data *d) -{ - void __iomem *base = irq_data_get_irq_chip_data(d); - unsigned int irq = d->hwirq; - u32 t; - - t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); - __raw_writel(t & ~(1 << irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE); - - /* flush write */ - __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); -} - -static void ar724x_misc_irq_ack(struct irq_data *d) -{ - void __iomem *base = irq_data_get_irq_chip_data(d); - unsigned int irq = d->hwirq; - u32 t; - - t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS); - __raw_writel(t & ~(1 << irq), base + AR71XX_RESET_REG_MISC_INT_STATUS); - - /* flush write */ - __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS); -} - -static struct irq_chip ath79_misc_irq_chip = { - .name = "MISC", - .irq_unmask = ar71xx_misc_irq_unmask, - .irq_mask = ar71xx_misc_irq_mask, -}; - -static void __init ath79_misc_irq_init(void) -{ - if (soc_is_ar71xx() || soc_is_ar913x()) - ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask; - else if (soc_is_ar724x() || - soc_is_ar933x() || - soc_is_ar934x() || - soc_is_qca955x()) - ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack; - else - BUG(); - - ath79_misc_intc_domain_init(NULL, ATH79_CPU_IRQ(6)); -} static void ar934x_ip2_irq_dispatch(struct irq_desc *desc) { @@ -212,142 +128,12 @@ static void qca955x_irq_init(void) irq_set_chained_handler(ATH79_CPU_IRQ(3), qca955x_ip3_irq_dispatch); } -/* - * The IP2/IP3 lines are tied to a PCI/WMAC/USB device. Drivers for - * these devices typically allocate coherent DMA memory, however the - * DMA controller may still have some unsynchronized data in the FIFO. - * Issue a flush in the handlers to ensure that the driver sees - * the update. - * - * This array map the interrupt lines to the DDR write buffer channels. - */ - -static unsigned irq_wb_chan[8] = { - -1, -1, -1, -1, -1, -1, -1, -1, -}; - -asmlinkage void plat_irq_dispatch(void) -{ - unsigned long pending; - int irq; - - pending = read_c0_status() & read_c0_cause() & ST0_IM; - - if (!pending) { - spurious_interrupt(); - return; - } - - pending >>= CAUSEB_IP; - while (pending) { - irq = fls(pending) - 1; - if (irq < ARRAY_SIZE(irq_wb_chan) && irq_wb_chan[irq] != -1) - ath79_ddr_wb_flush(irq_wb_chan[irq]); - do_IRQ(MIPS_CPU_IRQ_BASE + irq); - pending &= ~BIT(irq); - } -} - -static int misc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) -{ - irq_set_chip_and_handler(irq, &ath79_misc_irq_chip, handle_level_irq); - irq_set_chip_data(irq, d->host_data); - return 0; -} - -static const struct irq_domain_ops misc_irq_domain_ops = { - .xlate = irq_domain_xlate_onecell, - .map = misc_map, -}; - -static void __init ath79_misc_intc_domain_init( - struct device_node *node, int irq) -{ - void __iomem *base = ath79_reset_base; - struct irq_domain *domain; - - domain = irq_domain_add_legacy(node, ATH79_MISC_IRQ_COUNT, - ATH79_MISC_IRQ_BASE, 0, &misc_irq_domain_ops, base); - if (!domain) - panic("Failed to add MISC irqdomain"); - - /* Disable and clear all interrupts */ - __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE); - __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS); - - irq_set_chained_handler_and_data(irq, ath79_misc_irq_handler, domain); -} - -static int __init ath79_misc_intc_of_init( - struct device_node *node, struct device_node *parent) -{ - int irq; - - irq = irq_of_parse_and_map(node, 0); - if (!irq) - panic("Failed to get MISC IRQ"); - - ath79_misc_intc_domain_init(node, irq); - return 0; -} - -static int __init ar7100_misc_intc_of_init( - struct device_node *node, struct device_node *parent) -{ - ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask; - return ath79_misc_intc_of_init(node, parent); -} - -IRQCHIP_DECLARE(ar7100_misc_intc, "qca,ar7100-misc-intc", - ar7100_misc_intc_of_init); - -static int __init ar7240_misc_intc_of_init( - struct device_node *node, struct device_node *parent) -{ - ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack; - return ath79_misc_intc_of_init(node, parent); -} - -IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc", - ar7240_misc_intc_of_init); - -static int __init ar79_cpu_intc_of_init( - struct device_node *node, struct device_node *parent) -{ - int err, i, count; - - /* Fill the irq_wb_chan table */ - count = of_count_phandle_with_args( - node, "qca,ddr-wb-channels", "#qca,ddr-wb-channel-cells"); - - for (i = 0; i < count; i++) { - struct of_phandle_args args; - u32 irq = i; - - of_property_read_u32_index( - node, "qca,ddr-wb-channel-interrupts", i, &irq); - if (irq >= ARRAY_SIZE(irq_wb_chan)) - continue; - - err = of_parse_phandle_with_args( - node, "qca,ddr-wb-channels", - "#qca,ddr-wb-channel-cells", - i, &args); - if (err) - return err; - - irq_wb_chan[irq] = args.args[0]; - pr_info("IRQ: Set flush channel of IRQ%d to %d\n", - irq, args.args[0]); - } - - return mips_cpu_irq_of_init(node, parent); -} -IRQCHIP_DECLARE(ar79_cpu_intc, "qca,ar7100-cpu-intc", - ar79_cpu_intc_of_init); - void __init arch_init_irq(void) { + unsigned irq_wb_chan2 = -1; + unsigned irq_wb_chan3 = -1; + bool misc_is_ar71xx; + if (mips_machtype == ATH79_MACH_GENERIC_OF) { irqchip_init(); return; @@ -355,14 +141,26 @@ void __init arch_init_irq(void) if (soc_is_ar71xx() || soc_is_ar724x() || soc_is_ar913x() || soc_is_ar933x()) { - irq_wb_chan[2] = 3; - irq_wb_chan[3] = 2; + irq_wb_chan2 = 3; + irq_wb_chan3 = 2; } else if (soc_is_ar934x()) { - irq_wb_chan[3] = 2; + irq_wb_chan3 = 2; } - mips_cpu_irq_init(); - ath79_misc_irq_init(); + ath79_cpu_irq_init(irq_wb_chan2, irq_wb_chan3); + + if (soc_is_ar71xx() || soc_is_ar913x()) + misc_is_ar71xx = true; + else if (soc_is_ar724x() || + soc_is_ar933x() || + soc_is_ar934x() || + soc_is_qca955x()) + misc_is_ar71xx = false; + else + BUG(); + ath79_misc_irq_init( + ath79_reset_base + AR71XX_RESET_REG_MISC_INT_STATUS, + ATH79_CPU_IRQ(6), ATH79_MISC_IRQ_BASE, misc_is_ar71xx); if (soc_is_ar934x()) ar934x_ip2_irq_init(); diff --git a/arch/mips/bmips/irq.c b/arch/mips/bmips/irq.c index e7fc6f9348baa..7efefcf440338 100644 --- a/arch/mips/bmips/irq.c +++ b/arch/mips/bmips/irq.c @@ -15,6 +15,12 @@ #include #include +static const struct of_device_id smp_intc_dt_match[] = { + { .compatible = "brcm,bcm7038-l1-intc" }, + { .compatible = "brcm,bcm6345-l1-intc" }, + {} +}; + unsigned int get_c0_compare_int(void) { return CP0_LEGACY_COMPARE_IRQ; @@ -24,8 +30,8 @@ void __init arch_init_irq(void) { struct device_node *dn; - /* Only the STB (bcm7038) controller supports SMP IRQ affinity */ - dn = of_find_compatible_node(NULL, NULL, "brcm,bcm7038-l1-intc"); + /* Only these controllers support SMP IRQ affinity */ + dn = of_find_matching_node(NULL, smp_intc_dt_match); if (dn) of_node_put(dn); else diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c index 408799a839b42..f7521142deda5 100644 --- a/arch/mips/boot/compressed/uart-16550.c +++ b/arch/mips/boot/compressed/uart-16550.c @@ -17,7 +17,7 @@ #define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset)) #endif -#ifdef CONFIG_MACH_JZ4740 +#if defined(CONFIG_MACH_JZ4740) || defined(CONFIG_MACH_JZ4780) #include #define PORT(offset) (CKSEG1ADDR(JZ4740_UART0_BASE_ADDR) + (4 * offset)) #endif diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h index 2b3487213d1e9..441faa92c3cd4 100644 --- a/arch/mips/include/asm/mach-ath79/ath79.h +++ b/arch/mips/include/asm/mach-ath79/ath79.h @@ -144,4 +144,8 @@ static inline u32 ath79_reset_rr(unsigned reg) void ath79_device_reset_set(u32 mask); void ath79_device_reset_clear(u32 mask); +void ath79_cpu_irq_init(unsigned irq_wb_chan2, unsigned irq_wb_chan3); +void ath79_misc_irq_init(void __iomem *regs, int irq, + int irq_base, bool is_ar71xx); + #endif /* __ASM_MACH_ATH79_H */ diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 6ba1fb8b11e22..db7c322f057f9 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -44,8 +44,9 @@ static inline void plat_smp_setup(void) mp_ops->smp_setup(); } -extern void gic_send_ipi_single(int cpu, unsigned int action); -extern void gic_send_ipi_mask(const struct cpumask *mask, unsigned int action); +extern void mips_smp_send_ipi_single(int cpu, unsigned int action); +extern void mips_smp_send_ipi_mask(const struct cpumask *mask, + unsigned int action); #else /* !CONFIG_SMP */ diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c index 8c6d76c9b2d69..d9907e57e9b98 100644 --- a/arch/mips/jz4740/gpio.c +++ b/arch/mips/jz4740/gpio.c @@ -270,7 +270,7 @@ uint32_t jz_gpio_port_get_value(int port, uint32_t mask) } EXPORT_SYMBOL(jz_gpio_port_get_value); -#define IRQ_TO_BIT(irq) BIT(irq_to_gpio(irq) & 0x1f) +#define IRQ_TO_BIT(irq) BIT((irq - JZ4740_IRQ_GPIO(0)) & 0x1f) static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int irq) { diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 68e2b7db9348f..b0988fd62fcc3 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -52,7 +52,6 @@ obj-$(CONFIG_MIPS_MT_SMP) += smp-mt.o obj-$(CONFIG_MIPS_CMP) += smp-cmp.o obj-$(CONFIG_MIPS_CPS) += smp-cps.o cps-vec.o obj-$(CONFIG_MIPS_CPS_NS16550) += cps-vec-ns16550.o -obj-$(CONFIG_MIPS_GIC_IPI) += smp-gic.o obj-$(CONFIG_MIPS_SPRAM) += spram.o obj-$(CONFIG_MIPS_VPE_LOADER) += vpe.o diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S index 5ce3b746cedc0..b4ac6374a38f2 100644 --- a/arch/mips/kernel/r2300_fpu.S +++ b/arch/mips/kernel/r2300_fpu.S @@ -125,7 +125,7 @@ LEAF(_restore_fp_context) END(_restore_fp_context) .set reorder - .type fault@function + .type fault, @function .ent fault fault: li v0, -EFAULT jr ra diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index f09546ee2cdc9..17732f876eff1 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -358,7 +358,7 @@ LEAF(_restore_msa_all_upper) .set reorder - .type fault@function + .type fault, @function .ent fault fault: li v0, -EFAULT # failure jr ra diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 5fdaf8bdcd2eb..4f607341a7938 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -732,21 +732,23 @@ static void __init resource_init(void) end = HIGHMEM_START - 1; res = alloc_bootmem(sizeof(struct resource)); + + res->start = start; + res->end = end; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + switch (boot_mem_map.map[i].type) { case BOOT_MEM_RAM: case BOOT_MEM_INIT_RAM: case BOOT_MEM_ROM_DATA: res->name = "System RAM"; + res->flags |= IORESOURCE_SYSRAM; break; case BOOT_MEM_RESERVED: default: res->name = "reserved"; } - res->start = start; - res->end = end; - - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); /* diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c index d5e0f949dc480..76923349b4fe1 100644 --- a/arch/mips/kernel/smp-cmp.c +++ b/arch/mips/kernel/smp-cmp.c @@ -149,8 +149,8 @@ void __init cmp_prepare_cpus(unsigned int max_cpus) } struct plat_smp_ops cmp_smp_ops = { - .send_ipi_single = gic_send_ipi_single, - .send_ipi_mask = gic_send_ipi_mask, + .send_ipi_single = mips_smp_send_ipi_single, + .send_ipi_mask = mips_smp_send_ipi_mask, .init_secondary = cmp_init_secondary, .smp_finish = cmp_smp_finish, .boot_secondary = cmp_boot_secondary, diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 2ad4e4c96d61c..253e1409338c1 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -472,8 +472,8 @@ static struct plat_smp_ops cps_smp_ops = { .boot_secondary = cps_boot_secondary, .init_secondary = cps_init_secondary, .smp_finish = cps_smp_finish, - .send_ipi_single = gic_send_ipi_single, - .send_ipi_mask = gic_send_ipi_mask, + .send_ipi_single = mips_smp_send_ipi_single, + .send_ipi_mask = mips_smp_send_ipi_mask, #ifdef CONFIG_HOTPLUG_CPU .cpu_disable = cps_cpu_disable, .cpu_die = cps_cpu_die, diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c index 86311a164ef12..4f9570a57e8d8 100644 --- a/arch/mips/kernel/smp-mt.c +++ b/arch/mips/kernel/smp-mt.c @@ -121,7 +121,7 @@ static void vsmp_send_ipi_single(int cpu, unsigned int action) #ifdef CONFIG_MIPS_GIC if (gic_present) { - gic_send_ipi_single(cpu, action); + mips_smp_send_ipi_single(cpu, action); return; } #endif diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index bd4385a8e6e86..37708d9af6381 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -33,12 +33,16 @@ #include #include #include +#include +#include +#include #include #include #include #include #include +#include #include #include #include @@ -79,6 +83,11 @@ static cpumask_t cpu_core_setup_map; cpumask_t cpu_coherent_mask; +#ifdef CONFIG_GENERIC_IRQ_IPI +static struct irq_desc *call_desc; +static struct irq_desc *sched_desc; +#endif + static inline void set_cpu_sibling_map(int cpu) { int i; @@ -121,6 +130,7 @@ static inline void calculate_cpu_foreign_map(void) cpumask_t temp_foreign_map; /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); for_each_online_cpu(i) { core_present = 0; for_each_cpu(k, &temp_foreign_map) @@ -145,6 +155,133 @@ void register_smp_ops(struct plat_smp_ops *ops) mp_ops = ops; } +#ifdef CONFIG_GENERIC_IRQ_IPI +void mips_smp_send_ipi_single(int cpu, unsigned int action) +{ + mips_smp_send_ipi_mask(cpumask_of(cpu), action); +} + +void mips_smp_send_ipi_mask(const struct cpumask *mask, unsigned int action) +{ + unsigned long flags; + unsigned int core; + int cpu; + + local_irq_save(flags); + + switch (action) { + case SMP_CALL_FUNCTION: + __ipi_send_mask(call_desc, mask); + break; + + case SMP_RESCHEDULE_YOURSELF: + __ipi_send_mask(sched_desc, mask); + break; + + default: + BUG(); + } + + if (mips_cpc_present()) { + for_each_cpu(cpu, mask) { + core = cpu_data[cpu].core; + + if (core == current_cpu_data.core) + continue; + + while (!cpumask_test_cpu(cpu, &cpu_coherent_mask)) { + mips_cpc_lock_other(core); + write_cpc_co_cmd(CPC_Cx_CMD_PWRUP); + mips_cpc_unlock_other(); + } + } + } + + local_irq_restore(flags); +} + + +static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) +{ + scheduler_ipi(); + + return IRQ_HANDLED; +} + +static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) +{ + generic_smp_call_function_interrupt(); + + return IRQ_HANDLED; +} + +static struct irqaction irq_resched = { + .handler = ipi_resched_interrupt, + .flags = IRQF_PERCPU, + .name = "IPI resched" +}; + +static struct irqaction irq_call = { + .handler = ipi_call_interrupt, + .flags = IRQF_PERCPU, + .name = "IPI call" +}; + +static __init void smp_ipi_init_one(unsigned int virq, + struct irqaction *action) +{ + int ret; + + irq_set_handler(virq, handle_percpu_irq); + ret = setup_irq(virq, action); + BUG_ON(ret); +} + +static int __init mips_smp_ipi_init(void) +{ + unsigned int call_virq, sched_virq; + struct irq_domain *ipidomain; + struct device_node *node; + + node = of_irq_find_parent(of_root); + ipidomain = irq_find_matching_host(node, DOMAIN_BUS_IPI); + + /* + * Some platforms have half DT setup. So if we found irq node but + * didn't find an ipidomain, try to search for one that is not in the + * DT. + */ + if (node && !ipidomain) + ipidomain = irq_find_matching_host(NULL, DOMAIN_BUS_IPI); + + BUG_ON(!ipidomain); + + call_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask); + BUG_ON(!call_virq); + + sched_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask); + BUG_ON(!sched_virq); + + if (irq_domain_is_ipi_per_cpu(ipidomain)) { + int cpu; + + for_each_cpu(cpu, cpu_possible_mask) { + smp_ipi_init_one(call_virq + cpu, &irq_call); + smp_ipi_init_one(sched_virq + cpu, &irq_resched); + } + } else { + smp_ipi_init_one(call_virq, &irq_call); + smp_ipi_init_one(sched_virq, &irq_resched); + } + + call_desc = irq_to_desc(call_virq); + sched_desc = irq_to_desc(sched_virq); + + return 0; +} +early_initcall(mips_smp_ipi_init); +#endif + /* * First C code run on the secondary CPUs after being started up by * the master. @@ -191,7 +328,7 @@ asmlinkage void start_secondary(void) WARN_ON_ONCE(!irqs_disabled()); mp_ops->smp_finish(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } static void stop_this_cpu(void *dummy) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index ae790c575d4fe..bf14da9f3e33b 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode) asmlinkage void do_ov(struct pt_regs *regs) { enum ctx_state prev_state; - siginfo_t info; + siginfo_t info = { + .si_signo = SIGFPE, + .si_code = FPE_INTOVF, + .si_addr = (void __user *)regs->cp0_epc, + }; prev_state = exception_enter(); die_if_kernel("Integer overflow", regs); - info.si_code = FPE_INTOVF; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); exception_exit(prev_state); } @@ -874,7 +874,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) void do_trap_or_bp(struct pt_regs *regs, unsigned int code, const char *str) { - siginfo_t info; + siginfo_t info = { 0 }; char b[40]; #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, else info.si_code = FPE_INTOVF; info.si_signo = SIGFPE; - info.si_errno = 0; info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); break; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 8bc3977576e6a..70ef1a43c1148 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -445,8 +445,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; - if (waitqueue_active(&dvcpu->wq)) - wake_up_interruptible(&dvcpu->wq); + if (swait_active(&dvcpu->wq)) + swake_up(&dvcpu->wq); return 0; } @@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_to_user(uaddr, vs, 16); + return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_from_user(vs, uaddr, 16); + return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -1174,8 +1174,8 @@ static void kvm_mips_comparecount_func(unsigned long data) kvm_mips_callbacks->queue_timer_int(vcpu); vcpu->arch.wait = 0; - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) + swake_up(&vcpu->wq); } /* low level hrtimer wake routine */ diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 249647578e587..91dec32c77b72 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void) sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK; sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF; - c->scache.sets = 64 << sets; + if (sets) + c->scache.sets = 64 << sets; line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK; line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF; - c->scache.linesz = 2 << line_sz; + if (line_sz) + c->scache.linesz = 2 << line_sz; assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK; assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF; @@ -176,9 +178,12 @@ static int __init mips_sc_probe_cm3(void) c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize); - c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + if (c->scache.linesz) { + c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + return 1; + } - return 1; + return 0; } static inline int __init mips_sc_probe(void) diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index f984193718b10..426173c4b0b90 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -675,7 +675,7 @@ int __init start_secondary(void *unused) #ifdef CONFIG_GENERIC_CLOCKEVENTS init_clockevents(); #endif - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); return 0; } diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h index 3d0e17bcc8e90..df0f52bd18b45 100644 --- a/arch/parisc/include/asm/cache.h +++ b/arch/parisc/include/asm/cache.h @@ -22,6 +22,9 @@ #define __read_mostly __attribute__((__section__(".data..read_mostly"))) +/* Read-only memory is marked before mark_rodata_ro() is called. */ +#define __ro_after_init __read_mostly + void parisc_cache_init(void); /* initializes cache-flushing */ void disable_sr_hashing_asm(int); /* low level support for above */ void disable_sr_hashing(void); /* turns off space register hashing */ diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 845272ce9cc58..7bd69bd43a018 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -121,10 +121,6 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma } } -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); -#endif - #include #define ARCH_HAS_KMAP diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h index f84ff12574b73..6d8276cd25cad 100644 --- a/arch/parisc/include/asm/floppy.h +++ b/arch/parisc/include/asm/floppy.h @@ -33,7 +33,7 @@ * floppy accesses go through the track buffer. */ #define _CROSS_64KB(a,s,vdma) \ -(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) +(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) #define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1) diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 35bdccbb20362..b75039f921164 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -361,8 +361,9 @@ #define __NR_membarrier (__NR_Linux + 343) #define __NR_userfaultfd (__NR_Linux + 344) #define __NR_mlock2 (__NR_Linux + 345) +#define __NR_copy_file_range (__NR_Linux + 346) -#define __NR_Linux_syscalls (__NR_mlock2 + 1) +#define __NR_Linux_syscalls (__NR_copy_file_range + 1) #define __IGNORE_select /* newselect */ diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9585c81f755fc..ce0b2b4075c70 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - /* Do the secure computing check first. */ secure_computing_strict(regs->gr[20]); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - ret = -1L; + tracehook_report_syscall_entry(regs)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + regs->gr[20] = -1UL; + goto out; + } #ifdef CONFIG_64BIT if (!is_compat_task()) @@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); - return ret ? : regs->gr[20]; +out: + return regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 52e85973a283c..c2a9cc55a62f6 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -305,7 +305,7 @@ void __init smp_callin(void) local_irq_enable(); /* Interrupts have been off until now */ - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); /* NOTREACHED */ panic("smp_callin() AAAAaaaaahhhh....\n"); diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 3fbd7252a4b27..fbafa0d0e2bf8 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -343,7 +343,7 @@ tracesys_next: #endif comiclr,>>= __NR_Linux_syscalls, %r20, %r0 - b,n .Lsyscall_nosys + b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 @@ -359,6 +359,9 @@ tracesys_next: be 0(%sr7,%r19) ldo R%tracesys_exit(%r2),%r2 +.Ltracesys_nosys: + ldo -ENOSYS(%r0),%r28 /* set errno */ + /* Do *not* call this function on the gateway page, because it makes a direct call to syscall_trace. */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index d4ffcfbc98851..585d50fc75c0f 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -441,6 +441,7 @@ ENTRY_SAME(membarrier) ENTRY_SAME(userfaultfd) ENTRY_SAME(mlock2) /* 345 */ + ENTRY_SAME(copy_file_range) .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 1b366c4776872..3c07d6b968772 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -55,12 +55,12 @@ signed char pfnnid_map[PFNNID_MAP_MAX] __read_mostly; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource pdcdata_resource = { @@ -201,7 +201,7 @@ static void __init setup_bootmem(void) res->name = "System RAM"; res->start = pmem_ranges[i].start_pfn << PAGE_SHIFT; res->end = res->start + (pmem_ranges[i].pages << PAGE_SHIFT)-1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); } diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 9d08d8cbed1a1..c98afa538b3ae 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -289,7 +289,7 @@ struct kvmppc_vcore { struct list_head runnable_threads; struct list_head preempt_list; spinlock_t lock; - wait_queue_head_t wq; + struct swait_queue_head wq; spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ u64 stolen_tb; u64 preempt_tb; @@ -629,7 +629,7 @@ struct kvm_vcpu_arch { u8 prodded; u32 last_inst; - wait_queue_head_t *wqp; + struct swait_queue_head *wqp; struct kvmppc_vcore *vcore; int ret; int trap; diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 05e804cdecaa9..aec9a1b1d25bc 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -109,8 +109,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp) * If the breakpoint is unregistered between a hw_breakpoint_handler() * and the single_step_dabr_instruction(), then cleanup the breakpoint * restoration variables to prevent dangling pointers. + * FIXME, this should not be using bp->ctx at all! Sayeth peterz. */ - if (bp->ctx && bp->ctx->task) + if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) bp->ctx->task->thread.last_hit_ubp = NULL; } diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index ad8c9db612372..d544fa3117576 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -114,8 +114,6 @@ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { - lockdep_init(); - /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5c03a6a9b0542..f98be8383a399 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -255,9 +255,6 @@ void __init early_setup(unsigned long dt_ptr) setup_paca(&boot_paca); fixup_boot_paca(); - /* Initialize lockdep early or else spinlocks will blow */ - lockdep_init(); - /* -------- printk is now safe to use ------- */ /* Enable early debugging if any specified (see udbg.h) */ diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ec9ec2058d2d3..cc13d4c832916 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -727,7 +727,7 @@ void start_secondary(void *unused) local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); BUG(); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index baeddb06811d7..f1187bb6dd4d7 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -114,11 +114,11 @@ static bool kvmppc_ipi_thread(int cpu) static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { int cpu; - wait_queue_head_t *wqp; + struct swait_queue_head *wqp; wqp = kvm_arch_vcpu_wq(vcpu); - if (waitqueue_active(wqp)) { - wake_up_interruptible(wqp); + if (swait_active(wqp)) { + swake_up(wqp); ++vcpu->stat.halt_wakeup; } @@ -701,8 +701,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) tvcpu->arch.prodded = 1; smp_mb(); if (vcpu->arch.ceded) { - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) { + swake_up(&vcpu->wq); vcpu->stat.halt_wakeup++; } } @@ -1459,7 +1459,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) INIT_LIST_HEAD(&vcore->runnable_threads); spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); - init_waitqueue_head(&vcore->wq); + init_swait_queue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; vcore->first_vcpuid = core * threads_per_subcore; @@ -2531,10 +2531,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) { struct kvm_vcpu *vcpu; int do_sleep = 1; + DECLARE_SWAITQUEUE(wait); - DEFINE_WAIT(wait); - - prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); /* * Check one last time for pending exceptions and ceded state after @@ -2548,7 +2547,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } if (!do_sleep) { - finish_wait(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); return; } @@ -2556,7 +2555,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); schedule(); - finish_wait(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; trace_kvmppc_vcore_blocked(vc, 1); @@ -2612,7 +2611,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - wake_up(&vc->wq); + swake_up(&vc->wq); } } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 6ee26de9a1ded..25ae2c9913c39 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_ACOP(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) + /* + * Restore various registers to 0, where non-zero values + * set by the guest could disrupt the host. + */ + li r0, 0 + mtspr SPRN_IAMR, r0 + mtspr SPRN_CIABR, r0 + mtspr SPRN_DAWRX, r0 + mtspr SPRN_TCSCR, r0 + mtspr SPRN_WORT, r0 + /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ + li r0, 1 + sldi r0, r0, 31 + mtspr SPRN_MMCRS, r0 8: /* Save and reset AMR and UAMOR before turning on the MMU */ diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c index 7e6d0880813fe..83a8be791e064 100644 --- a/arch/powerpc/mm/hugetlbpage-book3e.c +++ b/arch/powerpc/mm/hugetlbpage-book3e.c @@ -8,6 +8,8 @@ #include #include +#include + #ifdef CONFIG_PPC_FSL_BOOK3E #ifdef CONFIG_PPC64 static inline int tlb1_next(void) @@ -60,6 +62,14 @@ static inline void book3e_tlb_lock(void) unsigned long tmp; int token = smp_processor_id() + 1; + /* + * Besides being unnecessary in the absence of SMT, this + * check prevents trying to do lbarx/stbcx. on e5500 which + * doesn't implement either feature. + */ + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + asm volatile("1: lbarx %0, 0, %1;" "cmpwi %0, 0;" "bne 2f;" @@ -80,6 +90,9 @@ static inline void book3e_tlb_unlock(void) { struct paca_struct *paca = get_paca(); + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + isync(); paca->tcd_ptr->lock = 0; } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index d0f0a514b04ed..f078a1f94fc26 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -541,7 +541,7 @@ static int __init add_system_ram_resources(void) res->name = "System RAM"; res->start = base; res->end = base + size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; WARN_ON(request_resource(&iomem_resource, res) < 0); } } diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 8959ebb6d2c9e..b0c8ad0799c7f 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -467,7 +467,7 @@ struct kvm_s390_irq_payload { struct kvm_s390_local_interrupt { spinlock_t lock; struct kvm_s390_float_interrupt *float_int; - wait_queue_head_t *wq; + struct swait_queue_head *wq; atomic_t *cpuflags; DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); struct kvm_s390_irq_payload irq; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fb1b93ea3e3fe..e485817f7b1a9 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,17 +15,25 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + spin_lock_init(&mm->context.list_lock); + INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.attach_count, 0); mm->context.flush_mm = 0; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; - mm->context.asce_bits |= _ASCE_TYPE_REGION3; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - mm->context.asce_limit = STACK_TOP_MAX; + if (mm->context.asce_limit == 0) { + /* context created by exec, set asce limit to 4TB */ + mm->context.asce_bits = _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + mm->context.asce_limit = STACK_TOP_MAX; + } else if (mm->context.asce_limit == (1UL << 31)) { + mm_inc_nr_pmds(mm); + } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; } @@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev, static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - if (oldmm->context.asce_limit < mm->context.asce_limit) - crst_table_downgrade(mm, oldmm->context.asce_limit); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b7858f158b45..d7cc79fb61911 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - spin_lock_init(&mm->context.list_lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); - INIT_LIST_HEAD(&mm->context.gmap_list); - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + if (mm->context.asce_limit == (1UL << 31)) { + /* Forking a compat process with 2 page table levels */ + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } + } + return (pgd_t *) table; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (mm->context.asce_limit == (1UL << 31)) + pgtable_pmd_page_dtor(virt_to_page(pgd)); + crst_table_free(mm, (unsigned long *) pgd); } -#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index c55576bbaa1f7..a0684de5a93b9 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -448,7 +448,6 @@ void __init startup_init(void) rescue_initrd(); clear_bss_section(); init_kernel_storage_key(); - lockdep_init(); lockdep_off(); setup_lowcore_early(); setup_facility_list(); diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index c5febe84eba63..03c2b469c4725 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -16,7 +16,7 @@ __HEAD ENTRY(startup_continue) - tm __LC_STFLE_FAC_LIST+6,0x80 # LPP available ? + tm __LC_STFLE_FAC_LIST+5,0x80 # LPP available ? jz 0f xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid mvi __LC_LPP,0x80 # and set LPP_MAGIC diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 9220db5c996aa..cedb0198675f7 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -374,17 +374,17 @@ static void __init setup_lowcore(void) static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource __initdata *standard_resources[] = { @@ -408,7 +408,7 @@ static void __init setup_resources(void) for_each_memblock(memory, reg) { res = alloc_bootmem_low(sizeof(*res)); - res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; res->name = "System RAM"; res->start = reg->base; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 3c65a8eae34d3..40a6b4f9c36ce 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -798,7 +798,7 @@ static void smp_start_secondary(void *cpuvoid) set_cpu_online(smp_processor_id(), true); inc_irq_stat(CPU_RST); local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } /* Upping and downing of CPUs */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index f88ca72c3a77a..9ffc732217921 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -966,13 +966,13 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) { - if (waitqueue_active(&vcpu->wq)) { + if (swait_active(&vcpu->wq)) { /* * The vcpu gave up the cpu voluntarily, mark it as a good * yield-candidate. */ vcpu->preempted = true; - wake_up_interruptible(&vcpu->wq); + swake_up(&vcpu->wq); vcpu->stat.halt_wakeup++; } } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4af21c771f9b3..03dfe9c667f4e 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2381,7 +2381,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) /* manually convert vector registers if necessary */ if (MACHINE_HAS_VX) { - convert_vx_to_fp(fprs, current->thread.fpu.vxrs); + convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, fprs, 128); } else { diff --git a/arch/score/kernel/setup.c b/arch/score/kernel/setup.c index b48459afefddb..f3a0649ab5217 100644 --- a/arch/score/kernel/setup.c +++ b/arch/score/kernel/setup.c @@ -101,7 +101,7 @@ static void __init resource_init(void) res->name = "System RAM"; res->start = MEMORY_START; res->end = MEMORY_START + MEMORY_SIZE - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); request_resource(res, &code_resource); diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index de19cfa768f20..3f1c18b28e8af 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -78,17 +78,17 @@ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0, }; static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; unsigned long memory_start; @@ -202,7 +202,7 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn, res->name = "System RAM"; res->start = start; res->end = end - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; if (request_resource(&iomem_resource, res)) { pr_err("unable to request memory_resource 0x%lx 0x%lx\n", diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index de6be008fc014..13f633add29ac 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -203,7 +203,7 @@ asmlinkage void start_secondary(void) set_cpu_online(cpu, true); per_cpu(cpu_state, cpu) = CPU_ONLINE; - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } extern struct { diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index eaee14637d93e..8496a074bd0eb 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -24,7 +24,13 @@ LDFLAGS := -m elf32_sparc export BITS := 32 UTS_MACHINE := sparc +# We are adding -Wa,-Av8 to KBUILD_CFLAGS to deal with a specs bug in some +# versions of gcc. Some gcc versions won't pass -Av8 to binutils when you +# give -mcpu=v8. This silently worked with older bintutils versions but +# does not any more. KBUILD_CFLAGS += -m32 -mcpu=v8 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7 +KBUILD_CFLAGS += -Wa,-Av8 + KBUILD_AFLAGS += -m32 -Wa,-Av8 else diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index 1c26d440d288d..b6de8b10a55b8 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -422,8 +422,9 @@ #define __NR_listen 354 #define __NR_setsockopt 355 #define __NR_mlock2 356 +#define __NR_copy_file_range 357 -#define NR_syscalls 357 +#define NR_syscalls 358 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 33c02b15f4785..a83707c83be80 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -948,7 +948,24 @@ linux_syscall_trace: cmp %o0, 0 bne 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ld [%sp + STACKFRAME_SZ + PT_G1], %g1 + sethi %hi(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I0], %i0 + or %l7, %lo(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I1], %i1 + ld [%sp + STACKFRAME_SZ + PT_I2], %i2 + ld [%sp + STACKFRAME_SZ + PT_I3], %i3 + ld [%sp + STACKFRAME_SZ + PT_I4], %i4 + ld [%sp + STACKFRAME_SZ + PT_I5], %i5 + cmp %g1, NR_syscalls + bgeu 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + ld [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index f2d30cab5b3f3..cd1f592cd3479 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -696,14 +696,6 @@ tlb_fixup_done: call __bzero sub %o1, %o0, %o1 -#ifdef CONFIG_LOCKDEP - /* We have this call this super early, as even prom_init can grab - * spinlocks and thus call into the lockdep code. - */ - call lockdep_init - nop -#endif - call prom_init mov %l7, %o0 ! OpenPROM cif handler diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index afbaba52d2f16..d127130bf4246 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -338,8 +338,9 @@ ENTRY(sun4v_mach_set_watchdog) mov %o1, %o4 mov HV_FAST_MACH_SET_WATCHDOG, %o5 ta HV_FAST_TRAP + brnz,a,pn %o4, 0f stx %o1, [%o4] - retl +0: retl nop ENDPROC(sun4v_mach_set_watchdog) diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index d88beff47bab3..39aaec173f66e 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) unsigned char fenab; int err; - flush_user_windows(); + synchronize_user_stack(); if (get_thread_wsaved() || (((unsigned long)ucp) & (sizeof(unsigned long)-1)) || (!__access_ok(ucp, sizeof(*ucp)))) diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index b3a5d81b20f0f..fb30e7c6a5b15 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -364,7 +364,7 @@ static void sparc_start_secondary(void *arg) local_irq_enable(); wmb(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); /* We should never reach here! */ BUG(); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 19cd08d186728..8a6151a628ce9 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -134,7 +134,7 @@ void smp_callin(void) local_irq_enable(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } void cpu_panic(void) diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index a92d5d2c46a3a..9e034f29dcc52 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -37,6 +37,7 @@ EXPORT_SYMBOL(sun4v_niagara_getperf); EXPORT_SYMBOL(sun4v_niagara_setperf); EXPORT_SYMBOL(sun4v_niagara2_getperf); EXPORT_SYMBOL(sun4v_niagara2_setperf); +EXPORT_SYMBOL(sun4v_mach_set_watchdog); /* from hweight.S */ EXPORT_SYMBOL(__arch_hweight8); diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index bb0008927598b..c4a1b5c40e4ef 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -158,7 +158,25 @@ linux_syscall_trace32: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 srl %i0, 0, %o0 + lduw [%l7 + %l4], %l7 srl %i4, 0, %o4 srl %i1, 0, %o1 srl %i2, 0, %o2 @@ -170,7 +188,25 @@ linux_syscall_trace: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + lduw [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index e663b6c78de2e..6c3dd6c52f8bd 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -88,4 +88,4 @@ sys_call_table: /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen -/*355*/ .long sys_setsockopt, sys_mlock2 +/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 1557121f4cdce..12b524cfcfa01 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -89,7 +89,7 @@ sys_call_table32: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word compat_sys_setsockopt, sys_mlock2 + .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range #endif /* CONFIG_COMPAT */ @@ -170,4 +170,4 @@ sys_call_table: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word sys_setsockopt, sys_mlock2 + .word sys_setsockopt, sys_mlock2, sys_copy_file_range diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 6f216853f2724..1cfe6aab7a115 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2863,17 +2863,17 @@ void hugetlb_setup(struct pt_regs *regs) static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static inline resource_size_t compute_kern_paddr(void *addr) @@ -2909,7 +2909,7 @@ static int __init report_memory(void) res->name = "System RAM"; res->start = pavail[i].phys_addr; res->end = pavail[i].phys_addr + pavail[i].reg_size - 1; - res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; if (insert_resource(&iomem_resource, res) < 0) { pr_warn("Resource insertion failed.\n"); diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index bbb855de65698..a992238e9b582 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -1632,14 +1632,14 @@ static struct resource data_resource = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; /* @@ -1673,10 +1673,15 @@ insert_ram_resource(u64 start_pfn, u64 end_pfn, bool reserved) kzalloc(sizeof(struct resource), GFP_ATOMIC); if (!res) return NULL; - res->name = reserved ? "Reserved" : "System RAM"; res->start = start_pfn << PAGE_SHIFT; res->end = (end_pfn << PAGE_SHIFT) - 1; res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + if (reserved) { + res->name = "Reserved"; + } else { + res->name = "System RAM"; + res->flags |= IORESOURCE_SYSRAM; + } if (insert_resource(&iomem_resource, res)) { kfree(res); return NULL; diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c index 20d52a98e1716..6c0abaacec335 100644 --- a/arch/tile/kernel/smpboot.c +++ b/arch/tile/kernel/smpboot.c @@ -208,7 +208,7 @@ void online_secondary(void) /* Set up tile-timer clock-event device on this cpu */ setup_tile_timer(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } int __cpu_up(unsigned int cpu, struct task_struct *tidle) diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 9bdf67a092a53..b60a9f8cda755 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -12,6 +12,7 @@ #include void (*pm_power_off)(void); +EXPORT_SYMBOL(pm_power_off); static void kill_off_processes(void) { diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index fc8be0e3a4ff8..57acbd67d85db 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs) struct ksignal ksig; int handled_sig = 0; - if (get_signal(&ksig)) { + while (get_signal(&ksig)) { handled_sig = 1; /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c index 3fa317f961221..c2bffa5614a48 100644 --- a/arch/unicore32/kernel/setup.c +++ b/arch/unicore32/kernel/setup.c @@ -72,13 +72,13 @@ static struct resource mem_res[] = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM }, { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM } }; @@ -211,7 +211,7 @@ request_standard_resources(struct meminfo *mi) res->name = "System RAM"; res->start = mi->bank[i].start; res->end = mi->bank[i].start + mi->bank[i].size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 1538562cc720e..eb3abf8ac44eb 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -1,6 +1,7 @@ - obj-y += entry/ +obj-$(CONFIG_PERF_EVENTS) += events/ + obj-$(CONFIG_KVM) += kvm/ # Xen paravirtualization support diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c46662f64c392..8f2e6659281b7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -303,6 +303,9 @@ config ARCH_SUPPORTS_UPROBES config FIX_EARLYCON_MEM def_bool y +config DEBUG_RODATA + def_bool y + config PGTABLE_LEVELS int default 4 if X86_64 @@ -1160,22 +1163,23 @@ config MICROCODE bool "CPU microcode loading support" default y depends on CPU_SUP_AMD || CPU_SUP_INTEL - depends on BLK_DEV_INITRD select FW_LOADER ---help--- - If you say Y here, you will be able to update the microcode on - certain Intel and AMD processors. The Intel support is for the - IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, - Xeon etc. The AMD support is for families 0x10 and later. You will - obviously need the actual microcode binary data itself which is not - shipped with the Linux kernel. - - This option selects the general module only, you need to select - at least one vendor specific module as well. - - To compile this driver as a module, choose M here: the module - will be called microcode. + Intel and AMD processors. The Intel support is for the IA32 family, + e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The + AMD support is for families 0x10 and later. You will obviously need + the actual microcode binary data itself which is not shipped with + the Linux kernel. + + The preferred method to load microcode from a detached initrd is described + in Documentation/x86/early-microcode.txt. For that you need to enable + CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the + initrd for microcode blobs. + + In addition, you can build-in the microcode into the kernel. For that you + need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode + to the CONFIG_EXTRA_FIRMWARE config option. config MICROCODE_INTEL bool "Intel microcode loading support" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 9b18ed97a8a29..67eec55093a5d 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -74,28 +74,16 @@ config EFI_PGT_DUMP issues with the mapping of the EFI runtime regions into that table. -config DEBUG_RODATA - bool "Write protect kernel read-only data structures" - default y - depends on DEBUG_KERNEL - ---help--- - Mark the kernel read-only data as write-protected in the pagetables, - in order to catch accidental (and incorrect) writes to such const - data. This is recommended so that we can catch kernel bugs sooner. - If in doubt, say "Y". - config DEBUG_RODATA_TEST - bool "Testcase for the DEBUG_RODATA feature" - depends on DEBUG_RODATA + bool "Testcase for the marking rodata read-only" default y ---help--- - This option enables a testcase for the DEBUG_RODATA - feature as well as for the change_page_attr() infrastructure. + This option enables a testcase for the setting rodata read-only + as well as for the change_page_attr() infrastructure. If in doubt, say "N" config DEBUG_WX bool "Warn on W+X mappings at boot" - depends on DEBUG_RODATA select X86_PTDUMP_CORE ---help--- Generate a warning if any W+X mappings are found at boot. @@ -350,16 +338,6 @@ config DEBUG_IMR_SELFTEST If unsure say N here. -config X86_DEBUG_STATIC_CPU_HAS - bool "Debug alternatives" - depends on DEBUG_KERNEL - ---help--- - This option causes additional code to be generated which - fails if static_cpu_has() is used before alternatives have - run. - - If unsure, say N. - config X86_DEBUG_FPU bool "Debug the x86 FPU code" depends on DEBUG_KERNEL diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h index ea97697e51e40..4cb404fd45cea 100644 --- a/arch/x86/boot/cpuflags.h +++ b/arch/x86/boot/cpuflags.h @@ -1,7 +1,7 @@ #ifndef BOOT_CPUFLAGS_H #define BOOT_CPUFLAGS_H -#include +#include #include struct cpu_features { diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c index 637097e66a62a..f72498dc90d23 100644 --- a/arch/x86/boot/mkcpustr.c +++ b/arch/x86/boot/mkcpustr.c @@ -17,7 +17,7 @@ #include "../include/asm/required-features.h" #include "../include/asm/disabled-features.h" -#include "../include/asm/cpufeature.h" +#include "../include/asm/cpufeatures.h" #include "../kernel/cpu/capflags.c" int main(void) diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index a7661c430cd98..0702d2531bc7f 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -49,7 +49,6 @@ typedef unsigned int u32; /* This must be large enough to hold the entire setup */ u8 buf[SETUP_SECT_MAX*512]; -int is_big_kernel; #define PECOFF_RELOC_RESERVE 0x20 diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 028be48c88397..e25a1630320cc 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -288,7 +288,7 @@ CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y CONFIG_PRINTK_TIME=y # CONFIG_ENABLE_WARN_DEPRECATED is not set -CONFIG_FRAME_WARN=2048 +CONFIG_FRAME_WARN=1024 CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_KERNEL=y diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 07d2c6c86a548..27226df3f7d8a 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -33,7 +33,7 @@ #include #include -#include +#include #include #include diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 0e9871693f246..0857b1a1de3bd 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -30,7 +30,7 @@ #include #include -#include +#include #include #include diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c index a3fcfc97a311d..cd4df93225014 100644 --- a/arch/x86/crypto/crct10dif-pclmul_glue.c +++ b/arch/x86/crypto/crct10dif-pclmul_glue.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf, diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index e32206e098682..9a9e5884066c6 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -201,37 +201,6 @@ For 32-bit we have the following conventions - kernel is built with .byte 0xf1 .endm -#else /* CONFIG_X86_64 */ - -/* - * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These - * are different from the entry_32.S versions in not changing the segment - * registers. So only suitable for in kernel use, not when transitioning - * from or to user space. The resulting stack frame is not a standard - * pt_regs frame. The main use case is calling C code from assembler - * when all the registers need to be preserved. - */ - - .macro SAVE_ALL - pushl %eax - pushl %ebp - pushl %edi - pushl %esi - pushl %edx - pushl %ecx - pushl %ebx - .endm - - .macro RESTORE_ALL - popl %ebx - popl %ecx - popl %edx - popl %esi - popl %edi - popl %ebp - popl %eax - .endm - #endif /* CONFIG_X86_64 */ /* diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03663740c8665..e79d93d44ecd9 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -26,6 +26,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -44,6 +45,8 @@ __visible void enter_from_user_mode(void) CT_WARN_ON(ct_state() != CONTEXT_USER); user_exit(); } +#else +static inline void enter_from_user_mode(void) {} #endif static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) @@ -84,17 +87,6 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; -#ifdef CONFIG_CONTEXT_TRACKING - /* - * If TIF_NOHZ is set, we are required to call user_exit() before - * doing anything that could touch RCU. - */ - if (work & _TIF_NOHZ) { - enter_from_user_mode(); - work &= ~_TIF_NOHZ; - } -#endif - #ifdef CONFIG_SECCOMP /* * Do seccomp first -- it should minimize exposure of other @@ -171,16 +163,6 @@ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); - /* - * If we stepped into a sysenter/syscall insn, it trapped in - * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. - * If user-mode had set TF itself, then it's still clear from - * do_debug() and we need to set it again to restore the user - * state. If we entered on the slow path, TF was already set. - */ - if (work & _TIF_SINGLESTEP) - regs->flags |= X86_EFLAGS_TF; - #ifdef CONFIG_SECCOMP /* * Call seccomp_phase2 before running the other hooks so that @@ -268,6 +250,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* Called with IRQs disabled. */ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) { + struct thread_info *ti = pt_regs_to_thread_info(regs); u32 cached_flags; if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) @@ -275,12 +258,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) lockdep_sys_exit(); - cached_flags = - READ_ONCE(pt_regs_to_thread_info(regs)->flags); + cached_flags = READ_ONCE(ti->flags); if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) exit_to_usermode_loop(regs, cached_flags); +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. We need to clear it *after* signal + * handling, because syscall restart has a fixup for compat + * syscalls. The fixup is exercised by the ptrace_syscall_32 + * selftest. + */ + ti->status &= ~TS_COMPAT; +#endif + user_enter(); } @@ -332,33 +325,45 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) syscall_slow_exit_work(regs, cached_flags); -#ifdef CONFIG_COMPAT + local_irq_disable(); + prepare_exit_to_usermode(regs); +} + +#ifdef CONFIG_X86_64 +__visible void do_syscall_64(struct pt_regs *regs) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + unsigned long nr = regs->orig_ax; + + enter_from_user_mode(); + local_irq_enable(); + + if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) + nr = syscall_trace_enter(regs); + /* - * Compat syscalls set TS_COMPAT. Make sure we clear it before - * returning to user mode. + * NB: Native and x32 syscalls are dispatched from the same + * table. The only functional difference is the x32 bit in + * regs->orig_ax, which changes the behavior of some syscalls. */ - ti->status &= ~TS_COMPAT; -#endif + if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { + regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + regs->di, regs->si, regs->dx, + regs->r10, regs->r8, regs->r9); + } - local_irq_disable(); - prepare_exit_to_usermode(regs); + syscall_return_slowpath(regs); } +#endif #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) /* - * Does a 32-bit syscall. Called with IRQs on and does all entry and - * exit work and returns with IRQs off. This function is extremely hot - * in workloads that use it, and it's usually called from + * Does a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. Does + * all entry and exit work and returns with IRQs off. This function is + * extremely hot in workloads that use it, and it's usually called from * do_fast_syscall_32, so forcibly inline it to improve performance. */ -#ifdef CONFIG_X86_32 -/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */ -__visible -#else -/* 64-bit kernels use do_syscall_32_irqs_off() instead. */ -static -#endif -__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) +static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) { struct thread_info *ti = pt_regs_to_thread_info(regs); unsigned int nr = (unsigned int)regs->orig_ax; @@ -393,14 +398,13 @@ __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) syscall_return_slowpath(regs); } -#ifdef CONFIG_X86_64 -/* Handles INT80 on 64-bit kernels */ -__visible void do_syscall_32_irqs_off(struct pt_regs *regs) +/* Handles int $0x80 */ +__visible void do_int80_syscall_32(struct pt_regs *regs) { + enter_from_user_mode(); local_irq_enable(); do_syscall_32_irqs_on(regs); } -#endif /* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ __visible long do_fast_syscall_32(struct pt_regs *regs) @@ -420,12 +424,11 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) */ regs->ip = landing_pad; - /* - * Fetch EBP from where the vDSO stashed it. - * - * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! - */ + enter_from_user_mode(); + local_irq_enable(); + + /* Fetch EBP from where the vDSO stashed it. */ if ( #ifdef CONFIG_X86_64 /* @@ -443,9 +446,6 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) /* User code screwed up. */ local_irq_disable(); regs->ax = -EFAULT; -#ifdef CONFIG_CONTEXT_TRACKING - enter_from_user_mode(); -#endif prepare_exit_to_usermode(regs); return 0; /* Keep it simple: use IRET. */ } diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index bb3e376d0f33c..10868aa734dc0 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -40,7 +40,7 @@ #include #include #include -#include +#include #include #include #include @@ -287,20 +287,93 @@ need_resched: END(resume_kernel) #endif - # SYSENTER call handler stub +GLOBAL(__begin_SYSENTER_singlestep_region) +/* + * All code from here through __end_SYSENTER_singlestep_region is subject + * to being single-stepped if a user program sets TF and executes SYSENTER. + * There is absolutely nothing that we can do to prevent this from happening + * (thanks Intel!). To keep our handling of this situation as simple as + * possible, we handle TF just like AC and NT, except that our #DB handler + * will ignore all of the single-step traps generated in this range. + */ + +#ifdef CONFIG_XEN +/* + * Xen doesn't set %esp to be precisely what the normal SYSENTER + * entry point expects, so fix it up before using the normal path. + */ +ENTRY(xen_sysenter_target) + addl $5*4, %esp /* remove xen-provided frame */ + jmp sysenter_past_esp +#endif + +/* + * 32-bit SYSENTER entry. + * + * 32-bit system calls through the vDSO's __kernel_vsyscall enter here + * if X86_FEATURE_SEP is available. This is the preferred system call + * entry on 32-bit systems. + * + * The SYSENTER instruction, in principle, should *only* occur in the + * vDSO. In practice, a small number of Android devices were shipped + * with a copy of Bionic that inlined a SYSENTER instruction. This + * never happened in any of Google's Bionic versions -- it only happened + * in a narrow range of Intel-provided versions. + * + * SYSENTER loads SS, ESP, CS, and EIP from previously programmed MSRs. + * IF and VM in RFLAGS are cleared (IOW: interrupts are off). + * SYSENTER does not save anything on the stack, + * and does not save old EIP (!!!), ESP, or EFLAGS. + * + * To avoid losing track of EFLAGS.VM (and thus potentially corrupting + * user and/or vm86 state), we explicitly disable the SYSENTER + * instruction in vm86 mode by reprogramming the MSRs. + * + * Arguments: + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp user stack + * 0(%ebp) arg6 + */ ENTRY(entry_SYSENTER_32) movl TSS_sysenter_sp0(%esp), %esp sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ - ASM_CLAC /* Clear AC after saving FLAGS */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ pushl %eax /* pt_regs->orig_ax */ SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ + /* + * SYSENTER doesn't filter flags, so we need to clear NT, AC + * and TF ourselves. To save a few cycles, we can check whether + * either was set instead of doing an unconditional popfq. + * This needs to happen before enabling interrupts so that + * we don't get preempted with NT set. + * + * If TF is set, we will single-step all the way to here -- do_debug + * will ignore all the traps. (Yes, this is slow, but so is + * single-stepping in general. This allows us to avoid having + * a more complicated code to handle the case where a user program + * forces us to single-step through the SYSENTER entry code.) + * + * NB.: .Lsysenter_fix_flags is a label with the code under it moved + * out-of-line as an optimization: NT is unlikely to be set in the + * majority of the cases and instead of polluting the I$ unnecessarily, + * we're keeping that code behind a branch which will predict as + * not-taken and therefore its instructions won't be fetched. + */ + testl $X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, PT_EFLAGS(%esp) + jnz .Lsysenter_fix_flags +.Lsysenter_flags_fixed: + /* * User mode is traced as though IRQs are on, and SYSENTER * turned them off. @@ -326,6 +399,15 @@ sysenter_past_esp: popl %ebp /* pt_regs->bp */ popl %eax /* pt_regs->ax */ + /* + * Restore all flags except IF. (We restore IF separately because + * STI gives a one-instruction window in which we won't be interrupted, + * whereas POPF does not.) + */ + addl $PT_EFLAGS-PT_DS, %esp /* point esp at pt_regs->flags */ + btr $X86_EFLAGS_IF_BIT, (%esp) + popfl + /* * Return back to the vDSO, which will pop ecx and edx. * Don't bother with DS and ES (they already contain __USER_DS). @@ -339,28 +421,63 @@ sysenter_past_esp: .popsection _ASM_EXTABLE(1b, 2b) PTGS_TO_GS_EX + +.Lsysenter_fix_flags: + pushl $X86_EFLAGS_FIXED + popfl + jmp .Lsysenter_flags_fixed +GLOBAL(__end_SYSENTER_singlestep_region) ENDPROC(entry_SYSENTER_32) - # system call handler stub +/* + * 32-bit legacy system call entry. + * + * 32-bit x86 Linux system calls traditionally used the INT $0x80 + * instruction. INT $0x80 lands here. + * + * This entry point can be used by any 32-bit perform system calls. + * Instances of INT $0x80 can be found inline in various programs and + * libraries. It is also used by the vDSO's __kernel_vsyscall + * fallback for hardware that doesn't support a faster entry method. + * Restarted 32-bit system calls also fall back to INT $0x80 + * regardless of what instruction was originally used to do the system + * call. (64-bit programs can use INT $0x80 as well, but they can + * only run on 64-bit kernels and therefore land in + * entry_INT80_compat.) + * + * This is considered a slow path. It is not used by most libc + * implementations on modern hardware except during process startup. + * + * Arguments: + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp arg6 + */ ENTRY(entry_INT80_32) ASM_CLAC pushl %eax /* pt_regs->orig_ax */ SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ /* - * User mode is traced as though IRQs are on. Unlike the 64-bit - * case, INT80 is a trap gate on 32-bit kernels, so interrupts - * are already on (unless user code is messing around with iopl). + * User mode is traced as though IRQs are on, and the interrupt gate + * turned them off. */ + TRACE_IRQS_OFF movl %esp, %eax - call do_syscall_32_irqs_on + call do_int80_syscall_32 .Lsyscall_32_done: restore_all: TRACE_IRQS_IRET restore_all_notrace: #ifdef CONFIG_X86_ESPFIX32 + ALTERNATIVE "jmp restore_nocheck", "", X86_BUG_ESPFIX + movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS /* * Warning: PT_OLDSS(%esp) contains the wrong/random values if we @@ -387,19 +504,6 @@ ENTRY(iret_exc ) #ifdef CONFIG_X86_ESPFIX32 ldt_ss: -#ifdef CONFIG_PARAVIRT - /* - * The kernel can't run on a non-flat stack if paravirt mode - * is active. Rather than try to fixup the high bits of - * ESP, bypass this code entirely. This may break DOSemu - * and/or Wine support in a paravirt VM, although the option - * is still available to implement the setting of the high - * 16-bits in the INTERRUPT_RETURN paravirt-op. - */ - cmpl $0, pv_info+PARAVIRT_enabled - jne restore_nocheck -#endif - /* * Setup and switch to ESPFIX stack * @@ -632,14 +736,6 @@ ENTRY(spurious_interrupt_bug) END(spurious_interrupt_bug) #ifdef CONFIG_XEN -/* - * Xen doesn't set %esp to be precisely what the normal SYSENTER - * entry point expects, so fix it up before using the normal path. - */ -ENTRY(xen_sysenter_target) - addl $5*4, %esp /* remove xen-provided frame */ - jmp sysenter_past_esp - ENTRY(xen_hypervisor_callback) pushl $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL @@ -939,51 +1035,48 @@ error_code: jmp ret_from_exception END(page_fault) -/* - * Debug traps and NMI can happen at the one SYSENTER instruction - * that sets up the real kernel stack. Check here, since we can't - * allow the wrong stack to be used. - * - * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have - * already pushed 3 words if it hits on the sysenter instruction: - * eflags, cs and eip. - * - * We just load the right stack, and push the three (known) values - * by hand onto the new stack - while updating the return eip past - * the instruction that would have done it for sysenter. - */ -.macro FIX_STACK offset ok label - cmpw $__KERNEL_CS, 4(%esp) - jne \ok -\label: - movl TSS_sysenter_sp0 + \offset(%esp), %esp - pushfl - pushl $__KERNEL_CS - pushl $sysenter_past_esp -.endm - ENTRY(debug) + /* + * #DB can happen at the first instruction of + * entry_SYSENTER_32 or in Xen's SYSENTER prologue. If this + * happens, then we will be running on a very small stack. We + * need to detect this condition and switch to the thread + * stack before calling any C code at all. + * + * If you edit this code, keep in mind that NMIs can happen in here. + */ ASM_CLAC - cmpl $entry_SYSENTER_32, (%esp) - jne debug_stack_correct - FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn -debug_stack_correct: pushl $-1 # mark this as an int SAVE_ALL - TRACE_IRQS_OFF xorl %edx, %edx # error code 0 movl %esp, %eax # pt_regs pointer + + /* Are we currently on the SYSENTER stack? */ + PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ + cmpl $SIZEOF_SYSENTER_stack, %ecx + jb .Ldebug_from_sysenter_stack + + TRACE_IRQS_OFF + call do_debug + jmp ret_from_exception + +.Ldebug_from_sysenter_stack: + /* We're on the SYSENTER stack. Switch off. */ + movl %esp, %ebp + movl PER_CPU_VAR(cpu_current_top_of_stack), %esp + TRACE_IRQS_OFF call do_debug + movl %ebp, %esp jmp ret_from_exception END(debug) /* - * NMI is doubly nasty. It can happen _while_ we're handling - * a debug fault, and the debug fault hasn't yet been able to - * clear up the stack. So we first check whether we got an - * NMI on the sysenter entry path, but after that we need to - * check whether we got an NMI on the debug path where the debug - * fault happened on the sysenter path. + * NMI is doubly nasty. It can happen on the first instruction of + * entry_SYSENTER_32 (just like #DB), but it can also interrupt the beginning + * of the #DB handler even if that #DB in turn hit before entry_SYSENTER_32 + * switched stacks. We handle both conditions by simply checking whether we + * interrupted kernel code running on the SYSENTER stack. */ ENTRY(nmi) ASM_CLAC @@ -994,41 +1087,32 @@ ENTRY(nmi) popl %eax je nmi_espfix_stack #endif - cmpl $entry_SYSENTER_32, (%esp) - je nmi_stack_fixup - pushl %eax - movl %esp, %eax - /* - * Do not access memory above the end of our stack page, - * it might not exist. - */ - andl $(THREAD_SIZE-1), %eax - cmpl $(THREAD_SIZE-20), %eax - popl %eax - jae nmi_stack_correct - cmpl $entry_SYSENTER_32, 12(%esp) - je nmi_debug_stack_check -nmi_stack_correct: - pushl %eax + + pushl %eax # pt_regs->orig_ax SAVE_ALL xorl %edx, %edx # zero error code movl %esp, %eax # pt_regs pointer + + /* Are we currently on the SYSENTER stack? */ + PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ + cmpl $SIZEOF_SYSENTER_stack, %ecx + jb .Lnmi_from_sysenter_stack + + /* Not on SYSENTER stack. */ call do_nmi jmp restore_all_notrace -nmi_stack_fixup: - FIX_STACK 12, nmi_stack_correct, 1 - jmp nmi_stack_correct - -nmi_debug_stack_check: - cmpw $__KERNEL_CS, 16(%esp) - jne nmi_stack_correct - cmpl $debug, (%esp) - jb nmi_stack_correct - cmpl $debug_esp_fix_insn, (%esp) - ja nmi_stack_correct - FIX_STACK 24, nmi_stack_correct, 1 - jmp nmi_stack_correct +.Lnmi_from_sysenter_stack: + /* + * We're on the SYSENTER stack. Switch off. No one (not even debug) + * is using the thread stack right now, so it's safe for us to use it. + */ + movl %esp, %ebp + movl PER_CPU_VAR(cpu_current_top_of_stack), %esp + call do_nmi + movl %ebp, %esp + jmp restore_all_notrace #ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9d34d3cfceb61..858b555e274b8 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -103,6 +103,16 @@ ENDPROC(native_usergs_sysret64) /* * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers. * + * This is the only entry point used for 64-bit system calls. The + * hardware interface is reasonably well designed and the register to + * argument mapping Linux uses fits well with the registers that are + * available when SYSCALL is used. + * + * SYSCALL instructions can be found inlined in libc implementations as + * well as some other programs and libraries. There are also a handful + * of SYSCALL instructions in the vDSO used, for example, as a + * clock_gettimeofday fallback. + * * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, * then loads new ss, cs, and rip from previously programmed MSRs. * rflags gets masked by a value from another MSR (so CLD and CLAC @@ -145,17 +155,11 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) movq %rsp, PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + TRACE_IRQS_OFF + /* Construct struct pt_regs on stack */ pushq $__USER_DS /* pt_regs->ss */ pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ - /* - * Re-enable interrupts. - * We use 'rsp_scratch' as a scratch space, hence irq-off block above - * must execute atomically in the face of possible interrupt-driven - * task preemption. We must enable interrupts only after we're done - * with using rsp_scratch: - */ - ENABLE_INTERRUPTS(CLBR_NONE) pushq %r11 /* pt_regs->flags */ pushq $__USER_CS /* pt_regs->cs */ pushq %rcx /* pt_regs->ip */ @@ -171,9 +175,21 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r11 /* pt_regs->r11 */ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz tracesys + /* + * If we need to do entry work or if we guess we'll need to do + * exit work, go straight to the slow path. + */ + testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz entry_SYSCALL64_slow_path + entry_SYSCALL_64_fastpath: + /* + * Easy case: enable interrupts and issue the syscall. If the syscall + * needs pt_regs, we'll call a stub that disables interrupts again + * and jumps to the slow path. + */ + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) #if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max, %rax #else @@ -182,103 +198,56 @@ entry_SYSCALL_64_fastpath: #endif ja 1f /* return -ENOSYS (already in pt_regs->ax) */ movq %r10, %rcx + + /* + * This call instruction is handled specially in stub_ptregs_64. + * It might end up jumping to the slow path. If it jumps, RAX + * and all argument registers are clobbered. + */ call *sys_call_table(, %rax, 8) +.Lentry_SYSCALL_64_after_fastpath_call: + movq %rax, RAX(%rsp) 1: -/* - * Syscall return path ending with SYSRET (fast path). - * Has incompletely filled pt_regs. - */ - LOCKDEP_SYS_EXIT - /* - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - DISABLE_INTERRUPTS(CLBR_NONE) /* - * We must check ti flags with interrupts (or at least preemption) - * off because we must *never* return to userspace without - * processing exit work that is enqueued if we're preempted here. - * In particular, returning to userspace with any of the one-shot - * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is - * very bad. + * If we get here, then we know that pt_regs is clean for SYSRET64. + * If we see that no exit work is required (which we are required + * to check with IRQs off), then we can go straight to SYSRET64. */ + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ + jnz 1f - RESTORE_C_REGS_EXCEPT_RCX_R11 + LOCKDEP_SYS_EXIT + TRACE_IRQS_ON /* user mode is traced as IRQs on */ movq RIP(%rsp), %rcx movq EFLAGS(%rsp), %r11 + RESTORE_C_REGS_EXCEPT_RCX_R11 movq RSP(%rsp), %rsp - /* - * 64-bit SYSRET restores rip from rcx, - * rflags from r11 (but RF and VM bits are forced to 0), - * cs and ss are loaded from MSRs. - * Restoration of rflags re-enables interrupts. - * - * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss - * descriptor is not reinitialized. This means that we should - * avoid SYSRET with SS == NULL, which could happen if we schedule, - * exit the kernel, and re-enter using an interrupt vector. (All - * interrupt entries on x86_64 set SS to NULL.) We prevent that - * from happening by reloading SS in __switch_to. (Actually - * detecting the failure in 64-bit userspace is tricky but can be - * done.) - */ USERGS_SYSRET64 -GLOBAL(int_ret_from_sys_call_irqs_off) +1: + /* + * The fast path looked good when we started, but something changed + * along the way and we need to switch to the slow path. Calling + * raise(3) will trigger this, for example. IRQs are off. + */ TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - jmp int_ret_from_sys_call - - /* Do syscall entry tracing */ -tracesys: - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - call syscall_trace_enter_phase1 - test %rax, %rax - jnz tracesys_phase2 /* if needed, run the slow path */ - RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ - movq ORIG_RAX(%rsp), %rax - jmp entry_SYSCALL_64_fastpath /* and return to the fast path */ - -tracesys_phase2: SAVE_EXTRA_REGS movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - movq %rax, %rdx - call syscall_trace_enter_phase2 - - /* - * Reload registers from stack in case ptrace changed them. - * We don't reload %rax because syscall_trace_entry_phase2() returned - * the value it wants us to use in the table lookup. - */ - RESTORE_C_REGS_EXCEPT_RAX - RESTORE_EXTRA_REGS -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx /* fixup for C */ - call *sys_call_table(, %rax, 8) - movq %rax, RAX(%rsp) -1: - /* Use IRET because user could have changed pt_regs->foo */ + call syscall_return_slowpath /* returns with IRQs disabled */ + jmp return_from_SYSCALL_64 -/* - * Syscall return path ending with IRET. - * Has correct iret frame. - */ -GLOBAL(int_ret_from_sys_call) +entry_SYSCALL64_slow_path: + /* IRQs are off. */ SAVE_EXTRA_REGS movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ + call do_syscall_64 /* returns with IRQs disabled */ + +return_from_SYSCALL_64: RESTORE_EXTRA_REGS TRACE_IRQS_IRETQ /* we're about to change IF */ @@ -355,83 +324,45 @@ opportunistic_sysret_failed: jmp restore_c_regs_and_iret END(entry_SYSCALL_64) +ENTRY(stub_ptregs_64) + /* + * Syscalls marked as needing ptregs land here. + * If we are on the fast path, we need to save the extra regs, + * which we achieve by trying again on the slow path. If we are on + * the slow path, the extra regs are already saved. + * + * RAX stores a pointer to the C function implementing the syscall. + * IRQs are on. + */ + cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) + jne 1f - .macro FORK_LIKE func -ENTRY(stub_\func) - SAVE_EXTRA_REGS 8 - jmp sys_\func -END(stub_\func) - .endm - - FORK_LIKE clone - FORK_LIKE fork - FORK_LIKE vfork - -ENTRY(stub_execve) - call sys_execve -return_from_execve: - testl %eax, %eax - jz 1f - /* exec failed, can use fast SYSRET code path in this case */ - ret -1: - /* must use IRET code path (pt_regs->cs may have changed) */ - addq $8, %rsp - ZERO_EXTRA_REGS - movq %rax, RAX(%rsp) - jmp int_ret_from_sys_call -END(stub_execve) -/* - * Remaining execve stubs are only 7 bytes long. - * ENTRY() often aligns to 16 bytes, which in this case has no benefits. - */ - .align 8 -GLOBAL(stub_execveat) - call sys_execveat - jmp return_from_execve -END(stub_execveat) - -#if defined(CONFIG_X86_X32_ABI) - .align 8 -GLOBAL(stub_x32_execve) - call compat_sys_execve - jmp return_from_execve -END(stub_x32_execve) - .align 8 -GLOBAL(stub_x32_execveat) - call compat_sys_execveat - jmp return_from_execve -END(stub_x32_execveat) -#endif - -/* - * sigreturn is special because it needs to restore all registers on return. - * This cannot be done with SYSRET, so use the IRET return path instead. - */ -ENTRY(stub_rt_sigreturn) /* - * SAVE_EXTRA_REGS result is not normally needed: - * sigreturn overwrites all pt_regs->GPREGS. - * But sigreturn can fail (!), and there is no easy way to detect that. - * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error, - * we SAVE_EXTRA_REGS here. + * Called from fast path -- disable IRQs again, pop return address + * and jump to slow path */ - SAVE_EXTRA_REGS 8 - call sys_rt_sigreturn -return_from_stub: - addq $8, %rsp - RESTORE_EXTRA_REGS - movq %rax, RAX(%rsp) - jmp int_ret_from_sys_call -END(stub_rt_sigreturn) + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + popq %rax + jmp entry_SYSCALL64_slow_path -#ifdef CONFIG_X86_X32_ABI -ENTRY(stub_x32_rt_sigreturn) - SAVE_EXTRA_REGS 8 - call sys32_x32_rt_sigreturn - jmp return_from_stub -END(stub_x32_rt_sigreturn) -#endif +1: + /* Called from C */ + jmp *%rax /* called from C */ +END(stub_ptregs_64) + +.macro ptregs_stub func +ENTRY(ptregs_\func) + leaq \func(%rip), %rax + jmp stub_ptregs_64 +END(ptregs_\func) +.endm + +/* Instantiate ptregs_stub for each ptregs-using syscall */ +#define __SYSCALL_64_QUAL_(sym) +#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym +#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) +#include /* * A newly forked process directly context switches into this address. @@ -439,7 +370,6 @@ END(stub_x32_rt_sigreturn) * rdi: prev task we switched from */ ENTRY(ret_from_fork) - LOCK ; btr $TIF_FORK, TI_flags(%r8) pushq $0x0002 @@ -447,28 +377,32 @@ ENTRY(ret_from_fork) call schedule_tail /* rdi: 'prev' task parameter */ - RESTORE_EXTRA_REGS - testb $3, CS(%rsp) /* from kernel_thread? */ + jnz 1f /* - * By the time we get here, we have no idea whether our pt_regs, - * ti flags, and ti status came from the 64-bit SYSCALL fast path, - * the slow path, or one of the 32-bit compat paths. - * Use IRET code path to return, since it can safely handle - * all of the above. + * We came from kernel_thread. This code path is quite twisted, and + * someone should clean it up. + * + * copy_thread_tls stashes the function pointer in RBX and the + * parameter to be passed in RBP. The called function is permitted + * to call do_execve and thereby jump to user mode. */ - jnz int_ret_from_sys_call + movq RBP(%rsp), %rdi + call *RBX(%rsp) + movl $0, RAX(%rsp) /* - * We came from kernel_thread - * nb: we depend on RESTORE_EXTRA_REGS above + * Fall through as though we're exiting a syscall. This makes a + * twisted sort of sense if we just called do_execve. */ - movq %rbp, %rdi - call *%rbx - movl $0, RAX(%rsp) - RESTORE_EXTRA_REGS - jmp int_ret_from_sys_call + +1: + movq %rsp, %rdi + call syscall_return_slowpath /* returns with IRQs disabled */ + TRACE_IRQS_ON /* user mode is traced as IRQS on */ + SWAPGS + jmp restore_regs_and_iret END(ret_from_fork) /* diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 3c990eeee40bd..847f2f0c31e50 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -19,12 +19,21 @@ .section .entry.text, "ax" /* - * 32-bit SYSENTER instruction entry. + * 32-bit SYSENTER entry. * - * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs. - * IF and VM in rflags are cleared (IOW: interrupts are off). + * 32-bit system calls through the vDSO's __kernel_vsyscall enter here + * on 64-bit kernels running on Intel CPUs. + * + * The SYSENTER instruction, in principle, should *only* occur in the + * vDSO. In practice, a small number of Android devices were shipped + * with a copy of Bionic that inlined a SYSENTER instruction. This + * never happened in any of Google's Bionic versions -- it only happened + * in a narrow range of Intel-provided versions. + * + * SYSENTER loads SS, RSP, CS, and RIP from previously programmed MSRs. + * IF and VM in RFLAGS are cleared (IOW: interrupts are off). * SYSENTER does not save anything on the stack, - * and does not save old rip (!!!) and rflags. + * and does not save old RIP (!!!), RSP, or RFLAGS. * * Arguments: * eax system call number @@ -35,10 +44,6 @@ * edi arg5 * ebp user stack * 0(%ebp) arg6 - * - * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. We set up a complete hardware stack frame to share code - * with the int 0x80 path. */ ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ @@ -66,8 +71,6 @@ ENTRY(entry_SYSENTER_compat) */ pushfq /* pt_regs->flags (except IF = 0) */ orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ - ASM_CLAC /* Clear AC after saving FLAGS */ - pushq $__USER32_CS /* pt_regs->cs */ xorq %r8,%r8 pushq %r8 /* pt_regs->ip = 0 (placeholder) */ @@ -90,19 +93,25 @@ ENTRY(entry_SYSENTER_compat) cld /* - * Sysenter doesn't filter flags, so we need to clear NT + * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether - * NT was set instead of doing an unconditional popfq. + * either was set instead of doing an unconditional popfq. * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * + * If TF is set, we will single-step all the way to here -- do_debug + * will ignore all the traps. (Yes, this is slow, but so is + * single-stepping in general. This allows us to avoid having + * a more complicated code to handle the case where a user program + * forces us to single-step through the SYSENTER entry code.) + * * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ unnecessarily, * we're keeping that code behind a branch which will predict as * not-taken and therefore its instructions won't be fetched. */ - testl $X86_EFLAGS_NT, EFLAGS(%rsp) + testl $X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, EFLAGS(%rsp) jnz .Lsysenter_fix_flags .Lsysenter_flags_fixed: @@ -123,20 +132,42 @@ ENTRY(entry_SYSENTER_compat) pushq $X86_EFLAGS_FIXED popfq jmp .Lsysenter_flags_fixed +GLOBAL(__end_entry_SYSENTER_compat) ENDPROC(entry_SYSENTER_compat) /* - * 32-bit SYSCALL instruction entry. + * 32-bit SYSCALL entry. + * + * 32-bit system calls through the vDSO's __kernel_vsyscall enter here + * on 64-bit kernels running on AMD CPUs. + * + * The SYSCALL instruction, in principle, should *only* occur in the + * vDSO. In practice, it appears that this really is the case. + * As evidence: + * + * - The calling convention for SYSCALL has changed several times without + * anyone noticing. * - * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, - * then loads new ss, cs, and rip from previously programmed MSRs. - * rflags gets masked by a value from another MSR (so CLD and CLAC - * are not needed). SYSCALL does not save anything on the stack - * and does not change rsp. + * - Prior to the in-kernel X86_BUG_SYSRET_SS_ATTRS fixup, anything + * user task that did SYSCALL without immediately reloading SS + * would randomly crash. * - * Note: rflags saving+masking-with-MSR happens only in Long mode + * - Most programmers do not directly target AMD CPUs, and the 32-bit + * SYSCALL instruction does not exist on Intel CPUs. Even on AMD + * CPUs, Linux disables the SYSCALL instruction on 32-bit kernels + * because the SYSCALL instruction in legacy/native 32-bit mode (as + * opposed to compat mode) is sufficiently poorly designed as to be + * essentially unusable. + * + * 32-bit SYSCALL saves RIP to RCX, clears RFLAGS.RF, then saves + * RFLAGS to R11, then loads new SS, CS, and RIP from previously + * programmed MSRs. RFLAGS gets masked by a value from another MSR + * (so CLD and CLAC are not needed). SYSCALL does not save anything on + * the stack and does not change RSP. + * + * Note: RFLAGS saving+masking-with-MSR happens only in Long mode * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it). - * Don't get confused: rflags saving+masking depends on Long Mode Active bit + * Don't get confused: RFLAGS saving+masking depends on Long Mode Active bit * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes * or target CS descriptor's L bit (SYSCALL does not read segment descriptors). * @@ -236,7 +267,21 @@ sysret32_from_system_call: END(entry_SYSCALL_compat) /* - * Emulated IA32 system calls via int 0x80. + * 32-bit legacy system call entry. + * + * 32-bit x86 Linux system calls traditionally used the INT $0x80 + * instruction. INT $0x80 lands here. + * + * This entry point can be used by 32-bit and 64-bit programs to perform + * 32-bit system calls. Instances of INT $0x80 can be found inline in + * various programs and libraries. It is also used by the vDSO's + * __kernel_vsyscall fallback for hardware that doesn't support a faster + * entry method. Restarted 32-bit system calls also fall back to INT + * $0x80 regardless of what instruction was originally used to do the + * system call. + * + * This is considered a slow path. It is not used by most libc + * implementations on modern hardware except during process startup. * * Arguments: * eax system call number @@ -245,17 +290,8 @@ END(entry_SYSCALL_compat) * edx arg3 * esi arg4 * edi arg5 - * ebp arg6 (note: not saved in the stack frame, should not be touched) - * - * Notes: - * Uses the same stack frame as the x86-64 version. - * All registers except eax must be saved (but ptrace may violate that). - * Arguments are zero extended. For system calls that want sign extension and - * take long arguments a wrapper is needed. Most calls can just be called - * directly. - * Assumes it is only called from user space and entered with interrupts off. + * ebp arg6 */ - ENTRY(entry_INT80_compat) /* * Interrupts are off on entry. @@ -300,7 +336,7 @@ ENTRY(entry_INT80_compat) TRACE_IRQS_OFF movq %rsp, %rdi - call do_syscall_32_irqs_off + call do_int80_syscall_32 .Lsyscall_32_done: /* Go back to user mode. */ diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 9a6649857106a..8f895ee13a1cb 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -6,17 +6,11 @@ #include #include -#ifdef CONFIG_IA32_EMULATION -#define SYM(sym, compat) compat -#else -#define SYM(sym, compat) sym -#endif - -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include #undef __SYSCALL_I386 -#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat), +#define __SYSCALL_I386(nr, sym, qual) [nr] = sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 41283d22be7a9..9dbc5abb6162f 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -6,19 +6,14 @@ #include #include -#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#define __SYSCALL_64_QUAL_(sym) sym +#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym -#ifdef CONFIG_X86_X32_ABI -# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat) -#else -# define __SYSCALL_X32(nr, sym, compat) /* nothing */ -#endif - -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, compat) [nr] = sym, +#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index dc1040a50bdc2..2e5b565adacc5 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -21,7 +21,7 @@ 12 common brk sys_brk 13 64 rt_sigaction sys_rt_sigaction 14 common rt_sigprocmask sys_rt_sigprocmask -15 64 rt_sigreturn stub_rt_sigreturn +15 64 rt_sigreturn sys_rt_sigreturn/ptregs 16 64 ioctl sys_ioctl 17 common pread64 sys_pread64 18 common pwrite64 sys_pwrite64 @@ -62,10 +62,10 @@ 53 common socketpair sys_socketpair 54 64 setsockopt sys_setsockopt 55 64 getsockopt sys_getsockopt -56 common clone stub_clone -57 common fork stub_fork -58 common vfork stub_vfork -59 64 execve stub_execve +56 common clone sys_clone/ptregs +57 common fork sys_fork/ptregs +58 common vfork sys_vfork/ptregs +59 64 execve sys_execve/ptregs 60 common exit sys_exit 61 common wait4 sys_wait4 62 common kill sys_kill @@ -178,7 +178,7 @@ 169 common reboot sys_reboot 170 common sethostname sys_sethostname 171 common setdomainname sys_setdomainname -172 common iopl sys_iopl +172 common iopl sys_iopl/ptregs 173 common ioperm sys_ioperm 174 64 create_module 175 common init_module sys_init_module @@ -328,7 +328,7 @@ 319 common memfd_create sys_memfd_create 320 common kexec_file_load sys_kexec_file_load 321 common bpf sys_bpf -322 64 execveat stub_execveat +322 64 execveat sys_execveat/ptregs 323 common userfaultfd sys_userfaultfd 324 common membarrier sys_membarrier 325 common mlock2 sys_mlock2 @@ -339,14 +339,14 @@ # for native 64-bit operation. # 512 x32 rt_sigaction compat_sys_rt_sigaction -513 x32 rt_sigreturn stub_x32_rt_sigreturn +513 x32 rt_sigreturn sys32_x32_rt_sigreturn 514 x32 ioctl compat_sys_ioctl 515 x32 readv compat_sys_readv 516 x32 writev compat_sys_writev 517 x32 recvfrom compat_sys_recvfrom 518 x32 sendmsg compat_sys_sendmsg 519 x32 recvmsg compat_sys_recvmsg -520 x32 execve stub_x32_execve +520 x32 execve compat_sys_execve/ptregs 521 x32 ptrace compat_sys_ptrace 522 x32 rt_sigpending compat_sys_rt_sigpending 523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait @@ -371,4 +371,4 @@ 542 x32 getsockopt compat_sys_getsockopt 543 x32 io_setup compat_sys_io_setup 544 x32 io_submit compat_sys_io_submit -545 x32 execveat stub_x32_execveat +545 x32 execveat compat_sys_execveat/ptregs diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 0e7f8ec071e76..cd3d3015d7df8 100644 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh @@ -3,13 +3,63 @@ in="$1" out="$2" +syscall_macro() { + abi="$1" + nr="$2" + entry="$3" + + # Entry can be either just a function name or "function/qualifier" + real_entry="${entry%%/*}" + qualifier="${entry:${#real_entry}}" # Strip the function name + qualifier="${qualifier:1}" # Strip the slash, if any + + echo "__SYSCALL_${abi}($nr, $real_entry, $qualifier)" +} + +emit() { + abi="$1" + nr="$2" + entry="$3" + compat="$4" + + if [ "$abi" == "64" -a -n "$compat" ]; then + echo "a compat entry for a 64-bit syscall makes no sense" >&2 + exit 1 + fi + + if [ -z "$compat" ]; then + if [ -n "$entry" ]; then + syscall_macro "$abi" "$nr" "$entry" + fi + else + echo "#ifdef CONFIG_X86_32" + if [ -n "$entry" ]; then + syscall_macro "$abi" "$nr" "$entry" + fi + echo "#else" + syscall_macro "$abi" "$nr" "$compat" + echo "#endif" + fi +} + grep '^[0-9]' "$in" | sort -n | ( while read nr abi name entry compat; do abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` - if [ -n "$compat" ]; then - echo "__SYSCALL_${abi}($nr, $entry, $compat)" - elif [ -n "$entry" ]; then - echo "__SYSCALL_${abi}($nr, $entry, $entry)" + if [ "$abi" == "COMMON" -o "$abi" == "64" ]; then + # COMMON is the same as 64, except that we don't expect X32 + # programs to use it. Our expectation has nothing to do with + # any generated code, so treat them the same. + emit 64 "$nr" "$entry" "$compat" + elif [ "$abi" == "X32" ]; then + # X32 is equivalent to 64 on an X32-compatible kernel. + echo "#ifdef CONFIG_X86_X32_ABI" + emit 64 "$nr" "$entry" "$compat" + echo "#endif" + elif [ "$abi" == "I386" ]; then + emit "$abi" "$nr" "$entry" "$compat" + else + echo "Unknown abi $abi" >&2 + exit 1 fi done ) > "$out" diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 0224987556ce8..63a03bb91497e 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -140,7 +140,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, fprintf(outfile, "#include \n"); fprintf(outfile, "\n"); fprintf(outfile, - "static unsigned char raw_data[%lu] __page_aligned_data = {", + "static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {", mapping_size); for (j = 0; j < stripped_len; j++) { if (j % 10 == 0) @@ -150,16 +150,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, } fprintf(outfile, "\n};\n\n"); - fprintf(outfile, "static struct page *pages[%lu];\n\n", - mapping_size / 4096); - fprintf(outfile, "const struct vdso_image %s = {\n", name); fprintf(outfile, "\t.data = raw_data,\n"); fprintf(outfile, "\t.size = %lu,\n", mapping_size); - fprintf(outfile, "\t.text_mapping = {\n"); - fprintf(outfile, "\t\t.name = \"[vdso]\",\n"); - fprintf(outfile, "\t\t.pages = pages,\n"); - fprintf(outfile, "\t},\n"); if (alt_sec) { fprintf(outfile, "\t.alt = %lu,\n", (unsigned long)GET_LE(&alt_sec->sh_offset)); diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 08a317a9ae4b5..7853b53959cd3 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -11,7 +11,6 @@ #include #include -#include #include #include diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index 3a1d9297074bc..0109ac6cb79cc 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -3,7 +3,7 @@ */ #include -#include +#include #include /* diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index b8f69e264ac41..10f7045849226 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -20,6 +20,7 @@ #include #include #include +#include #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; @@ -27,13 +28,7 @@ unsigned int __read_mostly vdso64_enabled = 1; void __init init_vdso_image(const struct vdso_image *image) { - int i; - int npages = (image->size) / PAGE_SIZE; - BUG_ON(image->size % PAGE_SIZE != 0); - for (i = 0; i < npages; i++) - image->text_mapping.pages[i] = - virt_to_page(image->data + i*PAGE_SIZE); apply_alternatives((struct alt_instr *)(image->data + image->alt), (struct alt_instr *)(image->data + image->alt + @@ -90,18 +85,87 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) #endif } +static int vdso_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + const struct vdso_image *image = vma->vm_mm->context.vdso_image; + + if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size) + return VM_FAULT_SIGBUS; + + vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT)); + get_page(vmf->page); + return 0; +} + +static const struct vm_special_mapping text_mapping = { + .name = "[vdso]", + .fault = vdso_fault, +}; + +static int vvar_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + const struct vdso_image *image = vma->vm_mm->context.vdso_image; + long sym_offset; + int ret = -EFAULT; + + if (!image) + return VM_FAULT_SIGBUS; + + sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) + + image->sym_vvar_start; + + /* + * Sanity check: a symbol offset of zero means that the page + * does not exist for this vdso image, not that the page is at + * offset zero relative to the text mapping. This should be + * impossible here, because sym_offset should only be zero for + * the page past the end of the vvar mapping. + */ + if (sym_offset == 0) + return VM_FAULT_SIGBUS; + + if (sym_offset == image->sym_vvar_page) { + ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, + __pa_symbol(&__vvar_page) >> PAGE_SHIFT); + } else if (sym_offset == image->sym_hpet_page) { +#ifdef CONFIG_HPET_TIMER + if (hpet_address && vclock_was_used(VCLOCK_HPET)) { + ret = vm_insert_pfn_prot( + vma, + (unsigned long)vmf->virtual_address, + hpet_address >> PAGE_SHIFT, + pgprot_noncached(PAGE_READONLY)); + } +#endif + } else if (sym_offset == image->sym_pvclock_page) { + struct pvclock_vsyscall_time_info *pvti = + pvclock_pvti_cpu0_va(); + if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) { + ret = vm_insert_pfn( + vma, + (unsigned long)vmf->virtual_address, + __pa(pvti) >> PAGE_SHIFT); + } + } + + if (ret == 0 || ret == -EBUSY) + return VM_FAULT_NOPAGE; + + return VM_FAULT_SIGBUS; +} + static int map_vdso(const struct vdso_image *image, bool calculate_addr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long addr, text_start; int ret = 0; - static struct page *no_pages[] = {NULL}; - static struct vm_special_mapping vvar_mapping = { + static const struct vm_special_mapping vvar_mapping = { .name = "[vvar]", - .pages = no_pages, + .fault = vvar_fault, }; - struct pvclock_vsyscall_time_info *pvti; if (calculate_addr) { addr = vdso_addr(current->mm->start_stack, @@ -121,6 +185,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) text_start = addr - image->sym_vvar_start; current->mm->context.vdso = (void __user *)text_start; + current->mm->context.vdso_image = image; /* * MAYWRITE to allow gdb to COW and set breakpoints @@ -130,7 +195,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) image->size, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - &image->text_mapping); + &text_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); @@ -140,7 +205,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) vma = _install_special_mapping(mm, addr, -image->sym_vvar_start, - VM_READ|VM_MAYREAD, + VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP| + VM_PFNMAP, &vvar_mapping); if (IS_ERR(vma)) { @@ -148,41 +214,6 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) goto up_fail; } - if (image->sym_vvar_page) - ret = remap_pfn_range(vma, - text_start + image->sym_vvar_page, - __pa_symbol(&__vvar_page) >> PAGE_SHIFT, - PAGE_SIZE, - PAGE_READONLY); - - if (ret) - goto up_fail; - -#ifdef CONFIG_HPET_TIMER - if (hpet_address && image->sym_hpet_page) { - ret = io_remap_pfn_range(vma, - text_start + image->sym_hpet_page, - hpet_address >> PAGE_SHIFT, - PAGE_SIZE, - pgprot_noncached(PAGE_READONLY)); - - if (ret) - goto up_fail; - } -#endif - - pvti = pvclock_pvti_cpu0_va(); - if (pvti && image->sym_pvclock_page) { - ret = remap_pfn_range(vma, - text_start + image->sym_pvclock_page, - __pa(pvti) >> PAGE_SHIFT, - PAGE_SIZE, - PAGE_READONLY); - - if (ret) - goto up_fail; - } - up_fail: if (ret) current->mm->context.vdso = NULL; @@ -254,7 +285,7 @@ static void vgetcpu_cpu_init(void *arg) #ifdef CONFIG_NUMA node = cpu_to_node(cpu); #endif - if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP)) + if (static_cpu_has(X86_FEATURE_RDTSCP)) write_rdtscp_aux((node << 12) | cpu); /* diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c index 51e3304169951..0fb3a104ac626 100644 --- a/arch/x86/entry/vsyscall/vsyscall_gtod.c +++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c @@ -16,6 +16,8 @@ #include #include +int vclocks_used __read_mostly; + DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); void update_vsyscall_tz(void) @@ -26,12 +28,17 @@ void update_vsyscall_tz(void) void update_vsyscall(struct timekeeper *tk) { + int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data; + /* Mark the new vclock used. */ + BUILD_BUG_ON(VCLOCK_MAX >= 32); + WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode)); + gtod_write_begin(vdata); /* copy vsyscall data */ - vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->vclock_mode = vclock_mode; vdata->cycle_last = tk->tkr_mono.cycle_last; vdata->mask = tk->tkr_mono.mask; vdata->mult = tk->tkr_mono.mult; diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile new file mode 100644 index 0000000000000..fdfea1511cc0e --- /dev/null +++ b/arch/x86/events/Makefile @@ -0,0 +1,13 @@ +obj-y += core.o + +obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o +obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o +ifdef CONFIG_AMD_IOMMU +obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o +endif +obj-$(CONFIG_CPU_SUP_INTEL) += intel/core.o intel/bts.o intel/cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel/cstate.o intel/ds.o intel/knc.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel/lbr.o intel/p4.o intel/p6.o intel/pt.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel/rapl.o msr.o +obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore.o intel/uncore_nhmex.o +obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore_snb.o intel/uncore_snbep.o diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/events/amd/core.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_amd.c rename to arch/x86/events/amd/core.c index 58610539b0486..049ada8d4e9c9 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/events/amd/core.c @@ -5,7 +5,7 @@ #include #include -#include "perf_event.h" +#include "../perf_event.h" static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/events/amd/ibs.c similarity index 98% rename from arch/x86/kernel/cpu/perf_event_amd_ibs.c rename to arch/x86/events/amd/ibs.c index 989d3c215d2bc..51087c29b2c23 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -14,7 +14,7 @@ #include -#include "perf_event.h" +#include "../perf_event.h" static u32 ibs_caps; @@ -670,7 +670,7 @@ static __init int perf_event_ibs_init(void) perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs"); - printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps); + pr_info("perf: AMD IBS detected (0x%08x)\n", ibs_caps); return 0; } @@ -774,14 +774,14 @@ static int setup_ibs_ctl(int ibs_eilvt_off) pci_read_config_dword(cpu_cfg, IBSCTL, &value); if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) { pci_dev_put(cpu_cfg); - printk(KERN_DEBUG "Failed to setup IBS LVT offset, " - "IBSCTL = 0x%08x\n", value); + pr_debug("Failed to setup IBS LVT offset, IBSCTL = 0x%08x\n", + value); return -EINVAL; } } while (1); if (!nodes) { - printk(KERN_DEBUG "No CPU node configured for IBS\n"); + pr_debug("No CPU node configured for IBS\n"); return -ENODEV; } @@ -810,7 +810,7 @@ static void force_ibs_eilvt_setup(void) preempt_enable(); if (offset == APIC_EILVT_NR_MAX) { - printk(KERN_DEBUG "No EILVT entry available\n"); + pr_debug("No EILVT entry available\n"); return; } diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/events/amd/iommu.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_amd_iommu.c rename to arch/x86/events/amd/iommu.c index 97242a9242bdf..635e5eba0caf8 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -16,8 +16,8 @@ #include #include -#include "perf_event.h" -#include "perf_event_amd_iommu.h" +#include "../perf_event.h" +#include "iommu.h" #define COUNTER_SHIFT 16 diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.h b/arch/x86/events/amd/iommu.h similarity index 100% rename from arch/x86/kernel/cpu/perf_event_amd_iommu.h rename to arch/x86/events/amd/iommu.h diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/events/amd/uncore.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_amd_uncore.c rename to arch/x86/events/amd/uncore.c index 8836fc9fa84b0..3db9569e658c8 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -538,7 +538,7 @@ static int __init amd_uncore_init(void) if (ret) goto fail_nb; - printk(KERN_INFO "perf: AMD NB counters detected\n"); + pr_info("perf: AMD NB counters detected\n"); ret = 0; } @@ -552,7 +552,7 @@ static int __init amd_uncore_init(void) if (ret) goto fail_l2; - printk(KERN_INFO "perf: AMD L2I counters detected\n"); + pr_info("perf: AMD L2I counters detected\n"); ret = 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/events/core.c similarity index 98% rename from arch/x86/kernel/cpu/perf_event.c rename to arch/x86/events/core.c index 1b443db2db500..5e830d0c95c99 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/events/core.c @@ -254,15 +254,16 @@ static bool check_hw_exists(void) * We still allow the PMU driver to operate: */ if (bios_fail) { - printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n"); - printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail); + pr_cont("Broken BIOS detected, complain to your hardware vendor.\n"); + pr_err(FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", + reg_fail, val_fail); } return true; msr_fail: - printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); - printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + pr_cont("Broken PMU hardware detected, using software events only.\n"); + pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n", boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, reg, val_new); @@ -596,6 +597,19 @@ void x86_pmu_disable_all(void) } } +/* + * There may be PMI landing after enabled=0. The PMI hitting could be before or + * after disable_all. + * + * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. + * It will not be re-enabled in the NMI handler again, because enabled=0. After + * handling the NMI, disable_all will be called, which will not change the + * state either. If PMI hits after disable_all, the PMU is already disabled + * before entering NMI handler. The NMI handler will not change the state + * either. + * + * So either situation is harmless. + */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/events/intel/bts.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_intel_bts.c rename to arch/x86/events/intel/bts.c index 2cad71d1b14cf..b99dc9258c0f9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/events/intel/bts.c @@ -26,7 +26,7 @@ #include #include -#include "perf_event.h" +#include "../perf_event.h" struct bts_ctx { struct perf_output_handle handle; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/events/intel/core.c similarity index 98% rename from arch/x86/kernel/cpu/perf_event_intel.c rename to arch/x86/events/intel/core.c index fed2ab1f1065d..68fa55b4d42e6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/events/intel/core.c @@ -18,7 +18,7 @@ #include #include -#include "perf_event.h" +#include "../perf_event.h" /* * Intel PerfMon, used on Core and later. @@ -1502,7 +1502,15 @@ static __initconst const u64 knl_hw_cache_extra_regs }; /* - * Use from PMIs where the LBRs are already disabled. + * Used from PMIs where the LBRs are already disabled. + * + * This function could be called consecutively. It is required to remain in + * disabled state if called consecutively. + * + * During consecutive calls, the same disable value will be written to related + * registers, so the PMU state remains unchanged. hw.state in + * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive + * calls. */ static void __intel_pmu_disable_all(void) { @@ -1884,6 +1892,16 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) if (__test_and_clear_bit(62, (unsigned long *)&status)) { handled++; x86_pmu.drain_pebs(regs); + /* + * There are cases where, even though, the PEBS ovfl bit is set + * in GLOBAL_OVF_STATUS, the PEBS events may also have their + * overflow bits set for their counters. We must clear them + * here because they have been processed as exact samples in + * the drain_pebs() routine. They must not be processed again + * in the for_each_bit_set() loop for regular samples below. + */ + status &= ~cpuc->pebs_enabled; + status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; } /* @@ -1929,7 +1947,10 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) goto again; done: - __intel_pmu_enable_all(0, true); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + __intel_pmu_enable_all(0, true); + /* * Only unmask the NMI after the overflow counters * have been reset. This avoids spurious NMIs on @@ -3396,6 +3417,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); x86_add_quirk(intel_nehalem_quirk); pr_cont("Nehalem events, "); @@ -3459,6 +3481,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); pr_cont("Westmere events, "); break; @@ -3581,7 +3604,7 @@ __init int intel_pmu_init(void) intel_pmu_lbr_init_hsw(); x86_pmu.event_constraints = intel_bdw_event_constraints; - x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.pebs_constraints = intel_bdw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; x86_pmu.pebs_prec_dist = true; diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/events/intel/cqm.c similarity index 98% rename from arch/x86/kernel/cpu/perf_event_intel_cqm.c rename to arch/x86/events/intel/cqm.c index a316ca96f1b63..93cb412a55792 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -7,7 +7,7 @@ #include #include #include -#include "perf_event.h" +#include "../perf_event.h" #define MSR_IA32_PQR_ASSOC 0x0c8f #define MSR_IA32_QM_CTR 0x0c8e @@ -1244,15 +1244,12 @@ static struct pmu intel_cqm_pmu = { static inline void cqm_pick_event_reader(int cpu) { - int phys_id = topology_physical_package_id(cpu); - int i; + int reader; - for_each_cpu(i, &cqm_cpumask) { - if (phys_id == topology_physical_package_id(i)) - return; /* already got reader for this socket */ - } - - cpumask_set_cpu(cpu, &cqm_cpumask); + /* First online cpu in package becomes the reader */ + reader = cpumask_any_and(&cqm_cpumask, topology_core_cpumask(cpu)); + if (reader >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cqm_cpumask); } static void intel_cqm_cpu_starting(unsigned int cpu) @@ -1270,24 +1267,17 @@ static void intel_cqm_cpu_starting(unsigned int cpu) static void intel_cqm_cpu_exit(unsigned int cpu) { - int phys_id = topology_physical_package_id(cpu); - int i; + int target; - /* - * Is @cpu a designated cqm reader? - */ + /* Is @cpu the current cqm reader for this package ? */ if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask)) return; - for_each_online_cpu(i) { - if (i == cpu) - continue; + /* Find another online reader in this package */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - if (phys_id == topology_physical_package_id(i)) { - cpumask_set_cpu(i, &cqm_cpumask); - break; - } - } + if (target < nr_cpu_ids) + cpumask_set_cpu(target, &cqm_cpumask); } static int intel_cqm_cpu_notifier(struct notifier_block *nb, diff --git a/arch/x86/kernel/cpu/perf_event_intel_cstate.c b/arch/x86/events/intel/cstate.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_intel_cstate.c rename to arch/x86/events/intel/cstate.c index 75a38b5a2e26a..7946c4231169f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -89,7 +89,7 @@ #include #include #include -#include "perf_event.h" +#include "../perf_event.h" #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/events/intel/ds.c similarity index 93% rename from arch/x86/kernel/cpu/perf_event_intel_ds.c rename to arch/x86/events/intel/ds.c index 10602f0a438fd..ce7211a07c0b8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/events/intel/ds.c @@ -5,7 +5,7 @@ #include #include -#include "perf_event.h" +#include "../perf_event.h" /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -51,7 +51,8 @@ union intel_x86_pebs_dse { #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) -static const u64 pebs_data_source[] = { +/* Version for Sandy Bridge and later */ +static u64 pebs_data_source[] = { P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = { OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ }; +/* Patch up minor differences in the bits */ +void __init intel_pmu_pebs_data_source_nhm(void) +{ + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); + buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu) per_cpu(insn_buffer, cpu) = ibuffer; } - max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; + max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size; ds->pebs_buffer_base = (u64)(unsigned long)buffer; ds->pebs_index = ds->pebs_buffer_base; @@ -722,6 +731,30 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_bdw_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), + EVENT_CONSTRAINT_END +}; + + struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ @@ -1319,19 +1352,28 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; int format = x86_pmu.intel_cap.pebs_format; switch (format) { case 0: - printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); + pr_cont("PEBS fmt0%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); + /* + * Using >PAGE_SIZE buffers makes the WRMSR to + * PERF_GLOBAL_CTRL in intel_pmu_enable_all() + * mysteriously hang on Core2. + * + * As a workaround, we don't do this. + */ + x86_pmu.pebs_buffer_size = PAGE_SIZE; x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; break; case 1: - printk(KERN_CONT "PEBS fmt1%c, ", pebs_type); + pr_cont("PEBS fmt1%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm); x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; @@ -1351,7 +1393,7 @@ void __init intel_ds_init(void) break; default: - printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); + pr_cont("no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; } } diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/events/intel/knc.c similarity index 98% rename from arch/x86/kernel/cpu/perf_event_knc.c rename to arch/x86/events/intel/knc.c index 5b0c232d1ee62..548d5f774b07e 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/events/intel/knc.c @@ -5,7 +5,7 @@ #include -#include "perf_event.h" +#include "../perf_event.h" static const u64 knc_perfmon_event_map[] = { @@ -263,7 +263,9 @@ static int knc_pmu_handle_irq(struct pt_regs *regs) goto again; done: - knc_pmu_enable_all(0); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + knc_pmu_enable_all(0); return handled; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/events/intel/lbr.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_intel_lbr.c rename to arch/x86/events/intel/lbr.c index 653f88d259878..69dd11887dd1e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -5,7 +5,7 @@ #include #include -#include "perf_event.h" +#include "../perf_event.h" enum { LBR_FORMAT_32 = 0x00, diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/events/intel/p4.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_p4.c rename to arch/x86/events/intel/p4.c index f2e56783af3d8..0a5ede187d9c1 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/events/intel/p4.c @@ -13,7 +13,7 @@ #include #include -#include "perf_event.h" +#include "../perf_event.h" #define P4_CNTR_LIMIT 3 /* diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/events/intel/p6.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_p6.c rename to arch/x86/events/intel/p6.c index 7c1a0c07b607f..1f5c47ab4c655 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/events/intel/p6.c @@ -1,7 +1,7 @@ #include #include -#include "perf_event.h" +#include "../perf_event.h" /* * Not sure about some of these diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/events/intel/pt.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_intel_pt.c rename to arch/x86/events/intel/pt.c index c0bbd1033b7cb..6af7cf71d6b2e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/events/intel/pt.c @@ -29,8 +29,8 @@ #include #include -#include "perf_event.h" -#include "intel_pt.h" +#include "../perf_event.h" +#include "pt.h" static DEFINE_PER_CPU(struct pt, pt_ctx); diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/events/intel/pt.h similarity index 100% rename from arch/x86/kernel/cpu/intel_pt.h rename to arch/x86/events/intel/pt.h diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/events/intel/rapl.c similarity index 74% rename from arch/x86/kernel/cpu/perf_event_intel_rapl.c rename to arch/x86/events/intel/rapl.c index 24a351ad628d2..b834a3f55a015 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -44,11 +44,14 @@ * the duration of the measurement. Tools may use a function such as * ldexp(raw_count, -32); */ + +#define pr_fmt(fmt) "RAPL PMU: " fmt + #include #include #include #include -#include "perf_event.h" +#include "../perf_event.h" /* * RAPL energy status counters @@ -107,7 +110,7 @@ static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ static struct kobj_attribute format_attr_##_var = \ __ATTR(_name, 0444, __rapl_##_var##_show, NULL) -#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ +#define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ static struct perf_pmu_events_attr event_attr_##v = { \ @@ -117,23 +120,33 @@ static struct perf_pmu_events_attr event_attr_##v = { \ }; struct rapl_pmu { - spinlock_t lock; - int n_active; /* number of active events */ - struct list_head active_list; - struct pmu *pmu; /* pointer to rapl_pmu_class */ - ktime_t timer_interval; /* in ktime_t unit */ - struct hrtimer hrtimer; + raw_spinlock_t lock; + int n_active; + int cpu; + struct list_head active_list; + struct pmu *pmu; + ktime_t timer_interval; + struct hrtimer hrtimer; }; -static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; /* 1/2^hw_unit Joule */ -static struct pmu rapl_pmu_class; +struct rapl_pmus { + struct pmu pmu; + unsigned int maxpkg; + struct rapl_pmu *pmus[]; +}; + + /* 1/2^hw_unit Joule */ +static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; +static struct rapl_pmus *rapl_pmus; static cpumask_t rapl_cpu_mask; -static int rapl_cntr_mask; +static unsigned int rapl_cntr_mask; +static u64 rapl_timer_ms; -static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); -static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); +static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) +{ + return rapl_pmus->pmus[topology_logical_package_id(cpu)]; +} -static struct x86_pmu_quirk *rapl_quirks; static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; @@ -141,19 +154,10 @@ static inline u64 rapl_read_counter(struct perf_event *event) return raw; } -#define rapl_add_quirk(func_) \ -do { \ - static struct x86_pmu_quirk __quirk __initdata = { \ - .func = func_, \ - }; \ - __quirk.next = rapl_quirks; \ - rapl_quirks = &__quirk; \ -} while (0) - static inline u64 rapl_scale(u64 v, int cfg) { if (cfg > NR_RAPL_DOMAINS) { - pr_warn("invalid domain %d, failed to scale data\n", cfg); + pr_warn("Invalid domain %d, failed to scale data\n", cfg); return v; } /* @@ -206,27 +210,21 @@ static void rapl_start_hrtimer(struct rapl_pmu *pmu) HRTIMER_MODE_REL_PINNED); } -static void rapl_stop_hrtimer(struct rapl_pmu *pmu) -{ - hrtimer_cancel(&pmu->hrtimer); -} - static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); struct perf_event *event; unsigned long flags; if (!pmu->n_active) return HRTIMER_NORESTART; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); - list_for_each_entry(event, &pmu->active_list, active_entry) { + list_for_each_entry(event, &pmu->active_list, active_entry) rapl_event_update(event); - } - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); hrtimer_forward_now(hrtimer, pmu->timer_interval); @@ -260,28 +258,28 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu, static void rapl_pmu_event_start(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = event->pmu_private; unsigned long flags; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); __rapl_pmu_event_start(pmu, event); - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); } static void rapl_pmu_event_stop(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); /* mark event as deactivated and stopped */ if (!(hwc->state & PERF_HES_STOPPED)) { WARN_ON_ONCE(pmu->n_active <= 0); pmu->n_active--; if (pmu->n_active == 0) - rapl_stop_hrtimer(pmu); + hrtimer_cancel(&pmu->hrtimer); list_del(&event->active_entry); @@ -299,23 +297,23 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode) hwc->state |= PERF_HES_UPTODATE; } - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); } static int rapl_pmu_event_add(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (mode & PERF_EF_START) __rapl_pmu_event_start(pmu, event); - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); return 0; } @@ -329,15 +327,19 @@ static int rapl_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config & RAPL_EVENT_MASK; int bit, msr, ret = 0; + struct rapl_pmu *pmu; /* only look at RAPL events */ - if (event->attr.type != rapl_pmu_class.type) + if (event->attr.type != rapl_pmus->pmu.type) return -ENOENT; /* check only supported bits are set */ if (event->attr.config & ~RAPL_EVENT_MASK) return -EINVAL; + if (event->cpu < 0) + return -EINVAL; + /* * check event is known (determines counter) */ @@ -376,6 +378,9 @@ static int rapl_pmu_event_init(struct perf_event *event) return -EINVAL; /* must be done before validate_group */ + pmu = cpu_to_rapl_pmu(event->cpu); + event->cpu = pmu->cpu; + event->pmu_private = pmu; event->hw.event_base = msr; event->hw.config = cfg; event->hw.idx = bit; @@ -506,139 +511,62 @@ const struct attribute_group *rapl_attr_groups[] = { NULL, }; -static struct pmu rapl_pmu_class = { - .attr_groups = rapl_attr_groups, - .task_ctx_nr = perf_invalid_context, /* system-wide only */ - .event_init = rapl_pmu_event_init, - .add = rapl_pmu_event_add, /* must have */ - .del = rapl_pmu_event_del, /* must have */ - .start = rapl_pmu_event_start, - .stop = rapl_pmu_event_stop, - .read = rapl_pmu_event_read, -}; - static void rapl_cpu_exit(int cpu) { - struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); - int i, phys_id = topology_physical_package_id(cpu); - int target = -1; + struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); + int target; - /* find a new cpu on same package */ - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (phys_id == topology_physical_package_id(i)) { - target = i; - break; - } - } - /* - * clear cpu from cpumask - * if was set in cpumask and still some cpu on package, - * then move to new cpu - */ - if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0) - cpumask_set_cpu(target, &rapl_cpu_mask); + /* Check if exiting cpu is used for collecting rapl events */ + if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask)) + return; - WARN_ON(cpumask_empty(&rapl_cpu_mask)); - /* - * migrate events and context to new cpu - */ - if (target >= 0) - perf_pmu_migrate_context(pmu->pmu, cpu, target); + pmu->cpu = -1; + /* Find a new cpu to collect rapl events */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - /* cancel overflow polling timer for CPU */ - rapl_stop_hrtimer(pmu); + /* Migrate rapl events to the new target */ + if (target < nr_cpu_ids) { + cpumask_set_cpu(target, &rapl_cpu_mask); + pmu->cpu = target; + perf_pmu_migrate_context(pmu->pmu, cpu, target); + } } static void rapl_cpu_init(int cpu) { - int i, phys_id = topology_physical_package_id(cpu); + struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); + int target; - /* check if phys_is is already covered */ - for_each_cpu(i, &rapl_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) - return; - } - /* was not found, so add it */ - cpumask_set_cpu(cpu, &rapl_cpu_mask); -} - -static __init void rapl_hsw_server_quirk(void) -{ /* - * DRAM domain on HSW server has fixed energy unit which can be - * different than the unit from power unit MSR. - * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 - * of 2. Datasheet, September 2014, Reference Number: 330784-001 " + * Check if there is an online cpu in the package which collects rapl + * events already. */ - rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16; + target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu)); + if (target < nr_cpu_ids) + return; + + cpumask_set_cpu(cpu, &rapl_cpu_mask); + pmu->cpu = cpu; } static int rapl_cpu_prepare(int cpu) { - struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); - int phys_id = topology_physical_package_id(cpu); - u64 ms; + struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); if (pmu) return 0; - if (phys_id < 0) - return -1; - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) - return -1; - spin_lock_init(&pmu->lock); + return -ENOMEM; + raw_spin_lock_init(&pmu->lock); INIT_LIST_HEAD(&pmu->active_list); - - pmu->pmu = &rapl_pmu_class; - - /* - * use reference of 200W for scaling the timeout - * to avoid missing counter overflows. - * 200W = 200 Joules/sec - * divide interval by 2 to avoid lockstep (2 * 100) - * if hw unit is 32, then we use 2 ms 1/200/2 - */ - if (rapl_hw_unit[0] < 32) - ms = (1000 / (2 * 100)) * (1ULL << (32 - rapl_hw_unit[0] - 1)); - else - ms = 2; - - pmu->timer_interval = ms_to_ktime(ms); - + pmu->pmu = &rapl_pmus->pmu; + pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + pmu->cpu = -1; rapl_hrtimer_init(pmu); - - /* set RAPL pmu for this cpu for now */ - per_cpu(rapl_pmu, cpu) = pmu; - per_cpu(rapl_pmu_to_free, cpu) = NULL; - - return 0; -} - -static void rapl_cpu_kfree(int cpu) -{ - struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu); - - kfree(pmu); - - per_cpu(rapl_pmu_to_free, cpu) = NULL; -} - -static int rapl_cpu_dying(int cpu) -{ - struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); - - if (!pmu) - return 0; - - per_cpu(rapl_pmu, cpu) = NULL; - - per_cpu(rapl_pmu_to_free, cpu) = pmu; - + rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; return 0; } @@ -651,28 +579,20 @@ static int rapl_cpu_notifier(struct notifier_block *self, case CPU_UP_PREPARE: rapl_cpu_prepare(cpu); break; - case CPU_STARTING: - rapl_cpu_init(cpu); - break; - case CPU_UP_CANCELED: - case CPU_DYING: - rapl_cpu_dying(cpu); - break; + + case CPU_DOWN_FAILED: case CPU_ONLINE: - case CPU_DEAD: - rapl_cpu_kfree(cpu); + rapl_cpu_init(cpu); break; + case CPU_DOWN_PREPARE: rapl_cpu_exit(cpu); break; - default: - break; } - return NOTIFY_OK; } -static int rapl_check_hw_unit(void) +static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; int i; @@ -683,28 +603,107 @@ static int rapl_check_hw_unit(void) for (i = 0; i < NR_RAPL_DOMAINS; i++) rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + /* + * DRAM domain on HSW server and KNL has fixed energy unit which can be + * different than the unit from power unit MSR. See + * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 + * of 2. Datasheet, September 2014, Reference Number: 330784-001 " + */ + if (apply_quirk) + rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16; + + /* + * Calculate the timer rate: + * Use reference of 200W for scaling the timeout to avoid counter + * overflows. 200W = 200 Joules/sec + * Divide interval by 2 to avoid lockstep (2 * 100) + * if hw unit is 32, then we use 2 ms 1/200/2 + */ + rapl_timer_ms = 2; + if (rapl_hw_unit[0] < 32) { + rapl_timer_ms = (1000 / (2 * 100)); + rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1)); + } + return 0; +} + +static void __init rapl_advertise(void) +{ + int i; + + pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n", + hweight32(rapl_cntr_mask), rapl_timer_ms); + + for (i = 0; i < NR_RAPL_DOMAINS; i++) { + if (rapl_cntr_mask & (1 << i)) { + pr_info("hw unit of domain %s 2^-%d Joules\n", + rapl_domain_names[i], rapl_hw_unit[i]); + } + } +} + +static int __init rapl_prepare_cpus(void) +{ + unsigned int cpu, pkg; + int ret; + + for_each_online_cpu(cpu) { + pkg = topology_logical_package_id(cpu); + if (rapl_pmus->pmus[pkg]) + continue; + + ret = rapl_cpu_prepare(cpu); + if (ret) + return ret; + rapl_cpu_init(cpu); + } + return 0; +} + +static void __init cleanup_rapl_pmus(void) +{ + int i; + + for (i = 0; i < rapl_pmus->maxpkg; i++) + kfree(rapl_pmus->pmus + i); + kfree(rapl_pmus); +} + +static int __init init_rapl_pmus(void) +{ + int maxpkg = topology_max_packages(); + size_t size; + + size = sizeof(*rapl_pmus) + maxpkg * sizeof(struct rapl_pmu *); + rapl_pmus = kzalloc(size, GFP_KERNEL); + if (!rapl_pmus) + return -ENOMEM; + + rapl_pmus->maxpkg = maxpkg; + rapl_pmus->pmu.attr_groups = rapl_attr_groups; + rapl_pmus->pmu.task_ctx_nr = perf_invalid_context; + rapl_pmus->pmu.event_init = rapl_pmu_event_init; + rapl_pmus->pmu.add = rapl_pmu_event_add; + rapl_pmus->pmu.del = rapl_pmu_event_del; + rapl_pmus->pmu.start = rapl_pmu_event_start; + rapl_pmus->pmu.stop = rapl_pmu_event_stop; + rapl_pmus->pmu.read = rapl_pmu_event_read; return 0; } -static const struct x86_cpu_id rapl_cpu_match[] = { +static const struct x86_cpu_id rapl_cpu_match[] __initconst = { [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, [1] = {}, }; static int __init rapl_pmu_init(void) { - struct rapl_pmu *pmu; - int cpu, ret; - struct x86_pmu_quirk *quirk; - int i; + bool apply_quirk = false; + int ret; - /* - * check for Intel processor family 6 - */ if (!x86_match_cpu(rapl_cpu_match)) - return 0; + return -ENODEV; - /* check supported CPU */ switch (boot_cpu_data.x86_model) { case 42: /* Sandy Bridge */ case 58: /* Ivy Bridge */ @@ -712,7 +711,7 @@ static int __init rapl_pmu_init(void) rapl_pmu_events_group.attrs = rapl_events_cln_attr; break; case 63: /* Haswell-Server */ - rapl_add_quirk(rapl_hsw_server_quirk); + apply_quirk = true; rapl_cntr_mask = RAPL_IDX_SRV; rapl_pmu_events_group.attrs = rapl_events_srv_attr; break; @@ -728,56 +727,41 @@ static int __init rapl_pmu_init(void) rapl_pmu_events_group.attrs = rapl_events_srv_attr; break; case 87: /* Knights Landing */ - rapl_add_quirk(rapl_hsw_server_quirk); + apply_quirk = true; rapl_cntr_mask = RAPL_IDX_KNL; rapl_pmu_events_group.attrs = rapl_events_knl_attr; - + break; default: - /* unsupported */ - return 0; + return -ENODEV; } - ret = rapl_check_hw_unit(); + + ret = rapl_check_hw_unit(apply_quirk); if (ret) return ret; - /* run cpu model quirks */ - for (quirk = rapl_quirks; quirk; quirk = quirk->next) - quirk->func(); - cpu_notifier_register_begin(); + ret = init_rapl_pmus(); + if (ret) + return ret; - for_each_online_cpu(cpu) { - ret = rapl_cpu_prepare(cpu); - if (ret) - goto out; - rapl_cpu_init(cpu); - } + cpu_notifier_register_begin(); - __perf_cpu_notifier(rapl_cpu_notifier); + ret = rapl_prepare_cpus(); + if (ret) + goto out; - ret = perf_pmu_register(&rapl_pmu_class, "power", -1); - if (WARN_ON(ret)) { - pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret); - cpu_notifier_register_done(); - return -1; - } + ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); + if (ret) + goto out; - pmu = __this_cpu_read(rapl_pmu); + __perf_cpu_notifier(rapl_cpu_notifier); + cpu_notifier_register_done(); + rapl_advertise(); + return 0; - pr_info("RAPL PMU detected," - " API unit is 2^-32 Joules," - " %d fixed counters" - " %llu ms ovfl timer\n", - hweight32(rapl_cntr_mask), - ktime_to_ms(pmu->timer_interval)); - for (i = 0; i < NR_RAPL_DOMAINS; i++) { - if (rapl_cntr_mask & (1 << i)) { - pr_info("hw unit of domain %s 2^-%d Joules\n", - rapl_domain_names[i], rapl_hw_unit[i]); - } - } out: + pr_warn("Initialization failed (%d), disabled\n", ret); + cleanup_rapl_pmus(); cpu_notifier_register_done(); - - return 0; + return ret; } device_initcall(rapl_pmu_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/events/intel/uncore.c similarity index 75% rename from arch/x86/kernel/cpu/perf_event_intel_uncore.c rename to arch/x86/events/intel/uncore.c index 3bf41d4137750..7012d18bb2930 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1,4 +1,4 @@ -#include "perf_event_intel_uncore.h" +#include "uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; struct intel_uncore_type **uncore_msr_uncores = empty_uncore; @@ -9,9 +9,9 @@ struct pci_driver *uncore_pci_driver; /* pci bus to socket mapping */ DEFINE_RAW_SPINLOCK(pci2phy_map_lock); struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head); -struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +struct pci_extra_dev *uncore_extra_pci_dev; +static int max_packages; -static DEFINE_RAW_SPINLOCK(uncore_box_lock); /* mask of cpus that collect uncore events */ static cpumask_t uncore_cpu_mask; @@ -21,7 +21,7 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); -int uncore_pcibus_to_physid(struct pci_bus *bus) +static int uncore_pcibus_to_physid(struct pci_bus *bus) { struct pci2phy_map *map; int phys_id = -1; @@ -38,6 +38,16 @@ int uncore_pcibus_to_physid(struct pci_bus *bus) return phys_id; } +static void uncore_free_pcibus_map(void) +{ + struct pci2phy_map *map, *tmp; + + list_for_each_entry_safe(map, tmp, &pci2phy_map_head, list) { + list_del(&map->list); + kfree(map); + } +} + struct pci2phy_map *__find_pci2phy_map(int segment) { struct pci2phy_map *map, *alloc = NULL; @@ -82,43 +92,9 @@ ssize_t uncore_event_show(struct kobject *kobj, return sprintf(buf, "%s", event->config); } -struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) -{ - return container_of(event->pmu, struct intel_uncore_pmu, pmu); -} - struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - struct intel_uncore_box *box; - - box = *per_cpu_ptr(pmu->box, cpu); - if (box) - return box; - - raw_spin_lock(&uncore_box_lock); - /* Recheck in lock to handle races. */ - if (*per_cpu_ptr(pmu->box, cpu)) - goto out; - list_for_each_entry(box, &pmu->box_list, list) { - if (box->phys_id == topology_physical_package_id(cpu)) { - atomic_inc(&box->refcnt); - *per_cpu_ptr(pmu->box, cpu) = box; - break; - } - } -out: - raw_spin_unlock(&uncore_box_lock); - - return *per_cpu_ptr(pmu->box, cpu); -} - -struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) -{ - /* - * perf core schedules event on the basis of cpu, uncore events are - * collected by one of the cpus inside a physical package. - */ - return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); + return pmu->boxes[topology_logical_package_id(cpu)]; } u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) @@ -207,7 +183,8 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) return config; } -static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx) +static void uncore_assign_hw_event(struct intel_uncore_box *box, + struct perf_event *event, int idx) { struct hw_perf_event *hwc = &event->hw; @@ -302,24 +279,25 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node) +static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, + int node) { + int i, size, numshared = type->num_shared_regs ; struct intel_uncore_box *box; - int i, size; - size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); + size = sizeof(*box) + numshared * sizeof(struct intel_uncore_extra_reg); box = kzalloc_node(size, GFP_KERNEL, node); if (!box) return NULL; - for (i = 0; i < type->num_shared_regs; i++) + for (i = 0; i < numshared; i++) raw_spin_lock_init(&box->shared_regs[i].lock); uncore_pmu_init_hrtimer(box); - atomic_set(&box->refcnt, 1); box->cpu = -1; - box->phys_id = -1; + box->pci_phys_id = -1; + box->pkgid = -1; /* set default hrtimer timeout */ box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL; @@ -341,7 +319,8 @@ static bool is_uncore_event(struct perf_event *event) } static int -uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) +uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, + bool dogrp) { struct perf_event *event; int n, max_count; @@ -402,7 +381,8 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve return &type->unconstrainted; } -static void uncore_put_event_constraint(struct intel_uncore_box *box, struct perf_event *event) +static void uncore_put_event_constraint(struct intel_uncore_box *box, + struct perf_event *event) { if (box->pmu->type->ops->put_constraint) box->pmu->type->ops->put_constraint(box, event); @@ -582,7 +562,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags) if (event == box->event_list[i]) { uncore_put_event_constraint(box, event); - while (++i < box->n_events) + for (++i; i < box->n_events; i++) box->event_list[i - 1] = box->event_list[i]; --box->n_events; @@ -676,6 +656,7 @@ static int uncore_pmu_event_init(struct perf_event *event) if (!box || box->cpu < 0) return -EINVAL; event->cpu = box->cpu; + event->pmu_private = box; event->hw.idx = -1; event->hw.last_tag = ~0ULL; @@ -760,64 +741,110 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) } ret = perf_pmu_register(&pmu->pmu, pmu->name, -1); + if (!ret) + pmu->registered = true; return ret; } +static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) +{ + if (!pmu->registered) + return; + perf_pmu_unregister(&pmu->pmu); + pmu->registered = false; +} + +static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) +{ + struct intel_uncore_pmu *pmu = type->pmus; + struct intel_uncore_box *box; + int i, pkg; + + if (pmu) { + pkg = topology_physical_package_id(cpu); + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box) + uncore_box_exit(box); + } + } +} + +static void __init uncore_exit_boxes(void *dummy) +{ + struct intel_uncore_type **types; + + for (types = uncore_msr_uncores; *types; types++) + __uncore_exit_boxes(*types++, smp_processor_id()); +} + +static void uncore_free_boxes(struct intel_uncore_pmu *pmu) +{ + int pkg; + + for (pkg = 0; pkg < max_packages; pkg++) + kfree(pmu->boxes[pkg]); + kfree(pmu->boxes); +} + static void __init uncore_type_exit(struct intel_uncore_type *type) { + struct intel_uncore_pmu *pmu = type->pmus; int i; - for (i = 0; i < type->num_boxes; i++) - free_percpu(type->pmus[i].box); - kfree(type->pmus); - type->pmus = NULL; + if (pmu) { + for (i = 0; i < type->num_boxes; i++, pmu++) { + uncore_pmu_unregister(pmu); + uncore_free_boxes(pmu); + } + kfree(type->pmus); + type->pmus = NULL; + } kfree(type->events_group); type->events_group = NULL; } static void __init uncore_types_exit(struct intel_uncore_type **types) { - int i; - for (i = 0; types[i]; i++) - uncore_type_exit(types[i]); + for (; *types; types++) + uncore_type_exit(*types); } -static int __init uncore_type_init(struct intel_uncore_type *type) +static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) { struct intel_uncore_pmu *pmus; struct attribute_group *attr_group; struct attribute **attrs; + size_t size; int i, j; pmus = kzalloc(sizeof(*pmus) * type->num_boxes, GFP_KERNEL); if (!pmus) return -ENOMEM; - type->pmus = pmus; + size = max_packages * sizeof(struct intel_uncore_box *); + for (i = 0; i < type->num_boxes; i++) { + pmus[i].func_id = setid ? i : -1; + pmus[i].pmu_idx = i; + pmus[i].type = type; + pmus[i].boxes = kzalloc(size, GFP_KERNEL); + if (!pmus[i].boxes) + return -ENOMEM; + } + + type->pmus = pmus; type->unconstrainted = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, 0, type->num_counters, 0, 0); - for (i = 0; i < type->num_boxes; i++) { - pmus[i].func_id = -1; - pmus[i].pmu_idx = i; - pmus[i].type = type; - INIT_LIST_HEAD(&pmus[i].box_list); - pmus[i].box = alloc_percpu(struct intel_uncore_box *); - if (!pmus[i].box) - goto fail; - } - if (type->event_descs) { - i = 0; - while (type->event_descs[i].attr.attr.name) - i++; + for (i = 0; type->event_descs[i].attr.attr.name; i++); attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + sizeof(*attr_group), GFP_KERNEL); if (!attr_group) - goto fail; + return -ENOMEM; attrs = (struct attribute **)(attr_group + 1); attr_group->name = "events"; @@ -831,25 +858,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type) type->pmu_group = &uncore_pmu_attr_group; return 0; -fail: - uncore_type_exit(type); - return -ENOMEM; } -static int __init uncore_types_init(struct intel_uncore_type **types) +static int __init +uncore_types_init(struct intel_uncore_type **types, bool setid) { - int i, ret; + int ret; - for (i = 0; types[i]; i++) { - ret = uncore_type_init(types[i]); + for (; *types; types++) { + ret = uncore_type_init(*types, setid); if (ret) - goto fail; + return ret; } return 0; -fail: - while (--i >= 0) - uncore_type_exit(types[i]); - return ret; } /* @@ -857,28 +878,28 @@ static int __init uncore_types_init(struct intel_uncore_type **types) */ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { + struct intel_uncore_type *type; struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - struct intel_uncore_type *type; - int phys_id; - bool first_box = false; + int phys_id, pkg, ret; phys_id = uncore_pcibus_to_physid(pdev->bus); if (phys_id < 0) return -ENODEV; + pkg = topology_phys_to_logical_pkg(phys_id); + if (WARN_ON_ONCE(pkg < 0)) + return -EINVAL; + if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { int idx = UNCORE_PCI_DEV_IDX(id->driver_data); - uncore_extra_pci_dev[phys_id][idx] = pdev; + + uncore_extra_pci_dev[pkg].dev[idx] = pdev; pci_set_drvdata(pdev, NULL); return 0; } type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; - box = uncore_alloc_box(type, NUMA_NO_NODE); - if (!box) - return -ENOMEM; - /* * for performance monitoring unit with multiple boxes, * each box has a different function id. @@ -890,44 +911,60 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id * some device types. Hence PCI device idx would be 0 for all devices. * So increment pmu pointer to point to an unused array element. */ - if (boot_cpu_data.x86_model == 87) + if (boot_cpu_data.x86_model == 87) { while (pmu->func_id >= 0) pmu++; + } + + if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL)) + return -EINVAL; + + box = uncore_alloc_box(type, NUMA_NO_NODE); + if (!box) + return -ENOMEM; + if (pmu->func_id < 0) pmu->func_id = pdev->devfn; else WARN_ON_ONCE(pmu->func_id != pdev->devfn); - box->phys_id = phys_id; + atomic_inc(&box->refcnt); + box->pci_phys_id = phys_id; + box->pkgid = pkg; box->pci_dev = pdev; box->pmu = pmu; uncore_box_init(box); pci_set_drvdata(pdev, box); - raw_spin_lock(&uncore_box_lock); - if (list_empty(&pmu->box_list)) - first_box = true; - list_add_tail(&box->list, &pmu->box_list); - raw_spin_unlock(&uncore_box_lock); + pmu->boxes[pkg] = box; + if (atomic_inc_return(&pmu->activeboxes) > 1) + return 0; - if (first_box) - uncore_pmu_register(pmu); - return 0; + /* First active box registers the pmu */ + ret = uncore_pmu_register(pmu); + if (ret) { + pci_set_drvdata(pdev, NULL); + pmu->boxes[pkg] = NULL; + uncore_box_exit(box); + kfree(box); + } + return ret; } static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); struct intel_uncore_pmu *pmu; - int i, cpu, phys_id; - bool last_box = false; + int i, phys_id, pkg; phys_id = uncore_pcibus_to_physid(pdev->bus); + pkg = topology_phys_to_logical_pkg(phys_id); + box = pci_get_drvdata(pdev); if (!box) { for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { - if (uncore_extra_pci_dev[phys_id][i] == pdev) { - uncore_extra_pci_dev[phys_id][i] = NULL; + if (uncore_extra_pci_dev[pkg].dev[i] == pdev) { + uncore_extra_pci_dev[pkg].dev[i] = NULL; break; } } @@ -936,33 +973,20 @@ static void uncore_pci_remove(struct pci_dev *pdev) } pmu = box->pmu; - if (WARN_ON_ONCE(phys_id != box->phys_id)) + if (WARN_ON_ONCE(phys_id != box->pci_phys_id)) return; pci_set_drvdata(pdev, NULL); - - raw_spin_lock(&uncore_box_lock); - list_del(&box->list); - if (list_empty(&pmu->box_list)) - last_box = true; - raw_spin_unlock(&uncore_box_lock); - - for_each_possible_cpu(cpu) { - if (*per_cpu_ptr(pmu->box, cpu) == box) { - *per_cpu_ptr(pmu->box, cpu) = NULL; - atomic_dec(&box->refcnt); - } - } - - WARN_ON_ONCE(atomic_read(&box->refcnt) != 1); + pmu->boxes[pkg] = NULL; + if (atomic_dec_return(&pmu->activeboxes) == 0) + uncore_pmu_unregister(pmu); + uncore_box_exit(box); kfree(box); - - if (last_box) - perf_pmu_unregister(&pmu->pmu); } static int __init uncore_pci_init(void) { + size_t size; int ret; switch (boot_cpu_data.x86_model) { @@ -999,25 +1023,40 @@ static int __init uncore_pci_init(void) ret = skl_uncore_pci_init(); break; default: - return 0; + return -ENODEV; } if (ret) return ret; - ret = uncore_types_init(uncore_pci_uncores); + size = max_packages * sizeof(struct pci_extra_dev); + uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL); + if (!uncore_extra_pci_dev) { + ret = -ENOMEM; + goto err; + } + + ret = uncore_types_init(uncore_pci_uncores, false); if (ret) - return ret; + goto errtype; uncore_pci_driver->probe = uncore_pci_probe; uncore_pci_driver->remove = uncore_pci_remove; ret = pci_register_driver(uncore_pci_driver); - if (ret == 0) - pcidrv_registered = true; - else - uncore_types_exit(uncore_pci_uncores); + if (ret) + goto errtype; + + pcidrv_registered = true; + return 0; +errtype: + uncore_types_exit(uncore_pci_uncores); + kfree(uncore_extra_pci_dev); + uncore_extra_pci_dev = NULL; + uncore_free_pcibus_map(); +err: + uncore_pci_uncores = empty_uncore; return ret; } @@ -1027,173 +1066,139 @@ static void __init uncore_pci_exit(void) pcidrv_registered = false; pci_unregister_driver(uncore_pci_driver); uncore_types_exit(uncore_pci_uncores); - } -} - -/* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */ -static LIST_HEAD(boxes_to_free); - -static void uncore_kfree_boxes(void) -{ - struct intel_uncore_box *box; - - while (!list_empty(&boxes_to_free)) { - box = list_entry(boxes_to_free.next, - struct intel_uncore_box, list); - list_del(&box->list); - kfree(box); + kfree(uncore_extra_pci_dev); + uncore_free_pcibus_map(); } } static void uncore_cpu_dying(int cpu) { - struct intel_uncore_type *type; + struct intel_uncore_type *type, **types = uncore_msr_uncores; struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, j; - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - box = *per_cpu_ptr(pmu->box, cpu); - *per_cpu_ptr(pmu->box, cpu) = NULL; - if (box && atomic_dec_and_test(&box->refcnt)) - list_add(&box->list, &boxes_to_free); + int i, pkg; + + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); } } } -static int uncore_cpu_starting(int cpu) +static void uncore_cpu_starting(int cpu, bool init) { - struct intel_uncore_type *type; + struct intel_uncore_type *type, **types = uncore_msr_uncores; struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box, *exist; - int i, j, k, phys_id; - - phys_id = topology_physical_package_id(cpu); - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - box = *per_cpu_ptr(pmu->box, cpu); - /* called by uncore_cpu_init? */ - if (box && box->phys_id >= 0) { - uncore_box_init(box); - continue; - } + struct intel_uncore_box *box; + int i, pkg, ncpus = 1; - for_each_online_cpu(k) { - exist = *per_cpu_ptr(pmu->box, k); - if (exist && exist->phys_id == phys_id) { - atomic_inc(&exist->refcnt); - *per_cpu_ptr(pmu->box, cpu) = exist; - if (box) { - list_add(&box->list, - &boxes_to_free); - box = NULL; - } - break; - } - } + if (init) { + /* + * On init we get the number of online cpus in the package + * and set refcount for all of them. + */ + ncpus = cpumask_weight(topology_core_cpumask(cpu)); + } - if (box) { - box->phys_id = phys_id; + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box) + continue; + /* The first cpu on a package activates the box */ + if (atomic_add_return(ncpus, &box->refcnt) == ncpus) uncore_box_init(box); - } } } - return 0; } -static int uncore_cpu_prepare(int cpu, int phys_id) +static int uncore_cpu_prepare(int cpu) { - struct intel_uncore_type *type; + struct intel_uncore_type *type, **types = uncore_msr_uncores; struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, j; - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - if (pmu->func_id < 0) - pmu->func_id = j; - + int i, pkg; + + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[pkg]) + continue; + /* First cpu of a package allocates the box */ box = uncore_alloc_box(type, cpu_to_node(cpu)); if (!box) return -ENOMEM; - box->pmu = pmu; - box->phys_id = phys_id; - *per_cpu_ptr(pmu->box, cpu) = box; + box->pkgid = pkg; + pmu->boxes[pkg] = box; } } return 0; } -static void -uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu) +static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu, + int new_cpu) { - struct intel_uncore_type *type; - struct intel_uncore_pmu *pmu; + struct intel_uncore_pmu *pmu = type->pmus; struct intel_uncore_box *box; - int i, j; + int i, pkg; - for (i = 0; uncores[i]; i++) { - type = uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - if (old_cpu < 0) - box = uncore_pmu_to_box(pmu, new_cpu); - else - box = uncore_pmu_to_box(pmu, old_cpu); - if (!box) - continue; - - if (old_cpu < 0) { - WARN_ON_ONCE(box->cpu != -1); - box->cpu = new_cpu; - continue; - } + pkg = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu); + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box) + continue; - WARN_ON_ONCE(box->cpu != old_cpu); - if (new_cpu >= 0) { - uncore_pmu_cancel_hrtimer(box); - perf_pmu_migrate_context(&pmu->pmu, - old_cpu, new_cpu); - box->cpu = new_cpu; - } else { - box->cpu = -1; - } + if (old_cpu < 0) { + WARN_ON_ONCE(box->cpu != -1); + box->cpu = new_cpu; + continue; } + + WARN_ON_ONCE(box->cpu != old_cpu); + box->cpu = -1; + if (new_cpu < 0) + continue; + + uncore_pmu_cancel_hrtimer(box); + perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu); + box->cpu = new_cpu; } } +static void uncore_change_context(struct intel_uncore_type **uncores, + int old_cpu, int new_cpu) +{ + for (; *uncores; uncores++) + uncore_change_type_ctx(*uncores, old_cpu, new_cpu); +} + static void uncore_event_exit_cpu(int cpu) { - int i, phys_id, target; + int target; - /* if exiting cpu is used for collecting uncore events */ + /* Check if exiting cpu is used for collecting uncore events */ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) return; - /* find a new cpu to collect uncore events */ - phys_id = topology_physical_package_id(cpu); - target = -1; - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (phys_id == topology_physical_package_id(i)) { - target = i; - break; - } - } + /* Find a new cpu to collect uncore events */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - /* migrate uncore events to the new cpu */ - if (target >= 0) + /* Migrate uncore events to the new target */ + if (target < nr_cpu_ids) cpumask_set_cpu(target, &uncore_cpu_mask); + else + target = -1; uncore_change_context(uncore_msr_uncores, cpu, target); uncore_change_context(uncore_pci_uncores, cpu, target); @@ -1201,13 +1206,15 @@ static void uncore_event_exit_cpu(int cpu) static void uncore_event_init_cpu(int cpu) { - int i, phys_id; + int target; - phys_id = topology_physical_package_id(cpu); - for_each_cpu(i, &uncore_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) - return; - } + /* + * Check if there is an online cpu in the package + * which collects uncore events already. + */ + target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu)); + if (target < nr_cpu_ids) + return; cpumask_set_cpu(cpu, &uncore_cpu_mask); @@ -1220,39 +1227,25 @@ static int uncore_cpu_notifier(struct notifier_block *self, { unsigned int cpu = (long)hcpu; - /* allocate/free data structure for uncore box */ switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - uncore_cpu_prepare(cpu, -1); - break; + return notifier_from_errno(uncore_cpu_prepare(cpu)); + case CPU_STARTING: - uncore_cpu_starting(cpu); + uncore_cpu_starting(cpu, false); + case CPU_DOWN_FAILED: + uncore_event_init_cpu(cpu); break; + case CPU_UP_CANCELED: case CPU_DYING: uncore_cpu_dying(cpu); break; - case CPU_ONLINE: - case CPU_DEAD: - uncore_kfree_boxes(); - break; - default: - break; - } - /* select the cpu that collects uncore events */ - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_FAILED: - case CPU_STARTING: - uncore_event_init_cpu(cpu); - break; case CPU_DOWN_PREPARE: uncore_event_exit_cpu(cpu); break; - default: - break; } - return NOTIFY_OK; } @@ -1265,9 +1258,29 @@ static struct notifier_block uncore_cpu_nb = { .priority = CPU_PRI_PERF + 1, }; -static void __init uncore_cpu_setup(void *dummy) +static int __init type_pmu_register(struct intel_uncore_type *type) { - uncore_cpu_starting(smp_processor_id()); + int i, ret; + + for (i = 0; i < type->num_boxes; i++) { + ret = uncore_pmu_register(&type->pmus[i]); + if (ret) + return ret; + } + return 0; +} + +static int __init uncore_msr_pmus_register(void) +{ + struct intel_uncore_type **types = uncore_msr_uncores; + int ret; + + for (; *types; types++) { + ret = type_pmu_register(*types); + if (ret) + return ret; + } + return 0; } static int __init uncore_cpu_init(void) @@ -1311,71 +1324,61 @@ static int __init uncore_cpu_init(void) knl_uncore_cpu_init(); break; default: - return 0; + return -ENODEV; } - ret = uncore_types_init(uncore_msr_uncores); + ret = uncore_types_init(uncore_msr_uncores, true); if (ret) - return ret; + goto err; + ret = uncore_msr_pmus_register(); + if (ret) + goto err; return 0; +err: + uncore_types_exit(uncore_msr_uncores); + uncore_msr_uncores = empty_uncore; + return ret; } -static int __init uncore_pmus_register(void) +static void __init uncore_cpu_setup(void *dummy) { - struct intel_uncore_pmu *pmu; - struct intel_uncore_type *type; - int i, j; - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - uncore_pmu_register(pmu); - } - } - - return 0; + uncore_cpu_starting(smp_processor_id(), true); } -static void __init uncore_cpumask_init(void) -{ - int cpu; - - /* - * ony invoke once from msr or pci init code - */ - if (!cpumask_empty(&uncore_cpu_mask)) - return; +/* Lazy to avoid allocation of a few bytes for the normal case */ +static __initdata DECLARE_BITMAP(packages, MAX_LOCAL_APIC); - cpu_notifier_register_begin(); +static int __init uncore_cpumask_init(bool msr) +{ + unsigned int cpu; for_each_online_cpu(cpu) { - int i, phys_id = topology_physical_package_id(cpu); + unsigned int pkg = topology_logical_package_id(cpu); + int ret; - for_each_cpu(i, &uncore_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) { - phys_id = -1; - break; - } - } - if (phys_id < 0) + if (test_and_set_bit(pkg, packages)) continue; - - uncore_cpu_prepare(cpu, phys_id); + /* + * The first online cpu of each package allocates and takes + * the refcounts for all other online cpus in that package. + * If msrs are not enabled no allocation is required. + */ + if (msr) { + ret = uncore_cpu_prepare(cpu); + if (ret) + return ret; + } uncore_event_init_cpu(cpu); + smp_call_function_single(cpu, uncore_cpu_setup, NULL, 1); } - on_each_cpu(uncore_cpu_setup, NULL, 1); - __register_cpu_notifier(&uncore_cpu_nb); - - cpu_notifier_register_done(); + return 0; } - static int __init intel_uncore_init(void) { - int ret; + int pret, cret, ret; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return -ENODEV; @@ -1383,19 +1386,27 @@ static int __init intel_uncore_init(void) if (cpu_has_hypervisor) return -ENODEV; - ret = uncore_pci_init(); - if (ret) - goto fail; - ret = uncore_cpu_init(); - if (ret) { - uncore_pci_exit(); - goto fail; - } - uncore_cpumask_init(); + max_packages = topology_max_packages(); + + pret = uncore_pci_init(); + cret = uncore_cpu_init(); - uncore_pmus_register(); + if (cret && pret) + return -ENODEV; + + cpu_notifier_register_begin(); + ret = uncore_cpumask_init(!cret); + if (ret) + goto err; + cpu_notifier_register_done(); return 0; -fail: + +err: + /* Undo box->init_box() */ + on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1); + uncore_types_exit(uncore_msr_uncores); + uncore_pci_exit(); + cpu_notifier_register_done(); return ret; } device_initcall(intel_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/events/intel/uncore.h similarity index 90% rename from arch/x86/kernel/cpu/perf_event_intel_uncore.h rename to arch/x86/events/intel/uncore.h index a7086b8621566..79766b9a35809 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -1,8 +1,10 @@ #include #include #include +#include + #include -#include "perf_event.h" +#include "../perf_event.h" #define UNCORE_PMU_NAME_LEN 32 #define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) @@ -19,11 +21,12 @@ #define UNCORE_EXTRA_PCI_DEV 0xff #define UNCORE_EXTRA_PCI_DEV_MAX 3 -/* support up to 8 sockets */ -#define UNCORE_SOCKET_MAX 8 - #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) +struct pci_extra_dev { + struct pci_dev *dev[UNCORE_EXTRA_PCI_DEV_MAX]; +}; + struct intel_uncore_ops; struct intel_uncore_pmu; struct intel_uncore_box; @@ -61,6 +64,7 @@ struct intel_uncore_type { struct intel_uncore_ops { void (*init_box)(struct intel_uncore_box *); + void (*exit_box)(struct intel_uncore_box *); void (*disable_box)(struct intel_uncore_box *); void (*enable_box)(struct intel_uncore_box *); void (*disable_event)(struct intel_uncore_box *, struct perf_event *); @@ -73,13 +77,14 @@ struct intel_uncore_ops { }; struct intel_uncore_pmu { - struct pmu pmu; - char name[UNCORE_PMU_NAME_LEN]; - int pmu_idx; - int func_id; - struct intel_uncore_type *type; - struct intel_uncore_box ** __percpu box; - struct list_head box_list; + struct pmu pmu; + char name[UNCORE_PMU_NAME_LEN]; + int pmu_idx; + int func_id; + bool registered; + atomic_t activeboxes; + struct intel_uncore_type *type; + struct intel_uncore_box **boxes; }; struct intel_uncore_extra_reg { @@ -89,7 +94,8 @@ struct intel_uncore_extra_reg { }; struct intel_uncore_box { - int phys_id; + int pci_phys_id; + int pkgid; int n_active; /* number of active events */ int n_events; int cpu; /* cpu to collect events */ @@ -123,7 +129,6 @@ struct pci2phy_map { int pbus_to_physid[256]; }; -int uncore_pcibus_to_physid(struct pci_bus *bus); struct pci2phy_map *__find_pci2phy_map(int segment); ssize_t uncore_event_show(struct kobject *kobj, @@ -305,14 +310,30 @@ static inline void uncore_box_init(struct intel_uncore_box *box) } } +static inline void uncore_box_exit(struct intel_uncore_box *box) +{ + if (test_and_clear_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->exit_box) + box->pmu->type->ops->exit_box(box); + } +} + static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { - return (box->phys_id < 0); + return (box->pkgid < 0); +} + +static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct intel_uncore_pmu, pmu); +} + +static inline struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +{ + return event->pmu_private; } -struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event); struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu); -struct intel_uncore_box *uncore_event_to_box(struct perf_event *event); u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event); void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); @@ -328,7 +349,7 @@ extern struct intel_uncore_type **uncore_pci_uncores; extern struct pci_driver *uncore_pci_driver; extern raw_spinlock_t pci2phy_map_lock; extern struct list_head pci2phy_map_head; -extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +extern struct pci_extra_dev *uncore_extra_pci_dev; extern struct event_constraint uncore_constraint_empty; /* perf_event_intel_uncore_snb.c */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c rename to arch/x86/events/intel/uncore_nhmex.c index 2749965afed0b..cda5693320050 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -1,5 +1,5 @@ /* Nehalem-EX/Westmere-EX uncore support */ -#include "perf_event_intel_uncore.h" +#include "uncore.h" /* NHM-EX event control */ #define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff @@ -201,6 +201,11 @@ static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); } +static void nhmex_uncore_msr_exit_box(struct intel_uncore_box *box) +{ + wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, 0); +} + static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) { unsigned msr = uncore_msr_box_ctl(box); @@ -250,6 +255,7 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p #define NHMEX_UNCORE_OPS_COMMON_INIT() \ .init_box = nhmex_uncore_msr_init_box, \ + .exit_box = nhmex_uncore_msr_exit_box, \ .disable_box = nhmex_uncore_msr_disable_box, \ .enable_box = nhmex_uncore_msr_enable_box, \ .disable_event = nhmex_uncore_msr_disable_event, \ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/events/intel/uncore_snb.c similarity index 98% rename from arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c rename to arch/x86/events/intel/uncore_snb.c index 2bd030ddd0db3..96531d2b843fc 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1,5 +1,5 @@ /* Nehalem/SandBridge/Haswell uncore support */ -#include "perf_event_intel_uncore.h" +#include "uncore.h" /* Uncore IMC PCI IDs */ #define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 @@ -95,6 +95,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void snb_uncore_msr_exit_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, 0); +} + static struct uncore_event_desc snb_uncore_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), { /* end: all zeroes */ }, @@ -116,6 +122,7 @@ static struct attribute_group snb_uncore_format_group = { static struct intel_uncore_ops snb_uncore_msr_ops = { .init_box = snb_uncore_msr_init_box, + .exit_box = snb_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, .read_counter = uncore_msr_read_counter, @@ -231,6 +238,11 @@ static void snb_uncore_imc_init_box(struct intel_uncore_box *box) box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; } +static void snb_uncore_imc_exit_box(struct intel_uncore_box *box) +{ + iounmap(box->io_addr); +} + static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) {} @@ -301,6 +313,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event) return -EINVAL; event->cpu = box->cpu; + event->pmu_private = box; event->hw.idx = -1; event->hw.last_tag = ~0ULL; @@ -458,6 +471,7 @@ static struct pmu snb_uncore_imc_pmu = { static struct intel_uncore_ops snb_uncore_imc_ops = { .init_box = snb_uncore_imc_init_box, + .exit_box = snb_uncore_imc_exit_box, .enable_box = snb_uncore_imc_enable_box, .disable_box = snb_uncore_imc_disable_box, .disable_event = snb_uncore_imc_disable_event, diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c similarity index 99% rename from arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c rename to arch/x86/events/intel/uncore_snbep.c index 33acb884ccf1b..93f6bd9bf7610 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1,6 +1,5 @@ /* SandyBridge-EP/IvyTown uncore support */ -#include "perf_event_intel_uncore.h" - +#include "uncore.h" /* SNB-EP Box level control */ #define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) @@ -987,7 +986,9 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve if (reg1->idx != EXTRA_REG_NONE) { int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; - struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx]; + int pkg = topology_phys_to_logical_pkg(box->pci_phys_id); + struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx]; + if (filter_pdev) { pci_write_config_dword(filter_pdev, reg1->reg, (u32)reg1->config); @@ -2521,14 +2522,16 @@ static struct intel_uncore_type *hswep_msr_uncores[] = { void hswep_uncore_cpu_init(void) { + int pkg = topology_phys_to_logical_pkg(0); + if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; /* Detect 6-8 core systems with only two SBOXes */ - if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) { + if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { u32 capid4; - pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3], + pci_read_config_dword(uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3], 0x94, &capid4); if (((capid4 >> 6) & 0x3) == 0) hswep_uncore_sbox.num_boxes = 2; @@ -2875,11 +2878,13 @@ static struct intel_uncore_type bdx_uncore_sbox = { .format_group = &hswep_uncore_sbox_format_group, }; +#define BDX_MSR_UNCORE_SBOX 3 + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, - &bdx_uncore_sbox, &hswep_uncore_pcu, + &bdx_uncore_sbox, NULL, }; @@ -2888,6 +2893,10 @@ void bdx_uncore_cpu_init(void) if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; + + /* BDX-DE doesn't have SBOX */ + if (boot_cpu_data.x86_model == 86) + uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; } static struct intel_uncore_type bdx_uncore_ha = { diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/events/msr.c similarity index 100% rename from arch/x86/kernel/cpu/perf_event_msr.c rename to arch/x86/events/msr.c diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/events/perf_event.h similarity index 99% rename from arch/x86/kernel/cpu/perf_event.h rename to arch/x86/events/perf_event.h index 7bb61e32fb29f..68155cafa8a13 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -586,6 +586,7 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1; int pebs_record_size; + int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); @@ -860,6 +861,8 @@ extern struct event_constraint intel_ivb_pebs_event_constraints[]; extern struct event_constraint intel_hsw_pebs_event_constraints[]; +extern struct event_constraint intel_bdw_pebs_event_constraints[]; + extern struct event_constraint intel_skl_pebs_event_constraints[]; struct event_constraint *intel_pebs_constraints(struct perf_event *event); @@ -904,6 +907,8 @@ void intel_pmu_lbr_init_skl(void); void intel_pmu_lbr_init_knl(void); +void intel_pmu_pebs_data_source_nhm(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 7bfc85bbb8ffc..99afb665a004c 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -151,12 +151,6 @@ static inline int alternatives_text_reserved(void *start, void *end) ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ ".popsection" -/* - * This must be included *after* the definition of ALTERNATIVE due to - * - */ -#include - /* * Alternative instructions for different CPU types or capabilities. * diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 3c56ef1ae068e..5e828da2e18f6 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -27,15 +27,23 @@ struct amd_l3_cache { }; struct threshold_block { - unsigned int block; - unsigned int bank; - unsigned int cpu; - u32 address; - u16 interrupt_enable; - bool interrupt_capable; - u16 threshold_limit; - struct kobject kobj; - struct list_head miscj; + unsigned int block; /* Number within bank */ + unsigned int bank; /* MCA bank the block belongs to */ + unsigned int cpu; /* CPU which controls MCA bank */ + u32 address; /* MSR address for the block */ + u16 interrupt_enable; /* Enable/Disable APIC interrupt */ + bool interrupt_capable; /* Bank can generate an interrupt. */ + + u16 threshold_limit; /* + * Value upon which threshold + * interrupt is generated. + */ + + struct kobject kobj; /* sysfs object */ + struct list_head miscj; /* + * List of threshold blocks + * within a bank. + */ }; struct threshold_bank { diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index c80f6b6f3da22..0899cfc8dfe8f 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -6,7 +6,6 @@ #include #include -#include #include #include #include diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h index 259a7c1ef7099..02e799fa43d1b 100644 --- a/arch/x86/include/asm/arch_hweight.h +++ b/arch/x86/include/asm/arch_hweight.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_HWEIGHT_H #define _ASM_X86_HWEIGHT_H +#include + #ifdef CONFIG_64BIT /* popcnt %edi, %eax -- redundant REX prefix for alignment */ #define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7" diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 189679aba7035..f5063b6659eb3 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -44,19 +44,22 @@ /* Exception table entry */ #ifdef __ASSEMBLY__ -# define _ASM_EXTABLE(from,to) \ +# define _ASM_EXTABLE_HANDLE(from, to, handler) \ .pushsection "__ex_table","a" ; \ - .balign 8 ; \ + .balign 4 ; \ .long (from) - . ; \ .long (to) - . ; \ + .long (handler) - . ; \ .popsection -# define _ASM_EXTABLE_EX(from,to) \ - .pushsection "__ex_table","a" ; \ - .balign 8 ; \ - .long (from) - . ; \ - .long (to) - . + 0x7ffffff0 ; \ - .popsection +# define _ASM_EXTABLE(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) + +# define _ASM_EXTABLE_FAULT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) + +# define _ASM_EXTABLE_EX(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) # define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ @@ -89,19 +92,24 @@ .endm #else -# define _ASM_EXTABLE(from,to) \ +# define _EXPAND_EXTABLE_HANDLE(x) #x +# define _ASM_EXTABLE_HANDLE(from, to, handler) \ " .pushsection \"__ex_table\",\"a\"\n" \ - " .balign 8\n" \ + " .balign 4\n" \ " .long (" #from ") - .\n" \ " .long (" #to ") - .\n" \ + " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \ " .popsection\n" -# define _ASM_EXTABLE_EX(from,to) \ - " .pushsection \"__ex_table\",\"a\"\n" \ - " .balign 8\n" \ - " .long (" #from ") - .\n" \ - " .long (" #to ") - . + 0x7ffffff0\n" \ - " .popsection\n" +# define _ASM_EXTABLE(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) + +# define _ASM_EXTABLE_FAULT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) + +# define _ASM_EXTABLE_EX(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) + /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index a584e1c509184..bfb28caf97b1b 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -6,18 +6,17 @@ /* * Force strict CPU ordering. - * And yes, this is required on UP too when we're talking + * And yes, this might be required on UP too when we're talking * to devices. */ #ifdef CONFIG_X86_32 -/* - * Some non-Intel clones support out of order store. wmb() ceases to be a - * nop for these. - */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") +#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") +#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") #else #define mb() asm volatile("mfence":::"memory") #define rmb() asm volatile("lfence":::"memory") diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index cfe3b954d5e41..7766d1cf096e8 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -91,7 +91,7 @@ set_bit(long nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __set_bit(long nr, volatile unsigned long *addr) +static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory"); } @@ -128,13 +128,13 @@ clear_bit(long nr, volatile unsigned long *addr) * clear_bit() is atomic and implies release semantics before the memory * operation. It can be used for an unlock. */ -static inline void clear_bit_unlock(long nr, volatile unsigned long *addr) +static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); clear_bit(nr, addr); } -static inline void __clear_bit(long nr, volatile unsigned long *addr) +static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { asm volatile("btr %1,%0" : ADDR : "Ir" (nr)); } @@ -151,7 +151,7 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr) * No memory barrier is required here, because x86 cannot reorder stores past * older loads. Same principle as spin_unlock. */ -static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) +static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); __clear_bit(nr, addr); @@ -166,7 +166,7 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __change_bit(long nr, volatile unsigned long *addr) +static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { asm volatile("btc %1,%0" : ADDR : "Ir" (nr)); } @@ -180,7 +180,7 @@ static inline void __change_bit(long nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void change_bit(long nr, volatile unsigned long *addr) +static __always_inline void change_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "xorb %1,%0" @@ -201,7 +201,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline int test_and_set_bit(long nr, volatile unsigned long *addr) { GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c"); } @@ -228,7 +228,7 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -247,7 +247,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *addr) { GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c"); } @@ -268,7 +268,7 @@ static inline int test_and_clear_bit(long nr, volatile unsigned long *addr) * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ -static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -280,7 +280,7 @@ static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr) } /* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline int __test_and_change_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -300,7 +300,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline int test_and_change_bit(long nr, volatile unsigned long *addr) { GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c"); } @@ -311,7 +311,7 @@ static __always_inline int constant_test_bit(long nr, const volatile unsigned lo (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } -static inline int variable_test_bit(long nr, volatile const unsigned long *addr) +static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr) { int oldbit; @@ -343,7 +343,7 @@ static int test_bit(int nr, const volatile unsigned long *addr); * * Undefined if no bit exists, so code should check against 0 first. */ -static inline unsigned long __ffs(unsigned long word) +static __always_inline unsigned long __ffs(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) @@ -357,7 +357,7 @@ static inline unsigned long __ffs(unsigned long word) * * Undefined if no zero exists, so code should check against ~0UL first. */ -static inline unsigned long ffz(unsigned long word) +static __always_inline unsigned long ffz(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) @@ -371,7 +371,7 @@ static inline unsigned long ffz(unsigned long word) * * Undefined if no set bit exists, so code should check against 0 first. */ -static inline unsigned long __fls(unsigned long word) +static __always_inline unsigned long __fls(unsigned long word) { asm("bsr %1,%0" : "=r" (word) @@ -393,7 +393,7 @@ static inline unsigned long __fls(unsigned long word) * set bit if value is nonzero. The first (least significant) bit * is at position 1. */ -static inline int ffs(int x) +static __always_inline int ffs(int x) { int r; @@ -434,7 +434,7 @@ static inline int ffs(int x) * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ -static inline int fls(int x) +static __always_inline int fls(int x) { int r; diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index e63aa38e85fb2..61518cf794376 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -91,16 +91,10 @@ void clflush_cache_range(void *addr, unsigned int size); #define mmio_flush_range(addr, size) clflush_cache_range(addr, size) -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); extern const int rodata_test_data; extern int kernel_set_to_readonly; void set_kernel_text_rw(void); void set_kernel_text_ro(void); -#else -static inline void set_kernel_text_rw(void) { } -static inline void set_kernel_text_ro(void) { } -#endif #ifdef CONFIG_DEBUG_RODATA_TEST int rodata_test(void); diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index eda81dc0f4ae0..d194266acb28e 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -3,10 +3,11 @@ #ifndef _ASM_X86_CLOCKSOURCE_H #define _ASM_X86_CLOCKSOURCE_H -#define VCLOCK_NONE 0 /* No vDSO clock available. */ -#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ -#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */ -#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */ +#define VCLOCK_NONE 0 /* No vDSO clock available. */ +#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */ +#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */ +#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */ +#define VCLOCK_MAX 3 struct arch_clocksource_data { int vclock_mode; diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index ad19841eddfe1..9733361fed6f4 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -2,6 +2,7 @@ #define ASM_X86_CMPXCHG_H #include +#include #include /* Provides LOCK_PREFIX */ /* diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 7ad8c94642977..68e4e8258b841 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -1,288 +1,7 @@ -/* - * Defines x86 CPU feature bits - */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H -#ifndef _ASM_X86_REQUIRED_FEATURES_H -#include -#endif - -#ifndef _ASM_X86_DISABLED_FEATURES_H -#include -#endif - -#define NCAPINTS 16 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ - -/* - * Note: If the comment begins with a quoted string, that string is used - * in /proc/cpuinfo instead of the macro name. If the string is "", - * this feature bit is not displayed in /proc/cpuinfo at all. - */ - -/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */ -#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */ - /* (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ -#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ -#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ -#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ -#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ -#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ - -/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ -/* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */ -#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ -#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */ -#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */ -#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */ - -/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ - -/* Other features, Linux-defined mapping, word 3 */ -/* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ -/* cpu types for specific tunings: */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */ -/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */ -#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */ -#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */ -#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */ -/* free, was #define X86_FEATURE_11AP ( 3*32+19) * "" Bad local APIC aka 11AP */ -#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ -#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ -#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ -#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */ -#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ - -/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ -#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ -#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */ -#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ -#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */ -#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ -#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ -#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ -#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ -#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ -#define X86_FEATURE_PDCM ( 4*32+15) /* Performance Capabilities */ -#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ -#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ -#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ -#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ -#define X86_FEATURE_X2APIC ( 4*32+21) /* x2APIC */ -#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ -#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ -#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* Tsc deadline timer */ -#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ -#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ -#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE enabled in the OS */ -#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */ -#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ - -/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ -#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ -#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ -#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ -#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ - -/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */ -#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */ -#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */ -#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */ -#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */ -#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ -#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ -#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ -#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ -#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ - -/* - * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc, word 7. - * - * Reuse free bits when adding new feature flags! - */ - -#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ - -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ - -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ - -/* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ - -#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ -#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ - - -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ -#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ -#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */ -#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ -#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ -#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ -#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ -#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ -#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ -#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ - -/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ -#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */ -#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ -#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ - -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ -#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ - -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ -#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ - -/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ -#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ - -/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ -#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ -#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ -#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ -#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ -#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ -#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ -#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ - -/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ -#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ -#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ -#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ -#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ - -/* - * BUG word(s) - */ -#define X86_BUG(x) (NCAPINTS*32 + (x)) - -#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ -#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ -#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ -#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ -#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ -#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ -#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ -#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ -#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#include #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -369,8 +88,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; * is not relevant. */ #define cpu_feature_enabled(bit) \ - (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : \ - cpu_has(&boot_cpu_data, bit)) + (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit)) #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) @@ -406,106 +124,19 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) /* - * Do not add any more of those clumsy macros - use static_cpu_has_safe() for + * Do not add any more of those clumsy macros - use static_cpu_has() for * fast paths and boot_cpu_has() otherwise! */ -#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS) -extern void warn_pre_alternatives(void); -extern bool __static_cpu_has_safe(u16 bit); - +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). - * These are only valid after alternatives have run, but will statically - * patch the target code for additional performance. + * These will statically patch the target code for additional + * performance. */ -static __always_inline __pure bool __static_cpu_has(u16 bit) -{ -#ifdef CC_HAVE_ASM_GOTO - -#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS - - /* - * Catch too early usage of this before alternatives - * have run. - */ - asm_volatile_goto("1: jmp %l[t_warn]\n" - "2:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" - " .long 0\n" /* no replacement */ - " .word %P0\n" /* 1: do replace */ - " .byte 2b - 1b\n" /* source len */ - " .byte 0\n" /* replacement len */ - " .byte 0\n" /* pad len */ - ".previous\n" - /* skipping size check since replacement size = 0 */ - : : "i" (X86_FEATURE_ALWAYS) : : t_warn); - -#endif - - asm_volatile_goto("1: jmp %l[t_no]\n" - "2:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" - " .long 0\n" /* no replacement */ - " .word %P0\n" /* feature bit */ - " .byte 2b - 1b\n" /* source len */ - " .byte 0\n" /* replacement len */ - " .byte 0\n" /* pad len */ - ".previous\n" - /* skipping size check since replacement size = 0 */ - : : "i" (bit) : : t_no); - return true; - t_no: - return false; - -#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS - t_warn: - warn_pre_alternatives(); - return false; -#endif - -#else /* CC_HAVE_ASM_GOTO */ - - u8 flag; - /* Open-coded due to __stringify() in ALTERNATIVE() */ - asm volatile("1: movb $0,%0\n" - "2:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" - " .long 3f - .\n" - " .word %P1\n" /* feature bit */ - " .byte 2b - 1b\n" /* source len */ - " .byte 4f - 3f\n" /* replacement len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .discard,\"aw\",@progbits\n" - " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "3: movb $1,%0\n" - "4:\n" - ".previous\n" - : "=qm" (flag) : "i" (bit)); - return flag; - -#endif /* CC_HAVE_ASM_GOTO */ -} - -#define static_cpu_has(bit) \ -( \ - __builtin_constant_p(boot_cpu_has(bit)) ? \ - boot_cpu_has(bit) : \ - __builtin_constant_p(bit) ? \ - __static_cpu_has(bit) : \ - boot_cpu_has(bit) \ -) - -static __always_inline __pure bool _static_cpu_has_safe(u16 bit) +static __always_inline __pure bool _static_cpu_has(u16 bit) { -#ifdef CC_HAVE_ASM_GOTO - asm_volatile_goto("1: jmp %l[t_dynamic]\n" + asm_volatile_goto("1: jmp 6f\n" "2:\n" ".skip -(((5f-4f) - (2b-1b)) > 0) * " "((5f-4f) - (2b-1b)),0x90\n" @@ -530,66 +161,34 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) " .byte 0\n" /* repl len */ " .byte 0\n" /* pad len */ ".previous\n" - : : "i" (bit), "i" (X86_FEATURE_ALWAYS) - : : t_dynamic, t_no); + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" + : : "i" (bit), "i" (X86_FEATURE_ALWAYS), + [bitnum] "i" (1 << (bit & 7)), + [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + : : t_yes, t_no); + t_yes: return true; t_no: return false; - t_dynamic: - return __static_cpu_has_safe(bit); -#else - u8 flag; - /* Open-coded due to __stringify() in ALTERNATIVE() */ - asm volatile("1: movb $2,%0\n" - "2:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 3f - .\n" /* repl offset */ - " .word %P2\n" /* always replace */ - " .byte 2b - 1b\n" /* source len */ - " .byte 4f - 3f\n" /* replacement len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .discard,\"aw\",@progbits\n" - " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "3: movb $0,%0\n" - "4:\n" - ".previous\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 5f - .\n" /* repl offset */ - " .word %P1\n" /* feature bit */ - " .byte 4b - 3b\n" /* src len */ - " .byte 6f - 5f\n" /* repl len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .discard,\"aw\",@progbits\n" - " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "5: movb $1,%0\n" - "6:\n" - ".previous\n" - : "=qm" (flag) - : "i" (bit), "i" (X86_FEATURE_ALWAYS)); - return (flag == 2 ? __static_cpu_has_safe(bit) : flag); -#endif /* CC_HAVE_ASM_GOTO */ } -#define static_cpu_has_safe(bit) \ +#define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ - _static_cpu_has_safe(bit) \ + _static_cpu_has(bit) \ ) #else /* - * gcc 3.x is too stupid to do the static test; fall back to dynamic. + * Fall back to dynamic for gcc versions which don't support asm goto. Should be + * a minority now anyway. */ #define static_cpu_has(bit) boot_cpu_has(bit) -#define static_cpu_has_safe(bit) boot_cpu_has(bit) #endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) @@ -597,7 +196,6 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) #define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)) #define static_cpu_has_bug(bit) static_cpu_has((bit)) -#define static_cpu_has_bug_safe(bit) static_cpu_has_safe((bit)) #define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) #define MAX_CPU_FEATURES (NCAPINTS * 32) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h new file mode 100644 index 0000000000000..074b7604bd512 --- /dev/null +++ b/arch/x86/include/asm/cpufeatures.h @@ -0,0 +1,300 @@ +#ifndef _ASM_X86_CPUFEATURES_H +#define _ASM_X86_CPUFEATURES_H + +#ifndef _ASM_X86_REQUIRED_FEATURES_H +#include +#endif + +#ifndef _ASM_X86_DISABLED_FEATURES_H +#include +#endif + +/* + * Defines x86 CPU feature bits + */ +#define NCAPINTS 16 /* N 32-bit words worth of info */ +#define NBUGINTS 1 /* N 32-bit bug flags */ + +/* + * Note: If the comment begins with a quoted string, that string is used + * in /proc/cpuinfo instead of the macro name. If the string is "", + * this feature bit is not displayed in /proc/cpuinfo at all. + */ + +/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */ + /* (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ +#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ +#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ +#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ +#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ +#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ + +/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ +/* Don't duplicate feature flags which are redundant with Intel! */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */ +#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */ + +/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ + +/* Other features, Linux-defined mapping, word 3 */ +/* This range is used for feature bits which conflict or are synthesized */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ +/* cpu types for specific tunings: */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ +#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */ +#define X86_FEATURE_ART ( 3*32+10) /* Platform has always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */ +#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */ +#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */ +/* free, was #define X86_FEATURE_11AP ( 3*32+19) * "" Bad local APIC aka 11AP */ +#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ +/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ +#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */ + +/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ +#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */ +#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */ +#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ +#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* Performance Capabilities */ +#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ +#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* x2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* Tsc deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ + +/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ +#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ +#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ +#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ +#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ + +/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ +#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ + +/* + * Auxiliary flags: Linux defined - For features scattered in various + * CPUID levels like 0x6, 0xA etc, word 7. + * + * Reuse free bits when adding new feature flags! + */ + +#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ + +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ + +#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ + +/* Virtualization flags: Linux defined, word 8 */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ +#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ + +#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ + + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ +#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ + +/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ +#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ +#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ + +/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ +#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ + +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ + +/* + * BUG word(s) + */ +#define X86_BUG(x) (NCAPINTS*32 + (x)) + +#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ +#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ + +#ifdef CONFIG_X86_32 +/* + * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional + * to avoid confusion. + */ +#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#endif + +#endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index 278441f39856e..eb5deb42484d5 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -98,4 +98,27 @@ struct desc_ptr { #endif /* !__ASSEMBLY__ */ +/* Access rights as returned by LAR */ +#define AR_TYPE_RODATA (0 * (1 << 9)) +#define AR_TYPE_RWDATA (1 * (1 << 9)) +#define AR_TYPE_RODATA_EXPDOWN (2 * (1 << 9)) +#define AR_TYPE_RWDATA_EXPDOWN (3 * (1 << 9)) +#define AR_TYPE_XOCODE (4 * (1 << 9)) +#define AR_TYPE_XRCODE (5 * (1 << 9)) +#define AR_TYPE_XOCODE_CONF (6 * (1 << 9)) +#define AR_TYPE_XRCODE_CONF (7 * (1 << 9)) +#define AR_TYPE_MASK (7 * (1 << 9)) + +#define AR_DPL0 (0 * (1 << 13)) +#define AR_DPL3 (3 * (1 << 13)) +#define AR_DPL_MASK (3 * (1 << 13)) + +#define AR_A (1 << 8) /* "Accessed" */ +#define AR_S (1 << 12) /* If clear, "System" segment */ +#define AR_P (1 << 15) /* "Present" */ +#define AR_AVL (1 << 20) /* "AVaiLable" (no HW effect) */ +#define AR_L (1 << 21) /* "Long mode" for code segments */ +#define AR_DB (1 << 22) /* D/B, effect depends on type */ +#define AR_G (1 << 23) /* "Granularity" (limit in pages) */ + #endif /* _ASM_X86_DESC_DEFS_H */ diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index 535192f6bfad8..3c69fed215c56 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -15,7 +15,7 @@ static __always_inline __init void *dmi_alloc(unsigned len) /* Use early IO mappings for DMI because it's initialized early */ #define dmi_early_remap early_ioremap #define dmi_early_unmap early_iounmap -#define dmi_remap ioremap +#define dmi_remap ioremap_cache #define dmi_unmap iounmap #endif /* _ASM_X86_DMI_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1514753fd4355..15340e36ddcb3 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -256,7 +256,7 @@ extern int force_personality32; instruction set this CPU supports. This could be done in user space, but it's not easy, and we've already done it here. */ -#define ELF_HWCAP (boot_cpu_data.x86_capability[0]) +#define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 6d7d0e52ed5a5..8554f960e21b7 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -138,7 +138,7 @@ extern void reserve_top_address(unsigned long reserve); extern int fixmaps_set; extern pte_t *kmap_pte; -extern pgprot_t kmap_prot; +#define kmap_prot PAGE_KERNEL extern pte_t *pkmap_page_table; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 0fd440df63f18..a2124343edf54 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -17,6 +17,7 @@ #include #include #include +#include /* * High level FPU state handling functions: @@ -58,22 +59,22 @@ extern u64 fpu__get_supported_xfeatures_mask(void); */ static __always_inline __pure bool use_eager_fpu(void) { - return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); + return static_cpu_has(X86_FEATURE_EAGER_FPU); } static __always_inline __pure bool use_xsaveopt(void) { - return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); + return static_cpu_has(X86_FEATURE_XSAVEOPT); } static __always_inline __pure bool use_xsave(void) { - return static_cpu_has_safe(X86_FEATURE_XSAVE); + return static_cpu_has(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { - return static_cpu_has_safe(X86_FEATURE_FXSR); + return static_cpu_has(X86_FEATURE_FXSR); } /* @@ -300,7 +301,7 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) WARN_ON(system_state != SYSTEM_BOOTING); - if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + if (static_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XSAVES, xstate, lmask, hmask, err); else XSTATE_OP(XSAVE, xstate, lmask, hmask, err); @@ -322,7 +323,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) WARN_ON(system_state != SYSTEM_BOOTING); - if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + if (static_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); @@ -460,7 +461,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) * pending. Clear the x87 state here by setting it to fixed values. * "m" is a random variable that should be in L1. */ - if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { + if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" @@ -589,7 +590,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) * If the task has used the math, pre-load the FPU on xsave processors * or if the past 5 consecutive context-switches used math. */ - fpu.preload = new_fpu->fpstate_active && + fpu.preload = static_cpu_has(X86_FEATURE_FPU) && + new_fpu->fpstate_active && (use_eager_fpu() || new_fpu->counter > 5); if (old_fpu->fpregs_active) { diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index af30fdeb140da..f23cd8c80b1c8 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -20,16 +20,15 @@ /* Supported features which support lazy state saving */ #define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ - XFEATURE_MASK_SSE) - -/* Supported features which require eager state saving */ -#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | \ - XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM) +/* Supported features which require eager state saving */ +#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR) + /* All currently supported features */ #define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER) diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 793179cf8e21a..6e4d170726b75 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -1,23 +1,44 @@ -#ifdef __ASSEMBLY__ +#ifndef _ASM_X86_FRAME_H +#define _ASM_X86_FRAME_H #include -/* The annotation hides the frame from the unwinder and makes it look - like a ordinary ebp save/restore. This avoids some special cases for - frame pointer later */ +/* + * These are stack frame creation macros. They should be used by every + * callable non-leaf asm function to make kernel stack traces more reliable. + */ + #ifdef CONFIG_FRAME_POINTER - .macro FRAME - __ASM_SIZE(push,) %__ASM_REG(bp) - __ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp) - .endm - .macro ENDFRAME - __ASM_SIZE(pop,) %__ASM_REG(bp) - .endm -#else - .macro FRAME - .endm - .macro ENDFRAME - .endm -#endif - -#endif /* __ASSEMBLY__ */ + +#ifdef __ASSEMBLY__ + +.macro FRAME_BEGIN + push %_ASM_BP + _ASM_MOV %_ASM_SP, %_ASM_BP +.endm + +.macro FRAME_END + pop %_ASM_BP +.endm + +#else /* !__ASSEMBLY__ */ + +#define FRAME_BEGIN \ + "push %" _ASM_BP "\n" \ + _ASM_MOV "%" _ASM_SP ", %" _ASM_BP "\n" + +#define FRAME_END "pop %" _ASM_BP "\n" + +#endif /* __ASSEMBLY__ */ + +#define FRAME_OFFSET __ASM_SEL(4, 8) + +#else /* !CONFIG_FRAME_POINTER */ + +#define FRAME_BEGIN +#define FRAME_END +#define FRAME_OFFSET 0 + +#endif /* CONFIG_FRAME_POINTER */ + +#endif /* _ASM_X86_FRAME_H */ diff --git a/arch/x86/include/asm/imr.h b/arch/x86/include/asm/imr.h index cd2ce4068441b..ebea2c9d2cdc0 100644 --- a/arch/x86/include/asm/imr.h +++ b/arch/x86/include/asm/imr.h @@ -53,7 +53,7 @@ #define IMR_MASK (IMR_ALIGN - 1) int imr_add_range(phys_addr_t base, size_t size, - unsigned int rmask, unsigned int wmask, bool lock); + unsigned int rmask, unsigned int wmask); int imr_remove_range(phys_addr_t base, size_t size); diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index cfc9a0d2d07ce..a4fe16e42b7b2 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -57,67 +57,13 @@ static inline void __xapic_wait_icr_idle(void) cpu_relax(); } -static inline void -__default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest) -{ - /* - * Subtle. In the case of the 'never do double writes' workaround - * we have to lock out interrupts to be safe. As we don't care - * of the value read we use an atomic rmw access to avoid costly - * cli/sti. Otherwise we use an even cheaper single atomic write - * to the APIC. - */ - unsigned int cfg; - - /* - * Wait for idle. - */ - __xapic_wait_icr_idle(); - - /* - * No need to touch the target chip field - */ - cfg = __prepare_ICR(shortcut, vector, dest); - - /* - * Send the IPI. The write to APIC_ICR fires this off. - */ - native_apic_mem_write(APIC_ICR, cfg); -} +void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest); /* * This is used to send an IPI with no shorthand notation (the destination is * specified in bits 56 to 63 of the ICR). */ -static inline void - __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest) -{ - unsigned long cfg; - - /* - * Wait for idle. - */ - if (unlikely(vector == NMI_VECTOR)) - safe_apic_wait_icr_idle(); - else - __xapic_wait_icr_idle(); - - /* - * prepare target chip field - */ - cfg = __prepare_ICR2(mask); - native_apic_mem_write(APIC_ICR2, cfg); - - /* - * program the ICR - */ - cfg = __prepare_ICR(0, vector, dest); - - /* - * Send the IPI. The write to APIC_ICR fires this off. - */ - native_apic_mem_write(APIC_ICR, cfg); -} +void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest); extern void default_send_IPI_single(int cpu, int vector); extern void default_send_IPI_single_phys(int cpu, int vector); diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index 78162f8e248bd..d0afb05c84fc1 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -1,7 +1,7 @@ #ifndef _ASM_IRQ_WORK_H #define _ASM_IRQ_WORK_H -#include +#include static inline bool arch_irq_work_has_interrupt(void) { diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index c1adf33fdd0d6..bc62e7cbf1b1f 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -17,15 +17,8 @@ static inline bool kvm_check_and_clear_guest_paused(void) } #endif /* CONFIG_KVM_GUEST */ -#ifdef CONFIG_DEBUG_RODATA #define KVM_HYPERCALL \ ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL) -#else -/* On AMD processors, vmcall will generate a trap that we will - * then rewrite to the appropriate instruction. - */ -#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" -#endif /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall * instruction. The hypervisor may replace it with something else but only the diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 2ea4527e462f1..92b6f651fa4fc 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -40,8 +40,20 @@ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ /* AMD-specific bits */ -#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */ +#define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */ #define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */ +#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */ + +/* + * McaX field if set indicates a given bank supports MCA extensions: + * - Deferred error interrupt type is specifiable by bank. + * - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers, + * But should not be used to determine MSR numbers. + * - TCC bit is present in MCx_STATUS. + */ +#define MCI_CONFIG_MCAX 0x1 +#define MCI_IPID_MCATYPE 0xFFFF0000 +#define MCI_IPID_HWID 0xFFF /* * Note that the full MCACOD field of IA32_MCi_STATUS MSR is @@ -91,6 +103,16 @@ #define MCE_LOG_LEN 32 #define MCE_LOG_SIGNATURE "MACHINECHECK" +/* AMD Scalable MCA */ +#define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003 +#define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004 +#define MSR_AMD64_SMCA_MC0_IPID 0xc0002005 +#define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a +#define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) + /* * This structure contains all data related to the MCE log. Also * carries a signature to make it easier to find from external @@ -113,6 +135,7 @@ struct mca_config { bool ignore_ce; bool disabled; bool ser; + bool recovery; bool bios_cmci_threshold; u8 banks; s8 bootlog; @@ -287,4 +310,49 @@ struct cper_sec_mem_err; extern void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err); +/* + * Enumerate new IP types and HWID values in AMD processors which support + * Scalable MCA. + */ +#ifdef CONFIG_X86_MCE_AMD +enum amd_ip_types { + SMCA_F17H_CORE = 0, /* Core errors */ + SMCA_DF, /* Data Fabric */ + SMCA_UMC, /* Unified Memory Controller */ + SMCA_PB, /* Parameter Block */ + SMCA_PSP, /* Platform Security Processor */ + SMCA_SMU, /* System Management Unit */ + N_AMD_IP_TYPES +}; + +struct amd_hwid { + const char *name; + unsigned int hwid; +}; + +extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES]; + +enum amd_core_mca_blocks { + SMCA_LS = 0, /* Load Store */ + SMCA_IF, /* Instruction Fetch */ + SMCA_L2_CACHE, /* L2 cache */ + SMCA_DE, /* Decoder unit */ + RES, /* Reserved */ + SMCA_EX, /* Execution unit */ + SMCA_FP, /* Floating Point */ + SMCA_L3_CACHE, /* L3 cache */ + N_CORE_MCA_BLOCKS +}; + +extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS]; + +enum amd_df_mca_blocks { + SMCA_CS = 0, /* Coherent Slave */ + SMCA_PIE, /* Power management, Interrupts, etc */ + N_DF_BLOCKS +}; + +extern const char * const amd_df_mcablock_names[N_DF_BLOCKS]; +#endif + #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 1e1b07a5a7388..9d3a96c4da789 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -3,6 +3,7 @@ #include #include +#include #define native_rdmsr(msr, val1, val2) \ do { \ @@ -143,4 +144,29 @@ static inline void reload_early_microcode(void) { } static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } #endif + +static inline unsigned long get_initrd_start(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + return initrd_start; +#else + return 0; +#endif +} + +static inline unsigned long get_initrd_start_addr(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD +#ifdef CONFIG_X86_32 + unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + + return (unsigned long)__pa_nodebug(*initrd_start_p); +#else + return get_initrd_start(); +#endif +#else /* CONFIG_BLK_DEV_INITRD */ + return 0; +#endif +} + #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 8559b0102ea1f..603417f8dd6cf 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -40,7 +40,6 @@ struct extended_sigtable { #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) #define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) #define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) -#define DWSIZE (sizeof(u32)) #define get_totalsize(mc) \ (((struct microcode_intel *)mc)->hdr.datasize ? \ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 55234d5e7160d..1ea0baef1175c 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -19,7 +19,8 @@ typedef struct { #endif struct mutex lock; - void __user *vdso; + void __user *vdso; /* vdso base address */ + const struct vdso_image *vdso_image; /* vdso image in use */ atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */ } mm_context_t; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b05402ef3b842..984ab75bf6218 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -1,7 +1,12 @@ #ifndef _ASM_X86_MSR_INDEX_H #define _ASM_X86_MSR_INDEX_H -/* CPU model specific register (MSR) numbers */ +/* + * CPU model specific register (MSR) numbers. + * + * Do not add new entries to this file unless the definitions are shared + * between multiple compilation units. + */ /* x86-64 specific MSRs */ #define MSR_EFER 0xc0000080 /* extended feature register */ diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index c70689b5e5aa4..0deeb2d26df7c 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -3,6 +3,8 @@ #include +#include + #define MWAIT_SUBSTATE_MASK 0xf #define MWAIT_CSTATE_MASK 0xf #define MWAIT_SUBSTATE_SIZE 4 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7bcb861a04e5c..5a2ed3ed2f261 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -165,6 +165,7 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_ASIF BIT_ULL(60) #define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) #define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* * IBS cpuid feature detection diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 20c11d1aa4ccc..983738ac014c6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -13,7 +13,7 @@ struct vm86; #include #include #include -#include +#include #include #include #include @@ -24,7 +24,6 @@ struct vm86; #include #include -#include #include #include #include @@ -129,6 +128,8 @@ struct cpuinfo_x86 { u16 booted_cores; /* Physical processor id: */ u16 phys_proc_id; + /* Logical processor id: */ + u16 logical_proc_id; /* Core id: */ u16 cpu_core_id; /* Compute unit id */ @@ -298,10 +299,13 @@ struct tss_struct { */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; +#ifdef CONFIG_X86_32 /* - * Space for the temporary SYSENTER stack: + * Space for the temporary SYSENTER stack. */ + unsigned long SYSENTER_stack_canary; unsigned long SYSENTER_stack[64]; +#endif } ____cacheline_aligned; diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index a4a77286cb1dd..9b9b30b194418 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -7,12 +7,23 @@ void syscall_init(void); +#ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); -void entry_SYSCALL_compat(void); +#endif + +#ifdef CONFIG_X86_32 void entry_INT80_32(void); -void entry_INT80_compat(void); void entry_SYSENTER_32(void); +void __begin_SYSENTER_singlestep_region(void); +void __end_SYSENTER_singlestep_region(void); +#endif + +#ifdef CONFIG_IA32_EMULATION void entry_SYSENTER_compat(void); +void __end_entry_SYSENTER_compat(void); +void entry_SYSCALL_compat(void); +void entry_INT80_compat(void); +#endif void x86_configure_nx(void); void x86_report_nx(void); diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 0a52424286590..13b6cdd0af570 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -7,7 +7,7 @@ extern char __brk_base[], __brk_limit[]; extern struct exception_table_entry __stop___ex_table[]; -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; #endif diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index 89db46752a8f0..452c88b8ad069 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -13,7 +13,6 @@ X86_EFLAGS_CF | X86_EFLAGS_RF) void signal_fault(struct pt_regs *regs, void __user *frame, char *where); -int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc); int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask); diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index ba665ebd17bb8..db333300bd4be 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -15,7 +15,7 @@ #include #include -#include +#include /* "Raw" instruction opcodes */ #define __ASM_CLAC .byte 0x0f,0x01,0xca diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index dfcf0727623b3..20a3de5cb3b0d 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -16,7 +16,6 @@ #endif #include #include -#include extern int smp_num_siblings; extern unsigned int num_processors; diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index ff8b9a17dc4b2..ca6ba36077054 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -78,6 +78,19 @@ int strcmp(const char *cs, const char *ct); #define memset(s, c, n) __memset(s, c, n) #endif +/** + * memcpy_mcsafe - copy memory with indication if a machine check happened + * + * @dst: destination address + * @src: source address + * @cnt: number of bytes to copy + * + * Low level memory copy function that catches machine checks + * + * Return true for success, false for fail + */ +bool memcpy_mcsafe(void *dst, const void *src, size_t cnt); + #endif /* __KERNEL__ */ #endif /* _ASM_X86_STRING_64_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index c7b551028740f..82866697fcf18 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -49,7 +49,7 @@ */ #ifndef __ASSEMBLY__ struct task_struct; -#include +#include #include struct thread_info { @@ -134,10 +134,13 @@ struct thread_info { #define _TIF_ADDR32 (1 << TIF_ADDR32) #define _TIF_X32 (1 << TIF_X32) -/* work to do in syscall_trace_enter() */ +/* + * work to do in syscall_trace_enter(). Also includes TIF_NOHZ for + * enter_from_user_mode() + */ #define _TIF_WORK_SYSCALL_ENTRY \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \ + _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) /* work to do on any return to user space */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6df2029405a3a..c24b4224d4392 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -5,8 +5,57 @@ #include #include +#include #include +static inline void __invpcid(unsigned long pcid, unsigned long addr, + unsigned long type) +{ + struct { u64 d[2]; } desc = { { pcid, addr } }; + + /* + * The memory clobber is because the whole point is to invalidate + * stale TLB entries and, especially if we're flushing global + * mappings, we don't want the compiler to reorder any subsequent + * memory accesses before the TLB flush. + * + * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and + * invpcid (%rcx), %rax in long mode. + */ + asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01" + : : "m" (desc), "a" (type), "c" (&desc) : "memory"); +} + +#define INVPCID_TYPE_INDIV_ADDR 0 +#define INVPCID_TYPE_SINGLE_CTXT 1 +#define INVPCID_TYPE_ALL_INCL_GLOBAL 2 +#define INVPCID_TYPE_ALL_NON_GLOBAL 3 + +/* Flush all mappings for a given pcid and addr, not including globals. */ +static inline void invpcid_flush_one(unsigned long pcid, + unsigned long addr) +{ + __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR); +} + +/* Flush all mappings for a given PCID, not including globals. */ +static inline void invpcid_flush_single_context(unsigned long pcid) +{ + __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT); +} + +/* Flush all mappings, including globals, for all PCIDs. */ +static inline void invpcid_flush_all(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL); +} + +/* Flush all mappings for all PCIDs except globals. */ +static inline void invpcid_flush_all_nonglobals(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL); +} + #ifdef CONFIG_PARAVIRT #include #else @@ -104,6 +153,15 @@ static inline void __native_flush_tlb_global(void) { unsigned long flags; + if (static_cpu_has(X86_FEATURE_INVPCID)) { + /* + * Using INVPCID is considerably faster than a pair of writes + * to CR4 sandwiched inside an IRQ flag save/restore. + */ + invpcid_flush_all(); + return; + } + /* * Read-modify-write to CR4 - protect it from preemption and * from interrupts. (Use the raw variant because this code can diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 0fb46482dfde1..7f991bd5031b2 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -119,12 +119,23 @@ static inline void setup_node_to_cpumask_map(void) { } extern const struct cpumask *cpu_coregroup_mask(int cpu); +#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id) #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) #ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) + +extern unsigned int __max_logical_packages; +#define topology_max_packages() (__max_logical_packages) +int topology_update_package_map(unsigned int apicid, unsigned int cpu); +extern int topology_phys_to_logical_pkg(unsigned int pkg); +#else +#define topology_max_packages() (1) +static inline int +topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } +static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 6d7c5479bceae..174c4212780af 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -29,6 +29,8 @@ static inline cycles_t get_cycles(void) return rdtsc(); } +extern struct system_counterval_t convert_art_to_tsc(cycle_t art); + extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a4a30e4b2d343..c0f27d7ea7ff9 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -90,12 +90,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un likely(!