From 49e7e0f3545dcec6653e2f9af57d0df236d1abfe Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 14 Jun 2009 13:42:43 -0700 Subject: [PATCH] --- yaml --- r: 149406 b: refs/heads/master c: 2cf4d4514d5b43c1f3b64bd0ec8b9853bde8f1dc h: refs/heads/master v: v3 --- [refs] | 2 +- trunk/Documentation/ABI/testing/sysfs-block | 59 + .../ABI/testing/sysfs-bus-pci-devices-cciss | 33 + .../ABI/testing/sysfs-devices-cache_disable | 18 + trunk/Documentation/Changes | 15 + trunk/Documentation/DMA-API.txt | 12 + trunk/Documentation/DocBook/Makefile | 3 +- trunk/Documentation/DocBook/tracepoint.tmpl | 89 + trunk/Documentation/RCU/trace.txt | 102 +- trunk/Documentation/Smack.txt | 20 +- trunk/Documentation/SubmittingPatches | 76 +- trunk/Documentation/block/biodoc.txt | 2 +- .../development-process/5.Posting | 31 +- .../feature-removal-schedule.txt | 10 + trunk/Documentation/filesystems/debugfs.txt | 158 + .../Documentation/filesystems/gfs2-glocks.txt | 2 +- trunk/Documentation/filesystems/gfs2.txt | 19 +- trunk/Documentation/futex-requeue-pi.txt | 131 + trunk/Documentation/i2c/busses/i2c-ocores | 17 + trunk/Documentation/ide/ide.txt | 2 + trunk/Documentation/kernel-parameters.txt | 67 +- trunk/Documentation/kmemleak.txt | 142 + trunk/Documentation/lguest/Makefile | 3 +- trunk/Documentation/lguest/lguest.c | 1008 +-- trunk/Documentation/lguest/lguest.txt | 1 - trunk/Documentation/memory-barriers.txt | 129 +- trunk/Documentation/power/devices.txt | 34 +- .../scheduler/sched-rt-group.txt | 20 +- .../sound/alsa/ALSA-Configuration.txt | 36 +- .../sound/alsa/HD-Audio-Models.txt | 18 +- trunk/Documentation/sound/alsa/Procfile.txt | 36 +- trunk/Documentation/sound/alsa/README.maya44 | 163 + trunk/Documentation/sound/alsa/soc/dapm.txt | 1 + trunk/Documentation/sysctl/kernel.txt | 11 + trunk/Documentation/trace/events.txt | 90 + trunk/Documentation/trace/ftrace.txt | 17 +- trunk/Documentation/trace/power.txt | 17 + trunk/Documentation/x86/boot.txt | 122 +- .../Documentation/x86/x86_64/boot-options.txt | 49 +- trunk/Documentation/x86/x86_64/machinecheck | 8 +- trunk/Documentation/x86/x86_64/mm.txt | 9 +- trunk/MAINTAINERS | 50 +- trunk/Makefile | 4 +- trunk/arch/alpha/include/asm/atomic.h | 2 +- trunk/arch/alpha/include/asm/bitsperlong.h | 8 + trunk/arch/alpha/include/asm/page.h | 2 +- trunk/arch/alpha/include/asm/signal.h | 2 +- trunk/arch/alpha/include/asm/suspend.h | 6 - trunk/arch/alpha/include/asm/types.h | 3 - trunk/arch/alpha/kernel/osf_sys.c | 3 - trunk/arch/alpha/kernel/sys_dp264.c | 8 +- trunk/arch/alpha/kernel/sys_titan.c | 4 +- trunk/arch/alpha/mm/extable.c | 21 + trunk/arch/arm/common/gic.c | 4 +- trunk/arch/arm/include/asm/atomic.h | 2 +- trunk/arch/arm/include/asm/bitsperlong.h | 1 + trunk/arch/arm/include/asm/cache.h | 16 + trunk/arch/arm/include/asm/mman.h | 2 +- trunk/arch/arm/include/asm/page.h | 9 +- trunk/arch/arm/include/asm/signal.h | 2 +- trunk/arch/arm/include/asm/suspend.h | 4 - trunk/arch/arm/mach-mx2/clock_imx21.c | 2 +- trunk/arch/arm/mach-mx2/clock_imx27.c | 2 +- trunk/arch/arm/mach-mx3/clock-imx35.c | 2 +- trunk/arch/arm/mach-mx3/clock.c | 2 +- trunk/arch/arm/mach-pxa/devices.c | 5 +- trunk/arch/arm/mach-pxa/imote2.c | 2 +- trunk/arch/arm/mm/proc-v7.S | 36 +- .../arch/arm/plat-mxc/include/mach/imx-uart.h | 5 + trunk/arch/arm/plat-omap/mailbox.c | 63 +- trunk/arch/avr32/boards/atngw100/Kconfig | 27 +- trunk/arch/avr32/boards/atngw100/Kconfig_mrmt | 80 + trunk/arch/avr32/boards/atngw100/Makefile | 1 + trunk/arch/avr32/boards/atngw100/mrmt.c | 373 + trunk/arch/avr32/boards/atngw100/setup.c | 5 + trunk/arch/avr32/boards/merisc/setup.c | 7 +- trunk/arch/avr32/boards/mimc200/setup.c | 29 +- .../avr32/configs/atngw100_mrmt_defconfig | 1363 ++++ trunk/arch/avr32/include/asm/atomic.h | 2 +- trunk/arch/avr32/include/asm/bitsperlong.h | 1 + trunk/arch/avr32/include/asm/hw_irq.h | 2 +- trunk/arch/avr32/include/asm/mman.h | 2 +- trunk/arch/avr32/include/asm/signal.h | 2 +- trunk/arch/avr32/include/asm/termios.h | 2 +- trunk/arch/avr32/kernel/module.c | 2 - trunk/arch/avr32/kernel/traps.c | 11 +- .../avr32/mach-at32ap/include/mach/board.h | 2 +- trunk/arch/blackfin/Kconfig | 84 +- trunk/arch/blackfin/Kconfig.debug | 13 + .../blackfin/configs/BF518F-EZBRD_defconfig | 101 +- .../blackfin/configs/BF526-EZBRD_defconfig | 219 +- .../blackfin/configs/BF527-EZKIT_defconfig | 211 +- .../blackfin/configs/BF533-EZKIT_defconfig | 103 +- .../blackfin/configs/BF533-STAMP_defconfig | 105 +- .../blackfin/configs/BF537-STAMP_defconfig | 109 +- .../blackfin/configs/BF538-EZKIT_defconfig | 106 +- .../blackfin/configs/BF548-EZKIT_defconfig | 253 +- .../blackfin/configs/BF561-EZKIT_defconfig | 116 +- .../blackfin/configs/BlackStamp_defconfig | 4 +- .../arch/blackfin/configs/CM-BF527_defconfig | 29 +- .../arch/blackfin/configs/CM-BF533_defconfig | 12 +- .../arch/blackfin/configs/CM-BF537E_defconfig | 499 +- .../arch/blackfin/configs/CM-BF537U_defconfig | 12 +- .../arch/blackfin/configs/CM-BF548_defconfig | 12 +- .../arch/blackfin/configs/CM-BF561_defconfig | 12 +- trunk/arch/blackfin/configs/H8606_defconfig | 8 +- trunk/arch/blackfin/configs/IP0X_defconfig | 8 +- trunk/arch/blackfin/configs/PNAV-10_defconfig | 39 +- trunk/arch/blackfin/configs/SRV1_defconfig | 4 +- .../arch/blackfin/configs/TCM-BF537_defconfig | 27 +- trunk/arch/blackfin/include/asm/atomic.h | 2 +- trunk/arch/blackfin/include/asm/bitsperlong.h | 1 + trunk/arch/blackfin/include/asm/cacheflush.h | 40 +- trunk/arch/blackfin/include/asm/cplb.h | 35 +- trunk/arch/blackfin/include/asm/dma.h | 10 +- trunk/arch/blackfin/include/asm/elf.h | 84 +- trunk/arch/blackfin/include/asm/entry.h | 92 +- trunk/arch/blackfin/include/asm/gptimers.h | 43 +- trunk/arch/blackfin/include/asm/io.h | 29 +- trunk/arch/blackfin/include/asm/ipipe.h | 4 +- trunk/arch/blackfin/include/asm/page.h | 2 +- trunk/arch/blackfin/include/asm/pda.h | 2 - trunk/arch/blackfin/include/asm/processor.h | 4 +- trunk/arch/blackfin/include/asm/signal.h | 2 +- trunk/arch/blackfin/include/asm/time.h | 1 + trunk/arch/blackfin/include/asm/uaccess.h | 32 +- trunk/arch/blackfin/kernel/bfin_dma_5xx.c | 86 + trunk/arch/blackfin/kernel/bfin_gpio.c | 18 - trunk/arch/blackfin/kernel/bfin_ksyms.c | 1 - .../arch/blackfin/kernel/cplb-mpu/cacheinit.c | 9 +- .../arch/blackfin/kernel/cplb-mpu/cplbinit.c | 2 +- .../blackfin/kernel/cplb-nompu/cacheinit.c | 9 +- trunk/arch/blackfin/kernel/early_printk.c | 16 +- trunk/arch/blackfin/kernel/gptimers.c | 30 +- trunk/arch/blackfin/kernel/ipipe.c | 9 +- trunk/arch/blackfin/kernel/irqchip.c | 2 + trunk/arch/blackfin/kernel/kgdb.c | 60 +- trunk/arch/blackfin/kernel/module.c | 22 +- trunk/arch/blackfin/kernel/process.c | 3 + trunk/arch/blackfin/kernel/setup.c | 79 +- trunk/arch/blackfin/kernel/sys_bfin.c | 5 - trunk/arch/blackfin/kernel/time-ts.c | 222 +- trunk/arch/blackfin/kernel/time.c | 53 +- trunk/arch/blackfin/kernel/traps.c | 52 +- trunk/arch/blackfin/kernel/vmlinux.lds.S | 5 + trunk/arch/blackfin/mach-bf518/Kconfig | 1 + trunk/arch/blackfin/mach-bf518/boards/ezbrd.c | 19 +- .../mach-bf518/include/mach/anomaly.h | 35 +- .../mach-bf518/include/mach/portmux.h | 6 +- trunk/arch/blackfin/mach-bf527/Kconfig | 1 + .../blackfin/mach-bf527/boards/cm_bf527.c | 10 +- trunk/arch/blackfin/mach-bf527/boards/ezbrd.c | 10 +- trunk/arch/blackfin/mach-bf527/boards/ezkit.c | 28 +- .../mach-bf527/include/mach/anomaly.h | 168 +- trunk/arch/blackfin/mach-bf533/Kconfig | 1 + trunk/arch/blackfin/mach-bf533/boards/H8606.c | 4 +- .../blackfin/mach-bf533/boards/cm_bf533.c | 4 +- trunk/arch/blackfin/mach-bf533/boards/ezkit.c | 4 +- trunk/arch/blackfin/mach-bf533/boards/stamp.c | 6 +- .../mach-bf533/include/mach/anomaly.h | 88 +- trunk/arch/blackfin/mach-bf537/Kconfig | 1 + .../blackfin/mach-bf537/boards/cm_bf537.c | 4 +- .../arch/blackfin/mach-bf537/boards/pnav10.c | 8 +- trunk/arch/blackfin/mach-bf537/boards/stamp.c | 69 +- .../blackfin/mach-bf537/boards/tcm_bf537.c | 4 +- .../mach-bf537/include/mach/anomaly.h | 84 +- trunk/arch/blackfin/mach-bf538/Kconfig | 1 + .../mach-bf538/include/mach/anomaly.h | 60 +- .../mach-bf538/include/mach/blackfin.h | 19 - .../mach-bf538/include/mach/cdefBF538.h | 65 +- .../mach-bf538/include/mach/defBF539.h | 56 + trunk/arch/blackfin/mach-bf548/Kconfig | 8 + trunk/arch/blackfin/mach-bf548/boards/ezkit.c | 85 +- .../mach-bf548/include/mach/anomaly.h | 44 +- .../mach-bf548/include/mach/portmux.h | 64 +- trunk/arch/blackfin/mach-bf561/Kconfig | 16 +- .../blackfin/mach-bf561/boards/cm_bf561.c | 4 +- trunk/arch/blackfin/mach-bf561/coreb.c | 396 +- .../mach-bf561/include/mach/anomaly.h | 25 +- .../mach-bf561/include/mach/cdefBF561.h | 29 + .../mach-bf561/include/mach/defBF561.h | 56 + trunk/arch/blackfin/mach-bf561/smp.c | 4 +- trunk/arch/blackfin/mach-common/arch_checks.c | 7 + trunk/arch/blackfin/mach-common/cache.S | 46 +- trunk/arch/blackfin/mach-common/clocks-init.c | 1 + trunk/arch/blackfin/mach-common/cpufreq.c | 3 +- trunk/arch/blackfin/mach-common/entry.S | 76 +- trunk/arch/blackfin/mach-common/head.S | 34 +- trunk/arch/blackfin/mach-common/interrupt.S | 27 + .../arch/blackfin/mach-common/ints-priority.c | 50 +- trunk/arch/blackfin/mach-common/smp.c | 12 +- trunk/arch/blackfin/mm/blackfin_sram.h | 1 - trunk/arch/blackfin/mm/init.c | 33 +- trunk/arch/blackfin/mm/isram-driver.c | 2 +- trunk/arch/blackfin/mm/sram-alloc.c | 21 +- trunk/arch/cris/arch-v32/kernel/irq.c | 4 +- trunk/arch/cris/include/asm/atomic.h | 2 +- trunk/arch/cris/include/asm/bitsperlong.h | 1 + trunk/arch/cris/include/asm/mman.h | 2 +- trunk/arch/cris/include/asm/page.h | 2 +- trunk/arch/cris/include/asm/signal.h | 2 +- trunk/arch/cris/kernel/module.c | 2 - trunk/arch/frv/Kconfig | 1 + trunk/arch/frv/include/asm/atomic.h | 2 +- trunk/arch/frv/include/asm/bitops.h | 29 +- trunk/arch/frv/include/asm/bitsperlong.h | 1 + trunk/arch/frv/include/asm/elf.h | 1 + trunk/arch/frv/include/asm/mman.h | 2 +- trunk/arch/frv/include/asm/page.h | 2 +- trunk/arch/frv/include/asm/pci.h | 20 +- trunk/arch/frv/include/asm/ptrace.h | 11 +- trunk/arch/frv/include/asm/signal.h | 123 +- trunk/arch/frv/include/asm/syscall.h | 123 + trunk/arch/frv/include/asm/termios.h | 2 +- trunk/arch/frv/include/asm/thread_info.h | 10 +- trunk/arch/frv/kernel/entry.S | 13 +- trunk/arch/frv/kernel/module.c | 2 - trunk/arch/frv/kernel/ptrace.c | 755 +- trunk/arch/frv/kernel/signal.c | 10 + trunk/arch/frv/kernel/uaccess.c | 6 +- trunk/arch/frv/mb93090-mb00/pci-dma-nommu.c | 6 +- trunk/arch/frv/mb93090-mb00/pci-dma.c | 6 +- trunk/arch/h8300/include/asm/atomic.h | 2 +- trunk/arch/h8300/include/asm/bitsperlong.h | 1 + trunk/arch/h8300/include/asm/mman.h | 2 +- trunk/arch/h8300/include/asm/page.h | 2 +- trunk/arch/h8300/include/asm/signal.h | 2 +- trunk/arch/h8300/kernel/module.c | 2 - trunk/arch/ia64/hp/sim/hpsim_irq.c | 3 +- trunk/arch/ia64/include/asm/atomic.h | 2 +- trunk/arch/ia64/include/asm/bitsperlong.h | 8 + trunk/arch/ia64/include/asm/kvm_host.h | 6 +- trunk/arch/ia64/include/asm/mman.h | 2 +- trunk/arch/ia64/include/asm/pgtable.h | 2 + trunk/arch/ia64/include/asm/signal.h | 2 +- trunk/arch/ia64/include/asm/suspend.h | 1 - trunk/arch/ia64/include/asm/types.h | 7 - trunk/arch/ia64/kernel/acpi.c | 5 +- trunk/arch/ia64/kernel/iosapic.c | 10 +- trunk/arch/ia64/kernel/irq_ia64.c | 3 + trunk/arch/ia64/kernel/msi_ia64.c | 16 +- trunk/arch/ia64/kvm/Kconfig | 2 +- trunk/arch/ia64/kvm/kvm-ia64.c | 263 +- trunk/arch/ia64/kvm/kvm_fw.c | 28 +- trunk/arch/ia64/kvm/lapic.h | 6 +- trunk/arch/ia64/kvm/optvfault.S | 30 + trunk/arch/ia64/kvm/process.c | 5 + trunk/arch/ia64/kvm/vcpu.c | 20 +- trunk/arch/ia64/kvm/vmm.c | 12 +- trunk/arch/ia64/kvm/vmm_ivt.S | 18 +- trunk/arch/ia64/kvm/vtlb.c | 3 +- trunk/arch/ia64/mm/extable.c | 26 + trunk/arch/ia64/sn/kernel/irq.c | 4 +- trunk/arch/ia64/sn/kernel/msi_sn.c | 8 +- trunk/arch/m32r/include/asm/atomic.h | 2 +- trunk/arch/m32r/include/asm/bitsperlong.h | 1 + trunk/arch/m32r/include/asm/mman.h | 2 +- trunk/arch/m32r/include/asm/page.h | 2 +- trunk/arch/m32r/include/asm/pci.h | 2 - trunk/arch/m32r/include/asm/signal.h | 2 +- trunk/arch/m32r/kernel/module.c | 2 - trunk/arch/m68k/include/asm/atomic_mm.h | 2 +- trunk/arch/m68k/include/asm/atomic_no.h | 2 +- trunk/arch/m68k/include/asm/bitsperlong.h | 1 + trunk/arch/m68k/include/asm/m520xsim.h | 9 + trunk/arch/m68k/include/asm/m523xsim.h | 9 + trunk/arch/m68k/include/asm/m527xsim.h | 9 + trunk/arch/m68k/include/asm/m528xsim.h | 8 + trunk/arch/m68k/include/asm/m532xsim.h | 12 + trunk/arch/m68k/include/asm/mman.h | 2 +- trunk/arch/m68k/include/asm/page_mm.h | 2 +- trunk/arch/m68k/include/asm/page_no.h | 2 +- trunk/arch/m68k/include/asm/processor_no.h | 8 +- trunk/arch/m68k/include/asm/signal.h | 2 +- trunk/arch/m68k/include/asm/suspend.h | 6 - trunk/arch/m68k/include/asm/swab.h | 2 +- trunk/arch/m68k/include/asm/system_no.h | 107 - trunk/arch/m68k/kernel/module.c | 2 - trunk/arch/m68knommu/kernel/entry.S | 1 - trunk/arch/m68knommu/kernel/module.c | 2 - trunk/arch/m68knommu/kernel/setup.c | 16 +- trunk/arch/m68knommu/mm/init.c | 4 +- trunk/arch/m68knommu/platform/5206/config.c | 18 +- trunk/arch/m68knommu/platform/5206e/config.c | 18 +- trunk/arch/m68knommu/platform/520x/config.c | 15 +- trunk/arch/m68knommu/platform/523x/config.c | 14 +- trunk/arch/m68knommu/platform/5249/config.c | 18 +- trunk/arch/m68knommu/platform/5272/config.c | 18 +- trunk/arch/m68knommu/platform/527x/config.c | 15 +- trunk/arch/m68knommu/platform/528x/config.c | 13 +- trunk/arch/m68knommu/platform/5307/config.c | 16 +- trunk/arch/m68knommu/platform/532x/config.c | 12 +- trunk/arch/m68knommu/platform/5407/config.c | 16 +- .../m68knommu/platform/coldfire/vectors.c | 7 - trunk/arch/microblaze/Kconfig | 121 +- trunk/arch/microblaze/Makefile | 6 + trunk/arch/microblaze/boot/Makefile | 2 + trunk/arch/microblaze/configs/mmu_defconfig | 798 ++ trunk/arch/microblaze/include/asm/Kbuild | 25 +- trunk/arch/microblaze/include/asm/atomic.h | 2 +- .../arch/microblaze/include/asm/bitsperlong.h | 1 + .../arch/microblaze/include/asm/cacheflush.h | 20 +- trunk/arch/microblaze/include/asm/checksum.h | 14 +- trunk/arch/microblaze/include/asm/current.h | 8 + .../arch/microblaze/include/asm/dma-mapping.h | 130 +- trunk/arch/microblaze/include/asm/dma.h | 5 + trunk/arch/microblaze/include/asm/elf.h | 93 + trunk/arch/microblaze/include/asm/entry.h | 37 +- .../arch/microblaze/include/asm/exceptions.h | 24 +- trunk/arch/microblaze/include/asm/flat.h | 1 - trunk/arch/microblaze/include/asm/gpio.h | 6 +- trunk/arch/microblaze/include/asm/io.h | 31 + trunk/arch/microblaze/include/asm/mmu.h | 104 +- .../arch/microblaze/include/asm/mmu_context.h | 26 +- .../microblaze/include/asm/mmu_context_mm.h | 140 + .../microblaze/include/asm/mmu_context_no.h | 23 + trunk/arch/microblaze/include/asm/page.h | 168 +- trunk/arch/microblaze/include/asm/pgalloc.h | 191 + trunk/arch/microblaze/include/asm/pgtable.h | 538 ++ .../arch/microblaze/include/asm/posix_types.h | 2 +- trunk/arch/microblaze/include/asm/processor.h | 95 +- trunk/arch/microblaze/include/asm/ptrace.h | 1 - trunk/arch/microblaze/include/asm/registers.h | 21 +- trunk/arch/microblaze/include/asm/sections.h | 3 + trunk/arch/microblaze/include/asm/segment.h | 20 +- trunk/arch/microblaze/include/asm/setup.h | 10 +- trunk/arch/microblaze/include/asm/signal.h | 2 +- trunk/arch/microblaze/include/asm/stat.h | 77 +- trunk/arch/microblaze/include/asm/string.h | 2 +- trunk/arch/microblaze/include/asm/syscalls.h | 3 + trunk/arch/microblaze/include/asm/termios.h | 2 +- .../arch/microblaze/include/asm/thread_info.h | 20 + trunk/arch/microblaze/include/asm/tlb.h | 8 + trunk/arch/microblaze/include/asm/tlbflush.h | 48 + trunk/arch/microblaze/include/asm/uaccess.h | 305 +- trunk/arch/microblaze/include/asm/unaligned.h | 3 +- trunk/arch/microblaze/kernel/Makefile | 1 + trunk/arch/microblaze/kernel/asm-offsets.c | 21 +- trunk/arch/microblaze/kernel/early_printk.c | 3 + trunk/arch/microblaze/kernel/entry-nommu.S | 2 +- trunk/arch/microblaze/kernel/entry.S | 1116 +++ trunk/arch/microblaze/kernel/exceptions.c | 45 +- trunk/arch/microblaze/kernel/head.S | 190 + .../microblaze/kernel/hw_exception_handler.S | 746 +- .../arch/microblaze/kernel/microblaze_ksyms.c | 2 + trunk/arch/microblaze/kernel/misc.S | 120 + trunk/arch/microblaze/kernel/process.c | 59 + trunk/arch/microblaze/kernel/prom.c | 7 +- trunk/arch/microblaze/kernel/setup.c | 62 +- trunk/arch/microblaze/kernel/signal.c | 109 +- trunk/arch/microblaze/kernel/syscall_table.S | 6 +- trunk/arch/microblaze/kernel/traps.c | 42 +- trunk/arch/microblaze/kernel/vmlinux.lds.S | 5 +- trunk/arch/microblaze/lib/Makefile | 3 +- trunk/arch/microblaze/lib/checksum.c | 31 +- trunk/arch/microblaze/lib/memcpy.c | 5 - trunk/arch/microblaze/lib/uaccess_old.S | 135 + trunk/arch/microblaze/mm/Makefile | 2 + trunk/arch/microblaze/mm/fault.c | 304 + trunk/arch/microblaze/mm/init.c | 169 +- trunk/arch/microblaze/mm/mmu_context.c | 70 + trunk/arch/microblaze/mm/pgtable.c | 286 + trunk/arch/mips/Kconfig | 5 +- trunk/arch/mips/cavium-octeon/octeon-irq.c | 8 +- trunk/arch/mips/include/asm/atomic.h | 2 +- trunk/arch/mips/include/asm/bitsperlong.h | 8 + trunk/arch/mips/include/asm/cpu-info.h | 4 +- trunk/arch/mips/include/asm/delay.h | 92 +- trunk/arch/mips/include/asm/ioctl.h | 4 + trunk/arch/mips/include/asm/irq.h | 2 +- trunk/arch/mips/include/asm/page.h | 2 +- trunk/arch/mips/include/asm/signal.h | 2 +- trunk/arch/mips/include/asm/suspend.h | 6 - trunk/arch/mips/include/asm/types.h | 3 - trunk/arch/mips/kernel/irq-gic.c | 5 +- trunk/arch/mips/kernel/module.c | 2 - trunk/arch/mips/kernel/proc.c | 2 +- trunk/arch/mips/lib/Makefile | 4 +- trunk/arch/mips/lib/delay.c | 56 + trunk/arch/mips/mti-malta/malta-smtc.c | 4 +- trunk/arch/mips/sibyte/bcm1480/irq.c | 8 +- trunk/arch/mips/sibyte/cfe/setup.c | 8 +- trunk/arch/mips/sibyte/sb1250/irq.c | 8 +- trunk/arch/mn10300/Kconfig | 1 + trunk/arch/mn10300/include/asm/atomic.h | 2 +- trunk/arch/mn10300/include/asm/bitsperlong.h | 1 + trunk/arch/mn10300/include/asm/elf.h | 3 +- trunk/arch/mn10300/include/asm/mman.h | 2 +- trunk/arch/mn10300/include/asm/processor.h | 8 +- trunk/arch/mn10300/include/asm/ptrace.h | 8 + trunk/arch/mn10300/include/asm/signal.h | 2 +- trunk/arch/mn10300/kernel/entry.S | 13 +- trunk/arch/mn10300/kernel/module.c | 2 - trunk/arch/mn10300/kernel/ptrace.c | 454 +- trunk/arch/mn10300/kernel/signal.c | 9 + trunk/arch/mn10300/mm/tlb-mn10300.S | 18 - trunk/arch/parisc/include/asm/atomic.h | 2 +- trunk/arch/parisc/include/asm/bitsperlong.h | 20 + trunk/arch/parisc/include/asm/page.h | 2 +- trunk/arch/parisc/include/asm/types.h | 8 - trunk/arch/parisc/include/asm/uaccess.h | 2 +- trunk/arch/parisc/kernel/irq.c | 6 +- trunk/arch/parisc/kernel/module.c | 2 - trunk/arch/powerpc/include/asm/atomic.h | 2 +- trunk/arch/powerpc/include/asm/bitsperlong.h | 12 + trunk/arch/powerpc/include/asm/hw_irq.h | 36 + trunk/arch/powerpc/include/asm/mman.h | 2 +- trunk/arch/powerpc/include/asm/mpc52xx_psc.h | 11 + trunk/arch/powerpc/include/asm/paca.h | 1 + trunk/arch/powerpc/include/asm/page_32.h | 2 +- trunk/arch/powerpc/include/asm/page_64.h | 2 +- trunk/arch/powerpc/include/asm/perf_counter.h | 98 + trunk/arch/powerpc/include/asm/reg.h | 2 + trunk/arch/powerpc/include/asm/signal.h | 2 +- trunk/arch/powerpc/include/asm/systbl.h | 2 +- trunk/arch/powerpc/include/asm/termios.h | 2 +- trunk/arch/powerpc/include/asm/types.h | 9 - trunk/arch/powerpc/include/asm/unistd.h | 1 + trunk/arch/powerpc/kernel/Makefile | 3 + trunk/arch/powerpc/kernel/asm-offsets.c | 1 + trunk/arch/powerpc/kernel/entry_64.S | 9 + trunk/arch/powerpc/kernel/irq.c | 6 + trunk/arch/powerpc/kernel/module.c | 2 - trunk/arch/powerpc/kernel/perf_counter.c | 1263 +++ trunk/arch/powerpc/kernel/power4-pmu.c | 598 ++ trunk/arch/powerpc/kernel/power5+-pmu.c | 671 ++ trunk/arch/powerpc/kernel/power5-pmu.c | 611 ++ trunk/arch/powerpc/kernel/power6-pmu.c | 532 ++ trunk/arch/powerpc/kernel/power7-pmu.c | 357 + trunk/arch/powerpc/kernel/ppc970-pmu.c | 482 ++ trunk/arch/powerpc/kvm/powerpc.c | 6 + trunk/arch/powerpc/mm/fault.c | 10 +- trunk/arch/powerpc/platforms/Kconfig.cputype | 1 + trunk/arch/powerpc/platforms/pseries/xics.c | 12 +- trunk/arch/powerpc/sysdev/axonram.c | 2 +- trunk/arch/powerpc/sysdev/mpic.c | 4 +- trunk/arch/powerpc/sysdev/mpic.h | 2 +- trunk/arch/s390/Kconfig | 23 + trunk/arch/s390/include/asm/atomic.h | 2 +- trunk/arch/s390/include/asm/bitsperlong.h | 13 + trunk/arch/s390/include/asm/compat.h | 19 +- trunk/arch/s390/include/asm/cpu.h | 32 - trunk/arch/s390/include/asm/cputime.h | 19 + trunk/arch/s390/include/asm/ftrace.h | 21 + trunk/arch/s390/include/asm/kvm_host.h | 5 +- trunk/arch/s390/include/asm/lowcore.h | 9 +- trunk/arch/s390/include/asm/mman.h | 2 +- trunk/arch/s390/include/asm/page.h | 2 +- trunk/arch/s390/include/asm/pgtable.h | 7 +- trunk/arch/s390/include/asm/seccomp.h | 16 + trunk/arch/s390/include/asm/signal.h | 2 +- trunk/arch/s390/include/asm/spinlock.h | 19 +- trunk/arch/s390/include/asm/suspend.h | 5 - trunk/arch/s390/include/asm/syscall.h | 1 + trunk/arch/s390/include/asm/termios.h | 2 +- trunk/arch/s390/include/asm/thread_info.h | 12 +- trunk/arch/s390/include/asm/types.h | 6 - trunk/arch/s390/include/asm/uaccess.h | 16 +- trunk/arch/s390/include/asm/unistd.h | 4 +- trunk/arch/s390/kernel/Makefile | 7 +- trunk/arch/s390/kernel/compat_wrapper.S | 17 + trunk/arch/s390/kernel/early.c | 4 + trunk/arch/s390/kernel/entry.S | 7 +- trunk/arch/s390/kernel/entry64.S | 7 +- trunk/arch/s390/kernel/ftrace.c | 260 + trunk/arch/s390/kernel/head.S | 65 +- trunk/arch/s390/kernel/kprobes.c | 31 +- trunk/arch/s390/kernel/mcount.S | 212 +- trunk/arch/s390/kernel/module.c | 2 - trunk/arch/s390/kernel/nmi.c | 2 +- trunk/arch/s390/kernel/process.c | 3 +- trunk/arch/s390/kernel/ptrace.c | 23 +- trunk/arch/s390/kernel/s390_ext.c | 5 +- trunk/arch/s390/kernel/sclp.S | 327 + trunk/arch/s390/kernel/setup.c | 2 + trunk/arch/s390/kernel/signal.c | 3 +- trunk/arch/s390/kernel/smp.c | 3 +- trunk/arch/s390/kernel/syscalls.S | 2 + trunk/arch/s390/kernel/time.c | 9 +- trunk/arch/s390/kernel/vdso.c | 19 +- trunk/arch/s390/kernel/vmlinux.lds.S | 1 + trunk/arch/s390/kernel/vtime.c | 2 +- trunk/arch/s390/kvm/intercept.c | 28 +- trunk/arch/s390/kvm/interrupt.c | 59 +- trunk/arch/s390/kvm/kvm-s390.c | 65 +- trunk/arch/s390/kvm/kvm-s390.h | 4 +- trunk/arch/s390/kvm/priv.c | 4 +- trunk/arch/s390/kvm/sigp.c | 16 +- trunk/arch/s390/lib/spinlock.c | 40 + trunk/arch/s390/mm/Makefile | 2 +- trunk/arch/s390/mm/fault.c | 3 +- trunk/arch/s390/mm/maccess.c | 61 + trunk/arch/s390/mm/mmap.c | 11 +- trunk/arch/s390/mm/pgtable.c | 16 +- trunk/arch/sh/Kconfig | 126 +- trunk/arch/sh/Kconfig.cpu | 8 - trunk/arch/sh/Kconfig.debug | 23 +- trunk/arch/sh/Makefile | 73 +- trunk/arch/sh/boards/Kconfig | 15 +- trunk/arch/sh/boards/board-ap325rxa.c | 12 + trunk/arch/sh/boards/board-sh7785lcr.c | 44 +- trunk/arch/sh/boards/mach-cayman/Makefile | 2 +- trunk/arch/sh/boards/mach-cayman/irq.c | 17 +- trunk/arch/sh/boards/mach-cayman/panic.c | 49 + trunk/arch/sh/boards/mach-cayman/setup.c | 2 +- trunk/arch/sh/boards/mach-dreamcast/setup.c | 6 - trunk/arch/sh/boards/mach-migor/setup.c | 19 + trunk/arch/sh/boards/mach-r2d/setup.c | 50 + trunk/arch/sh/boards/mach-se/7724/Makefile | 10 + trunk/arch/sh/boards/mach-se/7724/irq.c | 139 + trunk/arch/sh/boards/mach-se/7724/setup.c | 448 ++ trunk/arch/sh/boards/mach-se/7751/Makefile | 2 - trunk/arch/sh/boards/mach-se/7751/io.c | 16 - trunk/arch/sh/boards/mach-se/7751/pci.c | 147 - trunk/arch/sh/boards/mach-se/7780/irq.c | 27 +- trunk/arch/sh/boards/mach-se/Makefile | 1 + trunk/arch/sh/boards/mach-sh03/rtc.c | 10 +- trunk/arch/sh/boards/mach-snapgear/io.c | 16 - trunk/arch/sh/boards/mach-systemh/io.c | 16 - trunk/arch/sh/boards/mach-titan/io.c | 20 +- trunk/arch/sh/boot/Makefile | 6 +- trunk/arch/sh/boot/compressed/Makefile | 50 +- trunk/arch/sh/boot/compressed/Makefile_32 | 46 - trunk/arch/sh/boot/compressed/Makefile_64 | 43 - trunk/arch/sh/boot/compressed/head_64.S | 5 +- trunk/arch/sh/boot/compressed/vmlinux_64.lds | 64 - trunk/arch/sh/cchips