__range_not_ok(addr, size, user_addr_max())) /* - * The exception table consists of pairs of addresses relative to the - * exception table enty itself: the first is the address of an - * instruction that is allowed to fault, and the second is the address - * at which the program should continue. No registers are modified, - * so it is entirely up to the continuation code to figure out what to - * do. + * The exception table consists of triples of addresses relative to the + * exception table entry itself. The first address is of an instruction + * that is allowed to fault, the second is the target at which the program + * should continue. The third is a handler function to deal with the fault + * caused by the instruction in the first field. * * All the routines below use bits of fixup code that are out of line * with the main instruction path. This means when everything is well, @@ -104,13 +103,14 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un */ struct exception_table_entry { - int insn, fixup; + int insn, fixup, handler; }; /* This is not the generic standard exception_table_entry format */ #define ARCH_HAS_SORT_EXTABLE #define ARCH_HAS_SEARCH_EXTABLE -extern int fixup_exception(struct pt_regs *regs); +extern int fixup_exception(struct pt_regs *regs, int trapnr); +extern bool ex_has_fault_handler(unsigned long ip); extern int early_fixup_exception(unsigned long *ip); /* diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index b89c34c4019b5..307698688fa1c 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include /* diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index deabaf9759b64..43dc55be524e7 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -13,9 +13,6 @@ struct vdso_image { void *data; unsigned long size; /* Always a multiple of PAGE_SIZE */ - /* text_mapping.pages is big enough for data/size page pointers */ - struct vm_special_mapping text_mapping; - unsigned long alt, alt_len; long sym_vvar_start; /* Negative offset to the vvar area */ diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index f556c4843aa18..e728699db7741 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -37,6 +37,12 @@ struct vsyscall_gtod_data { }; extern struct vsyscall_gtod_data vsyscall_gtod_data; +extern int vclocks_used; +static inline bool vclock_was_used(int vclock) +{ + return READ_ONCE(vclocks_used) & (1 << vclock); +} + static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s) { unsigned ret; diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index d485232f1e9f9..62d4111c1c549 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -256,7 +256,7 @@ struct sigcontext_64 { __u16 cs; __u16 gs; __u16 fs; - __u16 __pad0; + __u16 ss; __u64 err; __u64 trapno; __u64 oldmask; @@ -341,9 +341,37 @@ struct sigcontext { __u64 rip; __u64 eflags; /* RFLAGS */ __u16 cs; + + /* + * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"), + * Linux saved and restored fs and gs in these slots. This + * was counterproductive, as fsbase and gsbase were never + * saved, so arch_prctl was presumably unreliable. + * + * These slots should never be reused without extreme caution: + * + * - Some DOSEMU versions stash fs and gs in these slots manually, + * thus overwriting anything the kernel expects to be preserved + * in these slots. + * + * - If these slots are ever needed for any other purpose, + * there is some risk that very old 64-bit binaries could get + * confused. I doubt that many such binaries still work, + * though, since the same patch in 2.5.64 also removed the + * 64-bit set_thread_area syscall, so it appears that there + * is no TLS API beyond modify_ldt that works in both pre- + * and post-2.5.64 kernels. + * + * If the kernel ever adds explicit fs, gs, fsbase, and gsbase + * save/restore, it will most likely need to be opt-in and use + * different context slots. + */ __u16 gs; __u16 fs; - __u16 __pad0; + union { + __u16 ss; /* If UC_SIGCONTEXT_SS */ + __u16 __pad0; /* Alias name for old (!UC_SIGCONTEXT_SS) user-space */ + }; __u64 err; __u64 trapno; __u64 oldmask; diff --git a/arch/x86/include/uapi/asm/ucontext.h b/arch/x86/include/uapi/asm/ucontext.h index b7c29c8017f28..e3d1ec90616ed 100644 --- a/arch/x86/include/uapi/asm/ucontext.h +++ b/arch/x86/include/uapi/asm/ucontext.h @@ -1,11 +1,54 @@ #ifndef _ASM_X86_UCONTEXT_H #define _ASM_X86_UCONTEXT_H -#define UC_FP_XSTATE 0x1 /* indicates the presence of extended state - * information in the memory layout pointed - * by the fpstate pointer in the ucontext's - * sigcontext struct (uc_mcontext). - */ +/* + * Indicates the presence of extended state information in the memory + * layout pointed by the fpstate pointer in the ucontext's sigcontext + * struct (uc_mcontext). + */ +#define UC_FP_XSTATE 0x1 + +#ifdef __x86_64__ +/* + * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on + * kernels that save SS in the sigcontext. All kernels that set + * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp + * regardless of SS (i.e. they implement espfix). + * + * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS + * when delivering a signal that came from 64-bit code. + * + * Sigreturn restores SS as follows: + * + * if (saved SS is valid || UC_STRICT_RESTORE_SS is set || + * saved CS is not 64-bit) + * new SS = saved SS (will fail IRET and signal if invalid) + * else + * new SS = a flat 32-bit data segment + * + * This behavior serves three purposes: + * + * - Legacy programs that construct a 64-bit sigcontext from scratch + * with zero or garbage in the SS slot (e.g. old CRIU) and call + * sigreturn will still work. + * + * - Old DOSEMU versions sometimes catch a signal from a segmented + * context, delete the old SS segment (with modify_ldt), and change + * the saved CS to a 64-bit segment. These DOSEMU versions expect + * sigreturn to send them back to 64-bit mode without killing them, + * despite the fact that the SS selector when the signal was raised is + * no longer valid. UC_STRICT_RESTORE_SS will be clear, so the kernel + * will fix up SS for these DOSEMU versions. + * + * - Old and new programs that catch a signal and return without + * modifying the saved context will end up in exactly the state they + * started in, even if they were running in a segmented context when + * the signal was raised.. Old kernels would lose track of the + * previous SS value. + */ +#define UC_SIGCONTEXT_SS 0x2 +#define UC_STRICT_RESTORE_SS 0x4 +#endif #include diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index d1daead5fcddd..adb3eaf8fe2a5 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include #include +#include #include "../../realmode/rm/wakeup.h" #include "sleep.h" @@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + /* + * Pause/unpause graph tracing around do_suspend_lowlevel as it has + * inconsistent call/return info after it jumps to the wakeup vector. + */ + pause_graph_tracing(); do_suspend_lowlevel(); + unpause_graph_tracing(); return 0; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 8a5cddac7d444..531b9611c51d5 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2077,6 +2077,20 @@ int generic_processor_info(int apicid, int version) } else cpu = cpumask_next_zero(-1, cpu_present_mask); + /* + * This can happen on physical hotplug. The sanity check at boot time + * is done from native_smp_prepare_cpus() after num_possible_cpus() is + * established. + */ + if (topology_update_package_map(apicid, cpu) < 0) { + int thiscpu = max + disabled_cpus; + + pr_warning("ACPI: Package limit reached. Processor %d/0x%x ignored.\n", + thiscpu, apicid); + disabled_cpus++; + return -ENOSPC; + } + /* * Validate version */ diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 9968f30cca3e1..76f89e2b245af 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -53,7 +53,7 @@ void flat_init_apic_ldr(void) apic_write(APIC_LDR, val); } -static inline void _flat_send_IPI_mask(unsigned long mask, int vector) +static void _flat_send_IPI_mask(unsigned long mask, int vector) { unsigned long flags; diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index c80c02c6ec494..ab5c2c685a3ce 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -30,7 +30,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x) unsigned long value; unsigned int id = (x >> 24) & 0xff; - if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) { + if (static_cpu_has(X86_FEATURE_NODEID_MSR)) { rdmsrl(MSR_FAM10H_NODE_ID, value); id |= (value << 2) & 0xff00; } @@ -178,7 +178,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) this_cpu_write(cpu_llc_id, node); /* Account for nodes per socket in multi-core-module processors */ - if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) { + if (static_cpu_has(X86_FEATURE_NODEID_MSR)) { rdmsrl(MSR_FAM10H_NODE_ID, val); nodes = ((val >> 3) & 7) + 1; } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index eb45fc9b61248..28bde88b0085d 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -18,6 +18,66 @@ #include #include +void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest) +{ + /* + * Subtle. In the case of the 'never do double writes' workaround + * we have to lock out interrupts to be safe. As we don't care + * of the value read we use an atomic rmw access to avoid costly + * cli/sti. Otherwise we use an even cheaper single atomic write + * to the APIC. + */ + unsigned int cfg; + + /* + * Wait for idle. + */ + __xapic_wait_icr_idle(); + + /* + * No need to touch the target chip field + */ + cfg = __prepare_ICR(shortcut, vector, dest); + + /* + * Send the IPI. The write to APIC_ICR fires this off. + */ + native_apic_mem_write(APIC_ICR, cfg); +} + +/* + * This is used to send an IPI with no shorthand notation (the destination is + * specified in bits 56 to 63 of the ICR). + */ +void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest) +{ + unsigned long cfg; + + /* + * Wait for idle. + */ + if (unlikely(vector == NMI_VECTOR)) + safe_apic_wait_icr_idle(); + else + __xapic_wait_icr_idle(); + + /* + * prepare target chip field + */ + cfg = __prepare_ICR2(mask); + native_apic_mem_write(APIC_ICR2, cfg); + + /* + * program the ICR + */ + cfg = __prepare_ICR(0, vector, dest); + + /* + * Send the IPI. The write to APIC_ICR fires this off. + */ + native_apic_mem_write(APIC_ICR, cfg); +} + void default_send_IPI_single_phys(int cpu, int vector) { unsigned long flags; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 84a7524b202ca..5c042466f274d 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -59,7 +59,6 @@ void common(void) { #ifdef CONFIG_PARAVIRT BLANK(); - OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops); OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops); OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 6ce39025f467f..ecdc1d217dc0f 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -7,7 +7,7 @@ #include #include "../../../drivers/lguest/lg.h" -#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +#define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls[] = { #include }; @@ -52,6 +52,11 @@ void foo(void) DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - offsetofend(struct tss_struct, SYSENTER_stack)); + /* Offset from cpu_tss to SYSENTER_stack */ + OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); + /* Size of SYSENTER_stack */ + DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); + #if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index f2edafb5f24eb..d875f97d4e0ba 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -4,17 +4,11 @@ #include -#define __SYSCALL_64(nr, sym, compat) [nr] = 1, -#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, -#ifdef CONFIG_X86_X32_ABI -# define __SYSCALL_X32(nr, sym, compat) [nr] = 1, -#else -# define __SYSCALL_X32(nr, sym, compat) /* nothing */ -#endif +#define __SYSCALL_64(nr, sym, qual) [nr] = 1, static char syscalls_64[] = { #include }; -#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +#define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls_ia32[] = { #include }; diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 58031303e3048..0d373d7affc8d 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -30,33 +30,11 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o - -ifdef CONFIG_PERF_EVENTS -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o perf_event_amd_uncore.o -ifdef CONFIG_AMD_IOMMU -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o -endif -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o perf_event_intel_cqm.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o perf_event_intel_bts.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_cstate.o - -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \ - perf_event_intel_uncore_snb.o \ - perf_event_intel_uncore_snbep.o \ - perf_event_intel_uncore_nhmex.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_msr.o -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_msr.o -endif - - obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ -obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o +obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o @@ -64,7 +42,7 @@ ifdef CONFIG_X86_FEATURE_NAMES quiet_cmd_mkcapflags = MKCAP $@ cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@ -cpufeature = $(src)/../../include/asm/cpufeature.h +cpufeature = $(src)/../../include/asm/cpufeatures.h targets += capflags.c $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a07956a08936e..97c59fd60702f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -117,7 +117,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) void (*f_vide)(void); u64 d, d2; - printk(KERN_INFO "AMD K6 stepping B detected - "); + pr_info("AMD K6 stepping B detected - "); /* * It looks like AMD fixed the 2.6.2 bug and improved indirect @@ -133,10 +133,9 @@ static void init_amd_k6(struct cpuinfo_x86 *c) d = d2-d; if (d > 20*K6_BUG_LOOP) - printk(KERN_CONT - "system stability may be impaired when more than 32 MB are used.\n"); + pr_cont("system stability may be impaired when more than 32 MB are used.\n"); else - printk(KERN_CONT "probably OK (after B9730xxxx).\n"); + pr_cont("probably OK (after B9730xxxx).\n"); } /* K6 with old style WHCR */ @@ -154,7 +153,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) wbinvd(); wrmsr(MSR_K6_WHCR, l, h); local_irq_restore(flags); - printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n", + pr_info("Enabling old style K6 write allocation for %d Mb\n", mbytes); } return; @@ -175,7 +174,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) wbinvd(); wrmsr(MSR_K6_WHCR, l, h); local_irq_restore(flags); - printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n", + pr_info("Enabling new style K6 write allocation for %d Mb\n", mbytes); } @@ -202,7 +201,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) */ if (c->x86_model >= 6 && c->x86_model <= 10) { if (!cpu_has(c, X86_FEATURE_XMM)) { - printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); + pr_info("Enabling disabled K7/SSE Support.\n"); msr_clear_bit(MSR_K7_HWCR, 15); set_cpu_cap(c, X86_FEATURE_XMM); } @@ -216,9 +215,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { - printk(KERN_INFO - "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", - l, ((l & 0x000fffff)|0x20000000)); + pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", + l, ((l & 0x000fffff)|0x20000000)); wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h); } } @@ -485,7 +483,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { unsigned long pfn = tseg >> PAGE_SHIFT; - printk(KERN_DEBUG "tseg: %010llx\n", tseg); + pr_debug("tseg: %010llx\n", tseg); if (pfn_range_is_mapped(pfn, pfn + 1)) set_memory_4k((unsigned long)__va(tseg), 1); } @@ -500,8 +498,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) rdmsrl(MSR_K7_HWCR, val); if (!(val & BIT(24))) - printk(KERN_WARNING FW_BUG "TSC doesn't count " - "with P0 frequency!\n"); + pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n"); } } diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c index 04f0fe5af83ec..a972ac4c7e7df 100644 --- a/arch/x86/kernel/cpu/bugs_64.c +++ b/arch/x86/kernel/cpu/bugs_64.c @@ -15,7 +15,7 @@ void __init check_bugs(void) { identify_boot_cpu(); #if !defined(CONFIG_SMP) - printk(KERN_INFO "CPU: "); + pr_info("CPU: "); print_cpu_info(&boot_cpu_data); #endif alternative_instructions(); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index ae20be6e483c7..1661d8ec92805 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,7 +1,7 @@ #include #include -#include +#include #include #include #include @@ -29,7 +29,7 @@ static void init_c3(struct cpuinfo_x86 *c) rdmsr(MSR_VIA_FCR, lo, hi); lo |= ACE_FCR; /* enable ACE unit */ wrmsr(MSR_VIA_FCR, lo, hi); - printk(KERN_INFO "CPU: Enabled ACE h/w crypto\n"); + pr_info("CPU: Enabled ACE h/w crypto\n"); } /* enable RNG unit, if present and disabled */ @@ -37,7 +37,7 @@ static void init_c3(struct cpuinfo_x86 *c) rdmsr(MSR_VIA_RNG, lo, hi); lo |= RNG_ENABLE; /* enable RNG unit */ wrmsr(MSR_VIA_RNG, lo, hi); - printk(KERN_INFO "CPU: Enabled h/w RNG\n"); + pr_info("CPU: Enabled h/w RNG\n"); } /* store Centaur Extended Feature Flags as @@ -130,7 +130,7 @@ static void init_centaur(struct cpuinfo_x86 *c) name = "C6"; fcr_set = ECX8|DSMC|EDCTLB|EMMX|ERETSTK; fcr_clr = DPDC; - printk(KERN_NOTICE "Disabling bugged TSC.\n"); + pr_notice("Disabling bugged TSC.\n"); clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: @@ -163,11 +163,11 @@ static void init_centaur(struct cpuinfo_x86 *c) newlo = (lo|fcr_set) & (~fcr_clr); if (newlo != lo) { - printk(KERN_INFO "Centaur FCR was 0x%X now 0x%X\n", + pr_info("Centaur FCR was 0x%X now 0x%X\n", lo, newlo); wrmsr(MSR_IDT_FCR1, newlo, hi); } else { - printk(KERN_INFO "Centaur FCR is 0x%X\n", lo); + pr_info("Centaur FCR is 0x%X\n", lo); } /* Emulate MTRRs using Centaur's MCR. */ set_cpu_cap(c, X86_FEATURE_CENTAUR_MCR); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 37830de8f60a8..249461f958516 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -162,6 +162,22 @@ static int __init x86_mpx_setup(char *s) } __setup("nompx", x86_mpx_setup); +static int __init x86_noinvpcid_setup(char *s) +{ + /* noinvpcid doesn't accept parameters */ + if (s) + return -EINVAL; + + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_INVPCID)) + return 0; + + setup_clear_cpu_cap(X86_FEATURE_INVPCID); + pr_info("noinvpcid: INVPCID feature disabled\n"); + return 0; +} +early_param("noinvpcid", x86_noinvpcid_setup); + #ifdef CONFIG_X86_32 static int cachesize_override = -1; static int disable_x86_serial_nr = 1; @@ -228,7 +244,7 @@ static void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) lo |= 0x200000; wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi); - printk(KERN_NOTICE "CPU serial number disabled.\n"); + pr_notice("CPU serial number disabled.\n"); clear_cpu_cap(c, X86_FEATURE_PN); /* Disabling the serial number may affect the cpuid level */ @@ -329,9 +345,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) if (!warn) continue; - printk(KERN_WARNING - "CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n", - x86_cap_flag(df->feature), df->level); + pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n", + x86_cap_flag(df->feature), df->level); } } @@ -510,7 +525,7 @@ void detect_ht(struct cpuinfo_x86 *c) smp_num_siblings = (ebx & 0xff0000) >> 16; if (smp_num_siblings == 1) { - printk_once(KERN_INFO "CPU0: Hyper-Threading is disabled\n"); + pr_info_once("CPU0: Hyper-Threading is disabled\n"); goto out; } @@ -531,10 +546,10 @@ void detect_ht(struct cpuinfo_x86 *c) out: if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) { - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - printk(KERN_INFO "CPU: Processor Core ID: %d\n", - c->cpu_core_id); + pr_info("CPU: Physical Processor ID: %d\n", + c->phys_proc_id); + pr_info("CPU: Processor Core ID: %d\n", + c->cpu_core_id); printed = 1; } #endif @@ -559,9 +574,8 @@ static void get_cpu_vendor(struct cpuinfo_x86 *c) } } - printk_once(KERN_ERR - "CPU: vendor_id '%s' unknown, using generic init.\n" \ - "CPU: Your system may be unstable.\n", v); + pr_err_once("CPU: vendor_id '%s' unknown, using generic init.\n" \ + "CPU: Your system may be unstable.\n", v); c->x86_vendor = X86_VENDOR_UNKNOWN; this_cpu = &default_cpu; @@ -760,7 +774,7 @@ void __init early_cpu_init(void) int count = 0; #ifdef CONFIG_PROCESSOR_SELECT - printk(KERN_INFO "KERNEL supported cpus:\n"); + pr_info("KERNEL supported cpus:\n"); #endif for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { @@ -778,7 +792,7 @@ void __init early_cpu_init(void) for (j = 0; j < 2; j++) { if (!cpudev->c_ident[j]) continue; - printk(KERN_INFO " %s %s\n", cpudev->c_vendor, + pr_info(" %s %s\n", cpudev->c_vendor, cpudev->c_ident[j]); } } @@ -802,6 +816,31 @@ static void detect_nopl(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_NOPL); #else set_cpu_cap(c, X86_FEATURE_NOPL); +#endif + + /* + * ESPFIX is a strange bug. All real CPUs have it. Paravirt + * systems that run Linux at CPL > 0 may or may not have the + * issue, but, even if they have the issue, there's absolutely + * nothing we can do about it because we can't use the real IRET + * instruction. + * + * NB: For the time being, only 32-bit kernels support + * X86_BUG_ESPFIX as such. 64-bit kernels directly choose + * whether to apply espfix using paravirt hooks. If any + * non-paravirt system ever shows up that does *not* have the + * ESPFIX issue, we can change this. + */ +#ifdef CONFIG_X86_32 +#ifdef CONFIG_PARAVIRT + do { + extern void native_iret(void); + if (pv_cpu_ops.iret == native_iret) + set_cpu_bug(c, X86_BUG_ESPFIX); + } while (0); +#else + set_cpu_bug(c, X86_BUG_ESPFIX); +#endif #endif } @@ -977,6 +1016,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif + /* The boot/hotplug time assigment got cleared, restore it */ + c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id); } /* @@ -1061,7 +1102,7 @@ static void __print_cpu_msr(void) for (index = index_min; index < index_max; index++) { if (rdmsrl_safe(index, &val)) continue; - printk(KERN_INFO " MSR%08x: %016llx\n", index, val); + pr_info(" MSR%08x: %016llx\n", index, val); } } } @@ -1100,19 +1141,19 @@ void print_cpu_info(struct cpuinfo_x86 *c) } if (vendor && !strstr(c->x86_model_id, vendor)) - printk(KERN_CONT "%s ", vendor); + pr_cont("%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", c->x86_model_id); + pr_cont("%s", c->x86_model_id); else - printk(KERN_CONT "%d86", c->x86); + pr_cont("%d86", c->x86); - printk(KERN_CONT " (family: 0x%x, model: 0x%x", c->x86, c->x86_model); + pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT ", stepping: 0x%x)\n", c->x86_mask); + pr_cont(", stepping: 0x%x)\n", c->x86_mask); else - printk(KERN_CONT ")\n"); + pr_cont(")\n"); print_cpu_msr(c); } @@ -1438,7 +1479,7 @@ void cpu_init(void) show_ucode_info_early(); - printk(KERN_INFO "Initializing CPU#%d\n", cpu); + pr_info("Initializing CPU#%d\n", cpu); if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || @@ -1475,20 +1516,6 @@ void cpu_init(void) } #endif -#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS -void warn_pre_alternatives(void) -{ - WARN(1, "You're using static_cpu_has before alternatives have run!\n"); -} -EXPORT_SYMBOL_GPL(warn_pre_alternatives); -#endif - -inline bool __static_cpu_has_safe(u16 bit) -{ - return boot_cpu_has(bit); -} -EXPORT_SYMBOL_GPL(__static_cpu_has_safe); - static void bsp_resume(void) { if (this_cpu->c_bsp_resume) diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index aaf152e796373..6adef9cac23ee 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "cpu.h" @@ -103,7 +104,7 @@ static void check_cx686_slop(struct cpuinfo_x86 *c) local_irq_restore(flags); if (ccr5 & 2) { /* possible wrong calibration done */ - printk(KERN_INFO "Recalibrating delay loop with SLOP bit reset\n"); + pr_info("Recalibrating delay loop with SLOP bit reset\n"); calibrate_delay(); c->loops_per_jiffy = loops_per_jiffy; } @@ -115,7 +116,7 @@ static void set_cx86_reorder(void) { u8 ccr3; - printk(KERN_INFO "Enable Memory access reorder on Cyrix/NSC processor.\n"); + pr_info("Enable Memory access reorder on Cyrix/NSC processor.\n"); ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ @@ -128,7 +129,7 @@ static void set_cx86_reorder(void) static void set_cx86_memwb(void) { - printk(KERN_INFO "Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); + pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); /* CCR2 bit 2: unlock NW bit */ setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04); @@ -268,7 +269,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) * VSA1 we work around however. */ - printk(KERN_INFO "Working around Cyrix MediaGX virtual DMA bugs.\n"); + pr_info("Working around Cyrix MediaGX virtual DMA bugs.\n"); isa_dma_bridge_buggy = 2; /* We do this before the PCI layer is running. However we @@ -426,7 +427,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c) if (dir0 == 5 || dir0 == 3) { unsigned char ccr3; unsigned long flags; - printk(KERN_INFO "Enabling CPUID on Cyrix processor.\n"); + pr_info("Enabling CPUID on Cyrix processor.\n"); local_irq_save(flags); ccr3 = getCx86(CX86_CCR3); /* enable MAPEN */ diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index d820d8eae96be..73d391ae452f8 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -56,7 +56,7 @@ detect_hypervisor_vendor(void) } if (max_pri) - printk(KERN_INFO "Hypervisor detected: %s\n", x86_hyper->name); + pr_info("Hypervisor detected: %s\n", x86_hyper->name); } void init_hypervisor(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 565648bc1a0ae..1f7fdb91a818b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include #include @@ -61,7 +61,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && c->microcode < 0x20e) { - printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n"); + pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); } @@ -140,7 +140,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) { - printk(KERN_INFO "Disabled fast string operations\n"); + pr_info("Disabled fast string operations\n"); setup_clear_cpu_cap(X86_FEATURE_REP_GOOD); setup_clear_cpu_cap(X86_FEATURE_ERMS); } @@ -160,6 +160,19 @@ static void early_init_intel(struct cpuinfo_x86 *c) pr_info("Disabling PGE capability bit\n"); setup_clear_cpu_cap(X86_FEATURE_PGE); } + + if (c->cpuid_level >= 0x00000001) { + u32 eax, ebx, ecx, edx; + + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); + /* + * If HTT (EDX[28]) is set EBX[16:23] contain the number of + * apicids which are reserved per package. Store the resulting + * shift value for the package management code. + */ + if (edx & (1U << 28)) + c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); + } } #ifdef CONFIG_X86_32 @@ -176,7 +189,7 @@ int ppro_with_ram_bug(void) boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_mask < 8) { - printk(KERN_INFO "Pentium Pro with Errata#50 detected. Taking evasive action.\n"); + pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } return 0; @@ -225,7 +238,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_F00F); if (!f00f_workaround_enabled) { - printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n"); + pr_notice("Intel Pentium with F0 0F bug - workaround enabled.\n"); f00f_workaround_enabled = 1; } } @@ -244,7 +257,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Forcefully enable PAE if kernel parameter "forcepae" is present. */ if (forcepae) { - printk(KERN_WARNING "PAE forced!\n"); + pr_warn("PAE forced!\n"); set_cpu_cap(c, X86_FEATURE_PAE); add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); } diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 0b6c52388cf48..de6626c18e427 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -14,7 +14,7 @@ #include #include -#include +#include #include #include @@ -444,7 +444,7 @@ static ssize_t store_cache_disable(struct cacheinfo *this_leaf, err = amd_set_l3_disable_slot(nb, cpu, slot, val); if (err) { if (err == -EEXIST) - pr_warning("L3 slot %d in use/index already disabled!\n", + pr_warn("L3 slot %d in use/index already disabled!\n", slot); return err; } diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index afa9f0d487ea0..fbb5e90557a52 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -1,5 +1,5 @@ #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 4cfba4371a71f..517619ea6498b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -115,7 +115,7 @@ static int raise_local(void) int cpu = m->extcpu; if (m->inject_flags & MCJ_EXCEPTION) { - printk(KERN_INFO "Triggering MCE exception on CPU %d\n", cpu); + pr_info("Triggering MCE exception on CPU %d\n", cpu); switch (context) { case MCJ_CTX_IRQ: /* @@ -128,15 +128,15 @@ static int raise_local(void) raise_exception(m, NULL); break; default: - printk(KERN_INFO "Invalid MCE context\n"); + pr_info("Invalid MCE context\n"); ret = -EINVAL; } - printk(KERN_INFO "MCE exception done on CPU %d\n", cpu); + pr_info("MCE exception done on CPU %d\n", cpu); } else if (m->status) { - printk(KERN_INFO "Starting machine check poll CPU %d\n", cpu); + pr_info("Starting machine check poll CPU %d\n", cpu); raise_poll(m); mce_notify_irq(); - printk(KERN_INFO "Machine check poll done on CPU %d\n", cpu); + pr_info("Machine check poll done on CPU %d\n", cpu); } else m->finished = 0; @@ -183,8 +183,7 @@ static void raise_mce(struct mce *m) start = jiffies; while (!cpumask_empty(mce_inject_cpumask)) { if (!time_before(jiffies, start + 2*HZ)) { - printk(KERN_ERR - "Timeout waiting for mce inject %lx\n", + pr_err("Timeout waiting for mce inject %lx\n", *cpumask_bits(mce_inject_cpumask)); break; } @@ -241,7 +240,7 @@ static int inject_init(void) { if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) return -ENOMEM; - printk(KERN_INFO "Machine check injector initialized\n"); + pr_info("Machine check injector initialized\n"); register_mce_write_callback(mce_write); register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify"); diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 9c682c222071d..5119766d98892 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "mce-internal.h" @@ -29,7 +30,7 @@ * panic situations) */ -enum context { IN_KERNEL = 1, IN_USER = 2 }; +enum context { IN_KERNEL = 1, IN_USER = 2, IN_KERNEL_RECOV = 3 }; enum ser { SER_REQUIRED = 1, NO_SER = 2 }; enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 }; @@ -48,6 +49,7 @@ static struct severity { #define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c } #define KERNEL .context = IN_KERNEL #define USER .context = IN_USER +#define KERNEL_RECOV .context = IN_KERNEL_RECOV #define SER .ser = SER_REQUIRED #define NOSER .ser = NO_SER #define EXCP .excp = EXCP_CONTEXT @@ -86,6 +88,10 @@ static struct severity { PANIC, "In kernel and no restart IP", EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) ), + MCESEV( + PANIC, "In kernel and no restart IP", + EXCP, KERNEL_RECOV, MCGMASK(MCG_STATUS_RIPV, 0) + ), MCESEV( DEFERRED, "Deferred error", NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED) @@ -122,6 +128,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR, MCI_UC_SAR|MCI_ADDR), MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV) ), + MCESEV( + AR, "Action required: data load in error recoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL_RECOV + ), MCESEV( AR, "Action required: data load error in a user process", SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), @@ -170,6 +181,9 @@ static struct severity { ) /* always matches. keep at end */ }; +#define mc_recoverable(mcg) (((mcg) & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) == \ + (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) + /* * If mcgstatus indicated that ip/cs on the stack were * no good, then "m->cs" will be zero and we will have @@ -183,7 +197,11 @@ static struct severity { */ static int error_context(struct mce *m) { - return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; + if ((m->cs & 3) == 3) + return IN_USER; + if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip)) + return IN_KERNEL_RECOV; + return IN_KERNEL; } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index a006f4cd792b1..f0c921b03e424 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -961,6 +961,20 @@ static void mce_clear_state(unsigned long *toclear) } } +static int do_memory_failure(struct mce *m) +{ + int flags = MF_ACTION_REQUIRED; + int ret; + + pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr); + if (!(m->mcgstatus & MCG_STATUS_RIPV)) + flags |= MF_MUST_KILL; + ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags); + if (ret) + pr_err("Memory error not recovered"); + return ret; +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -998,8 +1012,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - u64 recover_paddr = ~0ull; - int flags = MF_ACTION_REQUIRED; int lmce = 0; /* If this CPU is offline, just bail out. */ @@ -1136,22 +1148,13 @@ void do_machine_check(struct pt_regs *regs, long error_code) } /* - * At insane "tolerant" levels we take no action. Otherwise - * we only die if we have no other choice. For less serious - * issues we try to recover, or limit damage to the current - * process. + * If tolerant is at an insane level we drop requests to kill + * processes and continue even when there is no way out. */ - if (cfg->tolerant < 3) { - if (no_way_out) - mce_panic("Fatal machine check on current CPU", &m, msg); - if (worst == MCE_AR_SEVERITY) { - recover_paddr = m.addr; - if (!(m.mcgstatus & MCG_STATUS_RIPV)) - flags |= MF_MUST_KILL; - } else if (kill_it) { - force_sig(SIGBUS, current); - } - } + if (cfg->tolerant == 3) + kill_it = 0; + else if (no_way_out) + mce_panic("Fatal machine check on current CPU", &m, msg); if (worst > 0) mce_report_event(regs); @@ -1159,25 +1162,24 @@ void do_machine_check(struct pt_regs *regs, long error_code) out: sync_core(); - if (recover_paddr == ~0ull) - goto done; + if (worst != MCE_AR_SEVERITY && !kill_it) + goto out_ist; - pr_err("Uncorrected hardware memory error in user-access at %llx", - recover_paddr); - /* - * We must call memory_failure() here even if the current process is - * doomed. We still need to mark the page as poisoned and alert any - * other users of the page. - */ - ist_begin_non_atomic(regs); - local_irq_enable(); - if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) { - pr_err("Memory error not recovered"); - force_sig(SIGBUS, current); + /* Fault was in user mode and we need to take some action */ + if ((m.cs & 3) == 3) { + ist_begin_non_atomic(regs); + local_irq_enable(); + + if (kill_it || do_memory_failure(&m)) + force_sig(SIGBUS, current); + local_irq_disable(); + ist_end_non_atomic(); + } else { + if (!fixup_exception(regs, X86_TRAP_MC)) + mce_panic("Failed kernel mode recovery", &m, NULL); } - local_irq_disable(); - ist_end_non_atomic(); -done: + +out_ist: ist_exit(regs); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -1576,6 +1578,17 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model == 45) quirk_no_way_out = quirk_sandybridge_ifu; + /* + * MCG_CAP.MCG_SER_P is necessary but not sufficient to know + * whether this processor will actually generate recoverable + * machine checks. Check to see if this is an E7 model Xeon. + * We can't do a model number check because E5 and E7 use the + * same model number. E5 doesn't support recovery, E7 does. + */ + if (mca_cfg.recovery || (mca_cfg.ser && + !strncmp(c->x86_model_id, + "Intel(R) Xeon(R) CPU E7-", 24))) + set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY); } if (cfg->monarch_timeout < 0) cfg->monarch_timeout = 0; @@ -1617,10 +1630,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) case X86_VENDOR_AMD: { u32 ebx = cpuid_ebx(0x80000007); - mce_amd_feature_init(c); mce_flags.overflow_recov = !!(ebx & BIT(0)); mce_flags.succor = !!(ebx & BIT(1)); mce_flags.smca = !!(ebx & BIT(3)); + mce_amd_feature_init(c); break; } @@ -2028,6 +2041,8 @@ static int __init mcheck_enable(char *str) cfg->bootlog = (str[0] == 'b'); else if (!strcmp(str, "bios_cmci_threshold")) cfg->bios_cmci_threshold = true; + else if (!strcmp(str, "recovery")) + cfg->recovery = true; else if (isdigit(str[0])) { if (get_option(&str, &cfg->tolerant) == 2) get_option(&str, &(cfg->monarch_timeout)); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index e99b15077e946..9d656fd436efd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -1,5 +1,5 @@ /* - * (c) 2005-2015 Advanced Micro Devices, Inc. + * (c) 2005-2016 Advanced Micro Devices, Inc. * Your use of this code is subject to the terms and conditions of the * GNU general public license version 2. See "COPYING" or * http://www.gnu.org/licenses/gpl.html @@ -28,7 +28,7 @@ #include #include -#define NR_BLOCKS 9 +#define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 #define MASK_VALID_HI 0x80000000 @@ -49,6 +49,19 @@ #define DEF_LVT_OFF 0x2 #define DEF_INT_TYPE_APIC 0x2 +/* Scalable MCA: */ + +/* Threshold LVT offset is at MSR0xC0000410[15:12] */ +#define SMCA_THR_LVT_OFF 0xF000 + +/* + * OS is required to set the MCAX bit to acknowledge that it is now using the + * new MSR ranges and new registers under each bank. It also means that the OS + * will configure deferred errors in the new MCx_CONFIG register. If the bit is + * not set, uncorrectable errors will cause a system panic. + */ +#define SMCA_MCAX_EN_OFF 0x1 + static const char * const th_names[] = { "load_store", "insn_fetch", @@ -58,6 +71,35 @@ static const char * const th_names[] = { "execution_unit", }; +/* Define HWID to IP type mappings for Scalable MCA */ +struct amd_hwid amd_hwids[] = { + [SMCA_F17H_CORE] = { "f17h_core", 0xB0 }, + [SMCA_DF] = { "data_fabric", 0x2E }, + [SMCA_UMC] = { "umc", 0x96 }, + [SMCA_PB] = { "param_block", 0x5 }, + [SMCA_PSP] = { "psp", 0xFF }, + [SMCA_SMU] = { "smu", 0x1 }, +}; +EXPORT_SYMBOL_GPL(amd_hwids); + +const char * const amd_core_mcablock_names[] = { + [SMCA_LS] = "load_store", + [SMCA_IF] = "insn_fetch", + [SMCA_L2_CACHE] = "l2_cache", + [SMCA_DE] = "decode_unit", + [RES] = "", + [SMCA_EX] = "execution_unit", + [SMCA_FP] = "floating_point", + [SMCA_L3_CACHE] = "l3_cache", +}; +EXPORT_SYMBOL_GPL(amd_core_mcablock_names); + +const char * const amd_df_mcablock_names[] = { + [SMCA_CS] = "coherent_slave", + [SMCA_PIE] = "pie", +}; +EXPORT_SYMBOL_GPL(amd_df_mcablock_names); + static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ @@ -84,6 +126,13 @@ struct thresh_restart { static inline bool is_shared_bank(int bank) { + /* + * Scalable MCA provides for only one core to have access to the MSRs of + * a shared bank. + */ + if (mce_flags.smca) + return false; + /* Bank 4 is for northbridge reporting and is thus shared */ return (bank == 4); } @@ -135,6 +184,14 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) } if (apic != msr) { + /* + * On SMCA CPUs, LVT offset is programmed at a different MSR, and + * the BIOS provides the value. The original field where LVT offset + * was set is reserved. Return early here: + */ + if (mce_flags.smca) + return 0; + pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d " "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, apic, b->bank, b->block, b->address, hi, lo); @@ -144,10 +201,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) return 1; }; -/* - * Called via smp_call_function_single(), must be called with correct - * cpu affinity. - */ +/* Reprogram MCx_MISC MSR behind this threshold bank. */ static void threshold_restart_bank(void *_tr) { struct thresh_restart *tr = _tr; @@ -247,27 +301,116 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) wrmsr(MSR_CU_DEF_ERR, low, high); } +static u32 get_block_address(u32 current_addr, u32 low, u32 high, + unsigned int bank, unsigned int block) +{ + u32 addr = 0, offset = 0; + + if (mce_flags.smca) { + if (!block) { + addr = MSR_AMD64_SMCA_MCx_MISC(bank); + } else { + /* + * For SMCA enabled processors, BLKPTR field of the + * first MISC register (MCx_MISC0) indicates presence of + * additional MISC register set (MISC1-4). + */ + u32 low, high; + + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) + return addr; + + if (!(low & MCI_CONFIG_MCAX)) + return addr; + + if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && + (low & MASK_BLKPTR_LO)) + addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + } + return addr; + } + + /* Fall back to method we used for older processors: */ + switch (block) { + case 0: + addr = MSR_IA32_MCx_MISC(bank); + break; + case 1: + offset = ((low & MASK_BLKPTR_LO) >> 21); + if (offset) + addr = MCG_XBLK_ADDR + offset; + break; + default: + addr = ++current_addr; + } + return addr; +} + +static int +prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, + int offset, u32 misc_high) +{ + unsigned int cpu = smp_processor_id(); + struct threshold_block b; + int new; + + if (!block) + per_cpu(bank_map, cpu) |= (1 << bank); + + memset(&b, 0, sizeof(b)); + b.cpu = cpu; + b.bank = bank; + b.block = block; + b.address = addr; + b.interrupt_capable = lvt_interrupt_supported(bank, misc_high); + + if (!b.interrupt_capable) + goto done; + + b.interrupt_enable = 1; + + if (mce_flags.smca) { + u32 smca_low, smca_high; + u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); + + if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { + smca_high |= SMCA_MCAX_EN_OFF; + wrmsr(smca_addr, smca_low, smca_high); + } + + /* Gather LVT offset for thresholding: */ + if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) + goto out; + + new = (smca_low & SMCA_THR_LVT_OFF) >> 12; + } else { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + } + + offset = setup_APIC_mce_threshold(offset, new); + + if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) + mce_threshold_vector = amd_threshold_interrupt; + +done: + mce_threshold_block_init(&b, offset); + +out: + return offset; +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { - struct threshold_block b; - unsigned int cpu = smp_processor_id(); u32 low = 0, high = 0, address = 0; unsigned int bank, block; - int offset = -1, new; + int offset = -1; for (bank = 0; bank < mca_cfg.banks; ++bank) { for (block = 0; block < NR_BLOCKS; ++block) { - if (block == 0) - address = MSR_IA32_MCx_MISC(bank); - else if (block == 1) { - address = (low & MASK_BLKPTR_LO) >> 21; - if (!address) - break; - - address += MCG_XBLK_ADDR; - } else - ++address; + address = get_block_address(address, low, high, bank, block); + if (!address) + break; if (rdmsr_safe(address, &low, &high)) break; @@ -279,29 +422,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) (high & MASK_LOCKED_HI)) continue; - if (!block) - per_cpu(bank_map, cpu) |= (1 << bank); - - memset(&b, 0, sizeof(b)); - b.cpu = cpu; - b.bank = bank; - b.block = block; - b.address = address; - b.interrupt_capable = lvt_interrupt_supported(bank, high); - - if (!b.interrupt_capable) - goto init; - - b.interrupt_enable = 1; - new = (high & MASK_LVTOFF_HI) >> 20; - offset = setup_APIC_mce_threshold(offset, new); - - if ((offset == new) && - (mce_threshold_vector != amd_threshold_interrupt)) - mce_threshold_vector = amd_threshold_interrupt; - -init: - mce_threshold_block_init(&b, offset); + offset = prepare_threshold_block(bank, block, address, offset, high); } } @@ -394,16 +515,9 @@ static void amd_threshold_interrupt(void) if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; for (block = 0; block < NR_BLOCKS; ++block) { - if (block == 0) { - address = MSR_IA32_MCx_MISC(bank); - } else if (block == 1) { - address = (low & MASK_BLKPTR_LO) >> 21; - if (!address) - break; - address += MCG_XBLK_ADDR; - } else { - ++address; - } + address = get_block_address(address, low, high, bank, block); + if (!address) + break; if (rdmsr_safe(address, &low, &high)) break; @@ -623,16 +737,11 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, if (err) goto out_free; recurse: - if (!block) { - address = (low & MASK_BLKPTR_LO) >> 21; - if (!address) - return 0; - address += MCG_XBLK_ADDR; - } else { - ++address; - } + address = get_block_address(address, low, high, bank, ++block); + if (!address) + return 0; - err = allocate_threshold_blocks(cpu, bank, ++block, address); + err = allocate_threshold_blocks(cpu, bank, block, address); if (err) goto out_free; diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 12402e10aeffd..2a0717bf80337 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -26,14 +26,12 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); - printk(KERN_EMERG - "CPU#%d: Machine Check Exception: 0x%8X (type 0x%8X).\n", - smp_processor_id(), loaddr, lotype); + pr_emerg("CPU#%d: Machine Check Exception: 0x%8X (type 0x%8X).\n", + smp_processor_id(), loaddr, lotype); if (lotype & (1<<5)) { - printk(KERN_EMERG - "CPU#%d: Possible thermal failure (CPU on fire ?).\n", - smp_processor_id()); + pr_emerg("CPU#%d: Possible thermal failure (CPU on fire ?).\n", + smp_processor_id()); } add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); @@ -61,12 +59,10 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c) /* Read registers before enabling: */ rdmsr(MSR_IA32_P5_MC_ADDR, l, h); rdmsr(MSR_IA32_P5_MC_TYPE, l, h); - printk(KERN_INFO - "Intel old style machine check architecture supported.\n"); + pr_info("Intel old style machine check architecture supported.\n"); /* Enable MCE: */ cr4_set_bits(X86_CR4_MCE); - printk(KERN_INFO - "Intel old style machine check reporting enabled on CPU#%d.\n", - smp_processor_id()); + pr_info("Intel old style machine check reporting enabled on CPU#%d.\n", + smp_processor_id()); } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 2c5aaf8c2e2f3..0b445c2ff735d 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -190,7 +190,7 @@ static int therm_throt_process(bool new_event, int event, int level) /* if we just entered the thermal event */ if (new_event) { if (event == THERMAL_THROTTLING_EVENT) - printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); @@ -198,8 +198,7 @@ static int therm_throt_process(bool new_event, int event, int level) } if (old_event) { if (event == THERMAL_THROTTLING_EVENT) - printk(KERN_INFO "CPU%d: %s temperature/speed normal\n", - this_cpu, + pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); return 1; } @@ -417,8 +416,8 @@ static void intel_thermal_interrupt(void) static void unexpected_thermal_interrupt(void) { - printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n", - smp_processor_id()); + pr_err("CPU%d: Unexpected LVT thermal interrupt!\n", + smp_processor_id()); } static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; @@ -499,7 +498,7 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { if (system_state == SYSTEM_BOOTING) - printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu); + pr_debug("CPU%d: Thermal monitoring handled by SMI\n", cpu); return; } @@ -557,8 +556,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c) l = apic_read(APIC_LVTTHMR); apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - printk_once(KERN_INFO "CPU0: Thermal monitoring enabled (%s)\n", - tm2 ? "TM2" : "TM1"); + pr_info_once("CPU0: Thermal monitoring enabled (%s)\n", + tm2 ? "TM2" : "TM1"); /* enable thermal throttle processing */ atomic_set(&therm_throt_en, 1); diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index 7245980186eea..fcf9ae9384f4c 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -12,8 +12,8 @@ static void default_threshold_interrupt(void) { - printk(KERN_ERR "Unexpected threshold interrupt at vector %x\n", - THRESHOLD_APIC_VECTOR); + pr_err("Unexpected threshold interrupt at vector %x\n", + THRESHOLD_APIC_VECTOR); } void (*mce_threshold_vector)(void) = default_threshold_interrupt; diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 01dd8702880b7..c6a722e1d0114 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -17,7 +17,7 @@ static void winchip_machine_check(struct pt_regs *regs, long error_code) { ist_enter(regs); - printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); + pr_emerg("CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); ist_exit(regs); @@ -39,6 +39,5 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c) cr4_set_bits(X86_CR4_MCE); - printk(KERN_INFO - "Winchip machine check reporting enabled on CPU#0.\n"); + pr_info("Winchip machine check reporting enabled on CPU#0.\n"); } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 2233f8a766156..8581963894c79 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -431,10 +431,6 @@ int __init save_microcode_in_initrd_amd(void) else container = cont_va; - if (ucode_new_rev) - pr_info("microcode: updated early to new patch_level=0x%08x\n", - ucode_new_rev); - eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); @@ -469,8 +465,7 @@ void reload_ucode_amd(void) if (mc && rev < mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { ucode_new_rev = mc->hdr.patch_id; - pr_info("microcode: reload patch_level=0x%08x\n", - ucode_new_rev); + pr_info("reload patch_level=0x%08x\n", ucode_new_rev); } } } @@ -793,15 +788,13 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover) return -EINVAL; } - patch->data = kzalloc(patch_size, GFP_KERNEL); + patch->data = kmemdup(fw + SECTION_HDR_SIZE, patch_size, GFP_KERNEL); if (!patch->data) { pr_err("Patch data allocation failure.\n"); kfree(patch); return -EINVAL; } - /* All looks ok, copy patch... */ - memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size); INIT_LIST_HEAD(&patch->plist); patch->patch_id = mc_hdr->patch_id; patch->equiv_cpu = proc_id; @@ -953,10 +946,14 @@ struct microcode_ops * __init init_amd_microcode(void) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { - pr_warning("AMD CPU family 0x%x not supported\n", c->x86); + pr_warn("AMD CPU family 0x%x not supported\n", c->x86); return NULL; } + if (ucode_new_rev) + pr_info_once("microcode updated early to new patch_level=0x%08x\n", + ucode_new_rev); + return µcode_amd_ops; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index faec7120c5085..ac360bfbbdb6d 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -43,16 +43,8 @@ #define MICROCODE_VERSION "2.01" static struct microcode_ops *microcode_ops; - static bool dis_ucode_ldr; -static int __init disable_loader(char *str) -{ - dis_ucode_ldr = true; - return 1; -} -__setup("dis_ucode_ldr", disable_loader); - /* * Synchronization. * @@ -81,15 +73,16 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { + static const char *__dis_opt_str = "dis_ucode_ldr"; + #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); - const char *opt = "dis_ucode_ldr"; - const char *option = (const char *)__pa_nodebug(opt); + const char *option = (const char *)__pa_nodebug(__dis_opt_str); bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); #else /* CONFIG_X86_64 */ const char *cmdline = boot_command_line; - const char *option = "dis_ucode_ldr"; + const char *option = __dis_opt_str; bool *res = &dis_ucode_ldr; #endif @@ -479,7 +472,7 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) enum ucode_state ustate; struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - if (uci && uci->valid) + if (uci->valid) return UCODE_OK; if (collect_cpu_info(cpu)) @@ -630,7 +623,7 @@ int __init microcode_init(void) struct cpuinfo_x86 *c = &boot_cpu_data; int error; - if (paravirt_enabled() || dis_ucode_ldr) + if (dis_ucode_ldr) return -EINVAL; if (c->x86_vendor == X86_VENDOR_INTEL) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ee81c544ee0da..cbb3cf09b0652 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -39,9 +39,15 @@ #include #include -static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; +/* + * Temporary microcode blobs pointers storage. We note here the pointers to + * microcode blobs we've got from whatever storage (detached initrd, builtin). + * Later on, we put those into final storage mc_saved_data.mc_saved. + */ +static unsigned long mc_tmp_ptrs[MAX_UCODE_COUNT]; + static struct mc_saved_data { - unsigned int mc_saved_count; + unsigned int num_saved; struct microcode_intel **mc_saved; } mc_saved_data; @@ -78,53 +84,50 @@ load_microcode_early(struct microcode_intel **saved, } static inline void -copy_initrd_ptrs(struct microcode_intel **mc_saved, unsigned long *initrd, - unsigned long off, int num_saved) +copy_ptrs(struct microcode_intel **mc_saved, unsigned long *mc_ptrs, + unsigned long off, int num_saved) { int i; for (i = 0; i < num_saved; i++) - mc_saved[i] = (struct microcode_intel *)(initrd[i] + off); + mc_saved[i] = (struct microcode_intel *)(mc_ptrs[i] + off); } #ifdef CONFIG_X86_32 static void -microcode_phys(struct microcode_intel **mc_saved_tmp, - struct mc_saved_data *mc_saved_data) +microcode_phys(struct microcode_intel **mc_saved_tmp, struct mc_saved_data *mcs) { int i; struct microcode_intel ***mc_saved; - mc_saved = (struct microcode_intel ***) - __pa_nodebug(&mc_saved_data->mc_saved); - for (i = 0; i < mc_saved_data->mc_saved_count; i++) { + mc_saved = (struct microcode_intel ***)__pa_nodebug(&mcs->mc_saved); + + for (i = 0; i < mcs->num_saved; i++) { struct microcode_intel *p; - p = *(struct microcode_intel **) - __pa_nodebug(mc_saved_data->mc_saved + i); + p = *(struct microcode_intel **)__pa_nodebug(mcs->mc_saved + i); mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p); } } #endif static enum ucode_state -load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, - unsigned long initrd_start, struct ucode_cpu_info *uci) +load_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs, + unsigned long offset, struct ucode_cpu_info *uci) { struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int count = mc_saved_data->mc_saved_count; + unsigned int count = mcs->num_saved; - if (!mc_saved_data->mc_saved) { - copy_initrd_ptrs(mc_saved_tmp, initrd, initrd_start, count); + if (!mcs->mc_saved) { + copy_ptrs(mc_saved_tmp, mc_ptrs, offset, count); return load_microcode_early(mc_saved_tmp, count, uci); } else { #ifdef CONFIG_X86_32 - microcode_phys(mc_saved_tmp, mc_saved_data); + microcode_phys(mc_saved_tmp, mcs); return load_microcode_early(mc_saved_tmp, count, uci); #else - return load_microcode_early(mc_saved_data->mc_saved, - count, uci); + return load_microcode_early(mcs->mc_saved, count, uci); #endif } } @@ -175,25 +178,25 @@ matching_model_microcode(struct microcode_header_intel *mc_header, } static int -save_microcode(struct mc_saved_data *mc_saved_data, +save_microcode(struct mc_saved_data *mcs, struct microcode_intel **mc_saved_src, - unsigned int mc_saved_count) + unsigned int num_saved) { int i, j; struct microcode_intel **saved_ptr; int ret; - if (!mc_saved_count) + if (!num_saved) return -EINVAL; /* * Copy new microcode data. */ - saved_ptr = kcalloc(mc_saved_count, sizeof(struct microcode_intel *), GFP_KERNEL); + saved_ptr = kcalloc(num_saved, sizeof(struct microcode_intel *), GFP_KERNEL); if (!saved_ptr) return -ENOMEM; - for (i = 0; i < mc_saved_count; i++) { + for (i = 0; i < num_saved; i++) { struct microcode_header_intel *mc_hdr; struct microcode_intel *mc; unsigned long size; @@ -207,20 +210,18 @@ save_microcode(struct mc_saved_data *mc_saved_data, mc_hdr = &mc->hdr; size = get_totalsize(mc_hdr); - saved_ptr[i] = kmalloc(size, GFP_KERNEL); + saved_ptr[i] = kmemdup(mc, size, GFP_KERNEL); if (!saved_ptr[i]) { ret = -ENOMEM; goto err; } - - memcpy(saved_ptr[i], mc, size); } /* * Point to newly saved microcode. */ - mc_saved_data->mc_saved = saved_ptr; - mc_saved_data->mc_saved_count = mc_saved_count; + mcs->mc_saved = saved_ptr; + mcs->num_saved = num_saved; return 0; @@ -284,22 +285,20 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved, * BSP can stay in the platform. */ static enum ucode_state __init -get_matching_model_microcode(int cpu, unsigned long start, - void *data, size_t size, - struct mc_saved_data *mc_saved_data, - unsigned long *mc_saved_in_initrd, +get_matching_model_microcode(unsigned long start, void *data, size_t size, + struct mc_saved_data *mcs, unsigned long *mc_ptrs, struct ucode_cpu_info *uci) { - u8 *ucode_ptr = data; - unsigned int leftover = size; + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + struct microcode_header_intel *mc_header; + unsigned int num_saved = mcs->num_saved; enum ucode_state state = UCODE_OK; + unsigned int leftover = size; + u8 *ucode_ptr = data; unsigned int mc_size; - struct microcode_header_intel *mc_header; - struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int mc_saved_count = mc_saved_data->mc_saved_count; int i; - while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { + while (leftover && num_saved < ARRAY_SIZE(mc_saved_tmp)) { if (leftover < sizeof(mc_header)) break; @@ -318,32 +317,31 @@ get_matching_model_microcode(int cpu, unsigned long start, * the platform, we need to find and save microcode patches * with the same family and model as the BSP. */ - if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != - UCODE_OK) { + if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != UCODE_OK) { ucode_ptr += mc_size; continue; } - mc_saved_count = _save_mc(mc_saved_tmp, ucode_ptr, mc_saved_count); + num_saved = _save_mc(mc_saved_tmp, ucode_ptr, num_saved); ucode_ptr += mc_size; } if (leftover) { state = UCODE_ERROR; - goto out; + return state; } - if (mc_saved_count == 0) { + if (!num_saved) { state = UCODE_NFOUND; - goto out; + return state; } - for (i = 0; i < mc_saved_count; i++) - mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start; + for (i = 0; i < num_saved; i++) + mc_ptrs[i] = (unsigned long)mc_saved_tmp[i] - start; + + mcs->num_saved = num_saved; - mc_saved_data->mc_saved_count = mc_saved_count; -out: return state; } @@ -373,7 +371,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); csig.pf = 1 << ((val[1] >> 18) & 7); } - native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + native_wrmsrl(MSR_IA32_UCODE_REV, 0); /* As documented in the SDM: Do a CPUID 1 here */ sync_core(); @@ -396,11 +394,11 @@ static void show_saved_mc(void) unsigned int sig, pf, rev, total_size, data_size, date; struct ucode_cpu_info uci; - if (mc_saved_data.mc_saved_count == 0) { + if (!mc_saved_data.num_saved) { pr_debug("no microcode data saved.\n"); return; } - pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); + pr_debug("Total microcode saved: %d\n", mc_saved_data.num_saved); collect_cpu_info_early(&uci); @@ -409,7 +407,7 @@ static void show_saved_mc(void) rev = uci.cpu_sig.rev; pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev); - for (i = 0; i < mc_saved_data.mc_saved_count; i++) { + for (i = 0; i < mc_saved_data.num_saved; i++) { struct microcode_header_intel *mc_saved_header; struct extended_sigtable *ext_header; int ext_sigcount; @@ -465,7 +463,7 @@ int save_mc_for_early(u8 *mc) { struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; unsigned int mc_saved_count_init; - unsigned int mc_saved_count; + unsigned int num_saved; struct microcode_intel **mc_saved; int ret = 0; int i; @@ -476,23 +474,23 @@ int save_mc_for_early(u8 *mc) */ mutex_lock(&x86_cpu_microcode_mutex); - mc_saved_count_init = mc_saved_data.mc_saved_count; - mc_saved_count = mc_saved_data.mc_saved_count; + mc_saved_count_init = mc_saved_data.num_saved; + num_saved = mc_saved_data.num_saved; mc_saved = mc_saved_data.mc_saved; - if (mc_saved && mc_saved_count) + if (mc_saved && num_saved) memcpy(mc_saved_tmp, mc_saved, - mc_saved_count * sizeof(struct microcode_intel *)); + num_saved * sizeof(struct microcode_intel *)); /* * Save the microcode patch mc in mc_save_tmp structure if it's a newer * version. */ - mc_saved_count = _save_mc(mc_saved_tmp, mc, mc_saved_count); + num_saved = _save_mc(mc_saved_tmp, mc, num_saved); /* * Save the mc_save_tmp in global mc_saved_data. */ - ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count); + ret = save_microcode(&mc_saved_data, mc_saved_tmp, num_saved); if (ret) { pr_err("Cannot save microcode patch.\n"); goto out; @@ -536,7 +534,7 @@ static bool __init load_builtin_intel_microcode(struct cpio_data *cp) static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; static __init enum ucode_state -scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, +scan_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs, unsigned long start, unsigned long size, struct ucode_cpu_info *uci) { @@ -551,14 +549,18 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, cd.data = NULL; cd.size = 0; - cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) { + /* try built-in microcode if no initrd */ + if (!size) { if (!load_builtin_intel_microcode(&cd)) return UCODE_ERROR; + } else { + cd = find_cpio_data(p, (void *)start, size, &offset); + if (!cd.data) + return UCODE_ERROR; } - return get_matching_model_microcode(0, start, cd.data, cd.size, - mc_saved_data, initrd, uci); + return get_matching_model_microcode(start, cd.data, cd.size, + mcs, mc_ptrs, uci); } /* @@ -567,14 +569,11 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, static void print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) { - int cpu = smp_processor_id(); - - pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", - cpu, - uci->cpu_sig.rev, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); + pr_info_once("microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", + uci->cpu_sig.rev, + date & 0xffff, + date >> 24, + (date >> 16) & 0xff); } #ifdef CONFIG_X86_32 @@ -603,19 +602,19 @@ void show_ucode_info_early(void) */ static void print_ucode(struct ucode_cpu_info *uci) { - struct microcode_intel *mc_intel; + struct microcode_intel *mc; int *delay_ucode_info_p; int *current_mc_date_p; - mc_intel = uci->mc; - if (mc_intel == NULL) + mc = uci->mc; + if (!mc) return; delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); *delay_ucode_info_p = 1; - *current_mc_date_p = mc_intel->hdr.date; + *current_mc_date_p = mc->hdr.date; } #else @@ -630,37 +629,35 @@ static inline void flush_tlb_early(void) static inline void print_ucode(struct ucode_cpu_info *uci) { - struct microcode_intel *mc_intel; + struct microcode_intel *mc; - mc_intel = uci->mc; - if (mc_intel == NULL) + mc = uci->mc; + if (!mc) return; - print_ucode_info(uci, mc_intel->hdr.date); + print_ucode_info(uci, mc->hdr.date); } #endif static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { - struct microcode_intel *mc_intel; + struct microcode_intel *mc; unsigned int val[2]; - mc_intel = uci->mc; - if (mc_intel == NULL) + mc = uci->mc; + if (!mc) return 0; /* write microcode via MSR 0x79 */ - native_wrmsr(MSR_IA32_UCODE_WRITE, - (unsigned long) mc_intel->bits, - (unsigned long) mc_intel->bits >> 16 >> 16); - native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); + native_wrmsrl(MSR_IA32_UCODE_REV, 0); /* As documented in the SDM: Do a CPUID 1 here */ sync_core(); /* get the current revision from MSR 0x8B */ native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc_intel->hdr.rev) + if (val[1] != mc->hdr.rev) return -1; #ifdef CONFIG_X86_64 @@ -672,25 +669,26 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) if (early) print_ucode(uci); else - print_ucode_info(uci, mc_intel->hdr.date); + print_ucode_info(uci, mc->hdr.date); return 0; } /* * This function converts microcode patch offsets previously stored in - * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data. + * mc_tmp_ptrs to pointers and stores the pointers in mc_saved_data. */ int __init save_microcode_in_initrd_intel(void) { - unsigned int count = mc_saved_data.mc_saved_count; + unsigned int count = mc_saved_data.num_saved; struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; int ret = 0; - if (count == 0) + if (!count) return ret; - copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); + copy_ptrs(mc_saved, mc_tmp_ptrs, get_initrd_start(), count); + ret = save_microcode(&mc_saved_data, mc_saved, count); if (ret) pr_err("Cannot save microcode patches from initrd.\n"); @@ -701,8 +699,7 @@ int __init save_microcode_in_initrd_intel(void) } static void __init -_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, - unsigned long *initrd, +_load_ucode_intel_bsp(struct mc_saved_data *mcs, unsigned long *mc_ptrs, unsigned long start, unsigned long size) { struct ucode_cpu_info uci; @@ -710,11 +707,11 @@ _load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, collect_cpu_info_early(&uci); - ret = scan_microcode(mc_saved_data, initrd, start, size, &uci); + ret = scan_microcode(mcs, mc_ptrs, start, size, &uci); if (ret != UCODE_OK) return; - ret = load_microcode(mc_saved_data, initrd, start, &uci); + ret = load_microcode(mcs, mc_ptrs, start, &uci); if (ret != UCODE_OK) return; @@ -728,53 +725,49 @@ void __init load_ucode_intel_bsp(void) struct boot_params *p; p = (struct boot_params *)__pa_nodebug(&boot_params); - start = p->hdr.ramdisk_image; size = p->hdr.ramdisk_size; - _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), - start, size); + /* + * Set start only if we have an initrd image. We cannot use initrd_start + * because it is not set that early yet. + */ + start = (size ? p->hdr.ramdisk_image : 0); + + _load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_tmp_ptrs), + start, size); #else - start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; size = boot_params.hdr.ramdisk_size; + start = (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0); - _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); + _load_ucode_intel_bsp(&mc_saved_data, mc_tmp_ptrs, start, size); #endif } void load_ucode_intel_ap(void) { - struct mc_saved_data *mc_saved_data_p; + unsigned long *mcs_tmp_p; + struct mc_saved_data *mcs_p; struct ucode_cpu_info uci; - unsigned long *mc_saved_in_initrd_p; - unsigned long initrd_start_addr; enum ucode_state ret; #ifdef CONFIG_X86_32 - unsigned long *initrd_start_p; - mc_saved_in_initrd_p = - (unsigned long *)__pa_nodebug(mc_saved_in_initrd); - mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); - initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); + mcs_tmp_p = (unsigned long *)__pa_nodebug(mc_tmp_ptrs); + mcs_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); #else - mc_saved_data_p = &mc_saved_data; - mc_saved_in_initrd_p = mc_saved_in_initrd; - initrd_start_addr = initrd_start; + mcs_tmp_p = mc_tmp_ptrs; + mcs_p = &mc_saved_data; #endif /* * If there is no valid ucode previously saved in memory, no need to * update ucode on this AP. */ - if (mc_saved_data_p->mc_saved_count == 0) + if (!mcs_p->num_saved) return; collect_cpu_info_early(&uci); - ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, - initrd_start_addr, &uci); - + ret = load_microcode(mcs_p, mcs_tmp_p, get_initrd_start_addr(), &uci); if (ret != UCODE_OK) return; @@ -786,13 +779,13 @@ void reload_ucode_intel(void) struct ucode_cpu_info uci; enum ucode_state ret; - if (!mc_saved_data.mc_saved_count) + if (!mc_saved_data.num_saved) return; collect_cpu_info_early(&uci); ret = load_microcode_early(mc_saved_data.mc_saved, - mc_saved_data.mc_saved_count, &uci); + mc_saved_data.num_saved, &uci); if (ret != UCODE_OK) return; @@ -825,7 +818,7 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) * return 0 - no update found * return 1 - found update */ -static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) +static int get_matching_mc(struct microcode_intel *mc, int cpu) { struct cpu_signature cpu_sig; unsigned int csig, cpf, crev; @@ -836,39 +829,36 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) cpf = cpu_sig.pf; crev = cpu_sig.rev; - return has_newer_microcode(mc_intel, csig, cpf, crev); + return has_newer_microcode(mc, csig, cpf, crev); } static int apply_microcode_intel(int cpu) { - struct microcode_intel *mc_intel; + struct microcode_intel *mc; struct ucode_cpu_info *uci; + struct cpuinfo_x86 *c; unsigned int val[2]; - int cpu_num = raw_smp_processor_id(); - struct cpuinfo_x86 *c = &cpu_data(cpu_num); - - uci = ucode_cpu_info + cpu; - mc_intel = uci->mc; /* We should bind the task to the CPU */ - BUG_ON(cpu_num != cpu); + if (WARN_ON(raw_smp_processor_id() != cpu)) + return -1; - if (mc_intel == NULL) + uci = ucode_cpu_info + cpu; + mc = uci->mc; + if (!mc) return 0; /* * Microcode on this CPU could be updated earlier. Only apply the - * microcode patch in mc_intel when it is newer than the one on this + * microcode patch in mc when it is newer than the one on this * CPU. */ - if (get_matching_mc(mc_intel, cpu) == 0) + if (!get_matching_mc(mc, cpu)) return 0; /* write microcode via MSR 0x79 */ - wrmsr(MSR_IA32_UCODE_WRITE, - (unsigned long) mc_intel->bits, - (unsigned long) mc_intel->bits >> 16 >> 16); - wrmsr(MSR_IA32_UCODE_REV, 0, 0); + wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); + wrmsrl(MSR_IA32_UCODE_REV, 0); /* As documented in the SDM: Do a CPUID 1 here */ sync_core(); @@ -876,16 +866,19 @@ static int apply_microcode_intel(int cpu) /* get the current revision from MSR 0x8B */ rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc_intel->hdr.rev) { + if (val[1] != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", - cpu_num, mc_intel->hdr.rev); + cpu, mc->hdr.rev); return -1; } + pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n", - cpu_num, val[1], - mc_intel->hdr.date & 0xffff, - mc_intel->hdr.date >> 24, - (mc_intel->hdr.date >> 16) & 0xff); + cpu, val[1], + mc->hdr.date & 0xffff, + mc->hdr.date >> 24, + (mc->hdr.date >> 16) & 0xff); + + c = &cpu_data(cpu); uci->cpu_sig.rev = val[1]; c->microcode = val[1]; diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index b96896bcbdaf1..2ce1a7dc45b73 100644 --- a/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -49,7 +49,7 @@ int microcode_sanity_check(void *mc, int print_err) unsigned long total_size, data_size, ext_table_size; struct microcode_header_intel *mc_header = mc; struct extended_sigtable *ext_header = NULL; - int sum, orig_sum, ext_sigcount = 0, i; + u32 sum, orig_sum, ext_sigcount = 0, i; struct extended_signature *ext_sig; total_size = get_totalsize(mc_header); @@ -57,69 +57,85 @@ int microcode_sanity_check(void *mc, int print_err) if (data_size + MC_HEADER_SIZE > total_size) { if (print_err) - pr_err("error! Bad data size in microcode data file\n"); + pr_err("Error: bad microcode data file size.\n"); return -EINVAL; } if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { if (print_err) - pr_err("error! Unknown microcode update format\n"); + pr_err("Error: invalid/unknown microcode update format.\n"); return -EINVAL; } + ext_table_size = total_size - (MC_HEADER_SIZE + data_size); if (ext_table_size) { + u32 ext_table_sum = 0; + u32 *ext_tablep; + if ((ext_table_size < EXT_HEADER_SIZE) || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { if (print_err) - pr_err("error! Small exttable size in microcode data file\n"); + pr_err("Error: truncated extended signature table.\n"); return -EINVAL; } + ext_header = mc + MC_HEADER_SIZE + data_size; if (ext_table_size != exttable_size(ext_header)) { if (print_err) - pr_err("error! Bad exttable size in microcode data file\n"); + pr_err("Error: extended signature table size mismatch.\n"); return -EFAULT; } + ext_sigcount = ext_header->count; - } - /* check extended table checksum */ - if (ext_table_size) { - int ext_table_sum = 0; - int *ext_tablep = (int *)ext_header; + /* + * Check extended table checksum: the sum of all dwords that + * comprise a valid table must be 0. + */ + ext_tablep = (u32 *)ext_header; - i = ext_table_size / DWSIZE; + i = ext_table_size / sizeof(u32); while (i--) ext_table_sum += ext_tablep[i]; + if (ext_table_sum) { if (print_err) - pr_warn("aborting, bad extended signature table checksum\n"); + pr_warn("Bad extended signature table checksum, aborting.\n"); return -EINVAL; } } - /* calculate the checksum */ + /* + * Calculate the checksum of update data and header. The checksum of + * valid update data and header including the extended signature table + * must be 0. + */ orig_sum = 0; - i = (MC_HEADER_SIZE + data_size) / DWSIZE; + i = (MC_HEADER_SIZE + data_size) / sizeof(u32); while (i--) - orig_sum += ((int *)mc)[i]; + orig_sum += ((u32 *)mc)[i]; + if (orig_sum) { if (print_err) - pr_err("aborting, bad checksum\n"); + pr_err("Bad microcode data checksum, aborting.\n"); return -EINVAL; } + if (!ext_table_size) return 0; - /* check extended signature checksum */ + + /* + * Check extended signature checksum: 0 => valid. + */ for (i = 0; i < ext_sigcount; i++) { ext_sig = (void *)ext_header + EXT_HEADER_SIZE + EXT_SIGNATURE_SIZE * i; - sum = orig_sum - - (mc_header->sig + mc_header->pf + mc_header->cksum) - + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); + + sum = (mc_header->sig + mc_header->pf + mc_header->cksum) - + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); if (sum) { if (print_err) - pr_err("aborting, bad checksum\n"); + pr_err("Bad extended signature checksum, aborting.\n"); return -EINVAL; } } diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 3f20710a5b23b..6988c74409a82 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -1,6 +1,6 @@ #!/bin/sh # -# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h +# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h # IN=$1 @@ -49,8 +49,8 @@ dump_array() trap 'rm "$OUT"' EXIT ( - echo "#ifndef _ASM_X86_CPUFEATURE_H" - echo "#include " + echo "#ifndef _ASM_X86_CPUFEATURES_H" + echo "#include " echo "#endif" echo "" diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 20e242ea1bc46..4e7c6933691cc 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -161,8 +161,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("HyperV: features 0x%x, hints 0x%x\n", + ms_hyperv.features, ms_hyperv.hints); #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { @@ -174,8 +174,8 @@ static void __init ms_hyperv_init_platform(void) rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency); hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ); lapic_timer_frequency = hv_lapic_frequency; - printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n", - lapic_timer_frequency); + pr_info("HyperV: LAPIC Timer Frequency: %#x\n", + lapic_timer_frequency); } #endif diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index 316fe3e60a976..3d689937fc1b1 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -103,7 +103,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t */ if (type != MTRR_TYPE_WRCOMB && (centaur_mcr_type == 0 || type != MTRR_TYPE_UNCACHABLE)) { - pr_warning("mtrr: only write-combining%s supported\n", + pr_warn("mtrr: only write-combining%s supported\n", centaur_mcr_type ? " and uncacheable are" : " is"); return -EINVAL; } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 0d98503c2245a..31e951ce6dff3 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -57,9 +57,9 @@ static int __initdata nr_range; static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; static int __initdata debug_print; -#define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0) +#define Dprintk(x...) do { if (debug_print) pr_debug(x); } while (0) -#define BIOS_BUG_MSG KERN_WARNING \ +#define BIOS_BUG_MSG \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" static int __init @@ -81,9 +81,9 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, base, base + size); } if (debug_print) { - printk(KERN_DEBUG "After WB checking\n"); + pr_debug("After WB checking\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + pr_debug("MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end); } @@ -101,7 +101,7 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { /* Var MTRR contains UC entry below 1M? Skip it: */ - printk(BIOS_BUG_MSG, i); + pr_warn(BIOS_BUG_MSG, i); if (base + size <= (1<<(20-PAGE_SHIFT))) continue; size -= (1<<(20-PAGE_SHIFT)) - base; @@ -114,11 +114,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, extra_remove_base + extra_remove_size); if (debug_print) { - printk(KERN_DEBUG "After UC checking\n"); + pr_debug("After UC checking\n"); for (i = 0; i < RANGE_NUM; i++) { if (!range[i].end) continue; - printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + pr_debug("MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end); } } @@ -126,9 +126,9 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, /* sort the ranges */ nr_range = clean_sort_range(range, RANGE_NUM); if (debug_print) { - printk(KERN_DEBUG "After sorting\n"); + pr_debug("After sorting\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + pr_debug("MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end); } @@ -544,7 +544,7 @@ static void __init print_out_mtrr_range_state(void) start_base = to_size_factor(start_base, &start_factor), type = range_state[i].type; - printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n", + pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", i, start_base, start_factor, size_base, size_factor, (type == MTRR_TYPE_UNCACHABLE) ? "UC" : @@ -713,7 +713,7 @@ int __init mtrr_cleanup(unsigned address_bits) return 0; /* Print original var MTRRs at first, for debugging: */ - printk(KERN_DEBUG "original variable MTRRs\n"); + pr_debug("original variable MTRRs\n"); print_out_mtrr_range_state(); memset(range, 0, sizeof(range)); @@ -733,7 +733,7 @@ int __init mtrr_cleanup(unsigned address_bits) x_remove_base, x_remove_size); range_sums = sum_ranges(range, nr_range); - printk(KERN_INFO "total RAM covered: %ldM\n", + pr_info("total RAM covered: %ldM\n", range_sums >> (20 - PAGE_SHIFT)); if (mtrr_chunk_size && mtrr_gran_size) { @@ -745,12 +745,11 @@ int __init mtrr_cleanup(unsigned address_bits) if (!result[i].bad) { set_var_mtrr_all(address_bits); - printk(KERN_DEBUG "New variable MTRRs\n"); + pr_debug("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } - printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, " - "will find optimal one\n"); + pr_info("invalid mtrr_gran_size or mtrr_chunk_size, will find optimal one\n"); } i = 0; @@ -768,7 +767,7 @@ int __init mtrr_cleanup(unsigned address_bits) x_remove_base, x_remove_size, i); if (debug_print) { mtrr_print_out_one_result(i); - printk(KERN_INFO "\n"); + pr_info("\n"); } i++; @@ -779,7 +778,7 @@ int __init mtrr_cleanup(unsigned address_bits) index_good = mtrr_search_optimal_index(); if (index_good != -1) { - printk(KERN_INFO "Found optimal setting for mtrr clean up\n"); + pr_info("Found optimal setting for mtrr clean up\n"); i = index_good; mtrr_print_out_one_result(i); @@ -790,7 +789,7 @@ int __init mtrr_cleanup(unsigned address_bits) gran_size <<= 10; x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); set_var_mtrr_all(address_bits); - printk(KERN_DEBUG "New variable MTRRs\n"); + pr_debug("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } else { @@ -799,8 +798,8 @@ int __init mtrr_cleanup(unsigned address_bits) mtrr_print_out_one_result(i); } - printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n"); - printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n"); + pr_info("mtrr_cleanup: can not find optimal value\n"); + pr_info("please specify mtrr_gran_size/mtrr_chunk_size\n"); return 0; } @@ -918,7 +917,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* kvm/qemu doesn't have mtrr set right, don't trim them all: */ if (!highest_pfn) { - printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n"); + pr_info("CPU MTRRs all blank - virtualized system.\n"); return 0; } @@ -973,7 +972,8 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) end_pfn); if (total_trim_size) { - pr_warning("WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing %lluMB of RAM.\n", total_trim_size >> 20); + pr_warn("WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing %lluMB of RAM.\n", + total_trim_size >> 20); if (!changed_by_mtrr_cleanup) WARN_ON(1); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index c870af1610083..fcbcb2f678ca4 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -55,7 +55,7 @@ static inline void k8_check_syscfg_dram_mod_en(void) rdmsr(MSR_K8_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { - printk(KERN_ERR FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" + pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" " not cleared by BIOS, clearing this bit\n", smp_processor_id()); lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY; @@ -501,14 +501,14 @@ void __init mtrr_state_warn(void) if (!mask) return; if (mask & MTRR_CHANGE_MASK_FIXED) - pr_warning("mtrr: your CPUs had inconsistent fixed MTRR settings\n"); + pr_warn("mtrr: your CPUs had inconsistent fixed MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_VARIABLE) - pr_warning("mtrr: your CPUs had inconsistent variable MTRR settings\n"); + pr_warn("mtrr: your CPUs had inconsistent variable MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_DEFTYPE) - pr_warning("mtrr: your CPUs had inconsistent MTRRdefType settings\n"); + pr_warn("mtrr: your CPUs had inconsistent MTRRdefType settings\n"); - printk(KERN_INFO "mtrr: probably your BIOS does not setup all CPUs.\n"); - printk(KERN_INFO "mtrr: corrected configuration.\n"); + pr_info("mtrr: probably your BIOS does not setup all CPUs.\n"); + pr_info("mtrr: corrected configuration.\n"); } /* @@ -519,8 +519,7 @@ void __init mtrr_state_warn(void) void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b) { if (wrmsr_safe(msr, a, b) < 0) { - printk(KERN_ERR - "MTRR: CPU %u: Writing MSR %x to %x:%x failed\n", + pr_err("MTRR: CPU %u: Writing MSR %x to %x:%x failed\n", smp_processor_id(), msr, a, b); } } @@ -607,7 +606,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, tmp |= ~((1ULL<<(hi - 1)) - 1); if (tmp != mask) { - printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); + pr_warn("mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); mask = tmp; } @@ -858,13 +857,13 @@ int generic_validate_add_page(unsigned long base, unsigned long size, boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_mask <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { - pr_warning("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); + pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; } if (!(base + size < 0x70000 || base > 0x7003F) && (type == MTRR_TYPE_WRCOMB || type == MTRR_TYPE_WRBACK)) { - pr_warning("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n"); + pr_warn("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n"); return -EINVAL; } } @@ -878,7 +877,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, lbase = lbase >> 1, last = last >> 1) ; if (lbase != last) { - pr_warning("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size); + pr_warn("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size); return -EINVAL; } return 0; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 5c3d149ee91cb..10f8d47962407 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -47,7 +47,7 @@ #include #include -#include +#include #include #include #include @@ -300,24 +300,24 @@ int mtrr_add_page(unsigned long base, unsigned long size, return error; if (type >= MTRR_NUM_TYPES) { - pr_warning("mtrr: type: %u invalid\n", type); + pr_warn("mtrr: type: %u invalid\n", type); return -EINVAL; } /* If the type is WC, check that this processor supports it */ if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) { - pr_warning("mtrr: your processor doesn't support write-combining\n"); + pr_warn("mtrr: your processor doesn't support write-combining\n"); return -ENOSYS; } if (!size) { - pr_warning("mtrr: zero sized request\n"); + pr_warn("mtrr: zero sized request\n"); return -EINVAL; } if ((base | (base + size - 1)) >> (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { - pr_warning("mtrr: base or size exceeds the MTRR width\n"); + pr_warn("mtrr: base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -348,7 +348,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, } else if (types_compatible(type, ltype)) continue; } - pr_warning("mtrr: 0x%lx000,0x%lx000 overlaps existing" + pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing" " 0x%lx000,0x%lx000\n", base, size, lbase, lsize); goto out; @@ -357,7 +357,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (ltype != type) { if (types_compatible(type, ltype)) continue; - pr_warning("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n", + pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n", base, size, mtrr_attrib_to_str(ltype), mtrr_attrib_to_str(type)); goto out; @@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, static int mtrr_check(unsigned long base, unsigned long size) { if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { - pr_warning("mtrr: size and base must be multiples of 4 kiB\n"); + pr_warn("mtrr: size and base must be multiples of 4 kiB\n"); pr_debug("mtrr: size: 0x%lx base: 0x%lx\n", size, base); dump_stack(); return -1; @@ -493,16 +493,16 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) } } if (reg >= max) { - pr_warning("mtrr: register: %d too big\n", reg); + pr_warn("mtrr: register: %d too big\n", reg); goto out; } mtrr_if->get(reg, &lbase, &lsize, <ype); if (lsize < 1) { - pr_warning("mtrr: MTRR %d not used\n", reg); + pr_warn("mtrr: MTRR %d not used\n", reg); goto out; } if (mtrr_usage_table[reg] < 1) { - pr_warning("mtrr: reg: %d has count=0\n", reg); + pr_warn("mtrr: reg: %d has count=0\n", reg); goto out; } if (--mtrr_usage_table[reg] < 1) diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 819d94982e078..f6f50c4ceaece 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -51,7 +51,7 @@ void x86_init_rdrand(struct cpuinfo_x86 *c) for (i = 0; i < SANITY_CHECK_LOOPS; i++) { if (!rdrand_long(&tmp)) { clear_cpu_cap(c, X86_FEATURE_RDRAND); - printk_once(KERN_WARNING "rdrand: disabled\n"); + pr_warn_once("rdrand: disabled\n"); return; } } diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 4c60eaf0571c2..cd531355e8386 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -87,10 +87,10 @@ void detect_extended_topology(struct cpuinfo_x86 *c) c->x86_max_cores = (core_level_siblings / smp_num_siblings); if (!printed) { - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", + pr_info("CPU: Physical Processor ID: %d\n", c->phys_proc_id); if (c->x86_max_cores > 1) - printk(KERN_INFO "CPU: Processor Core ID: %d\n", + pr_info("CPU: Processor Core ID: %d\n", c->cpu_core_id); printed = 1; } diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 252da7aceca67..34178564be2a7 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,6 +1,6 @@ #include #include -#include +#include #include #include "cpu.h" @@ -33,7 +33,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) if (max >= 0x80860001) { cpuid(0x80860001, &dummy, &cpu_rev, &cpu_freq, &cpu_flags); if (cpu_rev != 0x02000000) { - printk(KERN_INFO "CPU: Processor revision %u.%u.%u.%u, %u MHz\n", + pr_info("CPU: Processor revision %u.%u.%u.%u, %u MHz\n", (cpu_rev >> 24) & 0xff, (cpu_rev >> 16) & 0xff, (cpu_rev >> 8) & 0xff, @@ -44,10 +44,10 @@ static void init_transmeta(struct cpuinfo_x86 *c) if (max >= 0x80860002) { cpuid(0x80860002, &new_cpu_rev, &cms_rev1, &cms_rev2, &dummy); if (cpu_rev == 0x02000000) { - printk(KERN_INFO "CPU: Processor revision %08X, %u MHz\n", + pr_info("CPU: Processor revision %08X, %u MHz\n", new_cpu_rev, cpu_freq); } - printk(KERN_INFO "CPU: Code Morphing Software revision %u.%u.%u-%u-%u\n", + pr_info("CPU: Code Morphing Software revision %u.%u.%u-%u-%u\n", (cms_rev1 >> 24) & 0xff, (cms_rev1 >> 16) & 0xff, (cms_rev1 >> 8) & 0xff, @@ -76,7 +76,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) (void *)&cpu_info[56], (void *)&cpu_info[60]); cpu_info[64] = '\0'; - printk(KERN_INFO "CPU: %s\n", cpu_info); + pr_info("CPU: %s\n", cpu_info); } /* Unhide possibly hidden capability flags */ diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 628a059a9a066..364e583468975 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -62,7 +62,7 @@ static unsigned long vmware_get_tsc_khz(void) tsc_hz = eax | (((uint64_t)ebx) << 32); do_div(tsc_hz, 1000); BUG_ON(tsc_hz >> 32); - printk(KERN_INFO "TSC freq read from hypervisor : %lu.%03lu MHz\n", + pr_info("TSC freq read from hypervisor : %lu.%03lu MHz\n", (unsigned long) tsc_hz / 1000, (unsigned long) tsc_hz % 1000); @@ -84,8 +84,7 @@ static void __init vmware_platform_setup(void) if (ebx != UINT_MAX) x86_platform.calibrate_tsc = vmware_get_tsc_khz; else - printk(KERN_WARNING - "Failed to get TSC freq from the hypervisor\n"); + pr_warn("Failed to get TSC freq from the hypervisor\n"); } /* diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 58f34319b29ab..9ef978d69c22e 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -57,10 +57,9 @@ struct crash_elf_data { struct kimage *image; /* * Total number of ram ranges we have after various adjustments for - * GART, crash reserved region etc. + * crash reserved region, etc. */ unsigned int max_nr_ranges; - unsigned long gart_start, gart_end; /* Pointer to elf header */ void *ehdr; @@ -201,17 +200,6 @@ static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) return 0; } -static int get_gart_ranges_callback(u64 start, u64 end, void *arg) -{ - struct crash_elf_data *ced = arg; - - ced->gart_start = start; - ced->gart_end = end; - - /* Not expecting more than 1 gart aperture */ - return 1; -} - /* Gather all the required information to prepare elf headers for ram regions */ static void fill_up_crash_elf_data(struct crash_elf_data *ced, @@ -226,22 +214,6 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->max_nr_ranges = nr_ranges; - /* - * We don't create ELF headers for GART aperture as an attempt - * to dump this memory in second kernel leads to hang/crash. - * If gart aperture is present, one needs to exclude that region - * and that could lead to need of extra phdr. - */ - walk_iomem_res("GART", IORESOURCE_MEM, 0, -1, - ced, get_gart_ranges_callback); - - /* - * If we have gart region, excluding that could potentially split - * a memory range, resulting in extra header. Account for that. - */ - if (ced->gart_end) - ced->max_nr_ranges++; - /* Exclusion of crash region could split memory ranges */ ced->max_nr_ranges++; @@ -350,13 +322,6 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, return ret; } - /* Exclude GART region */ - if (ced->gart_end) { - ret = exclude_mem_range(cmem, ced->gart_start, ced->gart_end); - if (ret) - return ret; - } - return ret; } @@ -599,12 +564,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) /* Add ACPI tables */ cmd.type = E820_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; - walk_iomem_res("ACPI Tables", flags, 0, -1, &cmd, + walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, memmap_entry_callback); /* Add ACPI Non-volatile Storage */ cmd.type = E820_NVS; - walk_iomem_res("ACPI Non-volatile Storage", flags, 0, -1, &cmd, + walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, memmap_entry_callback); /* Add crashk_low_res region */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 569c1e4f96feb..621b501f89351 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -24,6 +24,7 @@ #include #include #include +#include /* * The e820 map is the map that gets modified e.g. with command line parameters @@ -925,6 +926,41 @@ static const char *e820_type_to_string(int e820_type) } } +static unsigned long e820_type_to_iomem_type(int e820_type) +{ + switch (e820_type) { + case E820_RESERVED_KERN: + case E820_RAM: + return IORESOURCE_SYSTEM_RAM; + case E820_ACPI: + case E820_NVS: + case E820_UNUSABLE: + case E820_PRAM: + case E820_PMEM: + default: + return IORESOURCE_MEM; + } +} + +static unsigned long e820_type_to_iores_desc(int e820_type) +{ + switch (e820_type) { + case E820_ACPI: + return IORES_DESC_ACPI_TABLES; + case E820_NVS: + return IORES_DESC_ACPI_NV_STORAGE; + case E820_PMEM: + return IORES_DESC_PERSISTENT_MEMORY; + case E820_PRAM: + return IORES_DESC_PERSISTENT_MEMORY_LEGACY; + case E820_RESERVED_KERN: + case E820_RAM: + case E820_UNUSABLE: + default: + return IORES_DESC_NONE; + } +} + static bool do_mark_busy(u32 type, struct resource *res) { /* this is the legacy bios/dos rom-shadow + mmio region */ @@ -967,7 +1003,8 @@ void __init e820_reserve_resources(void) res->start = e820.map[i].addr; res->end = end; - res->flags = IORESOURCE_MEM; + res->flags = e820_type_to_iomem_type(e820.map[i].type); + res->desc = e820_type_to_iores_desc(e820.map[i].type); /* * don't register the region that could be conflicted with diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d25097c3fc1d1..0b1b9abd4d5fe 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -114,6 +114,10 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); if (fpu->fpregs_active) { + /* + * Ignore return value -- we don't care if reg state + * is clobbered. + */ copy_fpregs_to_fpstate(fpu); } else { this_cpu_write(fpu_fpregs_owner_ctx, NULL); @@ -189,8 +193,12 @@ void fpu__save(struct fpu *fpu) preempt_disable(); if (fpu->fpregs_active) { - if (!copy_fpregs_to_fpstate(fpu)) - fpregs_deactivate(fpu); + if (!copy_fpregs_to_fpstate(fpu)) { + if (use_eager_fpu()) + copy_kernel_to_fpregs(&fpu->state); + else + fpregs_deactivate(fpu); + } } preempt_enable(); } @@ -223,14 +231,15 @@ void fpstate_init(union fpregs_state *state) } EXPORT_SYMBOL_GPL(fpstate_init); -/* - * Copy the current task's FPU state to a new task's FPU context. - * - * In both the 'eager' and the 'lazy' case we save hardware registers - * directly to the destination buffer. - */ -static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) +int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { + dst_fpu->counter = 0; + dst_fpu->fpregs_active = 0; + dst_fpu->last_cpu = -1; + + if (!src_fpu->fpstate_active || !cpu_has_fpu) + return 0; + WARN_ON_FPU(src_fpu != ¤t->thread.fpu); /* @@ -243,10 +252,9 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * - * If the FPU context got destroyed in the process (FNSAVE - * done on old CPUs) then copy it back into the source - * context and mark the current task for lazy restore. + * In lazy mode, if the FPU context isn't loaded into + * fpregs, CR0.TS will be set and do_device_not_available + * will load the FPU context. * * We have to do all this with preemption disabled, * mostly because of the FNSAVE case, because in that @@ -259,19 +267,13 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { memcpy(&src_fpu->state, &dst_fpu->state, xstate_size); - fpregs_deactivate(src_fpu); + + if (use_eager_fpu()) + copy_kernel_to_fpregs(&src_fpu->state); + else + fpregs_deactivate(src_fpu); } preempt_enable(); -} - -int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) -{ - dst_fpu->counter = 0; - dst_fpu->fpregs_active = 0; - dst_fpu->last_cpu = -1; - - if (src_fpu->fpstate_active && cpu_has_fpu) - fpu_copy(dst_fpu, src_fpu); return 0; } @@ -409,8 +411,10 @@ static inline void copy_init_fpstate_to_fpregs(void) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, -1); - else + else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); + else + copy_kernel_to_fregs(&init_fpstate.fsave); } /* @@ -423,7 +427,7 @@ void fpu__clear(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ - if (!use_eager_fpu()) { + if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) { /* FPU state will be reallocated lazily at the first use. */ fpu__drop(fpu); } else { diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 6d9f0a7ef4c8e..54c86fffbf9f8 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -78,13 +78,15 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) cr0 &= ~(X86_CR0_TS | X86_CR0_EM); write_cr0(cr0); - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); + if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + } #ifndef CONFIG_MATH_EMULATION if (!cpu_has_fpu) { @@ -132,7 +134,7 @@ static void __init fpu__init_system_generic(void) * Set up the legacy init FPU context. (xstate init might overwrite this * with a more modern format, if the CPU supports it.) */ - fpstate_init_fxstate(&init_fpstate.fxsave); + fpstate_init(&init_fpstate); fpu__init_system_mxcsr(); } @@ -260,7 +262,10 @@ static void __init fpu__init_system_xstate_size_legacy(void) * not only saved the restores along the way, but we also have the * FPU ready to be used for the original task. * - * 'eager' switching is used on modern CPUs, there we switch the FPU + * 'lazy' is deprecated because it's almost never a performance win + * and it's much more complicated than 'eager'. + * + * 'eager' switching is by default on all CPUs, there we switch the FPU * state during every context switch, regardless of whether the task * has used FPU instructions in that time slice or not. This is done * because modern FPU context saving instructions are able to optimize @@ -271,7 +276,7 @@ static void __init fpu__init_system_xstate_size_legacy(void) * to use 'eager' restores, if we detect that a task is using the FPU * frequently. See the fpu->counter logic in fpu/internal.h for that. ] */ -static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; +static enum { ENABLE, DISABLE } eagerfpu = ENABLE; /* * Find supported xfeatures based on cpu features and command-line input. @@ -300,12 +305,6 @@ u64 __init fpu__get_supported_xfeatures_mask(void) static void __init fpu__clear_eager_fpu_features(void) { setup_clear_cpu_cap(X86_FEATURE_MPX); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - setup_clear_cpu_cap(X86_FEATURE_AVX512F); - setup_clear_cpu_cap(X86_FEATURE_AVX512PF); - setup_clear_cpu_cap(X86_FEATURE_AVX512ER); - setup_clear_cpu_cap(X86_FEATURE_AVX512CD); } /* @@ -348,15 +347,9 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { - /* - * No need to check "eagerfpu=auto" again, since it is the - * initial default. - */ if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) { eagerfpu = DISABLE; fpu__clear_eager_fpu_features(); - } else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) { - eagerfpu = ENABLE; } if (cmdline_find_option_bool(boot_command_line, "no387")) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index d425cda5ae6d0..6e8354f5a5935 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -51,6 +51,9 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_AVX512PF); setup_clear_cpu_cap(X86_FEATURE_AVX512ER); setup_clear_cpu_cap(X86_FEATURE_AVX512CD); + setup_clear_cpu_cap(X86_FEATURE_AVX512DQ); + setup_clear_cpu_cap(X86_FEATURE_AVX512BW); + setup_clear_cpu_cap(X86_FEATURE_AVX512VL); setup_clear_cpu_cap(X86_FEATURE_MPX); setup_clear_cpu_cap(X86_FEATURE_XGETBV1); } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 29408d6d66267..702547ce33c9c 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -81,9 +81,9 @@ within(unsigned long addr, unsigned long start, unsigned long end) static unsigned long text_ip_addr(unsigned long ip) { /* - * On x86_64, kernel text mappings are mapped read-only with - * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead - * of the kernel text mapping to modify the kernel text. + * On x86_64, kernel text mappings are mapped read-only, so we use + * the kernel identity mapping instead of the kernel text mapping + * to modify the kernel text. * * For 32bit kernels, these mappings are same and we can use * kernel identity mapping to modify code. @@ -697,9 +697,8 @@ static inline void tramp_free(void *tramp) { } #endif /* Defined as markers to the end of the ftrace default trampolines */ -extern void ftrace_caller_end(void); extern void ftrace_regs_caller_end(void); -extern void ftrace_return(void); +extern void ftrace_epilogue(void); extern void ftrace_caller_op_ptr(void); extern void ftrace_regs_caller_op_ptr(void); @@ -746,7 +745,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) op_offset = (unsigned long)ftrace_regs_caller_op_ptr; } else { start_offset = (unsigned long)ftrace_caller; - end_offset = (unsigned long)ftrace_caller_end; + end_offset = (unsigned long)ftrace_epilogue; op_offset = (unsigned long)ftrace_caller_op_ptr; } @@ -754,7 +753,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* * Allocate enough size to store the ftrace_caller code, - * the jmp to ftrace_return, as well as the address of + * the jmp to ftrace_epilogue, as well as the address of * the ftrace_ops this trampoline is used for. */ trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *)); @@ -772,8 +771,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) ip = (unsigned long)trampoline + size; - /* The trampoline ends with a jmp to ftrace_return */ - jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_return); + /* The trampoline ends with a jmp to ftrace_epilogue */ + jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_epilogue); memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE); /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 2c0f3407bd1f1..1f4422d5c8d01 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -40,13 +40,8 @@ pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { - unsigned long i; - - for (i = 0; i < PTRS_PER_PGD-1; i++) - early_level4_pgt[i].pgd = 0; - + memset(early_level4_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_level4_pgt)); } @@ -54,7 +49,6 @@ static void __init reset_early_page_tables(void) int __init early_make_pgtable(unsigned long address) { unsigned long physaddr = address - __PAGE_OFFSET; - unsigned long i; pgdval_t pgd, *pgd_p; pudval_t pud, *pud_p; pmdval_t pmd, *pmd_p; @@ -81,8 +75,7 @@ int __init early_make_pgtable(unsigned long address) } pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++]; - for (i = 0; i < PTRS_PER_PUD; i++) - pud_p[i] = 0; + memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } pud_p += pud_index(address); @@ -97,8 +90,7 @@ int __init early_make_pgtable(unsigned long address) } pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++]; - for (i = 0; i < PTRS_PER_PMD; i++) - pmd_p[i] = 0; + memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } pmd = (physaddr & PMD_MASK) + early_pmd_flags; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 6bc9ae24b6d2a..54cdbd2003fe0 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include #include @@ -389,6 +389,12 @@ default_entry: /* Make changes effective */ wrmsr + /* + * And make sure that all the mappings we set up have NX set from + * the beginning. + */ + orl $(1 << (_PAGE_BIT_NX - 32)), pa(__supported_pte_mask + 4) + enable_paging: /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ffdc0e8603902..22fbf9df61bb4 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -38,7 +38,6 @@ #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET) -L3_PAGE_OFFSET = pud_index(__PAGE_OFFSET) L4_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) @@ -76,9 +75,7 @@ startup_64: subq $_text - __START_KERNEL_map, %rbp /* Is the address not 2M aligned? */ - movq %rbp, %rax - andl $~PMD_PAGE_MASK, %eax - testl %eax, %eax + testl $~PMD_PAGE_MASK, %ebp jnz bad_address /* diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index b8e6ff5cd5d05..be0ebbb6d1d14 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -12,6 +12,7 @@ #include #include +#include #include #include #include diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 44256a62702b2..ed15cd486d063 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -750,9 +750,7 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { int err; -#ifdef CONFIG_DEBUG_RODATA char opc[BREAK_INSTR_SIZE]; -#endif /* CONFIG_DEBUG_RODATA */ bpt->type = BP_BREAKPOINT; err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, @@ -761,7 +759,6 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) return err; err = probe_kernel_write((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); -#ifdef CONFIG_DEBUG_RODATA if (!err) return err; /* @@ -778,13 +775,12 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE)) return -EINVAL; bpt->type = BP_POKE_BREAKPOINT; -#endif /* CONFIG_DEBUG_RODATA */ + return err; } int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) { -#ifdef CONFIG_DEBUG_RODATA int err; char opc[BREAK_INSTR_SIZE]; @@ -801,8 +797,8 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE)) goto knl_write; return err; + knl_write: -#endif /* CONFIG_DEBUG_RODATA */ return probe_kernel_write((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 1deffe6cc8736..0f05deeff5ce2 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -988,7 +988,7 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * In case the user-specified fault handler returned * zero, try to fix up. */ - if (fixup_exception(regs)) + if (fixup_exception(regs, trapnr)) return 1; /* diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 87e1762e2bca7..ed48a9f465f84 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -168,12 +168,14 @@ GLOBAL(ftrace_call) restore_mcount_regs /* - * The copied trampoline must call ftrace_return as it + * The copied trampoline must call ftrace_epilogue as it * still may need to call the function graph tracer. + * + * The code up to this label is copied into trampolines so + * think twice before adding any new code or changing the + * layout here. */ -GLOBAL(ftrace_caller_end) - -GLOBAL(ftrace_return) +GLOBAL(ftrace_epilogue) #ifdef CONFIG_FUNCTION_GRAPH_TRACER GLOBAL(ftrace_graph_call) @@ -244,14 +246,14 @@ GLOBAL(ftrace_regs_call) popfq /* - * As this jmp to ftrace_return can be a short jump + * As this jmp to ftrace_epilogue can be a short jump * it must not be copied into the trampoline. * The trampoline will add the code to jump * to the return. */ GLOBAL(ftrace_regs_caller_end) - jmp ftrace_return + jmp ftrace_epilogue END(ftrace_regs_caller) diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 30ca7607cbbbb..97340f2c437c6 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -408,7 +408,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; - processor.featureflag = boot_cpu_data.x86_capability[0]; + processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; for (i = 0; i < 2; i++) { diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 64f9616f93f1e..7f3550acde1b8 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -40,7 +40,7 @@ #include #include -#include +#include #include static struct class *msr_class; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 8a2cdd736fa4d..04b132a767f11 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -30,6 +30,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -69,7 +70,7 @@ struct nmi_stats { static DEFINE_PER_CPU(struct nmi_stats, nmi_stats); -static int ignore_nmis; +static int ignore_nmis __read_mostly; int unknown_nmi_panic; /* diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 14415aff18136..92f70147a9a67 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -13,11 +13,11 @@ static int found(u64 start, u64 end, void *data) static __init int register_e820_pmem(void) { - char *pmem = "Persistent Memory (legacy)"; struct platform_device *pdev; int rc; - rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found); + rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY, + IORESOURCE_MEM, 0, -1, NULL, found); if (rc <= 0) return 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9f7c21c22477e..2915d54e9dd5f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -57,6 +57,9 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { */ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif +#ifdef CONFIG_X86_32 + .SYSENTER_stack_canary = STACK_END_MAGIC, +#endif }; EXPORT_PER_CPU_SYMBOL(cpu_tss); @@ -418,9 +421,9 @@ static void mwait_idle(void) if (!current_set_polling_and_test()) { trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { - smp_mb(); /* quirk */ + mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); - smp_mb(); /* quirk */ + mb(); /* quirk */ } __monitor((void *)¤t_thread_info()->flags, 0, 0); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d3d80e6d42a20..aa52c10094755 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -152,21 +152,21 @@ static struct resource data_resource = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource bss_resource = { .name = "Kernel bss", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index cb6282c3638ff..548ddf7d6fd20 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -61,7 +61,38 @@ regs->seg = GET_SEG(seg) | 3; \ } while (0) -int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) +#ifdef CONFIG_X86_64 +/* + * If regs->ss will cause an IRET fault, change it. Otherwise leave it + * alone. Using this generally makes no sense unless + * user_64bit_mode(regs) would return true. + */ +static void force_valid_ss(struct pt_regs *regs) +{ + u32 ar; + asm volatile ("lar %[old_ss], %[ar]\n\t" + "jz 1f\n\t" /* If invalid: */ + "xorl %[ar], %[ar]\n\t" /* set ar = 0 */ + "1:" + : [ar] "=r" (ar) + : [old_ss] "rm" ((u16)regs->ss)); + + /* + * For a valid 64-bit user context, we need DPL 3, type + * read-write data or read-write exp-down data, and S and P + * set. We can't use VERW because VERW doesn't check the + * P bit. + */ + ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK; + if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) && + ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) + regs->ss = __USER_DS; +} +#endif + +static int restore_sigcontext(struct pt_regs *regs, + struct sigcontext __user *sc, + unsigned long uc_flags) { unsigned long buf_val; void __user *buf; @@ -94,15 +125,18 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) COPY(r15); #endif /* CONFIG_X86_64 */ -#ifdef CONFIG_X86_32 COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); -#else /* !CONFIG_X86_32 */ - /* Kernel saves and restores only the CS segment register on signals, - * which is the bare minimum needed to allow mixed 32/64-bit code. - * App's signal handler can save/restore other segments if needed. */ - COPY_SEG_CPL3(cs); -#endif /* CONFIG_X86_32 */ + +#ifdef CONFIG_X86_64 + /* + * Fix up SS if needed for the benefit of old DOSEMU and + * CRIU. + */ + if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && + user_64bit_mode(regs))) + force_valid_ss(regs); +#endif get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); @@ -165,6 +199,7 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, put_user_ex(regs->cs, &sc->cs); put_user_ex(0, &sc->gs); put_user_ex(0, &sc->fs); + put_user_ex(regs->ss, &sc->ss); #endif /* CONFIG_X86_32 */ put_user_ex(fpstate, &sc->fpstate); @@ -403,6 +438,21 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, return 0; } #else /* !CONFIG_X86_32 */ +static unsigned long frame_uc_flags(struct pt_regs *regs) +{ + unsigned long flags; + + if (cpu_has_xsave) + flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; + else + flags = UC_SIGCONTEXT_SS; + + if (likely(user_64bit_mode(regs))) + flags |= UC_STRICT_RESTORE_SS; + + return flags; +} + static int __setup_rt_frame(int sig, struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { @@ -422,10 +472,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, put_user_try { /* Create the ucontext. */ - if (cpu_has_xsave) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); save_altstack_ex(&frame->uc.uc_stack, regs->sp); @@ -459,10 +506,28 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->sp = (unsigned long)frame; - /* Set up the CS register to run signal handlers in 64-bit mode, - even if the handler happens to be interrupting 32-bit code. */ + /* + * Set up the CS and SS registers to run signal handlers in + * 64-bit mode, even if the handler happens to be interrupting + * 32-bit or 16-bit code. + * + * SS is subtle. In 64-bit mode, we don't need any particular + * SS descriptor, but we do need SS to be valid. It's possible + * that the old SS is entirely bogus -- this can happen if the + * signal we're trying to deliver is #GP or #SS caused by a bad + * SS value. We also have a compatbility issue here: DOSEMU + * relies on the contents of the SS register indicating the + * SS value at the time of the signal, even though that code in + * DOSEMU predates sigreturn's ability to restore SS. (DOSEMU + * avoids relying on sigreturn to restore SS; instead it uses + * a trampoline.) So we do our best: if the old SS was valid, + * we keep it. Otherwise we replace it. + */ regs->cs = __USER_CS; + if (unlikely(regs->ss != __USER_DS)) + force_valid_ss(regs); + return 0; } #endif /* CONFIG_X86_32 */ @@ -489,10 +554,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, put_user_try { /* Create the ucontext. */ - if (cpu_has_xsave) - put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); - else - put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); @@ -554,7 +616,11 @@ asmlinkage unsigned long sys_sigreturn(void) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->sc)) + /* + * x86_32 has no uc_flags bits relevant to restore_sigcontext. + * Save a few cycles by skipping the __get_user. + */ + if (restore_sigcontext(regs, &frame->sc, 0)) goto badframe; return regs->ax; @@ -570,16 +636,19 @@ asmlinkage long sys_rt_sigreturn(void) struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; sigset_t set; + unsigned long uc_flags; frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; + if (__get_user(uc_flags, &frame->uc.uc_flags)) + goto badframe; set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; if (restore_altstack(&frame->uc.uc_stack)) @@ -692,12 +761,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { -#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64) +#ifdef CONFIG_X86_64 + if (is_ia32_task()) + return __NR_ia32_restart_syscall; +#endif +#ifdef CONFIG_X86_X32_ABI + return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); +#else return __NR_restart_syscall; -#else /* !CONFIG_X86_32 && CONFIG_X86_64 */ - return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : - __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); -#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */ +#endif } /* @@ -763,6 +835,7 @@ asmlinkage long sys32_x32_rt_sigreturn(void) struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_x32 __user *frame; sigset_t set; + unsigned long uc_flags; frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); @@ -770,10 +843,12 @@ asmlinkage long sys32_x32_rt_sigreturn(void) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; + if (__get_user(uc_flags, &frame->uc.uc_flags)) + goto badframe; set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; if (compat_restore_altstack(&frame->uc.uc_stack)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 24d57f77b3c19..643dbdccf4bc9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -97,6 +97,14 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +/* Logical package management. We might want to allocate that dynamically */ +static int *physical_to_logical_pkg __read_mostly; +static unsigned long *physical_package_map __read_mostly;; +static unsigned long *logical_package_map __read_mostly; +static unsigned int max_physical_pkg_id __read_mostly; +unsigned int __max_logical_packages __read_mostly; +EXPORT_SYMBOL(__max_logical_packages); + static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { unsigned long flags; @@ -248,7 +256,98 @@ static void notrace start_secondary(void *unused) x86_cpuinit.setup_percpu_clockev(); wmb(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); +} + +int topology_update_package_map(unsigned int apicid, unsigned int cpu) +{ + unsigned int new, pkg = apicid >> boot_cpu_data.x86_coreid_bits; + + /* Called from early boot ? */ + if (!physical_package_map) + return 0; + + if (pkg >= max_physical_pkg_id) + return -EINVAL; + + /* Set the logical package id */ + if (test_and_set_bit(pkg, physical_package_map)) + goto found; + + if (pkg < __max_logical_packages) { + set_bit(pkg, logical_package_map); + physical_to_logical_pkg[pkg] = pkg; + goto found; + } + new = find_first_zero_bit(logical_package_map, __max_logical_packages); + if (new >= __max_logical_packages) { + physical_to_logical_pkg[pkg] = -1; + pr_warn("APIC(%x) Package %u exceeds logical package map\n", + apicid, pkg); + return -ENOSPC; + } + set_bit(new, logical_package_map); + pr_info("APIC(%x) Converting physical %u to logical package %u\n", + apicid, pkg, new); + physical_to_logical_pkg[pkg] = new; + +found: + cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg]; + return 0; +} + +/** + * topology_phys_to_logical_pkg - Map a physical package id to a logical + * + * Returns logical package id or -1 if not found + */ +int topology_phys_to_logical_pkg(unsigned int phys_pkg) +{ + if (phys_pkg >= max_physical_pkg_id) + return -1; + return physical_to_logical_pkg[phys_pkg]; +} +EXPORT_SYMBOL(topology_phys_to_logical_pkg); + +static void __init smp_init_package_map(void) +{ + unsigned int ncpus, cpu; + size_t size; + + /* + * Today neither Intel nor AMD support heterogenous systems. That + * might change in the future.... + */ + ncpus = boot_cpu_data.x86_max_cores * smp_num_siblings; + __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); + + /* + * Possibly larger than what we need as the number of apic ids per + * package can be smaller than the actual used apic ids. + */ + max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus); + size = max_physical_pkg_id * sizeof(unsigned int); + physical_to_logical_pkg = kmalloc(size, GFP_KERNEL); + memset(physical_to_logical_pkg, 0xff, size); + size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long); + physical_package_map = kzalloc(size, GFP_KERNEL); + size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long); + logical_package_map = kzalloc(size, GFP_KERNEL); + + pr_info("Max logical packages: %u\n", __max_logical_packages); + + for_each_present_cpu(cpu) { + unsigned int apicid = apic->cpu_present_to_apicid(cpu); + + if (apicid == BAD_APICID || !apic->apic_id_valid(apicid)) + continue; + if (!topology_update_package_map(apicid, cpu)) + continue; + pr_warn("CPU %u APICId %x disabled\n", cpu, apicid); + per_cpu(x86_bios_cpu_apicid, cpu) = BAD_APICID; + set_cpu_possible(cpu, false); + set_cpu_present(cpu, false); + } } void __init smp_store_boot_cpu_info(void) @@ -258,6 +357,7 @@ void __init smp_store_boot_cpu_info(void) *c = boot_cpu_data; c->cpu_index = id; + smp_init_package_map(); } /* diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c index 3f92ce07e525f..27538f183c3b1 100644 --- a/arch/x86/kernel/test_nx.c +++ b/arch/x86/kernel/test_nx.c @@ -142,7 +142,6 @@ static int test_NX(void) * by the error message */ -#ifdef CONFIG_DEBUG_RODATA /* Test 3: Check if the .rodata section is executable */ if (rodata_test_data != 0xC3) { printk(KERN_ERR "test_nx: .rodata marker has invalid value\n"); @@ -151,7 +150,6 @@ static int test_NX(void) printk(KERN_ERR "test_nx: .rodata section is executable\n"); ret = -ENODEV; } -#endif #if 0 /* Test 4: Check if the .data section of a module is executable */ diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c index 5ecbfe5099dad..cb4a01b41e277 100644 --- a/arch/x86/kernel/test_rodata.c +++ b/arch/x86/kernel/test_rodata.c @@ -76,5 +76,5 @@ int rodata_test(void) } MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Testcase for the DEBUG_RODATA infrastructure"); +MODULE_DESCRIPTION("Testcase for marking rodata as read-only"); MODULE_AUTHOR("Arjan van de Ven "); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ade185a46b1da..06cbe25861f15 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -83,30 +83,16 @@ gate_desc idt_table[NR_VECTORS] __page_aligned_bss; DECLARE_BITMAP(used_vectors, NR_VECTORS); EXPORT_SYMBOL_GPL(used_vectors); -static inline void conditional_sti(struct pt_regs *regs) +static inline void cond_local_irq_enable(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } -static inline void preempt_conditional_sti(struct pt_regs *regs) -{ - preempt_count_inc(); - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); -} - -static inline void conditional_cli(struct pt_regs *regs) -{ - if (regs->flags & X86_EFLAGS_IF) - local_irq_disable(); -} - -static inline void preempt_conditional_cli(struct pt_regs *regs) +static inline void cond_local_irq_disable(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); - preempt_count_dec(); } void ist_enter(struct pt_regs *regs) @@ -199,7 +185,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, } if (!user_mode(regs)) { - if (!fixup_exception(regs)) { + if (!fixup_exception(regs, trapnr)) { tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; die(str, regs, error_code); @@ -262,7 +248,6 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; -#ifdef CONFIG_X86_64 if (show_unhandled_signals && unhandled_signal(tsk, signr) && printk_ratelimit()) { pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx", @@ -271,7 +256,6 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, print_vma_addr(" in ", regs->ip); pr_cont("\n"); } -#endif force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk); } @@ -286,7 +270,7 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str, if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { - conditional_sti(regs); + cond_local_irq_enable(regs); do_trap(trapnr, signr, str, regs, error_code, fill_trap_info(regs, signr, trapnr, &info)); } @@ -368,7 +352,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) if (notify_die(DIE_TRAP, "bounds", regs, error_code, X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) return; - conditional_sti(regs); + cond_local_irq_enable(regs); if (!user_mode(regs)) die("bounds", regs, error_code); @@ -443,7 +427,7 @@ do_general_protection(struct pt_regs *regs, long error_code) struct task_struct *tsk; RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - conditional_sti(regs); + cond_local_irq_enable(regs); if (v8086_mode(regs)) { local_irq_enable(); @@ -453,7 +437,7 @@ do_general_protection(struct pt_regs *regs, long error_code) tsk = current; if (!user_mode(regs)) { - if (fixup_exception(regs)) + if (fixup_exception(regs, X86_TRAP_GP)) return; tsk->thread.error_code = error_code; @@ -517,9 +501,11 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - preempt_conditional_sti(regs); + preempt_disable(); + cond_local_irq_enable(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); - preempt_conditional_cli(regs); + cond_local_irq_disable(regs); + preempt_enable_no_resched(); debug_stack_usage_dec(); exit: ist_exit(regs); @@ -571,6 +557,29 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) NOKPROBE_SYMBOL(fixup_bad_iret); #endif +static bool is_sysenter_singlestep(struct pt_regs *regs) +{ + /* + * We don't try for precision here. If we're anywhere in the region of + * code that can be single-stepped in the SYSENTER entry path, then + * assume that this is a useless single-step trap due to SYSENTER + * being invoked with TF set. (We don't know in advance exactly + * which instructions will be hit because BTF could plausibly + * be set.) + */ +#ifdef CONFIG_X86_32 + return (regs->ip - (unsigned long)__begin_SYSENTER_singlestep_region) < + (unsigned long)__end_SYSENTER_singlestep_region - + (unsigned long)__begin_SYSENTER_singlestep_region; +#elif defined(CONFIG_IA32_EMULATION) + return (regs->ip - (unsigned long)entry_SYSENTER_compat) < + (unsigned long)__end_entry_SYSENTER_compat - + (unsigned long)entry_SYSENTER_compat; +#else + return false; +#endif +} + /* * Our handling of the processor debug registers is non-trivial. * We do not clear them on entry and exit from the kernel. Therefore @@ -605,10 +614,41 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) ist_enter(regs); get_debugreg(dr6, 6); + /* + * The Intel SDM says: + * + * Certain debug exceptions may clear bits 0-3. The remaining + * contents of the DR6 register are never cleared by the + * processor. To avoid confusion in identifying debug + * exceptions, debug handlers should clear the register before + * returning to the interrupted task. + * + * Keep it simple: clear DR6 immediately. + */ + set_debugreg(0, 6); /* Filter out all the reserved bits which are preset to 1 */ dr6 &= ~DR6_RESERVED; + /* + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." Clear TIF_BLOCKSTEP to keep + * TIF_BLOCKSTEP in sync with the hardware BTF flag. + */ + clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP); + + if (unlikely(!user_mode(regs) && (dr6 & DR_STEP) && + is_sysenter_singlestep(regs))) { + dr6 &= ~DR_STEP; + if (!dr6) + goto exit; + /* + * else we might have gotten a single-step trap and hit a + * watchpoint at the same time, in which case we should fall + * through and handle the watchpoint. + */ + } + /* * If dr6 has no reason to give us about the origin of this trap, * then it's very likely the result of an icebp/int01 trap. @@ -617,18 +657,10 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) if (!dr6 && user_mode(regs)) user_icebp = 1; - /* Catch kmemcheck conditions first of all! */ + /* Catch kmemcheck conditions! */ if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) goto exit; - /* DR6 may or may not be cleared by the CPU */ - set_debugreg(0, 6); - - /* - * The processor cleared BTF, so don't mark that we need it set. - */ - clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP); - /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; @@ -648,24 +680,25 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - preempt_conditional_sti(regs); + preempt_disable(); + cond_local_irq_enable(regs); if (v8086_mode(regs)) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); - preempt_conditional_cli(regs); + cond_local_irq_disable(regs); + preempt_enable_no_resched(); debug_stack_usage_dec(); goto exit; } - /* - * Single-stepping through system calls: ignore any exceptions in - * kernel space, but re-enable TF when returning to user mode. - * - * We already checked v86 mode above, so we can check for kernel mode - * by just checking the CPL of CS. - */ - if ((dr6 & DR_STEP) && !user_mode(regs)) { + if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) { + /* + * Historical junk that used to handle SYSENTER single-stepping. + * This should be unreachable now. If we survive for a while + * without anyone hitting this warning, we'll turn this into + * an oops. + */ tsk->thread.debugreg6 &= ~DR_STEP; set_tsk_thread_flag(tsk, TIF_SINGLESTEP); regs->flags &= ~X86_EFLAGS_TF; @@ -673,10 +706,19 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) si_code = get_si_code(tsk->thread.debugreg6); if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); - preempt_conditional_cli(regs); + cond_local_irq_disable(regs); + preempt_enable_no_resched(); debug_stack_usage_dec(); exit: +#if defined(CONFIG_X86_32) + /* + * This is the most likely code path that involves non-trivial use + * of the SYSENTER stack. Check that we haven't overrun it. + */ + WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC, + "Overran or corrupted SYSENTER stack\n"); +#endif ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -696,10 +738,10 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP) return; - conditional_sti(regs); + cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (!fixup_exception(regs)) { + if (!fixup_exception(regs, trapnr)) { task->thread.error_code = error_code; task->thread.trap_nr = trapnr; die(str, regs, error_code); @@ -743,20 +785,19 @@ do_simd_coprocessor_error(struct pt_regs *regs, long error_code) dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) { - conditional_sti(regs); + cond_local_irq_enable(regs); } dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION - if (read_cr0() & X86_CR0_EM) { + if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) { struct math_emu_info info = { }; - conditional_sti(regs); + cond_local_irq_enable(regs); info.regs = regs; math_emulate(&info); @@ -765,7 +806,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) #endif fpu__restore(¤t->thread.fpu); /* interrupts still off */ #ifdef CONFIG_X86_32 - conditional_sti(regs); + cond_local_irq_enable(regs); #endif } NOKPROBE_SYMBOL(do_device_not_available); @@ -868,7 +909,7 @@ void __init trap_init(void) #endif #ifdef CONFIG_X86_32 - set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); + set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); set_bit(IA32_SYSCALL_VECTOR, used_vectors); #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 3d743da828d38..56380440d8622 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -43,6 +43,11 @@ static DEFINE_STATIC_KEY_FALSE(__use_tsc); int tsc_clocksource_reliable; +static u32 art_to_tsc_numerator; +static u32 art_to_tsc_denominator; +static u64 art_to_tsc_offset; +struct clocksource *art_related_clocksource; + /* * Use a ring-buffer like data structure, where a writer advances the head by * writing a new data entry and a reader advances the tail when it observes a @@ -964,6 +969,37 @@ core_initcall(cpufreq_tsc); #endif /* CONFIG_CPU_FREQ */ +#define ART_CPUID_LEAF (0x15) +#define ART_MIN_DENOMINATOR (1) + + +/* + * If ART is present detect the numerator:denominator to convert to TSC + */ +static void detect_art(void) +{ + unsigned int unused[2]; + + if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) + return; + + cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, + &art_to_tsc_numerator, unused, unused+1); + + /* Don't enable ART in a VM, non-stop TSC required */ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || + !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || + art_to_tsc_denominator < ART_MIN_DENOMINATOR) + return; + + if (rdmsrl_safe(MSR_IA32_TSC_ADJUST, &art_to_tsc_offset)) + return; + + /* Make this sticky over multiple CPU init calls */ + setup_force_cpu_cap(X86_FEATURE_ART); +} + + /* clocksource code */ static struct clocksource clocksource_tsc; @@ -1071,6 +1107,25 @@ int unsynchronized_tsc(void) return 0; } +/* + * Convert ART to TSC given numerator/denominator found in detect_art() + */ +struct system_counterval_t convert_art_to_tsc(cycle_t art) +{ + u64 tmp, res, rem; + + rem = do_div(art, art_to_tsc_denominator); + + res = art * art_to_tsc_numerator; + tmp = rem * art_to_tsc_numerator; + + do_div(tmp, art_to_tsc_denominator); + res += tmp + art_to_tsc_offset; + + return (struct system_counterval_t) {.cs = art_related_clocksource, + .cycles = res}; +} +EXPORT_SYMBOL(convert_art_to_tsc); static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); @@ -1142,6 +1197,8 @@ static void tsc_refine_calibration_work(struct work_struct *work) (unsigned long)tsc_khz % 1000); out: + if (boot_cpu_has(X86_FEATURE_ART)) + art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); } @@ -1235,6 +1292,8 @@ void __init tsc_init(void) mark_tsc_unstable("TSCs unsynchronized"); check_system_tsc_reliable(); + + detect_art(); } #ifdef CONFIG_SMP @@ -1246,14 +1305,14 @@ void __init tsc_init(void) */ unsigned long calibrate_delay_is_known(void) { - int i, cpu = smp_processor_id(); + int sibling, cpu = smp_processor_id(); if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC)) return 0; - for_each_online_cpu(i) - if (cpu_data(i).phys_proc_id == cpu_data(cpu).phys_proc_id) - return cpu_data(i).loops_per_jiffy; + sibling = cpumask_any_but(topology_core_cpumask(cpu), cpu); + if (sibling < nr_cpu_ids) + return cpu_data(sibling).loops_per_jiffy; return 0; } #endif diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 07efb35ee4bc3..014ea59aa153e 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -30,7 +30,7 @@ * appropriately. Either display a message or halt. */ -#include +#include #include verify_cpu: diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index e574b85465185..3dce1ca0a6530 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -362,7 +362,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) /* make room for real-mode segments */ tsk->thread.sp0 += 16; - if (static_cpu_has_safe(X86_FEATURE_SEP)) + if (static_cpu_has(X86_FEATURE_SEP)) tsk->thread.sysenter_cs = 0; load_sp0(tss, &tsk->thread); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 74e4bf11f562e..5af9958cbdb6b 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -41,29 +41,28 @@ ENTRY(phys_startup_64) jiffies_64 = jiffies; #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) /* - * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA - * we retain large page mappings for boundaries spanning kernel text, rodata - * and data sections. + * On 64-bit, align RODATA to 2MB so we retain large page mappings for + * boundaries spanning kernel text, rodata and data sections. * * However, kernel identity mappings will have different RWX permissions * to the pages mapping to text and to the pages padding (which are freed) the * text section. Hence kernel identity mappings will be broken to smaller * pages. For 64-bit, kernel text and kernel identity mappings are different, - * so we can enable protection checks that come with CONFIG_DEBUG_RODATA, - * as well as retain 2MB large page mappings for kernel text. + * so we can enable protection checks as well as retain 2MB large page + * mappings for kernel text. */ -#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); +#define X64_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); -#define X64_ALIGN_DEBUG_RODATA_END \ +#define X64_ALIGN_RODATA_END \ . = ALIGN(HPAGE_SIZE); \ __end_rodata_hpage_align = .; #else -#define X64_ALIGN_DEBUG_RODATA_BEGIN -#define X64_ALIGN_DEBUG_RODATA_END +#define X64_ALIGN_RODATA_BEGIN +#define X64_ALIGN_RODATA_END #endif @@ -112,13 +111,11 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 -#if defined(CONFIG_DEBUG_RODATA) /* .text should occupy whole number of pages */ . = ALIGN(PAGE_SIZE); -#endif - X64_ALIGN_DEBUG_RODATA_BEGIN + X64_ALIGN_RODATA_BEGIN RO_DATA(PAGE_SIZE) - X64_ALIGN_DEBUG_RODATA_END + X64_ALIGN_RODATA_END /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { @@ -195,6 +192,17 @@ SECTIONS :init #endif + /* + * Section for code used exclusively before alternatives are run. All + * references to such code must be patched out by alternatives, normally + * by using X86_FEATURE_ALWAYS CPU feature bit. + * + * See static_cpu_has() for an example. + */ + .altinstr_aux : AT(ADDR(.altinstr_aux) - LOAD_OFFSET) { + *(.altinstr_aux) + } + INIT_DATA_SECTION(16) .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) { diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a0695be19864e..cd05942bc9189 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -37,6 +37,8 @@ EXPORT_SYMBOL(__copy_user_nocache); EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(_copy_to_user); +EXPORT_SYMBOL_GPL(memcpy_mcsafe); + EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 36591faed13be..3a045f39ed811 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1195,7 +1195,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic) static void apic_timer_expired(struct kvm_lapic *apic) { struct kvm_vcpu *vcpu = apic->vcpu; - wait_queue_head_t *q = &vcpu->wq; + struct swait_queue_head *q = &vcpu->wq; struct kvm_timer *ktimer = &apic->lapic_timer; if (atomic_read(&apic->lapic_timer.pending)) @@ -1204,8 +1204,8 @@ static void apic_timer_expired(struct kvm_lapic *apic) atomic_inc(&apic->lapic_timer.pending); kvm_set_pending_timer(vcpu); - if (waitqueue_active(q)) - wake_up_interruptible(q); + if (swait_active(q)) + swake_up(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 95a955de5964b..1e7a49bfc94fb 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3721,13 +3721,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, - context->shadow_root_level, context->nx, + context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e2951b6edbbce..9bd8f44baded2 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -596,6 +596,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -1811,6 +1813,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1848,26 +1857,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1878,16 +1892,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -2127,14 +2146,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - /* Setup TSC multiplier */ - if (cpu_has_vmx_tsc_scaling()) - vmcs_write64(TSC_MULTIPLIER, - vcpu->arch.tsc_scaling_ratio); - vmx->loaded_vmcs->cpu = cpu; } + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + vmx_vcpu_pi_load(vcpu, cpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f4891f2ece233..eaf6ee8c28b8f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2752,7 +2752,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); - vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -6619,12 +6618,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { - int i; - WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops->sync_dirty_debug_regs(vcpu); - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + kvm_update_dr0123(vcpu); + kvm_update_dr6(vcpu); + kvm_update_dr7(vcpu); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 4ba229ac3f4ff..fd57d3ae7e16d 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1520,12 +1520,6 @@ __init void lguest_init(void) */ reserve_top_address(lguest_data.reserve_mem); - /* - * If we don't initialize the lock dependency checker now, it crashes - * atomic_notifier_chain_register, then paravirt_disable_iospace. - */ - lockdep_init(); - /* Hook in our special panic hypercall code. */ atomic_notifier_chain_register(&panic_notifier_list, &paniced); @@ -1535,7 +1529,7 @@ __init void lguest_init(void) */ cpu_detect(&new_cpu_data); /* head.S usually sets up the first capability word, so do it here. */ - new_cpu_data.x86_capability[0] = cpuid_edx(1); + new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); /* Math is always hard! */ set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index a2fe51b00ccef..65be7cfaf9472 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,5 +1,5 @@ #include -#include +#include #include /* diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 422db000d7276..5cc78bf572325 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -21,12 +21,16 @@ static inline int myisspace(u8 c) * @option: option string to look for * * Returns the position of that @option (starts counting with 1) - * or 0 on not found. + * or 0 on not found. @option will only be found if it is found + * as an entire word in @cmdline. For instance, if @option="car" + * then a cmdline which contains "cart" will not match. */ -int cmdline_find_option_bool(const char *cmdline, const char *option) +static int +__cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, + const char *option) { char c; - int len, pos = 0, wstart = 0; + int pos = 0, wstart = 0; const char *opptr = NULL; enum { st_wordstart = 0, /* Start of word/after whitespace */ @@ -37,11 +41,11 @@ int cmdline_find_option_bool(const char *cmdline, const char *option) if (!cmdline) return -1; /* No command line */ - len = min_t(int, strlen(cmdline), COMMAND_LINE_SIZE); - if (!len) - return 0; - - while (len--) { + /* + * This 'pos' check ensures we do not overrun + * a non-NULL-terminated 'cmdline' + */ + while (pos < max_cmdline_size) { c = *(char *)cmdline++; pos++; @@ -58,18 +62,35 @@ int cmdline_find_option_bool(const char *cmdline, const char *option) /* fall through */ case st_wordcmp: - if (!*opptr) + if (!*opptr) { + /* + * We matched all the way to the end of the + * option we were looking for. If the + * command-line has a space _or_ ends, then + * we matched! + */ if (!c || myisspace(c)) return wstart; - else - state = st_wordskip; - else if (!c) + /* + * We hit the end of the option, but _not_ + * the end of a word on the cmdline. Not + * a match. + */ + } else if (!c) { + /* + * Hit the NULL terminator on the end of + * cmdline. + */ return 0; - else if (c != *opptr++) - state = st_wordskip; - else if (!len) /* last word and is matching */ - return wstart; - break; + } else if (c == *opptr++) { + /* + * We are currently matching, so continue + * to the next character on the cmdline. + */ + break; + } + state = st_wordskip; + /* fall through */ case st_wordskip: if (!c) @@ -82,3 +103,8 @@ int cmdline_find_option_bool(const char *cmdline, const char *option) return 0; /* Buffer overrun */ } + +int cmdline_find_option_bool(const char *cmdline, const char *option) +{ + return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option); +} diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 009f98216b7eb..24ef1c2104d42 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -1,7 +1,7 @@ /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */ #include -#include +#include #include /* diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 27f89c79a44b7..2b0ef26da0bde 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index e912b2f6d36e5..2f07c291dcc85 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -102,7 +102,7 @@ static void delay_mwaitx(unsigned long __loops) * Use cpu_tss as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(this_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 16698bba87deb..cbb8ee5830ff1 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -1,7 +1,7 @@ /* Copyright 2002 Andi Kleen */ #include -#include +#include #include /* @@ -177,3 +177,120 @@ ENTRY(memcpy_orig) .Lend: retq ENDPROC(memcpy_orig) + +#ifndef CONFIG_UML +/* + * memcpy_mcsafe - memory copy with machine check exception handling + * Note that we only catch machine checks when reading the source addresses. + * Writes to target are posted and don't generate machine checks. + */ +ENTRY(memcpy_mcsafe) + cmpl $8, %edx + /* Less than 8 bytes? Go to byte copy loop */ + jb .L_no_whole_words + + /* Check for bad alignment of source */ + testl $7, %esi + /* Already aligned */ + jz .L_8byte_aligned + + /* Copy one byte at a time until source is 8-byte aligned */ + movl %esi, %ecx + andl $7, %ecx + subl $8, %ecx + negl %ecx + subl %ecx, %edx +.L_copy_leading_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_leading_bytes + +.L_8byte_aligned: + /* Figure out how many whole cache lines (64-bytes) to copy */ + movl %edx, %ecx + andl $63, %edx + shrl $6, %ecx + jz .L_no_whole_cache_lines + + /* Loop copying whole cache lines */ +.L_cache_w0: movq (%rsi), %r8 +.L_cache_w1: movq 1*8(%rsi), %r9 +.L_cache_w2: movq 2*8(%rsi), %r10 +.L_cache_w3: movq 3*8(%rsi), %r11 + movq %r8, (%rdi) + movq %r9, 1*8(%rdi) + movq %r10, 2*8(%rdi) + movq %r11, 3*8(%rdi) +.L_cache_w4: movq 4*8(%rsi), %r8 +.L_cache_w5: movq 5*8(%rsi), %r9 +.L_cache_w6: movq 6*8(%rsi), %r10 +.L_cache_w7: movq 7*8(%rsi), %r11 + movq %r8, 4*8(%rdi) + movq %r9, 5*8(%rdi) + movq %r10, 6*8(%rdi) + movq %r11, 7*8(%rdi) + leaq 64(%rsi), %rsi + leaq 64(%rdi), %rdi + decl %ecx + jnz .L_cache_w0 + + /* Are there any trailing 8-byte words? */ +.L_no_whole_cache_lines: + movl %edx, %ecx + andl $7, %edx + shrl $3, %ecx + jz .L_no_whole_words + + /* Copy trailing words */ +.L_copy_trailing_words: + movq (%rsi), %r8 + mov %r8, (%rdi) + leaq 8(%rsi), %rsi + leaq 8(%rdi), %rdi + decl %ecx + jnz .L_copy_trailing_words + + /* Any trailing bytes? */ +.L_no_whole_words: + andl %edx, %edx + jz .L_done_memcpy_trap + + /* Copy trailing bytes */ + movl %edx, %ecx +.L_copy_trailing_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_trailing_bytes + + /* Copy successful. Return true */ +.L_done_memcpy_trap: + xorq %rax, %rax + ret +ENDPROC(memcpy_mcsafe) + + .section .fixup, "ax" + /* Return false for any failure */ +.L_memcpy_mcsafe_fail: + mov $1, %rax + ret + + .previous + + _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) +#endif diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index ca2afdd6d98ed..90ce01bee00c1 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -6,7 +6,7 @@ * - Copyright 2011 Fenghua Yu */ #include -#include +#include #include #undef memmove diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 2661fad058271..c9c81227ea37d 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -1,7 +1,7 @@ /* Copyright 2002 Andi Kleen, SuSE Labs */ #include -#include +#include #include .weak memset diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 4a6f1d9b51060..99bfb192803ff 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -358,20 +358,19 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, #define pgd_none(a) pud_none(__pud(pgd_val(a))) #endif -#ifdef CONFIG_X86_64 static inline bool is_hypervisor_range(int idx) { +#ifdef CONFIG_X86_64 /* * ffff800000000000 - ffff87ffffffffff is reserved for * the hypervisor. */ - return paravirt_enabled() && - (idx >= pgd_index(__PAGE_OFFSET) - 16) && - (idx < pgd_index(__PAGE_OFFSET)); -} + return (idx >= pgd_index(__PAGE_OFFSET) - 16) && + (idx < pgd_index(__PAGE_OFFSET)); #else -static inline bool is_hypervisor_range(int idx) { return false; } + return false; #endif +} static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, bool checkwx) diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 903ec1e9c3263..9dd7e4b7fcdee 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -3,6 +3,9 @@ #include #include +typedef bool (*ex_handler_t)(const struct exception_table_entry *, + struct pt_regs *, int); + static inline unsigned long ex_insn_addr(const struct exception_table_entry *x) { @@ -13,11 +16,56 @@ ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } +static inline ex_handler_t +ex_fixup_handler(const struct exception_table_entry *x) +{ + return (ex_handler_t)((unsigned long)&x->handler + x->handler); +} -int fixup_exception(struct pt_regs *regs) +bool ex_handler_default(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) { - const struct exception_table_entry *fixup; - unsigned long new_ip; + regs->ip = ex_fixup_addr(fixup); + return true; +} +EXPORT_SYMBOL(ex_handler_default); + +bool ex_handler_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + regs->ip = ex_fixup_addr(fixup); + regs->ax = trapnr; + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_fault); + +bool ex_handler_ext(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + /* Special hack for uaccess_err */ + current_thread_info()->uaccess_err = 1; + regs->ip = ex_fixup_addr(fixup); + return true; +} +EXPORT_SYMBOL(ex_handler_ext); + +bool ex_has_fault_handler(unsigned long ip) +{ + const struct exception_table_entry *e; + ex_handler_t handler; + + e = search_exception_tables(ip); + if (!e) + return false; + handler = ex_fixup_handler(e); + + return handler == ex_handler_fault; +} + +int fixup_exception(struct pt_regs *regs, int trapnr) +{ + const struct exception_table_entry *e; + ex_handler_t handler; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { @@ -33,42 +81,34 @@ int fixup_exception(struct pt_regs *regs) } #endif - fixup = search_exception_tables(regs->ip); - if (fixup) { - new_ip = ex_fixup_addr(fixup); - - if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) { - /* Special hack for uaccess_err */ - current_thread_info()->uaccess_err = 1; - new_ip -= 0x7ffffff0; - } - regs->ip = new_ip; - return 1; - } + e = search_exception_tables(regs->ip); + if (!e) + return 0; - return 0; + handler = ex_fixup_handler(e); + return handler(e, regs, trapnr); } /* Restricted version used during very early boot */ int __init early_fixup_exception(unsigned long *ip) { - const struct exception_table_entry *fixup; + const struct exception_table_entry *e; unsigned long new_ip; + ex_handler_t handler; - fixup = search_exception_tables(*ip); - if (fixup) { - new_ip = ex_fixup_addr(fixup); + e = search_exception_tables(*ip); + if (!e) + return 0; - if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) { - /* uaccess handling not supported during early boot */ - return 0; - } + new_ip = ex_fixup_addr(e); + handler = ex_fixup_handler(e); - *ip = new_ip; - return 1; - } + /* special handling not supported during early boot */ + if (handler != ex_handler_default) + return 0; - return 0; + *ip = new_ip; + return 1; } /* @@ -133,6 +173,8 @@ void sort_extable(struct exception_table_entry *start, i += 4; p->fixup += i; i += 4; + p->handler += i; + i += 4; } sort(start, finish - start, sizeof(struct exception_table_entry), @@ -145,6 +187,8 @@ void sort_extable(struct exception_table_entry *start, i += 4; p->fixup -= i; i += 4; + p->handler -= i; + i += 4; } } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e830c71a13232..03898aea6e0f2 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -663,7 +663,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, int sig; /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs)) { + if (fixup_exception(regs, X86_TRAP_PF)) { /* * Any interrupt that takes a fault gets the fixup. This makes * the below recursive fault logic only apply to a faults from diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index cb4ef3de61f9a..bd7a9b9e2e14a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -388,7 +388,6 @@ kernel_physical_mapping_init(unsigned long start, } pte_t *kmap_pte; -pgprot_t kmap_prot; static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr) { @@ -405,8 +404,6 @@ static void __init kmap_init(void) */ kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN); kmap_pte = kmap_get_fixmap_pte(kmap_vstart); - - kmap_prot = PAGE_KERNEL; } #ifdef CONFIG_HIGHMEM @@ -871,7 +868,6 @@ static noinline int do_test_wp_bit(void) return flag; } -#ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); @@ -960,5 +956,3 @@ void mark_rodata_ro(void) if (__supported_pte_mask & _PAGE_NX) debug_checkwx(); } -#endif - diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 5488d21123bd2..214afda979114 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include "mm_internal.h" @@ -1074,7 +1075,6 @@ void __init mem_init(void) mem_init_print_info(NULL); } -#ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); @@ -1166,8 +1166,6 @@ void mark_rodata_ro(void) debug_checkwx(); } -#endif - int kern_addr_valid(unsigned long addr) { unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; @@ -1206,26 +1204,13 @@ int kern_addr_valid(unsigned long addr) static unsigned long probe_memory_block_size(void) { - /* start from 2g */ - unsigned long bz = 1UL<<31; - - if (totalram_pages >= (64ULL << (30 - PAGE_SHIFT))) { - pr_info("Using 2GB memory block size for large-memory system\n"); - return 2UL * 1024 * 1024 * 1024; - } - - /* less than 64g installed */ - if ((max_pfn << PAGE_SHIFT) < (16UL << 32)) - return MIN_MEMORY_BLOCK_SIZE; + unsigned long bz = MIN_MEMORY_BLOCK_SIZE; - /* get the tail size */ - while (bz > MIN_MEMORY_BLOCK_SIZE) { - if (!((max_pfn << PAGE_SHIFT) & (bz - 1))) - break; - bz >>= 1; - } + /* if system is UV or has 64GB of RAM or more, use large blocks */ + if (is_uv_system() || ((max_pfn << PAGE_SHIFT) >= (64UL << 30))) + bz = 2UL << 30; /* 2GB */ - printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20); + pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20); return bz; } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index d470cf219a2d8..1b1110fa00570 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -120,11 +120,22 @@ void __init kasan_init(void) kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); - memset(kasan_zero_page, 0, PAGE_SIZE); - load_cr3(init_level4_pgt); __flush_tlb_all(); - init_task.kasan_depth = 0; + /* + * kasan_zero_page has been used as early shadow memory, thus it may + * contain some garbage. Now we can clear and write protect it, since + * after the TLB flush no one should write to it. + */ + memset(kasan_zero_page, 0, PAGE_SIZE); + for (i = 0; i < PTRS_PER_PTE; i++) { + pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO); + set_pte(&kasan_zero_pte[i], pte); + } + /* Flush TLBs again to be sure that write protection applied. */ + __flush_tlb_all(); + + init_task.kasan_depth = 0; pr_info("KernelAddressSanitizer initialized\n"); } diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 637ab34ed6328..ddb2244b06a1d 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -33,7 +33,7 @@ struct kmmio_fault_page { struct list_head list; struct kmmio_fault_page *release_next; - unsigned long page; /* location of the fault page */ + unsigned long addr; /* the requested address */ pteval_t old_presence; /* page presence prior to arming */ bool armed; @@ -70,9 +70,16 @@ unsigned int kmmio_count; static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE]; static LIST_HEAD(kmmio_probes); -static struct list_head *kmmio_page_list(unsigned long page) +static struct list_head *kmmio_page_list(unsigned long addr) { - return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)]; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + + if (!pte) + return NULL; + addr &= page_level_mask(l); + + return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)]; } /* Accessed per-cpu */ @@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr) } /* You must be holding RCU read lock. */ -static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page) +static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr) { struct list_head *head; struct kmmio_fault_page *f; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); - page &= PAGE_MASK; - head = kmmio_page_list(page); + if (!pte) + return NULL; + addr &= page_level_mask(l); + head = kmmio_page_list(addr); list_for_each_entry_rcu(f, head, list) { - if (f->page == page) + if (f->addr == addr) return f; } return NULL; @@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old) static int clear_page_presence(struct kmmio_fault_page *f, bool clear) { unsigned int level; - pte_t *pte = lookup_address(f->page, &level); + pte_t *pte = lookup_address(f->addr, &level); if (!pte) { - pr_err("no pte for page 0x%08lx\n", f->page); + pr_err("no pte for addr 0x%08lx\n", f->addr); return -1; } @@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->page); + __flush_tlb_one(f->addr); return 0; } @@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f) int ret; WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n")); if (f->armed) { - pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n", - f->page, f->count, !!f->old_presence); + pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n", + f->addr, f->count, !!f->old_presence); } ret = clear_page_presence(f, true); - WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"), - f->page); + WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"), + f->addr); f->armed = true; return ret; } @@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f) { int ret = clear_page_presence(f, false); WARN_ONCE(ret < 0, - KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page); + KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr); f->armed = false; } @@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) struct kmmio_context *ctx; struct kmmio_fault_page *faultpage; int ret = 0; /* default to fault not handled */ + unsigned long page_base = addr; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + if (!pte) + return -EINVAL; + page_base &= page_level_mask(l); /* * Preemption is now disabled to prevent process switch during @@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) preempt_disable(); rcu_read_lock(); - faultpage = get_kmmio_fault_page(addr); + faultpage = get_kmmio_fault_page(page_base); if (!faultpage) { /* * Either this page fault is not caused by kmmio, or @@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx = &get_cpu_var(kmmio_ctx); if (ctx->active) { - if (addr == ctx->addr) { + if (page_base == ctx->addr) { /* * A second fault on the same page means some other * condition needs handling by do_page_fault(), the @@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx->active++; ctx->fpage = faultpage; - ctx->probe = get_kmmio_probe(addr); + ctx->probe = get_kmmio_probe(page_base); ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - ctx->addr = addr; + ctx->addr = page_base; if (ctx->probe && ctx->probe->pre_handler) ctx->probe->pre_handler(ctx->probe, regs, addr); @@ -354,12 +371,11 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) } /* You must be holding kmmio_lock. */ -static int add_kmmio_fault_page(unsigned long page) +static int add_kmmio_fault_page(unsigned long addr) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (f) { if (!f->count) arm_kmmio_fault_page(f); @@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page) return -1; f->count = 1; - f->page = page; + f->addr = addr; if (arm_kmmio_fault_page(f)) { kfree(f); return -1; } - list_add_rcu(&f->list, kmmio_page_list(f->page)); + list_add_rcu(&f->list, kmmio_page_list(f->addr)); return 0; } /* You must be holding kmmio_lock. */ -static void release_kmmio_fault_page(unsigned long page, +static void release_kmmio_fault_page(unsigned long addr, struct kmmio_fault_page **release_list) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (!f) return; @@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p) int ret = 0; unsigned long size = 0; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); + unsigned int l; + pte_t *pte; spin_lock_irqsave(&kmmio_lock, flags); if (get_kmmio_probe(p->addr)) { ret = -EEXIST; goto out; } + + pte = lookup_address(p->addr, &l); + if (!pte) { + ret = -EINVAL; + goto out; + } + kmmio_count++; list_add_rcu(&p->list, &kmmio_probes); while (size < size_lim) { if (add_kmmio_fault_page(p->addr + size)) pr_err("Unable to set page fault.\n"); - size += PAGE_SIZE; + size += page_level_size(l); } out: spin_unlock_irqrestore(&kmmio_lock, flags); @@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p) const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); struct kmmio_fault_page *release_list = NULL; struct kmmio_delayed_release *drelease; + unsigned int l; + pte_t *pte; + + pte = lookup_address(p->addr, &l); + if (!pte) + return; spin_lock_irqsave(&kmmio_lock, flags); while (size < size_lim) { release_kmmio_fault_page(p->addr + size, &release_list); - size += PAGE_SIZE; + size += page_level_size(l); } list_del_rcu(&p->list); kmmio_count--; diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 72bb52f93c3d6..d2dc0438d654a 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -93,18 +93,6 @@ static unsigned long mmap_base(unsigned long rnd) return PAGE_ALIGN(TASK_SIZE - gap - rnd); } -/* - * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 - * does, but not when emulating X86_32 - */ -static unsigned long mmap_legacy_base(unsigned long rnd) -{ - if (mmap_is_ia32()) - return TASK_UNMAPPED_BASE; - else - return TASK_UNMAPPED_BASE + rnd; -} - /* * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: @@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); - mm->mmap_legacy_base = mmap_legacy_base(random_factor); + mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor; if (mmap_is_legacy()) { mm->mmap_base = mm->mmap_legacy_base; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index d04f8094bc232..f70c1ff461251 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -465,46 +465,67 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) return true; } +/* + * Mark all currently memblock-reserved physical memory (which covers the + * kernel's own memory ranges) as hot-unswappable. + */ static void __init numa_clear_kernel_node_hotplug(void) { - int i, nid; - nodemask_t numa_kernel_nodes = NODE_MASK_NONE; - phys_addr_t start, end; - struct memblock_region *r; + nodemask_t reserved_nodemask = NODE_MASK_NONE; + struct memblock_region *mb_region; + int i; /* + * We have to do some preprocessing of memblock regions, to + * make them suitable for reservation. + * * At this time, all memory regions reserved by memblock are - * used by the kernel. Set the nid in memblock.reserved will - * mark out all the nodes the kernel resides in. + * used by the kernel, but those regions are not split up + * along node boundaries yet, and don't necessarily have their + * node ID set yet either. + * + * So iterate over all memory known to the x86 architecture, + * and use those ranges to set the nid in memblock.reserved. + * This will split up the memblock regions along node + * boundaries and will set the node IDs as well. */ for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = &numa_meminfo.blk[i]; + struct numa_memblk *mb = numa_meminfo.blk + i; + int ret; - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.reserved, mb->nid); + ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid); + WARN_ON_ONCE(ret); } /* - * Mark all kernel nodes. + * Now go over all reserved memblock regions, to construct a + * node mask of all kernel reserved memory areas. * - * When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo - * may not include all the memblock.reserved memory ranges because - * trim_snb_memory() reserves specific pages for Sandy Bridge graphics. + * [ Note, when booting with mem=nn[kMG] or in a kdump kernel, + * numa_meminfo might not include all memblock.reserved + * memory ranges, because quirks such as trim_snb_memory() + * reserve specific pages for Sandy Bridge graphics. ] */ - for_each_memblock(reserved, r) - if (r->nid != MAX_NUMNODES) - node_set(r->nid, numa_kernel_nodes); + for_each_memblock(reserved, mb_region) { + if (mb_region->nid != MAX_NUMNODES) + node_set(mb_region->nid, reserved_nodemask); + } - /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ + /* + * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory + * belonging to the reserved node mask. + * + * Note that this will include memory regions that reside + * on nodes that contain kernel memory - entire nodes + * become hot-unpluggable: + */ for (i = 0; i < numa_meminfo.nr_blks; i++) { - nid = numa_meminfo.blk[i].nid; - if (!node_isset(nid, numa_kernel_nodes)) - continue; + struct numa_memblk *mb = numa_meminfo.blk + i; - start = numa_meminfo.blk[i].start; - end = numa_meminfo.blk[i].end; + if (!node_isset(mb->nid, reserved_nodemask)) + continue; - memblock_clear_hotplug(start, end - start); + memblock_clear_hotplug(mb->start, mb->end - mb->start); } } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 9cf96d82147a8..007ebe2d81572 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -283,7 +283,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, __pa_symbol(__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) /* * Once the kernel maps the text as RO (kernel_set_to_readonly is set), * kernel text mappings for the large page aligned text, rodata sections @@ -1128,8 +1128,10 @@ static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, /* * Ignore all non primary paths. */ - if (!primary) + if (!primary) { + cpa->numpages = 1; return 0; + } /* * Ignore the NULL PTE for kernel identity mapping, as it is expected diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index f4ae536b0914d..04e2e7144beee 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -943,7 +943,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, return -EINVAL; } - *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | + *prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) | cachemode2protval(pcm)); return 0; @@ -959,7 +959,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, /* Set prot based on lookup */ pcm = lookup_memtype(pfn_t_to_phys(pfn)); - *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | + *prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) | cachemode2protval(pcm)); return 0; diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 92e2eacb33216..8bea84724a7da 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -4,6 +4,7 @@ #include #include +#include static int disable_nx; @@ -31,9 +32,8 @@ early_param("noexec", noexec_setup); void x86_configure_nx(void) { - if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) - __supported_pte_mask |= _PAGE_NX; - else + /* If disable_nx is set, clear NX on all new mappings going forward. */ + if (disable_nx) __supported_pte_mask &= ~_PAGE_NX; } diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 50d86c0e9ba49..660a83c8287b6 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -24,7 +24,6 @@ #include #include #include -#include #include "op_x86_model.h" #include "op_counter.h" diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 2d66db8f80f99..ed30e79347e86 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -130,6 +130,27 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) } EXPORT_SYMBOL_GPL(efi_query_variable_store); +/* + * Helper function for efi_reserve_boot_services() to figure out if we + * can free regions in efi_free_boot_services(). + * + * Use this function to ensure we do not free regions owned by somebody + * else. We must only reserve (and then free) regions: + * + * - Not within any part of the kernel + * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc) + */ +static bool can_free_region(u64 start, u64 size) +{ + if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) + return false; + + if (!e820_all_mapped(start, start+size, E820_RAM)) + return false; + + return true; +} + /* * The UEFI specification makes it clear that the operating system is free to do * whatever it wants with boot services code after ExitBootServices() has been @@ -147,26 +168,50 @@ void __init efi_reserve_boot_services(void) efi_memory_desc_t *md = p; u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; + bool already_reserved; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Only reserve where possible: - * - Not within any already allocated areas - * - Not over any memory area (really needed, if above?) - * - Not within any part of the kernel - * - Not the bios reserved area - */ - if ((start + size > __pa_symbol(_text) - && start <= __pa_symbol(_end)) || - !e820_all_mapped(start, start+size, E820_RAM) || - memblock_is_region_reserved(start, size)) { - /* Could not reserve, skip it */ - md->num_pages = 0; - memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", - start, start+size-1); - } else + + already_reserved = memblock_is_region_reserved(start, size); + + /* + * Because the following memblock_reserve() is paired + * with free_bootmem_late() for this region in + * efi_free_boot_services(), we must be extremely + * careful not to reserve, and subsequently free, + * critical regions of memory (like the kernel image) or + * those regions that somebody else has already + * reserved. + * + * A good example of a critical region that must not be + * freed is page zero (first 4Kb of memory), which may + * contain boot services code/data but is marked + * E820_RESERVED by trim_bios_range(). + */ + if (!already_reserved) { memblock_reserve(start, size); + + /* + * If we are the first to reserve the region, no + * one else cares about it. We own it and can + * free it later. + */ + if (can_free_region(start, size)) + continue; + } + + /* + * We don't own the region. We must not free it. + * + * Setting this bit for a boot services region really + * doesn't make sense as far as the firmware is + * concerned, but it does provide us with a way to tag + * those regions that must not be paired with + * free_bootmem_late(). + */ + md->attribute |= EFI_MEMORY_RUNTIME; } } @@ -183,8 +228,8 @@ void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Could not reserve boot area */ - if (!size) + /* Do not free, someone else owns it: */ + if (md->attribute & EFI_MEMORY_RUNTIME) continue; free_bootmem_late(start, size); diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c index 76b6632d31433..1865c196f1363 100644 --- a/arch/x86/platform/geode/alix.c +++ b/arch/x86/platform/geode/alix.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include #include @@ -35,6 +35,11 @@ #define BIOS_SIGNATURE_COREBOOT 0x500 #define BIOS_REGION_SIZE 0x10000 +/* + * This driver is not modular, but to keep back compatibility + * with existing use cases, continuing with module_param is + * the easiest way forward. + */ static bool force = 0; module_param(force, bool, 0444); /* FIXME: Award bios is not automatically detected as Alix platform */ @@ -192,9 +197,4 @@ static int __init alix_init(void) return 0; } - -module_init(alix_init); - -MODULE_AUTHOR("Ed Wildgoose "); -MODULE_DESCRIPTION("PCEngines ALIX System Setup"); -MODULE_LICENSE("GPL"); +device_initcall(alix_init); diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c index aa733fba24712..4fcdb91318a08 100644 --- a/arch/x86/platform/geode/geos.c +++ b/arch/x86/platform/geode/geos.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -120,9 +119,4 @@ static int __init geos_init(void) return 0; } - -module_init(geos_init); - -MODULE_AUTHOR("Philip Prindeville "); -MODULE_DESCRIPTION("Traverse Technologies Geos System Setup"); -MODULE_LICENSE("GPL"); +device_initcall(geos_init); diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c index 927e38c0089fa..a2f6b982a7295 100644 --- a/arch/x86/platform/geode/net5501.c +++ b/arch/x86/platform/geode/net5501.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -146,9 +145,4 @@ static int __init net5501_init(void) return 0; } - -module_init(net5501_init); - -MODULE_AUTHOR("Philip Prindeville "); -MODULE_DESCRIPTION("Soekris net5501 System Setup"); -MODULE_LICENSE("GPL"); +device_initcall(net5501_init); diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c index 23381d2174ae1..1eb47b6298c20 100644 --- a/arch/x86/platform/intel-mid/mfld.c +++ b/arch/x86/platform/intel-mid/mfld.c @@ -52,10 +52,7 @@ static unsigned long __init mfld_calibrate_tsc(void) /* mark tsc clocksource as reliable */ set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE); - if (fast_calibrate) - return fast_calibrate; - - return 0; + return fast_calibrate; } static void __init penwell_arch_setup(void) diff --git a/arch/x86/platform/intel-mid/mrfl.c b/arch/x86/platform/intel-mid/mrfl.c index aaca91753d326..bd1adc6217811 100644 --- a/arch/x86/platform/intel-mid/mrfl.c +++ b/arch/x86/platform/intel-mid/mrfl.c @@ -81,10 +81,7 @@ static unsigned long __init tangier_calibrate_tsc(void) /* mark tsc clocksource as reliable */ set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE); - if (fast_calibrate) - return fast_calibrate; - - return 0; + return fast_calibrate; } static void __init tangier_arch_setup(void) diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index bfadcd0f49442..17d6d2296e4d8 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -1,5 +1,5 @@ /** - * imr.c + * imr.c -- Intel Isolated Memory Region driver * * Copyright(c) 2013 Intel Corporation. * Copyright(c) 2015 Bryan O'Donoghue @@ -31,7 +31,6 @@ #include #include #include -#include #include struct imr_device { @@ -135,11 +134,9 @@ static int imr_read(struct imr_device *idev, u32 imr_id, struct imr_regs *imr) * @idev: pointer to imr_device structure. * @imr_id: IMR entry to write. * @imr: IMR structure representing address and access masks. - * @lock: indicates if the IMR lock bit should be applied. * @return: 0 on success or error code passed from mbi_iosf on failure. */ -static int imr_write(struct imr_device *idev, u32 imr_id, - struct imr_regs *imr, bool lock) +static int imr_write(struct imr_device *idev, u32 imr_id, struct imr_regs *imr) { unsigned long flags; u32 reg = imr_id * IMR_NUM_REGS + idev->reg_base; @@ -163,15 +160,6 @@ static int imr_write(struct imr_device *idev, u32 imr_id, if (ret) goto failed; - /* Lock bit must be set separately to addr_lo address bits. */ - if (lock) { - imr->addr_lo |= IMR_LOCK; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, - reg - IMR_NUM_REGS, imr->addr_lo); - if (ret) - goto failed; - } - local_irq_restore(flags); return 0; failed: @@ -269,17 +257,6 @@ static int imr_debugfs_register(struct imr_device *idev) return PTR_ERR_OR_ZERO(idev->file); } -/** - * imr_debugfs_unregister - unregister debugfs hooks. - * - * @idev: pointer to imr_device structure. - * @return: - */ -static void imr_debugfs_unregister(struct imr_device *idev) -{ - debugfs_remove(idev->file); -} - /** * imr_check_params - check passed address range IMR alignment and non-zero size * @@ -334,11 +311,10 @@ static inline int imr_address_overlap(phys_addr_t addr, struct imr_regs *imr) * @size: physical size of region in bytes must be aligned to 1KiB. * @read_mask: read access mask. * @write_mask: write access mask. - * @lock: indicates whether or not to permanently lock this region. * @return: zero on success or negative value indicating error. */ int imr_add_range(phys_addr_t base, size_t size, - unsigned int rmask, unsigned int wmask, bool lock) + unsigned int rmask, unsigned int wmask) { phys_addr_t end; unsigned int i; @@ -411,7 +387,7 @@ int imr_add_range(phys_addr_t base, size_t size, imr.rmask = rmask; imr.wmask = wmask; - ret = imr_write(idev, reg, &imr, lock); + ret = imr_write(idev, reg, &imr); if (ret < 0) { /* * In the highly unlikely event iosf_mbi_write failed @@ -422,7 +398,7 @@ int imr_add_range(phys_addr_t base, size_t size, imr.addr_hi = 0; imr.rmask = IMR_READ_ACCESS_ALL; imr.wmask = IMR_WRITE_ACCESS_ALL; - imr_write(idev, reg, &imr, false); + imr_write(idev, reg, &imr); } failed: mutex_unlock(&idev->lock); @@ -518,7 +494,7 @@ static int __imr_remove_range(int reg, phys_addr_t base, size_t size) imr.rmask = IMR_READ_ACCESS_ALL; imr.wmask = IMR_WRITE_ACCESS_ALL; - ret = imr_write(idev, reg, &imr, false); + ret = imr_write(idev, reg, &imr); failed: mutex_unlock(&idev->lock); @@ -599,7 +575,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev) * We don't round up @size since it is already PAGE_SIZE aligned. * See vmlinux.lds.S for details. */ - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU); if (ret < 0) { pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n", size / 1024, start, end); @@ -614,7 +590,6 @@ static const struct x86_cpu_id imr_ids[] __initconst = { { X86_VENDOR_INTEL, 5, 9 }, /* Intel Quark SoC X1000. */ {} }; -MODULE_DEVICE_TABLE(x86cpu, imr_ids); /** * imr_init - entry point for IMR driver. @@ -640,22 +615,4 @@ static int __init imr_init(void) imr_fixup_memmap(idev); return 0; } - -/** - * imr_exit - exit point for IMR code. - * - * Deregisters debugfs, leave IMR state as-is. - * - * return: - */ -static void __exit imr_exit(void) -{ - imr_debugfs_unregister(&imr_dev); -} - -module_init(imr_init); -module_exit(imr_exit); - -MODULE_AUTHOR("Bryan O'Donoghue "); -MODULE_DESCRIPTION("Intel Isolated Memory Region driver"); -MODULE_LICENSE("Dual BSD/GPL"); +device_initcall(imr_init); diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index 278e4da4222f7..f5bad40936ac5 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -1,5 +1,5 @@ /** - * imr_selftest.c + * imr_selftest.c -- Intel Isolated Memory Region self-test driver * * Copyright(c) 2013 Intel Corporation. * Copyright(c) 2015 Bryan O'Donoghue @@ -15,7 +15,6 @@ #include #include #include -#include #include #define SELFTEST KBUILD_MODNAME ": " @@ -61,30 +60,30 @@ static void __init imr_self_test(void) int ret; /* Test zero zero. */ - ret = imr_add_range(0, 0, 0, 0, false); + ret = imr_add_range(0, 0, 0, 0); imr_self_test_result(ret < 0, "zero sized IMR\n"); /* Test exact overlap. */ - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU); imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size)); /* Test overlap with base inside of existing. */ base += size - IMR_ALIGN; - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU); imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size)); /* Test overlap with end inside of existing. */ base -= size + IMR_ALIGN * 2; - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU); imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size)); /* Test that a 1 KiB IMR @ zero with read/write all will bomb out. */ ret = imr_add_range(0, IMR_ALIGN, IMR_READ_ACCESS_ALL, - IMR_WRITE_ACCESS_ALL, false); + IMR_WRITE_ACCESS_ALL); imr_self_test_result(ret < 0, "1KiB IMR @ 0x00000000 - access-all\n"); /* Test that a 1 KiB IMR @ zero with CPU only will work. */ - ret = imr_add_range(0, IMR_ALIGN, IMR_CPU, IMR_CPU, false); + ret = imr_add_range(0, IMR_ALIGN, IMR_CPU, IMR_CPU); imr_self_test_result(ret >= 0, "1KiB IMR @ 0x00000000 - cpu-access\n"); if (ret >= 0) { ret = imr_remove_range(0, IMR_ALIGN); @@ -93,8 +92,7 @@ static void __init imr_self_test(void) /* Test 2 KiB works. */ size = IMR_ALIGN * 2; - ret = imr_add_range(0, size, IMR_READ_ACCESS_ALL, - IMR_WRITE_ACCESS_ALL, false); + ret = imr_add_range(0, size, IMR_READ_ACCESS_ALL, IMR_WRITE_ACCESS_ALL); imr_self_test_result(ret >= 0, "2KiB IMR @ 0x00000000\n"); if (ret >= 0) { ret = imr_remove_range(0, size); @@ -106,7 +104,6 @@ static const struct x86_cpu_id imr_ids[] __initconst = { { X86_VENDOR_INTEL, 5, 9 }, /* Intel Quark SoC X1000. */ {} }; -MODULE_DEVICE_TABLE(x86cpu, imr_ids); /** * imr_self_test_init - entry point for IMR driver. @@ -125,13 +122,4 @@ static int __init imr_self_test_init(void) * * return: */ -static void __exit imr_self_test_exit(void) -{ -} - -module_init(imr_self_test_init); -module_exit(imr_self_test_exit); - -MODULE_AUTHOR("Bryan O'Donoghue "); -MODULE_DESCRIPTION("Intel Isolated Memory Region self-test driver"); -MODULE_LICENSE("Dual BSD/GPL"); +device_initcall(imr_self_test_init); diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 174781a404ff3..00c319048d52d 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -3,7 +3,7 @@ #include #include -#include +#include #include #include diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c index 8502ad30e61bc..5adb6a2fd117d 100644 --- a/arch/x86/um/os-Linux/task_size.c +++ b/arch/x86/um/os-Linux/task_size.c @@ -109,7 +109,7 @@ unsigned long os_get_top_address(void) exit(1); } - printf("0x%x\n", bottom << UM_KERN_PAGE_SHIFT); + printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT); printf("Locating the top of the address space ... "); fflush(stdout); @@ -134,7 +134,7 @@ unsigned long os_get_top_address(void) exit(1); } top <<= UM_KERN_PAGE_SHIFT; - printf("0x%x\n", top); + printf("0x%lx\n", top); return top; } diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 439c0994b6968..bfce503dffae2 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -25,11 +25,11 @@ #define old_mmap sys_old_mmap -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include #undef __SYSCALL_I386 -#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym, +#define __SYSCALL_I386(nr, sym, qual) [ nr ] = sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index b74ea6c2c0e7b..f306413d3eb6e 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -35,14 +35,11 @@ #define stub_execveat sys_execveat #define stub_rt_sigreturn sys_rt_sigreturn -#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) -#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ - -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, compat) [ nr ] = sym, +#define __SYSCALL_64(nr, sym, qual) [ nr ] = sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index ce7e3607a870f..470564bbd08ea 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -9,14 +9,12 @@ #include #ifdef __i386__ -#define __SYSCALL_I386(nr, sym, compat) [nr] = 1, +#define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls[] = { #include }; #else -#define __SYSCALL_64(nr, sym, compat) [nr] = 1, -#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1, -#define __SYSCALL_X32(nr, sym, compat) /* Not supported */ +#define __SYSCALL_64(nr, sym, qual) [nr] = 1, static char syscalls[] = { #include }; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index d09e4c9d7cc5b..2c261082eadf8 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1654,7 +1654,7 @@ asmlinkage __visible void __init xen_start_kernel(void) cpu_detect(&new_cpu_data); set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); new_cpu_data.wp_works_ok = 1; - new_cpu_data.x86_capability[0] = cpuid_edx(1); + new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); #endif if (xen_start_info->mod_start) { diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 724a08740a04b..9466354d3e496 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -11,7 +11,7 @@ #include "pmu.h" /* x86_pmu.handle_irq definition */ -#include "../kernel/cpu/perf_event.h" +#include "../events/perf_event.h" #define XENPMU_IRQ_PROCESSING 1 struct xenpmu { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 3f4ebf0261f28..3c6d17fd423a8 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -112,7 +112,7 @@ asmlinkage __visible void cpu_bringup_and_idle(int cpu) xen_pvh_secondary_vcpu_init(cpu); #endif cpu_bringup(); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } static void xen_smp_intr_free(unsigned int cpu) diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 4d02e38514f54..fc4ad21a5ed44 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -157,7 +157,7 @@ void secondary_start_kernel(void) complete(&cpu_running); - cpu_startup_entry(CPUHP_ONLINE); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } static void mx_cpu_start(void *p) diff --git a/block/blk-map.c b/block/blk-map.c index f565e11f465aa..a54f0543b956e 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -57,6 +57,49 @@ static int __blk_rq_unmap_user(struct bio *bio) return ret; } +static int __blk_rq_map_user_iov(struct request *rq, + struct rq_map_data *map_data, struct iov_iter *iter, + gfp_t gfp_mask, bool copy) +{ + struct request_queue *q = rq->q; + struct bio *bio, *orig_bio; + int ret; + + if (copy) + bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); + else + bio = bio_map_user_iov(q, iter, gfp_mask); + + if (IS_ERR(bio)) + return PTR_ERR(bio); + + if (map_data && map_data->null_mapped) + bio_set_flag(bio, BIO_NULL_MAPPED); + + iov_iter_advance(iter, bio->bi_iter.bi_size); + if (map_data) + map_data->offset += bio->bi_iter.bi_size; + + orig_bio = bio; + blk_queue_bounce(q, &bio); + + /* + * We link the bounce buffer in and could have to traverse it + * later so we have to get a ref to prevent it from being freed + */ + bio_get(bio); + + ret = blk_rq_append_bio(q, rq, bio); + if (ret) { + bio_endio(bio); + __blk_rq_unmap_user(orig_bio); + bio_put(bio); + return ret; + } + + return 0; +} + /** * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage * @q: request queue where request should be inserted @@ -82,10 +125,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { - struct bio *bio; - int unaligned = 0; - struct iov_iter i; struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0}; + bool copy = (q->dma_pad_mask & iter->count) || map_data; + struct bio *bio = NULL; + struct iov_iter i; + int ret; if (!iter || !iter->count) return -EINVAL; @@ -101,42 +145,29 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, */ if ((uaddr & queue_dma_alignment(q)) || iovec_gap_to_prv(q, &prv, &iov)) - unaligned = 1; + copy = true; prv.iov_base = iov.iov_base; prv.iov_len = iov.iov_len; } - if (unaligned || (q->dma_pad_mask & iter->count) || map_data) - bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); - else - bio = bio_map_user_iov(q, iter, gfp_mask); - - if (IS_ERR(bio)) - return PTR_ERR(bio); - - if (map_data && map_data->null_mapped) - bio_set_flag(bio, BIO_NULL_MAPPED); - - if (bio->bi_iter.bi_size != iter->count) { - /* - * Grab an extra reference to this bio, as bio_unmap_user() - * expects to be able to drop it twice as it happens on the - * normal IO completion path - */ - bio_get(bio); - bio_endio(bio); - __blk_rq_unmap_user(bio); - return -EINVAL; - } + i = *iter; + do { + ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy); + if (ret) + goto unmap_rq; + if (!bio) + bio = rq->bio; + } while (iov_iter_count(&i)); if (!bio_flagged(bio, BIO_USER_MAPPED)) rq->cmd_flags |= REQ_COPY_USER; - - blk_queue_bounce(q, &bio); - bio_get(bio); - blk_rq_bio_prep(q, rq, bio); return 0; + +unmap_rq: + __blk_rq_unmap_user(bio); + rq->bio = NULL; + return -EINVAL; } EXPORT_SYMBOL(blk_rq_map_user_iov); diff --git a/block/blk-merge.c b/block/blk-merge.c index 888a7fec81f71..261353166dcf3 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -304,7 +304,6 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { struct bio_vec end_bv = { NULL }, nxt_bv; - struct bvec_iter iter; if (!blk_queue_cluster(q)) return 0; @@ -316,11 +315,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, if (!bio_has_data(bio)) return 1; - bio_for_each_segment(end_bv, bio, iter) - if (end_bv.bv_len == iter.bi_size) - break; - - nxt_bv = bio_iovec(nxt); + bio_get_last_bvec(bio, &end_bv); + bio_get_first_bvec(nxt, &nxt_bv); if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv)) return 0; diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index 296b7a14893aa..b6f7fa3a1d403 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -62,7 +62,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev) if (count < 0) { return NULL; } else if (count > 0) { - resources = kmalloc(count * sizeof(struct resource), + resources = kzalloc(count * sizeof(struct resource), GFP_KERNEL); if (!resources) { dev_err(&adev->dev, "No memory for resources\n"); diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index 305218539df28..d48cbed342c1d 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -269,8 +269,7 @@ acpi_ps_get_next_namepath(struct acpi_walk_state *walk_state, */ if (ACPI_SUCCESS(status) && possible_method_call && (node->type == ACPI_TYPE_METHOD)) { - if (GET_CURRENT_ARG_TYPE(walk_state->arg_types) == - ARGP_SUPERNAME) { + if (walk_state->opcode == AML_UNLOAD_OP) { /* * acpi_ps_get_next_namestring has increased the AML pointer, * so we need to restore the saved AML pointer for method call. @@ -697,7 +696,7 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state * * PARAMETERS: walk_state - Current state * parser_state - Current parser state object - * arg_type - The parser argument type (ARGP_*) + * arg_type - The argument type (AML_*_ARG) * return_arg - Where the next arg is returned * * RETURN: Status, and an op object containing the next argument. @@ -817,9 +816,9 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state, return_ACPI_STATUS(AE_NO_MEMORY); } - /* super_name allows argument to be a method call */ + /* To support super_name arg of Unload */ - if (arg_type == ARGP_SUPERNAME) { + if (walk_state->opcode == AML_UNLOAD_OP) { status = acpi_ps_get_next_namepath(walk_state, parser_state, arg, diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index 0431883653bed..559c1173de1c9 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -519,7 +519,7 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3, u64 param4) { int rc; - unsigned long pfn; + u64 base_addr, size; /* If user manually set "flags", make sure it is legal */ if (flags && (flags & @@ -545,10 +545,17 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, /* * Disallow crazy address masks that give BIOS leeway to pick * injection address almost anywhere. Insist on page or - * better granularity and that target address is normal RAM. + * better granularity and that target address is normal RAM or + * NVDIMM. */ - pfn = PFN_DOWN(param1 & param2); - if (!page_is_ram(pfn) || ((param2 & PAGE_MASK) != PAGE_MASK)) + base_addr = param1 & param2; + size = ~param2 + 1; + + if (((param2 & PAGE_MASK) != PAGE_MASK) || + ((region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE) + != REGION_INTERSECTS) && + (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY) + != REGION_INTERSECTS))) return -EINVAL; inject: diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index fb53db1878544..35947ac876445 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1590,14 +1590,21 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, start = ndr_desc->res->start; len = ndr_desc->res->end - ndr_desc->res->start + 1; + /* + * If ARS is unimplemented, unsupported, or if the 'Persistent Memory + * Scrub' flag in extended status is not set, skip this but continue + * initialization + */ rc = ars_get_cap(nd_desc, ars_cap, start, len); + if (rc == -ENOTTY) { + dev_dbg(acpi_desc->dev, + "Address Range Scrub is not implemented, won't create an error list\n"); + rc = 0; + goto out; + } if (rc) goto out; - /* - * If ARS is unsupported, or if the 'Persistent Memory Scrub' flag in - * extended status is not set, skip this but continue initialization - */ if ((ars_cap->status & 0xffff) || !(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) { dev_warn(acpi_desc->dev, diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 546a3692774f8..146dc0b8ec617 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -367,15 +367,21 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d2), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d6), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -1325,6 +1331,44 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host) {} #endif +#ifdef CONFIG_ARM64 +/* + * Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently. + * Workaround is to make sure all pending IRQs are served before leaving + * handler. + */ +static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv; + unsigned int rc = 0; + void __iomem *mmio; + u32 irq_stat, irq_masked; + unsigned int handled = 1; + + VPRINTK("ENTER\n"); + hpriv = host->private_data; + mmio = hpriv->mmio; + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + do { + irq_masked = irq_stat & hpriv->port_map; + spin_lock(&host->lock); + rc = ahci_handle_port_intr(host, irq_masked); + if (!rc) + handled = 0; + writel(irq_stat, mmio + HOST_IRQ_STAT); + irq_stat = readl(mmio + HOST_IRQ_STAT); + spin_unlock(&host->lock); + } while (irq_stat); + VPRINTK("EXIT\n"); + + return IRQ_RETVAL(handled); +} +#endif + /* * ahci_init_msix() - optionally enable per-port MSI-X otherwise defer * to single msi. @@ -1560,6 +1604,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ahci_broken_devslp(pdev)) hpriv->flags |= AHCI_HFLAG_NO_DEVSLP; +#ifdef CONFIG_ARM64 + if (pdev->vendor == 0x177d && pdev->device == 0xa01c) + hpriv->irq_handler = ahci_thunderx_irq_handler; +#endif + /* save initial config */ ahci_pci_save_initial_config(pdev, hpriv); diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index a44c75d4c2845..167ba7e3b92e8 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -240,8 +240,7 @@ enum { error-handling stage) */ AHCI_HFLAG_NO_DEVSLP = (1 << 17), /* no device sleep */ AHCI_HFLAG_NO_FBS = (1 << 18), /* no FBS */ - AHCI_HFLAG_EDGE_IRQ = (1 << 19), /* HOST_IRQ_STAT behaves as - Edge Triggered */ + #ifdef CONFIG_PCI_MSI AHCI_HFLAG_MULTI_MSI = (1 << 20), /* multiple PCI MSIs */ AHCI_HFLAG_MULTI_MSIX = (1 << 21), /* per-port MSI-X */ @@ -361,6 +360,7 @@ struct ahci_host_priv { * be overridden anytime before the host is activated. */ void (*start_engine)(struct ata_port *ap); + irqreturn_t (*irq_handler)(int irq, void *dev_instance); }; #ifdef CONFIG_PCI_MSI @@ -424,6 +424,7 @@ int ahci_reset_em(struct ata_host *host); void ahci_print_info(struct ata_host *host, const char *scc_s); int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht); void ahci_error_handler(struct ata_port *ap); +u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked); static inline void __iomem *__ahci_port_base(struct ata_host *host, unsigned int port_no) diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index e2c6d9e0c5ac5..8e3f7faf00d38 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -548,6 +548,88 @@ static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class, return rc; } +/** + * xgene_ahci_handle_broken_edge_irq - Handle the broken irq. + * @ata_host: Host that recieved the irq + * @irq_masked: HOST_IRQ_STAT value + * + * For hardware with broken edge trigger latch + * the HOST_IRQ_STAT register misses the edge interrupt + * when clearing of HOST_IRQ_STAT register and hardware + * reporting the PORT_IRQ_STAT register at the + * same clock cycle. + * As such, the algorithm below outlines the workaround. + * + * 1. Read HOST_IRQ_STAT register and save the state. + * 2. Clear the HOST_IRQ_STAT register. + * 3. Read back the HOST_IRQ_STAT register. + * 4. If HOST_IRQ_STAT register equals to zero, then + * traverse the rest of port's PORT_IRQ_STAT register + * to check if an interrupt is triggered at that point else + * go to step 6. + * 5. If PORT_IRQ_STAT register of rest ports is not equal to zero + * then update the state of HOST_IRQ_STAT saved in step 1. + * 6. Handle port interrupts. + * 7. Exit + */ +static int xgene_ahci_handle_broken_edge_irq(struct ata_host *host, + u32 irq_masked) +{ + struct ahci_host_priv *hpriv = host->private_data; + void __iomem *port_mmio; + int i; + + if (!readl(hpriv->mmio + HOST_IRQ_STAT)) { + for (i = 0; i < host->n_ports; i++) { + if (irq_masked & (1 << i)) + continue; + + port_mmio = ahci_port_base(host->ports[i]); + if (readl(port_mmio + PORT_IRQ_STAT)) + irq_masked |= (1 << i); + } + } + + return ahci_handle_port_intr(host, irq_masked); +} + +static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv; + unsigned int rc = 0; + void __iomem *mmio; + u32 irq_stat, irq_masked; + + VPRINTK("ENTER\n"); + + hpriv = host->private_data; + mmio = hpriv->mmio; + + /* sigh. 0xffffffff is a valid return from h/w */ + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + irq_masked = irq_stat & hpriv->port_map; + + spin_lock(&host->lock); + + /* + * HOST_IRQ_STAT behaves as edge triggered latch meaning that + * it should be cleared before all the port events are cleared. + */ + writel(irq_stat, mmio + HOST_IRQ_STAT); + + rc = xgene_ahci_handle_broken_edge_irq(host, irq_masked); + + spin_unlock(&host->lock); + + VPRINTK("EXIT\n"); + + return IRQ_RETVAL(rc); +} + static struct ata_port_operations xgene_ahci_v1_ops = { .inherits = &ahci_ops, .host_stop = xgene_ahci_host_stop, @@ -779,7 +861,8 @@ static int xgene_ahci_probe(struct platform_device *pdev) hpriv->flags = AHCI_HFLAG_NO_NCQ; break; case XGENE_AHCI_V2: - hpriv->flags |= AHCI_HFLAG_YES_FBS | AHCI_HFLAG_EDGE_IRQ; + hpriv->flags |= AHCI_HFLAG_YES_FBS; + hpriv->irq_handler = xgene_ahci_irq_intr; break; default: break; diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 402967902cbe3..85ea5142a0951 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -113,6 +113,7 @@ static ssize_t ahci_store_em_buffer(struct device *dev, const char *buf, size_t size); static ssize_t ahci_show_em_supported(struct device *dev, struct device_attribute *attr, char *buf); +static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance); static DEVICE_ATTR(ahci_host_caps, S_IRUGO, ahci_show_host_caps, NULL); static DEVICE_ATTR(ahci_host_cap2, S_IRUGO, ahci_show_host_cap2, NULL); @@ -512,6 +513,9 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) if (!hpriv->start_engine) hpriv->start_engine = ahci_start_engine; + + if (!hpriv->irq_handler) + hpriv->irq_handler = ahci_single_level_irq_intr; } EXPORT_SYMBOL_GPL(ahci_save_initial_config); @@ -1164,8 +1168,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); - if ((tmp & PORT_CMD_HPCP) || - ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS))) + if ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)) ap->pflags |= ATA_PFLAG_EXTERNAL; } @@ -1846,7 +1849,7 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance) return IRQ_HANDLED; } -static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) +u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) { unsigned int i, handled = 0; @@ -1872,43 +1875,7 @@ static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) return handled; } - -static irqreturn_t ahci_single_edge_irq_intr(int irq, void *dev_instance) -{ - struct ata_host *host = dev_instance; - struct ahci_host_priv *hpriv; - unsigned int rc = 0; - void __iomem *mmio; - u32 irq_stat, irq_masked; - - VPRINTK("ENTER\n"); - - hpriv = host->private_data; - mmio = hpriv->mmio; - - /* sigh. 0xffffffff is a valid return from h/w */ - irq_stat = readl(mmio + HOST_IRQ_STAT); - if (!irq_stat) - return IRQ_NONE; - - irq_masked = irq_stat & hpriv->port_map; - - spin_lock(&host->lock); - - /* - * HOST_IRQ_STAT behaves as edge triggered latch meaning that - * it should be cleared before all the port events are cleared. - */ - writel(irq_stat, mmio + HOST_IRQ_STAT); - - rc = ahci_handle_port_intr(host, irq_masked); - - spin_unlock(&host->lock); - - VPRINTK("EXIT\n"); - - return IRQ_RETVAL(rc); -} +EXPORT_SYMBOL_GPL(ahci_handle_port_intr); static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance) { @@ -2535,14 +2502,18 @@ int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht) int irq = hpriv->irq; int rc; - if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) + if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) { + if (hpriv->irq_handler) + dev_warn(host->dev, "both AHCI_HFLAG_MULTI_MSI flag set \ + and custom irq handler implemented\n"); + rc = ahci_host_activate_multi_irqs(host, sht); - else if (hpriv->flags & AHCI_HFLAG_EDGE_IRQ) - rc = ata_host_activate(host, irq, ahci_single_edge_irq_intr, - IRQF_SHARED, sht); - else - rc = ata_host_activate(host, irq, ahci_single_level_irq_intr, + } else { + rc = ata_host_activate(host, irq, hpriv->irq_handler, IRQF_SHARED, sht); + } + + return rc; } EXPORT_SYMBOL_GPL(ahci_host_activate); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7e959f90c0203..e417e1a1d02c5 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -675,19 +675,18 @@ static int ata_ioc32(struct ata_port *ap) int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev, int cmd, void __user *arg) { - int val = -EINVAL, rc = -EINVAL; + unsigned long val; + int rc = -EINVAL; unsigned long flags; switch (cmd) { - case ATA_IOC_GET_IO32: + case HDIO_GET_32BIT: spin_lock_irqsave(ap->lock, flags); val = ata_ioc32(ap); spin_unlock_irqrestore(ap->lock, flags); - if (copy_to_user(arg, &val, 1)) - return -EFAULT; - return 0; + return put_user(val, (unsigned long __user *)arg); - case ATA_IOC_SET_IO32: + case HDIO_SET_32BIT: val = (unsigned long) arg; rc = 0; spin_lock_irqsave(ap->lock, flags); diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c index 12fe0f3bb7e9b..c8b6a780a2905 100644 --- a/drivers/ata/pata_rb532_cf.c +++ b/drivers/ata/pata_rb532_cf.c @@ -32,6 +32,8 @@ #include #include +#include + #define DRV_NAME "pata-rb532-cf" #define DRV_VERSION "0.1.0" #define DRV_DESC "PATA driver for RouterBOARD 532 Compact Flash" @@ -107,6 +109,7 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) int gpio; struct resource *res; struct ata_host *ah; + struct cf_device *pdata; struct rb532_cf_info *info; int ret; @@ -122,7 +125,13 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) return -ENOENT; } - gpio = irq_to_gpio(irq); + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + dev_err(&pdev->dev, "no platform data specified\n"); + return -EINVAL; + } + + gpio = pdata->gpio_pin; if (gpio < 0) { dev_err(&pdev->dev, "no GPIO found for irq%d\n", irq); return -ENOENT; diff --git a/drivers/base/property.c b/drivers/base/property.c index c359351d50f1c..a163f2c59aa36 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -218,7 +218,7 @@ bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname) bool ret; ret = __fwnode_property_present(fwnode, propname); - if (ret == false && fwnode && fwnode->secondary) + if (ret == false && fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) ret = __fwnode_property_present(fwnode->secondary, propname); return ret; } @@ -423,7 +423,7 @@ EXPORT_SYMBOL_GPL(device_property_match_string); int _ret_; \ _ret_ = FWNODE_PROP_READ(_fwnode_, _propname_, _type_, _proptype_, \ _val_, _nval_); \ - if (_ret_ == -EINVAL && _fwnode_ && _fwnode_->secondary) \ + if (_ret_ == -EINVAL && _fwnode_ && !IS_ERR_OR_NULL(_fwnode_->secondary)) \ _ret_ = FWNODE_PROP_READ(_fwnode_->secondary, _propname_, _type_, \ _proptype_, _val_, _nval_); \ _ret_; \ @@ -593,7 +593,7 @@ int fwnode_property_read_string_array(struct fwnode_handle *fwnode, int ret; ret = __fwnode_property_read_string_array(fwnode, propname, val, nval); - if (ret == -EINVAL && fwnode && fwnode->secondary) + if (ret == -EINVAL && fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) ret = __fwnode_property_read_string_array(fwnode->secondary, propname, val, nval); return ret; @@ -621,7 +621,7 @@ int fwnode_property_read_string(struct fwnode_handle *fwnode, int ret; ret = __fwnode_property_read_string(fwnode, propname, val); - if (ret == -EINVAL && fwnode && fwnode->secondary) + if (ret == -EINVAL && fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) ret = __fwnode_property_read_string(fwnode->secondary, propname, val); return ret; diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 33db7406c0e27..c346be650892a 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -160,6 +160,7 @@ config CLKSRC_EFM32 config CLKSRC_LPC32XX bool "Clocksource for LPC32XX" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS && HAS_IOMEM + depends on ARM select CLKSRC_MMIO select CLKSRC_OF help diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index c64d543d64bf6..f0dd9d42bc7b1 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -32,6 +32,14 @@ #define CNTTIDR 0x08 #define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4)) +#define CNTACR(n) (0x40 + ((n) * 4)) +#define CNTACR_RPCT BIT(0) +#define CNTACR_RVCT BIT(1) +#define CNTACR_RFRQ BIT(2) +#define CNTACR_RVOFF BIT(3) +#define CNTACR_RWVT BIT(4) +#define CNTACR_RWPT BIT(5) + #define CNTVCT_LO 0x08 #define CNTVCT_HI 0x0c #define CNTFRQ 0x10 @@ -266,10 +274,12 @@ static void __arch_timer_setup(unsigned type, if (arch_timer_use_virtual) { clk->irq = arch_timer_ppi[VIRT_PPI]; clk->set_state_shutdown = arch_timer_shutdown_virt; + clk->set_state_oneshot_stopped = arch_timer_shutdown_virt; clk->set_next_event = arch_timer_set_next_event_virt; } else { clk->irq = arch_timer_ppi[PHYS_SECURE_PPI]; clk->set_state_shutdown = arch_timer_shutdown_phys; + clk->set_state_oneshot_stopped = arch_timer_shutdown_phys; clk->set_next_event = arch_timer_set_next_event_phys; } } else { @@ -279,10 +289,12 @@ static void __arch_timer_setup(unsigned type, clk->cpumask = cpu_all_mask; if (arch_timer_mem_use_virtual) { clk->set_state_shutdown = arch_timer_shutdown_virt_mem; + clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem; clk->set_next_event = arch_timer_set_next_event_virt_mem; } else { clk->set_state_shutdown = arch_timer_shutdown_phys_mem; + clk->set_state_oneshot_stopped = arch_timer_shutdown_phys_mem; clk->set_next_event = arch_timer_set_next_event_phys_mem; } @@ -757,7 +769,6 @@ static void __init arch_timer_mem_init(struct device_node *np) } cnttidr = readl_relaxed(cntctlbase + CNTTIDR); - iounmap(cntctlbase); /* * Try to find a virtual capable frame. Otherwise fall back to a @@ -765,20 +776,31 @@ static void __init arch_timer_mem_init(struct device_node *np) */ for_each_available_child_of_node(np, frame) { int n; + u32 cntacr; if (of_property_read_u32(frame, "frame-number", &n)) { pr_err("arch_timer: Missing frame-number\n"); - of_node_put(best_frame); of_node_put(frame); - return; + goto out; } - if (cnttidr & CNTTIDR_VIRT(n)) { + /* Try enabling everything, and see what sticks */ + cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT | + CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT; + writel_relaxed(cntacr, cntctlbase + CNTACR(n)); + cntacr = readl_relaxed(cntctlbase + CNTACR(n)); + + if ((cnttidr & CNTTIDR_VIRT(n)) && + !(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) { of_node_put(best_frame); best_frame = frame; arch_timer_mem_use_virtual = true; break; } + + if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT)) + continue; + of_node_put(best_frame); best_frame = of_node_get(frame); } @@ -786,24 +808,26 @@ static void __init arch_timer_mem_init(struct device_node *np) base = arch_counter_base = of_iomap(best_frame, 0); if (!base) { pr_err("arch_timer: Can't map frame's registers\n"); - of_node_put(best_frame); - return; + goto out; } if (arch_timer_mem_use_virtual) irq = irq_of_parse_and_map(best_frame, 1); else irq = irq_of_parse_and_map(best_frame, 0); - of_node_put(best_frame); + if (!irq) { pr_err("arch_timer: Frame missing %s irq", arch_timer_mem_use_virtual ? "virt" : "phys"); - return; + goto out; } arch_timer_detect_rate(base, np); arch_timer_mem_register(base, irq); arch_timer_common_init(); +out: + iounmap(cntctlbase); + of_node_put(best_frame); } CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem", arch_timer_mem_init); diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index d189d8cb69f70..9df0d1699d22b 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -174,6 +175,7 @@ static int gt_clockevents_init(struct clock_event_device *clk) clk->set_state_shutdown = gt_clockevent_shutdown; clk->set_state_periodic = gt_clockevent_set_periodic; clk->set_state_oneshot = gt_clockevent_shutdown; + clk->set_state_oneshot_stopped = gt_clockevent_shutdown; clk->set_next_event = gt_clockevent_set_next_event; clk->cpumask = cpumask_of(cpu); clk->rating = 300; @@ -221,6 +223,21 @@ static u64 notrace gt_sched_clock_read(void) } #endif +static unsigned long gt_read_long(void) +{ + return readl_relaxed(gt_base + GT_COUNTER0); +} + +static struct delay_timer gt_delay_timer = { + .read_current_timer = gt_read_long, +}; + +static void __init gt_delay_timer_init(void) +{ + gt_delay_timer.freq = gt_clk_rate; + register_current_timer_delay(>_delay_timer); +} + static void __init gt_clocksource_init(void) { writel(0, gt_base + GT_CONTROL); @@ -317,6 +334,7 @@ static void __init global_timer_of_register(struct device_node *np) /* Immediately configure the timer on the boot CPU */ gt_clocksource_init(); gt_clockevents_init(this_cpu_ptr(gt_evt)); + gt_delay_timer_init(); return; diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index ff44082a0827d..be09bc0b5e269 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -313,6 +313,7 @@ static struct clock_event_device mct_comp_device = { .set_state_periodic = mct_set_state_periodic, .set_state_shutdown = mct_set_state_shutdown, .set_state_oneshot = mct_set_state_shutdown, + .set_state_oneshot_stopped = mct_set_state_shutdown, .tick_resume = mct_set_state_shutdown, }; @@ -452,6 +453,7 @@ static int exynos4_local_timer_setup(struct mct_clock_event_device *mevt) evt->set_state_periodic = set_state_periodic; evt->set_state_shutdown = set_state_shutdown; evt->set_state_oneshot = set_state_shutdown; + evt->set_state_oneshot_stopped = set_state_shutdown; evt->tick_resume = set_state_shutdown; evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; evt->rating = 450; diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c index 8c77a529d0d44..b991b288c8032 100644 --- a/drivers/clocksource/rockchip_timer.c +++ b/drivers/clocksource/rockchip_timer.c @@ -122,23 +122,23 @@ static void __init rk_timer_init(struct device_node *np) pclk = of_clk_get_by_name(np, "pclk"); if (IS_ERR(pclk)) { pr_err("Failed to get pclk for '%s'\n", TIMER_NAME); - return; + goto out_unmap; } if (clk_prepare_enable(pclk)) { pr_err("Failed to enable pclk for '%s'\n", TIMER_NAME); - return; + goto out_unmap; } timer_clk = of_clk_get_by_name(np, "timer"); if (IS_ERR(timer_clk)) { pr_err("Failed to get timer clock for '%s'\n", TIMER_NAME); - return; + goto out_timer_clk; } if (clk_prepare_enable(timer_clk)) { pr_err("Failed to enable timer clock\n"); - return; + goto out_timer_clk; } bc_timer.freq = clk_get_rate(timer_clk); @@ -146,7 +146,7 @@ static void __init rk_timer_init(struct device_node *np) irq = irq_of_parse_and_map(np, 0); if (!irq) { pr_err("Failed to map interrupts for '%s'\n", TIMER_NAME); - return; + goto out_irq; } ce->name = TIMER_NAME; @@ -164,10 +164,19 @@ static void __init rk_timer_init(struct device_node *np) ret = request_irq(irq, rk_timer_interrupt, IRQF_TIMER, TIMER_NAME, ce); if (ret) { pr_err("Failed to initialize '%s': %d\n", TIMER_NAME, ret); - return; + goto out_irq; } clockevents_config_and_register(ce, bc_timer.freq, 1, UINT_MAX); + + return; + +out_irq: + clk_disable_unprepare(timer_clk); +out_timer_clk: + clk_disable_unprepare(pclk); +out_unmap: + iounmap(bc_timer.base); } CLOCKSOURCE_OF_DECLARE(rk_timer, "rockchip,rk3288-timer", rk_timer_init); diff --git a/drivers/clocksource/time-lpc32xx.c b/drivers/clocksource/time-lpc32xx.c index 1316876b487a7..daae61e8c820e 100644 --- a/drivers/clocksource/time-lpc32xx.c +++ b/drivers/clocksource/time-lpc32xx.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -43,6 +44,7 @@ struct lpc32xx_clock_event_ddata { struct clock_event_device evtdev; void __iomem *base; + u32 ticks_per_jiffy; }; /* Needed for the sched clock */ @@ -53,6 +55,15 @@ static u64 notrace lpc32xx_read_sched_clock(void) return readl(clocksource_timer_counter); } +static unsigned long lpc32xx_delay_timer_read(void) +{ + return readl(clocksource_timer_counter); +} + +static struct delay_timer lpc32xx_delay_timer = { + .read_current_timer = lpc32xx_delay_timer_read, +}; + static int lpc32xx_clkevt_next_event(unsigned long delta, struct clock_event_device *evtdev) { @@ -60,14 +71,13 @@ static int lpc32xx_clkevt_next_event(unsigned long delta, container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev); /* - * Place timer in reset and program the delta in the prescale - * register (PR). When the prescale counter matches the value - * in PR the counter register is incremented and the compare - * match will trigger. After setup the timer is released from - * reset and enabled. + * Place timer in reset and program the delta in the match + * channel 0 (MR0). When the timer counter matches the value + * in MR0 register the match will trigger an interrupt. + * After setup the timer is released from reset and enabled. */ writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR); - writel_relaxed(delta, ddata->base + LPC32XX_TIMER_PR); + writel_relaxed(delta, ddata->base + LPC32XX_TIMER_MR0); writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR); return 0; @@ -86,11 +96,39 @@ static int lpc32xx_clkevt_shutdown(struct clock_event_device *evtdev) static int lpc32xx_clkevt_oneshot(struct clock_event_device *evtdev) { + struct lpc32xx_clock_event_ddata *ddata = + container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev); + /* * When using oneshot, we must also disable the timer * to wait for the first call to set_next_event(). */ - return lpc32xx_clkevt_shutdown(evtdev); + writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR); + + /* Enable interrupt, reset on match and stop on match (MCR). */ + writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R | + LPC32XX_TIMER_MCR_MR0S, ddata->base + LPC32XX_TIMER_MCR); + return 0; +} + +static int lpc32xx_clkevt_periodic(struct clock_event_device *evtdev) +{ + struct lpc32xx_clock_event_ddata *ddata = + container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev); + + /* Enable interrupt and reset on match. */ + writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R, + ddata->base + LPC32XX_TIMER_MCR); + + /* + * Place timer in reset and program the delta in the match + * channel 0 (MR0). + */ + writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR); + writel_relaxed(ddata->ticks_per_jiffy, ddata->base + LPC32XX_TIMER_MR0); + writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR); + + return 0; } static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id) @@ -108,11 +146,13 @@ static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id) static struct lpc32xx_clock_event_ddata lpc32xx_clk_event_ddata = { .evtdev = { .name = "lpc3220 clockevent", - .features = CLOCK_EVT_FEAT_ONESHOT, + .features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_PERIODIC, .rating = 300, .set_next_event = lpc32xx_clkevt_next_event, .set_state_shutdown = lpc32xx_clkevt_shutdown, .set_state_oneshot = lpc32xx_clkevt_oneshot, + .set_state_periodic = lpc32xx_clkevt_periodic, }, }; @@ -162,6 +202,8 @@ static int __init lpc32xx_clocksource_init(struct device_node *np) } clocksource_timer_counter = base + LPC32XX_TIMER_TC; + lpc32xx_delay_timer.freq = rate; + register_current_timer_delay(&lpc32xx_delay_timer); sched_clock_register(lpc32xx_read_sched_clock, 32, rate); return 0; @@ -210,18 +252,16 @@ static int __init lpc32xx_clockevent_init(struct device_node *np) /* * Disable timer and clear any pending interrupt (IR) on match - * channel 0 (MR0). Configure a compare match value of 1 on MR0 - * and enable interrupt, reset on match and stop on match (MCR). + * channel 0 (MR0). Clear the prescaler as it's not used. */ writel_relaxed(0, base + LPC32XX_TIMER_TCR); + writel_relaxed(0, base + LPC32XX_TIMER_PR); writel_relaxed(0, base + LPC32XX_TIMER_CTCR); writel_relaxed(LPC32XX_TIMER_IR_MR0INT, base + LPC32XX_TIMER_IR); - writel_relaxed(1, base + LPC32XX_TIMER_MR0); - writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R | - LPC32XX_TIMER_MCR_MR0S, base + LPC32XX_TIMER_MCR); rate = clk_get_rate(clk); lpc32xx_clk_event_ddata.base = base; + lpc32xx_clk_event_ddata.ticks_per_jiffy = DIV_ROUND_CLOSEST(rate, HZ); clockevents_config_and_register(&lpc32xx_clk_event_ddata.evtdev, rate, 1, -1); diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 659879a56dbac..f93511031177f 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -296,6 +296,7 @@ endif config QORIQ_CPUFREQ tristate "CPU frequency scaling driver for Freescale QorIQ SoCs" depends on OF && COMMON_CLK && (PPC_E500MC || ARM) + depends on !CPU_THERMAL || THERMAL select CLK_QORIQ help This adds the CPUFreq driver support for Freescale QorIQ SoCs diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 0031069b64c95..14b1f9393b057 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -84,10 +84,10 @@ config ARM_KIRKWOOD_CPUFREQ SoCs. config ARM_MT8173_CPUFREQ - bool "Mediatek MT8173 CPUFreq support" + tristate "Mediatek MT8173 CPUFreq support" depends on ARCH_MEDIATEK && REGULATOR depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST) - depends on !CPU_THERMAL || THERMAL=y + depends on !CPU_THERMAL || THERMAL select PM_OPP help This adds the CPUFreq driver support for Mediatek MT8173 SoC. diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index cd83d477e32d4..3a4b39afc0abb 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1431,7 +1431,7 @@ static int __init intel_pstate_init(void) if (!all_cpu_data) return -ENOMEM; - if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) { + if (static_cpu_has(X86_FEATURE_HWP) && !no_hwp) { pr_info("intel_pstate: HWP enabled\n"); hwp_active++; } diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c index 1efba340456df..2058e6d292ce9 100644 --- a/drivers/cpufreq/mt8173-cpufreq.c +++ b/drivers/cpufreq/mt8173-cpufreq.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 64f5d1bdbb48d..8e304b1befc56 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -176,6 +176,7 @@ #define AT_XDMAC_MAX_CHAN 0x20 #define AT_XDMAC_MAX_CSIZE 16 /* 16 data */ #define AT_XDMAC_MAX_DWIDTH 8 /* 64 bits */ +#define AT_XDMAC_RESIDUE_MAX_RETRIES 5 #define AT_XDMAC_DMA_BUSWIDTHS\ (BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\ @@ -1395,8 +1396,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, struct at_xdmac_desc *desc, *_desc; struct list_head *descs_list; enum dma_status ret; - int residue; - u32 cur_nda, mask, value; + int residue, retry; + u32 cur_nda, check_nda, cur_ubc, mask, value; u8 dwidth = 0; unsigned long flags; @@ -1433,7 +1434,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, cpu_relax(); } + /* + * When processing the residue, we need to read two registers but we + * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where + * we stand in the descriptor list and AT_XDMAC_CUBC is used + * to know how many data are remaining for the current descriptor. + * Since the dma channel is not paused to not loose data, between the + * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of + * descriptor. + * For that reason, after reading AT_XDMAC_CUBC, we check if we are + * still using the same descriptor by reading a second time + * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to + * read again AT_XDMAC_CUBC. + * Memory barriers are used to ensure the read order of the registers. + * A max number of retries is set because unlikely it can never ends if + * we are transferring a lot of data with small buffers. + */ cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) { + rmb(); + check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + + if (likely(cur_nda == check_nda)) + break; + + cur_nda = check_nda; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + } + + if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) { + ret = DMA_ERROR; + goto spin_unlock; + } + /* * Remove size of all microblocks already transferred and the current * one. Then add the remaining size to transfer of the current @@ -1446,7 +1482,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda) break; } - residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth; + residue += cur_ubc << dwidth; dma_set_residue(txstate, residue); diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 2209f75fdf05b..aac85c30c2cf6 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -522,6 +522,8 @@ static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan, chan_dbg(chan, "LD %p callback\n", desc); txd->callback(txd->callback_param); } + + dma_descriptor_unmap(txd); } /* Run any dependencies */ diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c index e4f43125e0fbb..f039cfadf17b3 100644 --- a/drivers/dma/iop-adma.c +++ b/drivers/dma/iop-adma.c @@ -1300,10 +1300,10 @@ static int iop_adma_probe(struct platform_device *pdev) * note: writecombine gives slightly better performance, but * requires that we explicitly flush the writes */ - adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev, - plat_data->pool_size, - &adev->dma_desc_pool, - GFP_KERNEL); + adev->dma_desc_pool_virt = dma_alloc_wc(&pdev->dev, + plat_data->pool_size, + &adev->dma_desc_pool, + GFP_KERNEL); if (!adev->dma_desc_pool_virt) { ret = -ENOMEM; goto err_free_adev; diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 14091f878f80a..3922a5d568060 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -964,8 +964,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev, * requires that we explicitly flush the writes */ mv_chan->dma_desc_pool_virt = - dma_alloc_writecombine(&pdev->dev, MV_XOR_POOL_SIZE, - &mv_chan->dma_desc_pool, GFP_KERNEL); + dma_alloc_wc(&pdev->dev, MV_XOR_POOL_SIZE, &mv_chan->dma_desc_pool, + GFP_KERNEL); if (!mv_chan->dma_desc_pool_virt) return ERR_PTR(-ENOMEM); diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index f2a0310ae7718..debca824bed67 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -583,6 +583,8 @@ static void set_updater_desc(struct pxad_desc_sw *sw_desc, (PXA_DCMD_LENGTH & sizeof(u32)); if (flags & DMA_PREP_INTERRUPT) updater->dcmd |= PXA_DCMD_ENDIRQEN; + if (sw_desc->cyclic) + sw_desc->hw_desc[sw_desc->nb_desc - 2]->ddadr = sw_desc->first; } static bool is_desc_completed(struct virt_dma_desc *vd) @@ -673,6 +675,10 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id) dev_dbg(&chan->vc.chan.dev->device, "%s(): checking txd %p[%x]: completed=%d\n", __func__, vd, vd->tx.cookie, is_desc_completed(vd)); + if (to_pxad_sw_desc(vd)->cyclic) { + vchan_cyclic_callback(vd); + break; + } if (is_desc_completed(vd)) { list_del(&vd->node); vchan_cookie_complete(vd); @@ -1080,7 +1086,7 @@ pxad_prep_dma_cyclic(struct dma_chan *dchan, return NULL; pxad_get_config(chan, dir, &dcmd, &dsadr, &dtadr); - dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH | period_len); + dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH & period_len); dev_dbg(&chan->vc.chan.dev->device, "%s(): buf_addr=0x%lx len=%zu period=%zu dir=%d flags=%lx\n", __func__, (unsigned long)buf_addr, len, period_len, dir, flags); diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c index 5a250cdc83769..d34aef7a101b6 100644 --- a/drivers/dma/qcom_bam_dma.c +++ b/drivers/dma/qcom_bam_dma.c @@ -502,8 +502,8 @@ static int bam_alloc_chan(struct dma_chan *chan) return 0; /* allocate FIFO descriptor space, but only if necessary */ - bchan->fifo_virt = dma_alloc_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, - &bchan->fifo_phys, GFP_KERNEL); + bchan->fifo_virt = dma_alloc_wc(bdev->dev, BAM_DESC_FIFO_SIZE, + &bchan->fifo_phys, GFP_KERNEL); if (!bchan->fifo_virt) { dev_err(bdev->dev, "Failed to allocate desc fifo\n"); @@ -538,8 +538,8 @@ static void bam_free_chan(struct dma_chan *chan) bam_reset_channel(bchan); spin_unlock_irqrestore(&bchan->vc.lock, flags); - dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt, - bchan->fifo_phys); + dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt, + bchan->fifo_phys); bchan->fifo_virt = NULL; /* mask irq for pipe/channel */ @@ -1231,9 +1231,9 @@ static int bam_dma_remove(struct platform_device *pdev) bam_dma_terminate_all(&bdev->channels[i].vc.chan); tasklet_kill(&bdev->channels[i].vc.task); - dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, - bdev->channels[i].fifo_virt, - bdev->channels[i].fifo_phys); + dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE, + bdev->channels[i].fifo_virt, + bdev->channels[i].fifo_phys); } tasklet_kill(&bdev->task); diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index e3a945ce374b8..49768c08ac073 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -147,6 +147,135 @@ static const char * const mc6_mce_desc[] = { "Status Register File", }; +/* Scalable MCA error strings */ +static const char * const f17h_ls_mce_desc[] = { + "Load queue parity", + "Store queue parity", + "Miss address buffer payload parity", + "L1 TLB parity", + "", /* reserved */ + "DC tag error type 6", + "DC tag error type 1", + "Internal error type 1", + "Internal error type 2", + "Sys Read data error thread 0", + "Sys read data error thread 1", + "DC tag error type 2", + "DC data error type 1 (poison comsumption)", + "DC data error type 2", + "DC data error type 3", + "DC tag error type 4", + "L2 TLB parity", + "PDC parity error", + "DC tag error type 3", + "DC tag error type 5", + "L2 fill data error", +}; + +static const char * const f17h_if_mce_desc[] = { + "microtag probe port parity error", + "IC microtag or full tag multi-hit error", + "IC full tag parity", + "IC data array parity", + "Decoupling queue phys addr parity error", + "L0 ITLB parity error", + "L1 ITLB parity error", + "L2 ITLB parity error", + "BPQ snoop parity on Thread 0", + "BPQ snoop parity on Thread 1", + "L1 BTB multi-match error", + "L2 BTB multi-match error", +}; + +static const char * const f17h_l2_mce_desc[] = { + "L2M tag multi-way-hit error", + "L2M tag ECC error", + "L2M data ECC error", + "HW assert", +}; + +static const char * const f17h_de_mce_desc[] = { + "uop cache tag parity error", + "uop cache data parity error", + "Insn buffer parity error", + "Insn dispatch queue parity error", + "Fetch address FIFO parity", + "Patch RAM data parity", + "Patch RAM sequencer parity", + "uop buffer parity" +}; + +static const char * const f17h_ex_mce_desc[] = { + "Watchdog timeout error", + "Phy register file parity", + "Flag register file parity", + "Immediate displacement register file parity", + "Address generator payload parity", + "EX payload parity", + "Checkpoint queue parity", + "Retire dispatch queue parity", +}; + +static const char * const f17h_fp_mce_desc[] = { + "Physical register file parity", + "Freelist parity error", + "Schedule queue parity", + "NSQ parity error", + "Retire queue parity", + "Status register file parity", +}; + +static const char * const f17h_l3_mce_desc[] = { + "Shadow tag macro ECC error", + "Shadow tag macro multi-way-hit error", + "L3M tag ECC error", + "L3M tag multi-way-hit error", + "L3M data ECC error", + "XI parity, L3 fill done channel error", + "L3 victim queue parity", + "L3 HW assert", +}; + +static const char * const f17h_cs_mce_desc[] = { + "Illegal request from transport layer", + "Address violation", + "Security violation", + "Illegal response from transport layer", + "Unexpected response", + "Parity error on incoming request or probe response data", + "Parity error on incoming read response data", + "Atomic request parity", + "ECC error on probe filter access", +}; + +static const char * const f17h_pie_mce_desc[] = { + "HW assert", + "Internal PIE register security violation", + "Error on GMI link", + "Poison data written to internal PIE register", +}; + +static const char * const f17h_umc_mce_desc[] = { + "DRAM ECC error", + "Data poison error on DRAM", + "SDP parity error", + "Advanced peripheral bus error", + "Command/address parity error", + "Write data CRC error", +}; + +static const char * const f17h_pb_mce_desc[] = { + "Parameter Block RAM ECC error", +}; + +static const char * const f17h_psp_mce_desc[] = { + "PSP RAM ECC or parity error", +}; + +static const char * const f17h_smu_mce_desc[] = { + "SMU RAM ECC or parity error", +}; + static bool f12h_mc0_mce(u16 ec, u8 xec) { bool ret = false; @@ -691,6 +820,177 @@ static void decode_mc6_mce(struct mce *m) pr_emerg(HW_ERR "Corrupted MC6 MCE info?\n"); } +static void decode_f17h_core_errors(const char *ip_name, u8 xec, + unsigned int mca_type) +{ + const char * const *error_desc_array; + size_t len; + + pr_emerg(HW_ERR "%s Error: ", ip_name); + + switch (mca_type) { + case SMCA_LS: + error_desc_array = f17h_ls_mce_desc; + len = ARRAY_SIZE(f17h_ls_mce_desc) - 1; + + if (xec == 0x4) { + pr_cont("Unrecognized LS MCA error code.\n"); + return; + } + break; + + case SMCA_IF: + error_desc_array = f17h_if_mce_desc; + len = ARRAY_SIZE(f17h_if_mce_desc) - 1; + break; + + case SMCA_L2_CACHE: + error_desc_array = f17h_l2_mce_desc; + len = ARRAY_SIZE(f17h_l2_mce_desc) - 1; + break; + + case SMCA_DE: + error_desc_array = f17h_de_mce_desc; + len = ARRAY_SIZE(f17h_de_mce_desc) - 1; + break; + + case SMCA_EX: + error_desc_array = f17h_ex_mce_desc; + len = ARRAY_SIZE(f17h_ex_mce_desc) - 1; + break; + + case SMCA_FP: + error_desc_array = f17h_fp_mce_desc; + len = ARRAY_SIZE(f17h_fp_mce_desc) - 1; + break; + + case SMCA_L3_CACHE: + error_desc_array = f17h_l3_mce_desc; + len = ARRAY_SIZE(f17h_l3_mce_desc) - 1; + break; + + default: + pr_cont("Corrupted MCA core error info.\n"); + return; + } + + if (xec > len) { + pr_cont("Unrecognized %s MCA bank error code.\n", + amd_core_mcablock_names[mca_type]); + return; + } + + pr_cont("%s.\n", error_desc_array[xec]); +} + +static void decode_df_errors(u8 xec, unsigned int mca_type) +{ + const char * const *error_desc_array; + size_t len; + + pr_emerg(HW_ERR "Data Fabric Error: "); + + switch (mca_type) { + case SMCA_CS: + error_desc_array = f17h_cs_mce_desc; + len = ARRAY_SIZE(f17h_cs_mce_desc) - 1; + break; + + case SMCA_PIE: + error_desc_array = f17h_pie_mce_desc; + len = ARRAY_SIZE(f17h_pie_mce_desc) - 1; + break; + + default: + pr_cont("Corrupted MCA Data Fabric info.\n"); + return; + } + + if (xec > len) { + pr_cont("Unrecognized %s MCA bank error code.\n", + amd_df_mcablock_names[mca_type]); + return; + } + + pr_cont("%s.\n", error_desc_array[xec]); +} + +/* Decode errors according to Scalable MCA specification */ +static void decode_smca_errors(struct mce *m) +{ + u32 addr = MSR_AMD64_SMCA_MCx_IPID(m->bank); + unsigned int hwid, mca_type, i; + u8 xec = XEC(m->status, xec_mask); + const char * const *error_desc_array; + const char *ip_name; + u32 low, high; + size_t len; + + if (rdmsr_safe(addr, &low, &high)) { + pr_emerg("Invalid IP block specified, error information is unreliable.\n"); + return; + } + + hwid = high & MCI_IPID_HWID; + mca_type = (high & MCI_IPID_MCATYPE) >> 16; + + pr_emerg(HW_ERR "MC%d IPID value: 0x%08x%08x\n", m->bank, high, low); + + /* + * Based on hwid and mca_type values, decode errors from respective IPs. + * Note: mca_type values make sense only in the context of an hwid. + */ + for (i = 0; i < ARRAY_SIZE(amd_hwids); i++) + if (amd_hwids[i].hwid == hwid) + break; + + switch (i) { + case SMCA_F17H_CORE: + ip_name = (mca_type == SMCA_L3_CACHE) ? + "L3 Cache" : "F17h Core"; + return decode_f17h_core_errors(ip_name, xec, mca_type); + break; + + case SMCA_DF: + return decode_df_errors(xec, mca_type); + break; + + case SMCA_UMC: + error_desc_array = f17h_umc_mce_desc; + len = ARRAY_SIZE(f17h_umc_mce_desc) - 1; + break; + + case SMCA_PB: + error_desc_array = f17h_pb_mce_desc; + len = ARRAY_SIZE(f17h_pb_mce_desc) - 1; + break; + + case SMCA_PSP: + error_desc_array = f17h_psp_mce_desc; + len = ARRAY_SIZE(f17h_psp_mce_desc) - 1; + break; + + case SMCA_SMU: + error_desc_array = f17h_smu_mce_desc; + len = ARRAY_SIZE(f17h_smu_mce_desc) - 1; + break; + + default: + pr_emerg(HW_ERR "HWID:%d does not match any existing IPs.\n", hwid); + return; + } + + ip_name = amd_hwids[i].name; + pr_emerg(HW_ERR "%s Error: ", ip_name); + + if (xec > len) { + pr_cont("Unrecognized %s MCA bank error code.\n", ip_name); + return; + } + + pr_cont("%s.\n", error_desc_array[xec]); +} + static inline void amd_decode_err_code(u16 ec) { if (INT_ERROR(ec)) { @@ -752,6 +1052,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) struct mce *m = (struct mce *)data; struct cpuinfo_x86 *c = &cpu_data(m->extcpu); int ecc; + u32 ebx = cpuid_ebx(0x80000007); if (amd_filter_mce(m)) return NOTIFY_STOP; @@ -769,11 +1070,20 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) ((m->status & MCI_STATUS_PCC) ? "PCC" : "-"), ((m->status & MCI_STATUS_ADDRV) ? "AddrV" : "-")); - if (c->x86 == 0x15 || c->x86 == 0x16) + if (c->x86 >= 0x15) pr_cont("|%s|%s", ((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"), ((m->status & MCI_STATUS_POISON) ? "Poison" : "-")); + if (!!(ebx & BIT(3))) { + u32 low, high; + u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); + + if (!rdmsr_safe(addr, &low, &high) && + (low & MCI_CONFIG_MCAX)) + pr_cont("|%s", ((m->status & MCI_STATUS_TCC) ? "TCC" : "-")); + } + /* do the two bits[14:13] together */ ecc = (m->status >> 45) & 0x3; if (ecc) @@ -784,6 +1094,11 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) if (m->status & MCI_STATUS_ADDRV) pr_emerg(HW_ERR "MC%d Error Address: 0x%016llx\n", m->bank, m->addr); + if (!!(ebx & BIT(3))) { + decode_smca_errors(m); + goto err_code; + } + if (!fam_ops) goto err_code; @@ -834,6 +1149,7 @@ static struct notifier_block amd_mce_dec_nb = { static int __init mce_amd_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + u32 ebx; if (c->x86_vendor != X86_VENDOR_AMD) return -ENODEV; @@ -888,10 +1204,18 @@ static int __init mce_amd_init(void) fam_ops->mc2_mce = f16h_mc2_mce; break; + case 0x17: + ebx = cpuid_ebx(0x80000007); + xec_mask = 0x3f; + if (!(ebx & BIT(3))) { + printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n"); + goto err_out; + } + break; + default: printk(KERN_WARNING "Huh? What family is it: 0x%x?!\n", c->x86); - kfree(fam_ops); - fam_ops = NULL; + goto err_out; } pr_info("MCE: In-kernel MCE decoding enabled.\n"); @@ -899,6 +1223,11 @@ static int __init mce_amd_init(void) mce_register_decode_chain(&amd_mce_dec_nb); return 0; + +err_out: + kfree(fam_ops); + fam_ops = NULL; + return -EINVAL; } early_initcall(mce_amd_init); diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index e438ee5b433f3..93f0d4120289f 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -1574,7 +1574,7 @@ static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes) for (cha = 0; cha < KNL_MAX_CHAS; cha++) { if (knl_get_mc_route(target, mc_route_reg[cha]) == channel - && participants[channel]) { + && !participants[channel]) { participant_count++; participants[channel] = 1; break; @@ -1839,8 +1839,8 @@ static void get_memory_layout(const struct mem_ctl_info *mci) edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n", n_tads, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, - (u32)TAD_SOCK(reg), - (u32)TAD_CH(reg), + (u32)(1 << TAD_SOCK(reg)), + (u32)TAD_CH(reg) + 1, (u32)TAD_TGT0(reg), (u32)TAD_TGT1(reg), (u32)TAD_TGT2(reg), @@ -2118,7 +2118,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, } ch_way = TAD_CH(reg) + 1; - sck_way = TAD_SOCK(reg) + 1; + sck_way = 1 << TAD_SOCK(reg); if (ch_way == 3) idx = addr >> 6; @@ -2175,7 +2175,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, n_tads, addr, limit, - (u32)TAD_SOCK(reg), + sck_way, ch_way, offset, idx, @@ -2190,18 +2190,12 @@ static int get_memory_error_data(struct mem_ctl_info *mci, offset, addr); return -EINVAL; } - addr -= offset; - /* Store the low bits [0:6] of the addr */ - ch_addr = addr & 0x7f; - /* Remove socket wayness and remove 6 bits */ - addr >>= 6; - addr = div_u64(addr, sck_xch); -#if 0 - /* Divide by channel way */ - addr = addr / ch_way; -#endif - /* Recover the last 6 bits */ - ch_addr |= addr << 6; + + ch_addr = addr - offset; + ch_addr >>= (6 + shiftup); + ch_addr /= ch_way * sck_way; + ch_addr <<= (6 + shiftup); + ch_addr |= addr & ((1 << (6 + shiftup)) - 1); /* * Step 3) Decode rank diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index cf41440aff919..d9ab0cd1d2059 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -196,6 +196,44 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) return 0; } +static void gpio_rcar_irq_bus_lock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_get_sync(&p->pdev->dev); +} + +static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_put(&p->pdev->dev); +} + + +static int gpio_rcar_irq_request_resources(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + int error; + + error = pm_runtime_get_sync(&p->pdev->dev); + if (error < 0) + return error; + + return 0; +} + +static void gpio_rcar_irq_release_resources(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_put(&p->pdev->dev); +} + static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id) { struct gpio_rcar_priv *p = dev_id; @@ -450,6 +488,10 @@ static int gpio_rcar_probe(struct platform_device *pdev) irq_chip->irq_unmask = gpio_rcar_irq_enable; irq_chip->irq_set_type = gpio_rcar_irq_set_type; irq_chip->irq_set_wake = gpio_rcar_irq_set_wake; + irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock; + irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock; + irq_chip->irq_request_resources = gpio_rcar_irq_request_resources; + irq_chip->irq_release_resources = gpio_rcar_irq_release_resources; irq_chip->flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND; ret = gpiochip_add_data(gpio_chip, p); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 89c3dd62ba21e..119cdc2c43e7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -77,7 +77,7 @@ void amdgpu_connector_hotplug(struct drm_connector *connector) } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { /* Don't try to start link training before we * have the dpcd */ - if (!amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) + if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) return; /* set it to OFF so that drm_helper_connector_dpms() diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 8297bc319369d..1846d65b72859 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - while (amdgpuCrtc->enabled && repcnt--) { + while (amdgpuCrtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -112,13 +112,13 @@ static void amdgpu_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); if (min_udelay > vblank->framedur_ns / 2000) { /* Don't wait ridiculously long - something is wrong */ repcnt = 0; break; } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 66855b62a6037..95a4a25d8df9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -649,9 +649,6 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; - adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; - /* wait for the rings to drain */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -670,6 +667,9 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) /* update displays */ amdgpu_dpm_display_configuration_changed(adev); + adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; + adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c index b9d0d55f6b47d..3cb6d6c413c71 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c @@ -143,8 +143,10 @@ static int amdgpu_pp_late_init(void *handle) adev->powerplay.pp_handle); #ifdef CONFIG_DRM_AMD_POWERPLAY - if (adev->pp_enabled) + if (adev->pp_enabled) { amdgpu_pm_sysfs_init(adev); + amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_COMPLETE_INIT, NULL, NULL); + } #endif return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c index 21aacc1f45c1f..bf731e9f643e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c @@ -265,15 +265,27 @@ static int amdgpu_atombios_dp_get_dp_link_config(struct drm_connector *connector unsigned max_lane_num = drm_dp_max_lane_count(dpcd); unsigned lane_num, i, max_pix_clock; - for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { - for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { - max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector) == + ENCODER_OBJECT_ID_NUTMEG) { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + max_pix_clock = (lane_num * 270000 * 8) / bpp; if (max_pix_clock >= pix_clock) { *dp_lanes = lane_num; - *dp_rate = link_rates[i]; + *dp_rate = 270000; return 0; } } + } else { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (max_pix_clock >= pix_clock) { + *dp_lanes = lane_num; + *dp_rate = link_rates[i]; + return 0; + } + } + } } return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 9056355309d18..e7ef2261ff4a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -2202,8 +2202,7 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) AMD_PG_STATE_GATE); cz_enable_vce_dpm(adev, false); - /* TODO: to figure out why vce can't be poweroff. */ - /* cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF); */ + cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF); pi->vce_power_gated = true; } else { cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerON); @@ -2226,10 +2225,8 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) } } else { /*pi->caps_vce_pg*/ cz_update_vce_dpm(adev); - cz_enable_vce_dpm(adev, true); + cz_enable_vce_dpm(adev, !gate); } - - return; } const struct amd_ip_funcs cz_dpm_ip_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 7732059ae30f5..06602df707f86 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3628,6 +3628,19 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr) { int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX); + uint32_t seq = ring->fence_drv.sync_seq; + uint64_t addr = ring->fence_drv.gpu_addr; + + amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); + amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); + amdgpu_ring_write(ring, seq); + amdgpu_ring_write(ring, 0xffffffff); + amdgpu_ring_write(ring, 4); /* poll interval */ + if (usepfp) { /* synce CE with ME to prevent CE fetch CEIB before context switch done */ amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 1c40bd90afbb3..7086ac17abee1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4809,7 +4809,8 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ - WAIT_REG_MEM_FUNCTION(3))); /* equal */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index aa67244a77ae3..589599f66fcce 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -402,8 +402,11 @@ int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_event event_id, void *input, data.requested_ui_label = power_state_convert(ps); ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); + break; } - break; + case AMD_PP_EVENT_COMPLETE_INIT: + ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); + break; default: break; } diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c index 83be3cf210e01..6b52c78cb4048 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c @@ -165,6 +165,7 @@ const struct action_chain resume_action_chain = { }; static const pem_event_action *complete_init_event[] = { + unblock_adjust_power_state_tasks, adjust_power_state_tasks, enable_gfx_clock_gating_tasks, enable_gfx_voltage_island_power_gating_tasks, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c index ad7700822a1cb..ff08ce41bde92 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c @@ -226,7 +226,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) } } else { cz_dpm_update_vce_dpm(hwmgr); - cz_enable_disable_vce_dpm(hwmgr, true); + cz_enable_disable_vce_dpm(hwmgr, !bgate); return 0; } diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 9759009d1da36..b1480acbb3c35 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -227,7 +227,7 @@ static int ast_get_dram_info(struct drm_device *dev) } while (ast_read32(ast, 0x10000) != 0x01); data = ast_read32(ast, 0x10004); - if (data & 0x400) + if (data & 0x40) ast->dram_bus_width = 16; else ast->dram_bus_width = 32; diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index e5df53b6e229f..1f500a1b99695 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -109,8 +109,8 @@ struct drm_gem_cma_object *drm_gem_cma_create(struct drm_device *drm, if (IS_ERR(cma_obj)) return cma_obj; - cma_obj->vaddr = dma_alloc_writecombine(drm->dev, size, - &cma_obj->paddr, GFP_KERNEL | __GFP_NOWARN); + cma_obj->vaddr = dma_alloc_wc(drm->dev, size, &cma_obj->paddr, + GFP_KERNEL | __GFP_NOWARN); if (!cma_obj->vaddr) { dev_err(drm->dev, "failed to allocate buffer with size %zu\n", size); @@ -192,8 +192,8 @@ void drm_gem_cma_free_object(struct drm_gem_object *gem_obj) cma_obj = to_drm_gem_cma_obj(gem_obj); if (cma_obj->vaddr) { - dma_free_writecombine(gem_obj->dev->dev, cma_obj->base.size, - cma_obj->vaddr, cma_obj->paddr); + dma_free_wc(gem_obj->dev->dev, cma_obj->base.size, + cma_obj->vaddr, cma_obj->paddr); } else if (gem_obj->import_attach) { drm_prime_gem_destroy(gem_obj, cma_obj->sgt); } @@ -324,9 +324,8 @@ static int drm_gem_cma_mmap_obj(struct drm_gem_cma_object *cma_obj, vma->vm_flags &= ~VM_PFNMAP; vma->vm_pgoff = 0; - ret = dma_mmap_writecombine(cma_obj->base.dev->dev, vma, - cma_obj->vaddr, cma_obj->paddr, - vma->vm_end - vma->vm_start); + ret = dma_mmap_wc(cma_obj->base.dev->dev, vma, cma_obj->vaddr, + cma_obj->paddr, vma->vm_end - vma->vm_start); if (ret) drm_gem_vm_close(vma); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index a33162cf4f4cc..3c1ce44483d99 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1113,8 +1113,8 @@ struct etnaviv_cmdbuf *etnaviv_gpu_cmdbuf_new(struct etnaviv_gpu *gpu, u32 size, if (!cmdbuf) return NULL; - cmdbuf->vaddr = dma_alloc_writecombine(gpu->dev, size, &cmdbuf->paddr, - GFP_KERNEL); + cmdbuf->vaddr = dma_alloc_wc(gpu->dev, size, &cmdbuf->paddr, + GFP_KERNEL); if (!cmdbuf->vaddr) { kfree(cmdbuf); return NULL; @@ -1128,8 +1128,8 @@ struct etnaviv_cmdbuf *etnaviv_gpu_cmdbuf_new(struct etnaviv_gpu *gpu, u32 size, void etnaviv_gpu_cmdbuf_free(struct etnaviv_cmdbuf *cmdbuf) { - dma_free_writecombine(cmdbuf->gpu->dev, cmdbuf->size, - cmdbuf->vaddr, cmdbuf->paddr); + dma_free_wc(cmdbuf->gpu->dev, cmdbuf->size, cmdbuf->vaddr, + cmdbuf->paddr); kfree(cmdbuf); } diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 34e38749a8176..f8ee740c0e264 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -1382,8 +1382,16 @@ static void tda998x_connector_destroy(struct drm_connector *connector) drm_connector_cleanup(connector); } +static int tda998x_connector_dpms(struct drm_connector *connector, int mode) +{ + if (drm_core_check_feature(connector->dev, DRIVER_ATOMIC)) + return drm_atomic_helper_connector_dpms(connector, mode); + else + return drm_helper_connector_dpms(connector, mode); +} + static const struct drm_connector_funcs tda998x_connector_funcs = { - .dpms = drm_atomic_helper_connector_dpms, + .dpms = tda998x_connector_dpms, .reset = drm_atomic_helper_connector_reset, .fill_modes = drm_helper_probe_single_connector_modes, .detect = tda998x_connector_detect, diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 31f6d212fb1bb..30f921421b0c9 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -527,6 +527,8 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder) mutex_lock(&dev_priv->av_mutex); intel_dig_port->audio_connector = connector; + /* referred in audio callbacks */ + dev_priv->dig_port_map[port] = intel_encoder; mutex_unlock(&dev_priv->av_mutex); if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) @@ -554,6 +556,7 @@ void intel_audio_codec_disable(struct intel_encoder *intel_encoder) mutex_lock(&dev_priv->av_mutex); intel_dig_port->audio_connector = NULL; + dev_priv->dig_port_map[port] = NULL; mutex_unlock(&dev_priv->av_mutex); if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 0f3df2c39f7cd..084d5586585d0 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -3358,7 +3358,6 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->get_config = intel_ddi_get_config; intel_dig_port->port = port; - dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & (DDI_BUF_PORT_REVERSAL | DDI_A_4_LANES); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 1d8de43bed568..cdc2c15873dcc 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -6045,7 +6045,6 @@ intel_dp_init(struct drm_device *dev, } intel_dig_port->port = port; - dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->dp.output_reg = output_reg; intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index cb5d1b15755c3..616108c4bc3e5 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -2154,7 +2154,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, void intel_hdmi_init(struct drm_device *dev, i915_reg_t hdmi_reg, enum port port) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_digital_port *intel_dig_port; struct intel_encoder *intel_encoder; struct intel_connector *intel_connector; @@ -2223,7 +2222,6 @@ void intel_hdmi_init(struct drm_device *dev, intel_encoder->cloneable |= 1 << INTEL_OUTPUT_HDMI; intel_dig_port->port = port; - dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->hdmi.hdmi_reg = hdmi_reg; intel_dig_port->dp.output_reg = INVALID_MMIO_REG; diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index deb8282c26d83..52fbe530fc9ea 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -664,6 +664,12 @@ int intel_setup_gmbus(struct drm_device *dev) bus->adapter.algo = &gmbus_algorithm; + /* + * We wish to retry with bit banging + * after a timed out GMBUS attempt. + */ + bus->adapter.retries = 1; + /* By default use a conservative clock rate */ bus->reg0 = pin | GMBUS_RATE_100KHZ; diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 678ed3475d7ec..4f43d9b32e663 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2303,15 +2303,15 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume) */ void intel_power_domains_suspend(struct drm_i915_private *dev_priv) { - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) - skl_display_core_uninit(dev_priv); - /* * Even if power well support was disabled we still want to disable * power wells while we are system suspended. */ if (!i915.disable_power_well) intel_display_power_put(dev_priv, POWER_DOMAIN_INIT); + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + skl_display_core_uninit(dev_priv); } /** @@ -2349,22 +2349,20 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; struct device *device = &dev->pdev->dev; - int ret; - - if (!IS_ENABLED(CONFIG_PM)) - return true; - ret = pm_runtime_get_if_in_use(device); + if (IS_ENABLED(CONFIG_PM)) { + int ret = pm_runtime_get_if_in_use(device); - /* - * In cases runtime PM is disabled by the RPM core and we get an - * -EINVAL return value we are not supposed to call this function, - * since the power state is undefined. This applies atm to the - * late/early system suspend/resume handlers. - */ - WARN_ON_ONCE(ret < 0); - if (ret <= 0) - return false; + /* + * In cases runtime PM is disabled by the RPM core and we get + * an -EINVAL return value we are not supposed to call this + * function, since the power state is undefined. This applies + * atm to the late/early system suspend/resume handlers. + */ + WARN_ON_ONCE(ret < 0); + if (ret <= 0) + return false; + } atomic_inc(&dev_priv->pm.wakeref_count); assert_rpm_wakelock_held(dev_priv); diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 30a57185bdb4e..287226311413c 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -64,6 +64,7 @@ static void ipu_fb_enable(struct ipu_crtc *ipu_crtc) /* Start DC channel and DI after IDMAC */ ipu_dc_enable_channel(ipu_crtc->dc); ipu_di_enable(ipu_crtc->di); + drm_crtc_vblank_on(&ipu_crtc->base); ipu_crtc->enabled = 1; } @@ -80,6 +81,7 @@ static void ipu_fb_disable(struct ipu_crtc *ipu_crtc) ipu_di_disable(ipu_crtc->di); ipu_plane_disable(ipu_crtc->plane[0]); ipu_dc_disable(ipu); + drm_crtc_vblank_off(&ipu_crtc->base); ipu_crtc->enabled = 0; } diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 591ba2f1ae036..26bb1b626fe3d 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -42,6 +42,7 @@ static const uint32_t ipu_plane_formats[] = { DRM_FORMAT_YVYU, DRM_FORMAT_YUV420, DRM_FORMAT_YVU420, + DRM_FORMAT_RGB565, }; int ipu_plane_irq(struct ipu_plane *ipu_plane) diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c index dfebdc4aa0f24..85dfe3674b413 100644 --- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c +++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c @@ -573,10 +573,9 @@ static int omap_dmm_remove(struct platform_device *dev) kfree(omap_dmm->engines); if (omap_dmm->refill_va) - dma_free_writecombine(omap_dmm->dev, - REFILL_BUFFER_SIZE * omap_dmm->num_engines, - omap_dmm->refill_va, - omap_dmm->refill_pa); + dma_free_wc(omap_dmm->dev, + REFILL_BUFFER_SIZE * omap_dmm->num_engines, + omap_dmm->refill_va, omap_dmm->refill_pa); if (omap_dmm->dummy_page) __free_page(omap_dmm->dummy_page); @@ -701,9 +700,9 @@ static int omap_dmm_probe(struct platform_device *dev) omap_dmm->dummy_pa = page_to_phys(omap_dmm->dummy_page); /* alloc refill memory */ - omap_dmm->refill_va = dma_alloc_writecombine(&dev->dev, - REFILL_BUFFER_SIZE * omap_dmm->num_engines, - &omap_dmm->refill_pa, GFP_KERNEL); + omap_dmm->refill_va = dma_alloc_wc(&dev->dev, + REFILL_BUFFER_SIZE * omap_dmm->num_engines, + &omap_dmm->refill_pa, GFP_KERNEL); if (!omap_dmm->refill_va) { dev_err(&dev->dev, "could not allocate refill memory\n"); goto fail; diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 8495a1a4b6174..359b0d7e8ef78 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -1330,8 +1330,8 @@ void omap_gem_free_object(struct drm_gem_object *obj) omap_gem_detach_pages(obj); if (!is_shmem(obj)) { - dma_free_writecombine(dev->dev, obj->size, - omap_obj->vaddr, omap_obj->paddr); + dma_free_wc(dev->dev, obj->size, omap_obj->vaddr, + omap_obj->paddr); } else if (omap_obj->vaddr) { vunmap(omap_obj->vaddr); } @@ -1395,8 +1395,8 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev, /* attempt to allocate contiguous memory if we don't * have DMM for remappign discontiguous buffers */ - omap_obj->vaddr = dma_alloc_writecombine(dev->dev, size, - &omap_obj->paddr, GFP_KERNEL); + omap_obj->vaddr = dma_alloc_wc(dev->dev, size, + &omap_obj->paddr, GFP_KERNEL); if (!omap_obj->vaddr) { kfree(omap_obj); diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 44ee72e04df9e..6af832545bc5b 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -315,15 +315,27 @@ int radeon_dp_get_dp_link_config(struct drm_connector *connector, unsigned max_lane_num = drm_dp_max_lane_count(dpcd); unsigned lane_num, i, max_pix_clock; - for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { - for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { - max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) == + ENCODER_OBJECT_ID_NUTMEG) { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + max_pix_clock = (lane_num * 270000 * 8) / bpp; if (max_pix_clock >= pix_clock) { *dp_lanes = lane_num; - *dp_rate = link_rates[i]; + *dp_rate = 270000; return 0; } } + } else { + for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) { + for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) { + max_pix_clock = (lane_num * link_rates[i] * 8) / bpp; + if (max_pix_clock >= pix_clock) { + *dp_lanes = lane_num; + *dp_rate = link_rates[i]; + return 0; + } + } + } } return -EINVAL; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 902b59cebac58..4197ca1bb1e4d 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1744,7 +1744,6 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } drm_kms_helper_poll_enable(dev); - drm_helper_hpd_irq_event(dev); /* set the power state here in case we are a PX system or headless */ if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 2b9ba03a7c1a8..2d9196a447fdc 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -455,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - while (radeon_crtc->enabled && repcnt--) { + while (radeon_crtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -471,13 +471,13 @@ static void radeon_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); if (min_udelay > vblank->framedur_ns / 2000) { /* Don't wait ridiculously long - something is wrong */ repcnt = 0; break; } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index ca3be90a3bb43..7a98823bacd1c 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1079,10 +1079,8 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev) /* update display watermarks based on new power state */ radeon_bandwidth_update(rdev); - - rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; - rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; - rdev->pm.dpm.single_display = single_display; + /* update displays */ + radeon_dpm_display_configuration_changed(rdev); /* wait for the rings to drain */ for (i = 0; i < RADEON_NUM_RINGS; i++) { @@ -1099,8 +1097,9 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev) radeon_dpm_post_set_power_state(rdev); - /* update displays */ - radeon_dpm_display_configuration_changed(rdev); + rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; + rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; + rdev->pm.dpm.single_display = single_display; if (rdev->asic->dpm.force_performance_level) { if (rdev->pm.dpm.thermal_active) { diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c index 807863106b8da..bd736ace3f814 100644 --- a/drivers/gpu/drm/sti/sti_cursor.c +++ b/drivers/gpu/drm/sti/sti_cursor.c @@ -157,17 +157,15 @@ static void sti_cursor_atomic_update(struct drm_plane *drm_plane, cursor->height = src_h; if (cursor->pixmap.base) - dma_free_writecombine(cursor->dev, - cursor->pixmap.size, - cursor->pixmap.base, - cursor->pixmap.paddr); + dma_free_wc(cursor->dev, cursor->pixmap.size, + cursor->pixmap.base, cursor->pixmap.paddr); cursor->pixmap.size = cursor->width * cursor->height; - cursor->pixmap.base = dma_alloc_writecombine(cursor->dev, - cursor->pixmap.size, - &cursor->pixmap.paddr, - GFP_KERNEL | GFP_DMA); + cursor->pixmap.base = dma_alloc_wc(cursor->dev, + cursor->pixmap.size, + &cursor->pixmap.paddr, + GFP_KERNEL | GFP_DMA); if (!cursor->pixmap.base) { DRM_ERROR("Failed to allocate memory for pixmap\n"); return; @@ -252,8 +250,8 @@ struct drm_plane *sti_cursor_create(struct drm_device *drm_dev, /* Allocate clut buffer */ size = 0x100 * sizeof(unsigned short); - cursor->clut = dma_alloc_writecombine(dev, size, &cursor->clut_paddr, - GFP_KERNEL | GFP_DMA); + cursor->clut = dma_alloc_wc(dev, size, &cursor->clut_paddr, + GFP_KERNEL | GFP_DMA); if (!cursor->clut) { DRM_ERROR("Failed to allocate memory for cursor clut\n"); @@ -286,7 +284,7 @@ struct drm_plane *sti_cursor_create(struct drm_device *drm_dev, return &cursor->plane.drm_plane; err_plane: - dma_free_writecombine(dev, size, cursor->clut, cursor->clut_paddr); + dma_free_wc(dev, size, cursor->clut, cursor->clut_paddr); err_clut: devm_kfree(dev, cursor); return NULL; diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c index f9a1d92c9d951..514551c857bbd 100644 --- a/drivers/gpu/drm/sti/sti_gdp.c +++ b/drivers/gpu/drm/sti/sti_gdp.c @@ -312,8 +312,7 @@ static void sti_gdp_init(struct sti_gdp *gdp) /* Allocate all the nodes within a single memory page */ size = sizeof(struct sti_gdp_node) * GDP_NODE_PER_FIELD * GDP_NODE_NB_BANK; - base = dma_alloc_writecombine(gdp->dev, - size, &dma_addr, GFP_KERNEL | GFP_DMA); + base = dma_alloc_wc(gdp->dev, size, &dma_addr, GFP_KERNEL | GFP_DMA); if (!base) { DRM_ERROR("Failed to allocate memory for GDP node\n"); diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index 43861b52261d7..1d3c3d029603d 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -617,9 +617,9 @@ static void sti_hqvdp_init(struct sti_hqvdp *hqvdp) /* Allocate memory for the VDP commands */ size = NB_VDP_CMD * sizeof(struct sti_hqvdp_cmd); - hqvdp->hqvdp_cmd = dma_alloc_writecombine(hqvdp->dev, size, - &hqvdp->hqvdp_cmd_paddr, - GFP_KERNEL | GFP_DMA); + hqvdp->hqvdp_cmd = dma_alloc_wc(hqvdp->dev, size, + &hqvdp->hqvdp_cmd_paddr, + GFP_KERNEL | GFP_DMA); if (!hqvdp->hqvdp_cmd) { DRM_ERROR("Failed to allocate memory for VDP cmd\n"); return; diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 33add93b4ed96..3b0d8c392b707 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -175,8 +175,7 @@ static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo) sg_free_table(bo->sgt); kfree(bo->sgt); } else if (bo->vaddr) { - dma_free_writecombine(drm->dev, bo->gem.size, bo->vaddr, - bo->paddr); + dma_free_wc(drm->dev, bo->gem.size, bo->vaddr, bo->paddr); } } @@ -233,8 +232,8 @@ static int tegra_bo_alloc(struct drm_device *drm, struct tegra_bo *bo) } else { size_t size = bo->gem.size; - bo->vaddr = dma_alloc_writecombine(drm->dev, size, &bo->paddr, - GFP_KERNEL | __GFP_NOWARN); + bo->vaddr = dma_alloc_wc(drm->dev, size, &bo->paddr, + GFP_KERNEL | __GFP_NOWARN); if (!bo->vaddr) { dev_err(drm->dev, "failed to allocate buffer of size %zu\n", @@ -472,8 +471,8 @@ int tegra_drm_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags &= ~VM_PFNMAP; vma->vm_pgoff = 0; - ret = dma_mmap_writecombine(gem->dev->dev, vma, bo->vaddr, - bo->paddr, gem->size); + ret = dma_mmap_wc(gem->dev->dev, vma, bo->vaddr, bo->paddr, + gem->size); if (ret) { drm_gem_vm_close(vma); return ret; diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 22278bcfc60ea..034ef2de90376 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -398,9 +398,8 @@ int vc4_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_flags &= ~VM_PFNMAP; vma->vm_pgoff = 0; - ret = dma_mmap_writecombine(bo->base.base.dev->dev, vma, - bo->base.vaddr, bo->base.paddr, - vma->vm_end - vma->vm_start); + ret = dma_mmap_wc(bo->base.base.dev->dev, vma, bo->base.vaddr, + bo->base.paddr, vma->vm_end - vma->vm_start); if (ret) drm_gem_vm_close(vma); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index db082bea8dafd..c5a1a08b04490 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -563,6 +563,8 @@ static void vmw_sou_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs vmw_sou_connector_funcs = { .dpms = vmw_du_connector_dpms, + .detect = vmw_du_connector_detect, + .fill_modes = vmw_du_connector_fill_modes, .set_property = vmw_du_connector_set_property, .destroy = vmw_sou_connector_destroy, }; diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index da462afcb225e..dd2dbb9746ceb 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "bus.h" #include "dev.h" @@ -394,6 +395,7 @@ static int host1x_device_add(struct host1x *host1x, device->dev.coherent_dma_mask = host1x->dev->coherent_dma_mask; device->dev.dma_mask = &device->dev.coherent_dma_mask; dev_set_name(&device->dev, "%s", driver->driver.name); + of_dma_configure(&device->dev, host1x->dev->of_node); device->dev.release = host1x_device_release; device->dev.bus = &host1x_bus_type; device->dev.parent = host1x->dev; diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c index 5a8c8d55317ab..a18db4d5347ce 100644 --- a/drivers/gpu/host1x/cdma.c +++ b/drivers/gpu/host1x/cdma.c @@ -52,8 +52,8 @@ static void host1x_pushbuffer_destroy(struct push_buffer *pb) struct host1x *host1x = cdma_to_host1x(cdma); if (pb->phys != 0) - dma_free_writecombine(host1x->dev, pb->size_bytes + 4, - pb->mapped, pb->phys); + dma_free_wc(host1x->dev, pb->size_bytes + 4, pb->mapped, + pb->phys); pb->mapped = NULL; pb->phys = 0; @@ -76,8 +76,8 @@ static int host1x_pushbuffer_init(struct push_buffer *pb) pb->pos = 0; /* allocate and map pushbuffer memory */ - pb->mapped = dma_alloc_writecombine(host1x->dev, pb->size_bytes + 4, - &pb->phys, GFP_KERNEL); + pb->mapped = dma_alloc_wc(host1x->dev, pb->size_bytes + 4, &pb->phys, + GFP_KERNEL); if (!pb->mapped) goto fail; diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 314bf3718cc79..ff348690df94a 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -23,6 +23,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -68,6 +69,7 @@ static const struct host1x_info host1x01_info = { .nb_bases = 8, .init = host1x01_init, .sync_offset = 0x3000, + .dma_mask = DMA_BIT_MASK(32), }; static const struct host1x_info host1x02_info = { @@ -77,6 +79,7 @@ static const struct host1x_info host1x02_info = { .nb_bases = 12, .init = host1x02_init, .sync_offset = 0x3000, + .dma_mask = DMA_BIT_MASK(32), }; static const struct host1x_info host1x04_info = { @@ -86,6 +89,7 @@ static const struct host1x_info host1x04_info = { .nb_bases = 64, .init = host1x04_init, .sync_offset = 0x2100, + .dma_mask = DMA_BIT_MASK(34), }; static const struct host1x_info host1x05_info = { @@ -95,6 +99,7 @@ static const struct host1x_info host1x05_info = { .nb_bases = 64, .init = host1x05_init, .sync_offset = 0x2100, + .dma_mask = DMA_BIT_MASK(34), }; static struct of_device_id host1x_of_match[] = { @@ -148,6 +153,8 @@ static int host1x_probe(struct platform_device *pdev) if (IS_ERR(host->regs)) return PTR_ERR(host->regs); + dma_set_mask_and_coherent(host->dev, host->info->dma_mask); + if (host->info->init) { err = host->info->init(host); if (err) diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index 0b6e8e9629c53..dace124994bb2 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -96,6 +96,7 @@ struct host1x_info { int nb_mlocks; /* host1x: number of mlocks */ int (*init)(struct host1x *); /* initialize per SoC ops */ int sync_offset; + u64 dma_mask; /* mask of addressable memory */ }; struct host1x { diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 63bd63f3c7dfd..defa7995f2131 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -467,9 +467,8 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev) size += g->words * sizeof(u32); } - job->gather_copy_mapped = dma_alloc_writecombine(dev, size, - &job->gather_copy, - GFP_KERNEL); + job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy, + GFP_KERNEL); if (!job->gather_copy_mapped) { job->gather_copy_mapped = NULL; return -ENOMEM; @@ -578,9 +577,8 @@ void host1x_job_unpin(struct host1x_job *job) job->num_unpins = 0; if (job->gather_copy_size) - dma_free_writecombine(job->channel->dev, job->gather_copy_size, - job->gather_copy_mapped, - job->gather_copy); + dma_free_wc(job->channel->dev, job->gather_copy_size, + job->gather_copy_mapped, job->gather_copy); } EXPORT_SYMBOL(host1x_job_unpin); diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index f2e13eb8339ff..e00db3f510dd4 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -1050,6 +1050,17 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) for (i = 0; i < ARRAY_SIZE(client_reg); i++) { const struct ipu_platform_reg *reg = &client_reg[i]; struct platform_device *pdev; + struct device_node *of_node; + + /* Associate subdevice with the corresponding port node */ + of_node = of_graph_get_port_by_id(dev->of_node, i); + if (!of_node) { + dev_info(dev, + "no port@%d node in %s, not using %s%d\n", + i, dev->of_node->full_name, + (i / 2) ? "DI" : "CSI", i % 2); + continue; + } pdev = platform_device_alloc(reg->name, id++); if (!pdev) { @@ -1057,17 +1068,9 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) goto err_register; } + pdev->dev.of_node = of_node; pdev->dev.parent = dev; - /* Associate subdevice with the corresponding port node */ - pdev->dev.of_node = of_graph_get_port_by_id(dev->of_node, i); - if (!pdev->dev.of_node) { - dev_err(dev, "missing port@%d node in %s\n", i, - dev->of_node->full_name); - ret = -ENODEV; - goto err_register; - } - ret = platform_device_add_data(pdev, ®->pdata, sizeof(reg->pdata)); if (!ret) @@ -1289,10 +1292,6 @@ static int ipu_probe(struct platform_device *pdev) ipu->irq_sync = irq_sync; ipu->irq_err = irq_err; - ret = ipu_irq_init(ipu); - if (ret) - goto out_failed_irq; - ret = device_reset(&pdev->dev); if (ret) { dev_err(&pdev->dev, "failed to reset: %d\n", ret); @@ -1302,6 +1301,10 @@ static int ipu_probe(struct platform_device *pdev) if (ret) goto out_failed_reset; + ret = ipu_irq_init(ipu); + if (ret) + goto out_failed_irq; + /* Set MCU_T to divide MCU access window into 2 */ ipu_cm_write(ipu, 0x00400000L | (IPU_MCU_T_DEFAULT << 18), IPU_DISP_GEN); @@ -1324,9 +1327,9 @@ static int ipu_probe(struct platform_device *pdev) failed_add_clients: ipu_submodules_exit(ipu); failed_submodules_init: -out_failed_reset: ipu_irq_exit(ipu); out_failed_irq: +out_failed_reset: clk_disable_unprepare(ipu->clk); return ret; } diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 3711df1d45262..4a45408dd8206 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -586,8 +586,7 @@ static int brcmstb_i2c_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; - dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(struct bsc_regs *), - GFP_KERNEL); + dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(*dev->bsc_regmap), GFP_KERNEL); if (!dev->bsc_regmap) return -ENOMEM; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 00da80e021542..94b80a51ab68e 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -358,6 +358,7 @@ int ib_register_device(struct ib_device *device, ret = device->query_device(device, &device->attrs, &uhw); if (ret) { printk(KERN_WARNING "Couldn't query the device attributes\n"); + ib_cache_cleanup_one(device); goto out; } diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index f334090bb6129..1e37f3515d98a 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1071,7 +1071,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num, } } - if (rec->hop_limit > 1 || use_roce) { + if (rec->hop_limit > 0 || use_roce) { ah_attr->ah_flags = IB_AH_GRH; ah_attr->grh.dgid = rec->dgid; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 6ffc9c4e93afb..6c6fbff19752e 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1970,7 +1970,8 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, resp_size); INIT_UDATA(&uhw, buf + sizeof(cmd), (unsigned long)cmd.response + resp_size, - in_len - sizeof(cmd), out_len - resp_size); + in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), + out_len - resp_size); memset(&cmd_ex, 0, sizeof(cmd_ex)); cmd_ex.user_handle = cmd.user_handle; @@ -3413,7 +3414,8 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file, INIT_UDATA(&udata, buf + sizeof cmd, (unsigned long) cmd.response + sizeof resp, - in_len - sizeof cmd, out_len - sizeof resp); + in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr), + out_len - sizeof resp); ret = __uverbs_create_xsrq(file, ib_dev, &xcmd, &udata); if (ret) @@ -3439,7 +3441,8 @@ ssize_t ib_uverbs_create_xsrq(struct ib_uverbs_file *file, INIT_UDATA(&udata, buf + sizeof cmd, (unsigned long) cmd.response + sizeof resp, - in_len - sizeof cmd, out_len - sizeof resp); + in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr), + out_len - sizeof resp); ret = __uverbs_create_xsrq(file, ib_dev, &cmd, &udata); if (ret) diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 4659256cd95e6..3b2ddd64a3716 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -75,7 +75,8 @@ static void mlx5_ib_srq_event(struct mlx5_core_srq *srq, enum mlx5_event type) static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, struct mlx5_create_srq_mbox_in **in, - struct ib_udata *udata, int buf_size, int *inlen) + struct ib_udata *udata, int buf_size, int *inlen, + int is_xrc) { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_ib_create_srq ucmd = {}; @@ -87,13 +88,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, int ncont; u32 offset; u32 uidx = MLX5_IB_DEFAULT_UIDX; - int drv_data = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr); - if (drv_data < 0) - return -EINVAL; - - ucmdlen = (drv_data < sizeof(ucmd)) ? - drv_data : sizeof(ucmd); + ucmdlen = min(udata->inlen, sizeof(ucmd)); if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) { mlx5_ib_dbg(dev, "failed copy udata\n"); @@ -103,15 +99,17 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, if (ucmd.reserved0 || ucmd.reserved1) return -EINVAL; - if (drv_data > sizeof(ucmd) && + if (udata->inlen > sizeof(ucmd) && !ib_is_udata_cleared(udata, sizeof(ucmd), - drv_data - sizeof(ucmd))) + udata->inlen - sizeof(ucmd))) return -EINVAL; - err = get_srq_user_index(to_mucontext(pd->uobject->context), - &ucmd, udata->inlen, &uidx); - if (err) - return err; + if (is_xrc) { + err = get_srq_user_index(to_mucontext(pd->uobject->context), + &ucmd, udata->inlen, &uidx); + if (err) + return err; + } srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE); @@ -151,7 +149,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT; (*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26); - if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) { + if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) && + is_xrc){ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in, xrc_srq_context_entry); MLX5_SET(xrc_srqc, xsrqc, user_index, uidx); @@ -170,7 +169,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, struct mlx5_create_srq_mbox_in **in, int buf_size, - int *inlen) + int *inlen, int is_xrc) { int err; int i; @@ -224,7 +223,8 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT; - if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) { + if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) && + is_xrc){ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in, xrc_srq_context_entry); /* 0xffffff means we ask to work with cqe version 0 */ @@ -302,10 +302,14 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs, srq->msrq.max_avail_gather); + is_xrc = (init_attr->srq_type == IB_SRQT_XRC); + if (pd->uobject) - err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen); + err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen, + is_xrc); else - err = create_srq_kernel(dev, srq, &in, buf_size, &inlen); + err = create_srq_kernel(dev, srq, &in, buf_size, &inlen, + is_xrc); if (err) { mlx5_ib_warn(dev, "create srq %s failed, err %d\n", @@ -313,7 +317,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, goto err_srq; } - is_xrc = (init_attr->srq_type == IB_SRQT_XRC); in->ctx.state_log_sz = ilog2(srq->msrq.max); flgs = ((srq->msrq.wqe_shift - 4) | (is_xrc << 5) | (srq->wq_sig << 7)) << 24; xrcdn = 0; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index e5e223938eecc..374c129219ef0 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -114,6 +114,7 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); +static void detach_device(struct device *dev); /* * For dynamic growth the aperture size is split into ranges of 128MB of @@ -384,6 +385,9 @@ static void iommu_uninit_device(struct device *dev) if (!dev_data) return; + if (dev_data->domain) + detach_device(dev); + iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev, dev); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 013bdfff2d4d0..bf4959f4225bd 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -228,6 +228,10 @@ static int amd_iommu_enable_interrupts(void); static int __init iommu_go_to_state(enum iommu_init_state state); static void init_device_table_dma(void); +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write); + static inline void update_last_devid(u16 devid) { if (devid > amd_iommu_last_bdf) @@ -1015,6 +1019,34 @@ static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) pci_write_config_dword(iommu->dev, 0xf0, 0x90); } +/* + * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission) + * Workaround: + * BIOS should enable ATS write permission check by setting + * L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b + */ +static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu) +{ + u32 value; + + if ((boot_cpu_data.x86 != 0x15) || + (boot_cpu_data.x86_model < 0x30) || + (boot_cpu_data.x86_model > 0x3f)) + return; + + /* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */ + value = iommu_read_l2(iommu, 0x47); + + if (value & BIT(0)) + return; + + /* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */ + iommu_write_l2(iommu, 0x47, value | BIT(0)); + + pr_info("AMD-Vi: Applying ATS write check workaround for IOMMU at %s\n", + dev_name(&iommu->dev->dev)); +} + /* * This function clues the initialization function for one IOMMU * together and also allocates the command buffer and programs the @@ -1142,8 +1174,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu) amd_iommu_pc_present = true; /* Check if the performance counters can be written to */ - if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) || - (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) || + if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) || + (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) || (val != val2)) { pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n"); amd_iommu_pc_present = false; @@ -1284,6 +1316,7 @@ static int iommu_init_pci(struct amd_iommu *iommu) } amd_iommu_erratum_746_workaround(iommu); + amd_iommu_ats_write_check_workaround(iommu); iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu, amd_iommu_groups, "ivhd%d", @@ -2283,22 +2316,15 @@ u8 amd_iommu_pc_get_max_counters(u16 devid) } EXPORT_SYMBOL(amd_iommu_pc_get_max_counters); -int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, u64 *value, bool is_write) { - struct amd_iommu *iommu; u32 offset; u32 max_offset_lim; - /* Make sure the IOMMU PC resource is available */ - if (!amd_iommu_pc_present) - return -ENODEV; - - /* Locate the iommu associated with the device ID */ - iommu = amd_iommu_rlookup_table[devid]; - /* Check for valid iommu and pc register indexing */ - if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7))) + if (WARN_ON((fxn > 0x28) || (fxn & 7))) return -ENODEV; offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn); @@ -2322,3 +2348,16 @@ int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, return 0; } EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val); + +int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write) +{ + struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; + + /* Make sure the IOMMU PC resource is available */ + if (!amd_iommu_pc_present || iommu == NULL) + return -ENODEV; + + return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn, + value, is_write); +} diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index fb092f3f11cb3..8ffd7568fc919 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -329,7 +329,8 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, /* Only care about add/remove events for physical functions */ if (pdev->is_virtfn) return NOTIFY_DONE; - if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE) + if (action != BUS_NOTIFY_ADD_DEVICE && + action != BUS_NOTIFY_REMOVED_DEVICE) return NOTIFY_DONE; info = dmar_alloc_pci_notify_info(pdev, action); @@ -339,7 +340,7 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, down_write(&dmar_global_lock); if (action == BUS_NOTIFY_ADD_DEVICE) dmar_pci_bus_add_dev(info); - else if (action == BUS_NOTIFY_DEL_DEVICE) + else if (action == BUS_NOTIFY_REMOVED_DEVICE) dmar_pci_bus_del_dev(info); up_write(&dmar_global_lock); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 986a53e3eb96b..a2e1b7f14df29 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4367,7 +4367,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) rmrru->devices_cnt); if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { dmar_remove_dev_scope(info, rmrr->segment, rmrru->devices, rmrru->devices_cnt); } @@ -4387,7 +4387,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) break; else if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { if (dmar_remove_dev_scope(info, atsr->segment, atsru->devices, atsru->devices_cnt)) break; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index fb50911b3940c..7e8c441ff2de3 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -60,6 +60,17 @@ config ARM_VIC_NR The maximum number of VICs available in the system, for power management. +config ARMADA_370_XP_IRQ + bool + select GENERIC_IRQ_CHIP + select PCI_MSI_IRQ_DOMAIN if PCI_MSI + +config ALPINE_MSI + bool + depends on PCI && PCI_MSI + select GENERIC_IRQ_CHIP + select PCI_MSI_IRQ_DOMAIN + config ATMEL_AIC_IRQ bool select GENERIC_IRQ_CHIP @@ -78,6 +89,11 @@ config I8259 bool select IRQ_DOMAIN +config BCM6345_L1_IRQ + bool + select GENERIC_IRQ_CHIP + select IRQ_DOMAIN + config BCM7038_L1_IRQ bool select GENERIC_IRQ_CHIP @@ -151,6 +167,11 @@ config ST_IRQCHIP help Enables SysCfg Controlled IRQs on STi based platforms. +config TANGO_IRQ + bool + select IRQ_DOMAIN + select GENERIC_IRQ_CHIP + config TB10X_IRQC bool select IRQ_DOMAIN @@ -160,6 +181,7 @@ config TS4800_IRQ tristate "TS-4800 IRQ controller" select IRQ_DOMAIN depends on HAS_IOMEM + depends on SOC_IMX51 || COMPILE_TEST help Support for the TS-4800 FPGA IRQ controller @@ -193,6 +215,8 @@ config KEYSTONE_IRQ config MIPS_GIC bool + select GENERIC_IRQ_IPI + select IRQ_DOMAIN_HIERARCHY select MIPS_CM config INGENIC_IRQ @@ -218,3 +242,7 @@ config IRQ_MXS def_bool y if MACH_ASM9260 || ARCH_MXS select IRQ_DOMAIN select STMP_DEVICE + +config MVEBU_ODMI + bool + select GENERIC_MSI_IRQ_DOMAIN diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 18caacb60d581..b03cfcbbac6b9 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -1,11 +1,13 @@ obj-$(CONFIG_IRQCHIP) += irqchip.o +obj-$(CONFIG_ALPINE_MSI) += irq-alpine-msi.o +obj-$(CONFIG_ATH79) += irq-ath79-cpu.o +obj-$(CONFIG_ATH79) += irq-ath79-misc.o obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2835.o obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2836.o obj-$(CONFIG_ARCH_EXYNOS) += exynos-combiner.o obj-$(CONFIG_ARCH_HIP04) += irq-hip04.o obj-$(CONFIG_ARCH_MMP) += irq-mmp.o -obj-$(CONFIG_ARCH_MVEBU) += irq-armada-370-xp.o obj-$(CONFIG_IRQ_MXS) += irq-mxs.o obj-$(CONFIG_ARCH_TEGRA) += irq-tegra.o obj-$(CONFIG_ARCH_S3C24XX) += irq-s3c24xx.o @@ -28,6 +30,7 @@ obj-$(CONFIG_ARM_GIC_V3_ITS) += irq-gic-v3-its.o irq-gic-v3-its-pci-msi.o irq-g obj-$(CONFIG_HISILICON_IRQ_MBIGEN) += irq-mbigen.o obj-$(CONFIG_ARM_NVIC) += irq-nvic.o obj-$(CONFIG_ARM_VIC) += irq-vic.o +obj-$(CONFIG_ARMADA_370_XP_IRQ) += irq-armada-370-xp.o obj-$(CONFIG_ATMEL_AIC_IRQ) += irq-atmel-aic-common.o irq-atmel-aic.o obj-$(CONFIG_ATMEL_AIC5_IRQ) += irq-atmel-aic-common.o irq-atmel-aic5.o obj-$(CONFIG_I8259) += irq-i8259.o @@ -40,12 +43,14 @@ obj-$(CONFIG_VERSATILE_FPGA_IRQ) += irq-versatile-fpga.o obj-$(CONFIG_ARCH_NSPIRE) += irq-zevio.o obj-$(CONFIG_ARCH_VT8500) += irq-vt8500.o obj-$(CONFIG_ST_IRQCHIP) += irq-st.o +obj-$(CONFIG_TANGO_IRQ) += irq-tango.o obj-$(CONFIG_TB10X_IRQC) += irq-tb10x.o obj-$(CONFIG_TS4800_IRQ) += irq-ts4800.o obj-$(CONFIG_XTENSA) += irq-xtensa-pic.o obj-$(CONFIG_XTENSA_MX) += irq-xtensa-mx.o obj-$(CONFIG_IRQ_CROSSBAR) += irq-crossbar.o obj-$(CONFIG_SOC_VF610) += irq-vf610-mscm-ir.o +obj-$(CONFIG_BCM6345_L1_IRQ) += irq-bcm6345-l1.o obj-$(CONFIG_BCM7038_L1_IRQ) += irq-bcm7038-l1.o obj-$(CONFIG_BCM7120_L2_IRQ) += irq-bcm7120-l2.o obj-$(CONFIG_BRCMSTB_L2_IRQ) += irq-brcmstb-l2.o @@ -59,3 +64,4 @@ obj-$(CONFIG_ARCH_SA1100) += irq-sa11x0.o obj-$(CONFIG_INGENIC_IRQ) += irq-ingenic.o obj-$(CONFIG_IMX_GPCV2) += irq-imx-gpcv2.o obj-$(CONFIG_PIC32_EVIC) += irq-pic32-evic.o +obj-$(CONFIG_MVEBU_ODMI) += irq-mvebu-odmi.o diff --git a/drivers/irqchip/irq-alpine-msi.c b/drivers/irqchip/irq-alpine-msi.c new file mode 100644 index 0000000000000..25384255b30f5 --- /dev/null +++ b/drivers/irqchip/irq-alpine-msi.c @@ -0,0 +1,293 @@ +/* + * Annapurna Labs MSIX support services + * + * Copyright (C) 2016, Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * Antoine Tenart + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +/* MSIX message address format: local GIC target */ +#define ALPINE_MSIX_SPI_TARGET_CLUSTER0 BIT(16) + +struct alpine_msix_data { + spinlock_t msi_map_lock; + phys_addr_t addr; + u32 spi_first; /* The SGI number that MSIs start */ + u32 num_spis; /* The number of SGIs for MSIs */ + unsigned long *msi_map; +}; + +static void alpine_msix_mask_msi_irq(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void alpine_msix_unmask_msi_irq(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} + +static struct irq_chip alpine_msix_irq_chip = { + .name = "MSIx", + .irq_mask = alpine_msix_mask_msi_irq, + .irq_unmask = alpine_msix_unmask_msi_irq, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, +}; + +static int alpine_msix_allocate_sgi(struct alpine_msix_data *priv, int num_req) +{ + int first; + + spin_lock(&priv->msi_map_lock); + + first = bitmap_find_next_zero_area(priv->msi_map, priv->num_spis, 0, + num_req, 0); + if (first >= priv->num_spis) { + spin_unlock(&priv->msi_map_lock); + return -ENOSPC; + } + + bitmap_set(priv->msi_map, first, num_req); + + spin_unlock(&priv->msi_map_lock); + + return priv->spi_first + first; +} + +static void alpine_msix_free_sgi(struct alpine_msix_data *priv, unsigned sgi, + int num_req) +{ + int first = sgi - priv->spi_first; + + spin_lock(&priv->msi_map_lock); + + bitmap_clear(priv->msi_map, first, num_req); + + spin_unlock(&priv->msi_map_lock); +} + +static void alpine_msix_compose_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + struct alpine_msix_data *priv = irq_data_get_irq_chip_data(data); + phys_addr_t msg_addr = priv->addr; + + msg_addr |= (data->hwirq << 3); + + msg->address_hi = upper_32_bits(msg_addr); + msg->address_lo = lower_32_bits(msg_addr); + msg->data = 0; +} + +static struct msi_domain_info alpine_msix_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .chip = &alpine_msix_irq_chip, +}; + +static struct irq_chip middle_irq_chip = { + .name = "alpine_msix_middle", + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_compose_msi_msg = alpine_msix_compose_msi_msg, +}; + +static int alpine_msix_gic_domain_alloc(struct irq_domain *domain, + unsigned int virq, int sgi) +{ + struct irq_fwspec fwspec; + struct irq_data *d; + int ret; + + if (!is_of_node(domain->parent->fwnode)) + return -EINVAL; + + fwspec.fwnode = domain->parent->fwnode; + fwspec.param_count = 3; + fwspec.param[0] = 0; + fwspec.param[1] = sgi; + fwspec.param[2] = IRQ_TYPE_EDGE_RISING; + + ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec); + if (ret) + return ret; + + d = irq_domain_get_irq_data(domain->parent, virq); + d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING); + + return 0; +} + +static int alpine_msix_middle_domain_alloc(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct alpine_msix_data *priv = domain->host_data; + int sgi, err, i; + + sgi = alpine_msix_allocate_sgi(priv, nr_irqs); + if (sgi < 0) + return sgi; + + for (i = 0; i < nr_irqs; i++) { + err = alpine_msix_gic_domain_alloc(domain, virq + i, sgi + i); + if (err) + goto err_sgi; + + irq_domain_set_hwirq_and_chip(domain, virq + i, sgi + i, + &middle_irq_chip, priv); + } + + return 0; + +err_sgi: + while (--i >= 0) + irq_domain_free_irqs_parent(domain, virq, i); + alpine_msix_free_sgi(priv, sgi, nr_irqs); + return err; +} + +static void alpine_msix_middle_domain_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct alpine_msix_data *priv = irq_data_get_irq_chip_data(d); + + irq_domain_free_irqs_parent(domain, virq, nr_irqs); + alpine_msix_free_sgi(priv, d->hwirq, nr_irqs); +} + +static const struct irq_domain_ops alpine_msix_middle_domain_ops = { + .alloc = alpine_msix_middle_domain_alloc, + .free = alpine_msix_middle_domain_free, +}; + +static int alpine_msix_init_domains(struct alpine_msix_data *priv, + struct device_node *node) +{ + struct irq_domain *middle_domain, *msi_domain, *gic_domain; + struct device_node *gic_node; + + gic_node = of_irq_find_parent(node); + if (!gic_node) { + pr_err("Failed to find the GIC node\n"); + return -ENODEV; + } + + gic_domain = irq_find_host(gic_node); + if (!gic_domain) { + pr_err("Failed to find the GIC domain\n"); + return -ENXIO; + } + + middle_domain = irq_domain_add_tree(NULL, + &alpine_msix_middle_domain_ops, + priv); + if (!middle_domain) { + pr_err("Failed to create the MSIX middle domain\n"); + return -ENOMEM; + } + + middle_domain->parent = gic_domain; + + msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(node), + &alpine_msix_domain_info, + middle_domain); + if (!msi_domain) { + pr_err("Failed to create MSI domain\n"); + irq_domain_remove(middle_domain); + return -ENOMEM; + } + + return 0; +} + +static int alpine_msix_init(struct device_node *node, + struct device_node *parent) +{ + struct alpine_msix_data *priv; + struct resource res; + int ret; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->msi_map_lock); + + ret = of_address_to_resource(node, 0, &res); + if (ret) { + pr_err("Failed to allocate resource\n"); + goto err_priv; + } + + /* + * The 20 least significant bits of addr provide direct information + * regarding the interrupt destination. + * + * To select the primary GIC as the target GIC, bits [18:17] must be set + * to 0x0. In this case, bit 16 (SPI_TARGET_CLUSTER0) must be set. + */ + priv->addr = res.start & GENMASK_ULL(63,20); + priv->addr |= ALPINE_MSIX_SPI_TARGET_CLUSTER0; + + if (of_property_read_u32(node, "al,msi-base-spi", &priv->spi_first)) { + pr_err("Unable to parse MSI base\n"); + ret = -EINVAL; + goto err_priv; + } + + if (of_property_read_u32(node, "al,msi-num-spis", &priv->num_spis)) { + pr_err("Unable to parse MSI numbers\n"); + ret = -EINVAL; + goto err_priv; + } + + priv->msi_map = kzalloc(sizeof(*priv->msi_map) * BITS_TO_LONGS(priv->num_spis), + GFP_KERNEL); + if (!priv->msi_map) { + ret = -ENOMEM; + goto err_priv; + } + + pr_debug("Registering %d msixs, starting at %d\n", + priv->num_spis, priv->spi_first); + + ret = alpine_msix_init_domains(priv, node); + if (ret) + goto err_map; + + return 0; + +err_map: + kfree(priv->msi_map); +err_priv: + kfree(priv); + return ret; +} +IRQCHIP_DECLARE(alpine_msix, "al,alpine-msix", alpine_msix_init); diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 3f3a8c3d2175e..e7dc6cbda2a1b 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -71,6 +71,7 @@ static u32 doorbell_mask_reg; static int parent_irq; #ifdef CONFIG_PCI_MSI static struct irq_domain *armada_370_xp_msi_domain; +static struct irq_domain *armada_370_xp_msi_inner_domain; static DECLARE_BITMAP(msi_used, PCI_MSI_DOORBELL_NR); static DEFINE_MUTEX(msi_used_lock); static phys_addr_t msi_doorbell_addr; @@ -115,127 +116,102 @@ static void armada_370_xp_irq_unmask(struct irq_data *d) #ifdef CONFIG_PCI_MSI -static int armada_370_xp_alloc_msi(void) -{ - int hwirq; +static struct irq_chip armada_370_xp_msi_irq_chip = { + .name = "MPIC MSI", + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; - mutex_lock(&msi_used_lock); - hwirq = find_first_zero_bit(&msi_used, PCI_MSI_DOORBELL_NR); - if (hwirq >= PCI_MSI_DOORBELL_NR) - hwirq = -ENOSPC; - else - set_bit(hwirq, msi_used); - mutex_unlock(&msi_used_lock); +static struct msi_domain_info armada_370_xp_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI), + .chip = &armada_370_xp_msi_irq_chip, +}; - return hwirq; +static void armada_370_xp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + msg->address_lo = lower_32_bits(msi_doorbell_addr); + msg->address_hi = upper_32_bits(msi_doorbell_addr); + msg->data = 0xf00 | (data->hwirq + PCI_MSI_DOORBELL_START); } -static void armada_370_xp_free_msi(int hwirq) +static int armada_370_xp_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) { - mutex_lock(&msi_used_lock); - if (!test_bit(hwirq, msi_used)) - pr_err("trying to free unused MSI#%d\n", hwirq); - else - clear_bit(hwirq, msi_used); - mutex_unlock(&msi_used_lock); + return -EINVAL; } -static int armada_370_xp_setup_msi_irq(struct msi_controller *chip, - struct pci_dev *pdev, - struct msi_desc *desc) -{ - struct msi_msg msg; - int virq, hwirq; +static struct irq_chip armada_370_xp_msi_bottom_irq_chip = { + .name = "MPIC MSI", + .irq_compose_msi_msg = armada_370_xp_compose_msi_msg, + .irq_set_affinity = armada_370_xp_msi_set_affinity, +}; - /* We support MSI, but not MSI-X */ - if (desc->msi_attrib.is_msix) - return -EINVAL; +static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + int hwirq, i; - hwirq = armada_370_xp_alloc_msi(); - if (hwirq < 0) - return hwirq; + mutex_lock(&msi_used_lock); - virq = irq_create_mapping(armada_370_xp_msi_domain, hwirq); - if (!virq) { - armada_370_xp_free_msi(hwirq); - return -EINVAL; + hwirq = bitmap_find_next_zero_area(msi_used, PCI_MSI_DOORBELL_NR, + 0, nr_irqs, 0); + if (hwirq >= PCI_MSI_DOORBELL_NR) { + mutex_unlock(&msi_used_lock); + return -ENOSPC; } - irq_set_msi_desc(virq, desc); - - msg.address_lo = msi_doorbell_addr; - msg.address_hi = 0; - msg.data = 0xf00 | (hwirq + 16); - - pci_write_msi_msg(virq, &msg); - return 0; -} + bitmap_set(msi_used, hwirq, nr_irqs); + mutex_unlock(&msi_used_lock); -static void armada_370_xp_teardown_msi_irq(struct msi_controller *chip, - unsigned int irq) -{ - struct irq_data *d = irq_get_irq_data(irq); - unsigned long hwirq = d->hwirq; + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, hwirq + i, + &armada_370_xp_msi_bottom_irq_chip, + domain->host_data, handle_simple_irq, + NULL, NULL); + } - irq_dispose_mapping(irq); - armada_370_xp_free_msi(hwirq); + return hwirq; } -static struct irq_chip armada_370_xp_msi_irq_chip = { - .name = "armada_370_xp_msi_irq", - .irq_enable = pci_msi_unmask_irq, - .irq_disable = pci_msi_mask_irq, - .irq_mask = pci_msi_mask_irq, - .irq_unmask = pci_msi_unmask_irq, -}; - -static int armada_370_xp_msi_map(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hw) +static void armada_370_xp_msi_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) { - irq_set_chip_and_handler(virq, &armada_370_xp_msi_irq_chip, - handle_simple_irq); + struct irq_data *d = irq_domain_get_irq_data(domain, virq); - return 0; + mutex_lock(&msi_used_lock); + bitmap_clear(msi_used, d->hwirq, nr_irqs); + mutex_unlock(&msi_used_lock); } -static const struct irq_domain_ops armada_370_xp_msi_irq_ops = { - .map = armada_370_xp_msi_map, +static const struct irq_domain_ops armada_370_xp_msi_domain_ops = { + .alloc = armada_370_xp_msi_alloc, + .free = armada_370_xp_msi_free, }; static int armada_370_xp_msi_init(struct device_node *node, phys_addr_t main_int_phys_base) { - struct msi_controller *msi_chip; u32 reg; - int ret; msi_doorbell_addr = main_int_phys_base + ARMADA_370_XP_SW_TRIG_INT_OFFS; - msi_chip = kzalloc(sizeof(*msi_chip), GFP_KERNEL); - if (!msi_chip) + armada_370_xp_msi_inner_domain = + irq_domain_add_linear(NULL, PCI_MSI_DOORBELL_NR, + &armada_370_xp_msi_domain_ops, NULL); + if (!armada_370_xp_msi_inner_domain) return -ENOMEM; - msi_chip->setup_irq = armada_370_xp_setup_msi_irq; - msi_chip->teardown_irq = armada_370_xp_teardown_msi_irq; - msi_chip->of_node = node; - armada_370_xp_msi_domain = - irq_domain_add_linear(NULL, PCI_MSI_DOORBELL_NR, - &armada_370_xp_msi_irq_ops, - NULL); + pci_msi_create_irq_domain(of_node_to_fwnode(node), + &armada_370_xp_msi_domain_info, + armada_370_xp_msi_inner_domain); if (!armada_370_xp_msi_domain) { - kfree(msi_chip); + irq_domain_remove(armada_370_xp_msi_inner_domain); return -ENOMEM; } - ret = of_pci_msi_chip_add(msi_chip); - if (ret < 0) { - irq_domain_remove(armada_370_xp_msi_domain); - kfree(msi_chip); - return ret; - } - reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS) | PCI_MSI_DOORBELL_MASK; @@ -280,7 +256,7 @@ static int armada_xp_set_affinity(struct irq_data *d, #endif static struct irq_chip armada_370_xp_irq_chip = { - .name = "armada_370_xp_irq", + .name = "MPIC", .irq_mask = armada_370_xp_irq_mask, .irq_mask_ack = armada_370_xp_irq_mask, .irq_unmask = armada_370_xp_irq_unmask, @@ -427,12 +403,12 @@ static void armada_370_xp_handle_msi_irq(struct pt_regs *regs, bool is_chained) continue; if (is_chained) { - irq = irq_find_mapping(armada_370_xp_msi_domain, - msinr - 16); + irq = irq_find_mapping(armada_370_xp_msi_inner_domain, + msinr - PCI_MSI_DOORBELL_START); generic_handle_irq(irq); } else { - irq = msinr - 16; - handle_domain_irq(armada_370_xp_msi_domain, + irq = msinr - PCI_MSI_DOORBELL_START; + handle_domain_irq(armada_370_xp_msi_inner_domain, irq, regs); } } @@ -604,8 +580,8 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node, armada_370_xp_mpic_domain = irq_domain_add_linear(node, nr_irqs, &armada_370_xp_mpic_irq_ops, NULL); - BUG_ON(!armada_370_xp_mpic_domain); + armada_370_xp_mpic_domain->bus_token = DOMAIN_BUS_WIRED; /* Setup for the boot CPU */ armada_xp_mpic_perf_init(); diff --git a/drivers/irqchip/irq-ath79-cpu.c b/drivers/irqchip/irq-ath79-cpu.c new file mode 100644 index 0000000000000..befe93c5a51a2 --- /dev/null +++ b/drivers/irqchip/irq-ath79-cpu.c @@ -0,0 +1,97 @@ +/* + * Atheros AR71xx/AR724x/AR913x specific interrupt handling + * + * Copyright (C) 2015 Alban Bedel + * Copyright (C) 2010-2011 Jaiganesh Narayanan + * Copyright (C) 2008-2011 Gabor Juhos + * Copyright (C) 2008 Imre Kaloz + * + * Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include +#include +#include + +#include +#include + +/* + * The IP2/IP3 lines are tied to a PCI/WMAC/USB device. Drivers for + * these devices typically allocate coherent DMA memory, however the + * DMA controller may still have some unsynchronized data in the FIFO. + * Issue a flush in the handlers to ensure that the driver sees + * the update. + * + * This array map the interrupt lines to the DDR write buffer channels. + */ + +static unsigned irq_wb_chan[8] = { + -1, -1, -1, -1, -1, -1, -1, -1, +}; + +asmlinkage void plat_irq_dispatch(void) +{ + unsigned long pending; + int irq; + + pending = read_c0_status() & read_c0_cause() & ST0_IM; + + if (!pending) { + spurious_interrupt(); + return; + } + + pending >>= CAUSEB_IP; + while (pending) { + irq = fls(pending) - 1; + if (irq < ARRAY_SIZE(irq_wb_chan) && irq_wb_chan[irq] != -1) + ath79_ddr_wb_flush(irq_wb_chan[irq]); + do_IRQ(MIPS_CPU_IRQ_BASE + irq); + pending &= ~BIT(irq); + } +} + +static int __init ar79_cpu_intc_of_init( + struct device_node *node, struct device_node *parent) +{ + int err, i, count; + + /* Fill the irq_wb_chan table */ + count = of_count_phandle_with_args( + node, "qca,ddr-wb-channels", "#qca,ddr-wb-channel-cells"); + + for (i = 0; i < count; i++) { + struct of_phandle_args args; + u32 irq = i; + + of_property_read_u32_index( + node, "qca,ddr-wb-channel-interrupts", i, &irq); + if (irq >= ARRAY_SIZE(irq_wb_chan)) + continue; + + err = of_parse_phandle_with_args( + node, "qca,ddr-wb-channels", + "#qca,ddr-wb-channel-cells", + i, &args); + if (err) + return err; + + irq_wb_chan[irq] = args.args[0]; + } + + return mips_cpu_irq_of_init(node, parent); +} +IRQCHIP_DECLARE(ar79_cpu_intc, "qca,ar7100-cpu-intc", + ar79_cpu_intc_of_init); + +void __init ath79_cpu_irq_init(unsigned irq_wb_chan2, unsigned irq_wb_chan3) +{ + irq_wb_chan[2] = irq_wb_chan2; + irq_wb_chan[3] = irq_wb_chan3; + mips_cpu_irq_init(); +} diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c new file mode 100644 index 0000000000000..aa72907846360 --- /dev/null +++ b/drivers/irqchip/irq-ath79-misc.c @@ -0,0 +1,189 @@ +/* + * Atheros AR71xx/AR724x/AR913x MISC interrupt controller + * + * Copyright (C) 2015 Alban Bedel + * Copyright (C) 2010-2011 Jaiganesh Narayanan + * Copyright (C) 2008-2011 Gabor Juhos + * Copyright (C) 2008 Imre Kaloz + * + * Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include +#include +#include +#include + +#define AR71XX_RESET_REG_MISC_INT_STATUS 0 +#define AR71XX_RESET_REG_MISC_INT_ENABLE 4 + +#define ATH79_MISC_IRQ_COUNT 32 + +static void ath79_misc_irq_handler(struct irq_desc *desc) +{ + struct irq_domain *domain = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + void __iomem *base = domain->host_data; + u32 pending; + + chained_irq_enter(chip, desc); + + pending = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS) & + __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); + + if (!pending) { + spurious_interrupt(); + chained_irq_exit(chip, desc); + return; + } + + while (pending) { + int bit = __ffs(pending); + + generic_handle_irq(irq_linear_revmap(domain, bit)); + pending &= ~BIT(bit); + } + + chained_irq_exit(chip, desc); +} + +static void ar71xx_misc_irq_unmask(struct irq_data *d) +{ + void __iomem *base = irq_data_get_irq_chip_data(d); + unsigned int irq = d->hwirq; + u32 t; + + t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); + __raw_writel(t | BIT(irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE); + + /* flush write */ + __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); +} + +static void ar71xx_misc_irq_mask(struct irq_data *d) +{ + void __iomem *base = irq_data_get_irq_chip_data(d); + unsigned int irq = d->hwirq; + u32 t; + + t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); + __raw_writel(t & ~BIT(irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE); + + /* flush write */ + __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); +} + +static void ar724x_misc_irq_ack(struct irq_data *d) +{ + void __iomem *base = irq_data_get_irq_chip_data(d); + unsigned int irq = d->hwirq; + u32 t; + + t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS); + __raw_writel(t & ~BIT(irq), base + AR71XX_RESET_REG_MISC_INT_STATUS); + + /* flush write */ + __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS); +} + +static struct irq_chip ath79_misc_irq_chip = { + .name = "MISC", + .irq_unmask = ar71xx_misc_irq_unmask, + .irq_mask = ar71xx_misc_irq_mask, +}; + +static int misc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) +{ + irq_set_chip_and_handler(irq, &ath79_misc_irq_chip, handle_level_irq); + irq_set_chip_data(irq, d->host_data); + return 0; +} + +static const struct irq_domain_ops misc_irq_domain_ops = { + .xlate = irq_domain_xlate_onecell, + .map = misc_map, +}; + +static void __init ath79_misc_intc_domain_init( + struct irq_domain *domain, int irq) +{ + void __iomem *base = domain->host_data; + + /* Disable and clear all interrupts */ + __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE); + __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS); + + irq_set_chained_handler_and_data(irq, ath79_misc_irq_handler, domain); +} + +static int __init ath79_misc_intc_of_init( + struct device_node *node, struct device_node *parent) +{ + struct irq_domain *domain; + void __iomem *base; + int irq; + + irq = irq_of_parse_and_map(node, 0); + if (!irq) { + pr_err("Failed to get MISC IRQ\n"); + return -EINVAL; + } + + base = of_iomap(node, 0); + if (!base) { + pr_err("Failed to get MISC IRQ registers\n"); + return -ENOMEM; + } + + domain = irq_domain_add_linear(node, ATH79_MISC_IRQ_COUNT, + &misc_irq_domain_ops, base); + if (!domain) { + pr_err("Failed to add MISC irqdomain\n"); + return -EINVAL; + } + + ath79_misc_intc_domain_init(domain, irq); + return 0; +} + +static int __init ar7100_misc_intc_of_init( + struct device_node *node, struct device_node *parent) +{ + ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask; + return ath79_misc_intc_of_init(node, parent); +} + +IRQCHIP_DECLARE(ar7100_misc_intc, "qca,ar7100-misc-intc", + ar7100_misc_intc_of_init); + +static int __init ar7240_misc_intc_of_init( + struct device_node *node, struct device_node *parent) +{ + ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack; + return ath79_misc_intc_of_init(node, parent); +} + +IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc", + ar7240_misc_intc_of_init); + +void __init ath79_misc_irq_init(void __iomem *regs, int irq, + int irq_base, bool is_ar71xx) +{ + struct irq_domain *domain; + + if (is_ar71xx) + ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask; + else + ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack; + + domain = irq_domain_add_legacy(NULL, ATH79_MISC_IRQ_COUNT, + irq_base, 0, &misc_irq_domain_ops, regs); + if (!domain) + panic("Failed to create MISC irqdomain"); + + ath79_misc_intc_domain_init(domain, irq); +} diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c index 37199b9b2cfa2..28b26c80f4cf9 100644 --- a/drivers/irqchip/irq-atmel-aic-common.c +++ b/drivers/irqchip/irq-atmel-aic-common.c @@ -80,16 +80,10 @@ int aic_common_set_type(struct irq_data *d, unsigned type, unsigned *val) return 0; } -int aic_common_set_priority(int priority, unsigned *val) +void aic_common_set_priority(int priority, unsigned *val) { - if (priority < AT91_AIC_IRQ_MIN_PRIORITY || - priority > AT91_AIC_IRQ_MAX_PRIORITY) - return -EINVAL; - *val &= ~AT91_AIC_PRIOR; *val |= priority; - - return 0; } int aic_common_irq_domain_xlate(struct irq_domain *d, @@ -193,7 +187,7 @@ void __init aic_common_rtt_irq_fixup(struct device_node *root) } } -void __init aic_common_irq_fixup(const struct of_device_id *matches) +static void __init aic_common_irq_fixup(const struct of_device_id *matches) { struct device_node *root = of_find_node_by_path("/"); const struct of_device_id *match; @@ -214,7 +208,8 @@ void __init aic_common_irq_fixup(const struct of_device_id *matches) struct irq_domain *__init aic_common_of_init(struct device_node *node, const struct irq_domain_ops *ops, - const char *name, int nirqs) + const char *name, int nirqs, + const struct of_device_id *matches) { struct irq_chip_generic *gc; struct irq_domain *domain; @@ -264,6 +259,7 @@ struct irq_domain *__init aic_common_of_init(struct device_node *node, } aic_common_ext_irq_of_init(domain); + aic_common_irq_fixup(matches); return domain; diff --git a/drivers/irqchip/irq-atmel-aic-common.h b/drivers/irqchip/irq-atmel-aic-common.h index 603f0a9d5411a..af60376d50deb 100644 --- a/drivers/irqchip/irq-atmel-aic-common.h +++ b/drivers/irqchip/irq-atmel-aic-common.h @@ -19,7 +19,7 @@ int aic_common_set_type(struct irq_data *d, unsigned type, unsigned *val); -int aic_common_set_priority(int priority, unsigned *val); +void aic_common_set_priority(int priority, unsigned *val); int aic_common_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, @@ -30,12 +30,11 @@ int aic_common_irq_domain_xlate(struct irq_domain *d, struct irq_domain *__init aic_common_of_init(struct device_node *node, const struct irq_domain_ops *ops, - const char *name, int nirqs); + const char *name, int nirqs, + const struct of_device_id *matches); void __init aic_common_rtc_irq_fixup(struct device_node *root); void __init aic_common_rtt_irq_fixup(struct device_node *root); -void __init aic_common_irq_fixup(const struct of_device_id *matches); - #endif /* __IRQ_ATMEL_AIC_COMMON_H */ diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c index 8a0c7f2881984..112e17c2768be 100644 --- a/drivers/irqchip/irq-atmel-aic.c +++ b/drivers/irqchip/irq-atmel-aic.c @@ -196,9 +196,8 @@ static int aic_irq_domain_xlate(struct irq_domain *d, irq_gc_lock(gc); smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq)); - ret = aic_common_set_priority(intspec[2], &smr); - if (!ret) - irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq)); + aic_common_set_priority(intspec[2], &smr); + irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq)); irq_gc_unlock(gc); return ret; @@ -248,12 +247,10 @@ static int __init aic_of_init(struct device_node *node, return -EEXIST; domain = aic_common_of_init(node, &aic_irq_ops, "atmel-aic", - NR_AIC_IRQS); + NR_AIC_IRQS, aic_irq_fixups); if (IS_ERR(domain)) return PTR_ERR(domain); - aic_common_irq_fixup(aic_irq_fixups); - aic_domain = domain; gc = irq_get_domain_generic_chip(domain, 0); diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c index 62bb840c613f2..4f0d068e1abec 100644 --- a/drivers/irqchip/irq-atmel-aic5.c +++ b/drivers/irqchip/irq-atmel-aic5.c @@ -272,9 +272,8 @@ static int aic5_irq_domain_xlate(struct irq_domain *d, irq_gc_lock(bgc); irq_reg_writel(bgc, *out_hwirq, AT91_AIC5_SSR); smr = irq_reg_readl(bgc, AT91_AIC5_SMR); - ret = aic_common_set_priority(intspec[2], &smr); - if (!ret) - irq_reg_writel(bgc, intspec[2] | smr, AT91_AIC5_SMR); + aic_common_set_priority(intspec[2], &smr); + irq_reg_writel(bgc, smr, AT91_AIC5_SMR); irq_gc_unlock(bgc); return ret; @@ -312,12 +311,10 @@ static int __init aic5_of_init(struct device_node *node, return -EEXIST; domain = aic_common_of_init(node, &aic5_irq_ops, "atmel-aic5", - nirqs); + nirqs, aic5_irq_fixups); if (IS_ERR(domain)) return PTR_ERR(domain); - aic_common_irq_fixup(aic5_irq_fixups); - aic5_domain = domain; nchips = aic5_domain->revmap_size / 32; for (i = 0; i < nchips; i++) { diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c index 963065a0d7741..b6e950d4782a1 100644 --- a/drivers/irqchip/irq-bcm2836.c +++ b/drivers/irqchip/irq-bcm2836.c @@ -229,7 +229,6 @@ int __init bcm2836_smp_boot_secondary(unsigned int cpu, unsigned long secondary_startup_phys = (unsigned long)virt_to_phys((void *)secondary_startup); - dsb(); writel(secondary_startup_phys, intc.base + LOCAL_MAILBOX3_SET0 + 16 * cpu); diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c new file mode 100644 index 0000000000000..b844c89a95067 --- /dev/null +++ b/drivers/irqchip/irq-bcm6345-l1.c @@ -0,0 +1,364 @@ +/* + * Broadcom BCM6345 style Level 1 interrupt controller driver + * + * Copyright (C) 2014 Broadcom Corporation + * Copyright 2015 Simon Arlott + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This is based on the BCM7038 (which supports SMP) but with a single + * enable register instead of separate mask/set/clear registers. + * + * The BCM3380 has a similar mask/status register layout, but each pair + * of words is at separate locations (and SMP is not supported). + * + * ENABLE/STATUS words are packed next to each other for each CPU: + * + * BCM6368: + * 0x1000_0020: CPU0_W0_ENABLE + * 0x1000_0024: CPU0_W1_ENABLE + * 0x1000_0028: CPU0_W0_STATUS IRQs 31-63 + * 0x1000_002c: CPU0_W1_STATUS IRQs 0-31 + * 0x1000_0030: CPU1_W0_ENABLE + * 0x1000_0034: CPU1_W1_ENABLE + * 0x1000_0038: CPU1_W0_STATUS IRQs 31-63 + * 0x1000_003c: CPU1_W1_STATUS IRQs 0-31 + * + * BCM63168: + * 0x1000_0020: CPU0_W0_ENABLE + * 0x1000_0024: CPU0_W1_ENABLE + * 0x1000_0028: CPU0_W2_ENABLE + * 0x1000_002c: CPU0_W3_ENABLE + * 0x1000_0030: CPU0_W0_STATUS IRQs 96-127 + * 0x1000_0034: CPU0_W1_STATUS IRQs 64-95 + * 0x1000_0038: CPU0_W2_STATUS IRQs 32-63 + * 0x1000_003c: CPU0_W3_STATUS IRQs 0-31 + * 0x1000_0040: CPU1_W0_ENABLE + * 0x1000_0044: CPU1_W1_ENABLE + * 0x1000_0048: CPU1_W2_ENABLE + * 0x1000_004c: CPU1_W3_ENABLE + * 0x1000_0050: CPU1_W0_STATUS IRQs 96-127 + * 0x1000_0054: CPU1_W1_STATUS IRQs 64-95 + * 0x1000_0058: CPU1_W2_STATUS IRQs 32-63 + * 0x1000_005c: CPU1_W3_STATUS IRQs 0-31 + * + * IRQs are numbered in CPU native endian order + * (which is big-endian in these examples) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define IRQS_PER_WORD 32 +#define REG_BYTES_PER_IRQ_WORD (sizeof(u32) * 2) + +struct bcm6345_l1_cpu; + +struct bcm6345_l1_chip { + raw_spinlock_t lock; + unsigned int n_words; + struct irq_domain *domain; + struct cpumask cpumask; + struct bcm6345_l1_cpu *cpus[NR_CPUS]; +}; + +struct bcm6345_l1_cpu { + void __iomem *map_base; + unsigned int parent_irq; + u32 enable_cache[]; +}; + +static inline unsigned int reg_enable(struct bcm6345_l1_chip *intc, + unsigned int word) +{ +#ifdef __BIG_ENDIAN + return (1 * intc->n_words - word - 1) * sizeof(u32); +#else + return (0 * intc->n_words + word) * sizeof(u32); +#endif +} + +static inline unsigned int reg_status(struct bcm6345_l1_chip *intc, + unsigned int word) +{ +#ifdef __BIG_ENDIAN + return (2 * intc->n_words - word - 1) * sizeof(u32); +#else + return (1 * intc->n_words + word) * sizeof(u32); +#endif +} + +static inline unsigned int cpu_for_irq(struct bcm6345_l1_chip *intc, + struct irq_data *d) +{ + return cpumask_first_and(&intc->cpumask, irq_data_get_affinity_mask(d)); +} + +static void bcm6345_l1_irq_handle(struct irq_desc *desc) +{ + struct bcm6345_l1_chip *intc = irq_desc_get_handler_data(desc); + struct bcm6345_l1_cpu *cpu; + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned int idx; + +#ifdef CONFIG_SMP + cpu = intc->cpus[cpu_logical_map(smp_processor_id())]; +#else + cpu = intc->cpus[0]; +#endif + + chained_irq_enter(chip, desc); + + for (idx = 0; idx < intc->n_words; idx++) { + int base = idx * IRQS_PER_WORD; + unsigned long pending; + irq_hw_number_t hwirq; + unsigned int irq; + + pending = __raw_readl(cpu->map_base + reg_status(intc, idx)); + pending &= __raw_readl(cpu->map_base + reg_enable(intc, idx)); + + for_each_set_bit(hwirq, &pending, IRQS_PER_WORD) { + irq = irq_linear_revmap(intc->domain, base + hwirq); + if (irq) + do_IRQ(irq); + else + spurious_interrupt(); + } + } + + chained_irq_exit(chip, desc); +} + +static inline void __bcm6345_l1_unmask(struct irq_data *d) +{ + struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d); + u32 word = d->hwirq / IRQS_PER_WORD; + u32 mask = BIT(d->hwirq % IRQS_PER_WORD); + unsigned int cpu_idx = cpu_for_irq(intc, d); + + intc->cpus[cpu_idx]->enable_cache[word] |= mask; + __raw_writel(intc->cpus[cpu_idx]->enable_cache[word], + intc->cpus[cpu_idx]->map_base + reg_enable(intc, word)); +} + +static inline void __bcm6345_l1_mask(struct irq_data *d) +{ + struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d); + u32 word = d->hwirq / IRQS_PER_WORD; + u32 mask = BIT(d->hwirq % IRQS_PER_WORD); + unsigned int cpu_idx = cpu_for_irq(intc, d); + + intc->cpus[cpu_idx]->enable_cache[word] &= ~mask; + __raw_writel(intc->cpus[cpu_idx]->enable_cache[word], + intc->cpus[cpu_idx]->map_base + reg_enable(intc, word)); +} + +static void bcm6345_l1_unmask(struct irq_data *d) +{ + struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d); + unsigned long flags; + + raw_spin_lock_irqsave(&intc->lock, flags); + __bcm6345_l1_unmask(d); + raw_spin_unlock_irqrestore(&intc->lock, flags); +} + +static void bcm6345_l1_mask(struct irq_data *d) +{ + struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d); + unsigned long flags; + + raw_spin_lock_irqsave(&intc->lock, flags); + __bcm6345_l1_mask(d); + raw_spin_unlock_irqrestore(&intc->lock, flags); +} + +static int bcm6345_l1_set_affinity(struct irq_data *d, + const struct cpumask *dest, + bool force) +{ + struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d); + u32 word = d->hwirq / IRQS_PER_WORD; + u32 mask = BIT(d->hwirq % IRQS_PER_WORD); + unsigned int old_cpu = cpu_for_irq(intc, d); + unsigned int new_cpu; + struct cpumask valid; + unsigned long flags; + bool enabled; + + if (!cpumask_and(&valid, &intc->cpumask, dest)) + return -EINVAL; + + new_cpu = cpumask_any_and(&valid, cpu_online_mask); + if (new_cpu >= nr_cpu_ids) + return -EINVAL; + + dest = cpumask_of(new_cpu); + + raw_spin_lock_irqsave(&intc->lock, flags); + if (old_cpu != new_cpu) { + enabled = intc->cpus[old_cpu]->enable_cache[word] & mask; + if (enabled) + __bcm6345_l1_mask(d); + cpumask_copy(irq_data_get_affinity_mask(d), dest); + if (enabled) + __bcm6345_l1_unmask(d); + } else { + cpumask_copy(irq_data_get_affinity_mask(d), dest); + } + raw_spin_unlock_irqrestore(&intc->lock, flags); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +static int __init bcm6345_l1_init_one(struct device_node *dn, + unsigned int idx, + struct bcm6345_l1_chip *intc) +{ + struct resource res; + resource_size_t sz; + struct bcm6345_l1_cpu *cpu; + unsigned int i, n_words; + + if (of_address_to_resource(dn, idx, &res)) + return -EINVAL; + sz = resource_size(&res); + n_words = sz / REG_BYTES_PER_IRQ_WORD; + + if (!intc->n_words) + intc->n_words = n_words; + else if (intc->n_words != n_words) + return -EINVAL; + + cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32), + GFP_KERNEL); + if (!cpu) + return -ENOMEM; + + cpu->map_base = ioremap(res.start, sz); + if (!cpu->map_base) + return -ENOMEM; + + for (i = 0; i < n_words; i++) { + cpu->enable_cache[i] = 0; + __raw_writel(0, cpu->map_base + reg_enable(intc, i)); + } + + cpu->parent_irq = irq_of_parse_and_map(dn, idx); + if (!cpu->parent_irq) { + pr_err("failed to map parent interrupt %d\n", cpu->parent_irq); + return -EINVAL; + } + irq_set_chained_handler_and_data(cpu->parent_irq, + bcm6345_l1_irq_handle, intc); + + return 0; +} + +static struct irq_chip bcm6345_l1_irq_chip = { + .name = "bcm6345-l1", + .irq_mask = bcm6345_l1_mask, + .irq_unmask = bcm6345_l1_unmask, + .irq_set_affinity = bcm6345_l1_set_affinity, +}; + +static int bcm6345_l1_map(struct irq_domain *d, unsigned int virq, + irq_hw_number_t hw_irq) +{ + irq_set_chip_and_handler(virq, + &bcm6345_l1_irq_chip, handle_percpu_irq); + irq_set_chip_data(virq, d->host_data); + return 0; +} + +static const struct irq_domain_ops bcm6345_l1_domain_ops = { + .xlate = irq_domain_xlate_onecell, + .map = bcm6345_l1_map, +}; + +static int __init bcm6345_l1_of_init(struct device_node *dn, + struct device_node *parent) +{ + struct bcm6345_l1_chip *intc; + unsigned int idx; + int ret; + + intc = kzalloc(sizeof(*intc), GFP_KERNEL); + if (!intc) + return -ENOMEM; + + for_each_possible_cpu(idx) { + ret = bcm6345_l1_init_one(dn, idx, intc); + if (ret) + pr_err("failed to init intc L1 for cpu %d: %d\n", + idx, ret); + else + cpumask_set_cpu(idx, &intc->cpumask); + } + + if (!cpumask_weight(&intc->cpumask)) { + ret = -ENODEV; + goto out_free; + } + + raw_spin_lock_init(&intc->lock); + + intc->domain = irq_domain_add_linear(dn, IRQS_PER_WORD * intc->n_words, + &bcm6345_l1_domain_ops, + intc); + if (!intc->domain) { + ret = -ENOMEM; + goto out_unmap; + } + + pr_info("registered BCM6345 L1 intc (IRQs: %d)\n", + IRQS_PER_WORD * intc->n_words); + for_each_cpu(idx, &intc->cpumask) { + struct bcm6345_l1_cpu *cpu = intc->cpus[idx]; + + pr_info(" CPU%u at MMIO 0x%p (irq = %d)\n", idx, + cpu->map_base, cpu->parent_irq); + } + + return 0; + +out_unmap: + for_each_possible_cpu(idx) { + struct bcm6345_l1_cpu *cpu = intc->cpus[idx]; + + if (cpu) { + if (cpu->map_base) + iounmap(cpu->map_base); + kfree(cpu); + } + } +out_free: + kfree(intc); + return ret; +} + +IRQCHIP_DECLARE(bcm6345_l1, "brcm,bcm6345-l1-intc", bcm6345_l1_of_init); diff --git a/drivers/irqchip/irq-gic-realview.c b/drivers/irqchip/irq-gic-realview.c index aa46eb280a7f0..54c296401525c 100644 --- a/drivers/irqchip/irq-gic-realview.c +++ b/drivers/irqchip/irq-gic-realview.c @@ -10,7 +10,8 @@ #include #define REALVIEW_SYS_LOCK_OFFSET 0x20 -#define REALVIEW_PB11MP_SYS_PLD_CTRL1 0x74 +#define REALVIEW_SYS_PLD_CTRL1 0x74 +#define REALVIEW_EB_REVB_SYS_PLD_CTRL1 0xD8 #define VERSATILE_LOCK_VAL 0xA05F #define PLD_INTMODE_MASK BIT(22)|BIT(23)|BIT(24) #define PLD_INTMODE_LEGACY 0x0 @@ -18,26 +19,57 @@ #define PLD_INTMODE_NEW_NO_DCC BIT(23) #define PLD_INTMODE_FIQ_ENABLE BIT(24) +/* For some reason RealView EB Rev B moved this register */ +static const struct of_device_id syscon_pldset_of_match[] = { + { + .compatible = "arm,realview-eb11mp-revb-syscon", + .data = (void *)REALVIEW_EB_REVB_SYS_PLD_CTRL1, + }, + { + .compatible = "arm,realview-eb11mp-revc-syscon", + .data = (void *)REALVIEW_SYS_PLD_CTRL1, + }, + { + .compatible = "arm,realview-eb-syscon", + .data = (void *)REALVIEW_SYS_PLD_CTRL1, + }, + { + .compatible = "arm,realview-pb11mp-syscon", + .data = (void *)REALVIEW_SYS_PLD_CTRL1, + }, + {}, +}; + static int __init realview_gic_of_init(struct device_node *node, struct device_node *parent) { static struct regmap *map; + struct device_node *np; + const struct of_device_id *gic_id; + u32 pld1_ctrl; + + np = of_find_matching_node_and_match(NULL, syscon_pldset_of_match, + &gic_id); + if (!np) + return -ENODEV; + pld1_ctrl = (u32)gic_id->data; /* The PB11MPCore GIC needs to be configured in the syscon */ - map = syscon_regmap_lookup_by_compatible("arm,realview-pb11mp-syscon"); + map = syscon_node_to_regmap(np); if (!IS_ERR(map)) { /* new irq mode with no DCC */ regmap_write(map, REALVIEW_SYS_LOCK_OFFSET, VERSATILE_LOCK_VAL); - regmap_update_bits(map, REALVIEW_PB11MP_SYS_PLD_CTRL1, + regmap_update_bits(map, pld1_ctrl, PLD_INTMODE_NEW_NO_DCC, PLD_INTMODE_MASK); regmap_write(map, REALVIEW_SYS_LOCK_OFFSET, 0x0000); - pr_info("TC11MP GIC: set up interrupt controller to NEW mode, no DCC\n"); + pr_info("RealView GIC: set up interrupt controller to NEW mode, no DCC\n"); } else { - pr_err("TC11MP GIC setup: could not find syscon\n"); - return -ENXIO; + pr_err("RealView GIC setup: could not find syscon\n"); + return -ENODEV; } return gic_of_init(node, parent); } IRQCHIP_DECLARE(armtc11mp_gic, "arm,tc11mp-gic", realview_gic_of_init); +IRQCHIP_DECLARE(armeb11mp_gic, "arm,eb11mp-gic", realview_gic_of_init); diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index c779f83e511d4..28f047c61baae 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -92,18 +92,6 @@ static struct msi_domain_info gicv2m_msi_domain_info = { .chip = &gicv2m_msi_irq_chip, }; -static int gicv2m_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) -{ - int ret; - - ret = irq_chip_set_affinity_parent(irq_data, mask, force); - if (ret == IRQ_SET_MASK_OK) - ret = IRQ_SET_MASK_OK_DONE; - - return ret; -} - static void gicv2m_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct v2m_data *v2m = irq_data_get_irq_chip_data(data); @@ -122,7 +110,7 @@ static struct irq_chip gicv2m_irq_chip = { .irq_mask = irq_chip_mask_parent, .irq_unmask = irq_chip_unmask_parent, .irq_eoi = irq_chip_eoi_parent, - .irq_set_affinity = gicv2m_set_affinity, + .irq_set_affinity = irq_chip_set_affinity_parent, .irq_compose_msi_msg = gicv2m_compose_msi_msg, }; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 43dfd15c1dd22..39261798c59f9 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -103,7 +103,6 @@ struct its_device { static LIST_HEAD(its_nodes); static DEFINE_SPINLOCK(its_lock); -static struct device_node *gic_root_node; static struct rdists *gic_rdists; #define gic_data_rdist() (raw_cpu_ptr(gic_rdists->rdist)) @@ -671,7 +670,7 @@ static int its_chunk_to_lpi(int chunk) return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192; } -static int its_lpi_init(u32 id_bits) +static int __init its_lpi_init(u32 id_bits) { lpi_chunks = its_lpi_to_chunk(1UL << id_bits); @@ -1430,7 +1429,8 @@ static void its_enable_quirks(struct its_node *its) gic_enable_quirks(iidr, its_quirks, its); } -static int its_probe(struct device_node *node, struct irq_domain *parent) +static int __init its_probe(struct device_node *node, + struct irq_domain *parent) { struct resource res; struct its_node *its; @@ -1591,7 +1591,7 @@ static struct of_device_id its_device_id[] = { {}, }; -int its_init(struct device_node *node, struct rdists *rdists, +int __init its_init(struct device_node *node, struct rdists *rdists, struct irq_domain *parent_domain) { struct device_node *np; @@ -1607,8 +1607,6 @@ int its_init(struct device_node *node, struct rdists *rdists, } gic_rdists = rdists; - gic_root_node = node; - its_alloc_lpi_tables(); its_lpi_init(rdists->id_bits); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index d7be6ddc34f68..5b7d3c2129d87 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -15,10 +15,12 @@ * along with this program. If not, see . */ +#include #include #include #include #include +#include #include #include #include @@ -38,6 +40,7 @@ struct redist_region { void __iomem *redist_base; phys_addr_t phys_base; + bool single_redist; }; struct gic_chip_data { @@ -434,6 +437,9 @@ static int gic_populate_rdist(void) return 0; } + if (gic_data.redist_regions[i].single_redist) + break; + if (gic_data.redist_stride) { ptr += gic_data.redist_stride; } else { @@ -634,7 +640,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, else gic_dist_wait_for_rwp(); - return IRQ_SET_MASK_OK; + return IRQ_SET_MASK_OK_DONE; } #else #define gic_set_affinity NULL @@ -764,6 +770,15 @@ static int gic_irq_domain_translate(struct irq_domain *d, return 0; } + if (is_fwnode_irqchip(fwspec->fwnode)) { + if(fwspec->param_count != 2) + return -EINVAL; + + *hwirq = fwspec->param[0]; + *type = fwspec->param[1]; + return 0; + } + return -EINVAL; } @@ -811,17 +826,88 @@ static void gicv3_enable_quirks(void) #endif } +static int __init gic_init_bases(void __iomem *dist_base, + struct redist_region *rdist_regs, + u32 nr_redist_regions, + u64 redist_stride, + struct fwnode_handle *handle) +{ + struct device_node *node; + u32 typer; + int gic_irqs; + int err; + + if (!is_hyp_mode_available()) + static_key_slow_dec(&supports_deactivate); + + if (static_key_true(&supports_deactivate)) + pr_info("GIC: Using split EOI/Deactivate mode\n"); + + gic_data.dist_base = dist_base; + gic_data.redist_regions = rdist_regs; + gic_data.nr_redist_regions = nr_redist_regions; + gic_data.redist_stride = redist_stride; + + gicv3_enable_quirks(); + + /* + * Find out how many interrupts are supported. + * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI) + */ + typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); + gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer); + gic_irqs = GICD_TYPER_IRQS(typer); + if (gic_irqs > 1020) + gic_irqs = 1020; + gic_data.irq_nr = gic_irqs; + + gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, + &gic_data); + gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist)); + + if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { + err = -ENOMEM; + goto out_free; + } + + set_handle_irq(gic_handle_irq); + + node = to_of_node(handle); + if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis() && + node) /* Temp hack to prevent ITS init for ACPI */ + its_init(node, &gic_data.rdists, gic_data.domain); + + gic_smp_init(); + gic_dist_init(); + gic_cpu_init(); + gic_cpu_pm_init(); + + return 0; + +out_free: + if (gic_data.domain) + irq_domain_remove(gic_data.domain); + free_percpu(gic_data.rdists.rdist); + return err; +} + +static int __init gic_validate_dist_version(void __iomem *dist_base) +{ + u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; + + if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) + return -ENODEV; + + return 0; +} + static int __init gic_of_init(struct device_node *node, struct device_node *parent) { void __iomem *dist_base; struct redist_region *rdist_regs; u64 redist_stride; u32 nr_redist_regions; - u32 typer; - u32 reg; - int gic_irqs; - int err; - int i; + int err, i; dist_base = of_iomap(node, 0); if (!dist_base) { @@ -830,11 +916,10 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare return -ENXIO; } - reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; - if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) { + err = gic_validate_dist_version(dist_base); + if (err) { pr_err("%s: no distributor detected, giving up\n", node->full_name); - err = -ENODEV; goto out_unmap_dist; } @@ -865,63 +950,229 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare if (of_property_read_u64(node, "redistributor-stride", &redist_stride)) redist_stride = 0; - if (!is_hyp_mode_available()) - static_key_slow_dec(&supports_deactivate); + err = gic_init_bases(dist_base, rdist_regs, nr_redist_regions, + redist_stride, &node->fwnode); + if (!err) + return 0; - if (static_key_true(&supports_deactivate)) - pr_info("GIC: Using split EOI/Deactivate mode\n"); +out_unmap_rdist: + for (i = 0; i < nr_redist_regions; i++) + if (rdist_regs[i].redist_base) + iounmap(rdist_regs[i].redist_base); + kfree(rdist_regs); +out_unmap_dist: + iounmap(dist_base); + return err; +} - gic_data.dist_base = dist_base; - gic_data.redist_regions = rdist_regs; - gic_data.nr_redist_regions = nr_redist_regions; - gic_data.redist_stride = redist_stride; +IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init); - gicv3_enable_quirks(); +#ifdef CONFIG_ACPI +static void __iomem *dist_base; +static struct redist_region *redist_regs __initdata; +static u32 nr_redist_regions __initdata; +static bool single_redist; + +static void __init +gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base) +{ + static int count = 0; + + redist_regs[count].phys_base = phys_base; + redist_regs[count].redist_base = redist_base; + redist_regs[count].single_redist = single_redist; + count++; +} + +static int __init +gic_acpi_parse_madt_redist(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_generic_redistributor *redist = + (struct acpi_madt_generic_redistributor *)header; + void __iomem *redist_base; + + redist_base = ioremap(redist->base_address, redist->length); + if (!redist_base) { + pr_err("Couldn't map GICR region @%llx\n", redist->base_address); + return -ENOMEM; + } + + gic_acpi_register_redist(redist->base_address, redist_base); + return 0; +} + +static int __init +gic_acpi_parse_madt_gicc(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_generic_interrupt *gicc = + (struct acpi_madt_generic_interrupt *)header; + u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; + u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2; + void __iomem *redist_base; + + redist_base = ioremap(gicc->gicr_base_address, size); + if (!redist_base) + return -ENOMEM; + + gic_acpi_register_redist(gicc->gicr_base_address, redist_base); + return 0; +} + +static int __init gic_acpi_collect_gicr_base(void) +{ + acpi_tbl_entry_handler redist_parser; + enum acpi_madt_type type; + + if (single_redist) { + type = ACPI_MADT_TYPE_GENERIC_INTERRUPT; + redist_parser = gic_acpi_parse_madt_gicc; + } else { + type = ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR; + redist_parser = gic_acpi_parse_madt_redist; + } + + /* Collect redistributor base addresses in GICR entries */ + if (acpi_table_parse_madt(type, redist_parser, 0) > 0) + return 0; + + pr_info("No valid GICR entries exist\n"); + return -ENODEV; +} + +static int __init gic_acpi_match_gicr(struct acpi_subtable_header *header, + const unsigned long end) +{ + /* Subtable presence means that redist exists, that's it */ + return 0; +} + +static int __init gic_acpi_match_gicc(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_generic_interrupt *gicc = + (struct acpi_madt_generic_interrupt *)header; /* - * Find out how many interrupts are supported. - * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI) + * If GICC is enabled and has valid gicr base address, then it means + * GICR base is presented via GICC */ - typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); - gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer); - gic_irqs = GICD_TYPER_IRQS(typer); - if (gic_irqs > 1020) - gic_irqs = 1020; - gic_data.irq_nr = gic_irqs; + if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address) + return 0; - gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops, - &gic_data); - gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist)); + return -ENODEV; +} - if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { +static int __init gic_acpi_count_gicr_regions(void) +{ + int count; + + /* + * Count how many redistributor regions we have. It is not allowed + * to mix redistributor description, GICR and GICC subtables have to be + * mutually exclusive. + */ + count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR, + gic_acpi_match_gicr, 0); + if (count > 0) { + single_redist = false; + return count; + } + + count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, + gic_acpi_match_gicc, 0); + if (count > 0) + single_redist = true; + + return count; +} + +static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header, + struct acpi_probe_entry *ape) +{ + struct acpi_madt_generic_distributor *dist; + int count; + + dist = (struct acpi_madt_generic_distributor *)header; + if (dist->version != ape->driver_data) + return false; + + /* We need to do that exercise anyway, the sooner the better */ + count = gic_acpi_count_gicr_regions(); + if (count <= 0) + return false; + + nr_redist_regions = count; + return true; +} + +#define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K) + +static int __init +gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end) +{ + struct acpi_madt_generic_distributor *dist; + struct fwnode_handle *domain_handle; + int i, err; + + /* Get distributor base address */ + dist = (struct acpi_madt_generic_distributor *)header; + dist_base = ioremap(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE); + if (!dist_base) { + pr_err("Unable to map GICD registers\n"); + return -ENOMEM; + } + + err = gic_validate_dist_version(dist_base); + if (err) { + pr_err("No distributor detected at @%p, giving up", dist_base); + goto out_dist_unmap; + } + + redist_regs = kzalloc(sizeof(*redist_regs) * nr_redist_regions, + GFP_KERNEL); + if (!redist_regs) { err = -ENOMEM; - goto out_free; + goto out_dist_unmap; } - set_handle_irq(gic_handle_irq); + err = gic_acpi_collect_gicr_base(); + if (err) + goto out_redist_unmap; - if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis()) - its_init(node, &gic_data.rdists, gic_data.domain); + domain_handle = irq_domain_alloc_fwnode(dist_base); + if (!domain_handle) { + err = -ENOMEM; + goto out_redist_unmap; + } - gic_smp_init(); - gic_dist_init(); - gic_cpu_init(); - gic_cpu_pm_init(); + err = gic_init_bases(dist_base, redist_regs, nr_redist_regions, 0, + domain_handle); + if (err) + goto out_fwhandle_free; + acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, domain_handle); return 0; -out_free: - if (gic_data.domain) - irq_domain_remove(gic_data.domain); - free_percpu(gic_data.rdists.rdist); -out_unmap_rdist: +out_fwhandle_free: + irq_domain_free_fwnode(domain_handle); +out_redist_unmap: for (i = 0; i < nr_redist_regions; i++) - if (rdist_regs[i].redist_base) - iounmap(rdist_regs[i].redist_base); - kfree(rdist_regs); -out_unmap_dist: + if (redist_regs[i].redist_base) + iounmap(redist_regs[i].redist_base); + kfree(redist_regs); +out_dist_unmap: iounmap(dist_base); return err; } - -IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init); +IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, + acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V3, + gic_acpi_init); +IRQCHIP_ACPI_DECLARE(gic_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, + acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V4, + gic_acpi_init); +IRQCHIP_ACPI_DECLARE(gic_v3_or_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, + acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_NONE, + gic_acpi_init); +#endif diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 8f9ebf714e2bb..282344b95ec2b 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -319,7 +319,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, writel_relaxed(val | bit, reg); raw_spin_unlock_irqrestore(&irq_controller_lock, flags); - return IRQ_SET_MASK_OK; + return IRQ_SET_MASK_OK_DONE; } #endif diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 9e17ef27a183d..94a30da0cfaca 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -29,16 +29,32 @@ struct gic_pcpu_mask { DECLARE_BITMAP(pcpu_mask, GIC_MAX_INTRS); }; +struct gic_irq_spec { + enum { + GIC_DEVICE, + GIC_IPI + } type; + + union { + struct cpumask *ipimask; + unsigned int hwirq; + }; +}; + static unsigned long __gic_base_addr; + static void __iomem *gic_base; static struct gic_pcpu_mask pcpu_masks[NR_CPUS]; static DEFINE_SPINLOCK(gic_lock); static struct irq_domain *gic_irq_domain; +static struct irq_domain *gic_dev_domain; +static struct irq_domain *gic_ipi_domain; static int gic_shared_intrs; static int gic_vpes; static unsigned int gic_cpu_pin; static unsigned int timer_cpu_pin; static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller; +DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS); static void __gic_irq_dispatch(void); @@ -264,9 +280,11 @@ static void gic_bind_eic_interrupt(int irq, int set) GIC_VPE_EIC_SS(irq), set); } -void gic_send_ipi(unsigned int intr) +static void gic_send_ipi(struct irq_data *d, unsigned int cpu) { - gic_write(GIC_REG(SHARED, GIC_SH_WEDGE), GIC_SH_WEDGE_SET(intr)); + irq_hw_number_t hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(d)); + + gic_write(GIC_REG(SHARED, GIC_SH_WEDGE), GIC_SH_WEDGE_SET(hwirq)); } int gic_get_c0_compare_int(void) @@ -449,7 +467,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, gic_map_to_vpe(irq, mips_cm_vp_id(cpumask_first(&tmp))); /* Update the pcpu_masks */ - for (i = 0; i < NR_CPUS; i++) + for (i = 0; i < gic_vpes; i++) clear_bit(irq, pcpu_masks[i].pcpu_mask); set_bit(irq, pcpu_masks[cpumask_first(&tmp)].pcpu_mask); @@ -479,6 +497,7 @@ static struct irq_chip gic_edge_irq_controller = { #ifdef CONFIG_SMP .irq_set_affinity = gic_set_affinity, #endif + .ipi_send_single = gic_send_ipi, }; static void gic_handle_local_int(bool chained) @@ -572,83 +591,6 @@ static void gic_irq_dispatch(struct irq_desc *desc) gic_handle_shared_int(true); } -#ifdef CONFIG_MIPS_GIC_IPI -static int gic_resched_int_base; -static int gic_call_int_base; - -unsigned int plat_ipi_resched_int_xlate(unsigned int cpu) -{ - return gic_resched_int_base + cpu; -} - -unsigned int plat_ipi_call_int_xlate(unsigned int cpu) -{ - return gic_call_int_base + cpu; -} - -static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) -{ - scheduler_ipi(); - - return IRQ_HANDLED; -} - -static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) -{ - generic_smp_call_function_interrupt(); - - return IRQ_HANDLED; -} - -static struct irqaction irq_resched = { - .handler = ipi_resched_interrupt, - .flags = IRQF_PERCPU, - .name = "IPI resched" -}; - -static struct irqaction irq_call = { - .handler = ipi_call_interrupt, - .flags = IRQF_PERCPU, - .name = "IPI call" -}; - -static __init void gic_ipi_init_one(unsigned int intr, int cpu, - struct irqaction *action) -{ - int virq = irq_create_mapping(gic_irq_domain, - GIC_SHARED_TO_HWIRQ(intr)); - int i; - - gic_map_to_vpe(intr, mips_cm_vp_id(cpu)); - for (i = 0; i < NR_CPUS; i++) - clear_bit(intr, pcpu_masks[i].pcpu_mask); - set_bit(intr, pcpu_masks[cpu].pcpu_mask); - - irq_set_irq_type(virq, IRQ_TYPE_EDGE_RISING); - - irq_set_handler(virq, handle_percpu_irq); - setup_irq(virq, action); -} - -static __init void gic_ipi_init(void) -{ - int i; - - /* Use last 2 * NR_CPUS interrupts as IPIs */ - gic_resched_int_base = gic_shared_intrs - nr_cpu_ids; - gic_call_int_base = gic_resched_int_base - nr_cpu_ids; - - for (i = 0; i < nr_cpu_ids; i++) { - gic_ipi_init_one(gic_call_int_base + i, i, &irq_call); - gic_ipi_init_one(gic_resched_int_base + i, i, &irq_resched); - } -} -#else -static inline void gic_ipi_init(void) -{ -} -#endif - static void __init gic_basic_init(void) { unsigned int i; @@ -753,19 +695,21 @@ static int gic_local_irq_domain_map(struct irq_domain *d, unsigned int virq, } static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, - irq_hw_number_t hw) + irq_hw_number_t hw, unsigned int vpe) { int intr = GIC_HWIRQ_TO_SHARED(hw); unsigned long flags; + int i; irq_set_chip_and_handler(virq, &gic_level_irq_controller, handle_level_irq); spin_lock_irqsave(&gic_lock, flags); gic_map_to_pin(intr, gic_cpu_pin); - /* Map to VPE 0 by default */ - gic_map_to_vpe(intr, 0); - set_bit(intr, pcpu_masks[0].pcpu_mask); + gic_map_to_vpe(intr, vpe); + for (i = 0; i < gic_vpes; i++) + clear_bit(intr, pcpu_masks[i].pcpu_mask); + set_bit(intr, pcpu_masks[vpe].pcpu_mask); spin_unlock_irqrestore(&gic_lock, flags); return 0; @@ -776,10 +720,93 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, { if (GIC_HWIRQ_TO_LOCAL(hw) < GIC_NUM_LOCAL_INTRS) return gic_local_irq_domain_map(d, virq, hw); - return gic_shared_irq_domain_map(d, virq, hw); + return gic_shared_irq_domain_map(d, virq, hw, 0); } -static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, +static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct gic_irq_spec *spec = arg; + irq_hw_number_t hwirq, base_hwirq; + int cpu, ret, i; + + if (spec->type == GIC_DEVICE) { + /* verify that it doesn't conflict with an IPI irq */ + if (test_bit(spec->hwirq, ipi_resrv)) + return -EBUSY; + } else { + base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs); + if (base_hwirq == gic_shared_intrs) { + return -ENOMEM; + } + + /* check that we have enough space */ + for (i = base_hwirq; i < nr_irqs; i++) { + if (!test_bit(i, ipi_resrv)) + return -EBUSY; + } + bitmap_clear(ipi_resrv, base_hwirq, nr_irqs); + + /* map the hwirq for each cpu consecutively */ + i = 0; + for_each_cpu(cpu, spec->ipimask) { + hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i); + + ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq, + &gic_edge_irq_controller, + NULL); + if (ret) + goto error; + + ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu); + if (ret) + goto error; + + i++; + } + + /* + * tell the parent about the base hwirq we allocated so it can + * set its own domain data + */ + spec->hwirq = base_hwirq; + } + + return 0; +error: + bitmap_set(ipi_resrv, base_hwirq, nr_irqs); + return ret; +} + +void gic_irq_domain_free(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs) +{ + irq_hw_number_t base_hwirq; + struct irq_data *data; + + data = irq_get_irq_data(virq); + if (!data) + return; + + base_hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(data)); + bitmap_set(ipi_resrv, base_hwirq, nr_irqs); +} + +int gic_irq_domain_match(struct irq_domain *d, struct device_node *node, + enum irq_domain_bus_token bus_token) +{ + /* this domain should'nt be accessed directly */ + return 0; +} + +static const struct irq_domain_ops gic_irq_domain_ops = { + .map = gic_irq_domain_map, + .alloc = gic_irq_domain_alloc, + .free = gic_irq_domain_free, + .match = gic_irq_domain_match, +}; + +static int gic_dev_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, const u32 *intspec, unsigned int intsize, irq_hw_number_t *out_hwirq, unsigned int *out_type) @@ -798,9 +825,130 @@ static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, return 0; } -static const struct irq_domain_ops gic_irq_domain_ops = { - .map = gic_irq_domain_map, - .xlate = gic_irq_domain_xlate, +static int gic_dev_domain_alloc(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_fwspec *fwspec = arg; + struct gic_irq_spec spec = { + .type = GIC_DEVICE, + .hwirq = fwspec->param[1], + }; + int i, ret; + bool is_shared = fwspec->param[0] == GIC_SHARED; + + if (is_shared) { + ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec); + if (ret) + return ret; + } + + for (i = 0; i < nr_irqs; i++) { + irq_hw_number_t hwirq; + + if (is_shared) + hwirq = GIC_SHARED_TO_HWIRQ(spec.hwirq + i); + else + hwirq = GIC_LOCAL_TO_HWIRQ(spec.hwirq + i); + + ret = irq_domain_set_hwirq_and_chip(d, virq + i, + hwirq, + &gic_level_irq_controller, + NULL); + if (ret) + return ret; + } + + return 0; +} + +void gic_dev_domain_free(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs) +{ + /* no real allocation is done for dev irqs, so no need to free anything */ + return; +} + +static struct irq_domain_ops gic_dev_domain_ops = { + .xlate = gic_dev_domain_xlate, + .alloc = gic_dev_domain_alloc, + .free = gic_dev_domain_free, +}; + +static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, + unsigned int *out_type) +{ + /* + * There's nothing to translate here. hwirq is dynamically allocated and + * the irq type is always edge triggered. + * */ + *out_hwirq = 0; + *out_type = IRQ_TYPE_EDGE_RISING; + + return 0; +} + +static int gic_ipi_domain_alloc(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct cpumask *ipimask = arg; + struct gic_irq_spec spec = { + .type = GIC_IPI, + .ipimask = ipimask + }; + int ret, i; + + ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec); + if (ret) + return ret; + + /* the parent should have set spec.hwirq to the base_hwirq it allocated */ + for (i = 0; i < nr_irqs; i++) { + ret = irq_domain_set_hwirq_and_chip(d, virq + i, + GIC_SHARED_TO_HWIRQ(spec.hwirq + i), + &gic_edge_irq_controller, + NULL); + if (ret) + goto error; + + ret = irq_set_irq_type(virq + i, IRQ_TYPE_EDGE_RISING); + if (ret) + goto error; + } + + return 0; +error: + irq_domain_free_irqs_parent(d, virq, nr_irqs); + return ret; +} + +void gic_ipi_domain_free(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs) +{ + irq_domain_free_irqs_parent(d, virq, nr_irqs); +} + +int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node, + enum irq_domain_bus_token bus_token) +{ + bool is_ipi; + + switch (bus_token) { + case DOMAIN_BUS_IPI: + is_ipi = d->bus_token == bus_token; + return to_of_node(d->fwnode) == node && is_ipi; + break; + default: + return 0; + } +} + +static struct irq_domain_ops gic_ipi_domain_ops = { + .xlate = gic_ipi_domain_xlate, + .alloc = gic_ipi_domain_alloc, + .free = gic_ipi_domain_free, + .match = gic_ipi_domain_match, }; static void __init __gic_init(unsigned long gic_base_addr, @@ -809,6 +957,7 @@ static void __init __gic_init(unsigned long gic_base_addr, struct device_node *node) { unsigned int gicconfig; + unsigned int v[2]; __gic_base_addr = gic_base_addr; @@ -864,9 +1013,32 @@ static void __init __gic_init(unsigned long gic_base_addr, if (!gic_irq_domain) panic("Failed to add GIC IRQ domain"); - gic_basic_init(); + gic_dev_domain = irq_domain_add_hierarchy(gic_irq_domain, 0, + GIC_NUM_LOCAL_INTRS + gic_shared_intrs, + node, &gic_dev_domain_ops, NULL); + if (!gic_dev_domain) + panic("Failed to add GIC DEV domain"); + + gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain, + IRQ_DOMAIN_FLAG_IPI_PER_CPU, + GIC_NUM_LOCAL_INTRS + gic_shared_intrs, + node, &gic_ipi_domain_ops, NULL); + if (!gic_ipi_domain) + panic("Failed to add GIC IPI domain"); - gic_ipi_init(); + gic_ipi_domain->bus_token = DOMAIN_BUS_IPI; + + if (node && + !of_property_read_u32_array(node, "mti,reserved-ipi-vectors", v, 2)) { + bitmap_set(ipi_resrv, v[0], v[1]); + } else { + /* Make the last 2 * gic_vpes available for IPIs */ + bitmap_set(ipi_resrv, + gic_shared_intrs - 2 * gic_vpes, + 2 * gic_vpes); + } + + gic_basic_init(); } void __init gic_init(unsigned long gic_base_addr, diff --git a/drivers/irqchip/irq-mvebu-odmi.c b/drivers/irqchip/irq-mvebu-odmi.c new file mode 100644 index 0000000000000..b4d367868dbbe --- /dev/null +++ b/drivers/irqchip/irq-mvebu-odmi.c @@ -0,0 +1,236 @@ +/* + * Copyright (C) 2016 Marvell + * + * Thomas Petazzoni + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#define pr_fmt(fmt) "GIC-ODMI: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#define GICP_ODMIN_SET 0x40 +#define GICP_ODMI_INT_NUM_SHIFT 12 +#define GICP_ODMIN_GM_EP_R0 0x110 +#define GICP_ODMIN_GM_EP_R1 0x114 +#define GICP_ODMIN_GM_EA_R0 0x108 +#define GICP_ODMIN_GM_EA_R1 0x118 + +/* + * We don't support the group events, so we simply have 8 interrupts + * per frame. + */ +#define NODMIS_SHIFT 3 +#define NODMIS_PER_FRAME (1 << NODMIS_SHIFT) +#define NODMIS_MASK (NODMIS_PER_FRAME - 1) + +struct odmi_data { + struct resource res; + void __iomem *base; + unsigned int spi_base; +}; + +static struct odmi_data *odmis; +static unsigned long *odmis_bm; +static unsigned int odmis_count; + +/* Protects odmis_bm */ +static DEFINE_SPINLOCK(odmis_bm_lock); + +static void odmi_compose_msi_msg(struct irq_data *d, struct msi_msg *msg) +{ + struct odmi_data *odmi; + phys_addr_t addr; + unsigned int odmin; + + if (WARN_ON(d->hwirq >= odmis_count * NODMIS_PER_FRAME)) + return; + + odmi = &odmis[d->hwirq >> NODMIS_SHIFT]; + odmin = d->hwirq & NODMIS_MASK; + + addr = odmi->res.start + GICP_ODMIN_SET; + + msg->address_hi = upper_32_bits(addr); + msg->address_lo = lower_32_bits(addr); + msg->data = odmin << GICP_ODMI_INT_NUM_SHIFT; +} + +static struct irq_chip odmi_irq_chip = { + .name = "ODMI", + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_compose_msi_msg = odmi_compose_msi_msg, +}; + +static int odmi_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct odmi_data *odmi = NULL; + struct irq_fwspec fwspec; + struct irq_data *d; + unsigned int hwirq, odmin; + int ret; + + spin_lock(&odmis_bm_lock); + hwirq = find_first_zero_bit(odmis_bm, NODMIS_PER_FRAME * odmis_count); + if (hwirq >= NODMIS_PER_FRAME * odmis_count) { + spin_unlock(&odmis_bm_lock); + return -ENOSPC; + } + + __set_bit(hwirq, odmis_bm); + spin_unlock(&odmis_bm_lock); + + odmi = &odmis[hwirq >> NODMIS_SHIFT]; + odmin = hwirq & NODMIS_MASK; + + fwspec.fwnode = domain->parent->fwnode; + fwspec.param_count = 3; + fwspec.param[0] = GIC_SPI; + fwspec.param[1] = odmi->spi_base - 32 + odmin; + fwspec.param[2] = IRQ_TYPE_EDGE_RISING; + + ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec); + if (ret) { + pr_err("Cannot allocate parent IRQ\n"); + spin_lock(&odmis_bm_lock); + __clear_bit(odmin, odmis_bm); + spin_unlock(&odmis_bm_lock); + return ret; + } + + /* Configure the interrupt line to be edge */ + d = irq_domain_get_irq_data(domain->parent, virq); + d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING); + + irq_domain_set_hwirq_and_chip(domain, virq, hwirq, + &odmi_irq_chip, NULL); + + return 0; +} + +static void odmi_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + + if (d->hwirq >= odmis_count * NODMIS_PER_FRAME) { + pr_err("Failed to teardown msi. Invalid hwirq %lu\n", d->hwirq); + return; + } + + irq_domain_free_irqs_parent(domain, virq, nr_irqs); + + /* Actually free the MSI */ + spin_lock(&odmis_bm_lock); + __clear_bit(d->hwirq, odmis_bm); + spin_unlock(&odmis_bm_lock); +} + +static const struct irq_domain_ops odmi_domain_ops = { + .alloc = odmi_irq_domain_alloc, + .free = odmi_irq_domain_free, +}; + +static struct irq_chip odmi_msi_irq_chip = { + .name = "ODMI", +}; + +static struct msi_domain_ops odmi_msi_ops = { +}; + +static struct msi_domain_info odmi_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS), + .ops = &odmi_msi_ops, + .chip = &odmi_msi_irq_chip, +}; + +static int __init mvebu_odmi_init(struct device_node *node, + struct device_node *parent) +{ + struct irq_domain *inner_domain, *plat_domain; + int ret, i; + + if (of_property_read_u32(node, "marvell,odmi-frames", &odmis_count)) + return -EINVAL; + + odmis = kcalloc(odmis_count, sizeof(struct odmi_data), GFP_KERNEL); + if (!odmis) + return -ENOMEM; + + odmis_bm = kcalloc(BITS_TO_LONGS(odmis_count * NODMIS_PER_FRAME), + sizeof(long), GFP_KERNEL); + if (!odmis_bm) { + ret = -ENOMEM; + goto err_alloc; + } + + for (i = 0; i < odmis_count; i++) { + struct odmi_data *odmi = &odmis[i]; + + ret = of_address_to_resource(node, i, &odmi->res); + if (ret) + goto err_unmap; + + odmi->base = of_io_request_and_map(node, i, "odmi"); + if (IS_ERR(odmi->base)) { + ret = PTR_ERR(odmi->base); + goto err_unmap; + } + + if (of_property_read_u32_index(node, "marvell,spi-base", + i, &odmi->spi_base)) { + ret = -EINVAL; + goto err_unmap; + } + } + + inner_domain = irq_domain_create_linear(of_node_to_fwnode(node), + odmis_count * NODMIS_PER_FRAME, + &odmi_domain_ops, NULL); + if (!inner_domain) { + ret = -ENOMEM; + goto err_unmap; + } + + inner_domain->parent = irq_find_host(parent); + + plat_domain = platform_msi_create_irq_domain(of_node_to_fwnode(node), + &odmi_msi_domain_info, + inner_domain); + if (!plat_domain) { + ret = -ENOMEM; + goto err_remove_inner; + } + + return 0; + +err_remove_inner: + irq_domain_remove(inner_domain); +err_unmap: + for (i = 0; i < odmis_count; i++) { + struct odmi_data *odmi = &odmis[i]; + + if (odmi->base && !IS_ERR(odmi->base)) + iounmap(odmis[i].base); + } + kfree(odmis_bm); +err_alloc: + kfree(odmis); + return ret; +} + +IRQCHIP_DECLARE(mvebu_odmi, "marvell,odmi-controller", mvebu_odmi_init); diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index efe50845939d9..17304705f2cf9 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -183,7 +183,7 @@ static void __iomem * __init icoll_init_iobase(struct device_node *np) void __iomem *icoll_base; icoll_base = of_io_request_and_map(np, 0, np->name); - if (!icoll_base) + if (IS_ERR(icoll_base)) panic("%s: unable to map resource", np->full_name); return icoll_base; } diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c index 0820f67cc9a76..668730c5cb66f 100644 --- a/drivers/irqchip/irq-sunxi-nmi.c +++ b/drivers/irqchip/irq-sunxi-nmi.c @@ -160,9 +160,9 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node, gc = irq_get_domain_generic_chip(domain, 0); gc->reg_base = of_io_request_and_map(node, 0, of_node_full_name(node)); - if (!gc->reg_base) { + if (IS_ERR(gc->reg_base)) { pr_err("unable to map resource\n"); - ret = -ENOMEM; + ret = PTR_ERR(gc->reg_base); goto fail_irqd_remove; } diff --git a/drivers/irqchip/irq-tango.c b/drivers/irqchip/irq-tango.c new file mode 100644 index 0000000000000..bdbb5c0ff7fe3 --- /dev/null +++ b/drivers/irqchip/irq-tango.c @@ -0,0 +1,232 @@ +/* + * Copyright (C) 2014 Mans Rullgard + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define IRQ0_CTL_BASE 0x0000 +#define IRQ1_CTL_BASE 0x0100 +#define EDGE_CTL_BASE 0x0200 +#define IRQ2_CTL_BASE 0x0300 + +#define IRQ_CTL_HI 0x18 +#define EDGE_CTL_HI 0x20 + +#define IRQ_STATUS 0x00 +#define IRQ_RAWSTAT 0x04 +#define IRQ_EN_SET 0x08 +#define IRQ_EN_CLR 0x0c +#define IRQ_SOFT_SET 0x10 +#define IRQ_SOFT_CLR 0x14 + +#define EDGE_STATUS 0x00 +#define EDGE_RAWSTAT 0x04 +#define EDGE_CFG_RISE 0x08 +#define EDGE_CFG_FALL 0x0c +#define EDGE_CFG_RISE_SET 0x10 +#define EDGE_CFG_RISE_CLR 0x14 +#define EDGE_CFG_FALL_SET 0x18 +#define EDGE_CFG_FALL_CLR 0x1c + +struct tangox_irq_chip { + void __iomem *base; + unsigned long ctl; +}; + +static inline u32 intc_readl(struct tangox_irq_chip *chip, int reg) +{ + return readl_relaxed(chip->base + reg); +} + +static inline void intc_writel(struct tangox_irq_chip *chip, int reg, u32 val) +{ + writel_relaxed(val, chip->base + reg); +} + +static void tangox_dispatch_irqs(struct irq_domain *dom, unsigned int status, + int base) +{ + unsigned int hwirq; + unsigned int virq; + + while (status) { + hwirq = __ffs(status); + virq = irq_find_mapping(dom, base + hwirq); + if (virq) + generic_handle_irq(virq); + status &= ~BIT(hwirq); + } +} + +static void tangox_irq_handler(struct irq_desc *desc) +{ + struct irq_domain *dom = irq_desc_get_handler_data(desc); + struct irq_chip *host_chip = irq_desc_get_chip(desc); + struct tangox_irq_chip *chip = dom->host_data; + unsigned int status_lo, status_hi; + + chained_irq_enter(host_chip, desc); + + status_lo = intc_readl(chip, chip->ctl + IRQ_STATUS); + status_hi = intc_readl(chip, chip->ctl + IRQ_CTL_HI + IRQ_STATUS); + + tangox_dispatch_irqs(dom, status_lo, 0); + tangox_dispatch_irqs(dom, status_hi, 32); + + chained_irq_exit(host_chip, desc); +} + +static int tangox_irq_set_type(struct irq_data *d, unsigned int flow_type) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct tangox_irq_chip *chip = gc->domain->host_data; + struct irq_chip_regs *regs = &gc->chip_types[0].regs; + + switch (flow_type & IRQ_TYPE_SENSE_MASK) { + case IRQ_TYPE_EDGE_RISING: + intc_writel(chip, regs->type + EDGE_CFG_RISE_SET, d->mask); + intc_writel(chip, regs->type + EDGE_CFG_FALL_CLR, d->mask); + break; + + case IRQ_TYPE_EDGE_FALLING: + intc_writel(chip, regs->type + EDGE_CFG_RISE_CLR, d->mask); + intc_writel(chip, regs->type + EDGE_CFG_FALL_SET, d->mask); + break; + + case IRQ_TYPE_LEVEL_HIGH: + intc_writel(chip, regs->type + EDGE_CFG_RISE_CLR, d->mask); + intc_writel(chip, regs->type + EDGE_CFG_FALL_CLR, d->mask); + break; + + case IRQ_TYPE_LEVEL_LOW: + intc_writel(chip, regs->type + EDGE_CFG_RISE_SET, d->mask); + intc_writel(chip, regs->type + EDGE_CFG_FALL_SET, d->mask); + break; + + default: + pr_err("Invalid trigger mode %x for IRQ %d\n", + flow_type, d->irq); + return -EINVAL; + } + + return irq_setup_alt_chip(d, flow_type); +} + +static void __init tangox_irq_init_chip(struct irq_chip_generic *gc, + unsigned long ctl_offs, + unsigned long edge_offs) +{ + struct tangox_irq_chip *chip = gc->domain->host_data; + struct irq_chip_type *ct = gc->chip_types; + unsigned long ctl_base = chip->ctl + ctl_offs; + unsigned long edge_base = EDGE_CTL_BASE + edge_offs; + int i; + + gc->reg_base = chip->base; + gc->unused = 0; + + for (i = 0; i < 2; i++) { + ct[i].chip.irq_ack = irq_gc_ack_set_bit; + ct[i].chip.irq_mask = irq_gc_mask_disable_reg; + ct[i].chip.irq_mask_ack = irq_gc_mask_disable_reg_and_ack; + ct[i].chip.irq_unmask = irq_gc_unmask_enable_reg; + ct[i].chip.irq_set_type = tangox_irq_set_type; + ct[i].chip.name = gc->domain->name; + + ct[i].regs.enable = ctl_base + IRQ_EN_SET; + ct[i].regs.disable = ctl_base + IRQ_EN_CLR; + ct[i].regs.ack = edge_base + EDGE_RAWSTAT; + ct[i].regs.type = edge_base; + } + + ct[0].type = IRQ_TYPE_LEVEL_MASK; + ct[0].handler = handle_level_irq; + + ct[1].type = IRQ_TYPE_EDGE_BOTH; + ct[1].handler = handle_edge_irq; + + intc_writel(chip, ct->regs.disable, 0xffffffff); + intc_writel(chip, ct->regs.ack, 0xffffffff); +} + +static void __init tangox_irq_domain_init(struct irq_domain *dom) +{ + struct irq_chip_generic *gc; + int i; + + for (i = 0; i < 2; i++) { + gc = irq_get_domain_generic_chip(dom, i * 32); + tangox_irq_init_chip(gc, i * IRQ_CTL_HI, i * EDGE_CTL_HI); + } +} + +static int __init tangox_irq_init(void __iomem *base, struct resource *baseres, + struct device_node *node) +{ + struct tangox_irq_chip *chip; + struct irq_domain *dom; + struct resource res; + int irq; + int err; + + irq = irq_of_parse_and_map(node, 0); + if (!irq) + panic("%s: failed to get IRQ", node->name); + + err = of_address_to_resource(node, 0, &res); + if (err) + panic("%s: failed to get address", node->name); + + chip = kzalloc(sizeof(*chip), GFP_KERNEL); + chip->ctl = res.start - baseres->start; + chip->base = base; + + dom = irq_domain_add_linear(node, 64, &irq_generic_chip_ops, chip); + if (!dom) + panic("%s: failed to create irqdomain", node->name); + + err = irq_alloc_domain_generic_chips(dom, 32, 2, node->name, + handle_level_irq, 0, 0, 0); + if (err) + panic("%s: failed to allocate irqchip", node->name); + + tangox_irq_domain_init(dom); + + irq_set_chained_handler(irq, tangox_irq_handler); + irq_set_handler_data(irq, dom); + + return 0; +} + +static int __init tangox_of_irq_init(struct device_node *node, + struct device_node *parent) +{ + struct device_node *c; + struct resource res; + void __iomem *base; + + base = of_iomap(node, 0); + if (!base) + panic("%s: of_iomap failed", node->name); + + of_address_to_resource(node, 0, &res); + + for_each_child_of_node(node, c) + tangox_irq_init(base, &res, c); + + return 0; +} +IRQCHIP_DECLARE(tangox_intc, "sigma,smp8642-intc", tangox_of_irq_init); diff --git a/drivers/irqchip/irq-ts4800.c b/drivers/irqchip/irq-ts4800.c index 4192bdcd27340..2325fb3c482b8 100644 --- a/drivers/irqchip/irq-ts4800.c +++ b/drivers/irqchip/irq-ts4800.c @@ -59,7 +59,7 @@ static int ts4800_irqdomain_map(struct irq_domain *d, unsigned int irq, return 0; } -struct irq_domain_ops ts4800_ic_ops = { +static const struct irq_domain_ops ts4800_ic_ops = { .map = ts4800_irqdomain_map, .xlate = irq_domain_xlate_onecell, }; diff --git a/drivers/media/i2c/adp1653.c b/drivers/media/i2c/adp1653.c index 7e9cbf757e956..fb7ed730d9322 100644 --- a/drivers/media/i2c/adp1653.c +++ b/drivers/media/i2c/adp1653.c @@ -497,7 +497,7 @@ static int adp1653_probe(struct i2c_client *client, if (!client->dev.platform_data) { dev_err(&client->dev, "Neither DT not platform data provided\n"); - return EINVAL; + return -EINVAL; } flash->platform_data = client->dev.platform_data; } diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index f8dd7505b5294..e1719ffdfb3db 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -1960,10 +1960,9 @@ static int adv76xx_isr(struct v4l2_subdev *sd, u32 status, bool *handled) } /* tx 5v detect */ - tx_5v = io_read(sd, 0x70) & info->cable_det_mask; + tx_5v = irq_reg_0x70 & info->cable_det_mask; if (tx_5v) { v4l2_dbg(1, debug, sd, "%s: tx_5v: 0x%x\n", __func__, tx_5v); - io_write(sd, 0x71, tx_5v); adv76xx_s_detect_tx_5v_ctrl(sd); if (handled) *handled = true; diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 7dae0ac0f3aec..e9219f528d7e8 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -20,6 +20,9 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +/* We need to access legacy defines from linux/media.h */ +#define __NEED_MEDIA_LEGACY_API + #include #include #include @@ -115,6 +118,26 @@ static long media_device_enum_entities(struct media_device *mdev, u_ent.group_id = 0; /* Unused */ u_ent.pads = ent->num_pads; u_ent.links = ent->num_links - ent->num_backlinks; + + /* + * Workaround for a bug at media-ctl <= v1.10 that makes it to + * do the wrong thing if the entity function doesn't belong to + * either MEDIA_ENT_F_OLD_BASE or MEDIA_ENT_F_OLD_SUBDEV_BASE + * Ranges. + * + * Non-subdevices are expected to be at the MEDIA_ENT_F_OLD_BASE, + * or, otherwise, will be silently ignored by media-ctl when + * printing the graphviz diagram. So, map them into the devnode + * old range. + */ + if (ent->function < MEDIA_ENT_F_OLD_BASE || + ent->function > MEDIA_ENT_T_DEVNODE_UNKNOWN) { + if (is_media_entity_v4l2_subdev(ent)) + u_ent.type = MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN; + else if (ent->function != MEDIA_ENT_F_IO_V4L) + u_ent.type = MEDIA_ENT_T_DEVNODE_UNKNOWN; + } + memcpy(&u_ent.raw, &ent->info, sizeof(ent->info)); if (copy_to_user(uent, &u_ent, sizeof(u_ent))) return -EFAULT; diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c index 7d28899f89ce1..38aacc7fc6920 100644 --- a/drivers/media/platform/coda/coda-bit.c +++ b/drivers/media/platform/coda/coda-bit.c @@ -1455,9 +1455,9 @@ static int coda_alloc_bitstream_buffer(struct coda_ctx *ctx, return 0; ctx->bitstream.size = roundup_pow_of_two(q_data->sizeimage * 2); - ctx->bitstream.vaddr = dma_alloc_writecombine( - &ctx->dev->plat_dev->dev, ctx->bitstream.size, - &ctx->bitstream.paddr, GFP_KERNEL); + ctx->bitstream.vaddr = dma_alloc_wc(&ctx->dev->plat_dev->dev, + ctx->bitstream.size, + &ctx->bitstream.paddr, GFP_KERNEL); if (!ctx->bitstream.vaddr) { v4l2_err(&ctx->dev->v4l2_dev, "failed to allocate bitstream ringbuffer"); @@ -1474,8 +1474,8 @@ static void coda_free_bitstream_buffer(struct coda_ctx *ctx) if (ctx->bitstream.vaddr == NULL) return; - dma_free_writecombine(&ctx->dev->plat_dev->dev, ctx->bitstream.size, - ctx->bitstream.vaddr, ctx->bitstream.paddr); + dma_free_wc(&ctx->dev->plat_dev->dev, ctx->bitstream.size, + ctx->bitstream.vaddr, ctx->bitstream.paddr); ctx->bitstream.vaddr = NULL; kfifo_init(&ctx->bitstream_fifo, NULL, 0); } diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index 8c54fd21022e4..a136257228482 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -1843,8 +1843,7 @@ static void au0828_analog_create_entities(struct au0828_dev *dev) ent->function = MEDIA_ENT_F_CONN_RF; break; default: /* AU0828_VMUX_DEBUG */ - ent->function = MEDIA_ENT_F_CONN_TEST; - break; + continue; } ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]); diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 4c1903f781fc1..0c6c17a1c59e3 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -415,7 +415,7 @@ static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev) delta = mftb() - psl_tb; if (delta < 0) delta = -delta; - } while (cputime_to_usecs(delta) > 16); + } while (tb_to_ns(delta) > 16000); return 0; } diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c index 11fdadc68e53e..2a6eaf1122b4e 100644 --- a/drivers/misc/lkdtm.c +++ b/drivers/misc/lkdtm.c @@ -103,6 +103,7 @@ enum ctype { CT_EXEC_USERSPACE, CT_ACCESS_USERSPACE, CT_WRITE_RO, + CT_WRITE_RO_AFTER_INIT, CT_WRITE_KERN, }; @@ -140,6 +141,7 @@ static char* cp_type[] = { "EXEC_USERSPACE", "ACCESS_USERSPACE", "WRITE_RO", + "WRITE_RO_AFTER_INIT", "WRITE_KERN", }; @@ -162,6 +164,7 @@ static DEFINE_SPINLOCK(lock_me_up); static u8 data_area[EXEC_SIZE]; static const unsigned long rodata = 0xAA55AA55; +static unsigned long ro_after_init __ro_after_init = 0x55AA5500; module_param(recur_count, int, 0644); MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test"); @@ -503,11 +506,28 @@ static void lkdtm_do_action(enum ctype which) break; } case CT_WRITE_RO: { - unsigned long *ptr; + /* Explicitly cast away "const" for the test. */ + unsigned long *ptr = (unsigned long *)&rodata; - ptr = (unsigned long *)&rodata; + pr_info("attempting bad rodata write at %p\n", ptr); + *ptr ^= 0xabcd1234; - pr_info("attempting bad write at %p\n", ptr); + break; + } + case CT_WRITE_RO_AFTER_INIT: { + unsigned long *ptr = &ro_after_init; + + /* + * Verify we were written to during init. Since an Oops + * is considered a "success", a failure is to just skip the + * real test. + */ + if ((*ptr & 0xAA) != 0xAA) { + pr_info("%p was NOT written during init!?\n", ptr); + break; + } + + pr_info("attempting bad ro_after_init write at %p\n", ptr); *ptr ^= 0xabcd1234; break; @@ -817,6 +837,9 @@ static int __init lkdtm_module_init(void) int n_debugfs_entries = 1; /* Assume only the direct entry */ int i; + /* Make sure we can write to __ro_after_init values during __init */ + ro_after_init |= 0xAA; + /* Register debugfs interface */ lkdtm_debugfs_root = debugfs_create_dir("provoke-crash", NULL); if (!lkdtm_debugfs_root) { diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c index 79316159eec63..88b6c81cebbe6 100644 --- a/drivers/mtd/tests/mtd_nandecctest.c +++ b/drivers/mtd/tests/mtd_nandecctest.c @@ -187,7 +187,7 @@ static int double_bit_error_detect(void *error_data, void *error_ecc, __nand_calculate_ecc(error_data, size, calc_ecc); ret = __nand_correct_data(error_data, error_ecc, calc_ecc, size); - return (ret == -1) ? 0 : -EINVAL; + return (ret == -EBADMSG) ? 0 : -EINVAL; } static const struct nand_ecc_test nand_ecc_test[] = { diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 2a1b6e037e1a1..0134ba32a0578 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -193,7 +193,7 @@ int ubi_start_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, vol->changing_leb = 1; vol->ch_lnum = req->lnum; - vol->upd_buf = vmalloc(req->bytes); + vol->upd_buf = vmalloc(ALIGN((int)req->bytes, ubi->min_io_size)); if (!vol->upd_buf) return -ENOMEM; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 575790e8a75af..74a7dfecee278 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -843,7 +843,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id) if (clear_intf) mcp251x_write_bits(spi, CANINTF, clear_intf, 0x00); - if (eflag) + if (eflag & (EFLG_RX0OVR | EFLG_RX1OVR)) mcp251x_write_bits(spi, EFLG, eflag, 0x00); /* Update can state */ diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 5eee62badf454..cbc99d5649afa 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -826,9 +826,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface static void gs_destroy_candev(struct gs_can *dev) { unregister_candev(dev->netdev); - free_candev(dev->netdev); usb_kill_anchored_urbs(&dev->tx_submitted); - kfree(dev); + free_candev(dev->netdev); } static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -913,12 +912,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id * for (i = 0; i < icount; i++) { dev->canch[i] = gs_make_candev(i, intf); if (IS_ERR_OR_NULL(dev->canch[i])) { + /* save error code to return later */ + rc = PTR_ERR(dev->canch[i]); + /* on failure destroy previously created candevs */ icount = i; - for (i = 0; i < icount; i++) { + for (i = 0; i < icount; i++) gs_destroy_candev(dev->canch[i]); - dev->canch[i] = NULL; - } + + usb_kill_anchored_urbs(&dev->rx_submitted); kfree(dev); return rc; } @@ -939,16 +941,12 @@ static void gs_usb_disconnect(struct usb_interface *intf) return; } - for (i = 0; i < GS_MAX_INTF; i++) { - struct gs_can *can = dev->canch[i]; - - if (!can) - continue; - - gs_destroy_candev(can); - } + for (i = 0; i < GS_MAX_INTF; i++) + if (dev->canch[i]) + gs_destroy_candev(dev->canch[i]); usb_kill_anchored_urbs(&dev->rx_submitted); + kfree(dev); } static const struct usb_device_id gs_usb_table[] = { diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 79e1a0282163d..17b2126075e01 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -2461,7 +2461,7 @@ boomerang_interrupt(int irq, void *dev_id) int i; pci_unmap_single(VORTEX_PCI(vp), le32_to_cpu(vp->tx_ring[entry].frag[0].addr), - le32_to_cpu(vp->tx_ring[entry].frag[0].length), + le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF, PCI_DMA_TODEVICE); for (i=1; i<=skb_shinfo(skb)->nr_frags; i++) diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 17472851674f1..f749e4d389eb1 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -193,7 +193,6 @@ static void altera_tse_mdio_destroy(struct net_device *dev) priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); priv->mdio = NULL; } diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index f71ab2647a3bc..08a23e6b60e94 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1460,7 +1460,19 @@ static int nb8800_probe(struct platform_device *pdev) goto err_disable_clk; } - priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + if (of_phy_is_fixed_link(pdev->dev.of_node)) { + ret = of_phy_register_fixed_link(pdev->dev.of_node); + if (ret < 0) { + dev_err(&pdev->dev, "bad fixed-link spec\n"); + goto err_free_bus; + } + priv->phy_node = of_node_get(pdev->dev.of_node); + } + + if (!priv->phy_node) + priv->phy_node = of_parse_phandle(pdev->dev.of_node, + "phy-handle", 0); + if (!priv->phy_node) { dev_err(&pdev->dev, "no PHY specified\n"); ret = -ENODEV; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 27aa0802d87d5..91874d24fd560 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -4896,9 +4896,9 @@ struct c2s_pri_trans_table_entry { * cfc delete event data */ struct cfc_del_event_data { - u32 cid; - u32 reserved0; - u32 reserved1; + __le32 cid; + __le32 reserved0; + __le32 reserved1; }; @@ -5114,15 +5114,9 @@ struct vf_pf_channel_zone_trigger { * zone that triggers the in-bound interrupt */ struct trigger_vf_zone { -#if defined(__BIG_ENDIAN) - u16 reserved1; - u8 reserved0; - struct vf_pf_channel_zone_trigger vf_pf_channel; -#elif defined(__LITTLE_ENDIAN) struct vf_pf_channel_zone_trigger vf_pf_channel; u8 reserved0; u16 reserved1; -#endif u32 reserved2; }; @@ -5207,9 +5201,9 @@ struct e2_integ_data { * set mac event data */ struct eth_event_data { - u32 echo; - u32 reserved0; - u32 reserved1; + __le32 echo; + __le32 reserved0; + __le32 reserved1; }; @@ -5219,9 +5213,9 @@ struct eth_event_data { struct vf_pf_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 msg_addr_lo; - u32 msg_addr_hi; + __le16 reserved1; + __le32 msg_addr_lo; + __le32 msg_addr_hi; }; /* @@ -5230,9 +5224,9 @@ struct vf_pf_event_data { struct vf_flr_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* @@ -5241,9 +5235,9 @@ struct vf_flr_event_data { struct malicious_vf_event_data { u8 vf_id; u8 err_id; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 6c4e3a69976fc..2bf9c871144f7 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -5280,14 +5280,14 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; - u32 cid = elem->message.data.eth_event.echo & BNX2X_SWCID_MASK; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); + u32 cid = echo & BNX2X_SWCID_MASK; struct bnx2x_vlan_mac_obj *vlan_mac_obj; /* Always push next commands out, don't wait here */ __set_bit(RAMROD_CONT, &ramrod_flags); - switch (le32_to_cpu((__force __le32)elem->message.data.eth_event.echo) - >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: DP(BNX2X_MSG_SP, "Got SETUP_MAC completions\n"); if (CNIC_LOADED(bp) && (cid == BNX2X_ISCSI_ETH_CID(bp))) @@ -5308,8 +5308,7 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, bnx2x_handle_mcast_eqe(bp); return; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } @@ -5478,9 +5477,6 @@ static void bnx2x_eq_int(struct bnx2x *bp) goto next_spqe; } - /* elem CID originates from FW; actually LE */ - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); opcode = elem->message.opcode; /* handle eq element */ @@ -5503,6 +5499,10 @@ static void bnx2x_eq_int(struct bnx2x *bp) * we may want to verify here that the bp state is * HALTING */ + + /* elem CID originates from FW; actually LE */ + cid = SW_CID(elem->message.data.cfc_del_event.cid); + DP(BNX2X_MSG_SP, "got delete ramrod for MULTI[%d]\n", cid); @@ -5596,10 +5596,8 @@ static void bnx2x_eq_int(struct bnx2x *bp) BNX2X_STATE_OPENING_WAIT4_PORT): case (EVENT_RING_OPCODE_RSS_UPDATE_RULES | BNX2X_STATE_CLOSING_WAIT4_HALT): - cid = elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK; DP(BNX2X_MSG_SP, "got RSS_UPDATE ramrod. CID %d\n", - cid); + SW_CID(elem->message.data.eth_event.echo)); rss_raw->clear_pending(rss_raw); break; @@ -5684,7 +5682,7 @@ static void bnx2x_sp_task(struct work_struct *work) if (status & BNX2X_DEF_SB_IDX) { struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp); - if (FCOE_INIT(bp) && + if (FCOE_INIT(bp) && (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) { /* Prevent local bottom-halves from running as * we are going to change the local NAPI list. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 9d027348cd09b..632daff117d30 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1672,11 +1672,12 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); /* Always push next commands out, don't wait here */ set_bit(RAMROD_CONT, &ramrod_flags); - switch (elem->message.data.eth_event.echo >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: rc = vfq->mac_obj.complete(bp, &vfq->mac_obj, elem, &ramrod_flags); @@ -1686,8 +1687,7 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, &ramrod_flags); break; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } if (rc < 0) @@ -1747,16 +1747,14 @@ int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem) switch (opcode) { case EVENT_RING_OPCODE_CFC_DEL: - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); + cid = SW_CID(elem->message.data.cfc_del_event.cid); DP(BNX2X_MSG_IOV, "checking cfc-del comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_CLASSIFICATION_RULES: case EVENT_RING_OPCODE_MULTICAST_RULES: case EVENT_RING_OPCODE_FILTERS_RULES: case EVENT_RING_OPCODE_RSS_UPDATE_RULES: - cid = (elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK); + cid = SW_CID(elem->message.data.eth_event.echo); DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_VF_FLR: diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 1374e5394a797..bfae300cf25ff 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -2187,8 +2187,10 @@ void bnx2x_vf_mbx_schedule(struct bnx2x *bp, /* Update VFDB with current message and schedule its handling */ mutex_lock(&BP_VFDB(bp)->event_mutex); - BP_VF_MBX(bp, vf_idx)->vf_addr_hi = vfpf_event->msg_addr_hi; - BP_VF_MBX(bp, vf_idx)->vf_addr_lo = vfpf_event->msg_addr_lo; + BP_VF_MBX(bp, vf_idx)->vf_addr_hi = + le32_to_cpu(vfpf_event->msg_addr_hi); + BP_VF_MBX(bp, vf_idx)->vf_addr_lo = + le32_to_cpu(vfpf_event->msg_addr_lo); BP_VFDB(bp)->event_occur |= (1ULL << vf_idx); mutex_unlock(&BP_VFDB(bp)->event_mutex); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8ab000dd52d95..82f191382989b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -248,7 +248,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action); - end = PTR_ALIGN(pdata + length + 1, 8) - 1; + end = pdata + length; + end = PTR_ALIGN(end, 8) - 1; *end = 0; skb_copy_from_linear_data(skb, pdata, len); diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c index 04b0d16b210e8..95bc470ae441a 100644 --- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c +++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c @@ -987,7 +987,7 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf) if (!list_empty(&rxf->ucast_pending_add_q)) { mac = list_first_entry(&rxf->ucast_pending_add_q, struct bna_mac, qe); - list_add_tail(&mac->qe, &rxf->ucast_active_q); + list_move_tail(&mac->qe, &rxf->ucast_active_q); bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_ADD_REQ); return 1; } diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 688828865c482..34e9acea87479 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -116,6 +116,15 @@ #define NIC_PF_INTR_ID_MBOX0 8 #define NIC_PF_INTR_ID_MBOX1 9 +/* Minimum FIFO level before all packets for the CQ are dropped + * + * This value ensures that once a packet has been "accepted" + * for reception it will not get dropped due to non-availability + * of CQ descriptor. An errata in HW mandates this value to be + * atleast 0x100. + */ +#define NICPF_CQM_MIN_DROP_LEVEL 0x100 + /* Global timer for CQ timer thresh interrupts * Calculated for SCLK of 700Mhz * value written should be a 1/16th of what is expected diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 4dded90076c87..95f17f8cadacc 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -304,6 +304,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) static void nic_init_hw(struct nicpf *nic) { int i; + u64 cqm_cfg; /* Enable NIC HW block */ nic_reg_write(nic, NIC_PF_CFG, 0x3); @@ -340,6 +341,11 @@ static void nic_init_hw(struct nicpf *nic) /* Enable VLAN ethertype matching and stripping */ nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7, (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q); + + /* Check if HW expected value is higher (could be in future chips) */ + cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG); + if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL) + nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL); } /* Channel parse index configuration */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index dd536be201931..afb10e326b4fc 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -21,7 +21,7 @@ #define NIC_PF_TCP_TIMER (0x0060) #define NIC_PF_BP_CFG (0x0080) #define NIC_PF_RRM_CFG (0x0088) -#define NIC_PF_CQM_CF (0x00A0) +#define NIC_PF_CQM_CFG (0x00A0) #define NIC_PF_CNM_CF (0x00A8) #define NIC_PF_CNM_STATUS (0x00B0) #define NIC_PF_CQ_AVG_CFG (0x00C0) diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index cf837831304be..f9751294ece79 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -531,6 +531,7 @@ struct be_adapter { struct delayed_work be_err_detection_work; u8 err_flags; + bool pcicfg_mapped; /* pcicfg obtained via pci_iomap() */ u32 flags; u32 cmd_privileges; /* Ethtool knobs and info */ diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 241819b36ca72..6d9a8d78e8ad8 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -622,10 +622,13 @@ enum be_if_flags { BE_IF_FLAGS_VLAN_PROMISCUOUS |\ BE_IF_FLAGS_MCAST_PROMISCUOUS) -#define BE_IF_EN_FLAGS (BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\ - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED) +#define BE_IF_FILT_FLAGS_BASIC (BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS | \ + BE_IF_FLAGS_UNTAGGED) -#define BE_IF_ALL_FILT_FLAGS (BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS) +#define BE_IF_ALL_FILT_FLAGS (BE_IF_FILT_FLAGS_BASIC | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_ALL_PROMISCUOUS) /* An RX interface is an object with one or more MAC addresses and * filtering capabilities. */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index f99de3657ce3b..d1cf1274fc2f4 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -125,6 +125,11 @@ static const char * const ue_status_hi_desc[] = { "Unknown" }; +#define BE_VF_IF_EN_FLAGS (BE_IF_FLAGS_UNTAGGED | \ + BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS) + static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q) { struct be_dma_mem *mem = &q->dma_mem; @@ -3537,7 +3542,7 @@ static int be_enable_if_filters(struct be_adapter *adapter) { int status; - status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON); + status = be_cmd_rx_filter(adapter, BE_IF_FILT_FLAGS_BASIC, ON); if (status) return status; @@ -3857,8 +3862,7 @@ static int be_vfs_if_create(struct be_adapter *adapter) int status; /* If a FW profile exists, then cap_flags are updated */ - cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS; + cap_flags = BE_VF_IF_EN_FLAGS; for_all_vfs(adapter, vf_cfg, vf) { if (!BE3_chip(adapter)) { @@ -3874,10 +3878,8 @@ static int be_vfs_if_create(struct be_adapter *adapter) } } - en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED | - BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | - BE_IF_FLAGS_PASS_L3L4_ERRORS); + /* PF should enable IF flags during proxy if_create call */ + en_flags = cap_flags & BE_VF_IF_EN_FLAGS; status = be_cmd_if_create(adapter, cap_flags, en_flags, &vf_cfg->if_handle, vf + 1); if (status) @@ -4968,6 +4970,8 @@ static void be_unmap_pci_bars(struct be_adapter *adapter) pci_iounmap(adapter->pdev, adapter->csr); if (adapter->db) pci_iounmap(adapter->pdev, adapter->db); + if (adapter->pcicfg && adapter->pcicfg_mapped) + pci_iounmap(adapter->pdev, adapter->pcicfg); } static int db_bar(struct be_adapter *adapter) @@ -5019,8 +5023,10 @@ static int be_map_pci_bars(struct be_adapter *adapter) if (!addr) goto pci_map_err; adapter->pcicfg = addr; + adapter->pcicfg_mapped = true; } else { adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET; + adapter->pcicfg_mapped = false; } } diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 62fa136554ac2..41b0106451009 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1265,7 +1265,6 @@ static int ethoc_remove(struct platform_device *pdev) if (priv->mdio) { mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } if (priv->clk) diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 623aa1c8ebc6b..79a210aaf0bbd 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2791,6 +2791,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) goto fman_free; } + fman->dev = &of_dev->dev; + return fman; fman_node_put: @@ -2845,8 +2847,6 @@ static int fman_probe(struct platform_device *of_dev) dev_set_drvdata(dev, fman); - fman->dev = dev; - dev_dbg(dev, "FMan%d probed\n", fman->dts_params.id); return 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 2aa7b401cc3be..b9ecf197ad117 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1111,8 +1111,10 @@ static void __gfar_detect_errata_85xx(struct gfar_private *priv) if ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) == 0x20)) priv->errata |= GFAR_ERRATA_12; + /* P2020/P1010 Rev 1; MPC8548 Rev 2 */ if (((SVR_SOC_VER(svr) == SVR_P2020) && (SVR_REV(svr) < 0x20)) || - ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20))) + ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)) || + ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) < 0x31))) priv->errata |= GFAR_ERRATA_76; /* aka eTSEC 20 */ } #endif diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 74beb1867230c..4ccc032633c4e 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -25,6 +25,7 @@ config HIX5HD2_GMAC config HIP04_ETH tristate "HISILICON P04 Ethernet support" + depends on HAS_IOMEM # For MFD_SYSCON select MARVELL_PHY select MFD_SYSCON select HNS_MDIO diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index a0070d0e740da..d4f92ed322d6e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -675,8 +675,12 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, { int ret; struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); switch (loop) { + case MAC_INTERNALLOOP_PHY: + ret = 0; + break; case MAC_INTERNALLOOP_SERDES: ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en); break; @@ -686,6 +690,10 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, default: ret = -EINVAL; } + + if (!ret) + hns_dsaf_set_inner_lb(mac_cb->dsaf_dev, mac_cb->mac_id, en); + return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 9439f04962e1d..38fc5be3870cc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -230,6 +230,30 @@ static void hns_dsaf_mix_def_qid_cfg(struct dsaf_device *dsaf_dev) } } +static void hns_dsaf_inner_qid_cfg(struct dsaf_device *dsaf_dev) +{ + u16 max_q_per_vf, max_vfn; + u32 q_id, q_num_per_port; + u32 mac_id; + + if (AE_IS_VER1(dsaf_dev->dsaf_ver)) + return; + + hns_rcb_get_queue_mode(dsaf_dev->dsaf_mode, + HNS_DSAF_COMM_SERVICE_NW_IDX, + &max_vfn, &max_q_per_vf); + q_num_per_port = max_vfn * max_q_per_vf; + + for (mac_id = 0, q_id = 0; mac_id < DSAF_SERVICE_NW_NUM; mac_id++) { + dsaf_set_dev_field(dsaf_dev, + DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_QID_M, + DSAFV2_SERDES_LBK_QID_S, + q_id); + q_id += q_num_per_port; + } +} + /** * hns_dsaf_sw_port_type_cfg - cfg sw type * @dsaf_id: dsa fabric id @@ -691,6 +715,16 @@ void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en) dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_MIX_MODE_S, !!en); } +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en) +{ + if (AE_IS_VER1(dsaf_dev->dsaf_ver) || + dsaf_dev->mac_cb[mac_id].mac_type == HNAE_PORT_DEBUG) + return; + + dsaf_set_dev_bit(dsaf_dev, DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_EN_B, !!en); +} + /** * hns_dsaf_tbl_stat_en - tbl * @dsaf_id: dsa fabric id @@ -1022,6 +1056,9 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev) /* set promisc def queue id */ hns_dsaf_mix_def_qid_cfg(dsaf_dev); + /* set inner loopback queue id */ + hns_dsaf_inner_qid_cfg(dsaf_dev); + /* in non switch mode, set all port to access mode */ hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 40205b910f80e..5fea226efaf33 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -417,5 +417,6 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port); void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data); int hns_dsaf_get_regs_count(void); void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en); +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en); #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index f0c4f9b09d5b0..60d695daa471e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -134,6 +134,7 @@ #define DSAF_XGE_INT_STS_0_REG 0x1C0 #define DSAF_PPE_INT_STS_0_REG 0x1E0 #define DSAF_ROCEE_INT_STS_0_REG 0x200 +#define DSAFV2_SERDES_LBK_0_REG 0x220 #define DSAF_PPE_QID_CFG_0_REG 0x300 #define DSAF_SW_PORT_TYPE_0_REG 0x320 #define DSAF_STP_PORT_TYPE_0_REG 0x340 @@ -857,6 +858,10 @@ #define PPEV2_CFG_RSS_TBL_4N3_S 24 #define PPEV2_CFG_RSS_TBL_4N3_M (((1UL << 5) - 1) << PPEV2_CFG_RSS_TBL_4N3_S) +#define DSAFV2_SERDES_LBK_EN_B 8 +#define DSAFV2_SERDES_LBK_QID_S 0 +#define DSAFV2_SERDES_LBK_QID_M (((1UL << 8) - 1) << DSAFV2_SERDES_LBK_QID_S) + #define PPE_CNT_CLR_CE_B 0 #define PPE_CNT_CLR_SNAP_EN_B 1 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 3df22840fcd15..3c4a3bc31a892 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -295,8 +295,10 @@ static int __lb_setup(struct net_device *ndev, switch (loop) { case MAC_INTERNALLOOP_PHY: - if ((phy_dev) && (!phy_dev->is_c45)) + if ((phy_dev) && (!phy_dev->is_c45)) { ret = hns_nic_config_phy_loopback(phy_dev, 0x1); + ret |= h->dev->ops->set_loopback(h, loop, 0x1); + } break; case MAC_INTERNALLOOP_MAC: if ((h->dev->ops->set_loopback) && @@ -376,6 +378,7 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, struct sk_buff *skb) { struct net_device *ndev; + struct hns_nic_priv *priv; struct hnae_ring *ring; struct netdev_queue *dev_queue; struct sk_buff *new_skb; @@ -385,8 +388,17 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, char buff[33]; /* 32B data and the last character '\0' */ if (!ring_data) { /* Just for doing create frame*/ + ndev = skb->dev; + priv = netdev_priv(ndev); + frame_size = skb->len; memset(skb->data, 0xFF, frame_size); + if ((!AE_IS_VER1(priv->enet_ver)) && + (priv->ae_handle->port_type == HNAE_PORT_SERVICE)) { + memcpy(skb->data, ndev->dev_addr, 6); + skb->data[5] += 0x1f; + } + frame_size &= ~1ul; memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); memset(&skb->data[frame_size / 2 + 10], 0xBE, @@ -486,6 +498,7 @@ static int __lb_run_test(struct net_device *ndev, /* place data into test skb */ (void)skb_put(skb, size); + skb->dev = ndev; __lb_other_process(NULL, skb); skb->queue_mapping = NIC_LB_TEST_RING_ID; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 335417b4756b7..ebe60719e489c 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1166,7 +1166,10 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, if (!firmware_has_feature(FW_FEATURE_CMO)) netdev_err(netdev, "tx: unable to map xmit buffer\n"); adapter->tx_map_failed++; - skb_linearize(skb); + if (skb_linearize(skb)) { + netdev->stats.tx_dropped++; + goto out; + } force_bounce = 1; goto retry_bounce; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7d65708437238..6e9e16eee5d0e 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1348,44 +1348,44 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) crq.request_capability.cmd = REQUEST_CAPABILITY; crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_tx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_add_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_tx_entries_per_subcrq); + cpu_to_be64(adapter->req_tx_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_rx_add_entries_per_subcrq); + cpu_to_be64(adapter->req_rx_add_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_MTU); - crq.request_capability.number = cpu_to_be32(adapter->req_mtu); + crq.request_capability.number = cpu_to_be64(adapter->req_mtu); ibmvnic_send_crq(adapter, &crq); if (adapter->netdev->flags & IFF_PROMISC) { if (adapter->promisc_supported) { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(1); + crq.request_capability.number = cpu_to_be64(1); ibmvnic_send_crq(adapter, &crq); } } else { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(0); + crq.request_capability.number = cpu_to_be64(0); ibmvnic_send_crq(adapter, &crq); } @@ -2312,93 +2312,93 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, switch (be16_to_cpu(crq->query_capability.capability)) { case MIN_TX_QUEUES: adapter->min_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_queues = %lld\n", adapter->min_tx_queues); break; case MIN_RX_QUEUES: adapter->min_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_queues = %lld\n", adapter->min_rx_queues); break; case MIN_RX_ADD_QUEUES: adapter->min_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_queues = %lld\n", adapter->min_rx_add_queues); break; case MAX_TX_QUEUES: adapter->max_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_queues = %lld\n", adapter->max_tx_queues); break; case MAX_RX_QUEUES: adapter->max_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_queues = %lld\n", adapter->max_rx_queues); break; case MAX_RX_ADD_QUEUES: adapter->max_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_queues = %lld\n", adapter->max_rx_add_queues); break; case MIN_TX_ENTRIES_PER_SUBCRQ: adapter->min_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n", adapter->min_tx_entries_per_subcrq); break; case MIN_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->min_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n", adapter->min_rx_add_entries_per_subcrq); break; case MAX_TX_ENTRIES_PER_SUBCRQ: adapter->max_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n", adapter->max_tx_entries_per_subcrq); break; case MAX_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->max_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n", adapter->max_rx_add_entries_per_subcrq); break; case TCP_IP_OFFLOAD: adapter->tcp_ip_offload = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "tcp_ip_offload = %lld\n", adapter->tcp_ip_offload); break; case PROMISC_SUPPORTED: adapter->promisc_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "promisc_supported = %lld\n", adapter->promisc_supported); break; case MIN_MTU: - adapter->min_mtu = be32_to_cpu(crq->query_capability.number); + adapter->min_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu); break; case MAX_MTU: - adapter->max_mtu = be32_to_cpu(crq->query_capability.number); + adapter->max_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu); break; case MAX_MULTICAST_FILTERS: adapter->max_multicast_filters = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_multicast_filters = %lld\n", adapter->max_multicast_filters); break; case VLAN_HEADER_INSERTION: adapter->vlan_header_insertion = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); if (adapter->vlan_header_insertion) netdev->features |= NETIF_F_HW_VLAN_STAG_TX; netdev_dbg(netdev, "vlan_header_insertion = %lld\n", @@ -2406,43 +2406,43 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, break; case MAX_TX_SG_ENTRIES: adapter->max_tx_sg_entries = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_sg_entries = %lld\n", adapter->max_tx_sg_entries); break; case RX_SG_SUPPORTED: adapter->rx_sg_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "rx_sg_supported = %lld\n", adapter->rx_sg_supported); break; case OPT_TX_COMP_SUB_QUEUES: adapter->opt_tx_comp_sub_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n", adapter->opt_tx_comp_sub_queues); break; case OPT_RX_COMP_QUEUES: adapter->opt_rx_comp_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n", adapter->opt_rx_comp_queues); break; case OPT_RX_BUFADD_Q_PER_RX_COMP_Q: adapter->opt_rx_bufadd_q_per_rx_comp_q = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n", adapter->opt_rx_bufadd_q_per_rx_comp_q); break; case OPT_TX_ENTRIES_PER_SUBCRQ: adapter->opt_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n", adapter->opt_tx_entries_per_subcrq); break; case OPT_RXBA_ENTRIES_PER_SUBCRQ: adapter->opt_rxba_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n", adapter->opt_rxba_entries_per_subcrq); break; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 1242925ad34cb..1a9993cc79b57 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -319,10 +319,8 @@ struct ibmvnic_capability { u8 first; u8 cmd; __be16 capability; /* one of ibmvnic_capabilities */ + __be64 number; struct ibmvnic_rc rc; - __be32 number; /*FIX: should be __be64, but I'm getting the least - * significant word first - */ } __packed __aligned(8); struct ibmvnic_login { diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index fa593dd3efe12..3772f3ac956e9 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -83,6 +83,15 @@ config E1000E To compile this driver as a module, choose M here. The module will be called e1000e. +config E1000E_HWTS + bool "Support HW cross-timestamp on PCH devices" + default y + depends on E1000E && X86 + ---help--- + Say Y to enable hardware supported cross-timestamping on PCH + devices. The cross-timestamp is available through the PTP clock + driver precise cross-timestamp ioctl (PTP_SYS_OFFSET_PRECISE). + config IGB tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support" depends on PCI diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index f7c7804d79e57..0641c00987380 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -528,6 +528,11 @@ #define E1000_RXCW_C 0x20000000 /* Receive config */ #define E1000_RXCW_SYNCH 0x40000000 /* Receive config synch */ +/* HH Time Sync */ +#define E1000_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK 0x0000F000 /* max delay */ +#define E1000_TSYNCTXCTL_SYNC_COMP 0x40000000 /* sync complete */ +#define E1000_TSYNCTXCTL_START_SYNC 0x80000000 /* initiate sync */ + #define E1000_TSYNCTXCTL_VALID 0x00000001 /* Tx timestamp valid */ #define E1000_TSYNCTXCTL_ENABLED 0x00000010 /* enable Tx timestamping */ diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 25a0ad5102d63..e2ff3ef75d5d6 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -26,6 +26,12 @@ #include "e1000.h" +#ifdef CONFIG_E1000E_HWTS +#include +#include +#include +#endif + /** * e1000e_phc_adjfreq - adjust the frequency of the hardware clock * @ptp: ptp clock structure @@ -98,6 +104,78 @@ static int e1000e_phc_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } +#ifdef CONFIG_E1000E_HWTS +#define MAX_HW_WAIT_COUNT (3) + +/** + * e1000e_phc_get_syncdevicetime - Callback given to timekeeping code reads system/device registers + * @device: current device time + * @system: system counter value read synchronously with device time + * @ctx: context provided by timekeeping code + * + * Read device and system (ART) clock simultaneously and return the corrected + * clock values in ns. + **/ +static int e1000e_phc_get_syncdevicetime(ktime_t *device, + struct system_counterval_t *system, + void *ctx) +{ + struct e1000_adapter *adapter = (struct e1000_adapter *)ctx; + struct e1000_hw *hw = &adapter->hw; + unsigned long flags; + int i; + u32 tsync_ctrl; + cycle_t dev_cycles; + cycle_t sys_cycles; + + tsync_ctrl = er32(TSYNCTXCTL); + tsync_ctrl |= E1000_TSYNCTXCTL_START_SYNC | + E1000_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK; + ew32(TSYNCTXCTL, tsync_ctrl); + for (i = 0; i < MAX_HW_WAIT_COUNT; ++i) { + udelay(1); + tsync_ctrl = er32(TSYNCTXCTL); + if (tsync_ctrl & E1000_TSYNCTXCTL_SYNC_COMP) + break; + } + + if (i == MAX_HW_WAIT_COUNT) + return -ETIMEDOUT; + + dev_cycles = er32(SYSSTMPH); + dev_cycles <<= 32; + dev_cycles |= er32(SYSSTMPL); + spin_lock_irqsave(&adapter->systim_lock, flags); + *device = ns_to_ktime(timecounter_cyc2time(&adapter->tc, dev_cycles)); + spin_unlock_irqrestore(&adapter->systim_lock, flags); + + sys_cycles = er32(PLTSTMPH); + sys_cycles <<= 32; + sys_cycles |= er32(PLTSTMPL); + *system = convert_art_to_tsc(sys_cycles); + + return 0; +} + +/** + * e1000e_phc_getsynctime - Reads the current system/device cross timestamp + * @ptp: ptp clock structure + * @cts: structure containing timestamp + * + * Read device and system (ART) clock simultaneously and return the scaled + * clock values in ns. + **/ +static int e1000e_phc_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *xtstamp) +{ + struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, + ptp_clock_info); + + return get_device_system_crosststamp(e1000e_phc_get_syncdevicetime, + adapter, NULL, xtstamp); +} +#endif/*CONFIG_E1000E_HWTS*/ + /** * e1000e_phc_gettime - Reads the current time from the hardware clock * @ptp: ptp clock structure @@ -236,6 +314,13 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) break; } +#ifdef CONFIG_E1000E_HWTS + /* CPU must have ART and GBe must be from Sunrise Point or greater */ + if (hw->mac.type >= e1000_pch_spt && boot_cpu_has(X86_FEATURE_ART)) + adapter->ptp_clock_info.getcrosststamp = + e1000e_phc_getcrosststamp; +#endif/*CONFIG_E1000E_HWTS*/ + INIT_DELAYED_WORK(&adapter->systim_overflow_work, e1000e_systim_overflow_work); diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h index 1d5e0b77062a0..0cb4d365e5ad7 100644 --- a/drivers/net/ethernet/intel/e1000e/regs.h +++ b/drivers/net/ethernet/intel/e1000e/regs.h @@ -245,6 +245,10 @@ #define E1000_SYSTIML 0x0B600 /* System time register Low - RO */ #define E1000_SYSTIMH 0x0B604 /* System time register High - RO */ #define E1000_TIMINCA 0x0B608 /* Increment attributes register - RW */ +#define E1000_SYSSTMPL 0x0B648 /* HH Timesync system stamp low register */ +#define E1000_SYSSTMPH 0x0B64C /* HH Timesync system stamp hi register */ +#define E1000_PLTSTMPL 0x0B640 /* HH Timesync platform stamp low register */ +#define E1000_PLTSTMPH 0x0B644 /* HH Timesync platform stamp hi register */ #define E1000_RXMTRL 0x0B634 /* Time sync Rx EtherType and Msg Type - RW */ #define E1000_RXUDP 0x0B638 /* Time Sync Rx UDP Port - RW */ diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b1de7afd41166..3ddf657bc10bc 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme) } static inline void -jme_clear_pm(struct jme_adapter *jme) +jme_clear_pm_enable_wol(struct jme_adapter *jme) { jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs); } +static inline void +jme_clear_pm_disable_wol(struct jme_adapter *jme) +{ + jwrite32(jme, JME_PMCS, PMCS_STMASK); +} + static int jme_reload_eeprom(struct jme_adapter *jme) { @@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev) struct jme_adapter *jme = netdev_priv(netdev); int rc; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); JME_NAPI_ENABLE(jme); tasklet_init(&jme->linkch_task, jme_link_change_tasklet, @@ -1925,11 +1931,11 @@ jme_wait_link(struct jme_adapter *jme) static void jme_powersave_phy(struct jme_adapter *jme) { - if (jme->reg_pmcs) { + if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) { jme_set_100m_half(jme); if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN)) jme_wait_link(jme); - jme_clear_pm(jme); + jme_clear_pm_enable_wol(jme); } else { jme_phy_off(jme); } @@ -2646,9 +2652,6 @@ jme_set_wol(struct net_device *netdev, if (wol->wolopts & WAKE_MAGIC) jme->reg_pmcs |= PMCS_MFEN; - jwrite32(jme, JME_PMCS, jme->reg_pmcs); - device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs)); - return 0; } @@ -3172,8 +3175,8 @@ jme_init_one(struct pci_dev *pdev, jme->mii_if.mdio_read = jme_mdio_read; jme->mii_if.mdio_write = jme_mdio_write; - jme_clear_pm(jme); - device_set_wakeup_enable(&pdev->dev, true); + jme_clear_pm_disable_wol(jme); + device_init_wakeup(&pdev->dev, true); jme_set_phyfifo_5level(jme); jme->pcirev = pdev->revision; @@ -3304,7 +3307,7 @@ jme_resume(struct device *dev) if (!netif_running(netdev)) return 0; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); jme_phy_on(jme); if (test_bit(JME_FLAG_SSET, &jme->flags)) jme_set_settings(netdev, &jme->old_ecmd); @@ -3312,13 +3315,14 @@ jme_resume(struct device *dev) jme_reset_phy_processor(jme); jme_phy_calibration(jme); jme_phy_setEA(jme); - jme_start_irq(jme); netif_device_attach(netdev); atomic_inc(&jme->link_changing); jme_reset_link(jme); + jme_start_irq(jme); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index f191a16125893..21e2c09602716 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2245,7 +2245,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) struct mlx4_en_dev *mdev = en_priv->mdev; u64 mac_u64 = mlx4_mac_to_u64(mac); - if (!is_valid_ether_addr(mac)) + if (is_multicast_ether_addr(mac)) return -EINVAL; return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2cc3c626c3fea..f8674ae62752d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1256,6 +1256,7 @@ static ssize_t set_port_ib_mtu(struct device *dev, static int mlx4_mf_bond(struct mlx4_dev *dev) { int err = 0; + int nvfs; struct mlx4_slaves_pport slaves_port1; struct mlx4_slaves_pport slaves_port2; DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX); @@ -1272,11 +1273,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev) return -EINVAL; } + /* number of virtual functions is number of total functions minus one + * physical function for each port. + */ + nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + + bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2; + /* limit on maximum allowed VFs */ - if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + - bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) > - MAX_MF_BOND_ALLOWED_SLAVES) + if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) { + mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n", + nvfs, MAX_MF_BOND_ALLOWED_SLAVES); return -EINVAL; + } if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) { mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n"); diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 787b7bb54d52a..211c65087997d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -193,10 +193,10 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -389,10 +389,10 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -479,10 +479,10 @@ int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -588,10 +588,10 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -764,10 +764,10 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index aac071a7e830b..5b1753233c5dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -223,6 +223,7 @@ struct mlx5e_pport_stats { static const char rq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "csum_none", "csum_sw", "lro_packets", @@ -232,16 +233,18 @@ static const char rq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_rq_stats { u64 packets; + u64 bytes; u64 csum_none; u64 csum_sw; u64 lro_packets; u64 lro_bytes; u64 wqe_err; -#define NUM_RQ_STATS 6 +#define NUM_RQ_STATS 7 }; static const char sq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "tso_packets", "tso_bytes", "csum_offload_none", @@ -253,6 +256,7 @@ static const char sq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_sq_stats { u64 packets; + u64 bytes; u64 tso_packets; u64 tso_bytes; u64 csum_offload_none; @@ -260,7 +264,7 @@ struct mlx5e_sq_stats { u64 wake; u64 dropped; u64 nop; -#define NUM_SQ_STATS 8 +#define NUM_SQ_STATS 9 }; struct mlx5e_stats { @@ -304,14 +308,9 @@ enum { MLX5E_RQ_STATE_POST_WQES_ENABLE, }; -enum cq_flags { - MLX5E_CQ_HAS_CQES = 1, -}; - struct mlx5e_cq { /* data path - accessed per cqe */ struct mlx5_cqwq wq; - unsigned long flags; /* data path - accessed per napi poll */ struct napi_struct *napi; @@ -452,6 +451,8 @@ enum mlx5e_traffic_types { MLX5E_NUM_TT, }; +#define IS_HASHING_TT(tt) (tt != MLX5E_TT_ANY) + enum mlx5e_rqt_ix { MLX5E_INDIRECTION_RQT, MLX5E_SINGLE_RQ_RQT, @@ -618,9 +619,12 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); int mlx5e_redirect_rqt(struct mlx5e_priv *priv, enum mlx5e_rqt_ix rqt_ix); +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv); int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels); static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, struct mlx5e_tx_wqe *wqe, int bf_sz) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index be6543570b2be..2018eebe15315 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -62,10 +62,11 @@ static void mlx5e_timestamp_overflow(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, overflow_work); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period); } @@ -136,10 +137,11 @@ static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns = timespec64_to_ns(ts); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_init(&tstamp->clock, &tstamp->cycles, ns); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -150,10 +152,11 @@ static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns; + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); ns = timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); *ts = ns_to_timespec64(ns); @@ -164,10 +167,11 @@ static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_adjtime(&tstamp->clock, delta); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -176,6 +180,7 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) { u64 adj; u32 diff; + unsigned long flags; int neg_adj = 0; struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); @@ -189,11 +194,11 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : tstamp->nominal_c_mult + diff; - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 65624ac65b4c3..5abeb00fceb8b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -385,6 +385,8 @@ static int mlx5e_set_channels(struct net_device *dev, mlx5e_close_locked(dev); priv->params.num_channels = count; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); if (was_opened) err = mlx5e_open_locked(dev); @@ -703,18 +705,36 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return 0; } +static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen) +{ + struct mlx5_core_dev *mdev = priv->mdev; + void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx); + int i; + + MLX5_SET(modify_tir_in, in, bitmask.hash, 1); + mlx5e_build_tir_ctx_hash(tirc, priv); + + for (i = 0; i < MLX5E_NUM_TT; i++) + if (IS_HASHING_TT(i)) + mlx5_core_modify_tir(mdev, priv->tirn[i], in, inlen); +} + static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc) { struct mlx5e_priv *priv = netdev_priv(dev); - bool close_open; - int err = 0; + int inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + void *in; if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_XOR) && (hfunc != ETH_RSS_HASH_TOP)) return -EINVAL; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + mutex_lock(&priv->state_lock); if (indir) { @@ -723,11 +743,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, mlx5e_redirect_rqt(priv, MLX5E_INDIRECTION_RQT); } - close_open = (key || (hfunc != ETH_RSS_HASH_NO_CHANGE)) && - test_bit(MLX5E_STATE_OPENED, &priv->state); - if (close_open) - mlx5e_close_locked(dev); - if (key) memcpy(priv->params.toeplitz_hash_key, key, sizeof(priv->params.toeplitz_hash_key)); @@ -735,12 +750,13 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE) priv->params.rss_hfunc = hfunc; - if (close_open) - err = mlx5e_open_locked(priv->netdev); + mlx5e_modify_tirs_hash(priv, in, inlen); mutex_unlock(&priv->state_lock); - return err; + kvfree(in); + + return 0; } static int mlx5e_get_rxnfc(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d4e1c30452009..402994bf7e167 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -141,6 +141,10 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) return; /* Collect firts the SW counters and then HW for consistency */ + s->rx_packets = 0; + s->rx_bytes = 0; + s->tx_packets = 0; + s->tx_bytes = 0; s->tso_packets = 0; s->tso_bytes = 0; s->tx_queue_stopped = 0; @@ -155,6 +159,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (i = 0; i < priv->params.num_channels; i++) { rq_stats = &priv->channel[i]->rq.stats; + s->rx_packets += rq_stats->packets; + s->rx_bytes += rq_stats->bytes; s->lro_packets += rq_stats->lro_packets; s->lro_bytes += rq_stats->lro_bytes; s->rx_csum_none += rq_stats->csum_none; @@ -164,6 +170,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (j = 0; j < priv->params.num_tc; j++) { sq_stats = &priv->channel[i]->sq[j].stats; + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; s->tso_packets += sq_stats->tso_packets; s->tso_bytes += sq_stats->tso_bytes; s->tx_queue_stopped += sq_stats->stopped; @@ -225,23 +233,6 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) s->tx_broadcast_bytes = MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); - s->rx_packets = - s->rx_unicast_packets + - s->rx_multicast_packets + - s->rx_broadcast_packets; - s->rx_bytes = - s->rx_unicast_bytes + - s->rx_multicast_bytes + - s->rx_broadcast_bytes; - s->tx_packets = - s->tx_unicast_packets + - s->tx_multicast_packets + - s->tx_broadcast_packets; - s->tx_bytes = - s->tx_unicast_bytes + - s->tx_multicast_bytes + - s->tx_broadcast_bytes; - /* Update calculated offload counters */ s->tx_csum_offload = s->tx_packets - tx_offload_none; s->rx_csum_good = s->rx_packets - s->rx_csum_none - @@ -1199,7 +1190,6 @@ static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc) ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE); ix = priv->params.indirection_rqt[ix]; - ix = ix % priv->params.num_channels; MLX5_SET(rqtc, rqtc, rq_num[i], test_bit(MLX5E_STATE_OPENED, &priv->state) ? priv->channel[ix]->rq.rqn : @@ -1317,7 +1307,22 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv) lro_timer_supported_periods[2])); } -static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv) +{ + MLX5_SET(tirc, tirc, rx_hash_fn, + mlx5e_rx_hash_fn(priv->params.rss_hfunc)); + if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { + void *rss_key = MLX5_ADDR_OF(tirc, tirc, + rx_hash_toeplitz_key); + size_t len = MLX5_FLD_SZ_BYTES(tirc, + rx_hash_toeplitz_key); + + MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); + memcpy(rss_key, priv->params.toeplitz_hash_key, len); + } +} + +static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -1325,6 +1330,7 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) void *tirc; int inlen; int err; + int tt; inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = mlx5_vzalloc(inlen); @@ -1336,7 +1342,11 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) mlx5e_build_tir_ctx_lro(tirc, priv); - err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + for (tt = 0; tt < MLX5E_NUM_TT; tt++) { + err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + if (err) + break; + } kvfree(in); @@ -1672,17 +1682,7 @@ static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt) default: MLX5_SET(tirc, tirc, indirect_table, priv->rqtn[MLX5E_INDIRECTION_RQT]); - MLX5_SET(tirc, tirc, rx_hash_fn, - mlx5e_rx_hash_fn(priv->params.rss_hfunc)); - if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { - void *rss_key = MLX5_ADDR_OF(tirc, tirc, - rx_hash_toeplitz_key); - size_t len = MLX5_FLD_SZ_BYTES(tirc, - rx_hash_toeplitz_key); - - MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); - memcpy(rss_key, priv->params.toeplitz_hash_key, len); - } + mlx5e_build_tir_ctx_hash(tirc, priv); break; } @@ -1885,8 +1885,10 @@ static int mlx5e_set_features(struct net_device *netdev, mlx5e_close_locked(priv->netdev); priv->params.lro_en = !!(features & NETIF_F_LRO); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV4_TCP); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV6_TCP); + err = mlx5e_modify_tirs_lro(priv); + if (err) + mlx5_core_warn(priv->mdev, "lro modify failed, %d\n", + err); if (was_opened) err = mlx5e_open_locked(priv->netdev); @@ -2089,12 +2091,20 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev) 2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/; } +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels) +{ + int i; + + for (i = 0; i < len; i++) + indirection_rqt[i] = i % num_channels; +} + static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, struct net_device *netdev, int num_channels) { struct mlx5e_priv *priv = netdev_priv(netdev); - int i; priv->params.log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; @@ -2118,8 +2128,8 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, netdev_rss_key_fill(priv->params.toeplitz_hash_key, sizeof(priv->params.toeplitz_hash_key)); - for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) - priv->params.indirection_rqt[i] = i % num_channels; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, num_channels); priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index dd959d929aadd..59658b9d05d1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -230,10 +230,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); int work_done; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return 0; - for (work_done = 0; work_done < budget; work_done++) { struct mlx5e_rx_wqe *wqe; struct mlx5_cqe64 *cqe; @@ -267,6 +263,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) mlx5e_build_rx_skb(cqe, rq, skb); rq->stats.packets++; + rq->stats.bytes += be32_to_cpu(cqe->byte_cnt); napi_gro_receive(cq->napi, skb); wq_ll_pop: @@ -279,8 +276,5 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb(); - if (work_done == budget) - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2c3fba0fff546..bb4eeeb007dec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -179,6 +179,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) unsigned int skb_len = skb->len; u8 opcode = MLX5_OPCODE_SEND; dma_addr_t dma_addr = 0; + unsigned int num_bytes; bool bf = false; u16 headlen; u16 ds_cnt; @@ -204,8 +205,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) opcode = MLX5_OPCODE_LSO; ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); payload_len = skb->len - ihs; - wi->num_bytes = skb->len + - (skb_shinfo(skb)->gso_segs - 1) * ihs; + num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; sq->stats.tso_packets++; sq->stats.tso_bytes += payload_len; } else { @@ -213,9 +213,11 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) !skb->xmit_more && !skb_shinfo(skb)->nr_frags; ihs = mlx5e_get_inline_hdr_size(sq, skb, bf); - wi->num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); } + wi->num_bytes = num_bytes; + if (skb_vlan_tag_present(skb)) { mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs, &skb_data, &skb_len); @@ -307,6 +309,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->bf_budget = bf ? sq->bf_budget - 1 : 0; sq->stats.packets++; + sq->stats.bytes += num_bytes; return NETDEV_TX_OK; dma_unmap_wqe_err: @@ -335,10 +338,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) u16 sqcc; int i; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return false; - sq = container_of(cq, struct mlx5e_sq, cq); npkts = 0; @@ -422,10 +421,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) netif_tx_wake_queue(sq->txq); sq->stats.wake++; } - if (i == MLX5E_TX_CQ_POLL_BUDGET) { - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return true; - } - return false; + return (i == MLX5E_TX_CQ_POLL_BUDGET); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 4ac8d716dbddf..66d51a77609e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -88,7 +88,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq) { struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags); barrier(); napi_schedule(cq->napi); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c071077aafbdb..7992c553c1f5c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -215,7 +215,7 @@ mlxsw_pci_queue_elem_info_producer_get(struct mlxsw_pci_queue *q) { int index = q->producer_counter & (q->count - 1); - if ((q->producer_counter - q->consumer_counter) == q->count) + if ((u16) (q->producer_counter - q->consumer_counter) == q->count) return NULL; return mlxsw_pci_queue_elem_info_get(q, index); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 09ce451c283bb..a94daa8c346ca 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2358,9 +2358,7 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, if (mlxsw_sp_port->bridged) { mlxsw_sp_port_active_vlans_del(mlxsw_sp_port); mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false); - - if (lag->ref_count == 1) - mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); + mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); } if (lag->ref_count == 1) { diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 00cfd95ca59d5..3e67f451f2ab9 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -474,9 +474,9 @@ static int moxart_mac_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ndev->base_addr = res->start; priv->base = devm_ioremap_resource(p_dev, res); - ret = IS_ERR(priv->base); - if (ret) { + if (IS_ERR(priv->base)) { dev_err(p_dev, "devm_ioremap_resource failed\n"); + ret = PTR_ERR(priv->base); goto init_fail; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 689a4a5c8dcfc..1ef03939d25f4 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -811,7 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev) dev->netdev_ops = &qcaspi_netdev_ops; qcaspi_set_ethtool_ops(dev); dev->watchdog_timeo = QCASPI_TX_TIMEOUT; - dev->flags = IFF_MULTICAST; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->tx_queue_len = 100; qca = netdev_priv(dev); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 537974cfd4270..dd2cf3738b738 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4933,8 +4933,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_40: - RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: @@ -4943,8 +4941,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_47: case RTL_GIGA_MAC_VER_48: - RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: @@ -7730,10 +7726,13 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; + struct pci_dev *pdev = tp->pci_dev; struct rtl8169_counters *counters = tp->counters; unsigned int start; - if (netif_running(dev)) + pm_runtime_get_noresume(&pdev->dev); + + if (netif_running(dev) && pm_runtime_active(&pdev->dev)) rtl8169_rx_missed(dev, ioaddr); do { @@ -7761,7 +7760,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) * Fetch additonal counter values missing in stats collected by driver * from tally counters. */ - rtl8169_update_counters(dev); + if (pm_runtime_active(&pdev->dev)) + rtl8169_update_counters(dev); /* * Subtract values fetched during initalization. @@ -7774,6 +7774,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) - le16_to_cpu(tp->tc_offset.tx_aborted); + pm_runtime_put_noidle(&pdev->dev); + return stats; } @@ -7853,6 +7855,10 @@ static int rtl8169_runtime_suspend(struct device *device) rtl8169_net_suspend(dev); + /* Update counters before going runtime suspend */ + rtl8169_rx_missed(dev, tp->mmio_addr); + rtl8169_update_counters(dev); + return 0; } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 744d7806a9eec..86449c357168e 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1722,7 +1722,6 @@ static int ravb_set_gti(struct net_device *ndev) static int ravb_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - const struct of_device_id *match; struct ravb_private *priv; enum ravb_chip_id chip_id; struct net_device *ndev; @@ -1754,8 +1753,7 @@ static int ravb_probe(struct platform_device *pdev) ndev->base_addr = res->start; ndev->dma = -1; - match = of_match_device(of_match_ptr(ravb_match_table), &pdev->dev); - chip_id = (enum ravb_chip_id)match->data; + chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev); if (chip_id == RCAR_GEN3) irq = platform_get_irq_byname(pdev, "ch22"); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index dfa9e59c94428..7384499928761 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3061,15 +3061,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev) mdp->ether_link_active_low = pd->ether_link_active_low; /* set cpu data */ - if (id) { + if (id) mdp->cd = (struct sh_eth_cpu_data *)id->driver_data; - } else { - const struct of_device_id *match; + else + mdp->cd = (struct sh_eth_cpu_data *)of_device_get_match_data(&pdev->dev); - match = of_match_device(of_match_ptr(sh_eth_match_table), - &pdev->dev); - mdp->cd = (struct sh_eth_cpu_data *)match->data; - } mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type); if (!mdp->reg_offset) { dev_err(&pdev->dev, "Unknown register type (%d)\n", diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 0faf163360353..efb54f356a67c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -199,21 +199,12 @@ int stmmac_mdio_register(struct net_device *ndev) struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; int addr, found; - struct device_node *mdio_node = NULL; - struct device_node *child_node = NULL; + struct device_node *mdio_node = priv->plat->mdio_node; if (!mdio_bus_data) return 0; if (IS_ENABLED(CONFIG_OF)) { - for_each_child_of_node(priv->device->of_node, child_node) { - if (of_device_is_compatible(child_node, - "snps,dwmac-mdio")) { - mdio_node = child_node; - break; - } - } - if (mdio_node) { netdev_dbg(ndev, "FOUND MDIO subnode\n"); } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6a52fa18cbf2e..4514ba73d9611 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -110,6 +110,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + struct device_node *child_node = NULL; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -140,13 +141,19 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->phy_node = of_node_get(np); } + for_each_child_of_node(np, child_node) + if (of_device_is_compatible(child_node, "snps,dwmac-mdio")) { + plat->mdio_node = child_node; + break; + } + /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name) + if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node) plat->mdio_bus_data = NULL; else plat->mdio_bus_data = diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index fc8bbff2d7e37..af11ed1e0bcc0 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -426,7 +426,7 @@ #define DWC_MMC_RXOCTETCOUNT_GB 0x0784 #define DWC_MMC_RXPACKETCOUNT_GB 0x0780 -static int debug = 3; +static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "DWC_eth_qos debug level (0=none,...,16=all)"); @@ -650,6 +650,11 @@ struct net_local { u32 mmc_tx_counters_mask; struct dwceqos_flowcontrol flowcontrol; + + /* Tracks the intermediate state of phy started but hardware + * init not finished yet. + */ + bool phy_defer; }; static void dwceqos_read_mmc_counters(struct net_local *lp, u32 rx_mask, @@ -901,6 +906,9 @@ static void dwceqos_adjust_link(struct net_device *ndev) struct phy_device *phydev = lp->phy_dev; int status_change = 0; + if (lp->phy_defer) + return; + if (phydev->link) { if ((lp->speed != phydev->speed) || (lp->duplex != phydev->duplex)) { @@ -1113,7 +1121,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) /* Allocate DMA descriptors */ size = DWCEQOS_RX_DCNT * sizeof(struct dwceqos_dma_desc); lp->rx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->rx_descs_addr, 0); + &lp->rx_descs_addr, GFP_KERNEL); if (!lp->rx_descs) goto err_out; lp->rx_descs_tail_addr = lp->rx_descs_addr + @@ -1121,7 +1129,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) size = DWCEQOS_TX_DCNT * sizeof(struct dwceqos_dma_desc); lp->tx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->tx_descs_addr, 0); + &lp->tx_descs_addr, GFP_KERNEL); if (!lp->tx_descs) goto err_out; lp->tx_descs_tail_addr = lp->tx_descs_addr + @@ -1635,6 +1643,12 @@ static void dwceqos_init_hw(struct net_local *lp) regval = dwceqos_read(lp, REG_DWCEQOS_MAC_CFG); dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, regval | DWCEQOS_MAC_CFG_TE | DWCEQOS_MAC_CFG_RE); + + lp->phy_defer = false; + mutex_lock(&lp->phy_dev->lock); + phy_read_status(lp->phy_dev); + dwceqos_adjust_link(lp->ndev); + mutex_unlock(&lp->phy_dev->lock); } static void dwceqos_tx_reclaim(unsigned long data) @@ -1880,9 +1894,13 @@ static int dwceqos_open(struct net_device *ndev) } netdev_reset_queue(ndev); + /* The dwceqos reset state machine requires all phy clocks to complete, + * hence the unusual init order with phy_start first. + */ + lp->phy_defer = true; + phy_start(lp->phy_dev); dwceqos_init_hw(lp); napi_enable(&lp->napi); - phy_start(lp->phy_dev); netif_start_queue(ndev); tasklet_enable(&lp->tx_bdreclaim_tasklet); @@ -1915,18 +1933,19 @@ static int dwceqos_stop(struct net_device *ndev) { struct net_local *lp = netdev_priv(ndev); - phy_stop(lp->phy_dev); - tasklet_disable(&lp->tx_bdreclaim_tasklet); - netif_stop_queue(ndev); napi_disable(&lp->napi); - dwceqos_drain_dma(lp); + /* Stop all tx before we drain the tx dma. */ + netif_tx_lock_bh(lp->ndev); + netif_stop_queue(ndev); + netif_tx_unlock_bh(lp->ndev); - netif_tx_lock(lp->ndev); + dwceqos_drain_dma(lp); dwceqos_reset_hw(lp); + phy_stop(lp->phy_dev); + dwceqos_descriptor_free(lp); - netif_tx_unlock(lp->ndev); return 0; } @@ -2178,12 +2197,10 @@ static int dwceqos_start_xmit(struct sk_buff *skb, struct net_device *ndev) ((trans.initial_descriptor + trans.nr_descriptors) % DWCEQOS_TX_DCNT)); - dwceqos_tx_finalize(skb, lp, &trans); - - netdev_sent_queue(ndev, skb->len); - spin_lock_bh(&lp->tx_lock); lp->tx_free -= trans.nr_descriptors; + dwceqos_tx_finalize(skb, lp, &trans); + netdev_sent_queue(ndev, skb->len); spin_unlock_bh(&lp->tx_lock); ndev->trans_start = jiffies; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 03833dbfca67d..dc85f7095e510 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -297,6 +297,17 @@ static int kszphy_config_init(struct phy_device *phydev) if (priv->led_mode >= 0) kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode); + if (phy_interrupt_is_valid(phydev)) { + int ctl = phy_read(phydev, MII_BMCR); + + if (ctl < 0) + return ctl; + + ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE); + if (ret < 0) + return ret; + } + return 0; } @@ -635,6 +646,21 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } +static int kszphy_resume(struct phy_device *phydev) +{ + int value; + + mutex_lock(&phydev->lock); + + value = phy_read(phydev, MII_BMCR); + phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN); + + kszphy_config_intr(phydev); + mutex_unlock(&phydev->lock); + + return 0; +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -844,7 +870,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8061, .name = "Micrel KSZ8061", diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index fc8ad001bc949..d61da9ece3ba0 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -443,9 +443,14 @@ static ssize_t ppp_read(struct file *file, char __user *buf, * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && - (ppp->flags & SC_LOOP_TRAFFIC) == 0) + (ppp->flags & SC_LOOP_TRAFFIC) == 0) { + ppp_recv_unlock(ppp); break; + } + ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) @@ -532,9 +537,12 @@ static unsigned int ppp_poll(struct file *file, poll_table *wait) else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= POLLIN | POLLRDNORM; + ppp_recv_unlock(ppp); } return mask; @@ -2808,6 +2816,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, out2: mutex_unlock(&pn->all_ppp_mutex); + rtnl_unlock(); free_netdev(dev); out1: *retp = ret; diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 224e7d82de6d2..cf77f2dffa698 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -134,7 +134,6 @@ static void ax88172a_remove_mdio(struct usbnet *dev) netdev_info(dev->net, "deregistering mdio bus %s\n", priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index dc0212c3cc28c..86ba30ba35e8f 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -837,7 +837,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; - /* reset data interface */ + /* Reset data interface. Some devices will not reset properly + * unless they are configured first. Toggle the altsetting to + * force a reset + */ + usb_set_interface(dev->udev, iface_no, data_altsetting); temp = usb_set_interface(dev->udev, iface_no, 0); if (temp) { dev_dbg(&intf->dev, "set interface failed\n"); @@ -984,8 +988,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting); static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) { - int ret; - /* MBIM backwards compatible function? */ if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM) return -ENODEV; @@ -994,16 +996,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) * Additionally, generic NCM devices are assumed to accept arbitrarily * placed NDP. */ - ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); - - /* - * We should get an event when network connection is "connected" or - * "disconnected". Set network connection in "disconnected" state - * (carrier is OFF) during attach, so the IP network stack does not - * start IPv6 negotiation and more. - */ - usbnet_link_change(dev, 0, 0); - return ret; + return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); } static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max) @@ -1586,7 +1579,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) static const struct driver_info cdc_ncm_info = { .description = "CDC NCM", - .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET, + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_LINK_INTR, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1599,7 +1593,7 @@ static const struct driver_info cdc_ncm_info = { static const struct driver_info wwan_info = { .description = "Mobile Broadband Network Device", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN, + | FLAG_LINK_INTR | FLAG_WWAN, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1612,7 +1606,7 @@ static const struct driver_info wwan_info = { static const struct driver_info wwan_noarp_info = { .description = "Mobile Broadband Network Device (NO ARP)", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN | FLAG_NOARP, + | FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 570deef53f743..a3a4ccf7cf527 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -861,8 +861,10 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx/EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ @@ -885,6 +887,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ {QMI_FIXED_INTF(0x1e0e, 0x9001, 5)}, /* SIMCom 7230E */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 0b0ba7ef14e4e..10798128c03fc 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1769,6 +1769,13 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if (info->unbind) info->unbind (dev, udev); out1: + /* subdrivers must undo all they did in bind() if they + * fail it, but we may fail later and a deferred kevent + * may trigger an error resubmitting itself and, worse, + * schedule a timer. So we kill it all just in case. + */ + cancel_work_sync(&dev->kevent); + del_timer_sync(&dev->delay); free_netdev(net); out: return status; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 0cbf520cea778..fc895d0e85d9c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -814,7 +814,7 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) /* - * parse and copy relevant protocol headers: + * parse relevant protocol headers: * For a tso pkt, relevant headers are L2/3/4 including options * For a pkt requesting csum offloading, they are L2/3 and may include L4 * if it's a TCP/UDP pkt @@ -827,15 +827,14 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) * Other effects: * 1. related *ctx fields are updated. * 2. ctx->copy_size is # of bytes copied - * 3. the portion copied is guaranteed to be in the linear part + * 3. the portion to be copied is guaranteed to be in the linear part * */ static int -vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, - struct vmxnet3_tx_ctx *ctx, - struct vmxnet3_adapter *adapter) +vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) { - struct Vmxnet3_TxDataDesc *tdd; u8 protocol = 0; if (ctx->mss) { /* TSO */ @@ -892,16 +891,34 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, return 0; } + return 1; +err: + return -1; +} + +/* + * copy relevant protocol headers to the transmit ring: + * For a tso pkt, relevant headers are L2/3/4 including options + * For a pkt requesting csum offloading, they are L2/3 and may include L4 + * if it's a TCP/UDP pkt + * + * + * Note that this requires that vmxnet3_parse_hdr be called first to set the + * appropriate bits in ctx first + */ +static void +vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_TxDataDesc *tdd; + tdd = tq->data_ring.base + tq->tx_ring.next2fill; memcpy(tdd->data, skb->data, ctx->copy_size); netdev_dbg(adapter->netdev, "copy %u bytes to dataRing[%u]\n", ctx->copy_size, tq->tx_ring.next2fill); - return 1; - -err: - return -1; } @@ -998,22 +1015,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } - spin_lock_irqsave(&tq->tx_lock, flags); - - if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { - tq->stats.tx_ring_full++; - netdev_dbg(adapter->netdev, - "tx queue stopped on %s, next2comp %u" - " next2fill %u\n", adapter->netdev->name, - tq->tx_ring.next2comp, tq->tx_ring.next2fill); - - vmxnet3_tq_stop(tq, adapter); - spin_unlock_irqrestore(&tq->tx_lock, flags); - return NETDEV_TX_BUSY; - } - - - ret = vmxnet3_parse_and_copy_hdr(skb, tq, &ctx, adapter); + ret = vmxnet3_parse_hdr(skb, tq, &ctx, adapter); if (ret >= 0) { BUG_ON(ret <= 0 && ctx.copy_size != 0); /* hdrs parsed, check against other limits */ @@ -1033,9 +1035,26 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } else { tq->stats.drop_hdr_inspect_err++; - goto unlock_drop_pkt; + goto drop_pkt; } + spin_lock_irqsave(&tq->tx_lock, flags); + + if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { + tq->stats.tx_ring_full++; + netdev_dbg(adapter->netdev, + "tx queue stopped on %s, next2comp %u" + " next2fill %u\n", adapter->netdev->name, + tq->tx_ring.next2comp, tq->tx_ring.next2fill); + + vmxnet3_tq_stop(tq, adapter); + spin_unlock_irqrestore(&tq->tx_lock, flags); + return NETDEV_TX_BUSY; + } + + + vmxnet3_copy_hdr(skb, tq, &ctx, adapter); + /* fill tx descs related to addr & len */ if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter)) goto unlock_drop_pkt; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 66addb7a7911b..bdcf617a9d52b 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -104,20 +104,23 @@ static struct dst_ops vrf_dst_ops = { #if IS_ENABLED(CONFIG_IPV6) static bool check_ipv6_frame(const struct sk_buff *skb) { - const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data; - size_t hlen = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h; + struct ipv6hdr _ipv6h; bool rc = true; - if (skb->len < hlen) + ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h); + if (!ipv6h) goto out; if (ipv6h->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; + struct icmp6hdr _icmph; - if (skb->len < hlen + sizeof(*icmph)) + icmph = skb_header_pointer(skb, sizeof(_ipv6h), + sizeof(_icmph), &_icmph); + if (!icmph) goto out; - icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h)); switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e6944b29588e1..1c32bd1047973 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -931,8 +931,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + cb->args[1] = err; goto out; + } skip: ++idx; } @@ -1306,8 +1308,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) gbp = (struct vxlanhdr_gbp *)vxh; md->gbp = ntohs(gbp->policy_id); - if (tun_dst) + if (tun_dst) { tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; + tun_dst->u.tun_info.options_len = sizeof(*md); + } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 4ed5180c547bb..0ccc697fef76c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -107,7 +107,7 @@ static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant) sizeof(tx_ant_cmd), &tx_ant_cmd); } -static void iwl_free_fw_paging(struct iwl_mvm *mvm) +void iwl_free_fw_paging(struct iwl_mvm *mvm) { int i; @@ -127,6 +127,8 @@ static void iwl_free_fw_paging(struct iwl_mvm *mvm) get_order(mvm->fw_paging_db[i].fw_paging_size)); } kfree(mvm->trans->paging_download_buf); + mvm->trans->paging_download_buf = NULL; + memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db)); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 5f3ac8cccf49d..ff7c6df9f9418 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1225,6 +1225,9 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm, void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); +/* Paging */ +void iwl_free_fw_paging(struct iwl_mvm *mvm); + /* MVM debugfs */ #ifdef CONFIG_IWLWIFI_DEBUGFS int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 89ea70deeb844..e80be9a595207 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -684,6 +684,8 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode) for (i = 0; i < NVM_MAX_NUM_SECTIONS; i++) kfree(mvm->nvm_sections[i].data); + iwl_free_fw_paging(mvm); + iwl_mvm_tof_clean(mvm); ieee80211_free_hw(mvm->hw); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 0914ec2fd5746..a040edc550570 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -423,6 +423,15 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) return -1; } + /* + * Increase the pending frames counter, so that later when a reply comes + * in and the counter is decreased - we don't start getting negative + * values. + * Note that we don't need to make sure it isn't agg'd, since we're + * TXing non-sta + */ + atomic_inc(&mvm->pending_frames[sta_id]); + return 0; } diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c index b0045a505dc88..95825b38559ad 100644 --- a/drivers/nvdimm/e820.c +++ b/drivers/nvdimm/e820.c @@ -55,7 +55,7 @@ static int e820_pmem_probe(struct platform_device *pdev) for (p = iomem_resource.child; p ; p = p->sibling) { struct nd_region_desc ndr_desc; - if (strncmp(p->name, "Persistent Memory (legacy)", 26) != 0) + if (p->desc != IORES_DESC_PERSISTENT_MEMORY_LEGACY) continue; memset(&ndr_desc, 0, sizeof(ndr_desc)); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3cd921e6121ec..03c46412fff4d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -55,8 +55,9 @@ static void nvme_free_ns(struct kref *kref) ns->disk->private_data = NULL; spin_unlock(&dev_list_lock); - nvme_put_ctrl(ns->ctrl); put_disk(ns->disk); + ida_simple_remove(&ns->ctrl->ns_ida, ns->instance); + nvme_put_ctrl(ns->ctrl); kfree(ns); } @@ -183,7 +184,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, goto out_unmap; } - if (meta_buffer) { + if (meta_buffer && meta_len) { struct bio_integrity_payload *bip; meta = kmalloc(meta_len, GFP_KERNEL); @@ -373,6 +374,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) if (copy_from_user(&io, uio, sizeof(io))) return -EFAULT; + if (io.flags) + return -EINVAL; switch (io.opcode) { case nvme_cmd_write: @@ -424,6 +427,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return -EACCES; if (copy_from_user(&cmd, ucmd, sizeof(cmd))) return -EFAULT; + if (cmd.flags) + return -EINVAL; memset(&c, 0, sizeof(c)); c.common.opcode = cmd.opcode; @@ -556,6 +561,10 @@ static int nvme_revalidate_disk(struct gendisk *disk) u16 old_ms; unsigned short bs; + if (test_bit(NVME_NS_DEAD, &ns->flags)) { + set_capacity(disk, 0); + return -ENODEV; + } if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) { dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n", __func__, ns->ctrl->instance, ns->ns_id); @@ -831,6 +840,23 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) return ret; } +static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, + struct request_queue *q) +{ + if (ctrl->max_hw_sectors) { + u32 max_segments = + (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1; + + blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); + blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); + } + if (ctrl->stripe_size) + blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9); + if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) + blk_queue_flush(q, REQ_FLUSH | REQ_FUA); + blk_queue_virt_boundary(q, ctrl->page_size - 1); +} + /* * Initialize the cached copies of the Identify data and various controller * register in our nvme_ctrl structure. This should be called as soon as @@ -888,6 +914,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) } } + nvme_set_queue_limits(ctrl, ctrl->admin_q); + kfree(id); return 0; } @@ -1118,9 +1146,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (!ns) return; + ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL); + if (ns->instance < 0) + goto out_free_ns; + ns->queue = blk_mq_init_queue(ctrl->tagset); if (IS_ERR(ns->queue)) - goto out_free_ns; + goto out_release_instance; queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue); ns->queue->queuedata = ns; ns->ctrl = ctrl; @@ -1134,17 +1166,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->disk = disk; ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */ + blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); - if (ctrl->max_hw_sectors) { - blk_queue_max_hw_sectors(ns->queue, ctrl->max_hw_sectors); - blk_queue_max_segments(ns->queue, - (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1); - } - if (ctrl->stripe_size) - blk_queue_chunk_sectors(ns->queue, ctrl->stripe_size >> 9); - if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) - blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA); - blk_queue_virt_boundary(ns->queue, ctrl->page_size - 1); + nvme_set_queue_limits(ctrl, ns->queue); disk->major = nvme_major; disk->first_minor = 0; @@ -1153,7 +1177,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) disk->queue = ns->queue; disk->driverfs_dev = ctrl->device; disk->flags = GENHD_FL_EXT_DEVT; - sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, nsid); + sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance); if (nvme_revalidate_disk(ns->disk)) goto out_free_disk; @@ -1173,40 +1197,29 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) kfree(disk); out_free_queue: blk_cleanup_queue(ns->queue); + out_release_instance: + ida_simple_remove(&ctrl->ns_ida, ns->instance); out_free_ns: kfree(ns); } static void nvme_ns_remove(struct nvme_ns *ns) { - bool kill = nvme_io_incapable(ns->ctrl) && - !blk_queue_dying(ns->queue); - - lockdep_assert_held(&ns->ctrl->namespaces_mutex); - - if (kill) { - blk_set_queue_dying(ns->queue); + if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) + return; - /* - * The controller was shutdown first if we got here through - * device removal. The shutdown may requeue outstanding - * requests. These need to be aborted immediately so - * del_gendisk doesn't block indefinitely for their completion. - */ - blk_mq_abort_requeue_list(ns->queue); - } if (ns->disk->flags & GENHD_FL_UP) { if (blk_get_integrity(ns->disk)) blk_integrity_unregister(ns->disk); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_attr_group); del_gendisk(ns->disk); - } - if (kill || !blk_queue_dying(ns->queue)) { blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); } + mutex_lock(&ns->ctrl->namespaces_mutex); list_del_init(&ns->list); + mutex_unlock(&ns->ctrl->namespaces_mutex); nvme_put_ns(ns); } @@ -1300,10 +1313,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) { struct nvme_ns *ns, *next; - mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) nvme_ns_remove(ns); - mutex_unlock(&ctrl->namespaces_mutex); } static DEFINE_IDA(nvme_instance_ida); @@ -1350,6 +1361,7 @@ static void nvme_free_ctrl(struct kref *kref) put_device(ctrl->device); nvme_release_instance(ctrl); + ida_destroy(&ctrl->ns_ida); ctrl->ops->free_ctrl(ctrl); } @@ -1390,6 +1402,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, } get_device(ctrl->device); dev_set_drvdata(ctrl->device, ctrl); + ida_init(&ctrl->ns_ida); spin_lock(&dev_list_lock); list_add_tail(&ctrl->node, &nvme_ctrl_list); @@ -1402,6 +1415,38 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return ret; } +/** + * nvme_kill_queues(): Ends all namespace queues + * @ctrl: the dead controller that needs to end + * + * Call this function when the driver determines it is unable to get the + * controller in a state capable of servicing IO. + */ +void nvme_kill_queues(struct nvme_ctrl *ctrl) +{ + struct nvme_ns *ns; + + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { + if (!kref_get_unless_zero(&ns->kref)) + continue; + + /* + * Revalidating a dead namespace sets capacity to 0. This will + * end buffered writers dirtying pages that can't be synced. + */ + if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + revalidate_disk(ns->disk); + + blk_set_queue_dying(ns->queue); + blk_mq_abort_requeue_list(ns->queue); + blk_mq_start_stopped_hw_queues(ns->queue, true); + + nvme_put_ns(ns); + } + mutex_unlock(&ctrl->namespaces_mutex); +} + void nvme_stop_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9664d07d807d8..fb15ba5f5d19f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -72,6 +72,7 @@ struct nvme_ctrl { struct mutex namespaces_mutex; struct device *device; /* char device */ struct list_head node; + struct ida ns_ida; char name[12]; char serial[20]; @@ -102,6 +103,7 @@ struct nvme_ns { struct request_queue *queue; struct gendisk *disk; struct kref kref; + int instance; u8 eui[8]; u8 uuid[16]; @@ -112,6 +114,11 @@ struct nvme_ns { bool ext; u8 pi_type; int type; + unsigned long flags; + +#define NVME_NS_REMOVING 0 +#define NVME_NS_DEAD 1 + u64 mode_select_num_blocks; u32 mode_select_block_len; }; @@ -240,6 +247,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl); void nvme_stop_queues(struct nvme_ctrl *ctrl); void nvme_start_queues(struct nvme_ctrl *ctrl); +void nvme_kill_queues(struct nvme_ctrl *ctrl); struct request *nvme_alloc_request(struct request_queue *q, struct nvme_command *cmd, unsigned int flags); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a128672472ecf..680f5780750cf 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -86,7 +86,6 @@ struct nvme_queue; static int nvme_reset(struct nvme_dev *dev); static void nvme_process_cq(struct nvme_queue *nvmeq); -static void nvme_remove_dead_ctrl(struct nvme_dev *dev); static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); /* @@ -120,6 +119,7 @@ struct nvme_dev { unsigned long flags; #define NVME_CTRL_RESETTING 0 +#define NVME_CTRL_REMOVING 1 struct nvme_ctrl ctrl; struct completion ioq_wait; @@ -286,6 +286,17 @@ static int nvme_init_request(void *data, struct request *req, return 0; } +static void nvme_queue_scan(struct nvme_dev *dev) +{ + /* + * Do not queue new scan work when a controller is reset during + * removal. + */ + if (test_bit(NVME_CTRL_REMOVING, &dev->flags)) + return; + queue_work(nvme_workq, &dev->scan_work); +} + static void nvme_complete_async_event(struct nvme_dev *dev, struct nvme_completion *cqe) { @@ -300,7 +311,7 @@ static void nvme_complete_async_event(struct nvme_dev *dev, switch (result & 0xff07) { case NVME_AER_NOTICE_NS_CHANGED: dev_info(dev->dev, "rescanning\n"); - queue_work(nvme_workq, &dev->scan_work); + nvme_queue_scan(dev); default: dev_warn(dev->dev, "async event result %08x\n", result); } @@ -679,7 +690,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, spin_lock_irq(&nvmeq->q_lock); if (unlikely(nvmeq->cq_vector < 0)) { - ret = BLK_MQ_RQ_QUEUE_BUSY; + if (ns && !test_bit(NVME_NS_DEAD, &ns->flags)) + ret = BLK_MQ_RQ_QUEUE_BUSY; + else + ret = BLK_MQ_RQ_QUEUE_ERROR; spin_unlock_irq(&nvmeq->q_lock); goto out; } @@ -1250,6 +1264,12 @@ static struct blk_mq_ops nvme_mq_ops = { static void nvme_dev_remove_admin(struct nvme_dev *dev) { if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) { + /* + * If the controller was reset during removal, it's possible + * user requests may be waiting on a stopped queue. Start the + * queue to flush these to completion. + */ + blk_mq_start_stopped_hw_queues(dev->ctrl.admin_q, true); blk_cleanup_queue(dev->ctrl.admin_q); blk_mq_free_tag_set(&dev->admin_tagset); } @@ -1690,14 +1710,14 @@ static int nvme_dev_add(struct nvme_dev *dev) return 0; dev->ctrl.tagset = &dev->tagset; } - queue_work(nvme_workq, &dev->scan_work); + nvme_queue_scan(dev); return 0; } -static int nvme_dev_map(struct nvme_dev *dev) +static int nvme_pci_enable(struct nvme_dev *dev) { u64 cap; - int bars, result = -ENOMEM; + int result = -ENOMEM; struct pci_dev *pdev = to_pci_dev(dev->dev); if (pci_enable_device_mem(pdev)) @@ -1705,24 +1725,14 @@ static int nvme_dev_map(struct nvme_dev *dev) dev->entry[0].vector = pdev->irq; pci_set_master(pdev); - bars = pci_select_bars(pdev, IORESOURCE_MEM); - if (!bars) - goto disable_pci; - - if (pci_request_selected_regions(pdev, bars, "nvme")) - goto disable_pci; if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) && dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32))) goto disable; - dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); - if (!dev->bar) - goto disable; - if (readl(dev->bar + NVME_REG_CSTS) == -1) { result = -ENODEV; - goto unmap; + goto disable; } /* @@ -1732,7 +1742,7 @@ static int nvme_dev_map(struct nvme_dev *dev) if (!pdev->irq) { result = pci_enable_msix(pdev, dev->entry, 1); if (result < 0) - goto unmap; + goto disable; } cap = lo_hi_readq(dev->bar + NVME_REG_CAP); @@ -1759,17 +1769,19 @@ static int nvme_dev_map(struct nvme_dev *dev) pci_save_state(pdev); return 0; - unmap: - iounmap(dev->bar); - dev->bar = NULL; disable: - pci_release_regions(pdev); - disable_pci: pci_disable_device(pdev); return result; } static void nvme_dev_unmap(struct nvme_dev *dev) +{ + if (dev->bar) + iounmap(dev->bar); + pci_release_regions(to_pci_dev(dev->dev)); +} + +static void nvme_pci_disable(struct nvme_dev *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); @@ -1778,12 +1790,6 @@ static void nvme_dev_unmap(struct nvme_dev *dev) else if (pdev->msix_enabled) pci_disable_msix(pdev); - if (dev->bar) { - iounmap(dev->bar); - dev->bar = NULL; - pci_release_regions(pdev); - } - if (pci_is_enabled(pdev)) { pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); @@ -1842,7 +1848,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_dev_list_remove(dev); mutex_lock(&dev->shutdown_lock); - if (dev->bar) { + if (pci_is_enabled(to_pci_dev(dev->dev))) { nvme_stop_queues(&dev->ctrl); csts = readl(dev->bar + NVME_REG_CSTS); } @@ -1855,7 +1861,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); } - nvme_dev_unmap(dev); + nvme_pci_disable(dev); for (i = dev->queue_count - 1; i >= 0; i--) nvme_clear_queue(dev->queues[i]); @@ -1899,10 +1905,20 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) kfree(dev); } +static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) +{ + dev_warn(dev->dev, "Removing after probe failure status: %d\n", status); + + kref_get(&dev->ctrl.kref); + nvme_dev_disable(dev, false); + if (!schedule_work(&dev->remove_work)) + nvme_put_ctrl(&dev->ctrl); +} + static void nvme_reset_work(struct work_struct *work) { struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work); - int result; + int result = -ENODEV; if (WARN_ON(test_bit(NVME_CTRL_RESETTING, &dev->flags))) goto out; @@ -1911,37 +1927,37 @@ static void nvme_reset_work(struct work_struct *work) * If we're called to reset a live controller first shut it down before * moving on. */ - if (dev->bar) + if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); set_bit(NVME_CTRL_RESETTING, &dev->flags); - result = nvme_dev_map(dev); + result = nvme_pci_enable(dev); if (result) goto out; result = nvme_configure_admin_queue(dev); if (result) - goto unmap; + goto out; nvme_init_queue(dev->queues[0], 0); result = nvme_alloc_admin_tags(dev); if (result) - goto disable; + goto out; result = nvme_init_identify(&dev->ctrl); if (result) - goto free_tags; + goto out; result = nvme_setup_io_queues(dev); if (result) - goto free_tags; + goto out; dev->ctrl.event_limit = NVME_NR_AEN_COMMANDS; result = nvme_dev_list_add(dev); if (result) - goto remove; + goto out; /* * Keep the controller around but remove all namespaces if we don't have @@ -1958,19 +1974,8 @@ static void nvme_reset_work(struct work_struct *work) clear_bit(NVME_CTRL_RESETTING, &dev->flags); return; - remove: - nvme_dev_list_remove(dev); - free_tags: - nvme_dev_remove_admin(dev); - blk_put_queue(dev->ctrl.admin_q); - dev->ctrl.admin_q = NULL; - dev->queues[0]->tags = NULL; - disable: - nvme_disable_admin_queue(dev, false); - unmap: - nvme_dev_unmap(dev); out: - nvme_remove_dead_ctrl(dev); + nvme_remove_dead_ctrl(dev, result); } static void nvme_remove_dead_ctrl_work(struct work_struct *work) @@ -1978,19 +1983,12 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work) struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work); struct pci_dev *pdev = to_pci_dev(dev->dev); + nvme_kill_queues(&dev->ctrl); if (pci_get_drvdata(pdev)) pci_stop_and_remove_bus_device_locked(pdev); nvme_put_ctrl(&dev->ctrl); } -static void nvme_remove_dead_ctrl(struct nvme_dev *dev) -{ - dev_warn(dev->dev, "Removing after probe failure\n"); - kref_get(&dev->ctrl.kref); - if (!schedule_work(&dev->remove_work)) - nvme_put_ctrl(&dev->ctrl); -} - static int nvme_reset(struct nvme_dev *dev) { if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q)) @@ -2042,6 +2040,27 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = { .free_ctrl = nvme_pci_free_ctrl, }; +static int nvme_dev_map(struct nvme_dev *dev) +{ + int bars; + struct pci_dev *pdev = to_pci_dev(dev->dev); + + bars = pci_select_bars(pdev, IORESOURCE_MEM); + if (!bars) + return -ENODEV; + if (pci_request_selected_regions(pdev, bars, "nvme")) + return -ENODEV; + + dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); + if (!dev->bar) + goto release; + + return 0; + release: + pci_release_regions(pdev); + return -ENODEV; +} + static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int node, result = -ENOMEM; @@ -2066,6 +2085,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev->dev = get_device(&pdev->dev); pci_set_drvdata(pdev, dev); + result = nvme_dev_map(dev); + if (result) + goto free; + INIT_LIST_HEAD(&dev->node); INIT_WORK(&dev->scan_work, nvme_dev_scan); INIT_WORK(&dev->reset_work, nvme_reset_work); @@ -2089,6 +2112,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) nvme_release_prp_pools(dev); put_pci: put_device(dev->dev); + nvme_dev_unmap(dev); free: kfree(dev->queues); kfree(dev->entry); @@ -2112,10 +2136,16 @@ static void nvme_shutdown(struct pci_dev *pdev) nvme_dev_disable(dev, true); } +/* + * The driver's remove may be called on a device in a partially initialized + * state. This function must not have any dependencies on the device state in + * order to proceed. + */ static void nvme_remove(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); + set_bit(NVME_CTRL_REMOVING, &dev->flags); pci_set_drvdata(pdev, NULL); flush_work(&dev->scan_work); nvme_remove_namespaces(&dev->ctrl); @@ -2126,6 +2156,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_free_queues(dev, 0); nvme_release_cmb(dev); nvme_release_prp_pools(dev); + nvme_dev_unmap(dev); nvme_put_ctrl(&dev->ctrl); } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 39c4be41ef83d..365dc7e83ab43 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -305,6 +305,7 @@ EXPORT_SYMBOL(of_phy_find_device); * @dev: pointer to net_device claiming the phy * @phy_np: Pointer to device tree node for the PHY * @hndlr: Link state callback for the network device + * @flags: flags to pass to the PHY * @iface: PHY data interface type * * If successful, returns a pointer to the phy_device with the embedded diff --git a/drivers/parisc/eisa_enumerator.c b/drivers/parisc/eisa_enumerator.c index a656d9e833430..21905fef2cbf0 100644 --- a/drivers/parisc/eisa_enumerator.c +++ b/drivers/parisc/eisa_enumerator.c @@ -91,7 +91,7 @@ static int configure_memory(const unsigned char *buf, for (i=0;iname = name; @@ -183,7 +183,7 @@ static int configure_port(const unsigned char *buf, struct resource *io_parent, for (i=0;iname = board; res->start = get_16(buf+len+1); res->end = get_16(buf+len+1)+(c&HPEE_PORT_SIZE_MASK)+1; diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c index ed34c9520a029..6153853ca9c31 100644 --- a/drivers/pci/host/pci-keystone-dw.c +++ b/drivers/pci/host/pci-keystone-dw.c @@ -58,11 +58,6 @@ #define to_keystone_pcie(x) container_of(x, struct keystone_pcie, pp) -static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys) -{ - return sys->private_data; -} - static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset, u32 *bit_pos) { @@ -108,7 +103,7 @@ static void ks_dw_pcie_msi_irq_ack(struct irq_data *d) struct pcie_port *pp; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); update_reg_offset_bit_pos(offset, ®_offset, &bit_pos); @@ -146,7 +141,7 @@ static void ks_dw_pcie_msi_irq_mask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); @@ -167,7 +162,7 @@ static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c index 3923bed93c7e0..f39961bcf7aad 100644 --- a/drivers/pci/host/pci-layerscape.c +++ b/drivers/pci/host/pci-layerscape.c @@ -77,6 +77,16 @@ static void ls_pcie_fix_class(struct ls_pcie *pcie) iowrite16(PCI_CLASS_BRIDGE_PCI, pcie->dbi + PCI_CLASS_DEVICE); } +/* Drop MSG TLP except for Vendor MSG */ +static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie) +{ + u32 val; + + val = ioread32(pcie->dbi + PCIE_STRFMR1); + val &= 0xDFFFFFFF; + iowrite32(val, pcie->dbi + PCIE_STRFMR1); +} + static int ls1021_pcie_link_up(struct pcie_port *pp) { u32 state; @@ -97,7 +107,7 @@ static int ls1021_pcie_link_up(struct pcie_port *pp) static void ls1021_pcie_host_init(struct pcie_port *pp) { struct ls_pcie *pcie = to_ls_pcie(pp); - u32 val, index[2]; + u32 index[2]; pcie->scfg = syscon_regmap_lookup_by_phandle(pp->dev->of_node, "fsl,pcie-scfg"); @@ -116,13 +126,7 @@ static void ls1021_pcie_host_init(struct pcie_port *pp) dw_pcie_setup_rc(pp); - /* - * LS1021A Workaround for internal TKT228622 - * to fix the INTx hang issue - */ - val = ioread32(pcie->dbi + PCIE_STRFMR1); - val &= 0xffff; - iowrite32(val, pcie->dbi + PCIE_STRFMR1); + ls_pcie_drop_msg_tlp(pcie); } static int ls_pcie_link_up(struct pcie_port *pp) @@ -147,6 +151,7 @@ static void ls_pcie_host_init(struct pcie_port *pp) iowrite32(1, pcie->dbi + PCIE_DBI_RO_WR_EN); ls_pcie_fix_class(pcie); ls_pcie_clear_multifunction(pcie); + ls_pcie_drop_msg_tlp(pcie); iowrite32(0, pcie->dbi + PCIE_DBI_RO_WR_EN); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 602eb42235106..f89db3af06072 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4772,8 +4772,10 @@ int pci_get_new_domain_nr(void) void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent) { static int use_dt_domains = -1; - int domain = of_get_pci_domain_nr(parent->of_node); + int domain = -1; + if (parent) + domain = of_get_pci_domain_nr(parent->of_node); /* * Check DT domain and use_dt_domains values. * diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index da7bae9915523..579fd65299a0c 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "ptp_private.h" @@ -120,11 +121,13 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) struct ptp_clock_caps caps; struct ptp_clock_request req; struct ptp_sys_offset *sysoff = NULL; + struct ptp_sys_offset_precise precise_offset; struct ptp_pin_desc pd; struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); struct ptp_clock_info *ops = ptp->info; struct ptp_clock_time *pct; struct timespec64 ts; + struct system_device_crosststamp xtstamp; int enable, err = 0; unsigned int i, pin_index; @@ -138,6 +141,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) caps.n_per_out = ptp->info->n_per_out; caps.pps = ptp->info->pps; caps.n_pins = ptp->info->n_pins; + caps.cross_timestamping = ptp->info->getcrosststamp != NULL; if (copy_to_user((void __user *)arg, &caps, sizeof(caps))) err = -EFAULT; break; @@ -180,6 +184,29 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) err = ops->enable(ops, &req, enable); break; + case PTP_SYS_OFFSET_PRECISE: + if (!ptp->info->getcrosststamp) { + err = -EOPNOTSUPP; + break; + } + err = ptp->info->getcrosststamp(ptp->info, &xtstamp); + if (err) + break; + + ts = ktime_to_timespec64(xtstamp.device); + precise_offset.device.sec = ts.tv_sec; + precise_offset.device.nsec = ts.tv_nsec; + ts = ktime_to_timespec64(xtstamp.sys_realtime); + precise_offset.sys_realtime.sec = ts.tv_sec; + precise_offset.sys_realtime.nsec = ts.tv_nsec; + ts = ktime_to_timespec64(xtstamp.sys_monoraw); + precise_offset.sys_monoraw.sec = ts.tv_sec; + precise_offset.sys_monoraw.nsec = ts.tv_nsec; + if (copy_to_user((void __user *)arg, &precise_offset, + sizeof(precise_offset))) + err = -EFAULT; + break; + case PTP_SYS_OFFSET: sysoff = kmalloc(sizeof(*sysoff), GFP_KERNEL); if (!sysoff) { diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c index d7b87c64b7cd2..e220edc85c68a 100644 --- a/drivers/rapidio/rio.c +++ b/drivers/rapidio/rio.c @@ -117,7 +117,7 @@ int rio_request_inb_mbox(struct rio_mport *mport, if (mport->ops->open_inb_mbox == NULL) goto out; - res = kmalloc(sizeof(struct resource), GFP_KERNEL); + res = kzalloc(sizeof(struct resource), GFP_KERNEL); if (res) { rio_init_mbox_res(res, mbox, mbox); @@ -185,7 +185,7 @@ int rio_request_outb_mbox(struct rio_mport *mport, if (mport->ops->open_outb_mbox == NULL) goto out; - res = kmalloc(sizeof(struct resource), GFP_KERNEL); + res = kzalloc(sizeof(struct resource), GFP_KERNEL); if (res) { rio_init_mbox_res(res, mbox, mbox); @@ -285,7 +285,7 @@ int rio_request_inb_dbell(struct rio_mport *mport, { int rc = 0; - struct resource *res = kmalloc(sizeof(struct resource), GFP_KERNEL); + struct resource *res = kzalloc(sizeof(struct resource), GFP_KERNEL); if (res) { rio_init_dbell_res(res, start, end); @@ -360,7 +360,7 @@ int rio_release_inb_dbell(struct rio_mport *mport, u16 start, u16 end) struct resource *rio_request_outb_dbell(struct rio_dev *rdev, u16 start, u16 end) { - struct resource *res = kmalloc(sizeof(struct resource), GFP_KERNEL); + struct resource *res = kzalloc(sizeof(struct resource), GFP_KERNEL); if (res) { rio_init_dbell_res(res, start, end); diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index cb61f300f8b5d..277b5c8c825ca 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -67,7 +67,7 @@ static const u8 DASD_DIAG_CMS1[] = { 0xc3, 0xd4, 0xe2, 0xf1 };/* EBCDIC CMS1 */ * and function code cmd. * In case of an exception return 3. Otherwise return result of bitwise OR of * resulting condition code and DIAG return code. */ -static inline int dia250(void *iob, int cmd) +static inline int __dia250(void *iob, int cmd) { register unsigned long reg2 asm ("2") = (unsigned long) iob; typedef union { @@ -77,7 +77,6 @@ static inline int dia250(void *iob, int cmd) int rc; rc = 3; - diag_stat_inc(DIAG_STAT_X250); asm volatile( " diag 2,%2,0x250\n" "0: ipm %0\n" @@ -91,6 +90,12 @@ static inline int dia250(void *iob, int cmd) return rc; } +static inline int dia250(void *iob, int cmd) +{ + diag_stat_inc(DIAG_STAT_X250); + return __dia250(iob, cmd); +} + /* Initialize block I/O to DIAG device using the specified blocksize and * block offset. On success, return zero and set end_block to contain the * number of blocks on the device minus the specified offset. Return non-zero diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 3b3e0998fa6e7..d6a691e27d333 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -4002,6 +4002,7 @@ static ssize_t ipr_store_update_fw(struct device *dev, struct ipr_sglist *sglist; char fname[100]; char *src; + char *endline; int result, dnld_size; if (!capable(CAP_SYS_ADMIN)) @@ -4009,6 +4010,10 @@ static ssize_t ipr_store_update_fw(struct device *dev, snprintf(fname, sizeof(fname), "%s", buf); + endline = strchr(fname, '\n'); + if (endline) + *endline = '\0'; + if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) { dev_err(&ioa_cfg->pdev->dev, "Firmware file %s not found\n", fname); return -EIO; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index fa6b2c4eb7a2b..8c6e31874171b 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1344,6 +1344,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret) switch (ret) { case BLKPREP_KILL: + case BLKPREP_INVALID: req->errors = DID_NO_CONNECT << 16; /* release the command and kill it */ if (req->special) { diff --git a/drivers/sh/superhyway/superhyway.c b/drivers/sh/superhyway/superhyway.c index 2d9e7f3d56115..bb1fb77121340 100644 --- a/drivers/sh/superhyway/superhyway.c +++ b/drivers/sh/superhyway/superhyway.c @@ -66,7 +66,7 @@ int superhyway_add_device(unsigned long base, struct superhyway_device *sdev, superhyway_read_vcr(dev, base, &dev->vcr); if (!dev->resource) { - dev->resource = kmalloc(sizeof(struct resource), GFP_KERNEL); + dev->resource = kzalloc(sizeof(struct resource), GFP_KERNEL); if (!dev->resource) { kfree(dev); return -ENOMEM; diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 6a4ff27f4357e..c688efa95e29b 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -204,8 +204,8 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, { struct spi_imx_data *spi_imx = spi_master_get_devdata(master); - if (spi_imx->dma_is_inited && - transfer->len > spi_imx->wml * sizeof(u32)) + if (spi_imx->dma_is_inited && transfer->len >= spi_imx->wml && + (transfer->len % spi_imx->wml) == 0) return true; return false; } @@ -919,8 +919,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL; int ret; unsigned long timeout; - u32 dma; - int left; struct spi_master *master = spi_imx->bitbang.master; struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg; @@ -954,13 +952,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, /* Trigger the cspi module. */ spi_imx->dma_finished = 0; - dma = readl(spi_imx->base + MX51_ECSPI_DMA); - dma = dma & (~MX51_ECSPI_DMA_RXT_WML_MASK); - /* Change RX_DMA_LENGTH trigger dma fetch tail data */ - left = transfer->len % spi_imx->wml; - if (left) - writel(dma | (left << MX51_ECSPI_DMA_RXT_WML_OFFSET), - spi_imx->base + MX51_ECSPI_DMA); /* * Set these order to avoid potential RX overflow. The overflow may * happen if we enable SPI HW before starting RX DMA due to rescheduling @@ -992,10 +983,6 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, spi_imx->devtype_data->reset(spi_imx); dmaengine_terminate_all(master->dma_rx); } - dma &= ~MX51_ECSPI_DMA_RXT_WML_MASK; - writel(dma | - spi_imx->wml << MX51_ECSPI_DMA_RXT_WML_OFFSET, - spi_imx->base + MX51_ECSPI_DMA); } spi_imx->dma_finished = 1; diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 79a8bc4f6cec9..7cb1b2d710c10 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -749,6 +749,7 @@ static int rockchip_spi_probe(struct platform_device *pdev) return 0; err_register_master: + pm_runtime_disable(&pdev->dev); if (rs->dma_tx.ch) dma_release_channel(rs->dma_tx.ch); if (rs->dma_rx.ch) @@ -778,6 +779,8 @@ static int rockchip_spi_remove(struct platform_device *pdev) if (rs->dma_rx.ch) dma_release_channel(rs->dma_rx.ch); + spi_master_put(master); + return 0; } diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig index 0c675861623f4..d8e4219c23249 100644 --- a/drivers/ssb/Kconfig +++ b/drivers/ssb/Kconfig @@ -83,6 +83,7 @@ config SSB_SDIOHOST config SSB_HOST_SOC bool "Support for SSB bus on SoC" depends on SSB && BCM47XX_NVRAM + select SSB_SPROM help Host interface for a SSB directly mapped into memory. This is for some Broadcom SoCs from the BCM47xx and BCM53xx lines. diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c index 3ec7e65a3ffa5..db49af90217e3 100644 --- a/drivers/staging/media/davinci_vpfe/vpfe_video.c +++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c @@ -147,7 +147,7 @@ static int vpfe_prepare_pipeline(struct vpfe_video_device *video) mutex_lock(&mdev->graph_mutex); ret = media_entity_graph_walk_init(&graph, entity->graph_obj.mdev); if (ret) { - mutex_unlock(&video->lock); + mutex_unlock(&mdev->graph_mutex); return -ENOMEM; } media_entity_graph_walk_start(&graph, entity); diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 82a663ba98009..4f229e711e1c1 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -177,7 +177,6 @@ void core_tmr_abort_task( if (!__target_check_io_state(se_cmd, se_sess, 0)) { spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - target_put_sess_cmd(se_cmd); goto out; } list_del_init(&se_cmd->se_cmd_list); diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c index 45f86da1d6d37..03b6743461d15 100644 --- a/drivers/usb/chipidea/otg.c +++ b/drivers/usb/chipidea/otg.c @@ -158,7 +158,7 @@ static void ci_otg_work(struct work_struct *work) int ci_hdrc_otg_init(struct ci_hdrc *ci) { INIT_WORK(&ci->work, ci_otg_work); - ci->wq = create_singlethread_workqueue("ci_otg"); + ci->wq = create_freezable_workqueue("ci_otg"); if (!ci->wq) { dev_err(ci->dev, "can't create workqueue\n"); return -ENODEV; diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig index f612dda9c9778..56ecb8b5115dd 100644 --- a/drivers/usb/serial/Kconfig +++ b/drivers/usb/serial/Kconfig @@ -475,22 +475,6 @@ config USB_SERIAL_MOS7840 To compile this driver as a module, choose M here: the module will be called mos7840. If unsure, choose N. -config USB_SERIAL_MXUPORT11 - tristate "USB Moxa UPORT 11x0 Serial Driver" - ---help--- - Say Y here if you want to use a MOXA UPort 11x0 Serial hub. - - This driver supports: - - - UPort 1110 : 1 port RS-232 USB to Serial Hub. - - UPort 1130 : 1 port RS-422/485 USB to Serial Hub. - - UPort 1130I : 1 port RS-422/485 USB to Serial Hub with Isolation. - - UPort 1150 : 1 port RS-232/422/485 USB to Serial Hub. - - UPort 1150I : 1 port RS-232/422/485 USB to Serial Hub with Isolation. - - To compile this driver as a module, choose M here: the - module will be called mxu11x0. - config USB_SERIAL_MXUPORT tristate "USB Moxa UPORT Serial Driver" ---help--- diff --git a/drivers/usb/serial/Makefile b/drivers/usb/serial/Makefile index f3fa5e53702d8..349d9df0895f5 100644 --- a/drivers/usb/serial/Makefile +++ b/drivers/usb/serial/Makefile @@ -38,7 +38,6 @@ obj-$(CONFIG_USB_SERIAL_METRO) += metro-usb.o obj-$(CONFIG_USB_SERIAL_MOS7720) += mos7720.o obj-$(CONFIG_USB_SERIAL_MOS7840) += mos7840.o obj-$(CONFIG_USB_SERIAL_MXUPORT) += mxuport.o -obj-$(CONFIG_USB_SERIAL_MXUPORT11) += mxu11x0.o obj-$(CONFIG_USB_SERIAL_NAVMAN) += navman.o obj-$(CONFIG_USB_SERIAL_OMNINET) += omninet.o obj-$(CONFIG_USB_SERIAL_OPTICON) += opticon.o diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 7c319e7edda22..73a366de5102a 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -165,6 +165,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ + { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ diff --git a/drivers/usb/serial/mxu11x0.c b/drivers/usb/serial/mxu11x0.c deleted file mode 100644 index 619607323bfdf..0000000000000 --- a/drivers/usb/serial/mxu11x0.c +++ /dev/null @@ -1,1006 +0,0 @@ -/* - * USB Moxa UPORT 11x0 Serial Driver - * - * Copyright (C) 2007 MOXA Technologies Co., Ltd. - * Copyright (C) 2015 Mathieu Othacehe - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * - * Supports the following Moxa USB to serial converters: - * UPort 1110, 1 port RS-232 USB to Serial Hub. - * UPort 1130, 1 port RS-422/485 USB to Serial Hub. - * UPort 1130I, 1 port RS-422/485 USB to Serial Hub with isolation - * protection. - * UPort 1150, 1 port RS-232/422/485 USB to Serial Hub. - * UPort 1150I, 1 port RS-232/422/485 USB to Serial Hub with isolation - * protection. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* Vendor and product ids */ -#define MXU1_VENDOR_ID 0x110a -#define MXU1_1110_PRODUCT_ID 0x1110 -#define MXU1_1130_PRODUCT_ID 0x1130 -#define MXU1_1150_PRODUCT_ID 0x1150 -#define MXU1_1151_PRODUCT_ID 0x1151 -#define MXU1_1131_PRODUCT_ID 0x1131 - -/* Commands */ -#define MXU1_GET_VERSION 0x01 -#define MXU1_GET_PORT_STATUS 0x02 -#define MXU1_GET_PORT_DEV_INFO 0x03 -#define MXU1_GET_CONFIG 0x04 -#define MXU1_SET_CONFIG 0x05 -#define MXU1_OPEN_PORT 0x06 -#define MXU1_CLOSE_PORT 0x07 -#define MXU1_START_PORT 0x08 -#define MXU1_STOP_PORT 0x09 -#define MXU1_TEST_PORT 0x0A -#define MXU1_PURGE_PORT 0x0B -#define MXU1_RESET_EXT_DEVICE 0x0C -#define MXU1_GET_OUTQUEUE 0x0D -#define MXU1_WRITE_DATA 0x80 -#define MXU1_READ_DATA 0x81 -#define MXU1_REQ_TYPE_CLASS 0x82 - -/* Module identifiers */ -#define MXU1_I2C_PORT 0x01 -#define MXU1_IEEE1284_PORT 0x02 -#define MXU1_UART1_PORT 0x03 -#define MXU1_UART2_PORT 0x04 -#define MXU1_RAM_PORT 0x05 - -/* Modem status */ -#define MXU1_MSR_DELTA_CTS 0x01 -#define MXU1_MSR_DELTA_DSR 0x02 -#define MXU1_MSR_DELTA_RI 0x04 -#define MXU1_MSR_DELTA_CD 0x08 -#define MXU1_MSR_CTS 0x10 -#define MXU1_MSR_DSR 0x20 -#define MXU1_MSR_RI 0x40 -#define MXU1_MSR_CD 0x80 -#define MXU1_MSR_DELTA_MASK 0x0F -#define MXU1_MSR_MASK 0xF0 - -/* Line status */ -#define MXU1_LSR_OVERRUN_ERROR 0x01 -#define MXU1_LSR_PARITY_ERROR 0x02 -#define MXU1_LSR_FRAMING_ERROR 0x04 -#define MXU1_LSR_BREAK 0x08 -#define MXU1_LSR_ERROR 0x0F -#define MXU1_LSR_RX_FULL 0x10 -#define MXU1_LSR_TX_EMPTY 0x20 - -/* Modem control */ -#define MXU1_MCR_LOOP 0x04 -#define MXU1_MCR_DTR 0x10 -#define MXU1_MCR_RTS 0x20 - -/* Mask settings */ -#define MXU1_UART_ENABLE_RTS_IN 0x0001 -#define MXU1_UART_DISABLE_RTS 0x0002 -#define MXU1_UART_ENABLE_PARITY_CHECKING 0x0008 -#define MXU1_UART_ENABLE_DSR_OUT 0x0010 -#define MXU1_UART_ENABLE_CTS_OUT 0x0020 -#define MXU1_UART_ENABLE_X_OUT 0x0040 -#define MXU1_UART_ENABLE_XA_OUT 0x0080 -#define MXU1_UART_ENABLE_X_IN 0x0100 -#define MXU1_UART_ENABLE_DTR_IN 0x0800 -#define MXU1_UART_DISABLE_DTR 0x1000 -#define MXU1_UART_ENABLE_MS_INTS 0x2000 -#define MXU1_UART_ENABLE_AUTO_START_DMA 0x4000 -#define MXU1_UART_SEND_BREAK_SIGNAL 0x8000 - -/* Parity */ -#define MXU1_UART_NO_PARITY 0x00 -#define MXU1_UART_ODD_PARITY 0x01 -#define MXU1_UART_EVEN_PARITY 0x02 -#define MXU1_UART_MARK_PARITY 0x03 -#define MXU1_UART_SPACE_PARITY 0x04 - -/* Stop bits */ -#define MXU1_UART_1_STOP_BITS 0x00 -#define MXU1_UART_1_5_STOP_BITS 0x01 -#define MXU1_UART_2_STOP_BITS 0x02 - -/* Bits per character */ -#define MXU1_UART_5_DATA_BITS 0x00 -#define MXU1_UART_6_DATA_BITS 0x01 -#define MXU1_UART_7_DATA_BITS 0x02 -#define MXU1_UART_8_DATA_BITS 0x03 - -/* Operation modes */ -#define MXU1_UART_232 0x00 -#define MXU1_UART_485_RECEIVER_DISABLED 0x01 -#define MXU1_UART_485_RECEIVER_ENABLED 0x02 - -/* Pipe transfer mode and timeout */ -#define MXU1_PIPE_MODE_CONTINUOUS 0x01 -#define MXU1_PIPE_MODE_MASK 0x03 -#define MXU1_PIPE_TIMEOUT_MASK 0x7C -#define MXU1_PIPE_TIMEOUT_ENABLE 0x80 - -/* Config struct */ -struct mxu1_uart_config { - __be16 wBaudRate; - __be16 wFlags; - u8 bDataBits; - u8 bParity; - u8 bStopBits; - char cXon; - char cXoff; - u8 bUartMode; -} __packed; - -/* Purge modes */ -#define MXU1_PURGE_OUTPUT 0x00 -#define MXU1_PURGE_INPUT 0x80 - -/* Read/Write data */ -#define MXU1_RW_DATA_ADDR_SFR 0x10 -#define MXU1_RW_DATA_ADDR_IDATA 0x20 -#define MXU1_RW_DATA_ADDR_XDATA 0x30 -#define MXU1_RW_DATA_ADDR_CODE 0x40 -#define MXU1_RW_DATA_ADDR_GPIO 0x50 -#define MXU1_RW_DATA_ADDR_I2C 0x60 -#define MXU1_RW_DATA_ADDR_FLASH 0x70 -#define MXU1_RW_DATA_ADDR_DSP 0x80 - -#define MXU1_RW_DATA_UNSPECIFIED 0x00 -#define MXU1_RW_DATA_BYTE 0x01 -#define MXU1_RW_DATA_WORD 0x02 -#define MXU1_RW_DATA_DOUBLE_WORD 0x04 - -struct mxu1_write_data_bytes { - u8 bAddrType; - u8 bDataType; - u8 bDataCounter; - __be16 wBaseAddrHi; - __be16 wBaseAddrLo; - u8 bData[0]; -} __packed; - -/* Interrupt codes */ -#define MXU1_CODE_HARDWARE_ERROR 0xFF -#define MXU1_CODE_DATA_ERROR 0x03 -#define MXU1_CODE_MODEM_STATUS 0x04 - -static inline int mxu1_get_func_from_code(unsigned char code) -{ - return code & 0x0f; -} - -/* Download firmware max packet size */ -#define MXU1_DOWNLOAD_MAX_PACKET_SIZE 64 - -/* Firmware image header */ -struct mxu1_firmware_header { - __le16 wLength; - u8 bCheckSum; -} __packed; - -#define MXU1_UART_BASE_ADDR 0xFFA0 -#define MXU1_UART_OFFSET_MCR 0x0004 - -#define MXU1_BAUD_BASE 923077 - -#define MXU1_TRANSFER_TIMEOUT 2 -#define MXU1_DOWNLOAD_TIMEOUT 1000 -#define MXU1_DEFAULT_CLOSING_WAIT 4000 /* in .01 secs */ - -struct mxu1_port { - u8 msr; - u8 mcr; - u8 uart_mode; - spinlock_t spinlock; /* Protects msr */ - struct mutex mutex; /* Protects mcr */ - bool send_break; -}; - -struct mxu1_device { - u16 mxd_model; -}; - -static const struct usb_device_id mxu1_idtable[] = { - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1110_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1130_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) }, - { } -}; - -MODULE_DEVICE_TABLE(usb, mxu1_idtable); - -/* Write the given buffer out to the control pipe. */ -static int mxu1_send_ctrl_data_urb(struct usb_serial *serial, - u8 request, - u16 value, u16 index, - void *data, size_t size) -{ - int status; - - status = usb_control_msg(serial->dev, - usb_sndctrlpipe(serial->dev, 0), - request, - (USB_DIR_OUT | USB_TYPE_VENDOR | - USB_RECIP_DEVICE), value, index, - data, size, - USB_CTRL_SET_TIMEOUT); - if (status < 0) { - dev_err(&serial->interface->dev, - "%s - usb_control_msg failed: %d\n", - __func__, status); - return status; - } - - if (status != size) { - dev_err(&serial->interface->dev, - "%s - short write (%d / %zd)\n", - __func__, status, size); - return -EIO; - } - - return 0; -} - -/* Send a vendor request without any data */ -static int mxu1_send_ctrl_urb(struct usb_serial *serial, - u8 request, u16 value, u16 index) -{ - return mxu1_send_ctrl_data_urb(serial, request, value, index, - NULL, 0); -} - -static int mxu1_download_firmware(struct usb_serial *serial, - const struct firmware *fw_p) -{ - int status = 0; - int buffer_size; - int pos; - int len; - int done; - u8 cs = 0; - u8 *buffer; - struct usb_device *dev = serial->dev; - struct mxu1_firmware_header *header; - unsigned int pipe; - - pipe = usb_sndbulkpipe(dev, serial->port[0]->bulk_out_endpointAddress); - - buffer_size = fw_p->size + sizeof(*header); - buffer = kmalloc(buffer_size, GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - memcpy(buffer, fw_p->data, fw_p->size); - memset(buffer + fw_p->size, 0xff, buffer_size - fw_p->size); - - for (pos = sizeof(*header); pos < buffer_size; pos++) - cs = (u8)(cs + buffer[pos]); - - header = (struct mxu1_firmware_header *)buffer; - header->wLength = cpu_to_le16(buffer_size - sizeof(*header)); - header->bCheckSum = cs; - - dev_dbg(&dev->dev, "%s - downloading firmware\n", __func__); - - for (pos = 0; pos < buffer_size; pos += done) { - len = min(buffer_size - pos, MXU1_DOWNLOAD_MAX_PACKET_SIZE); - - status = usb_bulk_msg(dev, pipe, buffer + pos, len, &done, - MXU1_DOWNLOAD_TIMEOUT); - if (status) - break; - } - - kfree(buffer); - - if (status) { - dev_err(&dev->dev, "failed to download firmware: %d\n", status); - return status; - } - - msleep_interruptible(100); - usb_reset_device(dev); - - dev_dbg(&dev->dev, "%s - download successful\n", __func__); - - return 0; -} - -static int mxu1_port_probe(struct usb_serial_port *port) -{ - struct mxu1_port *mxport; - struct mxu1_device *mxdev; - - if (!port->interrupt_in_urb) { - dev_err(&port->dev, "no interrupt urb\n"); - return -ENODEV; - } - - mxport = kzalloc(sizeof(struct mxu1_port), GFP_KERNEL); - if (!mxport) - return -ENOMEM; - - spin_lock_init(&mxport->spinlock); - mutex_init(&mxport->mutex); - - mxdev = usb_get_serial_data(port->serial); - - switch (mxdev->mxd_model) { - case MXU1_1110_PRODUCT_ID: - case MXU1_1150_PRODUCT_ID: - case MXU1_1151_PRODUCT_ID: - mxport->uart_mode = MXU1_UART_232; - break; - case MXU1_1130_PRODUCT_ID: - case MXU1_1131_PRODUCT_ID: - mxport->uart_mode = MXU1_UART_485_RECEIVER_DISABLED; - break; - } - - usb_set_serial_port_data(port, mxport); - - port->port.closing_wait = - msecs_to_jiffies(MXU1_DEFAULT_CLOSING_WAIT * 10); - port->port.drain_delay = 1; - - return 0; -} - -static int mxu1_port_remove(struct usb_serial_port *port) -{ - struct mxu1_port *mxport; - - mxport = usb_get_serial_port_data(port); - kfree(mxport); - - return 0; -} - -static int mxu1_startup(struct usb_serial *serial) -{ - struct mxu1_device *mxdev; - struct usb_device *dev = serial->dev; - struct usb_host_interface *cur_altsetting; - char fw_name[32]; - const struct firmware *fw_p = NULL; - int err; - - dev_dbg(&serial->interface->dev, "%s - product 0x%04X, num configurations %d, configuration value %d\n", - __func__, le16_to_cpu(dev->descriptor.idProduct), - dev->descriptor.bNumConfigurations, - dev->actconfig->desc.bConfigurationValue); - - /* create device structure */ - mxdev = kzalloc(sizeof(struct mxu1_device), GFP_KERNEL); - if (!mxdev) - return -ENOMEM; - - usb_set_serial_data(serial, mxdev); - - mxdev->mxd_model = le16_to_cpu(dev->descriptor.idProduct); - - cur_altsetting = serial->interface->cur_altsetting; - - /* if we have only 1 configuration, download firmware */ - if (cur_altsetting->desc.bNumEndpoints == 1) { - - snprintf(fw_name, - sizeof(fw_name), - "moxa/moxa-%04x.fw", - mxdev->mxd_model); - - err = request_firmware(&fw_p, fw_name, &serial->interface->dev); - if (err) { - dev_err(&serial->interface->dev, "failed to request firmware: %d\n", - err); - goto err_free_mxdev; - } - - err = mxu1_download_firmware(serial, fw_p); - if (err) - goto err_release_firmware; - - /* device is being reset */ - err = -ENODEV; - goto err_release_firmware; - } - - return 0; - -err_release_firmware: - release_firmware(fw_p); -err_free_mxdev: - kfree(mxdev); - - return err; -} - -static void mxu1_release(struct usb_serial *serial) -{ - struct mxu1_device *mxdev; - - mxdev = usb_get_serial_data(serial); - kfree(mxdev); -} - -static int mxu1_write_byte(struct usb_serial_port *port, u32 addr, - u8 mask, u8 byte) -{ - int status; - size_t size; - struct mxu1_write_data_bytes *data; - - dev_dbg(&port->dev, "%s - addr 0x%08X, mask 0x%02X, byte 0x%02X\n", - __func__, addr, mask, byte); - - size = sizeof(struct mxu1_write_data_bytes) + 2; - data = kzalloc(size, GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->bAddrType = MXU1_RW_DATA_ADDR_XDATA; - data->bDataType = MXU1_RW_DATA_BYTE; - data->bDataCounter = 1; - data->wBaseAddrHi = cpu_to_be16(addr >> 16); - data->wBaseAddrLo = cpu_to_be16(addr); - data->bData[0] = mask; - data->bData[1] = byte; - - status = mxu1_send_ctrl_data_urb(port->serial, MXU1_WRITE_DATA, 0, - MXU1_RAM_PORT, data, size); - if (status < 0) - dev_err(&port->dev, "%s - failed: %d\n", __func__, status); - - kfree(data); - - return status; -} - -static int mxu1_set_mcr(struct usb_serial_port *port, unsigned int mcr) -{ - int status; - - status = mxu1_write_byte(port, - MXU1_UART_BASE_ADDR + MXU1_UART_OFFSET_MCR, - MXU1_MCR_RTS | MXU1_MCR_DTR | MXU1_MCR_LOOP, - mcr); - return status; -} - -static void mxu1_set_termios(struct tty_struct *tty, - struct usb_serial_port *port, - struct ktermios *old_termios) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct mxu1_uart_config *config; - tcflag_t cflag, iflag; - speed_t baud; - int status; - unsigned int mcr; - - cflag = tty->termios.c_cflag; - iflag = tty->termios.c_iflag; - - if (old_termios && - !tty_termios_hw_change(&tty->termios, old_termios) && - tty->termios.c_iflag == old_termios->c_iflag) { - dev_dbg(&port->dev, "%s - nothing to change\n", __func__); - return; - } - - dev_dbg(&port->dev, - "%s - cflag 0x%08x, iflag 0x%08x\n", __func__, cflag, iflag); - - if (old_termios) { - dev_dbg(&port->dev, "%s - old cflag 0x%08x, old iflag 0x%08x\n", - __func__, - old_termios->c_cflag, - old_termios->c_iflag); - } - - config = kzalloc(sizeof(*config), GFP_KERNEL); - if (!config) - return; - - /* these flags must be set */ - config->wFlags |= MXU1_UART_ENABLE_MS_INTS; - config->wFlags |= MXU1_UART_ENABLE_AUTO_START_DMA; - if (mxport->send_break) - config->wFlags |= MXU1_UART_SEND_BREAK_SIGNAL; - config->bUartMode = mxport->uart_mode; - - switch (C_CSIZE(tty)) { - case CS5: - config->bDataBits = MXU1_UART_5_DATA_BITS; - break; - case CS6: - config->bDataBits = MXU1_UART_6_DATA_BITS; - break; - case CS7: - config->bDataBits = MXU1_UART_7_DATA_BITS; - break; - default: - case CS8: - config->bDataBits = MXU1_UART_8_DATA_BITS; - break; - } - - if (C_PARENB(tty)) { - config->wFlags |= MXU1_UART_ENABLE_PARITY_CHECKING; - if (C_CMSPAR(tty)) { - if (C_PARODD(tty)) - config->bParity = MXU1_UART_MARK_PARITY; - else - config->bParity = MXU1_UART_SPACE_PARITY; - } else { - if (C_PARODD(tty)) - config->bParity = MXU1_UART_ODD_PARITY; - else - config->bParity = MXU1_UART_EVEN_PARITY; - } - } else { - config->bParity = MXU1_UART_NO_PARITY; - } - - if (C_CSTOPB(tty)) - config->bStopBits = MXU1_UART_2_STOP_BITS; - else - config->bStopBits = MXU1_UART_1_STOP_BITS; - - if (C_CRTSCTS(tty)) { - /* RTS flow control must be off to drop RTS for baud rate B0 */ - if (C_BAUD(tty) != B0) - config->wFlags |= MXU1_UART_ENABLE_RTS_IN; - config->wFlags |= MXU1_UART_ENABLE_CTS_OUT; - } - - if (I_IXOFF(tty) || I_IXON(tty)) { - config->cXon = START_CHAR(tty); - config->cXoff = STOP_CHAR(tty); - - if (I_IXOFF(tty)) - config->wFlags |= MXU1_UART_ENABLE_X_IN; - - if (I_IXON(tty)) - config->wFlags |= MXU1_UART_ENABLE_X_OUT; - } - - baud = tty_get_baud_rate(tty); - if (!baud) - baud = 9600; - config->wBaudRate = MXU1_BAUD_BASE / baud; - - dev_dbg(&port->dev, "%s - BaudRate=%d, wBaudRate=%d, wFlags=0x%04X, bDataBits=%d, bParity=%d, bStopBits=%d, cXon=%d, cXoff=%d, bUartMode=%d\n", - __func__, baud, config->wBaudRate, config->wFlags, - config->bDataBits, config->bParity, config->bStopBits, - config->cXon, config->cXoff, config->bUartMode); - - cpu_to_be16s(&config->wBaudRate); - cpu_to_be16s(&config->wFlags); - - status = mxu1_send_ctrl_data_urb(port->serial, MXU1_SET_CONFIG, 0, - MXU1_UART1_PORT, config, - sizeof(*config)); - if (status) - dev_err(&port->dev, "cannot set config: %d\n", status); - - mutex_lock(&mxport->mutex); - mcr = mxport->mcr; - - if (C_BAUD(tty) == B0) - mcr &= ~(MXU1_MCR_DTR | MXU1_MCR_RTS); - else if (old_termios && (old_termios->c_cflag & CBAUD) == B0) - mcr |= MXU1_MCR_DTR | MXU1_MCR_RTS; - - status = mxu1_set_mcr(port, mcr); - if (status) - dev_err(&port->dev, "cannot set modem control: %d\n", status); - else - mxport->mcr = mcr; - - mutex_unlock(&mxport->mutex); - - kfree(config); -} - -static int mxu1_get_serial_info(struct usb_serial_port *port, - struct serial_struct __user *ret_arg) -{ - struct serial_struct ret_serial; - unsigned cwait; - - if (!ret_arg) - return -EFAULT; - - cwait = port->port.closing_wait; - if (cwait != ASYNC_CLOSING_WAIT_NONE) - cwait = jiffies_to_msecs(cwait) / 10; - - memset(&ret_serial, 0, sizeof(ret_serial)); - - ret_serial.type = PORT_16550A; - ret_serial.line = port->minor; - ret_serial.port = 0; - ret_serial.xmit_fifo_size = port->bulk_out_size; - ret_serial.baud_base = MXU1_BAUD_BASE; - ret_serial.close_delay = 5*HZ; - ret_serial.closing_wait = cwait; - - if (copy_to_user(ret_arg, &ret_serial, sizeof(*ret_arg))) - return -EFAULT; - - return 0; -} - - -static int mxu1_set_serial_info(struct usb_serial_port *port, - struct serial_struct __user *new_arg) -{ - struct serial_struct new_serial; - unsigned cwait; - - if (copy_from_user(&new_serial, new_arg, sizeof(new_serial))) - return -EFAULT; - - cwait = new_serial.closing_wait; - if (cwait != ASYNC_CLOSING_WAIT_NONE) - cwait = msecs_to_jiffies(10 * new_serial.closing_wait); - - port->port.closing_wait = cwait; - - return 0; -} - -static int mxu1_ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg) -{ - struct usb_serial_port *port = tty->driver_data; - - switch (cmd) { - case TIOCGSERIAL: - return mxu1_get_serial_info(port, - (struct serial_struct __user *)arg); - case TIOCSSERIAL: - return mxu1_set_serial_info(port, - (struct serial_struct __user *)arg); - } - - return -ENOIOCTLCMD; -} - -static int mxu1_tiocmget(struct tty_struct *tty) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - unsigned int result; - unsigned int msr; - unsigned int mcr; - unsigned long flags; - - mutex_lock(&mxport->mutex); - spin_lock_irqsave(&mxport->spinlock, flags); - - msr = mxport->msr; - mcr = mxport->mcr; - - spin_unlock_irqrestore(&mxport->spinlock, flags); - mutex_unlock(&mxport->mutex); - - result = ((mcr & MXU1_MCR_DTR) ? TIOCM_DTR : 0) | - ((mcr & MXU1_MCR_RTS) ? TIOCM_RTS : 0) | - ((mcr & MXU1_MCR_LOOP) ? TIOCM_LOOP : 0) | - ((msr & MXU1_MSR_CTS) ? TIOCM_CTS : 0) | - ((msr & MXU1_MSR_CD) ? TIOCM_CAR : 0) | - ((msr & MXU1_MSR_RI) ? TIOCM_RI : 0) | - ((msr & MXU1_MSR_DSR) ? TIOCM_DSR : 0); - - dev_dbg(&port->dev, "%s - 0x%04X\n", __func__, result); - - return result; -} - -static int mxu1_tiocmset(struct tty_struct *tty, - unsigned int set, unsigned int clear) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - int err; - unsigned int mcr; - - mutex_lock(&mxport->mutex); - mcr = mxport->mcr; - - if (set & TIOCM_RTS) - mcr |= MXU1_MCR_RTS; - if (set & TIOCM_DTR) - mcr |= MXU1_MCR_DTR; - if (set & TIOCM_LOOP) - mcr |= MXU1_MCR_LOOP; - - if (clear & TIOCM_RTS) - mcr &= ~MXU1_MCR_RTS; - if (clear & TIOCM_DTR) - mcr &= ~MXU1_MCR_DTR; - if (clear & TIOCM_LOOP) - mcr &= ~MXU1_MCR_LOOP; - - err = mxu1_set_mcr(port, mcr); - if (!err) - mxport->mcr = mcr; - - mutex_unlock(&mxport->mutex); - - return err; -} - -static void mxu1_break(struct tty_struct *tty, int break_state) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - - if (break_state == -1) - mxport->send_break = true; - else - mxport->send_break = false; - - mxu1_set_termios(tty, port, NULL); -} - -static int mxu1_open(struct tty_struct *tty, struct usb_serial_port *port) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct usb_serial *serial = port->serial; - int status; - u16 open_settings; - - open_settings = (MXU1_PIPE_MODE_CONTINUOUS | - MXU1_PIPE_TIMEOUT_ENABLE | - (MXU1_TRANSFER_TIMEOUT << 2)); - - mxport->msr = 0; - - status = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); - if (status) { - dev_err(&port->dev, "failed to submit interrupt urb: %d\n", - status); - return status; - } - - if (tty) - mxu1_set_termios(tty, port, NULL); - - status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT, - open_settings, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send open command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send start command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT, - MXU1_PURGE_INPUT, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot clear input buffers: %d\n", - status); - - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT, - MXU1_PURGE_OUTPUT, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot clear output buffers: %d\n", - status); - - goto unlink_int_urb; - } - - /* - * reset the data toggle on the bulk endpoints to work around bug in - * host controllers where things get out of sync some times - */ - usb_clear_halt(serial->dev, port->write_urb->pipe); - usb_clear_halt(serial->dev, port->read_urb->pipe); - - if (tty) - mxu1_set_termios(tty, port, NULL); - - status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT, - open_settings, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send open command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send start command: %d\n", status); - goto unlink_int_urb; - } - - status = usb_serial_generic_open(tty, port); - if (status) - goto unlink_int_urb; - - return 0; - -unlink_int_urb: - usb_kill_urb(port->interrupt_in_urb); - - return status; -} - -static void mxu1_close(struct usb_serial_port *port) -{ - int status; - - usb_serial_generic_close(port); - usb_kill_urb(port->interrupt_in_urb); - - status = mxu1_send_ctrl_urb(port->serial, MXU1_CLOSE_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "failed to send close port command: %d\n", - status); - } -} - -static void mxu1_handle_new_msr(struct usb_serial_port *port, u8 msr) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct async_icount *icount; - unsigned long flags; - - dev_dbg(&port->dev, "%s - msr 0x%02X\n", __func__, msr); - - spin_lock_irqsave(&mxport->spinlock, flags); - mxport->msr = msr & MXU1_MSR_MASK; - spin_unlock_irqrestore(&mxport->spinlock, flags); - - if (msr & MXU1_MSR_DELTA_MASK) { - icount = &port->icount; - if (msr & MXU1_MSR_DELTA_CTS) - icount->cts++; - if (msr & MXU1_MSR_DELTA_DSR) - icount->dsr++; - if (msr & MXU1_MSR_DELTA_CD) - icount->dcd++; - if (msr & MXU1_MSR_DELTA_RI) - icount->rng++; - - wake_up_interruptible(&port->port.delta_msr_wait); - } -} - -static void mxu1_interrupt_callback(struct urb *urb) -{ - struct usb_serial_port *port = urb->context; - unsigned char *data = urb->transfer_buffer; - int length = urb->actual_length; - int function; - int status; - u8 msr; - - switch (urb->status) { - case 0: - break; - case -ECONNRESET: - case -ENOENT: - case -ESHUTDOWN: - dev_dbg(&port->dev, "%s - urb shutting down: %d\n", - __func__, urb->status); - return; - default: - dev_dbg(&port->dev, "%s - nonzero urb status: %d\n", - __func__, urb->status); - goto exit; - } - - if (length != 2) { - dev_dbg(&port->dev, "%s - bad packet size: %d\n", - __func__, length); - goto exit; - } - - if (data[0] == MXU1_CODE_HARDWARE_ERROR) { - dev_err(&port->dev, "hardware error: %d\n", data[1]); - goto exit; - } - - function = mxu1_get_func_from_code(data[0]); - - dev_dbg(&port->dev, "%s - function %d, data 0x%02X\n", - __func__, function, data[1]); - - switch (function) { - case MXU1_CODE_DATA_ERROR: - dev_dbg(&port->dev, "%s - DATA ERROR, data 0x%02X\n", - __func__, data[1]); - break; - - case MXU1_CODE_MODEM_STATUS: - msr = data[1]; - mxu1_handle_new_msr(port, msr); - break; - - default: - dev_err(&port->dev, "unknown interrupt code: 0x%02X\n", - data[1]); - break; - } - -exit: - status = usb_submit_urb(urb, GFP_ATOMIC); - if (status) { - dev_err(&port->dev, "resubmit interrupt urb failed: %d\n", - status); - } -} - -static struct usb_serial_driver mxu11x0_device = { - .driver = { - .owner = THIS_MODULE, - .name = "mxu11x0", - }, - .description = "MOXA UPort 11x0", - .id_table = mxu1_idtable, - .num_ports = 1, - .port_probe = mxu1_port_probe, - .port_remove = mxu1_port_remove, - .attach = mxu1_startup, - .release = mxu1_release, - .open = mxu1_open, - .close = mxu1_close, - .ioctl = mxu1_ioctl, - .set_termios = mxu1_set_termios, - .tiocmget = mxu1_tiocmget, - .tiocmset = mxu1_tiocmset, - .tiocmiwait = usb_serial_generic_tiocmiwait, - .get_icount = usb_serial_generic_get_icount, - .break_ctl = mxu1_break, - .read_int_callback = mxu1_interrupt_callback, -}; - -static struct usb_serial_driver *const serial_drivers[] = { - &mxu11x0_device, NULL -}; - -module_usb_serial_driver(serial_drivers, mxu1_idtable); - -MODULE_AUTHOR("Mathieu Othacehe "); -MODULE_DESCRIPTION("MOXA UPort 11x0 USB to Serial Hub Driver"); -MODULE_LICENSE("GPL"); -MODULE_FIRMWARE("moxa/moxa-1110.fw"); -MODULE_FIRMWARE("moxa/moxa-1130.fw"); -MODULE_FIRMWARE("moxa/moxa-1131.fw"); -MODULE_FIRMWARE("moxa/moxa-1150.fw"); -MODULE_FIRMWARE("moxa/moxa-1151.fw"); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 8849439a8f18f..348e19834b83e 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -270,6 +270,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_UE910_V2 0x1012 #define TELIT_PRODUCT_LE922_USBCFG0 0x1042 #define TELIT_PRODUCT_LE922_USBCFG3 0x1043 +#define TELIT_PRODUCT_LE922_USBCFG5 0x1045 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 @@ -1132,6 +1133,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), @@ -1183,6 +1186,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3), .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 9919d2a9faf27..1bc6089b90083 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -157,14 +157,17 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9056)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9060)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9061)}, /* Sierra Wireless Modem */ - {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx/EM74xx */ - {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx/EM74xx */ + {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9078)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81b1)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 2760a7ba3f309..8c80a48e32335 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -446,7 +446,8 @@ static long vfio_pci_ioctl(void *device_data, info.num_regions = VFIO_PCI_NUM_REGIONS; info.num_irqs = VFIO_PCI_NUM_IRQS; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct pci_dev *pdev = vdev->pdev; @@ -520,7 +521,8 @@ static long vfio_pci_ioctl(void *device_data, return -EINVAL; } - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -555,7 +557,8 @@ static long vfio_pci_ioctl(void *device_data, else info.flags |= VFIO_IRQ_INFO_NORESIZE; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 418cdd9ba3f48..e65b142d34222 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -219,7 +219,8 @@ static long vfio_platform_ioctl(void *device_data, info.num_regions = vdev->num_regions; info.num_irqs = vdev->num_irqs; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct vfio_region_info info; @@ -240,7 +241,8 @@ static long vfio_platform_ioctl(void *device_data, info.size = vdev->regions[info.index].size; info.flags = vdev->regions[info.index].flags; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -259,7 +261,8 @@ static long vfio_platform_ioctl(void *device_data, info.flags = vdev->irqs[info.index].flags; info.count = vdev->irqs[info.index].count; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6f1ea3dddbad9..75b24e93cedb3 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -999,7 +999,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.iova_pgsizes = vfio_pgsize_bitmap(iommu); - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_IOMMU_MAP_DMA) { struct vfio_iommu_type1_dma_map map; @@ -1032,7 +1033,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, if (ret) return ret; - return copy_to_user((void __user *)arg, &unmap, minsz); + return copy_to_user((void __user *)arg, &unmap, minsz) ? + -EFAULT : 0; } return -ENOTTY; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index ad2146a9ab2d4..236553e81027c 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1156,6 +1156,8 @@ int vhost_init_used(struct vhost_virtqueue *vq) { __virtio16 last_used_idx; int r; + bool is_le = vq->is_le; + if (!vq->private_data) { vq->is_le = virtio_legacy_is_little_endian(); return 0; @@ -1165,15 +1167,20 @@ int vhost_init_used(struct vhost_virtqueue *vq) r = vhost_update_used_flags(vq); if (r) - return r; + goto err; vq->signalled_used_valid = false; - if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) - return -EFAULT; + if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) { + r = -EFAULT; + goto err; + } r = __get_user(last_used_idx, &vq->used->idx); if (r) - return r; + goto err; vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx); return 0; +err: + vq->is_le = is_le; + return r; } EXPORT_SYMBOL_GPL(vhost_init_used); diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 92f394927f241..6e92917ba77a9 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -709,6 +709,7 @@ static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, } if (!err) { + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; if (vc) @@ -956,6 +957,7 @@ static const char *fbcon_startup(void) ops->currcon = -1; ops->graphics = 1; ops->cur_rotate = -1; + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; p->con_rotate = initial_rotation; set_blitting_type(vc, info); diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c index a305caea58eea..fb75b7e5a19ab 100644 --- a/drivers/video/fbdev/acornfb.c +++ b/drivers/video/fbdev/acornfb.c @@ -1040,8 +1040,8 @@ static int acornfb_probe(struct platform_device *dev) * for the framebuffer if we are not using * VRAM. */ - base = dma_alloc_writecombine(current_par.dev, size, &handle, - GFP_KERNEL); + base = dma_alloc_wc(current_par.dev, size, &handle, + GFP_KERNEL); if (base == NULL) { printk(KERN_ERR "acornfb: unable to allocate screen " "memory\n"); diff --git a/drivers/video/fbdev/amba-clcd-versatile.c b/drivers/video/fbdev/amba-clcd-versatile.c index 7a8afcd4573e5..a8a22daa3f9d2 100644 --- a/drivers/video/fbdev/amba-clcd-versatile.c +++ b/drivers/video/fbdev/amba-clcd-versatile.c @@ -154,8 +154,8 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize) { dma_addr_t dma; - fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, framesize, - &dma, GFP_KERNEL); + fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, framesize, &dma, + GFP_KERNEL); if (!fb->fb.screen_base) { pr_err("CLCD: unable to map framebuffer\n"); return -ENOMEM; @@ -169,14 +169,12 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize) int versatile_clcd_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, - fb->fb.screen_base, - fb->fb.fix.smem_start, - fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } void versatile_clcd_remove_dma(struct clcd_fb *fb) { - dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, - fb->fb.screen_base, fb->fb.fix.smem_start); + dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, + fb->fb.fix.smem_start); } diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c index 9362424c23404..fe274b5851c77 100644 --- a/drivers/video/fbdev/amba-clcd.c +++ b/drivers/video/fbdev/amba-clcd.c @@ -774,8 +774,8 @@ static int clcdfb_of_dma_setup(struct clcd_fb *fb) static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, fb->fb.screen_base, - fb->fb.fix.smem_start, fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } static void clcdfb_of_dma_remove(struct clcd_fb *fb) diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index 19eb42b57d874..56c60e67316a5 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -414,8 +414,8 @@ static inline void atmel_lcdfb_free_video_memory(struct atmel_lcdfb_info *sinfo) { struct fb_info *info = sinfo->info; - dma_free_writecombine(info->device, info->fix.smem_len, - info->screen_base, info->fix.smem_start); + dma_free_wc(info->device, info->fix.smem_len, info->screen_base, + info->fix.smem_start); } /** @@ -435,8 +435,9 @@ static int atmel_lcdfb_alloc_video_memory(struct atmel_lcdfb_info *sinfo) * ((var->bits_per_pixel + 7) / 8)); info->fix.smem_len = max(smem_len, sinfo->smem_len); - info->screen_base = dma_alloc_writecombine(info->device, info->fix.smem_len, - (dma_addr_t *)&info->fix.smem_start, GFP_KERNEL); + info->screen_base = dma_alloc_wc(info->device, info->fix.smem_len, + (dma_addr_t *)&info->fix.smem_start, + GFP_KERNEL); if (!info->screen_base) { return -ENOMEM; diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c index 5b1081030cbbb..75f0db25d19fe 100644 --- a/drivers/video/fbdev/ep93xx-fb.c +++ b/drivers/video/fbdev/ep93xx-fb.c @@ -316,9 +316,8 @@ static int ep93xxfb_mmap(struct fb_info *info, struct vm_area_struct *vma) unsigned int offset = vma->vm_pgoff << PAGE_SHIFT; if (offset < info->fix.smem_len) { - return dma_mmap_writecombine(info->dev, vma, info->screen_base, - info->fix.smem_start, - info->fix.smem_len); + return dma_mmap_wc(info->dev, vma, info->screen_base, + info->fix.smem_start, info->fix.smem_len); } return -EINVAL; @@ -428,8 +427,7 @@ static int ep93xxfb_alloc_videomem(struct fb_info *info) /* Maximum 16bpp -> used memory is maximum x*y*2 bytes */ fb_size = EP93XXFB_MAX_XRES * EP93XXFB_MAX_YRES * 2; - virt_addr = dma_alloc_writecombine(info->dev, fb_size, - &phys_addr, GFP_KERNEL); + virt_addr = dma_alloc_wc(info->dev, fb_size, &phys_addr, GFP_KERNEL); if (!virt_addr) return -ENOMEM; diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c index b63d55f481fae..1a242b1338e9a 100644 --- a/drivers/video/fbdev/gbefb.c +++ b/drivers/video/fbdev/gbefb.c @@ -1185,8 +1185,8 @@ static int gbefb_probe(struct platform_device *p_dev) } else { /* try to allocate memory with the classical allocator * this has high chance to fail on low memory machines */ - gbe_mem = dma_alloc_writecombine(NULL, gbe_mem_size, - &gbe_dma_addr, GFP_KERNEL); + gbe_mem = dma_alloc_wc(NULL, gbe_mem_size, &gbe_dma_addr, + GFP_KERNEL); if (!gbe_mem) { printk(KERN_ERR "gbefb: couldn't allocate framebuffer memory\n"); ret = -ENOMEM; @@ -1238,7 +1238,7 @@ static int gbefb_probe(struct platform_device *p_dev) out_gbe_unmap: arch_phys_wc_del(par->wc_cookie); if (gbe_dma_addr) - dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys); + dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys); out_tiles_free: dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t), (void *)gbe_tiles.cpu, gbe_tiles.dma); @@ -1259,7 +1259,7 @@ static int gbefb_remove(struct platform_device* p_dev) gbe_turn_off(); arch_phys_wc_del(par->wc_cookie); if (gbe_dma_addr) - dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys); + dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys); dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t), (void *)gbe_tiles.cpu, gbe_tiles.dma); release_mem_region(GBE_BASE, sizeof(struct sgi_gbe)); diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index bb2f1e8660201..76b6a7784b06c 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -937,8 +937,8 @@ static int imxfb_probe(struct platform_device *pdev) } fbi->map_size = PAGE_ALIGN(info->fix.smem_len); - info->screen_base = dma_alloc_writecombine(&pdev->dev, fbi->map_size, - &fbi->map_dma, GFP_KERNEL); + info->screen_base = dma_alloc_wc(&pdev->dev, fbi->map_size, + &fbi->map_dma, GFP_KERNEL); if (!info->screen_base) { dev_err(&pdev->dev, "Failed to allocate video RAM: %d\n", ret); @@ -1005,8 +1005,8 @@ static int imxfb_probe(struct platform_device *pdev) if (pdata && pdata->exit) pdata->exit(fbi->pdev); failed_platform_init: - dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base, - fbi->map_dma); + dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base, + fbi->map_dma); failed_map: iounmap(fbi->regs); failed_ioremap: @@ -1041,8 +1041,8 @@ static int imxfb_remove(struct platform_device *pdev) kfree(info->pseudo_palette); framebuffer_release(info); - dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base, - fbi->map_dma); + dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base, + fbi->map_dma); iounmap(fbi->regs); release_mem_region(res->start, resource_size(res)); diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c index 7947634ee6b06..f91b1db262b04 100644 --- a/drivers/video/fbdev/mx3fb.c +++ b/drivers/video/fbdev/mx3fb.c @@ -1336,9 +1336,8 @@ static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len, int retval = 0; dma_addr_t addr; - fbi->screen_base = dma_alloc_writecombine(fbi->device, - mem_len, - &addr, GFP_DMA | GFP_KERNEL); + fbi->screen_base = dma_alloc_wc(fbi->device, mem_len, &addr, + GFP_DMA | GFP_KERNEL); if (!fbi->screen_base) { dev_err(fbi->device, "Cannot allocate %u bytes framebuffer memory\n", @@ -1378,8 +1377,8 @@ static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len, */ static int mx3fb_unmap_video_memory(struct fb_info *fbi) { - dma_free_writecombine(fbi->device, fbi->fix.smem_len, - fbi->screen_base, fbi->fix.smem_start); + dma_free_wc(fbi->device, fbi->fix.smem_len, fbi->screen_base, + fbi->fix.smem_start); fbi->screen_base = NULL; mutex_lock(&fbi->mm_lock); diff --git a/drivers/video/fbdev/nuc900fb.c b/drivers/video/fbdev/nuc900fb.c index 389fa2cbb7131..6680edae4696d 100644 --- a/drivers/video/fbdev/nuc900fb.c +++ b/drivers/video/fbdev/nuc900fb.c @@ -396,8 +396,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info) dev_dbg(fbi->dev, "nuc900fb_map_video_memory(fbi=%p) map_size %lu\n", fbi, map_size); - info->screen_base = dma_alloc_writecombine(fbi->dev, map_size, - &map_dma, GFP_KERNEL); + info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma, + GFP_KERNEL); if (!info->screen_base) return -ENOMEM; @@ -411,8 +411,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info) static inline void nuc900fb_unmap_video_memory(struct fb_info *info) { struct nuc900fb_info *fbi = info->par; - dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len), - info->screen_base, info->fix.smem_start); + dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len), + info->screen_base, info->fix.smem_start); } static irqreturn_t nuc900fb_irqhandler(int irq, void *dev_id) diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c index 6efa2591eaa8d..e3d9b9ea5498e 100644 --- a/drivers/video/fbdev/omap/lcdc.c +++ b/drivers/video/fbdev/omap/lcdc.c @@ -612,8 +612,8 @@ static void lcdc_dma_handler(u16 status, void *data) static int alloc_palette_ram(void) { - lcdc.palette_virt = dma_alloc_writecombine(lcdc.fbdev->dev, - MAX_PALETTE_SIZE, &lcdc.palette_phys, GFP_KERNEL); + lcdc.palette_virt = dma_alloc_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE, + &lcdc.palette_phys, GFP_KERNEL); if (lcdc.palette_virt == NULL) { dev_err(lcdc.fbdev->dev, "failed to alloc palette memory\n"); return -ENOMEM; @@ -625,8 +625,8 @@ static int alloc_palette_ram(void) static void free_palette_ram(void) { - dma_free_writecombine(lcdc.fbdev->dev, MAX_PALETTE_SIZE, - lcdc.palette_virt, lcdc.palette_phys); + dma_free_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE, lcdc.palette_virt, + lcdc.palette_phys); } static int alloc_fbmem(struct omapfb_mem_region *region) @@ -642,8 +642,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region) if (region->size > frame_size) frame_size = region->size; lcdc.vram_size = frame_size; - lcdc.vram_virt = dma_alloc_writecombine(lcdc.fbdev->dev, - lcdc.vram_size, &lcdc.vram_phys, GFP_KERNEL); + lcdc.vram_virt = dma_alloc_wc(lcdc.fbdev->dev, lcdc.vram_size, + &lcdc.vram_phys, GFP_KERNEL); if (lcdc.vram_virt == NULL) { dev_err(lcdc.fbdev->dev, "unable to allocate FB DMA memory\n"); return -ENOMEM; @@ -660,8 +660,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region) static void free_fbmem(void) { - dma_free_writecombine(lcdc.fbdev->dev, lcdc.vram_size, - lcdc.vram_virt, lcdc.vram_phys); + dma_free_wc(lcdc.fbdev->dev, lcdc.vram_size, lcdc.vram_virt, + lcdc.vram_phys); } static int setup_fbmem(struct omapfb_mem_desc *req_md) diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c index efb57c0599976..def3a501acd64 100644 --- a/drivers/video/fbdev/pxa168fb.c +++ b/drivers/video/fbdev/pxa168fb.c @@ -680,8 +680,8 @@ static int pxa168fb_probe(struct platform_device *pdev) */ info->fix.smem_len = PAGE_ALIGN(DEFAULT_FB_SIZE); - info->screen_base = dma_alloc_writecombine(fbi->dev, info->fix.smem_len, - &fbi->fb_start_dma, GFP_KERNEL); + info->screen_base = dma_alloc_wc(fbi->dev, info->fix.smem_len, + &fbi->fb_start_dma, GFP_KERNEL); if (info->screen_base == NULL) { ret = -ENOMEM; goto failed_free_info; @@ -804,8 +804,8 @@ static int pxa168fb_remove(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); - dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len), - info->screen_base, info->fix.smem_start); + dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len), + info->screen_base, info->fix.smem_start); clk_disable(fbi->clk); diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index 33b2bb315a2a4..2c0487f4f805c 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -2446,8 +2446,8 @@ static int pxafb_remove(struct platform_device *dev) free_pages_exact(fbi->video_mem, fbi->video_mem_size); - dma_free_writecombine(&dev->dev, fbi->dma_buff_size, - fbi->dma_buff, fbi->dma_buff_phys); + dma_free_wc(&dev->dev, fbi->dma_buff_size, fbi->dma_buff, + fbi->dma_buff_phys); iounmap(fbi->mmio_base); diff --git a/drivers/video/fbdev/s3c-fb.c b/drivers/video/fbdev/s3c-fb.c index f72dd12456f96..5f4f696c2ecfd 100644 --- a/drivers/video/fbdev/s3c-fb.c +++ b/drivers/video/fbdev/s3c-fb.c @@ -1105,8 +1105,7 @@ static int s3c_fb_alloc_memory(struct s3c_fb *sfb, struct s3c_fb_win *win) dev_dbg(sfb->dev, "want %u bytes for window\n", size); - fbi->screen_base = dma_alloc_writecombine(sfb->dev, size, - &map_dma, GFP_KERNEL); + fbi->screen_base = dma_alloc_wc(sfb->dev, size, &map_dma, GFP_KERNEL); if (!fbi->screen_base) return -ENOMEM; @@ -1131,8 +1130,8 @@ static void s3c_fb_free_memory(struct s3c_fb *sfb, struct s3c_fb_win *win) struct fb_info *fbi = win->fbinfo; if (fbi->screen_base) - dma_free_writecombine(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len), - fbi->screen_base, fbi->fix.smem_start); + dma_free_wc(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len), + fbi->screen_base, fbi->fix.smem_start); } /** diff --git a/drivers/video/fbdev/s3c2410fb.c b/drivers/video/fbdev/s3c2410fb.c index d6704add1601c..0dd86be36afbb 100644 --- a/drivers/video/fbdev/s3c2410fb.c +++ b/drivers/video/fbdev/s3c2410fb.c @@ -645,8 +645,8 @@ static int s3c2410fb_map_video_memory(struct fb_info *info) dprintk("map_video_memory(fbi=%p) map_size %u\n", fbi, map_size); - info->screen_base = dma_alloc_writecombine(fbi->dev, map_size, - &map_dma, GFP_KERNEL); + info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma, + GFP_KERNEL); if (info->screen_base) { /* prevent initial garbage on screen */ @@ -667,8 +667,8 @@ static inline void s3c2410fb_unmap_video_memory(struct fb_info *info) { struct s3c2410fb_info *fbi = info->par; - dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len), - info->screen_base, info->fix.smem_start); + dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len), + info->screen_base, info->fix.smem_start); } static inline void modify_gpio(void __iomem *reg, diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c index dcf774c158896..fc2aaa5aca234 100644 --- a/drivers/video/fbdev/sa1100fb.c +++ b/drivers/video/fbdev/sa1100fb.c @@ -567,8 +567,8 @@ static int sa1100fb_mmap(struct fb_info *info, if (off < info->fix.smem_len) { vma->vm_pgoff += 1; /* skip over the palette */ - return dma_mmap_writecombine(fbi->dev, vma, fbi->map_cpu, - fbi->map_dma, fbi->map_size); + return dma_mmap_wc(fbi->dev, vma, fbi->map_cpu, fbi->map_dma, + fbi->map_size); } vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); @@ -1099,8 +1099,8 @@ static int sa1100fb_map_video_memory(struct sa1100fb_info *fbi) * of the framebuffer. */ fbi->map_size = PAGE_ALIGN(fbi->fb.fix.smem_len + PAGE_SIZE); - fbi->map_cpu = dma_alloc_writecombine(fbi->dev, fbi->map_size, - &fbi->map_dma, GFP_KERNEL); + fbi->map_cpu = dma_alloc_wc(fbi->dev, fbi->map_size, &fbi->map_dma, + GFP_KERNEL); if (fbi->map_cpu) { fbi->fb.screen_base = fbi->map_cpu + PAGE_SIZE; diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index c0c11fad4611a..7760fc1a2218e 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -679,7 +679,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) pci_read_config_dword(pci_dev, notify + offsetof(struct virtio_pci_notify_cap, - cap.length), + cap.offset), ¬ify_offset); /* We don't know how many VQs we'll map, ahead of the time. diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 0f6d8515ba4f1..80825a7e8e48e 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1569,6 +1569,17 @@ config WATCHDOG_RIO machines. The watchdog timeout period is normally one minute but can be changed with a boot-time parameter. +config WATCHDOG_SUN4V + tristate "Sun4v Watchdog support" + select WATCHDOG_CORE + depends on SPARC64 + help + Say Y here to support the hypervisor watchdog capability embedded + in the SPARC sun4v architecture. + + To compile this driver as a module, choose M here. The module will + be called sun4v_wdt. + # XTENSA Architecture # Xen Architecture diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index f566753256abb..f6a6a387c6c71 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -179,6 +179,7 @@ obj-$(CONFIG_SH_WDT) += shwdt.o obj-$(CONFIG_WATCHDOG_RIO) += riowd.o obj-$(CONFIG_WATCHDOG_CP1XXX) += cpwd.o +obj-$(CONFIG_WATCHDOG_SUN4V) += sun4v_wdt.o # XTENSA Architecture diff --git a/drivers/watchdog/sun4v_wdt.c b/drivers/watchdog/sun4v_wdt.c new file mode 100644 index 0000000000000..1467fe50a76fa --- /dev/null +++ b/drivers/watchdog/sun4v_wdt.c @@ -0,0 +1,191 @@ +/* + * sun4v watchdog timer + * (c) Copyright 2016 Oracle Corporation + * + * Implement a simple watchdog driver using the built-in sun4v hypervisor + * watchdog support. If time expires, the hypervisor stops or bounces + * the guest domain. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#define WDT_TIMEOUT 60 +#define WDT_MAX_TIMEOUT 31536000 +#define WDT_MIN_TIMEOUT 1 +#define WDT_DEFAULT_RESOLUTION_MS 1000 /* 1 second */ + +static unsigned int timeout; +module_param(timeout, uint, 0); +MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default=" + __MODULE_STRING(WDT_TIMEOUT) ")"); + +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, S_IRUGO); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +static int sun4v_wdt_stop(struct watchdog_device *wdd) +{ + sun4v_mach_set_watchdog(0, NULL); + + return 0; +} + +static int sun4v_wdt_ping(struct watchdog_device *wdd) +{ + int hverr; + + /* + * HV watchdog timer will round up the timeout + * passed in to the nearest multiple of the + * watchdog resolution in milliseconds. + */ + hverr = sun4v_mach_set_watchdog(wdd->timeout * 1000, NULL); + if (hverr == HV_EINVAL) + return -EINVAL; + + return 0; +} + +static int sun4v_wdt_set_timeout(struct watchdog_device *wdd, + unsigned int timeout) +{ + wdd->timeout = timeout; + + return 0; +} + +static const struct watchdog_info sun4v_wdt_ident = { + .options = WDIOF_SETTIMEOUT | + WDIOF_MAGICCLOSE | + WDIOF_KEEPALIVEPING, + .identity = "sun4v hypervisor watchdog", + .firmware_version = 0, +}; + +static struct watchdog_ops sun4v_wdt_ops = { + .owner = THIS_MODULE, + .start = sun4v_wdt_ping, + .stop = sun4v_wdt_stop, + .ping = sun4v_wdt_ping, + .set_timeout = sun4v_wdt_set_timeout, +}; + +static struct watchdog_device wdd = { + .info = &sun4v_wdt_ident, + .ops = &sun4v_wdt_ops, + .min_timeout = WDT_MIN_TIMEOUT, + .max_timeout = WDT_MAX_TIMEOUT, + .timeout = WDT_TIMEOUT, +}; + +static int __init sun4v_wdt_init(void) +{ + struct mdesc_handle *handle; + u64 node; + const u64 *value; + int err = 0; + unsigned long major = 1, minor = 1; + + /* + * There are 2 properties that can be set from the control + * domain for the watchdog. + * watchdog-resolution + * watchdog-max-timeout + * + * We can expect a handle to be returned otherwise something + * serious is wrong. Correct to return -ENODEV here. + */ + + handle = mdesc_grab(); + if (!handle) + return -ENODEV; + + node = mdesc_node_by_name(handle, MDESC_NODE_NULL, "platform"); + err = -ENODEV; + if (node == MDESC_NODE_NULL) + goto out_release; + + /* + * This is a safe way to validate if we are on the right + * platform. + */ + if (sun4v_hvapi_register(HV_GRP_CORE, major, &minor)) + goto out_hv_unreg; + + /* Allow value of watchdog-resolution up to 1s (default) */ + value = mdesc_get_property(handle, node, "watchdog-resolution", NULL); + err = -EINVAL; + if (value) { + if (*value == 0 || + *value > WDT_DEFAULT_RESOLUTION_MS) + goto out_hv_unreg; + } + + value = mdesc_get_property(handle, node, "watchdog-max-timeout", NULL); + if (value) { + /* + * If the property value (in ms) is smaller than + * min_timeout, return -EINVAL. + */ + if (*value < wdd.min_timeout * 1000) + goto out_hv_unreg; + + /* + * If the property value is smaller than + * default max_timeout then set watchdog max_timeout to + * the value of the property in seconds. + */ + if (*value < wdd.max_timeout * 1000) + wdd.max_timeout = *value / 1000; + } + + watchdog_init_timeout(&wdd, timeout, NULL); + + watchdog_set_nowayout(&wdd, nowayout); + + err = watchdog_register_device(&wdd); + if (err) + goto out_hv_unreg; + + pr_info("initialized (timeout=%ds, nowayout=%d)\n", + wdd.timeout, nowayout); + + mdesc_release(handle); + + return 0; + +out_hv_unreg: + sun4v_hvapi_unregister(HV_GRP_CORE); + +out_release: + mdesc_release(handle); + return err; +} + +static void __exit sun4v_wdt_exit(void) +{ + sun4v_hvapi_unregister(HV_GRP_CORE); + watchdog_unregister_device(&wdd); +} + +module_init(sun4v_wdt_init); +module_exit(sun4v_wdt_exit); + +MODULE_AUTHOR("Wim Coekaerts "); +MODULE_DESCRIPTION("sun4v watchdog driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 12eab503efd1b..dc4305b407bf6 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -257,7 +257,7 @@ static struct resource *additional_memory_resource(phys_addr_t size) return NULL; res->name = "System RAM"; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; ret = allocate_resource(&iomem_resource, res, size, 0, -1, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4545e2e2ad45a..5699bbc23feba 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -931,7 +931,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags) if (bio_flags & EXTENT_BIO_TREE_LOG) return 0; #ifdef CONFIG_X86 - if (static_cpu_has_safe(X86_FEATURE_XMM4_2)) + if (static_cpu_has(X86_FEATURE_XMM4_2)) return 0; #endif return 1; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7cf8509deda7c..2c849b08a91b5 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + if (err == -EEXIST) + err = 0; if (err) { - BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c22213789090f..19adeb0ef82a3 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1756,6 +1756,10 @@ int ceph_pool_perm_check(struct ceph_inode_info *ci, int need) u32 pool; int ret, flags; + /* does not support pool namespace yet */ + if (ci->i_pool_ns_len) + return -EIO; + if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode), NOPOOLPERM)) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index cdbf8cf3d52c3..6fe0ad26a7dfc 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2753,7 +2753,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, void *inline_data, int inline_len, struct ceph_buffer *xattr_buf, struct ceph_mds_session *session, - struct ceph_cap *cap, int issued) + struct ceph_cap *cap, int issued, + u32 pool_ns_len) __releases(ci->i_ceph_lock) __releases(mdsc->snap_rwsem) { @@ -2873,6 +2874,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) { /* file layout may have changed */ ci->i_layout = grant->layout; + ci->i_pool_ns_len = pool_ns_len; + /* size/truncate_seq? */ queue_trunc = ceph_fill_file_size(inode, issued, le32_to_cpu(grant->truncate_seq), @@ -3411,6 +3414,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, u32 inline_len = 0; void *snaptrace; size_t snaptrace_len; + u32 pool_ns_len = 0; void *p, *end; dout("handle_caps from mds%d\n", mds); @@ -3463,6 +3467,21 @@ void ceph_handle_caps(struct ceph_mds_session *session, p += inline_len; } + if (le16_to_cpu(msg->hdr.version) >= 8) { + u64 flush_tid; + u32 caller_uid, caller_gid; + u32 osd_epoch_barrier; + /* version >= 5 */ + ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad); + /* version >= 6 */ + ceph_decode_64_safe(&p, end, flush_tid, bad); + /* version >= 7 */ + ceph_decode_32_safe(&p, end, caller_uid, bad); + ceph_decode_32_safe(&p, end, caller_gid, bad); + /* version >= 8 */ + ceph_decode_32_safe(&p, end, pool_ns_len, bad); + } + /* lookup ino */ inode = ceph_find_inode(sb, vino); ci = ceph_inode(inode); @@ -3518,7 +3537,8 @@ void ceph_handle_caps(struct ceph_mds_session *session, &cap, &issued); handle_cap_grant(mdsc, inode, h, inline_version, inline_data, inline_len, - msg->middle, session, cap, issued); + msg->middle, session, cap, issued, + pool_ns_len); if (realm) ceph_put_snap_realm(mdsc, realm); goto done_unlocked; @@ -3542,7 +3562,8 @@ void ceph_handle_caps(struct ceph_mds_session *session, issued |= __ceph_caps_dirty(ci); handle_cap_grant(mdsc, inode, h, inline_version, inline_data, inline_len, - msg->middle, session, cap, issued); + msg->middle, session, cap, issued, + pool_ns_len); goto done_unlocked; case CEPH_CAP_OP_FLUSH_ACK: diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index fb4ba2e4e2a5f..5849b88bbed3c 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -396,6 +396,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) ci->i_symlink = NULL; memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout)); + ci->i_pool_ns_len = 0; ci->i_fragtree = RB_ROOT; mutex_init(&ci->i_fragtree_mutex); @@ -756,6 +757,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool) ci->i_ceph_flags &= ~CEPH_I_POOL_PERM; ci->i_layout = info->layout; + ci->i_pool_ns_len = iinfo->pool_ns_len; queue_trunc = ceph_fill_file_size(inode, issued, le32_to_cpu(info->truncate_seq), diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index e7b130a637f9f..911d64d865f17 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -100,6 +100,14 @@ static int parse_reply_info_in(void **p, void *end, } else info->inline_version = CEPH_INLINE_NONE; + if (features & CEPH_FEATURE_FS_FILE_LAYOUT_V2) { + ceph_decode_32_safe(p, end, info->pool_ns_len, bad); + ceph_decode_need(p, end, info->pool_ns_len, bad); + *p += info->pool_ns_len; + } else { + info->pool_ns_len = 0; + } + return 0; bad: return err; @@ -2298,6 +2306,14 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); + /* deny access to directories with pool_ns layouts */ + if (req->r_inode && S_ISDIR(req->r_inode->i_mode) && + ceph_inode(req->r_inode)->i_pool_ns_len) + return -EIO; + if (req->r_locked_dir && + ceph_inode(req->r_locked_dir)->i_pool_ns_len) + return -EIO; + /* issue */ mutex_lock(&mdsc->mutex); __register_request(mdsc, req, dir); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index ccf11ef0ca871..37712ccffcc6b 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -44,6 +44,7 @@ struct ceph_mds_reply_info_in { u64 inline_version; u32 inline_len; char *inline_data; + u32 pool_ns_len; }; /* diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 75b7d125ce668..9c458eb522458 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -287,6 +287,7 @@ struct ceph_inode_info { struct ceph_dir_layout i_dir_layout; struct ceph_file_layout i_layout; + size_t i_pool_ns_len; char *i_symlink; /* for dirs */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c48ca13673e37..2eea40353e608 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1013,7 +1013,6 @@ const struct file_operations cifs_file_strict_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .clone_file_range = cifs_clone_file_range, - .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 68c4547528c48..83aac8ba50b0e 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -31,19 +31,15 @@ * so that it will fit. We use hash_64 to convert the value to 31 bits, and * then add 1, to ensure that we don't end up with a 0 as the value. */ -#if BITS_PER_LONG == 64 static inline ino_t cifs_uniqueid_to_ino_t(u64 fileid) { + if ((sizeof(ino_t)) < (sizeof(u64))) + return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; + return (ino_t)fileid; + } -#else -static inline ino_t -cifs_uniqueid_to_ino_t(u64 fileid) -{ - return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; -} -#endif extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 90b4f9f7de660..76fcb50295a38 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1396,11 +1396,10 @@ CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, int *oplock, * current bigbuf. */ static int -cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = get_rfc1002_length(server->smallbuf); int remaining = rfclen + 4 - server->total_read; - struct cifs_readdata *rdata = mid->callback_data; while (remaining > 0) { int length; @@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) remaining -= length; } - dequeue_mid(mid, rdata->result); return 0; } +static int +cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + int length; + struct cifs_readdata *rdata = mid->callback_data; + + length = discard_remaining_data(server); + dequeue_mid(mid, rdata->result); + return length; +} + int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { @@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_status_pending && + server->ops->is_status_pending(buf, server, 0)) { + discard_remaining_data(server); + return -1; + } + /* Was the SMB read successful? */ rdata->result = server->ops->map_error(buf, false); if (rdata->result != 0) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 10f8d5cf5681e..42e1f440eb1e9 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1106,21 +1106,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, { char *data_offset; struct create_context *cc; - unsigned int next = 0; + unsigned int next; + unsigned int remaining; char *name; data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); + remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; - do { - cc = (struct create_context *)((char *)cc + next); + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) != 4 || - strncmp(name, "RqLs", 4)) { - next = le32_to_cpu(cc->Next); - continue; - } - return server->ops->parse_lease_buf(cc, epoch); - } while (next != 0); + if (le16_to_cpu(cc->NameLength) == 4 && + strncmp(name, "RqLs", 4) == 0) + return server->ops->parse_lease_buf(cc, epoch); + + next = le32_to_cpu(cc->Next); + if (!next) + break; + remaining -= next; + cc = (struct create_context *)((char *)cc + next); + } return 0; } diff --git a/fs/dax.c b/fs/dax.c index 711172450da64..bbb2ad7837702 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1056,6 +1056,7 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault); int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct file *file = vma->vm_file; + int error; /* * We pass NO_SECTOR to dax_radix_entry() because we expect that a @@ -1065,7 +1066,13 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) * saves us from having to make a call to get_block() here to look * up the sector. */ - dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, true); + error = dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, + true); + + if (error == -ENOMEM) + return VM_FAULT_OOM; + if (error) + return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); diff --git a/fs/dcache.c b/fs/dcache.c index 92d5140de8516..2398f9f943375 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } -/* - * Make sure other CPUs see the inode attached before the type is set. - */ static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry, unsigned flags; dentry->d_inode = inode; - smp_wmb(); flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; WRITE_ONCE(dentry->d_flags, flags); } -/* - * Ideally, we want to make sure that other CPUs see the flags cleared before - * the inode is detached, but this is really a violation of RCU principles - * since the ordering suggests we should always set inode before flags. - * - * We should instead replace or discard the entire dentry - but that sucks - * performancewise on mass deletion/rename. - */ static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); - smp_wmb(); dentry->d_inode = NULL; } @@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; + + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1758,8 +1747,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); if (inode) hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); fsnotify_d_instantiate(dentry, inode); } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index e032a0423e351..4098acc701c3e 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -390,6 +390,7 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); if (*err < 0) break; + bh = bh->b_this_page; } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1f76d8950a57f..5c46ed9f3e140 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi, #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ +static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); +static struct workqueue_struct *isw_wq; + void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -317,7 +320,6 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; - struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -424,8 +426,9 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) wb_put(new_wb); iput(inode); - deactivate_super(sb); kfree(isw); + + atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) @@ -435,7 +438,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); - schedule_work(&isw->work); + queue_work(isw_wq, &isw->work); } /** @@ -471,20 +474,20 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); - - if (inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) - goto out_unlock; - - if (!atomic_inc_not_zero(&inode->i_sb->s_active)) - goto out_unlock; - + if (!(inode->i_sb->s_flags & MS_ACTIVE) || + inode->i_state & (I_WB_SWITCH | I_FREEING) || + inode_to_wb(inode) == isw->new_wb) { + spin_unlock(&inode->i_lock); + goto out_free; + } inode->i_state |= I_WB_SWITCH; spin_unlock(&inode->i_lock); ihold(inode); isw->inode = inode; + atomic_inc(&isw_nr_in_flight); + /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the mapping's @@ -494,8 +497,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; -out_unlock: - spin_unlock(&inode->i_lock); out_free: if (isw->new_wb) wb_put(isw->new_wb); @@ -847,6 +848,33 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, wb_put(last_wb); } +/** + * cgroup_writeback_umount - flush inode wb switches for umount + * + * This function is called when a super_block is about to be destroyed and + * flushes in-flight inode wb switches. An inode wb switch goes through + * RCU and then workqueue, so the two need to be flushed in order to ensure + * that all previously scheduled switches are finished. As wb switches are + * rare occurrences and synchronize_rcu() can take a while, perform + * flushing iff wb switches are in flight. + */ +void cgroup_writeback_umount(void) +{ + if (atomic_read(&isw_nr_in_flight)) { + synchronize_rcu(); + flush_workqueue(isw_wq); + } +} + +static int __init cgroup_writeback_init(void) +{ + isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); + if (!isw_wq) + return -ENOMEM; + return 0; +} +fs_initcall(cgroup_writeback_init); + #else /* CONFIG_CGROUP_WRITEBACK */ static struct bdi_writeback * diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking index 3ea36554107fc..8918ac905a3b1 100644 --- a/fs/jffs2/README.Locking +++ b/fs/jffs2/README.Locking @@ -2,10 +2,6 @@ JFFS2 LOCKING DOCUMENTATION --------------------------- -At least theoretically, JFFS2 does not require the Big Kernel Lock -(BKL), which was always helpfully obtained for it by Linux 2.4 VFS -code. It has its own locking, as described below. - This document attempts to describe the existing locking rules for JFFS2. It is not expected to remain perfectly up to date, but ought to be fairly close. @@ -69,6 +65,7 @@ Ordering constraints: any f->sem held. 2. Never attempt to lock two file mutexes in one thread. No ordering rules have been made for doing so. + 3. Never lock a page cache page with f->sem held. erase_completion_lock spinlock diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index 0ae91ad6df2dc..b288c8ae1236b 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -50,7 +50,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c) static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, - struct jffs2_inode_cache *ic) + struct jffs2_inode_cache *ic, + int *dir_hardlinks) { struct jffs2_full_dirent *fd; @@ -69,19 +70,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n", fd->name, fd->ino, ic->ino); jffs2_mark_node_obsolete(c, fd->raw); + /* Clear the ic/raw union so it doesn't cause problems later. */ + fd->ic = NULL; continue; } + /* From this point, fd->raw is no longer used so we can set fd->ic */ + fd->ic = child_ic; + child_ic->pino_nlink++; + /* If we appear (at this stage) to have hard-linked directories, + * set a flag to trigger a scan later */ if (fd->type == DT_DIR) { - if (child_ic->pino_nlink) { - JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n", - fd->name, fd->ino, ic->ino); - /* TODO: What do we do about it? */ - } else { - child_ic->pino_nlink = ic->ino; - } - } else - child_ic->pino_nlink++; + child_ic->flags |= INO_FLAGS_IS_DIR; + if (child_ic->pino_nlink > 1) + *dir_hardlinks = 1; + } dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino); /* Can't free scan_dents so far. We might need them in pass 2 */ @@ -95,8 +98,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, */ static int jffs2_build_filesystem(struct jffs2_sb_info *c) { - int ret; - int i; + int ret, i, dir_hardlinks = 0; struct jffs2_inode_cache *ic; struct jffs2_full_dirent *fd; struct jffs2_full_dirent *dead_fds = NULL; @@ -120,7 +122,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) /* Now scan the directory tree, increasing nlink according to every dirent found. */ for_each_inode(i, c, ic) { if (ic->scan_dents) { - jffs2_build_inode_pass1(c, ic); + jffs2_build_inode_pass1(c, ic, &dir_hardlinks); cond_resched(); } } @@ -156,6 +158,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) } dbg_fsbuild("pass 2a complete\n"); + + if (dir_hardlinks) { + /* If we detected directory hardlinks earlier, *hopefully* + * they are gone now because some of the links were from + * dead directories which still had some old dirents lying + * around and not yet garbage-collected, but which have + * been discarded above. So clear the pino_nlink field + * in each directory, so that the final scan below can + * print appropriate warnings. */ + for_each_inode(i, c, ic) { + if (ic->flags & INO_FLAGS_IS_DIR) + ic->pino_nlink = 0; + } + } dbg_fsbuild("freeing temporary data structures\n"); /* Finally, we can scan again and free the dirent structs */ @@ -163,6 +179,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) while(ic->scan_dents) { fd = ic->scan_dents; ic->scan_dents = fd->next; + /* We do use the pino_nlink field to count nlink of + * directories during fs build, so set it to the + * parent ino# now. Now that there's hopefully only + * one. */ + if (fd->type == DT_DIR) { + if (!fd->ic) { + /* We'll have complained about it and marked the coresponding + raw node obsolete already. Just skip it. */ + continue; + } + + /* We *have* to have set this in jffs2_build_inode_pass1() */ + BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR)); + + /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks + * is set. Otherwise, we know this should never trigger anyway, so + * we don't do the check. And ic->pino_nlink still contains the nlink + * value (which is 1). */ + if (dir_hardlinks && fd->ic->pino_nlink) { + JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n", + fd->name, fd->ino, ic->ino, fd->ic->pino_nlink); + /* Should we unlink it from its previous parent? */ + } + + /* For directories, ic->pino_nlink holds that parent inode # */ + fd->ic->pino_nlink = ic->ino; + } jffs2_free_full_dirent(fd); } ic->scan_dents = NULL; @@ -241,11 +284,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c, /* Reduce nlink of the child. If it's now zero, stick it on the dead_fds list to be cleaned up later. Else just free the fd */ - - if (fd->type == DT_DIR) - child_ic->pino_nlink = 0; - else - child_ic->pino_nlink--; + child_ic->pino_nlink--; if (!child_ic->pino_nlink) { dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n", diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index d211b8e185667..30c4c9ebb693f 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n", __func__, ret); - /* Might as well let the VFS know */ - d_instantiate(new_dentry, d_inode(old_dentry)); - ihold(d_inode(old_dentry)); + /* + * We can't keep the target in dcache after that. + * For one thing, we can't afford dentry aliases for directories. + * For another, if there was a victim, we _can't_ set new inode + * for that sucker and we have to trigger mount eviction - the + * caller won't do it on its own since we are returning an error. + */ + d_invalidate(new_dentry); new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); return ret; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index c5ac5944bc1bd..cad86bac34530 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -137,39 +137,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; - uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; - jffs2_dbg(1, "%s()\n", __func__); - - if (pageofs > inode->i_size) { - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - return ret; - } - - mutex_lock(&f->sem); pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) { - if (alloc_len) - jffs2_complete_reservation(c); - mutex_unlock(&f->sem); + if (!pg) return -ENOMEM; - } *pagep = pg; - if (alloc_len) { + jffs2_dbg(1, "%s()\n", __func__); + + if (pageofs > inode->i_size) { /* Make new hole frag from old EOF to new page */ + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; + uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + goto out_page; + + mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -196,6 +190,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -210,10 +205,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; + mutex_unlock(&f->sem); } /* @@ -222,18 +219,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { + mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); + mutex_unlock(&f->sem); if (ret) goto out_page; } - mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); - mutex_unlock(&f->sem); return ret; } diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 5a2dec2b064c9..95d5880a63ee1 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era BUG_ON(start > orig_start); } - /* First, use readpage() to read the appropriate page into the page cache */ - /* Q: What happens if we actually try to GC the _same_ page for which commit_write() - * triggered garbage collection in the first place? - * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the - * page OK. We'll actually write it out again in commit_write, which is a little - * suboptimal, but at least we're correct. - */ + /* The rules state that we must obtain the page lock *before* f->sem, so + * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's + * actually going to *change* so we're safe; we only allow reading. + * + * It is important to note that jffs2_write_begin() will ensure that its + * page is marked Uptodate before allocating space. That means that if we + * end up here trying to GC the *same* page that jffs2_write_begin() is + * trying to write out, read_cache_page() will not deadlock. */ + mutex_unlock(&f->sem); pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg); + mutex_lock(&f->sem); if (IS_ERR(pg_ptr)) { pr_warn("read_cache_page() returned error: %ld\n", diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index fa35ff79ab358..0637271f37701 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -194,6 +194,7 @@ struct jffs2_inode_cache { #define INO_STATE_CLEARING 6 /* In clear_inode() */ #define INO_FLAGS_XATTR_CHECKED 0x01 /* has no duplicate xattr_ref */ +#define INO_FLAGS_IS_DIR 0x02 /* is a directory */ #define RAWNODE_CLASS_INODE_CACHE 0 #define RAWNODE_CLASS_XATTR_DATUM 1 @@ -249,7 +250,10 @@ struct jffs2_readinode_info struct jffs2_full_dirent { - struct jffs2_raw_node_ref *raw; + union { + struct jffs2_raw_node_ref *raw; + struct jffs2_inode_cache *ic; /* Just during part of build */ + }; struct jffs2_full_dirent *next; uint32_t version; uint32_t ino; /* == zero for unlink */ diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 26c2de2de13fd..b7f8eaeea5d83 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx, d_rehash(newdent); } else { spin_lock(&dentry->d_lock); - NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE; + NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE; spin_unlock(&dentry->d_lock); } } else { diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 9581d190f6e12..77ebc2bc1cca1 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -147,6 +147,10 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret < 0) { mlog_errno(ret); + if (ret == -ENOMEM) + ret = VM_FAULT_OOM; + else + ret = VM_FAULT_SIGBUS; goto out; } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index ed95272d57a61..52f6de5d40a92 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -618,7 +618,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir) * sole user of this dentry. Too tricky... Just unhash for * now. */ - d_drop(dentry); + if (!err) + d_drop(dentry); inode_unlock(dir); return err; @@ -903,6 +904,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, if (!overwrite && new_is_dir && !old_opaque && new_opaque) ovl_remove_opaque(newdentry); + /* + * Old dentry now lives in different location. Dentries in + * lowerstack are stale. We cannot drop them here because + * access to them is lockless. This could be only pure upper + * or opaque directory - numlower is zero. Or upper non-dir + * entry - its pureness is tracked by flag opaque. + */ if (old_opaque != new_opaque) { ovl_dentry_set_opaque(old, new_opaque); if (!overwrite) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 49e204560655a..a4ff5d0d7db91 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -65,6 +65,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) inode_lock(upperdentry->d_inode); err = notify_change(upperdentry, attr, NULL); + if (!err) + ovl_copyattr(upperdentry->d_inode, dentry->d_inode); inode_unlock(upperdentry->d_inode); } ovl_drop_write(dentry); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 8d826bd56b26b..619ad4b016d20 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -76,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) if (oe->__upperdentry) { type = __OVL_PATH_UPPER; - if (oe->numlower) { - if (S_ISDIR(dentry->d_inode->i_mode)) - type |= __OVL_PATH_MERGE; - } else if (!oe->opaque) { + /* + * Non-dir dentry can hold lower dentry from previous + * location. Its purity depends only on opaque flag. + */ + if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode)) + type |= __OVL_PATH_MERGE; + else if (!oe->opaque) type |= __OVL_PATH_PURE; - } } else { if (oe->numlower > 1) type |= __OVL_PATH_MERGE; @@ -341,6 +343,7 @@ static const struct dentry_operations ovl_dentry_operations = { static const struct dentry_operations ovl_reval_dentry_operations = { .d_release = ovl_dentry_release, + .d_select_inode = ovl_d_select_inode, .d_revalidate = ovl_dentry_revalidate, .d_weak_revalidate = ovl_dentry_weak_revalidate, }; diff --git a/fs/super.c b/fs/super.c index 1182af8fd5ff3..74914b1bae70f 100644 --- a/fs/super.c +++ b/fs/super.c @@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb) sb->s_flags &= ~MS_ACTIVE; fsnotify_unmount_inodes(sb); + cgroup_writeback_umount(); evict_inodes(sb); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 50311703135bc..66cdb44616d5a 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -286,6 +286,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address, if (unlikely(ACCESS_ONCE(ctx->released))) goto out; + /* + * We don't do userfault handling for the final child pid update. + */ + if (current->flags & PF_EXITING) + goto out; + /* * Check that we can return VM_FAULT_RETRY. * diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 594f7e63b4324..be5568839442d 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1109,27 +1109,10 @@ xlog_verify_head( bool tmp_wrapped; /* - * Search backwards through the log looking for the log record header - * block. This wraps all the way back around to the head so something is - * seriously wrong if we can't find it. - */ - found = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, rhead_blk, - rhead, wrapped); - if (found < 0) - return found; - if (!found) { - xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); - return -EIO; - } - - *tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn)); - - /* - * Now that we have a tail block, check the head of the log for torn - * writes. Search again until we hit the tail or the maximum number of - * log record I/Os that could have been in flight at one time. Use a - * temporary buffer so we don't trash the rhead/bp pointer from the - * call above. + * Check the head of the log for torn writes. Search backwards from the + * head until we hit the tail or the maximum number of log record I/Os + * that could have been in flight at one time. Use a temporary buffer so + * we don't trash the rhead/bp pointers from the caller. */ tmp_bp = xlog_get_bp(log, 1); if (!tmp_bp) @@ -1215,6 +1198,115 @@ xlog_verify_head( return error; } +/* + * Check whether the head of the log points to an unmount record. In other + * words, determine whether the log is clean. If so, update the in-core state + * appropriately. + */ +static int +xlog_check_unmount_rec( + struct xlog *log, + xfs_daddr_t *head_blk, + xfs_daddr_t *tail_blk, + struct xlog_rec_header *rhead, + xfs_daddr_t rhead_blk, + struct xfs_buf *bp, + bool *clean) +{ + struct xlog_op_header *op_head; + xfs_daddr_t umount_data_blk; + xfs_daddr_t after_umount_blk; + int hblks; + int error; + char *offset; + + *clean = false; + + /* + * Look for unmount record. If we find it, then we know there was a + * clean unmount. Since 'i' could be the last block in the physical + * log, we convert to a log block before comparing to the head_blk. + * + * Save the current tail lsn to use to pass to xlog_clear_stale_blocks() + * below. We won't want to clear the unmount record if there is one, so + * we pass the lsn of the unmount record rather than the block after it. + */ + if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { + int h_size = be32_to_cpu(rhead->h_size); + int h_version = be32_to_cpu(rhead->h_version); + + if ((h_version & XLOG_VERSION_2) && + (h_size > XLOG_HEADER_CYCLE_SIZE)) { + hblks = h_size / XLOG_HEADER_CYCLE_SIZE; + if (h_size % XLOG_HEADER_CYCLE_SIZE) + hblks++; + } else { + hblks = 1; + } + } else { + hblks = 1; + } + after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)); + after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize); + if (*head_blk == after_umount_blk && + be32_to_cpu(rhead->h_num_logops) == 1) { + umount_data_blk = rhead_blk + hblks; + umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize); + error = xlog_bread(log, umount_data_blk, 1, bp, &offset); + if (error) + return error; + + op_head = (struct xlog_op_header *)offset; + if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) { + /* + * Set tail and last sync so that newly written log + * records will point recovery to after the current + * unmount record. + */ + xlog_assign_atomic_lsn(&log->l_tail_lsn, + log->l_curr_cycle, after_umount_blk); + xlog_assign_atomic_lsn(&log->l_last_sync_lsn, + log->l_curr_cycle, after_umount_blk); + *tail_blk = after_umount_blk; + + *clean = true; + } + } + + return 0; +} + +static void +xlog_set_state( + struct xlog *log, + xfs_daddr_t head_blk, + struct xlog_rec_header *rhead, + xfs_daddr_t rhead_blk, + bool bump_cycle) +{ + /* + * Reset log values according to the state of the log when we + * crashed. In the case where head_blk == 0, we bump curr_cycle + * one because the next write starts a new cycle rather than + * continuing the cycle of the last good log record. At this + * point we have guaranteed that all partial log records have been + * accounted for. Therefore, we know that the last good log record + * written was complete and ended exactly on the end boundary + * of the physical log. + */ + log->l_prev_block = rhead_blk; + log->l_curr_block = (int)head_blk; + log->l_curr_cycle = be32_to_cpu(rhead->h_cycle); + if (bump_cycle) + log->l_curr_cycle++; + atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); + atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); + xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle, + BBTOB(log->l_curr_block)); + xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle, + BBTOB(log->l_curr_block)); +} + /* * Find the sync block number or the tail of the log. * @@ -1238,22 +1330,20 @@ xlog_find_tail( xfs_daddr_t *tail_blk) { xlog_rec_header_t *rhead; - xlog_op_header_t *op_head; char *offset = NULL; xfs_buf_t *bp; int error; - xfs_daddr_t umount_data_blk; - xfs_daddr_t after_umount_blk; xfs_daddr_t rhead_blk; xfs_lsn_t tail_lsn; - int hblks; bool wrapped = false; + bool clean = false; /* * Find previous log record */ if ((error = xlog_find_head(log, head_blk))) return error; + ASSERT(*head_blk < INT_MAX); bp = xlog_get_bp(log, 1); if (!bp) @@ -1271,99 +1361,74 @@ xlog_find_tail( } /* - * Trim the head block back to skip over torn records. We can have - * multiple log I/Os in flight at any time, so we assume CRC failures - * back through the previous several records are torn writes and skip - * them. + * Search backwards through the log looking for the log record header + * block. This wraps all the way back around to the head so something is + * seriously wrong if we can't find it. */ - ASSERT(*head_blk < INT_MAX); - error = xlog_verify_head(log, head_blk, tail_blk, bp, &rhead_blk, - &rhead, &wrapped); - if (error) - goto done; + error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, + &rhead_blk, &rhead, &wrapped); + if (error < 0) + return error; + if (!error) { + xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__); + return -EIO; + } + *tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn)); /* - * Reset log values according to the state of the log when we - * crashed. In the case where head_blk == 0, we bump curr_cycle - * one because the next write starts a new cycle rather than - * continuing the cycle of the last good log record. At this - * point we have guaranteed that all partial log records have been - * accounted for. Therefore, we know that the last good log record - * written was complete and ended exactly on the end boundary - * of the physical log. + * Set the log state based on the current head record. */ - log->l_prev_block = rhead_blk; - log->l_curr_block = (int)*head_blk; - log->l_curr_cycle = be32_to_cpu(rhead->h_cycle); - if (wrapped) - log->l_curr_cycle++; - atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); - atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); - xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle, - BBTOB(log->l_curr_block)); - xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle, - BBTOB(log->l_curr_block)); + xlog_set_state(log, *head_blk, rhead, rhead_blk, wrapped); + tail_lsn = atomic64_read(&log->l_tail_lsn); /* - * Look for unmount record. If we find it, then we know there - * was a clean unmount. Since 'i' could be the last block in - * the physical log, we convert to a log block before comparing - * to the head_blk. + * Look for an unmount record at the head of the log. This sets the log + * state to determine whether recovery is necessary. + */ + error = xlog_check_unmount_rec(log, head_blk, tail_blk, rhead, + rhead_blk, bp, &clean); + if (error) + goto done; + + /* + * Verify the log head if the log is not clean (e.g., we have anything + * but an unmount record at the head). This uses CRC verification to + * detect and trim torn writes. If discovered, CRC failures are + * considered torn writes and the log head is trimmed accordingly. * - * Save the current tail lsn to use to pass to - * xlog_clear_stale_blocks() below. We won't want to clear the - * unmount record if there is one, so we pass the lsn of the - * unmount record rather than the block after it. + * Note that we can only run CRC verification when the log is dirty + * because there's no guarantee that the log data behind an unmount + * record is compatible with the current architecture. */ - if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) { - int h_size = be32_to_cpu(rhead->h_size); - int h_version = be32_to_cpu(rhead->h_version); + if (!clean) { + xfs_daddr_t orig_head = *head_blk; - if ((h_version & XLOG_VERSION_2) && - (h_size > XLOG_HEADER_CYCLE_SIZE)) { - hblks = h_size / XLOG_HEADER_CYCLE_SIZE; - if (h_size % XLOG_HEADER_CYCLE_SIZE) - hblks++; - } else { - hblks = 1; - } - } else { - hblks = 1; - } - after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len)); - after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize); - tail_lsn = atomic64_read(&log->l_tail_lsn); - if (*head_blk == after_umount_blk && - be32_to_cpu(rhead->h_num_logops) == 1) { - umount_data_blk = rhead_blk + hblks; - umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize); - error = xlog_bread(log, umount_data_blk, 1, bp, &offset); + error = xlog_verify_head(log, head_blk, tail_blk, bp, + &rhead_blk, &rhead, &wrapped); if (error) goto done; - op_head = (xlog_op_header_t *)offset; - if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) { - /* - * Set tail and last sync so that newly written - * log records will point recovery to after the - * current unmount record. - */ - xlog_assign_atomic_lsn(&log->l_tail_lsn, - log->l_curr_cycle, after_umount_blk); - xlog_assign_atomic_lsn(&log->l_last_sync_lsn, - log->l_curr_cycle, after_umount_blk); - *tail_blk = after_umount_blk; - - /* - * Note that the unmount was clean. If the unmount - * was not clean, we need to know this to rebuild the - * superblock counters from the perag headers if we - * have a filesystem using non-persistent counters. - */ - log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN; + /* update in-core state again if the head changed */ + if (*head_blk != orig_head) { + xlog_set_state(log, *head_blk, rhead, rhead_blk, + wrapped); + tail_lsn = atomic64_read(&log->l_tail_lsn); + error = xlog_check_unmount_rec(log, head_blk, tail_blk, + rhead, rhead_blk, bp, + &clean); + if (error) + goto done; } } + /* + * Note that the unmount was clean. If the unmount was not clean, we + * need to know this to rebuild the superblock counters from the perag + * headers if we have a filesystem using non-persistent counters. + */ + if (clean) + log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN; + /* * Make sure that there are no blocks in front of the head * with the same cycle number as the head. This can happen diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 39e1cb201b8ea..35a52a880b2f8 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -119,11 +119,6 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock) } #endif -/* - * Initializier - */ -#define __ARCH_SPIN_LOCK_UNLOCKED { ATOMIC_INIT(0) } - /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h index 85f888e86761e..034acd0c4956b 100644 --- a/include/asm-generic/qspinlock_types.h +++ b/include/asm-generic/qspinlock_types.h @@ -32,6 +32,11 @@ typedef struct qspinlock { atomic_t val; } arch_spinlock_t; +/* + * Initializier + */ +#define __ARCH_SPIN_LOCK_UNLOCKED { ATOMIC_INIT(0) } + /* * Bitfields in the atomic value: * diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c4bd0e2c173c0..772c784ba7630 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -256,6 +256,7 @@ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_rodata) = .; \ *(.rodata) *(.rodata.*) \ + *(.data..ro_after_init) /* Read only after init */ \ *(__vermagic) /* Kernel version magic */ \ . = ALIGN(8); \ VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .; \ diff --git a/include/linux/ata.h b/include/linux/ata.h index d2992bfa17063..c1a2f345cbe61 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -487,8 +487,8 @@ enum ata_tf_protocols { }; enum ata_ioctls { - ATA_IOC_GET_IO32 = 0x309, - ATA_IOC_SET_IO32 = 0x324, + ATA_IOC_GET_IO32 = 0x309, /* HDIO_GET_32BIT */ + ATA_IOC_SET_IO32 = 0x324, /* HDIO_SET_32BIT */ }; /* core structures */ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 301de78d65f75..6c502cb13c95a 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -548,6 +548,27 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif +/** + * fetch_or - perform *ptr |= mask and return old value of *ptr + * @ptr: pointer to value + * @mask: mask to OR on the value + * + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#ifndef fetch_or +#define fetch_or(ptr, mask) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (mask)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) +#endif + + #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif diff --git a/include/linux/bio.h b/include/linux/bio.h index 5349e6816cbb0..88bc64f00bb53 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -310,6 +310,38 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) bio->bi_flags &= ~(1U << bit); } +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = bio_iovec(bio); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + if (unlikely(!bio_multiple_segments(bio))) { + *bv = bio_iovec(bio); + return; + } + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4571ef1a12a96..413c84fbc4eda 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -895,7 +895,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) { struct request_queue *q = rq->q; - if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC)) + if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD)) @@ -1372,6 +1372,13 @@ static inline void put_dev_sector(Sector p) page_cache_release(p.v); } +static inline bool __bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + return offset || + ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); +} + /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. @@ -1381,18 +1388,22 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, { if (!queue_virt_boundary(q)) return false; - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return __bvec_gap_to_prev(q, bprv, offset); } static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev)) - return false; + if (bio_has_data(prev) && queue_virt_boundary(q)) { + struct bio_vec pb, nb; + + bio_get_last_bvec(prev, &pb); + bio_get_first_bvec(next, &nb); - return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + } + + return false; } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) diff --git a/include/linux/cache.h b/include/linux/cache.h index 17e7e82d2aa75..1be04f8c563a0 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -12,10 +12,24 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif +/* + * __read_mostly is used to keep rarely changing variables out of frequently + * updated cachelines. If an architecture doesn't support it, ignore the + * hint. + */ #ifndef __read_mostly #define __read_mostly #endif +/* + * __ro_after_init is used to mark things that are read-only after init (i.e. + * after mark_rodata_ro() has been called). These are effectively read-only, + * but may get written to during init, so can't live in .rodata (via "const"). + */ +#ifndef __ro_after_init +#define __ro_after_init __attribute__((__section__(".data..ro_after_init"))) +#endif + #ifndef ____cacheline_aligned #define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) #endif diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index c1ef6f14e7be7..15151f3c41202 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -75,6 +75,7 @@ #define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ // duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 #define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ +#define CEPH_FEATURE_FS_FILE_LAYOUT_V2 (1ULL<<58) /* file_layout_t */ /* * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index bdcf358dfce2a..0d442e34c3497 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -190,9 +190,9 @@ extern void clockevents_config_and_register(struct clock_event_device *dev, extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq); static inline void -clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec) +clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 maxsec) { - return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, freq, minsec); + return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, freq, maxsec); } extern void clockevents_suspend(void); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 6013021a3b394..a307bf62974fd 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -118,6 +118,23 @@ struct clocksource { /* simplify initialization of mask field */ #define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) +static inline u32 clocksource_freq2mult(u32 freq, u32 shift_constant, u64 from) +{ + /* freq = cyc/from + * mult/2^shift = ns/cyc + * mult = ns/cyc * 2^shift + * mult = from/freq * 2^shift + * mult = from * 2^shift / freq + * mult = (from<member) __force *) &(p)->member)) +#else /* __CHECKER__ */ # define __user # define __kernel # define __safe @@ -44,7 +46,9 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __percpu # define __rcu # define __pmem -#endif +# define __private +# define ACCESS_PRIVATE(p, member) ((p)->member) +#endif /* __CHECKER__ */ /* Indirect macros required for expanded argument pasting, eg. __LINE__. */ #define ___PASTE(a,b) a##b @@ -263,8 +267,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * In contrast to ACCESS_ONCE these two macros will also work on aggregate * data types like structs or unions. If the size of the accessed data * type exceeds the word size of the machine (e.g., 32 bits or 64 bits) - * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a - * compile-time warning. + * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at + * least two memcpy()s: one for the __builtin_memcpy() and then one for + * the macro doing the copy of variable - '__u' allocated on the stack. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d2ca8c38f9c45..f9b1fab4388a2 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -16,6 +16,7 @@ #include #include #include +#include struct device; struct device_node; @@ -27,6 +28,9 @@ struct cpu { struct device dev; }; +extern void boot_cpu_init(void); +extern void boot_cpu_state_init(void); + extern int register_cpu(struct cpu *cpu, int num); extern struct device *get_cpu_device(unsigned cpu); extern bool cpu_is_hotpluggable(unsigned cpu); @@ -74,7 +78,7 @@ enum { /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, - CPU_PRI_SMPBOOT = 9, + /* bring up workqueues before normal notifiers and down after */ CPU_PRI_WORKQUEUE_UP = 5, CPU_PRI_WORKQUEUE_DOWN = -5, @@ -97,9 +101,7 @@ enum { * Called on the new cpu, just before * enabling interrupts. Must not sleep, * must not fail */ -#define CPU_DYING_IDLE 0x000B /* CPU (unsigned)v dying, reached - * idle loop. */ -#define CPU_BROKEN 0x000C /* CPU (unsigned)v did not die properly, +#define CPU_BROKEN 0x000B /* CPU (unsigned)v did not die properly, * perhaps due to preemption. */ /* Used for CPU hotplug events occurring while tasks are frozen due to a suspend @@ -118,6 +120,7 @@ enum { #ifdef CONFIG_SMP +extern bool cpuhp_tasks_frozen; /* Need to know about CPUs going up/down? */ #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) #define cpu_notifier(fn, pri) { \ @@ -167,7 +170,6 @@ static inline void __unregister_cpu_notifier(struct notifier_block *nb) } #endif -void smpboot_thread_init(void); int cpu_up(unsigned int cpu); void notify_cpu_starting(unsigned int cpu); extern void cpu_maps_update_begin(void); @@ -177,6 +179,7 @@ extern void cpu_maps_update_done(void); #define cpu_notifier_register_done cpu_maps_update_done #else /* CONFIG_SMP */ +#define cpuhp_tasks_frozen 0 #define cpu_notifier(fn, pri) do { (void)(fn); } while (0) #define __cpu_notifier(fn, pri) do { (void)(fn); } while (0) @@ -215,10 +218,6 @@ static inline void cpu_notifier_register_done(void) { } -static inline void smpboot_thread_init(void) -{ -} - #endif /* CONFIG_SMP */ extern struct bus_type cpu_subsys; @@ -265,11 +264,6 @@ static inline int disable_nonboot_cpus(void) { return 0; } static inline void enable_nonboot_cpus(void) {} #endif /* !CONFIG_PM_SLEEP_SMP */ -enum cpuhp_state { - CPUHP_OFFLINE, - CPUHP_ONLINE, -}; - void cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); @@ -280,14 +274,15 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void arch_cpu_idle_dead(void); -DECLARE_PER_CPU(bool, cpu_dead_idle); - int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); #ifdef CONFIG_HOTPLUG_CPU bool cpu_wait_death(unsigned int cpu, int seconds); bool cpu_report_death(void); +void cpuhp_report_idle_dead(void); +#else +static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h new file mode 100644 index 0000000000000..5d68e15e46b77 --- /dev/null +++ b/include/linux/cpuhotplug.h @@ -0,0 +1,93 @@ +#ifndef __CPUHOTPLUG_H +#define __CPUHOTPLUG_H + +enum cpuhp_state { + CPUHP_OFFLINE, + CPUHP_CREATE_THREADS, + CPUHP_NOTIFY_PREPARE, + CPUHP_BRINGUP_CPU, + CPUHP_AP_IDLE_DEAD, + CPUHP_AP_OFFLINE, + CPUHP_AP_NOTIFY_STARTING, + CPUHP_AP_ONLINE, + CPUHP_TEARDOWN_CPU, + CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_SMPBOOT_THREADS, + CPUHP_AP_NOTIFY_ONLINE, + CPUHP_AP_ONLINE_DYN, + CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, + CPUHP_ONLINE, +}; + +int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)); + +/** + * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks + * @state: The state for which the calls are installed + * @name: Name of the callback (will be used in debug output) + * @startup: startup callback function + * @teardown: teardown callback function + * + * Installs the callback functions and invokes the startup callback on + * the present cpus which have already reached the @state. + */ +static inline int cpuhp_setup_state(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state(state, name, true, startup, teardown); +} + +/** + * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the + * callbacks + * @state: The state for which the calls are installed + * @name: Name of the callback. + * @startup: startup callback function + * @teardown: teardown callback function + * + * Same as @cpuhp_setup_state except that no calls are executed are invoked + * during installation of this callback. NOP if SMP=n or HOTPLUG_CPU=n. + */ +static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + return __cpuhp_setup_state(state, name, false, startup, teardown); +} + +void __cpuhp_remove_state(enum cpuhp_state state, bool invoke); + +/** + * cpuhp_remove_state - Remove hotplug state callbacks and invoke the teardown + * @state: The state for which the calls are removed + * + * Removes the callback functions and invokes the teardown callback on + * the present cpus which have already reached the @state. + */ +static inline void cpuhp_remove_state(enum cpuhp_state state) +{ + __cpuhp_remove_state(state, true); +} + +/** + * cpuhp_remove_state_nocalls - Remove hotplug state callbacks without invoking + * teardown + * @state: The state for which the calls are removed + */ +static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state) +{ + __cpuhp_remove_state(state, false); +} + +#ifdef CONFIG_SMP +void cpuhp_online_idle(enum cpuhp_state state); +#else +static inline void cpuhp_online_idle(enum cpuhp_state state) { } +#endif + +#endif diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 7781ce1105035..c4b5f4b3f8f8b 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -409,9 +409,7 @@ static inline bool d_mountpoint(const struct dentry *dentry) */ static inline unsigned __d_entry_type(const struct dentry *dentry) { - unsigned type = READ_ONCE(dentry->d_flags); - smp_rmb(); - return type & DCACHE_ENTRY_TYPE; + return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 75857cda38e98..5e45cf930a3f5 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -386,7 +386,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size, if (dma_release_from_coherent(dev, get_order(size), cpu_addr)) return; - if (!ops->free) + if (!ops->free || !cpu_addr) return; debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); @@ -641,31 +641,40 @@ static inline void dmam_release_declared_memory(struct device *dev) } #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ -static inline void *dma_alloc_writecombine(struct device *dev, size_t size, - dma_addr_t *dma_addr, gfp_t gfp) +static inline void *dma_alloc_wc(struct device *dev, size_t size, + dma_addr_t *dma_addr, gfp_t gfp) { DEFINE_DMA_ATTRS(attrs); dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs); } +#ifndef dma_alloc_writecombine +#define dma_alloc_writecombine dma_alloc_wc +#endif -static inline void dma_free_writecombine(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t dma_addr) +static inline void dma_free_wc(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_addr) { DEFINE_DMA_ATTRS(attrs); dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs); } +#ifndef dma_free_writecombine +#define dma_free_writecombine dma_free_wc +#endif -static inline int dma_mmap_writecombine(struct device *dev, - struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, - size_t size) +static inline int dma_mmap_wc(struct device *dev, + struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, + size_t size) { DEFINE_DMA_ATTRS(attrs); dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs); } +#ifndef dma_mmap_writecombine +#define dma_mmap_writecombine dma_mmap_wc +#endif #ifdef CONFIG_NEED_DMA_MAP_STATE #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index c2b340e23f62d..6d9df3f7e334c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -713,6 +713,18 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) +static inline unsigned long get_lock_parent_ip(void) +{ + unsigned long addr = CALLER_ADDR0; + + if (!in_lock_functions(addr)) + return addr; + addr = CALLER_ADDR1; + if (!in_lock_functions(addr)) + return addr; + return CALLER_ADDR2; +} + #ifdef CONFIG_IRQSOFF_TRACER extern void time_hardirqs_on(unsigned long a0, unsigned long a1); extern void time_hardirqs_off(unsigned long a0, unsigned long a1); diff --git a/include/linux/init.h b/include/linux/init.h index b449f378f995a..aedb254abc372 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -142,6 +142,10 @@ void prepare_namespace(void); void __init load_default_modules(void); int __init init_rootfs(void); +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void); +#endif + extern void (*late_time_init)(void); extern bool initcall_debug; diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 24bea087e7af8..afb45597fb5f0 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -20,6 +20,7 @@ struct resource { resource_size_t end; const char *name; unsigned long flags; + unsigned long desc; struct resource *parent, *sibling, *child; }; @@ -49,12 +50,19 @@ struct resource { #define IORESOURCE_WINDOW 0x00200000 /* forwarded by bridge */ #define IORESOURCE_MUXED 0x00400000 /* Resource is software muxed */ +#define IORESOURCE_EXT_TYPE_BITS 0x01000000 /* Resource extended types */ +#define IORESOURCE_SYSRAM 0x01000000 /* System RAM (modifier) */ + #define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */ + #define IORESOURCE_DISABLED 0x10000000 #define IORESOURCE_UNSET 0x20000000 /* No address assigned yet */ #define IORESOURCE_AUTO 0x40000000 #define IORESOURCE_BUSY 0x80000000 /* Driver has marked this resource busy */ +/* I/O resource extended types */ +#define IORESOURCE_SYSTEM_RAM (IORESOURCE_MEM|IORESOURCE_SYSRAM) + /* PnP IRQ specific bits (IORESOURCE_BITS) */ #define IORESOURCE_IRQ_HIGHEDGE (1<<0) #define IORESOURCE_IRQ_LOWEDGE (1<<1) @@ -105,6 +113,22 @@ struct resource { /* PCI control bits. Shares IORESOURCE_BITS with above PCI ROM. */ #define IORESOURCE_PCI_FIXED (1<<4) /* Do not move resource */ +/* + * I/O Resource Descriptors + * + * Descriptors are used by walk_iomem_res_desc() and region_intersects() + * for searching a specific resource range in the iomem table. Assign + * a new descriptor when a resource range supports the search interfaces. + * Otherwise, resource.desc must be set to IORES_DESC_NONE (0). + */ +enum { + IORES_DESC_NONE = 0, + IORES_DESC_CRASH_KERNEL = 1, + IORES_DESC_ACPI_TABLES = 2, + IORES_DESC_ACPI_NV_STORAGE = 3, + IORES_DESC_PERSISTENT_MEMORY = 4, + IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, +}; /* helpers to define resources */ #define DEFINE_RES_NAMED(_start, _size, _name, _flags) \ @@ -113,6 +137,7 @@ struct resource { .end = (_start) + (_size) - 1, \ .name = (_name), \ .flags = (_flags), \ + .desc = IORES_DESC_NONE, \ } #define DEFINE_RES_IO_NAMED(_start, _size, _name) \ @@ -170,6 +195,10 @@ static inline unsigned long resource_type(const struct resource *res) { return res->flags & IORESOURCE_TYPE_BITS; } +static inline unsigned long resource_ext_type(const struct resource *res) +{ + return res->flags & IORESOURCE_EXT_TYPE_BITS; +} /* True iff r1 completely contains r2 */ static inline bool resource_contains(struct resource *r1, struct resource *r2) { @@ -239,8 +268,8 @@ extern int walk_system_ram_res(u64 start, u64 end, void *arg, int (*func)(u64, u64, void *)); extern int -walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, void *arg, - int (*func)(u64, u64, void *)); +walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end, + void *arg, int (*func)(u64, u64, void *)); /* True if any part of r1 overlaps r2 */ static inline bool resource_overlaps(struct resource *r1, struct resource *r2) diff --git a/include/linux/irq.h b/include/linux/irq.h index 3c1c96786248c..c4de62348ff22 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -133,17 +133,23 @@ struct irq_domain; * Use accessor functions to deal with it * @node: node index useful for balancing * @handler_data: per-IRQ data for the irq_chip methods - * @affinity: IRQ affinity on SMP + * @affinity: IRQ affinity on SMP. If this is an IPI + * related irq, then this is the mask of the + * CPUs to which an IPI can be sent. * @msi_desc: MSI descriptor + * @ipi_offset: Offset of first IPI target cpu in @affinity. Optional. */ struct irq_common_data { - unsigned int state_use_accessors; + unsigned int __private state_use_accessors; #ifdef CONFIG_NUMA unsigned int node; #endif void *handler_data; struct msi_desc *msi_desc; cpumask_var_t affinity; +#ifdef CONFIG_GENERIC_IRQ_IPI + unsigned int ipi_offset; +#endif }; /** @@ -208,7 +214,7 @@ enum { IRQD_FORWARDED_TO_VCPU = (1 << 20), }; -#define __irqd_to_state(d) ((d)->common->state_use_accessors) +#define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) static inline bool irqd_is_setaffinity_pending(struct irq_data *d) { @@ -299,6 +305,8 @@ static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d) __irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU; } +#undef __irqd_to_state + static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) { return d->hwirq; @@ -341,6 +349,8 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_get_irqchip_state: return the internal state of an interrupt * @irq_set_irqchip_state: set the internal state of a interrupt * @irq_set_vcpu_affinity: optional to target a vCPU in a virtual machine + * @ipi_send_single: send a single IPI to destination cpus + * @ipi_send_mask: send an IPI to destination cpus in cpumask * @flags: chip specific flags */ struct irq_chip { @@ -385,6 +395,9 @@ struct irq_chip { int (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info); + void (*ipi_send_single)(struct irq_data *data, unsigned int cpu); + void (*ipi_send_mask)(struct irq_data *data, const struct cpumask *dest); + unsigned long flags; }; @@ -934,4 +947,12 @@ static inline u32 irq_reg_readl(struct irq_chip_generic *gc, return readl(gc->reg_base + reg_offset); } +/* Contrary to Linux irqs, for hardware irqs the irq number 0 is valid */ +#define INVALID_HWIRQ (~0UL) +irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu); +int __ipi_send_single(struct irq_desc *desc, unsigned int cpu); +int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest); +int ipi_send_single(unsigned int virq, unsigned int cpu); +int ipi_send_mask(unsigned int virq, const struct cpumask *dest); + #endif /* _LINUX_IRQ_H */ diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index ce824db48d64c..80f89e4a29ac5 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -261,9 +261,6 @@ extern void gic_write_compare(cycle_t cnt); extern void gic_write_cpu_compare(cycle_t cnt, int cpu); extern void gic_start_count(void); extern void gic_stop_count(void); -extern void gic_send_ipi(unsigned int intr); -extern unsigned int plat_ipi_call_int_xlate(unsigned int); -extern unsigned int plat_ipi_resched_int_xlate(unsigned int); extern int gic_get_c0_compare_int(void); extern int gic_get_c0_perfcount_int(void); extern int gic_get_c0_fdc_int(void); diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 04579d9fbce4f..ed48594e96d25 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -74,6 +74,7 @@ enum irq_domain_bus_token { DOMAIN_BUS_PCI_MSI, DOMAIN_BUS_PLATFORM_MSI, DOMAIN_BUS_NEXUS, + DOMAIN_BUS_IPI, }; /** @@ -172,6 +173,12 @@ enum { /* Core calls alloc/free recursive through the domain hierarchy. */ IRQ_DOMAIN_FLAG_AUTO_RECURSIVE = (1 << 1), + /* Irq domain is an IPI domain with virq per cpu */ + IRQ_DOMAIN_FLAG_IPI_PER_CPU = (1 << 2), + + /* Irq domain is an IPI domain with single virq */ + IRQ_DOMAIN_FLAG_IPI_SINGLE = (1 << 3), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the @@ -206,6 +213,8 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, extern struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token); extern void irq_set_default_host(struct irq_domain *host); +extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, + irq_hw_number_t hwirq, int node); static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) { @@ -335,6 +344,11 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr, const u32 *intspec, unsigned int intsize, irq_hw_number_t *out_hwirq, unsigned int *out_type); +/* IPI functions */ +unsigned int irq_reserve_ipi(struct irq_domain *domain, + const struct cpumask *dest); +void irq_destroy_ipi(unsigned int irq); + /* V2 interfaces to support hierarchy IRQ domains. */ extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, unsigned int virq); @@ -400,6 +414,22 @@ static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) { return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY; } + +static inline bool irq_domain_is_ipi(struct irq_domain *domain) +{ + return domain->flags & + (IRQ_DOMAIN_FLAG_IPI_PER_CPU | IRQ_DOMAIN_FLAG_IPI_SINGLE); +} + +static inline bool irq_domain_is_ipi_per_cpu(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_IPI_PER_CPU; +} + +static inline bool irq_domain_is_ipi_single(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_IPI_SINGLE; +} #else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ static inline void irq_domain_activate_irq(struct irq_data *data) { } static inline void irq_domain_deactivate_irq(struct irq_data *data) { } @@ -413,6 +443,21 @@ static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) { return false; } + +static inline bool irq_domain_is_ipi(struct irq_domain *domain) +{ + return false; +} + +static inline bool irq_domain_is_ipi_per_cpu(struct irq_domain *domain) +{ + return false; +} + +static inline bool irq_domain_is_ipi_single(struct irq_domain *domain) +{ + return false; +} #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #else /* CONFIG_IRQ_DOMAIN */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 4b9f85c963d07..0fdc798e3ff79 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -1,6 +1,7 @@ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H +#include #include struct kmem_cache; @@ -13,7 +14,6 @@ struct vm_struct; #include #include -#include extern unsigned char kasan_zero_page[PAGE_SIZE]; extern pte_t kasan_zero_pte[PTRS_PER_PTE]; @@ -43,6 +43,8 @@ static inline void kasan_disable_current(void) void kasan_unpoison_shadow(const void *address, size_t size); +void kasan_unpoison_task_stack(struct task_struct *task); + void kasan_alloc_pages(struct page *page, unsigned int order); void kasan_free_pages(struct page *page, unsigned int order); @@ -66,6 +68,8 @@ void kasan_free_shadow(const struct vm_struct *vm); static inline void kasan_unpoison_shadow(const void *address, size_t size) {} +static inline void kasan_unpoison_task_stack(struct task_struct *task) {} + static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 861f690aa7911..5276fe0916fcc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -218,7 +219,7 @@ struct kvm_vcpu { int fpu_active; int guest_fpu_loaded, guest_xcr0_loaded; unsigned char fpu_counter; - wait_queue_head_t wq; + struct swait_queue_head wq; struct pid *pid; int sigset_active; sigset_t sigset; @@ -782,7 +783,7 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) } #endif -static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP return vcpu->arch.wqp; diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h index e23121f9d82a0..59ccab297ae06 100644 --- a/include/linux/latencytop.h +++ b/include/linux/latencytop.h @@ -37,6 +37,9 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter) void clear_all_latency_tracing(struct task_struct *p); +extern int sysctl_latencytop(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); + #else static inline void diff --git a/include/linux/libata.h b/include/linux/libata.h index bec2abbd7ab28..2c4ebef79d0c6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -720,7 +720,7 @@ struct ata_device { union { u16 id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */ u32 gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */ - }; + } ____cacheline_aligned; /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; diff --git a/include/linux/list.h b/include/linux/list.h index 30cf4200ab40e..5356f4d661a72 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -113,17 +113,6 @@ extern void __list_del_entry(struct list_head *entry); extern void list_del(struct list_head *entry); #endif -#ifdef CONFIG_DEBUG_LIST -/* - * See devm_memremap_pages() which wants DEBUG_LIST=y to assert if one - * of the pages it allocates is ever passed to list_add() - */ -extern void list_force_poison(struct list_head *entry); -#else -/* fallback to the less strict LIST_POISON* definitions */ -#define list_force_poison list_del -#endif - /** * list_replace - replace old entry by new one * @old : the element to be replaced diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 4dca42fd32f52..d026b190c5306 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -261,7 +261,6 @@ struct held_lock { /* * Initialization, self-test and debugging-output methods: */ -extern void lockdep_init(void); extern void lockdep_info(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); @@ -392,7 +391,6 @@ static inline void lockdep_on(void) # define lockdep_set_current_reclaim_state(g) do { } while (0) # define lockdep_clear_current_reclaim_state() do { } while (0) # define lockdep_trace_alloc(g) do { } while (0) -# define lockdep_init() do { } while (0) # define lockdep_info() do { } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b8..58eef02edc7e8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4245,7 +4245,9 @@ struct mlx5_ifc_modify_tir_bitmask_bits { u8 reserved_at_20[0x1b]; u8 self_lb_en[0x1]; - u8 reserved_at_3c[0x3]; + u8 reserved_at_3c[0x1]; + u8 hash[0x1]; + u8 reserved_at_3e[0x1]; u8 lro[0x1]; }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 516e149443397..3579d1e2fe3ac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -387,7 +387,8 @@ enum { REGION_MIXED, }; -int region_intersects(resource_size_t offset, size_t size, const char *type); +int region_intersects(resource_size_t offset, size_t size, unsigned long flags, + unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); @@ -2138,6 +2139,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); +int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 624b78b848b89..944b2b37313b4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -566,10 +566,26 @@ static inline void clear_tlb_flush_pending(struct mm_struct *mm) } #endif -struct vm_special_mapping -{ - const char *name; +struct vm_fault; + +struct vm_special_mapping { + const char *name; /* The name, e.g. "[vdso]". */ + + /* + * If .fault is not provided, this points to a + * NULL-terminated array of pages that back the special mapping. + * + * This must not be NULL unless .fault is provided. + */ struct page **pages; + + /* + * If non-NULL, then this is called to resolve page faults + * on the special mapping. If used, .pages is not checked. + */ + int (*fault)(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, + struct vm_fault *vmf); }; enum tlb_flush_reason { diff --git a/include/linux/notifier.h b/include/linux/notifier.h index d14a4c3624657..4149868de4e6c 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -47,6 +47,8 @@ * runtime initialization. */ +struct notifier_block; + typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f5c5a3fa2c810..79ec7bbf01557 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -468,6 +468,7 @@ struct perf_event { int group_flags; struct perf_event *group_leader; struct pmu *pmu; + void *pmu_private; enum perf_event_active_state state; unsigned int attach_state; @@ -1109,12 +1110,6 @@ static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } #endif -#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL) -extern bool perf_event_can_stop_tick(void); -#else -static inline bool perf_event_can_stop_tick(void) { return true; } -#endif - #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 907f3fd191aca..62d44c1760718 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -128,9 +128,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer); void run_posix_cpu_timers(struct task_struct *task); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); - -bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk); - void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval); diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 54bf1484d41f0..35ac903956c7c 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -111,22 +111,17 @@ static inline void timespec_to_pps_ktime(struct pps_ktime *kt, kt->nsec = ts.tv_nsec; } -#ifdef CONFIG_NTP_PPS - static inline void pps_get_ts(struct pps_event_time *ts) { - ktime_get_raw_and_real_ts64(&ts->ts_raw, &ts->ts_real); -} + struct system_time_snapshot snap; -#else /* CONFIG_NTP_PPS */ - -static inline void pps_get_ts(struct pps_event_time *ts) -{ - ktime_get_real_ts64(&ts->ts_real); + ktime_get_snapshot(&snap); + ts->ts_real = ktime_to_timespec64(snap.real); +#ifdef CONFIG_NTP_PPS + ts->ts_raw = ktime_to_timespec64(snap.raw); +#endif } -#endif /* CONFIG_NTP_PPS */ - /* Subtract known time delay from PPS event time(s) */ static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec64 delta) { diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index b8b73066d1379..6b15e168148a3 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -38,6 +38,7 @@ struct ptp_clock_request { }; }; +struct system_device_crosststamp; /** * struct ptp_clock_info - decribes a PTP hardware clock * @@ -67,6 +68,11 @@ struct ptp_clock_request { * @gettime64: Reads the current time from the hardware clock. * parameter ts: Holds the result. * + * @getcrosststamp: Reads the current time from the hardware clock and + * system clock simultaneously. + * parameter cts: Contains timestamp (device,system) pair, + * where system time is realtime and monotonic. + * * @settime64: Set the current time on the hardware clock. * parameter ts: Time value to set. * @@ -105,6 +111,8 @@ struct ptp_clock_info { int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*getcrosststamp)(struct ptp_clock_info *ptp, + struct system_device_crosststamp *cts); int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); int (*enable)(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 14e6f47ee16fe..2657aff2725b4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -332,9 +332,7 @@ void rcu_init(void); void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); -struct notifier_block; -int rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu); +void rcu_report_dead(unsigned int cpu); #ifndef CONFIG_TINY_RCU void rcu_end_inkernel_boot(void); @@ -360,8 +358,6 @@ void rcu_user_exit(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } -static inline void rcu_user_hooks_switch(struct task_struct *prev, - struct task_struct *next) { } #endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU diff --git a/include/linux/sched.h b/include/linux/sched.h index a10494a94cc30..c617ea12c6b7c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -182,8 +182,6 @@ extern void update_cpu_load_nohz(int active); static inline void update_cpu_load_nohz(int active) { } #endif -extern unsigned long get_parent_ip(unsigned long addr); - extern void dump_cpu_task(int cpu); struct seq_file; @@ -719,6 +717,10 @@ struct signal_struct { /* Earliest-expiration cache. */ struct task_cputime cputime_expires; +#ifdef CONFIG_NO_HZ_FULL + unsigned long tick_dep_mask; +#endif + struct list_head cpu_timers[3]; struct pid *tty_old_pgrp; @@ -920,6 +922,10 @@ static inline int sched_info_on(void) #endif } +#ifdef CONFIG_SCHEDSTATS +void force_schedstat_enabled(void); +#endif + enum cpu_idle_type { CPU_IDLE, CPU_NOT_IDLE, @@ -1289,6 +1295,8 @@ struct sched_rt_entity { unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; + unsigned short on_rq; + unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED @@ -1329,10 +1337,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_new tells if a new instance arrived. If so we must - * start executing it with full runtime and reset its absolute - * deadline; - * * @dl_boosted tells if we are boosted due to DI. If so we are * outside bandwidth enforcement mechanism (but only until we * exit the critical section); @@ -1340,7 +1344,7 @@ struct sched_dl_entity { * @dl_yielded tells if task gave up the cpu before consuming * all its available runtime during the last job. */ - int dl_throttled, dl_new, dl_boosted, dl_yielded; + int dl_throttled, dl_boosted, dl_yielded; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -1542,6 +1546,10 @@ struct task_struct { VTIME_SYS, } vtime_snap_whence; #endif + +#ifdef CONFIG_NO_HZ_FULL + unsigned long tick_dep_mask; +#endif unsigned long nvcsw, nivcsw; /* context switch counts */ u64 start_time; /* monotonic time in nsec */ u64 real_start_time; /* boot based time in nsec */ @@ -2356,10 +2364,7 @@ static inline void wake_up_nohz_cpu(int cpu) { } #endif #ifdef CONFIG_NO_HZ_FULL -extern bool sched_can_stop_tick(void); extern u64 scheduler_tick_max_deferment(void); -#else -static inline bool sched_can_stop_tick(void) { return false; } #endif #ifdef CONFIG_SCHED_AUTOGROUP diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c9e4731cf10b8..4f080ab4f2cd1 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -95,4 +95,8 @@ extern int sysctl_numa_balancing(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +extern int sysctl_schedstats(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); + #endif /* _SCHED_SYSCTL_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4ce9ff7086f48..d3fcd4591ce4a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1985,6 +1985,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +/** + * skb_tailroom_reserve - adjust reserved_tailroom + * @skb: buffer to alter + * @mtu: maximum amount of headlen permitted + * @needed_tailroom: minimum amount of reserved_tailroom + * + * Set reserved_tailroom so that headlen can be as large as possible but + * not larger than mtu and tailroom cannot be smaller than + * needed_tailroom. + * The required headroom should already have been reserved before using + * this function. + */ +static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, + unsigned int needed_tailroom) +{ + SKB_LINEAR_ASSERT(skb); + if (mtu < skb_tailroom(skb) - needed_tailroom) + /* use at most mtu */ + skb->reserved_tailroom = skb_tailroom(skb) - mtu; + else + /* use up to all available space */ + skb->reserved_tailroom = needed_tailroom; +} + #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 diff --git a/include/linux/srcu.h b/include/linux/srcu.h index f5f80c5643ac5..dc8eb63c6568a 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -99,8 +99,23 @@ void process_srcu(struct work_struct *work); } /* - * define and init a srcu struct at build time. - * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it. + * Define and initialize a srcu struct at build time. + * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it. + * + * Note that although DEFINE_STATIC_SRCU() hides the name from other + * files, the per-CPU variable rules nevertheless require that the + * chosen name be globally unique. These rules also prohibit use of + * DEFINE_STATIC_SRCU() within a function. If these rules are too + * restrictive, declare the srcu_struct manually. For example, in + * each file: + * + * static struct srcu_struct my_srcu; + * + * Then, before the first use of each my_srcu, manually initialize it: + * + * init_srcu_struct(&my_srcu); + * + * See include/linux/percpu-defs.h for the rules on per-CPU variables. */ #define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index eead8ab93c0a3..881a79d524675 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -100,6 +100,7 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; diff --git a/include/linux/swait.h b/include/linux/swait.h new file mode 100644 index 0000000000000..c1f9c62a8a507 --- /dev/null +++ b/include/linux/swait.h @@ -0,0 +1,172 @@ +#ifndef _LINUX_SWAIT_H +#define _LINUX_SWAIT_H + +#include +#include +#include +#include + +/* + * Simple wait queues + * + * While these are very similar to the other/complex wait queues (wait.h) the + * most important difference is that the simple waitqueue allows for + * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold + * times. + * + * In order to make this so, we had to drop a fair number of features of the + * other waitqueue code; notably: + * + * - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue; + * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right + * sleeper state. + * + * - the exclusive mode; because this requires preserving the list order + * and this is hard. + * + * - custom wake functions; because you cannot give any guarantees about + * random code. + * + * As a side effect of this; the data structures are slimmer. + * + * One would recommend using this wait queue where possible. + */ + +struct task_struct; + +struct swait_queue_head { + raw_spinlock_t lock; + struct list_head task_list; +}; + +struct swait_queue { + struct task_struct *task; + struct list_head task_list; +}; + +#define __SWAITQUEUE_INITIALIZER(name) { \ + .task = current, \ + .task_list = LIST_HEAD_INIT((name).task_list), \ +} + +#define DECLARE_SWAITQUEUE(name) \ + struct swait_queue name = __SWAITQUEUE_INITIALIZER(name) + +#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .task_list = LIST_HEAD_INIT((name).task_list), \ +} + +#define DECLARE_SWAIT_QUEUE_HEAD(name) \ + struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name) + +extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name, + struct lock_class_key *key); + +#define init_swait_queue_head(q) \ + do { \ + static struct lock_class_key __key; \ + __init_swait_queue_head((q), #q, &__key); \ + } while (0) + +#ifdef CONFIG_LOCKDEP +# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ + ({ init_swait_queue_head(&name); name; }) +# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ + struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) +#else +# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ + DECLARE_SWAIT_QUEUE_HEAD(name) +#endif + +static inline int swait_active(struct swait_queue_head *q) +{ + return !list_empty(&q->task_list); +} + +extern void swake_up(struct swait_queue_head *q); +extern void swake_up_all(struct swait_queue_head *q); +extern void swake_up_locked(struct swait_queue_head *q); + +extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); +extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); +extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); + +extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); +extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); + +/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ +#define ___swait_event(wq, condition, state, ret, cmd) \ +({ \ + struct swait_queue __wait; \ + long __ret = ret; \ + \ + INIT_LIST_HEAD(&__wait.task_list); \ + for (;;) { \ + long __int = prepare_to_swait_event(&wq, &__wait, state);\ + \ + if (condition) \ + break; \ + \ + if (___wait_is_interruptible(state) && __int) { \ + __ret = __int; \ + break; \ + } \ + \ + cmd; \ + } \ + finish_swait(&wq, &__wait); \ + __ret; \ +}) + +#define __swait_event(wq, condition) \ + (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ + schedule()) + +#define swait_event(wq, condition) \ +do { \ + if (condition) \ + break; \ + __swait_event(wq, condition); \ +} while (0) + +#define __swait_event_timeout(wq, condition, timeout) \ + ___swait_event(wq, ___wait_cond_timeout(condition), \ + TASK_UNINTERRUPTIBLE, timeout, \ + __ret = schedule_timeout(__ret)) + +#define swait_event_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __swait_event_timeout(wq, condition, timeout); \ + __ret; \ +}) + +#define __swait_event_interruptible(wq, condition) \ + ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ + schedule()) + +#define swait_event_interruptible(wq, condition) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __swait_event_interruptible(wq, condition); \ + __ret; \ +}) + +#define __swait_event_interruptible_timeout(wq, condition, timeout) \ + ___swait_event(wq, ___wait_cond_timeout(condition), \ + TASK_INTERRUPTIBLE, timeout, \ + __ret = schedule_timeout(__ret)) + +#define swait_event_interruptible_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __swait_event_interruptible_timeout(wq, \ + condition, timeout); \ + __ret; \ +}) + +#endif /* _LINUX_SWAIT_H */ diff --git a/include/linux/tick.h b/include/linux/tick.h index 97fd4e543846b..21f73649a4dc5 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -97,6 +97,19 @@ static inline void tick_broadcast_exit(void) tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT); } +enum tick_dep_bits { + TICK_DEP_BIT_POSIX_TIMER = 0, + TICK_DEP_BIT_PERF_EVENTS = 1, + TICK_DEP_BIT_SCHED = 2, + TICK_DEP_BIT_CLOCK_UNSTABLE = 3 +}; + +#define TICK_DEP_MASK_NONE 0 +#define TICK_DEP_MASK_POSIX_TIMER (1 << TICK_DEP_BIT_POSIX_TIMER) +#define TICK_DEP_MASK_PERF_EVENTS (1 << TICK_DEP_BIT_PERF_EVENTS) +#define TICK_DEP_MASK_SCHED (1 << TICK_DEP_BIT_SCHED) +#define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) + #ifdef CONFIG_NO_HZ_COMMON extern int tick_nohz_enabled; extern int tick_nohz_tick_stopped(void); @@ -154,9 +167,73 @@ static inline int housekeeping_any_cpu(void) return cpumask_any_and(housekeeping_mask, cpu_online_mask); } -extern void tick_nohz_full_kick(void); +extern void tick_nohz_dep_set(enum tick_dep_bits bit); +extern void tick_nohz_dep_clear(enum tick_dep_bits bit); +extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit); +extern void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit); +extern void tick_nohz_dep_set_task(struct task_struct *tsk, + enum tick_dep_bits bit); +extern void tick_nohz_dep_clear_task(struct task_struct *tsk, + enum tick_dep_bits bit); +extern void tick_nohz_dep_set_signal(struct signal_struct *signal, + enum tick_dep_bits bit); +extern void tick_nohz_dep_clear_signal(struct signal_struct *signal, + enum tick_dep_bits bit); + +/* + * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases + * on top of static keys. + */ +static inline void tick_dep_set(enum tick_dep_bits bit) +{ + if (tick_nohz_full_enabled()) + tick_nohz_dep_set(bit); +} + +static inline void tick_dep_clear(enum tick_dep_bits bit) +{ + if (tick_nohz_full_enabled()) + tick_nohz_dep_clear(bit); +} + +static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) +{ + if (tick_nohz_full_cpu(cpu)) + tick_nohz_dep_set_cpu(cpu, bit); +} + +static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit) +{ + if (tick_nohz_full_cpu(cpu)) + tick_nohz_dep_clear_cpu(cpu, bit); +} + +static inline void tick_dep_set_task(struct task_struct *tsk, + enum tick_dep_bits bit) +{ + if (tick_nohz_full_enabled()) + tick_nohz_dep_set_task(tsk, bit); +} +static inline void tick_dep_clear_task(struct task_struct *tsk, + enum tick_dep_bits bit) +{ + if (tick_nohz_full_enabled()) + tick_nohz_dep_clear_task(tsk, bit); +} +static inline void tick_dep_set_signal(struct signal_struct *signal, + enum tick_dep_bits bit) +{ + if (tick_nohz_full_enabled()) + tick_nohz_dep_set_signal(signal, bit); +} +static inline void tick_dep_clear_signal(struct signal_struct *signal, + enum tick_dep_bits bit) +{ + if (tick_nohz_full_enabled()) + tick_nohz_dep_clear_signal(signal, bit); +} + extern void tick_nohz_full_kick_cpu(int cpu); -extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(void); #else static inline int housekeeping_any_cpu(void) @@ -166,9 +243,21 @@ static inline int housekeeping_any_cpu(void) static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } + +static inline void tick_dep_set(enum tick_dep_bits bit) { } +static inline void tick_dep_clear(enum tick_dep_bits bit) { } +static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } +static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } +static inline void tick_dep_set_task(struct task_struct *tsk, + enum tick_dep_bits bit) { } +static inline void tick_dep_clear_task(struct task_struct *tsk, + enum tick_dep_bits bit) { } +static inline void tick_dep_set_signal(struct signal_struct *signal, + enum tick_dep_bits bit) { } +static inline void tick_dep_clear_signal(struct signal_struct *signal, + enum tick_dep_bits bit) { } + static inline void tick_nohz_full_kick_cpu(int cpu) { } -static inline void tick_nohz_full_kick(void) { } -static inline void tick_nohz_full_kick_all(void) { } static inline void __tick_nohz_task_switch(void) { } #endif diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 25247220b4b7d..e88005459035e 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -50,6 +50,7 @@ struct tk_read_base { * @offs_tai: Offset clock monotonic -> clock tai * @tai_offset: The current UTC to TAI offset in seconds * @clock_was_set_seq: The sequence number of clock was set events + * @cs_was_changed_seq: The sequence number of clocksource change events * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second * @raw_time: Monotonic raw base time in timespec64 format * @cycle_interval: Number of clock cycles in one NTP interval @@ -91,6 +92,7 @@ struct timekeeper { ktime_t offs_tai; s32 tai_offset; unsigned int clock_was_set_seq; + u8 cs_was_changed_seq; ktime_t next_leap_ktime; struct timespec64 raw_time; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index ec89d846324ca..96f37bee3bc13 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -266,6 +266,64 @@ extern void timekeeping_inject_sleeptime64(struct timespec64 *delta); extern void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, struct timespec64 *ts_real); +/* + * struct system_time_snapshot - simultaneous raw/real time capture with + * counter value + * @cycles: Clocksource counter value to produce the system times + * @real: Realtime system time + * @raw: Monotonic raw system time + * @clock_was_set_seq: The sequence number of clock was set events + * @cs_was_changed_seq: The sequence number of clocksource change events + */ +struct system_time_snapshot { + cycle_t cycles; + ktime_t real; + ktime_t raw; + unsigned int clock_was_set_seq; + u8 cs_was_changed_seq; +}; + +/* + * struct system_device_crosststamp - system/device cross-timestamp + * (syncronized capture) + * @device: Device time + * @sys_realtime: Realtime simultaneous with device time + * @sys_monoraw: Monotonic raw simultaneous with device time + */ +struct system_device_crosststamp { + ktime_t device; + ktime_t sys_realtime; + ktime_t sys_monoraw; +}; + +/* + * struct system_counterval_t - system counter value with the pointer to the + * corresponding clocksource + * @cycles: System counter value + * @cs: Clocksource corresponding to system counter value. Used by + * timekeeping code to verify comparibility of two cycle values + */ +struct system_counterval_t { + cycle_t cycles; + struct clocksource *cs; +}; + +/* + * Get cross timestamp between system clock and device clock + */ +extern int get_device_system_crosststamp( + int (*get_time_fn)(ktime_t *device_time, + struct system_counterval_t *system_counterval, + void *ctx), + void *ctx, + struct system_time_snapshot *history, + struct system_device_crosststamp *xtstamp); + +/* + * Simultaneously snapshot realtime and monotonic raw clocks + */ +extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); + /* * Persistent clock related interfaces */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 429fdfc3baf59..925730bc9fc1b 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -568,6 +568,8 @@ enum { FILTER_DYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, + FILTER_COMM, + FILTER_CPU, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index acfdbf353a0b5..be586c632a0c0 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -134,9 +134,6 @@ extern void syscall_unregfunc(void); void *it_func; \ void *__data; \ \ - if (!cpu_online(raw_smp_processor_id())) \ - return; \ - \ if (!(cond)) \ return; \ prercu; \ @@ -343,15 +340,19 @@ extern void syscall_unregfunc(void); * "void *__data, proto" as the callback prototype. */ #define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , 1, void *__data, __data) + __DECLARE_TRACE(name, void, , \ + cpu_online(raw_smp_processor_id()), \ + void *__data, __data) #define DECLARE_TRACE(name, proto, args) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1, \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) #define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) diff --git a/include/linux/wait.h b/include/linux/wait.h index ae71a769b89e3..27d7a0ab5da3e 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -338,7 +338,7 @@ do { \ schedule(); try_to_freeze()) /** - * wait_event - sleep (or freeze) until a condition gets true + * wait_event_freezable - sleep (or freeze) until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b333c945e5711..d0b5ca5d4e080 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -198,6 +198,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_io(struct writeback_control *wbc, struct page *page, size_t bytes); +void cgroup_writeback_umount(void); /** * inode_attach_wb - associate an inode with its wb @@ -301,6 +302,10 @@ static inline void wbc_account_io(struct writeback_control *wbc, { } +static inline void cgroup_writeback_umount(void) +{ +} + #endif /* CONFIG_CGROUP_WRITEBACK */ /* diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index 8f81bbbc38fc9..e0f4109e64c6f 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); +#ifdef CONFIG_WEXT_CORE +/* flush all previous wext events - if work is done from netdev notifiers */ +void wireless_nlevent_flush(void); +#else +static inline void wireless_nlevent_flush(void) {} +#endif /* We may need a function to send a stream of events to user space. * More on that later... */ diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h index 317a1ed2f4acc..9130dd5a184a2 100644 --- a/include/trace/events/asoc.h +++ b/include/trace/events/asoc.h @@ -231,13 +231,13 @@ TRACE_EVENT(snd_soc_jack_report, TP_ARGS(jack, mask, val), TP_STRUCT__entry( - __string( name, jack->jack->name ) + __string( name, jack->jack->id ) __field( int, mask ) __field( int, val ) ), TP_fast_assign( - __assign_str(name, jack->jack->name); + __assign_str(name, jack->jack->id); __entry->mask = mask; __entry->val = val; ), @@ -253,12 +253,12 @@ TRACE_EVENT(snd_soc_jack_notify, TP_ARGS(jack, val), TP_STRUCT__entry( - __string( name, jack->jack->name ) + __string( name, jack->jack->id ) __field( int, val ) ), TP_fast_assign( - __assign_str(name, jack->jack->name); + __assign_str(name, jack->jack->id); __entry->val = val; ), diff --git a/include/trace/events/cpuhp.h b/include/trace/events/cpuhp.h new file mode 100644 index 0000000000000..a72bd93ec7e5b --- /dev/null +++ b/include/trace/events/cpuhp.h @@ -0,0 +1,66 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM cpuhp + +#if !defined(_TRACE_CPUHP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_CPUHP_H + +#include + +TRACE_EVENT(cpuhp_enter, + + TP_PROTO(unsigned int cpu, + int target, + int idx, + int (*fun)(unsigned int)), + + TP_ARGS(cpu, target, idx, fun), + + TP_STRUCT__entry( + __field( unsigned int, cpu ) + __field( int, target ) + __field( int, idx ) + __field( void *, fun ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->target = target; + __entry->idx = idx; + __entry->fun = fun; + ), + + TP_printk("cpu: %04u target: %3d step: %3d (%pf)", + __entry->cpu, __entry->target, __entry->idx, __entry->fun) +); + +TRACE_EVENT(cpuhp_exit, + + TP_PROTO(unsigned int cpu, + int state, + int idx, + int ret), + + TP_ARGS(cpu, state, idx, ret), + + TP_STRUCT__entry( + __field( unsigned int, cpu ) + __field( int, state ) + __field( int, idx ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->state = state; + __entry->idx = idx; + __entry->ret = ret; + ), + + TP_printk(" cpu: %04u state: %3d step: %3d ret: %d", + __entry->cpu, __entry->state, __entry->idx, __entry->ret) +); + +#endif + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 073b9ac245ba0..51440131d3372 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -328,23 +328,49 @@ TRACE_EVENT(itimer_expire, ); #ifdef CONFIG_NO_HZ_COMMON + +#define TICK_DEP_NAMES \ + tick_dep_name(NONE) \ + tick_dep_name(POSIX_TIMER) \ + tick_dep_name(PERF_EVENTS) \ + tick_dep_name(SCHED) \ + tick_dep_name_end(CLOCK_UNSTABLE) + +#undef tick_dep_name +#undef tick_dep_name_end + +#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); + +TICK_DEP_NAMES + +#undef tick_dep_name +#undef tick_dep_name_end + +#define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, +#define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } + +#define show_tick_dep_name(val) \ + __print_symbolic(val, TICK_DEP_NAMES) + TRACE_EVENT(tick_stop, - TP_PROTO(int success, char *error_msg), + TP_PROTO(int success, int dependency), - TP_ARGS(success, error_msg), + TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) - __string( msg, error_msg ) + __field( int , dependency ) ), TP_fast_assign( __entry->success = success; - __assign_str(msg, error_msg); + __entry->dependency = dependency; ), - TP_printk("success=%s msg=%s", __entry->success ? "yes" : "no", __get_str(msg)) + TP_printk("success=%d dependency=%s", __entry->success, \ + show_tick_dep_name(__entry->dependency)) ); #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index aa6f8571de136..5df4881dea7b5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -292,6 +292,9 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 1e3c8cb43bd7a..a8e3a8c0d85a9 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -66,27 +66,33 @@ struct media_device_info { /* * DVB entities */ -#define MEDIA_ENT_F_DTV_DEMOD (MEDIA_ENT_F_BASE + 1) -#define MEDIA_ENT_F_TS_DEMUX (MEDIA_ENT_F_BASE + 2) -#define MEDIA_ENT_F_DTV_CA (MEDIA_ENT_F_BASE + 3) -#define MEDIA_ENT_F_DTV_NET_DECAP (MEDIA_ENT_F_BASE + 4) +#define MEDIA_ENT_F_DTV_DEMOD (MEDIA_ENT_F_BASE + 0x00001) +#define MEDIA_ENT_F_TS_DEMUX (MEDIA_ENT_F_BASE + 0x00002) +#define MEDIA_ENT_F_DTV_CA (MEDIA_ENT_F_BASE + 0x00003) +#define MEDIA_ENT_F_DTV_NET_DECAP (MEDIA_ENT_F_BASE + 0x00004) /* - * Connectors + * I/O entities */ -/* It is a responsibility of the entity drivers to add connectors and links */ -#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 21) -#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 22) -#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 23) -/* For internal test signal generators and other debug connectors */ -#define MEDIA_ENT_F_CONN_TEST (MEDIA_ENT_F_BASE + 24) +#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 0x01001) +#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 0x01002) +#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 0x01003) /* - * I/O entities + * Connectors */ -#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 31) -#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 32) -#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 33) +/* It is a responsibility of the entity drivers to add connectors and links */ +#ifdef __KERNEL__ + /* + * For now, it should not be used in userspace, as some + * definitions may change + */ + +#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 0x30001) +#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 0x30002) +#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 0x30003) + +#endif /* * Don't touch on those. The ranges MEDIA_ENT_F_OLD_BASE and @@ -114,7 +120,7 @@ struct media_device_info { #define MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN MEDIA_ENT_F_OLD_SUBDEV_BASE -#ifndef __KERNEL__ +#if !defined(__KERNEL__) || defined(__NEED_MEDIA_LEGACY_API) /* * Legacy symbols used to avoid userspace compilation breakages @@ -127,6 +133,10 @@ struct media_device_info { #define MEDIA_ENT_TYPE_MASK 0x00ff0000 #define MEDIA_ENT_SUBTYPE_MASK 0x0000ffff +/* End of the old subdev reserved numberspace */ +#define MEDIA_ENT_T_DEVNODE_UNKNOWN (MEDIA_ENT_T_DEVNODE | \ + MEDIA_ENT_SUBTYPE_MASK) + #define MEDIA_ENT_T_DEVNODE MEDIA_ENT_F_OLD_BASE #define MEDIA_ENT_T_DEVNODE_V4L MEDIA_ENT_F_IO_V4L #define MEDIA_ENT_T_DEVNODE_FB (MEDIA_ENT_T_DEVNODE + 2) @@ -291,14 +301,14 @@ struct media_v2_entity { __u32 id; char name[64]; /* FIXME: move to a property? (RFC says so) */ __u32 function; /* Main function of the entity */ - __u16 reserved[12]; -}; + __u32 reserved[6]; +} __attribute__ ((packed)); /* Should match the specific fields at media_intf_devnode */ struct media_v2_intf_devnode { __u32 major; __u32 minor; -}; +} __attribute__ ((packed)); struct media_v2_interface { __u32 id; @@ -310,22 +320,22 @@ struct media_v2_interface { struct media_v2_intf_devnode devnode; __u32 raw[16]; }; -}; +} __attribute__ ((packed)); struct media_v2_pad { __u32 id; __u32 entity_id; __u32 flags; - __u16 reserved[9]; -}; + __u32 reserved[5]; +} __attribute__ ((packed)); struct media_v2_link { __u32 id; __u32 source_id; __u32 sink_id; __u32 flags; - __u32 reserved[5]; -}; + __u32 reserved[6]; +} __attribute__ ((packed)); struct media_v2_topology { __u64 topology_version; @@ -345,7 +355,7 @@ struct media_v2_topology { __u32 num_links; __u32 reserved4; __u64 ptr_links; -}; +} __attribute__ ((packed)); static inline void __user *media_get_uptr(__u64 arg) { diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index f0b7bfe5da920..ac6dded80ffa9 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -51,7 +51,9 @@ struct ptp_clock_caps { int n_per_out; /* Number of programmable periodic signals. */ int pps; /* Whether the clock supports a PPS callback. */ int n_pins; /* Number of input/output pins. */ - int rsv[14]; /* Reserved for future use. */ + /* Whether the clock supports precise system-device cross timestamps */ + int cross_timestamping; + int rsv[13]; /* Reserved for future use. */ }; struct ptp_extts_request { @@ -81,6 +83,13 @@ struct ptp_sys_offset { struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1]; }; +struct ptp_sys_offset_precise { + struct ptp_clock_time device; + struct ptp_clock_time sys_realtime; + struct ptp_clock_time sys_monoraw; + unsigned int rsv[4]; /* Reserved for future use. */ +}; + enum ptp_pin_function { PTP_PF_NONE, PTP_PF_EXTTS, @@ -124,6 +133,8 @@ struct ptp_pin_desc { #define PTP_SYS_OFFSET _IOW(PTP_CLK_MAGIC, 5, struct ptp_sys_offset) #define PTP_PIN_GETFUNC _IOWR(PTP_CLK_MAGIC, 6, struct ptp_pin_desc) #define PTP_PIN_SETFUNC _IOW(PTP_CLK_MAGIC, 7, struct ptp_pin_desc) +#define PTP_SYS_OFFSET_PRECISE \ + _IOWR(PTP_CLK_MAGIC, 8, struct ptp_sys_offset_precise) struct ptp_extts_event { struct ptp_clock_time t; /* Time event occured. */ diff --git a/init/main.c b/init/main.c index 58c9e374704bb..8dc93df20f7fd 100644 --- a/init/main.c +++ b/init/main.c @@ -93,9 +93,6 @@ static int kernel_init(void *); extern void init_IRQ(void); extern void fork_init(void); extern void radix_tree_init(void); -#ifndef CONFIG_DEBUG_RODATA -static inline void mark_rodata_ro(void) { } -#endif /* * Debug helper: via this flag we know that we are in 'early bootup code' @@ -388,7 +385,6 @@ static noinline void __init_refok rest_init(void) int pid; rcu_scheduler_starting(); - smpboot_thread_init(); /* * We need to spawn init first so that it obtains pid 1, however * the init task will end up wanting to create kthreads, which, if @@ -452,20 +448,6 @@ void __init parse_early_param(void) done = 1; } -/* - * Activate the first processor. - */ - -static void __init boot_cpu_init(void) -{ - int cpu = smp_processor_id(); - /* Mark the boot cpu "present", "online" etc for SMP and UP case */ - set_cpu_online(cpu, true); - set_cpu_active(cpu, true); - set_cpu_present(cpu, true); - set_cpu_possible(cpu, true); -} - void __init __weak smp_setup_processor_id(void) { } @@ -499,11 +481,6 @@ asmlinkage __visible void __init start_kernel(void) char *command_line; char *after_dashes; - /* - * Need to run as early as possible, to initialize the - * lockdep hash: - */ - lockdep_init(); set_task_stack_end_magic(&init_task); smp_setup_processor_id(); debug_objects_early_init(); @@ -530,6 +507,7 @@ asmlinkage __visible void __init start_kernel(void) setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); + boot_cpu_state_init(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ build_all_zonelists(NULL, NULL); @@ -929,6 +907,28 @@ static int try_to_run_init_process(const char *init_filename) static noinline void __init kernel_init_freeable(void); +#ifdef CONFIG_DEBUG_RODATA +static bool rodata_enabled = true; +static int __init set_debug_rodata(char *str) +{ + return strtobool(str, &rodata_enabled); +} +__setup("rodata=", set_debug_rodata); + +static void mark_readonly(void) +{ + if (rodata_enabled) + mark_rodata_ro(); + else + pr_info("Kernel memory protection disabled.\n"); +} +#else +static inline void mark_readonly(void) +{ + pr_warn("This architecture does not have kernel memory protection.\n"); +} +#endif + static int __ref kernel_init(void *unused) { int ret; @@ -937,7 +937,7 @@ static int __ref kernel_init(void *unused) /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); free_initmem(); - mark_rodata_ro(); + mark_readonly(); system_state = SYSTEM_RUNNING; numa_default_policy(); diff --git a/kernel/cpu.c b/kernel/cpu.c index 5b9d39633ce9d..6ea42e8da861b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -22,13 +22,88 @@ #include #include #include +#include + #include +#define CREATE_TRACE_POINTS +#include #include "smpboot.h" +/** + * cpuhp_cpu_state - Per cpu hotplug state storage + * @state: The current cpu state + * @target: The target state + * @thread: Pointer to the hotplug thread + * @should_run: Thread should execute + * @cb_stat: The state for a single callback (install/uninstall) + * @cb: Single callback function (install/uninstall) + * @result: Result of the operation + * @done: Signal completion to the issuer of the task + */ +struct cpuhp_cpu_state { + enum cpuhp_state state; + enum cpuhp_state target; +#ifdef CONFIG_SMP + struct task_struct *thread; + bool should_run; + enum cpuhp_state cb_state; + int (*cb)(unsigned int cpu); + int result; + struct completion done; +#endif +}; + +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); + +/** + * cpuhp_step - Hotplug state machine step + * @name: Name of the step + * @startup: Startup function of the step + * @teardown: Teardown function of the step + * @skip_onerr: Do not invoke the functions on error rollback + * Will go away once the notifiers are gone + * @cant_stop: Bringup/teardown can't be stopped at this step + */ +struct cpuhp_step { + const char *name; + int (*startup)(unsigned int cpu); + int (*teardown)(unsigned int cpu); + bool skip_onerr; + bool cant_stop; +}; + +static DEFINE_MUTEX(cpuhp_state_mutex); +static struct cpuhp_step cpuhp_bp_states[]; +static struct cpuhp_step cpuhp_ap_states[]; + +/** + * cpuhp_invoke_callback _ Invoke the callbacks for a given state + * @cpu: The cpu for which the callback should be invoked + * @step: The step in the state machine + * @cb: The callback function to invoke + * + * Called from cpu hotplug and from the state register machinery + */ +static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step, + int (*cb)(unsigned int)) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret = 0; + + if (cb) { + trace_cpuhp_enter(cpu, st->target, step, cb); + ret = cb(cpu); + trace_cpuhp_exit(cpu, st->state, step, ret); + } + return ret; +} + #ifdef CONFIG_SMP /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); +bool cpuhp_tasks_frozen; +EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when @@ -207,31 +282,281 @@ int __register_cpu_notifier(struct notifier_block *nb) return raw_notifier_chain_register(&cpu_chain, nb); } -static int __cpu_notify(unsigned long val, void *v, int nr_to_call, +static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call, int *nr_calls) { + unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0; + void *hcpu = (void *)(long)cpu; + int ret; - ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call, + ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call, nr_calls); return notifier_to_errno(ret); } -static int cpu_notify(unsigned long val, void *v) +static int cpu_notify(unsigned long val, unsigned int cpu) { - return __cpu_notify(val, v, -1, NULL); + return __cpu_notify(val, cpu, -1, NULL); } -#ifdef CONFIG_HOTPLUG_CPU +/* Notifier wrappers for transitioning to state machine */ +static int notify_prepare(unsigned int cpu) +{ + int nr_calls = 0; + int ret; + + ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls); + if (ret) { + nr_calls--; + printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n", + __func__, cpu); + __cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL); + } + return ret; +} + +static int notify_online(unsigned int cpu) +{ + cpu_notify(CPU_ONLINE, cpu); + return 0; +} + +static int notify_starting(unsigned int cpu) +{ + cpu_notify(CPU_STARTING, cpu); + return 0; +} + +static int bringup_wait_for_ap(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + wait_for_completion(&st->done); + return st->result; +} + +static int bringup_cpu(unsigned int cpu) +{ + struct task_struct *idle = idle_thread_get(cpu); + int ret; + + /* Arch-specific enabling code. */ + ret = __cpu_up(cpu, idle); + if (ret) { + cpu_notify(CPU_UP_CANCELED, cpu); + return ret; + } + ret = bringup_wait_for_ap(cpu); + BUG_ON(!cpu_online(cpu)); + return ret; +} + +/* + * Hotplug state machine related functions + */ +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = steps + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->startup); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + struct cpuhp_step *step = steps + st->state; + + ret = cpuhp_invoke_callback(cpu, st->state, step->teardown); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st, steps); + break; + } + } + return ret; +} + +static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps) +{ + for (st->state--; st->state > st->target; st->state--) { + struct cpuhp_step *step = steps + st->state; + + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, step->teardown); + } +} + +static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + struct cpuhp_step *steps, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + while (st->state < target) { + struct cpuhp_step *step; + + st->state++; + step = steps + st->state; + ret = cpuhp_invoke_callback(cpu, st->state, step->startup); + if (ret) { + st->target = prev_state; + undo_cpu_up(cpu, st, steps); + break; + } + } + return ret; +} + +/* + * The cpu hotplug threads manage the bringup and teardown of the cpus + */ +static void cpuhp_create(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + init_completion(&st->done); +} + +static int cpuhp_should_run(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + + return st->should_run; +} + +/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ +static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); + + return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target); +} + +/* Execute the online startup callbacks. Used to be CPU_ONLINE */ +static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + return cpuhp_up_callbacks(cpu, st, cpuhp_ap_states, st->target); +} + +/* + * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke + * callbacks when a state gets [un]installed at runtime. + */ +static void cpuhp_thread_fun(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + int ret = 0; + + /* + * Paired with the mb() in cpuhp_kick_ap_work and + * cpuhp_invoke_ap_callback, so the work set is consistent visible. + */ + smp_mb(); + if (!st->should_run) + return; + + st->should_run = false; + + /* Single callback invocation for [un]install ? */ + if (st->cb) { + if (st->cb_state < CPUHP_AP_ONLINE) { + local_irq_disable(); + ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb); + local_irq_enable(); + } else { + ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb); + } + } else { + /* Cannot happen .... */ + BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + + /* Regular hotplug work */ + if (st->state < st->target) + ret = cpuhp_ap_online(cpu, st); + else if (st->state > st->target) + ret = cpuhp_ap_offline(cpu, st); + } + st->result = ret; + complete(&st->done); +} -static void cpu_notify_nofail(unsigned long val, void *v) +/* Invoke a single callback on a remote cpu */ +static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, + int (*cb)(unsigned int)) { - BUG_ON(cpu_notify(val, v)); + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + if (!cpu_online(cpu)) + return 0; + + st->cb_state = state; + st->cb = cb; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_completion(&st->done); + return st->result; } + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) +{ + st->result = 0; + st->cb = NULL; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); +} + +static int cpuhp_kick_ap_work(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + enum cpuhp_state state = st->state; + + trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); + __cpuhp_kick_ap_work(st); + wait_for_completion(&st->done); + trace_cpuhp_exit(cpu, st->state, state, st->result); + return st->result; +} + +static struct smp_hotplug_thread cpuhp_threads = { + .store = &cpuhp_state.thread, + .create = &cpuhp_create, + .thread_should_run = cpuhp_should_run, + .thread_fn = cpuhp_thread_fun, + .thread_comm = "cpuhp/%u", + .selfparking = true, +}; + +void __init cpuhp_threads_init(void) +{ + BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); + kthread_unpark(this_cpu_read(cpuhp_state.thread)); +} + +#ifdef CONFIG_HOTPLUG_CPU EXPORT_SYMBOL(register_cpu_notifier); EXPORT_SYMBOL(__register_cpu_notifier); - void unregister_cpu_notifier(struct notifier_block *nb) { cpu_maps_update_begin(); @@ -311,57 +636,60 @@ static inline void check_for_tasks(int dead_cpu) read_unlock(&tasklist_lock); } -struct take_cpu_down_param { - unsigned long mod; - void *hcpu; -}; +static void cpu_notify_nofail(unsigned long val, unsigned int cpu) +{ + BUG_ON(cpu_notify(val, cpu)); +} + +static int notify_down_prepare(unsigned int cpu) +{ + int err, nr_calls = 0; + + err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls); + if (err) { + nr_calls--; + __cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL); + pr_warn("%s: attempt to take down CPU %u failed\n", + __func__, cpu); + } + return err; +} + +static int notify_dying(unsigned int cpu) +{ + cpu_notify(CPU_DYING, cpu); + return 0; +} /* Take this CPU down. */ static int take_cpu_down(void *_param) { - struct take_cpu_down_param *param = _param; - int err; + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); + int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; - cpu_notify(CPU_DYING | param->mod, param->hcpu); + /* Invoke the former CPU_DYING callbacks */ + for (; st->state > target; st->state--) { + struct cpuhp_step *step = cpuhp_ap_states + st->state; + + cpuhp_invoke_callback(cpu, st->state, step->teardown); + } /* Give up timekeeping duties */ tick_handover_do_timer(); /* Park the stopper thread */ - stop_machine_park((long)param->hcpu); + stop_machine_park(cpu); return 0; } -/* Requires cpu_add_remove_lock to be held */ -static int _cpu_down(unsigned int cpu, int tasks_frozen) +static int takedown_cpu(unsigned int cpu) { - int err, nr_calls = 0; - void *hcpu = (void *)(long)cpu; - unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; - struct take_cpu_down_param tcd_param = { - .mod = mod, - .hcpu = hcpu, - }; - - if (num_online_cpus() == 1) - return -EBUSY; - - if (!cpu_online(cpu)) - return -EINVAL; - - cpu_hotplug_begin(); - - err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); - if (err) { - nr_calls--; - __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL); - pr_warn("%s: attempt to take down CPU %u failed\n", - __func__, cpu); - goto out_release; - } + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int err; /* * By now we've cleared cpu_active_mask, wait for all preempt-disabled @@ -378,6 +706,8 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) else synchronize_rcu(); + /* Park the smpboot threads */ + kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); smpboot_park_threads(cpu); /* @@ -389,12 +719,12 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* * So now all preempt/rcu users must observe !cpu_active(). */ - err = stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); + err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ - cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); + cpu_notify_nofail(CPU_DOWN_FAILED, cpu); irq_unlock_sparse(); - goto out_release; + return err; } BUG_ON(cpu_online(cpu)); @@ -405,10 +735,8 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) * * Wait for the stop thread to go away. */ - while (!per_cpu(cpu_dead_idle, cpu)) - cpu_relax(); - smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */ - per_cpu(cpu_dead_idle, cpu) = false; + wait_for_completion(&st->done); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); @@ -417,20 +745,104 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen) /* This actually kills the CPU. */ __cpu_die(cpu); - /* CPU is completely dead: tell everyone. Too late to complain. */ tick_cleanup_dead_cpu(cpu); - cpu_notify_nofail(CPU_DEAD | mod, hcpu); + return 0; +} +static int notify_dead(unsigned int cpu) +{ + cpu_notify_nofail(CPU_DEAD, cpu); check_for_tasks(cpu); + return 0; +} -out_release: +static void cpuhp_complete_idle_dead(void *arg) +{ + struct cpuhp_cpu_state *st = arg; + + complete(&st->done); +} + +void cpuhp_report_idle_dead(void) +{ + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + + BUG_ON(st->state != CPUHP_AP_OFFLINE); + rcu_report_dead(smp_processor_id()); + st->state = CPUHP_AP_IDLE_DEAD; + /* + * We cannot call complete after rcu_report_dead() so we delegate it + * to an online cpu. + */ + smp_call_function_single(cpumask_first(cpu_online_mask), + cpuhp_complete_idle_dead, st, 0); +} + +#else +#define notify_down_prepare NULL +#define takedown_cpu NULL +#define notify_dead NULL +#define notify_dying NULL +#endif + +#ifdef CONFIG_HOTPLUG_CPU + +/* Requires cpu_add_remove_lock to be held */ +static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, + enum cpuhp_state target) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int prev_state, ret = 0; + bool hasdied = false; + + if (num_online_cpus() == 1) + return -EBUSY; + + if (!cpu_present(cpu)) + return -EINVAL; + + cpu_hotplug_begin(); + + cpuhp_tasks_frozen = tasks_frozen; + + prev_state = st->state; + st->target = target; + /* + * If the current CPU state is in the range of the AP hotplug thread, + * then we need to kick the thread. + */ + if (st->state > CPUHP_TEARDOWN_CPU) { + ret = cpuhp_kick_ap_work(cpu); + /* + * The AP side has done the error rollback already. Just + * return the error code.. + */ + if (ret) + goto out; + + /* + * We might have stopped still in the range of the AP hotplug + * thread. Nothing to do anymore. + */ + if (st->state > CPUHP_TEARDOWN_CPU) + goto out; + } + /* + * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need + * to do the further cleanups. + */ + ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target); + + hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE; +out: cpu_hotplug_done(); - if (!err) - cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); - return err; + /* This post dead nonsense must die */ + if (!ret && hasdied) + cpu_notify_nofail(CPU_POST_DEAD, cpu); + return ret; } -int cpu_down(unsigned int cpu) +static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; @@ -441,100 +853,131 @@ int cpu_down(unsigned int cpu) goto out; } - err = _cpu_down(cpu, 0); + err = _cpu_down(cpu, 0, target); out: cpu_maps_update_done(); return err; } +int cpu_down(unsigned int cpu) +{ + return do_cpu_down(cpu, CPUHP_OFFLINE); +} EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/ -/* - * Unpark per-CPU smpboot kthreads at CPU-online time. +/** + * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers + * @cpu: cpu that just started + * + * This function calls the cpu_chain notifiers with CPU_STARTING. + * It must be called by the arch code on the new cpu, before the new cpu + * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ -static int smpboot_thread_call(struct notifier_block *nfb, - unsigned long action, void *hcpu) +void notify_cpu_starting(unsigned int cpu) { - int cpu = (long)hcpu; - - switch (action & ~CPU_TASKS_FROZEN) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); - case CPU_DOWN_FAILED: - case CPU_ONLINE: - smpboot_unpark_threads(cpu); - break; + while (st->state < target) { + struct cpuhp_step *step; - default: - break; + st->state++; + step = cpuhp_ap_states + st->state; + cpuhp_invoke_callback(cpu, st->state, step->startup); } - - return NOTIFY_OK; } -static struct notifier_block smpboot_thread_notifier = { - .notifier_call = smpboot_thread_call, - .priority = CPU_PRI_SMPBOOT, -}; - -void smpboot_thread_init(void) +/* + * Called from the idle task. We need to set active here, so we can kick off + * the stopper thread and unpark the smpboot threads. If the target state is + * beyond CPUHP_AP_ONLINE_IDLE we kick cpuhp thread and let it bring up the + * cpu further. + */ +void cpuhp_online_idle(enum cpuhp_state state) { - register_cpu_notifier(&smpboot_thread_notifier); + struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); + unsigned int cpu = smp_processor_id(); + + /* Happens for the boot cpu */ + if (state != CPUHP_AP_ONLINE_IDLE) + return; + + st->state = CPUHP_AP_ONLINE_IDLE; + + /* The cpu is marked online, set it active now */ + set_cpu_active(cpu, true); + /* Unpark the stopper thread and the hotplug thread of this cpu */ + stop_machine_unpark(cpu); + kthread_unpark(st->thread); + + /* Should we go further up ? */ + if (st->target > CPUHP_AP_ONLINE_IDLE) + __cpuhp_kick_ap_work(st); + else + complete(&st->done); } /* Requires cpu_add_remove_lock to be held */ -static int _cpu_up(unsigned int cpu, int tasks_frozen) +static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { - int ret, nr_calls = 0; - void *hcpu = (void *)(long)cpu; - unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; + int ret = 0; cpu_hotplug_begin(); - if (cpu_online(cpu) || !cpu_present(cpu)) { + if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } - idle = idle_thread_get(cpu); - if (IS_ERR(idle)) { - ret = PTR_ERR(idle); - goto out; - } - - ret = smpboot_create_threads(cpu); - if (ret) + /* + * The caller of do_cpu_up might have raced with another + * caller. Ignore it for now. + */ + if (st->state >= target) goto out; - ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); - if (ret) { - nr_calls--; - pr_warn("%s: attempt to bring up CPU %u failed\n", - __func__, cpu); - goto out_notify; + if (st->state == CPUHP_OFFLINE) { + /* Let it fail before we try to bring the cpu up */ + idle = idle_thread_get(cpu); + if (IS_ERR(idle)) { + ret = PTR_ERR(idle); + goto out; + } } - /* Arch-specific enabling code. */ - ret = __cpu_up(cpu, idle); - - if (ret != 0) - goto out_notify; - BUG_ON(!cpu_online(cpu)); + cpuhp_tasks_frozen = tasks_frozen; - /* Now call notifier in preparation. */ - cpu_notify(CPU_ONLINE | mod, hcpu); + st->target = target; + /* + * If the current CPU state is in the range of the AP hotplug thread, + * then we need to kick the thread once more. + */ + if (st->state > CPUHP_BRINGUP_CPU) { + ret = cpuhp_kick_ap_work(cpu); + /* + * The AP side has done the error rollback already. Just + * return the error code.. + */ + if (ret) + goto out; + } -out_notify: - if (ret != 0) - __cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL); + /* + * Try to reach the target state. We max out on the BP at + * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is + * responsible for bringing it up to the target state. + */ + target = min((int)target, CPUHP_BRINGUP_CPU); + ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target); out: cpu_hotplug_done(); - return ret; } -int cpu_up(unsigned int cpu) +static int do_cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; @@ -558,12 +1001,16 @@ int cpu_up(unsigned int cpu) goto out; } - err = _cpu_up(cpu, 0); - + err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } + +int cpu_up(unsigned int cpu) +{ + return do_cpu_up(cpu, CPUHP_ONLINE); +} EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMP @@ -586,7 +1033,7 @@ int disable_nonboot_cpus(void) if (cpu == first_cpu) continue; trace_suspend_resume(TPS("CPU_OFF"), cpu, true); - error = _cpu_down(cpu, 1); + error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); @@ -636,7 +1083,7 @@ void enable_nonboot_cpus(void) for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); - error = _cpu_up(cpu, 1); + error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); @@ -709,26 +1156,463 @@ core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ +#endif /* CONFIG_SMP */ + +/* Boot processor state steps */ +static struct cpuhp_step cpuhp_bp_states[] = { + [CPUHP_OFFLINE] = { + .name = "offline", + .startup = NULL, + .teardown = NULL, + }, +#ifdef CONFIG_SMP + [CPUHP_CREATE_THREADS]= { + .name = "threads:create", + .startup = smpboot_create_threads, + .teardown = NULL, + .cant_stop = true, + }, + /* + * Preparatory and dead notifiers. Will be replaced once the notifiers + * are converted to states. + */ + [CPUHP_NOTIFY_PREPARE] = { + .name = "notify:prepare", + .startup = notify_prepare, + .teardown = notify_dead, + .skip_onerr = true, + .cant_stop = true, + }, + /* Kicks the plugged cpu into life */ + [CPUHP_BRINGUP_CPU] = { + .name = "cpu:bringup", + .startup = bringup_cpu, + .teardown = NULL, + .cant_stop = true, + }, + /* + * Handled on controll processor until the plugged processor manages + * this itself. + */ + [CPUHP_TEARDOWN_CPU] = { + .name = "cpu:teardown", + .startup = NULL, + .teardown = takedown_cpu, + .cant_stop = true, + }, +#endif +}; + +/* Application processor state steps */ +static struct cpuhp_step cpuhp_ap_states[] = { +#ifdef CONFIG_SMP + /* Final state before CPU kills itself */ + [CPUHP_AP_IDLE_DEAD] = { + .name = "idle:dead", + }, + /* + * Last state before CPU enters the idle loop to die. Transient state + * for synchronization. + */ + [CPUHP_AP_OFFLINE] = { + .name = "ap:offline", + .cant_stop = true, + }, + /* + * Low level startup/teardown notifiers. Run with interrupts + * disabled. Will be removed once the notifiers are converted to + * states. + */ + [CPUHP_AP_NOTIFY_STARTING] = { + .name = "notify:starting", + .startup = notify_starting, + .teardown = notify_dying, + .skip_onerr = true, + .cant_stop = true, + }, + /* Entry state on starting. Interrupts enabled from here on. Transient + * state for synchronsization */ + [CPUHP_AP_ONLINE] = { + .name = "ap:online", + }, + /* Handle smpboot threads park/unpark */ + [CPUHP_AP_SMPBOOT_THREADS] = { + .name = "smpboot:threads", + .startup = smpboot_unpark_threads, + .teardown = NULL, + }, + /* + * Online/down_prepare notifiers. Will be removed once the notifiers + * are converted to states. + */ + [CPUHP_AP_NOTIFY_ONLINE] = { + .name = "notify:online", + .startup = notify_online, + .teardown = notify_down_prepare, + }, +#endif + /* + * The dynamically registered state space is here + */ + + /* CPU is fully up and running. */ + [CPUHP_ONLINE] = { + .name = "online", + .startup = NULL, + .teardown = NULL, + }, +}; + +/* Sanity check for callbacks */ +static int cpuhp_cb_check(enum cpuhp_state state) +{ + if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) + return -EINVAL; + return 0; +} + +static bool cpuhp_is_ap_state(enum cpuhp_state state) +{ + /* + * The extra check for CPUHP_TEARDOWN_CPU is only for documentation + * purposes as that state is handled explicitely in cpu_down. + */ + return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; +} + +static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) +{ + struct cpuhp_step *sp; + + sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states; + return sp + state; +} + +static void cpuhp_store_callbacks(enum cpuhp_state state, + const char *name, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) +{ + /* (Un)Install the callbacks for further cpu hotplug operations */ + struct cpuhp_step *sp; + + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(state); + sp->startup = startup; + sp->teardown = teardown; + sp->name = name; + mutex_unlock(&cpuhp_state_mutex); +} + +static void *cpuhp_get_teardown_cb(enum cpuhp_state state) +{ + return cpuhp_get_step(state)->teardown; +} + +/* + * Call the startup/teardown function for a step either on the AP or + * on the current CPU. + */ +static int cpuhp_issue_call(int cpu, enum cpuhp_state state, + int (*cb)(unsigned int), bool bringup) +{ + int ret; + + if (!cb) + return 0; + /* + * The non AP bound callbacks can fail on bringup. On teardown + * e.g. module removal we crash for now. + */ +#ifdef CONFIG_SMP + if (cpuhp_is_ap_state(state)) + ret = cpuhp_invoke_ap_callback(cpu, state, cb); + else + ret = cpuhp_invoke_callback(cpu, state, cb); +#else + ret = cpuhp_invoke_callback(cpu, state, cb); +#endif + BUG_ON(ret && !bringup); + return ret; +} + +/* + * Called from __cpuhp_setup_state on a recoverable failure. + * + * Note: The teardown callbacks for rollback are not allowed to fail! + */ +static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, + int (*teardown)(unsigned int cpu)) +{ + int cpu; + + if (!teardown) + return; + + /* Roll back the already executed steps on the other cpus */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpu >= failedcpu) + break; + + /* Did we invoke the startup call on that cpu ? */ + if (cpustate >= state) + cpuhp_issue_call(cpu, state, teardown, false); + } +} + +/* + * Returns a free for dynamic slot assignment of the Online state. The states + * are protected by the cpuhp_slot_states mutex and an empty slot is identified + * by having no name assigned. + */ +static int cpuhp_reserve_state(enum cpuhp_state state) +{ + enum cpuhp_state i; + + mutex_lock(&cpuhp_state_mutex); + for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) { + if (cpuhp_ap_states[i].name) + continue; + + cpuhp_ap_states[i].name = "Reserved"; + mutex_unlock(&cpuhp_state_mutex); + return i; + } + mutex_unlock(&cpuhp_state_mutex); + WARN(1, "No more dynamic states available for CPU hotplug\n"); + return -ENOSPC; +} + /** - * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers - * @cpu: cpu that just started + * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state + * @state: The state to setup + * @invoke: If true, the startup function is invoked for cpus where + * cpu state >= @state + * @startup: startup callback function + * @teardown: teardown callback function * - * This function calls the cpu_chain notifiers with CPU_STARTING. - * It must be called by the arch code on the new cpu, before the new cpu - * enables interrupts and before the "boot" cpu returns from __cpu_up(). + * Returns 0 if successful, otherwise a proper error code */ -void notify_cpu_starting(unsigned int cpu) +int __cpuhp_setup_state(enum cpuhp_state state, + const char *name, bool invoke, + int (*startup)(unsigned int cpu), + int (*teardown)(unsigned int cpu)) { - unsigned long val = CPU_STARTING; + int cpu, ret = 0; + int dyn_state = 0; -#ifdef CONFIG_PM_SLEEP_SMP - if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus)) - val = CPU_STARTING_FROZEN; -#endif /* CONFIG_PM_SLEEP_SMP */ - cpu_notify(val, (void *)(long)cpu); + if (cpuhp_cb_check(state) || !name) + return -EINVAL; + + get_online_cpus(); + + /* currently assignments for the ONLINE state are possible */ + if (state == CPUHP_AP_ONLINE_DYN) { + dyn_state = 1; + ret = cpuhp_reserve_state(state); + if (ret < 0) + goto out; + state = ret; + } + + cpuhp_store_callbacks(state, name, startup, teardown); + + if (!invoke || !startup) + goto out; + + /* + * Try to call the startup callback for each present cpu + * depending on the hotplug state of the cpu. + */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpustate < state) + continue; + + ret = cpuhp_issue_call(cpu, state, startup, true); + if (ret) { + cpuhp_rollback_install(cpu, state, teardown); + cpuhp_store_callbacks(state, NULL, NULL, NULL); + goto out; + } + } +out: + put_online_cpus(); + if (!ret && dyn_state) + return state; + return ret; } +EXPORT_SYMBOL(__cpuhp_setup_state); -#endif /* CONFIG_SMP */ +/** + * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state + * @state: The state to remove + * @invoke: If true, the teardown function is invoked for cpus where + * cpu state >= @state + * + * The teardown callback is currently not allowed to fail. Think + * about module removal! + */ +void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) +{ + int (*teardown)(unsigned int cpu) = cpuhp_get_teardown_cb(state); + int cpu; + + BUG_ON(cpuhp_cb_check(state)); + + get_online_cpus(); + + if (!invoke || !teardown) + goto remove; + + /* + * Call the teardown callback for each present cpu depending + * on the hotplug state of the cpu. This function is not + * allowed to fail currently! + */ + for_each_present_cpu(cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int cpustate = st->state; + + if (cpustate >= state) + cpuhp_issue_call(cpu, state, teardown, false); + } +remove: + cpuhp_store_callbacks(state, NULL, NULL, NULL); + put_online_cpus(); +} +EXPORT_SYMBOL(__cpuhp_remove_state); + +#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) +static ssize_t show_cpuhp_state(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->state); +} +static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL); + +static ssize_t write_cpuhp_target(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int target, ret; + + ret = kstrtoint(buf, 10, &target); + if (ret) + return ret; + +#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL + if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) + return -EINVAL; +#else + if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) + return -EINVAL; +#endif + + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; + + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(target); + ret = !sp->name || sp->cant_stop ? -EINVAL : 0; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + if (st->state < target) + ret = do_cpu_up(dev->id, target); + else + ret = do_cpu_down(dev->id, target); + + unlock_device_hotplug(); + return ret ? ret : count; +} + +static ssize_t show_cpuhp_target(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->target); +} +static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static struct attribute *cpuhp_cpu_attrs[] = { + &dev_attr_state.attr, + &dev_attr_target.attr, + NULL +}; + +static struct attribute_group cpuhp_cpu_attr_group = { + .attrs = cpuhp_cpu_attrs, + .name = "hotplug", + NULL +}; + +static ssize_t show_cpuhp_states(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t cur, res = 0; + int i; + + mutex_lock(&cpuhp_state_mutex); + for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { + struct cpuhp_step *sp = cpuhp_get_step(i); + + if (sp->name) { + cur = sprintf(buf, "%3d: %s\n", i, sp->name); + buf += cur; + res += cur; + } + } + mutex_unlock(&cpuhp_state_mutex); + return res; +} +static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL); + +static struct attribute *cpuhp_cpu_root_attrs[] = { + &dev_attr_states.attr, + NULL +}; + +static struct attribute_group cpuhp_cpu_root_attr_group = { + .attrs = cpuhp_cpu_root_attrs, + .name = "hotplug", + NULL +}; + +static int __init cpuhp_sysfs_init(void) +{ + int cpu, ret; + + ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpuhp_cpu_root_attr_group); + if (ret) + return ret; + + for_each_possible_cpu(cpu) { + struct device *dev = get_cpu_device(cpu); + + if (!dev) + continue; + ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); + if (ret) + return ret; + } + return 0; +} +device_initcall(cpuhp_sysfs_init); +#endif /* * cpu_bit_bitmap[] is a special, "compressed" data structure that @@ -789,3 +1673,25 @@ void init_cpu_online(const struct cpumask *src) { cpumask_copy(&__cpu_online_mask, src); } + +/* + * Activate the first processor. + */ +void __init boot_cpu_init(void) +{ + int cpu = smp_processor_id(); + + /* Mark the boot cpu "present", "online" etc for SMP and UP case */ + set_cpu_online(cpu, true); + set_cpu_active(cpu, true); + set_cpu_present(cpu, true); + set_cpu_possible(cpu, true); +} + +/* + * Must be called _AFTER_ setting up the per_cpu areas + */ +void __init boot_cpu_state_init(void) +{ + per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; +} diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index e1dbf4a2c69e4..90ff129c88a27 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -153,13 +153,11 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp) } else { kdb_printf("%s: failed to set breakpoint at 0x%lx\n", __func__, bp->bp_addr); -#ifdef CONFIG_DEBUG_RODATA if (!bp->bp_type) { kdb_printf("Software breakpoints are unavailable.\n" - " Change the kernel CONFIG_DEBUG_RODATA=n\n" + " Boot the kernel with rodata=off\n" " OR use hw breaks: help bph\n"); } -#endif return 1; } return 0; diff --git a/kernel/events/core.c b/kernel/events/core.c index 614614821f00a..712570dddacde 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3112,17 +3112,6 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx) return rotate; } -#ifdef CONFIG_NO_HZ_FULL -bool perf_event_can_stop_tick(void) -{ - if (atomic_read(&nr_freq_events) || - __this_cpu_read(perf_throttled_count)) - return false; - else - return true; -} -#endif - void perf_event_task_tick(void) { struct list_head *head = this_cpu_ptr(&active_ctx_list); @@ -3133,6 +3122,7 @@ void perf_event_task_tick(void) __this_cpu_inc(perf_throttled_seq); throttled = __this_cpu_xchg(perf_throttled_count, 0); + tick_dep_clear_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); list_for_each_entry_safe(ctx, tmp, head, active_ctx_list) perf_adjust_freq_unthr_context(ctx, throttled); @@ -3564,6 +3554,28 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu) atomic_dec(&per_cpu(perf_cgroup_events, cpu)); } +#ifdef CONFIG_NO_HZ_FULL +static DEFINE_SPINLOCK(nr_freq_lock); +#endif + +static void unaccount_freq_event_nohz(void) +{ +#ifdef CONFIG_NO_HZ_FULL + spin_lock(&nr_freq_lock); + if (atomic_dec_and_test(&nr_freq_events)) + tick_nohz_dep_clear(TICK_DEP_BIT_PERF_EVENTS); + spin_unlock(&nr_freq_lock); +#endif +} + +static void unaccount_freq_event(void) +{ + if (tick_nohz_full_enabled()) + unaccount_freq_event_nohz(); + else + atomic_dec(&nr_freq_events); +} + static void unaccount_event(struct perf_event *event) { bool dec = false; @@ -3580,7 +3592,7 @@ static void unaccount_event(struct perf_event *event) if (event->attr.task) atomic_dec(&nr_task_events); if (event->attr.freq) - atomic_dec(&nr_freq_events); + unaccount_freq_event(); if (event->attr.context_switch) { dec = true; atomic_dec(&nr_switch_events); @@ -6424,9 +6436,9 @@ static int __perf_event_overflow(struct perf_event *event, if (unlikely(throttle && hwc->interrupts >= max_samples_per_tick)) { __this_cpu_inc(perf_throttled_count); + tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); hwc->interrupts = MAX_INTERRUPTS; perf_log_throttle(event, 0); - tick_nohz_full_kick(); ret = 1; } } @@ -6785,7 +6797,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash) kfree_rcu(hlist, rcu_head); } -static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) +static void swevent_hlist_put_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); @@ -6797,15 +6809,15 @@ static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) mutex_unlock(&swhash->hlist_mutex); } -static void swevent_hlist_put(struct perf_event *event) +static void swevent_hlist_put(void) { int cpu; for_each_possible_cpu(cpu) - swevent_hlist_put_cpu(event, cpu); + swevent_hlist_put_cpu(cpu); } -static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) +static int swevent_hlist_get_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); int err = 0; @@ -6828,14 +6840,13 @@ static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) return err; } -static int swevent_hlist_get(struct perf_event *event) +static int swevent_hlist_get(void) { - int err; - int cpu, failed_cpu; + int err, cpu, failed_cpu; get_online_cpus(); for_each_possible_cpu(cpu) { - err = swevent_hlist_get_cpu(event, cpu); + err = swevent_hlist_get_cpu(cpu); if (err) { failed_cpu = cpu; goto fail; @@ -6848,7 +6859,7 @@ static int swevent_hlist_get(struct perf_event *event) for_each_possible_cpu(cpu) { if (cpu == failed_cpu) break; - swevent_hlist_put_cpu(event, cpu); + swevent_hlist_put_cpu(cpu); } put_online_cpus(); @@ -6864,7 +6875,7 @@ static void sw_perf_event_destroy(struct perf_event *event) WARN_ON(event->parent); static_key_slow_dec(&perf_swevent_enabled[event_id]); - swevent_hlist_put(event); + swevent_hlist_put(); } static int perf_swevent_init(struct perf_event *event) @@ -6895,7 +6906,7 @@ static int perf_swevent_init(struct perf_event *event) if (!event->parent) { int err; - err = swevent_hlist_get(event); + err = swevent_hlist_get(); if (err) return err; @@ -7816,6 +7827,27 @@ static void account_event_cpu(struct perf_event *event, int cpu) atomic_inc(&per_cpu(perf_cgroup_events, cpu)); } +/* Freq events need the tick to stay alive (see perf_event_task_tick). */ +static void account_freq_event_nohz(void) +{ +#ifdef CONFIG_NO_HZ_FULL + /* Lock so we don't race with concurrent unaccount */ + spin_lock(&nr_freq_lock); + if (atomic_inc_return(&nr_freq_events) == 1) + tick_nohz_dep_set(TICK_DEP_BIT_PERF_EVENTS); + spin_unlock(&nr_freq_lock); +#endif +} + +static void account_freq_event(void) +{ + if (tick_nohz_full_enabled()) + account_freq_event_nohz(); + else + atomic_inc(&nr_freq_events); +} + + static void account_event(struct perf_event *event) { bool inc = false; @@ -7831,10 +7863,8 @@ static void account_event(struct perf_event *event) atomic_inc(&nr_comm_events); if (event->attr.task) atomic_inc(&nr_task_events); - if (event->attr.freq) { - if (atomic_inc_return(&nr_freq_events) == 1) - tick_nohz_full_kick_all(); - } + if (event->attr.freq) + account_freq_event(); if (event->attr.context_switch) { atomic_inc(&nr_switch_events); inc = true; @@ -8001,6 +8031,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, } } + /* symmetric to unaccount_event() in _free_event() */ + account_event(event); + return event; err_per_task: @@ -8364,8 +8397,6 @@ SYSCALL_DEFINE5(perf_event_open, } } - account_event(event); - /* * Special case software events and allow them to be part of * any hardware group. @@ -8662,8 +8693,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, /* Mark owner so we could distinguish it from user events. */ event->owner = TASK_TOMBSTONE; - account_event(event); - ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); @@ -9447,6 +9476,7 @@ ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, return 0; } +EXPORT_SYMBOL_GPL(perf_event_sysfs_show); static int __init perf_event_sysfs_init(void) { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 0167679182c08..5f6ce931f1eac 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1178,6 +1178,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) goto free_area; area->xol_mapping.name = "[uprobes]"; + area->xol_mapping.fault = NULL; area->xol_mapping.pages = area->pages; area->pages[0] = alloc_page(GFP_HIGHUSER); if (!area->pages[0]) diff --git a/kernel/futex.c b/kernel/futex.c index 5d6ce6413ef1d..a5d2e74c89e0b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -124,16 +124,16 @@ * futex_wait(futex, val); * * waiters++; (a) - * mb(); (A) <-- paired with -. - * | - * lock(hash_bucket(futex)); | - * | - * uval = *futex; | - * | *futex = newval; - * | sys_futex(WAKE, futex); - * | futex_wake(futex); - * | - * `-------> mb(); (B) + * smp_mb(); (A) <-- paired with -. + * | + * lock(hash_bucket(futex)); | + * | + * uval = *futex; | + * | *futex = newval; + * | sys_futex(WAKE, futex); + * | futex_wake(futex); + * | + * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); @@ -334,7 +334,7 @@ static inline void futex_get_mm(union futex_key *key) /* * Ensure futex_get_mm() implies a full barrier such that * get_futex_key() implies a full barrier. This is relied upon - * as full barrier (B), see the ordering comment above. + * as smp_mb(); (B), see the ordering comment above. */ smp_mb__after_atomic(); } @@ -407,10 +407,10 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - ihold(key->shared.inode); /* implies MB (B) */ + ihold(key->shared.inode); /* implies smp_mb(); (B) */ break; case FUT_OFF_MMSHARED: - futex_get_mm(key); /* implies MB (B) */ + futex_get_mm(key); /* implies smp_mb(); (B) */ break; default: /* @@ -418,7 +418,7 @@ static void get_futex_key_refs(union futex_key *key) * mm, therefore the only purpose of calling get_futex_key_refs * is because we need the barrier for the lockless waiter check. */ - smp_mb(); /* explicit MB (B) */ + smp_mb(); /* explicit smp_mb(); (B) */ } } @@ -497,7 +497,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) if (!fshared) { key->private.mm = mm; key->private.address = address; - get_futex_key_refs(key); /* implies MB (B) */ + get_futex_key_refs(key); /* implies smp_mb(); (B) */ return 0; } @@ -520,7 +520,20 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) else err = 0; - lock_page(page); + /* + * The treatment of mapping from this point on is critical. The page + * lock protects many things but in this context the page lock + * stabilizes mapping, prevents inode freeing in the shared + * file-backed region case and guards against movement to swap cache. + * + * Strictly speaking the page lock is not needed in all cases being + * considered here and page lock forces unnecessarily serialization + * From this point on, mapping will be re-verified if necessary and + * page lock will be acquired only if it is unavoidable + */ + page = compound_head(page); + mapping = READ_ONCE(page->mapping); + /* * If page->mapping is NULL, then it cannot be a PageAnon * page; but it might be the ZERO_PAGE or in the gate area or @@ -536,19 +549,31 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for page->mapping. */ - mapping = compound_head(page)->mapping; - if (!mapping) { - int shmem_swizzled = PageSwapCache(page); + if (unlikely(!mapping)) { + int shmem_swizzled; + + /* + * Page lock is required to identify which special case above + * applies. If this is really a shmem page then the page lock + * will prevent unexpected transitions. + */ + lock_page(page); + shmem_swizzled = PageSwapCache(page) || page->mapping; unlock_page(page); put_page(page); + if (shmem_swizzled) goto again; + return -EFAULT; } /* * Private mappings are handled in a simple way. * + * If the futex key is stored on an anonymous page, then the associated + * object is the mm which is implicitly pinned by the calling process. + * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. @@ -566,16 +591,74 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; + + get_futex_key_refs(key); /* implies smp_mb(); (B) */ + } else { + struct inode *inode; + + /* + * The associated futex object in this case is the inode and + * the page->mapping must be traversed. Ordinarily this should + * be stabilised under page lock but it's not strictly + * necessary in this case as we just want to pin the inode, not + * update the radix tree or anything like that. + * + * The RCU read lock is taken as the inode is finally freed + * under RCU. If the mapping still matches expectations then the + * mapping->host can be safely accessed as being a valid inode. + */ + rcu_read_lock(); + + if (READ_ONCE(page->mapping) != mapping) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + inode = READ_ONCE(mapping->host); + if (!inode) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + /* + * Take a reference unless it is about to be freed. Previously + * this reference was taken by ihold under the page lock + * pinning the inode in place so i_lock was unnecessary. The + * only way for this check to fail is if the inode was + * truncated in parallel so warn for now if this happens. + * + * We are not calling into get_futex_key_refs() in file-backed + * cases, therefore a successful atomic_inc return below will + * guarantee that get_futex_key() will still imply smp_mb(); (B). + */ + if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + /* Should be impossible but lets be paranoid for now */ + if (WARN_ON_ONCE(inode->i_mapping != mapping)) { + err = -EFAULT; + rcu_read_unlock(); + iput(inode); + + goto out; + } + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = mapping->host; + key->shared.inode = inode; key->shared.pgoff = basepage_index(page); + rcu_read_unlock(); } - get_futex_key_refs(key); /* implies MB (B) */ - out: - unlock_page(page); put_page(page); return err; } @@ -1864,7 +1947,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) q->lock_ptr = &hb->lock; - spin_lock(&hb->lock); /* implies MB (A) */ + spin_lock(&hb->lock); /* implies smp_mb(); (A) */ return hb; } @@ -1927,8 +2010,12 @@ static int unqueue_me(struct futex_q *q) /* In the common case we don't take the spinlock, which is nice. */ retry: - lock_ptr = q->lock_ptr; - barrier(); + /* + * q->lock_ptr can change between this read and the following spin_lock. + * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and + * optimizing lock_ptr out of the logic below. + */ + lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 3b48dab801648..3bbfd6a9c4756 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -64,6 +64,10 @@ config IRQ_DOMAIN_HIERARCHY bool select IRQ_DOMAIN +# Generic IRQ IPI support +config GENERIC_IRQ_IPI + bool + # Generic MSI interrupt support config GENERIC_MSI_IRQ bool diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 2fc9cbdf35b62..2ee42e95a3ce1 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -8,3 +8,4 @@ obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o +obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 5797909f4e5b1..2f9f2b0e79f2d 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -961,6 +961,7 @@ void irq_chip_mask_parent(struct irq_data *data) data = data->parent_data; data->chip->irq_mask(data); } +EXPORT_SYMBOL_GPL(irq_chip_mask_parent); /** * irq_chip_unmask_parent - Unmask the parent interrupt @@ -971,6 +972,7 @@ void irq_chip_unmask_parent(struct irq_data *data) data = data->parent_data; data->chip->irq_unmask(data); } +EXPORT_SYMBOL_GPL(irq_chip_unmask_parent); /** * irq_chip_eoi_parent - Invoke EOI on the parent interrupt @@ -981,6 +983,7 @@ void irq_chip_eoi_parent(struct irq_data *data) data = data->parent_data; data->chip->irq_eoi(data); } +EXPORT_SYMBOL_GPL(irq_chip_eoi_parent); /** * irq_chip_set_affinity_parent - Set affinity on the parent interrupt @@ -1016,6 +1019,7 @@ int irq_chip_set_type_parent(struct irq_data *data, unsigned int type) return -ENOSYS; } +EXPORT_SYMBOL_GPL(irq_chip_set_type_parent); /** * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 57bff7857e879..a15b5485b446e 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -136,10 +136,9 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval = IRQ_NONE; unsigned int flags = 0, irq = desc->irq_data.irq; - struct irqaction *action = desc->action; + struct irqaction *action; - /* action might have become NULL since we dropped the lock */ - while (action) { + for_each_action_of_desc(desc, action) { irqreturn_t res; trace_irq_handler_entry(irq, action); @@ -173,7 +172,6 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) } retval |= res; - action = action->next; } add_interrupt_randomness(irq, flags); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index fcab63c669059..09be2c903c6d3 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -131,6 +131,9 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc) #define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK) #define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU) +#define for_each_action_of_desc(desc, act) \ + for (act = desc->act; act; act = act->next) + struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check); @@ -160,6 +163,8 @@ irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) __irq_put_desc_unlock(desc, flags, false); } +#define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) + /* * Manipulation functions for irq_data.state */ @@ -188,6 +193,8 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) return __irqd_to_state(d) & mask; } +#undef __irqd_to_state + static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __this_cpu_inc(*desc->kstat_irqs); diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c new file mode 100644 index 0000000000000..c37f34b00a115 --- /dev/null +++ b/kernel/irq/ipi.c @@ -0,0 +1,326 @@ +/* + * linux/kernel/irq/ipi.c + * + * Copyright (C) 2015 Imagination Technologies Ltd + * Author: Qais Yousef + * + * This file contains driver APIs to the IPI subsystem. + */ + +#define pr_fmt(fmt) "genirq/ipi: " fmt + +#include +#include + +/** + * irq_reserve_ipi() - Setup an IPI to destination cpumask + * @domain: IPI domain + * @dest: cpumask of cpus which can receive the IPI + * + * Allocate a virq that can be used to send IPI to any CPU in dest mask. + * + * On success it'll return linux irq number and 0 on failure + */ +unsigned int irq_reserve_ipi(struct irq_domain *domain, + const struct cpumask *dest) +{ + unsigned int nr_irqs, offset; + struct irq_data *data; + int virq, i; + + if (!domain ||!irq_domain_is_ipi(domain)) { + pr_warn("Reservation on a non IPI domain\n"); + return 0; + } + + if (!cpumask_subset(dest, cpu_possible_mask)) { + pr_warn("Reservation is not in possible_cpu_mask\n"); + return 0; + } + + nr_irqs = cpumask_weight(dest); + if (!nr_irqs) { + pr_warn("Reservation for empty destination mask\n"); + return 0; + } + + if (irq_domain_is_ipi_single(domain)) { + /* + * If the underlying implementation uses a single HW irq on + * all cpus then we only need a single Linux irq number for + * it. We have no restrictions vs. the destination mask. The + * underlying implementation can deal with holes nicely. + */ + nr_irqs = 1; + offset = 0; + } else { + unsigned int next; + + /* + * The IPI requires a seperate HW irq on each CPU. We require + * that the destination mask is consecutive. If an + * implementation needs to support holes, it can reserve + * several IPI ranges. + */ + offset = cpumask_first(dest); + /* + * Find a hole and if found look for another set bit after the + * hole. For now we don't support this scenario. + */ + next = cpumask_next_zero(offset, dest); + if (next < nr_cpu_ids) + next = cpumask_next(next, dest); + if (next < nr_cpu_ids) { + pr_warn("Destination mask has holes\n"); + return 0; + } + } + + virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE); + if (virq <= 0) { + pr_warn("Can't reserve IPI, failed to alloc descs\n"); + return 0; + } + + virq = __irq_domain_alloc_irqs(domain, virq, nr_irqs, NUMA_NO_NODE, + (void *) dest, true); + + if (virq <= 0) { + pr_warn("Can't reserve IPI, failed to alloc hw irqs\n"); + goto free_descs; + } + + for (i = 0; i < nr_irqs; i++) { + data = irq_get_irq_data(virq + i); + cpumask_copy(data->common->affinity, dest); + data->common->ipi_offset = offset; + } + return virq; + +free_descs: + irq_free_descs(virq, nr_irqs); + return 0; +} + +/** + * irq_destroy_ipi() - unreserve an IPI that was previously allocated + * @irq: linux irq number to be destroyed + * + * Return the IPIs allocated with irq_reserve_ipi() to the system destroying + * all virqs associated with them. + */ +void irq_destroy_ipi(unsigned int irq) +{ + struct irq_data *data = irq_get_irq_data(irq); + struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; + struct irq_domain *domain; + unsigned int nr_irqs; + + if (!irq || !data || !ipimask) + return; + + domain = data->domain; + if (WARN_ON(domain == NULL)) + return; + + if (!irq_domain_is_ipi(domain)) { + pr_warn("Trying to destroy a non IPI domain!\n"); + return; + } + + if (irq_domain_is_ipi_per_cpu(domain)) + nr_irqs = cpumask_weight(ipimask); + else + nr_irqs = 1; + + irq_domain_free_irqs(irq, nr_irqs); +} + +/** + * ipi_get_hwirq - Get the hwirq associated with an IPI to a cpu + * @irq: linux irq number + * @cpu: the target cpu + * + * When dealing with coprocessors IPI, we need to inform the coprocessor of + * the hwirq it needs to use to receive and send IPIs. + * + * Returns hwirq value on success and INVALID_HWIRQ on failure. + */ +irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu) +{ + struct irq_data *data = irq_get_irq_data(irq); + struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; + + if (!data || !ipimask || cpu > nr_cpu_ids) + return INVALID_HWIRQ; + + if (!cpumask_test_cpu(cpu, ipimask)) + return INVALID_HWIRQ; + + /* + * Get the real hardware irq number if the underlying implementation + * uses a seperate irq per cpu. If the underlying implementation uses + * a single hardware irq for all cpus then the IPI send mechanism + * needs to take care of the cpu destinations. + */ + if (irq_domain_is_ipi_per_cpu(data->domain)) + data = irq_get_irq_data(irq + cpu - data->common->ipi_offset); + + return data ? irqd_to_hwirq(data) : INVALID_HWIRQ; +} +EXPORT_SYMBOL_GPL(ipi_get_hwirq); + +static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, + const struct cpumask *dest, unsigned int cpu) +{ + struct cpumask *ipimask = irq_data_get_affinity_mask(data); + + if (!chip || !ipimask) + return -EINVAL; + + if (!chip->ipi_send_single && !chip->ipi_send_mask) + return -EINVAL; + + if (cpu > nr_cpu_ids) + return -EINVAL; + + if (dest) { + if (!cpumask_subset(dest, ipimask)) + return -EINVAL; + } else { + if (!cpumask_test_cpu(cpu, ipimask)) + return -EINVAL; + } + return 0; +} + +/** + * __ipi_send_single - send an IPI to a target Linux SMP CPU + * @desc: pointer to irq_desc of the IRQ + * @cpu: destination CPU, must in the destination mask passed to + * irq_reserve_ipi() + * + * This function is for architecture or core code to speed up IPI sending. Not + * usable from driver code. + * + * Returns zero on success and negative error number on failure. + */ +int __ipi_send_single(struct irq_desc *desc, unsigned int cpu) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_chip *chip = irq_data_get_irq_chip(data); + +#ifdef DEBUG + /* + * Minimise the overhead by omitting the checks for Linux SMP IPIs. + * Since the callers should be arch or core code which is generally + * trusted, only check for errors when debugging. + */ + if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu))) + return -EINVAL; +#endif + if (!chip->ipi_send_single) { + chip->ipi_send_mask(data, cpumask_of(cpu)); + return 0; + } + + /* FIXME: Store this information in irqdata flags */ + if (irq_domain_is_ipi_per_cpu(data->domain) && + cpu != data->common->ipi_offset) { + /* use the correct data for that cpu */ + unsigned irq = data->irq + cpu - data->common->ipi_offset; + + data = irq_get_irq_data(irq); + } + chip->ipi_send_single(data, cpu); + return 0; +} + +/** + * ipi_send_mask - send an IPI to target Linux SMP CPU(s) + * @desc: pointer to irq_desc of the IRQ + * @dest: dest CPU(s), must be a subset of the mask passed to + * irq_reserve_ipi() + * + * This function is for architecture or core code to speed up IPI sending. Not + * usable from driver code. + * + * Returns zero on success and negative error number on failure. + */ +int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + struct irq_chip *chip = irq_data_get_irq_chip(data); + unsigned int cpu; + +#ifdef DEBUG + /* + * Minimise the overhead by omitting the checks for Linux SMP IPIs. + * Since the callers should be arch or core code which is generally + * trusted, only check for errors when debugging. + */ + if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0))) + return -EINVAL; +#endif + if (chip->ipi_send_mask) { + chip->ipi_send_mask(data, dest); + return 0; + } + + if (irq_domain_is_ipi_per_cpu(data->domain)) { + unsigned int base = data->irq; + + for_each_cpu(cpu, dest) { + unsigned irq = base + cpu - data->common->ipi_offset; + + data = irq_get_irq_data(irq); + chip->ipi_send_single(data, cpu); + } + } else { + for_each_cpu(cpu, dest) + chip->ipi_send_single(data, cpu); + } + return 0; +} + +/** + * ipi_send_single - Send an IPI to a single CPU + * @virq: linux irq number from irq_reserve_ipi() + * @cpu: destination CPU, must in the destination mask passed to + * irq_reserve_ipi() + * + * Returns zero on success and negative error number on failure. + */ +int ipi_send_single(unsigned int virq, unsigned int cpu) +{ + struct irq_desc *desc = irq_to_desc(virq); + struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL; + struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL; + + if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu))) + return -EINVAL; + + return __ipi_send_single(desc, cpu); +} +EXPORT_SYMBOL_GPL(ipi_send_single); + +/** + * ipi_send_mask - Send an IPI to target CPU(s) + * @virq: linux irq number from irq_reserve_ipi() + * @dest: dest CPU(s), must be a subset of the mask passed to + * irq_reserve_ipi() + * + * Returns zero on success and negative error number on failure. + */ +int ipi_send_mask(unsigned int virq, const struct cpumask *dest) +{ + struct irq_desc *desc = irq_to_desc(virq); + struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL; + struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL; + + if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0))) + return -EINVAL; + + return __ipi_send_mask(desc, dest); +} +EXPORT_SYMBOL_GPL(ipi_send_mask); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 0409da0bcc335..0ccd028817d71 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -24,10 +24,27 @@ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) +static int __init irq_affinity_setup(char *str) +{ + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); + cpulist_parse(str, irq_default_affinity); + /* + * Set at least the boot cpu. We don't want to end up with + * bugreports caused by random comandline masks + */ + cpumask_set_cpu(smp_processor_id(), irq_default_affinity); + return 1; +} +__setup("irqaffinity=", irq_affinity_setup); + static void __init init_irq_default_affinity(void) { - alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); - cpumask_setall(irq_default_affinity); +#ifdef CONFIG_CPUMASK_OFFSTACK + if (!irq_default_affinity) + zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); +#endif + if (cpumask_empty(irq_default_affinity)) + cpumask_setall(irq_default_affinity); } #else static void __init init_irq_default_affinity(void) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 3e56d2f03e24e..3a519a01118b0 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -23,8 +23,6 @@ static DEFINE_MUTEX(irq_domain_mutex); static DEFINE_MUTEX(revmap_trees_mutex); static struct irq_domain *irq_default_domain; -static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, - irq_hw_number_t hwirq, int node); static void irq_domain_check_hierarchy(struct irq_domain *domain); struct irqchip_fwid { @@ -840,8 +838,8 @@ const struct irq_domain_ops irq_domain_simple_ops = { }; EXPORT_SYMBOL_GPL(irq_domain_simple_ops); -static int irq_domain_alloc_descs(int virq, unsigned int cnt, - irq_hw_number_t hwirq, int node) +int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq, + int node) { unsigned int hint; @@ -895,6 +893,7 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, return domain; } +EXPORT_SYMBOL_GPL(irq_domain_create_hierarchy); static void irq_domain_insert_irq(int virq) { @@ -1045,6 +1044,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, return 0; } +EXPORT_SYMBOL_GPL(irq_domain_set_hwirq_and_chip); /** * irq_domain_set_info - Set the complete data for a @virq in @domain @@ -1078,6 +1078,7 @@ void irq_domain_reset_irq_data(struct irq_data *irq_data) irq_data->chip = &no_irq_chip; irq_data->chip_data = NULL; } +EXPORT_SYMBOL_GPL(irq_domain_reset_irq_data); /** * irq_domain_free_irqs_common - Clear irq_data and free the parent @@ -1275,6 +1276,7 @@ int irq_domain_alloc_irqs_parent(struct irq_domain *domain, nr_irqs, arg); return -ENOSYS; } +EXPORT_SYMBOL_GPL(irq_domain_alloc_irqs_parent); /** * irq_domain_free_irqs_parent - Free interrupts from parent domain @@ -1292,6 +1294,7 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, irq_domain_free_irqs_recursive(domain->parent, irq_base, nr_irqs); } +EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); /** * irq_domain_activate_irq - Call domain_ops->activate recursively to activate diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 841187239adc8..3ddd2297ee95d 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -144,13 +144,11 @@ int irq_can_set_affinity(unsigned int irq) */ void irq_set_thread_affinity(struct irq_desc *desc) { - struct irqaction *action = desc->action; + struct irqaction *action; - while (action) { + for_each_action_of_desc(desc, action) if (action->thread) set_bit(IRQTF_AFFINITY, &action->thread_flags); - action = action->next; - } } #ifdef CONFIG_GENERIC_PENDING_IRQ @@ -994,7 +992,7 @@ void irq_wake_thread(unsigned int irq, void *dev_id) return; raw_spin_lock_irqsave(&desc->lock, flags); - for (action = desc->action; action; action = action->next) { + for_each_action_of_desc(desc, action) { if (action->dev_id == dev_id) { if (action->thread) __irq_wake_thread(desc, action); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index a2c02fd5d6d0f..4e1b947268180 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -291,7 +291,7 @@ static int name_unique(unsigned int irq, struct irqaction *new_action) int ret = 1; raw_spin_lock_irqsave(&desc->lock, flags); - for (action = desc->action ; action; action = action->next) { + for_each_action_of_desc(desc, action) { if ((action != new_action) && action->name && !strcmp(new_action->name, action->name)) { ret = 0; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 32144175458d7..5707f97a3e6ac 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -211,14 +211,12 @@ static void __report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret) * desc->lock here. See synchronize_irq(). */ raw_spin_lock_irqsave(&desc->lock, flags); - action = desc->action; - while (action) { + for_each_action_of_desc(desc, action) { printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler); if (action->thread_fn) printk(KERN_CONT " threaded [<%p>] %pf", action->thread_fn, action->thread_fn); printk(KERN_CONT "\n"); - action = action->next; } raw_spin_unlock_irqrestore(&desc->lock, flags); } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 8dc6591448699..8d34308ea449a 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -66,13 +66,15 @@ struct resource crashk_res = { .name = "Crash kernel", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL }; struct resource crashk_low_res = { .name = "Crash kernel", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL }; int kexec_should_crash(struct task_struct *p) @@ -959,7 +961,7 @@ int crash_shrink_memory(unsigned long new_size) ram_res->start = end; ram_res->end = crashk_res.end; - ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; ram_res->name = "System RAM"; crashk_res.end = end - 1; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 007b791f676d5..56b18eb1f0013 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -524,10 +524,10 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz, /* Walk the RAM ranges and allocate a suitable range for the buffer */ if (image->type == KEXEC_TYPE_CRASH) - ret = walk_iomem_res("Crash kernel", - IORESOURCE_MEM | IORESOURCE_BUSY, - crashk_res.start, crashk_res.end, kbuf, - locate_mem_hole_callback); + ret = walk_iomem_res_desc(crashk_res.desc, + IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, + crashk_res.start, crashk_res.end, kbuf, + locate_mem_hole_callback); else ret = walk_system_ram_res(0, -1, kbuf, locate_mem_hole_callback); diff --git a/kernel/latencytop.c b/kernel/latencytop.c index a02812743a7e6..b5c30d9f46c50 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -47,12 +47,12 @@ * of times) */ -#include #include #include #include #include #include +#include #include #include #include @@ -289,4 +289,16 @@ static int __init init_lstats_procfs(void) proc_create("latency_stats", 0644, NULL, &lstats_fops); return 0; } + +int sysctl_latencytop(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err; + + err = proc_dointvec(table, write, buffer, lenp, ppos); + if (latencytop_enabled) + force_schedstat_enabled(); + + return err; +} device_initcall(init_lstats_procfs); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 716547fdb8731..f894a2cd9b2aa 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -123,8 +123,6 @@ static inline int debug_locks_off_graph_unlock(void) return ret; } -static int lockdep_initialized; - unsigned long nr_list_entries; static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; @@ -433,19 +431,6 @@ unsigned int nr_process_chains; unsigned int max_lockdep_depth; #ifdef CONFIG_DEBUG_LOCKDEP -/* - * We cannot printk in early bootup code. Not even early_printk() - * might work. So we mark any initialization errors and printk - * about it later on, in lockdep_info(). - */ -static int lockdep_init_error; -static const char *lock_init_error; -static unsigned long lockdep_init_trace_data[20]; -static struct stack_trace lockdep_init_trace = { - .max_entries = ARRAY_SIZE(lockdep_init_trace_data), - .entries = lockdep_init_trace_data, -}; - /* * Various lockdep statistics: */ @@ -669,20 +654,6 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) struct hlist_head *hash_head; struct lock_class *class; -#ifdef CONFIG_DEBUG_LOCKDEP - /* - * If the architecture calls into lockdep before initializing - * the hashes then we'll warn about it later. (we cannot printk - * right now) - */ - if (unlikely(!lockdep_initialized)) { - lockdep_init(); - lockdep_init_error = 1; - lock_init_error = lock->name; - save_stack_trace(&lockdep_init_trace); - } -#endif - if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { debug_locks_off(); printk(KERN_ERR @@ -2010,6 +1981,53 @@ struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i) return lock_classes + chain_hlocks[chain->base + i]; } +/* + * Returns the index of the first held_lock of the current chain + */ +static inline int get_first_held_lock(struct task_struct *curr, + struct held_lock *hlock) +{ + int i; + struct held_lock *hlock_curr; + + for (i = curr->lockdep_depth - 1; i >= 0; i--) { + hlock_curr = curr->held_locks + i; + if (hlock_curr->irq_context != hlock->irq_context) + break; + + } + + return ++i; +} + +/* + * Checks whether the chain and the current held locks are consistent + * in depth and also in content. If they are not it most likely means + * that there was a collision during the calculation of the chain_key. + * Returns: 0 not passed, 1 passed + */ +static int check_no_collision(struct task_struct *curr, + struct held_lock *hlock, + struct lock_chain *chain) +{ +#ifdef CONFIG_DEBUG_LOCKDEP + int i, j, id; + + i = get_first_held_lock(curr, hlock); + + if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) + return 0; + + for (j = 0; j < chain->depth - 1; j++, i++) { + id = curr->held_locks[i].class_idx - 1; + + if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) + return 0; + } +#endif + return 1; +} + /* * Look up a dependency chain. If the key is not present yet then * add it and return 1 - in this case the new dependency chain is @@ -2023,7 +2041,6 @@ static inline int lookup_chain_cache(struct task_struct *curr, struct lock_class *class = hlock_class(hlock); struct hlist_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; - struct held_lock *hlock_curr; int i, j; /* @@ -2041,6 +2058,9 @@ static inline int lookup_chain_cache(struct task_struct *curr, if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(chain_lookup_hits); + if (!check_no_collision(curr, hlock, chain)) + return 0; + if (very_verbose(class)) printk("\nhash chain already cached, key: " "%016Lx tail class: [%p] %s\n", @@ -2078,13 +2098,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, chain = lock_chains + nr_lock_chains++; chain->chain_key = chain_key; chain->irq_context = hlock->irq_context; - /* Find the first held_lock of current chain */ - for (i = curr->lockdep_depth - 1; i >= 0; i--) { - hlock_curr = curr->held_locks + i; - if (hlock_curr->irq_context != hlock->irq_context) - break; - } - i++; + i = get_first_held_lock(curr, hlock); chain->depth = curr->lockdep_depth + 1 - i; if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = nr_chain_hlocks; @@ -2172,7 +2186,7 @@ static void check_chain_key(struct task_struct *curr) { #ifdef CONFIG_DEBUG_LOCKDEP struct held_lock *hlock, *prev_hlock = NULL; - unsigned int i, id; + unsigned int i; u64 chain_key = 0; for (i = 0; i < curr->lockdep_depth; i++) { @@ -2189,17 +2203,16 @@ static void check_chain_key(struct task_struct *curr) (unsigned long long)hlock->prev_chain_key); return; } - id = hlock->class_idx - 1; /* * Whoops ran out of static storage again? */ - if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + if (DEBUG_LOCKS_WARN_ON(hlock->class_idx > MAX_LOCKDEP_KEYS)) return; if (prev_hlock && (prev_hlock->irq_context != hlock->irq_context)) chain_key = 0; - chain_key = iterate_chain_key(chain_key, id); + chain_key = iterate_chain_key(chain_key, hlock->class_idx); prev_hlock = hlock; } if (chain_key != curr->curr_chain_key) { @@ -3077,7 +3090,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, struct task_struct *curr = current; struct lock_class *class = NULL; struct held_lock *hlock; - unsigned int depth, id; + unsigned int depth; int chain_head = 0; int class_idx; u64 chain_key; @@ -3180,11 +3193,10 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, * The 'key ID' is what is the most compact key value to drive * the hash, not class->key. */ - id = class - lock_classes; /* * Whoops, we did it again.. ran straight out of our static allocation. */ - if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + if (DEBUG_LOCKS_WARN_ON(class_idx > MAX_LOCKDEP_KEYS)) return 0; chain_key = curr->curr_chain_key; @@ -3202,7 +3214,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, chain_key = 0; chain_head = 1; } - chain_key = iterate_chain_key(chain_key, id); + chain_key = iterate_chain_key(chain_key, class_idx); if (nest_lock && !__lock_is_held(nest_lock)) return print_lock_nested_lock_not_held(curr, hlock, ip); @@ -4013,28 +4025,6 @@ void lockdep_reset_lock(struct lockdep_map *lock) raw_local_irq_restore(flags); } -void lockdep_init(void) -{ - int i; - - /* - * Some architectures have their own start_kernel() - * code which calls lockdep_init(), while we also - * call lockdep_init() from the start_kernel() itself, - * and we want to initialize the hashes only once: - */ - if (lockdep_initialized) - return; - - for (i = 0; i < CLASSHASH_SIZE; i++) - INIT_HLIST_HEAD(classhash_table + i); - - for (i = 0; i < CHAINHASH_SIZE; i++) - INIT_HLIST_HEAD(chainhash_table + i); - - lockdep_initialized = 1; -} - void __init lockdep_info(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); @@ -4061,14 +4051,6 @@ void __init lockdep_info(void) printk(" per task-struct memory footprint: %lu bytes\n", sizeof(struct held_lock) * MAX_LOCK_DEPTH); - -#ifdef CONFIG_DEBUG_LOCKDEP - if (lockdep_init_error) { - printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error); - printk("Call stack leading to lockdep invocation was:\n"); - print_stack_trace(&lockdep_init_trace, 0); - } -#endif } static void diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 5b9102a47ea52..c835270f0c2f9 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -67,7 +67,13 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) node->locked = 0; node->next = NULL; - prev = xchg_acquire(lock, node); + /* + * We rely on the full barrier with global transitivity implied by the + * below xchg() to order the initialization stores above against any + * observation of @node. And to provide the ACQUIRE ordering associated + * with a LOCK primitive. + */ + prev = xchg(lock, node); if (likely(prev == NULL)) { /* * Lock acquired, don't need to set node->locked to 1. Threads diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 0551c219c40e5..e364b424b019f 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -716,6 +716,7 @@ static inline void __mutex_unlock_common_slowpath(struct mutex *lock, int nested) { unsigned long flags; + WAKE_Q(wake_q); /* * As a performance measurement, release the lock before doing other @@ -743,11 +744,11 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested) struct mutex_waiter, list); debug_mutex_wake_waiter(lock, waiter); - - wake_up_process(waiter->task); + wake_q_add(&wake_q, waiter->task); } spin_unlock_mutex(&lock->wait_lock, flags); + wake_up_q(&wake_q); } /* diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 393d1874b9e0c..ce2f75e32ae15 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -358,8 +358,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * sequentiality; this is because not all clear_pending_set_locked() * implementations imply full barriers. */ - while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK) - cpu_relax(); + smp_cond_acquire(!(atomic_read(&lock->val) & _Q_LOCKED_MASK)); /* * take ownership and clear the pending bit. @@ -435,7 +434,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * * The PV pv_wait_head_or_lock function, if active, will acquire * the lock and return a non-zero value. So we have to skip the - * smp_load_acquire() call. As the next PV queue head hasn't been + * smp_cond_acquire() call. As the next PV queue head hasn't been * designated yet, there is no way for the locked value to become * _Q_SLOW_VAL. So both the set_locked() and the * atomic_cmpxchg_relaxed() calls will be safe. @@ -466,7 +465,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) break; } /* - * The smp_load_acquire() call above has provided the necessary + * The smp_cond_acquire() call above has provided the necessary * acquire semantics required for locking. At most two * iterations of this loop may be ran. */ diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 87bb235c34480..21ede57f68b32 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -54,6 +54,11 @@ struct pv_node { u8 state; }; +/* + * Include queued spinlock statistics code + */ +#include "qspinlock_stat.h" + /* * By replacing the regular queued_spin_trylock() with the function below, * it will be called once when a lock waiter enter the PV slowpath before @@ -65,9 +70,11 @@ struct pv_node { static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock) { struct __qspinlock *l = (void *)lock; + int ret = !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) && + (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0); - return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) && - (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0); + qstat_inc(qstat_pv_lock_stealing, ret); + return ret; } /* @@ -137,11 +144,6 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock) } #endif /* _Q_PENDING_BITS == 8 */ -/* - * Include queued spinlock statistics code - */ -#include "qspinlock_stat.h" - /* * Lock and MCS node addresses hash table for fast lookup * @@ -398,6 +400,11 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) if (READ_ONCE(pn->state) == vcpu_hashed) lp = (struct qspinlock **)1; + /* + * Tracking # of slowpath locking operations + */ + qstat_inc(qstat_pv_lock_slowpath, true); + for (;; waitcnt++) { /* * Set correct vCPU state to be used by queue node wait-early diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 640dcecdd1df7..eb2a2c9bc3fc1 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -22,6 +22,7 @@ * pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake * pv_latency_kick - average latency (ns) of vCPU kick operation * pv_latency_wake - average latency (ns) from vCPU kick to wakeup + * pv_lock_slowpath - # of locking operations via the slowpath * pv_lock_stealing - # of lock stealing operations * pv_spurious_wakeup - # of spurious wakeups * pv_wait_again - # of vCPU wait's that happened after a vCPU kick @@ -45,6 +46,7 @@ enum qlock_stats { qstat_pv_kick_wake, qstat_pv_latency_kick, qstat_pv_latency_wake, + qstat_pv_lock_slowpath, qstat_pv_lock_stealing, qstat_pv_spurious_wakeup, qstat_pv_wait_again, @@ -70,6 +72,7 @@ static const char * const qstat_names[qstat_num + 1] = { [qstat_pv_spurious_wakeup] = "pv_spurious_wakeup", [qstat_pv_latency_kick] = "pv_latency_kick", [qstat_pv_latency_wake] = "pv_latency_wake", + [qstat_pv_lock_slowpath] = "pv_lock_slowpath", [qstat_pv_lock_stealing] = "pv_lock_stealing", [qstat_pv_wait_again] = "pv_wait_again", [qstat_pv_wait_early] = "pv_wait_early", @@ -279,19 +282,6 @@ static inline void __pv_wait(u8 *ptr, u8 val) #define pv_kick(c) __pv_kick(c) #define pv_wait(p, v) __pv_wait(p, v) -/* - * PV unfair trylock count tracking function - */ -static inline int qstat_spin_steal_lock(struct qspinlock *lock) -{ - int ret = pv_queued_spin_steal_lock(lock); - - qstat_inc(qstat_pv_lock_stealing, ret); - return ret; -} -#undef queued_spin_trylock -#define queued_spin_trylock(l) qstat_spin_steal_lock(l) - #else /* CONFIG_QUEUED_LOCK_STAT */ static inline void qstat_inc(enum qlock_stats stat, bool cond) { } diff --git a/kernel/memremap.c b/kernel/memremap.c index b981a7b023f04..fb9b88787ebc2 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -29,10 +29,10 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) static void *try_ram_remap(resource_size_t offset, size_t size) { - struct page *page = pfn_to_page(offset >> PAGE_SHIFT); + unsigned long pfn = PHYS_PFN(offset); /* In the simple case just return the existing linear address */ - if (!PageHighMem(page)) + if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn))) return __va(offset); return NULL; /* fallback to ioremap_cache */ } @@ -47,7 +47,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * being mapped does not have i/o side effects and the __iomem * annotation is not applicable. * - * MEMREMAP_WB - matches the default mapping for "System RAM" on + * MEMREMAP_WB - matches the default mapping for System RAM on * the architecture. This is usually a read-allocate write-back cache. * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM * memremap() will bypass establishing a new mapping and instead return @@ -56,11 +56,12 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * MEMREMAP_WT - establish a mapping whereby writes either bypass the * cache or are written through to memory and never exist in a * cache-dirty state with respect to program visibility. Attempts to - * map "System RAM" with this mapping type will fail. + * map System RAM with this mapping type will fail. */ void *memremap(resource_size_t offset, size_t size, unsigned long flags) { - int is_ram = region_intersects(offset, size, "System RAM"); + int is_ram = region_intersects(offset, size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); void *addr = NULL; if (is_ram == REGION_MIXED) { @@ -76,7 +77,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * MEMREMAP_WB is special in that it can be satisifed * from the direct map. Some archs depend on the * capability of memremap() to autodetect cases where - * the requested range is potentially in "System RAM" + * the requested range is potentially in System RAM. */ if (is_ram == REGION_INTERSECTS) addr = try_ram_remap(offset, size); @@ -88,7 +89,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * If we don't have a mapping yet and more request flags are * pending then we will be attempting to establish a new virtual * address mapping. Enforce that this mapping is not aliasing - * "System RAM" + * System RAM. */ if (!addr && is_ram == REGION_INTERSECTS && flags) { WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", @@ -270,13 +271,17 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { - int is_ram = region_intersects(res->start, resource_size(res), - "System RAM"); resource_size_t key, align_start, align_size, align_end; struct dev_pagemap *pgmap; struct page_map *page_map; + int error, nid, is_ram; unsigned long pfn; - int error, nid; + + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) + - align_start; + is_ram = region_intersects(align_start, align_size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); if (is_ram == REGION_MIXED) { WARN_ONCE(1, "%s attempted on mixed region %pr\n", @@ -314,8 +319,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, mutex_lock(&pgmap_lock); error = 0; - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); align_end = align_start + align_size - 1; for (key = align_start; key <= align_end; key += SECTION_SIZE) { struct dev_pagemap *dup; @@ -351,8 +354,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, for_each_device_pfn(pfn, page_map) { struct page *page = pfn_to_page(pfn); - /* ZONE_DEVICE pages must never appear on a slab lru */ - list_force_poison(&page->lru); + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back + * pointer. It is a bug if a ZONE_DEVICE page is ever + * freed or placed on a driver-private list. Seed the + * storage with LIST_POISON* values. + */ + list_del(&page->lru); page->pgmap = pgmap; } devres_add(dev, page_map); diff --git a/kernel/profile.c b/kernel/profile.c index 99513e1160e51..51369697466e3 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -59,6 +59,7 @@ int profile_setup(char *str) if (!strncmp(str, sleepstr, strlen(sleepstr))) { #ifdef CONFIG_SCHEDSTATS + force_schedstat_enabled(); prof_on = SLEEP_PROFILING; if (str[strlen(sleepstr)] == ',') str += strlen(sleepstr) + 1; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index d2988d047d668..65ae0e5c35da1 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -932,12 +932,14 @@ rcu_torture_writer(void *arg) int nsynctypes = 0; VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); - pr_alert("%s" TORTURE_FLAG - " Grace periods expedited from boot/sysfs for %s,\n", - torture_type, cur_ops->name); - pr_alert("%s" TORTURE_FLAG - " Testing of dynamic grace-period expediting diabled.\n", - torture_type); + if (!can_expedite) { + pr_alert("%s" TORTURE_FLAG + " Grace periods expedited from boot/sysfs for %s,\n", + torture_type, cur_ops->name); + pr_alert("%s" TORTURE_FLAG + " Disabled dynamic grace-period expediting.\n", + torture_type); + } /* Initialize synctype[] array. If none set, take default. */ if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync1) diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index e492a5253e0f1..196f0302e2f43 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -23,7 +23,7 @@ */ #include -#include +#include #include #include @@ -122,18 +122,7 @@ static int __init rcutiny_trace_init(void) debugfs_remove_recursive(rcudir); return 1; } - -static void __exit rcutiny_trace_cleanup(void) -{ - debugfs_remove_recursive(rcudir); -} - -module_init(rcutiny_trace_init); -module_exit(rcutiny_trace_cleanup); - -MODULE_AUTHOR("Paul E. McKenney"); -MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation"); -MODULE_LICENSE("GPL"); +device_initcall(rcutiny_trace_init); static void check_cpu_stall(struct rcu_ctrlblk *rcp) { diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e41dd4131f7a1..9a535a86e7326 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -108,7 +108,6 @@ RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); static struct rcu_state *const rcu_state_p; -static struct rcu_data __percpu *const rcu_data_p; LIST_HEAD(rcu_struct_flavors); /* Dump rcu_node combining tree at boot to verify correct setup. */ @@ -1083,13 +1082,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, rcu_sysidle_check_cpu(rdp, isidle, maxj); if ((rdp->dynticks_snap & 0x1) == 0) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); - return 1; - } else { if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rdp->mynode->gpnum)) WRITE_ONCE(rdp->gpwrap, true); - return 0; + return 1; } + return 0; } /* @@ -1173,15 +1171,16 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, smp_mb(); /* ->cond_resched_completed before *rcrmp. */ WRITE_ONCE(*rcrmp, READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask); - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ - rdp->rsp->jiffies_resched += 5; /* Enable beating. */ - } else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { - /* Time to beat on that CPU again! */ - resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ - rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ } + rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ } + /* And if it has been a really long time, kick the CPU as well. */ + if (ULONG_CMP_GE(jiffies, + rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) || + ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs)) + resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ + return 0; } @@ -1246,7 +1245,7 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) if (rnp->qsmask & (1UL << cpu)) dump_cpu_task(rnp->grplo + cpu); } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1266,12 +1265,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) raw_spin_lock_irqsave_rcu_node(rnp, flags); delta = jiffies - READ_ONCE(rsp->jiffies_stall); if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* * OK, time to rat on our buddy... @@ -1292,7 +1291,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) ndetected++; } } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } print_cpu_stall_info_end(); @@ -1357,7 +1356,7 @@ static void print_cpu_stall(struct rcu_state *rsp) if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* * Attempt to revive the RCU machinery by forcing a context switch. @@ -1595,7 +1594,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, } unlock_out: if (rnp != rnp_root) - raw_spin_unlock(&rnp_root->lock); + raw_spin_unlock_rcu_node(rnp_root); out: if (c_out != NULL) *c_out = c; @@ -1614,7 +1613,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) int needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - rcu_nocb_gp_cleanup(rsp, rnp); rnp->need_future_gp[c & 0x1] = 0; needmore = rnp->need_future_gp[(c + 1) & 0x1]; trace_rcu_future_gp(rnp, rdp, c, @@ -1635,7 +1633,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - wake_up(&rsp->gp_wq); + swake_up(&rsp->gp_wq); } /* @@ -1815,7 +1813,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) return; } needwake = __note_gp_changes(rsp, rnp, rdp); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) rcu_gp_kthread_wake(rsp); } @@ -1840,7 +1838,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) raw_spin_lock_irq_rcu_node(rnp); if (!READ_ONCE(rsp->gp_flags)) { /* Spurious wakeup, tell caller to go back to sleep. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); return false; } WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */ @@ -1850,7 +1848,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) * Grace period already in progress, don't start another. * Not supposed to be able to happen. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); return false; } @@ -1859,7 +1857,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* Record GP times before starting GP, hence smp_store_release(). */ smp_store_release(&rsp->gpnum, rsp->gpnum + 1); trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); /* * Apply per-leaf buffered online and offline operations to the @@ -1873,7 +1871,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); continue; } @@ -1907,7 +1905,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) rcu_cleanup_dead_rnp(rnp); } - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); } /* @@ -1938,7 +1936,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) trace_rcu_grace_period_init(rsp->name, rnp->gpnum, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); cond_resched_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); } @@ -1996,7 +1994,7 @@ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) raw_spin_lock_irq_rcu_node(rnp); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS); - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); } } @@ -2010,6 +2008,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) int nocb = 0; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); + struct swait_queue_head *sq; WRITE_ONCE(rsp->gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); @@ -2025,7 +2024,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) * safe for us to drop the lock in order to mark the grace * period as completed in all of the rcu_node structures. */ - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); /* * Propagate new ->completed value to rcu_node structures so @@ -2046,7 +2045,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); - raw_spin_unlock_irq(&rnp->lock); + sq = rcu_nocb_gp_get(rnp); + raw_spin_unlock_irq_rcu_node(rnp); + rcu_nocb_gp_cleanup(sq); cond_resched_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); rcu_gp_slow(rsp, gp_cleanup_delay); @@ -2068,7 +2069,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) READ_ONCE(rsp->gpnum), TPS("newreq")); } - raw_spin_unlock_irq(&rnp->lock); + raw_spin_unlock_irq_rcu_node(rnp); } /* @@ -2092,7 +2093,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - wait_event_interruptible(rsp->gp_wq, + swait_event_interruptible(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; @@ -2122,7 +2123,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = wait_event_interruptible_timeout(rsp->gp_wq, + ret = swait_event_interruptible_timeout(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ @@ -2234,19 +2235,21 @@ static bool rcu_start_gp(struct rcu_state *rsp) } /* - * Report a full set of quiescent states to the specified rcu_state - * data structure. This involves cleaning up after the prior grace - * period and letting rcu_start_gp() start up the next grace period - * if one is needed. Note that the caller must hold rnp->lock, which - * is released before return. + * Report a full set of quiescent states to the specified rcu_state data + * structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period + * kthread if another grace period is required. Whether we wake + * the grace-period kthread or it awakens itself for the next round + * of quiescent-state forcing, that kthread will clean up after the + * just-completed grace period. Note that the caller must hold rnp->lock, + * which is released before return. */ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - rcu_gp_kthread_wake(rsp); + raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ } /* @@ -2275,7 +2278,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * Our bit has already been cleared, or the * relevant grace period is already over, so done. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ @@ -2287,7 +2290,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { /* Other bits still set at this level, so done. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } mask = rnp->grpmask; @@ -2297,7 +2300,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, break; } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); rnp_c = rnp; rnp = rnp->parent; raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -2329,7 +2332,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; /* Still need more quiescent states! */ } @@ -2346,19 +2349,14 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, /* Report up the rest of the hierarchy, tracking current ->gpnum. */ gps = rnp->gpnum; mask = rnp->grpmask; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags); } /* * Record a quiescent state for the specified CPU to that CPU's rcu_data - * structure. This must be either called from the specified CPU, or - * called when the specified CPU is known to be offline (and when it is - * also known that no other CPU is concurrently trying to help the offline - * CPU). The lastcomp argument is used to make sure we are still in the - * grace period of interest. We don't want to end the current grace period - * based on quiescent states detected in an earlier grace period! + * structure. This must be called from the specified CPU. */ static void rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) @@ -2383,14 +2381,14 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) */ rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } mask = rdp->grpmask; if ((rnp->qsmask & mask) == 0) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } else { - rdp->core_needs_qs = 0; + rdp->core_needs_qs = false; /* * This GP can't end until cpu checks in, so all of our @@ -2599,35 +2597,14 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) rnp->qsmaskinit &= ~mask; rnp->qsmask &= ~mask; if (rnp->qsmaskinit) { - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); + /* irqs remain disabled. */ return; } - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ } } -/* - * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinit - * bit masks. - */ -static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) -{ - unsigned long flags; - unsigned long mask; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ - - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return; - - /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ - mask = rdp->grpmask; - raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ - rnp->qsmaskinitnext &= ~mask; - raw_spin_unlock_irqrestore(&rnp->lock, flags); -} - /* * The CPU has been completely removed, and some other CPU is reporting * this fact from process context. Do the remainder of the cleanup, @@ -2859,7 +2836,7 @@ static void force_qs_rnp(struct rcu_state *rsp, rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); } else { /* Nothing to do here, so just drop the lock. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } } @@ -2895,12 +2872,12 @@ static void force_quiescent_state(struct rcu_state *rsp) raw_spin_unlock(&rnp_old->fqslock); if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { rsp->n_force_qs_lh++; - raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); return; /* Someone beat us to it. */ } WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - rcu_gp_kthread_wake(rsp); + raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ } /* @@ -2925,7 +2902,7 @@ __rcu_process_callbacks(struct rcu_state *rsp) if (cpu_needs_another_gp(rsp, rdp)) { raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */ needwake = rcu_start_gp(rsp); - raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); if (needwake) rcu_gp_kthread_wake(rsp); } else { @@ -3016,7 +2993,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, raw_spin_lock_rcu_node(rnp_root); needwake = rcu_start_gp(rsp); - raw_spin_unlock(&rnp_root->lock); + raw_spin_unlock_rcu_node(rnp_root); if (needwake) rcu_gp_kthread_wake(rsp); } else { @@ -3436,14 +3413,14 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmaskinit == rnp->expmaskinitnext) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); continue; /* No new CPUs, nothing to do. */ } /* Update this node's mask, track old value for propagation. */ oldmask = rnp->expmaskinit; rnp->expmaskinit = rnp->expmaskinitnext; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* If was already nonzero, nothing to propagate. */ if (oldmask) @@ -3458,7 +3435,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) if (rnp_up->expmaskinit) done = true; rnp_up->expmaskinit |= mask; - raw_spin_unlock_irqrestore(&rnp_up->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp_up, flags); if (done) break; mask = rnp_up->grpmask; @@ -3481,7 +3458,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) raw_spin_lock_irqsave_rcu_node(rnp, flags); WARN_ON_ONCE(rnp->expmask); rnp->expmask = rnp->expmaskinit; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -3522,19 +3499,19 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, if (!rnp->expmask) rcu_initiate_boost(rnp, flags); else - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); break; } if (rnp->parent == NULL) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - wake_up(&rsp->expedited_wq); + swake_up(&rsp->expedited_wq); } break; } mask = rnp->grpmask; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled */ rnp = rnp->parent; raw_spin_lock_rcu_node(rnp); /* irqs already disabled */ WARN_ON_ONCE(!(rnp->expmask & mask)); @@ -3569,7 +3546,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!(rnp->expmask & mask)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } rnp->expmask &= ~mask; @@ -3730,7 +3707,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, */ if (rcu_preempt_has_tasks(rnp)) rnp->exp_tasks = rnp->blkd_tasks.next; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* IPI the remaining CPUs for expedited quiescent state. */ mask = 1; @@ -3747,7 +3724,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, raw_spin_lock_irqsave_rcu_node(rnp, flags); if (cpu_online(cpu) && (rnp->expmask & mask)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); schedule_timeout_uninterruptible(1); if (cpu_online(cpu) && (rnp->expmask & mask)) @@ -3756,7 +3733,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, } if (!(rnp->expmask & mask)) mask_ofl_ipi &= ~mask; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Report quiescent states for those that went offline. */ mask_ofl_test |= mask_ofl_ipi; @@ -3780,7 +3757,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) jiffies_start = jiffies; for (;;) { - ret = wait_event_interruptible_timeout( + ret = swait_event_timeout( rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); @@ -3788,7 +3765,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) return; if (ret < 0) { /* Hit a signal, disable CPU stall warnings. */ - wait_event(rsp->expedited_wq, + swait_event(rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root)); return; } @@ -4163,7 +4140,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) return; raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */ rnp->qsmaskinit |= mask; - raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */ } } @@ -4187,7 +4164,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->rsp = rsp; mutex_init(&rdp->exp_funnel_mutex); rcu_boot_init_nocb_percpu_data(rdp); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* @@ -4215,7 +4192,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rcu_sysidle_init_percpu_data(rdp->dynticks); atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ /* * Add CPU to leaf rcu_node pending-online bitmask. Any needed @@ -4236,7 +4213,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu); rdp->core_needs_qs = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } static void rcu_prepare_cpu(int cpu) @@ -4247,6 +4224,46 @@ static void rcu_prepare_cpu(int cpu) rcu_init_percpu_data(cpu, rsp); } +#ifdef CONFIG_HOTPLUG_CPU +/* + * The CPU is exiting the idle loop into the arch_cpu_idle_dead() + * function. We now remove it from the rcu_node tree's ->qsmaskinit + * bit masks. + * The CPU is exiting the idle loop into the arch_cpu_idle_dead() + * function. We now remove it from the rcu_node tree's ->qsmaskinit + * bit masks. + */ +static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return; + + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ + mask = rdp->grpmask; + raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ + rnp->qsmaskinitnext &= ~mask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +void rcu_report_dead(unsigned int cpu) +{ + struct rcu_state *rsp; + + /* QS for any half-done expedited RCU-sched GP. */ + preempt_disable(); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(rcu_sched_state.rda), true); + preempt_enable(); + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_idle_cpu(cpu, rsp); +} +#endif + /* * Handle CPU online/offline notification events. */ @@ -4278,17 +4295,6 @@ int rcu_cpu_notify(struct notifier_block *self, for_each_rcu_flavor(rsp) rcu_cleanup_dying_cpu(rsp); break; - case CPU_DYING_IDLE: - /* QS for any half-done expedited RCU-sched GP. */ - preempt_disable(); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(rcu_sched_state.rda), true); - preempt_enable(); - - for_each_rcu_flavor(rsp) { - rcu_cleanup_dying_idle_cpu(cpu, rsp); - } - break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: @@ -4358,7 +4364,7 @@ static int __init rcu_spawn_gp_kthread(void) sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); wake_up_process(t); } rcu_spawn_nocb_kthreads(); @@ -4449,8 +4455,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) cpustride *= levelspread[i]; rnp = rsp->level[i]; for (j = 0; j < levelcnt[i]; j++, rnp++) { - raw_spin_lock_init(&rnp->lock); - lockdep_set_class_and_name(&rnp->lock, + raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock)); + lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock), &rcu_node_class[i], buf[i]); raw_spin_lock_init(&rnp->fqslock); lockdep_set_class_and_name(&rnp->fqslock, @@ -4482,8 +4488,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) } } - init_waitqueue_head(&rsp->gp_wq); - init_waitqueue_head(&rsp->expedited_wq); + init_swait_queue_head(&rsp->gp_wq); + init_swait_queue_head(&rsp->expedited_wq); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 83360b4f43527..df668c0f9e649 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -27,6 +27,7 @@ #include #include #include +#include #include /* @@ -149,8 +150,9 @@ struct rcu_dynticks { * Definition for node within the RCU grace-period-detection hierarchy. */ struct rcu_node { - raw_spinlock_t lock; /* Root rcu_node's lock protects some */ - /* rcu_state fields as well as following. */ + raw_spinlock_t __private lock; /* Root rcu_node's lock protects */ + /* some rcu_state fields as well as */ + /* following. */ unsigned long gpnum; /* Current grace period for this node. */ /* This will either be equal to or one */ /* behind the root rcu_node's gpnum. */ @@ -243,7 +245,7 @@ struct rcu_node { /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ #ifdef CONFIG_RCU_NOCB_CPU - wait_queue_head_t nocb_gp_wq[2]; + struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ int need_future_gp[2]; @@ -399,7 +401,7 @@ struct rcu_data { atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ struct rcu_head **nocb_follower_tail; - wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ + struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ @@ -478,7 +480,7 @@ struct rcu_state { unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ - wait_queue_head_t gp_wq; /* Where GP task waits. */ + struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ short gp_state; /* GP kthread sleep state. */ @@ -506,7 +508,7 @@ struct rcu_state { unsigned long expedited_sequence; /* Take a ticket. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ - wait_queue_head_t expedited_wq; /* Wait for check-ins. */ + struct swait_queue_head expedited_wq; /* Wait for check-ins. */ int ncpus_snap; /* # CPUs seen last time. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ @@ -621,7 +623,8 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags); @@ -680,7 +683,7 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) #endif /* #else #ifdef CONFIG_PPC */ /* - * Wrappers for the rcu_node::lock acquire. + * Wrappers for the rcu_node::lock acquire and release. * * Because the rcu_nodes form a tree, the tree traversal locking will observe * different lock values, this in turn means that an UNLOCK of one level @@ -689,29 +692,48 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) * * In order to restore full ordering between tree levels, augment the regular * lock acquire functions with smp_mb__after_unlock_lock(). + * + * As ->lock of struct rcu_node is a __private field, therefore one should use + * these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock. */ static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp) { - raw_spin_lock(&rnp->lock); + raw_spin_lock(&ACCESS_PRIVATE(rnp, lock)); smp_mb__after_unlock_lock(); } +static inline void raw_spin_unlock_rcu_node(struct rcu_node *rnp) +{ + raw_spin_unlock(&ACCESS_PRIVATE(rnp, lock)); +} + static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp) { - raw_spin_lock_irq(&rnp->lock); + raw_spin_lock_irq(&ACCESS_PRIVATE(rnp, lock)); smp_mb__after_unlock_lock(); } -#define raw_spin_lock_irqsave_rcu_node(rnp, flags) \ -do { \ - typecheck(unsigned long, flags); \ - raw_spin_lock_irqsave(&(rnp)->lock, flags); \ - smp_mb__after_unlock_lock(); \ +static inline void raw_spin_unlock_irq_rcu_node(struct rcu_node *rnp) +{ + raw_spin_unlock_irq(&ACCESS_PRIVATE(rnp, lock)); +} + +#define raw_spin_lock_irqsave_rcu_node(rnp, flags) \ +do { \ + typecheck(unsigned long, flags); \ + raw_spin_lock_irqsave(&ACCESS_PRIVATE(rnp, lock), flags); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +#define raw_spin_unlock_irqrestore_rcu_node(rnp, flags) \ +do { \ + typecheck(unsigned long, flags); \ + raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(rnp, lock), flags); \ } while (0) static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp) { - bool locked = raw_spin_trylock(&rnp->lock); + bool locked = raw_spin_trylock(&ACCESS_PRIVATE(rnp, lock)); if (locked) smp_mb__after_unlock_lock(); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 9467a8b7e7561..efdf7b61ce120 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -235,7 +235,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) rnp->gp_tasks = &t->rcu_node_entry; if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; - raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* interrupts remain disabled. */ /* * Report the quiescent state for the expedited GP. This expedited @@ -489,7 +489,7 @@ void rcu_read_unlock_special(struct task_struct *t) !!rnp->gp_tasks); rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags); } else { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Unboost if we were boosted. */ @@ -518,14 +518,14 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!rcu_preempt_blocked_readers_cgp(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } t = list_entry(rnp->gp_tasks->prev, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) sched_show_task(t); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* @@ -807,7 +807,6 @@ void exit_rcu(void) #else /* #ifdef CONFIG_PREEMPT_RCU */ static struct rcu_state *const rcu_state_p = &rcu_sched_state; -static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data; /* * Tell them what RCU they are running. @@ -991,7 +990,7 @@ static int rcu_boost(struct rcu_node *rnp) * might exit their RCU read-side critical sections on their own. */ if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return 0; } @@ -1028,7 +1027,7 @@ static int rcu_boost(struct rcu_node *rnp) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&rnp->boost_mtx, t); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* Lock only for side effect: boosts task t's priority. */ rt_mutex_lock(&rnp->boost_mtx); rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */ @@ -1088,7 +1087,7 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { rnp->n_balk_exp_gp_tasks++; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } if (rnp->exp_tasks != NULL || @@ -1098,13 +1097,13 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) ULONG_CMP_GE(jiffies, rnp->boost_time))) { if (rnp->exp_tasks == NULL) rnp->boost_tasks = rnp->gp_tasks; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); t = rnp->boost_kthread_task; if (t) rcu_wake_cond(t, rnp->boost_kthread_status); } else { rcu_initiate_boost_trace(rnp); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -1172,7 +1171,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, return PTR_ERR(t); raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ @@ -1308,7 +1307,7 @@ static void rcu_prepare_kthreads(int cpu) static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } static void invoke_rcu_callbacks_kthread(void) @@ -1559,7 +1558,7 @@ static void rcu_prepare_for_idle(void) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ if (needwake) rcu_gp_kthread_wake(rsp); } @@ -1811,9 +1810,9 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll); * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended * grace period. */ -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { - wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + swake_up_all(sq); } /* @@ -1829,10 +1828,15 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return &rnp->nocb_gp_wq[rnp->completed & 0x1]; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { - init_waitqueue_head(&rnp->nocb_gp_wq[0]); - init_waitqueue_head(&rnp->nocb_gp_wq[1]); + init_swait_queue_head(&rnp->nocb_gp_wq[0]); + init_swait_queue_head(&rnp->nocb_gp_wq[1]); } #ifndef CONFIG_RCU_NOCB_CPU_ALL @@ -1857,7 +1861,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); - wake_up(&rdp_leader->nocb_wq); + swake_up(&rdp_leader->nocb_wq); } } @@ -2059,7 +2063,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) raw_spin_lock_irqsave_rcu_node(rnp, flags); needwake = rcu_start_future_gp(rnp, rdp, &c); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) rcu_gp_kthread_wake(rdp->rsp); @@ -2069,7 +2073,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - wait_event_interruptible( + swait_event_interruptible( rnp->nocb_gp_wq[c & 0x1], (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); if (likely(d)) @@ -2097,7 +2101,7 @@ static void nocb_leader_wait(struct rcu_data *my_rdp) /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); - wait_event_interruptible(my_rdp->nocb_wq, + swait_event_interruptible(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); /* Memory barrier handled by smp_mb() calls below and repoll. */ } else if (firsttime) { @@ -2172,7 +2176,7 @@ static void nocb_leader_wait(struct rcu_data *my_rdp) * List was empty, wake up the follower. * Memory barriers supplied by atomic_long_add(). */ - wake_up(&rdp->nocb_wq); + swake_up(&rdp->nocb_wq); } } @@ -2193,7 +2197,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) if (!rcu_nocb_poll) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "FollowerSleep"); - wait_event_interruptible(rdp->nocb_wq, + swait_event_interruptible(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); } else if (firsttime) { /* Don't drown trace log with "Poll"! */ @@ -2352,7 +2356,7 @@ void __init rcu_init_nohz(void) static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { rdp->nocb_tail = &rdp->nocb_head; - init_waitqueue_head(&rdp->nocb_wq); + init_swait_queue_head(&rdp->nocb_wq); rdp->nocb_follower_tail = &rdp->nocb_follower_head; } @@ -2502,7 +2506,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) return false; } -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { } @@ -2510,6 +2514,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) { } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return NULL; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { } diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 76b94e19430b2..ca828b41c938b 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -128,6 +128,7 @@ bool rcu_gp_is_normal(void) { return READ_ONCE(rcu_normal); } +EXPORT_SYMBOL_GPL(rcu_gp_is_normal); static atomic_t rcu_expedited_nesting = ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0); diff --git a/kernel/resource.c b/kernel/resource.c index 3669d1bfc4254..4d466052426b3 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -333,13 +333,13 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); /* - * Finds the lowest iomem reosurce exists with-in [res->start.res->end) - * the caller must specify res->start, res->end, res->flags and "name". - * If found, returns 0, res is overwritten, if not found, returns -1. - * This walks through whole tree and not just first level children - * until and unless first_level_children_only is true. + * Finds the lowest iomem resource existing within [res->start.res->end). + * The caller must specify res->start, res->end, res->flags, and optionally + * desc. If found, returns 0, res is overwritten, if not found, returns -1. + * This function walks the whole tree and not just first level children until + * and unless first_level_children_only is true. */ -static int find_next_iomem_res(struct resource *res, char *name, +static int find_next_iomem_res(struct resource *res, unsigned long desc, bool first_level_children_only) { resource_size_t start, end; @@ -358,9 +358,9 @@ static int find_next_iomem_res(struct resource *res, char *name, read_lock(&resource_lock); for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) { - if (p->flags != res->flags) + if ((p->flags & res->flags) != res->flags) continue; - if (name && strcmp(p->name, name)) + if ((desc != IORES_DESC_NONE) && (desc != p->desc)) continue; if (p->start > end) { p = NULL; @@ -385,15 +385,18 @@ static int find_next_iomem_res(struct resource *res, char *name, * Walks through iomem resources and calls func() with matching resource * ranges. This walks through whole tree and not just first level children. * All the memory ranges which overlap start,end and also match flags and - * name are valid candidates. + * desc are valid candidates. * - * @name: name of resource - * @flags: resource flags + * @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check. + * @flags: I/O resource flags * @start: start addr * @end: end addr + * + * NOTE: For a new descriptor search, define a new IORES_DESC in + * and set it in 'desc' of a target resource entry. */ -int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, - void *arg, int (*func)(u64, u64, void *)) +int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, + u64 end, void *arg, int (*func)(u64, u64, void *)) { struct resource res; u64 orig_end; @@ -403,23 +406,27 @@ int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, res.end = end; res.flags = flags; orig_end = res.end; + while ((res.start < res.end) && - (!find_next_iomem_res(&res, name, false))) { + (!find_next_iomem_res(&res, desc, false))) { + ret = (*func)(res.start, res.end, arg); if (ret) break; + res.start = res.end + 1; res.end = orig_end; } + return ret; } /* - * This function calls callback against all memory range of "System RAM" - * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. - * Now, this function is only for "System RAM". This function deals with - * full ranges and not pfn. If resources are not pfn aligned, dealing - * with pfn can truncate ranges. + * This function calls the @func callback against all memory ranges of type + * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. + * Now, this function is only for System RAM, it deals with full ranges and + * not PFNs. If resources are not PFN-aligned, dealing with PFNs can truncate + * ranges. */ int walk_system_ram_res(u64 start, u64 end, void *arg, int (*func)(u64, u64, void *)) @@ -430,10 +437,10 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, res.start = start; res.end = end; - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; orig_end = res.end; while ((res.start < res.end) && - (!find_next_iomem_res(&res, "System RAM", true))) { + (!find_next_iomem_res(&res, IORES_DESC_NONE, true))) { ret = (*func)(res.start, res.end, arg); if (ret) break; @@ -446,9 +453,9 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY) /* - * This function calls callback against all memory range of "System RAM" - * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. - * Now, this function is only for "System RAM". + * This function calls the @func callback against all memory ranges of type + * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. + * It is to be used only for System RAM. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) @@ -460,10 +467,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, res.start = (u64) start_pfn << PAGE_SHIFT; res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; orig_end = res.end; while ((res.start < res.end) && - (find_next_iomem_res(&res, "System RAM", true) >= 0)) { + (find_next_iomem_res(&res, IORES_DESC_NONE, true) >= 0)) { pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; end_pfn = (res.end + 1) >> PAGE_SHIFT; if (end_pfn > pfn) @@ -484,7 +491,7 @@ static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) } /* * This generic page_is_ram() returns true if specified address is - * registered as "System RAM" in iomem_resource list. + * registered as System RAM in iomem_resource list. */ int __weak page_is_ram(unsigned long pfn) { @@ -496,30 +503,34 @@ EXPORT_SYMBOL_GPL(page_is_ram); * region_intersects() - determine intersection of region with known resources * @start: region start address * @size: size of region - * @name: name of resource (in iomem_resource) + * @flags: flags of resource (in iomem_resource) + * @desc: descriptor of resource (in iomem_resource) or IORES_DESC_NONE * * Check if the specified region partially overlaps or fully eclipses a - * resource identified by @name. Return REGION_DISJOINT if the region - * does not overlap @name, return REGION_MIXED if the region overlaps - * @type and another resource, and return REGION_INTERSECTS if the - * region overlaps @type and no other defined resource. Note, that - * REGION_INTERSECTS is also returned in the case when the specified - * region overlaps RAM and undefined memory holes. + * resource identified by @flags and @desc (optional with IORES_DESC_NONE). + * Return REGION_DISJOINT if the region does not overlap @flags/@desc, + * return REGION_MIXED if the region overlaps @flags/@desc and another + * resource, and return REGION_INTERSECTS if the region overlaps @flags/@desc + * and no other defined resource. Note that REGION_INTERSECTS is also + * returned in the case when the specified region overlaps RAM and undefined + * memory holes. * * region_intersect() is used by memory remapping functions to ensure * the user is not remapping RAM and is a vast speed up over walking * through the resource table page by page. */ -int region_intersects(resource_size_t start, size_t size, const char *name) +int region_intersects(resource_size_t start, size_t size, unsigned long flags, + unsigned long desc) { - unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY; resource_size_t end = start + size - 1; int type = 0; int other = 0; struct resource *p; read_lock(&resource_lock); for (p = iomem_resource.child; p ; p = p->sibling) { - bool is_type = strcmp(p->name, name) == 0 && p->flags == flags; + bool is_type = (((p->flags & flags) == flags) && + ((desc == IORES_DESC_NONE) || + (desc == p->desc))); if (start >= p->start && start <= p->end) is_type ? type++ : other++; @@ -538,6 +549,7 @@ int region_intersects(resource_size_t start, size_t size, const char *name) return REGION_DISJOINT; } +EXPORT_SYMBOL_GPL(region_intersects); void __weak arch_remove_reservations(struct resource *avail) { @@ -948,6 +960,7 @@ static void __init __reserve_region_with_split(struct resource *root, res->start = start; res->end = end; res->flags = IORESOURCE_BUSY; + res->desc = IORES_DESC_NONE; while (1) { @@ -982,6 +995,7 @@ static void __init __reserve_region_with_split(struct resource *root, next_res->start = conflict->end + 1; next_res->end = end; next_res->flags = IORESOURCE_BUSY; + next_res->desc = IORES_DESC_NONE; } } else { res->start = conflict->end + 1; @@ -1071,8 +1085,9 @@ struct resource * __request_region(struct resource *parent, res->name = name; res->start = start; res->end = start + n - 1; - res->flags = resource_type(parent); + res->flags = resource_type(parent) | resource_ext_type(parent); res->flags |= IORESOURCE_BUSY | flags; + res->desc = IORES_DESC_NONE; write_lock(&resource_lock); @@ -1238,6 +1253,7 @@ int release_mem_region_adjustable(struct resource *parent, new_res->start = end + 1; new_res->end = res->end; new_res->flags = res->flags; + new_res->desc = res->desc; new_res->parent = res->parent; new_res->sibling = res->sibling; new_res->child = NULL; @@ -1413,6 +1429,7 @@ static int __init reserve_setup(char *str) res->start = io_start; res->end = io_start + io_num - 1; res->flags = IORESOURCE_BUSY; + res->desc = IORES_DESC_NONE; res->child = NULL; if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0) reserved = x+1; diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 67687973ce80d..7d4cba227cbd3 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -13,7 +13,7 @@ endif obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o completion.o idle.o +obj-y += wait.o swait.o completion.o idle.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index bc54e84675da0..fedb967a98419 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -61,6 +61,7 @@ #include #include #include +#include /* * Scheduler clock - returns current time in nanosec units. @@ -89,6 +90,8 @@ static void __set_sched_clock_stable(void) { if (!sched_clock_stable()) static_key_slow_inc(&__sched_clock_stable); + + tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } void set_sched_clock_stable(void) @@ -108,6 +111,8 @@ static void __clear_sched_clock_stable(struct work_struct *work) /* XXX worry about clock continuity */ if (sched_clock_stable()) static_key_slow_dec(&__sched_clock_stable); + + tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); } static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 406182af99ac8..4d872e19244b1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -26,6 +26,7 @@ * Thomas Gleixner, Mike Kravetz */ +#include #include #include #include @@ -66,12 +67,10 @@ #include #include #include -#include #include #include #include #include -#include #include #include @@ -124,138 +123,6 @@ const_debug unsigned int sysctl_sched_features = #undef SCHED_FEAT -#ifdef CONFIG_SCHED_DEBUG -#define SCHED_FEAT(name, enabled) \ - #name , - -static const char * const sched_feat_names[] = { -#include "features.h" -}; - -#undef SCHED_FEAT - -static int sched_feat_show(struct seq_file *m, void *v) -{ - int i; - - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (!(sysctl_sched_features & (1UL << i))) - seq_puts(m, "NO_"); - seq_printf(m, "%s ", sched_feat_names[i]); - } - seq_puts(m, "\n"); - - return 0; -} - -#ifdef HAVE_JUMP_LABEL - -#define jump_label_key__true STATIC_KEY_INIT_TRUE -#define jump_label_key__false STATIC_KEY_INIT_FALSE - -#define SCHED_FEAT(name, enabled) \ - jump_label_key__##enabled , - -struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { -#include "features.h" -}; - -#undef SCHED_FEAT - -static void sched_feat_disable(int i) -{ - static_key_disable(&sched_feat_keys[i]); -} - -static void sched_feat_enable(int i) -{ - static_key_enable(&sched_feat_keys[i]); -} -#else -static void sched_feat_disable(int i) { }; -static void sched_feat_enable(int i) { }; -#endif /* HAVE_JUMP_LABEL */ - -static int sched_feat_set(char *cmp) -{ - int i; - int neg = 0; - - if (strncmp(cmp, "NO_", 3) == 0) { - neg = 1; - cmp += 3; - } - - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (strcmp(cmp, sched_feat_names[i]) == 0) { - if (neg) { - sysctl_sched_features &= ~(1UL << i); - sched_feat_disable(i); - } else { - sysctl_sched_features |= (1UL << i); - sched_feat_enable(i); - } - break; - } - } - - return i; -} - -static ssize_t -sched_feat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - char *cmp; - int i; - struct inode *inode; - - if (cnt > 63) - cnt = 63; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - cmp = strstrip(buf); - - /* Ensure the static_key remains in a consistent state */ - inode = file_inode(filp); - inode_lock(inode); - i = sched_feat_set(cmp); - inode_unlock(inode); - if (i == __SCHED_FEAT_NR) - return -EINVAL; - - *ppos += cnt; - - return cnt; -} - -static int sched_feat_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, sched_feat_show, NULL); -} - -static const struct file_operations sched_feat_fops = { - .open = sched_feat_open, - .write = sched_feat_write, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static __init int sched_init_debug(void) -{ - debugfs_create_file("sched_features", 0644, NULL, NULL, - &sched_feat_fops); - - return 0; -} -late_initcall(sched_init_debug); -#endif /* CONFIG_SCHED_DEBUG */ - /* * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. @@ -453,20 +320,6 @@ static inline void init_hrtick(void) } #endif /* CONFIG_SCHED_HRTICK */ -/* - * cmpxchg based fetch_or, macro so it works for different integer types - */ -#define fetch_or(ptr, val) \ -({ typeof(*(ptr)) __old, __val = *(ptr); \ - for (;;) { \ - __old = cmpxchg((ptr), __val, __val | (val)); \ - if (__old == __val) \ - break; \ - __val = __old; \ - } \ - __old; \ -}) - #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) /* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, @@ -715,31 +568,36 @@ static inline bool got_nohz_idle_kick(void) #endif /* CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL -bool sched_can_stop_tick(void) +bool sched_can_stop_tick(struct rq *rq) { + int fifo_nr_running; + + /* Deadline tasks, even if single, need the tick */ + if (rq->dl.dl_nr_running) + return false; + /* - * FIFO realtime policy runs the highest priority task. Other runnable - * tasks are of a lower priority. The scheduler tick does nothing. + * FIFO realtime policy runs the highest priority task (after DEADLINE). + * Other runnable tasks are of a lower priority. The scheduler tick + * isn't needed. */ - if (current->policy == SCHED_FIFO) + fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running; + if (fifo_nr_running) return true; /* * Round-robin realtime tasks time slice with other tasks at the same - * realtime priority. Is this task the only one at this priority? + * realtime priority. */ - if (current->policy == SCHED_RR) { - struct sched_rt_entity *rt_se = ¤t->rt; - - return list_is_singular(&rt_se->run_list); + if (rq->rt.rr_nr_running) { + if (rq->rt.rr_nr_running == 1) + return true; + else + return false; } - /* - * More than one running task need preemption. - * nr_running update is assumed to be visible - * after IPI is sent from wakers. - */ - if (this_rq()->nr_running > 1) + /* Normal multitasking need periodic preemption checks */ + if (rq->cfs.nr_running > 1) return false; return true; @@ -2093,7 +1951,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) ttwu_queue(p, cpu); stat: - ttwu_stat(p, cpu, wake_flags); + if (schedstat_enabled()) + ttwu_stat(p, cpu, wake_flags); out: raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -2141,7 +2000,8 @@ static void try_to_wake_up_local(struct task_struct *p) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_do_wakeup(rq, p, 0); - ttwu_stat(p, smp_processor_id(), 0); + if (schedstat_enabled()) + ttwu_stat(p, smp_processor_id(), 0); out: raw_spin_unlock(&p->pi_lock); } @@ -2183,7 +2043,6 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_throttled = 0; - dl_se->dl_new = 1; dl_se->dl_yielded = 0; } @@ -2210,6 +2069,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #endif #ifdef CONFIG_SCHEDSTATS + /* Even if schedstat is disabled, there should not be garbage */ memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif @@ -2218,6 +2078,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); + p->rt.timeout = 0; + p->rt.time_slice = sched_rr_timeslice; + p->rt.on_rq = 0; + p->rt.on_list = 0; #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2281,6 +2145,69 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, #endif #endif +DEFINE_STATIC_KEY_FALSE(sched_schedstats); + +#ifdef CONFIG_SCHEDSTATS +static void set_schedstats(bool enabled) +{ + if (enabled) + static_branch_enable(&sched_schedstats); + else + static_branch_disable(&sched_schedstats); +} + +void force_schedstat_enabled(void) +{ + if (!schedstat_enabled()) { + pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n"); + static_branch_enable(&sched_schedstats); + } +} + +static int __init setup_schedstats(char *str) +{ + int ret = 0; + if (!str) + goto out; + + if (!strcmp(str, "enable")) { + set_schedstats(true); + ret = 1; + } else if (!strcmp(str, "disable")) { + set_schedstats(false); + ret = 1; + } +out: + if (!ret) + pr_warn("Unable to parse schedstats=\n"); + + return ret; +} +__setup("schedstats=", setup_schedstats); + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_schedstats(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_schedstats); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_schedstats(state); + return err; +} +#endif +#endif + /* * fork()/clone()-time setup: */ @@ -3010,16 +2937,6 @@ u64 scheduler_tick_max_deferment(void) } #endif -notrace unsigned long get_parent_ip(unsigned long addr) -{ - if (in_lock_functions(addr)) { - addr = CALLER_ADDR2; - if (in_lock_functions(addr)) - addr = CALLER_ADDR3; - } - return addr; -} - #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_PREEMPT_TRACER)) @@ -3041,7 +2958,7 @@ void preempt_count_add(int val) PREEMPT_MASK - 10); #endif if (preempt_count() == val) { - unsigned long ip = get_parent_ip(CALLER_ADDR1); + unsigned long ip = get_lock_parent_ip(); #ifdef CONFIG_DEBUG_PREEMPT current->preempt_disable_ip = ip; #endif @@ -3068,7 +2985,7 @@ void preempt_count_sub(int val) #endif if (preempt_count() == val) - trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); __preempt_count_sub(val); } EXPORT_SYMBOL(preempt_count_sub); @@ -3280,7 +3197,6 @@ static void __sched notrace __schedule(bool preempt) trace_sched_switch(preempt, prev, next); rq = context_switch(rq, prev, next); /* unlocks the rq */ - cpu = cpu_of(rq); } else { lockdep_unpin_lock(&rq->lock); raw_spin_unlock_irq(&rq->lock); @@ -3466,7 +3382,7 @@ EXPORT_SYMBOL(default_wake_function); */ void rt_mutex_setprio(struct task_struct *p, int prio) { - int oldprio, queued, running, enqueue_flag = ENQUEUE_RESTORE; + int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE; struct rq *rq; const struct sched_class *prev_class; @@ -3494,11 +3410,15 @@ void rt_mutex_setprio(struct task_struct *p, int prio) trace_sched_pi_setprio(p, prio); oldprio = p->prio; + + if (oldprio == prio) + queue_flag &= ~DEQUEUE_MOVE; + prev_class = p->sched_class; queued = task_on_rq_queued(p); running = task_current(rq, p); if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); + dequeue_task(rq, p, queue_flag); if (running) put_prev_task(rq, p); @@ -3516,7 +3436,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (!dl_prio(p->normal_prio) || (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; - enqueue_flag |= ENQUEUE_REPLENISH; + queue_flag |= ENQUEUE_REPLENISH; } else p->dl.dl_boosted = 0; p->sched_class = &dl_sched_class; @@ -3524,7 +3444,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (dl_prio(oldprio)) p->dl.dl_boosted = 0; if (oldprio < prio) - enqueue_flag |= ENQUEUE_HEAD; + queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) @@ -3539,7 +3459,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); if (queued) - enqueue_task(rq, p, enqueue_flag); + enqueue_task(rq, p, queue_flag); check_class_changed(rq, p, prev_class, oldprio); out_unlock: @@ -3895,6 +3815,7 @@ static int __sched_setscheduler(struct task_struct *p, const struct sched_class *prev_class; struct rq *rq; int reset_on_fork; + int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); @@ -4077,17 +3998,14 @@ static int __sched_setscheduler(struct task_struct *p, * itself. */ new_effective_prio = rt_mutex_get_effective_prio(p, newprio); - if (new_effective_prio == oldprio) { - __setscheduler_params(p, attr); - task_rq_unlock(rq, p, &flags); - return 0; - } + if (new_effective_prio == oldprio) + queue_flags &= ~DEQUEUE_MOVE; } queued = task_on_rq_queued(p); running = task_current(rq, p); if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); + dequeue_task(rq, p, queue_flags); if (running) put_prev_task(rq, p); @@ -4097,15 +4015,14 @@ static int __sched_setscheduler(struct task_struct *p, if (running) p->sched_class->set_curr_task(rq); if (queued) { - int enqueue_flags = ENQUEUE_RESTORE; /* * We enqueue to tail when the priority of a task is * increased (user space view). */ - if (oldprio <= p->prio) - enqueue_flags |= ENQUEUE_HEAD; + if (oldprio < p->prio) + queue_flags |= ENQUEUE_HEAD; - enqueue_task(rq, p, enqueue_flags); + enqueue_task(rq, p, queue_flags); } check_class_changed(rq, p, prev_class, oldprio); @@ -5096,6 +5013,8 @@ void init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); + kasan_unpoison_task_stack(idle); + #ifdef CONFIG_SMP /* * Its possible that init_idle() gets called multiple times on a task, @@ -5405,183 +5324,6 @@ static void migrate_tasks(struct rq *dead_rq) } #endif /* CONFIG_HOTPLUG_CPU */ -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) - -static struct ctl_table sd_ctl_dir[] = { - { - .procname = "sched_domain", - .mode = 0555, - }, - {} -}; - -static struct ctl_table sd_ctl_root[] = { - { - .procname = "kernel", - .mode = 0555, - .child = sd_ctl_dir, - }, - {} -}; - -static struct ctl_table *sd_alloc_ctl_entry(int n) -{ - struct ctl_table *entry = - kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); - - return entry; -} - -static void sd_free_ctl_entry(struct ctl_table **tablep) -{ - struct ctl_table *entry; - - /* - * In the intermediate directories, both the child directory and - * procname are dynamically allocated and could fail but the mode - * will always be set. In the lowest directory the names are - * static strings and all have proc handlers. - */ - for (entry = *tablep; entry->mode; entry++) { - if (entry->child) - sd_free_ctl_entry(&entry->child); - if (entry->proc_handler == NULL) - kfree(entry->procname); - } - - kfree(*tablep); - *tablep = NULL; -} - -static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX-1; - -static void -set_table_entry(struct ctl_table *entry, - const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler, - bool load_idx) -{ - entry->procname = procname; - entry->data = data; - entry->maxlen = maxlen; - entry->mode = mode; - entry->proc_handler = proc_handler; - - if (load_idx) { - entry->extra1 = &min_load_idx; - entry->extra2 = &max_load_idx; - } -} - -static struct ctl_table * -sd_alloc_ctl_domain_table(struct sched_domain *sd) -{ - struct ctl_table *table = sd_alloc_ctl_entry(14); - - if (table == NULL) - return NULL; - - set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[9], "cache_nice_tries", - &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "max_newidle_lb_cost", - &sd->max_newidle_lb_cost, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[12], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[13] is terminator */ - - return table; -} - -static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) -{ - struct ctl_table *entry, *table; - struct sched_domain *sd; - int domain_num = 0, i; - char buf[32]; - - for_each_domain(cpu, sd) - domain_num++; - entry = table = sd_alloc_ctl_entry(domain_num + 1); - if (table == NULL) - return NULL; - - i = 0; - for_each_domain(cpu, sd) { - snprintf(buf, 32, "domain%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_domain_table(sd); - entry++; - i++; - } - return table; -} - -static struct ctl_table_header *sd_sysctl_header; -static void register_sched_domain_sysctl(void) -{ - int i, cpu_num = num_possible_cpus(); - struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); - char buf[32]; - - WARN_ON(sd_ctl_dir[0].child); - sd_ctl_dir[0].child = entry; - - if (entry == NULL) - return; - - for_each_possible_cpu(i) { - snprintf(buf, 32, "cpu%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_cpu_table(i); - entry++; - } - - WARN_ON(sd_sysctl_header); - sd_sysctl_header = register_sysctl_table(sd_ctl_root); -} - -/* may be called multiple times per register */ -static void unregister_sched_domain_sysctl(void) -{ - unregister_sysctl_table(sd_sysctl_header); - sd_sysctl_header = NULL; - if (sd_ctl_dir[0].child) - sd_free_ctl_entry(&sd_ctl_dir[0].child); -} -#else -static void register_sched_domain_sysctl(void) -{ -} -static void unregister_sched_domain_sysctl(void) -{ -} -#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */ - static void set_rq_online(struct rq *rq) { if (!rq->online) { @@ -5693,16 +5435,6 @@ static int sched_cpu_active(struct notifier_block *nfb, set_cpu_rq_start_time(); return NOTIFY_OK; - case CPU_ONLINE: - /* - * At this point a starting CPU has marked itself as online via - * set_cpu_online(). But it might not yet have marked itself - * as active, which is essential from here on. - */ - set_cpu_active(cpu, true); - stop_machine_unpark(cpu); - return NOTIFY_OK; - case CPU_DOWN_FAILED: set_cpu_active(cpu, true); return NOTIFY_OK; @@ -6174,11 +5906,16 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { + int ret; + alloc_bootmem_cpumask_var(&cpu_isolated_map); - cpulist_parse(str, cpu_isolated_map); + ret = cpulist_parse(str, cpu_isolated_map); + if (ret) { + pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); + return 0; + } return 1; } - __setup("isolcpus=", isolated_cpu_setup); struct s_data { @@ -7889,7 +7626,7 @@ void sched_move_task(struct task_struct *tsk) queued = task_on_rq_queued(tsk); if (queued) - dequeue_task(rq, tsk, DEQUEUE_SAVE); + dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE); if (unlikely(running)) put_prev_task(rq, tsk); @@ -7913,7 +7650,7 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->set_curr_task(rq); if (queued) - enqueue_task(rq, tsk, ENQUEUE_RESTORE); + enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE); task_rq_unlock(rq, tsk, &flags); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index b2ab2ffb1adc0..75f98c5498d55 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -262,21 +262,21 @@ static __always_inline bool steal_account_process_tick(void) #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { u64 steal; - cputime_t steal_ct; + unsigned long steal_jiffies; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; /* - * cputime_t may be less precise than nsecs (eg: if it's - * based on jiffies). Lets cast the result to cputime + * steal is in nsecs but our caller is expecting steal + * time in jiffies. Lets cast the result to jiffies * granularity and account the rest on the next rounds. */ - steal_ct = nsecs_to_cputime(steal); - this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + steal_jiffies = nsecs_to_jiffies(steal); + this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies); - account_steal_time(steal_ct); - return steal_ct; + account_steal_time(jiffies_to_cputime(steal_jiffies)); + return steal_jiffies; } #endif return false; @@ -668,26 +668,25 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static unsigned long long vtime_delta(struct task_struct *tsk) +static cputime_t vtime_delta(struct task_struct *tsk) { - unsigned long long clock; + unsigned long now = READ_ONCE(jiffies); - clock = local_clock(); - if (clock < tsk->vtime_snap) + if (time_before(now, (unsigned long)tsk->vtime_snap)) return 0; - return clock - tsk->vtime_snap; + return jiffies_to_cputime(now - tsk->vtime_snap); } static cputime_t get_vtime_delta(struct task_struct *tsk) { - unsigned long long delta = vtime_delta(tsk); + unsigned long now = READ_ONCE(jiffies); + unsigned long delta = now - tsk->vtime_snap; WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); - tsk->vtime_snap += delta; + tsk->vtime_snap = now; - /* CHECKME: always safe to convert nsecs to cputime? */ - return nsecs_to_cputime(delta); + return jiffies_to_cputime(delta); } static void __vtime_account_system(struct task_struct *tsk) @@ -699,6 +698,9 @@ static void __vtime_account_system(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { + if (!vtime_delta(tsk)) + return; + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); write_seqcount_end(&tsk->vtime_seqcount); @@ -707,7 +709,8 @@ void vtime_account_system(struct task_struct *tsk) void vtime_gen_account_irq_exit(struct task_struct *tsk) { write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; write_seqcount_end(&tsk->vtime_seqcount); @@ -718,16 +721,19 @@ void vtime_account_user(struct task_struct *tsk) cputime_t delta_cpu; write_seqcount_begin(&tsk->vtime_seqcount); - delta_cpu = get_vtime_delta(tsk); tsk->vtime_snap_whence = VTIME_SYS; - account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + if (vtime_delta(tsk)) { + delta_cpu = get_vtime_delta(tsk); + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + } write_seqcount_end(&tsk->vtime_seqcount); } void vtime_user_enter(struct task_struct *tsk) { write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); tsk->vtime_snap_whence = VTIME_USER; write_seqcount_end(&tsk->vtime_seqcount); } @@ -742,7 +748,8 @@ void vtime_guest_enter(struct task_struct *tsk) * that can thus safely catch up with a tickless delta. */ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); current->flags |= PF_VCPU; write_seqcount_end(&tsk->vtime_seqcount); } @@ -772,7 +779,7 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqcount_begin(¤t->vtime_seqcount); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock_cpu(smp_processor_id()); + current->vtime_snap = jiffies; write_seqcount_end(¤t->vtime_seqcount); } @@ -783,7 +790,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_save(flags); write_seqcount_begin(&t->vtime_seqcount); t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock_cpu(cpu); + t->vtime_snap = jiffies; write_seqcount_end(&t->vtime_seqcount); local_irq_restore(flags); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 04a569cdd613d..c7a036facbe1d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -352,7 +352,15 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(!dl_se->dl_new || dl_se->dl_throttled); + WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); + + /* + * We are racing with the deadline timer. So, do nothing because + * the deadline timer handler will take care of properly recharging + * the runtime and postponing the deadline + */ + if (dl_se->dl_throttled) + return; /* * We use the regular wall clock time to set deadlines in the @@ -361,7 +369,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, */ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; - dl_se->dl_new = 0; } /* @@ -503,15 +510,6 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - /* - * The arrival of a new instance needs special treatment, i.e., - * the actual scheduling parameters have to be "renewed". - */ - if (dl_se->dl_new) { - setup_new_dl_entity(dl_se, pi_se); - return; - } - if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; @@ -607,16 +605,6 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) goto unlock; } - /* - * This is possible if switched_from_dl() raced against a running - * callback that took the above !dl_task() path and we've since then - * switched back into SCHED_DEADLINE. - * - * There's nothing to do except drop our task reference. - */ - if (dl_se->dl_new) - goto unlock; - /* * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. @@ -925,7 +913,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, * parameters of the task might need updating. Otherwise, * we want a replenishment of its runtime. */ - if (dl_se->dl_new || flags & ENQUEUE_WAKEUP) + if (flags & ENQUEUE_WAKEUP) update_dl_entity(dl_se, pi_se); else if (flags & ENQUEUE_REPLENISH) replenish_dl_entity(dl_se, pi_se); @@ -1726,6 +1714,9 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) */ static void switched_to_dl(struct rq *rq, struct task_struct *p) { + if (dl_time_before(p->dl.deadline, rq_clock(rq))) + setup_new_dl_entity(&p->dl, &p->dl); + if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) @@ -1772,8 +1763,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, */ resched_curr(rq); #endif /* CONFIG_SMP */ - } else - switched_to_dl(rq, p); + } } const struct sched_class dl_sched_class = { diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 641511771ae6a..4fbc3bd5ff606 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "sched.h" @@ -58,6 +59,309 @@ static unsigned long nsec_low(unsigned long long nsec) #define SPLIT_NS(x) nsec_high(x), nsec_low(x) +#define SCHED_FEAT(name, enabled) \ + #name , + +static const char * const sched_feat_names[] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static int sched_feat_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (!(sysctl_sched_features & (1UL << i))) + seq_puts(m, "NO_"); + seq_printf(m, "%s ", sched_feat_names[i]); + } + seq_puts(m, "\n"); + + return 0; +} + +#ifdef HAVE_JUMP_LABEL + +#define jump_label_key__true STATIC_KEY_INIT_TRUE +#define jump_label_key__false STATIC_KEY_INIT_FALSE + +#define SCHED_FEAT(name, enabled) \ + jump_label_key__##enabled , + +struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static void sched_feat_disable(int i) +{ + static_key_disable(&sched_feat_keys[i]); +} + +static void sched_feat_enable(int i) +{ + static_key_enable(&sched_feat_keys[i]); +} +#else +static void sched_feat_disable(int i) { }; +static void sched_feat_enable(int i) { }; +#endif /* HAVE_JUMP_LABEL */ + +static int sched_feat_set(char *cmp) +{ + int i; + int neg = 0; + + if (strncmp(cmp, "NO_", 3) == 0) { + neg = 1; + cmp += 3; + } + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (strcmp(cmp, sched_feat_names[i]) == 0) { + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); + } + break; + } + } + + return i; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp; + int i; + struct inode *inode; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + cmp = strstrip(buf); + + /* Ensure the static_key remains in a consistent state */ + inode = file_inode(filp); + inode_lock(inode); + i = sched_feat_set(cmp); + inode_unlock(inode); + if (i == __SCHED_FEAT_NR) + return -EINVAL; + + *ppos += cnt; + + return cnt; +} + +static int sched_feat_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_feat_show, NULL); +} + +static const struct file_operations sched_feat_fops = { + .open = sched_feat_open, + .write = sched_feat_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static __init int sched_init_debug(void) +{ + debugfs_create_file("sched_features", 0644, NULL, NULL, + &sched_feat_fops); + + return 0; +} +late_initcall(sched_init_debug); + +#ifdef CONFIG_SMP + +#ifdef CONFIG_SYSCTL + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {} +}; + +static struct ctl_table sd_ctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {} +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + umode_t mode, proc_handler *proc_handler, + bool load_idx) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(14); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring, false); + /* &table[13] is terminator */ + + return table; +} + +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_possible_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_possible_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + WARN_ON(sd_sysctl_header); + sd_sysctl_header = register_sysctl_table(sd_ctl_root); +} + +/* may be called multiple times per register */ +void unregister_sched_domain_sysctl(void) +{ + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#endif /* CONFIG_SYSCTL */ +#endif /* CONFIG_SMP */ + #ifdef CONFIG_FAIR_GROUP_SCHED static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) { @@ -75,16 +379,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group PN(se->vruntime); PN(se->sum_exec_runtime); #ifdef CONFIG_SCHEDSTATS - PN(se->statistics.wait_start); - PN(se->statistics.sleep_start); - PN(se->statistics.block_start); - PN(se->statistics.sleep_max); - PN(se->statistics.block_max); - PN(se->statistics.exec_max); - PN(se->statistics.slice_max); - PN(se->statistics.wait_max); - PN(se->statistics.wait_sum); - P(se->statistics.wait_count); + if (schedstat_enabled()) { + PN(se->statistics.wait_start); + PN(se->statistics.sleep_start); + PN(se->statistics.block_start); + PN(se->statistics.sleep_max); + PN(se->statistics.block_max); + PN(se->statistics.exec_max); + PN(se->statistics.slice_max); + PN(se->statistics.wait_max); + PN(se->statistics.wait_sum); + P(se->statistics.wait_count); + } #endif P(se->load.weight); #ifdef CONFIG_SMP @@ -122,10 +428,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) (long long)(p->nvcsw + p->nivcsw), p->prio); #ifdef CONFIG_SCHEDSTATS - SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(p->se.statistics.wait_sum), - SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(p->se.statistics.sum_sleep_runtime)); + if (schedstat_enabled()) { + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", + SPLIT_NS(p->se.statistics.wait_sum), + SPLIT_NS(p->se.sum_exec_runtime), + SPLIT_NS(p->se.statistics.sum_sleep_runtime)); + } #else SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", 0LL, 0L, @@ -258,8 +566,17 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) { + struct dl_bw *dl_bw; + SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); +#ifdef CONFIG_SMP + dl_bw = &cpu_rq(cpu)->rd->dl_bw; +#else + dl_bw = &dl_rq->dl_bw; +#endif + SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw); + SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw); } extern __read_mostly int sched_clock_running; @@ -313,17 +630,18 @@ do { \ #define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); #define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); - P(yld_count); - - P(sched_count); - P(sched_goidle); #ifdef CONFIG_SMP P64(avg_idle); P64(max_idle_balance_cost); #endif - P(ttwu_count); - P(ttwu_local); + if (schedstat_enabled()) { + P(yld_count); + P(sched_count); + P(sched_goidle); + P(ttwu_count); + P(ttwu_local); + } #undef P #undef P64 @@ -569,38 +887,39 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) nr_switches = p->nvcsw + p->nivcsw; #ifdef CONFIG_SCHEDSTATS - PN(se.statistics.sum_sleep_runtime); - PN(se.statistics.wait_start); - PN(se.statistics.sleep_start); - PN(se.statistics.block_start); - PN(se.statistics.sleep_max); - PN(se.statistics.block_max); - PN(se.statistics.exec_max); - PN(se.statistics.slice_max); - PN(se.statistics.wait_max); - PN(se.statistics.wait_sum); - P(se.statistics.wait_count); - PN(se.statistics.iowait_sum); - P(se.statistics.iowait_count); P(se.nr_migrations); - P(se.statistics.nr_migrations_cold); - P(se.statistics.nr_failed_migrations_affine); - P(se.statistics.nr_failed_migrations_running); - P(se.statistics.nr_failed_migrations_hot); - P(se.statistics.nr_forced_migrations); - P(se.statistics.nr_wakeups); - P(se.statistics.nr_wakeups_sync); - P(se.statistics.nr_wakeups_migrate); - P(se.statistics.nr_wakeups_local); - P(se.statistics.nr_wakeups_remote); - P(se.statistics.nr_wakeups_affine); - P(se.statistics.nr_wakeups_affine_attempts); - P(se.statistics.nr_wakeups_passive); - P(se.statistics.nr_wakeups_idle); - { + if (schedstat_enabled()) { u64 avg_atom, avg_per_cpu; + PN(se.statistics.sum_sleep_runtime); + PN(se.statistics.wait_start); + PN(se.statistics.sleep_start); + PN(se.statistics.block_start); + PN(se.statistics.sleep_max); + PN(se.statistics.block_max); + PN(se.statistics.exec_max); + PN(se.statistics.slice_max); + PN(se.statistics.wait_max); + PN(se.statistics.wait_sum); + P(se.statistics.wait_count); + PN(se.statistics.iowait_sum); + P(se.statistics.iowait_count); + P(se.statistics.nr_migrations_cold); + P(se.statistics.nr_failed_migrations_affine); + P(se.statistics.nr_failed_migrations_running); + P(se.statistics.nr_failed_migrations_hot); + P(se.statistics.nr_forced_migrations); + P(se.statistics.nr_wakeups); + P(se.statistics.nr_wakeups_sync); + P(se.statistics.nr_wakeups_migrate); + P(se.statistics.nr_wakeups_local); + P(se.statistics.nr_wakeups_remote); + P(se.statistics.nr_wakeups_affine); + P(se.statistics.nr_wakeups_affine_attempts); + P(se.statistics.nr_wakeups_passive); + P(se.statistics.nr_wakeups_idle); + avg_atom = p->se.sum_exec_runtime; if (nr_switches) avg_atom = div64_ul(avg_atom, nr_switches); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cce3303296242..33130529e9b56 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -20,8 +20,8 @@ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ -#include #include +#include #include #include #include @@ -755,7 +755,9 @@ static void update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) { struct task_struct *p; - u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; + u64 delta; + + delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; if (entity_is_task(se)) { p = task_of(se); @@ -776,22 +778,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) se->statistics.wait_sum += delta; se->statistics.wait_start = 0; } -#else -static inline void -update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} - -static inline void -update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} -#endif /* * Task is being enqueued - update stats: */ -static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +static inline void +update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { /* * Are we enqueueing a waiting task? (for current tasks @@ -802,7 +794,7 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) } static inline void -update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { /* * Mark the end of the wait period if dequeueing a @@ -810,7 +802,40 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) */ if (se != cfs_rq->curr) update_stats_wait_end(cfs_rq, se); + + if (flags & DEQUEUE_SLEEP) { + if (entity_is_task(se)) { + struct task_struct *tsk = task_of(se); + + if (tsk->state & TASK_INTERRUPTIBLE) + se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); + if (tsk->state & TASK_UNINTERRUPTIBLE) + se->statistics.block_start = rq_clock(rq_of(cfs_rq)); + } + } + +} +#else +static inline void +update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ } +#endif /* * We are picking a new current task - update its stats: @@ -907,10 +932,11 @@ struct numa_group { spinlock_t lock; /* nr_tasks, tasks */ int nr_tasks; pid_t gid; + int active_nodes; struct rcu_head rcu; - nodemask_t active_nodes; unsigned long total_faults; + unsigned long max_faults_cpu; /* * Faults_cpu is used to decide whether memory should move * towards the CPU. As a consequence, these stats are weighted @@ -969,6 +995,18 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; } +/* + * A node triggering more than 1/3 as many NUMA faults as the maximum is + * considered part of a numa group's pseudo-interleaving set. Migrations + * between these nodes are slowed down, to allow things to settle down. + */ +#define ACTIVE_NODE_FRACTION 3 + +static bool numa_is_active_node(int nid, struct numa_group *ng) +{ + return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu; +} + /* Handle placement on systems where not all nodes are directly connected. */ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, int maxdist, bool task) @@ -1118,27 +1156,23 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, return true; /* - * Do not migrate if the destination is not a node that - * is actively used by this numa group. + * Destination node is much more heavily used than the source + * node? Allow migration. */ - if (!node_isset(dst_nid, ng->active_nodes)) - return false; - - /* - * Source is a node that is not actively used by this - * numa group, while the destination is. Migrate. - */ - if (!node_isset(src_nid, ng->active_nodes)) + if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) * + ACTIVE_NODE_FRACTION) return true; /* - * Both source and destination are nodes in active - * use by this numa group. Maximize memory bandwidth - * by migrating from more heavily used groups, to less - * heavily used ones, spreading the load around. - * Use a 1/4 hysteresis to avoid spurious page movement. + * Distribute memory according to CPU & memory use on each node, + * with 3/4 hysteresis to avoid unnecessary memory migrations: + * + * faults_cpu(dst) 3 faults_cpu(src) + * --------------- * - > --------------- + * faults_mem(dst) 4 faults_mem(src) */ - return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4); + return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 > + group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4; } static unsigned long weighted_cpuload(const int cpu); @@ -1484,7 +1518,7 @@ static int task_numa_migrate(struct task_struct *p) .best_task = NULL, .best_imp = 0, - .best_cpu = -1 + .best_cpu = -1, }; struct sched_domain *sd; unsigned long taskweight, groupweight; @@ -1536,8 +1570,7 @@ static int task_numa_migrate(struct task_struct *p) * multiple NUMA nodes; in order to better consolidate the group, * we need to check other locations. */ - if (env.best_cpu == -1 || (p->numa_group && - nodes_weight(p->numa_group->active_nodes) > 1)) { + if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) { for_each_online_node(nid) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1572,12 +1605,14 @@ static int task_numa_migrate(struct task_struct *p) * trying for a better one later. Do not set the preferred node here. */ if (p->numa_group) { + struct numa_group *ng = p->numa_group; + if (env.best_cpu == -1) nid = env.src_nid; else nid = env.dst_nid; - if (node_isset(nid, p->numa_group->active_nodes)) + if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng)) sched_setnuma(p, env.dst_nid); } @@ -1627,20 +1662,15 @@ static void numa_migrate_preferred(struct task_struct *p) } /* - * Find the nodes on which the workload is actively running. We do this by + * Find out how many nodes on the workload is actively running on. Do this by * tracking the nodes from which NUMA hinting faults are triggered. This can * be different from the set of nodes where the workload's memory is currently * located. - * - * The bitmask is used to make smarter decisions on when to do NUMA page - * migrations, To prevent flip-flopping, and excessive page migrations, nodes - * are added when they cause over 6/16 of the maximum number of faults, but - * only removed when they drop below 3/16. */ -static void update_numa_active_node_mask(struct numa_group *numa_group) +static void numa_group_count_active_nodes(struct numa_group *numa_group) { unsigned long faults, max_faults = 0; - int nid; + int nid, active_nodes = 0; for_each_online_node(nid) { faults = group_faults_cpu(numa_group, nid); @@ -1650,12 +1680,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group) for_each_online_node(nid) { faults = group_faults_cpu(numa_group, nid); - if (!node_isset(nid, numa_group->active_nodes)) { - if (faults > max_faults * 6 / 16) - node_set(nid, numa_group->active_nodes); - } else if (faults < max_faults * 3 / 16) - node_clear(nid, numa_group->active_nodes); + if (faults * ACTIVE_NODE_FRACTION > max_faults) + active_nodes++; } + + numa_group->max_faults_cpu = max_faults; + numa_group->active_nodes = active_nodes; } /* @@ -1946,7 +1976,7 @@ static void task_numa_placement(struct task_struct *p) update_task_scan_period(p, fault_types[0], fault_types[1]); if (p->numa_group) { - update_numa_active_node_mask(p->numa_group); + numa_group_count_active_nodes(p->numa_group); spin_unlock_irq(group_lock); max_nid = preferred_group_nid(p, max_group_nid); } @@ -1990,14 +2020,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, return; atomic_set(&grp->refcount, 1); + grp->active_nodes = 1; + grp->max_faults_cpu = 0; spin_lock_init(&grp->lock); grp->gid = p->pid; /* Second half of the array tracks nids where faults happen */ grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * nr_node_ids; - node_set(task_node(current), grp->active_nodes); - for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) grp->faults[i] = p->numa_faults[i]; @@ -2111,6 +2141,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) bool migrated = flags & TNF_MIGRATED; int cpu_node = task_node(current); int local = !!(flags & TNF_FAULT_LOCAL); + struct numa_group *ng; int priv; if (!static_branch_likely(&sched_numa_balancing)) @@ -2151,9 +2182,10 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) * actively using should be counted as local. This allows the * scan rate to slow down when a workload has settled down. */ - if (!priv && !local && p->numa_group && - node_isset(cpu_node, p->numa_group->active_nodes) && - node_isset(mem_node, p->numa_group->active_nodes)) + ng = p->numa_group; + if (!priv && !local && ng && ng->active_nodes > 1 && + numa_is_active_node(cpu_node, ng) && + numa_is_active_node(mem_node, ng)) local = 1; task_numa_placement(p); @@ -3102,6 +3134,26 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) static void check_enqueue_throttle(struct cfs_rq *cfs_rq); +static inline void check_schedstat_required(void) +{ +#ifdef CONFIG_SCHEDSTATS + if (schedstat_enabled()) + return; + + /* Force schedstat enabled if a dependent tracepoint is active */ + if (trace_sched_stat_wait_enabled() || + trace_sched_stat_sleep_enabled() || + trace_sched_stat_iowait_enabled() || + trace_sched_stat_blocked_enabled() || + trace_sched_stat_runtime_enabled()) { + pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, " + "stat_blocked and stat_runtime require the " + "kernel parameter schedstats=enabled or " + "kernel.sched_schedstats=1\n"); + } +#endif +} + static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { @@ -3122,11 +3174,15 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (flags & ENQUEUE_WAKEUP) { place_entity(cfs_rq, se, 0); - enqueue_sleeper(cfs_rq, se); + if (schedstat_enabled()) + enqueue_sleeper(cfs_rq, se); } - update_stats_enqueue(cfs_rq, se); - check_spread(cfs_rq, se); + check_schedstat_required(); + if (schedstat_enabled()) { + update_stats_enqueue(cfs_rq, se); + check_spread(cfs_rq, se); + } if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; @@ -3193,19 +3249,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_curr(cfs_rq); dequeue_entity_load_avg(cfs_rq, se); - update_stats_dequeue(cfs_rq, se); - if (flags & DEQUEUE_SLEEP) { -#ifdef CONFIG_SCHEDSTATS - if (entity_is_task(se)) { - struct task_struct *tsk = task_of(se); - - if (tsk->state & TASK_INTERRUPTIBLE) - se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); - if (tsk->state & TASK_UNINTERRUPTIBLE) - se->statistics.block_start = rq_clock(rq_of(cfs_rq)); - } -#endif - } + if (schedstat_enabled()) + update_stats_dequeue(cfs_rq, se, flags); clear_buddies(cfs_rq, se); @@ -3279,7 +3324,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * a CPU. So account for the time it spent waiting on the * runqueue. */ - update_stats_wait_end(cfs_rq, se); + if (schedstat_enabled()) + update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); update_load_avg(se, 1); } @@ -3292,7 +3338,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * least twice that of our own weight (i.e. dont track it * when there are only lesser-weight tasks around): */ - if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { + if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { se->statistics.slice_max = max(se->statistics.slice_max, se->sum_exec_runtime - se->prev_sum_exec_runtime); } @@ -3375,9 +3421,13 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) /* throttle cfs_rqs exceeding runtime */ check_cfs_rq_runtime(cfs_rq); - check_spread(cfs_rq, prev); + if (schedstat_enabled()) { + check_spread(cfs_rq, prev); + if (prev->on_rq) + update_stats_wait_start(cfs_rq, prev); + } + if (prev->on_rq) { - update_stats_wait_start(cfs_rq, prev); /* Put 'current' back into the tree. */ __enqueue_entity(cfs_rq, prev); /* in !on_rq case, update occurred at dequeue */ @@ -4459,9 +4509,17 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, /* scale is effectively 1 << i now, and >> i divides by scale */ - old_load = this_rq->cpu_load[i] - tickless_load; + old_load = this_rq->cpu_load[i]; old_load = decay_load_missed(old_load, pending_updates - 1, i); - old_load += tickless_load; + if (tickless_load) { + old_load -= decay_load_missed(tickless_load, pending_updates - 1, i); + /* + * old_load can never be a negative value because a + * decayed tickless_load cannot be greater than the + * original tickless_load. + */ + old_load += tickless_load; + } new_load = this_load; /* * Round up the averaging division if load is increasing. This @@ -4484,6 +4542,25 @@ static unsigned long weighted_cpuload(const int cpu) } #ifdef CONFIG_NO_HZ_COMMON +static void __update_cpu_load_nohz(struct rq *this_rq, + unsigned long curr_jiffies, + unsigned long load, + int active) +{ + unsigned long pending_updates; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + if (pending_updates) { + this_rq->last_load_update_tick = curr_jiffies; + /* + * In the regular NOHZ case, we were idle, this means load 0. + * In the NOHZ_FULL case, we were non-idle, we should consider + * its weighted load. + */ + __update_cpu_load(this_rq, load, pending_updates, active); + } +} + /* * There is no sane way to deal with nohz on smp when using jiffies because the * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading @@ -4501,22 +4578,15 @@ static unsigned long weighted_cpuload(const int cpu) * Called from nohz_idle_balance() to update the load ratings before doing the * idle balance. */ -static void update_idle_cpu_load(struct rq *this_rq) +static void update_cpu_load_idle(struct rq *this_rq) { - unsigned long curr_jiffies = READ_ONCE(jiffies); - unsigned long load = weighted_cpuload(cpu_of(this_rq)); - unsigned long pending_updates; - /* * bail if there's load or we're actually up-to-date. */ - if (load || curr_jiffies == this_rq->last_load_update_tick) + if (weighted_cpuload(cpu_of(this_rq))) return; - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - this_rq->last_load_update_tick = curr_jiffies; - - __update_cpu_load(this_rq, load, pending_updates, 0); + __update_cpu_load_nohz(this_rq, READ_ONCE(jiffies), 0, 0); } /* @@ -4527,22 +4597,12 @@ void update_cpu_load_nohz(int active) struct rq *this_rq = this_rq(); unsigned long curr_jiffies = READ_ONCE(jiffies); unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0; - unsigned long pending_updates; if (curr_jiffies == this_rq->last_load_update_tick) return; raw_spin_lock(&this_rq->lock); - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - if (pending_updates) { - this_rq->last_load_update_tick = curr_jiffies; - /* - * In the regular NOHZ case, we were idle, this means load 0. - * In the NOHZ_FULL case, we were non-idle, we should consider - * its weighted load. - */ - __update_cpu_load(this_rq, load, pending_updates, active); - } + __update_cpu_load_nohz(this_rq, curr_jiffies, load, active); raw_spin_unlock(&this_rq->lock); } #endif /* CONFIG_NO_HZ */ @@ -4554,7 +4614,7 @@ void update_cpu_load_active(struct rq *this_rq) { unsigned long load = weighted_cpuload(cpu_of(this_rq)); /* - * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). + * See the mess around update_cpu_load_idle() / update_cpu_load_nohz(). */ this_rq->last_load_update_tick = jiffies; __update_cpu_load(this_rq, load, 1, 1); @@ -7848,7 +7908,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) if (time_after_eq(jiffies, rq->next_balance)) { raw_spin_lock_irq(&rq->lock); update_rq_clock(rq); - update_idle_cpu_load(rq); + update_cpu_load_idle(rq); raw_spin_unlock_irq(&rq->lock); rebalance_domains(rq, CPU_IDLE); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 544a7133cbd1d..bd12c6c714ece 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -193,8 +194,6 @@ static void cpuidle_idle_call(void) rcu_idle_exit(); } -DEFINE_PER_CPU(bool, cpu_dead_idle); - /* * Generic idle loop implementation * @@ -221,10 +220,7 @@ static void cpu_idle_loop(void) rmb(); if (cpu_is_offline(smp_processor_id())) { - rcu_cpu_notify(NULL, CPU_DYING_IDLE, - (void *)(long)smp_processor_id()); - smp_mb(); /* all activity before dead. */ - this_cpu_write(cpu_dead_idle, true); + cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } @@ -291,5 +287,6 @@ void cpu_startup_entry(enum cpuhp_state state) boot_init_stack_canary(); #endif arch_cpu_idle_prepare(); + cpuhp_online_idle(state); cpu_idle_loop(); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8ec86abe0ea18..5624713294879 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -58,7 +58,15 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_lock(&rt_b->rt_runtime_lock); if (!rt_b->rt_period_active) { rt_b->rt_period_active = 1; - hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period); + /* + * SCHED_DEADLINE updates the bandwidth, as a run away + * RT task with a DL task could hog a CPU. But DL does + * not reset the period. If a deadline task was running + * without an RT task running, it can cause RT tasks to + * throttle when they start up. Kick the timer right away + * to update the period. + */ + hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0)); hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED); } raw_spin_unlock(&rt_b->rt_runtime_lock); @@ -436,7 +444,7 @@ static void dequeue_top_rt_rq(struct rt_rq *rt_rq); static inline int on_rt_rq(struct sched_rt_entity *rt_se) { - return !list_empty(&rt_se->run_list); + return rt_se->on_rq; } #ifdef CONFIG_RT_GROUP_SCHED @@ -482,8 +490,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) return rt_se->my_q; } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head); -static void dequeue_rt_entity(struct sched_rt_entity *rt_se); +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { @@ -499,7 +507,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) if (!rt_se) enqueue_top_rt_rq(rt_rq); else if (!on_rt_rq(rt_se)) - enqueue_rt_entity(rt_se, false); + enqueue_rt_entity(rt_se, 0); if (rt_rq->highest_prio.curr < curr->prio) resched_curr(rq); @@ -516,7 +524,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) if (!rt_se) dequeue_top_rt_rq(rt_rq); else if (on_rt_rq(rt_se)) - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, 0); } static inline int rt_rq_throttled(struct rt_rq *rt_rq) @@ -1141,6 +1149,20 @@ unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) return 1; } +static inline +unsigned int rt_se_rr_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + struct task_struct *tsk; + + if (group_rq) + return group_rq->rr_nr_running; + + tsk = rt_task_of(rt_se); + + return (tsk->policy == SCHED_RR) ? 1 : 0; +} + static inline void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { @@ -1148,6 +1170,7 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) WARN_ON(!rt_prio(prio)); rt_rq->rt_nr_running += rt_se_nr_running(rt_se); + rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se); inc_rt_prio(rt_rq, prio); inc_rt_migration(rt_se, rt_rq); @@ -1160,13 +1183,37 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) WARN_ON(!rt_prio(rt_se_prio(rt_se))); WARN_ON(!rt_rq->rt_nr_running); rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); + rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se); dec_rt_prio(rt_rq, rt_se_prio(rt_se)); dec_rt_migration(rt_se, rt_rq); dec_rt_group(rt_se, rt_rq); } -static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +/* + * Change rt_se->run_list location unless SAVE && !MOVE + * + * assumes ENQUEUE/DEQUEUE flags match + */ +static inline bool move_entity(unsigned int flags) +{ + if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE) + return false; + + return true; +} + +static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_array *array) +{ + list_del_init(&rt_se->run_list); + + if (list_empty(array->queue + rt_se_prio(rt_se))) + __clear_bit(rt_se_prio(rt_se), array->bitmap); + + rt_se->on_list = 0; +} + +static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; @@ -1179,26 +1226,37 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) * get throttled and the current group doesn't have any other * active members. */ - if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) + if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) { + if (rt_se->on_list) + __delist_rt_entity(rt_se, array); return; + } - if (head) - list_add(&rt_se->run_list, queue); - else - list_add_tail(&rt_se->run_list, queue); - __set_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(rt_se->on_list); + if (flags & ENQUEUE_HEAD) + list_add(&rt_se->run_list, queue); + else + list_add_tail(&rt_se->run_list, queue); + + __set_bit(rt_se_prio(rt_se), array->bitmap); + rt_se->on_list = 1; + } + rt_se->on_rq = 1; inc_rt_tasks(rt_se, rt_rq); } -static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; - list_del_init(&rt_se->run_list); - if (list_empty(array->queue + rt_se_prio(rt_se))) - __clear_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(!rt_se->on_list); + __delist_rt_entity(rt_se, array); + } + rt_se->on_rq = 0; dec_rt_tasks(rt_se, rt_rq); } @@ -1207,7 +1265,7 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) * Because the prio of an upper entry depends on the lower * entries, we must remove entries top - down. */ -static void dequeue_rt_stack(struct sched_rt_entity *rt_se) +static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags) { struct sched_rt_entity *back = NULL; @@ -1220,31 +1278,31 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) - __dequeue_rt_entity(rt_se); + __dequeue_rt_entity(rt_se, flags); } } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) - __enqueue_rt_entity(rt_se, head); + __enqueue_rt_entity(rt_se, flags); enqueue_top_rt_rq(&rq->rt); } -static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) { struct rt_rq *rt_rq = group_rt_rq(rt_se); if (rt_rq && rt_rq->rt_nr_running) - __enqueue_rt_entity(rt_se, false); + __enqueue_rt_entity(rt_se, flags); } enqueue_top_rt_rq(&rq->rt); } @@ -1260,7 +1318,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (flags & ENQUEUE_WAKEUP) rt_se->timeout = 0; - enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); + enqueue_rt_entity(rt_se, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); @@ -1271,7 +1329,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, flags); dequeue_pushable_task(rq, p); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4f6598ae4c315..e6d4a3fa3660b 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include @@ -318,7 +319,6 @@ extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, struct sched_entity *se, int cpu, struct sched_entity *parent); extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); -extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b); @@ -450,6 +450,7 @@ static inline int rt_bandwidth_enabled(void) struct rt_rq { struct rt_prio_array active; unsigned int rt_nr_running; + unsigned int rr_nr_running; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED struct { int curr; /* highest queued rt task prio */ @@ -909,6 +910,18 @@ static inline unsigned int group_first_cpu(struct sched_group *group) extern int group_balance_cpu(struct sched_group *sg); +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) +void register_sched_domain_sysctl(void); +void unregister_sched_domain_sysctl(void); +#else +static inline void register_sched_domain_sysctl(void) +{ +} +static inline void unregister_sched_domain_sysctl(void) +{ +} +#endif + #else static inline void sched_ttwu_pending(void) { } @@ -1022,6 +1035,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ extern struct static_key_false sched_numa_balancing; +extern struct static_key_false sched_schedstats; static inline u64 global_rt_period(void) { @@ -1130,18 +1144,40 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) extern const int sched_prio_to_weight[40]; extern const u32 sched_prio_to_wmult[40]; +/* + * {de,en}queue flags: + * + * DEQUEUE_SLEEP - task is no longer runnable + * ENQUEUE_WAKEUP - task just became runnable + * + * SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks + * are in a known state which allows modification. Such pairs + * should preserve as much state as possible. + * + * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location + * in the runqueue. + * + * ENQUEUE_HEAD - place at front of runqueue (tail if not specified) + * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline) + * ENQUEUE_WAKING - sched_class::task_waking was called + * + */ + +#define DEQUEUE_SLEEP 0x01 +#define DEQUEUE_SAVE 0x02 /* matches ENQUEUE_RESTORE */ +#define DEQUEUE_MOVE 0x04 /* matches ENQUEUE_MOVE */ + #define ENQUEUE_WAKEUP 0x01 -#define ENQUEUE_HEAD 0x02 +#define ENQUEUE_RESTORE 0x02 +#define ENQUEUE_MOVE 0x04 + +#define ENQUEUE_HEAD 0x08 +#define ENQUEUE_REPLENISH 0x10 #ifdef CONFIG_SMP -#define ENQUEUE_WAKING 0x04 /* sched_class::task_waking was called */ +#define ENQUEUE_WAKING 0x20 #else #define ENQUEUE_WAKING 0x00 #endif -#define ENQUEUE_REPLENISH 0x08 -#define ENQUEUE_RESTORE 0x10 - -#define DEQUEUE_SLEEP 0x01 -#define DEQUEUE_SAVE 0x02 #define RETRY_TASK ((void *)-1UL) @@ -1278,6 +1314,35 @@ unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); +#ifdef CONFIG_NO_HZ_FULL +extern bool sched_can_stop_tick(struct rq *rq); + +/* + * Tick may be needed by tasks in the runqueue depending on their policy and + * requirements. If tick is needed, lets send the target an IPI to kick it out of + * nohz mode if necessary. + */ +static inline void sched_update_tick_dependency(struct rq *rq) +{ + int cpu; + + if (!tick_nohz_full_enabled()) + return; + + cpu = cpu_of(rq); + + if (!tick_nohz_full_cpu(cpu)) + return; + + if (sched_can_stop_tick(rq)) + tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED); + else + tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED); +} +#else +static inline void sched_update_tick_dependency(struct rq *rq) { } +#endif + static inline void add_nr_running(struct rq *rq, unsigned count) { unsigned prev_nr = rq->nr_running; @@ -1289,26 +1354,16 @@ static inline void add_nr_running(struct rq *rq, unsigned count) if (!rq->rd->overload) rq->rd->overload = true; #endif - -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_cpu(rq->cpu)) { - /* - * Tick is needed if more than one task runs on a CPU. - * Send the target an IPI to kick it out of nohz mode. - * - * We assume that IPI implies full memory barrier and the - * new value of rq->nr_running is visible on reception - * from the target. - */ - tick_nohz_full_kick_cpu(rq->cpu); - } -#endif } + + sched_update_tick_dependency(rq); } static inline void sub_nr_running(struct rq *rq, unsigned count) { rq->nr_running -= count; + /* Check if we still need preemption */ + sched_update_tick_dependency(rq); } static inline void rq_last_tick_reset(struct rq *rq) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index b0fbc7632de5f..70b3b6a20fb0e 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -29,9 +29,10 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) if (rq) rq->rq_sched_info.run_delay += delta; } -# define schedstat_inc(rq, field) do { (rq)->field++; } while (0) -# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0) -# define schedstat_set(var, val) do { var = (val); } while (0) +# define schedstat_enabled() static_branch_unlikely(&sched_schedstats) +# define schedstat_inc(rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0) +# define schedstat_add(rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0) +# define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0) #else /* !CONFIG_SCHEDSTATS */ static inline void rq_sched_info_arrive(struct rq *rq, unsigned long long delta) @@ -42,6 +43,7 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) static inline void rq_sched_info_depart(struct rq *rq, unsigned long long delta) {} +# define schedstat_enabled() 0 # define schedstat_inc(rq, field) do { } while (0) # define schedstat_add(rq, field, amt) do { } while (0) # define schedstat_set(var, val) do { } while (0) diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c new file mode 100644 index 0000000000000..82f0dff90030f --- /dev/null +++ b/kernel/sched/swait.c @@ -0,0 +1,123 @@ +#include +#include + +void __init_swait_queue_head(struct swait_queue_head *q, const char *name, + struct lock_class_key *key) +{ + raw_spin_lock_init(&q->lock); + lockdep_set_class_and_name(&q->lock, key, name); + INIT_LIST_HEAD(&q->task_list); +} +EXPORT_SYMBOL(__init_swait_queue_head); + +/* + * The thing about the wake_up_state() return value; I think we can ignore it. + * + * If for some reason it would return 0, that means the previously waiting + * task is already running, so it will observe condition true (or has already). + */ +void swake_up_locked(struct swait_queue_head *q) +{ + struct swait_queue *curr; + + if (list_empty(&q->task_list)) + return; + + curr = list_first_entry(&q->task_list, typeof(*curr), task_list); + wake_up_process(curr->task); + list_del_init(&curr->task_list); +} +EXPORT_SYMBOL(swake_up_locked); + +void swake_up(struct swait_queue_head *q) +{ + unsigned long flags; + + if (!swait_active(q)) + return; + + raw_spin_lock_irqsave(&q->lock, flags); + swake_up_locked(q); + raw_spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(swake_up); + +/* + * Does not allow usage from IRQ disabled, since we must be able to + * release IRQs to guarantee bounded hold time. + */ +void swake_up_all(struct swait_queue_head *q) +{ + struct swait_queue *curr; + LIST_HEAD(tmp); + + if (!swait_active(q)) + return; + + raw_spin_lock_irq(&q->lock); + list_splice_init(&q->task_list, &tmp); + while (!list_empty(&tmp)) { + curr = list_first_entry(&tmp, typeof(*curr), task_list); + + wake_up_state(curr->task, TASK_NORMAL); + list_del_init(&curr->task_list); + + if (list_empty(&tmp)) + break; + + raw_spin_unlock_irq(&q->lock); + raw_spin_lock_irq(&q->lock); + } + raw_spin_unlock_irq(&q->lock); +} +EXPORT_SYMBOL(swake_up_all); + +void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + wait->task = current; + if (list_empty(&wait->task_list)) + list_add(&wait->task_list, &q->task_list); +} + +void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&q->lock, flags); + __prepare_to_swait(q, wait); + set_current_state(state); + raw_spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_swait); + +long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) +{ + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + prepare_to_swait(q, wait, state); + + return 0; +} +EXPORT_SYMBOL(prepare_to_swait_event); + +void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + __set_current_state(TASK_RUNNING); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); +} + +void finish_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + + if (!list_empty_careful(&wait->task_list)) { + raw_spin_lock_irqsave(&q->lock, flags); + list_del_init(&wait->task_list); + raw_spin_unlock_irqrestore(&q->lock, flags); + } +} +EXPORT_SYMBOL(finish_swait); diff --git a/kernel/smp.c b/kernel/smp.c index d903c02223afb..74165443c2401 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -105,13 +105,12 @@ void __init call_function_init(void) * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static void csd_lock_wait(struct call_single_data *csd) +static __always_inline void csd_lock_wait(struct call_single_data *csd) { - while (smp_load_acquire(&csd->flags) & CSD_FLAG_LOCK) - cpu_relax(); + smp_cond_acquire(!(csd->flags & CSD_FLAG_LOCK)); } -static void csd_lock(struct call_single_data *csd) +static __always_inline void csd_lock(struct call_single_data *csd) { csd_lock_wait(csd); csd->flags |= CSD_FLAG_LOCK; @@ -124,7 +123,7 @@ static void csd_lock(struct call_single_data *csd) smp_wmb(); } -static void csd_unlock(struct call_single_data *csd) +static __always_inline void csd_unlock(struct call_single_data *csd) { WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); @@ -569,6 +568,7 @@ void __init smp_init(void) unsigned int cpu; idle_threads_init(); + cpuhp_threads_init(); /* FIXME: This should be done in userspace --RR */ for_each_present_cpu(cpu) { diff --git a/kernel/smpboot.c b/kernel/smpboot.c index d264f59bff56c..13bc43d1fb227 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -226,7 +226,7 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp kthread_unpark(tsk); } -void smpboot_unpark_threads(unsigned int cpu) +int smpboot_unpark_threads(unsigned int cpu) { struct smp_hotplug_thread *cur; @@ -235,6 +235,7 @@ void smpboot_unpark_threads(unsigned int cpu) if (cpumask_test_cpu(cpu, cur->cpumask)) smpboot_unpark_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); + return 0; } static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) @@ -245,7 +246,7 @@ static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kthread_park(tsk); } -void smpboot_park_threads(unsigned int cpu) +int smpboot_park_threads(unsigned int cpu) { struct smp_hotplug_thread *cur; @@ -253,6 +254,7 @@ void smpboot_park_threads(unsigned int cpu) list_for_each_entry_reverse(cur, &hotplug_threads, list) smpboot_park_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); + return 0; } static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 72415a0eb955c..485b81cfab34f 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -14,7 +14,9 @@ static inline void idle_threads_init(void) { } #endif int smpboot_create_threads(unsigned int cpu); -void smpboot_park_threads(unsigned int cpu); -void smpboot_unpark_threads(unsigned int cpu); +int smpboot_park_threads(unsigned int cpu); +int smpboot_unpark_threads(unsigned int cpu); + +void __init cpuhp_threads_init(void); #endif diff --git a/kernel/softirq.c b/kernel/softirq.c index 479e4436f7876..8aae49dd7da86 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -116,9 +116,9 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) if (preempt_count() == cnt) { #ifdef CONFIG_DEBUG_PREEMPT - current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); + current->preempt_disable_ip = get_lock_parent_ip(); #endif - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); } } EXPORT_SYMBOL(__local_bh_disable_ip); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 97715fd9e790a..f5102fabef7f5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -350,6 +350,17 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_SCHEDSTATS + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SCHEDSTATS */ #endif /* CONFIG_SMP */ #ifdef CONFIG_NUMA_BALANCING { @@ -505,7 +516,7 @@ static struct ctl_table kern_table[] = { .data = &latencytop_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = sysctl_latencytop, }, #endif #ifdef CONFIG_BLK_DEV_INITRD diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 664de539299b6..56ece145a814a 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -323,13 +323,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) /* cs is a watchdog. */ if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + } + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_select_watchdog(bool fallback) +{ + struct clocksource *cs, *old_wd; + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + /* save current watchdog */ + old_wd = watchdog; + if (fallback) + watchdog = NULL; + + list_for_each_entry(cs, &clocksource_list, list) { + /* cs is a clocksource to be watched. */ + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) + continue; + + /* Skip current if we were requested for a fallback. */ + if (fallback && cs == old_wd) + continue; + /* Pick the best watchdog. */ - if (!watchdog || cs->rating > watchdog->rating) { + if (!watchdog || cs->rating > watchdog->rating) watchdog = cs; - /* Reset watchdog cycles */ - clocksource_reset_watchdog(); - } } + /* If we failed to find a fallback restore the old one. */ + if (!watchdog) + watchdog = old_wd; + + /* If we changed the watchdog we need to reset cycles. */ + if (watchdog != old_wd) + clocksource_reset_watchdog(); + /* Check if the watchdog timer needs to be started. */ clocksource_start_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); @@ -404,6 +433,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; } +static void clocksource_select_watchdog(bool fallback) { } static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } static inline int __clocksource_watchdog_kthread(void) { return 0; } @@ -736,6 +766,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) clocksource_enqueue(cs); clocksource_enqueue_watchdog(cs); clocksource_select(); + clocksource_select_watchdog(false); mutex_unlock(&clocksource_mutex); return 0; } @@ -758,6 +789,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating) mutex_lock(&clocksource_mutex); __clocksource_change_rating(cs, rating); clocksource_select(); + clocksource_select_watchdog(false); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); @@ -767,12 +799,12 @@ EXPORT_SYMBOL(clocksource_change_rating); */ static int clocksource_unbind(struct clocksource *cs) { - /* - * I really can't convince myself to support this on hardware - * designed by lobotomized monkeys. - */ - if (clocksource_is_watchdog(cs)) - return -EBUSY; + if (clocksource_is_watchdog(cs)) { + /* Select and try to install a replacement watchdog. */ + clocksource_select_watchdog(true); + if (clocksource_is_watchdog(cs)) + return -EBUSY; + } if (cs == curr_clocksource) { /* Select and try to install a replacement clock source */ diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 347fecf86a3fb..555e21f7b966c 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -68,7 +68,7 @@ static struct clocksource clocksource_jiffies = { .name = "jiffies", .rating = 1, /* lowest valid rating*/ .read = jiffies_read, - .mask = 0xffffffff, /*32bits*/ + .mask = CLOCKSOURCE_MASK(32), .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ .shift = JIFFIES_SHIFT, .max_cycles = 10, diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index f5e86d282d520..1cafba860b08c 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -333,7 +333,6 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) return err; } - /* * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. * This is called from sys_timer_create() and do_cpu_nanosleep() with the @@ -517,6 +516,10 @@ static void arm_timer(struct k_itimer *timer) cputime_expires->sched_exp = exp; break; } + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); + else + tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER); } } @@ -582,39 +585,6 @@ static int cpu_timer_sample_group(const clockid_t which_clock, return 0; } -#ifdef CONFIG_NO_HZ_FULL -static void nohz_kick_work_fn(struct work_struct *work) -{ - tick_nohz_full_kick_all(); -} - -static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn); - -/* - * We need the IPIs to be sent from sane process context. - * The posix cpu timers are always set with irqs disabled. - */ -static void posix_cpu_timer_kick_nohz(void) -{ - if (context_tracking_is_enabled()) - schedule_work(&nohz_kick_work); -} - -bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk) -{ - if (!task_cputime_zero(&tsk->cputime_expires)) - return false; - - /* Check if cputimer is running. This is accessed without locking. */ - if (READ_ONCE(tsk->signal->cputimer.running)) - return false; - - return true; -} -#else -static inline void posix_cpu_timer_kick_nohz(void) { } -#endif - /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. @@ -761,8 +731,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, sample_to_timespec(timer->it_clock, old_incr, &old->it_interval); } - if (!ret) - posix_cpu_timer_kick_nohz(); + return ret; } @@ -911,6 +880,8 @@ static void check_thread_timers(struct task_struct *tsk, __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); } } + if (task_cputime_zero(tsk_expires)) + tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER); } static inline void stop_process_timers(struct signal_struct *sig) @@ -919,6 +890,7 @@ static inline void stop_process_timers(struct signal_struct *sig) /* Turn off cputimer->running. This is done without locking. */ WRITE_ONCE(cputimer->running, false); + tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER); } static u32 onecputick; @@ -1095,8 +1067,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) arm_timer(timer); unlock_task_sighand(p, &flags); - /* Kick full dynticks CPUs in case they need to tick on the new timer */ - posix_cpu_timer_kick_nohz(); out: timer->it_overrun_last = timer->it_overrun; timer->it_overrun = -1; @@ -1270,7 +1240,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, } if (!*newval) - goto out; + return; *newval += now; } @@ -1288,8 +1258,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, tsk->signal->cputime_expires.virt_exp = *newval; break; } -out: - posix_cpu_timer_kick_nohz(); + + tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER); } static int do_cpu_nanosleep(const clockid_t which_clock, int flags, diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 0b17424349eb4..969e6704c3c9a 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include @@ -158,54 +157,63 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) cpumask_var_t tick_nohz_full_mask; cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; +static unsigned long tick_dep_mask; -static bool can_stop_full_tick(void) +static void trace_tick_dependency(unsigned long dep) +{ + if (dep & TICK_DEP_MASK_POSIX_TIMER) { + trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); + return; + } + + if (dep & TICK_DEP_MASK_PERF_EVENTS) { + trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); + return; + } + + if (dep & TICK_DEP_MASK_SCHED) { + trace_tick_stop(0, TICK_DEP_MASK_SCHED); + return; + } + + if (dep & TICK_DEP_MASK_CLOCK_UNSTABLE) + trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); +} + +static bool can_stop_full_tick(struct tick_sched *ts) { WARN_ON_ONCE(!irqs_disabled()); - if (!sched_can_stop_tick()) { - trace_tick_stop(0, "more than 1 task in runqueue\n"); + if (tick_dep_mask) { + trace_tick_dependency(tick_dep_mask); return false; } - if (!posix_cpu_timers_can_stop_tick(current)) { - trace_tick_stop(0, "posix timers running\n"); + if (ts->tick_dep_mask) { + trace_tick_dependency(ts->tick_dep_mask); return false; } - if (!perf_event_can_stop_tick()) { - trace_tick_stop(0, "perf events running\n"); + if (current->tick_dep_mask) { + trace_tick_dependency(current->tick_dep_mask); return false; } - /* sched_clock_tick() needs us? */ -#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK - /* - * TODO: kick full dynticks CPUs when - * sched_clock_stable is set. - */ - if (!sched_clock_stable()) { - trace_tick_stop(0, "unstable sched clock\n"); - /* - * Don't allow the user to think they can get - * full NO_HZ with this machine. - */ - WARN_ONCE(tick_nohz_full_running, - "NO_HZ FULL will not work with unstable sched clock"); + if (current->signal->tick_dep_mask) { + trace_tick_dependency(current->signal->tick_dep_mask); return false; } -#endif return true; } -static void nohz_full_kick_work_func(struct irq_work *work) +static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { - .func = nohz_full_kick_work_func, + .func = nohz_full_kick_func, }; /* @@ -214,7 +222,7 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ -void tick_nohz_full_kick(void) +static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; @@ -234,27 +242,112 @@ void tick_nohz_full_kick_cpu(int cpu) irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } -static void nohz_full_kick_ipi(void *info) -{ - /* Empty, the tick restart happens on tick_nohz_irq_exit() */ -} - /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ -void tick_nohz_full_kick_all(void) +static void tick_nohz_full_kick_all(void) { + int cpu; + if (!tick_nohz_full_running) return; preempt_disable(); - smp_call_function_many(tick_nohz_full_mask, - nohz_full_kick_ipi, NULL, false); - tick_nohz_full_kick(); + for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) + tick_nohz_full_kick_cpu(cpu); preempt_enable(); } +static void tick_nohz_dep_set_all(unsigned long *dep, + enum tick_dep_bits bit) +{ + unsigned long prev; + + prev = fetch_or(dep, BIT_MASK(bit)); + if (!prev) + tick_nohz_full_kick_all(); +} + +/* + * Set a global tick dependency. Used by perf events that rely on freq and + * by unstable clock. + */ +void tick_nohz_dep_set(enum tick_dep_bits bit) +{ + tick_nohz_dep_set_all(&tick_dep_mask, bit); +} + +void tick_nohz_dep_clear(enum tick_dep_bits bit) +{ + clear_bit(bit, &tick_dep_mask); +} + +/* + * Set per-CPU tick dependency. Used by scheduler and perf events in order to + * manage events throttling. + */ +void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) +{ + unsigned long prev; + struct tick_sched *ts; + + ts = per_cpu_ptr(&tick_cpu_sched, cpu); + + prev = fetch_or(&ts->tick_dep_mask, BIT_MASK(bit)); + if (!prev) { + preempt_disable(); + /* Perf needs local kick that is NMI safe */ + if (cpu == smp_processor_id()) { + tick_nohz_full_kick(); + } else { + /* Remote irq work not NMI-safe */ + if (!WARN_ON_ONCE(in_nmi())) + tick_nohz_full_kick_cpu(cpu); + } + preempt_enable(); + } +} + +void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) +{ + struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); + + clear_bit(bit, &ts->tick_dep_mask); +} + +/* + * Set a per-task tick dependency. Posix CPU timers need this in order to elapse + * per task timers. + */ +void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) +{ + /* + * We could optimize this with just kicking the target running the task + * if that noise matters for nohz full users. + */ + tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit); +} + +void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) +{ + clear_bit(bit, &tsk->tick_dep_mask); +} + +/* + * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse + * per process timers. + */ +void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit) +{ + tick_nohz_dep_set_all(&sig->tick_dep_mask, bit); +} + +void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) +{ + clear_bit(bit, &sig->tick_dep_mask); +} + /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: @@ -263,15 +356,19 @@ void tick_nohz_full_kick_all(void) void __tick_nohz_task_switch(void) { unsigned long flags; + struct tick_sched *ts; local_irq_save(flags); if (!tick_nohz_full_cpu(smp_processor_id())) goto out; - if (tick_nohz_tick_stopped() && !can_stop_full_tick()) - tick_nohz_full_kick(); + ts = this_cpu_ptr(&tick_cpu_sched); + if (ts->tick_stopped) { + if (current->tick_dep_mask || current->signal->tick_dep_mask) + tick_nohz_full_kick(); + } out: local_irq_restore(flags); } @@ -689,7 +786,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; - trace_tick_stop(1, " "); + trace_tick_stop(1, TICK_DEP_MASK_NONE); } /* @@ -740,7 +837,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) return; - if (can_stop_full_tick()) + if (can_stop_full_tick(ts)) tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); else if (ts->tick_stopped) tick_nohz_restart_sched_tick(ts, ktime_get(), 1); diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index a4a8d4e9baa13..eb4e32566a832 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -60,6 +60,7 @@ struct tick_sched { u64 next_timer; ktime_t idle_expires; int do_timer_last; + unsigned long tick_dep_mask; }; extern struct tick_sched *tick_get_tick_sched(int cpu); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 34b4cedfa80da..9c629bbed572b 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -233,6 +233,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; + ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.read = clock->read; @@ -298,17 +299,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; static inline u32 arch_gettimeoffset(void) { return 0; } #endif +static inline s64 timekeeping_delta_to_ns(struct tk_read_base *tkr, + cycle_t delta) +{ + s64 nsec; + + nsec = delta * tkr->mult + tkr->xtime_nsec; + nsec >>= tkr->shift; + + /* If arch requires, add in get_arch_timeoffset() */ + return nsec + arch_gettimeoffset(); +} + static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) { cycle_t delta; - s64 nsec; delta = timekeeping_get_delta(tkr); + return timekeeping_delta_to_ns(tkr, delta); +} - nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift; +static inline s64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, + cycle_t cycles) +{ + cycle_t delta; - /* If arch requires, add in get_arch_timeoffset() */ - return nsec + arch_gettimeoffset(); + /* calculate the delta since the last update_wall_time */ + delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); + return timekeeping_delta_to_ns(tkr, delta); } /** @@ -857,44 +875,262 @@ time64_t __ktime_get_real_seconds(void) return tk->xtime_sec; } +/** + * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter + * @systime_snapshot: pointer to struct receiving the system time snapshot + */ +void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned long seq; + ktime_t base_raw; + ktime_t base_real; + s64 nsec_raw; + s64 nsec_real; + cycle_t now; -#ifdef CONFIG_NTP_PPS + WARN_ON_ONCE(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + + now = tk->tkr_mono.read(tk->tkr_mono.clock); + systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; + systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; + base_real = ktime_add(tk->tkr_mono.base, + tk_core.timekeeper.offs_real); + base_raw = tk->tkr_raw.base; + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); + } while (read_seqcount_retry(&tk_core.seq, seq)); + + systime_snapshot->cycles = now; + systime_snapshot->real = ktime_add_ns(base_real, nsec_real); + systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); +} +EXPORT_SYMBOL_GPL(ktime_get_snapshot); + +/* Scale base by mult/div checking for overflow */ +static int scale64_check_overflow(u64 mult, u64 div, u64 *base) +{ + u64 tmp, rem; + + tmp = div64_u64_rem(*base, div, &rem); + + if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || + ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) + return -EOVERFLOW; + tmp *= mult; + rem *= mult; + + do_div(rem, div); + *base = tmp + rem; + return 0; +} /** - * ktime_get_raw_and_real_ts64 - get day and raw monotonic time in timespec format - * @ts_raw: pointer to the timespec to be set to raw monotonic time - * @ts_real: pointer to the timespec to be set to the time of day + * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval + * @history: Snapshot representing start of history + * @partial_history_cycles: Cycle offset into history (fractional part) + * @total_history_cycles: Total history length in cycles + * @discontinuity: True indicates clock was set on history period + * @ts: Cross timestamp that should be adjusted using + * partial/total ratio * - * This function reads both the time of day and raw monotonic time at the - * same time atomically and stores the resulting timestamps in timespec - * format. + * Helper function used by get_device_system_crosststamp() to correct the + * crosstimestamp corresponding to the start of the current interval to the + * system counter value (timestamp point) provided by the driver. The + * total_history_* quantities are the total history starting at the provided + * reference point and ending at the start of the current interval. The cycle + * count between the driver timestamp point and the start of the current + * interval is partial_history_cycles. */ -void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, struct timespec64 *ts_real) +static int adjust_historical_crosststamp(struct system_time_snapshot *history, + cycle_t partial_history_cycles, + cycle_t total_history_cycles, + bool discontinuity, + struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; - s64 nsecs_raw, nsecs_real; + u64 corr_raw, corr_real; + bool interp_forward; + int ret; - WARN_ON_ONCE(timekeeping_suspended); + if (total_history_cycles == 0 || partial_history_cycles == 0) + return 0; + + /* Interpolate shortest distance from beginning or end of history */ + interp_forward = partial_history_cycles > total_history_cycles/2 ? + true : false; + partial_history_cycles = interp_forward ? + total_history_cycles - partial_history_cycles : + partial_history_cycles; + + /* + * Scale the monotonic raw time delta by: + * partial_history_cycles / total_history_cycles + */ + corr_raw = (u64)ktime_to_ns( + ktime_sub(ts->sys_monoraw, history->raw)); + ret = scale64_check_overflow(partial_history_cycles, + total_history_cycles, &corr_raw); + if (ret) + return ret; + + /* + * If there is a discontinuity in the history, scale monotonic raw + * correction by: + * mult(real)/mult(raw) yielding the realtime correction + * Otherwise, calculate the realtime correction similar to monotonic + * raw calculation + */ + if (discontinuity) { + corr_real = mul_u64_u32_div + (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); + } else { + corr_real = (u64)ktime_to_ns( + ktime_sub(ts->sys_realtime, history->real)); + ret = scale64_check_overflow(partial_history_cycles, + total_history_cycles, &corr_real); + if (ret) + return ret; + } + + /* Fixup monotonic raw and real time time values */ + if (interp_forward) { + ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); + ts->sys_realtime = ktime_add_ns(history->real, corr_real); + } else { + ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); + ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); + } + + return 0; +} + +/* + * cycle_between - true if test occurs chronologically between before and after + */ +static bool cycle_between(cycle_t before, cycle_t test, cycle_t after) +{ + if (test > before && test < after) + return true; + if (test < before && before > after) + return true; + return false; +} + +/** + * get_device_system_crosststamp - Synchronously capture system/device timestamp + * @get_time_fn: Callback to get simultaneous device time and + * system counter from the device driver + * @ctx: Context passed to get_time_fn() + * @history_begin: Historical reference point used to interpolate system + * time when counter provided by the driver is before the current interval + * @xtstamp: Receives simultaneously captured system and device time + * + * Reads a timestamp from a device and correlates it to system time + */ +int get_device_system_crosststamp(int (*get_time_fn) + (ktime_t *device_time, + struct system_counterval_t *sys_counterval, + void *ctx), + void *ctx, + struct system_time_snapshot *history_begin, + struct system_device_crosststamp *xtstamp) +{ + struct system_counterval_t system_counterval; + struct timekeeper *tk = &tk_core.timekeeper; + cycle_t cycles, now, interval_start; + unsigned int clock_was_set_seq = 0; + ktime_t base_real, base_raw; + s64 nsec_real, nsec_raw; + u8 cs_was_changed_seq; + unsigned long seq; + bool do_interp; + int ret; do { seq = read_seqcount_begin(&tk_core.seq); + /* + * Try to synchronously capture device time and a system + * counter value calling back into the device driver + */ + ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); + if (ret) + return ret; + + /* + * Verify that the clocksource associated with the captured + * system counter value is the same as the currently installed + * timekeeper clocksource + */ + if (tk->tkr_mono.clock != system_counterval.cs) + return -ENODEV; + cycles = system_counterval.cycles; - *ts_raw = tk->raw_time; - ts_real->tv_sec = tk->xtime_sec; - ts_real->tv_nsec = 0; + /* + * Check whether the system counter value provided by the + * device driver is on the current timekeeping interval. + */ + now = tk->tkr_mono.read(tk->tkr_mono.clock); + interval_start = tk->tkr_mono.cycle_last; + if (!cycle_between(interval_start, cycles, now)) { + clock_was_set_seq = tk->clock_was_set_seq; + cs_was_changed_seq = tk->cs_was_changed_seq; + cycles = interval_start; + do_interp = true; + } else { + do_interp = false; + } - nsecs_raw = timekeeping_get_ns(&tk->tkr_raw); - nsecs_real = timekeeping_get_ns(&tk->tkr_mono); + base_real = ktime_add(tk->tkr_mono.base, + tk_core.timekeeper.offs_real); + base_raw = tk->tkr_raw.base; + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, + system_counterval.cycles); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, + system_counterval.cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); - timespec64_add_ns(ts_raw, nsecs_raw); - timespec64_add_ns(ts_real, nsecs_real); -} -EXPORT_SYMBOL(ktime_get_raw_and_real_ts64); + xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); + xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); -#endif /* CONFIG_NTP_PPS */ + /* + * Interpolate if necessary, adjusting back from the start of the + * current interval + */ + if (do_interp) { + cycle_t partial_history_cycles, total_history_cycles; + bool discontinuity; + + /* + * Check that the counter value occurs after the provided + * history reference and that the history doesn't cross a + * clocksource change + */ + if (!history_begin || + !cycle_between(history_begin->cycles, + system_counterval.cycles, cycles) || + history_begin->cs_was_changed_seq != cs_was_changed_seq) + return -EINVAL; + partial_history_cycles = cycles - system_counterval.cycles; + total_history_cycles = cycles - history_begin->cycles; + discontinuity = + history_begin->clock_was_set_seq != clock_was_set_seq; + + ret = adjust_historical_crosststamp(history_begin, + partial_history_cycles, + total_history_cycles, + discontinuity, xtstamp); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_gettimeofday - Returns the time of day in a timeval diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ab09829d3b97a..05ddc0820771e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name) struct ftrace_event_field *field; struct list_head *head; - field = __find_event_field(&ftrace_generic_fields, name); + head = trace_get_fields(call); + field = __find_event_field(head, name); if (field) return field; - field = __find_event_field(&ftrace_common_fields, name); + field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; - head = trace_get_fields(call); - return __find_event_field(head, name); + return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, @@ -171,8 +171,10 @@ static int trace_define_generic_fields(void) { int ret; - __generic_field(int, cpu, FILTER_OTHER); - __generic_field(char *, comm, FILTER_PTR_STRING); + __generic_field(int, CPU, FILTER_CPU); + __generic_field(int, cpu, FILTER_CPU); + __generic_field(char *, COMM, FILTER_COMM); + __generic_field(char *, comm, FILTER_COMM); return ret; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f93a219b18daa..6816302542b28 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps, return -EINVAL; } - if (is_string_field(field)) { + if (field->filter_type == FILTER_COMM) { + filter_build_regex(pred); + fn = filter_pred_comm; + pred->regex.field_len = TASK_COMM_LEN; + } else if (is_string_field(field)) { filter_build_regex(pred); - if (!strcmp(field->name, "comm")) { - fn = filter_pred_comm; - pred->regex.field_len = TASK_COMM_LEN; - } else if (field->filter_type == FILTER_STATIC_STRING) { + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) @@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps, } pred->val = val; - if (!strcmp(field->name, "cpu")) + if (field->filter_type == FILTER_CPU) fn = filter_pred_cpu; else fn = select_comparison_fn(pred->op, field->size, diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c9956440d0e60..21b81a41dae57 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -30,7 +30,7 @@ struct trace_kprobe { struct list_head list; struct kretprobe rp; /* Use rp.kp for kprobe use */ - unsigned long nhit; + unsigned long __percpu *nhit; const char *symbol; /* symbol name */ struct trace_probe tp; }; @@ -274,6 +274,10 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, if (!tk) return ERR_PTR(ret); + tk->nhit = alloc_percpu(unsigned long); + if (!tk->nhit) + goto error; + if (symbol) { tk->symbol = kstrdup(symbol, GFP_KERNEL); if (!tk->symbol) @@ -313,6 +317,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, error: kfree(tk->tp.call.name); kfree(tk->symbol); + free_percpu(tk->nhit); kfree(tk); return ERR_PTR(ret); } @@ -327,6 +332,7 @@ static void free_trace_kprobe(struct trace_kprobe *tk) kfree(tk->tp.call.class->system); kfree(tk->tp.call.name); kfree(tk->symbol); + free_percpu(tk->nhit); kfree(tk); } @@ -874,9 +880,14 @@ static const struct file_operations kprobe_events_ops = { static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_kprobe *tk = v; + unsigned long nhit = 0; + int cpu; + + for_each_possible_cpu(cpu) + nhit += *per_cpu_ptr(tk->nhit, cpu); seq_printf(m, " %-44s %15lu %15lu\n", - trace_event_name(&tk->tp.call), tk->nhit, + trace_event_name(&tk->tp.call), nhit, tk->rp.kp.nmissed); return 0; @@ -1225,7 +1236,7 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); - tk->nhit++; + raw_cpu_inc(*tk->nhit); if (tk->tp.flags & TP_FLAG_TRACE) kprobe_trace_func(tk, regs); @@ -1242,7 +1253,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp); - tk->nhit++; + raw_cpu_inc(*tk->nhit); if (tk->tp.flags & TP_FLAG_TRACE) kretprobe_trace_func(tk, ri, regs); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 0655afbea83f5..d1663083d903a 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -186,11 +186,11 @@ print_syscall_exit(struct trace_iterator *iter, int flags, extern char *__bad_type_size(void); -#define SYSCALL_FIELD(type, name) \ - sizeof(type) != sizeof(trace.name) ? \ +#define SYSCALL_FIELD(type, field, name) \ + sizeof(type) != sizeof(trace.field) ? \ __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), name), \ - sizeof(trace.name), is_signed_type(type) + #type, #name, offsetof(typeof(trace), field), \ + sizeof(trace.field), is_signed_type(type) static int __init __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) @@ -261,7 +261,8 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call) int i; int offset = offsetof(typeof(trace), args); - ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), + FILTER_OTHER); if (ret) return ret; @@ -281,11 +282,12 @@ static int __init syscall_exit_define_fields(struct trace_event_call *call) struct syscall_trace_exit trace; int ret; - ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), + FILTER_OTHER); if (ret) return ret; - ret = trace_define_field(call, SYSCALL_FIELD(long, ret), + ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret), FILTER_OTHER); return ret; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 975cb49e32bf8..f8e26ab963ed2 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -93,9 +93,11 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) { struct mm_struct *mm; - /* convert pages-usec to Mbyte-usec */ - stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB; - stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB; + /* convert pages-nsec/1024 to Mbyte-usec, see __acct_update_integrals */ + stats->coremem = p->acct_rss_mem1 * PAGE_SIZE; + do_div(stats->coremem, 1000 * KB); + stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE; + do_div(stats->virtmem, 1000 * KB); mm = get_task_mm(p); if (mm) { /* adjust to KB unit */ @@ -123,27 +125,28 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) static void __acct_update_integrals(struct task_struct *tsk, cputime_t utime, cputime_t stime) { - if (likely(tsk->mm)) { - cputime_t time, dtime; - struct timeval value; - unsigned long flags; - u64 delta; - - local_irq_save(flags); - time = stime + utime; - dtime = time - tsk->acct_timexpd; - jiffies_to_timeval(cputime_to_jiffies(dtime), &value); - delta = value.tv_sec; - delta = delta * USEC_PER_SEC + value.tv_usec; - - if (delta == 0) - goto out; - tsk->acct_timexpd = time; - tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); - tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; - out: - local_irq_restore(flags); - } + cputime_t time, dtime; + u64 delta; + + if (!likely(tsk->mm)) + return; + + time = stime + utime; + dtime = time - tsk->acct_timexpd; + /* Avoid division: cputime_t is often in nanoseconds already. */ + delta = cputime_to_nsecs(dtime); + + if (delta < TICK_NSEC) + return; + + tsk->acct_timexpd = time; + /* + * Divide by 1024 to avoid overflow, and to avoid division. + * The final unit reported to userspace is Mbyte-usecs, + * the rest of the math is done in xacct_add_tsk. + */ + tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10; + tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10; } /** @@ -153,9 +156,12 @@ static void __acct_update_integrals(struct task_struct *tsk, void acct_update_integrals(struct task_struct *tsk) { cputime_t utime, stime; + unsigned long flags; + local_irq_save(flags); task_cputime(tsk, &utime, &stime); __acct_update_integrals(tsk, utime, stime); + local_irq_restore(flags); } /** diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8bfd1aca7a3d0..f28f7fad452fe 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1442,6 +1442,19 @@ config DEBUG_BLOCK_EXT_DEVT Say N if you are unsure. +config CPU_HOTPLUG_STATE_CONTROL + bool "Enable CPU hotplug state control" + depends on DEBUG_KERNEL + depends on HOTPLUG_CPU + default n + help + Allows to write steps between "offline" and "online" to the CPUs + sysfs target file so states can be stepped granular. This is a debug + option for now as the hotplug machinery cannot be stopped and + restarted at arbitrary points yet. + + Say N if your are unsure. + config NOTIFIER_ERROR_INJECTION tristate "Notifier error injection" depends on DEBUG_KERNEL diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index d62de8bf022d2..1234818143204 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -17,7 +17,7 @@ #include #ifdef CONFIG_X86 -#include /* for boot_cpu_has below */ +#include /* for boot_cpu_has below */ #endif #define TEST(bit, op, c_op, val) \ diff --git a/lib/cpumask.c b/lib/cpumask.c index 5a70f6196f577..81dedaab36ccf 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -41,6 +41,7 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) break; return i; } +EXPORT_SYMBOL(cpumask_any_but); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK diff --git a/lib/list_debug.c b/lib/list_debug.c index 3345a089ef7b9..3859bf63561c6 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -12,13 +12,6 @@ #include #include -static struct list_head force_poison; -void list_force_poison(struct list_head *entry) -{ - entry->next = &force_poison; - entry->prev = &force_poison; -} - /* * Insert a new entry between two known consecutive entries. * @@ -30,8 +23,6 @@ void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { - WARN(new->next == &force_poison || new->prev == &force_poison, - "list_add attempted on force-poisoned entry\n"); WARN(next->prev != prev, "list_add corruption. next->prev should be " "prev (%p), but was %p. (next=%p).\n", diff --git a/lib/test_static_keys.c b/lib/test_static_keys.c index c61b299e367ff..915d75df20864 100644 --- a/lib/test_static_keys.c +++ b/lib/test_static_keys.c @@ -46,8 +46,11 @@ struct test_key { bool (*test_key)(void); }; -#define test_key_func(key, branch) \ - ({bool func(void) { return branch(key); } func; }) +#define test_key_func(key, branch) \ +static bool key ## _ ## branch(void) \ +{ \ + return branch(&key); \ +} static void invert_key(struct static_key *key) { @@ -92,6 +95,25 @@ static int verify_keys(struct test_key *keys, int size, bool invert) return 0; } +test_key_func(old_true_key, static_key_true) +test_key_func(old_false_key, static_key_false) +test_key_func(true_key, static_branch_likely) +test_key_func(true_key, static_branch_unlikely) +test_key_func(false_key, static_branch_likely) +test_key_func(false_key, static_branch_unlikely) +test_key_func(base_old_true_key, static_key_true) +test_key_func(base_inv_old_true_key, static_key_true) +test_key_func(base_old_false_key, static_key_false) +test_key_func(base_inv_old_false_key, static_key_false) +test_key_func(base_true_key, static_branch_likely) +test_key_func(base_true_key, static_branch_unlikely) +test_key_func(base_inv_true_key, static_branch_likely) +test_key_func(base_inv_true_key, static_branch_unlikely) +test_key_func(base_false_key, static_branch_likely) +test_key_func(base_false_key, static_branch_unlikely) +test_key_func(base_inv_false_key, static_branch_likely) +test_key_func(base_inv_false_key, static_branch_unlikely) + static int __init test_static_key_init(void) { int ret; @@ -102,95 +124,95 @@ static int __init test_static_key_init(void) { .init_state = true, .key = &old_true_key, - .test_key = test_key_func(&old_true_key, static_key_true), + .test_key = &old_true_key_static_key_true, }, { .init_state = false, .key = &old_false_key, - .test_key = test_key_func(&old_false_key, static_key_false), + .test_key = &old_false_key_static_key_false, }, /* internal keys - new keys */ { .init_state = true, .key = &true_key.key, - .test_key = test_key_func(&true_key, static_branch_likely), + .test_key = &true_key_static_branch_likely, }, { .init_state = true, .key = &true_key.key, - .test_key = test_key_func(&true_key, static_branch_unlikely), + .test_key = &true_key_static_branch_unlikely, }, { .init_state = false, .key = &false_key.key, - .test_key = test_key_func(&false_key, static_branch_likely), + .test_key = &false_key_static_branch_likely, }, { .init_state = false, .key = &false_key.key, - .test_key = test_key_func(&false_key, static_branch_unlikely), + .test_key = &false_key_static_branch_unlikely, }, /* external keys - old keys */ { .init_state = true, .key = &base_old_true_key, - .test_key = test_key_func(&base_old_true_key, static_key_true), + .test_key = &base_old_true_key_static_key_true, }, { .init_state = false, .key = &base_inv_old_true_key, - .test_key = test_key_func(&base_inv_old_true_key, static_key_true), + .test_key = &base_inv_old_true_key_static_key_true, }, { .init_state = false, .key = &base_old_false_key, - .test_key = test_key_func(&base_old_false_key, static_key_false), + .test_key = &base_old_false_key_static_key_false, }, { .init_state = true, .key = &base_inv_old_false_key, - .test_key = test_key_func(&base_inv_old_false_key, static_key_false), + .test_key = &base_inv_old_false_key_static_key_false, }, /* external keys - new keys */ { .init_state = true, .key = &base_true_key.key, - .test_key = test_key_func(&base_true_key, static_branch_likely), + .test_key = &base_true_key_static_branch_likely, }, { .init_state = true, .key = &base_true_key.key, - .test_key = test_key_func(&base_true_key, static_branch_unlikely), + .test_key = &base_true_key_static_branch_unlikely, }, { .init_state = false, .key = &base_inv_true_key.key, - .test_key = test_key_func(&base_inv_true_key, static_branch_likely), + .test_key = &base_inv_true_key_static_branch_likely, }, { .init_state = false, .key = &base_inv_true_key.key, - .test_key = test_key_func(&base_inv_true_key, static_branch_unlikely), + .test_key = &base_inv_true_key_static_branch_unlikely, }, { .init_state = false, .key = &base_false_key.key, - .test_key = test_key_func(&base_false_key, static_branch_likely), + .test_key = &base_false_key_static_branch_likely, }, { .init_state = false, .key = &base_false_key.key, - .test_key = test_key_func(&base_false_key, static_branch_unlikely), + .test_key = &base_false_key_static_branch_unlikely, }, { .init_state = true, .key = &base_inv_false_key.key, - .test_key = test_key_func(&base_inv_false_key, static_branch_likely), + .test_key = &base_inv_false_key_static_branch_likely, }, { .init_state = true, .key = &base_inv_false_key.key, - .test_key = test_key_func(&base_inv_false_key, static_branch_unlikely), + .test_key = &base_inv_false_key_static_branch_unlikely, }, }; diff --git a/mm/filemap.c b/mm/filemap.c index 3461d97ecb30b..da7a35d83de7e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -195,6 +195,30 @@ void __delete_from_page_cache(struct page *page, void *shadow, else cleancache_invalidate_page(mapping, page); + VM_BUG_ON_PAGE(page_mapped(page), page); + if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { + int mapcount; + + pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", + current->comm, page_to_pfn(page)); + dump_page(page, "still mapped when deleted"); + dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + + mapcount = page_mapcount(page); + if (mapping_exiting(mapping) && + page_count(page) >= mapcount + 2) { + /* + * All vmas have already been torn down, so it's + * a good bet that actually the page is unmapped, + * and we'd prefer not to leak it: if we're wrong, + * some other bad page check should catch it later. + */ + page_mapcount_reset(page); + atomic_sub(mapcount, &page->_count); + } + } + page_cache_tree_delete(mapping, page, shadow); page->mapping = NULL; @@ -205,7 +229,6 @@ void __delete_from_page_cache(struct page *page, void *shadow, __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __dec_zone_page_state(page, NR_SHMEM); - VM_BUG_ON_PAGE(page_mapped(page), page); /* * At this point page must be either written or cleaned by truncate. diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 01f2b48c8618a..aefba5a9cc47f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2751,7 +2751,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, int ret; if (!hugepages_supported()) - return -ENOTSUPP; + return -EOPNOTSUPP; table->data = &tmp; table->maxlen = sizeof(unsigned long); @@ -2792,7 +2792,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, int ret; if (!hugepages_supported()) - return -ENOTSUPP; + return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; @@ -3502,7 +3502,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, * COW. Warn that such a situation has occurred as it may not be obvious */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { - pr_warning("PID %d killed due to inadequate hugepage pool\n", + pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); return ret; } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index bc0a8d8b8f42f..1ad20ade8c913 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -60,6 +61,25 @@ void kasan_unpoison_shadow(const void *address, size_t size) } } +static void __kasan_unpoison_stack(struct task_struct *task, void *sp) +{ + void *base = task_stack_page(task); + size_t size = sp - base; + + kasan_unpoison_shadow(base, size); +} + +/* Unpoison the entire stack for a task. */ +void kasan_unpoison_task_stack(struct task_struct *task) +{ + __kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE); +} + +/* Unpoison the stack for the current task beyond a watermark sp value. */ +asmlinkage void kasan_unpoison_remaining_stack(void *sp) +{ + __kasan_unpoison_stack(current, sp); +} /* * All functions below always inlined so compiler could diff --git a/mm/memory.c b/mm/memory.c index 8132787ae4d50..906d8e3b42c00 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1550,9 +1550,30 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, */ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) +{ + return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_pfn); + +/** + * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * @pgprot: pgprot flags for the inserted page + * + * This is exactly like vm_insert_pfn, except that it allows drivers to + * to override pgprot on a per-page basis. + * + * This only makes sense for IO mappings, and it makes no sense for + * cow mappings. In general, using multiple vmas is preferable; + * vm_insert_pfn_prot should only be used if using multiple VMAs is + * impractical. + */ +int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot) { int ret; - pgprot_t pgprot = vma->vm_page_prot; /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like @@ -1574,7 +1595,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, return ret; } -EXPORT_SYMBOL(vm_insert_pfn); +EXPORT_SYMBOL(vm_insert_pfn_prot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 4af58a3a8ffa3..979b18cbd343e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -138,7 +138,7 @@ static struct resource *register_memory_resource(u64 start, u64 size) res->name = "System RAM"; res->start = start; res->end = start + size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; if (request_resource(&iomem_resource, res) < 0) { pr_debug("System RAM resource %pR cannot be added\n", res); kfree(res); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4c4187c0e1dee..9a3f6b90e6283 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -532,7 +532,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, nid = page_to_nid(page); if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT)) continue; - if (PageTail(page) && PageAnon(page)) { + if (PageTransCompound(page) && PageAnon(page)) { get_page(page); pte_unmap_unlock(pte, ptl); lock_page(page); diff --git a/mm/mempool.c b/mm/mempool.c index 004d42b1dfaf9..7924f4f58a6d4 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -135,8 +135,8 @@ static void *remove_element(mempool_t *pool) void *element = pool->elements[--pool->curr_nr]; BUG_ON(pool->curr_nr < 0); - check_element(pool, element); kasan_unpoison_element(pool, element); + check_element(pool, element); return element; } diff --git a/mm/mmap.c b/mm/mmap.c index 76d1ec29149bf..90e3b869a8b9d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3066,11 +3066,16 @@ static int special_mapping_fault(struct vm_area_struct *vma, pgoff_t pgoff; struct page **pages; - if (vma->vm_ops == &legacy_special_mapping_vmops) + if (vma->vm_ops == &legacy_special_mapping_vmops) { pages = vma->vm_private_data; - else - pages = ((struct vm_special_mapping *)vma->vm_private_data)-> - pages; + } else { + struct vm_special_mapping *sm = vma->vm_private_data; + + if (sm->fault) + return sm->fault(sm, vma, vmf); + + pages = sm->pages; + } for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 82e3e97050173..dcea4f4c62b3b 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -723,6 +723,8 @@ int br_fdb_dump(struct sk_buff *skb, struct net_bridge_fdb_entry *f; hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { + int err; + if (idx < cb->args[0]) goto skip; @@ -741,12 +743,15 @@ int br_fdb_dump(struct sk_buff *skb, if (!filter_dev && f->dst) goto skip; - if (fdb_fill_info(skb, br, f, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, - NLM_F_MULTI) < 0) + err = fdb_fill_info(skb, br, f, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI); + if (err < 0) { + cb->args[1] = err; break; + } skip: ++idx; } diff --git a/net/core/filter.c b/net/core/filter.c index 94d26201080d6..bba502f7cd575 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1752,7 +1752,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; - if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6))) + if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { @@ -1776,7 +1776,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info = &md->u.tun_info; info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY; + info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM; info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; @@ -1787,6 +1787,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) sizeof(from->remote_ipv6)); } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); + if (flags & BPF_F_ZERO_CSUM_TX) + info->key.tun_flags &= ~TUNNEL_CSUM; } return 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d735e854f9160..8261d95dd8466 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2911,6 +2911,7 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb, nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); out: netif_addr_unlock_bh(dev); + cb->args[1] = err; return idx; } EXPORT_SYMBOL(ndo_dflt_fdb_dump); @@ -2944,6 +2945,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) ops = br_dev->netdev_ops; } + cb->args[1] = 0; for_each_netdev(net, dev) { if (brport_idx && (dev->ifindex != brport_idx)) continue; @@ -2971,12 +2973,16 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, idx); } + if (cb->args[1] == -EMSGSIZE) + break; if (dev->netdev_ops->ndo_fdb_dump) idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, idx); else idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + if (cb->args[1] == -EMSGSIZE) + break; cops = NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5bf88f58bee74..8616d1147c938 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2947,6 +2947,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } EXPORT_SYMBOL_GPL(skb_append_pagefrags); +/** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update @@ -4084,9 +4102,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, if (!pskb_may_pull(skb_chk, offset)) goto err; - __skb_pull(skb_chk, offset); + skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); - __skb_push(skb_chk, offset); + skb_push_rcsum(skb_chk, offset); if (ret) goto err; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 05e4cba14162f..b3086cf270275 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 64878efa045c1..565bf64b2b7d6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1236,13 +1236,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (!skb) return -EINVAL; - cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { + if (skb->ip_summed != CHECKSUM_PARTIAL) + return -EOPNOTSUPP; + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } + cork->length += size; while (size > 0) { if (skb_is_gso(skb)) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 89e8861e05fcb..336e6892a93ce 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -661,6 +661,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -758,7 +760,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c8cbc2b4b7921..a726d7853ce53 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -550,7 +550,7 @@ void tcp_init_metrics(struct sock *sk) */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 75632a9258242..9b02af2139d3d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -455,7 +455,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 0; + newtp->segs_in = 1; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -815,6 +815,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 0ec08814f37d9..96599d1a13184 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -89,6 +89,8 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 5c5d23e59da59..9508a20fbf614 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, *fragoff = _frag_off; return hp->nexthdr; } - return -ENOENT; + if (!found) + return -ENOENT; + if (fragoff) + *fragoff = _frag_off; + break; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a69aad1e29d1e..c0d4dc1c5ea4c 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -777,6 +777,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) __u32 mtu; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 137fca42aaa6b..6c5dfec7a3779 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1180,6 +1180,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ee56d0a8699e..d64ee7e836649 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) return NULL; skb->priority = TC_PRIO_CONTROL; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* : diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 22e28a44e3c88..422dd014aa2ce 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -962,11 +962,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ + /* a return value > 0 means to resubmit the input */ if (ret > 0) - return -ret; + return ret; return 0; } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 10ad4ac1fa0ba..367784be5df20 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -291,7 +291,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } /* prepare A-MPDU MLME for Rx aggregation */ - tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); + tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL); if (!tid_agg_rx) goto end; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b84f6aa32c083..f006f4a44c0e6 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -92,7 +92,7 @@ struct ieee80211_fragment_entry { u16 extra_len; u16 last_frag; u8 rx_queue; - bool ccmp; /* Whether fragments were encrypted with CCMP */ + bool check_sequential_pn; /* needed for CCMP/GCMP */ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ }; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 3ece7d1034c81..b54f398cda5d0 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta) * computing cur_tp */ tmp_mrs = &mi->r[idx].stats; - tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma); + tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10; tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; return tmp_cur_tp; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 3928dbd24e257..370d677b547b2 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -414,15 +414,16 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) (max_tp_group != MINSTREL_CCK_GROUP)) return; + max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; + max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; + if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) { cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, mrs->prob_ewma); if (cur_tp_avg > tmp_tp_avg) mi->max_prob_rate = index; - max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; - max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; - max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, max_gpr_idx, max_gpr_prob); @@ -431,7 +432,7 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) } else { if (mrs->prob_ewma > tmp_prob) mi->max_prob_rate = index; - if (mrs->prob_ewma > mg->rates[mg->max_group_prob_rate].prob_ewma) + if (mrs->prob_ewma > max_gpr_prob) mg->max_group_prob_rate = index; } } @@ -691,7 +692,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (likely(sta->ampdu_mlme.tid_tx[tid])) return; - ieee80211_start_tx_ba_session(pubsta, tid, 5000); + ieee80211_start_tx_ba_session(pubsta, tid, 0); } static void @@ -871,7 +872,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, * - if station is in dynamic SMPS (and streams > 1) * - for fallback rates, to increase chances of getting through */ - if (offset > 0 && + if (offset > 0 || (mi->sta->smps_mode == IEEE80211_SMPS_DYNAMIC && group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; @@ -1334,7 +1335,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) prob = mi->groups[i].rates[j].prob_ewma; /* convert tp_avg from pkt per second in kbps */ - tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024; + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; + tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bc081850ac0e5..60d093f40f1d1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1753,7 +1753,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, entry->seq = seq; entry->rx_queue = rx_queue; entry->last_frag = frag; - entry->ccmp = 0; + entry->check_sequential_pn = false; entry->extra_len = 0; return entry; @@ -1849,15 +1849,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) rx->seqno_idx, &(rx->skb)); if (rx->key && (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) && + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && ieee80211_has_protected(fc)) { int queue = rx->security_idx; - /* Store CCMP PN so that we can verify that the next - * fragment has a sequential PN value. */ - entry->ccmp = 1; + + /* Store CCMP/GCMP PN so that we can verify that the + * next fragment has a sequential PN value. + */ + entry->check_sequential_pn = true; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); + BUILD_BUG_ON(offsetof(struct ieee80211_key, + u.ccmp.rx_pn) != + offsetof(struct ieee80211_key, + u.gcmp.rx_pn)); + BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) != + sizeof(rx->key->u.gcmp.rx_pn[queue])); + BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != + IEEE80211_GCMP_PN_LEN); } return RX_QUEUED; } @@ -1872,15 +1884,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* Verify that MPDUs within one MSDU have sequential PN values. - * (IEEE 802.11i, 8.3.3.4.5) */ - if (entry->ccmp) { + /* "The receiver shall discard MSDUs and MMPDUs whose constituent + * MPDU PN values are not incrementing in steps of 1." + * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP) + * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP) + */ + if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; int queue; + if (!rx->key || (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256)) + rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) return RX_DROP_UNUSABLE; memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { @@ -3366,6 +3384,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) return false; /* ignore action frames to TDLS-peers */ if (ieee80211_is_action(hdr->frame_control) && + !is_broadcast_ether_addr(bssid) && !ether_addr_equal(bssid, hdr->addr1)) return false; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d05869646515d..6b70399ab7812 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -62,6 +62,7 @@ static void ipt_destroy_target(struct xt_entry_target *t) struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, + .family = NFPROTO_IPV4, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -195,6 +196,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, par.hooknum = ipt->tcfi_hook; par.target = ipt->tcfi_t->u.kernel.target; par.targinfo = ipt->tcfi_t->data; + par.family = NFPROTO_IPV4; ret = par.target->target(skb, &par); switch (ret) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ec529121f38a0..ce46f1c7f133a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, } return 0; } + if (addr1->v6.sin6_port != addr2->v6.sin6_port) + return 0; if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ diff --git a/net/sctp/proc.c b/net/sctp/proc.c index ded7d931a6a5b..963dffcc2618b 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -482,7 +482,7 @@ static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v) static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) { struct sctp_association *assoc; - struct sctp_transport *tsp; + struct sctp_transport *transport, *tsp; if (v == SEQ_START_TOKEN) { seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " @@ -490,10 +490,10 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) return 0; } - tsp = (struct sctp_transport *)v; - if (!sctp_transport_hold(tsp)) + transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) return 0; - assoc = tsp->asoc; + assoc = transport->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { @@ -546,7 +546,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } - sctp_transport_put(tsp); + sctp_transport_put(transport); return 0; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 47f7da58a7f0e..8b5833c1ff2e8 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1093,8 +1093,11 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .cb = cb, .idx = idx, }; + int err; - switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb); + err = switchdev_port_obj_dump(dev, &dump.fdb.obj, + switchdev_port_fdb_dump_cb); + cb->args[1] = err; return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 69c29050f14ab..4d420bb273960 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -673,7 +673,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct iov_iter save = msg->msg_iter; uint mtu; int rc; @@ -687,14 +687,16 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, msg_set_nameupper(mhdr, seq->upper); msg_set_hdr_sz(mhdr, MCAST_H_SIZE); + skb_queue_head_init(&pktchain); + new_mtu: mtu = tipc_bcast_get_mtu(net); - rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain); if (unlikely(rc < 0)) return rc; do { - rc = tipc_bcast_xmit(net, pktchain); + rc = tipc_bcast_xmit(net, &pktchain); if (likely(!rc)) return dsz; @@ -704,7 +706,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; @@ -863,7 +865,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; u32 dnode, dport; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct sk_buff *skb; struct tipc_name_seq *seq; struct iov_iter save; @@ -924,17 +926,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) msg_set_hdr_sz(mhdr, BASIC_H_SIZE); } + skb_queue_head_init(&pktchain); save = m->msg_iter; new_mtu: mtu = tipc_node_get_mtu(net, dnode, tsk->portid); - rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain); if (rc < 0) return rc; do { - skb = skb_peek(pktchain); + skb = skb_peek(&pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid); if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; @@ -946,7 +949,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; @@ -1016,7 +1019,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); u32 portid = tsk->portid; int rc = -EINVAL; @@ -1044,17 +1047,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); dnode = tsk_peer_node(tsk); + skb_queue_head_init(&pktchain); next: save = m->msg_iter; mtu = tsk->max_pkt; send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); - rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain); if (unlikely(rc < 0)) return rc; + do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_node_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, &pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1063,7 +1068,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) goto next; } if (rc == -EMSGSIZE) { - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1077,7 +1082,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) rc = tipc_wait_for_sndpkt(sock, &timeo); } while (!rc); - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); return sent ? sent : rc; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 69ee2eeef9688..f9ff73a8d8154 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -296,7 +296,8 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub)) return tipc_conn_terminate(tn->topsrv, subscrb->conid); - tipc_nametbl_subscribe(sub); + if (sub) + tipc_nametbl_subscribe(sub); } /* Handle one request to establish a new subscriber */ diff --git a/net/wireless/core.c b/net/wireless/core.c index b0915515640ef..8f0bac7e03c40 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1147,6 +1147,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, return NOTIFY_DONE; } + wireless_nlevent_flush(); + return NOTIFY_OK; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d4786f2802aa3..711cb7ad6ae01 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7547,7 +7547,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) && no_ht) { - kfree(connkeys); + kzfree(connkeys); return -EINVAL; } } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 8020b5b094d4c..d49ed7666d4cb 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -917,6 +917,12 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); + /* stop critical protocol if supported */ + if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { + rdev->crit_proto_nlportid = 0; + rdev_crit_proto_stop(rdev, wdev); + } + /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c8717c1d082e7..b50ee5d622e14 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -342,6 +342,40 @@ static const int compat_event_type_size[] = { /* IW event code */ +void wireless_nlevent_flush(void) +{ + struct sk_buff *skb; + struct net *net; + + ASSERT_RTNL(); + + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } +} +EXPORT_SYMBOL_GPL(wireless_nlevent_flush); + +static int wext_netdev_notifier_call(struct notifier_block *nb, + unsigned long state, void *ptr) +{ + /* + * When a netdev changes state in any way, flush all pending messages + * to avoid them going out in a strange order, e.g. RTM_NEWLINK after + * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() + * or similar - all of which could otherwise happen due to delays from + * schedule_work(). + */ + wireless_nlevent_flush(); + + return NOTIFY_OK; +} + +static struct notifier_block wext_netdev_notifier = { + .notifier_call = wext_netdev_notifier_call, +}; + static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); @@ -360,7 +394,12 @@ static struct pernet_operations wext_pernet_ops = { static int __init wireless_nlevent_init(void) { - return register_pernet_subsys(&wext_pernet_ops); + int err = register_pernet_subsys(&wext_pernet_ops); + + if (err) + return err; + + return register_netdevice_notifier(&wext_netdev_notifier); } subsys_initcall(wireless_nlevent_init); @@ -368,17 +407,8 @@ subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { - struct sk_buff *skb; - struct net *net; - rtnl_lock(); - - for_each_net(net) { - while ((skb = skb_dequeue(&net->wext_nlevents))) - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, - GFP_KERNEL); - } - + wireless_nlevent_flush(); rtnl_unlock(); } diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 0147c91fa549e..874132b26d23d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -269,7 +269,8 @@ sub hash_show_words { __init_refok| __kprobes| __ref| - __rcu + __rcu| + __private }x; our $InitAttributePrefix = qr{__(?:mem|cpu|dev|net_|)}; our $InitAttributeData = qr{$InitAttributePrefix(?:initdata\b)}; diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh index d154f0877fd80..7bfe9fa1c8dc6 100755 --- a/scripts/ld-version.sh +++ b/scripts/ld-version.sh @@ -1,7 +1,7 @@ #!/usr/bin/awk -f # extract linker version number from stdin and turn into single number { - gsub(".*)", ""); + gsub(".*\\)", ""); gsub(".*version ", ""); gsub("-.*", ""); split($1,a, "."); diff --git a/scripts/sortextable.c b/scripts/sortextable.c index c2423d913b46b..7b29fb14f8702 100644 --- a/scripts/sortextable.c +++ b/scripts/sortextable.c @@ -209,6 +209,35 @@ static int compare_relative_table(const void *a, const void *b) return 0; } +static void x86_sort_relative_table(char *extab_image, int image_size) +{ + int i; + + i = 0; + while (i < image_size) { + uint32_t *loc = (uint32_t *)(extab_image + i); + + w(r(loc) + i, loc); + w(r(loc + 1) + i + 4, loc + 1); + w(r(loc + 2) + i + 8, loc + 2); + + i += sizeof(uint32_t) * 3; + } + + qsort(extab_image, image_size / 12, 12, compare_relative_table); + + i = 0; + while (i < image_size) { + uint32_t *loc = (uint32_t *)(extab_image + i); + + w(r(loc) - i, loc); + w(r(loc + 1) - (i + 4), loc + 1); + w(r(loc + 2) - (i + 8), loc + 2); + + i += sizeof(uint32_t) * 3; + } +} + static void sort_relative_table(char *extab_image, int image_size) { int i; @@ -281,6 +310,9 @@ do_file(char const *const fname) break; case EM_386: case EM_X86_64: + custom_sort = x86_sort_relative_table; + break; + case EM_S390: custom_sort = sort_relative_table; break; diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c index e9b98af6b52c8..e8da3b8ee7213 100644 --- a/sound/arm/pxa2xx-pcm-lib.c +++ b/sound/arm/pxa2xx-pcm-lib.c @@ -141,10 +141,8 @@ int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *vma) { struct snd_pcm_runtime *runtime = substream->runtime; - return dma_mmap_writecombine(substream->pcm->card->dev, vma, - runtime->dma_area, - runtime->dma_addr, - runtime->dma_bytes); + return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area, + runtime->dma_addr, runtime->dma_bytes); } EXPORT_SYMBOL(pxa2xx_pcm_mmap); @@ -156,8 +154,7 @@ int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream) buf->dev.type = SNDRV_DMA_TYPE_DEV; buf->dev.dev = pcm->card->dev; buf->private_data = NULL; - buf->area = dma_alloc_writecombine(pcm->card->dev, size, - &buf->addr, GFP_KERNEL); + buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL); if (!buf->area) return -ENOMEM; buf->bytes = size; @@ -178,8 +175,7 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm) buf = &substream->dma_buffer; if (!buf->area) continue; - dma_free_writecombine(pcm->card->dev, buf->bytes, - buf->area, buf->addr); + dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr); buf->area = NULL; } } diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index b9c0910fb8c4e..0608f216f3592 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -170,6 +170,19 @@ struct snd_ctl_elem_value32 { unsigned char reserved[128]; }; +#ifdef CONFIG_X86_X32 +/* x32 has a different alignment for 64bit values from ia32 */ +struct snd_ctl_elem_value_x32 { + struct snd_ctl_elem_id id; + unsigned int indirect; /* bit-field causes misalignment */ + union { + s32 integer[128]; + unsigned char data[512]; + s64 integer64[64]; + } value; + unsigned char reserved[128]; +}; +#endif /* CONFIG_X86_X32 */ /* get the value type and count of the control */ static int get_ctl_type(struct snd_card *card, struct snd_ctl_elem_id *id, @@ -219,9 +232,11 @@ static int get_elem_size(int type, int count) static int copy_ctl_value_from_user(struct snd_card *card, struct snd_ctl_elem_value *data, - struct snd_ctl_elem_value32 __user *data32, + void __user *userdata, + void __user *valuep, int *typep, int *countp) { + struct snd_ctl_elem_value32 __user *data32 = userdata; int i, type, size; int uninitialized_var(count); unsigned int indirect; @@ -239,8 +254,9 @@ static int copy_ctl_value_from_user(struct snd_card *card, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; - if (get_user(val, &data32->value.integer[i])) + if (get_user(val, &intp[i])) return -EFAULT; data->value.integer.value[i] = val; } @@ -250,8 +266,7 @@ static int copy_ctl_value_from_user(struct snd_card *card, dev_err(card->dev, "snd_ioctl32_ctl_elem_value: unknown type %d\n", type); return -EINVAL; } - if (copy_from_user(data->value.bytes.data, - data32->value.data, size)) + if (copy_from_user(data->value.bytes.data, valuep, size)) return -EFAULT; } @@ -261,7 +276,8 @@ static int copy_ctl_value_from_user(struct snd_card *card, } /* restore the value to 32bit */ -static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, +static int copy_ctl_value_to_user(void __user *userdata, + void __user *valuep, struct snd_ctl_elem_value *data, int type, int count) { @@ -270,22 +286,22 @@ static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; val = data->value.integer.value[i]; - if (put_user(val, &data32->value.integer[i])) + if (put_user(val, &intp[i])) return -EFAULT; } } else { size = get_elem_size(type, count); - if (copy_to_user(data32->value.data, - data->value.bytes.data, size)) + if (copy_to_user(valuep, data->value.bytes.data, size)) return -EFAULT; } return 0; } -static int snd_ctl_elem_read_user_compat(struct snd_card *card, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_read_user(struct snd_card *card, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; int err, type, count; @@ -294,7 +310,9 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -303,14 +321,15 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, err = snd_ctl_elem_read(card, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } -static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_write_user(struct snd_ctl_file *file, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; struct snd_card *card = file->card; @@ -320,7 +339,9 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -329,12 +350,39 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, err = snd_ctl_elem_write(card, file, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } +static int snd_ctl_elem_read_user_compat(struct snd_card *card, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} + +#ifdef CONFIG_X86_X32 +static int snd_ctl_elem_read_user_x32(struct snd_card *card, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_x32(struct snd_ctl_file *file, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} +#endif /* CONFIG_X86_X32 */ + /* add or replace a user control */ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file, struct snd_ctl_elem_info32 __user *data32, @@ -393,6 +441,10 @@ enum { SNDRV_CTL_IOCTL_ELEM_WRITE32 = _IOWR('U', 0x13, struct snd_ctl_elem_value32), SNDRV_CTL_IOCTL_ELEM_ADD32 = _IOWR('U', 0x17, struct snd_ctl_elem_info32), SNDRV_CTL_IOCTL_ELEM_REPLACE32 = _IOWR('U', 0x18, struct snd_ctl_elem_info32), +#ifdef CONFIG_X86_X32 + SNDRV_CTL_IOCTL_ELEM_READ_X32 = _IOWR('U', 0x12, struct snd_ctl_elem_value_x32), + SNDRV_CTL_IOCTL_ELEM_WRITE_X32 = _IOWR('U', 0x13, struct snd_ctl_elem_value_x32), +#endif /* CONFIG_X86_X32 */ }; static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -431,6 +483,12 @@ static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_ctl_elem_add_compat(ctl, argp, 0); case SNDRV_CTL_IOCTL_ELEM_REPLACE32: return snd_ctl_elem_add_compat(ctl, argp, 1); +#ifdef CONFIG_X86_X32 + case SNDRV_CTL_IOCTL_ELEM_READ_X32: + return snd_ctl_elem_read_user_x32(ctl->card, argp); + case SNDRV_CTL_IOCTL_ELEM_WRITE_X32: + return snd_ctl_elem_write_user_x32(ctl, argp); +#endif /* CONFIG_X86_X32 */ } down_read(&snd_ioctl_rwsem); diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 9630e9f72b7ba..1f64ab0c2a95a 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -183,6 +183,14 @@ static int snd_pcm_ioctl_channel_info_compat(struct snd_pcm_substream *substream return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 for snd_pcm_channel_info */ +static int snd_pcm_channel_info_user(struct snd_pcm_substream *substream, + struct snd_pcm_channel_info __user *src); +#define snd_pcm_ioctl_channel_info_x32(s, p) \ + snd_pcm_channel_info_user(s, p) +#endif /* CONFIG_X86_X32 */ + struct snd_pcm_status32 { s32 state; struct compat_timespec trigger_tstamp; @@ -243,6 +251,71 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream, return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_status_x32 { + s32 state; + u32 rsvd; /* alignment */ + struct timespec trigger_tstamp; + struct timespec tstamp; + u32 appl_ptr; + u32 hw_ptr; + s32 delay; + u32 avail; + u32 avail_max; + u32 overrange; + s32 suspended_state; + u32 audio_tstamp_data; + struct timespec audio_tstamp; + struct timespec driver_tstamp; + u32 audio_tstamp_accuracy; + unsigned char reserved[52-2*sizeof(struct timespec)]; +} __packed; + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_pcm_status_user_x32(struct snd_pcm_substream *substream, + struct snd_pcm_status_x32 __user *src, + bool ext) +{ + struct snd_pcm_status status; + int err; + + memset(&status, 0, sizeof(status)); + /* + * with extension, parameters are read/write, + * get audio_tstamp_data from user, + * ignore rest of status structure + */ + if (ext && get_user(status.audio_tstamp_data, + (u32 __user *)(&src->audio_tstamp_data))) + return -EFAULT; + err = snd_pcm_status(substream, &status); + if (err < 0) + return err; + + if (clear_user(src, sizeof(*src))) + return -EFAULT; + if (put_user(status.state, &src->state) || + put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) || + put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.appl_ptr, &src->appl_ptr) || + put_user(status.hw_ptr, &src->hw_ptr) || + put_user(status.delay, &src->delay) || + put_user(status.avail, &src->avail) || + put_user(status.avail_max, &src->avail_max) || + put_user(status.overrange, &src->overrange) || + put_user(status.suspended_state, &src->suspended_state) || + put_user(status.audio_tstamp_data, &src->audio_tstamp_data) || + put_timespec(&status.audio_tstamp, &src->audio_tstamp) || + put_timespec(&status.driver_tstamp, &src->driver_tstamp) || + put_user(status.audio_tstamp_accuracy, &src->audio_tstamp_accuracy)) + return -EFAULT; + + return err; +} +#endif /* CONFIG_X86_X32 */ + /* both for HW_PARAMS and HW_REFINE */ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, int refine, @@ -469,6 +542,93 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_mmap_status_x32 { + s32 state; + s32 pad1; + u32 hw_ptr; + u32 pad2; /* alignment */ + struct timespec tstamp; + s32 suspended_state; + struct timespec audio_tstamp; +} __packed; + +struct snd_pcm_mmap_control_x32 { + u32 appl_ptr; + u32 avail_min; +}; + +struct snd_pcm_sync_ptr_x32 { + u32 flags; + u32 rsvd; /* alignment */ + union { + struct snd_pcm_mmap_status_x32 status; + unsigned char reserved[64]; + } s; + union { + struct snd_pcm_mmap_control_x32 control; + unsigned char reserved[64]; + } c; +} __packed; + +static int snd_pcm_ioctl_sync_ptr_x32(struct snd_pcm_substream *substream, + struct snd_pcm_sync_ptr_x32 __user *src) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + volatile struct snd_pcm_mmap_status *status; + volatile struct snd_pcm_mmap_control *control; + u32 sflags; + struct snd_pcm_mmap_control scontrol; + struct snd_pcm_mmap_status sstatus; + snd_pcm_uframes_t boundary; + int err; + + if (snd_BUG_ON(!runtime)) + return -EINVAL; + + if (get_user(sflags, &src->flags) || + get_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + get_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + if (sflags & SNDRV_PCM_SYNC_PTR_HWSYNC) { + err = snd_pcm_hwsync(substream); + if (err < 0) + return err; + } + status = runtime->status; + control = runtime->control; + boundary = recalculate_boundary(runtime); + if (!boundary) + boundary = 0x7fffffff; + snd_pcm_stream_lock_irq(substream); + /* FIXME: we should consider the boundary for the sync from app */ + if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) + control->appl_ptr = scontrol.appl_ptr; + else + scontrol.appl_ptr = control->appl_ptr % boundary; + if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) + control->avail_min = scontrol.avail_min; + else + scontrol.avail_min = control->avail_min; + sstatus.state = status->state; + sstatus.hw_ptr = status->hw_ptr % boundary; + sstatus.tstamp = status->tstamp; + sstatus.suspended_state = status->suspended_state; + sstatus.audio_tstamp = status->audio_tstamp; + snd_pcm_stream_unlock_irq(substream); + if (put_user(sstatus.state, &src->s.status.state) || + put_user(sstatus.hw_ptr, &src->s.status.hw_ptr) || + put_timespec(&sstatus.tstamp, &src->s.status.tstamp) || + put_user(sstatus.suspended_state, &src->s.status.suspended_state) || + put_timespec(&sstatus.audio_tstamp, &src->s.status.audio_tstamp) || + put_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + put_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ /* */ @@ -487,7 +647,12 @@ enum { SNDRV_PCM_IOCTL_WRITEN_FRAMES32 = _IOW('A', 0x52, struct snd_xfern32), SNDRV_PCM_IOCTL_READN_FRAMES32 = _IOR('A', 0x53, struct snd_xfern32), SNDRV_PCM_IOCTL_SYNC_PTR32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr32), - +#ifdef CONFIG_X86_X32 + SNDRV_PCM_IOCTL_CHANNEL_INFO_X32 = _IOR('A', 0x32, struct snd_pcm_channel_info), + SNDRV_PCM_IOCTL_STATUS_X32 = _IOR('A', 0x20, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_STATUS_EXT_X32 = _IOWR('A', 0x24, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_SYNC_PTR_X32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -559,6 +724,16 @@ static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned l return snd_pcm_ioctl_rewind_compat(substream, argp); case SNDRV_PCM_IOCTL_FORWARD32: return snd_pcm_ioctl_forward_compat(substream, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_PCM_IOCTL_STATUS_X32: + return snd_pcm_status_user_x32(substream, argp, false); + case SNDRV_PCM_IOCTL_STATUS_EXT_X32: + return snd_pcm_status_user_x32(substream, argp, true); + case SNDRV_PCM_IOCTL_SYNC_PTR_X32: + return snd_pcm_ioctl_sync_ptr_x32(substream, argp); + case SNDRV_PCM_IOCTL_CHANNEL_INFO_X32: + return snd_pcm_ioctl_channel_info_x32(substream, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c index 5268c1f58c25b..f69764d7cdd70 100644 --- a/sound/core/rawmidi_compat.c +++ b/sound/core/rawmidi_compat.c @@ -85,8 +85,7 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile, if (err < 0) return err; - if (put_user(status.tstamp.tv_sec, &src->tstamp.tv_sec) || - put_user(status.tstamp.tv_nsec, &src->tstamp.tv_nsec) || + if (compat_put_timespec(&status.tstamp, &src->tstamp) || put_user(status.avail, &src->avail) || put_user(status.xruns, &src->xruns)) return -EFAULT; @@ -94,9 +93,58 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_rawmidi_status_x32 { + s32 stream; + u32 rsvd; /* alignment */ + struct timespec tstamp; + u32 avail; + u32 xruns; + unsigned char reserved[16]; +} __attribute__((packed)); + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile, + struct snd_rawmidi_status_x32 __user *src) +{ + int err; + struct snd_rawmidi_status status; + + if (rfile->output == NULL) + return -EINVAL; + if (get_user(status.stream, &src->stream)) + return -EFAULT; + + switch (status.stream) { + case SNDRV_RAWMIDI_STREAM_OUTPUT: + err = snd_rawmidi_output_status(rfile->output, &status); + break; + case SNDRV_RAWMIDI_STREAM_INPUT: + err = snd_rawmidi_input_status(rfile->input, &status); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + if (put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.avail, &src->avail) || + put_user(status.xruns, &src->xruns)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ + enum { SNDRV_RAWMIDI_IOCTL_PARAMS32 = _IOWR('W', 0x10, struct snd_rawmidi_params32), SNDRV_RAWMIDI_IOCTL_STATUS32 = _IOWR('W', 0x20, struct snd_rawmidi_status32), +#ifdef CONFIG_X86_X32 + SNDRV_RAWMIDI_IOCTL_STATUS_X32 = _IOWR('W', 0x20, struct snd_rawmidi_status_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -115,6 +163,10 @@ static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsign return snd_rawmidi_ioctl_params_compat(rfile, argp); case SNDRV_RAWMIDI_IOCTL_STATUS32: return snd_rawmidi_ioctl_status_compat(rfile, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_RAWMIDI_IOCTL_STATUS_X32: + return snd_rawmidi_ioctl_status_x32(rfile, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c index 8db156b207f18..8cdf489df80e0 100644 --- a/sound/core/seq/oss/seq_oss.c +++ b/sound/core/seq/oss/seq_oss.c @@ -149,8 +149,6 @@ odev_release(struct inode *inode, struct file *file) if ((dp = file->private_data) == NULL) return 0; - snd_seq_oss_drain_write(dp); - mutex_lock(®ister_mutex); snd_seq_oss_release(dp); mutex_unlock(®ister_mutex); diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h index b43924325249c..d7b4d016b5475 100644 --- a/sound/core/seq/oss/seq_oss_device.h +++ b/sound/core/seq/oss/seq_oss_device.h @@ -127,7 +127,6 @@ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int co unsigned int snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait); void snd_seq_oss_reset(struct seq_oss_devinfo *dp); -void snd_seq_oss_drain_write(struct seq_oss_devinfo *dp); /* */ void snd_seq_oss_process_queue(struct seq_oss_devinfo *dp, abstime_t time); diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index 6779e82b46dd7..92c96a95a903a 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -435,22 +435,6 @@ snd_seq_oss_release(struct seq_oss_devinfo *dp) } -/* - * Wait until the queue is empty (if we don't have nonblock) - */ -void -snd_seq_oss_drain_write(struct seq_oss_devinfo *dp) -{ - if (! dp->timer->running) - return; - if (is_write_mode(dp->file_mode) && !is_nonblock_mode(dp->file_mode) && - dp->writeq) { - while (snd_seq_oss_writeq_sync(dp->writeq)) - ; - } -} - - /* * reset sequencer devices */ diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c index e05802ae6e1b1..2e908225d754c 100644 --- a/sound/core/timer_compat.c +++ b/sound/core/timer_compat.c @@ -70,13 +70,14 @@ static int snd_timer_user_status_compat(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; - struct snd_timer_status status; + struct snd_timer_status32 status; tu = file->private_data; if (snd_BUG_ON(!tu->timeri)) return -ENXIO; memset(&status, 0, sizeof(status)); - status.tstamp = tu->tstamp; + status.tstamp.tv_sec = tu->tstamp.tv_sec; + status.tstamp.tv_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; @@ -88,12 +89,21 @@ static int snd_timer_user_status_compat(struct file *file, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 */ +#define snd_timer_user_status_x32(file, s) \ + snd_timer_user_status(file, s) +#endif /* CONFIG_X86_X32 */ + /* */ enum { SNDRV_TIMER_IOCTL_INFO32 = _IOR('T', 0x11, struct snd_timer_info32), SNDRV_TIMER_IOCTL_STATUS32 = _IOW('T', 0x14, struct snd_timer_status32), +#ifdef CONFIG_X86_X32 + SNDRV_TIMER_IOCTL_STATUS_X32 = _IOW('T', 0x14, struct snd_timer_status), +#endif /* CONFIG_X86_X32 */ }; static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -122,6 +132,10 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_timer_user_info_compat(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status_compat(file, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_TIMER_IOCTL_STATUS_X32: + return snd_timer_user_status_x32(file, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 8ee78dbd4c605..bcbc4ee10130a 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2477,13 +2477,6 @@ static int patch_generic_hdmi(struct hda_codec *codec) is_broxton(codec)) codec->core.link_power_control = 1; - if (codec_has_acomp(codec)) { - codec->depop_delay = 0; - spec->i915_audio_ops.audio_ptr = codec; - spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; - snd_hdac_i915_register_notifier(&spec->i915_audio_ops); - } - if (hdmi_parse_codec(codec) < 0) { if (spec->i915_bound) snd_hdac_i915_exit(&codec->bus->core); @@ -2505,6 +2498,18 @@ static int patch_generic_hdmi(struct hda_codec *codec) init_channel_allocations(); + if (codec_has_acomp(codec)) { + codec->depop_delay = 0; + spec->i915_audio_ops.audio_ptr = codec; + /* intel_audio_codec_enable() or intel_audio_codec_disable() + * will call pin_eld_notify with using audio_ptr pointer + * We need make sure audio_ptr is really setup + */ + wmb(); + spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; + snd_hdac_i915_register_notifier(&spec->i915_audio_ops); + } + return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1f357cd72d9c3..93d2156b62410 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5412,6 +5412,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK), SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK), + SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK), diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 2875b4f6d8c9e..7c8941b8b2def 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -2879,7 +2879,7 @@ static int snd_hdsp_get_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl { struct hdsp *hdsp = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdsp_dds_offset(hdsp); + ucontrol->value.integer.value[0] = hdsp_dds_offset(hdsp); return 0; } @@ -2891,7 +2891,7 @@ static int snd_hdsp_put_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl if (!snd_hdsp_use_is_exclusive(hdsp)) return -EBUSY; - val = ucontrol->value.enumerated.item[0]; + val = ucontrol->value.integer.value[0]; spin_lock_irq(&hdsp->lock); if (val != hdsp_dds_offset(hdsp)) change = (hdsp_set_dds_offset(hdsp, val) == 0) ? 1 : 0; diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index 8bc8016c173d6..a4a999a0317ea 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -1601,6 +1601,9 @@ static void hdspm_set_dds_value(struct hdspm *hdspm, int rate) { u64 n; + if (snd_BUG_ON(rate <= 0)) + return; + if (rate >= 112000) rate /= 4; else if (rate >= 56000) @@ -2215,6 +2218,8 @@ static int hdspm_get_system_sample_rate(struct hdspm *hdspm) } else { /* slave mode, return external sample rate */ rate = hdspm_external_sample_rate(hdspm); + if (!rate) + rate = hdspm->system_sample_rate; } } @@ -2260,8 +2265,11 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol, ucontrol) { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); + int rate = ucontrol->value.integer.value[0]; - hdspm_set_dds_value(hdspm, ucontrol->value.enumerated.item[0]); + if (rate < 27000 || rate > 207000) + return -EINVAL; + hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]); return 0; } @@ -4449,7 +4457,7 @@ static int snd_hdspm_get_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdspm->tco->term; + ucontrol->value.integer.value[0] = hdspm->tco->term; return 0; } @@ -4460,8 +4468,8 @@ static int snd_hdspm_put_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - if (hdspm->tco->term != ucontrol->value.enumerated.item[0]) { - hdspm->tco->term = ucontrol->value.enumerated.item[0]; + if (hdspm->tco->term != ucontrol->value.integer.value[0]) { + hdspm->tco->term = ucontrol->value.integer.value[0]; hdspm_tco_write(hdspm); diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c index affb192238a40..faae6936bae4f 100644 --- a/sound/soc/codecs/ab8500-codec.c +++ b/sound/soc/codecs/ab8500-codec.c @@ -1130,7 +1130,7 @@ static int sid_status_control_get(struct snd_kcontrol *kcontrol, struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev); mutex_lock(&drvdata->ctrl_lock); - ucontrol->value.integer.value[0] = drvdata->sid_status; + ucontrol->value.enumerated.item[0] = drvdata->sid_status; mutex_unlock(&drvdata->ctrl_lock); return 0; @@ -1147,7 +1147,7 @@ static int sid_status_control_put(struct snd_kcontrol *kcontrol, dev_dbg(codec->dev, "%s: Enter\n", __func__); - if (ucontrol->value.integer.value[0] != SID_APPLY_FIR) { + if (ucontrol->value.enumerated.item[0] != SID_APPLY_FIR) { dev_err(codec->dev, "%s: ERROR: This control supports '%s' only!\n", __func__, enum_sid_state[SID_APPLY_FIR]); @@ -1199,7 +1199,7 @@ static int anc_status_control_get(struct snd_kcontrol *kcontrol, struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev); mutex_lock(&drvdata->ctrl_lock); - ucontrol->value.integer.value[0] = drvdata->anc_status; + ucontrol->value.enumerated.item[0] = drvdata->anc_status; mutex_unlock(&drvdata->ctrl_lock); return 0; @@ -1220,7 +1220,7 @@ static int anc_status_control_put(struct snd_kcontrol *kcontrol, mutex_lock(&drvdata->ctrl_lock); - req = ucontrol->value.integer.value[0]; + req = ucontrol->value.enumerated.item[0]; if (req >= ARRAY_SIZE(enum_anc_state)) { status = -EINVAL; goto cleanup; diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h index e13583e6ff56a..5ae87a084d97e 100644 --- a/sound/soc/codecs/adau17x1.h +++ b/sound/soc/codecs/adau17x1.h @@ -103,9 +103,9 @@ bool adau17x1_has_dsp(struct adau *adau); #define ADAU17X1_CLOCK_CONTROL_CORECLK_SRC_PLL BIT(3) #define ADAU17X1_CLOCK_CONTROL_SYSCLK_EN BIT(0) -#define ADAU17X1_SERIAL_PORT1_BCLK32 (0x0 << 5) -#define ADAU17X1_SERIAL_PORT1_BCLK48 (0x1 << 5) -#define ADAU17X1_SERIAL_PORT1_BCLK64 (0x2 << 5) +#define ADAU17X1_SERIAL_PORT1_BCLK64 (0x0 << 5) +#define ADAU17X1_SERIAL_PORT1_BCLK32 (0x1 << 5) +#define ADAU17X1_SERIAL_PORT1_BCLK48 (0x2 << 5) #define ADAU17X1_SERIAL_PORT1_BCLK128 (0x3 << 5) #define ADAU17X1_SERIAL_PORT1_BCLK256 (0x4 << 5) #define ADAU17X1_SERIAL_PORT1_BCLK_MASK (0x7 << 5) diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c index b3951524339f9..35488f14e2378 100644 --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -60,15 +60,15 @@ static int cs42l51_get_chan_mix(struct snd_kcontrol *kcontrol, switch (value) { default: case 0: - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; break; /* same value : (L+R)/2 and (R+L)/2 */ case 1: case 2: - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; break; case 3: - ucontrol->value.integer.value[0] = 2; + ucontrol->value.enumerated.item[0] = 2; break; } @@ -85,7 +85,7 @@ static int cs42l51_set_chan_mix(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); unsigned char val; - switch (ucontrol->value.integer.value[0]) { + switch (ucontrol->value.enumerated.item[0]) { default: case 0: val = CHAN_MIX_NORMAL; diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c index 1d5a89c5164b8..461506a4ca6a2 100644 --- a/sound/soc/codecs/da732x.c +++ b/sound/soc/codecs/da732x.c @@ -334,7 +334,7 @@ static int da732x_hpf_set(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct soc_enum *enum_ctrl = (struct soc_enum *)kcontrol->private_value; unsigned int reg = enum_ctrl->reg; - unsigned int sel = ucontrol->value.integer.value[0]; + unsigned int sel = ucontrol->value.enumerated.item[0]; unsigned int bits; switch (sel) { @@ -368,13 +368,13 @@ static int da732x_hpf_get(struct snd_kcontrol *kcontrol, switch (val) { case DA732X_HPF_VOICE_EN: - ucontrol->value.integer.value[0] = DA732X_HPF_VOICE; + ucontrol->value.enumerated.item[0] = DA732X_HPF_VOICE; break; case DA732X_HPF_MUSIC_EN: - ucontrol->value.integer.value[0] = DA732X_HPF_MUSIC; + ucontrol->value.enumerated.item[0] = DA732X_HPF_MUSIC; break; default: - ucontrol->value.integer.value[0] = DA732X_HPF_DISABLED; + ucontrol->value.enumerated.item[0] = DA732X_HPF_DISABLED; break; } diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c index 20dcc496d39c9..fc22804cabc59 100644 --- a/sound/soc/codecs/max98088.c +++ b/sound/soc/codecs/max98088.c @@ -1496,7 +1496,7 @@ static int max98088_put_eq_enum(struct snd_kcontrol *kcontrol, struct max98088_pdata *pdata = max98088->pdata; int channel = max98088_get_channel(codec, kcontrol->id.name); struct max98088_cdata *cdata; - int sel = ucontrol->value.integer.value[0]; + int sel = ucontrol->value.enumerated.item[0]; if (channel < 0) return channel; diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c index 1fedac50355e9..3577003f39cf8 100644 --- a/sound/soc/codecs/max98095.c +++ b/sound/soc/codecs/max98095.c @@ -1499,7 +1499,7 @@ static int max98095_put_eq_enum(struct snd_kcontrol *kcontrol, struct max98095_pdata *pdata = max98095->pdata; int channel = max98095_get_eq_channel(kcontrol->id.name); struct max98095_cdata *cdata; - unsigned int sel = ucontrol->value.integer.value[0]; + unsigned int sel = ucontrol->value.enumerated.item[0]; struct max98095_eq_cfg *coef_set; int fs, best, best_val, i; int regmask, regsave; @@ -1653,7 +1653,7 @@ static int max98095_put_bq_enum(struct snd_kcontrol *kcontrol, struct max98095_pdata *pdata = max98095->pdata; int channel = max98095_get_bq_channel(codec, kcontrol->id.name); struct max98095_cdata *cdata; - unsigned int sel = ucontrol->value.integer.value[0]; + unsigned int sel = ucontrol->value.enumerated.item[0]; struct max98095_biquad_cfg *coef_set; int fs, best, best_val, i; int regmask, regsave; diff --git a/sound/soc/codecs/tlv320dac33.c b/sound/soc/codecs/tlv320dac33.c index 781398fb28415..f7a6ce7e5fb12 100644 --- a/sound/soc/codecs/tlv320dac33.c +++ b/sound/soc/codecs/tlv320dac33.c @@ -446,7 +446,7 @@ static int dac33_get_fifo_mode(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct tlv320dac33_priv *dac33 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = dac33->fifo_mode; + ucontrol->value.enumerated.item[0] = dac33->fifo_mode; return 0; } @@ -458,17 +458,16 @@ static int dac33_set_fifo_mode(struct snd_kcontrol *kcontrol, struct tlv320dac33_priv *dac33 = snd_soc_codec_get_drvdata(codec); int ret = 0; - if (dac33->fifo_mode == ucontrol->value.integer.value[0]) + if (dac33->fifo_mode == ucontrol->value.enumerated.item[0]) return 0; /* Do not allow changes while stream is running*/ if (snd_soc_codec_is_active(codec)) return -EPERM; - if (ucontrol->value.integer.value[0] < 0 || - ucontrol->value.integer.value[0] >= DAC33_FIFO_LAST_MODE) + if (ucontrol->value.enumerated.item[0] >= DAC33_FIFO_LAST_MODE) ret = -EINVAL; else - dac33->fifo_mode = ucontrol->value.integer.value[0]; + dac33->fifo_mode = ucontrol->value.enumerated.item[0]; return ret; } diff --git a/sound/soc/codecs/wl1273.c b/sound/soc/codecs/wl1273.c index 7693c1129babf..1b79778098d29 100644 --- a/sound/soc/codecs/wl1273.c +++ b/sound/soc/codecs/wl1273.c @@ -175,7 +175,7 @@ static int snd_wl1273_get_audio_route(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wl1273_priv *wl1273 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = wl1273->mode; + ucontrol->value.enumerated.item[0] = wl1273->mode; return 0; } @@ -193,18 +193,17 @@ static int snd_wl1273_set_audio_route(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wl1273_priv *wl1273 = snd_soc_codec_get_drvdata(codec); - if (wl1273->mode == ucontrol->value.integer.value[0]) + if (wl1273->mode == ucontrol->value.enumerated.item[0]) return 0; /* Do not allow changes while stream is running */ if (snd_soc_codec_is_active(codec)) return -EPERM; - if (ucontrol->value.integer.value[0] < 0 || - ucontrol->value.integer.value[0] >= ARRAY_SIZE(wl1273_audio_route)) + if (ucontrol->value.enumerated.item[0] >= ARRAY_SIZE(wl1273_audio_route)) return -EINVAL; - wl1273->mode = ucontrol->value.integer.value[0]; + wl1273->mode = ucontrol->value.enumerated.item[0]; return 1; } @@ -219,7 +218,7 @@ static int snd_wl1273_fm_audio_get(struct snd_kcontrol *kcontrol, dev_dbg(codec->dev, "%s: enter.\n", __func__); - ucontrol->value.integer.value[0] = wl1273->core->audio_mode; + ucontrol->value.enumerated.item[0] = wl1273->core->audio_mode; return 0; } @@ -233,7 +232,7 @@ static int snd_wl1273_fm_audio_put(struct snd_kcontrol *kcontrol, dev_dbg(codec->dev, "%s: enter.\n", __func__); - val = ucontrol->value.integer.value[0]; + val = ucontrol->value.enumerated.item[0]; if (wl1273->core->audio_mode == val) return 0; diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c index 61299ca372ffc..6f1024f48b193 100644 --- a/sound/soc/codecs/wm8753.c +++ b/sound/soc/codecs/wm8753.c @@ -233,7 +233,7 @@ static int wm8753_get_dai(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = wm8753->dai_func; + ucontrol->value.enumerated.item[0] = wm8753->dai_func; return 0; } @@ -244,7 +244,7 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol, struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec); u16 ioctl; - if (wm8753->dai_func == ucontrol->value.integer.value[0]) + if (wm8753->dai_func == ucontrol->value.enumerated.item[0]) return 0; if (snd_soc_codec_is_active(codec)) @@ -252,7 +252,7 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol, ioctl = snd_soc_read(codec, WM8753_IOCTL); - wm8753->dai_func = ucontrol->value.integer.value[0]; + wm8753->dai_func = ucontrol->value.enumerated.item[0]; if (((ioctl >> 2) & 0x3) == wm8753->dai_func) return 1; diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 8172e499e6ed1..edd7a77091942 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -396,7 +396,7 @@ static int wm8904_put_drc_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); struct wm8904_pdata *pdata = wm8904->pdata; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (value >= pdata->num_drc_cfgs) return -EINVAL; @@ -467,7 +467,7 @@ static int wm8904_put_retune_mobile_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec); struct wm8904_pdata *pdata = wm8904->pdata; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (value >= pdata->num_retune_mobile_cfgs) return -EINVAL; diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index c799cca5abeb7..6b864c0fc2b67 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -459,7 +459,7 @@ static int wm8958_put_mbc_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -549,7 +549,7 @@ static int wm8958_put_vss_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -582,7 +582,7 @@ static int wm8958_put_vss_hpf_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ @@ -749,7 +749,7 @@ static int wm8958_put_enh_eq_enum(struct snd_kcontrol *kcontrol, struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol); struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); struct wm8994 *control = wm8994->wm8994; - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; int reg; /* Don't allow on the fly reconfiguration */ diff --git a/sound/soc/codecs/wm8983.c b/sound/soc/codecs/wm8983.c index 7350ff654bbf3..0c002a5712cb4 100644 --- a/sound/soc/codecs/wm8983.c +++ b/sound/soc/codecs/wm8983.c @@ -497,9 +497,9 @@ static int eqmode_get(struct snd_kcontrol *kcontrol, reg = snd_soc_read(codec, WM8983_EQ1_LOW_SHELF); if (reg & WM8983_EQ3DMODE) - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; return 0; } @@ -511,18 +511,18 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, unsigned int regpwr2, regpwr3; unsigned int reg_eq; - if (ucontrol->value.integer.value[0] != 0 - && ucontrol->value.integer.value[0] != 1) + if (ucontrol->value.enumerated.item[0] != 0 + && ucontrol->value.enumerated.item[0] != 1) return -EINVAL; reg_eq = snd_soc_read(codec, WM8983_EQ1_LOW_SHELF); switch ((reg_eq & WM8983_EQ3DMODE) >> WM8983_EQ3DMODE_SHIFT) { case 0: - if (!ucontrol->value.integer.value[0]) + if (!ucontrol->value.enumerated.item[0]) return 0; break; case 1: - if (ucontrol->value.integer.value[0]) + if (ucontrol->value.enumerated.item[0]) return 0; break; } @@ -537,7 +537,7 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, /* set the desired eqmode */ snd_soc_update_bits(codec, WM8983_EQ1_LOW_SHELF, WM8983_EQ3DMODE_MASK, - ucontrol->value.integer.value[0] + ucontrol->value.enumerated.item[0] << WM8983_EQ3DMODE_SHIFT); /* restore DAC/ADC configuration */ snd_soc_write(codec, WM8983_POWER_MANAGEMENT_2, regpwr2); diff --git a/sound/soc/codecs/wm8985.c b/sound/soc/codecs/wm8985.c index 9918152a03c75..6ac76fe116b02 100644 --- a/sound/soc/codecs/wm8985.c +++ b/sound/soc/codecs/wm8985.c @@ -531,9 +531,9 @@ static int eqmode_get(struct snd_kcontrol *kcontrol, reg = snd_soc_read(codec, WM8985_EQ1_LOW_SHELF); if (reg & WM8985_EQ3DMODE) - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; return 0; } @@ -545,18 +545,18 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, unsigned int regpwr2, regpwr3; unsigned int reg_eq; - if (ucontrol->value.integer.value[0] != 0 - && ucontrol->value.integer.value[0] != 1) + if (ucontrol->value.enumerated.item[0] != 0 + && ucontrol->value.enumerated.item[0] != 1) return -EINVAL; reg_eq = snd_soc_read(codec, WM8985_EQ1_LOW_SHELF); switch ((reg_eq & WM8985_EQ3DMODE) >> WM8985_EQ3DMODE_SHIFT) { case 0: - if (!ucontrol->value.integer.value[0]) + if (!ucontrol->value.enumerated.item[0]) return 0; break; case 1: - if (ucontrol->value.integer.value[0]) + if (ucontrol->value.enumerated.item[0]) return 0; break; } @@ -573,7 +573,7 @@ static int eqmode_put(struct snd_kcontrol *kcontrol, /* set the desired eqmode */ snd_soc_update_bits(codec, WM8985_EQ1_LOW_SHELF, WM8985_EQ3DMODE_MASK, - ucontrol->value.integer.value[0] + ucontrol->value.enumerated.item[0] << WM8985_EQ3DMODE_SHIFT); /* restore DAC/ADC configuration */ snd_soc_write(codec, WM8985_POWER_MANAGEMENT_2, regpwr2); diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 2ccbb322df775..a18aecb499359 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -362,7 +362,7 @@ static int wm8994_put_drc_enum(struct snd_kcontrol *kcontrol, struct wm8994 *control = wm8994->wm8994; struct wm8994_pdata *pdata = &control->pdata; int drc = wm8994_get_drc(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (drc < 0) return drc; @@ -469,7 +469,7 @@ static int wm8994_put_retune_mobile_enum(struct snd_kcontrol *kcontrol, struct wm8994 *control = wm8994->wm8994; struct wm8994_pdata *pdata = &control->pdata; int block = wm8994_get_retune_mobile_block(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (block < 0) return block; diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c index 8d7d6c01a2f72..f99b34f7647b0 100644 --- a/sound/soc/codecs/wm8996.c +++ b/sound/soc/codecs/wm8996.c @@ -416,7 +416,7 @@ static int wm8996_put_retune_mobile_enum(struct snd_kcontrol *kcontrol, struct wm8996_priv *wm8996 = snd_soc_codec_get_drvdata(codec); struct wm8996_pdata *pdata = &wm8996->pdata; int block = wm8996_get_retune_mobile_block(kcontrol->id.name); - int value = ucontrol->value.integer.value[0]; + int value = ucontrol->value.enumerated.item[0]; if (block < 0) return block; diff --git a/sound/soc/codecs/wm9081.c b/sound/soc/codecs/wm9081.c index ccb3b15139ad9..363b3b6676163 100644 --- a/sound/soc/codecs/wm9081.c +++ b/sound/soc/codecs/wm9081.c @@ -344,9 +344,9 @@ static int speaker_mode_get(struct snd_kcontrol *kcontrol, reg = snd_soc_read(codec, WM9081_ANALOGUE_SPEAKER_2); if (reg & WM9081_SPK_MODE) - ucontrol->value.integer.value[0] = 1; + ucontrol->value.enumerated.item[0] = 1; else - ucontrol->value.integer.value[0] = 0; + ucontrol->value.enumerated.item[0] = 0; return 0; } @@ -365,7 +365,7 @@ static int speaker_mode_put(struct snd_kcontrol *kcontrol, unsigned int reg2 = snd_soc_read(codec, WM9081_ANALOGUE_SPEAKER_2); /* Are we changing anything? */ - if (ucontrol->value.integer.value[0] == + if (ucontrol->value.enumerated.item[0] == ((reg2 & WM9081_SPK_MODE) != 0)) return 0; @@ -373,7 +373,7 @@ static int speaker_mode_put(struct snd_kcontrol *kcontrol, if (reg_pwr & WM9081_SPK_ENA) return -EINVAL; - if (ucontrol->value.integer.value[0]) { + if (ucontrol->value.enumerated.item[0]) { /* Class AB */ reg2 &= ~(WM9081_SPK_INV_MUTE | WM9081_OUT_SPK_CTRL); reg2 |= WM9081_SPK_MODE; diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c index 79e143625ac3d..9849643ef8099 100644 --- a/sound/soc/codecs/wm9713.c +++ b/sound/soc/codecs/wm9713.c @@ -1212,7 +1212,7 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec) if (IS_ERR(wm9713->ac97)) return PTR_ERR(wm9713->ac97); - regmap = devm_regmap_init_ac97(wm9713->ac97, &wm9713_regmap_config); + regmap = regmap_init_ac97(wm9713->ac97, &wm9713_regmap_config); if (IS_ERR(regmap)) { snd_soc_free_ac97_codec(wm9713->ac97); return PTR_ERR(regmap); diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 33806d487b8ae..b9195b9c2b051 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -586,7 +586,7 @@ static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; struct wm_adsp *dsp = snd_soc_codec_get_drvdata(codec); - ucontrol->value.integer.value[0] = dsp[e->shift_l].fw; + ucontrol->value.enumerated.item[0] = dsp[e->shift_l].fw; return 0; } @@ -599,10 +599,10 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol, struct wm_adsp *dsp = snd_soc_codec_get_drvdata(codec); int ret = 0; - if (ucontrol->value.integer.value[0] == dsp[e->shift_l].fw) + if (ucontrol->value.enumerated.item[0] == dsp[e->shift_l].fw) return 0; - if (ucontrol->value.integer.value[0] >= WM_ADSP_NUM_FW) + if (ucontrol->value.enumerated.item[0] >= WM_ADSP_NUM_FW) return -EINVAL; mutex_lock(&dsp[e->shift_l].pwr_lock); @@ -610,7 +610,7 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol, if (dsp[e->shift_l].running || dsp[e->shift_l].compr) ret = -EBUSY; else - dsp[e->shift_l].fw = ucontrol->value.integer.value[0]; + dsp[e->shift_l].fw = ucontrol->value.enumerated.item[0]; mutex_unlock(&dsp[e->shift_l].pwr_lock); diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index ed8de1035cda1..40dfd8a364840 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -112,6 +112,20 @@ struct fsl_ssi_rxtx_reg_val { struct fsl_ssi_reg_val tx; }; +static const struct reg_default fsl_ssi_reg_defaults[] = { + {CCSR_SSI_SCR, 0x00000000}, + {CCSR_SSI_SIER, 0x00003003}, + {CCSR_SSI_STCR, 0x00000200}, + {CCSR_SSI_SRCR, 0x00000200}, + {CCSR_SSI_STCCR, 0x00040000}, + {CCSR_SSI_SRCCR, 0x00040000}, + {CCSR_SSI_SACNT, 0x00000000}, + {CCSR_SSI_STMSK, 0x00000000}, + {CCSR_SSI_SRMSK, 0x00000000}, + {CCSR_SSI_SACCEN, 0x00000000}, + {CCSR_SSI_SACCDIS, 0x00000000}, +}; + static bool fsl_ssi_readable_reg(struct device *dev, unsigned int reg) { switch (reg) { @@ -176,7 +190,8 @@ static const struct regmap_config fsl_ssi_regconfig = { .val_bits = 32, .reg_stride = 4, .val_format_endian = REGMAP_ENDIAN_NATIVE, - .num_reg_defaults_raw = CCSR_SSI_SACCDIS / sizeof(uint32_t) + 1, + .reg_defaults = fsl_ssi_reg_defaults, + .num_reg_defaults = ARRAY_SIZE(fsl_ssi_reg_defaults), .readable_reg = fsl_ssi_readable_reg, .volatile_reg = fsl_ssi_volatile_reg, .precious_reg = fsl_ssi_precious_reg, @@ -186,7 +201,6 @@ static const struct regmap_config fsl_ssi_regconfig = { struct fsl_ssi_soc_data { bool imx; - bool imx21regs; /* imx21-class SSI - no SACC{ST,EN,DIS} regs */ bool offline_config; u32 sisr_write_mask; }; @@ -289,7 +303,6 @@ static struct fsl_ssi_soc_data fsl_ssi_mpc8610 = { static struct fsl_ssi_soc_data fsl_ssi_imx21 = { .imx = true, - .imx21regs = true, .offline_config = true, .sisr_write_mask = 0, }; @@ -573,12 +586,8 @@ static void fsl_ssi_setup_ac97(struct fsl_ssi_private *ssi_private) */ regmap_write(regs, CCSR_SSI_SACNT, CCSR_SSI_SACNT_AC97EN | CCSR_SSI_SACNT_FV); - - /* no SACC{ST,EN,DIS} regs on imx21-class SSI */ - if (!ssi_private->soc->imx21regs) { - regmap_write(regs, CCSR_SSI_SACCDIS, 0xff); - regmap_write(regs, CCSR_SSI_SACCEN, 0x300); - } + regmap_write(regs, CCSR_SSI_SACCDIS, 0xff); + regmap_write(regs, CCSR_SSI_SACCEN, 0x300); /* * Enable SSI, Transmit and Receive. AC97 has to communicate with the @@ -1388,7 +1397,6 @@ static int fsl_ssi_probe(struct platform_device *pdev) struct resource *res; void __iomem *iomem; char name[64]; - struct regmap_config regconfig = fsl_ssi_regconfig; of_id = of_match_device(fsl_ssi_ids, &pdev->dev); if (!of_id || !of_id->data) @@ -1436,25 +1444,15 @@ static int fsl_ssi_probe(struct platform_device *pdev) return PTR_ERR(iomem); ssi_private->ssi_phys = res->start; - if (ssi_private->soc->imx21regs) { - /* - * According to datasheet imx21-class SSI - * don't have SACC{ST,EN,DIS} regs. - */ - regconfig.max_register = CCSR_SSI_SRMSK; - regconfig.num_reg_defaults_raw = - CCSR_SSI_SRMSK / sizeof(uint32_t) + 1; - } - ret = of_property_match_string(np, "clock-names", "ipg"); if (ret < 0) { ssi_private->has_ipg_clk_name = false; ssi_private->regs = devm_regmap_init_mmio(&pdev->dev, iomem, - ®config); + &fsl_ssi_regconfig); } else { ssi_private->has_ipg_clk_name = true; ssi_private->regs = devm_regmap_init_mmio_clk(&pdev->dev, - "ipg", iomem, ®config); + "ipg", iomem, &fsl_ssi_regconfig); } if (IS_ERR(ssi_private->regs)) { dev_err(&pdev->dev, "Failed to init register map\n"); diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c index 49d7513f429e5..e63cd5ecfd8fe 100644 --- a/sound/soc/fsl/imx-pcm-fiq.c +++ b/sound/soc/fsl/imx-pcm-fiq.c @@ -217,8 +217,8 @@ static int snd_imx_pcm_mmap(struct snd_pcm_substream *substream, struct snd_pcm_runtime *runtime = substream->runtime; int ret; - ret = dma_mmap_writecombine(substream->pcm->card->dev, vma, - runtime->dma_area, runtime->dma_addr, runtime->dma_bytes); + ret = dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area, + runtime->dma_addr, runtime->dma_bytes); pr_debug("%s: ret: %d %p %pad 0x%08x\n", __func__, ret, runtime->dma_area, @@ -247,8 +247,7 @@ static int imx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream) buf->dev.type = SNDRV_DMA_TYPE_DEV; buf->dev.dev = pcm->card->dev; buf->private_data = NULL; - buf->area = dma_alloc_writecombine(pcm->card->dev, size, - &buf->addr, GFP_KERNEL); + buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL); if (!buf->area) return -ENOMEM; buf->bytes = size; @@ -330,8 +329,7 @@ static void imx_pcm_free(struct snd_pcm *pcm) if (!buf->area) continue; - dma_free_writecombine(pcm->card->dev, buf->bytes, - buf->area, buf->addr); + dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr); buf->area = NULL; } } diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c index 2d3afddb0a2e8..a7b96a9a4e0ec 100644 --- a/sound/soc/intel/boards/cht_bsw_rt5645.c +++ b/sound/soc/intel/boards/cht_bsw_rt5645.c @@ -367,8 +367,12 @@ static int snd_cht_mc_probe(struct platform_device *pdev) } card->dev = &pdev->dev; sprintf(codec_name, "i2c-%s:00", drv->acpi_card->codec_id); + /* set correct codec name */ - strcpy((char *)card->dai_link[2].codec_name, codec_name); + for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) + if (!strcmp(card->dai_link[i].codec_name, "i2c-10EC5645:00")) + card->dai_link[i].codec_name = kstrdup(codec_name, GFP_KERNEL); + snd_soc_card_set_drvdata(card, drv); ret_val = devm_snd_soc_register_card(&pdev->dev, card); if (ret_val) { diff --git a/sound/soc/intel/boards/mfld_machine.c b/sound/soc/intel/boards/mfld_machine.c index 49c09a0add797..34f46c72a0e27 100644 --- a/sound/soc/intel/boards/mfld_machine.c +++ b/sound/soc/intel/boards/mfld_machine.c @@ -94,7 +94,7 @@ static const struct soc_enum lo_enum = static int headset_get_switch(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = hs_switch; + ucontrol->value.enumerated.item[0] = hs_switch; return 0; } @@ -104,12 +104,12 @@ static int headset_set_switch(struct snd_kcontrol *kcontrol, struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); struct snd_soc_dapm_context *dapm = &card->dapm; - if (ucontrol->value.integer.value[0] == hs_switch) + if (ucontrol->value.enumerated.item[0] == hs_switch) return 0; snd_soc_dapm_mutex_lock(dapm); - if (ucontrol->value.integer.value[0]) { + if (ucontrol->value.enumerated.item[0]) { pr_debug("hs_set HS path\n"); snd_soc_dapm_enable_pin_unlocked(dapm, "Headphones"); snd_soc_dapm_disable_pin_unlocked(dapm, "EPOUT"); @@ -123,7 +123,7 @@ static int headset_set_switch(struct snd_kcontrol *kcontrol, snd_soc_dapm_mutex_unlock(dapm); - hs_switch = ucontrol->value.integer.value[0]; + hs_switch = ucontrol->value.enumerated.item[0]; return 0; } @@ -148,7 +148,7 @@ static void lo_enable_out_pins(struct snd_soc_dapm_context *dapm) static int lo_get_switch(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = lo_dac; + ucontrol->value.enumerated.item[0] = lo_dac; return 0; } @@ -158,7 +158,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol, struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); struct snd_soc_dapm_context *dapm = &card->dapm; - if (ucontrol->value.integer.value[0] == lo_dac) + if (ucontrol->value.enumerated.item[0] == lo_dac) return 0; snd_soc_dapm_mutex_lock(dapm); @@ -168,7 +168,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol, */ lo_enable_out_pins(dapm); - switch (ucontrol->value.integer.value[0]) { + switch (ucontrol->value.enumerated.item[0]) { case 0: pr_debug("set vibra path\n"); snd_soc_dapm_disable_pin_unlocked(dapm, "VIB1OUT"); @@ -202,7 +202,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol, snd_soc_dapm_mutex_unlock(dapm); - lo_dac = ucontrol->value.integer.value[0]; + lo_dac = ucontrol->value.enumerated.item[0]; return 0; } diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index a294fee431f07..5a4837dcfce3e 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -978,7 +978,7 @@ static int skl_tplg_tlv_control_set(struct snd_kcontrol *kcontrol, return -EFAULT; } else { if (copy_from_user(ac->params, - data + 2 * sizeof(u32), size)) + data + 2, size)) return -EFAULT; } diff --git a/sound/soc/nuc900/nuc900-pcm.c b/sound/soc/nuc900/nuc900-pcm.c index e09326158bc2d..2cca055fd806c 100644 --- a/sound/soc/nuc900/nuc900-pcm.c +++ b/sound/soc/nuc900/nuc900-pcm.c @@ -267,10 +267,8 @@ static int nuc900_dma_mmap(struct snd_pcm_substream *substream, { struct snd_pcm_runtime *runtime = substream->runtime; - return dma_mmap_writecombine(substream->pcm->card->dev, vma, - runtime->dma_area, - runtime->dma_addr, - runtime->dma_bytes); + return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area, + runtime->dma_addr, runtime->dma_bytes); } static struct snd_pcm_ops nuc900_dma_ops = { diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c index 190f868e78b24..fdecb70431745 100644 --- a/sound/soc/omap/n810.c +++ b/sound/soc/omap/n810.c @@ -133,7 +133,7 @@ static struct snd_soc_ops n810_ops = { static int n810_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = n810_spk_func; + ucontrol->value.enumerated.item[0] = n810_spk_func; return 0; } @@ -143,10 +143,10 @@ static int n810_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (n810_spk_func == ucontrol->value.integer.value[0]) + if (n810_spk_func == ucontrol->value.enumerated.item[0]) return 0; - n810_spk_func = ucontrol->value.integer.value[0]; + n810_spk_func = ucontrol->value.enumerated.item[0]; n810_ext_control(&card->dapm); return 1; @@ -155,7 +155,7 @@ static int n810_set_spk(struct snd_kcontrol *kcontrol, static int n810_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = n810_jack_func; + ucontrol->value.enumerated.item[0] = n810_jack_func; return 0; } @@ -165,10 +165,10 @@ static int n810_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (n810_jack_func == ucontrol->value.integer.value[0]) + if (n810_jack_func == ucontrol->value.enumerated.item[0]) return 0; - n810_jack_func = ucontrol->value.integer.value[0]; + n810_jack_func = ucontrol->value.enumerated.item[0]; n810_ext_control(&card->dapm); return 1; @@ -177,7 +177,7 @@ static int n810_set_jack(struct snd_kcontrol *kcontrol, static int n810_get_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = n810_dmic_func; + ucontrol->value.enumerated.item[0] = n810_dmic_func; return 0; } @@ -187,10 +187,10 @@ static int n810_set_input(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (n810_dmic_func == ucontrol->value.integer.value[0]) + if (n810_dmic_func == ucontrol->value.enumerated.item[0]) return 0; - n810_dmic_func = ucontrol->value.integer.value[0]; + n810_dmic_func = ucontrol->value.enumerated.item[0]; n810_ext_control(&card->dapm); return 1; diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c index 6bb623a2a4dfc..99381a27295bb 100644 --- a/sound/soc/omap/omap-pcm.c +++ b/sound/soc/omap/omap-pcm.c @@ -156,10 +156,8 @@ static int omap_pcm_mmap(struct snd_pcm_substream *substream, { struct snd_pcm_runtime *runtime = substream->runtime; - return dma_mmap_writecombine(substream->pcm->card->dev, vma, - runtime->dma_area, - runtime->dma_addr, - runtime->dma_bytes); + return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area, + runtime->dma_addr, runtime->dma_bytes); } static struct snd_pcm_ops omap_pcm_ops = { @@ -183,8 +181,7 @@ static int omap_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, buf->dev.type = SNDRV_DMA_TYPE_DEV; buf->dev.dev = pcm->card->dev; buf->private_data = NULL; - buf->area = dma_alloc_writecombine(pcm->card->dev, size, - &buf->addr, GFP_KERNEL); + buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL); if (!buf->area) return -ENOMEM; @@ -207,8 +204,7 @@ static void omap_pcm_free_dma_buffers(struct snd_pcm *pcm) if (!buf->area) continue; - dma_free_writecombine(pcm->card->dev, buf->bytes, - buf->area, buf->addr); + dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr); buf->area = NULL; } } diff --git a/sound/soc/omap/rx51.c b/sound/soc/omap/rx51.c index 5e21f08579d80..54949242bc707 100644 --- a/sound/soc/omap/rx51.c +++ b/sound/soc/omap/rx51.c @@ -132,7 +132,7 @@ static struct snd_soc_ops rx51_ops = { static int rx51_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = rx51_spk_func; + ucontrol->value.enumerated.item[0] = rx51_spk_func; return 0; } @@ -142,10 +142,10 @@ static int rx51_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (rx51_spk_func == ucontrol->value.integer.value[0]) + if (rx51_spk_func == ucontrol->value.enumerated.item[0]) return 0; - rx51_spk_func = ucontrol->value.integer.value[0]; + rx51_spk_func = ucontrol->value.enumerated.item[0]; rx51_ext_control(&card->dapm); return 1; @@ -180,7 +180,7 @@ static int rx51_hp_event(struct snd_soc_dapm_widget *w, static int rx51_get_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = rx51_dmic_func; + ucontrol->value.enumerated.item[0] = rx51_dmic_func; return 0; } @@ -190,10 +190,10 @@ static int rx51_set_input(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (rx51_dmic_func == ucontrol->value.integer.value[0]) + if (rx51_dmic_func == ucontrol->value.enumerated.item[0]) return 0; - rx51_dmic_func = ucontrol->value.integer.value[0]; + rx51_dmic_func = ucontrol->value.enumerated.item[0]; rx51_ext_control(&card->dapm); return 1; @@ -202,7 +202,7 @@ static int rx51_set_input(struct snd_kcontrol *kcontrol, static int rx51_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = rx51_jack_func; + ucontrol->value.enumerated.item[0] = rx51_jack_func; return 0; } @@ -212,10 +212,10 @@ static int rx51_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (rx51_jack_func == ucontrol->value.integer.value[0]) + if (rx51_jack_func == ucontrol->value.enumerated.item[0]) return 0; - rx51_jack_func = ucontrol->value.integer.value[0]; + rx51_jack_func = ucontrol->value.enumerated.item[0]; rx51_ext_control(&card->dapm); return 1; diff --git a/sound/soc/pxa/corgi.c b/sound/soc/pxa/corgi.c index c97dc13d36087..dcbb7aa9830c0 100644 --- a/sound/soc/pxa/corgi.c +++ b/sound/soc/pxa/corgi.c @@ -163,7 +163,7 @@ static struct snd_soc_ops corgi_ops = { static int corgi_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = corgi_jack_func; + ucontrol->value.enumerated.item[0] = corgi_jack_func; return 0; } @@ -172,10 +172,10 @@ static int corgi_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (corgi_jack_func == ucontrol->value.integer.value[0]) + if (corgi_jack_func == ucontrol->value.enumerated.item[0]) return 0; - corgi_jack_func = ucontrol->value.integer.value[0]; + corgi_jack_func = ucontrol->value.enumerated.item[0]; corgi_ext_control(&card->dapm); return 1; } @@ -183,7 +183,7 @@ static int corgi_set_jack(struct snd_kcontrol *kcontrol, static int corgi_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = corgi_spk_func; + ucontrol->value.enumerated.item[0] = corgi_spk_func; return 0; } @@ -192,10 +192,10 @@ static int corgi_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (corgi_spk_func == ucontrol->value.integer.value[0]) + if (corgi_spk_func == ucontrol->value.enumerated.item[0]) return 0; - corgi_spk_func = ucontrol->value.integer.value[0]; + corgi_spk_func = ucontrol->value.enumerated.item[0]; corgi_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/pxa/magician.c b/sound/soc/pxa/magician.c index 241d0be42d7a0..62b8377a9d2b9 100644 --- a/sound/soc/pxa/magician.c +++ b/sound/soc/pxa/magician.c @@ -308,17 +308,17 @@ static int magician_set_spk(struct snd_kcontrol *kcontrol, static int magician_get_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = magician_in_sel; + ucontrol->value.enumerated.item[0] = magician_in_sel; return 0; } static int magician_set_input(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - if (magician_in_sel == ucontrol->value.integer.value[0]) + if (magician_in_sel == ucontrol->value.enumerated.item[0]) return 0; - magician_in_sel = ucontrol->value.integer.value[0]; + magician_in_sel = ucontrol->value.enumerated.item[0]; switch (magician_in_sel) { case MAGICIAN_MIC: diff --git a/sound/soc/pxa/poodle.c b/sound/soc/pxa/poodle.c index 84d0e2e508088..4b3b714f5ee7a 100644 --- a/sound/soc/pxa/poodle.c +++ b/sound/soc/pxa/poodle.c @@ -138,7 +138,7 @@ static struct snd_soc_ops poodle_ops = { static int poodle_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = poodle_jack_func; + ucontrol->value.enumerated.item[0] = poodle_jack_func; return 0; } @@ -147,10 +147,10 @@ static int poodle_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (poodle_jack_func == ucontrol->value.integer.value[0]) + if (poodle_jack_func == ucontrol->value.enumerated.item[0]) return 0; - poodle_jack_func = ucontrol->value.integer.value[0]; + poodle_jack_func = ucontrol->value.enumerated.item[0]; poodle_ext_control(&card->dapm); return 1; } @@ -158,7 +158,7 @@ static int poodle_set_jack(struct snd_kcontrol *kcontrol, static int poodle_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = poodle_spk_func; + ucontrol->value.enumerated.item[0] = poodle_spk_func; return 0; } @@ -167,10 +167,10 @@ static int poodle_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (poodle_spk_func == ucontrol->value.integer.value[0]) + if (poodle_spk_func == ucontrol->value.enumerated.item[0]) return 0; - poodle_spk_func = ucontrol->value.integer.value[0]; + poodle_spk_func = ucontrol->value.enumerated.item[0]; poodle_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/pxa/spitz.c b/sound/soc/pxa/spitz.c index b00222620fd01..0e02634c8b7f6 100644 --- a/sound/soc/pxa/spitz.c +++ b/sound/soc/pxa/spitz.c @@ -164,7 +164,7 @@ static struct snd_soc_ops spitz_ops = { static int spitz_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = spitz_jack_func; + ucontrol->value.enumerated.item[0] = spitz_jack_func; return 0; } @@ -173,10 +173,10 @@ static int spitz_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (spitz_jack_func == ucontrol->value.integer.value[0]) + if (spitz_jack_func == ucontrol->value.enumerated.item[0]) return 0; - spitz_jack_func = ucontrol->value.integer.value[0]; + spitz_jack_func = ucontrol->value.enumerated.item[0]; spitz_ext_control(&card->dapm); return 1; } @@ -184,7 +184,7 @@ static int spitz_set_jack(struct snd_kcontrol *kcontrol, static int spitz_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = spitz_spk_func; + ucontrol->value.enumerated.item[0] = spitz_spk_func; return 0; } @@ -193,10 +193,10 @@ static int spitz_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (spitz_spk_func == ucontrol->value.integer.value[0]) + if (spitz_spk_func == ucontrol->value.enumerated.item[0]) return 0; - spitz_spk_func = ucontrol->value.integer.value[0]; + spitz_spk_func = ucontrol->value.enumerated.item[0]; spitz_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/pxa/tosa.c b/sound/soc/pxa/tosa.c index 49518dd642aa1..c508f024ecfbc 100644 --- a/sound/soc/pxa/tosa.c +++ b/sound/soc/pxa/tosa.c @@ -95,7 +95,7 @@ static struct snd_soc_ops tosa_ops = { static int tosa_get_jack(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = tosa_jack_func; + ucontrol->value.enumerated.item[0] = tosa_jack_func; return 0; } @@ -104,10 +104,10 @@ static int tosa_set_jack(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (tosa_jack_func == ucontrol->value.integer.value[0]) + if (tosa_jack_func == ucontrol->value.enumerated.item[0]) return 0; - tosa_jack_func = ucontrol->value.integer.value[0]; + tosa_jack_func = ucontrol->value.enumerated.item[0]; tosa_ext_control(&card->dapm); return 1; } @@ -115,7 +115,7 @@ static int tosa_set_jack(struct snd_kcontrol *kcontrol, static int tosa_get_spk(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { - ucontrol->value.integer.value[0] = tosa_spk_func; + ucontrol->value.enumerated.item[0] = tosa_spk_func; return 0; } @@ -124,10 +124,10 @@ static int tosa_set_spk(struct snd_kcontrol *kcontrol, { struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); - if (tosa_spk_func == ucontrol->value.integer.value[0]) + if (tosa_spk_func == ucontrol->value.enumerated.item[0]) return 0; - tosa_spk_func = ucontrol->value.integer.value[0]; + tosa_spk_func = ucontrol->value.enumerated.item[0]; tosa_ext_control(&card->dapm); return 1; } diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 00b6c9d039cfa..e5101e0d2d372 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -355,7 +355,6 @@ static struct regmap_config lpass_cpu_regmap_config = { .readable_reg = lpass_cpu_regmap_readable, .volatile_reg = lpass_cpu_regmap_volatile, .cache_type = REGCACHE_FLAT, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index 84d9e77c0fbe1..70a2559b63f90 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -481,10 +481,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai, unsigned int cdcon_mask = 1 << i2s_regs->cdclkcon_off; unsigned int rsrc_mask = 1 << i2s_regs->rclksrc_off; u32 mod, mask, val = 0; + unsigned long flags; - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); switch (clk_id) { case SAMSUNG_I2S_OPCLK: @@ -575,11 +576,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); mod = (mod & ~mask) | val; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); return 0; } @@ -590,6 +591,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, struct i2s_dai *i2s = to_info(dai); int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave; u32 mod, tmp = 0; + unsigned long flags; lrp_shift = i2s->variant_regs->lrp_off; sdf_shift = i2s->variant_regs->sdf_off; @@ -649,7 +651,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); /* * Don't change the I2S mode if any controller is active on this @@ -657,7 +659,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, */ if (any_active(i2s) && ((mod & (sdf_mask | lrp_rlow | mod_slave)) != tmp)) { - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); dev_err(&i2s->pdev->dev, "%s:%d Other DAI busy\n", __func__, __LINE__); return -EAGAIN; @@ -666,7 +668,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, mod &= ~(sdf_mask | lrp_rlow | mod_slave); mod |= tmp; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); return 0; } @@ -676,6 +678,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, { struct i2s_dai *i2s = to_info(dai); u32 mod, mask = 0, val = 0; + unsigned long flags; if (!is_secondary(i2s)) mask |= (MOD_DC2_EN | MOD_DC1_EN); @@ -744,11 +747,11 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - spin_lock(i2s->lock); + spin_lock_irqsave(i2s->lock, flags); mod = readl(i2s->addr + I2SMOD); mod = (mod & ~mask) | val; writel(mod, i2s->addr + I2SMOD); - spin_unlock(i2s->lock); + spin_unlock_irqrestore(i2s->lock, flags); samsung_asoc_init_dma_data(dai, &i2s->dma_playback, &i2s->dma_capture); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 0d37079879002..581175a51ecf7 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3573,7 +3573,7 @@ static int snd_soc_dapm_dai_link_get(struct snd_kcontrol *kcontrol, { struct snd_soc_dapm_widget *w = snd_kcontrol_chip(kcontrol); - ucontrol->value.integer.value[0] = w->params_select; + ucontrol->value.enumerated.item[0] = w->params_select; return 0; } @@ -3587,13 +3587,13 @@ static int snd_soc_dapm_dai_link_put(struct snd_kcontrol *kcontrol, if (w->power) return -EBUSY; - if (ucontrol->value.integer.value[0] == w->params_select) + if (ucontrol->value.enumerated.item[0] == w->params_select) return 0; - if (ucontrol->value.integer.value[0] >= w->num_params) + if (ucontrol->value.enumerated.item[0] >= w->num_params) return -EINVAL; - w->params_select = ucontrol->value.integer.value[0]; + w->params_select = ucontrol->value.enumerated.item[0]; return 0; } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 4f6ce1cac8e20..c458d60d50300 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1124,6 +1124,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ + case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */ diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 4a96473b180f9..ee566e8bd1cff 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -85,7 +85,7 @@ $(OUTPUT)%.i: %.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_i_c) -$(OUTPUT)%.i: %.S FORCE +$(OUTPUT)%.s: %.S FORCE $(call rule_mkdir) $(call if_changed_dep,cc_i_c) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 02db3cdff20ff..6b7707270aa3b 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -27,7 +27,7 @@ endef # the rule that uses them - an example for that is the 'bionic' # feature check. ] # -FEATURE_TESTS ?= \ +FEATURE_TESTS_BASIC := \ backtrace \ dwarf \ fortify-source \ @@ -46,6 +46,7 @@ FEATURE_TESTS ?= \ libpython \ libpython-version \ libslang \ + libcrypto \ libunwind \ pthread-attr-setaffinity-np \ stackprotector-all \ @@ -56,6 +57,25 @@ FEATURE_TESTS ?= \ get_cpuid \ bpf +# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list +# of all feature tests +FEATURE_TESTS_EXTRA := \ + bionic \ + compile-32 \ + compile-x32 \ + cplus-demangle \ + hello \ + libbabeltrace \ + liberty \ + liberty-z \ + libunwind-debug-frame + +FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC) + +ifeq ($(FEATURE_TESTS),all) + FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA) +endif + FEATURE_DISPLAY ?= \ dwarf \ glibc \ @@ -68,6 +88,7 @@ FEATURE_DISPLAY ?= \ libperl \ libpython \ libslang \ + libcrypto \ libunwind \ libdw-dwarf-unwind \ zlib \ @@ -100,6 +121,14 @@ ifeq ($(feature-all), 1) # test-all.c passed - just set all the core feature flags to 1: # $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat))) + # + # test-all.c does not comprise these tests, so we need to + # for this case to get features proper values + # + $(call feature_check,compile-32) + $(call feature_check,compile-x32) + $(call feature_check,bionic) + $(call feature_check,libbabeltrace) else $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat))) endif diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index bf8f0352264dc..c5f4c417428d7 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -23,6 +23,7 @@ FILES= \ test-libpython.bin \ test-libpython-version.bin \ test-libslang.bin \ + test-libcrypto.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ test-pthread-attr-setaffinity-np.bin \ @@ -105,6 +106,9 @@ $(OUTPUT)test-libaudit.bin: $(OUTPUT)test-libslang.bin: $(BUILD) -I/usr/include/slang -lslang +$(OUTPUT)test-libcrypto.bin: + $(BUILD) -lcrypto + $(OUTPUT)test-gtk2.bin: $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 81025cade45fa..e499a36c1e4a9 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -129,6 +129,10 @@ # include "test-bpf.c" #undef main +#define main main_test_libcrypto +# include "test-libcrypto.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -158,6 +162,7 @@ int main(int argc, char *argv[]) main_test_lzma(); main_test_get_cpuid(); main_test_bpf(); + main_test_libcrypto(); return 0; } diff --git a/tools/build/feature/test-compile.c b/tools/build/feature/test-compile.c index 31dbf45bf99c5..c54e6551ae4c5 100644 --- a/tools/build/feature/test-compile.c +++ b/tools/build/feature/test-compile.c @@ -1,4 +1,6 @@ +#include int main(void) { + printf("Hello World!\n"); return 0; } diff --git a/tools/build/feature/test-libcrypto.c b/tools/build/feature/test-libcrypto.c new file mode 100644 index 0000000000000..bd79dc7f28d36 --- /dev/null +++ b/tools/build/feature/test-libcrypto.c @@ -0,0 +1,17 @@ +#include +#include + +int main(void) +{ + MD5_CTX context; + unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH]; + unsigned char dat[] = "12345"; + + MD5_Init(&context); + MD5_Update(&context, &dat[0], sizeof(dat)); + MD5_Final(&md[0], &context); + + SHA1(&dat[0], sizeof(dat), &md[0]); + + return 0; +} diff --git a/tools/lib/api/Build b/tools/lib/api/Build index e8b8a23b9bf4c..954c644f7ad9e 100644 --- a/tools/lib/api/Build +++ b/tools/lib/api/Build @@ -1,3 +1,4 @@ libapi-y += fd/ libapi-y += fs/ libapi-y += cpu.o +libapi-y += debug.o diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index d85904dc9b387..bbc82c614bee6 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -18,6 +18,7 @@ LIBFILE = $(OUTPUT)libapi.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +CFLAGS += -I$(srctree)/tools/lib/api RM = rm -f diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h new file mode 100644 index 0000000000000..188f7880eafe6 --- /dev/null +++ b/tools/lib/api/debug-internal.h @@ -0,0 +1,20 @@ +#ifndef __API_DEBUG_INTERNAL_H__ +#define __API_DEBUG_INTERNAL_H__ + +#include "debug.h" + +#define __pr(func, fmt, ...) \ +do { \ + if ((func)) \ + (func)("libapi: " fmt, ##__VA_ARGS__); \ +} while (0) + +extern libapi_print_fn_t __pr_warning; +extern libapi_print_fn_t __pr_info; +extern libapi_print_fn_t __pr_debug; + +#define pr_warning(fmt, ...) __pr(__pr_warning, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(__pr_info, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(__pr_debug, fmt, ##__VA_ARGS__) + +#endif /* __API_DEBUG_INTERNAL_H__ */ diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c new file mode 100644 index 0000000000000..5fa5cf500a1f9 --- /dev/null +++ b/tools/lib/api/debug.c @@ -0,0 +1,28 @@ +#include +#include +#include "debug.h" +#include "debug-internal.h" + +static int __base_pr(const char *format, ...) +{ + va_list args; + int err; + + va_start(args, format); + err = vfprintf(stderr, format, args); + va_end(args); + return err; +} + +libapi_print_fn_t __pr_warning = __base_pr; +libapi_print_fn_t __pr_info = __base_pr; +libapi_print_fn_t __pr_debug; + +void libapi_set_print(libapi_print_fn_t warn, + libapi_print_fn_t info, + libapi_print_fn_t debug) +{ + __pr_warning = warn; + __pr_info = info; + __pr_debug = debug; +} diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h new file mode 100644 index 0000000000000..a0872f68fc56b --- /dev/null +++ b/tools/lib/api/debug.h @@ -0,0 +1,10 @@ +#ifndef __API_DEBUG_H__ +#define __API_DEBUG_H__ + +typedef int (*libapi_print_fn_t)(const char *, ...); + +void libapi_set_print(libapi_print_fn_t warn, + libapi_print_fn_t info, + libapi_print_fn_t debug); + +#endif /* __API_DEBUG_H__ */ diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 459599d1b6c41..ef78c22ff44d4 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -13,6 +13,7 @@ #include #include "fs.h" +#include "debug-internal.h" #define _STR(x) #x #define STR(x) _STR(x) @@ -300,6 +301,56 @@ int filename__read_ull(const char *filename, unsigned long long *value) return err; } +#define STRERR_BUFSIZE 128 /* For the buffer size of strerror_r */ + +int filename__read_str(const char *filename, char **buf, size_t *sizep) +{ + size_t size = 0, alloc_size = 0; + void *bf = NULL, *nbf; + int fd, n, err = 0; + char sbuf[STRERR_BUFSIZE]; + + fd = open(filename, O_RDONLY); + if (fd < 0) + return -errno; + + do { + if (size == alloc_size) { + alloc_size += BUFSIZ; + nbf = realloc(bf, alloc_size); + if (!nbf) { + err = -ENOMEM; + break; + } + + bf = nbf; + } + + n = read(fd, bf + size, alloc_size - size); + if (n < 0) { + if (size) { + pr_warning("read failed %d: %s\n", errno, + strerror_r(errno, sbuf, sizeof(sbuf))); + err = 0; + } else + err = -errno; + + break; + } + + size += n; + } while (n > 0); + + if (!err) { + *sizep = size; + *buf = bf; + } else + free(bf); + + close(fd); + return err; +} + int sysfs__read_ull(const char *entry, unsigned long long *value) { char path[PATH_MAX]; @@ -326,6 +377,19 @@ int sysfs__read_int(const char *entry, int *value) return filename__read_int(path, value); } +int sysfs__read_str(const char *entry, char **buf, size_t *sizep) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + snprintf(path, sizeof(path), "%s/%s", sysfs, entry); + + return filename__read_str(path, buf, sizep); +} + int sysctl__read_int(const char *sysctl, int *value) { char path[PATH_MAX]; diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index d024a7f682f69..9f6598098dc58 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -2,6 +2,7 @@ #define __API_FS__ #include +#include /* * On most systems would have given us this, but not on some systems @@ -26,8 +27,10 @@ FS(tracefs) int filename__read_int(const char *filename, int *value); int filename__read_ull(const char *filename, unsigned long long *value); +int filename__read_str(const char *filename, char **buf, size_t *sizep); int sysctl__read_int(const char *sysctl, int *value); int sysfs__read_int(const char *entry, int *value); int sysfs__read_ull(const char *entry, unsigned long long *value); +int sysfs__read_str(const char *entry, char **buf, size_t *sizep); #endif /* __API_FS__ */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 8334a5a9d5d7f..7e543c3102d41 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -201,6 +201,7 @@ struct bpf_object { Elf_Data *data; } *reloc; int nr_reloc; + int maps_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -350,6 +351,7 @@ static struct bpf_object *bpf_object__new(const char *path, */ obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; + obj->efile.maps_shndx = -1; obj->loaded = false; @@ -529,12 +531,12 @@ bpf_object__init_maps(struct bpf_object *obj, void *data, } static int -bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) +bpf_object__init_maps_name(struct bpf_object *obj) { int i; Elf_Data *symbols = obj->efile.symbols; - if (!symbols || maps_shndx < 0) + if (!symbols || obj->efile.maps_shndx < 0) return -EINVAL; for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { @@ -544,7 +546,7 @@ bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) if (!gelf_getsym(symbols, i, &sym)) continue; - if (sym.st_shndx != maps_shndx) + if (sym.st_shndx != obj->efile.maps_shndx) continue; map_name = elf_strptr(obj->efile.elf, @@ -572,7 +574,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Scn *scn = NULL; - int idx = 0, err = 0, maps_shndx = -1; + int idx = 0, err = 0; /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { @@ -625,7 +627,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) else if (strcmp(name, "maps") == 0) { err = bpf_object__init_maps(obj, data->d_buf, data->d_size); - maps_shndx = idx; + obj->efile.maps_shndx = idx; } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", @@ -674,8 +676,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return LIBBPF_ERRNO__FORMAT; } - if (maps_shndx >= 0) - err = bpf_object__init_maps_name(obj, maps_shndx); + if (obj->efile.maps_shndx >= 0) + err = bpf_object__init_maps_name(obj); out: return err; } @@ -697,7 +699,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) static int bpf_program__collect_reloc(struct bpf_program *prog, size_t nr_maps, GElf_Shdr *shdr, - Elf_Data *data, Elf_Data *symbols) + Elf_Data *data, Elf_Data *symbols, + int maps_shndx) { int i, nrels; @@ -724,9 +727,6 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__FORMAT; } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { @@ -735,6 +735,15 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__FORMAT; } + if (sym.st_shndx != maps_shndx) { + pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", + prog->section_name, sym.st_shndx); + return -LIBBPF_ERRNO__RELOC; + } + + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u\n", insn_idx); + if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", insn_idx, insns[insn_idx].code); @@ -863,7 +872,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) err = bpf_program__collect_reloc(prog, nr_maps, shdr, data, - obj->efile.symbols); + obj->efile.symbols, + obj->efile.maps_shndx); if (err) return err; } diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index 90d2baeb621a5..1d57af56814b8 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -100,7 +100,7 @@ include $(srctree)/tools/build/Makefile.include do_compile_shared_library = \ ($(print_shared_lib_compile) \ - $(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -s $@ liblockdep.so)) + $(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -sf $@ liblockdep.so)) do_build_static_lib = \ ($(print_static_lib_build) \ diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c index 9be663340f0a4..d1c89cc06f5f6 100644 --- a/tools/lib/lockdep/common.c +++ b/tools/lib/lockdep/common.c @@ -11,11 +11,6 @@ static __thread struct task_struct current_obj; bool debug_locks = true; bool debug_locks_silent; -__attribute__((constructor)) static void liblockdep_init(void) -{ - lockdep_init(); -} - __attribute__((destructor)) static void liblockdep_exit(void) { debug_check_no_locks_held(); diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h index a60c14b9662ae..6e66277ec4375 100644 --- a/tools/lib/lockdep/include/liblockdep/common.h +++ b/tools/lib/lockdep/include/liblockdep/common.h @@ -44,7 +44,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); extern void debug_check_no_locks_freed(const void *from, unsigned long len); -extern void lockdep_init(void); #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c index f42b7e9aa48f2..a0a2e3a266af8 100644 --- a/tools/lib/lockdep/lockdep.c +++ b/tools/lib/lockdep/lockdep.c @@ -1,2 +1,8 @@ #include + +/* Trivial API wrappers, we don't (yet) have RCU in user-space: */ +#define hlist_for_each_entry_rcu hlist_for_each_entry +#define hlist_add_head_rcu hlist_add_head +#define hlist_del_rcu hlist_del + #include "../../../kernel/locking/lockdep.c" diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index 21cdf869a01b8..52844847569c9 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -439,7 +439,5 @@ __attribute__((constructor)) static void init_preload(void) ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock"); #endif - lockdep_init(); - __init_state = done; } diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c index 0f782ff404ac6..18211a5f354fe 100644 --- a/tools/lib/lockdep/tests/AA.c +++ b/tools/lib/lockdep/tests/AA.c @@ -1,13 +1,13 @@ #include -void main(void) +int main(void) { - pthread_mutex_t a, b; + pthread_mutex_t a; pthread_mutex_init(&a, NULL); - pthread_mutex_init(&b, NULL); pthread_mutex_lock(&a); - pthread_mutex_lock(&b); pthread_mutex_lock(&a); + + return 0; } diff --git a/tools/lib/lockdep/tests/ABA.c b/tools/lib/lockdep/tests/ABA.c new file mode 100644 index 0000000000000..0f782ff404ac6 --- /dev/null +++ b/tools/lib/lockdep/tests/ABA.c @@ -0,0 +1,13 @@ +#include + +void main(void) +{ + pthread_mutex_t a, b; + + pthread_mutex_init(&a, NULL); + pthread_mutex_init(&b, NULL); + + pthread_mutex_lock(&a); + pthread_mutex_lock(&b); + pthread_mutex_lock(&a); +} diff --git a/tools/lib/lockdep/tests/ABBA_2threads.c b/tools/lib/lockdep/tests/ABBA_2threads.c new file mode 100644 index 0000000000000..cd807d7363611 --- /dev/null +++ b/tools/lib/lockdep/tests/ABBA_2threads.c @@ -0,0 +1,46 @@ +#include +#include + +pthread_mutex_t a = PTHREAD_MUTEX_INITIALIZER; +pthread_mutex_t b = PTHREAD_MUTEX_INITIALIZER; +pthread_barrier_t bar; + +void *ba_lock(void *arg) +{ + int ret, i; + + pthread_mutex_lock(&b); + + if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD) + pthread_barrier_destroy(&bar); + + pthread_mutex_lock(&a); + + pthread_mutex_unlock(&a); + pthread_mutex_unlock(&b); +} + +int main(void) +{ + pthread_t t; + + pthread_barrier_init(&bar, NULL, 2); + + if (pthread_create(&t, NULL, ba_lock, NULL)) { + fprintf(stderr, "pthread_create() failed\n"); + return 1; + } + pthread_mutex_lock(&a); + + if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD) + pthread_barrier_destroy(&bar); + + pthread_mutex_lock(&b); + + pthread_mutex_unlock(&b); + pthread_mutex_unlock(&a); + + pthread_join(t, NULL); + + return 0; +} diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h index 6386dc3182a09..fd3e56a83fc27 100644 --- a/tools/lib/lockdep/uinclude/linux/compiler.h +++ b/tools/lib/lockdep/uinclude/linux/compiler.h @@ -3,6 +3,7 @@ #define __used __attribute__((__unused__)) #define unlikely +#define READ_ONCE(x) (x) #define WRITE_ONCE(x, val) x=(val) #define RCU_INIT_POINTER(p, v) p=(v) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index c3bd294a63d1f..190cc886ab910 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -1951,6 +1951,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) strcmp(token, "*") == 0 || strcmp(token, "^") == 0 || strcmp(token, "/") == 0 || + strcmp(token, "%") == 0 || strcmp(token, "<") == 0 || strcmp(token, ">") == 0 || strcmp(token, "<=") == 0 || @@ -2397,6 +2398,12 @@ static int arg_num_eval(struct print_arg *arg, long long *val) break; *val = left + right; break; + case '~': + ret = arg_num_eval(arg->op.right, &right); + if (!ret) + break; + *val = ~right; + break; default: do_warning("unknown op '%s'", arg->op.op); ret = 0; @@ -2634,6 +2641,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok) free_field: free_arg(arg->hex.field); + arg->hex.field = NULL; out: *tok = NULL; return EVENT_ERROR; @@ -2658,8 +2666,10 @@ process_int_array(struct event_format *event, struct print_arg *arg, char **tok) free_size: free_arg(arg->int_array.count); + arg->int_array.count = NULL; free_field: free_arg(arg->int_array.field); + arg->int_array.field = NULL; out: *tok = NULL; return EVENT_ERROR; @@ -3689,6 +3699,9 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg case '/': val = left / right; break; + case '%': + val = left % right; + break; case '*': val = left * right; break; @@ -4971,7 +4984,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event break; } } - if (pevent->long_size == 8 && ls && + if (pevent->long_size == 8 && ls == 1 && sizeof(long) != 8) { char *p; @@ -5335,41 +5348,45 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock) return false; } -void pevent_print_event(struct pevent *pevent, struct trace_seq *s, - struct pevent_record *record, bool use_trace_clock) +/** + * pevent_find_event_by_record - return the event from a given record + * @pevent: a handle to the pevent + * @record: The record to get the event from + * + * Returns the associated event for a given record, or NULL if non is + * is found. + */ +struct event_format * +pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record) { - static const char *spaces = " "; /* 20 spaces */ - struct event_format *event; - unsigned long secs; - unsigned long usecs; - unsigned long nsecs; - const char *comm; - void *data = record->data; int type; - int pid; - int len; - int p; - bool use_usec_format; - - use_usec_format = is_timestamp_in_us(pevent->trace_clock, - use_trace_clock); - if (use_usec_format) { - secs = record->ts / NSECS_PER_SEC; - nsecs = record->ts - secs * NSECS_PER_SEC; - } if (record->size < 0) { do_warning("ug! negative record size %d", record->size); - return; + return NULL; } - type = trace_parse_common_type(pevent, data); + type = trace_parse_common_type(pevent, record->data); - event = pevent_find_event(pevent, type); - if (!event) { - do_warning("ug! no event found for type %d", type); - return; - } + return pevent_find_event(pevent, type); +} + +/** + * pevent_print_event_task - Write the event task comm, pid and CPU + * @pevent: a handle to the pevent + * @s: the trace_seq to write to + * @event: the handle to the record's event + * @record: The record to get the event from + * + * Writes the tasks comm, pid and CPU to @s. + */ +void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s, + struct event_format *event, + struct pevent_record *record) +{ + void *data = record->data; + const char *comm; + int pid; pid = parse_common_pid(pevent, data); comm = find_cmdline(pevent, pid); @@ -5377,9 +5394,43 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s, if (pevent->latency_format) { trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu); - pevent_data_lat_fmt(pevent, s, record); } else trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu); +} + +/** + * pevent_print_event_time - Write the event timestamp + * @pevent: a handle to the pevent + * @s: the trace_seq to write to + * @event: the handle to the record's event + * @record: The record to get the event from + * @use_trace_clock: Set to parse according to the @pevent->trace_clock + * + * Writes the timestamp of the record into @s. + */ +void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s, + struct event_format *event, + struct pevent_record *record, + bool use_trace_clock) +{ + unsigned long secs; + unsigned long usecs; + unsigned long nsecs; + int p; + bool use_usec_format; + + use_usec_format = is_timestamp_in_us(pevent->trace_clock, + use_trace_clock); + if (use_usec_format) { + secs = record->ts / NSECS_PER_SEC; + nsecs = record->ts - secs * NSECS_PER_SEC; + } + + if (pevent->latency_format) { + trace_seq_printf(s, " %3d", record->cpu); + pevent_data_lat_fmt(pevent, s, record); + } else + trace_seq_printf(s, " [%03d]", record->cpu); if (use_usec_format) { if (pevent->flags & PEVENT_NSEC_OUTPUT) { @@ -5387,14 +5438,36 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s, p = 9; } else { usecs = (nsecs + 500) / NSECS_PER_USEC; + /* To avoid usecs larger than 1 sec */ + if (usecs >= 1000000) { + usecs -= 1000000; + secs++; + } p = 6; } - trace_seq_printf(s, " %5lu.%0*lu: %s: ", - secs, p, usecs, event->name); + trace_seq_printf(s, " %5lu.%0*lu:", secs, p, usecs); } else - trace_seq_printf(s, " %12llu: %s: ", - record->ts, event->name); + trace_seq_printf(s, " %12llu:", record->ts); +} + +/** + * pevent_print_event_data - Write the event data section + * @pevent: a handle to the pevent + * @s: the trace_seq to write to + * @event: the handle to the record's event + * @record: The record to get the event from + * + * Writes the parsing of the record's data to @s. + */ +void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s, + struct event_format *event, + struct pevent_record *record) +{ + static const char *spaces = " "; /* 20 spaces */ + int len; + + trace_seq_printf(s, " %s: ", event->name); /* Space out the event names evenly. */ len = strlen(event->name); @@ -5404,6 +5477,23 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s, pevent_event_info(s, event, record); } +void pevent_print_event(struct pevent *pevent, struct trace_seq *s, + struct pevent_record *record, bool use_trace_clock) +{ + struct event_format *event; + + event = pevent_find_event_by_record(pevent, record); + if (!event) { + do_warning("ug! no event found for type %d", + trace_parse_common_type(pevent, record->data)); + return; + } + + pevent_print_event_task(pevent, s, event, record); + pevent_print_event_time(pevent, s, event, record, use_trace_clock); + pevent_print_event_data(pevent, s, event, record); +} + static int events_id_cmp(const void *a, const void *b) { struct event_format * const * ea = a; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 706d9bc24066c..9ffde377e89d9 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -628,6 +628,16 @@ int pevent_register_print_string(struct pevent *pevent, const char *fmt, unsigned long long addr); int pevent_pid_is_registered(struct pevent *pevent, int pid); +void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s, + struct event_format *event, + struct pevent_record *record); +void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s, + struct event_format *event, + struct pevent_record *record, + bool use_trace_clock); +void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s, + struct event_format *event, + struct pevent_record *record); void pevent_print_event(struct pevent *pevent, struct trace_seq *s, struct pevent_record *record, bool use_trace_clock); @@ -694,6 +704,9 @@ struct event_format *pevent_find_event(struct pevent *pevent, int id); struct event_format * pevent_find_event_by_name(struct pevent *pevent, const char *sys, const char *name); +struct event_format * +pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record); + void pevent_data_lat_fmt(struct pevent *pevent, struct trace_seq *s, struct pevent_record *record); int pevent_data_type(struct pevent *pevent, struct pevent_record *rec); diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index b9ca1e304158d..15949e2a7805c 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -8,7 +8,7 @@ perf-config - Get and set variables in a configuration file. SYNOPSIS -------- [verse] -'perf config' -l | --list +'perf config' [] -l | --list DESCRIPTION ----------- @@ -21,6 +21,14 @@ OPTIONS --list:: Show current config variables, name and value, for all sections. +--user:: + For writing and reading options: write to user + '$HOME/.perfconfig' file or read it. + +--system:: + For writing and reading options: write to system-wide + '$(sysconfdir)/perfconfig' or read it. + CONFIGURATION FILE ------------------ @@ -30,6 +38,10 @@ The '$HOME/.perfconfig' file is used to store a per-user configuration. The file '$(sysconfdir)/perfconfig' can be used to store a system-wide default configuration. +When reading or writing, the values are read from the system and user +configuration files by default, and options '--system' and '--user' +can be used to tell the command to read from or write to only that location. + Syntax ~~~~~~ @@ -62,7 +74,7 @@ Given a $HOME/.perfconfig like this: medium = green, default normal = lightgray, default selected = white, lightgray - code = blue, default + jump_arrows = blue, default addr = magenta, default root = white, blue @@ -98,6 +110,347 @@ Given a $HOME/.perfconfig like this: order = caller sort-key = function +Variables +~~~~~~~~~ + +colors.*:: + The variables for customizing the colors used in the output for the + 'report', 'top' and 'annotate' in the TUI. They should specify the + foreground and background colors, separated by a comma, for example: + + medium = green, lightgray + + If you want to use the color configured for you terminal, just leave it + as 'default', for example: + + medium = default, lightgray + + Available colors: + red, yellow, green, cyan, gray, black, blue, + white, default, magenta, lightgray + + colors.top:: + 'top' means a overhead percentage which is more than 5%. + And values of this variable specify percentage colors. + Basic key values are foreground-color 'red' and + background-color 'default'. + colors.medium:: + 'medium' means a overhead percentage which has more than 0.5%. + Default values are 'green' and 'default'. + colors.normal:: + 'normal' means the rest of overhead percentages + except 'top', 'medium', 'selected'. + Default values are 'lightgray' and 'default'. + colors.selected:: + This selects the colors for the current entry in a list of entries + from sub-commands (top, report, annotate). + Default values are 'black' and 'lightgray'. + colors.jump_arrows:: + Colors for jump arrows on assembly code listings + such as 'jns', 'jmp', 'jane', etc. + Default values are 'blue', 'default'. + colors.addr:: + This selects colors for addresses from 'annotate'. + Default values are 'magenta', 'default'. + colors.root:: + Colors for headers in the output of a sub-commands (top, report). + Default values are 'white', 'blue'. + +tui.*, gtk.*:: + Subcommands that can be configured here are 'top', 'report' and 'annotate'. + These values are booleans, for example: + + [tui] + top = true + + will make the TUI be the default for the 'top' subcommand. Those will be + available if the required libs were detected at tool build time. + +buildid.*:: + buildid.dir:: + Each executable and shared library in modern distributions comes with a + content based identifier that, if available, will be inserted in a + 'perf.data' file header to, at analysis time find what is needed to do + symbol resolution, code annotation, etc. + + The recording tools also stores a hard link or copy in a per-user + directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms + and /proc/kcore files to be used at analysis time. + + The buildid.dir variable can be used to either change this directory + cache location, or to disable it altogether. If you want to disable it, + set buildid.dir to /dev/null. The default is $HOME/.debug + +annotate.*:: + These options work only for TUI. + These are in control of addresses, jump function, source code + in lines of assembly code from a specific program. + + annotate.hide_src_code:: + If a program which is analyzed has source code, + this option lets 'annotate' print a list of assembly code with the source code. + For example, let's see a part of a program. There're four lines. + If this option is 'true', they can be printed + without source code from a program as below. + + │ push %rbp + │ mov %rsp,%rbp + │ sub $0x10,%rsp + │ mov (%rdi),%rdx + + But if this option is 'false', source code of the part + can be also printed as below. Default is 'false'. + + │ struct rb_node *rb_next(const struct rb_node *node) + │ { + │ push %rbp + │ mov %rsp,%rbp + │ sub $0x10,%rsp + │ struct rb_node *parent; + │ + │ if (RB_EMPTY_NODE(node)) + │ mov (%rdi),%rdx + │ return n; + + annotate.use_offset:: + Basing on a first address of a loaded function, offset can be used. + Instead of using original addresses of assembly code, + addresses subtracted from a base address can be printed. + Let's illustrate an example. + If a base address is 0XFFFFFFFF81624d50 as below, + + ffffffff81624d50 + + an address on assembly code has a specific absolute address as below + + ffffffff816250b8:│ mov 0x8(%r14),%rdi + + but if use_offset is 'true', an address subtracted from a base address is printed. + Default is true. This option is only applied to TUI. + + 368:│ mov 0x8(%r14),%rdi + + annotate.jump_arrows:: + There can be jump instruction among assembly code. + Depending on a boolean value of jump_arrows, + arrows can be printed or not which represent + where do the instruction jump into as below. + + │ ┌──jmp 1333 + │ │ xchg %ax,%ax + │1330:│ mov %r15,%r10 + │1333:└─→cmp %r15,%r14 + + If jump_arrow is 'false', the arrows isn't printed as below. + Default is 'false'. + + │ ↓ jmp 1333 + │ xchg %ax,%ax + │1330: mov %r15,%r10 + │1333: cmp %r15,%r14 + + annotate.show_linenr:: + When showing source code if this option is 'true', + line numbers are printed as below. + + │1628 if (type & PERF_SAMPLE_IDENTIFIER) { + │ ↓ jne 508 + │1628 data->id = *array; + │1629 array++; + │1630 } + + However if this option is 'false', they aren't printed as below. + Default is 'false'. + + │ if (type & PERF_SAMPLE_IDENTIFIER) { + │ ↓ jne 508 + │ data->id = *array; + │ array++; + │ } + + annotate.show_nr_jumps:: + Let's see a part of assembly code. + + │1382: movb $0x1,-0x270(%rbp) + + If use this, the number of branches jumping to that address can be printed as below. + Default is 'false'. + + │1 1382: movb $0x1,-0x270(%rbp) + + annotate.show_total_period:: + To compare two records on an instruction base, with this option + provided, display total number of samples that belong to a line + in assembly code. If this option is 'true', total periods are printed + instead of percent values as below. + + 302 │ mov %eax,%eax + + But if this option is 'false', percent values for overhead are printed i.e. + Default is 'false'. + + 99.93 │ mov %eax,%eax + +hist.*:: + hist.percentage:: + This option control the way to calculate overhead of filtered entries - + that means the value of this option is effective only if there's a + filter (by comm, dso or symbol name). Suppose a following example: + + Overhead Symbols + ........ ....... + 33.33% foo + 33.33% bar + 33.33% baz + + This is an original overhead and we'll filter out the first 'foo' + entry. The value of 'relative' would increase the overhead of 'bar' + and 'baz' to 50.00% for each, while 'absolute' would show their + current overhead (33.33%). + +ui.*:: + ui.show-headers:: + This option controls display of column headers (like 'Overhead' and 'Symbol') + in 'report' and 'top'. If this option is false, they are hidden. + This option is only applied to TUI. + +call-graph.*:: + When sub-commands 'top' and 'report' work with -g/—-children + there're options in control of call-graph. + + call-graph.record-mode:: + The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'. + The value of 'dwarf' is effective only if perf detect needed library + (libunwind or a recent version of libdw). + 'lbr' only work for cpus that support it. + + call-graph.dump-size:: + The size of stack to dump in order to do post-unwinding. Default is 8192 (byte). + When using dwarf into record-mode, the default size will be used if omitted. + + call-graph.print-type:: + The print-types can be graph (graph absolute), fractal (graph relative), + flat and folded. This option controls a way to show overhead for each callchain + entry. Suppose a following example. + + Overhead Symbols + ........ ....... + 40.00% foo + | + ---foo + | + |--50.00%--bar + | main + | + --50.00%--baz + main + + This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly + half and half so 'fractal' shows 50.00% for each + (meaning that it assumes 100% total overhead of 'foo'). + + The 'graph' uses absolute overhead value of 'foo' as total so each of + 'bar' and 'baz' callchain will have 20.00% of overhead. + If 'flat' is used, single column and linear exposure of call chains. + 'folded' mean call chains are displayed in a line, separated by semicolons. + + call-graph.order:: + This option controls print order of callchains. The default is + 'callee' which means callee is printed at top and then followed by its + caller and so on. The 'caller' prints it in reverse order. + + If this option is not set and report.children or top.children is + set to true (or the equivalent command line option is given), + the default value of this option is changed to 'caller' for the + execution of 'perf report' or 'perf top'. Other commands will + still default to 'callee'. + + call-graph.sort-key:: + The callchains are merged if they contain same information. + The sort-key option determines a way to compare the callchains. + A value of 'sort-key' can be 'function' or 'address'. + The default is 'function'. + + call-graph.threshold:: + When there're many callchains it'd print tons of lines. So perf omits + small callchains under a certain overhead (threshold) and this option + control the threshold. Default is 0.5 (%). The overhead is calculated + by value depends on call-graph.print-type. + + call-graph.print-limit:: + This is a maximum number of lines of callchain printed for a single + histogram entry. Default is 0 which means no limitation. + +report.*:: + report.percent-limit:: + This one is mostly the same as call-graph.threshold but works for + histogram entries. Entries having an overhead lower than this + percentage will not be printed. Default is '0'. If percent-limit + is '10', only entries which have more than 10% of overhead will be + printed. + + report.queue-size:: + This option sets up the maximum allocation size of the internal + event queue for ordering events. Default is 0, meaning no limit. + + report.children:: + 'Children' means functions called from another function. + If this option is true, 'perf report' cumulates callchains of children + and show (accumulated) total overhead as well as 'Self' overhead. + Please refer to the 'perf report' manual. The default is 'true'. + + report.group:: + This option is to show event group information together. + Example output with this turned on, notice that there is one column + per event in the group, ref-cycles and cycles: + + # group: {ref-cycles,cycles} + # ======== + # + # Samples: 7K of event 'anon group { ref-cycles, cycles }' + # Event count (approx.): 6876107743 + # + # Overhead Command Shared Object Symbol + # ................ ....... ................. ................... + # + 99.84% 99.76% noploop noploop [.] main + 0.07% 0.00% noploop ld-2.15.so [.] strcmp + 0.03% 0.00% noploop [kernel.kallsyms] [k] timerqueue_del + +top.*:: + top.children:: + Same as 'report.children'. So if it is enabled, the output of 'top' + command will have 'Children' overhead column as well as 'Self' overhead + column by default. + The default is 'true'. + +man.*:: + man.viewer:: + This option can assign a tool to view manual pages when 'help' + subcommand was invoked. Supported tools are 'man', 'woman' + (with emacs client) and 'konqueror'. Default is 'man'. + + New man viewer tool can be also added using 'man..cmd' + or use different path using 'man..path' config option. + +pager.*:: + pager.:: + When the subcommand is run on stdio, determine whether it uses + pager or not based on this value. Default is 'unspecified'. + +kmem.*:: + kmem.default:: + This option decides which allocator is to be analyzed if neither + '--slab' nor '--page' option is used. Default is 'slab'. + +record.*:: + record.build-id:: + This option can be 'cache', 'no-cache' or 'skip'. + 'cache' is to post-process data and save/update the binaries into + the build-id cache (in ~/.debug). This is the default. + But if this option is 'no-cache', it will not update the build-id cache. + 'skip' skips post-processing and does not update the cache. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt index 0b1cedeef8953..87b2588d1cbde 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -53,6 +53,13 @@ include::itrace.txt[] --strip:: Use with --itrace to strip out non-synthesized events. +-j:: +--jit:: + Process jitdump files by injecting the mmap records corresponding to jitted + functions. This option also generates the ELF images for each jitted function + found in the jitdumps files captured in the input perf.data file. Use this option + if you are monitoring environment using JIT runtimes, such as Java, DART or V8. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index fbceb631387c3..19aa17532a167 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo. --buildid-all:: Record build-id of all DSOs regardless whether it's actually hit or not. +--all-kernel:: +Configure all used events to run in kernel space. + +--all-user:: +Configure all used events to run in user space. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 8a301f6afb37a..12113992ac9d0 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,22 @@ OPTIONS And default sort keys are changed to comm, dso_from, symbol_from, dso_to and symbol_to, see '--branch-stack'. + If the --mem-mode option is used, the following sort keys are also available + (incompatible with --branch-stack): + symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline. + + - symbol_daddr: name of data symbol being executed on at the time of sample + - dso_daddr: name of library or module containing the data being executed + on at the time of the sample + - locked: whether the bus was locked at the time of the sample + - tlb: type of tlb access for the data at the time of the sample + - mem: type of memory access for the data at the time of the sample + - snoop: type of snoop (if any) for the data at the time of the sample + - dcacheline: the cacheline the data address is on at the time of the sample + + And the default sort keys are changed to local_weight, mem, sym, dso, + symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. + If the data file has tracepoint event(s), following (dynamic) sort keys are also available: trace, trace_fields, [.][/raw] @@ -151,22 +167,6 @@ OPTIONS By default, every sort keys not specified in -F will be appended automatically. - If --mem-mode option is used, following sort keys are also available - (incompatible with --branch-stack): - symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline. - - - symbol_daddr: name of data symbol being executed on at the time of sample - - dso_daddr: name of library or module containing the data being executed - on at the time of sample - - locked: whether the bus was locked at the time of sample - - tlb: type of tlb access for the data at the time of sample - - mem: type of memory access for the data at the time of sample - - snoop: type of snoop (if any) for the data at the time of sample - - dcacheline: the cacheline the data address is on at the time of sample - - And default sort keys are changed to local_weight, mem, sym, dso, - symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. - -p:: --parent=:: A regex filter to identify parent. The parent is a caller of this @@ -351,7 +351,10 @@ OPTIONS --percent-limit:: Do not show entries which have an overhead under that percent. - (Default: 0). + (Default: 0). Note that this option also sets the percent limit (threshold) + of callchains. However the default value of callchain threshold is + different than the default value of hist entries. Please see the + --call-graph option for details. --percentage:: Determine how to display the overhead percentage of filtered entries. @@ -398,6 +401,9 @@ include::itrace.txt[] --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +--hierarchy:: + Enable hierarchical output. + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 52ef7a9d50aac..04f23b404bbc5 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -69,6 +69,14 @@ report:: --scale:: scale/normalize counter values +-d:: +--detailed:: + print more detailed statistics, can be specified up to 3 times + + -d: detailed events, L1 and LLC data cache + -d -d: more detailed events, dTLB and iTLB events + -d -d -d: very detailed events, adding prefetch events + -r:: --repeat=:: repeat command and print average + stddev (max: 100). 0 means forever. @@ -139,6 +147,10 @@ Print count deltas every N milliseconds (minimum: 10ms) The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution. example: 'perf stat -I 1000 -e cycles -a sleep 5' +--metric-only:: +Only print computed metrics. Print them in a single line. +Don't show any raw values. Not supported with --per-thread. + --per-socket:: Aggregate counts per processor socket for system-wide mode measurements. This is a useful mode to detect imbalance between sockets. To enable this mode, @@ -211,6 +223,29 @@ $ perf stat -- make -j Wall-clock time elapsed: 719.554352 msecs +CSV FORMAT +---------- + +With -x, perf stat is able to output a not-quite-CSV format output +Commas in the output are not put into "". To make it easy to parse +it is recommended to use a different character like -x \; + +The fields are in this order: + + - optional usec time stamp in fractions of second (with -I xxx) + - optional CPU, core, or socket identifier + - optional number of logical CPUs aggregated + - counter value + - unit of the counter value or empty + - event name + - run time of counter + - percentage of measurement time the counter was running + - optional variance if multiple values are collected with -r + - optional metric value + - optional unit of metric + +Additional metrics may be printed with all earlier fields being empty. + SEE ALSO -------- linkperf:perf-top[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index b0e60e17db389..19f046f027cd8 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -233,6 +233,9 @@ Default is to monitor all CPUS. --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +--hierarchy:: + Enable hierarchy output. + INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example index 767ea2436e1cd..1d8d5bc4cd2de 100644 --- a/tools/perf/Documentation/perfconfig.example +++ b/tools/perf/Documentation/perfconfig.example @@ -5,7 +5,7 @@ medium = green, lightgray normal = black, lightgray selected = lightgray, magenta - code = blue, lightgray + jump_arrows = blue, lightgray addr = magenta, lightgray [tui] diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index e0ce9573b79bd..5950b5a24efdf 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -27,3 +27,4 @@ Skip collecing build-id when recording: perf record -B To change sampling frequency to 100 Hz: perf record -F 100 See assembly instructions with percentage: perf annotate If you prefer Intel style assembly, try: perf annotate -M intel +For hierarchical output, try: perf report --hierarchy diff --git a/tools/perf/Makefile b/tools/perf/Makefile index dcd9a70c7193b..32a64e6190288 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -68,6 +68,20 @@ all tags TAGS: $(print_msg) $(make) +ifdef MAKECMDGOALS +has_clean := 0 +ifneq ($(filter clean,$(MAKECMDGOALS)),) + has_clean := 1 +endif # clean + +ifeq ($(has_clean),1) + rest := $(filter-out clean,$(MAKECMDGOALS)) + ifneq ($(rest),) +$(rest): clean + endif # rest +endif # has_clean +endif # MAKECMDGOALS + # # The clean target is not really parallel, don't print the jobs info: # @@ -75,10 +89,17 @@ clean: $(make) # -# The build-test target is not really parallel, don't print the jobs info: +# The build-test target is not really parallel, don't print the jobs info, +# it also uses only the tests/make targets that don't pollute the source +# repository, i.e. that uses O= or builds the tarpkg outside the source +# repo directories. +# +# For a full test, use: +# +# make -C tools/perf -f tests/make # build-test: - @$(MAKE) SHUF=1 -f tests/make --no-print-directory + @$(MAKE) SHUF=1 -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile SET_PARALLEL=1 --no-print-directory tarpkg out # # All other targets get passed through: diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5d34815c7ccb8..4a4fad4182f53 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -58,6 +58,9 @@ include config/utilities.mak # # Define NO_LIBBIONIC if you do not want bionic support # +# Define NO_LIBCRYPTO if you do not want libcrypto (openssl) support +# used for generating build-ids for ELFs generated by jitdump. +# # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support # for dwarf backtrace post unwind. # @@ -136,6 +139,8 @@ $(call allow-override,CC,$(CROSS_COMPILE)gcc) $(call allow-override,AR,$(CROSS_COMPILE)ar) $(call allow-override,LD,$(CROSS_COMPILE)ld) +LD += $(EXTRA_LDFLAGS) + PKG_CONFIG = $(CROSS_COMPILE)pkg-config RM = rm -f @@ -165,7 +170,16 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) endif endif +# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. +# Without this setting the output feature dump file misses some features, for +# example, liberty. Select all checkers so we won't get an incomplete feature +# dump file. ifeq ($(config),1) +ifdef MAKECMDGOALS +ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump) +FEATURE_TESTS := all +endif +endif include config/Makefile endif @@ -618,7 +632,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \ - $(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c + $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile index 7fbca175099ec..18b13518d8d87 100644 --- a/tools/perf/arch/arm/Makefile +++ b/tools/perf/arch/arm/Makefile @@ -1,3 +1,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif +PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 7fbca175099ec..18b13518d8d87 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -1,3 +1,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif +PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 7fbca175099ec..56e05f126ad87 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,3 +1,6 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif + +HAVE_KVM_STAT_SUPPORT := 1 +PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 7b8b0d1a1b626..c8fe2074d2177 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,6 @@ libperf-y += header.o libperf-y += sym-handling.o +libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h new file mode 100644 index 0000000000000..0dd6b7f2d44f1 --- /dev/null +++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h @@ -0,0 +1,123 @@ +#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H +#define ARCH_PERF_BOOK3S_HV_HCALLS_H + +/* + * PowerPC HCALL codes : hcall code to name mapping + */ +#define kvm_trace_symbol_hcall \ + {0x4, "H_REMOVE"}, \ + {0x8, "H_ENTER"}, \ + {0xc, "H_READ"}, \ + {0x10, "H_CLEAR_MOD"}, \ + {0x14, "H_CLEAR_REF"}, \ + {0x18, "H_PROTECT"}, \ + {0x1c, "H_GET_TCE"}, \ + {0x20, "H_PUT_TCE"}, \ + {0x24, "H_SET_SPRG0"}, \ + {0x28, "H_SET_DABR"}, \ + {0x2c, "H_PAGE_INIT"}, \ + {0x30, "H_SET_ASR"}, \ + {0x34, "H_ASR_ON"}, \ + {0x38, "H_ASR_OFF"}, \ + {0x3c, "H_LOGICAL_CI_LOAD"}, \ + {0x40, "H_LOGICAL_CI_STORE"}, \ + {0x44, "H_LOGICAL_CACHE_LOAD"}, \ + {0x48, "H_LOGICAL_CACHE_STORE"}, \ + {0x4c, "H_LOGICAL_ICBI"}, \ + {0x50, "H_LOGICAL_DCBF"}, \ + {0x54, "H_GET_TERM_CHAR"}, \ + {0x58, "H_PUT_TERM_CHAR"}, \ + {0x5c, "H_REAL_TO_LOGICAL"}, \ + {0x60, "H_HYPERVISOR_DATA"}, \ + {0x64, "H_EOI"}, \ + {0x68, "H_CPPR"}, \ + {0x6c, "H_IPI"}, \ + {0x70, "H_IPOLL"}, \ + {0x74, "H_XIRR"}, \ + {0x78, "H_MIGRATE_DMA"}, \ + {0x7c, "H_PERFMON"}, \ + {0xdc, "H_REGISTER_VPA"}, \ + {0xe0, "H_CEDE"}, \ + {0xe4, "H_CONFER"}, \ + {0xe8, "H_PROD"}, \ + {0xec, "H_GET_PPP"}, \ + {0xf0, "H_SET_PPP"}, \ + {0xf4, "H_PURR"}, \ + {0xf8, "H_PIC"}, \ + {0xfc, "H_REG_CRQ"}, \ + {0x100, "H_FREE_CRQ"}, \ + {0x104, "H_VIO_SIGNAL"}, \ + {0x108, "H_SEND_CRQ"}, \ + {0x110, "H_COPY_RDMA"}, \ + {0x114, "H_REGISTER_LOGICAL_LAN"}, \ + {0x118, "H_FREE_LOGICAL_LAN"}, \ + {0x11c, "H_ADD_LOGICAL_LAN_BUFFER"}, \ + {0x120, "H_SEND_LOGICAL_LAN"}, \ + {0x124, "H_BULK_REMOVE"}, \ + {0x130, "H_MULTICAST_CTRL"}, \ + {0x134, "H_SET_XDABR"}, \ + {0x138, "H_STUFF_TCE"}, \ + {0x13c, "H_PUT_TCE_INDIRECT"}, \ + {0x14c, "H_CHANGE_LOGICAL_LAN_MAC"}, \ + {0x150, "H_VTERM_PARTNER_INFO"}, \ + {0x154, "H_REGISTER_VTERM"}, \ + {0x158, "H_FREE_VTERM"}, \ + {0x15c, "H_RESET_EVENTS"}, \ + {0x160, "H_ALLOC_RESOURCE"}, \ + {0x164, "H_FREE_RESOURCE"}, \ + {0x168, "H_MODIFY_QP"}, \ + {0x16c, "H_QUERY_QP"}, \ + {0x170, "H_REREGISTER_PMR"}, \ + {0x174, "H_REGISTER_SMR"}, \ + {0x178, "H_QUERY_MR"}, \ + {0x17c, "H_QUERY_MW"}, \ + {0x180, "H_QUERY_HCA"}, \ + {0x184, "H_QUERY_PORT"}, \ + {0x188, "H_MODIFY_PORT"}, \ + {0x18c, "H_DEFINE_AQP1"}, \ + {0x190, "H_GET_TRACE_BUFFER"}, \ + {0x194, "H_DEFINE_AQP0"}, \ + {0x198, "H_RESIZE_MR"}, \ + {0x19c, "H_ATTACH_MCQP"}, \ + {0x1a0, "H_DETACH_MCQP"}, \ + {0x1a4, "H_CREATE_RPT"}, \ + {0x1a8, "H_REMOVE_RPT"}, \ + {0x1ac, "H_REGISTER_RPAGES"}, \ + {0x1b0, "H_DISABLE_AND_GETC"}, \ + {0x1b4, "H_ERROR_DATA"}, \ + {0x1b8, "H_GET_HCA_INFO"}, \ + {0x1bc, "H_GET_PERF_COUNT"}, \ + {0x1c0, "H_MANAGE_TRACE"}, \ + {0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"}, \ + {0x1d8, "H_POLL_PENDING"}, \ + {0x1e4, "H_QUERY_INT_STATE"}, \ + {0x244, "H_ILLAN_ATTRIBUTES"}, \ + {0x250, "H_MODIFY_HEA_QP"}, \ + {0x254, "H_QUERY_HEA_QP"}, \ + {0x258, "H_QUERY_HEA"}, \ + {0x25c, "H_QUERY_HEA_PORT"}, \ + {0x260, "H_MODIFY_HEA_PORT"}, \ + {0x264, "H_REG_BCMC"}, \ + {0x268, "H_DEREG_BCMC"}, \ + {0x26c, "H_REGISTER_HEA_RPAGES"}, \ + {0x270, "H_DISABLE_AND_GET_HEA"}, \ + {0x274, "H_GET_HEA_INFO"}, \ + {0x278, "H_ALLOC_HEA_RESOURCE"}, \ + {0x284, "H_ADD_CONN"}, \ + {0x288, "H_DEL_CONN"}, \ + {0x298, "H_JOIN"}, \ + {0x2a4, "H_VASI_STATE"}, \ + {0x2b0, "H_ENABLE_CRQ"}, \ + {0x2b8, "H_GET_EM_PARMS"}, \ + {0x2d0, "H_SET_MPP"}, \ + {0x2d4, "H_GET_MPP"}, \ + {0x2ec, "H_HOME_NODE_ASSOCIATIVITY"}, \ + {0x2f4, "H_BEST_ENERGY"}, \ + {0x2fc, "H_XIRR_X"}, \ + {0x300, "H_RANDOM"}, \ + {0x304, "H_COP"}, \ + {0x314, "H_GET_MPP_X"}, \ + {0x31c, "H_SET_MODE"}, \ + {0xf000, "H_RTAS"} \ + +#endif diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h new file mode 100644 index 0000000000000..e68ba2da8970c --- /dev/null +++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h @@ -0,0 +1,33 @@ +#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H +#define ARCH_PERF_BOOK3S_HV_EXITS_H + +/* + * PowerPC Interrupt vectors : exit code to name mapping + */ + +#define kvm_trace_symbol_exit \ + {0x0, "RETURN_TO_HOST"}, \ + {0x100, "SYSTEM_RESET"}, \ + {0x200, "MACHINE_CHECK"}, \ + {0x300, "DATA_STORAGE"}, \ + {0x380, "DATA_SEGMENT"}, \ + {0x400, "INST_STORAGE"}, \ + {0x480, "INST_SEGMENT"}, \ + {0x500, "EXTERNAL"}, \ + {0x501, "EXTERNAL_LEVEL"}, \ + {0x502, "EXTERNAL_HV"}, \ + {0x600, "ALIGNMENT"}, \ + {0x700, "PROGRAM"}, \ + {0x800, "FP_UNAVAIL"}, \ + {0x900, "DECREMENTER"}, \ + {0x980, "HV_DECREMENTER"}, \ + {0xc00, "SYSCALL"}, \ + {0xd00, "TRACE"}, \ + {0xe00, "H_DATA_STORAGE"}, \ + {0xe20, "H_INST_STORAGE"}, \ + {0xe40, "H_EMUL_ASSIST"}, \ + {0xf00, "PERFMON"}, \ + {0xf20, "ALTIVEC"}, \ + {0xf40, "VSX"} + +#endif diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c new file mode 100644 index 0000000000000..74eee30398f80 --- /dev/null +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -0,0 +1,170 @@ +#include "util/kvm-stat.h" +#include "util/parse-events.h" +#include "util/debug.h" + +#include "book3s_hv_exits.h" +#include "book3s_hcalls.h" + +#define NR_TPS 4 + +const char *vcpu_id_str = "vcpu_id"; +const int decode_str_len = 40; +const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter"; +const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit"; + +define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit); +define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall); + +/* Tracepoints specific to ppc_book3s_hv */ +const char *ppc_book3s_hv_kvm_tp[] = { + "kvm_hv:kvm_guest_enter", + "kvm_hv:kvm_guest_exit", + "kvm_hv:kvm_hcall_enter", + "kvm_hv:kvm_hcall_exit", + NULL, +}; + +/* 1 extra placeholder for NULL */ +const char *kvm_events_tp[NR_TPS + 1]; +const char *kvm_exit_reason; + +static void hcall_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = perf_evsel__intval(evsel, sample, "req"); +} + +static const char *get_hcall_exit_reason(u64 exit_code) +{ + struct exit_reasons_table *tbl = hcall_reasons; + + while (tbl->reason != NULL) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; + } + + pr_debug("Unknown hcall code: %lld\n", + (unsigned long long)exit_code); + return "UNKNOWN"; +} + +static bool hcall_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return (!strcmp(evsel->name, kvm_events_tp[3])); +} + +static bool hcall_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (!strcmp(evsel->name, kvm_events_tp[2])) { + hcall_event_get_key(evsel, sample, key); + return true; + } + + return false; +} +static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + const char *hcall_reason = get_hcall_exit_reason(key->key); + + scnprintf(decode, decode_str_len, "%s", hcall_reason); +} + +static struct kvm_events_ops hcall_events = { + .is_begin_event = hcall_event_begin, + .is_end_event = hcall_event_end, + .decode_key = hcall_event_decode_key, + .name = "HCALL-EVENT", +}; + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { .name = "hcall", .ops = &hcall_events }, + { NULL, NULL }, +}; + +const char * const kvm_skip_events[] = { + NULL, +}; + + +static int is_tracepoint_available(const char *str, struct perf_evlist *evlist) +{ + struct parse_events_error err; + int ret; + + err.str = NULL; + ret = parse_events(evlist, str, &err); + if (err.str) + pr_err("%s : %s\n", str, err.str); + return ret; +} + +static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm, + struct perf_evlist *evlist) +{ + const char **events_ptr; + int i, nr_tp = 0, err = -1; + + /* Check for book3s_hv tracepoints */ + for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) { + err = is_tracepoint_available(*events_ptr, evlist); + if (err) + return -1; + nr_tp++; + } + + for (i = 0; i < nr_tp; i++) + kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i]; + + kvm_events_tp[i] = NULL; + kvm_exit_reason = "trap"; + kvm->exit_reasons = hv_exit_reasons; + kvm->exit_reasons_isa = "HV"; + + return 0; +} + +/* Wrapper to setup kvm tracepoints */ +static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm) +{ + struct perf_evlist *evlist = perf_evlist__new(); + + if (evlist == NULL) + return -ENOMEM; + + /* Right now, only supported on book3s_hv */ + return ppc__setup_book3s_hv(kvm, evlist); +} + +int setup_kvm_events_tp(struct perf_kvm_stat *kvm) +{ + return ppc__setup_kvm_tp(kvm); +} + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) +{ + int ret; + + ret = ppc__setup_kvm_tp(kvm); + if (ret) { + kvm->exit_reasons = NULL; + kvm->exit_reasons_isa = NULL; + } + + return ret; +} diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index a5dbc07ec9dc7..ed57df2e6d687 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -10,7 +10,7 @@ */ #include "../../util/kvm-stat.h" -#include +#include define_exit_reasons_table(sie_exit_reasons, sie_intercept_code); define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes); @@ -18,6 +18,12 @@ define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes); define_exit_reasons_table(sie_diagnose_codes, diagnose_codes); define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes); +const char *vcpu_id_str = "id"; +const int decode_str_len = 40; +const char *kvm_exit_reason = "icptcode"; +const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter"; +const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit"; + static void event_icpt_insn_get_key(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) @@ -73,7 +79,7 @@ static struct kvm_events_ops exit_events = { .name = "VM-EXIT" }; -const char * const kvm_events_tp[] = { +const char *kvm_events_tp[] = { "kvm:kvm_s390_sie_enter", "kvm:kvm_s390_sie_exit", "kvm:kvm_s390_intercept_instruction", diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 09ba923debe86..269af21437353 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1 endif HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 +PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index 7bb0d13c235f7..72193f19d6d75 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -59,7 +59,7 @@ static u64 mmap_read_self(void *addr) u64 quot, rem; quot = (cyc >> time_shift); - rem = cyc & ((1 << time_shift) - 1); + rem = cyc & (((u64)1 << time_shift) - 1); delta = time_offset + quot * time_mult + ((rem * time_mult) >> time_shift); @@ -103,6 +103,7 @@ static int __test__rdpmc(void) sigfillset(&sa.sa_mask); sa.sa_sigaction = segfault_handler; + sa.sa_flags = 0; sigaction(SIGSEGV, &sa, NULL); fd = sys_perf_event_open(&attr, 0, -1, -1, diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 8d8150f1cf9bc..d66f9ad4df2ea 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -60,7 +60,9 @@ struct branch { u64 misc; }; -static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused) +static size_t +intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return INTEL_BTS_AUXTRACE_PRIV_SIZE; } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index f05daacc9e781..a3395179c9eeb 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -89,7 +89,7 @@ static int intel_pt_parse_terms_with_default(struct list_head *formats, *config = attr.config; out_free: - parse_events__free_terms(terms); + parse_events_terms__delete(terms); return err; } @@ -273,7 +273,9 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) return attr; } -static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused) +static size_t +intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return INTEL_PT_AUXTRACE_PRIV_SIZE; } diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index 14e4e668fad73..b63d4be655a24 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -1,5 +1,7 @@ #include "../../util/kvm-stat.h" -#include +#include +#include +#include define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS); @@ -11,6 +13,12 @@ static struct kvm_events_ops exit_events = { .name = "VM-EXIT" }; +const char *vcpu_id_str = "vcpu_id"; +const int decode_str_len = 20; +const char *kvm_exit_reason = "exit_reason"; +const char *kvm_entry_trace = "kvm:kvm_entry"; +const char *kvm_exit_trace = "kvm:kvm_exit"; + /* * For the mmio events, we treat: * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry @@ -65,7 +73,7 @@ static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { - scnprintf(decode, DECODE_STR_LEN, "%#lx:%s", + scnprintf(decode, decode_str_len, "%#lx:%s", (unsigned long)key->key, key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); } @@ -109,7 +117,7 @@ static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { - scnprintf(decode, DECODE_STR_LEN, "%#llx:%s", + scnprintf(decode, decode_str_len, "%#llx:%s", (unsigned long long)key->key, key->info ? "POUT" : "PIN"); } @@ -121,7 +129,7 @@ static struct kvm_events_ops ioport_events = { .name = "IO Port Access" }; -const char * const kvm_events_tp[] = { +const char *kvm_events_tp[] = { "kvm:kvm_entry", "kvm:kvm_exit", "kvm:kvm_mmio", diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index e4c2c30143b95..5c3cce082cb88 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -1,6 +1,11 @@ + +/* Various wrappers to make the kernel .S file build in user-space: */ + #define memcpy MEMCPY /* don't hide glibc's memcpy() */ #define altinstr_replacement text #define globl p2align 4; .globl +#define _ASM_EXTABLE_FAULT(x, y) + #include "../../../arch/x86/lib/memcpy_64.S" /* * We need to provide note.GNU-stack section, saying that we want diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index cc5c1267c738d..cfe366375c4b8 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -245,7 +245,7 @@ static int __cmd_annotate(struct perf_annotate *ann) hists__collapse_resort(hists, NULL); /* Don't sort callchain */ perf_evsel__reset_sample_bit(pos, CALLCHAIN); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(pos, NULL); if (symbol_conf.event_group && !perf_evsel__is_group_leader(pos)) diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index d93bff7fc0e40..632efc6b79a07 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -38,19 +38,7 @@ static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) static int build_id_cache__kcore_dir(char *dir, size_t sz) { - struct timeval tv; - struct tm tm; - char dt[32]; - - if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm)) - return -1; - - if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm)) - return -1; - - scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); - - return 0; + return fetch_current_timestamp(dir, sz); } static bool same_kallsyms_reloc(const char *from_dir, char *to_dir) diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index f04e804a9fadc..c42448ed5dfe2 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -13,8 +13,10 @@ #include "util/util.h" #include "util/debug.h" +static bool use_system_config, use_user_config; + static const char * const config_usage[] = { - "perf config [options]", + "perf config [] [options]", NULL }; @@ -25,6 +27,8 @@ enum actions { static struct option config_options[] = { OPT_SET_UINT('l', "list", &actions, "show current config variables", ACTION_LIST), + OPT_BOOLEAN(0, "system", &use_system_config, "use system config file"), + OPT_BOOLEAN(0, "user", &use_user_config, "use user config file"), OPT_END() }; @@ -42,10 +46,23 @@ static int show_config(const char *key, const char *value, int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) { int ret = 0; + char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); argc = parse_options(argc, argv, config_options, config_usage, PARSE_OPT_STOP_AT_NON_OPTION); + if (use_system_config && use_user_config) { + pr_err("Error: only one config file at a time\n"); + parse_options_usage(config_usage, config_options, "user", 0); + parse_options_usage(NULL, config_options, "system", 0); + return -1; + } + + if (use_system_config) + config_exclusive_filename = perf_etc_perfconfig(); + else if (use_user_config) + config_exclusive_filename = user_config; + switch (actions) { case ACTION_LIST: if (argc) { @@ -53,9 +70,13 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) parse_options_usage(config_usage, config_options, "l", 1); } else { ret = perf_config(show_config, NULL); - if (ret < 0) + if (ret < 0) { + const char * config_filename = config_exclusive_filename; + if (!config_exclusive_filename) + config_filename = user_config; pr_err("Nothing configured, " - "please check your ~/.perfconfig file\n"); + "please check your %s \n", config_filename); + } } break; default: diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 36ccc2b8827fd..4d72359fd15ad 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1264,8 +1264,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) if (ret < 0) return ret; - perf_config(perf_default_config, NULL); - argc = parse_options(argc, argv, options, diff_usage, 0); if (symbol__init(NULL) < 0) diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 96c1a4cfbbbf6..49d55e21b1b06 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -86,8 +86,7 @@ static int check_emacsclient_version(void) return -1; } - strbuf_remove(&buffer, 0, strlen("emacsclient")); - version = atoi(buffer.buf); + version = atoi(buffer.buf + strlen("emacsclient")); if (version < 22) { fprintf(stderr, @@ -273,7 +272,7 @@ static int perf_help_config(const char *var, const char *value, void *cb) if (!prefixcmp(var, "man.")) return add_man_viewer_info(var, value); - return perf_default_config(var, value, cb); + return 0; } static struct cmdnames main_cmds, other_cmds; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 0022e02ed31a7..7fa68663ed728 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -17,6 +17,7 @@ #include "util/build-id.h" #include "util/data.h" #include "util/auxtrace.h" +#include "util/jit.h" #include @@ -29,6 +30,7 @@ struct perf_inject { bool sched_stat; bool have_auxtrace; bool strip; + bool jit_mode; const char *input_name; struct perf_data_file output; u64 bytes_written; @@ -71,6 +73,15 @@ static int perf_event__repipe_oe_synth(struct perf_tool *tool, return perf_event__repipe_synth(tool, event); } +#ifdef HAVE_JITDUMP +static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct ordered_events *oe __maybe_unused) +{ + return 0; +} +#endif + static int perf_event__repipe_op2_synth(struct perf_tool *tool, union perf_event *event, struct perf_session *session @@ -234,6 +245,31 @@ static int perf_event__repipe_mmap(struct perf_tool *tool, return err; } +#ifdef HAVE_JITDUMP +static int perf_event__jit_repipe_mmap(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct perf_inject *inject = container_of(tool, struct perf_inject, tool); + u64 n = 0; + int ret; + + /* + * if jit marker, then inject jit mmaps and generate ELF images + */ + ret = jit_process(inject->session, &inject->output, machine, + event->mmap.filename, sample->pid, &n); + if (ret < 0) + return ret; + if (ret) { + inject->bytes_written += n; + return 0; + } + return perf_event__repipe_mmap(tool, event, sample, machine); +} +#endif + static int perf_event__repipe_mmap2(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -247,6 +283,31 @@ static int perf_event__repipe_mmap2(struct perf_tool *tool, return err; } +#ifdef HAVE_JITDUMP +static int perf_event__jit_repipe_mmap2(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct perf_inject *inject = container_of(tool, struct perf_inject, tool); + u64 n = 0; + int ret; + + /* + * if jit marker, then inject jit mmaps and generate ELF images + */ + ret = jit_process(inject->session, &inject->output, machine, + event->mmap2.filename, sample->pid, &n); + if (ret < 0) + return ret; + if (ret) { + inject->bytes_written += n; + return 0; + } + return perf_event__repipe_mmap2(tool, event, sample, machine); +} +#endif + static int perf_event__repipe_fork(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -626,12 +687,16 @@ static int __cmd_inject(struct perf_inject *inject) ret = perf_session__process_events(session); if (!file_out->is_pipe) { - if (inject->build_ids) { + if (inject->build_ids) perf_header__set_feat(&session->header, HEADER_BUILD_ID); - if (inject->have_auxtrace) - dsos__hit_all(session); - } + /* + * Keep all buildids when there is unprocessed AUX data because + * it is not known which ones the AUX trace hits. + */ + if (perf_header__has_feat(&session->header, HEADER_BUILD_ID) && + inject->have_auxtrace && !inject->itrace_synth_opts.set) + dsos__hit_all(session); /* * The AUX areas have been removed and replaced with * synthesized hardware events, so clear the feature flag and @@ -703,7 +768,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) }; int ret; - const struct option options[] = { + struct option options[] = { OPT_BOOLEAN('b', "build-ids", &inject.build_ids, "Inject build-ids into the output stream"), OPT_STRING('i', "input", &inject.input_name, "file", @@ -713,6 +778,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat, "Merge sched-stat and sched-switch for getting events " "where and how long tasks slept"), +#ifdef HAVE_JITDUMP + OPT_BOOLEAN('j', "jit", &inject.jit_mode, "merge jitdump files into perf.data file"), +#endif OPT_INCR('v', "verbose", &verbose, "be more verbose (show build ids, etc)"), OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file", @@ -729,7 +797,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) "perf inject []", NULL }; - +#ifndef HAVE_JITDUMP + set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true); +#endif argc = parse_options(argc, argv, options, inject_usage, 0); /* @@ -755,6 +825,29 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) if (inject.session == NULL) return -1; + if (inject.build_ids) { + /* + * to make sure the mmap records are ordered correctly + * and so that the correct especially due to jitted code + * mmaps. We cannot generate the buildid hit list and + * inject the jit mmaps at the same time for now. + */ + inject.tool.ordered_events = true; + inject.tool.ordering_requires_timestamps = true; + } +#ifdef HAVE_JITDUMP + if (inject.jit_mode) { + inject.tool.mmap2 = perf_event__jit_repipe_mmap2; + inject.tool.mmap = perf_event__jit_repipe_mmap; + inject.tool.ordered_events = true; + inject.tool.ordering_requires_timestamps = true; + /* + * JIT MMAP injection injects all MMAP events in one go, so it + * does not obey finished_round semantics. + */ + inject.tool.finished_round = perf_event__drop_oe; + } +#endif ret = symbol__init(&inject.session->header.env); if (ret < 0) goto out_delete; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 118010553d0cf..4d3340cce9a02 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1834,7 +1834,7 @@ static int __cmd_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -static int kmem_config(const char *var, const char *value, void *cb) +static int kmem_config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "kmem.default")) { if (!strcmp(value, "slab")) @@ -1847,7 +1847,7 @@ static int kmem_config(const char *var, const char *value, void *cb) return 0; } - return perf_default_config(var, value, cb); + return 0; } int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 4418d92148721..bff666458b28e 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -30,7 +30,6 @@ #include #ifdef HAVE_KVM_STAT_SUPPORT -#include #include "util/kvm-stat.h" void exit_event_get_key(struct perf_evsel *evsel, @@ -38,12 +37,12 @@ void exit_event_get_key(struct perf_evsel *evsel, struct event_key *key) { key->info = 0; - key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON); + key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason); } bool kvm_exit_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, KVM_EXIT_TRACE); + return !strcmp(evsel->name, kvm_exit_trace); } bool exit_event_begin(struct perf_evsel *evsel, @@ -59,7 +58,7 @@ bool exit_event_begin(struct perf_evsel *evsel, bool kvm_entry_event(struct perf_evsel *evsel) { - return !strcmp(evsel->name, KVM_ENTRY_TRACE); + return !strcmp(evsel->name, kvm_entry_trace); } bool exit_event_end(struct perf_evsel *evsel, @@ -91,7 +90,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm, const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, key->key); - scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason); + scnprintf(decode, decode_str_len, "%s", exit_reason); } static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) @@ -357,7 +356,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, time_diff = sample->time - time_begin; if (kvm->duration && time_diff > kvm->duration) { - char decode[DECODE_STR_LEN]; + char decode[decode_str_len]; kvm->events_ops->decode_key(kvm, &event->key, decode); if (!skip_event(decode)) { @@ -385,7 +384,8 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, return NULL; } - vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID); + vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, + vcpu_id_str); thread__set_priv(thread, vcpu_record); } @@ -574,7 +574,7 @@ static void show_timeofday(void) static void print_result(struct perf_kvm_stat *kvm) { - char decode[DECODE_STR_LEN]; + char decode[decode_str_len]; struct kvm_event *event; int vcpu = kvm->trace_vcpu; @@ -585,7 +585,7 @@ static void print_result(struct perf_kvm_stat *kvm) pr_info("\n\n"); print_vcpu_info(kvm); - pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name); + pr_info("%*s ", decode_str_len, kvm->events_ops->name); pr_info("%10s ", "Samples"); pr_info("%9s ", "Samples%"); @@ -604,7 +604,7 @@ static void print_result(struct perf_kvm_stat *kvm) min = get_event_min(event, vcpu); kvm->events_ops->decode_key(kvm, &event->key, decode); - pr_info("%*s ", DECODE_STR_LEN, decode); + pr_info("%*s ", decode_str_len, decode); pr_info("%10llu ", (unsigned long long)ecount); pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100); pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100); @@ -1132,6 +1132,11 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) _p; \ }) +int __weak setup_kvm_events_tp(struct perf_kvm_stat *kvm __maybe_unused) +{ + return 0; +} + static int kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) { @@ -1148,7 +1153,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) NULL }; const char * const *events_tp; + int ret; + events_tp_size = 0; + ret = setup_kvm_events_tp(kvm); + if (ret < 0) { + pr_err("Unable to setup the kvm tracepoints\n"); + return ret; + } for (events_tp = kvm_events_tp; *events_tp; events_tp++) events_tp_size++; @@ -1377,6 +1389,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, /* * generate the event list */ + err = setup_kvm_events_tp(kvm); + if (err < 0) { + pr_err("Unable to setup the kvm tracepoints\n"); + return err; + } + kvm->evlist = kvm_live_event_list(); if (kvm->evlist == NULL) { err = -1; diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 3901700416966..88aeac9aa1da1 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -6,6 +6,8 @@ #include "util/tool.h" #include "util/session.h" #include "util/data.h" +#include "util/mem-events.h" +#include "util/debug.h" #define MEM_OPERATION_LOAD 0x1 #define MEM_OPERATION_STORE 0x2 @@ -21,11 +23,56 @@ struct perf_mem { DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; +static int parse_record_events(const struct option *opt, + const char *str, int unset __maybe_unused) +{ + struct perf_mem *mem = *(struct perf_mem **)opt->value; + int j; + + if (strcmp(str, "list")) { + if (!perf_mem_events__parse(str)) { + mem->operation = 0; + return 0; + } + exit(-1); + } + + for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { + struct perf_mem_event *e = &perf_mem_events[j]; + + fprintf(stderr, "%-13s%-*s%s\n", + e->tag, + verbose ? 25 : 0, + verbose ? perf_mem_events__name(j) : "", + e->supported ? ": available" : ""); + } + exit(0); +} + +static const char * const __usage[] = { + "perf mem record [] []", + "perf mem record [] -- []", + NULL +}; + +static const char * const *record_mem_usage = __usage; + static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) { int rec_argc, i = 0, j; const char **rec_argv; int ret; + struct option options[] = { + OPT_CALLBACK('e', "event", &mem, "event", + "event selector. use 'perf mem record -e list' to list available events", + parse_record_events), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_END() + }; + + argc = parse_options(argc, argv, options, record_mem_usage, + PARSE_OPT_STOP_AT_NON_OPTION); rec_argc = argc + 7; /* max number of arguments */ rec_argv = calloc(rec_argc + 1, sizeof(char *)); @@ -35,23 +82,40 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "record"; if (mem->operation & MEM_OPERATION_LOAD) + perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; + + if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; - if (mem->operation & MEM_OPERATION_LOAD) { - rec_argv[i++] = "-e"; - rec_argv[i++] = "cpu/mem-loads/pp"; - } + for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { + if (!perf_mem_events[j].record) + continue; + + if (!perf_mem_events[j].supported) { + pr_err("failed: event '%s' not supported\n", + perf_mem_events__name(j)); + return -1; + } - if (mem->operation & MEM_OPERATION_STORE) { rec_argv[i++] = "-e"; - rec_argv[i++] = "cpu/mem-stores/pp"; - } + rec_argv[i++] = perf_mem_events__name(j); + }; - for (j = 1; j < argc; j++, i++) + for (j = 0; j < argc; j++, i++) rec_argv[i] = argv[j]; + if (verbose > 0) { + pr_debug("calling: record "); + + while (rec_argv[j]) { + pr_debug("%s ", rec_argv[j]); + j++; + } + pr_debug("\n"); + } + ret = cmd_record(i, rec_argv, NULL); free(rec_argv); return ret; @@ -298,6 +362,10 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; + if (perf_mem_events__init()) { + pr_err("failed: memory events not supported\n"); + return -1; + } argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 319712a4e02b7..515510ecc76a4 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -32,6 +32,8 @@ #include "util/parse-branch-options.h" #include "util/parse-regs-options.h" #include "util/llvm-utils.h" +#include "util/bpf-loader.h" +#include "asm/bug.h" #include #include @@ -49,7 +51,9 @@ struct record { const char *progname; int realtime_prio; bool no_buildid; + bool no_buildid_set; bool no_buildid_cache; + bool no_buildid_cache_set; bool buildid_all; unsigned long long samples; }; @@ -320,7 +324,10 @@ static int record__open(struct record *rec) } else { pr_err("failed to mmap with %d (%s)\n", errno, strerror_r(errno, msg, sizeof(msg))); - rc = -errno; + if (errno) + rc = -errno; + else + rc = -EINVAL; } goto out; } @@ -464,6 +471,29 @@ static void record__init_features(struct record *rec) perf_header__clear_feat(&session->header, HEADER_STAT); } +static void +record__finish_output(struct record *rec) +{ + struct perf_data_file *file = &rec->file; + int fd = perf_data_file__fd(file); + + if (file->is_pipe) + return; + + rec->session->header.data_size += rec->bytes_written; + file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR); + + if (!rec->no_buildid) { + process_buildids(rec); + + if (rec->buildid_all) + dsos__hit_all(rec->session); + } + perf_session__write_header(rec->session, rec->evlist, fd, true); + + return; +} + static volatile int workload_exec_errno; /* @@ -482,6 +512,74 @@ static void workload_exec_failed_signal(int signo __maybe_unused, static void snapshot_sig_handler(int sig); +static int record__synthesize(struct record *rec) +{ + struct perf_session *session = rec->session; + struct machine *machine = &session->machines.host; + struct perf_data_file *file = &rec->file; + struct record_opts *opts = &rec->opts; + struct perf_tool *tool = &rec->tool; + int fd = perf_data_file__fd(file); + int err = 0; + + if (file->is_pipe) { + err = perf_event__synthesize_attrs(tool, session, + process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize attrs.\n"); + goto out; + } + + if (have_tracepoints(&rec->evlist->entries)) { + /* + * FIXME err <= 0 here actually means that + * there were no tracepoints so its not really + * an error, just that we don't need to + * synthesize anything. We really have to + * return this more properly and also + * propagate errors that now are calling die() + */ + err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist, + process_synthesized_event); + if (err <= 0) { + pr_err("Couldn't record tracing data.\n"); + goto out; + } + rec->bytes_written += err; + } + } + + if (rec->opts.full_auxtrace) { + err = perf_event__synthesize_auxtrace_info(rec->itr, tool, + session, process_synthesized_event); + if (err) + goto out; + } + + err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, + machine); + WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n" + "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" + "Check /proc/kallsyms permission or run as root.\n"); + + err = perf_event__synthesize_modules(tool, process_synthesized_event, + machine); + WARN_ONCE(err < 0, "Couldn't record kernel module information.\n" + "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" + "Check /proc/modules permission or run as root.\n"); + + if (perf_guest) { + machines__process_guests(&session->machines, + perf_event__synthesize_guest_os, tool); + } + + err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads, + process_synthesized_event, opts->sample_address, + opts->proc_map_timeout); +out: + return err; +} + static int __cmd_record(struct record *rec, int argc, const char **argv) { int err; @@ -534,6 +632,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } + err = bpf__apply_obj_config(); + if (err) { + char errbuf[BUFSIZ]; + + bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf)); + pr_err("ERROR: Apply config to BPF failed: %s\n", + errbuf); + goto out_child; + } + /* * Normally perf_session__new would do this, but it doesn't have the * evlist. @@ -566,63 +674,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) machine = &session->machines.host; - if (file->is_pipe) { - err = perf_event__synthesize_attrs(tool, session, - process_synthesized_event); - if (err < 0) { - pr_err("Couldn't synthesize attrs.\n"); - goto out_child; - } - - if (have_tracepoints(&rec->evlist->entries)) { - /* - * FIXME err <= 0 here actually means that - * there were no tracepoints so its not really - * an error, just that we don't need to - * synthesize anything. We really have to - * return this more properly and also - * propagate errors that now are calling die() - */ - err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist, - process_synthesized_event); - if (err <= 0) { - pr_err("Couldn't record tracing data.\n"); - goto out_child; - } - rec->bytes_written += err; - } - } - - if (rec->opts.full_auxtrace) { - err = perf_event__synthesize_auxtrace_info(rec->itr, tool, - session, process_synthesized_event); - if (err) - goto out_delete_session; - } - - err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, - machine); - if (err < 0) - pr_err("Couldn't record kernel reference relocation symbol\n" - "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" - "Check /proc/kallsyms permission or run as root.\n"); - - err = perf_event__synthesize_modules(tool, process_synthesized_event, - machine); + err = record__synthesize(rec); if (err < 0) - pr_err("Couldn't record kernel module information.\n" - "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" - "Check /proc/modules permission or run as root.\n"); - - if (perf_guest) { - machines__process_guests(&session->machines, - perf_event__synthesize_guest_os, tool); - } - - err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads, - process_synthesized_event, opts->sample_address, - opts->proc_map_timeout); - if (err != 0) goto out_child; if (rec->realtime_prio) { @@ -758,18 +811,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) /* this will be recalculated during process_buildids() */ rec->samples = 0; - if (!err && !file->is_pipe) { - rec->session->header.data_size += rec->bytes_written; - file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR); - - if (!rec->no_buildid) { - process_buildids(rec); - - if (rec->buildid_all) - dsos__hit_all(rec->session); - } - perf_session__write_header(rec->session, rec->evlist, fd, true); - } + if (!err) + record__finish_output(rec); if (!err && !quiet) { char samples[128]; @@ -1097,10 +1140,12 @@ struct option __record_options[] = { OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"), OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples, "don't sample"), - OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache, - "do not update the buildid cache"), - OPT_BOOLEAN('B', "no-buildid", &record.no_buildid, - "do not collect buildids in perf.data"), + OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache, + &record.no_buildid_cache_set, + "do not update the buildid cache"), + OPT_BOOLEAN_SET('B', "no-buildid", &record.no_buildid, + &record.no_buildid_set, + "do not collect buildids in perf.data"), OPT_CALLBACK('G', "cgroup", &record.evlist, "name", "monitor event in cgroup name only", parse_cgroups), @@ -1136,6 +1181,12 @@ struct option __record_options[] = { "per thread proc mmap processing timeout in ms"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), + OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel, + "Configure all used events to run in kernel space.", + PARSE_OPT_EXCLUSIVE), + OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user, + "Configure all used events to run in user space.", + PARSE_OPT_EXCLUSIVE), OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path", "clang binary to use for compiling BPF scriptlets"), OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options", diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 2bf537f190a02..7eea49f9ed46b 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -75,7 +75,10 @@ static int report__config(const char *var, const char *value, void *cb) return 0; } if (!strcmp(var, "report.percent-limit")) { - rep->min_percent = strtof(value, NULL); + double pcnt = strtof(value, NULL); + + rep->min_percent = pcnt; + callchain_param.min_percent = pcnt; return 0; } if (!strcmp(var, "report.children")) { @@ -87,7 +90,7 @@ static int report__config(const char *var, const char *value, void *cb) return 0; } - return perf_default_config(var, value, cb); + return 0; } static int hist_iter__report_callback(struct hist_entry_iter *iter, @@ -466,10 +469,11 @@ static int report__browse_hists(struct report *rep) return ret; } -static void report__collapse_hists(struct report *rep) +static int report__collapse_hists(struct report *rep) { struct ui_progress prog; struct perf_evsel *pos; + int ret = 0; ui_progress__init(&prog, rep->nr_entries, "Merging related events..."); @@ -481,7 +485,9 @@ static void report__collapse_hists(struct report *rep) hists->socket_filter = rep->socket_filter; - hists__collapse_resort(hists, &prog); + ret = hists__collapse_resort(hists, &prog); + if (ret < 0) + break; /* Non-group events are considered as leader */ if (symbol_conf.event_group && @@ -494,6 +500,7 @@ static void report__collapse_hists(struct report *rep) } ui_progress__finish(); + return ret; } static void report__output_resort(struct report *rep) @@ -504,7 +511,7 @@ static void report__output_resort(struct report *rep) ui_progress__init(&prog, rep->nr_entries, "Sorting events for output..."); evlist__for_each(rep->session->evlist, pos) - hists__output_resort(evsel__hists(pos), &prog); + perf_evsel__output_resort(pos, &prog); ui_progress__finish(); } @@ -561,7 +568,11 @@ static int __cmd_report(struct report *rep) } } - report__collapse_hists(rep); + ret = report__collapse_hists(rep); + if (ret) { + ui__error("failed to process hist entry\n"); + return ret; + } if (session_done()) return 0; @@ -633,8 +644,10 @@ parse_percent_limit(const struct option *opt, const char *str, int unset __maybe_unused) { struct report *rep = opt->value; + double pcnt = strtof(str, NULL); - rep->min_percent = strtof(str, NULL); + rep->min_percent = pcnt; + callchain_param.min_percent = pcnt; return 0; } @@ -798,6 +811,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "only show processor socket that match with this filter"), OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, "Show raw trace event output (do not use print fmt or plugins)"), + OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy, + "Show entries in a hierarchy"), OPT_END() }; struct perf_data_file file = { @@ -907,13 +922,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) symbol_conf.cumulate_callchain = false; } - if (setup_sorting(session->evlist) < 0) { - if (sort_order) - parse_options_usage(report_usage, options, "s", 1); - if (field_order) - parse_options_usage(sort_order ? NULL : report_usage, - options, "F", 1); - goto error; + if (symbol_conf.report_hierarchy) { + /* disable incompatible options */ + symbol_conf.event_group = false; + symbol_conf.cumulate_callchain = false; + + if (field_order) { + pr_err("Error: --hierarchy and --fields options cannot be used together\n"); + parse_options_usage(report_usage, options, "F", 1); + parse_options_usage(NULL, options, "hierarchy", 0); + goto error; + } + + sort__need_collapse = true; } /* Force tty output for header output and per-thread stat. */ @@ -925,6 +946,15 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) else use_browser = 0; + if (setup_sorting(session->evlist) < 0) { + if (sort_order) + parse_options_usage(report_usage, options, "s", 1); + if (field_order) + parse_options_usage(sort_order ? NULL : report_usage, + options, "F", 1); + goto error; + } + if (report.header || report.header_only) { perf_session__fprintf_info(session, stdout, report.show_full_info); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index c691214d820f0..57f9a7e7f7d3e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -23,6 +23,7 @@ #include "util/stat.h" #include #include "asm/bug.h" +#include "util/mem-events.h" static char const *script_name; static char const *generate_script_lang; @@ -58,6 +59,9 @@ enum perf_output_field { PERF_OUTPUT_IREGS = 1U << 14, PERF_OUTPUT_BRSTACK = 1U << 15, PERF_OUTPUT_BRSTACKSYM = 1U << 16, + PERF_OUTPUT_DATA_SRC = 1U << 17, + PERF_OUTPUT_WEIGHT = 1U << 18, + PERF_OUTPUT_BPF_OUTPUT = 1U << 19, }; struct output_option { @@ -81,6 +85,9 @@ struct output_option { {.str = "iregs", .field = PERF_OUTPUT_IREGS}, {.str = "brstack", .field = PERF_OUTPUT_BRSTACK}, {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM}, + {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC}, + {.str = "weight", .field = PERF_OUTPUT_WEIGHT}, + {.str = "bpf-output", .field = PERF_OUTPUT_BPF_OUTPUT}, }; /* default set to maintain compatibility with current format */ @@ -101,7 +108,7 @@ static struct { PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, - .invalid_fields = PERF_OUTPUT_TRACE, + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, [PERF_TYPE_SOFTWARE] = { @@ -111,7 +118,7 @@ static struct { PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -121,7 +128,7 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | - PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE, + PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE }, [PERF_TYPE_RAW] = { @@ -131,9 +138,10 @@ static struct { PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | + PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT, - .invalid_fields = PERF_OUTPUT_TRACE, + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, [PERF_TYPE_BREAKPOINT] = { @@ -145,7 +153,7 @@ static struct { PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, - .invalid_fields = PERF_OUTPUT_TRACE, + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, }; @@ -242,6 +250,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, PERF_OUTPUT_ADDR, allow_user_set)) return -EINVAL; + if (PRINT_FIELD(DATA_SRC) && + perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", + PERF_OUTPUT_DATA_SRC)) + return -EINVAL; + + if (PRINT_FIELD(WEIGHT) && + perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", + PERF_OUTPUT_WEIGHT)) + return -EINVAL; + if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { pr_err("Display of symbols requested but neither sample IP nor " "sample address\nis selected. Hence, no addresses to convert " @@ -608,6 +626,84 @@ static void print_sample_flags(u32 flags) printf(" %-4s ", str); } +struct printer_data { + int line_no; + bool hit_nul; + bool is_printable; +}; + +static void +print_sample_bpf_output_printer(enum binary_printer_ops op, + unsigned int val, + void *extra) +{ + unsigned char ch = (unsigned char)val; + struct printer_data *printer_data = extra; + + switch (op) { + case BINARY_PRINT_DATA_BEGIN: + printf("\n"); + break; + case BINARY_PRINT_LINE_BEGIN: + printf("%17s", !printer_data->line_no ? "BPF output:" : + " "); + break; + case BINARY_PRINT_ADDR: + printf(" %04x:", val); + break; + case BINARY_PRINT_NUM_DATA: + printf(" %02x", val); + break; + case BINARY_PRINT_NUM_PAD: + printf(" "); + break; + case BINARY_PRINT_SEP: + printf(" "); + break; + case BINARY_PRINT_CHAR_DATA: + if (printer_data->hit_nul && ch) + printer_data->is_printable = false; + + if (!isprint(ch)) { + printf("%c", '.'); + + if (!printer_data->is_printable) + break; + + if (ch == '\0') + printer_data->hit_nul = true; + else + printer_data->is_printable = false; + } else { + printf("%c", ch); + } + break; + case BINARY_PRINT_CHAR_PAD: + printf(" "); + break; + case BINARY_PRINT_LINE_END: + printf("\n"); + printer_data->line_no++; + break; + case BINARY_PRINT_DATA_END: + default: + break; + } +} + +static void print_sample_bpf_output(struct perf_sample *sample) +{ + unsigned int nr_bytes = sample->raw_size; + struct printer_data printer_data = {0, false, true}; + + print_binary(sample->raw_data, nr_bytes, 8, + print_sample_bpf_output_printer, &printer_data); + + if (printer_data.is_printable && printer_data.hit_nul) + printf("%17s \"%s\"\n", "BPF string:", + (char *)(sample->raw_data)); +} + struct perf_script { struct perf_tool tool; struct perf_session *session; @@ -634,6 +730,23 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist) return max; } +static size_t data_src__printf(u64 data_src) +{ + struct mem_info mi = { .data_src.val = data_src }; + char decode[100]; + char out[100]; + static int maxlen; + int len; + + perf_script__meminfo_scnprintf(decode, 100, &mi); + + len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode); + if (maxlen < len) + maxlen = len; + + return printf("%-*s", maxlen, out); +} + static void process_event(struct perf_script *script, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) @@ -673,6 +786,12 @@ static void process_event(struct perf_script *script, union perf_event *event, if (PRINT_FIELD(ADDR)) print_sample_addr(event, sample, thread, attr); + if (PRINT_FIELD(DATA_SRC)) + data_src__printf(sample->data_src); + + if (PRINT_FIELD(WEIGHT)) + printf("%16" PRIu64, sample->weight); + if (PRINT_FIELD(IP)) { if (!symbol_conf.use_callchain) printf(" "); @@ -692,6 +811,9 @@ static void process_event(struct perf_script *script, union perf_event *event, else if (PRINT_FIELD(BRSTACKSYM)) print_sample_brstacksym(event, sample, thread, attr); + if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) + print_sample_bpf_output(sample); + printf("\n"); } @@ -1090,23 +1212,6 @@ static struct script_spec *script_spec__find(const char *spec) return NULL; } -static struct script_spec *script_spec__findnew(const char *spec, - struct scripting_ops *ops) -{ - struct script_spec *s = script_spec__find(spec); - - if (s) - return s; - - s = script_spec__new(spec, ops); - if (!s) - return NULL; - - script_spec__add(s); - - return s; -} - int script_spec_register(const char *spec, struct scripting_ops *ops) { struct script_spec *s; @@ -1115,9 +1220,11 @@ int script_spec_register(const char *spec, struct scripting_ops *ops) if (s) return -1; - s = script_spec__findnew(spec, ops); + s = script_spec__new(spec, ops); if (!s) return -1; + else + script_spec__add(s); return 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 038e877081b68..1f19f2f999c84 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -122,6 +122,7 @@ static bool sync_run = false; static unsigned int initial_delay = 0; static unsigned int unit_width = 4; /* strlen("unit") */ static bool forever = false; +static bool metric_only = false; static struct timespec ref_time; static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; @@ -735,6 +736,191 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr) } } +struct outstate { + FILE *fh; + bool newline; + const char *prefix; + int nfields; + int id, nr; + struct perf_evsel *evsel; +}; + +#define METRIC_LEN 35 + +static void new_line_std(void *ctx) +{ + struct outstate *os = ctx; + + os->newline = true; +} + +static void do_new_line_std(struct outstate *os) +{ + fputc('\n', os->fh); + fputs(os->prefix, os->fh); + aggr_printout(os->evsel, os->id, os->nr); + if (stat_config.aggr_mode == AGGR_NONE) + fprintf(os->fh, " "); + fprintf(os->fh, " "); +} + +static void print_metric_std(void *ctx, const char *color, const char *fmt, + const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + int n; + bool newline = os->newline; + + os->newline = false; + + if (unit == NULL || fmt == NULL) { + fprintf(out, "%-*s", METRIC_LEN, ""); + return; + } + + if (newline) + do_new_line_std(os); + + n = fprintf(out, " # "); + if (color) + n += color_fprintf(out, color, fmt, val); + else + n += fprintf(out, fmt, val); + fprintf(out, " %-*s", METRIC_LEN - n - 1, unit); +} + +static void new_line_csv(void *ctx) +{ + struct outstate *os = ctx; + int i; + + fputc('\n', os->fh); + if (os->prefix) + fprintf(os->fh, "%s%s", os->prefix, csv_sep); + aggr_printout(os->evsel, os->id, os->nr); + for (i = 0; i < os->nfields; i++) + fputs(csv_sep, os->fh); +} + +static void print_metric_csv(void *ctx, + const char *color __maybe_unused, + const char *fmt, const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + char buf[64], *vals, *ends; + + if (unit == NULL || fmt == NULL) { + fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep); + return; + } + snprintf(buf, sizeof(buf), fmt, val); + vals = buf; + while (isspace(*vals)) + vals++; + ends = vals; + while (isdigit(*ends) || *ends == '.') + ends++; + *ends = 0; + while (isspace(*unit)) + unit++; + fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit); +} + +#define METRIC_ONLY_LEN 20 + +/* Filter out some columns that don't work well in metrics only mode */ + +static bool valid_only_metric(const char *unit) +{ + if (!unit) + return false; + if (strstr(unit, "/sec") || + strstr(unit, "hz") || + strstr(unit, "Hz") || + strstr(unit, "CPUs utilized")) + return false; + return true; +} + +static const char *fixunit(char *buf, struct perf_evsel *evsel, + const char *unit) +{ + if (!strncmp(unit, "of all", 6)) { + snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel), + unit); + return buf; + } + return unit; +} + +static void print_metric_only(void *ctx, const char *color, const char *fmt, + const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + int n; + char buf[1024]; + unsigned mlen = METRIC_ONLY_LEN; + + if (!valid_only_metric(unit)) + return; + unit = fixunit(buf, os->evsel, unit); + if (color) + n = color_fprintf(out, color, fmt, val); + else + n = fprintf(out, fmt, val); + if (n > METRIC_ONLY_LEN) + n = METRIC_ONLY_LEN; + if (mlen < strlen(unit)) + mlen = strlen(unit) + 1; + fprintf(out, "%*s", mlen - n, ""); +} + +static void print_metric_only_csv(void *ctx, const char *color __maybe_unused, + const char *fmt, + const char *unit, double val) +{ + struct outstate *os = ctx; + FILE *out = os->fh; + char buf[64], *vals, *ends; + char tbuf[1024]; + + if (!valid_only_metric(unit)) + return; + unit = fixunit(tbuf, os->evsel, unit); + snprintf(buf, sizeof buf, fmt, val); + vals = buf; + while (isspace(*vals)) + vals++; + ends = vals; + while (isdigit(*ends) || *ends == '.') + ends++; + *ends = 0; + fprintf(out, "%s%s", vals, csv_sep); +} + +static void new_line_metric(void *ctx __maybe_unused) +{ +} + +static void print_metric_header(void *ctx, const char *color __maybe_unused, + const char *fmt __maybe_unused, + const char *unit, double val __maybe_unused) +{ + struct outstate *os = ctx; + char tbuf[1024]; + + if (!valid_only_metric(unit)) + return; + unit = fixunit(tbuf, os->evsel, unit); + if (csv_output) + fprintf(os->fh, "%s%s", unit, csv_sep); + else + fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit); +} + static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) { FILE *output = stat_config.output; @@ -763,6 +949,28 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); } +static int first_shadow_cpu(struct perf_evsel *evsel, int id) +{ + int i; + + if (!aggr_get_id) + return 0; + + if (stat_config.aggr_mode == AGGR_NONE) + return id; + + if (stat_config.aggr_mode == AGGR_GLOBAL) + return 0; + + for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) { + int cpu2 = perf_evsel__cpus(evsel)->map[i]; + + if (aggr_get_id(evsel_list->cpus, cpu2) == id) + return cpu2; + } + return 0; +} + static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) { FILE *output = stat_config.output; @@ -793,22 +1001,124 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); } -static void printout(int id, int nr, struct perf_evsel *counter, double uval) +static void printout(int id, int nr, struct perf_evsel *counter, double uval, + char *prefix, u64 run, u64 ena, double noise) { - int cpu = cpu_map__id_to_cpu(id); + struct perf_stat_output_ctx out; + struct outstate os = { + .fh = stat_config.output, + .prefix = prefix ? prefix : "", + .id = id, + .nr = nr, + .evsel = counter, + }; + print_metric_t pm = print_metric_std; + void (*nl)(void *); - if (stat_config.aggr_mode == AGGR_GLOBAL) - cpu = 0; + if (metric_only) { + nl = new_line_metric; + if (csv_output) + pm = print_metric_only_csv; + else + pm = print_metric_only; + } else + nl = new_line_std; + + if (csv_output && !metric_only) { + static int aggr_fields[] = { + [AGGR_GLOBAL] = 0, + [AGGR_THREAD] = 1, + [AGGR_NONE] = 1, + [AGGR_SOCKET] = 2, + [AGGR_CORE] = 2, + }; + + pm = print_metric_csv; + nl = new_line_csv; + os.nfields = 3; + os.nfields += aggr_fields[stat_config.aggr_mode]; + if (counter->cgrp) + os.nfields++; + } + if (run == 0 || ena == 0 || counter->counts->scaled == -1) { + if (metric_only) { + pm(&os, NULL, "", "", 0); + return; + } + aggr_printout(counter, id, nr); + + fprintf(stat_config.output, "%*s%s", + csv_output ? 0 : 18, + counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, + csv_sep); + + fprintf(stat_config.output, "%-*s%s", + csv_output ? 0 : unit_width, + counter->unit, csv_sep); + + fprintf(stat_config.output, "%*s", + csv_output ? 0 : -25, + perf_evsel__name(counter)); + + if (counter->cgrp) + fprintf(stat_config.output, "%s%s", + csv_sep, counter->cgrp->name); - if (nsec_counter(counter)) + if (!csv_output) + pm(&os, NULL, NULL, "", 0); + print_noise(counter, noise); + print_running(run, ena); + if (csv_output) + pm(&os, NULL, NULL, "", 0); + return; + } + + if (metric_only) + /* nothing */; + else if (nsec_counter(counter)) nsec_printout(id, nr, counter, uval); else abs_printout(id, nr, counter, uval); - if (!csv_output && !stat_config.interval) - perf_stat__print_shadow_stats(stat_config.output, counter, - uval, cpu, - stat_config.aggr_mode); + out.print_metric = pm; + out.new_line = nl; + out.ctx = &os; + + if (csv_output && !metric_only) { + print_noise(counter, noise); + print_running(run, ena); + } + + perf_stat__print_shadow_stats(counter, uval, + first_shadow_cpu(counter, id), + &out); + if (!csv_output && !metric_only) { + print_noise(counter, noise); + print_running(run, ena); + } +} + +static void aggr_update_shadow(void) +{ + int cpu, s2, id, s; + u64 val; + struct perf_evsel *counter; + + for (s = 0; s < aggr_map->nr; s++) { + id = aggr_map->map[s]; + evlist__for_each(evsel_list, counter) { + val = 0; + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + s2 = aggr_get_id(evsel_list->cpus, cpu); + if (s2 != id) + continue; + val += perf_counts(counter->counts, cpu, 0)->val; + } + val = val * counter->scale; + perf_stat__update_shadow_stats(counter, &val, + first_shadow_cpu(counter, id)); + } + } } static void print_aggr(char *prefix) @@ -818,12 +1128,23 @@ static void print_aggr(char *prefix) int cpu, s, s2, id, nr; double uval; u64 ena, run, val; + bool first; if (!(aggr_map || aggr_get_id)) return; + aggr_update_shadow(); + + /* + * With metric_only everything is on a single line. + * Without each counter has its own line. + */ for (s = 0; s < aggr_map->nr; s++) { + if (prefix && metric_only) + fprintf(output, "%s", prefix); + id = aggr_map->map[s]; + first = true; evlist__for_each(evsel_list, counter) { val = ena = run = 0; nr = 0; @@ -836,41 +1157,20 @@ static void print_aggr(char *prefix) run += perf_counts(counter->counts, cpu, 0)->run; nr++; } - if (prefix) - fprintf(output, "%s", prefix); - - if (run == 0 || ena == 0) { + if (first && metric_only) { + first = false; aggr_printout(counter, id, nr); - - fprintf(output, "%*s%s", - csv_output ? 0 : 18, - counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, - csv_sep); - - fprintf(output, "%-*s%s", - csv_output ? 0 : unit_width, - counter->unit, csv_sep); - - fprintf(output, "%*s", - csv_output ? 0 : -25, - perf_evsel__name(counter)); - - if (counter->cgrp) - fprintf(output, "%s%s", - csv_sep, counter->cgrp->name); - - print_running(run, ena); - fputc('\n', output); - continue; } - uval = val * counter->scale; - printout(id, nr, counter, uval); - if (!csv_output) - print_noise(counter, 1.0); + if (prefix && !metric_only) + fprintf(output, "%s", prefix); - print_running(run, ena); - fputc('\n', output); + uval = val * counter->scale; + printout(id, nr, counter, uval, prefix, run, ena, 1.0); + if (!metric_only) + fputc('\n', output); } + if (metric_only) + fputc('\n', output); } } @@ -895,12 +1195,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(thread, 0, counter, uval); - - if (!csv_output) - print_noise(counter, 1.0); - - print_running(run, ena); + printout(thread, 0, counter, uval, prefix, run, ena, 1.0); fputc('\n', output); } } @@ -914,43 +1209,19 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) FILE *output = stat_config.output; struct perf_stat_evsel *ps = counter->priv; double avg = avg_stats(&ps->res_stats[0]); - int scaled = counter->counts->scaled; double uval; double avg_enabled, avg_running; avg_enabled = avg_stats(&ps->res_stats[1]); avg_running = avg_stats(&ps->res_stats[2]); - if (prefix) + if (prefix && !metric_only) fprintf(output, "%s", prefix); - if (scaled == -1 || !counter->supported) { - fprintf(output, "%*s%s", - csv_output ? 0 : 18, - counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, - csv_sep); - fprintf(output, "%-*s%s", - csv_output ? 0 : unit_width, - counter->unit, csv_sep); - fprintf(output, "%*s", - csv_output ? 0 : -25, - perf_evsel__name(counter)); - - if (counter->cgrp) - fprintf(output, "%s%s", csv_sep, counter->cgrp->name); - - print_running(avg_running, avg_enabled); - fputc('\n', output); - return; - } - uval = avg * counter->scale; - printout(-1, 0, counter, uval); - - print_noise(counter, avg); - - print_running(avg_running, avg_enabled); - fprintf(output, "\n"); + printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg); + if (!metric_only) + fprintf(output, "\n"); } /* @@ -972,39 +1243,78 @@ static void print_counter(struct perf_evsel *counter, char *prefix) if (prefix) fprintf(output, "%s", prefix); - if (run == 0 || ena == 0) { - fprintf(output, "CPU%*d%s%*s%s", - csv_output ? 0 : -4, - perf_evsel__cpus(counter)->map[cpu], csv_sep, - csv_output ? 0 : 18, - counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, - csv_sep); + uval = val * counter->scale; + printout(cpu, 0, counter, uval, prefix, run, ena, 1.0); - fprintf(output, "%-*s%s", - csv_output ? 0 : unit_width, - counter->unit, csv_sep); + fputc('\n', output); + } +} - fprintf(output, "%*s", - csv_output ? 0 : -25, - perf_evsel__name(counter)); +static void print_no_aggr_metric(char *prefix) +{ + int cpu; + int nrcpus = 0; + struct perf_evsel *counter; + u64 ena, run, val; + double uval; - if (counter->cgrp) - fprintf(output, "%s%s", - csv_sep, counter->cgrp->name); + nrcpus = evsel_list->cpus->nr; + for (cpu = 0; cpu < nrcpus; cpu++) { + bool first = true; - print_running(run, ena); - fputc('\n', output); - continue; + if (prefix) + fputs(prefix, stat_config.output); + evlist__for_each(evsel_list, counter) { + if (first) { + aggr_printout(counter, cpu, 0); + first = false; + } + val = perf_counts(counter->counts, cpu, 0)->val; + ena = perf_counts(counter->counts, cpu, 0)->ena; + run = perf_counts(counter->counts, cpu, 0)->run; + + uval = val * counter->scale; + printout(cpu, 0, counter, uval, prefix, run, ena, 1.0); } + fputc('\n', stat_config.output); + } +} - uval = val * counter->scale; - printout(cpu, 0, counter, uval); - if (!csv_output) - print_noise(counter, 1.0); - print_running(run, ena); +static int aggr_header_lens[] = { + [AGGR_CORE] = 18, + [AGGR_SOCKET] = 12, + [AGGR_NONE] = 6, + [AGGR_THREAD] = 24, + [AGGR_GLOBAL] = 0, +}; - fputc('\n', output); +static void print_metric_headers(char *prefix) +{ + struct perf_stat_output_ctx out; + struct perf_evsel *counter; + struct outstate os = { + .fh = stat_config.output + }; + + if (prefix) + fprintf(stat_config.output, "%s", prefix); + + if (!csv_output) + fprintf(stat_config.output, "%*s", + aggr_header_lens[stat_config.aggr_mode], ""); + + /* Print metrics headers only */ + evlist__for_each(evsel_list, counter) { + os.evsel = counter; + out.ctx = &os; + out.print_metric = print_metric_header; + out.new_line = new_line_metric; + os.evsel = counter; + perf_stat__print_shadow_stats(counter, 0, + 0, + &out); } + fputc('\n', stat_config.output); } static void print_interval(char *prefix, struct timespec *ts) @@ -1014,7 +1324,7 @@ static void print_interval(char *prefix, struct timespec *ts) sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep); - if (num_print_interval == 0 && !csv_output) { + if (num_print_interval == 0 && !csv_output && !metric_only) { switch (stat_config.aggr_mode) { case AGGR_SOCKET: fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit"); @@ -1101,6 +1411,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) else print_header(argc, argv); + if (metric_only) { + static int num_print_iv; + + if (num_print_iv == 0) + print_metric_headers(prefix); + if (num_print_iv++ == 25) + num_print_iv = 0; + if (stat_config.aggr_mode == AGGR_GLOBAL && prefix) + fprintf(stat_config.output, "%s", prefix); + } + switch (stat_config.aggr_mode) { case AGGR_CORE: case AGGR_SOCKET: @@ -1113,10 +1434,16 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) case AGGR_GLOBAL: evlist__for_each(evsel_list, counter) print_counter_aggr(counter, prefix); + if (metric_only) + fputc('\n', stat_config.output); break; case AGGR_NONE: - evlist__for_each(evsel_list, counter) - print_counter(counter, prefix); + if (metric_only) + print_no_aggr_metric(prefix); + else { + evlist__for_each(evsel_list, counter) + print_counter(counter, prefix); + } break; case AGGR_UNSET: default: @@ -1237,6 +1564,8 @@ static const struct option stat_options[] = { "aggregate counts per thread", AGGR_THREAD), OPT_UINTEGER('D', "delay", &initial_delay, "ms to wait before starting measurement after program start"), + OPT_BOOLEAN(0, "metric-only", &metric_only, + "Only print computed metrics. No raw values"), OPT_END() }; @@ -1435,7 +1764,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) */ static int add_default_attributes(void) { - struct perf_event_attr default_attrs[] = { + struct perf_event_attr default_attrs0[] = { { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES }, @@ -1443,8 +1772,14 @@ static int add_default_attributes(void) { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, +}; + struct perf_event_attr frontend_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, +}; + struct perf_event_attr backend_attrs[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + struct perf_event_attr default_attrs1[] = { { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, @@ -1561,7 +1896,19 @@ static int add_default_attributes(void) } if (!evsel_list->nr_entries) { - if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0) + if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0) + return -1; + if (pmu_have_event("cpu", "stalled-cycles-frontend")) { + if (perf_evlist__add_default_attrs(evsel_list, + frontend_attrs) < 0) + return -1; + } + if (pmu_have_event("cpu", "stalled-cycles-backend")) { + if (perf_evlist__add_default_attrs(evsel_list, + backend_attrs) < 0) + return -1; + } + if (perf_evlist__add_default_attrs(evsel_list, default_attrs1) < 0) return -1; } @@ -1825,9 +2172,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (evsel_list == NULL) return -ENOMEM; + parse_events__shrink_config_terms(); argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands, (const char **) stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); + perf_stat__init_shadow_stats(); if (csv_sep) { csv_output = true; @@ -1858,6 +2207,16 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) goto out; } + if (metric_only && stat_config.aggr_mode == AGGR_THREAD) { + fprintf(stderr, "--metric-only is not supported with --per-thread\n"); + goto out; + } + + if (metric_only && run_count > 1) { + fprintf(stderr, "--metric-only is not supported with -r\n"); + goto out; + } + if (output_fd < 0) { fprintf(stderr, "argument to --log-fd must be a > 0\n"); parse_options_usage(stat_usage, stat_options, "log-fd", 0); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index bf01cbb0ef236..94af190f6843d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -252,7 +252,8 @@ static void perf_top__print_sym_table(struct perf_top *top) char bf[160]; int printed = 0; const int win_width = top->winsize.ws_col - 1; - struct hists *hists = evsel__hists(top->sym_evsel); + struct perf_evsel *evsel = top->sym_evsel; + struct hists *hists = evsel__hists(evsel); puts(CONSOLE_CLEAR); @@ -288,7 +289,7 @@ static void perf_top__print_sym_table(struct perf_top *top) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); @@ -540,6 +541,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) static void perf_top__sort_new_samples(void *arg) { struct perf_top *t = arg; + struct perf_evsel *evsel = t->sym_evsel; struct hists *hists; perf_top__reset_sample_counters(t); @@ -547,7 +549,7 @@ static void perf_top__sort_new_samples(void *arg) if (t->evlist->selected != NULL) t->sym_evsel = t->evlist->selected; - hists = evsel__hists(t->sym_evsel); + hists = evsel__hists(evsel); if (t->evlist->enabled) { if (t->zero) { @@ -559,7 +561,7 @@ static void perf_top__sort_new_samples(void *arg) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); } static void *display_thread_tui(void *arg) @@ -1063,7 +1065,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) return parse_callchain_top_opt(arg); } -static int perf_top_config(const char *var, const char *value, void *cb) +static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "top.call-graph")) var = "call-graph.record-mode"; /* fall-through */ @@ -1072,7 +1074,7 @@ static int perf_top_config(const char *var, const char *value, void *cb) return 0; } - return perf_default_config(var, value, cb); + return 0; } static int @@ -1212,6 +1214,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) parse_branch_stack), OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, "Show raw trace event output (do not use print fmt or plugins)"), + OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy, + "Show entries in a hierarchy"), OPT_END() }; const char * const top_usage[] = { @@ -1239,10 +1243,30 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) goto out_delete_evlist; } + if (symbol_conf.report_hierarchy) { + /* disable incompatible options */ + symbol_conf.event_group = false; + symbol_conf.cumulate_callchain = false; + + if (field_order) { + pr_err("Error: --hierarchy and --fields options cannot be used together\n"); + parse_options_usage(top_usage, options, "fields", 0); + parse_options_usage(NULL, options, "hierarchy", 0); + goto out_delete_evlist; + } + } + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ sort__need_collapse = 1; + if (top.use_stdio) + use_browser = 0; + else if (top.use_tui) + use_browser = 1; + + setup_browser(false); + if (setup_sorting(top.evlist) < 0) { if (sort_order) parse_options_usage(top_usage, options, "s", 1); @@ -1252,13 +1276,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) goto out_delete_evlist; } - if (top.use_stdio) - use_browser = 0; - else if (top.use_tui) - use_browser = 1; - - setup_browser(false); - status = target__validate(target); if (status) { target__strerror(target, status, errbuf, BUFSIZ); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 20916dd77aac2..8dc98c598b1ae 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -33,6 +33,7 @@ #include "util/stat.h" #include "trace-event.h" #include "util/parse-events.h" +#include "util/bpf-loader.h" #include #include @@ -1724,8 +1725,12 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc->args = sc->tp_format->format.fields; sc->nr_args = sc->tp_format->format.nr_fields; - /* drop nr field - not relevant here; does not exist on older kernels */ - if (sc->args && strcmp(sc->args->name, "nr") == 0) { + /* + * We need to check and discard the first variable '__syscall_nr' + * or 'nr' that mean the syscall number. It is needless here. + * So drop '__syscall_nr' or 'nr' field but does not exist on older kernels. + */ + if (sc->args && (!strcmp(sc->args->name, "__syscall_nr") || !strcmp(sc->args->name, "nr"))) { sc->args = sc->args->next; --sc->nr_args; } @@ -2177,6 +2182,37 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs return 0; } +static void bpf_output__printer(enum binary_printer_ops op, + unsigned int val, void *extra) +{ + FILE *output = extra; + unsigned char ch = (unsigned char)val; + + switch (op) { + case BINARY_PRINT_CHAR_DATA: + fprintf(output, "%c", isprint(ch) ? ch : '.'); + break; + case BINARY_PRINT_DATA_BEGIN: + case BINARY_PRINT_LINE_BEGIN: + case BINARY_PRINT_ADDR: + case BINARY_PRINT_NUM_DATA: + case BINARY_PRINT_NUM_PAD: + case BINARY_PRINT_SEP: + case BINARY_PRINT_CHAR_PAD: + case BINARY_PRINT_LINE_END: + case BINARY_PRINT_DATA_END: + default: + break; + } +} + +static void bpf_output__fprintf(struct trace *trace, + struct perf_sample *sample) +{ + print_binary(sample->raw_data, sample->raw_size, 8, + bpf_output__printer, trace->output); +} + static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -2189,7 +2225,9 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, fprintf(trace->output, "%s:", evsel->name); - if (evsel->tp_format) { + if (perf_evsel__is_bpf_output(evsel)) { + bpf_output__fprintf(trace, sample); + } else if (evsel->tp_format) { event_format__fprintf(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size, trace->output); @@ -2586,6 +2624,16 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (err < 0) goto out_error_open; + err = bpf__apply_obj_config(); + if (err) { + char errbuf[BUFSIZ]; + + bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf)); + pr_err("ERROR: Apply config to BPF failed: %s\n", + errbuf); + goto out_error_open; + } + /* * Better not use !target__has_task() here because we need to cover the * case where no threads were specified in the command line, but a diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 511141b102e84..eca6a912e8c22 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -61,50 +61,45 @@ endif ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 -else - # - # For linking with debug library, run like: - # - # make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ - # - ifdef LIBUNWIND_DIR - LIBUNWIND_CFLAGS = -I$(LIBUNWIND_DIR)/include - LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib - endif - LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS) - - # Set per-feature check compilation flags - FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS) - FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) - FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS) - FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) endif +# +# For linking with debug library, run like: +# +# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ +# +ifdef LIBUNWIND_DIR + LIBUNWIND_CFLAGS = -I$(LIBUNWIND_DIR)/include + LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib +endif +LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS) + +# Set per-feature check compilation flags +FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS) +FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) +FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS) +FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) ifeq ($(NO_PERF_REGS),0) CFLAGS += -DHAVE_PERF_REGS_SUPPORT endif -ifndef NO_LIBELF - # for linking with debug library, run like: - # make DEBUG=1 LIBDW_DIR=/opt/libdw/ - ifdef LIBDW_DIR - LIBDW_CFLAGS := -I$(LIBDW_DIR)/include - LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib - endif - FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) - FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw +# for linking with debug library, run like: +# make DEBUG=1 LIBDW_DIR=/opt/libdw/ +ifdef LIBDW_DIR + LIBDW_CFLAGS := -I$(LIBDW_DIR)/include + LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib endif +FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) +FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw -ifdef LIBBABELTRACE - # for linking with debug library, run like: - # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/ - ifdef LIBBABELTRACE_DIR - LIBBABELTRACE_CFLAGS := -I$(LIBBABELTRACE_DIR)/include - LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib - endif - FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) - FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf +# for linking with debug library, run like: +# make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/ +ifdef LIBBABELTRACE_DIR + LIBBABELTRACE_CFLAGS := -I$(LIBBABELTRACE_DIR)/include + LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib endif +FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) +FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi # include ARCH specific config @@ -145,28 +140,26 @@ ifdef PARSER_DEBUG $(call detected_var,PARSER_DEBUG_FLEX) endif -ifndef NO_LIBPYTHON - # Try different combinations to accommodate systems that only have - # python[2][-config] in weird combinations but always preferring - # python2 and python2-config as per pep-0394. If we catch a - # python[-config] in version 3, the version check will kill it. - PYTHON2 := $(if $(call get-executable,python2),python2,python) - override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2)) - PYTHON2_CONFIG := \ - $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config) - override PYTHON_CONFIG := \ - $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) +# Try different combinations to accommodate systems that only have +# python[2][-config] in weird combinations but always preferring +# python2 and python2-config as per pep-0394. If we catch a +# python[-config] in version 3, the version check will kill it. +PYTHON2 := $(if $(call get-executable,python2),python2,python) +override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2)) +PYTHON2_CONFIG := \ + $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config) +override PYTHON_CONFIG := \ + $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) - PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) +PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) - PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) - PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) +PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) +PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) - FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) - FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) - FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) -endif +FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) +FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) +FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) +FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) CFLAGS += -fno-omit-frame-pointer CFLAGS += -ggdb3 @@ -335,6 +328,13 @@ ifndef NO_LIBELF endif # NO_LIBBPF endif # NO_LIBELF +ifdef PERF_HAVE_JITDUMP + ifndef NO_DWARF + $(call detected,CONFIG_JITDUMP) + CFLAGS += -DHAVE_JITDUMP + endif +endif + ifeq ($(ARCH),powerpc) ifndef NO_DWARF CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX @@ -411,6 +411,17 @@ ifndef NO_LIBAUDIT endif endif +ifndef NO_LIBCRYPTO + ifneq ($(feature-libcrypto), 1) + msg := $(warning No libcrypto.h found, disables jitted code injection, please install libssl-devel or libssl-dev); + NO_LIBCRYPTO := 1 + else + CFLAGS += -DHAVE_LIBCRYPTO_SUPPORT + EXTLIBS += -lcrypto + $(call detected,CONFIG_CRYPTO) + endif +endif + ifdef NO_NEWT NO_SLANG=1 endif diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile new file mode 100644 index 0000000000000..5ce61a1bda9ca --- /dev/null +++ b/tools/perf/jvmti/Makefile @@ -0,0 +1,89 @@ +ARCH=$(shell uname -m) + +ifeq ($(ARCH), x86_64) +JARCH=amd64 +endif +ifeq ($(ARCH), armv7l) +JARCH=armhf +endif +ifeq ($(ARCH), armv6l) +JARCH=armhf +endif +ifeq ($(ARCH), aarch64) +JARCH=aarch64 +endif +ifeq ($(ARCH), ppc64) +JARCH=powerpc +endif +ifeq ($(ARCH), ppc64le) +JARCH=powerpc +endif + +DESTDIR=/usr/local + +VERSION=1 +REVISION=0 +AGE=0 + +LN=ln -sf +RM=rm + +SLIBJVMTI=libjvmti.so.$(VERSION).$(REVISION).$(AGE) +VLIBJVMTI=libjvmti.so.$(VERSION) +SLDFLAGS=-shared -Wl,-soname -Wl,$(VLIBJVMTI) +SOLIBEXT=so + +# The following works at least on fedora 23, you may need the next +# line for other distros. +ifneq (,$(wildcard /usr/sbin/update-java-alternatives)) +JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3) +else + ifneq (,$(wildcard /usr/sbin/alternatives)) + JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g') + endif +endif +ifndef JDIR +$(error Could not find alternatives command, you need to set JDIR= to point to the root of your Java directory) +else + ifeq (,$(wildcard $(JDIR)/include/jvmti.h)) + $(error the openjdk development package appears to me missing, install and try again) + endif +endif +$(info Using Java from $(JDIR)) +# -lrt required in 32-bit mode for clock_gettime() +LIBS=-lelf -lrt +INCDIR=-I $(JDIR)/include -I $(JDIR)/include/linux + +TARGETS=$(SLIBJVMTI) + +SRCS=libjvmti.c jvmti_agent.c +OBJS=$(SRCS:.c=.o) +SOBJS=$(OBJS:.o=.lo) +OPT=-O2 -g -Werror -Wall + +CFLAGS=$(INCDIR) $(OPT) + +all: $(TARGETS) + +.c.o: + $(CC) $(CFLAGS) -c $*.c +.c.lo: + $(CC) -fPIC -DPIC $(CFLAGS) -c $*.c -o $*.lo + +$(OBJS) $(SOBJS): Makefile jvmti_agent.h ../util/jitdump.h + +$(SLIBJVMTI): $(SOBJS) + $(CC) $(CFLAGS) $(SLDFLAGS) -o $@ $(SOBJS) $(LIBS) + $(LN) $@ libjvmti.$(SOLIBEXT) + +clean: + $(RM) -f *.o *.so.* *.so *.lo + +install: + -mkdir -p $(DESTDIR)/lib + install -m 755 $(SLIBJVMTI) $(DESTDIR)/lib/ + (cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) $(VLIBJVMTI)) + (cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) libjvmti.$(SOLIBEXT)) + ldconfig + +.SUFFIXES: .c .S .o .lo diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c new file mode 100644 index 0000000000000..6461e02ab940d --- /dev/null +++ b/tools/perf/jvmti/jvmti_agent.c @@ -0,0 +1,465 @@ +/* + * jvmti_agent.c: JVMTI agent interface + * + * Adapted from the Oprofile code in opagent.c: + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Copyright 2007 OProfile authors + * Jens Wilke + * Daniel Hansel + * Copyright IBM Corporation 2007 + */ +#include +#include /* for mkdir() */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* for gettid() */ +#include + +#include "jvmti_agent.h" +#include "../util/jitdump.h" + +#define JIT_LANG "java" + +static char jit_path[PATH_MAX]; +static void *marker_addr; + +/* + * padding buffer + */ +static const char pad_bytes[7]; + +static inline pid_t gettid(void) +{ + return (pid_t)syscall(__NR_gettid); +} + +static int get_e_machine(struct jitheader *hdr) +{ + ssize_t sret; + char id[16]; + int fd, ret = -1; + int m = -1; + struct { + uint16_t e_type; + uint16_t e_machine; + } info; + + fd = open("/proc/self/exe", O_RDONLY); + if (fd == -1) + return -1; + + sret = read(fd, id, sizeof(id)); + if (sret != sizeof(id)) + goto error; + + /* check ELF signature */ + if (id[0] != 0x7f || id[1] != 'E' || id[2] != 'L' || id[3] != 'F') + goto error; + + sret = read(fd, &info, sizeof(info)); + if (sret != sizeof(info)) + goto error; + + m = info.e_machine; + if (m < 0) + m = 0; /* ELF EM_NONE */ + + hdr->elf_mach = m; + ret = 0; +error: + close(fd); + return ret; +} + +#define NSEC_PER_SEC 1000000000 +static int perf_clk_id = CLOCK_MONOTONIC; + +static inline uint64_t +timespec_to_ns(const struct timespec *ts) +{ + return ((uint64_t) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; +} + +static inline uint64_t +perf_get_timestamp(void) +{ + struct timespec ts; + int ret; + + ret = clock_gettime(perf_clk_id, &ts); + if (ret) + return 0; + + return timespec_to_ns(&ts); +} + +static int +debug_cache_init(void) +{ + char str[32]; + char *base, *p; + struct tm tm; + time_t t; + int ret; + + time(&t); + localtime_r(&t, &tm); + + base = getenv("JITDUMPDIR"); + if (!base) + base = getenv("HOME"); + if (!base) + base = "."; + + strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm); + + snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base); + + ret = mkdir(jit_path, 0755); + if (ret == -1) { + if (errno != EEXIST) { + warn("jvmti: cannot create jit cache dir %s", jit_path); + return -1; + } + } + + snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base); + ret = mkdir(jit_path, 0755); + if (ret == -1) { + if (errno != EEXIST) { + warn("cannot create jit cache dir %s", jit_path); + return -1; + } + } + + snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str); + + p = mkdtemp(jit_path); + if (p != jit_path) { + warn("cannot create jit cache dir %s", jit_path); + return -1; + } + + return 0; +} + +static int +perf_open_marker_file(int fd) +{ + long pgsz; + + pgsz = sysconf(_SC_PAGESIZE); + if (pgsz == -1) + return -1; + + /* + * we mmap the jitdump to create an MMAP RECORD in perf.data file. + * The mmap is captured either live (perf record running when we mmap) + * or in deferred mode, via /proc/PID/maps + * the MMAP record is used as a marker of a jitdump file for more meta + * data info about the jitted code. Perf report/annotate detect this + * special filename and process the jitdump file. + * + * mapping must be PROT_EXEC to ensure it is captured by perf record + * even when not using -d option + */ + marker_addr = mmap(NULL, pgsz, PROT_READ|PROT_EXEC, MAP_PRIVATE, fd, 0); + return (marker_addr == MAP_FAILED) ? -1 : 0; +} + +static void +perf_close_marker_file(void) +{ + long pgsz; + + if (!marker_addr) + return; + + pgsz = sysconf(_SC_PAGESIZE); + if (pgsz == -1) + return; + + munmap(marker_addr, pgsz); +} + +void *jvmti_open(void) +{ + int pad_cnt; + char dump_path[PATH_MAX]; + struct jitheader header; + int fd; + FILE *fp; + + /* + * check if clockid is supported + */ + if (!perf_get_timestamp()) + warnx("jvmti: kernel does not support %d clock id", perf_clk_id); + + memset(&header, 0, sizeof(header)); + + debug_cache_init(); + + /* + * jitdump file name + */ + snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + + fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666); + if (fd == -1) + return NULL; + + /* + * create perf.data maker for the jitdump file + */ + if (perf_open_marker_file(fd)) { + warnx("jvmti: failed to create marker file"); + return NULL; + } + + fp = fdopen(fd, "w+"); + if (!fp) { + warn("jvmti: cannot create %s", dump_path); + close(fd); + goto error; + } + + warnx("jvmti: jitdump in %s", dump_path); + + if (get_e_machine(&header)) { + warn("get_e_machine failed\n"); + goto error; + } + + header.magic = JITHEADER_MAGIC; + header.version = JITHEADER_VERSION; + header.total_size = sizeof(header); + header.pid = getpid(); + + /* calculate amount of padding '\0' */ + pad_cnt = PADDING_8ALIGNED(header.total_size); + header.total_size += pad_cnt; + + header.timestamp = perf_get_timestamp(); + + if (!fwrite(&header, sizeof(header), 1, fp)) { + warn("jvmti: cannot write dumpfile header"); + goto error; + } + + /* write padding '\0' if necessary */ + if (pad_cnt && !fwrite(pad_bytes, pad_cnt, 1, fp)) { + warn("jvmti: cannot write dumpfile header padding"); + goto error; + } + + return fp; +error: + fclose(fp); + return NULL; +} + +int +jvmti_close(void *agent) +{ + struct jr_code_close rec; + FILE *fp = agent; + + if (!fp) { + warnx("jvmti: incalid fd in close_agent"); + return -1; + } + + rec.p.id = JIT_CODE_CLOSE; + rec.p.total_size = sizeof(rec); + + rec.p.timestamp = perf_get_timestamp(); + + if (!fwrite(&rec, sizeof(rec), 1, fp)) + return -1; + + fclose(fp); + + fp = NULL; + + perf_close_marker_file(); + + return 0; +} + +int +jvmti_write_code(void *agent, char const *sym, + uint64_t vma, void const *code, unsigned int const size) +{ + static int code_generation = 1; + struct jr_code_load rec; + size_t sym_len; + size_t padding_count; + FILE *fp = agent; + int ret = -1; + + /* don't care about 0 length function, no samples */ + if (size == 0) + return 0; + + if (!fp) { + warnx("jvmti: invalid fd in write_native_code"); + return -1; + } + + sym_len = strlen(sym) + 1; + + rec.p.id = JIT_CODE_LOAD; + rec.p.total_size = sizeof(rec) + sym_len; + padding_count = PADDING_8ALIGNED(rec.p.total_size); + rec.p. total_size += padding_count; + rec.p.timestamp = perf_get_timestamp(); + + rec.code_size = size; + rec.vma = vma; + rec.code_addr = vma; + rec.pid = getpid(); + rec.tid = gettid(); + + if (code) + rec.p.total_size += size; + + /* + * If JVM is multi-threaded, nultiple concurrent calls to agent + * may be possible, so protect file writes + */ + flockfile(fp); + + /* + * get code index inside lock to avoid race condition + */ + rec.code_index = code_generation++; + + ret = fwrite_unlocked(&rec, sizeof(rec), 1, fp); + fwrite_unlocked(sym, sym_len, 1, fp); + + if (padding_count) + fwrite_unlocked(pad_bytes, padding_count, 1, fp); + + if (code) + fwrite_unlocked(code, size, 1, fp); + + funlockfile(fp); + + ret = 0; + + return ret; +} + +int +jvmti_write_debug_info(void *agent, uint64_t code, const char *file, + jvmti_line_info_t *li, int nr_lines) +{ + struct jr_code_debug_info rec; + size_t sret, len, size, flen; + size_t padding_count; + uint64_t addr; + const char *fn = file; + FILE *fp = agent; + int i; + + /* + * no entry to write + */ + if (!nr_lines) + return 0; + + if (!fp) { + warnx("jvmti: invalid fd in write_debug_info"); + return -1; + } + + flen = strlen(file) + 1; + + rec.p.id = JIT_CODE_DEBUG_INFO; + size = sizeof(rec); + rec.p.timestamp = perf_get_timestamp(); + rec.code_addr = (uint64_t)(uintptr_t)code; + rec.nr_entry = nr_lines; + + /* + * on disk source line info layout: + * uint64_t : addr + * int : line number + * int : column discriminator + * file[] : source file name + * padding : pad to multiple of 8 bytes + */ + size += nr_lines * sizeof(struct debug_entry); + size += flen * nr_lines; + /* + * pad to 8 bytes + */ + padding_count = PADDING_8ALIGNED(size); + + rec.p.total_size = size + padding_count; + + /* + * If JVM is multi-threaded, nultiple concurrent calls to agent + * may be possible, so protect file writes + */ + flockfile(fp); + + sret = fwrite_unlocked(&rec, sizeof(rec), 1, fp); + if (sret != 1) + goto error; + + for (i = 0; i < nr_lines; i++) { + + addr = (uint64_t)li[i].pc; + len = sizeof(addr); + sret = fwrite_unlocked(&addr, len, 1, fp); + if (sret != 1) + goto error; + + len = sizeof(li[0].line_number); + sret = fwrite_unlocked(&li[i].line_number, len, 1, fp); + if (sret != 1) + goto error; + + len = sizeof(li[0].discrim); + sret = fwrite_unlocked(&li[i].discrim, len, 1, fp); + if (sret != 1) + goto error; + + sret = fwrite_unlocked(fn, flen, 1, fp); + if (sret != 1) + goto error; + } + if (padding_count) + sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp); + if (sret != 1) + goto error; + + funlockfile(fp); + return 0; +error: + funlockfile(fp); + return -1; +} diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h new file mode 100644 index 0000000000000..bedf5d0ba9ff9 --- /dev/null +++ b/tools/perf/jvmti/jvmti_agent.h @@ -0,0 +1,36 @@ +#ifndef __JVMTI_AGENT_H__ +#define __JVMTI_AGENT_H__ + +#include +#include +#include + +#define __unused __attribute__((unused)) + +#if defined(__cplusplus) +extern "C" { +#endif + +typedef struct { + unsigned long pc; + int line_number; + int discrim; /* discriminator -- 0 for now */ +} jvmti_line_info_t; + +void *jvmti_open(void); +int jvmti_close(void *agent); +int jvmti_write_code(void *agent, char const *symbol_name, + uint64_t vma, void const *code, + const unsigned int code_size); + +int jvmti_write_debug_info(void *agent, + uint64_t code, + const char *file, + jvmti_line_info_t *li, + int nr_lines); + +#if defined(__cplusplus) +} + +#endif +#endif /* __JVMTI_H__ */ diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c new file mode 100644 index 0000000000000..ac12e4b91a926 --- /dev/null +++ b/tools/perf/jvmti/libjvmti.c @@ -0,0 +1,304 @@ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "jvmti_agent.h" + +static int has_line_numbers; +void *jvmti_agent; + +static jvmtiError +do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci, + jvmti_line_info_t *tab, jint *nr) +{ + jint i, lines = 0; + jint nr_lines = 0; + jvmtiLineNumberEntry *loc_tab = NULL; + jvmtiError ret; + + ret = (*jvmti)->GetLineNumberTable(jvmti, m, &nr_lines, &loc_tab); + if (ret != JVMTI_ERROR_NONE) + return ret; + + for (i = 0; i < nr_lines; i++) { + if (loc_tab[i].start_location < bci) { + tab[lines].pc = (unsigned long)pc; + tab[lines].line_number = loc_tab[i].line_number; + tab[lines].discrim = 0; /* not yet used */ + lines++; + } else { + break; + } + } + (*jvmti)->Deallocate(jvmti, (unsigned char *)loc_tab); + *nr = lines; + return JVMTI_ERROR_NONE; +} + +static jvmtiError +get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t **tab, int *nr_lines) +{ + const jvmtiCompiledMethodLoadRecordHeader *hdr; + jvmtiCompiledMethodLoadInlineRecord *rec; + jvmtiLineNumberEntry *lne = NULL; + PCStackInfo *c; + jint nr, ret; + int nr_total = 0; + int i, lines_total = 0; + + if (!(tab && nr_lines)) + return JVMTI_ERROR_NULL_POINTER; + + /* + * Phase 1 -- get the number of lines necessary + */ + for (hdr = compile_info; hdr != NULL; hdr = hdr->next) { + if (hdr->kind == JVMTI_CMLR_INLINE_INFO) { + rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr; + for (i = 0; i < rec->numpcs; i++) { + c = rec->pcinfo + i; + nr = 0; + /* + * unfortunately, need a tab to get the number of lines! + */ + ret = (*jvmti)->GetLineNumberTable(jvmti, c->methods[0], &nr, &lne); + if (ret == JVMTI_ERROR_NONE) { + /* free what was allocated for nothing */ + (*jvmti)->Deallocate(jvmti, (unsigned char *)lne); + nr_total += (int)nr; + } + } + } + } + + if (nr_total == 0) + return JVMTI_ERROR_NOT_FOUND; + + /* + * Phase 2 -- allocate big enough line table + */ + *tab = malloc(nr_total * sizeof(**tab)); + if (!*tab) + return JVMTI_ERROR_OUT_OF_MEMORY; + + for (hdr = compile_info; hdr != NULL; hdr = hdr->next) { + if (hdr->kind == JVMTI_CMLR_INLINE_INFO) { + rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr; + for (i = 0; i < rec->numpcs; i++) { + c = rec->pcinfo + i; + nr = 0; + ret = do_get_line_numbers(jvmti, c->pc, + c->methods[0], + c->bcis[0], + *tab + lines_total, + &nr); + if (ret == JVMTI_ERROR_NONE) + lines_total += nr; + } + } + } + *nr_lines = lines_total; + return JVMTI_ERROR_NONE; +} + +static void JNICALL +compiled_method_load_cb(jvmtiEnv *jvmti, + jmethodID method, + jint code_size, + void const *code_addr, + jint map_length, + jvmtiAddrLocationMap const *map, + const void *compile_info) +{ + jvmti_line_info_t *line_tab = NULL; + jclass decl_class; + char *class_sign = NULL; + char *func_name = NULL; + char *func_sign = NULL; + char *file_name= NULL; + char fn[PATH_MAX]; + uint64_t addr = (uint64_t)(uintptr_t)code_addr; + jvmtiError ret; + int nr_lines = 0; /* in line_tab[] */ + size_t len; + + ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method, + &decl_class); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: cannot get declaring class"); + return; + } + + if (has_line_numbers && map && map_length) { + ret = get_line_numbers(jvmti, compile_info, &line_tab, &nr_lines); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: cannot get line table for method"); + nr_lines = 0; + } + } + + ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: cannot get source filename ret=%d", ret); + goto error; + } + + ret = (*jvmti)->GetClassSignature(jvmti, decl_class, + &class_sign, NULL); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: getclassignature failed"); + goto error; + } + + ret = (*jvmti)->GetMethodName(jvmti, method, &func_name, + &func_sign, NULL); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: failed getmethodname"); + goto error; + } + + /* + * Assume path name is class hierarchy, this is a common practice with Java programs + */ + if (*class_sign == 'L') { + int j, i = 0; + char *p = strrchr(class_sign, '/'); + if (p) { + /* drop the 'L' prefix and copy up to the final '/' */ + for (i = 0; i < (p - class_sign); i++) + fn[i] = class_sign[i+1]; + } + /* + * append file name, we use loops and not string ops to avoid modifying + * class_sign which is used later for the symbol name + */ + for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++) + fn[i] = file_name[j]; + fn[i] = '\0'; + } else { + /* fallback case */ + strcpy(fn, file_name); + } + /* + * write source line info record if we have it + */ + if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines)) + warnx("jvmti: write_debug_info() failed"); + + len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2; + { + char str[len]; + snprintf(str, len, "%s%s%s", class_sign, func_name, func_sign); + + if (jvmti_write_code(jvmti_agent, str, addr, code_addr, code_size)) + warnx("jvmti: write_code() failed"); + } +error: + (*jvmti)->Deallocate(jvmti, (unsigned char *)func_name); + (*jvmti)->Deallocate(jvmti, (unsigned char *)func_sign); + (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign); + (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name); + free(line_tab); +} + +static void JNICALL +code_generated_cb(jvmtiEnv *jvmti, + char const *name, + void const *code_addr, + jint code_size) +{ + uint64_t addr = (uint64_t)(unsigned long)code_addr; + int ret; + + ret = jvmti_write_code(jvmti_agent, name, addr, code_addr, code_size); + if (ret) + warnx("jvmti: write_code() failed for code_generated"); +} + +JNIEXPORT jint JNICALL +Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused) +{ + jvmtiEventCallbacks cb; + jvmtiCapabilities caps1; + jvmtiJlocationFormat format; + jvmtiEnv *jvmti = NULL; + jint ret; + + jvmti_agent = jvmti_open(); + if (!jvmti_agent) { + warnx("jvmti: open_agent failed"); + return -1; + } + + /* + * Request a JVMTI interface version 1 environment + */ + ret = (*jvm)->GetEnv(jvm, (void *)&jvmti, JVMTI_VERSION_1); + if (ret != JNI_OK) { + warnx("jvmti: jvmti version 1 not supported"); + return -1; + } + + /* + * acquire method_load capability, we require it + * request line numbers (optional) + */ + memset(&caps1, 0, sizeof(caps1)); + caps1.can_generate_compiled_method_load_events = 1; + + ret = (*jvmti)->AddCapabilities(jvmti, &caps1); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: acquire compiled_method capability failed"); + return -1; + } + ret = (*jvmti)->GetJLocationFormat(jvmti, &format); + if (ret == JVMTI_ERROR_NONE && format == JVMTI_JLOCATION_JVMBCI) { + memset(&caps1, 0, sizeof(caps1)); + caps1.can_get_line_numbers = 1; + caps1.can_get_source_file_name = 1; + ret = (*jvmti)->AddCapabilities(jvmti, &caps1); + if (ret == JVMTI_ERROR_NONE) + has_line_numbers = 1; + } + + memset(&cb, 0, sizeof(cb)); + + cb.CompiledMethodLoad = compiled_method_load_cb; + cb.DynamicCodeGenerated = code_generated_cb; + + ret = (*jvmti)->SetEventCallbacks(jvmti, &cb, sizeof(cb)); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: cannot set event callbacks"); + return -1; + } + + ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE, + JVMTI_EVENT_COMPILED_METHOD_LOAD, NULL); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: setnotification failed for method_load"); + return -1; + } + + ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE, + JVMTI_EVENT_DYNAMIC_CODE_GENERATED, NULL); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: setnotification failed on code_generated"); + return -1; + } + return 0; +} + +JNIEXPORT void JNICALL +Agent_OnUnload(JavaVM *jvm __unused) +{ + int ret; + + ret = jvmti_close(jvmti_agent); + if (ret) + errx(1, "Error: op_close_agent()"); +} diff --git a/tools/perf/perf.c b/tools/perf/perf.c index a929618b8eb61..aaee0a7827477 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -454,11 +454,12 @@ static void handle_internal_command(int argc, const char **argv) static void execv_dashed_external(const char **argv) { - struct strbuf cmd = STRBUF_INIT; + char *cmd; const char *tmp; int status; - strbuf_addf(&cmd, "perf-%s", argv[0]); + if (asprintf(&cmd, "perf-%s", argv[0]) < 0) + goto do_die; /* * argv[0] must be the perf command, but the argv array @@ -467,7 +468,7 @@ static void execv_dashed_external(const char **argv) * restore it on error. */ tmp = argv[0]; - argv[0] = cmd.buf; + argv[0] = cmd; /* * if we fail because the command is not found, it is @@ -475,15 +476,16 @@ static void execv_dashed_external(const char **argv) */ status = run_command_v_opt(argv, 0); if (status != -ERR_RUN_COMMAND_EXEC) { - if (IS_RUN_COMMAND_ERR(status)) + if (IS_RUN_COMMAND_ERR(status)) { +do_die: die("unable to run '%s'", argv[0]); + } exit(-status); } errno = ENOENT; /* as if we called execvp */ argv[0] = tmp; - - strbuf_release(&cmd); + zfree(&cmd); } static int run_argv(int *argcp, const char ***argv) @@ -546,6 +548,8 @@ int main(int argc, const char **argv) srandom(time(NULL)); + perf_config(perf_default_config, NULL); + /* get debugfs/tracefs mount point from /proc/mounts */ tracing_path_mount(); @@ -613,6 +617,8 @@ int main(int argc, const char **argv) */ pthread__block_sigwinch(); + perf_debug_setup(); + while (1) { static int done_help; int was_alias = run_argv(&argc, &argv); diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 90129accffbe8..5381a01c0610c 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -58,6 +58,8 @@ struct record_opts { bool full_auxtrace; bool auxtrace_snapshot_mode; bool record_switch_events; + bool all_kernel; + bool all_user; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py index 15c8400240fd9..1d95009592eb3 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py @@ -71,7 +71,10 @@ def clear_term(): except: if not audit_package_warned: audit_package_warned = True - print "Install the audit-libs-python package to get syscall names" + print "Install the audit-libs-python package to get syscall names.\n" \ + "For example:\n # apt-get install python-audit (Ubuntu)" \ + "\n # yum install audit-libs-python (Fedora)" \ + "\n etc.\n" def syscall_name(id): try: diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore index bf016c439fbd1..8cc30e731c739 100644 --- a/tools/perf/tests/.gitignore +++ b/tools/perf/tests/.gitignore @@ -1,3 +1,4 @@ llvm-src-base.c llvm-src-kbuild.c llvm-src-prologue.c +llvm-src-relocation.c diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 614899b88b377..1ba628ed049ad 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -31,7 +31,7 @@ perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o perf-y += kmod-path.o perf-y += thread-map.o -perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o +perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o perf-y += bpf.o perf-y += topology.o perf-y += cpumap.o @@ -59,6 +59,13 @@ $(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ +$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build + $(call rule_mkdir) + $(Q)echo '#include ' > $@ + $(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@ + $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ + $(Q)echo ';' >> $@ + ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index fb80c9eb6a95b..e7664fe3bd337 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -29,14 +29,59 @@ static int fd1; static int fd2; +static int fd3; static int overflows; +static int overflows_2; + +volatile long the_var; + + +/* + * Use ASM to ensure watchpoint and breakpoint can be triggered + * at one instruction. + */ +#if defined (__x86_64__) +extern void __test_function(volatile long *ptr); +asm ( + ".globl __test_function\n" + "__test_function:\n" + "incq (%rdi)\n" + "ret\n"); +#elif defined (__aarch64__) +extern void __test_function(volatile long *ptr); +asm ( + ".globl __test_function\n" + "__test_function:\n" + "str x30, [x0]\n" + "ret\n"); + +#else +static void __test_function(volatile long *ptr) +{ + *ptr = 0x1234; +} +#endif __attribute__ ((noinline)) static int test_function(void) { + __test_function(&the_var); + the_var++; return time(NULL); } +static void sig_handler_2(int signum __maybe_unused, + siginfo_t *oh __maybe_unused, + void *uc __maybe_unused) +{ + overflows_2++; + if (overflows_2 > 10) { + ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0); + } +} + static void sig_handler(int signum __maybe_unused, siginfo_t *oh __maybe_unused, void *uc __maybe_unused) @@ -54,10 +99,11 @@ static void sig_handler(int signum __maybe_unused, */ ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0); } } -static int bp_event(void *fn, int setup_signal) +static int __event(bool is_x, void *addr, int sig) { struct perf_event_attr pe; int fd; @@ -67,8 +113,8 @@ static int bp_event(void *fn, int setup_signal) pe.size = sizeof(struct perf_event_attr); pe.config = 0; - pe.bp_type = HW_BREAKPOINT_X; - pe.bp_addr = (unsigned long) fn; + pe.bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W; + pe.bp_addr = (unsigned long) addr; pe.bp_len = sizeof(long); pe.sample_period = 1; @@ -86,17 +132,25 @@ static int bp_event(void *fn, int setup_signal) return TEST_FAIL; } - if (setup_signal) { - fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC); - fcntl(fd, F_SETSIG, SIGIO); - fcntl(fd, F_SETOWN, getpid()); - } + fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC); + fcntl(fd, F_SETSIG, sig); + fcntl(fd, F_SETOWN, getpid()); ioctl(fd, PERF_EVENT_IOC_RESET, 0); return fd; } +static int bp_event(void *addr, int sig) +{ + return __event(true, addr, sig); +} + +static int wp_event(void *addr, int sig) +{ + return __event(false, addr, sig); +} + static long long bp_count(int fd) { long long count; @@ -114,7 +168,7 @@ static long long bp_count(int fd) int test__bp_signal(int subtest __maybe_unused) { struct sigaction sa; - long long count1, count2; + long long count1, count2, count3; /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); @@ -126,21 +180,52 @@ int test__bp_signal(int subtest __maybe_unused) return TEST_FAIL; } + sa.sa_sigaction = (void *) sig_handler_2; + if (sigaction(SIGUSR1, &sa, NULL) < 0) { + pr_debug("failed setting up signal handler 2\n"); + return TEST_FAIL; + } + /* * We create following events: * - * fd1 - breakpoint event on test_function with SIGIO + * fd1 - breakpoint event on __test_function with SIGIO * signal configured. We should get signal * notification each time the breakpoint is hit * - * fd2 - breakpoint event on sig_handler without SIGIO + * fd2 - breakpoint event on sig_handler with SIGUSR1 + * configured. We should get SIGUSR1 each time when + * breakpoint is hit + * + * fd3 - watchpoint event on __test_function with SIGIO * configured. * * Following processing should happen: - * - execute test_function - * - fd1 event breakpoint hit -> count1 == 1 - * - SIGIO is delivered -> overflows == 1 - * - fd2 event breakpoint hit -> count2 == 1 + * Exec: Action: Result: + * incq (%rdi) - fd1 event breakpoint hit -> count1 == 1 + * - SIGIO is delivered + * sig_handler - fd2 event breakpoint hit -> count2 == 1 + * - SIGUSR1 is delivered + * sig_handler_2 -> overflows_2 == 1 (nested signal) + * sys_rt_sigreturn - return from sig_handler_2 + * overflows++ -> overflows = 1 + * sys_rt_sigreturn - return from sig_handler + * incq (%rdi) - fd3 event watchpoint hit -> count3 == 1 (wp and bp in one insn) + * - SIGIO is delivered + * sig_handler - fd2 event breakpoint hit -> count2 == 2 + * - SIGUSR1 is delivered + * sig_handler_2 -> overflows_2 == 2 (nested signal) + * sys_rt_sigreturn - return from sig_handler_2 + * overflows++ -> overflows = 2 + * sys_rt_sigreturn - return from sig_handler + * the_var++ - fd3 event watchpoint hit -> count3 == 2 (standalone watchpoint) + * - SIGIO is delivered + * sig_handler - fd2 event breakpoint hit -> count2 == 3 + * - SIGUSR1 is delivered + * sig_handler_2 -> overflows_2 == 3 (nested signal) + * sys_rt_sigreturn - return from sig_handler_2 + * overflows++ -> overflows == 3 + * sys_rt_sigreturn - return from sig_handler * * The test case check following error conditions: * - we get stuck in signal handler because of debug @@ -152,11 +237,13 @@ int test__bp_signal(int subtest __maybe_unused) * */ - fd1 = bp_event(test_function, 1); - fd2 = bp_event(sig_handler, 0); + fd1 = bp_event(__test_function, SIGIO); + fd2 = bp_event(sig_handler, SIGUSR1); + fd3 = wp_event((void *)&the_var, SIGIO); ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0); ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_ENABLE, 0); /* * Kick off the test by trigering 'fd1' @@ -166,15 +253,18 @@ int test__bp_signal(int subtest __maybe_unused) ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0); count1 = bp_count(fd1); count2 = bp_count(fd2); + count3 = bp_count(fd3); close(fd1); close(fd2); + close(fd3); - pr_debug("count1 %lld, count2 %lld, overflow %d\n", - count1, count2, overflows); + pr_debug("count1 %lld, count2 %lld, count3 %lld, overflow %d, overflows_2 %d\n", + count1, count2, count3, overflows, overflows_2); if (count1 != 1) { if (count1 == 11) @@ -183,12 +273,18 @@ int test__bp_signal(int subtest __maybe_unused) pr_debug("failed: wrong count for bp1%lld\n", count1); } - if (overflows != 1) + if (overflows != 3) pr_debug("failed: wrong overflow hit\n"); - if (count2 != 1) + if (overflows_2 != 3) + pr_debug("failed: wrong overflow_2 hit\n"); + + if (count2 != 3) pr_debug("failed: wrong count for bp2\n"); - return count1 == 1 && overflows == 1 && count2 == 1 ? + if (count3 != 2) + pr_debug("failed: wrong count for bp3\n"); + + return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ? TEST_OK : TEST_FAIL; } diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c new file mode 100644 index 0000000000000..93af774218161 --- /dev/null +++ b/tools/perf/tests/bpf-script-test-relocation.c @@ -0,0 +1,50 @@ +/* + * bpf-script-test-relocation.c + * Test BPF loader checking relocation + */ +#ifndef LINUX_VERSION_CODE +# error Need LINUX_VERSION_CODE +# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' +#endif +#define BPF_ANY 0 +#define BPF_MAP_TYPE_ARRAY 2 +#define BPF_FUNC_map_lookup_elem 1 +#define BPF_FUNC_map_update_elem 2 + +static void *(*bpf_map_lookup_elem)(void *map, void *key) = + (void *) BPF_FUNC_map_lookup_elem; +static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) = + (void *) BPF_FUNC_map_update_elem; + +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; +}; + +#define SEC(NAME) __attribute__((section(NAME), used)) +struct bpf_map_def SEC("maps") my_table = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, +}; + +int this_is_a_global_val; + +SEC("func=sys_write") +int bpf_func__sys_write(void *ctx) +{ + int key = 0; + int value = 0; + + /* + * Incorrect relocation. Should not allow this program be + * loaded into kernel. + */ + bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0); + return 0; +} +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 33689a0cf821e..199501c71e272 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -1,7 +1,11 @@ #include #include +#include #include #include +#include +#include +#include #include "tests.h" #include "llvm.h" #include "debug.h" @@ -71,6 +75,15 @@ static struct { (NR_ITERS + 1) / 4, }, #endif + { + LLVM_TESTCASE_BPF_RELOCATION, + "Test BPF relocation checker", + "[bpf_relocation_test]", + "fix 'perf test LLVM' first", + "libbpf error when dealing with relocation", + NULL, + 0, + }, }; static int do_test(struct bpf_object *obj, int (*func)(void), @@ -99,7 +112,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), parse_evlist.error = &parse_error; INIT_LIST_HEAD(&parse_evlist.list); - err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj); + err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL); if (err || list_empty(&parse_evlist.list)) { pr_debug("Failed to add events selected by BPF\n"); return TEST_FAIL; @@ -190,7 +203,7 @@ static int __test__bpf(int idx) ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, bpf_testcase_table[idx].prog_id, - true); + true, NULL); if (ret != TEST_OK || !obj_buf || !obj_buf_sz) { pr_debug("Unable to get BPF object, %s\n", bpf_testcase_table[idx].msg_compile_fail); @@ -202,14 +215,21 @@ static int __test__bpf(int idx) obj = prepare_bpf(obj_buf, obj_buf_sz, bpf_testcase_table[idx].name); - if (!obj) { + if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) { + if (!obj) + pr_debug("Fail to load BPF object: %s\n", + bpf_testcase_table[idx].msg_load_fail); + else + pr_debug("Success unexpectedly: %s\n", + bpf_testcase_table[idx].msg_load_fail); ret = TEST_FAIL; goto out; } - ret = do_test(obj, - bpf_testcase_table[idx].target_func, - bpf_testcase_table[idx].expect_result); + if (obj) + ret = do_test(obj, + bpf_testcase_table[idx].target_func, + bpf_testcase_table[idx].expect_result); out: bpf__clear(); return ret; @@ -227,6 +247,36 @@ const char *test__bpf_subtest_get_desc(int i) return bpf_testcase_table[i].desc; } +static int check_env(void) +{ + int err; + unsigned int kver_int; + char license[] = "GPL"; + + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + err = fetch_kernel_version(&kver_int, NULL, 0); + if (err) { + pr_debug("Unable to get kernel version\n"); + return err; + } + + err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, + sizeof(insns) / sizeof(insns[0]), + license, kver_int, NULL, 0); + if (err < 0) { + pr_err("Missing basic BPF support, skip this test: %s\n", + strerror(errno)); + return err; + } + close(err); + + return 0; +} + int test__bpf(int i) { int err; @@ -239,6 +289,9 @@ int test__bpf(int i) return TEST_SKIP; } + if (check_env()) + return TEST_SKIP; + err = __test__bpf(i); return err; } diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 313a48c6b2bc8..afc9ad0a0515c 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -439,7 +439,7 @@ static int do_test_code_reading(bool try_kcore) .mmap_pages = UINT_MAX, .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, - .freq = 4000, + .freq = 500, .target = { .uses_mmap = true, }, @@ -559,7 +559,13 @@ static int do_test_code_reading(bool try_kcore) evlist = NULL; continue; } - pr_debug("perf_evlist__open failed\n"); + + if (verbose) { + char errbuf[512]; + perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); + pr_debug("perf_evlist__open() failed!\n%s\n", errbuf); + } + goto out_put; } break; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 5e6a86e50fb97..ecf136c385d5f 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -191,7 +191,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec * function since TEST_ASSERT_VAL() returns in case of failure. */ hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(hists_to_evsel(hists), NULL); if (verbose > 2) { pr_info("use callchain: %d, cumulate callchain: %d\n", diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 351a42463444a..34b945a55d4d2 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -145,7 +145,7 @@ int test__hists_filter(int subtest __maybe_unused) struct hists *hists = evsel__hists(evsel); hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("Normal histogram\n"); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index b231265148d89..23cce67c7e489 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -156,7 +156,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -256,7 +256,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -310,7 +310,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -388,7 +388,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -491,7 +491,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists, NULL); + perf_evsel__output_resort(evsel, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 06f45c1d42561..cff564fb4b667 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -6,12 +6,6 @@ #include "tests.h" #include "debug.h" -static int perf_config_cb(const char *var, const char *val, - void *arg __maybe_unused) -{ - return perf_default_config(var, val, arg); -} - #ifdef HAVE_LIBBPF_SUPPORT static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) { @@ -35,6 +29,7 @@ static int test__bpf_parsing(void *obj_buf __maybe_unused, static struct { const char *source; const char *desc; + bool should_load_fail; } bpf_source_table[__LLVM_TESTCASE_MAX] = { [LLVM_TESTCASE_BASE] = { .source = test_llvm__bpf_base_prog, @@ -48,14 +43,19 @@ static struct { .source = test_llvm__bpf_test_prologue_prog, .desc = "Compile source for BPF prologue generation test", }, + [LLVM_TESTCASE_BPF_RELOCATION] = { + .source = test_llvm__bpf_test_relocation, + .desc = "Compile source for BPF relocation test", + .should_load_fail = true, + }, }; - int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, enum test_llvm__testcase idx, - bool force) + bool force, + bool *should_load_fail) { const char *source; const char *desc; @@ -68,8 +68,8 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf, source = bpf_source_table[idx].source; desc = bpf_source_table[idx].desc; - - perf_config(perf_config_cb, NULL); + if (should_load_fail) + *should_load_fail = bpf_source_table[idx].should_load_fail; /* * Skip this test if user's .perfconfig doesn't set [llvm] section @@ -136,14 +136,15 @@ int test__llvm(int subtest) int ret; void *obj_buf = NULL; size_t obj_buf_sz = 0; + bool should_load_fail = false; if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) return TEST_FAIL; ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, - subtest, false); + subtest, false, &should_load_fail); - if (ret == TEST_OK) { + if (ret == TEST_OK && !should_load_fail) { ret = test__bpf_parsing(obj_buf, obj_buf_sz); if (ret != TEST_OK) { pr_debug("Failed to parse test case '%s'\n", diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h index 5150b4d6ef50a..0eaa604be99de 100644 --- a/tools/perf/tests/llvm.h +++ b/tools/perf/tests/llvm.h @@ -7,14 +7,17 @@ extern const char test_llvm__bpf_base_prog[]; extern const char test_llvm__bpf_test_kbuild_prog[]; extern const char test_llvm__bpf_test_prologue_prog[]; +extern const char test_llvm__bpf_test_relocation[]; enum test_llvm__testcase { LLVM_TESTCASE_BASE, LLVM_TESTCASE_KBUILD, LLVM_TESTCASE_BPF_PROLOGUE, + LLVM_TESTCASE_BPF_RELOCATION, __LLVM_TESTCASE_MAX, }; int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, - enum test_llvm__testcase index, bool force); + enum test_llvm__testcase index, bool force, + bool *should_load_fail); #endif diff --git a/tools/perf/tests/make b/tools/perf/tests/make index f918015512af9..cac15d93aea65 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -15,6 +15,7 @@ else PERF := . PERF_O := $(PERF) O_OPT := +FULL_O := $(shell readlink -f $(PERF_O) || echo $(PERF_O)) ifneq ($(O),) FULL_O := $(shell readlink -f $(O) || echo $(O)) @@ -79,6 +80,7 @@ make_no_libaudit := NO_LIBAUDIT=1 make_no_libbionic := NO_LIBBIONIC=1 make_no_auxtrace := NO_AUXTRACE=1 make_no_libbpf := NO_LIBBPF=1 +make_no_libcrypto := NO_LIBCRYPTO=1 make_tags := tags make_cscope := cscope make_help := help @@ -102,6 +104,7 @@ make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 +make_minimal += NO_LIBCRYPTO=1 # $(run) contains all available tests run := make_pure @@ -110,6 +113,9 @@ run := make_pure # disable features detection ifeq ($(MK),Makefile) run += make_clean_all +MAKE_F := $(MAKE) +else +MAKE_F := $(MAKE) -f $(MK) endif run += make_python_perf_so run += make_debug @@ -260,6 +266,8 @@ run := $(shell shuf -e $(run)) run_O := $(shell shuf -e $(run_O)) endif +max_width := $(shell echo $(run_O) | sed 's/ /\n/g' | wc -L) + ifdef DEBUG d := $(info run $(run)) d := $(info run_O $(run_O)) @@ -267,13 +275,13 @@ endif MAKEFLAGS := --no-print-directory -clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null) +clean := @(cd $(PERF); $(MAKE_F) -s $(O_OPT) clean >/dev/null) $(run): $(call clean) @TMP_DEST=$$(mktemp -d); \ - cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \ - echo "- $@: $$cmd" && echo $$cmd > $@ && \ + cmd="cd $(PERF) && $(MAKE_F) $($@) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST"; \ + printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1; \ echo " test: $(call test,$@)" >> $@ 2>&1; \ $(call test,$@) && \ @@ -283,8 +291,8 @@ $(run_O): $(call clean) @TMP_O=$$(mktemp -d); \ TMP_DEST=$$(mktemp -d); \ - cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \ - echo "- $@: $$cmd" && echo $$cmd > $@ && \ + cmd="cd $(PERF) && $(MAKE_F) $($(patsubst %_O,%,$@)) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST"; \ + printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1 && \ echo " test: $(call test_O,$@)" >> $@ 2>&1; \ $(call test_O,$@) && \ @@ -313,11 +321,43 @@ make_kernelsrc_tools: (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \ test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false) +FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP +FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC + all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools @echo OK + @rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC) out: $(run_O) @echo OK + @rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC) + +ifeq ($(REUSE_FEATURES_DUMP),1) +$(FEATURES_DUMP_FILE): + $(call clean) + @cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) feature-dump"; \ + echo "- $@: $$cmd" && echo $$cmd && \ + ( eval $$cmd ) > /dev/null 2>&1 + +$(FEATURES_DUMP_FILE_STATIC): + $(call clean) + @cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) LDFLAGS='-static' feature-dump"; \ + echo "- $@: $$cmd" && echo $$cmd && \ + ( eval $$cmd ) > /dev/null 2>&1 + +# Add feature dump dependency for run/run_O targets +$(foreach t,$(run) $(run_O),$(eval \ + $(t): $(if $(findstring make_static,$(t)),\ + $(FEATURES_DUMP_FILE_STATIC),\ + $(FEATURES_DUMP_FILE)))) + +# Append 'FEATURES_DUMP=' option to all test cases. For example: +# make_no_libbpf: NO_LIBBPF=1 --> NO_LIBBPF=1 FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP +# make_static: LDFLAGS=-static --> LDFLAGS=-static FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP_STATIC +$(foreach t,$(run),$(if $(findstring make_static,$(t)),\ + $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE_STATIC)),\ + $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE)))) +endif .PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools endif # ifndef MK diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index abe8849d1d703..7865f68dc0d82 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1271,6 +1271,38 @@ static int test__checkevent_precise_max_modifier(struct perf_evlist *evlist) return 0; } +static int test__checkevent_config_symbol(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0); + return 0; +} + +static int test__checkevent_config_raw(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0); + return 0; +} + +static int test__checkevent_config_num(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0); + return 0; +} + +static int test__checkevent_config_cache(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0); + return 0; +} + static int count_tracepoints(void) { struct dirent *events_ent; @@ -1579,6 +1611,26 @@ static struct evlist_test test__events[] = { .check = test__checkevent_precise_max_modifier, .id = 47, }, + { + .name = "instructions/name=insn/", + .check = test__checkevent_config_symbol, + .id = 48, + }, + { + .name = "r1234/name=rawpmu/", + .check = test__checkevent_config_raw, + .id = 49, + }, + { + .name = "4:0x6530160/name=numpmu/", + .check = test__checkevent_config_num, + .id = 50, + }, + { + .name = "L1-dcache-misses/name=cachepmu/", + .check = test__checkevent_config_cache, + .id = 51, + }, }; static struct evlist_test test__events_pmu[] = { @@ -1666,7 +1718,7 @@ static int test_term(struct terms_test *t) } ret = t->check(&terms); - parse_events__free_terms(&terms); + parse_events_terms__purge(&terms); return ret; } diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index f0bfc9e8fd9f6..630b0b409b973 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -110,7 +110,6 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused) */ for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) { struct symbol *pair, *first_pair; - bool backwards = true; sym = rb_entry(nd, struct symbol, rb_node); @@ -151,27 +150,14 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused) continue; } else { - struct rb_node *nnd; -detour: - nnd = backwards ? rb_prev(&pair->rb_node) : - rb_next(&pair->rb_node); - if (nnd) { - struct symbol *next = rb_entry(nnd, struct symbol, rb_node); - - if (UM(next->start) == mem_start) { - pair = next; + pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL); + if (pair) { + if (UM(pair->start) == mem_start) goto next_pair; - } - } - if (backwards) { - backwards = false; - pair = first_pair; - goto detour; + pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", + mem_start, sym->name, pair->name); } - - pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", - mem_start, sym->name, pair->name); } } else pr_debug("%#" PRIx64 ": %s not on kallsyms\n", diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index d37202121689a..af68a9d488bfc 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -531,8 +531,8 @@ static struct ui_browser_colorset { .bg = "yellow", }, { - .colorset = HE_COLORSET_CODE, - .name = "code", + .colorset = HE_COLORSET_JUMP_ARROWS, + .name = "jump_arrows", .fg = "blue", .bg = "default", }, diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 01781de59532c..be3b70eb5fca6 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -7,7 +7,7 @@ #define HE_COLORSET_MEDIUM 51 #define HE_COLORSET_NORMAL 52 #define HE_COLORSET_SELECTED 53 -#define HE_COLORSET_CODE 54 +#define HE_COLORSET_JUMP_ARROWS 54 #define HE_COLORSET_ADDR 55 #define HE_COLORSET_ROOT 56 diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 718bd46d47fa7..4fc208e82c6fc 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) to = (u64)btarget->idx; } - ui_browser__set_color(browser, HE_COLORSET_CODE); + ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS); __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width, from, to); } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 08c09ad755d2d..4b98165559462 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -32,6 +32,7 @@ struct hist_browser { bool show_headers; float min_pcnt; u64 nr_non_filtered_entries; + u64 nr_hierarchy_entries; u64 nr_callchain_rows; }; @@ -58,11 +59,11 @@ static int hist_browser__get_folding(struct hist_browser *browser) for (nd = rb_first(&hists->entries); (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL; - nd = rb_next(nd)) { + nd = rb_hierarchy_next(nd)) { struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); - if (he->unfolded) + if (he->leaf && he->unfolded) unfolded_rows += he->nr_rows; } return unfolded_rows; @@ -72,7 +73,9 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb) { u32 nr_entries; - if (hist_browser__has_filter(hb)) + if (symbol_conf.report_hierarchy) + nr_entries = hb->nr_hierarchy_entries; + else if (hist_browser__has_filter(hb)) nr_entries = hb->nr_non_filtered_entries; else nr_entries = hb->hists->nr_entries; @@ -247,6 +250,38 @@ static int callchain__count_rows(struct rb_root *chain) return n; } +static int hierarchy_count_rows(struct hist_browser *hb, struct hist_entry *he, + bool include_children) +{ + int count = 0; + struct rb_node *node; + struct hist_entry *child; + + if (he->leaf) + return callchain__count_rows(&he->sorted_chain); + + if (he->has_no_entry) + return 1; + + node = rb_first(&he->hroot_out); + while (node) { + float percent; + + child = rb_entry(node, struct hist_entry, rb_node); + percent = hist_entry__get_percent_limit(child); + + if (!child->filtered && percent >= hb->min_pcnt) { + count++; + + if (include_children && child->unfolded) + count += hierarchy_count_rows(hb, child, true); + } + + node = rb_next(node); + } + return count; +} + static bool hist_entry__toggle_fold(struct hist_entry *he) { if (!he) @@ -326,11 +361,17 @@ static void callchain__init_have_children(struct rb_root *root) static void hist_entry__init_have_children(struct hist_entry *he) { - if (!he->init_have_children) { + if (he->init_have_children) + return; + + if (he->leaf) { he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain); callchain__init_have_children(&he->sorted_chain); - he->init_have_children = true; + } else { + he->has_children = !RB_EMPTY_ROOT(&he->hroot_out); } + + he->init_have_children = true; } static bool hist_browser__toggle_fold(struct hist_browser *browser) @@ -349,17 +390,49 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser) has_children = callchain_list__toggle_fold(cl); if (has_children) { + int child_rows = 0; + hist_entry__init_have_children(he); browser->b.nr_entries -= he->nr_rows; - browser->nr_callchain_rows -= he->nr_rows; - if (he->unfolded) - he->nr_rows = callchain__count_rows(&he->sorted_chain); + if (he->leaf) + browser->nr_callchain_rows -= he->nr_rows; else + browser->nr_hierarchy_entries -= he->nr_rows; + + if (symbol_conf.report_hierarchy) + child_rows = hierarchy_count_rows(browser, he, true); + + if (he->unfolded) { + if (he->leaf) + he->nr_rows = callchain__count_rows(&he->sorted_chain); + else + he->nr_rows = hierarchy_count_rows(browser, he, false); + + /* account grand children */ + if (symbol_conf.report_hierarchy) + browser->b.nr_entries += child_rows - he->nr_rows; + + if (!he->leaf && he->nr_rows == 0) { + he->has_no_entry = true; + he->nr_rows = 1; + } + } else { + if (symbol_conf.report_hierarchy) + browser->b.nr_entries -= child_rows - he->nr_rows; + + if (he->has_no_entry) + he->has_no_entry = false; + he->nr_rows = 0; + } browser->b.nr_entries += he->nr_rows; - browser->nr_callchain_rows += he->nr_rows; + + if (he->leaf) + browser->nr_callchain_rows += he->nr_rows; + else + browser->nr_hierarchy_entries += he->nr_rows; return true; } @@ -422,13 +495,38 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold) return n; } -static void hist_entry__set_folding(struct hist_entry *he, bool unfold) +static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he, + bool unfold __maybe_unused) +{ + float percent; + struct rb_node *nd; + struct hist_entry *child; + int n = 0; + + for (nd = rb_first(&he->hroot_out); nd; nd = rb_next(nd)) { + child = rb_entry(nd, struct hist_entry, rb_node); + percent = hist_entry__get_percent_limit(child); + if (!child->filtered && percent >= hb->min_pcnt) + n++; + } + + return n; +} + +static void hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *hb, bool unfold) { hist_entry__init_have_children(he); he->unfolded = unfold ? he->has_children : false; if (he->has_children) { - int n = callchain__set_folding(&he->sorted_chain, unfold); + int n; + + if (he->leaf) + n = callchain__set_folding(&he->sorted_chain, unfold); + else + n = hierarchy_set_folding(hb, he, unfold); + he->nr_rows = unfold ? n : 0; } else he->nr_rows = 0; @@ -438,19 +536,38 @@ static void __hist_browser__set_folding(struct hist_browser *browser, bool unfold) { struct rb_node *nd; - struct hists *hists = browser->hists; + struct hist_entry *he; + double percent; - for (nd = rb_first(&hists->entries); - (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL; - nd = rb_next(nd)) { - struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); - hist_entry__set_folding(he, unfold); - browser->nr_callchain_rows += he->nr_rows; + nd = rb_first(&browser->hists->entries); + while (nd) { + he = rb_entry(nd, struct hist_entry, rb_node); + + /* set folding state even if it's currently folded */ + nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD); + + hist_entry__set_folding(he, browser, unfold); + + percent = hist_entry__get_percent_limit(he); + if (he->filtered || percent < browser->min_pcnt) + continue; + + if (!he->depth || unfold) + browser->nr_hierarchy_entries++; + if (he->leaf) + browser->nr_callchain_rows += he->nr_rows; + else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { + browser->nr_hierarchy_entries++; + he->has_no_entry = true; + he->nr_rows = 1; + } else + he->has_no_entry = false; } } static void hist_browser__set_folding(struct hist_browser *browser, bool unfold) { + browser->nr_hierarchy_entries = 0; browser->nr_callchain_rows = 0; __hist_browser__set_folding(browser, unfold); @@ -657,9 +774,24 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser, return 1; } +static bool check_percent_display(struct rb_node *node, u64 parent_total) +{ + struct callchain_node *child; + + if (node == NULL) + return false; + + if (rb_next(node)) + return true; + + child = rb_entry(node, struct callchain_node, rb_node); + return callchain_cumul_hits(child) != parent_total; +} + static int hist_browser__show_callchain_flat(struct hist_browser *browser, struct rb_root *root, unsigned short row, u64 total, + u64 parent_total, print_callchain_entry_fn print, struct callchain_print_arg *arg, check_output_full_fn is_output_full) @@ -669,7 +801,7 @@ static int hist_browser__show_callchain_flat(struct hist_browser *browser, bool need_percent; node = rb_first(root); - need_percent = node && rb_next(node); + need_percent = check_percent_display(node, parent_total); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); @@ -763,6 +895,7 @@ static char *hist_browser__folded_callchain_str(struct hist_browser *browser, static int hist_browser__show_callchain_folded(struct hist_browser *browser, struct rb_root *root, unsigned short row, u64 total, + u64 parent_total, print_callchain_entry_fn print, struct callchain_print_arg *arg, check_output_full_fn is_output_full) @@ -772,7 +905,7 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser, bool need_percent; node = rb_first(root); - need_percent = node && rb_next(node); + need_percent = check_percent_display(node, parent_total); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); @@ -844,20 +977,24 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser, return row - first_row; } -static int hist_browser__show_callchain(struct hist_browser *browser, +static int hist_browser__show_callchain_graph(struct hist_browser *browser, struct rb_root *root, int level, unsigned short row, u64 total, + u64 parent_total, print_callchain_entry_fn print, struct callchain_print_arg *arg, check_output_full_fn is_output_full) { struct rb_node *node; int first_row = row, offset = level * LEVEL_OFFSET_STEP; - u64 new_total; bool need_percent; + u64 percent_total = total; + + if (callchain_param.mode == CHAIN_GRAPH_REL) + percent_total = parent_total; node = rb_first(root); - need_percent = node && rb_next(node); + need_percent = check_percent_display(node, parent_total); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); @@ -878,7 +1015,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser, folded_sign = callchain_list__folded(chain); row += hist_browser__show_callchain_list(browser, child, - chain, row, total, + chain, row, percent_total, was_first && need_percent, offset + extra_offset, print, arg); @@ -893,13 +1030,9 @@ static int hist_browser__show_callchain(struct hist_browser *browser, if (folded_sign == '-') { const int new_level = level + (extra_offset ? 2 : 1); - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = child->children_hit; - else - new_total = total; - - row += hist_browser__show_callchain(browser, &child->rb_root, - new_level, row, new_total, + row += hist_browser__show_callchain_graph(browser, &child->rb_root, + new_level, row, total, + child->children_hit, print, arg, is_output_full); } if (is_output_full(browser, row)) @@ -910,6 +1043,45 @@ static int hist_browser__show_callchain(struct hist_browser *browser, return row - first_row; } +static int hist_browser__show_callchain(struct hist_browser *browser, + struct hist_entry *entry, int level, + unsigned short row, + print_callchain_entry_fn print, + struct callchain_print_arg *arg, + check_output_full_fn is_output_full) +{ + u64 total = hists__total_period(entry->hists); + u64 parent_total; + int printed; + + if (symbol_conf.cumulate_callchain) + parent_total = entry->stat_acc->period; + else + parent_total = entry->stat.period; + + if (callchain_param.mode == CHAIN_FLAT) { + printed = hist_browser__show_callchain_flat(browser, + &entry->sorted_chain, row, + total, parent_total, print, arg, + is_output_full); + } else if (callchain_param.mode == CHAIN_FOLDED) { + printed = hist_browser__show_callchain_folded(browser, + &entry->sorted_chain, row, + total, parent_total, print, arg, + is_output_full); + } else { + printed = hist_browser__show_callchain_graph(browser, + &entry->sorted_chain, level, row, + total, parent_total, print, arg, + is_output_full); + } + + if (arg->is_current_entry) + browser->he_selection = entry; + + return printed; +} + struct hpp_arg { struct ui_browser *b; char folded_sign; @@ -1006,7 +1178,6 @@ static int hist_browser__show_entry(struct hist_browser *browser, struct hist_entry *entry, unsigned short row) { - char s[256]; int printed = 0; int width = browser->b.width; char folded_sign = ' '; @@ -1031,16 +1202,18 @@ static int hist_browser__show_entry(struct hist_browser *browser, .folded_sign = folded_sign, .current_entry = current_entry, }; - struct perf_hpp hpp = { - .buf = s, - .size = sizeof(s), - .ptr = &arg, - }; int column = 0; hist_browser__gotorc(browser, row, 0); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { + char s[2048]; + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + .ptr = &arg, + }; + if (perf_hpp__should_skip(fmt, entry->hists) || column++ < browser->b.horiz_scroll) continue; @@ -1065,11 +1238,18 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (fmt->color) { - width -= fmt->color(fmt, &hpp, entry); + int ret = fmt->color(fmt, &hpp, entry); + hist_entry__snprintf_alignment(entry, &hpp, fmt, ret); + /* + * fmt->color() already used ui_browser to + * print the non alignment bits, skip it (+ret): + */ + ui_browser__printf(&browser->b, "%s", s + ret); } else { - width -= fmt->entry(fmt, &hpp, entry); + hist_entry__snprintf_alignment(entry, &hpp, fmt, fmt->entry(fmt, &hpp, entry)); ui_browser__printf(&browser->b, "%s", s); } + width -= hpp.buf - s; } /* The scroll bar isn't being used */ @@ -1084,43 +1264,246 @@ static int hist_browser__show_entry(struct hist_browser *browser, --row_offset; if (folded_sign == '-' && row != browser->b.rows) { - u64 total = hists__total_period(entry->hists); struct callchain_print_arg arg = { .row_offset = row_offset, .is_current_entry = current_entry, }; - if (callchain_param.mode == CHAIN_GRAPH_REL) { - if (symbol_conf.cumulate_callchain) - total = entry->stat_acc->period; - else - total = entry->stat.period; - } - - if (callchain_param.mode == CHAIN_FLAT) { - printed += hist_browser__show_callchain_flat(browser, - &entry->sorted_chain, row, total, - hist_browser__show_callchain_entry, &arg, - hist_browser__check_output_full); - } else if (callchain_param.mode == CHAIN_FOLDED) { - printed += hist_browser__show_callchain_folded(browser, - &entry->sorted_chain, row, total, + printed += hist_browser__show_callchain(browser, entry, 1, row, hist_browser__show_callchain_entry, &arg, hist_browser__check_output_full); + } + + return printed; +} + +static int hist_browser__show_hierarchy_entry(struct hist_browser *browser, + struct hist_entry *entry, + unsigned short row, + int level) +{ + int printed = 0; + int width = browser->b.width; + char folded_sign = ' '; + bool current_entry = ui_browser__is_current_entry(&browser->b, row); + off_t row_offset = entry->row_offset; + bool first = true; + struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; + struct hpp_arg arg = { + .b = &browser->b, + .current_entry = current_entry, + }; + int column = 0; + int hierarchy_indent = (entry->hists->nr_hpp_node - 2) * HIERARCHY_INDENT; + + if (current_entry) { + browser->he_selection = entry; + browser->selection = &entry->ms; + } + + hist_entry__init_have_children(entry); + folded_sign = hist_entry__folded(entry); + arg.folded_sign = folded_sign; + + if (entry->leaf && row_offset) { + row_offset--; + goto show_callchain; + } + + hist_browser__gotorc(browser, row, 0); + + if (current_entry && browser->b.navkeypressed) + ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED); + else + ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL); + + ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT); + width -= level * HIERARCHY_INDENT; + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&entry->hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + char s[2048]; + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + .ptr = &arg, + }; + + if (perf_hpp__should_skip(fmt, entry->hists) || + column++ < browser->b.horiz_scroll) + continue; + + if (current_entry && browser->b.navkeypressed) { + ui_browser__set_color(&browser->b, + HE_COLORSET_SELECTED); } else { - printed += hist_browser__show_callchain(browser, - &entry->sorted_chain, 1, row, total, - hist_browser__show_callchain_entry, &arg, - hist_browser__check_output_full); + ui_browser__set_color(&browser->b, + HE_COLORSET_NORMAL); + } + + if (first) { + ui_browser__printf(&browser->b, "%c", folded_sign); + width--; + first = false; + } else { + ui_browser__printf(&browser->b, " "); + width -= 2; + } + + if (fmt->color) { + int ret = fmt->color(fmt, &hpp, entry); + hist_entry__snprintf_alignment(entry, &hpp, fmt, ret); + /* + * fmt->color() already used ui_browser to + * print the non alignment bits, skip it (+ret): + */ + ui_browser__printf(&browser->b, "%s", s + ret); + } else { + int ret = fmt->entry(fmt, &hpp, entry); + hist_entry__snprintf_alignment(entry, &hpp, fmt, ret); + ui_browser__printf(&browser->b, "%s", s); + } + width -= hpp.buf - s; + } + + ui_browser__write_nstring(&browser->b, "", hierarchy_indent); + width -= hierarchy_indent; + + if (column >= browser->b.horiz_scroll) { + char s[2048]; + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + .ptr = &arg, + }; + + if (current_entry && browser->b.navkeypressed) { + ui_browser__set_color(&browser->b, + HE_COLORSET_SELECTED); + } else { + ui_browser__set_color(&browser->b, + HE_COLORSET_NORMAL); } - if (arg.is_current_entry) - browser->he_selection = entry; + perf_hpp_list__for_each_format(entry->hpp_list, fmt) { + ui_browser__write_nstring(&browser->b, "", 2); + width -= 2; + + /* + * No need to call hist_entry__snprintf_alignment() + * since this fmt is always the last column in the + * hierarchy mode. + */ + if (fmt->color) { + width -= fmt->color(fmt, &hpp, entry); + } else { + int i = 0; + + width -= fmt->entry(fmt, &hpp, entry); + ui_browser__printf(&browser->b, "%s", ltrim(s)); + + while (isspace(s[i++])) + width++; + } + } + } + + /* The scroll bar isn't being used */ + if (!browser->b.navkeypressed) + width += 1; + + ui_browser__write_nstring(&browser->b, "", width); + + ++row; + ++printed; + +show_callchain: + if (entry->leaf && folded_sign == '-' && row != browser->b.rows) { + struct callchain_print_arg carg = { + .row_offset = row_offset, + }; + + printed += hist_browser__show_callchain(browser, entry, + level + 1, row, + hist_browser__show_callchain_entry, &carg, + hist_browser__check_output_full); } return printed; } +static int hist_browser__show_no_entry(struct hist_browser *browser, + unsigned short row, int level) +{ + int width = browser->b.width; + bool current_entry = ui_browser__is_current_entry(&browser->b, row); + bool first = true; + int column = 0; + int ret; + struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; + int indent = browser->hists->nr_hpp_node - 2; + + if (current_entry) { + browser->he_selection = NULL; + browser->selection = NULL; + } + + hist_browser__gotorc(browser, row, 0); + + if (current_entry && browser->b.navkeypressed) + ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED); + else + ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL); + + ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT); + width -= level * HIERARCHY_INDENT; + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&browser->hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + if (perf_hpp__should_skip(fmt, browser->hists) || + column++ < browser->b.horiz_scroll) + continue; + + ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists)); + + if (first) { + /* for folded sign */ + first = false; + ret++; + } else { + /* space between columns */ + ret += 2; + } + + ui_browser__write_nstring(&browser->b, "", ret); + width -= ret; + } + + ui_browser__write_nstring(&browser->b, "", indent * HIERARCHY_INDENT); + width -= indent * HIERARCHY_INDENT; + + if (column >= browser->b.horiz_scroll) { + char buf[32]; + + ret = snprintf(buf, sizeof(buf), "no entry >= %.2f%%", browser->min_pcnt); + ui_browser__printf(&browser->b, " %s", buf); + width -= ret + 2; + } + + /* The scroll bar isn't being used */ + if (!browser->b.navkeypressed) + width += 1; + + ui_browser__write_nstring(&browser->b, "", width); + return 1; +} + static int advance_hpp_check(struct perf_hpp *hpp, int inc) { advance_hpp(hpp, inc); @@ -1144,7 +1527,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char * return ret; } - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { if (perf_hpp__should_skip(fmt, hists) || column++ < browser->b.horiz_scroll) continue; @@ -1160,11 +1543,96 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char * return ret; } +static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *browser, char *buf, size_t size) +{ + struct hists *hists = browser->hists; + struct perf_hpp dummy_hpp = { + .buf = buf, + .size = size, + }; + struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; + size_t ret = 0; + int column = 0; + int indent = hists->nr_hpp_node - 2; + bool first_node, first_col; + + ret = scnprintf(buf, size, " "); + if (advance_hpp_check(&dummy_hpp, ret)) + return ret; + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + if (column++ < browser->b.horiz_scroll) + continue; + + ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + + ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " "); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + } + + ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s", + indent * HIERARCHY_INDENT, ""); + if (advance_hpp_check(&dummy_hpp, ret)) + return ret; + + first_node = true; + list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) { + if (!first_node) { + ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " / "); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + } + first_node = false; + + first_col = true; + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + char *start; + + if (perf_hpp__should_skip(fmt, hists)) + continue; + + if (!first_col) { + ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "+"); + if (advance_hpp_check(&dummy_hpp, ret)) + break; + } + first_col = false; + + ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); + dummy_hpp.buf[ret] = '\0'; + rtrim(dummy_hpp.buf); + + start = ltrim(dummy_hpp.buf); + ret = strlen(start); + + if (start != dummy_hpp.buf) + memmove(dummy_hpp.buf, start, ret + 1); + + if (advance_hpp_check(&dummy_hpp, ret)) + break; + } + } + + return ret; +} + static void hist_browser__show_headers(struct hist_browser *browser) { char headers[1024]; - hists_browser__scnprintf_headers(browser, headers, sizeof(headers)); + if (symbol_conf.report_hierarchy) + hists_browser__scnprintf_hierarchy_headers(browser, headers, + sizeof(headers)); + else + hists_browser__scnprintf_headers(browser, headers, + sizeof(headers)); ui_browser__gotorc(&browser->b, 0, 0); ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1); @@ -1196,18 +1664,34 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) hb->he_selection = NULL; hb->selection = NULL; - for (nd = browser->top; nd; nd = rb_next(nd)) { + for (nd = browser->top; nd; nd = rb_hierarchy_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); float percent; - if (h->filtered) + if (h->filtered) { + /* let it move to sibling */ + h->unfolded = false; continue; + } percent = hist_entry__get_percent_limit(h); if (percent < hb->min_pcnt) continue; - row += hist_browser__show_entry(hb, h, row); + if (symbol_conf.report_hierarchy) { + row += hist_browser__show_hierarchy_entry(hb, h, row, + h->depth); + if (row == browser->rows) + break; + + if (h->has_no_entry) { + hist_browser__show_no_entry(hb, row, h->depth + 1); + row++; + } + } else { + row += hist_browser__show_entry(hb, h, row); + } + if (row == browser->rows) break; } @@ -1225,7 +1709,14 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd, if (!h->filtered && percent >= min_pcnt) return nd; - nd = rb_next(nd); + /* + * If it's filtered, its all children also were filtered. + * So move to sibling node. + */ + if (rb_next(nd)) + nd = rb_next(nd); + else + nd = rb_hierarchy_next(nd); } return NULL; @@ -1241,7 +1732,7 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd, if (!h->filtered && percent >= min_pcnt) return nd; - nd = rb_prev(nd); + nd = rb_hierarchy_prev(nd); } return NULL; @@ -1271,8 +1762,8 @@ static void ui_browser__hists_seek(struct ui_browser *browser, nd = browser->top; goto do_offset; case SEEK_END: - nd = hists__filter_prev_entries(rb_last(browser->entries), - hb->min_pcnt); + nd = rb_hierarchy_last(rb_last(browser->entries)); + nd = hists__filter_prev_entries(nd, hb->min_pcnt); first = false; break; default: @@ -1306,7 +1797,7 @@ static void ui_browser__hists_seek(struct ui_browser *browser, if (offset > 0) { do { h = rb_entry(nd, struct hist_entry, rb_node); - if (h->unfolded) { + if (h->unfolded && h->leaf) { u16 remaining = h->nr_rows - h->row_offset; if (offset > remaining) { offset -= remaining; @@ -1318,7 +1809,8 @@ static void ui_browser__hists_seek(struct ui_browser *browser, break; } } - nd = hists__filter_entries(rb_next(nd), hb->min_pcnt); + nd = hists__filter_entries(rb_hierarchy_next(nd), + hb->min_pcnt); if (nd == NULL) break; --offset; @@ -1327,7 +1819,7 @@ static void ui_browser__hists_seek(struct ui_browser *browser, } else if (offset < 0) { while (1) { h = rb_entry(nd, struct hist_entry, rb_node); - if (h->unfolded) { + if (h->unfolded && h->leaf) { if (first) { if (-offset > h->row_offset) { offset += h->row_offset; @@ -1351,7 +1843,7 @@ static void ui_browser__hists_seek(struct ui_browser *browser, } } - nd = hists__filter_prev_entries(rb_prev(nd), + nd = hists__filter_prev_entries(rb_hierarchy_prev(nd), hb->min_pcnt); if (nd == NULL) break; @@ -1364,7 +1856,7 @@ static void ui_browser__hists_seek(struct ui_browser *browser, * row_offset at its last entry. */ h = rb_entry(nd, struct hist_entry, rb_node); - if (h->unfolded) + if (h->unfolded && h->leaf) h->row_offset = h->nr_rows; break; } @@ -1378,17 +1870,14 @@ static void ui_browser__hists_seek(struct ui_browser *browser, } static int hist_browser__fprintf_callchain(struct hist_browser *browser, - struct hist_entry *he, FILE *fp) + struct hist_entry *he, FILE *fp, + int level) { - u64 total = hists__total_period(he->hists); struct callchain_print_arg arg = { .fp = fp, }; - if (symbol_conf.cumulate_callchain) - total = he->stat_acc->period; - - hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total, + hist_browser__show_callchain(browser, he, level, 0, hist_browser__fprintf_callchain_entry, &arg, hist_browser__check_dump_full); return arg.printed; @@ -1414,7 +1903,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, if (symbol_conf.use_callchain) printed += fprintf(fp, "%c ", folded_sign); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { if (perf_hpp__should_skip(fmt, he->hists)) continue; @@ -1425,12 +1914,71 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, first = false; ret = fmt->entry(fmt, &hpp, he); + ret = hist_entry__snprintf_alignment(he, &hpp, fmt, ret); advance_hpp(&hpp, ret); } - printed += fprintf(fp, "%s\n", rtrim(s)); + printed += fprintf(fp, "%s\n", s); if (folded_sign == '-') - printed += hist_browser__fprintf_callchain(browser, he, fp); + printed += hist_browser__fprintf_callchain(browser, he, fp, 1); + + return printed; +} + + +static int hist_browser__fprintf_hierarchy_entry(struct hist_browser *browser, + struct hist_entry *he, + FILE *fp, int level) +{ + char s[8192]; + int printed = 0; + char folded_sign = ' '; + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + }; + struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; + bool first = true; + int ret; + int hierarchy_indent = (he->hists->nr_hpp_node - 2) * HIERARCHY_INDENT; + + printed = fprintf(fp, "%*s", level * HIERARCHY_INDENT, ""); + + folded_sign = hist_entry__folded(he); + printed += fprintf(fp, "%c", folded_sign); + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&he->hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + if (!first) { + ret = scnprintf(hpp.buf, hpp.size, " "); + advance_hpp(&hpp, ret); + } else + first = false; + + ret = fmt->entry(fmt, &hpp, he); + advance_hpp(&hpp, ret); + } + + ret = scnprintf(hpp.buf, hpp.size, "%*s", hierarchy_indent, ""); + advance_hpp(&hpp, ret); + + perf_hpp_list__for_each_format(he->hpp_list, fmt) { + ret = scnprintf(hpp.buf, hpp.size, " "); + advance_hpp(&hpp, ret); + + ret = fmt->entry(fmt, &hpp, he); + advance_hpp(&hpp, ret); + } + + printed += fprintf(fp, "%s\n", rtrim(s)); + + if (he->leaf && folded_sign == '-') { + printed += hist_browser__fprintf_callchain(browser, he, fp, + he->depth + 1); + } return printed; } @@ -1444,8 +1992,16 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp) while (nd) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - printed += hist_browser__fprintf_entry(browser, h, fp); - nd = hists__filter_entries(rb_next(nd), browser->min_pcnt); + if (symbol_conf.report_hierarchy) { + printed += hist_browser__fprintf_hierarchy_entry(browser, + h, fp, + h->depth); + } else { + printed += hist_browser__fprintf_entry(browser, h, fp); + } + + nd = hists__filter_entries(rb_hierarchy_next(nd), + browser->min_pcnt); } return printed; @@ -1580,11 +2136,18 @@ static int hists__browser_title(struct hists *hists, if (hists->uid_filter_str) printed += snprintf(bf + printed, size - printed, ", UID: %s", hists->uid_filter_str); - if (thread) - printed += scnprintf(bf + printed, size - printed, + if (thread) { + if (sort__has_thread) { + printed += scnprintf(bf + printed, size - printed, ", Thread: %s(%d)", (thread->comm_set ? thread__comm_str(thread) : ""), thread->tid); + } else { + printed += scnprintf(bf + printed, size - printed, + ", Thread: %s", + (thread->comm_set ? thread__comm_str(thread) : "")); + } + } if (dso) printed += scnprintf(bf + printed, size - printed, ", DSO: %s", dso->short_name); @@ -1759,15 +2322,24 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act) { struct thread *thread = act->thread; + if ((!sort__has_thread && !sort__has_comm) || thread == NULL) + return 0; + if (browser->hists->thread_filter) { pstack__remove(browser->pstack, &browser->hists->thread_filter); perf_hpp__set_elide(HISTC_THREAD, false); thread__zput(browser->hists->thread_filter); ui_helpline__pop(); } else { - ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"", - thread->comm_set ? thread__comm_str(thread) : "", - thread->tid); + if (sort__has_thread) { + ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"", + thread->comm_set ? thread__comm_str(thread) : "", + thread->tid); + } else { + ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s thread\"", + thread->comm_set ? thread__comm_str(thread) : ""); + } + browser->hists->thread_filter = thread__get(thread); perf_hpp__set_elide(HISTC_THREAD, false); pstack__push(browser->pstack, &browser->hists->thread_filter); @@ -1782,13 +2354,22 @@ static int add_thread_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct thread *thread) { - if (thread == NULL) + int ret; + + if ((!sort__has_thread && !sort__has_comm) || thread == NULL) return 0; - if (asprintf(optstr, "Zoom %s %s(%d) thread", - browser->hists->thread_filter ? "out of" : "into", - thread->comm_set ? thread__comm_str(thread) : "", - thread->tid) < 0) + if (sort__has_thread) { + ret = asprintf(optstr, "Zoom %s %s(%d) thread", + browser->hists->thread_filter ? "out of" : "into", + thread->comm_set ? thread__comm_str(thread) : "", + thread->tid); + } else { + ret = asprintf(optstr, "Zoom %s %s thread", + browser->hists->thread_filter ? "out of" : "into", + thread->comm_set ? thread__comm_str(thread) : ""); + } + if (ret < 0) return 0; act->thread = thread; @@ -1801,6 +2382,9 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act) { struct map *map = act->ms.map; + if (!sort__has_dso || map == NULL) + return 0; + if (browser->hists->dso_filter) { pstack__remove(browser->pstack, &browser->hists->dso_filter); perf_hpp__set_elide(HISTC_DSO, false); @@ -1825,7 +2409,7 @@ static int add_dso_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct map *map) { - if (map == NULL) + if (!sort__has_dso || map == NULL) return 0; if (asprintf(optstr, "Zoom %s %s DSO", @@ -1850,7 +2434,7 @@ static int add_map_opt(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct map *map) { - if (map == NULL) + if (!sort__has_dso || map == NULL) return 0; if (asprintf(optstr, "Browse map details") < 0) @@ -1952,6 +2536,9 @@ add_exit_opt(struct hist_browser *browser __maybe_unused, static int do_zoom_socket(struct hist_browser *browser, struct popup_action *act) { + if (!sort__has_socket || act->socket < 0) + return 0; + if (browser->hists->socket_filter > -1) { pstack__remove(browser->pstack, &browser->hists->socket_filter); browser->hists->socket_filter = -1; @@ -1971,7 +2558,7 @@ static int add_socket_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, int socket_id) { - if (socket_id < 0) + if (!sort__has_socket || socket_id < 0) return 0; if (asprintf(optstr, "Zoom %s Processor Socket %d", @@ -1989,17 +2576,60 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb) u64 nr_entries = 0; struct rb_node *nd = rb_first(&hb->hists->entries); - if (hb->min_pcnt == 0) { + if (hb->min_pcnt == 0 && !symbol_conf.report_hierarchy) { hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries; return; } while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) { nr_entries++; - nd = rb_next(nd); + nd = rb_hierarchy_next(nd); } hb->nr_non_filtered_entries = nr_entries; + hb->nr_hierarchy_entries = nr_entries; +} + +static void hist_browser__update_percent_limit(struct hist_browser *hb, + double percent) +{ + struct hist_entry *he; + struct rb_node *nd = rb_first(&hb->hists->entries); + u64 total = hists__total_period(hb->hists); + u64 min_callchain_hits = total * (percent / 100); + + hb->min_pcnt = callchain_param.min_percent = percent; + + while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) { + he = rb_entry(nd, struct hist_entry, rb_node); + + if (he->has_no_entry) { + he->has_no_entry = false; + he->nr_rows = 0; + } + + if (!he->leaf || !symbol_conf.use_callchain) + goto next; + + if (callchain_param.mode == CHAIN_GRAPH_REL) { + total = he->stat.period; + + if (symbol_conf.cumulate_callchain) + total = he->stat_acc->period; + + min_callchain_hits = total * (percent / 100); + } + + callchain_param.sort(&he->sorted_chain, he->callchain, + min_callchain_hits, &callchain_param); + +next: + nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD); + + /* force to re-evaluate folding state of callchains */ + he->init_have_children = false; + hist_entry__set_folding(he, hb, false); + } } static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, @@ -2037,6 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "E Expand all callchains\n" \ "F Toggle percentage of filtered entries\n" \ "H Display column headers\n" \ + "L Change percent limit\n" \ "m Display context menu\n" \ "S Zoom into current Processor Socket\n" \ @@ -2077,7 +2708,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, memset(options, 0, sizeof(options)); memset(actions, 0, sizeof(actions)); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(browser->hists, fmt) { perf_hpp__reset_width(fmt, hists); /* * This is done just once, and activates the horizontal scrolling @@ -2192,6 +2823,24 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, top->zero = !top->zero; } continue; + case 'L': + if (ui_browser__input_window("Percent Limit", + "Please enter the value you want to hide entries under that percent.", + buf, "ENTER: OK, ESC: Cancel", + delay_secs * 2) == K_ENTER) { + char *end; + double new_percent = strtod(buf, &end); + + if (new_percent < 0 || new_percent > 100) { + ui_browser__warning(&browser->b, delay_secs * 2, + "Invalid percent: %.2f", new_percent); + continue; + } + + hist_browser__update_percent_limit(browser, new_percent); + hist_browser__reset(browser); + } + continue; case K_F1: case 'h': case '?': @@ -2263,10 +2912,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, continue; } - if (!sort__has_sym) - goto add_exit_option; - - if (browser->selection == NULL) + if (!sort__has_sym || browser->selection == NULL) goto skip_annotation; if (sort__mode == SORT_MODE__BRANCH) { @@ -2306,11 +2952,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, &options[nr_options], socked_id); /* perf script support */ + if (!is_report_browser(hbt)) + goto skip_scripting; + if (browser->he_selection) { - nr_options += add_script_opt(browser, - &actions[nr_options], - &options[nr_options], - thread, NULL); + if (sort__has_thread && thread) { + nr_options += add_script_opt(browser, + &actions[nr_options], + &options[nr_options], + thread, NULL); + } /* * Note that browser->selection != NULL * when browser->he_selection is not NULL, @@ -2320,16 +2971,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, * * See hist_browser__show_entry. */ - nr_options += add_script_opt(browser, - &actions[nr_options], - &options[nr_options], - NULL, browser->selection->sym); + if (sort__has_sym && browser->selection->sym) { + nr_options += add_script_opt(browser, + &actions[nr_options], + &options[nr_options], + NULL, browser->selection->sym); + } } nr_options += add_script_opt(browser, &actions[nr_options], &options[nr_options], NULL, NULL); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); -add_exit_option: +skip_scripting: nr_options += add_exit_opt(browser, &actions[nr_options], &options[nr_options]); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 0f8dcfdfb10f3..bd9bf7e343b1e 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -306,7 +306,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, nr_cols = 0; - perf_hpp__for_each_format(fmt) + hists__for_each_format(hists, fmt) col_types[nr_cols++] = G_TYPE_STRING; store = gtk_tree_store_newv(nr_cols, col_types); @@ -317,7 +317,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, hists)) continue; @@ -367,7 +367,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, h->hists)) continue; @@ -396,6 +396,194 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, gtk_container_add(GTK_CONTAINER(window), view); } +static void perf_gtk__add_hierarchy_entries(struct hists *hists, + struct rb_root *root, + GtkTreeStore *store, + GtkTreeIter *parent, + struct perf_hpp *hpp, + float min_pcnt) +{ + int col_idx = 0; + struct rb_node *node; + struct hist_entry *he; + struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; + u64 total = hists__total_period(hists); + int size; + + for (node = rb_first(root); node; node = rb_next(node)) { + GtkTreeIter iter; + float percent; + char *bf; + + he = rb_entry(node, struct hist_entry, rb_node); + if (he->filtered) + continue; + + percent = hist_entry__get_percent_limit(he); + if (percent < min_pcnt) + continue; + + gtk_tree_store_append(store, &iter, parent); + + col_idx = 0; + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + if (fmt->color) + fmt->color(fmt, hpp, he); + else + fmt->entry(fmt, hpp, he); + + gtk_tree_store_set(store, &iter, col_idx++, hpp->buf, -1); + } + + bf = hpp->buf; + size = hpp->size; + perf_hpp_list__for_each_format(he->hpp_list, fmt) { + int ret; + + if (fmt->color) + ret = fmt->color(fmt, hpp, he); + else + ret = fmt->entry(fmt, hpp, he); + + snprintf(hpp->buf + ret, hpp->size - ret, " "); + advance_hpp(hpp, ret + 2); + } + + gtk_tree_store_set(store, &iter, col_idx, ltrim(rtrim(bf)), -1); + + if (!he->leaf) { + hpp->buf = bf; + hpp->size = size; + + perf_gtk__add_hierarchy_entries(hists, &he->hroot_out, + store, &iter, hpp, + min_pcnt); + + if (!hist_entry__has_hierarchy_children(he, min_pcnt)) { + char buf[32]; + GtkTreeIter child; + + snprintf(buf, sizeof(buf), "no entry >= %.2f%%", + min_pcnt); + + gtk_tree_store_append(store, &child, &iter); + gtk_tree_store_set(store, &child, col_idx, buf, -1); + } + } + + if (symbol_conf.use_callchain && he->leaf) { + if (callchain_param.mode == CHAIN_GRAPH_REL) + total = symbol_conf.cumulate_callchain ? + he->stat_acc->period : he->stat.period; + + perf_gtk__add_callchain(&he->sorted_chain, store, &iter, + col_idx, total); + } + } + +} + +static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists, + float min_pcnt) +{ + struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; + GType col_types[MAX_COLUMNS]; + GtkCellRenderer *renderer; + GtkTreeStore *store; + GtkWidget *view; + int col_idx; + int nr_cols = 0; + char s[512]; + char buf[512]; + bool first_node, first_col; + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + }; + + hists__for_each_format(hists, fmt) { + if (perf_hpp__is_sort_entry(fmt) || + perf_hpp__is_dynamic_entry(fmt)) + break; + + col_types[nr_cols++] = G_TYPE_STRING; + } + col_types[nr_cols++] = G_TYPE_STRING; + + store = gtk_tree_store_newv(nr_cols, col_types); + view = gtk_tree_view_new(); + renderer = gtk_cell_renderer_text_new(); + + col_idx = 0; + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, fmt->name, + renderer, "markup", + col_idx++, NULL); + } + + /* construct merged column header since sort keys share single column */ + buf[0] = '\0'; + first_node = true; + list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) { + if (!first_node) + strcat(buf, " / "); + first_node = false; + + first_col = true; + perf_hpp_list__for_each_format(&fmt_node->hpp ,fmt) { + if (perf_hpp__should_skip(fmt, hists)) + continue; + + if (!first_col) + strcat(buf, "+"); + first_col = false; + + fmt->header(fmt, &hpp, hists_to_evsel(hists)); + strcat(buf, ltrim(rtrim(hpp.buf))); + } + } + + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, buf, + renderer, "markup", + col_idx++, NULL); + + for (col_idx = 0; col_idx < nr_cols; col_idx++) { + GtkTreeViewColumn *column; + + column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx); + gtk_tree_view_column_set_resizable(column, TRUE); + + if (col_idx == 0) { + gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view), + column); + } + } + + gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); + g_object_unref(GTK_TREE_MODEL(store)); + + perf_gtk__add_hierarchy_entries(hists, &hists->entries, store, + NULL, &hpp, min_pcnt); + + gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE); + + g_signal_connect(view, "row-activated", + G_CALLBACK(on_row_activated), NULL); + gtk_container_add(GTK_CONTAINER(window), view); +} + int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt __maybe_unused, @@ -463,7 +651,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, GTK_POLICY_AUTOMATIC, GTK_POLICY_AUTOMATIC); - perf_gtk__show_hists(scrolled_window, hists, min_pcnt); + if (symbol_conf.report_hierarchy) + perf_gtk__show_hierarchy(scrolled_window, hists, min_pcnt); + else + perf_gtk__show_hists(scrolled_window, hists, min_pcnt); tab_label = gtk_label_new(evname); diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index bf2a66e254eac..3baeaa6e71b5a 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -5,6 +5,7 @@ #include "../util/util.h" #include "../util/sort.h" #include "../util/evsel.h" +#include "../util/evlist.h" /* hist period print (hpp) functions */ @@ -371,7 +372,20 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, return 0; } -#define HPP__COLOR_PRINT_FNS(_name, _fn) \ +static bool perf_hpp__is_hpp_entry(struct perf_hpp_fmt *a) +{ + return a->header == hpp__header_fn; +} + +static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + if (!perf_hpp__is_hpp_entry(a) || !perf_hpp__is_hpp_entry(b)) + return false; + + return a->idx == b->idx; +} + +#define HPP__COLOR_PRINT_FNS(_name, _fn, _idx) \ { \ .name = _name, \ .header = hpp__header_fn, \ @@ -381,9 +395,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ .sort = hpp__sort_ ## _fn, \ + .idx = PERF_HPP__ ## _idx, \ + .equal = hpp__equal, \ } -#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn) \ +#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn, _idx) \ { \ .name = _name, \ .header = hpp__header_fn, \ @@ -393,9 +409,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ .sort = hpp__sort_ ## _fn, \ + .idx = PERF_HPP__ ## _idx, \ + .equal = hpp__equal, \ } -#define HPP__PRINT_FNS(_name, _fn) \ +#define HPP__PRINT_FNS(_name, _fn, _idx) \ { \ .name = _name, \ .header = hpp__header_fn, \ @@ -404,22 +422,25 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, .cmp = hpp__nop_cmp, \ .collapse = hpp__nop_cmp, \ .sort = hpp__sort_ ## _fn, \ + .idx = PERF_HPP__ ## _idx, \ + .equal = hpp__equal, \ } struct perf_hpp_fmt perf_hpp__format[] = { - HPP__COLOR_PRINT_FNS("Overhead", overhead), - HPP__COLOR_PRINT_FNS("sys", overhead_sys), - HPP__COLOR_PRINT_FNS("usr", overhead_us), - HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys), - HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us), - HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc), - HPP__PRINT_FNS("Samples", samples), - HPP__PRINT_FNS("Period", period) + HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD), + HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS), + HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US), + HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS), + HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US), + HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC), + HPP__PRINT_FNS("Samples", samples, SAMPLES), + HPP__PRINT_FNS("Period", period, PERIOD) }; -LIST_HEAD(perf_hpp__list); -LIST_HEAD(perf_hpp__sort_list); - +struct perf_hpp_list perf_hpp_list = { + .fields = LIST_HEAD_INIT(perf_hpp_list.fields), + .sorts = LIST_HEAD_INIT(perf_hpp_list.sorts), +}; #undef HPP__COLOR_PRINT_FNS #undef HPP__COLOR_ACC_PRINT_FNS @@ -485,63 +506,60 @@ void perf_hpp__init(void) hpp_dimension__add_output(PERF_HPP__PERIOD); } -void perf_hpp__column_register(struct perf_hpp_fmt *format) +void perf_hpp_list__column_register(struct perf_hpp_list *list, + struct perf_hpp_fmt *format) { - list_add_tail(&format->list, &perf_hpp__list); + list_add_tail(&format->list, &list->fields); } -void perf_hpp__column_unregister(struct perf_hpp_fmt *format) +void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format) { - list_del(&format->list); + list_add_tail(&format->sort_list, &list->sorts); } -void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) -{ - list_add_tail(&format->sort_list, &perf_hpp__sort_list); -} - -void perf_hpp__column_enable(unsigned col) -{ - BUG_ON(col >= PERF_HPP__MAX_INDEX); - perf_hpp__column_register(&perf_hpp__format[col]); -} - -void perf_hpp__column_disable(unsigned col) +void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { - BUG_ON(col >= PERF_HPP__MAX_INDEX); - perf_hpp__column_unregister(&perf_hpp__format[col]); + list_del(&format->list); } void perf_hpp__cancel_cumulate(void) { + struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp; + if (is_strict_order(field_order)) return; - perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC); - perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead"; + ovh = &perf_hpp__format[PERF_HPP__OVERHEAD]; + acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC]; + + perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) { + if (acc->equal(acc, fmt)) { + perf_hpp__column_unregister(fmt); + continue; + } + + if (ovh->equal(ovh, fmt)) + fmt->name = "Overhead"; + } } -void perf_hpp__setup_output_field(void) +static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + return a->equal && a->equal(a, b); +} + +void perf_hpp__setup_output_field(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt; /* append sort keys to output field */ - perf_hpp__for_each_sort_list(fmt) { - if (!list_empty(&fmt->list)) - continue; - - /* - * sort entry fields are dynamically created, - * so they can share a same sort key even though - * the list is empty. - */ - if (perf_hpp__is_sort_entry(fmt)) { - struct perf_hpp_fmt *pos; + perf_hpp_list__for_each_sort_list(list, fmt) { + struct perf_hpp_fmt *pos; - perf_hpp__for_each_format(pos) { - if (perf_hpp__same_sort_entry(pos, fmt)) - goto next; - } + perf_hpp_list__for_each_format(list, pos) { + if (fmt_equal(fmt, pos)) + goto next; } perf_hpp__column_register(fmt); @@ -550,27 +568,17 @@ void perf_hpp__setup_output_field(void) } } -void perf_hpp__append_sort_keys(void) +void perf_hpp__append_sort_keys(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt; /* append output fields to sort keys */ - perf_hpp__for_each_format(fmt) { - if (!list_empty(&fmt->sort_list)) - continue; - - /* - * sort entry fields are dynamically created, - * so they can share a same sort key even though - * the list is empty. - */ - if (perf_hpp__is_sort_entry(fmt)) { - struct perf_hpp_fmt *pos; + perf_hpp_list__for_each_format(list, fmt) { + struct perf_hpp_fmt *pos; - perf_hpp__for_each_sort_list(pos) { - if (perf_hpp__same_sort_entry(pos, fmt)) - goto next; - } + perf_hpp_list__for_each_sort_list(list, pos) { + if (fmt_equal(fmt, pos)) + goto next; } perf_hpp__register_sort_field(fmt); @@ -579,20 +587,29 @@ void perf_hpp__append_sort_keys(void) } } -void perf_hpp__reset_output_field(void) + +static void fmt_free(struct perf_hpp_fmt *fmt) +{ + if (fmt->free) + fmt->free(fmt); +} + +void perf_hpp__reset_output_field(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt, *tmp; /* reset output fields */ - perf_hpp__for_each_format_safe(fmt, tmp) { + perf_hpp_list__for_each_format_safe(list, fmt, tmp) { list_del_init(&fmt->list); list_del_init(&fmt->sort_list); + fmt_free(fmt); } /* reset sort keys */ - perf_hpp__for_each_sort_list_safe(fmt, tmp) { + perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp) { list_del_init(&fmt->list); list_del_init(&fmt->sort_list); + fmt_free(fmt); } } @@ -606,7 +623,7 @@ unsigned int hists__sort_list_width(struct hists *hists) bool first = true; struct perf_hpp dummy_hpp; - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, hists)) continue; @@ -624,22 +641,39 @@ unsigned int hists__sort_list_width(struct hists *hists) return ret; } -void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) +unsigned int hists__overhead_width(struct hists *hists) { - int idx; - - if (perf_hpp__is_sort_entry(fmt)) - return perf_hpp__reset_sort_width(fmt, hists); + struct perf_hpp_fmt *fmt; + int ret = 0; + bool first = true; + struct perf_hpp dummy_hpp; - for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { - if (fmt == &perf_hpp__format[idx]) + hists__for_each_format(hists, fmt) { + if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt)) break; + + if (first) + first = false; + else + ret += 2; + + ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists)); } - if (idx == PERF_HPP__MAX_INDEX) + return ret; +} + +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) +{ + if (perf_hpp__is_sort_entry(fmt)) + return perf_hpp__reset_sort_width(fmt, hists); + + if (perf_hpp__is_dynamic_entry(fmt)) return; - switch (idx) { + BUG_ON(fmt->idx >= PERF_HPP__MAX_INDEX); + + switch (fmt->idx) { case PERF_HPP__OVERHEAD: case PERF_HPP__OVERHEAD_SYS: case PERF_HPP__OVERHEAD_US: @@ -667,7 +701,7 @@ void perf_hpp__set_user_width(const char *width_list_str) struct perf_hpp_fmt *fmt; const char *ptr = width_list_str; - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { char *p; int len = strtol(ptr, &p, 10); @@ -679,3 +713,71 @@ void perf_hpp__set_user_width(const char *width_list_str) break; } } + +static int add_hierarchy_fmt(struct hists *hists, struct perf_hpp_fmt *fmt) +{ + struct perf_hpp_list_node *node = NULL; + struct perf_hpp_fmt *fmt_copy; + bool found = false; + bool skip = perf_hpp__should_skip(fmt, hists); + + list_for_each_entry(node, &hists->hpp_formats, list) { + if (node->level == fmt->level) { + found = true; + break; + } + } + + if (!found) { + node = malloc(sizeof(*node)); + if (node == NULL) + return -1; + + node->skip = skip; + node->level = fmt->level; + perf_hpp_list__init(&node->hpp); + + hists->nr_hpp_node++; + list_add_tail(&node->list, &hists->hpp_formats); + } + + fmt_copy = perf_hpp_fmt__dup(fmt); + if (fmt_copy == NULL) + return -1; + + if (!skip) + node->skip = false; + + list_add_tail(&fmt_copy->list, &node->hpp.fields); + list_add_tail(&fmt_copy->sort_list, &node->hpp.sorts); + + return 0; +} + +int perf_hpp__setup_hists_formats(struct perf_hpp_list *list, + struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + struct perf_hpp_fmt *fmt; + struct hists *hists; + int ret; + + if (!symbol_conf.report_hierarchy) + return 0; + + evlist__for_each(evlist, evsel) { + hists = evsel__hists(evsel); + + perf_hpp_list__for_each_sort_list(list, fmt) { + if (perf_hpp__is_dynamic_entry(fmt) && + !perf_hpp__defined_dynamic_entry(fmt, hists)) + continue; + + ret = add_hierarchy_fmt(hists, fmt); + if (ret < 0) + return ret; + } + } + + return 0; +} diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 387110d50b002..7aff5acf32657 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -165,8 +165,28 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, return ret; } +/* + * If have one single callchain root, don't bother printing + * its percentage (100 % in fractal mode and the same percentage + * than the hist in graph mode). This also avoid one level of column. + * + * However when percent-limit applied, it's possible that single callchain + * node have different (non-100% in fractal mode) percentage. + */ +static bool need_percent_display(struct rb_node *node, u64 parent_samples) +{ + struct callchain_node *cnode; + + if (rb_next(node)) + return true; + + cnode = rb_entry(node, struct callchain_node, rb_node); + return callchain_cumul_hits(cnode) != parent_samples; +} + static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, - u64 total_samples, int left_margin) + u64 total_samples, u64 parent_samples, + int left_margin) { struct callchain_node *cnode; struct callchain_list *chain; @@ -177,13 +197,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, int ret = 0; char bf[1024]; - /* - * If have one single callchain root, don't bother printing - * its percentage (100 % in fractal mode and the same percentage - * than the hist in graph mode). This also avoid one level of column. - */ node = rb_first(root); - if (node && !rb_next(node)) { + if (node && !need_percent_display(node, parent_samples)) { cnode = rb_entry(node, struct callchain_node, rb_node); list_for_each_entry(chain, &cnode->val, list) { /* @@ -213,9 +228,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, root = &cnode->rb_root; } + if (callchain_param.mode == CHAIN_GRAPH_REL) + total_samples = parent_samples; + ret += __callchain__fprintf_graph(fp, root, total_samples, 1, 1, left_margin); - ret += fprintf(fp, "\n"); + if (ret) { + /* do not add a blank line if it printed nothing */ + ret += fprintf(fp, "\n"); + } return ret; } @@ -323,16 +344,19 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, u64 total_samples, int left_margin, FILE *fp) { + u64 parent_samples = he->stat.period; + + if (symbol_conf.cumulate_callchain) + parent_samples = he->stat_acc->period; + switch (callchain_param.mode) { case CHAIN_GRAPH_REL: - return callchain__fprintf_graph(fp, &he->sorted_chain, - symbol_conf.cumulate_callchain ? - he->stat_acc->period : he->stat.period, - left_margin); + return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples, + parent_samples, left_margin); break; case CHAIN_GRAPH_ABS: return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples, - left_margin); + parent_samples, left_margin); break; case CHAIN_FLAT: return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples); @@ -349,45 +373,66 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, return 0; } -static size_t hist_entry__callchain_fprintf(struct hist_entry *he, - struct hists *hists, - FILE *fp) +static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) { - int left_margin = 0; - u64 total_period = hists->stats.total_period; + const char *sep = symbol_conf.field_sep; + struct perf_hpp_fmt *fmt; + char *start = hpp->buf; + int ret; + bool first = true; - if (field_order == NULL && (sort_order == NULL || - !prefixcmp(sort_order, "comm"))) { - struct perf_hpp_fmt *fmt; + if (symbol_conf.exclude_other && !he->parent) + return 0; - perf_hpp__for_each_format(fmt) { - if (!perf_hpp__is_sort_entry(fmt)) - continue; + hists__for_each_format(he->hists, fmt) { + if (perf_hpp__should_skip(fmt, he->hists)) + continue; - /* must be 'comm' sort entry */ - left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists)); - left_margin -= thread__comm_len(he->thread); - break; - } + /* + * If there's no field_sep, we still need + * to display initial ' '. + */ + if (!sep || !first) { + ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " "); + advance_hpp(hpp, ret); + } else + first = false; + + if (perf_hpp__use_color() && fmt->color) + ret = fmt->color(fmt, hpp, he); + else + ret = fmt->entry(fmt, hpp, he); + + ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret); + advance_hpp(hpp, ret); } - return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); + + return hpp->buf - start; } -static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) +static int hist_entry__hierarchy_fprintf(struct hist_entry *he, + struct perf_hpp *hpp, + struct hists *hists, + FILE *fp) { const char *sep = symbol_conf.field_sep; struct perf_hpp_fmt *fmt; - char *start = hpp->buf; - int ret; + struct perf_hpp_list_node *fmt_node; + char *buf = hpp->buf; + size_t size = hpp->size; + int ret, printed = 0; bool first = true; if (symbol_conf.exclude_other && !he->parent) return 0; - perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt, he->hists)) - continue; + ret = scnprintf(hpp->buf, hpp->size, "%*s", he->depth * HIERARCHY_INDENT, ""); + advance_hpp(hpp, ret); + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { /* * If there's no field_sep, we still need * to display initial ' '. @@ -403,10 +448,47 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) else ret = fmt->entry(fmt, hpp, he); + ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret); advance_hpp(hpp, ret); } - return hpp->buf - start; + if (!sep) + ret = scnprintf(hpp->buf, hpp->size, "%*s", + (hists->nr_hpp_node - 2) * HIERARCHY_INDENT, ""); + advance_hpp(hpp, ret); + + printed += fprintf(fp, "%s", buf); + + perf_hpp_list__for_each_format(he->hpp_list, fmt) { + hpp->buf = buf; + hpp->size = size; + + /* + * No need to call hist_entry__snprintf_alignment() since this + * fmt is always the last column in the hierarchy mode. + */ + if (perf_hpp__use_color() && fmt->color) + fmt->color(fmt, hpp, he); + else + fmt->entry(fmt, hpp, he); + + /* + * dynamic entries are right-aligned but we want left-aligned + * in the hierarchy mode + */ + printed += fprintf(fp, "%s%s", sep ?: " ", ltrim(buf)); + } + printed += putc('\n', fp); + + if (symbol_conf.use_callchain && he->leaf) { + u64 total = hists__total_period(hists); + + printed += hist_entry_callchain__fprintf(he, total, 0, fp); + goto out; + } + +out: + return printed; } static int hist_entry__fprintf(struct hist_entry *he, size_t size, @@ -418,24 +500,134 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, .buf = bf, .size = size, }; + u64 total_period = hists->stats.total_period; if (size == 0 || size > bfsz) size = hpp.size = bfsz; + if (symbol_conf.report_hierarchy) + return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp); + hist_entry__snprintf(he, &hpp); ret = fprintf(fp, "%s\n", bf); if (symbol_conf.use_callchain) - ret += hist_entry__callchain_fprintf(he, hists, fp); + ret += hist_entry_callchain__fprintf(he, total_period, 0, fp); return ret; } +static int print_hierarchy_indent(const char *sep, int indent, + const char *line, FILE *fp) +{ + if (sep != NULL || indent < 2) + return 0; + + return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line); +} + +static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp, + const char *sep, FILE *fp) +{ + bool first_node, first_col; + int indent; + int depth; + unsigned width = 0; + unsigned header_width = 0; + struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; + + indent = hists->nr_hpp_node; + + /* preserve max indent depth for column headers */ + print_hierarchy_indent(sep, indent, spaces, fp); + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&hists->hpp_formats, + struct perf_hpp_list_node, list); + + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + fmt->header(fmt, hpp, hists_to_evsel(hists)); + fprintf(fp, "%s%s", hpp->buf, sep ?: " "); + } + + /* combine sort headers with ' / ' */ + first_node = true; + list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) { + if (!first_node) + header_width += fprintf(fp, " / "); + first_node = false; + + first_col = true; + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + if (perf_hpp__should_skip(fmt, hists)) + continue; + + if (!first_col) + header_width += fprintf(fp, "+"); + first_col = false; + + fmt->header(fmt, hpp, hists_to_evsel(hists)); + rtrim(hpp->buf); + + header_width += fprintf(fp, "%s", ltrim(hpp->buf)); + } + } + + fprintf(fp, "\n# "); + + /* preserve max indent depth for initial dots */ + print_hierarchy_indent(sep, indent, dots, fp); + + /* the first hpp_list_node is for overhead columns */ + fmt_node = list_first_entry(&hists->hpp_formats, + struct perf_hpp_list_node, list); + + first_col = true; + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + if (!first_col) + fprintf(fp, "%s", sep ?: ".."); + first_col = false; + + width = fmt->width(fmt, hpp, hists_to_evsel(hists)); + fprintf(fp, "%.*s", width, dots); + } + + depth = 0; + list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) { + first_col = true; + width = depth * HIERARCHY_INDENT; + + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) { + if (perf_hpp__should_skip(fmt, hists)) + continue; + + if (!first_col) + width++; /* for '+' sign between column header */ + first_col = false; + + width += fmt->width(fmt, hpp, hists_to_evsel(hists)); + } + + if (width > header_width) + header_width = width; + + depth++; + } + + fprintf(fp, "%s%-.*s", sep ?: " ", header_width, dots); + + fprintf(fp, "\n#\n"); + + return 2; +} + size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp) { struct perf_hpp_fmt *fmt; + struct perf_hpp_list_node *fmt_node; struct rb_node *nd; size_t ret = 0; unsigned int width; @@ -449,10 +641,11 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, bool first = true; size_t linesz; char *line = NULL; + unsigned indent; init_rem_hits(); - perf_hpp__for_each_format(fmt) + hists__for_each_format(hists, fmt) perf_hpp__reset_width(fmt, hists); if (symbol_conf.col_width_list_str) @@ -463,7 +656,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, fprintf(fp, "# "); - perf_hpp__for_each_format(fmt) { + if (symbol_conf.report_hierarchy) { + list_for_each_entry(fmt_node, &hists->hpp_formats, list) { + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) + perf_hpp__reset_width(fmt, hists); + } + nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp); + goto print_entries; + } + + hists__for_each_format(hists, fmt) { if (perf_hpp__should_skip(fmt, hists)) continue; @@ -487,7 +689,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, fprintf(fp, "# "); - perf_hpp__for_each_format(fmt) { + hists__for_each_format(hists, fmt) { unsigned int i; if (perf_hpp__should_skip(fmt, hists)) @@ -520,7 +722,9 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, goto out; } - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + indent = hists__overhead_width(hists) + 4; + + for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); float percent; @@ -536,6 +740,20 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, if (max_rows && ++nr_rows >= max_rows) break; + /* + * If all children are filtered out or percent-limited, + * display "no entry >= x.xx%" message. + */ + if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) { + int depth = hists->nr_hpp_node + h->depth + 1; + + print_hierarchy_indent(sep, depth, spaces, fp); + fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt); + + if (max_rows && ++nr_rows >= max_rows) + break; + } + if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(h->thread->mg, MAP__FUNCTION, fp); diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 5eec53a3f4ac7..eea25e2424e99 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -82,6 +82,7 @@ libperf-y += parse-branch-options.o libperf-y += parse-regs-options.o libperf-y += term.o libperf-y += help-unknown-cmd.o +libperf-y += mem-events.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -105,8 +106,17 @@ libperf-y += scripting-engines/ libperf-$(CONFIG_ZLIB) += zlib.o libperf-$(CONFIG_LZMA) += lzma.o +libperf-y += demangle-java.o + +ifdef CONFIG_JITDUMP +libperf-$(CONFIG_LIBELF) += jitdump.o +libperf-$(CONFIG_LIBELF) += genelf.o +libperf-$(CONFIG_LIBELF) += genelf_debug.o +endif CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +# avoid compiler warnings in 32-bit mode +CFLAGS_genelf_debug.o += -Wno-packed $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c $(call rule_mkdir) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 360fda01f3b0d..ec164fe70718d 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -478,10 +478,11 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap) heap_array[last].ordinal); } -size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr) +size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, + struct perf_evlist *evlist) { if (itr) - return itr->info_priv_size(itr); + return itr->info_priv_size(itr, evlist); return 0; } @@ -852,7 +853,7 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, int err; pr_debug2("Synthesizing auxtrace information\n"); - priv_size = auxtrace_record__info_priv_size(itr); + priv_size = auxtrace_record__info_priv_size(itr, session->evlist); ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size); if (!ev) return -ENOMEM; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index b86f90db1352a..e5a8e2d4f2af4 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -293,7 +293,8 @@ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, struct perf_evlist *evlist, struct record_opts *opts); - size_t (*info_priv_size)(struct auxtrace_record *itr); + size_t (*info_priv_size)(struct auxtrace_record *itr, + struct perf_evlist *evlist); int (*info_fill)(struct auxtrace_record *itr, struct perf_session *session, struct auxtrace_info_event *auxtrace_info, @@ -429,7 +430,8 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, int auxtrace_record__options(struct auxtrace_record *itr, struct perf_evlist *evlist, struct record_opts *opts); -size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr); +size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr, + struct perf_evlist *evlist); int auxtrace_record__info_fill(struct auxtrace_record *itr, struct perf_session *session, struct auxtrace_info_event *auxtrace_info, diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 540a7efa657ea..0967ce6019316 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include "perf.h" @@ -16,6 +17,7 @@ #include "llvm-utils.h" #include "probe-event.h" #include "probe-finder.h" // for MAX_PROBES +#include "parse-events.h" #include "llvm-utils.h" #define DEFINE_PRINT_FN(name, level) \ @@ -108,8 +110,8 @@ void bpf__clear(void) } static void -bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused, - void *_priv) +clear_prog_priv(struct bpf_program *prog __maybe_unused, + void *_priv) { struct bpf_prog_priv *priv = _priv; @@ -337,7 +339,7 @@ config_bpf_program(struct bpf_program *prog) } pr_debug("bpf: config '%s' is ok\n", config_str); - err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear); + err = bpf_program__set_private(prog, priv, clear_prog_priv); if (err) { pr_debug("Failed to set priv for program '%s'\n", config_str); goto errout; @@ -739,6 +741,682 @@ int bpf__foreach_tev(struct bpf_object *obj, return 0; } +enum bpf_map_op_type { + BPF_MAP_OP_SET_VALUE, + BPF_MAP_OP_SET_EVSEL, +}; + +enum bpf_map_key_type { + BPF_MAP_KEY_ALL, + BPF_MAP_KEY_RANGES, +}; + +struct bpf_map_op { + struct list_head list; + enum bpf_map_op_type op_type; + enum bpf_map_key_type key_type; + union { + struct parse_events_array array; + } k; + union { + u64 value; + struct perf_evsel *evsel; + } v; +}; + +struct bpf_map_priv { + struct list_head ops_list; +}; + +static void +bpf_map_op__delete(struct bpf_map_op *op) +{ + if (!list_empty(&op->list)) + list_del(&op->list); + if (op->key_type == BPF_MAP_KEY_RANGES) + parse_events__clear_array(&op->k.array); + free(op); +} + +static void +bpf_map_priv__purge(struct bpf_map_priv *priv) +{ + struct bpf_map_op *pos, *n; + + list_for_each_entry_safe(pos, n, &priv->ops_list, list) { + list_del_init(&pos->list); + bpf_map_op__delete(pos); + } +} + +static void +bpf_map_priv__clear(struct bpf_map *map __maybe_unused, + void *_priv) +{ + struct bpf_map_priv *priv = _priv; + + bpf_map_priv__purge(priv); + free(priv); +} + +static int +bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term) +{ + op->key_type = BPF_MAP_KEY_ALL; + if (!term) + return 0; + + if (term->array.nr_ranges) { + size_t memsz = term->array.nr_ranges * + sizeof(op->k.array.ranges[0]); + + op->k.array.ranges = memdup(term->array.ranges, memsz); + if (!op->k.array.ranges) { + pr_debug("No enough memory to alloc indices for map\n"); + return -ENOMEM; + } + op->key_type = BPF_MAP_KEY_RANGES; + op->k.array.nr_ranges = term->array.nr_ranges; + } + return 0; +} + +static struct bpf_map_op * +bpf_map_op__new(struct parse_events_term *term) +{ + struct bpf_map_op *op; + int err; + + op = zalloc(sizeof(*op)); + if (!op) { + pr_debug("Failed to alloc bpf_map_op\n"); + return ERR_PTR(-ENOMEM); + } + INIT_LIST_HEAD(&op->list); + + err = bpf_map_op_setkey(op, term); + if (err) { + free(op); + return ERR_PTR(err); + } + return op; +} + +static int +bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op) +{ + struct bpf_map_priv *priv; + const char *map_name; + int err; + + map_name = bpf_map__get_name(map); + err = bpf_map__get_private(map, (void **)&priv); + if (err) { + pr_debug("Failed to get private from map %s\n", map_name); + return err; + } + + if (!priv) { + priv = zalloc(sizeof(*priv)); + if (!priv) { + pr_debug("No enough memory to alloc map private\n"); + return -ENOMEM; + } + INIT_LIST_HEAD(&priv->ops_list); + + if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) { + free(priv); + return -BPF_LOADER_ERRNO__INTERNAL; + } + } + + list_add_tail(&op->list, &priv->ops_list); + return 0; +} + +static struct bpf_map_op * +bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term) +{ + struct bpf_map_op *op; + int err; + + op = bpf_map_op__new(term); + if (IS_ERR(op)) + return op; + + err = bpf_map__add_op(map, op); + if (err) { + bpf_map_op__delete(op); + return ERR_PTR(err); + } + return op; +} + +static int +__bpf_map__config_value(struct bpf_map *map, + struct parse_events_term *term) +{ + struct bpf_map_def def; + struct bpf_map_op *op; + const char *map_name; + int err; + + map_name = bpf_map__get_name(map); + + err = bpf_map__get_def(map, &def); + if (err) { + pr_debug("Unable to get map definition from '%s'\n", + map_name); + return -BPF_LOADER_ERRNO__INTERNAL; + } + + if (def.type != BPF_MAP_TYPE_ARRAY) { + pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n", + map_name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; + } + if (def.key_size < sizeof(unsigned int)) { + pr_debug("Map %s has incorrect key size\n", map_name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE; + } + switch (def.value_size) { + case 1: + case 2: + case 4: + case 8: + break; + default: + pr_debug("Map %s has incorrect value size\n", map_name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE; + } + + op = bpf_map__add_newop(map, term); + if (IS_ERR(op)) + return PTR_ERR(op); + op->op_type = BPF_MAP_OP_SET_VALUE; + op->v.value = term->val.num; + return 0; +} + +static int +bpf_map__config_value(struct bpf_map *map, + struct parse_events_term *term, + struct perf_evlist *evlist __maybe_unused) +{ + if (!term->err_val) { + pr_debug("Config value not set\n"); + return -BPF_LOADER_ERRNO__OBJCONF_CONF; + } + + if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) { + pr_debug("ERROR: wrong value type for 'value'\n"); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE; + } + + return __bpf_map__config_value(map, term); +} + +static int +__bpf_map__config_event(struct bpf_map *map, + struct parse_events_term *term, + struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + struct bpf_map_def def; + struct bpf_map_op *op; + const char *map_name; + int err; + + map_name = bpf_map__get_name(map); + evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str); + if (!evsel) { + pr_debug("Event (for '%s') '%s' doesn't exist\n", + map_name, term->val.str); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT; + } + + err = bpf_map__get_def(map, &def); + if (err) { + pr_debug("Unable to get map definition from '%s'\n", + map_name); + return err; + } + + /* + * No need to check key_size and value_size: + * kernel has already checked them. + */ + if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map_name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; + } + + op = bpf_map__add_newop(map, term); + if (IS_ERR(op)) + return PTR_ERR(op); + op->op_type = BPF_MAP_OP_SET_EVSEL; + op->v.evsel = evsel; + return 0; +} + +static int +bpf_map__config_event(struct bpf_map *map, + struct parse_events_term *term, + struct perf_evlist *evlist) +{ + if (!term->err_val) { + pr_debug("Config value not set\n"); + return -BPF_LOADER_ERRNO__OBJCONF_CONF; + } + + if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) { + pr_debug("ERROR: wrong value type for 'event'\n"); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE; + } + + return __bpf_map__config_event(map, term, evlist); +} + +struct bpf_obj_config__map_func { + const char *config_opt; + int (*config_func)(struct bpf_map *, struct parse_events_term *, + struct perf_evlist *); +}; + +struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = { + {"value", bpf_map__config_value}, + {"event", bpf_map__config_event}, +}; + +static int +config_map_indices_range_check(struct parse_events_term *term, + struct bpf_map *map, + const char *map_name) +{ + struct parse_events_array *array = &term->array; + struct bpf_map_def def; + unsigned int i; + int err; + + if (!array->nr_ranges) + return 0; + if (!array->ranges) { + pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n", + map_name, (int)array->nr_ranges); + return -BPF_LOADER_ERRNO__INTERNAL; + } + + err = bpf_map__get_def(map, &def); + if (err) { + pr_debug("ERROR: Unable to get map definition from '%s'\n", + map_name); + return -BPF_LOADER_ERRNO__INTERNAL; + } + + for (i = 0; i < array->nr_ranges; i++) { + unsigned int start = array->ranges[i].start; + size_t length = array->ranges[i].length; + unsigned int idx = start + length - 1; + + if (idx >= def.max_entries) { + pr_debug("ERROR: index %d too large\n", idx); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG; + } + } + return 0; +} + +static int +bpf__obj_config_map(struct bpf_object *obj, + struct parse_events_term *term, + struct perf_evlist *evlist, + int *key_scan_pos) +{ + /* key is "map:." */ + char *map_name = strdup(term->config + sizeof("map:") - 1); + struct bpf_map *map; + int err = -BPF_LOADER_ERRNO__OBJCONF_OPT; + char *map_opt; + size_t i; + + if (!map_name) + return -ENOMEM; + + map_opt = strchr(map_name, '.'); + if (!map_opt) { + pr_debug("ERROR: Invalid map config: %s\n", map_name); + goto out; + } + + *map_opt++ = '\0'; + if (*map_opt == '\0') { + pr_debug("ERROR: Invalid map option: %s\n", term->config); + goto out; + } + + map = bpf_object__get_map_by_name(obj, map_name); + if (!map) { + pr_debug("ERROR: Map %s doesn't exist\n", map_name); + err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST; + goto out; + } + + *key_scan_pos += strlen(map_opt); + err = config_map_indices_range_check(term, map, map_name); + if (err) + goto out; + *key_scan_pos -= strlen(map_opt); + + for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) { + struct bpf_obj_config__map_func *func = + &bpf_obj_config__map_funcs[i]; + + if (strcmp(map_opt, func->config_opt) == 0) { + err = func->config_func(map, term, evlist); + goto out; + } + } + + pr_debug("ERROR: Invalid map config option '%s'\n", map_opt); + err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT; +out: + free(map_name); + if (!err) + key_scan_pos += strlen(map_opt); + return err; +} + +int bpf__config_obj(struct bpf_object *obj, + struct parse_events_term *term, + struct perf_evlist *evlist, + int *error_pos) +{ + int key_scan_pos = 0; + int err; + + if (!obj || !term || !term->config) + return -EINVAL; + + if (!prefixcmp(term->config, "map:")) { + key_scan_pos = sizeof("map:") - 1; + err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos); + goto out; + } + err = -BPF_LOADER_ERRNO__OBJCONF_OPT; +out: + if (error_pos) + *error_pos = key_scan_pos; + return err; + +} + +typedef int (*map_config_func_t)(const char *name, int map_fd, + struct bpf_map_def *pdef, + struct bpf_map_op *op, + void *pkey, void *arg); + +static int +foreach_key_array_all(map_config_func_t func, + void *arg, const char *name, + int map_fd, struct bpf_map_def *pdef, + struct bpf_map_op *op) +{ + unsigned int i; + int err; + + for (i = 0; i < pdef->max_entries; i++) { + err = func(name, map_fd, pdef, op, &i, arg); + if (err) { + pr_debug("ERROR: failed to insert value to %s[%u]\n", + name, i); + return err; + } + } + return 0; +} + +static int +foreach_key_array_ranges(map_config_func_t func, void *arg, + const char *name, int map_fd, + struct bpf_map_def *pdef, + struct bpf_map_op *op) +{ + unsigned int i, j; + int err; + + for (i = 0; i < op->k.array.nr_ranges; i++) { + unsigned int start = op->k.array.ranges[i].start; + size_t length = op->k.array.ranges[i].length; + + for (j = 0; j < length; j++) { + unsigned int idx = start + j; + + err = func(name, map_fd, pdef, op, &idx, arg); + if (err) { + pr_debug("ERROR: failed to insert value to %s[%u]\n", + name, idx); + return err; + } + } + } + return 0; +} + +static int +bpf_map_config_foreach_key(struct bpf_map *map, + map_config_func_t func, + void *arg) +{ + int err, map_fd; + const char *name; + struct bpf_map_op *op; + struct bpf_map_def def; + struct bpf_map_priv *priv; + + name = bpf_map__get_name(map); + + err = bpf_map__get_private(map, (void **)&priv); + if (err) { + pr_debug("ERROR: failed to get private from map %s\n", name); + return -BPF_LOADER_ERRNO__INTERNAL; + } + if (!priv || list_empty(&priv->ops_list)) { + pr_debug("INFO: nothing to config for map %s\n", name); + return 0; + } + + err = bpf_map__get_def(map, &def); + if (err) { + pr_debug("ERROR: failed to get definition from map %s\n", name); + return -BPF_LOADER_ERRNO__INTERNAL; + } + map_fd = bpf_map__get_fd(map); + if (map_fd < 0) { + pr_debug("ERROR: failed to get fd from map %s\n", name); + return map_fd; + } + + list_for_each_entry(op, &priv->ops_list, list) { + switch (def.type) { + case BPF_MAP_TYPE_ARRAY: + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + switch (op->key_type) { + case BPF_MAP_KEY_ALL: + err = foreach_key_array_all(func, arg, name, + map_fd, &def, op); + break; + case BPF_MAP_KEY_RANGES: + err = foreach_key_array_ranges(func, arg, name, + map_fd, &def, + op); + break; + default: + pr_debug("ERROR: keytype for map '%s' invalid\n", + name); + return -BPF_LOADER_ERRNO__INTERNAL; + } + if (err) + return err; + break; + default: + pr_debug("ERROR: type of '%s' incorrect\n", name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; + } + } + + return 0; +} + +static int +apply_config_value_for_key(int map_fd, void *pkey, + size_t val_size, u64 val) +{ + int err = 0; + + switch (val_size) { + case 1: { + u8 _val = (u8)(val); + err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY); + break; + } + case 2: { + u16 _val = (u16)(val); + err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY); + break; + } + case 4: { + u32 _val = (u32)(val); + err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY); + break; + } + case 8: { + err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY); + break; + } + default: + pr_debug("ERROR: invalid value size\n"); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE; + } + if (err && errno) + err = -errno; + return err; +} + +static int +apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, + struct perf_evsel *evsel) +{ + struct xyarray *xy = evsel->fd; + struct perf_event_attr *attr; + unsigned int key, events; + bool check_pass = false; + int *evt_fd; + int err; + + if (!xy) { + pr_debug("ERROR: evsel not ready for map %s\n", name); + return -BPF_LOADER_ERRNO__INTERNAL; + } + + if (xy->row_size / xy->entry_size != 1) { + pr_debug("ERROR: Dimension of target event is incorrect for map %s\n", + name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM; + } + + attr = &evsel->attr; + if (attr->inherit) { + pr_debug("ERROR: Can't put inherit event into map %s\n", name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH; + } + + if (perf_evsel__is_bpf_output(evsel)) + check_pass = true; + if (attr->type == PERF_TYPE_RAW) + check_pass = true; + if (attr->type == PERF_TYPE_HARDWARE) + check_pass = true; + if (!check_pass) { + pr_debug("ERROR: Event type is wrong for map %s\n", name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE; + } + + events = xy->entries / (xy->row_size / xy->entry_size); + key = *((unsigned int *)pkey); + if (key >= events) { + pr_debug("ERROR: there is no event %d for map %s\n", + key, name); + return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE; + } + evt_fd = xyarray__entry(xy, key, 0); + err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY); + if (err && errno) + err = -errno; + return err; +} + +static int +apply_obj_config_map_for_key(const char *name, int map_fd, + struct bpf_map_def *pdef __maybe_unused, + struct bpf_map_op *op, + void *pkey, void *arg __maybe_unused) +{ + int err; + + switch (op->op_type) { + case BPF_MAP_OP_SET_VALUE: + err = apply_config_value_for_key(map_fd, pkey, + pdef->value_size, + op->v.value); + break; + case BPF_MAP_OP_SET_EVSEL: + err = apply_config_evsel_for_key(name, map_fd, pkey, + op->v.evsel); + break; + default: + pr_debug("ERROR: unknown value type for '%s'\n", name); + err = -BPF_LOADER_ERRNO__INTERNAL; + } + return err; +} + +static int +apply_obj_config_map(struct bpf_map *map) +{ + return bpf_map_config_foreach_key(map, + apply_obj_config_map_for_key, + NULL); +} + +static int +apply_obj_config_object(struct bpf_object *obj) +{ + struct bpf_map *map; + int err; + + bpf_map__for_each(map, obj) { + err = apply_obj_config_map(map); + if (err) + return err; + } + return 0; +} + +int bpf__apply_obj_config(void) +{ + struct bpf_object *obj, *tmp; + int err; + + bpf_object__for_each_safe(obj, tmp) { + err = apply_obj_config_object(obj); + if (err) + return err; + } + + return 0; +} + #define ERRNO_OFFSET(e) ((e) - __BPF_LOADER_ERRNO__START) #define ERRCODE_OFFSET(c) ERRNO_OFFSET(BPF_LOADER_ERRNO__##c) #define NR_ERRNO (__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START) @@ -753,6 +1431,20 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = { [ERRCODE_OFFSET(PROLOGUE)] = "Failed to generate prologue", [ERRCODE_OFFSET(PROLOGUE2BIG)] = "Prologue too big for program", [ERRCODE_OFFSET(PROLOGUEOOB)] = "Offset out of bound for prologue", + [ERRCODE_OFFSET(OBJCONF_OPT)] = "Invalid object config option", + [ERRCODE_OFFSET(OBJCONF_CONF)] = "Config value not set (missing '=')", + [ERRCODE_OFFSET(OBJCONF_MAP_OPT)] = "Invalid object map config option", + [ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)] = "Target map doesn't exist", + [ERRCODE_OFFSET(OBJCONF_MAP_VALUE)] = "Incorrect value type for map", + [ERRCODE_OFFSET(OBJCONF_MAP_TYPE)] = "Incorrect map type", + [ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)] = "Incorrect map key size", + [ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)] = "Incorrect map value size", + [ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)] = "Event not found for map setting", + [ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)] = "Invalid map size for event setting", + [ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)] = "Event dimension too large", + [ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)] = "Doesn't support inherit event", + [ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)] = "Wrong event type for map", + [ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)] = "Index too large", }; static int @@ -872,3 +1564,29 @@ int bpf__strerror_load(struct bpf_object *obj, bpf__strerror_end(buf, size); return 0; } + +int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, + struct parse_events_term *term __maybe_unused, + struct perf_evlist *evlist __maybe_unused, + int *error_pos __maybe_unused, int err, + char *buf, size_t size) +{ + bpf__strerror_head(err, buf, size); + bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE, + "Can't use this config term with this map type"); + bpf__strerror_end(buf, size); + return 0; +} + +int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) +{ + bpf__strerror_head(err, buf, size); + bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM, + "Cannot set event to BPF map in multi-thread tracing"); + bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH, + "%s (Hint: use -i to turn off inherit)", emsg); + bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE, + "Can only put raw, hardware and BPF output event into a BPF map"); + bpf__strerror_end(buf, size); + return 0; +} diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 6fdc0457e2b66..be4311944e3da 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -10,6 +10,7 @@ #include #include #include "probe-event.h" +#include "evlist.h" #include "debug.h" enum bpf_loader_errno { @@ -24,10 +25,25 @@ enum bpf_loader_errno { BPF_LOADER_ERRNO__PROLOGUE, /* Failed to generate prologue */ BPF_LOADER_ERRNO__PROLOGUE2BIG, /* Prologue too big for program */ BPF_LOADER_ERRNO__PROLOGUEOOB, /* Offset out of bound for prologue */ + BPF_LOADER_ERRNO__OBJCONF_OPT, /* Invalid object config option */ + BPF_LOADER_ERRNO__OBJCONF_CONF, /* Config value not set (lost '=')) */ + BPF_LOADER_ERRNO__OBJCONF_MAP_OPT, /* Invalid object map config option */ + BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST, /* Target map not exist */ + BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE, /* Incorrect value type for map */ + BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE, /* Incorrect map type */ + BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE, /* Incorrect map key size */ + BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */ + BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT, /* Event not found for map setting */ + BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE, /* Invalid map size for event setting */ + BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM, /* Event dimension too large */ + BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH, /* Doesn't support inherit event */ + BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE, /* Wrong event type for map */ + BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG, /* Index too large */ __BPF_LOADER_ERRNO__END, }; struct bpf_object; +struct parse_events_term; #define PERF_BPF_PROBE_GROUP "perf_bpf_probe" typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev, @@ -53,6 +69,16 @@ int bpf__strerror_load(struct bpf_object *obj, int err, char *buf, size_t size); int bpf__foreach_tev(struct bpf_object *obj, bpf_prog_iter_callback_t func, void *arg); + +int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term, + struct perf_evlist *evlist, int *error_pos); +int bpf__strerror_config_obj(struct bpf_object *obj, + struct parse_events_term *term, + struct perf_evlist *evlist, + int *error_pos, int err, char *buf, + size_t size); +int bpf__apply_obj_config(void); +int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); #else static inline struct bpf_object * bpf__prepare_load(const char *filename __maybe_unused, @@ -83,6 +109,21 @@ bpf__foreach_tev(struct bpf_object *obj __maybe_unused, return 0; } +static inline int +bpf__config_obj(struct bpf_object *obj __maybe_unused, + struct parse_events_term *term __maybe_unused, + struct perf_evlist *evlist __maybe_unused, + int *error_pos __maybe_unused) +{ + return 0; +} + +static inline int +bpf__apply_obj_config(void) +{ + return 0; +} + static inline int __bpf_strerror(char *buf, size_t size) { @@ -118,5 +159,23 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused, { return __bpf_strerror(buf, size); } + +static inline int +bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused, + struct parse_events_term *term __maybe_unused, + struct perf_evlist *evlist __maybe_unused, + int *error_pos __maybe_unused, + int err __maybe_unused, + char *buf, size_t size) +{ + return __bpf_strerror(buf, size); +} + +static inline int +bpf__strerror_apply_obj_config(int err __maybe_unused, + char *buf, size_t size) +{ + return __bpf_strerror(buf, size); +} #endif #endif diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 6a7e273a514a6..f1479eeef7daf 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -166,6 +166,50 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) return build_id__filename(build_id_hex, bf, size); } +bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size) +{ + char *id_name, *ch; + struct stat sb; + + id_name = dso__build_id_filename(dso, bf, size); + if (!id_name) + goto err; + if (access(id_name, F_OK)) + goto err; + if (lstat(id_name, &sb) == -1) + goto err; + if ((size_t)sb.st_size > size - 1) + goto err; + if (readlink(id_name, bf, size - 1) < 0) + goto err; + + bf[sb.st_size] = '\0'; + + /* + * link should be: + * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92 + */ + ch = strrchr(bf, '/'); + if (!ch) + goto err; + if (ch - 3 < bf) + goto err; + + return strncmp(".ko", ch - 3, 3) == 0; +err: + /* + * If dso__build_id_filename work, get id_name again, + * because id_name points to bf and is broken. + */ + if (id_name) + id_name = dso__build_id_filename(dso, bf, size); + pr_err("Invalid build id: %s\n", id_name ? : + dso->long_name ? : + dso->short_name ? : + "[unknown]"); + return false; +} + #define dsos__for_each_with_build_id(pos, head) \ list_for_each_entry(pos, head, node) \ if (!pos->has_build_id) \ @@ -211,6 +255,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd) dsos__for_each_with_build_id(pos, &machine->dsos.head) { const char *name; size_t name_len; + bool in_kernel = false; if (!pos->hit) continue; @@ -227,8 +272,11 @@ static int machine__write_buildid_table(struct machine *machine, int fd) name_len = pos->long_name_len + 1; } + in_kernel = pos->kernel || + is_kernel_module(name, + PERF_RECORD_MISC_CPUMODE_UNKNOWN); err = write_buildid(name, name_len, pos->build_id, machine->pid, - pos->kernel ? kmisc : umisc, fd); + in_kernel ? kmisc : umisc, fd); if (err) break; } diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 27a14a8a945be..64af3e20610d7 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -16,6 +16,7 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id); int filename__sprintf_build_id(const char *pathname, char *sbuild_id); char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size); +bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 07b5d63947b11..3ca453f0c51f6 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -23,6 +23,8 @@ #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR" #define PERF_PAGER_ENVIRONMENT "PERF_PAGER" +extern const char *config_exclusive_filename; + typedef int (*config_fn_t)(const char *, const char *, void *); extern int perf_default_config(const char *, const char *, void *); extern int perf_config(config_fn_t fn, void *); @@ -31,6 +33,7 @@ extern u64 perf_config_u64(const char *, const char *); extern int perf_config_bool(const char *, const char *); extern int config_error_nonbool(const char *); extern const char *perf_config_dirname(const char *, const char *); +extern const char *perf_etc_perfconfig(void); char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 53c43eb9489e4..24b4bd0d77545 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -416,7 +416,7 @@ create_child(struct callchain_node *parent, bool inherit_children) /* * Fill the node with callchain values */ -static void +static int fill_node(struct callchain_node *node, struct callchain_cursor *cursor) { struct callchain_cursor_node *cursor_node; @@ -433,7 +433,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) call = zalloc(sizeof(*call)); if (!call) { perror("not enough memory for the code path tree"); - return; + return -1; } call->ip = cursor_node->ip; call->ms.sym = cursor_node->sym; @@ -443,6 +443,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) callchain_cursor_advance(cursor); cursor_node = callchain_cursor_current(cursor); } + return 0; } static struct callchain_node * @@ -453,7 +454,19 @@ add_child(struct callchain_node *parent, struct callchain_node *new; new = create_child(parent, false); - fill_node(new, cursor); + if (new == NULL) + return NULL; + + if (fill_node(new, cursor) < 0) { + struct callchain_list *call, *tmp; + + list_for_each_entry_safe(call, tmp, &new->val, list) { + list_del(&call->list); + free(call); + } + free(new); + return NULL; + } new->children_hit = 0; new->hit = period; @@ -462,16 +475,32 @@ add_child(struct callchain_node *parent, return new; } -static s64 match_chain(struct callchain_cursor_node *node, - struct callchain_list *cnode) +enum match_result { + MATCH_ERROR = -1, + MATCH_EQ, + MATCH_LT, + MATCH_GT, +}; + +static enum match_result match_chain(struct callchain_cursor_node *node, + struct callchain_list *cnode) { struct symbol *sym = node->sym; + u64 left, right; if (cnode->ms.sym && sym && - callchain_param.key == CCKEY_FUNCTION) - return cnode->ms.sym->start - sym->start; - else - return cnode->ip - node->ip; + callchain_param.key == CCKEY_FUNCTION) { + left = cnode->ms.sym->start; + right = sym->start; + } else { + left = cnode->ip; + right = node->ip; + } + + if (left == right) + return MATCH_EQ; + + return left > right ? MATCH_GT : MATCH_LT; } /* @@ -479,7 +508,7 @@ static s64 match_chain(struct callchain_cursor_node *node, * give a part of its callchain to the created child. * Then create another child to host the given callchain of new branch */ -static void +static int split_add_child(struct callchain_node *parent, struct callchain_cursor *cursor, struct callchain_list *to_split, @@ -491,6 +520,8 @@ split_add_child(struct callchain_node *parent, /* split */ new = create_child(parent, true); + if (new == NULL) + return -1; /* split the callchain and move a part to the new child */ old_tail = parent->val.prev; @@ -524,6 +555,8 @@ split_add_child(struct callchain_node *parent, node = callchain_cursor_current(cursor); new = add_child(parent, cursor, period); + if (new == NULL) + return -1; /* * This is second child since we moved parent's children @@ -534,7 +567,7 @@ split_add_child(struct callchain_node *parent, cnode = list_first_entry(&first->val, struct callchain_list, list); - if (match_chain(node, cnode) < 0) + if (match_chain(node, cnode) == MATCH_LT) pp = &p->rb_left; else pp = &p->rb_right; @@ -545,14 +578,15 @@ split_add_child(struct callchain_node *parent, parent->hit = period; parent->count = 1; } + return 0; } -static int +static enum match_result append_chain(struct callchain_node *root, struct callchain_cursor *cursor, u64 period); -static void +static int append_chain_children(struct callchain_node *root, struct callchain_cursor *cursor, u64 period) @@ -564,36 +598,42 @@ append_chain_children(struct callchain_node *root, node = callchain_cursor_current(cursor); if (!node) - return; + return -1; /* lookup in childrens */ while (*p) { - s64 ret; + enum match_result ret; parent = *p; rnode = rb_entry(parent, struct callchain_node, rb_node_in); /* If at least first entry matches, rely to children */ ret = append_chain(rnode, cursor, period); - if (ret == 0) + if (ret == MATCH_EQ) goto inc_children_hit; + if (ret == MATCH_ERROR) + return -1; - if (ret < 0) + if (ret == MATCH_LT) p = &parent->rb_left; else p = &parent->rb_right; } /* nothing in children, add to the current node */ rnode = add_child(root, cursor, period); + if (rnode == NULL) + return -1; + rb_link_node(&rnode->rb_node_in, parent, p); rb_insert_color(&rnode->rb_node_in, &root->rb_root_in); inc_children_hit: root->children_hit += period; root->children_count++; + return 0; } -static int +static enum match_result append_chain(struct callchain_node *root, struct callchain_cursor *cursor, u64 period) @@ -602,7 +642,7 @@ append_chain(struct callchain_node *root, u64 start = cursor->pos; bool found = false; u64 matches; - int cmp = 0; + enum match_result cmp = MATCH_ERROR; /* * Lookup in the current node @@ -618,7 +658,7 @@ append_chain(struct callchain_node *root, break; cmp = match_chain(node, cnode); - if (cmp) + if (cmp != MATCH_EQ) break; found = true; @@ -628,7 +668,7 @@ append_chain(struct callchain_node *root, /* matches not, relay no the parent */ if (!found) { - WARN_ONCE(!cmp, "Chain comparison error\n"); + WARN_ONCE(cmp == MATCH_ERROR, "Chain comparison error\n"); return cmp; } @@ -636,21 +676,25 @@ append_chain(struct callchain_node *root, /* we match only a part of the node. Split it and add the new chain */ if (matches < root->val_nr) { - split_add_child(root, cursor, cnode, start, matches, period); - return 0; + if (split_add_child(root, cursor, cnode, start, matches, + period) < 0) + return MATCH_ERROR; + + return MATCH_EQ; } /* we match 100% of the path, increment the hit */ if (matches == root->val_nr && cursor->pos == cursor->nr) { root->hit += period; root->count++; - return 0; + return MATCH_EQ; } /* We match the node and still have a part remaining */ - append_chain_children(root, cursor, period); + if (append_chain_children(root, cursor, period) < 0) + return MATCH_ERROR; - return 0; + return MATCH_EQ; } int callchain_append(struct callchain_root *root, @@ -662,7 +706,8 @@ int callchain_append(struct callchain_root *root, callchain_cursor_commit(cursor); - append_chain_children(&root->node, cursor, period); + if (append_chain_children(&root->node, cursor, period) < 0) + return -1; if (cursor->nr > root->max_depth) root->max_depth = cursor->nr; @@ -690,7 +735,8 @@ merge_chain_branch(struct callchain_cursor *cursor, if (src->hit) { callchain_cursor_commit(cursor); - append_chain_children(dst, cursor, src->hit); + if (append_chain_children(dst, cursor, src->hit) < 0) + return -1; } n = rb_first(&src->rb_root_in); diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index e5fb88bab9e1c..43e84aa27e4a6 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -32,14 +32,15 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) return 0; } -int perf_color_default_config(const char *var, const char *value, void *cb) +int perf_color_default_config(const char *var, const char *value, + void *cb __maybe_unused) { if (!strcmp(var, "color.ui")) { perf_use_color_default = perf_config_colorbool(var, value, -1); return 0; } - return perf_default_config(var, value, cb); + return 0; } static int __color_vsnprintf(char *bf, size_t size, const char *color, diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index d3e12e30e1d52..4e727635476ea 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -26,7 +26,7 @@ static const char *config_file_name; static int config_linenr; static int config_file_eof; -static const char *config_exclusive_filename; +const char *config_exclusive_filename; static int get_next_char(void) { @@ -434,7 +434,7 @@ static int perf_config_from_file(config_fn_t fn, const char *filename, void *dat return ret; } -static const char *perf_etc_perfconfig(void) +const char *perf_etc_perfconfig(void) { static const char *system_wide; if (!system_wide) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index fa935093a5994..9bcf2bed3a6d1 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -8,6 +8,10 @@ #include #include "asm/bug.h" +static int max_cpu_num; +static int max_node_num; +static int *cpunode_map; + static struct cpu_map *cpu_map__default_new(void) { struct cpu_map *cpus; @@ -486,6 +490,32 @@ static void set_max_node_num(void) pr_err("Failed to read max nodes, using default of %d\n", max_node_num); } +int cpu__max_node(void) +{ + if (unlikely(!max_node_num)) + set_max_node_num(); + + return max_node_num; +} + +int cpu__max_cpu(void) +{ + if (unlikely(!max_cpu_num)) + set_max_cpu_num(); + + return max_cpu_num; +} + +int cpu__get_node(int cpu) +{ + if (unlikely(cpunode_map == NULL)) { + pr_debug("cpu_map not initialized\n"); + return -1; + } + + return cpunode_map[cpu]; +} + static int init_cpunode_map(void) { int i; diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 71c41b9efabb3..81a2562aaa2b0 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -57,37 +57,11 @@ static inline bool cpu_map__empty(const struct cpu_map *map) return map ? map->map[0] == -1 : true; } -int max_cpu_num; -int max_node_num; -int *cpunode_map; - int cpu__setup_cpunode_map(void); -static inline int cpu__max_node(void) -{ - if (unlikely(!max_node_num)) - pr_debug("cpu_map not initialized\n"); - - return max_node_num; -} - -static inline int cpu__max_cpu(void) -{ - if (unlikely(!max_cpu_num)) - pr_debug("cpu_map not initialized\n"); - - return max_cpu_num; -} - -static inline int cpu__get_node(int cpu) -{ - if (unlikely(cpunode_map == NULL)) { - pr_debug("cpu_map not initialized\n"); - return -1; - } - - return cpunode_map[cpu]; -} +int cpu__max_node(void); +int cpu__max_cpu(void); +int cpu__get_node(int cpu); int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, int (*f)(struct cpu_map *map, int cpu, void *data), diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c index aada3ac5e891f..d4a5a21c2a7e2 100644 --- a/tools/perf/util/ctype.c +++ b/tools/perf/util/ctype.c @@ -31,9 +31,18 @@ unsigned char sane_ctype[256] = { }; const char *graph_line = + "_____________________________________________________________________" "_____________________________________________________________________" "_____________________________________________________________________"; const char *graph_dotted_line = "---------------------------------------------------------------------" "---------------------------------------------------------------------" "---------------------------------------------------------------------"; +const char *spaces = + " " + " " + " "; +const char *dots = + "....................................................................." + "....................................................................." + "....................................................................."; diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 34cd1e4039d35..811af89ce0bb8 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -352,6 +352,84 @@ static int add_tracepoint_values(struct ctf_writer *cw, return ret; } +static int +add_bpf_output_values(struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct perf_sample *sample) +{ + struct bt_ctf_field_type *len_type, *seq_type; + struct bt_ctf_field *len_field, *seq_field; + unsigned int raw_size = sample->raw_size; + unsigned int nr_elements = raw_size / sizeof(u32); + unsigned int i; + int ret; + + if (nr_elements * sizeof(u32) != raw_size) + pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n", + raw_size, nr_elements * sizeof(u32) - raw_size); + + len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len"); + len_field = bt_ctf_field_create(len_type); + if (!len_field) { + pr_err("failed to create 'raw_len' for bpf output event\n"); + ret = -1; + goto put_len_type; + } + + ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements); + if (ret) { + pr_err("failed to set field value for raw_len\n"); + goto put_len_field; + } + ret = bt_ctf_event_set_payload(event, "raw_len", len_field); + if (ret) { + pr_err("failed to set payload to raw_len\n"); + goto put_len_field; + } + + seq_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_data"); + seq_field = bt_ctf_field_create(seq_type); + if (!seq_field) { + pr_err("failed to create 'raw_data' for bpf output event\n"); + ret = -1; + goto put_seq_type; + } + + ret = bt_ctf_field_sequence_set_length(seq_field, len_field); + if (ret) { + pr_err("failed to set length of 'raw_data'\n"); + goto put_seq_field; + } + + for (i = 0; i < nr_elements; i++) { + struct bt_ctf_field *elem_field = + bt_ctf_field_sequence_get_field(seq_field, i); + + ret = bt_ctf_field_unsigned_integer_set_value(elem_field, + ((u32 *)(sample->raw_data))[i]); + + bt_ctf_field_put(elem_field); + if (ret) { + pr_err("failed to set raw_data[%d]\n", i); + goto put_seq_field; + } + } + + ret = bt_ctf_event_set_payload(event, "raw_data", seq_field); + if (ret) + pr_err("failed to set payload for raw_data\n"); + +put_seq_field: + bt_ctf_field_put(seq_field); +put_seq_type: + bt_ctf_field_type_put(seq_type); +put_len_field: + bt_ctf_field_put(len_field); +put_len_type: + bt_ctf_field_type_put(len_type); + return ret; +} + static int add_generic_values(struct ctf_writer *cw, struct bt_ctf_event *event, struct perf_evsel *evsel, @@ -597,6 +675,12 @@ static int process_sample_event(struct perf_tool *tool, return -1; } + if (perf_evsel__is_bpf_output(evsel)) { + ret = add_bpf_output_values(event_class, event, sample); + if (ret) + return -1; + } + cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel)); if (cs) { if (is_flush_needed(cs)) @@ -744,6 +828,25 @@ static int add_tracepoint_types(struct ctf_writer *cw, return ret; } +static int add_bpf_output_types(struct ctf_writer *cw, + struct bt_ctf_event_class *class) +{ + struct bt_ctf_field_type *len_type = cw->data.u32; + struct bt_ctf_field_type *seq_base_type = cw->data.u32_hex; + struct bt_ctf_field_type *seq_type; + int ret; + + ret = bt_ctf_event_class_add_field(class, len_type, "raw_len"); + if (ret) + return ret; + + seq_type = bt_ctf_field_type_sequence_create(seq_base_type, "raw_len"); + if (!seq_type) + return -1; + + return bt_ctf_event_class_add_field(class, seq_type, "raw_data"); +} + static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, struct bt_ctf_event_class *event_class) { @@ -755,7 +858,8 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, * ctf event header * PERF_SAMPLE_READ - TODO * PERF_SAMPLE_CALLCHAIN - TODO - * PERF_SAMPLE_RAW - tracepoint fields are handled separately + * PERF_SAMPLE_RAW - tracepoint fields and BPF output + * are handled separately * PERF_SAMPLE_BRANCH_STACK - TODO * PERF_SAMPLE_REGS_USER - TODO * PERF_SAMPLE_STACK_USER - TODO @@ -824,6 +928,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) goto err; } + if (perf_evsel__is_bpf_output(evsel)) { + ret = add_bpf_output_types(cw, event_class); + if (ret) + goto err; + } + ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class); if (ret) { pr("Failed to add event class into stream.\n"); @@ -858,6 +968,23 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session) return 0; } +static void cleanup_events(struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + struct evsel_priv *priv; + + priv = evsel->priv; + bt_ctf_event_class_put(priv->event_class); + zfree(&evsel->priv); + } + + perf_evlist__delete(evlist); + session->evlist = NULL; +} + static int setup_streams(struct ctf_writer *cw, struct perf_session *session) { struct ctf_stream **stream; @@ -953,6 +1080,12 @@ static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex) bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL)) goto err; +#if __BYTE_ORDER == __BIG_ENDIAN + bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_BIG_ENDIAN); +#else + bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_LITTLE_ENDIAN); +#endif + pr2("Created type: INTEGER %d-bit %ssigned %s\n", size, sign ? "un" : "", hex ? "hex" : ""); return type; @@ -1100,7 +1233,7 @@ static int convert__config(const char *var, const char *value, void *cb) return 0; } - return perf_default_config(var, value, cb); + return 0; } int bt_convert__perf2ctf(const char *input, const char *path, bool force) @@ -1171,6 +1304,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force) (double) c.events_size / 1024.0 / 1024.0, c.events_count); + cleanup_events(session); perf_session__delete(session); ctf_writer__cleanup(cw); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 86d9c73025983..8c4212abd19b4 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -5,6 +5,7 @@ #include #include #include +#include #include "cache.h" #include "color.h" @@ -22,7 +23,7 @@ int debug_ordered_events; static int redirect_to_stderr; int debug_data_convert; -static int _eprintf(int level, int var, const char *fmt, va_list args) +int veprintf(int level, int var, const char *fmt, va_list args) { int ret = 0; @@ -36,24 +37,19 @@ static int _eprintf(int level, int var, const char *fmt, va_list args) return ret; } -int veprintf(int level, int var, const char *fmt, va_list args) -{ - return _eprintf(level, var, fmt, args); -} - int eprintf(int level, int var, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); - ret = _eprintf(level, var, fmt, args); + ret = veprintf(level, var, fmt, args); va_end(args); return ret; } -static int __eprintf_time(u64 t, const char *fmt, va_list args) +static int veprintf_time(u64 t, const char *fmt, va_list args) { int ret = 0; u64 secs, usecs, nsecs = t; @@ -75,7 +71,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) if (var >= level) { va_start(args, fmt); - ret = __eprintf_time(t, fmt, args); + ret = veprintf_time(t, fmt, args); va_end(args); } @@ -91,7 +87,7 @@ void pr_stat(const char *fmt, ...) va_list args; va_start(args, fmt); - _eprintf(1, verbose, fmt, args); + veprintf(1, verbose, fmt, args); va_end(args); eprintf(1, verbose, "\n"); } @@ -110,40 +106,61 @@ int dump_printf(const char *fmt, ...) return ret; } +static void trace_event_printer(enum binary_printer_ops op, + unsigned int val, void *extra) +{ + const char *color = PERF_COLOR_BLUE; + union perf_event *event = (union perf_event *)extra; + unsigned char ch = (unsigned char)val; + + switch (op) { + case BINARY_PRINT_DATA_BEGIN: + printf("."); + color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n", + event->header.size); + break; + case BINARY_PRINT_LINE_BEGIN: + printf("."); + break; + case BINARY_PRINT_ADDR: + color_fprintf(stdout, color, " %04x: ", val); + break; + case BINARY_PRINT_NUM_DATA: + color_fprintf(stdout, color, " %02x", val); + break; + case BINARY_PRINT_NUM_PAD: + color_fprintf(stdout, color, " "); + break; + case BINARY_PRINT_SEP: + color_fprintf(stdout, color, " "); + break; + case BINARY_PRINT_CHAR_DATA: + color_fprintf(stdout, color, "%c", + isprint(ch) ? ch : '.'); + break; + case BINARY_PRINT_CHAR_PAD: + color_fprintf(stdout, color, " "); + break; + case BINARY_PRINT_LINE_END: + color_fprintf(stdout, color, "\n"); + break; + case BINARY_PRINT_DATA_END: + printf("\n"); + break; + default: + break; + } +} + void trace_event(union perf_event *event) { unsigned char *raw_event = (void *)event; - const char *color = PERF_COLOR_BLUE; - int i, j; if (!dump_trace) return; - printf("."); - color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n", - event->header.size); - - for (i = 0; i < event->header.size; i++) { - if ((i & 15) == 0) { - printf("."); - color_fprintf(stdout, color, " %04x: ", i); - } - - color_fprintf(stdout, color, " %02x", raw_event[i]); - - if (((i & 15) == 15) || i == event->header.size-1) { - color_fprintf(stdout, color, " "); - for (j = 0; j < 15-(i & 15); j++) - color_fprintf(stdout, color, " "); - for (j = i & ~15; j <= i; j++) { - color_fprintf(stdout, color, "%c", - isprint(raw_event[j]) ? - raw_event[j] : '.'); - } - color_fprintf(stdout, color, "\n"); - } - } - printf(".\n"); + print_binary(raw_event, event->header.size, 16, + trace_event_printer, event); } static struct debug_variable { @@ -192,3 +209,23 @@ int perf_debug_option(const char *str) free(s); return 0; } + +#define DEBUG_WRAPPER(__n, __l) \ +static int pr_ ## __n ## _wrapper(const char *fmt, ...) \ +{ \ + va_list args; \ + int ret; \ + \ + va_start(args, fmt); \ + ret = veprintf(__l, verbose, fmt, args); \ + va_end(args); \ + return ret; \ +} + +DEBUG_WRAPPER(warning, 0); +DEBUG_WRAPPER(debug, 1); + +void perf_debug_setup(void) +{ + libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper); +} diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 8b9a088c32ab4..14bafda79edae 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -53,5 +53,6 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__( int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); +void perf_debug_setup(void); #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c new file mode 100644 index 0000000000000..3e6062ab2cdda --- /dev/null +++ b/tools/perf/util/demangle-java.c @@ -0,0 +1,199 @@ +#include +#include +#include +#include "util.h" +#include "debug.h" +#include "symbol.h" + +#include "demangle-java.h" + +enum { + MODE_PREFIX = 0, + MODE_CLASS = 1, + MODE_FUNC = 2, + MODE_TYPE = 3, + MODE_CTYPE = 3, /* class arg */ +}; + +#define BASE_ENT(c, n) [c - 'A']=n +static const char *base_types['Z' - 'A' + 1] = { + BASE_ENT('B', "byte" ), + BASE_ENT('C', "char" ), + BASE_ENT('D', "double" ), + BASE_ENT('F', "float" ), + BASE_ENT('I', "int" ), + BASE_ENT('J', "long" ), + BASE_ENT('S', "short" ), + BASE_ENT('Z', "bool" ), +}; + +/* + * demangle Java symbol between str and end positions and stores + * up to maxlen characters into buf. The parser starts in mode. + * + * Use MODE_PREFIX to process entire prototype till end position + * Use MODE_TYPE to process return type if str starts on return type char + * + * Return: + * success: buf + * error : NULL + */ +static char * +__demangle_java_sym(const char *str, const char *end, char *buf, int maxlen, int mode) +{ + int rlen = 0; + int array = 0; + int narg = 0; + const char *q; + + if (!end) + end = str + strlen(str); + + for (q = str; q != end; q++) { + + if (rlen == (maxlen - 1)) + break; + + switch (*q) { + case 'L': + if (mode == MODE_PREFIX || mode == MODE_CTYPE) { + if (mode == MODE_CTYPE) { + if (narg) + rlen += scnprintf(buf + rlen, maxlen - rlen, ", "); + narg++; + } + rlen += scnprintf(buf + rlen, maxlen - rlen, "class "); + if (mode == MODE_PREFIX) + mode = MODE_CLASS; + } else + buf[rlen++] = *q; + break; + case 'B': + case 'C': + case 'D': + case 'F': + case 'I': + case 'J': + case 'S': + case 'Z': + if (mode == MODE_TYPE) { + if (narg) + rlen += scnprintf(buf + rlen, maxlen - rlen, ", "); + rlen += scnprintf(buf + rlen, maxlen - rlen, "%s", base_types[*q - 'A']); + while (array--) + rlen += scnprintf(buf + rlen, maxlen - rlen, "[]"); + array = 0; + narg++; + } else + buf[rlen++] = *q; + break; + case 'V': + if (mode == MODE_TYPE) { + rlen += scnprintf(buf + rlen, maxlen - rlen, "void"); + while (array--) + rlen += scnprintf(buf + rlen, maxlen - rlen, "[]"); + array = 0; + } else + buf[rlen++] = *q; + break; + case '[': + if (mode != MODE_TYPE) + goto error; + array++; + break; + case '(': + if (mode != MODE_FUNC) + goto error; + buf[rlen++] = *q; + mode = MODE_TYPE; + break; + case ')': + if (mode != MODE_TYPE) + goto error; + buf[rlen++] = *q; + narg = 0; + break; + case ';': + if (mode != MODE_CLASS && mode != MODE_CTYPE) + goto error; + /* safe because at least one other char to process */ + if (isalpha(*(q + 1))) + rlen += scnprintf(buf + rlen, maxlen - rlen, "."); + if (mode == MODE_CLASS) + mode = MODE_FUNC; + else if (mode == MODE_CTYPE) + mode = MODE_TYPE; + break; + case '/': + if (mode != MODE_CLASS && mode != MODE_CTYPE) + goto error; + rlen += scnprintf(buf + rlen, maxlen - rlen, "."); + break; + default : + buf[rlen++] = *q; + } + } + buf[rlen] = '\0'; + return buf; +error: + return NULL; +} + +/* + * Demangle Java function signature (openJDK, not GCJ) + * input: + * str: string to parse. String is not modified + * flags: comobination of JAVA_DEMANGLE_* flags to modify demangling + * return: + * if input can be demangled, then a newly allocated string is returned. + * if input cannot be demangled, then NULL is returned + * + * Note: caller is responsible for freeing demangled string + */ +char * +java_demangle_sym(const char *str, int flags) +{ + char *buf, *ptr; + char *p; + size_t len, l1 = 0; + + if (!str) + return NULL; + + /* find start of retunr type */ + p = strrchr(str, ')'); + if (!p) + return NULL; + + /* + * expansion factor estimated to 3x + */ + len = strlen(str) * 3 + 1; + buf = malloc(len); + if (!buf) + return NULL; + + buf[0] = '\0'; + if (!(flags & JAVA_DEMANGLE_NORET)) { + /* + * get return type first + */ + ptr = __demangle_java_sym(p + 1, NULL, buf, len, MODE_TYPE); + if (!ptr) + goto error; + + /* add space between return type and function prototype */ + l1 = strlen(buf); + buf[l1++] = ' '; + } + + /* process function up to return type */ + ptr = __demangle_java_sym(str, p + 1, buf + l1, len - l1, MODE_PREFIX); + if (!ptr) + goto error; + + return buf; +error: + free(buf); + return NULL; +} diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h new file mode 100644 index 0000000000000..a981c1f968fe9 --- /dev/null +++ b/tools/perf/util/demangle-java.h @@ -0,0 +1,10 @@ +#ifndef __PERF_DEMANGLE_JAVA +#define __PERF_DEMANGLE_JAVA 1 +/* + * demangle function flags + */ +#define JAVA_DEMANGLE_NORET 0x1 /* do not process return type */ + +char * java_demangle_sym(const char *str, int flags); + +#endif /* __PERF_DEMANGLE_JAVA */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index e8e9a9dbf5e39..8e6395439ca08 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso, debuglink--; if (*debuglink == '/') debuglink++; + + ret = -1; + if (!is_regular_file(filename)) + break; + ret = filename__read_debuglink(filename, debuglink, size - (debuglink - filename)); } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 7dd5939dea2e5..49a11d9d8b8f0 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -6,6 +6,8 @@ struct perf_env perf_env; void perf_env__exit(struct perf_env *env) { + int i; + zfree(&env->hostname); zfree(&env->os_release); zfree(&env->version); @@ -19,6 +21,10 @@ void perf_env__exit(struct perf_env *env) zfree(&env->numa_nodes); zfree(&env->pmu_mappings); zfree(&env->cpu); + + for (i = 0; i < env->caches_cnt; i++) + cpu_cache_level__free(&env->caches[i]); + zfree(&env->caches); } int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]) @@ -75,3 +81,10 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) env->nr_cpus_avail = nr_cpus; return 0; } + +void cpu_cache_level__free(struct cpu_cache_level *cache) +{ + free(cache->type); + free(cache->map); + free(cache->size); +} diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 0132b9557c02b..56cffb60a0b42 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -1,11 +1,23 @@ #ifndef __PERF_ENV_H #define __PERF_ENV_H +#include + struct cpu_topology_map { int socket_id; int core_id; }; +struct cpu_cache_level { + u32 level; + u32 line_size; + u32 sets; + u32 ways; + char *type; + char *size; + char *map; +}; + struct perf_env { char *hostname; char *os_release; @@ -31,6 +43,8 @@ struct perf_env { char *numa_nodes; char *pmu_mappings; struct cpu_topology_map *cpu; + struct cpu_cache_level *caches; + int caches_cnt; }; extern struct perf_env perf_env; @@ -41,4 +55,5 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]); int perf_env__read_cpu_topology_map(struct perf_env *env); +void cpu_cache_level__free(struct cpu_cache_level *cache); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 85155e91b61ba..7bad5c3fa7b71 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -282,7 +282,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n", &event->mmap2.start, &event->mmap2.len, prot, &event->mmap2.pgoff, &event->mmap2.maj, &event->mmap2.min, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d81f13de24769..86a03836a83fc 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1181,12 +1181,12 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, */ if (cpus != evlist->cpus) { cpu_map__put(evlist->cpus); - evlist->cpus = cpus; + evlist->cpus = cpu_map__get(cpus); } if (threads != evlist->threads) { thread_map__put(evlist->threads); - evlist->threads = threads; + evlist->threads = thread_map__get(threads); } perf_evlist__propagate_maps(evlist); @@ -1223,6 +1223,9 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) int err = 0; evlist__for_each(evlist, evsel) { + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + continue; + err = perf_evsel__set_filter(evsel, filter); if (err) break; @@ -1624,7 +1627,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) return printed + fprintf(fp, "\n"); } -int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, +int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size) { int printed, value; @@ -1652,7 +1655,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n" "Hint:\tThe current value is %d.", value); break; + case EINVAL: { + struct perf_evsel *first = perf_evlist__first(evlist); + int max_freq; + + if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0) + goto out_default; + + if (first->attr.sample_freq < (u64)max_freq) + goto out_default; + + printed = scnprintf(buf, size, + "Error:\t%s.\n" + "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n" + "Hint:\tThe current value is %d and %" PRIu64 " is being requested.", + emsg, max_freq, first->attr.sample_freq); + break; + } default: +out_default: scnprintf(buf, size, "%s", emsg); break; } @@ -1723,3 +1744,19 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist, tracking_evsel->tracking = true; } + +struct perf_evsel * +perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, + const char *str) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (!evsel->name) + continue; + if (strcmp(str, evsel->name) == 0) + return evsel; + } + + return NULL; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 7c4d9a2067769..a0d15221db6e8 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -294,4 +294,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist, struct perf_evsel *tracking_evsel); void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr); + +struct perf_evsel * +perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index cdbaf9b51e428..0902fe418754e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) if (evsel != NULL) perf_evsel__init(evsel, attr, idx); + if (perf_evsel__is_bpf_output(evsel)) { + evsel->attr.sample_type |= PERF_SAMPLE_RAW; + evsel->attr.sample_period = 1; + } + return evsel; } @@ -898,6 +903,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (evsel->precise_max) perf_event_attr__set_max_precise_ip(attr); + if (opts->all_user) { + attr->exclude_kernel = 1; + attr->exclude_user = 0; + } + + if (opts->all_kernel) { + attr->exclude_kernel = 0; + attr->exclude_user = 1; + } + /* * Apply event specific term settings, * it overloads any global configuration. @@ -2362,12 +2377,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, case EPERM: case EACCES: return scnprintf(msg, size, - "You may not have permission to collect %sstats.\n" - "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" - " -1 - Not paranoid at all\n" - " 0 - Disallow raw tracepoint access for unpriv\n" - " 1 - Disallow cpu events for unpriv\n" - " 2 - Disallow kernel profiling for unpriv", + "You may not have permission to collect %sstats.\n\n" + "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" + "which controls use of the performance events system by\n" + "unprivileged users (without CAP_SYS_ADMIN).\n\n" + "The default value is 1:\n\n" + " -1: Allow use of (almost) all events by all users\n" + ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" + ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" + ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN", target->system_wide ? "system-wide " : ""); case ENOENT: return scnprintf(msg, size, "The %s event is not supported.", diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 8e75434bd01c6..501ea6e565f13 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -93,10 +93,8 @@ struct perf_evsel { const char *unit; struct event_format *tp_format; off_t id_offset; - union { - void *priv; - u64 db_id; - }; + void *priv; + u64 db_id; struct cgroup_sel *cgrp; void *handler; struct cpu_map *cpus; @@ -364,6 +362,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel) #undef FUNCTION_EVENT } +static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) +{ + struct perf_event_attr *attr = &evsel->attr; + + return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) && + (attr->type == PERF_TYPE_SOFTWARE); +} + struct perf_attr_details { bool freq; bool verbose; diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c new file mode 100644 index 0000000000000..c1ef805c6a8f4 --- /dev/null +++ b/tools/perf/util/genelf.c @@ -0,0 +1,449 @@ +/* + * genelf.c + * Copyright (C) 2014, Google, Inc + * + * Contributed by: + * Stephane Eranian + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "perf.h" +#include "genelf.h" +#include "../util/jitdump.h" + +#define JVMTI + +#define BUILD_ID_URANDOM /* different uuid for each run */ + +#ifdef HAVE_LIBCRYPTO + +#define BUILD_ID_MD5 +#undef BUILD_ID_SHA /* does not seem to work well when linked with Java */ +#undef BUILD_ID_URANDOM /* different uuid for each run */ + +#ifdef BUILD_ID_SHA +#include +#endif + +#ifdef BUILD_ID_MD5 +#include +#endif +#endif + + +typedef struct { + unsigned int namesz; /* Size of entry's owner string */ + unsigned int descsz; /* Size of the note descriptor */ + unsigned int type; /* Interpretation of the descriptor */ + char name[0]; /* Start of the name+desc data */ +} Elf_Note; + +struct options { + char *output; + int fd; +}; + +static char shd_string_table[] = { + 0, + '.', 't', 'e', 'x', 't', 0, /* 1 */ + '.', 's', 'h', 's', 't', 'r', 't', 'a', 'b', 0, /* 7 */ + '.', 's', 'y', 'm', 't', 'a', 'b', 0, /* 17 */ + '.', 's', 't', 'r', 't', 'a', 'b', 0, /* 25 */ + '.', 'n', 'o', 't', 'e', '.', 'g', 'n', 'u', '.', 'b', 'u', 'i', 'l', 'd', '-', 'i', 'd', 0, /* 33 */ + '.', 'd', 'e', 'b', 'u', 'g', '_', 'l', 'i', 'n', 'e', 0, /* 52 */ + '.', 'd', 'e', 'b', 'u', 'g', '_', 'i', 'n', 'f', 'o', 0, /* 64 */ + '.', 'd', 'e', 'b', 'u', 'g', '_', 'a', 'b', 'b', 'r', 'e', 'v', 0, /* 76 */ +}; + +static struct buildid_note { + Elf_Note desc; /* descsz: size of build-id, must be multiple of 4 */ + char name[4]; /* GNU\0 */ + char build_id[20]; +} bnote; + +static Elf_Sym symtab[]={ + /* symbol 0 MUST be the undefined symbol */ + { .st_name = 0, /* index in sym_string table */ + .st_info = ELF_ST_TYPE(STT_NOTYPE), + .st_shndx = 0, /* for now */ + .st_value = 0x0, + .st_other = ELF_ST_VIS(STV_DEFAULT), + .st_size = 0, + }, + { .st_name = 1, /* index in sym_string table */ + .st_info = ELF_ST_BIND(STB_LOCAL) | ELF_ST_TYPE(STT_FUNC), + .st_shndx = 1, + .st_value = 0, /* for now */ + .st_other = ELF_ST_VIS(STV_DEFAULT), + .st_size = 0, /* for now */ + } +}; + +#ifdef BUILD_ID_URANDOM +static void +gen_build_id(struct buildid_note *note, + unsigned long load_addr __maybe_unused, + const void *code __maybe_unused, + size_t csize __maybe_unused) +{ + int fd; + size_t sz = sizeof(note->build_id); + ssize_t sret; + + fd = open("/dev/urandom", O_RDONLY); + if (fd == -1) + err(1, "cannot access /dev/urandom for builid"); + + sret = read(fd, note->build_id, sz); + + close(fd); + + if (sret != (ssize_t)sz) + memset(note->build_id, 0, sz); +} +#endif + +#ifdef BUILD_ID_SHA +static void +gen_build_id(struct buildid_note *note, + unsigned long load_addr __maybe_unused, + const void *code, + size_t csize) +{ + if (sizeof(note->build_id) < SHA_DIGEST_LENGTH) + errx(1, "build_id too small for SHA1"); + + SHA1(code, csize, (unsigned char *)note->build_id); +} +#endif + +#ifdef BUILD_ID_MD5 +static void +gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize) +{ + MD5_CTX context; + + if (sizeof(note->build_id) < 16) + errx(1, "build_id too small for MD5"); + + MD5_Init(&context); + MD5_Update(&context, &load_addr, sizeof(load_addr)); + MD5_Update(&context, code, csize); + MD5_Final((unsigned char *)note->build_id, &context); +} +#endif + +/* + * fd: file descriptor open for writing for the output file + * load_addr: code load address (could be zero, just used for buildid) + * sym: function name (for native code - used as the symbol) + * code: the native code + * csize: the code size in bytes + */ +int +jit_write_elf(int fd, uint64_t load_addr, const char *sym, + const void *code, int csize, + void *debug, int nr_debug_entries) +{ + Elf *e; + Elf_Data *d; + Elf_Scn *scn; + Elf_Ehdr *ehdr; + Elf_Shdr *shdr; + char *strsym = NULL; + int symlen; + int retval = -1; + + if (elf_version(EV_CURRENT) == EV_NONE) { + warnx("ELF initialization failed"); + return -1; + } + + e = elf_begin(fd, ELF_C_WRITE, NULL); + if (!e) { + warnx("elf_begin failed"); + goto error; + } + + /* + * setup ELF header + */ + ehdr = elf_newehdr(e); + if (!ehdr) { + warnx("cannot get ehdr"); + goto error; + } + + ehdr->e_ident[EI_DATA] = GEN_ELF_ENDIAN; + ehdr->e_ident[EI_CLASS] = GEN_ELF_CLASS; + ehdr->e_machine = GEN_ELF_ARCH; + ehdr->e_type = ET_DYN; + ehdr->e_entry = GEN_ELF_TEXT_OFFSET; + ehdr->e_version = EV_CURRENT; + ehdr->e_shstrndx= 2; /* shdr index for section name */ + + /* + * setup text section + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + goto error; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + goto error; + } + + d->d_align = 16; + d->d_off = 0LL; + d->d_buf = (void *)code; + d->d_type = ELF_T_BYTE; + d->d_size = csize; + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + goto error; + } + + shdr->sh_name = 1; + shdr->sh_type = SHT_PROGBITS; + shdr->sh_addr = GEN_ELF_TEXT_OFFSET; + shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + shdr->sh_entsize = 0; + + /* + * setup section headers string table + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + goto error; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + goto error; + } + + d->d_align = 1; + d->d_off = 0LL; + d->d_buf = shd_string_table; + d->d_type = ELF_T_BYTE; + d->d_size = sizeof(shd_string_table); + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + goto error; + } + + shdr->sh_name = 7; /* offset of '.shstrtab' in shd_string_table */ + shdr->sh_type = SHT_STRTAB; + shdr->sh_flags = 0; + shdr->sh_entsize = 0; + + /* + * setup symtab section + */ + symtab[1].st_size = csize; + symtab[1].st_value = GEN_ELF_TEXT_OFFSET; + + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + goto error; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + goto error; + } + + d->d_align = 8; + d->d_off = 0LL; + d->d_buf = symtab; + d->d_type = ELF_T_SYM; + d->d_size = sizeof(symtab); + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + goto error; + } + + shdr->sh_name = 17; /* offset of '.symtab' in shd_string_table */ + shdr->sh_type = SHT_SYMTAB; + shdr->sh_flags = 0; + shdr->sh_entsize = sizeof(Elf_Sym); + shdr->sh_link = 4; /* index of .strtab section */ + + /* + * setup symbols string table + * 2 = 1 for 0 in 1st entry, 1 for the 0 at end of symbol for 2nd entry + */ + symlen = 2 + strlen(sym); + strsym = calloc(1, symlen); + if (!strsym) { + warnx("cannot allocate strsym"); + goto error; + } + strcpy(strsym + 1, sym); + + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + goto error; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + goto error; + } + + d->d_align = 1; + d->d_off = 0LL; + d->d_buf = strsym; + d->d_type = ELF_T_BYTE; + d->d_size = symlen; + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + goto error; + } + + shdr->sh_name = 25; /* offset in shd_string_table */ + shdr->sh_type = SHT_STRTAB; + shdr->sh_flags = 0; + shdr->sh_entsize = 0; + + /* + * setup build-id section + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + goto error; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + goto error; + } + + /* + * build-id generation + */ + gen_build_id(&bnote, load_addr, code, csize); + bnote.desc.namesz = sizeof(bnote.name); /* must include 0 termination */ + bnote.desc.descsz = sizeof(bnote.build_id); + bnote.desc.type = NT_GNU_BUILD_ID; + strcpy(bnote.name, "GNU"); + + d->d_align = 4; + d->d_off = 0LL; + d->d_buf = &bnote; + d->d_type = ELF_T_BYTE; + d->d_size = sizeof(bnote); + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + goto error; + } + + shdr->sh_name = 33; /* offset in shd_string_table */ + shdr->sh_type = SHT_NOTE; + shdr->sh_addr = 0x0; + shdr->sh_flags = SHF_ALLOC; + shdr->sh_size = sizeof(bnote); + shdr->sh_entsize = 0; + + if (debug && nr_debug_entries) { + retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries); + if (retval) + goto error; + } else { + if (elf_update(e, ELF_C_WRITE) < 0) { + warnx("elf_update 4 failed"); + goto error; + } + } + + retval = 0; +error: + (void)elf_end(e); + + free(strsym); + + + return retval; +} + +#ifndef JVMTI + +static unsigned char x86_code[] = { + 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */ + 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */ + 0xCD, 0x80 /* int $0x80 */ +}; + +static struct options options; + +int main(int argc, char **argv) +{ + int c, fd, ret; + + while ((c = getopt(argc, argv, "o:h")) != -1) { + switch (c) { + case 'o': + options.output = optarg; + break; + case 'h': + printf("Usage: genelf -o output_file [-h]\n"); + return 0; + default: + errx(1, "unknown option"); + } + } + + fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666); + if (fd == -1) + err(1, "cannot create file %s", options.output); + + ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code)); + close(fd); + + if (ret != 0) + unlink(options.output); + + return ret; +} +#endif diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h new file mode 100644 index 0000000000000..45bf9c6d3257e --- /dev/null +++ b/tools/perf/util/genelf.h @@ -0,0 +1,67 @@ +#ifndef __GENELF_H__ +#define __GENELF_H__ + +/* genelf.c */ +extern int jit_write_elf(int fd, uint64_t code_addr, const char *sym, + const void *code, int csize, + void *debug, int nr_debug_entries); +/* genelf_debug.c */ +extern int jit_add_debug_info(Elf *e, uint64_t code_addr, + void *debug, int nr_debug_entries); + +#if defined(__arm__) +#define GEN_ELF_ARCH EM_ARM +#define GEN_ELF_ENDIAN ELFDATA2LSB +#define GEN_ELF_CLASS ELFCLASS32 +#elif defined(__aarch64__) +#define GEN_ELF_ARCH EM_AARCH64 +#define GEN_ELF_ENDIAN ELFDATA2LSB +#define GEN_ELF_CLASS ELFCLASS64 +#elif defined(__x86_64__) +#define GEN_ELF_ARCH EM_X86_64 +#define GEN_ELF_ENDIAN ELFDATA2LSB +#define GEN_ELF_CLASS ELFCLASS64 +#elif defined(__i386__) +#define GEN_ELF_ARCH EM_386 +#define GEN_ELF_ENDIAN ELFDATA2LSB +#define GEN_ELF_CLASS ELFCLASS32 +#elif defined(__ppcle__) +#define GEN_ELF_ARCH EM_PPC +#define GEN_ELF_ENDIAN ELFDATA2LSB +#define GEN_ELF_CLASS ELFCLASS64 +#elif defined(__powerpc__) +#define GEN_ELF_ARCH EM_PPC64 +#define GEN_ELF_ENDIAN ELFDATA2MSB +#define GEN_ELF_CLASS ELFCLASS64 +#elif defined(__powerpcle__) +#define GEN_ELF_ARCH EM_PPC64 +#define GEN_ELF_ENDIAN ELFDATA2LSB +#define GEN_ELF_CLASS ELFCLASS64 +#else +#error "unsupported architecture" +#endif + +#if GEN_ELF_CLASS == ELFCLASS64 +#define elf_newehdr elf64_newehdr +#define elf_getshdr elf64_getshdr +#define Elf_Ehdr Elf64_Ehdr +#define Elf_Shdr Elf64_Shdr +#define Elf_Sym Elf64_Sym +#define ELF_ST_TYPE(a) ELF64_ST_TYPE(a) +#define ELF_ST_BIND(a) ELF64_ST_BIND(a) +#define ELF_ST_VIS(a) ELF64_ST_VISIBILITY(a) +#else +#define elf_newehdr elf32_newehdr +#define elf_getshdr elf32_getshdr +#define Elf_Ehdr Elf32_Ehdr +#define Elf_Shdr Elf32_Shdr +#define Elf_Sym Elf32_Sym +#define ELF_ST_TYPE(a) ELF32_ST_TYPE(a) +#define ELF_ST_BIND(a) ELF32_ST_BIND(a) +#define ELF_ST_VIS(a) ELF32_ST_VISIBILITY(a) +#endif + +/* The .text section is directly after the ELF header */ +#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr) + +#endif diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c new file mode 100644 index 0000000000000..5980f7d256b17 --- /dev/null +++ b/tools/perf/util/genelf_debug.c @@ -0,0 +1,610 @@ +/* + * genelf_debug.c + * Copyright (C) 2015, Google, Inc + * + * Contributed by: + * Stephane Eranian + * + * Released under the GPL v2. + * + * based on GPLv2 source code from Oprofile + * @remark Copyright 2007 OProfile authors + * @author Philippe Elie + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "perf.h" +#include "genelf.h" +#include "../util/jitdump.h" + +#define BUFFER_EXT_DFL_SIZE (4 * 1024) + +typedef uint32_t uword; +typedef uint16_t uhalf; +typedef int32_t sword; +typedef int16_t shalf; +typedef uint8_t ubyte; +typedef int8_t sbyte; + +struct buffer_ext { + size_t cur_pos; + size_t max_sz; + void *data; +}; + +static void +buffer_ext_dump(struct buffer_ext *be, const char *msg) +{ + size_t i; + warnx("DUMP for %s", msg); + for (i = 0 ; i < be->cur_pos; i++) + warnx("%4zu 0x%02x", i, (((char *)be->data)[i]) & 0xff); +} + +static inline int +buffer_ext_add(struct buffer_ext *be, void *addr, size_t sz) +{ + void *tmp; + size_t be_sz = be->max_sz; + +retry: + if ((be->cur_pos + sz) < be_sz) { + memcpy(be->data + be->cur_pos, addr, sz); + be->cur_pos += sz; + return 0; + } + + if (!be_sz) + be_sz = BUFFER_EXT_DFL_SIZE; + else + be_sz <<= 1; + + tmp = realloc(be->data, be_sz); + if (!tmp) + return -1; + + be->data = tmp; + be->max_sz = be_sz; + + goto retry; +} + +static void +buffer_ext_init(struct buffer_ext *be) +{ + be->data = NULL; + be->cur_pos = 0; + be->max_sz = 0; +} + +static inline size_t +buffer_ext_size(struct buffer_ext *be) +{ + return be->cur_pos; +} + +static inline void * +buffer_ext_addr(struct buffer_ext *be) +{ + return be->data; +} + +struct debug_line_header { + // Not counting this field + uword total_length; + // version number (2 currently) + uhalf version; + // relative offset from next field to + // program statement + uword prolog_length; + ubyte minimum_instruction_length; + ubyte default_is_stmt; + // line_base - see DWARF 2 specs + sbyte line_base; + // line_range - see DWARF 2 specs + ubyte line_range; + // number of opcode + 1 + ubyte opcode_base; + /* follow the array of opcode args nr: ubytes [nr_opcode_base] */ + /* follow the search directories index, zero terminated string + * terminated by an empty string. + */ + /* follow an array of { filename, LEB128, LEB128, LEB128 }, first is + * the directory index entry, 0 means current directory, then mtime + * and filesize, last entry is followed by en empty string. + */ + /* follow the first program statement */ +} __attribute__((packed)); + +/* DWARF 2 spec talk only about one possible compilation unit header while + * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not + * related to the used arch, an ELF 32 can hold more than 4 Go of debug + * information. For now we handle only DWARF 2 32 bits comp unit. It'll only + * become a problem if we generate more than 4GB of debug information. + */ +struct compilation_unit_header { + uword total_length; + uhalf version; + uword debug_abbrev_offset; + ubyte pointer_size; +} __attribute__((packed)); + +#define DW_LNS_num_opcode (DW_LNS_set_isa + 1) + +/* field filled at run time are marked with -1 */ +static struct debug_line_header const default_debug_line_header = { + .total_length = -1, + .version = 2, + .prolog_length = -1, + .minimum_instruction_length = 1, /* could be better when min instruction size != 1 */ + .default_is_stmt = 1, /* we don't take care about basic block */ + .line_base = -5, /* sensible value for line base ... */ + .line_range = -14, /* ... and line range are guessed statically */ + .opcode_base = DW_LNS_num_opcode +}; + +static ubyte standard_opcode_length[] = +{ + 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1 +}; +#if 0 +{ + [DW_LNS_advance_pc] = 1, + [DW_LNS_advance_line] = 1, + [DW_LNS_set_file] = 1, + [DW_LNS_set_column] = 1, + [DW_LNS_fixed_advance_pc] = 1, + [DW_LNS_set_isa] = 1, +}; +#endif + +/* field filled at run time are marked with -1 */ +static struct compilation_unit_header default_comp_unit_header = { + .total_length = -1, + .version = 2, + .debug_abbrev_offset = 0, /* we reuse the same abbrev entries for all comp unit */ + .pointer_size = sizeof(void *) +}; + +static void emit_uword(struct buffer_ext *be, uword data) +{ + buffer_ext_add(be, &data, sizeof(uword)); +} + +static void emit_string(struct buffer_ext *be, const char *s) +{ + buffer_ext_add(be, (void *)s, strlen(s) + 1); +} + +static void emit_unsigned_LEB128(struct buffer_ext *be, + unsigned long data) +{ + do { + ubyte cur = data & 0x7F; + data >>= 7; + if (data) + cur |= 0x80; + buffer_ext_add(be, &cur, 1); + } while (data); +} + +static void emit_signed_LEB128(struct buffer_ext *be, long data) +{ + int more = 1; + int negative = data < 0; + int size = sizeof(long) * CHAR_BIT; + while (more) { + ubyte cur = data & 0x7F; + data >>= 7; + if (negative) + data |= - (1 << (size - 7)); + if ((data == 0 && !(cur & 0x40)) || + (data == -1l && (cur & 0x40))) + more = 0; + else + cur |= 0x80; + buffer_ext_add(be, &cur, 1); + } +} + +static void emit_extended_opcode(struct buffer_ext *be, ubyte opcode, + void *data, size_t data_len) +{ + buffer_ext_add(be, (char *)"", 1); + + emit_unsigned_LEB128(be, data_len + 1); + + buffer_ext_add(be, &opcode, 1); + buffer_ext_add(be, data, data_len); +} + +static void emit_opcode(struct buffer_ext *be, ubyte opcode) +{ + buffer_ext_add(be, &opcode, 1); +} + +static void emit_opcode_signed(struct buffer_ext *be, + ubyte opcode, long data) +{ + buffer_ext_add(be, &opcode, 1); + emit_signed_LEB128(be, data); +} + +static void emit_opcode_unsigned(struct buffer_ext *be, ubyte opcode, + unsigned long data) +{ + buffer_ext_add(be, &opcode, 1); + emit_unsigned_LEB128(be, data); +} + +static void emit_advance_pc(struct buffer_ext *be, unsigned long delta_pc) +{ + emit_opcode_unsigned(be, DW_LNS_advance_pc, delta_pc); +} + +static void emit_advance_lineno(struct buffer_ext *be, long delta_lineno) +{ + emit_opcode_signed(be, DW_LNS_advance_line, delta_lineno); +} + +static void emit_lne_end_of_sequence(struct buffer_ext *be) +{ + emit_extended_opcode(be, DW_LNE_end_sequence, NULL, 0); +} + +static void emit_set_file(struct buffer_ext *be, unsigned long idx) +{ + emit_opcode_unsigned(be, DW_LNS_set_file, idx); +} + +static void emit_lne_define_filename(struct buffer_ext *be, + const char *filename) +{ + buffer_ext_add(be, (void *)"", 1); + + /* LNE field, strlen(filename) + zero termination, 3 bytes for: the dir entry, timestamp, filesize */ + emit_unsigned_LEB128(be, strlen(filename) + 5); + emit_opcode(be, DW_LNE_define_file); + emit_string(be, filename); + /* directory index 0=do not know */ + emit_unsigned_LEB128(be, 0); + /* last modification date on file 0=do not know */ + emit_unsigned_LEB128(be, 0); + /* filesize 0=do not know */ + emit_unsigned_LEB128(be, 0); +} + +static void emit_lne_set_address(struct buffer_ext *be, + void *address) +{ + emit_extended_opcode(be, DW_LNE_set_address, &address, sizeof(unsigned long)); +} + +static ubyte get_special_opcode(struct debug_entry *ent, + unsigned int last_line, + unsigned long last_vma) +{ + unsigned int temp; + unsigned long delta_addr; + + /* + * delta from line_base + */ + temp = (ent->lineno - last_line) - default_debug_line_header.line_base; + + if (temp >= default_debug_line_header.line_range) + return 0; + + /* + * delta of addresses + */ + delta_addr = (ent->addr - last_vma) / default_debug_line_header.minimum_instruction_length; + + /* This is not sufficient to ensure opcode will be in [0-256] but + * sufficient to ensure when summing with the delta lineno we will + * not overflow the unsigned long opcode */ + + if (delta_addr <= 256 / default_debug_line_header.line_range) { + unsigned long opcode = temp + + (delta_addr * default_debug_line_header.line_range) + + default_debug_line_header.opcode_base; + + return opcode <= 255 ? opcode : 0; + } + return 0; +} + +static void emit_lineno_info(struct buffer_ext *be, + struct debug_entry *ent, size_t nr_entry, + unsigned long code_addr) +{ + size_t i; + + /* + * Machine state at start of a statement program + * address = 0 + * file = 1 + * line = 1 + * column = 0 + * is_stmt = default_is_stmt as given in the debug_line_header + * basic block = 0 + * end sequence = 0 + */ + + /* start state of the state machine we take care of */ + unsigned long last_vma = code_addr; + char const *cur_filename = NULL; + unsigned long cur_file_idx = 0; + int last_line = 1; + + emit_lne_set_address(be, (void *)code_addr); + + for (i = 0; i < nr_entry; i++, ent = debug_entry_next(ent)) { + int need_copy = 0; + ubyte special_opcode; + + /* + * check if filename changed, if so add it + */ + if (!cur_filename || strcmp(cur_filename, ent->name)) { + emit_lne_define_filename(be, ent->name); + cur_filename = ent->name; + emit_set_file(be, ++cur_file_idx); + need_copy = 1; + } + + special_opcode = get_special_opcode(ent, last_line, last_vma); + if (special_opcode != 0) { + last_line = ent->lineno; + last_vma = ent->addr; + emit_opcode(be, special_opcode); + } else { + /* + * lines differ, emit line delta + */ + if (last_line != ent->lineno) { + emit_advance_lineno(be, ent->lineno - last_line); + last_line = ent->lineno; + need_copy = 1; + } + /* + * addresses differ, emit address delta + */ + if (last_vma != ent->addr) { + emit_advance_pc(be, ent->addr - last_vma); + last_vma = ent->addr; + need_copy = 1; + } + /* + * add new row to matrix + */ + if (need_copy) + emit_opcode(be, DW_LNS_copy); + } + } +} + +static void add_debug_line(struct buffer_ext *be, + struct debug_entry *ent, size_t nr_entry, + unsigned long code_addr) +{ + struct debug_line_header * dbg_header; + size_t old_size; + + old_size = buffer_ext_size(be); + + buffer_ext_add(be, (void *)&default_debug_line_header, + sizeof(default_debug_line_header)); + + buffer_ext_add(be, &standard_opcode_length, sizeof(standard_opcode_length)); + + // empty directory entry + buffer_ext_add(be, (void *)"", 1); + + // empty filename directory + buffer_ext_add(be, (void *)"", 1); + + dbg_header = buffer_ext_addr(be) + old_size; + dbg_header->prolog_length = (buffer_ext_size(be) - old_size) - + offsetof(struct debug_line_header, minimum_instruction_length); + + emit_lineno_info(be, ent, nr_entry, code_addr); + + emit_lne_end_of_sequence(be); + + dbg_header = buffer_ext_addr(be) + old_size; + dbg_header->total_length = (buffer_ext_size(be) - old_size) - + offsetof(struct debug_line_header, version); +} + +static void +add_debug_abbrev(struct buffer_ext *be) +{ + emit_unsigned_LEB128(be, 1); + emit_unsigned_LEB128(be, DW_TAG_compile_unit); + emit_unsigned_LEB128(be, DW_CHILDREN_yes); + emit_unsigned_LEB128(be, DW_AT_stmt_list); + emit_unsigned_LEB128(be, DW_FORM_data4); + emit_unsigned_LEB128(be, 0); + emit_unsigned_LEB128(be, 0); + emit_unsigned_LEB128(be, 0); +} + +static void +add_compilation_unit(struct buffer_ext *be, + size_t offset_debug_line) +{ + struct compilation_unit_header *comp_unit_header; + size_t old_size = buffer_ext_size(be); + + buffer_ext_add(be, &default_comp_unit_header, + sizeof(default_comp_unit_header)); + + emit_unsigned_LEB128(be, 1); + emit_uword(be, offset_debug_line); + + comp_unit_header = buffer_ext_addr(be) + old_size; + comp_unit_header->total_length = (buffer_ext_size(be) - old_size) - + offsetof(struct compilation_unit_header, version); +} + +static int +jit_process_debug_info(uint64_t code_addr, + void *debug, int nr_debug_entries, + struct buffer_ext *dl, + struct buffer_ext *da, + struct buffer_ext *di) +{ + struct debug_entry *ent = debug; + int i; + + for (i = 0; i < nr_debug_entries; i++) { + ent->addr = ent->addr - code_addr; + ent = debug_entry_next(ent); + } + add_compilation_unit(di, buffer_ext_size(dl)); + add_debug_line(dl, debug, nr_debug_entries, 0); + add_debug_abbrev(da); + if (0) buffer_ext_dump(da, "abbrev"); + + return 0; +} + +int +jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries) +{ + Elf_Data *d; + Elf_Scn *scn; + Elf_Shdr *shdr; + struct buffer_ext dl, di, da; + int ret; + + buffer_ext_init(&dl); + buffer_ext_init(&di); + buffer_ext_init(&da); + + ret = jit_process_debug_info(code_addr, debug, nr_debug_entries, &dl, &da, &di); + if (ret) + return -1; + /* + * setup .debug_line section + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + return -1; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + return -1; + } + + d->d_align = 1; + d->d_off = 0LL; + d->d_buf = buffer_ext_addr(&dl); + d->d_type = ELF_T_BYTE; + d->d_size = buffer_ext_size(&dl); + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + return -1; + } + + shdr->sh_name = 52; /* .debug_line */ + shdr->sh_type = SHT_PROGBITS; + shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */ + shdr->sh_flags = 0; + shdr->sh_entsize = 0; + + /* + * setup .debug_info section + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + return -1; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + return -1; + } + + d->d_align = 1; + d->d_off = 0LL; + d->d_buf = buffer_ext_addr(&di); + d->d_type = ELF_T_BYTE; + d->d_size = buffer_ext_size(&di); + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + return -1; + } + + shdr->sh_name = 64; /* .debug_info */ + shdr->sh_type = SHT_PROGBITS; + shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */ + shdr->sh_flags = 0; + shdr->sh_entsize = 0; + + /* + * setup .debug_abbrev section + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + return -1; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + return -1; + } + + d->d_align = 1; + d->d_off = 0LL; + d->d_buf = buffer_ext_addr(&da); + d->d_type = ELF_T_BYTE; + d->d_size = buffer_ext_size(&da); + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + return -1; + } + + shdr->sh_name = 76; /* .debug_info */ + shdr->sh_type = SHT_PROGBITS; + shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */ + shdr->sh_flags = 0; + shdr->sh_entsize = 0; + + /* + * now we update the ELF image with all the sections + */ + if (elf_update(e, ELF_C_WRITE) < 0) { + warnx("elf_update debug failed"); + return -1; + } + return 0; +} diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index f50b7235ecb65..73e38e472ecd7 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -23,6 +23,8 @@ #include "strbuf.h" #include "build-id.h" #include "data.h" +#include +#include "asm/bug.h" /* * magic2 = "PERFILE2" @@ -868,6 +870,199 @@ static int write_auxtrace(int fd, struct perf_header *h, return err; } +static int cpu_cache_level__sort(const void *a, const void *b) +{ + struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a; + struct cpu_cache_level *cache_b = (struct cpu_cache_level *)b; + + return cache_a->level - cache_b->level; +} + +static bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b) +{ + if (a->level != b->level) + return false; + + if (a->line_size != b->line_size) + return false; + + if (a->sets != b->sets) + return false; + + if (a->ways != b->ways) + return false; + + if (strcmp(a->type, b->type)) + return false; + + if (strcmp(a->size, b->size)) + return false; + + if (strcmp(a->map, b->map)) + return false; + + return true; +} + +static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level) +{ + char path[PATH_MAX], file[PATH_MAX]; + struct stat st; + size_t len; + + scnprintf(path, PATH_MAX, "devices/system/cpu/cpu%d/cache/index%d/", cpu, level); + scnprintf(file, PATH_MAX, "%s/%s", sysfs__mountpoint(), path); + + if (stat(file, &st)) + return 1; + + scnprintf(file, PATH_MAX, "%s/level", path); + if (sysfs__read_int(file, (int *) &cache->level)) + return -1; + + scnprintf(file, PATH_MAX, "%s/coherency_line_size", path); + if (sysfs__read_int(file, (int *) &cache->line_size)) + return -1; + + scnprintf(file, PATH_MAX, "%s/number_of_sets", path); + if (sysfs__read_int(file, (int *) &cache->sets)) + return -1; + + scnprintf(file, PATH_MAX, "%s/ways_of_associativity", path); + if (sysfs__read_int(file, (int *) &cache->ways)) + return -1; + + scnprintf(file, PATH_MAX, "%s/type", path); + if (sysfs__read_str(file, &cache->type, &len)) + return -1; + + cache->type[len] = 0; + cache->type = rtrim(cache->type); + + scnprintf(file, PATH_MAX, "%s/size", path); + if (sysfs__read_str(file, &cache->size, &len)) { + free(cache->type); + return -1; + } + + cache->size[len] = 0; + cache->size = rtrim(cache->size); + + scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path); + if (sysfs__read_str(file, &cache->map, &len)) { + free(cache->map); + free(cache->type); + return -1; + } + + cache->map[len] = 0; + cache->map = rtrim(cache->map); + return 0; +} + +static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) +{ + fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); +} + +static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) +{ + u32 i, cnt = 0; + long ncpus; + u32 nr, cpu; + u16 level; + + ncpus = sysconf(_SC_NPROCESSORS_CONF); + if (ncpus < 0) + return -1; + + nr = (u32)(ncpus & UINT_MAX); + + for (cpu = 0; cpu < nr; cpu++) { + for (level = 0; level < 10; level++) { + struct cpu_cache_level c; + int err; + + err = cpu_cache_level__read(&c, cpu, level); + if (err < 0) + return err; + + if (err == 1) + break; + + for (i = 0; i < cnt; i++) { + if (cpu_cache_level__cmp(&c, &caches[i])) + break; + } + + if (i == cnt) + caches[cnt++] = c; + else + cpu_cache_level__free(&c); + + if (WARN_ONCE(cnt == size, "way too many cpu caches..")) + goto out; + } + } + out: + *cntp = cnt; + return 0; +} + +#define MAX_CACHES 2000 + +static int write_cache(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + struct cpu_cache_level caches[MAX_CACHES]; + u32 cnt = 0, i, version = 1; + int ret; + + ret = build_caches(caches, MAX_CACHES, &cnt); + if (ret) + goto out; + + qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort); + + ret = do_write(fd, &version, sizeof(u32)); + if (ret < 0) + goto out; + + ret = do_write(fd, &cnt, sizeof(u32)); + if (ret < 0) + goto out; + + for (i = 0; i < cnt; i++) { + struct cpu_cache_level *c = &caches[i]; + + #define _W(v) \ + ret = do_write(fd, &c->v, sizeof(u32)); \ + if (ret < 0) \ + goto out; + + _W(level) + _W(line_size) + _W(sets) + _W(ways) + #undef _W + + #define _W(v) \ + ret = do_write_string(fd, (const char *) c->v); \ + if (ret < 0) \ + goto out; + + _W(type) + _W(size) + _W(map) + #undef _W + } + +out: + for (i = 0; i < cnt; i++) + cpu_cache_level__free(&caches[i]); + return ret; +} + static int write_stat(int fd __maybe_unused, struct perf_header *h __maybe_unused, struct perf_evlist *evlist __maybe_unused) @@ -1172,6 +1367,18 @@ static void print_stat(struct perf_header *ph __maybe_unused, fprintf(fp, "# contains stat data\n"); } +static void print_cache(struct perf_header *ph __maybe_unused, + int fd __maybe_unused, FILE *fp __maybe_unused) +{ + int i; + + fprintf(fp, "# CPU cache info:\n"); + for (i = 0; i < ph->env.caches_cnt; i++) { + fprintf(fp, "# "); + cpu_cache_level__fprintf(fp, &ph->env.caches[i]); + } +} + static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { @@ -1920,6 +2127,68 @@ static int process_auxtrace(struct perf_file_section *section, return err; } +static int process_cache(struct perf_file_section *section __maybe_unused, + struct perf_header *ph __maybe_unused, int fd __maybe_unused, + void *data __maybe_unused) +{ + struct cpu_cache_level *caches; + u32 cnt, i, version; + + if (readn(fd, &version, sizeof(version)) != sizeof(version)) + return -1; + + if (ph->needs_swap) + version = bswap_32(version); + + if (version != 1) + return -1; + + if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt)) + return -1; + + if (ph->needs_swap) + cnt = bswap_32(cnt); + + caches = zalloc(sizeof(*caches) * cnt); + if (!caches) + return -1; + + for (i = 0; i < cnt; i++) { + struct cpu_cache_level c; + + #define _R(v) \ + if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\ + goto out_free_caches; \ + if (ph->needs_swap) \ + c.v = bswap_32(c.v); \ + + _R(level) + _R(line_size) + _R(sets) + _R(ways) + #undef _R + + #define _R(v) \ + c.v = do_read_string(fd, ph); \ + if (!c.v) \ + goto out_free_caches; + + _R(type) + _R(size) + _R(map) + #undef _R + + caches[i] = c; + } + + ph->env.caches = caches; + ph->env.caches_cnt = cnt; + return 0; +out_free_caches: + free(caches); + return -1; +} + struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); @@ -1962,6 +2231,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPP(HEADER_GROUP_DESC, group_desc), FEAT_OPP(HEADER_AUXTRACE, auxtrace), FEAT_OPA(HEADER_STAT, stat), + FEAT_OPF(HEADER_CACHE, cache), }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index cff9892452ee3..3d87ca823c0ae 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -32,6 +32,7 @@ enum { HEADER_GROUP_DESC, HEADER_AUXTRACE, HEADER_STAT, + HEADER_CACHE, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index dc1e41c9b054b..43a98a4dc1e1e 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -6,7 +6,8 @@ static int autocorrect; static struct cmdnames aliases; -static int perf_unknown_cmd_config(const char *var, const char *value, void *cb) +static int perf_unknown_cmd_config(const char *var, const char *value, + void *cb __maybe_unused) { if (!strcmp(var, "help.autocorrect")) autocorrect = perf_config_int(var,value); @@ -14,7 +15,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb) if (!prefixcmp(var, "alias.")) add_cmdname(&aliases, var + 6, strlen(var + 6)); - return perf_default_config(var, value, cb); + return 0; } static int levenshtein_compare(const void *p1, const void *p2) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 68a7612019dc3..290b3cbf68772 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -179,6 +179,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->transaction) hists__new_col_len(hists, HISTC_TRANSACTION, hist_entry__transaction_len()); + + if (h->trace_output) + hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output)); } void hists__output_recalc_col_len(struct hists *hists, int max_rows) @@ -245,6 +248,8 @@ static void he_stat__decay(struct he_stat *he_stat) /* XXX need decay for weight too? */ } +static void hists__delete_entry(struct hists *hists, struct hist_entry *he); + static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) { u64 prev_period = he->stat.period; @@ -260,21 +265,45 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) diff = prev_period - he->stat.period; - hists->stats.total_period -= diff; - if (!he->filtered) - hists->stats.total_non_filtered_period -= diff; + if (!he->depth) { + hists->stats.total_period -= diff; + if (!he->filtered) + hists->stats.total_non_filtered_period -= diff; + } + + if (!he->leaf) { + struct hist_entry *child; + struct rb_node *node = rb_first(&he->hroot_out); + while (node) { + child = rb_entry(node, struct hist_entry, rb_node); + node = rb_next(node); + + if (hists__decay_entry(hists, child)) + hists__delete_entry(hists, child); + } + } return he->stat.period == 0; } static void hists__delete_entry(struct hists *hists, struct hist_entry *he) { - rb_erase(&he->rb_node, &hists->entries); + struct rb_root *root_in; + struct rb_root *root_out; - if (sort__need_collapse) - rb_erase(&he->rb_node_in, &hists->entries_collapsed); - else - rb_erase(&he->rb_node_in, hists->entries_in); + if (he->parent_he) { + root_in = &he->parent_he->hroot_in; + root_out = &he->parent_he->hroot_out; + } else { + if (sort__need_collapse) + root_in = &hists->entries_collapsed; + else + root_in = hists->entries_in; + root_out = &hists->entries; + } + + rb_erase(&he->rb_node_in, root_in); + rb_erase(&he->rb_node, root_out); --hists->nr_entries; if (!he->filtered) @@ -393,6 +422,9 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, } INIT_LIST_HEAD(&he->pairs.node); thread__get(he->thread); + + if (!symbol_conf.report_hierarchy) + he->leaf = true; } return he; @@ -405,6 +437,16 @@ static u8 symbol__parent_filter(const struct symbol *parent) return 0; } +static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period) +{ + if (!symbol_conf.use_callchain) + return; + + he->hists->callchain_period += period; + if (!he->filtered) + he->hists->callchain_non_filtered_period += period; +} + static struct hist_entry *hists__findnew_entry(struct hists *hists, struct hist_entry *entry, struct addr_location *al, @@ -432,8 +474,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, cmp = hist_entry__cmp(he, entry); if (!cmp) { - if (sample_self) + if (sample_self) { he_stat__add_period(&he->stat, period, weight); + hist_entry__add_callchain_period(he, period); + } if (symbol_conf.cumulate_callchain) he_stat__add_period(he->stat_acc, period, weight); @@ -466,6 +510,8 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (!he) return NULL; + if (sample_self) + hist_entry__add_callchain_period(he, period); hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); @@ -951,10 +997,15 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { + struct hists *hists = left->hists; struct perf_hpp_fmt *fmt; int64_t cmp = 0; - perf_hpp__for_each_sort_list(fmt) { + hists__for_each_sort_list(hists, fmt) { + if (perf_hpp__is_dynamic_entry(fmt) && + !perf_hpp__defined_dynamic_entry(fmt, hists)) + continue; + cmp = fmt->cmp(fmt, left, right); if (cmp) break; @@ -966,10 +1017,15 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) { + struct hists *hists = left->hists; struct perf_hpp_fmt *fmt; int64_t cmp = 0; - perf_hpp__for_each_sort_list(fmt) { + hists__for_each_sort_list(hists, fmt) { + if (perf_hpp__is_dynamic_entry(fmt) && + !perf_hpp__defined_dynamic_entry(fmt, hists)) + continue; + cmp = fmt->collapse(fmt, left, right); if (cmp) break; @@ -1005,18 +1061,251 @@ void hist_entry__delete(struct hist_entry *he) free(he); } +/* + * If this is not the last column, then we need to pad it according to the + * pre-calculated max lenght for this column, otherwise don't bother adding + * spaces because that would break viewing this with, for instance, 'less', + * that would show tons of trailing spaces when a long C++ demangled method + * names is sampled. +*/ +int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp, + struct perf_hpp_fmt *fmt, int printed) +{ + if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) { + const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists)); + if (printed < width) { + advance_hpp(hpp, printed); + printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " "); + } + } + + return printed; +} + /* * collapse the histogram */ -bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, - struct rb_root *root, struct hist_entry *he) +static void hists__apply_filters(struct hists *hists, struct hist_entry *he); +static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *he, + enum hist_filter type); + +typedef bool (*fmt_chk_fn)(struct perf_hpp_fmt *fmt); + +static bool check_thread_entry(struct perf_hpp_fmt *fmt) +{ + return perf_hpp__is_thread_entry(fmt) || perf_hpp__is_comm_entry(fmt); +} + +static void hist_entry__check_and_remove_filter(struct hist_entry *he, + enum hist_filter type, + fmt_chk_fn check) +{ + struct perf_hpp_fmt *fmt; + bool type_match = false; + struct hist_entry *parent = he->parent_he; + + switch (type) { + case HIST_FILTER__THREAD: + if (symbol_conf.comm_list == NULL && + symbol_conf.pid_list == NULL && + symbol_conf.tid_list == NULL) + return; + break; + case HIST_FILTER__DSO: + if (symbol_conf.dso_list == NULL) + return; + break; + case HIST_FILTER__SYMBOL: + if (symbol_conf.sym_list == NULL) + return; + break; + case HIST_FILTER__PARENT: + case HIST_FILTER__GUEST: + case HIST_FILTER__HOST: + case HIST_FILTER__SOCKET: + default: + return; + } + + /* if it's filtered by own fmt, it has to have filter bits */ + perf_hpp_list__for_each_format(he->hpp_list, fmt) { + if (check(fmt)) { + type_match = true; + break; + } + } + + if (type_match) { + /* + * If the filter is for current level entry, propagate + * filter marker to parents. The marker bit was + * already set by default so it only needs to clear + * non-filtered entries. + */ + if (!(he->filtered & (1 << type))) { + while (parent) { + parent->filtered &= ~(1 << type); + parent = parent->parent_he; + } + } + } else { + /* + * If current entry doesn't have matching formats, set + * filter marker for upper level entries. it will be + * cleared if its lower level entries is not filtered. + * + * For lower-level entries, it inherits parent's + * filter bit so that lower level entries of a + * non-filtered entry won't set the filter marker. + */ + if (parent == NULL) + he->filtered |= (1 << type); + else + he->filtered |= (parent->filtered & (1 << type)); + } +} + +static void hist_entry__apply_hierarchy_filters(struct hist_entry *he) +{ + hist_entry__check_and_remove_filter(he, HIST_FILTER__THREAD, + check_thread_entry); + + hist_entry__check_and_remove_filter(he, HIST_FILTER__DSO, + perf_hpp__is_dso_entry); + + hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL, + perf_hpp__is_sym_entry); + + hists__apply_filters(he->hists, he); +} + +static struct hist_entry *hierarchy_insert_entry(struct hists *hists, + struct rb_root *root, + struct hist_entry *he, + struct hist_entry *parent_he, + struct perf_hpp_list *hpp_list) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter, *new; + struct perf_hpp_fmt *fmt; + int64_t cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node_in); + + cmp = 0; + perf_hpp_list__for_each_sort_list(hpp_list, fmt) { + cmp = fmt->collapse(fmt, iter, he); + if (cmp) + break; + } + + if (!cmp) { + he_stat__add_stat(&iter->stat, &he->stat); + return iter; + } + + if (cmp < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + + new = hist_entry__new(he, true); + if (new == NULL) + return NULL; + + hists->nr_entries++; + + /* save related format list for output */ + new->hpp_list = hpp_list; + new->parent_he = parent_he; + + hist_entry__apply_hierarchy_filters(new); + + /* some fields are now passed to 'new' */ + perf_hpp_list__for_each_sort_list(hpp_list, fmt) { + if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt)) + he->trace_output = NULL; + else + new->trace_output = NULL; + + if (perf_hpp__is_srcline_entry(fmt)) + he->srcline = NULL; + else + new->srcline = NULL; + + if (perf_hpp__is_srcfile_entry(fmt)) + he->srcfile = NULL; + else + new->srcfile = NULL; + } + + rb_link_node(&new->rb_node_in, parent, p); + rb_insert_color(&new->rb_node_in, root); + return new; +} + +static int hists__hierarchy_insert_entry(struct hists *hists, + struct rb_root *root, + struct hist_entry *he) +{ + struct perf_hpp_list_node *node; + struct hist_entry *new_he = NULL; + struct hist_entry *parent = NULL; + int depth = 0; + int ret = 0; + + list_for_each_entry(node, &hists->hpp_formats, list) { + /* skip period (overhead) and elided columns */ + if (node->level == 0 || node->skip) + continue; + + /* insert copy of 'he' for each fmt into the hierarchy */ + new_he = hierarchy_insert_entry(hists, root, he, parent, &node->hpp); + if (new_he == NULL) { + ret = -1; + break; + } + + root = &new_he->hroot_in; + new_he->depth = depth++; + parent = new_he; + } + + if (new_he) { + new_he->leaf = true; + + if (symbol_conf.use_callchain) { + callchain_cursor_reset(&callchain_cursor); + if (callchain_merge(&callchain_cursor, + new_he->callchain, + he->callchain) < 0) + ret = -1; + } + } + + /* 'he' is no longer used */ + hist_entry__delete(he); + + /* return 0 (or -1) since it already applied filters */ + return ret; +} + +int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root, + struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; int64_t cmp; + if (symbol_conf.report_hierarchy) + return hists__hierarchy_insert_entry(hists, root, he); + while (*p != NULL) { parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node_in); @@ -1024,18 +1313,21 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, cmp = hist_entry__collapse(iter, he); if (!cmp) { + int ret = 0; + he_stat__add_stat(&iter->stat, &he->stat); if (symbol_conf.cumulate_callchain) he_stat__add_stat(iter->stat_acc, he->stat_acc); if (symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); - callchain_merge(&callchain_cursor, - iter->callchain, - he->callchain); + if (callchain_merge(&callchain_cursor, + iter->callchain, + he->callchain) < 0) + ret = -1; } hist_entry__delete(he); - return false; + return ret; } if (cmp < 0) @@ -1047,7 +1339,7 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); - return true; + return 1; } struct rb_root *hists__get_rotate_entries_in(struct hists *hists) @@ -1073,14 +1365,15 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he) hists__filter_entry_by_socket(hists, he); } -void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) +int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) { struct rb_root *root; struct rb_node *next; struct hist_entry *n; + int ret; if (!sort__need_collapse) - return; + return 0; hists->nr_entries = 0; @@ -1095,7 +1388,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) next = rb_next(&n->rb_node_in); rb_erase(&n->rb_node_in, root); - if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) { + ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n); + if (ret < 0) + return -1; + + if (ret) { /* * If it wasn't combined with one of the entries already * collapsed, we need to apply the filters that may have @@ -1106,14 +1403,16 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) if (prog) ui_progress__update(prog, 1); } + return 0; } static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { + struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; int64_t cmp = 0; - perf_hpp__for_each_sort_list(fmt) { + hists__for_each_sort_list(hists, fmt) { if (perf_hpp__should_skip(fmt, a->hists)) continue; @@ -1154,6 +1453,113 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h) hists->stats.total_period += h->stat.period; } +static void hierarchy_recalc_total_periods(struct hists *hists) +{ + struct rb_node *node; + struct hist_entry *he; + + node = rb_first(&hists->entries); + + hists->stats.total_period = 0; + hists->stats.total_non_filtered_period = 0; + + /* + * recalculate total period using top-level entries only + * since lower level entries only see non-filtered entries + * but upper level entries have sum of both entries. + */ + while (node) { + he = rb_entry(node, struct hist_entry, rb_node); + node = rb_next(node); + + hists->stats.total_period += he->stat.period; + if (!he->filtered) + hists->stats.total_non_filtered_period += he->stat.period; + } +} + +static void hierarchy_insert_output_entry(struct rb_root *root, + struct hist_entry *he) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + struct perf_hpp_fmt *fmt; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + if (hist_entry__sort(he, iter) > 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, root); + + /* update column width of dynamic entry */ + perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { + if (perf_hpp__is_dynamic_entry(fmt)) + fmt->sort(fmt, he, NULL); + } +} + +static void hists__hierarchy_output_resort(struct hists *hists, + struct ui_progress *prog, + struct rb_root *root_in, + struct rb_root *root_out, + u64 min_callchain_hits, + bool use_callchain) +{ + struct rb_node *node; + struct hist_entry *he; + + *root_out = RB_ROOT; + node = rb_first(root_in); + + while (node) { + he = rb_entry(node, struct hist_entry, rb_node_in); + node = rb_next(node); + + hierarchy_insert_output_entry(root_out, he); + + if (prog) + ui_progress__update(prog, 1); + + if (!he->leaf) { + hists__hierarchy_output_resort(hists, prog, + &he->hroot_in, + &he->hroot_out, + min_callchain_hits, + use_callchain); + hists->nr_entries++; + if (!he->filtered) { + hists->nr_non_filtered_entries++; + hists__calc_col_len(hists, he); + } + + continue; + } + + if (!use_callchain) + continue; + + if (callchain_param.mode == CHAIN_GRAPH_REL) { + u64 total = he->stat.period; + + if (symbol_conf.cumulate_callchain) + total = he->stat_acc->period; + + min_callchain_hits = total * (callchain_param.min_percent / 100); + } + + callchain_param.sort(&he->sorted_chain, he->callchain, + min_callchain_hits, &callchain_param); + } +} + static void __hists__insert_output_entry(struct rb_root *entries, struct hist_entry *he, u64 min_callchain_hits, @@ -1162,10 +1568,20 @@ static void __hists__insert_output_entry(struct rb_root *entries, struct rb_node **p = &entries->rb_node; struct rb_node *parent = NULL; struct hist_entry *iter; + struct perf_hpp_fmt *fmt; + + if (use_callchain) { + if (callchain_param.mode == CHAIN_GRAPH_REL) { + u64 total = he->stat.period; + + if (symbol_conf.cumulate_callchain) + total = he->stat_acc->period; - if (use_callchain) + min_callchain_hits = total * (callchain_param.min_percent / 100); + } callchain_param.sort(&he->sorted_chain, he->callchain, min_callchain_hits, &callchain_param); + } while (*p != NULL) { parent = *p; @@ -1179,23 +1595,41 @@ static void __hists__insert_output_entry(struct rb_root *entries, rb_link_node(&he->rb_node, parent, p); rb_insert_color(&he->rb_node, entries); + + perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) { + if (perf_hpp__is_dynamic_entry(fmt) && + perf_hpp__defined_dynamic_entry(fmt, he->hists)) + fmt->sort(fmt, he, NULL); /* update column width */ + } } -void hists__output_resort(struct hists *hists, struct ui_progress *prog) +static void output_resort(struct hists *hists, struct ui_progress *prog, + bool use_callchain) { struct rb_root *root; struct rb_node *next; struct hist_entry *n; + u64 callchain_total; u64 min_callchain_hits; - struct perf_evsel *evsel = hists_to_evsel(hists); - bool use_callchain; - if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) - use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; - else - use_callchain = symbol_conf.use_callchain; + callchain_total = hists->callchain_period; + if (symbol_conf.filter_relative) + callchain_total = hists->callchain_non_filtered_period; - min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100); + min_callchain_hits = callchain_total * (callchain_param.min_percent / 100); + + hists__reset_stats(hists); + hists__reset_col_len(hists); + + if (symbol_conf.report_hierarchy) { + hists__hierarchy_output_resort(hists, prog, + &hists->entries_collapsed, + &hists->entries, + min_callchain_hits, + use_callchain); + hierarchy_recalc_total_periods(hists); + return; + } if (sort__need_collapse) root = &hists->entries_collapsed; @@ -1205,9 +1639,6 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog) next = rb_first(root); hists->entries = RB_ROOT; - hists__reset_stats(hists); - hists__reset_col_len(hists); - while (next) { n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); @@ -1223,15 +1654,136 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog) } } +void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog) +{ + bool use_callchain; + + if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) + use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; + else + use_callchain = symbol_conf.use_callchain; + + output_resort(evsel__hists(evsel), prog, use_callchain); +} + +void hists__output_resort(struct hists *hists, struct ui_progress *prog) +{ + output_resort(hists, prog, symbol_conf.use_callchain); +} + +static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd) +{ + if (he->leaf || hmd == HMD_FORCE_SIBLING) + return false; + + if (he->unfolded || hmd == HMD_FORCE_CHILD) + return true; + + return false; +} + +struct rb_node *rb_hierarchy_last(struct rb_node *node) +{ + struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node); + + while (can_goto_child(he, HMD_NORMAL)) { + node = rb_last(&he->hroot_out); + he = rb_entry(node, struct hist_entry, rb_node); + } + return node; +} + +struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_dir hmd) +{ + struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node); + + if (can_goto_child(he, hmd)) + node = rb_first(&he->hroot_out); + else + node = rb_next(node); + + while (node == NULL) { + he = he->parent_he; + if (he == NULL) + break; + + node = rb_next(&he->rb_node); + } + return node; +} + +struct rb_node *rb_hierarchy_prev(struct rb_node *node) +{ + struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node); + + node = rb_prev(node); + if (node) + return rb_hierarchy_last(node); + + he = he->parent_he; + if (he == NULL) + return NULL; + + return &he->rb_node; +} + +bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit) +{ + struct rb_node *node; + struct hist_entry *child; + float percent; + + if (he->leaf) + return false; + + node = rb_first(&he->hroot_out); + child = rb_entry(node, struct hist_entry, rb_node); + + while (node && child->filtered) { + node = rb_next(node); + child = rb_entry(node, struct hist_entry, rb_node); + } + + if (node) + percent = hist_entry__get_percent_limit(child); + else + percent = 0; + + return node && percent >= limit; +} + static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h, enum hist_filter filter) { h->filtered &= ~(1 << filter); + + if (symbol_conf.report_hierarchy) { + struct hist_entry *parent = h->parent_he; + + while (parent) { + he_stat__add_stat(&parent->stat, &h->stat); + + parent->filtered &= ~(1 << filter); + + if (parent->filtered) + goto next; + + /* force fold unfiltered entry for simplicity */ + parent->unfolded = false; + parent->has_no_entry = false; + parent->row_offset = 0; + parent->nr_rows = 0; +next: + parent = parent->parent_he; + } + } + if (h->filtered) return; /* force fold unfiltered entry for simplicity */ h->unfolded = false; + h->has_no_entry = false; h->row_offset = 0; h->nr_rows = 0; @@ -1254,28 +1806,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists, return false; } -void hists__filter_by_dso(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (symbol_conf.exclude_other && !h->parent) - continue; - - if (hists__filter_entry_by_dso(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__DSO); - } -} - static bool hists__filter_entry_by_thread(struct hists *hists, struct hist_entry *he) { @@ -1288,25 +1818,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists, return false; } -void hists__filter_by_thread(struct hists *hists) -{ - struct rb_node *nd; - - hists->stats.nr_non_filtered_samples = 0; - - hists__reset_filter_stats(hists); - hists__reset_col_len(hists); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (hists__filter_entry_by_thread(hists, h)) - continue; - - hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD); - } -} - static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he) { @@ -1320,7 +1831,21 @@ static bool hists__filter_entry_by_symbol(struct hists *hists, return false; } -void hists__filter_by_symbol(struct hists *hists) +static bool hists__filter_entry_by_socket(struct hists *hists, + struct hist_entry *he) +{ + if ((hists->socket_filter > -1) && + (he->socket != hists->socket_filter)) { + he->filtered |= (1 << HIST_FILTER__SOCKET); + return true; + } + + return false; +} + +typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he); + +static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter) { struct rb_node *nd; @@ -1332,42 +1857,155 @@ void hists__filter_by_symbol(struct hists *hists) for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (hists__filter_entry_by_symbol(hists, h)) + if (filter(hists, h)) continue; - hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL); + hists__remove_entry_filter(hists, h, type); } } -static bool hists__filter_entry_by_socket(struct hists *hists, - struct hist_entry *he) +static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he) { - if ((hists->socket_filter > -1) && - (he->socket != hists->socket_filter)) { - he->filtered |= (1 << HIST_FILTER__SOCKET); - return true; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + struct rb_root new_root = RB_ROOT; + struct rb_node *nd; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + if (hist_entry__sort(he, iter) > 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; } - return false; + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, root); + + if (he->leaf || he->filtered) + return; + + nd = rb_first(&he->hroot_out); + while (nd) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + nd = rb_next(nd); + rb_erase(&h->rb_node, &he->hroot_out); + + resort_filtered_entry(&new_root, h); + } + + he->hroot_out = new_root; } -void hists__filter_by_socket(struct hists *hists) +static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg) { struct rb_node *nd; + struct rb_root new_root = RB_ROOT; hists->stats.nr_non_filtered_samples = 0; hists__reset_filter_stats(hists); hists__reset_col_len(hists); - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + nd = rb_first(&hists->entries); + while (nd) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + int ret; - if (hists__filter_entry_by_socket(hists, h)) - continue; + ret = hist_entry__filter(h, type, arg); - hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET); + /* + * case 1. non-matching type + * zero out the period, set filter marker and move to child + */ + if (ret < 0) { + memset(&h->stat, 0, sizeof(h->stat)); + h->filtered |= (1 << type); + + nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_CHILD); + } + /* + * case 2. matched type (filter out) + * set filter marker and move to next + */ + else if (ret == 1) { + h->filtered |= (1 << type); + + nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING); + } + /* + * case 3. ok (not filtered) + * add period to hists and parents, erase the filter marker + * and move to next sibling + */ + else { + hists__remove_entry_filter(hists, h, type); + + nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING); + } + } + + hierarchy_recalc_total_periods(hists); + + /* + * resort output after applying a new filter since filter in a lower + * hierarchy can change periods in a upper hierarchy. + */ + nd = rb_first(&hists->entries); + while (nd) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + nd = rb_next(nd); + rb_erase(&h->rb_node, &hists->entries); + + resort_filtered_entry(&new_root, h); } + + hists->entries = new_root; +} + +void hists__filter_by_thread(struct hists *hists) +{ + if (symbol_conf.report_hierarchy) + hists__filter_hierarchy(hists, HIST_FILTER__THREAD, + hists->thread_filter); + else + hists__filter_by_type(hists, HIST_FILTER__THREAD, + hists__filter_entry_by_thread); +} + +void hists__filter_by_dso(struct hists *hists) +{ + if (symbol_conf.report_hierarchy) + hists__filter_hierarchy(hists, HIST_FILTER__DSO, + hists->dso_filter); + else + hists__filter_by_type(hists, HIST_FILTER__DSO, + hists__filter_entry_by_dso); +} + +void hists__filter_by_symbol(struct hists *hists) +{ + if (symbol_conf.report_hierarchy) + hists__filter_hierarchy(hists, HIST_FILTER__SYMBOL, + hists->symbol_filter_str); + else + hists__filter_by_type(hists, HIST_FILTER__SYMBOL, + hists__filter_entry_by_symbol); +} + +void hists__filter_by_socket(struct hists *hists) +{ + if (symbol_conf.report_hierarchy) + hists__filter_hierarchy(hists, HIST_FILTER__SOCKET, + &hists->socket_filter); + else + hists__filter_by_type(hists, HIST_FILTER__SOCKET, + hists__filter_entry_by_socket); } void events_stats__inc(struct events_stats *stats, u32 type) @@ -1585,7 +2223,7 @@ int perf_hist_config(const char *var, const char *value) return 0; } -int __hists__init(struct hists *hists) +int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list) { memset(hists, 0, sizeof(*hists)); hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; @@ -1594,6 +2232,8 @@ int __hists__init(struct hists *hists) hists->entries = RB_ROOT; pthread_mutex_init(&hists->lock, NULL); hists->socket_filter = -1; + hists->hpp_list = hpp_list; + INIT_LIST_HEAD(&hists->hpp_formats); return 0; } @@ -1622,15 +2262,26 @@ static void hists__delete_all_entries(struct hists *hists) static void hists_evsel__exit(struct perf_evsel *evsel) { struct hists *hists = evsel__hists(evsel); + struct perf_hpp_fmt *fmt, *pos; + struct perf_hpp_list_node *node, *tmp; hists__delete_all_entries(hists); + + list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) { + perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) { + list_del(&fmt->list); + free(fmt); + } + list_del(&node->list); + free(node); + } } static int hists_evsel__init(struct perf_evsel *evsel) { struct hists *hists = evsel__hists(evsel); - __hists__init(hists); + __hists__init(hists, &perf_hpp_list); return 0; } @@ -1649,3 +2300,9 @@ int hists__init(void) return err; } + +void perf_hpp_list__init(struct perf_hpp_list *list) +{ + INIT_LIST_HEAD(&list->fields); + INIT_LIST_HEAD(&list->sorts); +} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d4ec4822a1038..ead18c82294fa 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -66,6 +66,8 @@ struct hists { struct rb_root entries_collapsed; u64 nr_entries; u64 nr_non_filtered_entries; + u64 callchain_period; + u64 callchain_non_filtered_period; struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; @@ -75,6 +77,9 @@ struct hists { u64 event_stream; u16 col_len[HISTC_NR_COLS]; int socket_filter; + struct perf_hpp_list *hpp_list; + struct list_head hpp_formats; + int nr_hpp_node; }; struct hist_entry_iter; @@ -121,15 +126,21 @@ struct hist_entry *__hists__add_entry(struct hists *hists, int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int max_stack_depth, void *arg); +struct perf_hpp; +struct perf_hpp_fmt; + int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__transaction_len(void); int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); +int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp, + struct perf_hpp_fmt *fmt, int printed); void hist_entry__delete(struct hist_entry *he); +void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog); void hists__output_resort(struct hists *hists, struct ui_progress *prog); -void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); +int hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); void hists__delete_entries(struct hists *hists); @@ -185,10 +196,10 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) } int hists__init(void); -int __hists__init(struct hists *hists); +int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list); struct rb_root *hists__get_rotate_entries_in(struct hists *hists); -bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, +int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root, struct hist_entry *he); struct perf_hpp { @@ -214,28 +225,64 @@ struct perf_hpp_fmt { struct hist_entry *a, struct hist_entry *b); int64_t (*sort)(struct perf_hpp_fmt *fmt, struct hist_entry *a, struct hist_entry *b); + bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); + void (*free)(struct perf_hpp_fmt *fmt); struct list_head list; struct list_head sort_list; bool elide; int len; int user_len; + int idx; + int level; +}; + +struct perf_hpp_list { + struct list_head fields; + struct list_head sorts; }; -extern struct list_head perf_hpp__list; -extern struct list_head perf_hpp__sort_list; +extern struct perf_hpp_list perf_hpp_list; + +struct perf_hpp_list_node { + struct list_head list; + struct perf_hpp_list hpp; + int level; + bool skip; +}; + +void perf_hpp_list__column_register(struct perf_hpp_list *list, + struct perf_hpp_fmt *format); +void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format); + +static inline void perf_hpp__column_register(struct perf_hpp_fmt *format) +{ + perf_hpp_list__column_register(&perf_hpp_list, format); +} + +static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) +{ + perf_hpp_list__register_sort_field(&perf_hpp_list, format); +} + +#define perf_hpp_list__for_each_format(_list, format) \ + list_for_each_entry(format, &(_list)->fields, list) -#define perf_hpp__for_each_format(format) \ - list_for_each_entry(format, &perf_hpp__list, list) +#define perf_hpp_list__for_each_format_safe(_list, format, tmp) \ + list_for_each_entry_safe(format, tmp, &(_list)->fields, list) -#define perf_hpp__for_each_format_safe(format, tmp) \ - list_for_each_entry_safe(format, tmp, &perf_hpp__list, list) +#define perf_hpp_list__for_each_sort_list(_list, format) \ + list_for_each_entry(format, &(_list)->sorts, sort_list) -#define perf_hpp__for_each_sort_list(format) \ - list_for_each_entry(format, &perf_hpp__sort_list, sort_list) +#define perf_hpp_list__for_each_sort_list_safe(_list, format, tmp) \ + list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list) -#define perf_hpp__for_each_sort_list_safe(format, tmp) \ - list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list) +#define hists__for_each_format(hists, format) \ + perf_hpp_list__for_each_format((hists)->hpp_list, fmt) + +#define hists__for_each_sort_list(hists, format) \ + perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt) extern struct perf_hpp_fmt perf_hpp__format[]; @@ -254,21 +301,29 @@ enum { }; void perf_hpp__init(void); -void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_unregister(struct perf_hpp_fmt *format); -void perf_hpp__column_enable(unsigned col); -void perf_hpp__column_disable(unsigned col); void perf_hpp__cancel_cumulate(void); +void perf_hpp__setup_output_field(struct perf_hpp_list *list); +void perf_hpp__reset_output_field(struct perf_hpp_list *list); +void perf_hpp__append_sort_keys(struct perf_hpp_list *list); +int perf_hpp__setup_hists_formats(struct perf_hpp_list *list, + struct perf_evlist *evlist); -void perf_hpp__register_sort_field(struct perf_hpp_fmt *format); -void perf_hpp__setup_output_field(void); -void perf_hpp__reset_output_field(void); -void perf_hpp__append_sort_keys(void); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); -bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format); bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists); +bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt); + +struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt); + +int hist_entry__filter(struct hist_entry *he, int type, const void *arg); static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format, struct hists *hists) @@ -372,6 +427,7 @@ static inline int script_browse(const char *script_opt __maybe_unused) #endif unsigned int hists__sort_list_width(struct hists *hists); +unsigned int hists__overhead_width(struct hists *hists); void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, struct perf_sample *sample, bool nonany_branch_mode); @@ -381,4 +437,26 @@ int parse_filter_percentage(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused); int perf_hist_config(const char *var, const char *value); +void perf_hpp_list__init(struct perf_hpp_list *list); + +enum hierarchy_move_dir { + HMD_NORMAL, + HMD_FORCE_SIBLING, + HMD_FORCE_CHILD, +}; + +struct rb_node *rb_hierarchy_last(struct rb_node *node); +struct rb_node *__rb_hierarchy_next(struct rb_node *node, + enum hierarchy_move_dir hmd); +struct rb_node *rb_hierarchy_prev(struct rb_node *node); + +static inline struct rb_node *rb_hierarchy_next(struct rb_node *node) +{ + return __rb_hierarchy_next(node, HMD_NORMAL); +} + +#define HIERARCHY_INDENT 3 + +bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit); + #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h new file mode 100644 index 0000000000000..a1e99da0715a5 --- /dev/null +++ b/tools/perf/util/jit.h @@ -0,0 +1,15 @@ +#ifndef __JIT_H__ +#define __JIT_H__ + +#include + +extern int jit_process(struct perf_session *session, + struct perf_data_file *output, + struct machine *machine, + char *filename, + pid_t pid, + u64 *nbytes); + +extern int jit_inject_record(const char *filename); + +#endif /* __JIT_H__ */ diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c new file mode 100644 index 0000000000000..cd272cc21e05b --- /dev/null +++ b/tools/perf/util/jitdump.c @@ -0,0 +1,697 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "util.h" +#include "event.h" +#include "debug.h" +#include "evlist.h" +#include "symbol.h" +#include "strlist.h" +#include + +#include "session.h" +#include "jit.h" +#include "jitdump.h" +#include "genelf.h" +#include "../builtin.h" + +struct jit_buf_desc { + struct perf_data_file *output; + struct perf_session *session; + struct machine *machine; + union jr_entry *entry; + void *buf; + uint64_t sample_type; + size_t bufsize; + FILE *in; + bool needs_bswap; /* handles cross-endianess */ + void *debug_data; + size_t nr_debug_entries; + uint32_t code_load_count; + u64 bytes_written; + struct rb_root code_root; + char dir[PATH_MAX]; +}; + +struct debug_line_info { + unsigned long vma; + unsigned int lineno; + /* The filename format is unspecified, absolute path, relative etc. */ + char const filename[0]; +}; + +struct jit_tool { + struct perf_tool tool; + struct perf_data_file output; + struct perf_data_file input; + u64 bytes_written; +}; + +#define hmax(a, b) ((a) > (b) ? (a) : (b)) +#define get_jit_tool(t) (container_of(tool, struct jit_tool, tool)) + +static int +jit_emit_elf(char *filename, + const char *sym, + uint64_t code_addr, + const void *code, + int csize, + void *debug, + int nr_debug_entries) +{ + int ret, fd; + + if (verbose > 0) + fprintf(stderr, "write ELF image %s\n", filename); + + fd = open(filename, O_CREAT|O_TRUNC|O_WRONLY, 0644); + if (fd == -1) { + pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(errno)); + return -1; + } + + ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries); + + close(fd); + + if (ret) + unlink(filename); + + return ret; +} + +static void +jit_close(struct jit_buf_desc *jd) +{ + if (!(jd && jd->in)) + return; + funlockfile(jd->in); + fclose(jd->in); + jd->in = NULL; +} + +static int +jit_validate_events(struct perf_session *session) +{ + struct perf_evsel *evsel; + + /* + * check that all events use CLOCK_MONOTONIC + */ + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC) + return -1; + } + return 0; +} + +static int +jit_open(struct jit_buf_desc *jd, const char *name) +{ + struct jitheader header; + struct jr_prefix *prefix; + ssize_t bs, bsz = 0; + void *n, *buf = NULL; + int ret, retval = -1; + + jd->in = fopen(name, "r"); + if (!jd->in) + return -1; + + bsz = hmax(sizeof(header), sizeof(*prefix)); + + buf = malloc(bsz); + if (!buf) + goto error; + + /* + * protect from writer modifying the file while we are reading it + */ + flockfile(jd->in); + + ret = fread(buf, sizeof(header), 1, jd->in); + if (ret != 1) + goto error; + + memcpy(&header, buf, sizeof(header)); + + if (header.magic != JITHEADER_MAGIC) { + if (header.magic != JITHEADER_MAGIC_SW) + goto error; + jd->needs_bswap = true; + } + + if (jd->needs_bswap) { + header.version = bswap_32(header.version); + header.total_size = bswap_32(header.total_size); + header.pid = bswap_32(header.pid); + header.elf_mach = bswap_32(header.elf_mach); + header.timestamp = bswap_64(header.timestamp); + header.flags = bswap_64(header.flags); + } + + if (verbose > 2) + pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n", + header.version, + header.total_size, + (unsigned long long)header.timestamp, + header.pid, + header.elf_mach); + + if (header.flags & JITDUMP_FLAGS_RESERVED) { + pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n", + (unsigned long long)header.flags & JITDUMP_FLAGS_RESERVED); + goto error; + } + + /* + * validate event is using the correct clockid + */ + if (jit_validate_events(jd->session)) { + pr_err("error, jitted code must be sampled with perf record -k 1\n"); + goto error; + } + + bs = header.total_size - sizeof(header); + + if (bs > bsz) { + n = realloc(buf, bs); + if (!n) + goto error; + bsz = bs; + buf = n; + /* read extra we do not know about */ + ret = fread(buf, bs - bsz, 1, jd->in); + if (ret != 1) + goto error; + } + /* + * keep dirname for generating files and mmap records + */ + strcpy(jd->dir, name); + dirname(jd->dir); + + return 0; +error: + funlockfile(jd->in); + fclose(jd->in); + return retval; +} + +static union jr_entry * +jit_get_next_entry(struct jit_buf_desc *jd) +{ + struct jr_prefix *prefix; + union jr_entry *jr; + void *addr; + size_t bs, size; + int id, ret; + + if (!(jd && jd->in)) + return NULL; + + if (jd->buf == NULL) { + size_t sz = getpagesize(); + if (sz < sizeof(*prefix)) + sz = sizeof(*prefix); + + jd->buf = malloc(sz); + if (jd->buf == NULL) + return NULL; + + jd->bufsize = sz; + } + + prefix = jd->buf; + + /* + * file is still locked at this point + */ + ret = fread(prefix, sizeof(*prefix), 1, jd->in); + if (ret != 1) + return NULL; + + if (jd->needs_bswap) { + prefix->id = bswap_32(prefix->id); + prefix->total_size = bswap_32(prefix->total_size); + prefix->timestamp = bswap_64(prefix->timestamp); + } + id = prefix->id; + size = prefix->total_size; + + bs = (size_t)size; + if (bs < sizeof(*prefix)) + return NULL; + + if (id >= JIT_CODE_MAX) { + pr_warning("next_entry: unknown prefix %d, skipping\n", id); + return NULL; + } + if (bs > jd->bufsize) { + void *n; + n = realloc(jd->buf, bs); + if (!n) + return NULL; + jd->buf = n; + jd->bufsize = bs; + } + + addr = ((void *)jd->buf) + sizeof(*prefix); + + ret = fread(addr, bs - sizeof(*prefix), 1, jd->in); + if (ret != 1) + return NULL; + + jr = (union jr_entry *)jd->buf; + + switch(id) { + case JIT_CODE_DEBUG_INFO: + if (jd->needs_bswap) { + uint64_t n; + jr->info.code_addr = bswap_64(jr->info.code_addr); + jr->info.nr_entry = bswap_64(jr->info.nr_entry); + for (n = 0 ; n < jr->info.nr_entry; n++) { + jr->info.entries[n].addr = bswap_64(jr->info.entries[n].addr); + jr->info.entries[n].lineno = bswap_32(jr->info.entries[n].lineno); + jr->info.entries[n].discrim = bswap_32(jr->info.entries[n].discrim); + } + } + break; + case JIT_CODE_CLOSE: + break; + case JIT_CODE_LOAD: + if (jd->needs_bswap) { + jr->load.pid = bswap_32(jr->load.pid); + jr->load.tid = bswap_32(jr->load.tid); + jr->load.vma = bswap_64(jr->load.vma); + jr->load.code_addr = bswap_64(jr->load.code_addr); + jr->load.code_size = bswap_64(jr->load.code_size); + jr->load.code_index= bswap_64(jr->load.code_index); + } + jd->code_load_count++; + break; + case JIT_CODE_MOVE: + if (jd->needs_bswap) { + jr->move.pid = bswap_32(jr->move.pid); + jr->move.tid = bswap_32(jr->move.tid); + jr->move.vma = bswap_64(jr->move.vma); + jr->move.old_code_addr = bswap_64(jr->move.old_code_addr); + jr->move.new_code_addr = bswap_64(jr->move.new_code_addr); + jr->move.code_size = bswap_64(jr->move.code_size); + jr->move.code_index = bswap_64(jr->move.code_index); + } + break; + case JIT_CODE_MAX: + default: + return NULL; + } + return jr; +} + +static int +jit_inject_event(struct jit_buf_desc *jd, union perf_event *event) +{ + ssize_t size; + + size = perf_data_file__write(jd->output, event, event->header.size); + if (size < 0) + return -1; + + jd->bytes_written += size; + return 0; +} + +static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) +{ + struct perf_sample sample; + union perf_event *event; + struct perf_tool *tool = jd->session->tool; + uint64_t code, addr; + uintptr_t uaddr; + char *filename; + struct stat st; + size_t size; + u16 idr_size; + const char *sym; + uint32_t count; + int ret, csize; + pid_t pid, tid; + struct { + u32 pid, tid; + u64 time; + } *id; + + pid = jr->load.pid; + tid = jr->load.tid; + csize = jr->load.code_size; + addr = jr->load.code_addr; + sym = (void *)((unsigned long)jr + sizeof(jr->load)); + code = (unsigned long)jr + jr->load.p.total_size - csize; + count = jr->load.code_index; + idr_size = jd->machine->id_hdr_size; + + event = calloc(1, sizeof(*event) + idr_size); + if (!event) + return -1; + + filename = event->mmap2.filename; + size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so", + jd->dir, + pid, + count); + + size++; /* for \0 */ + + size = PERF_ALIGN(size, sizeof(u64)); + uaddr = (uintptr_t)code; + ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries); + + if (jd->debug_data && jd->nr_debug_entries) { + free(jd->debug_data); + jd->debug_data = NULL; + jd->nr_debug_entries = 0; + } + + if (ret) { + free(event); + return -1; + } + if (stat(filename, &st)) + memset(&st, 0, sizeof(stat)); + + event->mmap2.header.type = PERF_RECORD_MMAP2; + event->mmap2.header.misc = PERF_RECORD_MISC_USER; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size) + idr_size); + + event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET; + event->mmap2.start = addr; + event->mmap2.len = csize; + event->mmap2.pid = pid; + event->mmap2.tid = tid; + event->mmap2.ino = st.st_ino; + event->mmap2.maj = major(st.st_dev); + event->mmap2.min = minor(st.st_dev); + event->mmap2.prot = st.st_mode; + event->mmap2.flags = MAP_SHARED; + event->mmap2.ino_generation = 1; + + id = (void *)((unsigned long)event + event->mmap.header.size - idr_size); + if (jd->sample_type & PERF_SAMPLE_TID) { + id->pid = pid; + id->tid = tid; + } + if (jd->sample_type & PERF_SAMPLE_TIME) + id->time = jr->load.p.timestamp; + + /* + * create pseudo sample to induce dso hit increment + * use first address as sample address + */ + memset(&sample, 0, sizeof(sample)); + sample.pid = pid; + sample.tid = tid; + sample.time = id->time; + sample.ip = addr; + + ret = perf_event__process_mmap2(tool, event, &sample, jd->machine); + if (ret) + return ret; + + ret = jit_inject_event(jd, event); + /* + * mark dso as use to generate buildid in the header + */ + if (!ret) + build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine); + + return ret; +} + +static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) +{ + struct perf_sample sample; + union perf_event *event; + struct perf_tool *tool = jd->session->tool; + char *filename; + size_t size; + struct stat st; + u16 idr_size; + int ret; + pid_t pid, tid; + struct { + u32 pid, tid; + u64 time; + } *id; + + pid = jr->move.pid; + tid = jr->move.tid; + idr_size = jd->machine->id_hdr_size; + + /* + * +16 to account for sample_id_all (hack) + */ + event = calloc(1, sizeof(*event) + 16); + if (!event) + return -1; + + filename = event->mmap2.filename; + size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64, + jd->dir, + pid, + jr->move.code_index); + + size++; /* for \0 */ + + if (stat(filename, &st)) + memset(&st, 0, sizeof(stat)); + + size = PERF_ALIGN(size, sizeof(u64)); + + event->mmap2.header.type = PERF_RECORD_MMAP2; + event->mmap2.header.misc = PERF_RECORD_MISC_USER; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size) + idr_size); + event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET; + event->mmap2.start = jr->move.new_code_addr; + event->mmap2.len = jr->move.code_size; + event->mmap2.pid = pid; + event->mmap2.tid = tid; + event->mmap2.ino = st.st_ino; + event->mmap2.maj = major(st.st_dev); + event->mmap2.min = minor(st.st_dev); + event->mmap2.prot = st.st_mode; + event->mmap2.flags = MAP_SHARED; + event->mmap2.ino_generation = 1; + + id = (void *)((unsigned long)event + event->mmap.header.size - idr_size); + if (jd->sample_type & PERF_SAMPLE_TID) { + id->pid = pid; + id->tid = tid; + } + if (jd->sample_type & PERF_SAMPLE_TIME) + id->time = jr->load.p.timestamp; + + /* + * create pseudo sample to induce dso hit increment + * use first address as sample address + */ + memset(&sample, 0, sizeof(sample)); + sample.pid = pid; + sample.tid = tid; + sample.time = id->time; + sample.ip = jr->move.new_code_addr; + + ret = perf_event__process_mmap2(tool, event, &sample, jd->machine); + if (ret) + return ret; + + ret = jit_inject_event(jd, event); + if (!ret) + build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine); + + return ret; +} + +static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr) +{ + void *data; + size_t sz; + + if (!(jd && jr)) + return -1; + + sz = jr->prefix.total_size - sizeof(jr->info); + data = malloc(sz); + if (!data) + return -1; + + memcpy(data, &jr->info.entries, sz); + + jd->debug_data = data; + + /* + * we must use nr_entry instead of size here because + * we cannot distinguish actual entry from padding otherwise + */ + jd->nr_debug_entries = jr->info.nr_entry; + + return 0; +} + +static int +jit_process_dump(struct jit_buf_desc *jd) +{ + union jr_entry *jr; + int ret; + + while ((jr = jit_get_next_entry(jd))) { + switch(jr->prefix.id) { + case JIT_CODE_LOAD: + ret = jit_repipe_code_load(jd, jr); + break; + case JIT_CODE_MOVE: + ret = jit_repipe_code_move(jd, jr); + break; + case JIT_CODE_DEBUG_INFO: + ret = jit_repipe_debug_info(jd, jr); + break; + default: + ret = 0; + continue; + } + } + return ret; +} + +static int +jit_inject(struct jit_buf_desc *jd, char *path) +{ + int ret; + + if (verbose > 0) + fprintf(stderr, "injecting: %s\n", path); + + ret = jit_open(jd, path); + if (ret) + return -1; + + ret = jit_process_dump(jd); + + jit_close(jd); + + if (verbose > 0) + fprintf(stderr, "injected: %s (%d)\n", path, ret); + + return 0; +} + +/* + * File must be with pattern .../jit-XXXX.dump + * where XXXX is the PID of the process which did the mmap() + * as captured in the RECORD_MMAP record + */ +static int +jit_detect(char *mmap_name, pid_t pid) + { + char *p; + char *end = NULL; + pid_t pid2; + + if (verbose > 2) + fprintf(stderr, "jit marker trying : %s\n", mmap_name); + /* + * get file name + */ + p = strrchr(mmap_name, '/'); + if (!p) + return -1; + + /* + * match prefix + */ + if (strncmp(p, "/jit-", 5)) + return -1; + + /* + * skip prefix + */ + p += 5; + + /* + * must be followed by a pid + */ + if (!isdigit(*p)) + return -1; + + pid2 = (int)strtol(p, &end, 10); + if (!end) + return -1; + + /* + * pid does not match mmap pid + * pid==0 in system-wide mode (synthesized) + */ + if (pid && pid2 != pid) + return -1; + /* + * validate suffix + */ + if (strcmp(end, ".dump")) + return -1; + + if (verbose > 0) + fprintf(stderr, "jit marker found: %s\n", mmap_name); + + return 0; +} + +int +jit_process(struct perf_session *session, + struct perf_data_file *output, + struct machine *machine, + char *filename, + pid_t pid, + u64 *nbytes) +{ + struct perf_evsel *first; + struct jit_buf_desc jd; + int ret; + + /* + * first, detect marker mmap (i.e., the jitdump mmap) + */ + if (jit_detect(filename, pid)) + return 0; + + memset(&jd, 0, sizeof(jd)); + + jd.session = session; + jd.output = output; + jd.machine = machine; + + /* + * track sample_type to compute id_all layout + * perf sets the same sample type to all events as of now + */ + first = perf_evlist__first(session->evlist); + jd.sample_type = first->attr.sample_type; + + *nbytes = 0; + + ret = jit_inject(&jd, filename); + if (!ret) { + *nbytes = jd.bytes_written; + ret = 1; + } + + return ret; +} diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h new file mode 100644 index 0000000000000..b66c1f503d9ed --- /dev/null +++ b/tools/perf/util/jitdump.h @@ -0,0 +1,124 @@ +/* + * jitdump.h: jitted code info encapsulation file format + * + * Adapted from OProfile GPLv2 support jidump.h: + * Copyright 2007 OProfile authors + * Jens Wilke + * Daniel Hansel + * Copyright IBM Corporation 2007 + */ +#ifndef JITDUMP_H +#define JITDUMP_H + +#include +#include +#include + +/* JiTD */ +#define JITHEADER_MAGIC 0x4A695444 +#define JITHEADER_MAGIC_SW 0x4454694A + +#define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7) + +#define JITHEADER_VERSION 1 + +enum jitdump_flags_bits { + JITDUMP_FLAGS_MAX_BIT, +}; + +#define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \ + (~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0) + +struct jitheader { + uint32_t magic; /* characters "jItD" */ + uint32_t version; /* header version */ + uint32_t total_size; /* total size of header */ + uint32_t elf_mach; /* elf mach target */ + uint32_t pad1; /* reserved */ + uint32_t pid; /* JIT process id */ + uint64_t timestamp; /* timestamp */ + uint64_t flags; /* flags */ +}; + +enum jit_record_type { + JIT_CODE_LOAD = 0, + JIT_CODE_MOVE = 1, + JIT_CODE_DEBUG_INFO = 2, + JIT_CODE_CLOSE = 3, + + JIT_CODE_MAX, +}; + +/* record prefix (mandatory in each record) */ +struct jr_prefix { + uint32_t id; + uint32_t total_size; + uint64_t timestamp; +}; + +struct jr_code_load { + struct jr_prefix p; + + uint32_t pid; + uint32_t tid; + uint64_t vma; + uint64_t code_addr; + uint64_t code_size; + uint64_t code_index; +}; + +struct jr_code_close { + struct jr_prefix p; +}; + +struct jr_code_move { + struct jr_prefix p; + + uint32_t pid; + uint32_t tid; + uint64_t vma; + uint64_t old_code_addr; + uint64_t new_code_addr; + uint64_t code_size; + uint64_t code_index; +}; + +struct debug_entry { + uint64_t addr; + int lineno; /* source line number starting at 1 */ + int discrim; /* column discriminator, 0 is default */ + const char name[0]; /* null terminated filename, \xff\0 if same as previous entry */ +}; + +struct jr_code_debug_info { + struct jr_prefix p; + + uint64_t code_addr; + uint64_t nr_entry; + struct debug_entry entries[0]; +}; + +union jr_entry { + struct jr_code_debug_info info; + struct jr_code_close close; + struct jr_code_load load; + struct jr_code_move move; + struct jr_prefix prefix; +}; + +static inline struct debug_entry * +debug_entry_next(struct debug_entry *ent) +{ + void *a = ent + 1; + size_t l = strlen(ent->name) + 1; + return a + l; +} + +static inline char * +debug_entry_file(struct debug_entry *ent) +{ + void *a = ent + 1; + return a; +} + +#endif /* !JITDUMP_H */ diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index ae825d4ec110f..d01e73592f6e3 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm, bool kvm_exit_event(struct perf_evsel *evsel); bool kvm_entry_event(struct perf_evsel *evsel); +int setup_kvm_events_tp(struct perf_kvm_stat *kvm); #define define_exit_reasons_table(name, symbols) \ static struct exit_reasons_table name[] = { \ @@ -133,8 +134,13 @@ bool kvm_entry_event(struct perf_evsel *evsel); */ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid); -extern const char * const kvm_events_tp[]; +extern const char *kvm_events_tp[]; extern struct kvm_reg_events_ops kvm_reg_events_ops[]; extern const char * const kvm_skip_events[]; +extern const char *vcpu_id_str; +extern const int decode_str_len; +extern const char *kvm_exit_reason; +extern const char *kvm_entry_trace; +extern const char *kvm_exit_trace; #endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 2c2b443df5ba7..1a3e45baf97fb 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -179,6 +179,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine, mapp, filter); } +static inline +struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, + enum map_type type, const char *name, + struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_symbol_by_name(&machine->kmaps, type, name, + mapp, filter); +} + static inline struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, struct map **mapp, diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c new file mode 100644 index 0000000000000..75465f89a4131 --- /dev/null +++ b/tools/perf/util/mem-events.c @@ -0,0 +1,255 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include "mem-events.h" +#include "debug.h" +#include "symbol.h" + +#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } + +struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { + E("ldlat-loads", "cpu/mem-loads,ldlat=30/P", "mem-loads"), + E("ldlat-stores", "cpu/mem-stores/P", "mem-stores"), +}; +#undef E + +#undef E + +char *perf_mem_events__name(int i) +{ + return (char *)perf_mem_events[i].name; +} + +int perf_mem_events__parse(const char *str) +{ + char *tok, *saveptr = NULL; + bool found = false; + char *buf; + int j; + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(str) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, str); + + tok = strtok_r((char *)buf, ",", &saveptr); + + while (tok) { + for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { + struct perf_mem_event *e = &perf_mem_events[j]; + + if (strstr(e->tag, tok)) + e->record = found = true; + } + + tok = strtok_r(NULL, ",", &saveptr); + } + + free(buf); + + if (found) + return 0; + + pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str); + return -1; +} + +int perf_mem_events__init(void) +{ + const char *mnt = sysfs__mount(); + bool found = false; + int j; + + if (!mnt) + return -ENOENT; + + for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { + char path[PATH_MAX]; + struct perf_mem_event *e = &perf_mem_events[j]; + struct stat st; + + scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s", + mnt, e->sysfs_name); + + if (!stat(path, &st)) + e->supported = found = true; + } + + return found ? 0 : -ENOENT; +} + +static const char * const tlb_access[] = { + "N/A", + "HIT", + "MISS", + "L1", + "L2", + "Walker", + "Fault", +}; + +int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info) +{ + size_t l = 0, i; + u64 m = PERF_MEM_TLB_NA; + u64 hit, miss; + + sz -= 1; /* -1 for null termination */ + out[0] = '\0'; + + if (mem_info) + m = mem_info->data_src.mem_dtlb; + + hit = m & PERF_MEM_TLB_HIT; + miss = m & PERF_MEM_TLB_MISS; + + /* already taken care of */ + m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS); + + for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + l += scnprintf(out + l, sz - l, tlb_access[i]); + } + if (*out == '\0') + l += scnprintf(out, sz - l, "N/A"); + if (hit) + l += scnprintf(out + l, sz - l, " hit"); + if (miss) + l += scnprintf(out + l, sz - l, " miss"); + + return l; +} + +static const char * const mem_lvl[] = { + "N/A", + "HIT", + "MISS", + "L1", + "LFB", + "L2", + "L3", + "Local RAM", + "Remote RAM (1 hop)", + "Remote RAM (2 hops)", + "Remote Cache (1 hop)", + "Remote Cache (2 hops)", + "I/O", + "Uncached", +}; + +int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) +{ + size_t i, l = 0; + u64 m = PERF_MEM_LVL_NA; + u64 hit, miss; + + if (mem_info) + m = mem_info->data_src.mem_lvl; + + sz -= 1; /* -1 for null termination */ + out[0] = '\0'; + + hit = m & PERF_MEM_LVL_HIT; + miss = m & PERF_MEM_LVL_MISS; + + /* already taken care of */ + m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); + + for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + l += scnprintf(out + l, sz - l, mem_lvl[i]); + } + if (*out == '\0') + l += scnprintf(out, sz - l, "N/A"); + if (hit) + l += scnprintf(out + l, sz - l, " hit"); + if (miss) + l += scnprintf(out + l, sz - l, " miss"); + + return l; +} + +static const char * const snoop_access[] = { + "N/A", + "None", + "Miss", + "Hit", + "HitM", +}; + +int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info) +{ + size_t i, l = 0; + u64 m = PERF_MEM_SNOOP_NA; + + sz -= 1; /* -1 for null termination */ + out[0] = '\0'; + + if (mem_info) + m = mem_info->data_src.mem_snoop; + + for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + l += scnprintf(out + l, sz - l, snoop_access[i]); + } + + if (*out == '\0') + l += scnprintf(out, sz - l, "N/A"); + + return l; +} + +int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info) +{ + u64 mask = PERF_MEM_LOCK_NA; + int l; + + if (mem_info) + mask = mem_info->data_src.mem_lock; + + if (mask & PERF_MEM_LOCK_NA) + l = scnprintf(out, sz, "N/A"); + else if (mask & PERF_MEM_LOCK_LOCKED) + l = scnprintf(out, sz, "Yes"); + else + l = scnprintf(out, sz, "No"); + + return l; +} + +int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info) +{ + int i = 0; + + i += perf_mem__lvl_scnprintf(out, sz, mem_info); + i += scnprintf(out + i, sz - i, "|SNP "); + i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info); + i += scnprintf(out + i, sz - i, "|TLB "); + i += perf_mem__tlb_scnprintf(out + i, sz - i, mem_info); + i += scnprintf(out + i, sz - i, "|LCK "); + i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info); + + return i; +} diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h new file mode 100644 index 0000000000000..5d6d93066a6e8 --- /dev/null +++ b/tools/perf/util/mem-events.h @@ -0,0 +1,35 @@ +#ifndef __PERF_MEM_EVENTS_H +#define __PERF_MEM_EVENTS_H + +#include + +struct perf_mem_event { + bool record; + bool supported; + const char *tag; + const char *name; + const char *sysfs_name; +}; + +enum { + PERF_MEM_EVENTS__LOAD, + PERF_MEM_EVENTS__STORE, + PERF_MEM_EVENTS__MAX, +}; + +extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX]; + +int perf_mem_events__parse(const char *str); +int perf_mem_events__init(void); + +char *perf_mem_events__name(int i); + +struct mem_info; +int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info); +int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info); +int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info); +int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info); + +int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info); + +#endif /* __PERF_MEM_EVENTS_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 813d9b272c813..4c19d5e79d8c4 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -279,7 +279,24 @@ const char *event_type(int type) return "unknown"; } +static int parse_events__is_name_term(struct parse_events_term *term) +{ + return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; +} +static char *get_config_name(struct list_head *head_terms) +{ + struct parse_events_term *term; + + if (!head_terms) + return NULL; + + list_for_each_entry(term, head_terms, list) + if (parse_events__is_name_term(term)) + return term->val.str; + + return NULL; +} static struct perf_evsel * __add_event(struct list_head *list, int *idx, @@ -333,11 +350,25 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES] return -1; } +typedef int config_term_func_t(struct perf_event_attr *attr, + struct parse_events_term *term, + struct parse_events_error *err); +static int config_term_common(struct perf_event_attr *attr, + struct parse_events_term *term, + struct parse_events_error *err); +static int config_attr(struct perf_event_attr *attr, + struct list_head *head, + struct parse_events_error *err, + config_term_func_t config_term); + int parse_events_add_cache(struct list_head *list, int *idx, - char *type, char *op_result1, char *op_result2) + char *type, char *op_result1, char *op_result2, + struct parse_events_error *err, + struct list_head *head_config) { struct perf_event_attr attr; - char name[MAX_NAME_LEN]; + LIST_HEAD(config_terms); + char name[MAX_NAME_LEN], *config_name; int cache_type = -1, cache_op = -1, cache_result = -1; char *op_result[2] = { op_result1, op_result2 }; int i, n; @@ -351,6 +382,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, if (cache_type == -1) return -EINVAL; + config_name = get_config_name(head_config); n = snprintf(name, MAX_NAME_LEN, "%s", type); for (i = 0; (i < 2) && (op_result[i]); i++) { @@ -391,7 +423,16 @@ int parse_events_add_cache(struct list_head *list, int *idx, memset(&attr, 0, sizeof(attr)); attr.config = cache_type | (cache_op << 8) | (cache_result << 16); attr.type = PERF_TYPE_HW_CACHE; - return add_event(list, idx, &attr, name, NULL); + + if (head_config) { + if (config_attr(&attr, head_config, err, + config_term_common)) + return -EINVAL; + + if (get_config_terms(head_config, &config_terms)) + return -ENOMEM; + } + return add_event(list, idx, &attr, config_name ? : name, &config_terms); } static void tracepoint_error(struct parse_events_error *e, int err, @@ -540,6 +581,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, struct __add_bpf_event_param { struct parse_events_evlist *data; struct list_head *list; + struct list_head *head_config; }; static int add_bpf_event(struct probe_trace_event *tev, int fd, @@ -556,7 +598,8 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd, tev->group, tev->event, fd); err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group, - tev->event, evlist->error, NULL); + tev->event, evlist->error, + param->head_config); if (err) { struct perf_evsel *evsel, *tmp; @@ -581,11 +624,12 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd, int parse_events_load_bpf_obj(struct parse_events_evlist *data, struct list_head *list, - struct bpf_object *obj) + struct bpf_object *obj, + struct list_head *head_config) { int err; char errbuf[BUFSIZ]; - struct __add_bpf_event_param param = {data, list}; + struct __add_bpf_event_param param = {data, list, head_config}; static bool registered_unprobe_atexit = false; if (IS_ERR(obj) || !obj) { @@ -631,17 +675,99 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data, return err; } +static int +parse_events_config_bpf(struct parse_events_evlist *data, + struct bpf_object *obj, + struct list_head *head_config) +{ + struct parse_events_term *term; + int error_pos; + + if (!head_config || list_empty(head_config)) + return 0; + + list_for_each_entry(term, head_config, list) { + char errbuf[BUFSIZ]; + int err; + + if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) { + snprintf(errbuf, sizeof(errbuf), + "Invalid config term for BPF object"); + errbuf[BUFSIZ - 1] = '\0'; + + data->error->idx = term->err_term; + data->error->str = strdup(errbuf); + return -EINVAL; + } + + err = bpf__config_obj(obj, term, data->evlist, &error_pos); + if (err) { + bpf__strerror_config_obj(obj, term, data->evlist, + &error_pos, err, errbuf, + sizeof(errbuf)); + data->error->help = strdup( +"Hint:\tValid config terms:\n" +" \tmap:[].value=[value]\n" +" \tmap:[].event=[event]\n" +"\n" +" \twhere is something like [0,3...5] or [all]\n" +" \t(add -v to see detail)"); + data->error->str = strdup(errbuf); + if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE) + data->error->idx = term->err_val; + else + data->error->idx = term->err_term + error_pos; + return err; + } + } + return 0; +} + +/* + * Split config terms: + * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ... + * 'call-graph=fp' is 'evt config', should be applied to each + * events in bpf.c. + * 'map:array.value[0]=1' is 'obj config', should be processed + * with parse_events_config_bpf. + * + * Move object config terms from the first list to obj_head_config. + */ +static void +split_bpf_config_terms(struct list_head *evt_head_config, + struct list_head *obj_head_config) +{ + struct parse_events_term *term, *temp; + + /* + * Currectly, all possible user config term + * belong to bpf object. parse_events__is_hardcoded_term() + * happends to be a good flag. + * + * See parse_events_config_bpf() and + * config_term_tracepoint(). + */ + list_for_each_entry_safe(term, temp, evt_head_config, list) + if (!parse_events__is_hardcoded_term(term)) + list_move_tail(&term->list, obj_head_config); +} + int parse_events_load_bpf(struct parse_events_evlist *data, struct list_head *list, char *bpf_file_name, - bool source) + bool source, + struct list_head *head_config) { + int err; struct bpf_object *obj; + LIST_HEAD(obj_head_config); + + if (head_config) + split_bpf_config_terms(head_config, &obj_head_config); obj = bpf__prepare_load(bpf_file_name, source); if (IS_ERR(obj)) { char errbuf[BUFSIZ]; - int err; err = PTR_ERR(obj); @@ -659,7 +785,18 @@ int parse_events_load_bpf(struct parse_events_evlist *data, return err; } - return parse_events_load_bpf_obj(data, list, obj); + err = parse_events_load_bpf_obj(data, list, obj, head_config); + if (err) + return err; + err = parse_events_config_bpf(data, obj, &obj_head_config); + + /* + * Caller doesn't know anything about obj_head_config, + * so combine them together again before returnning. + */ + if (head_config) + list_splice_tail(&obj_head_config, head_config); + return err; } static int @@ -746,9 +883,59 @@ static int check_type_val(struct parse_events_term *term, return -EINVAL; } -typedef int config_term_func_t(struct perf_event_attr *attr, - struct parse_events_term *term, - struct parse_events_error *err); +/* + * Update according to parse-events.l + */ +static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { + [PARSE_EVENTS__TERM_TYPE_USER] = "", + [PARSE_EVENTS__TERM_TYPE_CONFIG] = "config", + [PARSE_EVENTS__TERM_TYPE_CONFIG1] = "config1", + [PARSE_EVENTS__TERM_TYPE_CONFIG2] = "config2", + [PARSE_EVENTS__TERM_TYPE_NAME] = "name", + [PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD] = "period", + [PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ] = "freq", + [PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE] = "branch_type", + [PARSE_EVENTS__TERM_TYPE_TIME] = "time", + [PARSE_EVENTS__TERM_TYPE_CALLGRAPH] = "call-graph", + [PARSE_EVENTS__TERM_TYPE_STACKSIZE] = "stack-size", + [PARSE_EVENTS__TERM_TYPE_NOINHERIT] = "no-inherit", + [PARSE_EVENTS__TERM_TYPE_INHERIT] = "inherit", +}; + +static bool config_term_shrinked; + +static bool +config_term_avail(int term_type, struct parse_events_error *err) +{ + if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) { + err->str = strdup("Invalid term_type"); + return false; + } + if (!config_term_shrinked) + return true; + + switch (term_type) { + case PARSE_EVENTS__TERM_TYPE_CONFIG: + case PARSE_EVENTS__TERM_TYPE_CONFIG1: + case PARSE_EVENTS__TERM_TYPE_CONFIG2: + case PARSE_EVENTS__TERM_TYPE_NAME: + return true; + default: + if (!err) + return false; + + /* term_type is validated so indexing is safe */ + if (asprintf(&err->str, "'%s' is not usable in 'perf stat'", + config_term_names[term_type]) < 0) + err->str = NULL; + return false; + } +} + +void parse_events__shrink_config_terms(void) +{ + config_term_shrinked = true; +} static int config_term_common(struct perf_event_attr *attr, struct parse_events_term *term, @@ -815,6 +1002,17 @@ do { \ return -EINVAL; } + /* + * Check term availbility after basic checking so + * PARSE_EVENTS__TERM_TYPE_USER can be found and filtered. + * + * If check availbility at the entry of this function, + * user will see "'' is not usable in 'perf stat'" + * if an invalid config term is provided for legacy events + * (for example, instructions/badterm/...), which is confusing. + */ + if (!config_term_avail(term->type_term, err)) + return -EINVAL; return 0; #undef CHECK_TYPE_VAL } @@ -961,23 +1159,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data, return -ENOMEM; } - return add_event(list, &data->idx, &attr, NULL, &config_terms); -} - -static int parse_events__is_name_term(struct parse_events_term *term) -{ - return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; -} - -static char *pmu_event_name(struct list_head *head_terms) -{ - struct parse_events_term *term; - - list_for_each_entry(term, head_terms, list) - if (parse_events__is_name_term(term)) - return term->val.str; - - return NULL; + return add_event(list, &data->idx, &attr, + get_config_name(head_config), &config_terms); } int parse_events_add_pmu(struct parse_events_evlist *data, @@ -1024,7 +1207,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data, return -EINVAL; evsel = __add_event(list, &data->idx, &attr, - pmu_event_name(head_config), pmu->cpus, + get_config_name(head_config), pmu->cpus, &config_terms); if (evsel) { evsel->unit = info.unit; @@ -1386,8 +1569,7 @@ int parse_events_terms(struct list_head *terms, const char *str) return 0; } - if (data.terms) - parse_events__free_terms(data.terms); + parse_events_terms__delete(data.terms); return ret; } @@ -1395,9 +1577,10 @@ int parse_events(struct perf_evlist *evlist, const char *str, struct parse_events_error *err) { struct parse_events_evlist data = { - .list = LIST_HEAD_INIT(data.list), - .idx = evlist->nr_entries, - .error = err, + .list = LIST_HEAD_INIT(data.list), + .idx = evlist->nr_entries, + .error = err, + .evlist = evlist, }; int ret; @@ -2068,12 +2251,29 @@ int parse_events_term__clone(struct parse_events_term **new, term->err_term, term->err_val); } -void parse_events__free_terms(struct list_head *terms) +void parse_events_terms__purge(struct list_head *terms) { struct parse_events_term *term, *h; - list_for_each_entry_safe(term, h, terms, list) + list_for_each_entry_safe(term, h, terms, list) { + if (term->array.nr_ranges) + free(term->array.ranges); + list_del_init(&term->list); free(term); + } +} + +void parse_events_terms__delete(struct list_head *terms) +{ + if (!terms) + return; + parse_events_terms__purge(terms); + free(terms); +} + +void parse_events__clear_array(struct parse_events_array *a) +{ + free(a->ranges); } void parse_events_evlist_error(struct parse_events_evlist *data, @@ -2088,6 +2288,33 @@ void parse_events_evlist_error(struct parse_events_evlist *data, WARN_ONCE(!err->str, "WARNING: failed to allocate error string"); } +static void config_terms_list(char *buf, size_t buf_sz) +{ + int i; + bool first = true; + + buf[0] = '\0'; + for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) { + const char *name = config_term_names[i]; + + if (!config_term_avail(i, NULL)) + continue; + if (!name) + continue; + if (name[0] == '<') + continue; + + if (strlen(buf) + strlen(name) + 2 >= buf_sz) + return; + + if (!first) + strcat(buf, ","); + else + first = false; + strcat(buf, name); + } +} + /* * Return string contains valid config terms of an event. * @additional_terms: For terms such as PMU sysfs terms. @@ -2095,17 +2322,18 @@ void parse_events_evlist_error(struct parse_events_evlist *data, char *parse_events_formats_error_string(char *additional_terms) { char *str; - static const char *static_terms = "config,config1,config2,name," - "period,freq,branch_type,time," - "call-graph,stack-size\n"; + /* "branch_type" is the longest name */ + char static_terms[__PARSE_EVENTS__TERM_TYPE_NR * + (sizeof("branch_type") - 1)]; + config_terms_list(static_terms, sizeof(static_terms)); /* valid terms */ if (additional_terms) { - if (!asprintf(&str, "valid terms: %s,%s", - additional_terms, static_terms)) + if (asprintf(&str, "valid terms: %s,%s", + additional_terms, static_terms) < 0) goto fail; } else { - if (!asprintf(&str, "valid terms: %s", static_terms)) + if (asprintf(&str, "valid terms: %s", static_terms) < 0) goto fail; } return str; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index f1a6db107241b..67e493088e81c 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -68,11 +68,21 @@ enum { PARSE_EVENTS__TERM_TYPE_CALLGRAPH, PARSE_EVENTS__TERM_TYPE_STACKSIZE, PARSE_EVENTS__TERM_TYPE_NOINHERIT, - PARSE_EVENTS__TERM_TYPE_INHERIT + PARSE_EVENTS__TERM_TYPE_INHERIT, + __PARSE_EVENTS__TERM_TYPE_NR, +}; + +struct parse_events_array { + size_t nr_ranges; + struct { + unsigned int start; + size_t length; + } *ranges; }; struct parse_events_term { char *config; + struct parse_events_array array; union { char *str; u64 num; @@ -98,12 +108,14 @@ struct parse_events_evlist { int idx; int nr_groups; struct parse_events_error *error; + struct perf_evlist *evlist; }; struct parse_events_terms { struct list_head *terms; }; +void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, int type_term, char *config, u64 num, @@ -115,7 +127,9 @@ int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx); int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term); -void parse_events__free_terms(struct list_head *terms); +void parse_events_terms__delete(struct list_head *terms); +void parse_events_terms__purge(struct list_head *terms); +void parse_events__clear_array(struct parse_events_array *a); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); int parse_events_name(struct list_head *list, char *name); @@ -126,18 +140,22 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, int parse_events_load_bpf(struct parse_events_evlist *data, struct list_head *list, char *bpf_file_name, - bool source); + bool source, + struct list_head *head_config); /* Provide this function for perf test */ struct bpf_object; int parse_events_load_bpf_obj(struct parse_events_evlist *data, struct list_head *list, - struct bpf_object *obj); + struct bpf_object *obj, + struct list_head *head_config); int parse_events_add_numeric(struct parse_events_evlist *data, struct list_head *list, u32 type, u64 config, struct list_head *head_config); int parse_events_add_cache(struct list_head *list, int *idx, - char *type, char *op_result1, char *op_result2); + char *type, char *op_result1, char *op_result2, + struct parse_events_error *error, + struct list_head *head_config); int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_evlist *data, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 58c5831ffd5c2..1477fbc78993c 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -9,8 +9,8 @@ %{ #include #include "../perf.h" -#include "parse-events-bison.h" #include "parse-events.h" +#include "parse-events-bison.h" char *parse_events_get_text(yyscan_t yyscanner); YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); @@ -111,6 +111,7 @@ do { \ %x mem %s config %x event +%x array group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* @@ -122,7 +123,7 @@ num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?.]* -name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.]* +name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* /* If you add a modifier you need to update check_modifier() */ modifier_event [ukhpPGHSDI]+ modifier_bp [rwx]{1,3} @@ -176,10 +177,17 @@ modifier_bp [rwx]{1,3} } +{ +"]" { BEGIN(config); return ']'; } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } +, { return ','; } +"\.\.\." { return PE_ARRAY_RANGE; } +} + { /* - * Please update parse_events_formats_error_string any time - * new static term is added. + * Please update config_term_names when new static term is added. */ config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } @@ -196,6 +204,8 @@ no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } +\[all\] { return PE_ARRAY_ALL; } +"[" { BEGIN(array); return '['; } } { @@ -238,6 +248,7 @@ cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } +bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } /* * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately. diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index ad379968d4c10..5be4a5f216d6d 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -28,7 +28,7 @@ do { \ INIT_LIST_HEAD(list); \ } while (0) -static inc_group_count(struct list_head *list, +static void inc_group_count(struct list_head *list, struct parse_events_evlist *data) { /* Count groups only have more than 1 members */ @@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list, %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP %token PE_ERROR %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT +%token PE_ARRAY_ALL PE_ARRAY_RANGE %type PE_VALUE %type PE_VALUE_SYM_HW %type PE_VALUE_SYM_SW @@ -64,6 +65,7 @@ static inc_group_count(struct list_head *list, %type PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT %type value_sym %type event_config +%type opt_event_config %type event_term %type event_pmu %type event_legacy_symbol @@ -82,6 +84,9 @@ static inc_group_count(struct list_head *list, %type group_def %type group %type groups +%type array +%type array_term +%type array_terms %union { @@ -93,6 +98,7 @@ static inc_group_count(struct list_head *list, char *sys; char *event; } tracepoint_name; + struct parse_events_array array; } %% @@ -211,24 +217,14 @@ event_def: event_pmu | event_bpf_file event_pmu: -PE_NAME '/' event_config '/' +PE_NAME opt_event_config { struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, $1, $3)); - parse_events__free_terms($3); - $$ = list; -} -| -PE_NAME '/' '/' -{ - struct parse_events_evlist *data = _data; - struct list_head *list; - - ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, $1, NULL)); + ABORT_ON(parse_events_add_pmu(data, list, $1, $2)); + parse_events_terms__delete($2); $$ = list; } | @@ -246,7 +242,7 @@ PE_KERNEL_PMU_EVENT sep_dc ALLOC_LIST(list); ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); - parse_events__free_terms(head); + parse_events_terms__delete(head); $$ = list; } | @@ -266,7 +262,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc ALLOC_LIST(list); ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); - parse_events__free_terms(head); + parse_events_terms__delete(head); $$ = list; } @@ -285,7 +281,7 @@ value_sym '/' event_config '/' ALLOC_LIST(list); ABORT_ON(parse_events_add_numeric(data, list, type, config, $3)); - parse_events__free_terms($3); + parse_events_terms__delete($3); $$ = list; } | @@ -302,33 +298,39 @@ value_sym sep_slash_dc } event_legacy_cache: -PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT +PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config { struct parse_events_evlist *data = _data; + struct parse_events_error *error = data->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5)); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6)); + parse_events_terms__delete($6); $$ = list; } | -PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT +PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config { struct parse_events_evlist *data = _data; + struct parse_events_error *error = data->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL)); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4)); + parse_events_terms__delete($4); $$ = list; } | -PE_NAME_CACHE_TYPE +PE_NAME_CACHE_TYPE opt_event_config { struct parse_events_evlist *data = _data; + struct parse_events_error *error = data->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL)); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2)); + parse_events_terms__delete($2); $$ = list; } @@ -378,24 +380,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc } event_legacy_tracepoint: -tracepoint_name -{ - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; - struct list_head *list; - - ALLOC_LIST(list); - if (error) - error->idx = @1.first_column; - - if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event, - error, NULL)) - return -1; - - $$ = list; -} -| -tracepoint_name '/' event_config '/' +tracepoint_name opt_event_config { struct parse_events_evlist *data = _data; struct parse_events_error *error = data->error; @@ -406,7 +391,7 @@ tracepoint_name '/' event_config '/' error->idx = @1.first_column; if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event, - error, $3)) + error, $2)) return -1; $$ = list; @@ -433,49 +418,68 @@ PE_NAME ':' PE_NAME } event_legacy_numeric: -PE_VALUE ':' PE_VALUE +PE_VALUE ':' PE_VALUE opt_event_config { struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL)); + ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4)); + parse_events_terms__delete($4); $$ = list; } event_legacy_raw: -PE_RAW +PE_RAW opt_event_config { struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL)); + ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2)); + parse_events_terms__delete($2); $$ = list; } event_bpf_file: -PE_BPF_OBJECT +PE_BPF_OBJECT opt_event_config { struct parse_events_evlist *data = _data; struct parse_events_error *error = data->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(data, list, $1, false)); + ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2)); + parse_events_terms__delete($2); $$ = list; } | -PE_BPF_SOURCE +PE_BPF_SOURCE opt_event_config { struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(data, list, $1, true)); + ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2)); + parse_events_terms__delete($2); $$ = list; } +opt_event_config: +'/' event_config '/' +{ + $$ = $2; +} +| +'/' '/' +{ + $$ = NULL; +} +| +{ + $$ = NULL; +} + start_terms: event_config { struct parse_events_terms *data = _data; @@ -573,6 +577,86 @@ PE_TERM ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL)); $$ = term; } +| +PE_NAME array '=' PE_NAME +{ + struct parse_events_term *term; + int i; + + ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $4, &@1, &@4)); + + term->array = $2; + $$ = term; +} +| +PE_NAME array '=' PE_VALUE +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $4, &@1, &@4)); + term->array = $2; + $$ = term; +} + +array: +'[' array_terms ']' +{ + $$ = $2; +} +| +PE_ARRAY_ALL +{ + $$.nr_ranges = 0; + $$.ranges = NULL; +} + +array_terms: +array_terms ',' array_term +{ + struct parse_events_array new_array; + + new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges; + new_array.ranges = malloc(sizeof(new_array.ranges[0]) * + new_array.nr_ranges); + ABORT_ON(!new_array.ranges); + memcpy(&new_array.ranges[0], $1.ranges, + $1.nr_ranges * sizeof(new_array.ranges[0])); + memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges, + $3.nr_ranges * sizeof(new_array.ranges[0])); + free($1.ranges); + free($3.ranges); + $$ = new_array; +} +| +array_term + +array_term: +PE_VALUE +{ + struct parse_events_array array; + + array.nr_ranges = 1; + array.ranges = malloc(sizeof(array.ranges[0])); + ABORT_ON(!array.ranges); + array.ranges[0].start = $1; + array.ranges[0].length = 1; + $$ = array; +} +| +PE_VALUE PE_ARRAY_RANGE PE_VALUE +{ + struct parse_events_array array; + + ABORT_ON($3 < $1); + array.nr_ranges = 1; + array.ranges = malloc(sizeof(array.ranges[0])); + ABORT_ON(!array.ranges); + array.ranges[0].start = $1; + array.ranges[0].length = $3 - $1 + 1; + $$ = array; +} sep_dc: ':' | diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index b597bcc8fc781..adef23b1352e8 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -98,7 +98,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * char scale[128]; int fd, ret = -1; char path[PATH_MAX]; - const char *lc; + char *lc; snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); @@ -123,6 +123,17 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * */ lc = setlocale(LC_NUMERIC, NULL); + /* + * The lc string may be allocated in static storage, + * so get a dynamic copy to make it survive setlocale + * call below. + */ + lc = strdup(lc); + if (!lc) { + ret = -ENOMEM; + goto error; + } + /* * force to C locale to ensure kernel * scale string is converted correctly. @@ -135,6 +146,8 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * /* restore locale */ setlocale(LC_NUMERIC, lc); + free(lc); + ret = 0; error: close(fd); @@ -153,7 +166,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n if (fd == -1) return -1; - sret = read(fd, alias->unit, UNIT_MAX_LEN); + sret = read(fd, alias->unit, UNIT_MAX_LEN); if (sret < 0) goto error; @@ -284,13 +297,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) { struct dirent *evt_ent; DIR *event_dir; - int ret = 0; event_dir = opendir(dir); if (!event_dir) return -EINVAL; - while (!ret && (evt_ent = readdir(event_dir))) { + while ((evt_ent = readdir(event_dir))) { char path[PATH_MAX]; char *name = evt_ent->d_name; FILE *file; @@ -306,17 +318,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) snprintf(path, PATH_MAX, "%s/%s", dir, name); - ret = -EINVAL; file = fopen(path, "r"); - if (!file) - break; + if (!file) { + pr_debug("Cannot open %s\n", path); + continue; + } - ret = perf_pmu__new_alias(head, dir, name, file); + if (perf_pmu__new_alias(head, dir, name, file) < 0) + pr_debug("Cannot set up %s\n", name); fclose(file); } closedir(event_dir); - return ret; + return 0; } /* @@ -354,7 +368,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, list_for_each_entry(term, &alias->terms, list) { ret = parse_events_term__clone(&cloned, term); if (ret) { - parse_events__free_terms(&list); + parse_events_terms__purge(&list); return ret; } list_add_tail(&cloned->list, &list); diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 544509c159cec..b3aabc0d4eb00 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -187,6 +187,9 @@ static void define_event_symbols(struct event_format *event, const char *ev_name, struct print_arg *args) { + if (args == NULL) + return; + switch (args->type) { case PRINT_NULL: break; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index d72fafc1c800d..fbd05242b4e59 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -205,6 +205,9 @@ static void define_event_symbols(struct event_format *event, const char *ev_name, struct print_arg *args) { + if (args == NULL) + return; + switch (args->type) { case PRINT_NULL: break; @@ -1091,8 +1094,6 @@ static int python_start_script(const char *script, int argc, const char **argv) goto error; } - free(command_line); - set_table_handlers(tables); if (tables->db_export_mode) { @@ -1101,6 +1102,8 @@ static int python_start_script(const char *script, int argc, const char **argv) goto error; } + free(command_line); + return err; error: Py_Finalize(); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 40b7a0d0905b8..60b3593d210db 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -240,14 +240,6 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused, return 0; } -static int process_build_id_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) -{ - dump_printf(": unhandled!\n"); - return 0; -} - static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct ordered_events *oe __maybe_unused) @@ -260,23 +252,6 @@ static int process_finished_round(struct perf_tool *tool, union perf_event *event, struct ordered_events *oe); -static int process_id_index_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *perf_session - __maybe_unused) -{ - dump_printf(": unhandled!\n"); - return 0; -} - -static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) -{ - dump_printf(": unhandled!\n"); - return 0; -} - static int skipn(int fd, off_t n) { char buf[4096]; @@ -303,10 +278,9 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused, return event->auxtrace.size; } -static -int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *session __maybe_unused) +static int process_event_op2_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -410,7 +384,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool) if (tool->tracing_data == NULL) tool->tracing_data = process_event_synth_tracing_data_stub; if (tool->build_id == NULL) - tool->build_id = process_build_id_stub; + tool->build_id = process_event_op2_stub; if (tool->finished_round == NULL) { if (tool->ordered_events) tool->finished_round = process_finished_round; @@ -418,13 +392,13 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->finished_round = process_finished_round_stub; } if (tool->id_index == NULL) - tool->id_index = process_id_index_stub; + tool->id_index = process_event_op2_stub; if (tool->auxtrace_info == NULL) - tool->auxtrace_info = process_event_auxtrace_info_stub; + tool->auxtrace_info = process_event_op2_stub; if (tool->auxtrace == NULL) tool->auxtrace = process_event_auxtrace_stub; if (tool->auxtrace_error == NULL) - tool->auxtrace_error = process_event_auxtrace_error_stub; + tool->auxtrace_error = process_event_op2_stub; if (tool->thread_map == NULL) tool->thread_map = process_event_thread_map_stub; if (tool->cpu_map == NULL) diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 1833103768cb9..c8680984d2d66 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -22,6 +22,7 @@ def finalize_options(self): # switch off several checks (need to be at the end of cflags list) cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ] +src_perf = getenv('srctree') + '/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') @@ -30,6 +31,9 @@ def finalize_options(self): ext_sources = [f.strip() for f in file('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] +# use full paths with source files +ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources) + perf = Extension('perf', sources = ext_sources, include_dirs = ['util/include'], diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index ec722346e6ffb..93fa136b0025c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -6,6 +6,7 @@ #include "evsel.h" #include "evlist.h" #include +#include "mem-events.h" regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -25,9 +26,19 @@ int sort__has_parent = 0; int sort__has_sym = 0; int sort__has_dso = 0; int sort__has_socket = 0; +int sort__has_thread = 0; +int sort__has_comm = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; - +/* + * Replaces all occurrences of a char used with the: + * + * -t, --field-separator + * + * option, that uses a special separator character and don't pad with spaces, + * replacing all occurances of this separator in symbol names (and other + * output) with a '.' character, that thus it's the only non valid separator. +*/ static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) { int n; @@ -80,10 +91,21 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf, width, width, comm ?: ""); } +static int hist_entry__thread_filter(struct hist_entry *he, int type, const void *arg) +{ + const struct thread *th = arg; + + if (type != HIST_FILTER__THREAD) + return -1; + + return th && he->thread != th; +} + struct sort_entry sort_thread = { .se_header = " Pid:Command", .se_cmp = sort__thread_cmp, .se_snprintf = hist_entry__thread_snprintf, + .se_filter = hist_entry__thread_filter, .se_width_idx = HISTC_THREAD, }; @@ -121,6 +143,7 @@ struct sort_entry sort_comm = { .se_collapse = sort__comm_collapse, .se_sort = sort__comm_sort, .se_snprintf = hist_entry__comm_snprintf, + .se_filter = hist_entry__thread_filter, .se_width_idx = HISTC_COMM, }; @@ -170,10 +193,21 @@ static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf, return _hist_entry__dso_snprintf(he->ms.map, bf, size, width); } +static int hist_entry__dso_filter(struct hist_entry *he, int type, const void *arg) +{ + const struct dso *dso = arg; + + if (type != HIST_FILTER__DSO) + return -1; + + return dso && (!he->ms.map || he->ms.map->dso != dso); +} + struct sort_entry sort_dso = { .se_header = "Shared Object", .se_cmp = sort__dso_cmp, .se_snprintf = hist_entry__dso_snprintf, + .se_filter = hist_entry__dso_filter, .se_width_idx = HISTC_DSO, }; @@ -246,10 +280,8 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name); ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", ip - map->unmap_ip(map, sym->start)); - ret += repsep_snprintf(bf + ret, size - ret, "%-*s", - width - ret, ""); } else { - ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + ret += repsep_snprintf(bf + ret, size - ret, "%.*s", width - ret, sym->name); } @@ -257,14 +289,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, size_t len = BITS_PER_LONG / 4; ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, ip); - ret += repsep_snprintf(bf + ret, size - ret, "%-*s", - width - ret, ""); } - if (ret > width) - bf[width] = '\0'; - - return width; + return ret; } static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, @@ -274,46 +301,56 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, he->level, bf, size, width); } +static int hist_entry__sym_filter(struct hist_entry *he, int type, const void *arg) +{ + const char *sym = arg; + + if (type != HIST_FILTER__SYMBOL) + return -1; + + return sym && (!he->ms.sym || !strstr(he->ms.sym->name, sym)); +} + struct sort_entry sort_sym = { .se_header = "Symbol", .se_cmp = sort__sym_cmp, .se_sort = sort__sym_sort, .se_snprintf = hist_entry__sym_snprintf, + .se_filter = hist_entry__sym_filter, .se_width_idx = HISTC_SYMBOL, }; /* --sort srcline */ +static char *hist_entry__get_srcline(struct hist_entry *he) +{ + struct map *map = he->ms.map; + + if (!map) + return SRCLINE_UNKNOWN; + + return get_srcline(map->dso, map__rip_2objdump(map, he->ip), + he->ms.sym, true); +} + static int64_t sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!left->srcline) { - if (!left->ms.map) - left->srcline = SRCLINE_UNKNOWN; - else { - struct map *map = left->ms.map; - left->srcline = get_srcline(map->dso, - map__rip_2objdump(map, left->ip), - left->ms.sym, true); - } - } - if (!right->srcline) { - if (!right->ms.map) - right->srcline = SRCLINE_UNKNOWN; - else { - struct map *map = right->ms.map; - right->srcline = get_srcline(map->dso, - map__rip_2objdump(map, right->ip), - right->ms.sym, true); - } - } + if (!left->srcline) + left->srcline = hist_entry__get_srcline(left); + if (!right->srcline) + right->srcline = hist_entry__get_srcline(right); + return strcmp(right->srcline, left->srcline); } static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline); + if (!he->srcline) + he->srcline = hist_entry__get_srcline(he); + + return repsep_snprintf(bf, size, "%-.*s", width, he->srcline); } struct sort_entry sort_srcline = { @@ -327,11 +364,14 @@ struct sort_entry sort_srcline = { static char no_srcfile[1]; -static char *get_srcfile(struct hist_entry *e) +static char *hist_entry__get_srcfile(struct hist_entry *e) { char *sf, *p; struct map *map = e->ms.map; + if (!map) + return no_srcfile; + sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip), e->ms.sym, false, true); if (!strcmp(sf, SRCLINE_UNKNOWN)) @@ -348,25 +388,21 @@ static char *get_srcfile(struct hist_entry *e) static int64_t sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!left->srcfile) { - if (!left->ms.map) - left->srcfile = no_srcfile; - else - left->srcfile = get_srcfile(left); - } - if (!right->srcfile) { - if (!right->ms.map) - right->srcfile = no_srcfile; - else - right->srcfile = get_srcfile(right); - } + if (!left->srcfile) + left->srcfile = hist_entry__get_srcfile(left); + if (!right->srcfile) + right->srcfile = hist_entry__get_srcfile(right); + return strcmp(right->srcfile, left->srcfile); } static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile); + if (!he->srcfile) + he->srcfile = hist_entry__get_srcfile(he); + + return repsep_snprintf(bf, size, "%-.*s", width, he->srcfile); } struct sort_entry sort_srcfile = { @@ -439,10 +475,21 @@ static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket); } +static int hist_entry__socket_filter(struct hist_entry *he, int type, const void *arg) +{ + int sk = *(const int *)arg; + + if (type != HIST_FILTER__SOCKET) + return -1; + + return sk >= 0 && he->socket != sk; +} + struct sort_entry sort_socket = { .se_header = "Socket", .se_cmp = sort__socket_cmp, .se_snprintf = hist_entry__socket_snprintf, + .se_filter = hist_entry__socket_filter, .se_width_idx = HISTC_SOCKET, }; @@ -483,9 +530,6 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right) if (right->trace_output == NULL) right->trace_output = get_trace_output(right); - hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output)); - hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output)); - return strcmp(right->trace_output, left->trace_output); } @@ -496,11 +540,11 @@ static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf, evsel = hists_to_evsel(he->hists); if (evsel->attr.type != PERF_TYPE_TRACEPOINT) - return scnprintf(bf, size, "%-*.*s", width, width, "N/A"); + return scnprintf(bf, size, "%-.*s", width, "N/A"); if (he->trace_output == NULL) he->trace_output = get_trace_output(he); - return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output); + return repsep_snprintf(bf, size, "%-.*s", width, he->trace_output); } struct sort_entry sort_trace = { @@ -532,6 +576,18 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } +static int hist_entry__dso_from_filter(struct hist_entry *he, int type, + const void *arg) +{ + const struct dso *dso = arg; + + if (type != HIST_FILTER__DSO) + return -1; + + return dso && (!he->branch_info || !he->branch_info->from.map || + he->branch_info->from.map->dso != dso); +} + static int64_t sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -552,6 +608,18 @@ static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } +static int hist_entry__dso_to_filter(struct hist_entry *he, int type, + const void *arg) +{ + const struct dso *dso = arg; + + if (type != HIST_FILTER__DSO) + return -1; + + return dso && (!he->branch_info || !he->branch_info->to.map || + he->branch_info->to.map->dso != dso); +} + static int64_t sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -613,10 +681,35 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); } +static int hist_entry__sym_from_filter(struct hist_entry *he, int type, + const void *arg) +{ + const char *sym = arg; + + if (type != HIST_FILTER__SYMBOL) + return -1; + + return sym && !(he->branch_info && he->branch_info->from.sym && + strstr(he->branch_info->from.sym->name, sym)); +} + +static int hist_entry__sym_to_filter(struct hist_entry *he, int type, + const void *arg) +{ + const char *sym = arg; + + if (type != HIST_FILTER__SYMBOL) + return -1; + + return sym && !(he->branch_info && he->branch_info->to.sym && + strstr(he->branch_info->to.sym->name, sym)); +} + struct sort_entry sort_dso_from = { .se_header = "Source Shared Object", .se_cmp = sort__dso_from_cmp, .se_snprintf = hist_entry__dso_from_snprintf, + .se_filter = hist_entry__dso_from_filter, .se_width_idx = HISTC_DSO_FROM, }; @@ -624,6 +717,7 @@ struct sort_entry sort_dso_to = { .se_header = "Target Shared Object", .se_cmp = sort__dso_to_cmp, .se_snprintf = hist_entry__dso_to_snprintf, + .se_filter = hist_entry__dso_to_filter, .se_width_idx = HISTC_DSO_TO, }; @@ -631,6 +725,7 @@ struct sort_entry sort_sym_from = { .se_header = "Source Symbol", .se_cmp = sort__sym_from_cmp, .se_snprintf = hist_entry__sym_from_snprintf, + .se_filter = hist_entry__sym_from_filter, .se_width_idx = HISTC_SYMBOL_FROM, }; @@ -638,6 +733,7 @@ struct sort_entry sort_sym_to = { .se_header = "Target Symbol", .se_cmp = sort__sym_to_cmp, .se_snprintf = hist_entry__sym_to_snprintf, + .se_filter = hist_entry__sym_to_filter, .se_width_idx = HISTC_SYMBOL_TO, }; @@ -797,20 +893,10 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - const char *out; - u64 mask = PERF_MEM_LOCK_NA; + char out[10]; - if (he->mem_info) - mask = he->mem_info->data_src.mem_lock; - - if (mask & PERF_MEM_LOCK_NA) - out = "N/A"; - else if (mask & PERF_MEM_LOCK_LOCKED) - out = "Yes"; - else - out = "No"; - - return repsep_snprintf(bf, size, "%-*s", width, out); + perf_mem__lck_scnprintf(out, sizeof(out), he->mem_info); + return repsep_snprintf(bf, size, "%.*s", width, out); } static int64_t @@ -832,54 +918,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right) return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb); } -static const char * const tlb_access[] = { - "N/A", - "HIT", - "MISS", - "L1", - "L2", - "Walker", - "Fault", -}; -#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *)) - static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; - size_t sz = sizeof(out) - 1; /* -1 for null termination */ - size_t l = 0, i; - u64 m = PERF_MEM_TLB_NA; - u64 hit, miss; - - out[0] = '\0'; - - if (he->mem_info) - m = he->mem_info->data_src.mem_dtlb; - - hit = m & PERF_MEM_TLB_HIT; - miss = m & PERF_MEM_TLB_MISS; - - /* already taken care of */ - m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS); - - for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) { - if (!(m & 0x1)) - continue; - if (l) { - strcat(out, " or "); - l += 4; - } - strncat(out, tlb_access[i], sz - l); - l += strlen(tlb_access[i]); - } - if (*out == '\0') - strcpy(out, "N/A"); - if (hit) - strncat(out, " hit", sz - l); - if (miss) - strncat(out, " miss", sz - l); + perf_mem__tlb_scnprintf(out, sizeof(out), he->mem_info); return repsep_snprintf(bf, size, "%-*s", width, out); } @@ -902,61 +946,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right) return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl); } -static const char * const mem_lvl[] = { - "N/A", - "HIT", - "MISS", - "L1", - "LFB", - "L2", - "L3", - "Local RAM", - "Remote RAM (1 hop)", - "Remote RAM (2 hops)", - "Remote Cache (1 hop)", - "Remote Cache (2 hops)", - "I/O", - "Uncached", -}; -#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *)) - static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; - size_t sz = sizeof(out) - 1; /* -1 for null termination */ - size_t i, l = 0; - u64 m = PERF_MEM_LVL_NA; - u64 hit, miss; - - if (he->mem_info) - m = he->mem_info->data_src.mem_lvl; - - out[0] = '\0'; - - hit = m & PERF_MEM_LVL_HIT; - miss = m & PERF_MEM_LVL_MISS; - - /* already taken care of */ - m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); - - for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) { - if (!(m & 0x1)) - continue; - if (l) { - strcat(out, " or "); - l += 4; - } - strncat(out, mem_lvl[i], sz - l); - l += strlen(mem_lvl[i]); - } - if (*out == '\0') - strcpy(out, "N/A"); - if (hit) - strncat(out, " hit", sz - l); - if (miss) - strncat(out, " miss", sz - l); + perf_mem__lvl_scnprintf(out, sizeof(out), he->mem_info); return repsep_snprintf(bf, size, "%-*s", width, out); } @@ -979,51 +974,15 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right) return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop); } -static const char * const snoop_access[] = { - "N/A", - "None", - "Miss", - "Hit", - "HitM", -}; -#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *)) - static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; - size_t sz = sizeof(out) - 1; /* -1 for null termination */ - size_t i, l = 0; - u64 m = PERF_MEM_SNOOP_NA; - - out[0] = '\0'; - - if (he->mem_info) - m = he->mem_info->data_src.mem_snoop; - - for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) { - if (!(m & 0x1)) - continue; - if (l) { - strcat(out, " or "); - l += 4; - } - strncat(out, snoop_access[i], sz - l); - l += strlen(snoop_access[i]); - } - - if (*out == '\0') - strcpy(out, "N/A"); + perf_mem__snp_scnprintf(out, sizeof(out), he->mem_info); return repsep_snprintf(bf, size, "%-*s", width, out); } -static inline u64 cl_address(u64 address) -{ - /* return the cacheline of the address */ - return (address & ~(cacheline_size - 1)); -} - static int64_t sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -1440,20 +1399,6 @@ struct hpp_sort_entry { struct sort_entry *se; }; -bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) -{ - struct hpp_sort_entry *hse_a; - struct hpp_sort_entry *hse_b; - - if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b)) - return false; - - hse_a = container_of(a, struct hpp_sort_entry, hpp); - hse_b = container_of(b, struct hpp_sort_entry, hpp); - - return hse_a->se == hse_b->se; -} - void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists) { struct hpp_sort_entry *hse; @@ -1539,8 +1484,56 @@ static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt, return sort_fn(a, b); } +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format) +{ + return format->header == __sort__hpp_header; +} + +#define MK_SORT_ENTRY_CHK(key) \ +bool perf_hpp__is_ ## key ## _entry(struct perf_hpp_fmt *fmt) \ +{ \ + struct hpp_sort_entry *hse; \ + \ + if (!perf_hpp__is_sort_entry(fmt)) \ + return false; \ + \ + hse = container_of(fmt, struct hpp_sort_entry, hpp); \ + return hse->se == &sort_ ## key ; \ +} + +MK_SORT_ENTRY_CHK(trace) +MK_SORT_ENTRY_CHK(srcline) +MK_SORT_ENTRY_CHK(srcfile) +MK_SORT_ENTRY_CHK(thread) +MK_SORT_ENTRY_CHK(comm) +MK_SORT_ENTRY_CHK(dso) +MK_SORT_ENTRY_CHK(sym) + + +static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + struct hpp_sort_entry *hse_a; + struct hpp_sort_entry *hse_b; + + if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b)) + return false; + + hse_a = container_of(a, struct hpp_sort_entry, hpp); + hse_b = container_of(b, struct hpp_sort_entry, hpp); + + return hse_a->se == hse_b->se; +} + +static void hse_free(struct perf_hpp_fmt *fmt) +{ + struct hpp_sort_entry *hse; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + free(hse); +} + static struct hpp_sort_entry * -__sort_dimension__alloc_hpp(struct sort_dimension *sd) +__sort_dimension__alloc_hpp(struct sort_dimension *sd, int level) { struct hpp_sort_entry *hse; @@ -1560,40 +1553,92 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) hse->hpp.cmp = __sort__hpp_cmp; hse->hpp.collapse = __sort__hpp_collapse; hse->hpp.sort = __sort__hpp_sort; + hse->hpp.equal = __sort__hpp_equal; + hse->hpp.free = hse_free; INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); hse->hpp.elide = false; hse->hpp.len = 0; hse->hpp.user_len = 0; + hse->hpp.level = level; return hse; } -bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format) +static void hpp_free(struct perf_hpp_fmt *fmt) { - return format->header == __sort__hpp_header; + free(fmt); +} + +static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd, + int level) +{ + struct perf_hpp_fmt *fmt; + + fmt = memdup(hd->fmt, sizeof(*fmt)); + if (fmt) { + INIT_LIST_HEAD(&fmt->list); + INIT_LIST_HEAD(&fmt->sort_list); + fmt->free = hpp_free; + fmt->level = level; + } + + return fmt; +} + +int hist_entry__filter(struct hist_entry *he, int type, const void *arg) +{ + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; + int ret = -1; + int r; + + perf_hpp_list__for_each_format(he->hpp_list, fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + if (hse->se->se_filter == NULL) + continue; + + /* + * hist entry is filtered if any of sort key in the hpp list + * is applied. But it should skip non-matched filter types. + */ + r = hse->se->se_filter(he, type, arg); + if (r >= 0) { + if (ret < 0) + ret = 0; + ret |= r; + } + } + + return ret; } -static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd) +static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd, + struct perf_hpp_list *list, + int level) { - struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level); if (hse == NULL) return -1; - perf_hpp__register_sort_field(&hse->hpp); + perf_hpp_list__register_sort_field(list, &hse->hpp); return 0; } -static int __sort_dimension__add_hpp_output(struct sort_dimension *sd) +static int __sort_dimension__add_hpp_output(struct sort_dimension *sd, + struct perf_hpp_list *list) { - struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0); if (hse == NULL) return -1; - perf_hpp__column_register(&hse->hpp); + perf_hpp_list__column_register(list, &hse->hpp); return 0; } @@ -1727,6 +1772,9 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, if (hde->raw_trace) goto raw_field; + if (!he->trace_output) + he->trace_output = get_trace_output(he); + field = hde->field; namelen = strlen(field->name); str = he->trace_output; @@ -1776,6 +1824,11 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + if (b == NULL) { + update_dynamic_len(hde, a); + return 0; + } + field = hde->field; if (field->flags & FIELD_IS_DYNAMIC) { unsigned long long dyn; @@ -1790,9 +1843,6 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, } else { offset = field->offset; size = field->size; - - update_dynamic_len(hde, a); - update_dynamic_len(hde, b); } return memcmp(a->raw_data + offset, b->raw_data + offset, size); @@ -1803,8 +1853,31 @@ bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt) return fmt->cmp == __sort__hde_cmp; } +static bool __sort__hde_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + struct hpp_dynamic_entry *hde_a; + struct hpp_dynamic_entry *hde_b; + + if (!perf_hpp__is_dynamic_entry(a) || !perf_hpp__is_dynamic_entry(b)) + return false; + + hde_a = container_of(a, struct hpp_dynamic_entry, hpp); + hde_b = container_of(b, struct hpp_dynamic_entry, hpp); + + return hde_a->field == hde_b->field; +} + +static void hde_free(struct perf_hpp_fmt *fmt) +{ + struct hpp_dynamic_entry *hde; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + free(hde); +} + static struct hpp_dynamic_entry * -__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) +__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field, + int level) { struct hpp_dynamic_entry *hde; @@ -1827,16 +1900,47 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) hde->hpp.cmp = __sort__hde_cmp; hde->hpp.collapse = __sort__hde_cmp; hde->hpp.sort = __sort__hde_cmp; + hde->hpp.equal = __sort__hde_equal; + hde->hpp.free = hde_free; INIT_LIST_HEAD(&hde->hpp.list); INIT_LIST_HEAD(&hde->hpp.sort_list); hde->hpp.elide = false; hde->hpp.len = 0; hde->hpp.user_len = 0; + hde->hpp.level = level; return hde; } +struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt) +{ + struct perf_hpp_fmt *new_fmt = NULL; + + if (perf_hpp__is_sort_entry(fmt)) { + struct hpp_sort_entry *hse, *new_hse; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + new_hse = memdup(hse, sizeof(*hse)); + if (new_hse) + new_fmt = &new_hse->hpp; + } else if (perf_hpp__is_dynamic_entry(fmt)) { + struct hpp_dynamic_entry *hde, *new_hde; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + new_hde = memdup(hde, sizeof(*hde)); + if (new_hde) + new_fmt = &new_hde->hpp; + } else { + new_fmt = memdup(fmt, sizeof(*fmt)); + } + + INIT_LIST_HEAD(&new_fmt->list); + INIT_LIST_HEAD(&new_fmt->sort_list); + + return new_fmt; +} + static int parse_field_name(char *str, char **event, char **field, char **opt) { char *event_name, *field_name, *opt_name; @@ -1908,11 +2012,11 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam static int __dynamic_dimension__add(struct perf_evsel *evsel, struct format_field *field, - bool raw_trace) + bool raw_trace, int level) { struct hpp_dynamic_entry *hde; - hde = __alloc_dynamic_entry(evsel, field); + hde = __alloc_dynamic_entry(evsel, field, level); if (hde == NULL) return -ENOMEM; @@ -1922,14 +2026,14 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel, return 0; } -static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace) +static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level) { int ret; struct format_field *field; field = evsel->tp_format->format.fields; while (field) { - ret = __dynamic_dimension__add(evsel, field, raw_trace); + ret = __dynamic_dimension__add(evsel, field, raw_trace, level); if (ret < 0) return ret; @@ -1938,7 +2042,8 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace) return 0; } -static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace) +static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace, + int level) { int ret; struct perf_evsel *evsel; @@ -1947,7 +2052,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace) if (evsel->attr.type != PERF_TYPE_TRACEPOINT) continue; - ret = add_evsel_fields(evsel, raw_trace); + ret = add_evsel_fields(evsel, raw_trace, level); if (ret < 0) return ret; } @@ -1955,7 +2060,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace) } static int add_all_matching_fields(struct perf_evlist *evlist, - char *field_name, bool raw_trace) + char *field_name, bool raw_trace, int level) { int ret = -ESRCH; struct perf_evsel *evsel; @@ -1969,14 +2074,15 @@ static int add_all_matching_fields(struct perf_evlist *evlist, if (field == NULL) continue; - ret = __dynamic_dimension__add(evsel, field, raw_trace); + ret = __dynamic_dimension__add(evsel, field, raw_trace, level); if (ret < 0) break; } return ret; } -static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) +static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, + int level) { char *str, *event_name, *field_name, *opt_name; struct perf_evsel *evsel; @@ -2006,12 +2112,12 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) } if (!strcmp(field_name, "trace_fields")) { - ret = add_all_dynamic_fields(evlist, raw_trace); + ret = add_all_dynamic_fields(evlist, raw_trace, level); goto out; } if (event_name == NULL) { - ret = add_all_matching_fields(evlist, field_name, raw_trace); + ret = add_all_matching_fields(evlist, field_name, raw_trace, level); goto out; } @@ -2029,7 +2135,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) } if (!strcmp(field_name, "*")) { - ret = add_evsel_fields(evsel, raw_trace); + ret = add_evsel_fields(evsel, raw_trace, level); } else { field = pevent_find_any_field(evsel->tp_format, field_name); if (field == NULL) { @@ -2038,7 +2144,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) return -ENOENT; } - ret = __dynamic_dimension__add(evsel, field, raw_trace); + ret = __dynamic_dimension__add(evsel, field, raw_trace, level); } out: @@ -2046,12 +2152,14 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) return ret; } -static int __sort_dimension__add(struct sort_dimension *sd) +static int __sort_dimension__add(struct sort_dimension *sd, + struct perf_hpp_list *list, + int level) { if (sd->taken) return 0; - if (__sort_dimension__add_hpp_sort(sd) < 0) + if (__sort_dimension__add_hpp_sort(sd, list, level) < 0) return -1; if (sd->entry->se_collapse) @@ -2062,46 +2170,63 @@ static int __sort_dimension__add(struct sort_dimension *sd) return 0; } -static int __hpp_dimension__add(struct hpp_dimension *hd) +static int __hpp_dimension__add(struct hpp_dimension *hd, + struct perf_hpp_list *list, + int level) { - if (!hd->taken) { - hd->taken = 1; + struct perf_hpp_fmt *fmt; - perf_hpp__register_sort_field(hd->fmt); - } + if (hd->taken) + return 0; + + fmt = __hpp_dimension__alloc_hpp(hd, level); + if (!fmt) + return -1; + + hd->taken = 1; + perf_hpp_list__register_sort_field(list, fmt); return 0; } -static int __sort_dimension__add_output(struct sort_dimension *sd) +static int __sort_dimension__add_output(struct perf_hpp_list *list, + struct sort_dimension *sd) { if (sd->taken) return 0; - if (__sort_dimension__add_hpp_output(sd) < 0) + if (__sort_dimension__add_hpp_output(sd, list) < 0) return -1; sd->taken = 1; return 0; } -static int __hpp_dimension__add_output(struct hpp_dimension *hd) +static int __hpp_dimension__add_output(struct perf_hpp_list *list, + struct hpp_dimension *hd) { - if (!hd->taken) { - hd->taken = 1; + struct perf_hpp_fmt *fmt; - perf_hpp__column_register(hd->fmt); - } + if (hd->taken) + return 0; + + fmt = __hpp_dimension__alloc_hpp(hd, 0); + if (!fmt) + return -1; + + hd->taken = 1; + perf_hpp_list__column_register(list, fmt); return 0; } int hpp_dimension__add_output(unsigned col) { BUG_ON(col >= PERF_HPP__MAX_INDEX); - return __hpp_dimension__add_output(&hpp_sort_dimensions[col]); + return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]); } -static int sort_dimension__add(const char *tok, - struct perf_evlist *evlist __maybe_unused) +static int sort_dimension__add(struct perf_hpp_list *list, const char *tok, + struct perf_evlist *evlist __maybe_unused, + int level) { unsigned int i; @@ -2136,9 +2261,13 @@ static int sort_dimension__add(const char *tok, sort__has_dso = 1; } else if (sd->entry == &sort_socket) { sort__has_socket = 1; + } else if (sd->entry == &sort_thread) { + sort__has_thread = 1; + } else if (sd->entry == &sort_comm) { + sort__has_comm = 1; } - return __sort_dimension__add(sd); + return __sort_dimension__add(sd, list, level); } for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { @@ -2147,7 +2276,7 @@ static int sort_dimension__add(const char *tok, if (strncasecmp(tok, hd->name, strlen(tok))) continue; - return __hpp_dimension__add(hd); + return __hpp_dimension__add(hd, list, level); } for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { @@ -2162,7 +2291,7 @@ static int sort_dimension__add(const char *tok, if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) sort__has_sym = 1; - __sort_dimension__add(sd); + __sort_dimension__add(sd, list, level); return 0; } @@ -2178,16 +2307,60 @@ static int sort_dimension__add(const char *tok, if (sd->entry == &sort_mem_daddr_sym) sort__has_sym = 1; - __sort_dimension__add(sd); + __sort_dimension__add(sd, list, level); return 0; } - if (!add_dynamic_entry(evlist, tok)) + if (!add_dynamic_entry(evlist, tok, level)) return 0; return -ESRCH; } +static int setup_sort_list(struct perf_hpp_list *list, char *str, + struct perf_evlist *evlist) +{ + char *tmp, *tok; + int ret = 0; + int level = 0; + int next_level = 1; + bool in_group = false; + + do { + tok = str; + tmp = strpbrk(str, "{}, "); + if (tmp) { + if (in_group) + next_level = level; + else + next_level = level + 1; + + if (*tmp == '{') + in_group = true; + else if (*tmp == '}') + in_group = false; + + *tmp = '\0'; + str = tmp + 1; + } + + if (*tok) { + ret = sort_dimension__add(list, tok, evlist, level); + if (ret == -EINVAL) { + error("Invalid --sort key: `%s'", tok); + break; + } else if (ret == -ESRCH) { + error("Unknown --sort key: `%s'", tok); + break; + } + } + + level = next_level; + } while (tmp); + + return ret; +} + static const char *get_default_sort_order(struct perf_evlist *evlist) { const char *default_sort_orders[] = { @@ -2282,7 +2455,7 @@ static char *setup_overhead(char *keys) static int __setup_sorting(struct perf_evlist *evlist) { - char *tmp, *tok, *str; + char *str; const char *sort_keys; int ret = 0; @@ -2320,17 +2493,7 @@ static int __setup_sorting(struct perf_evlist *evlist) } } - for (tok = strtok_r(str, ", ", &tmp); - tok; tok = strtok_r(NULL, ", ", &tmp)) { - ret = sort_dimension__add(tok, evlist); - if (ret == -EINVAL) { - error("Invalid --sort key: `%s'", tok); - break; - } else if (ret == -ESRCH) { - error("Unknown --sort key: `%s'", tok); - break; - } - } + ret = setup_sort_list(&perf_hpp_list, str, evlist); free(str); return ret; @@ -2341,7 +2504,7 @@ void perf_hpp__set_elide(int idx, bool elide) struct perf_hpp_fmt *fmt; struct hpp_sort_entry *hse; - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2401,7 +2564,7 @@ void sort__setup_elide(FILE *output) struct perf_hpp_fmt *fmt; struct hpp_sort_entry *hse; - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2413,7 +2576,7 @@ void sort__setup_elide(FILE *output) * It makes no sense to elide all of sort entries. * Just revert them to show up again. */ - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2421,7 +2584,7 @@ void sort__setup_elide(FILE *output) return; } - perf_hpp__for_each_format(fmt) { + perf_hpp_list__for_each_format(&perf_hpp_list, fmt) { if (!perf_hpp__is_sort_entry(fmt)) continue; @@ -2429,7 +2592,7 @@ void sort__setup_elide(FILE *output) } } -static int output_field_add(char *tok) +static int output_field_add(struct perf_hpp_list *list, char *tok) { unsigned int i; @@ -2439,7 +2602,7 @@ static int output_field_add(char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - return __sort_dimension__add_output(sd); + return __sort_dimension__add_output(list, sd); } for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { @@ -2448,7 +2611,7 @@ static int output_field_add(char *tok) if (strncasecmp(tok, hd->name, strlen(tok))) continue; - return __hpp_dimension__add_output(hd); + return __hpp_dimension__add_output(list, hd); } for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { @@ -2457,7 +2620,7 @@ static int output_field_add(char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - return __sort_dimension__add_output(sd); + return __sort_dimension__add_output(list, sd); } for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { @@ -2466,12 +2629,32 @@ static int output_field_add(char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - return __sort_dimension__add_output(sd); + return __sort_dimension__add_output(list, sd); } return -ESRCH; } +static int setup_output_list(struct perf_hpp_list *list, char *str) +{ + char *tmp, *tok; + int ret = 0; + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + ret = output_field_add(list, tok); + if (ret == -EINVAL) { + error("Invalid --fields key: `%s'", tok); + break; + } else if (ret == -ESRCH) { + error("Unknown --fields key: `%s'", tok); + break; + } + } + + return ret; +} + static void reset_dimensions(void) { unsigned int i; @@ -2496,7 +2679,7 @@ bool is_strict_order(const char *order) static int __setup_output_field(void) { - char *tmp, *tok, *str, *strp; + char *str, *strp; int ret = -EINVAL; if (field_order == NULL) @@ -2516,17 +2699,7 @@ static int __setup_output_field(void) goto out; } - for (tok = strtok_r(strp, ", ", &tmp); - tok; tok = strtok_r(NULL, ", ", &tmp)) { - ret = output_field_add(tok); - if (ret == -EINVAL) { - error("Invalid --fields key: `%s'", tok); - break; - } else if (ret == -ESRCH) { - error("Unknown --fields key: `%s'", tok); - break; - } - } + ret = setup_output_list(&perf_hpp_list, strp); out: free(str); @@ -2542,7 +2715,7 @@ int setup_sorting(struct perf_evlist *evlist) return err; if (parent_pattern != default_parent_pattern) { - err = sort_dimension__add("parent", evlist); + err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1); if (err < 0) return err; } @@ -2560,9 +2733,13 @@ int setup_sorting(struct perf_evlist *evlist) return err; /* copy sort keys to output fields */ - perf_hpp__setup_output_field(); + perf_hpp__setup_output_field(&perf_hpp_list); /* and then copy output fields to sort keys */ - perf_hpp__append_sort_keys(); + perf_hpp__append_sort_keys(&perf_hpp_list); + + /* setup hists-specific output fields */ + if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0) + return -1; return 0; } @@ -2578,5 +2755,5 @@ void reset_output_field(void) sort_order = NULL; reset_dimensions(); - perf_hpp__reset_output_field(); + perf_hpp__reset_output_field(&perf_hpp_list); } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 687bbb1244281..3f4e359981192 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -32,9 +32,12 @@ extern const char default_sort_order[]; extern regex_t ignore_callees_regex; extern int have_ignore_callees; extern int sort__need_collapse; +extern int sort__has_dso; extern int sort__has_parent; extern int sort__has_sym; extern int sort__has_socket; +extern int sort__has_thread; +extern int sort__has_comm; extern enum sort_mode sort__mode; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; @@ -94,9 +97,11 @@ struct hist_entry { s32 socket; s32 cpu; u8 cpumode; + u8 depth; /* We are added by hists__add_dummy_entry. */ bool dummy; + bool leaf; char level; u8 filtered; @@ -113,18 +118,28 @@ struct hist_entry { bool init_have_children; bool unfolded; bool has_children; + bool has_no_entry; }; }; char *srcline; char *srcfile; struct symbol *parent; - struct rb_root sorted_chain; struct branch_info *branch_info; struct hists *hists; struct mem_info *mem_info; void *raw_data; u32 raw_size; void *trace_output; + struct perf_hpp_list *hpp_list; + struct hist_entry *parent_he; + union { + /* this is for hierarchical entry structure */ + struct { + struct rb_root hroot_in; + struct rb_root hroot_out; + }; /* non-leaf entries */ + struct rb_root sorted_chain; /* leaf entry has callchains */ + }; struct callchain_root callchain[0]; /* must be last member */ }; @@ -160,6 +175,17 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he) return period * 100.0 / total_period; } +static inline u64 cl_address(u64 address) +{ + /* return the cacheline of the address */ + return (address & ~(cacheline_size - 1)); +} + +static inline u64 cl_offset(u64 address) +{ + /* return the cacheline of the address */ + return (address & (cacheline_size - 1)); +} enum sort_mode { SORT_MODE__NORMAL, @@ -221,6 +247,7 @@ struct sort_entry { int64_t (*se_sort)(struct hist_entry *, struct hist_entry *); int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); + int (*se_filter)(struct hist_entry *he, int type, const void *arg); u8 se_width_idx; }; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 6ac03146889d2..b33ffb2af2cf5 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -2,6 +2,7 @@ #include "evsel.h" #include "stat.h" #include "color.h" +#include "pmu.h" enum { CTX_BIT_USER = 1 << 0, @@ -14,6 +15,13 @@ enum { #define NUM_CTX CTX_BIT_MAX +/* + * AGGR_GLOBAL: Use CPU 0 + * AGGR_SOCKET: Use first CPU of socket + * AGGR_CORE: Use first CPU of core + * AGGR_NONE: Use matching CPU + * AGGR_THREAD: Not supported? + */ static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS]; @@ -28,9 +36,15 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS]; +static bool have_frontend_stalled; struct stats walltime_nsecs_stats; +void perf_stat__init_shadow_stats(void) +{ + have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend"); +} + static int evsel_context(struct perf_evsel *evsel) { int ctx = 0; @@ -137,9 +151,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static void print_stalled_cycles_frontend(FILE *out, int cpu, +static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel - __maybe_unused, double avg) + __maybe_unused, double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -152,14 +167,17 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu, color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio); - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " frontend cycles idle "); + if (ratio) + out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle", + ratio); + else + out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0); } -static void print_stalled_cycles_backend(FILE *out, int cpu, +static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel - __maybe_unused, double avg) + __maybe_unused, double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -172,14 +190,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu, color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio); - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " backend cycles idle "); + out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio); } -static void print_branch_misses(FILE *out, int cpu, +static void print_branch_misses(int cpu, struct perf_evsel *evsel __maybe_unused, - double avg) + double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -192,14 +209,13 @@ static void print_branch_misses(FILE *out, int cpu, color = get_ratio_color(GRC_CACHE_MISSES, ratio); - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " of all branches "); + out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio); } -static void print_l1_dcache_misses(FILE *out, int cpu, +static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __maybe_unused, - double avg) + double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -212,14 +228,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu, color = get_ratio_color(GRC_CACHE_MISSES, ratio); - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " of all L1-dcache hits "); + out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio); } -static void print_l1_icache_misses(FILE *out, int cpu, +static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __maybe_unused, - double avg) + double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -231,15 +246,13 @@ static void print_l1_icache_misses(FILE *out, int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " of all L1-icache hits "); + out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio); } -static void print_dtlb_cache_misses(FILE *out, int cpu, +static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __maybe_unused, - double avg) + double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -251,15 +264,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " of all dTLB cache hits "); + out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio); } -static void print_itlb_cache_misses(FILE *out, int cpu, +static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __maybe_unused, - double avg) + double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -271,15 +282,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " of all iTLB cache hits "); + out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio); } -static void print_ll_cache_misses(FILE *out, int cpu, +static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __maybe_unused, - double avg) + double avg, + struct perf_stat_output_ctx *out) { double total, ratio = 0.0; const char *color; @@ -291,15 +300,15 @@ static void print_ll_cache_misses(FILE *out, int cpu, ratio = avg / total * 100.0; color = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(out, " # "); - color_fprintf(out, color, "%6.2f%%", ratio); - fprintf(out, " of all LL-cache hits "); + out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio); } -void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, - double avg, int cpu, enum aggr_mode aggr) +void perf_stat__print_shadow_stats(struct perf_evsel *evsel, + double avg, int cpu, + struct perf_stat_output_ctx *out) { + void *ctxp = out->ctx; + print_metric_t print_metric = out->print_metric; double total, ratio = 0.0, total2; int ctx = evsel_context(evsel); @@ -307,119 +316,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, total = avg_stats(&runtime_cycles_stats[ctx][cpu]); if (total) { ratio = avg / total; - fprintf(out, " # %5.2f insns per cycle ", ratio); + print_metric(ctxp, NULL, "%7.2f ", + "insn per cycle", ratio); } else { - fprintf(out, " "); + print_metric(ctxp, NULL, NULL, "insn per cycle", 0); } total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]); total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu])); if (total && avg) { + out->new_line(ctxp); ratio = total / avg; - fprintf(out, "\n"); - if (aggr == AGGR_NONE) - fprintf(out, " "); - fprintf(out, " # %5.2f stalled cycles per insn", ratio); + print_metric(ctxp, NULL, "%7.2f ", + "stalled cycles per insn", + ratio); + } else if (have_frontend_stalled) { + print_metric(ctxp, NULL, NULL, + "stalled cycles per insn", 0); } - - } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) && - runtime_branches_stats[ctx][cpu].n != 0) { - print_branch_misses(out, cpu, evsel, avg); + } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { + if (runtime_branches_stats[ctx][cpu].n != 0) + print_branch_misses(cpu, evsel, avg, out); + else + print_metric(ctxp, NULL, NULL, "of all branches", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) && - runtime_l1_dcache_stats[ctx][cpu].n != 0) { - print_l1_dcache_misses(out, cpu, evsel, avg); + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { + if (runtime_l1_dcache_stats[ctx][cpu].n != 0) + print_l1_dcache_misses(cpu, evsel, avg, out); + else + print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) && - runtime_l1_icache_stats[ctx][cpu].n != 0) { - print_l1_icache_misses(out, cpu, evsel, avg); + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { + if (runtime_l1_icache_stats[ctx][cpu].n != 0) + print_l1_icache_misses(cpu, evsel, avg, out); + else + print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) && - runtime_dtlb_cache_stats[ctx][cpu].n != 0) { - print_dtlb_cache_misses(out, cpu, evsel, avg); + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { + if (runtime_dtlb_cache_stats[ctx][cpu].n != 0) + print_dtlb_cache_misses(cpu, evsel, avg, out); + else + print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) && - runtime_itlb_cache_stats[ctx][cpu].n != 0) { - print_itlb_cache_misses(out, cpu, evsel, avg); + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { + if (runtime_itlb_cache_stats[ctx][cpu].n != 0) + print_itlb_cache_misses(cpu, evsel, avg, out); + else + print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0); } else if ( evsel->attr.type == PERF_TYPE_HW_CACHE && evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL | ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) && - runtime_ll_cache_stats[ctx][cpu].n != 0) { - print_ll_cache_misses(out, cpu, evsel, avg); - } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) && - runtime_cacherefs_stats[ctx][cpu].n != 0) { + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { + if (runtime_ll_cache_stats[ctx][cpu].n != 0) + print_ll_cache_misses(cpu, evsel, avg, out); + else + print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0); + } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]); if (total) ratio = avg * 100 / total; - fprintf(out, " # %8.3f %% of all cache refs ", ratio); - + if (runtime_cacherefs_stats[ctx][cpu].n != 0) + print_metric(ctxp, NULL, "%8.3f %%", + "of all cache refs", ratio); + else + print_metric(ctxp, NULL, NULL, "of all cache refs", 0); } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(out, cpu, evsel, avg); + print_stalled_cycles_frontend(cpu, evsel, avg, out); } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(out, cpu, evsel, avg); + print_stalled_cycles_backend(cpu, evsel, avg, out); } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { total = avg_stats(&runtime_nsecs_stats[cpu]); if (total) { ratio = avg / total; - fprintf(out, " # %8.3f GHz ", ratio); + print_metric(ctxp, NULL, "%8.3f", "GHz", ratio); } else { - fprintf(out, " "); + print_metric(ctxp, NULL, NULL, "Ghz", 0); } } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) { total = avg_stats(&runtime_cycles_stats[ctx][cpu]); if (total) - fprintf(out, - " # %5.2f%% transactional cycles ", - 100.0 * (avg / total)); + print_metric(ctxp, NULL, + "%7.2f%%", "transactional cycles", + 100.0 * (avg / total)); + else + print_metric(ctxp, NULL, NULL, "transactional cycles", + 0); } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) { total = avg_stats(&runtime_cycles_stats[ctx][cpu]); total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]); if (total2 < avg) total2 = avg; if (total) - fprintf(out, - " # %5.2f%% aborted cycles ", + print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles", 100.0 * ((total2-avg) / total)); - } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) && - runtime_cycles_in_tx_stats[ctx][cpu].n != 0) { + else + print_metric(ctxp, NULL, NULL, "aborted cycles", 0); + } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) { total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]); if (avg) ratio = total / avg; - fprintf(out, " # %8.0f cycles / transaction ", ratio); - } else if (perf_stat_evsel__is(evsel, ELISION_START) && - runtime_cycles_in_tx_stats[ctx][cpu].n != 0) { + if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0) + print_metric(ctxp, NULL, "%8.0f", + "cycles / transaction", ratio); + else + print_metric(ctxp, NULL, NULL, "cycles / transaction", + 0); + } else if (perf_stat_evsel__is(evsel, ELISION_START)) { total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]); if (avg) ratio = total / avg; - fprintf(out, " # %8.0f cycles / elision ", ratio); + print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio); } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) - fprintf(out, " # %8.3f CPUs utilized ", avg / ratio); + print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", + avg / ratio); else - fprintf(out, " "); + print_metric(ctxp, NULL, NULL, "CPUs utilized", 0); } else if (runtime_nsecs_stats[cpu].n != 0) { char unit = 'M'; + char unit_buf[10]; total = avg_stats(&runtime_nsecs_stats[cpu]); @@ -429,9 +464,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, ratio *= 1000; unit = 'K'; } - - fprintf(out, " # %8.3f %c/sec ", ratio, unit); + snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); + print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio); } else { - fprintf(out, " "); + print_metric(ctxp, NULL, NULL, NULL, 0); } } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index afb0c45eba34b..4d9b481cf3b6e 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) { int i; struct perf_stat_evsel *ps = evsel->priv; @@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) perf_stat_evsel_id_init(evsel); } -int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) +static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat_evsel)); if (evsel->priv == NULL) @@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) return 0; } -void perf_evsel__free_stat_priv(struct perf_evsel *evsel) +static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) { zfree(&evsel->priv); } -int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, - int ncpus, int nthreads) +static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads) { struct perf_counts *counts; @@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, return counts ? 0 : -ENOMEM; } -void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) +static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) { perf_counts__delete(evsel->prev_raw_counts); evsel->prev_raw_counts = NULL; } -int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) +static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) { int ncpus = perf_evsel__nr_cpus(evsel); int nthreads = thread_map__nr(evsel->threads); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 086f4e128d635..0150e786ccc7c 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -68,21 +68,23 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel); extern struct stats walltime_nsecs_stats; +typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit, + const char *fmt, double val); +typedef void (*new_line_t )(void *ctx); + +void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, int cpu); -void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, - double avg, int cpu, enum aggr_mode aggr); - -void perf_evsel__reset_stat_priv(struct perf_evsel *evsel); -int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); -void perf_evsel__free_stat_priv(struct perf_evsel *evsel); - -int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, - int ncpus, int nthreads); -void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel); +struct perf_stat_output_ctx { + void *ctx; + print_metric_t print_metric; + new_line_t new_line; +}; -int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw); +void perf_stat__print_shadow_stats(struct perf_evsel *evsel, + double avg, int cpu, + struct perf_stat_output_ctx *out); int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); void perf_evlist__free_stats(struct perf_evlist *evlist); diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 25671fa166188..d3d279275432e 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -51,30 +51,6 @@ void strbuf_grow(struct strbuf *sb, size_t extra) ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); } -static void strbuf_splice(struct strbuf *sb, size_t pos, size_t len, - const void *data, size_t dlen) -{ - if (pos + len < pos) - die("you want to use way too much memory"); - if (pos > sb->len) - die("`pos' is too far after the end of the buffer"); - if (pos + len > sb->len) - die("`pos + len' is too far after the end of the buffer"); - - if (dlen >= len) - strbuf_grow(sb, dlen - len); - memmove(sb->buf + pos + dlen, - sb->buf + pos + len, - sb->len - pos - len); - memcpy(sb->buf + pos, data, dlen); - strbuf_setlen(sb, sb->len + dlen - len); -} - -void strbuf_remove(struct strbuf *sb, size_t pos, size_t len) -{ - strbuf_splice(sb, pos, len, NULL, 0); -} - void strbuf_add(struct strbuf *sb, const void *data, size_t len) { strbuf_grow(sb, len); diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index 529f2f0352491..7a32c838884d8 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -77,8 +77,6 @@ static inline void strbuf_addch(struct strbuf *sb, int c) { sb->buf[sb->len] = '\0'; } -extern void strbuf_remove(struct strbuf *, size_t pos, size_t len); - extern void strbuf_add(struct strbuf *, const void *, size_t); static inline void strbuf_addstr(struct strbuf *sb, const char *s) { strbuf_add(sb, s, strlen(s)); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 562b8ebeae5b2..b1dd68f358fcd 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -6,6 +6,7 @@ #include #include "symbol.h" +#include "demangle-java.h" #include "machine.h" #include "vdso.h" #include @@ -1077,6 +1078,8 @@ int dso__load_sym(struct dso *dso, struct map *map, demangle_flags = DMGL_PARAMS | DMGL_ANSI; demangled = bfd_demangle(NULL, elf_name, demangle_flags); + if (demangled == NULL) + demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET); if (demangled != NULL) elf_name = demangled; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index ab02209a7cf3b..e7588dc915181 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) + if (is_regular_file(name) && + filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); /* @@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) root_dir, name, PATH_MAX)) continue; + if (!is_regular_file(name)) + continue; + /* Name is now the name of the next image to try */ if (symsrc__init(ss, dso, name, symtab_type) < 0) continue; @@ -1525,6 +1529,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (!runtime_ss && syms_ss) runtime_ss = syms_ss; + if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE) + if (dso__build_id_is_kmod(dso, name, PATH_MAX)) + kmod = true; + if (syms_ss) ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod); else diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index ccd1caa40e116..a937053a0ae07 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -110,7 +110,8 @@ struct symbol_conf { has_filter, show_ref_callgraph, hide_unresolved, - raw_trace; + raw_trace, + report_hierarchy; const char *vmlinux_name, *kallsyms_name, *source_prefix, diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 802bb868d446c..8ae051e0ec790 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "trace-event.h" #include "machine.h" #include "util.h" diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c index 4d4210d4e13d1..1b741646eed00 100644 --- a/tools/perf/util/tsc.c +++ b/tools/perf/util/tsc.c @@ -19,7 +19,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) u64 quot, rem; quot = cyc >> tc->time_shift; - rem = cyc & ((1 << tc->time_shift) - 1); + rem = cyc & (((u64)1 << tc->time_shift) - 1); return tc->time_zero + quot * tc->time_mult + ((rem * tc->time_mult) >> tc->time_shift); } diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index ead9509835d23..b7766c577b015 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "callchain.h" #include "strlist.h" @@ -507,54 +508,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param) return ret; } -int filename__read_str(const char *filename, char **buf, size_t *sizep) -{ - size_t size = 0, alloc_size = 0; - void *bf = NULL, *nbf; - int fd, n, err = 0; - char sbuf[STRERR_BUFSIZE]; - - fd = open(filename, O_RDONLY); - if (fd < 0) - return -errno; - - do { - if (size == alloc_size) { - alloc_size += BUFSIZ; - nbf = realloc(bf, alloc_size); - if (!nbf) { - err = -ENOMEM; - break; - } - - bf = nbf; - } - - n = read(fd, bf + size, alloc_size - size); - if (n < 0) { - if (size) { - pr_warning("read failed %d: %s\n", errno, - strerror_r(errno, sbuf, sizeof(sbuf))); - err = 0; - } else - err = -errno; - - break; - } - - size += n; - } while (n > 0); - - if (!err) { - *sizep = size; - *buf = bf; - } else - free(bf); - - close(fd); - return err; -} - const char *get_filename_for_perf_kvm(void) { const char *filename; @@ -691,3 +644,66 @@ const char *perf_tip(const char *dirpath) return tip; } + +bool is_regular_file(const char *file) +{ + struct stat st; + + if (stat(file, &st)) + return false; + + return S_ISREG(st.st_mode); +} + +int fetch_current_timestamp(char *buf, size_t sz) +{ + struct timeval tv; + struct tm tm; + char dt[32]; + + if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm)) + return -1; + + if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm)) + return -1; + + scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); + + return 0; +} + +void print_binary(unsigned char *data, size_t len, + size_t bytes_per_line, print_binary_t printer, + void *extra) +{ + size_t i, j, mask; + + if (!printer) + return; + + bytes_per_line = roundup_pow_of_two(bytes_per_line); + mask = bytes_per_line - 1; + + printer(BINARY_PRINT_DATA_BEGIN, 0, extra); + for (i = 0; i < len; i++) { + if ((i & mask) == 0) { + printer(BINARY_PRINT_LINE_BEGIN, -1, extra); + printer(BINARY_PRINT_ADDR, i, extra); + } + + printer(BINARY_PRINT_NUM_DATA, data[i], extra); + + if (((i & mask) == mask) || i == len - 1) { + for (j = 0; j < mask-(i & mask); j++) + printer(BINARY_PRINT_NUM_PAD, -1, extra); + + printer(BINARY_PRINT_SEP, i, extra); + for (j = i & ~mask; j <= i; j++) + printer(BINARY_PRINT_CHAR_DATA, data[j], extra); + for (j = 0; j < mask-(i & mask); j++) + printer(BINARY_PRINT_CHAR_PAD, i, extra); + printer(BINARY_PRINT_LINE_END, -1, extra); + } + } + printer(BINARY_PRINT_DATA_END, -1, extra); +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index fe915e616f9b6..d0d50cef8b2af 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -82,6 +82,8 @@ extern const char *graph_line; extern const char *graph_dotted_line; +extern const char *spaces; +extern const char *dots; extern char buildid_dir[]; /* On most systems would have given us this, but @@ -303,7 +305,6 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, bool show_sym, bool unwind_inlines); void free_srcline(char *srcline); -int filename__read_str(const char *filename, char **buf, size_t *sizep); int perf_event_paranoid(void); void mem_bswap_64(void *src, int byte_size); @@ -343,5 +344,27 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) const char *perf_tip(const char *dirpath); +bool is_regular_file(const char *file); +int fetch_current_timestamp(char *buf, size_t sz); + +enum binary_printer_ops { + BINARY_PRINT_DATA_BEGIN, + BINARY_PRINT_LINE_BEGIN, + BINARY_PRINT_ADDR, + BINARY_PRINT_NUM_DATA, + BINARY_PRINT_NUM_PAD, + BINARY_PRINT_SEP, + BINARY_PRINT_CHAR_DATA, + BINARY_PRINT_CHAR_PAD, + BINARY_PRINT_LINE_END, + BINARY_PRINT_DATA_END, +}; + +typedef void (*print_binary_t)(enum binary_printer_ops, + unsigned int val, + void *extra); +void print_binary(unsigned char *data, size_t len, + size_t bytes_per_line, print_binary_t printer, + void *extra); #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 0dac7e05a6ac9..3fa94e291d16a 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1970,7 +1970,7 @@ int has_config_tdp(unsigned int family, unsigned int model) } static void -dump_cstate_pstate_config_info(family, model) +dump_cstate_pstate_config_info(unsigned int family, unsigned int model) { if (!do_nhm_platform_info) return; @@ -2142,7 +2142,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data #define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */ #define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */ -double get_tdp(model) +double get_tdp(unsigned int model) { unsigned long long msr; @@ -2256,7 +2256,7 @@ void rapl_probe(unsigned int family, unsigned int model) return; } -void perf_limit_reasons_probe(family, model) +void perf_limit_reasons_probe(unsigned int family, unsigned int model) { if (!genuine_intel) return; @@ -2792,7 +2792,7 @@ void process_cpuid() perf_limit_reasons_probe(family, model); if (debug) - dump_cstate_pstate_config_info(); + dump_cstate_pstate_config_info(family, model); if (has_skl_msrs(family, model)) calculate_tsc_tweak(); diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 844787a0d7bed..5eb49b7f864c7 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -33,7 +33,7 @@ if grep -Pq '\x00' < $file then print_warning Console output contains nul bytes, old qemu still running? fi -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags if test -s $1.diags then print_warning Assertion failure in $file $title @@ -64,10 +64,12 @@ then then summary="$summary lockdep: $n_badness" fi - n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|Stall ended before state dump start' $1` + n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1` if test "$n_stalls" -ne 0 then summary="$summary Stalls: $n_stalls" fi print_warning Summary: $summary +else + rm $1.diags fi diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index d0c473f658505..d5ce7d7aae3e4 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -4,15 +4,16 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean -TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall -TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \ +TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall \ + check_initial_reg_state sigreturn ldt_gdt +TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ - ldt_gdt \ vdso_restorer TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) +TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY) BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32) -BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64) +BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64) CFLAGS := -O2 -g -std=gnu99 -pthread -Wall @@ -40,7 +41,7 @@ clean: $(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c $(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm -$(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c +$(TARGETS_C_64BIT_ALL:%=%_64): %_64: %.c $(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl # x86_64 users should be encouraged to install 32-bit libraries @@ -65,3 +66,9 @@ endif sysret_ss_attrs_64: thunks.S ptrace_syscall_32: raw_syscall_helper_32.S test_syscall_vdso_32: thunks_32.S + +# check_initial_reg_state is special: it needs a custom entry, and it +# needs to be static so that its interpreter doesn't destroy its initial +# state. +check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static +check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static diff --git a/tools/testing/selftests/x86/check_initial_reg_state.c b/tools/testing/selftests/x86/check_initial_reg_state.c new file mode 100644 index 0000000000000..6aaed9b85bafb --- /dev/null +++ b/tools/testing/selftests/x86/check_initial_reg_state.c @@ -0,0 +1,109 @@ +/* + * check_initial_reg_state.c - check that execve sets the correct state + * Copyright (c) 2014-2016 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#define _GNU_SOURCE + +#include + +unsigned long ax, bx, cx, dx, si, di, bp, sp, flags; +unsigned long r8, r9, r10, r11, r12, r13, r14, r15; + +asm ( + ".pushsection .text\n\t" + ".type real_start, @function\n\t" + ".global real_start\n\t" + "real_start:\n\t" +#ifdef __x86_64__ + "mov %rax, ax\n\t" + "mov %rbx, bx\n\t" + "mov %rcx, cx\n\t" + "mov %rdx, dx\n\t" + "mov %rsi, si\n\t" + "mov %rdi, di\n\t" + "mov %rbp, bp\n\t" + "mov %rsp, sp\n\t" + "mov %r8, r8\n\t" + "mov %r9, r9\n\t" + "mov %r10, r10\n\t" + "mov %r11, r11\n\t" + "mov %r12, r12\n\t" + "mov %r13, r13\n\t" + "mov %r14, r14\n\t" + "mov %r15, r15\n\t" + "pushfq\n\t" + "popq flags\n\t" +#else + "mov %eax, ax\n\t" + "mov %ebx, bx\n\t" + "mov %ecx, cx\n\t" + "mov %edx, dx\n\t" + "mov %esi, si\n\t" + "mov %edi, di\n\t" + "mov %ebp, bp\n\t" + "mov %esp, sp\n\t" + "pushfl\n\t" + "popl flags\n\t" +#endif + "jmp _start\n\t" + ".size real_start, . - real_start\n\t" + ".popsection"); + +int main() +{ + int nerrs = 0; + + if (sp == 0) { + printf("[FAIL]\tTest was built incorrectly\n"); + return 1; + } + + if (ax || bx || cx || dx || si || di || bp +#ifdef __x86_64__ + || r8 || r9 || r10 || r11 || r12 || r13 || r14 || r15 +#endif + ) { + printf("[FAIL]\tAll GPRs except SP should be 0\n"); +#define SHOW(x) printf("\t" #x " = 0x%lx\n", x); + SHOW(ax); + SHOW(bx); + SHOW(cx); + SHOW(dx); + SHOW(si); + SHOW(di); + SHOW(bp); + SHOW(sp); +#ifdef __x86_64__ + SHOW(r8); + SHOW(r9); + SHOW(r10); + SHOW(r11); + SHOW(r12); + SHOW(r13); + SHOW(r14); + SHOW(r15); +#endif + nerrs++; + } else { + printf("[OK]\tAll GPRs except SP are 0\n"); + } + + if (flags != 0x202) { + printf("[FAIL]\tFLAGS is 0x%lx, but it should be 0x202\n", flags); + nerrs++; + } else { + printf("[OK]\tFLAGS is 0x202\n"); + } + + return nerrs ? 1 : 0; +} diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c index 5105b49cd8aa5..421456784bc64 100644 --- a/tools/testing/selftests/x86/ptrace_syscall.c +++ b/tools/testing/selftests/x86/ptrace_syscall.c @@ -103,6 +103,17 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), err(1, "sigaction"); } +static void setsigign(int sig, int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = (void *)SIG_IGN; + sa.sa_flags = flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + static void clearhandler(int sig) { struct sigaction sa; @@ -187,7 +198,7 @@ static void test_ptrace_syscall_restart(void) printf("[RUN]\tSYSEMU\n"); if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0) - err(1, "PTRACE_SYSCALL"); + err(1, "PTRACE_SYSEMU"); wait_trap(chld); if (ptrace(PTRACE_GETREGS, chld, 0, ®s) != 0) @@ -218,7 +229,7 @@ static void test_ptrace_syscall_restart(void) err(1, "PTRACE_SETREGS"); if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0) - err(1, "PTRACE_SYSCALL"); + err(1, "PTRACE_SYSEMU"); wait_trap(chld); if (ptrace(PTRACE_GETREGS, chld, 0, ®s) != 0) @@ -250,7 +261,7 @@ static void test_ptrace_syscall_restart(void) err(1, "PTRACE_SETREGS"); if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0) - err(1, "PTRACE_SYSCALL"); + err(1, "PTRACE_SYSEMU"); wait_trap(chld); if (ptrace(PTRACE_GETREGS, chld, 0, ®s) != 0) @@ -277,6 +288,119 @@ static void test_ptrace_syscall_restart(void) } } +static void test_restart_under_ptrace(void) +{ + printf("[RUN]\tkernel syscall restart under ptrace\n"); + pid_t chld = fork(); + if (chld < 0) + err(1, "fork"); + + if (chld == 0) { + if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0) + err(1, "PTRACE_TRACEME"); + + printf("\tChild will take a nap until signaled\n"); + setsigign(SIGUSR1, SA_RESTART); + raise(SIGSTOP); + + syscall(SYS_pause, 0, 0, 0, 0, 0, 0); + _exit(0); + } + + int status; + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status)) + err(1, "waitpid"); + + struct user_regs_struct regs; + + printf("[RUN]\tSYSCALL\n"); + if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0) + err(1, "PTRACE_SYSCALL"); + wait_trap(chld); + + /* We should be stopped at pause(2) entry. */ + + if (ptrace(PTRACE_GETREGS, chld, 0, ®s) != 0) + err(1, "PTRACE_GETREGS"); + + if (regs.user_syscall_nr != SYS_pause || + regs.user_arg0 != 0 || regs.user_arg1 != 0 || + regs.user_arg2 != 0 || regs.user_arg3 != 0 || + regs.user_arg4 != 0 || regs.user_arg5 != 0) { + printf("[FAIL]\tInitial args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5); + nerrs++; + } else { + printf("[OK]\tInitial nr and args are correct\n"); + } + + /* Interrupt it. */ + kill(chld, SIGUSR1); + + /* Advance. We should be stopped at exit. */ + printf("[RUN]\tSYSCALL\n"); + if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0) + err(1, "PTRACE_SYSCALL"); + wait_trap(chld); + + if (ptrace(PTRACE_GETREGS, chld, 0, ®s) != 0) + err(1, "PTRACE_GETREGS"); + + if (regs.user_syscall_nr != SYS_pause || + regs.user_arg0 != 0 || regs.user_arg1 != 0 || + regs.user_arg2 != 0 || regs.user_arg3 != 0 || + regs.user_arg4 != 0 || regs.user_arg5 != 0) { + printf("[FAIL]\tArgs after SIGUSR1 are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5); + nerrs++; + } else { + printf("[OK]\tArgs after SIGUSR1 are correct (ax = %ld)\n", + (long)regs.user_ax); + } + + /* Poke the regs back in. This must not break anything. */ + if (ptrace(PTRACE_SETREGS, chld, 0, ®s) != 0) + err(1, "PTRACE_SETREGS"); + + /* Catch the (ignored) SIGUSR1. */ + if (ptrace(PTRACE_CONT, chld, 0, 0) != 0) + err(1, "PTRACE_CONT"); + if (waitpid(chld, &status, 0) != chld) + err(1, "waitpid"); + if (!WIFSTOPPED(status)) { + printf("[FAIL]\tChild was stopped for SIGUSR1 (status = 0x%x)\n", status); + nerrs++; + } else { + printf("[OK]\tChild got SIGUSR1\n"); + } + + /* The next event should be pause(2) again. */ + printf("[RUN]\tStep again\n"); + if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0) + err(1, "PTRACE_SYSCALL"); + wait_trap(chld); + + /* We should be stopped at pause(2) entry. */ + + if (ptrace(PTRACE_GETREGS, chld, 0, ®s) != 0) + err(1, "PTRACE_GETREGS"); + + if (regs.user_syscall_nr != SYS_pause || + regs.user_arg0 != 0 || regs.user_arg1 != 0 || + regs.user_arg2 != 0 || regs.user_arg3 != 0 || + regs.user_arg4 != 0 || regs.user_arg5 != 0) { + printf("[FAIL]\tpause did not restart (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5); + nerrs++; + } else { + printf("[OK]\tpause(2) restarted correctly\n"); + } + + /* Kill it. */ + kill(chld, SIGKILL); + if (waitpid(chld, &status, 0) != chld) + err(1, "waitpid"); +} + int main() { printf("[RUN]\tCheck int80 return regs\n"); @@ -290,5 +414,7 @@ int main() test_ptrace_syscall_restart(); + test_restart_under_ptrace(); + return 0; } diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c index b5aa1bab74163..8a577e7070c64 100644 --- a/tools/testing/selftests/x86/sigreturn.c +++ b/tools/testing/selftests/x86/sigreturn.c @@ -54,6 +54,37 @@ #include #include +/* Pull in AR_xyz defines. */ +typedef unsigned int u32; +typedef unsigned short u16; +#include "../../../../arch/x86/include/asm/desc_defs.h" + +/* + * Copied from asm/ucontext.h, as asm/ucontext.h conflicts badly with the glibc + * headers. + */ +#ifdef __x86_64__ +/* + * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on + * kernels that save SS in the sigcontext. All kernels that set + * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp + * regardless of SS (i.e. they implement espfix). + * + * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS + * when delivering a signal that came from 64-bit code. + * + * Sigreturn restores SS as follows: + * + * if (saved SS is valid || UC_STRICT_RESTORE_SS is set || + * saved CS is not 64-bit) + * new SS = saved SS (will fail IRET and signal if invalid) + * else + * new SS = a flat 32-bit data segment + */ +#define UC_SIGCONTEXT_SS 0x2 +#define UC_STRICT_RESTORE_SS 0x4 +#endif + /* * In principle, this test can run on Linux emulation layers (e.g. * Illumos "LX branded zones"). Solaris-based kernels reserve LDT @@ -267,6 +298,9 @@ static gregset_t initial_regs, requested_regs, resulting_regs; /* Instructions for the SIGUSR1 handler. */ static volatile unsigned short sig_cs, sig_ss; static volatile sig_atomic_t sig_trapped, sig_err, sig_trapno; +#ifdef __x86_64__ +static volatile sig_atomic_t sig_corrupt_final_ss; +#endif /* Abstractions for some 32-bit vs 64-bit differences. */ #ifdef __x86_64__ @@ -305,9 +339,105 @@ static greg_t *csptr(ucontext_t *ctx) } #endif +/* + * Checks a given selector for its code bitness or returns -1 if it's not + * a usable code segment selector. + */ +int cs_bitness(unsigned short cs) +{ + uint32_t valid = 0, ar; + asm ("lar %[cs], %[ar]\n\t" + "jnz 1f\n\t" + "mov $1, %[valid]\n\t" + "1:" + : [ar] "=r" (ar), [valid] "+rm" (valid) + : [cs] "r" (cs)); + + if (!valid) + return -1; + + bool db = (ar & (1 << 22)); + bool l = (ar & (1 << 21)); + + if (!(ar & (1<<11))) + return -1; /* Not code. */ + + if (l && !db) + return 64; + else if (!l && db) + return 32; + else if (!l && !db) + return 16; + else + return -1; /* Unknown bitness. */ +} + +/* + * Checks a given selector for its code bitness or returns -1 if it's not + * a usable code segment selector. + */ +bool is_valid_ss(unsigned short cs) +{ + uint32_t valid = 0, ar; + asm ("lar %[cs], %[ar]\n\t" + "jnz 1f\n\t" + "mov $1, %[valid]\n\t" + "1:" + : [ar] "=r" (ar), [valid] "+rm" (valid) + : [cs] "r" (cs)); + + if (!valid) + return false; + + if ((ar & AR_TYPE_MASK) != AR_TYPE_RWDATA && + (ar & AR_TYPE_MASK) != AR_TYPE_RWDATA_EXPDOWN) + return false; + + return (ar & AR_P); +} + /* Number of errors in the current test case. */ static volatile sig_atomic_t nerrs; +static void validate_signal_ss(int sig, ucontext_t *ctx) +{ +#ifdef __x86_64__ + bool was_64bit = (cs_bitness(*csptr(ctx)) == 64); + + if (!(ctx->uc_flags & UC_SIGCONTEXT_SS)) { + printf("[FAIL]\tUC_SIGCONTEXT_SS was not set\n"); + nerrs++; + + /* + * This happens on Linux 4.1. The rest will fail, too, so + * return now to reduce the noise. + */ + return; + } + + /* UC_STRICT_RESTORE_SS is set iff we came from 64-bit mode. */ + if (!!(ctx->uc_flags & UC_STRICT_RESTORE_SS) != was_64bit) { + printf("[FAIL]\tUC_STRICT_RESTORE_SS was wrong in signal %d\n", + sig); + nerrs++; + } + + if (is_valid_ss(*ssptr(ctx))) { + /* + * DOSEMU was written before 64-bit sigcontext had SS, and + * it tries to figure out the signal source SS by looking at + * the physical register. Make sure that keeps working. + */ + unsigned short hw_ss; + asm ("mov %%ss, %0" : "=rm" (hw_ss)); + if (hw_ss != *ssptr(ctx)) { + printf("[FAIL]\tHW SS didn't match saved SS\n"); + nerrs++; + } + } +#endif +} + /* * SIGUSR1 handler. Sets CS and SS as requested and points IP to the * int3 trampoline. Sets SP to a large known value so that we can see @@ -317,6 +447,8 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void) { ucontext_t *ctx = (ucontext_t*)ctx_void; + validate_signal_ss(sig, ctx); + memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); *csptr(ctx) = sig_cs; @@ -334,13 +466,16 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void) } /* - * Called after a successful sigreturn. Restores our state so that - * the original raise(SIGUSR1) returns. + * Called after a successful sigreturn (via int3) or from a failed + * sigreturn (directly by kernel). Restores our state so that the + * original raise(SIGUSR1) returns. */ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) { ucontext_t *ctx = (ucontext_t*)ctx_void; + validate_signal_ss(sig, ctx); + sig_err = ctx->uc_mcontext.gregs[REG_ERR]; sig_trapno = ctx->uc_mcontext.gregs[REG_TRAPNO]; @@ -358,41 +493,62 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) memcpy(&resulting_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t)); +#ifdef __x86_64__ + if (sig_corrupt_final_ss) { + if (ctx->uc_flags & UC_STRICT_RESTORE_SS) { + printf("[FAIL]\tUC_STRICT_RESTORE_SS was set inappropriately\n"); + nerrs++; + } else { + /* + * DOSEMU transitions from 32-bit to 64-bit mode by + * adjusting sigcontext, and it requires that this work + * even if the saved SS is bogus. + */ + printf("\tCorrupting SS on return to 64-bit mode\n"); + *ssptr(ctx) = 0; + } + } +#endif + sig_trapped = sig; } -/* - * Checks a given selector for its code bitness or returns -1 if it's not - * a usable code segment selector. - */ -int cs_bitness(unsigned short cs) +#ifdef __x86_64__ +/* Tests recovery if !UC_STRICT_RESTORE_SS */ +static void sigusr2(int sig, siginfo_t *info, void *ctx_void) { - uint32_t valid = 0, ar; - asm ("lar %[cs], %[ar]\n\t" - "jnz 1f\n\t" - "mov $1, %[valid]\n\t" - "1:" - : [ar] "=r" (ar), [valid] "+rm" (valid) - : [cs] "r" (cs)); + ucontext_t *ctx = (ucontext_t*)ctx_void; - if (!valid) - return -1; + if (!(ctx->uc_flags & UC_STRICT_RESTORE_SS)) { + printf("[FAIL]\traise(2) didn't set UC_STRICT_RESTORE_SS\n"); + nerrs++; + return; /* We can't do the rest. */ + } - bool db = (ar & (1 << 22)); - bool l = (ar & (1 << 21)); + ctx->uc_flags &= ~UC_STRICT_RESTORE_SS; + *ssptr(ctx) = 0; - if (!(ar & (1<<11))) - return -1; /* Not code. */ + /* Return. The kernel should recover without sending another signal. */ +} - if (l && !db) - return 64; - else if (!l && db) - return 32; - else if (!l && !db) - return 16; - else - return -1; /* Unknown bitness. */ +static int test_nonstrict_ss(void) +{ + clearhandler(SIGUSR1); + clearhandler(SIGTRAP); + clearhandler(SIGSEGV); + clearhandler(SIGILL); + sethandler(SIGUSR2, sigusr2, 0); + + nerrs = 0; + + printf("[RUN]\tClear UC_STRICT_RESTORE_SS and corrupt SS\n"); + raise(SIGUSR2); + if (!nerrs) + printf("[OK]\tIt worked\n"); + + return nerrs; } +#endif /* Finds a usable code segment of the requested bitness. */ int find_cs(int bitness) @@ -576,6 +732,12 @@ static int test_bad_iret(int cs_bits, unsigned short ss, int force_cs) errdesc, strsignal(sig_trapped)); return 0; } else { + /* + * This also implicitly tests UC_STRICT_RESTORE_SS: + * We check that these signals set UC_STRICT_RESTORE_SS and, + * if UC_STRICT_RESTORE_SS doesn't cause strict behavior, + * then we won't get SIGSEGV. + */ printf("[FAIL]\tDid not get SIGSEGV\n"); return 1; } @@ -632,6 +794,14 @@ int main() GDT3(gdt_data16_idx)); } +#ifdef __x86_64__ + /* Nasty ABI case: check SS corruption handling. */ + sig_corrupt_final_ss = 1; + total_nerrs += test_valid_sigreturn(32, false, -1); + total_nerrs += test_valid_sigreturn(32, true, -1); + sig_corrupt_final_ss = 0; +#endif + /* * We're done testing valid sigreturn cases. Now we test states * for which sigreturn itself will succeed but the subsequent @@ -680,5 +850,9 @@ int main() if (gdt_npdata32_idx) test_bad_iret(32, GDT3(gdt_npdata32_idx), -1); +#ifdef __x86_64__ + total_nerrs += test_nonstrict_ss(); +#endif + return total_nerrs ? 1 : 0; } diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c index 60c06af4646a3..43fcab367fb0a 100644 --- a/tools/testing/selftests/x86/syscall_nt.c +++ b/tools/testing/selftests/x86/syscall_nt.c @@ -17,6 +17,9 @@ #include #include +#include +#include +#include #include #include @@ -26,6 +29,8 @@ # define WIDTH "l" #endif +static unsigned int nerrs; + static unsigned long get_eflags(void) { unsigned long eflags; @@ -39,16 +44,52 @@ static void set_eflags(unsigned long eflags) : : "rm" (eflags) : "flags"); } -int main() +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) { - printf("[RUN]\tSet NT and issue a syscall\n"); - set_eflags(get_eflags() | X86_EFLAGS_NT); + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void sigtrap(int sig, siginfo_t *si, void *ctx_void) +{ +} + +static void do_it(unsigned long extraflags) +{ + unsigned long flags; + + set_eflags(get_eflags() | extraflags); syscall(SYS_getpid); - if (get_eflags() & X86_EFLAGS_NT) { - printf("[OK]\tThe syscall worked and NT is still set\n"); - return 0; + flags = get_eflags(); + if ((flags & extraflags) == extraflags) { + printf("[OK]\tThe syscall worked and flags are still set\n"); } else { - printf("[FAIL]\tThe syscall worked but NT was cleared\n"); - return 1; + printf("[FAIL]\tThe syscall worked but flags were cleared (flags = 0x%lx but expected 0x%lx set)\n", + flags, extraflags); + nerrs++; } } + +int main(void) +{ + printf("[RUN]\tSet NT and issue a syscall\n"); + do_it(X86_EFLAGS_NT); + + /* + * Now try it again with TF set -- TF forces returns via IRET in all + * cases except non-ptregs-using 64-bit full fast path syscalls. + */ + + sethandler(SIGTRAP, sigtrap, 0); + + printf("[RUN]\tSet NT|TF and issue a syscall\n"); + do_it(X86_EFLAGS_NT | X86_EFLAGS_TF); + + return nerrs == 0 ? 0 : 1; +} diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index db2dd3335c6a6..65da997b430a8 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -97,8 +97,8 @@ static void async_pf_execute(struct work_struct *work) * This memory barrier pairs with prepare_to_wait's set_current_state() */ smp_mb(); - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) + swake_up(&vcpu->wq); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a11cfd20a6a0d..5af50c3ddd535 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -216,8 +216,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; - vcpu->halt_poll_ns = 0; - init_waitqueue_head(&vcpu->wq); + init_swait_queue_head(&vcpu->wq); kvm_async_pf_vcpu_init(vcpu); vcpu->pre_pcpu = -1; @@ -1952,6 +1951,9 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) else val *= halt_poll_ns_grow; + if (val > halt_poll_ns) + val = halt_poll_ns; + vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); } @@ -1990,7 +1992,7 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) void kvm_vcpu_block(struct kvm_vcpu *vcpu) { ktime_t start, cur; - DEFINE_WAIT(wait); + DECLARE_SWAITQUEUE(wait); bool waited = false; u64 block_ns; @@ -2015,7 +2017,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) kvm_arch_vcpu_blocking(vcpu); for (;;) { - prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; @@ -2024,7 +2026,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) schedule(); } - finish_wait(&vcpu->wq, &wait); + finish_swait(&vcpu->wq, &wait); cur = ktime_get(); kvm_arch_vcpu_unblocking(vcpu); @@ -2056,11 +2058,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { int me; int cpu = vcpu->cpu; - wait_queue_head_t *wqp; + struct swait_queue_head *wqp; wqp = kvm_arch_vcpu_wq(vcpu); - if (waitqueue_active(wqp)) { - wake_up_interruptible(wqp); + if (swait_active(wqp)) { + swake_up(wqp); ++vcpu->stat.halt_wakeup; } @@ -2161,7 +2163,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me) continue; if (vcpu == me) continue; - if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue;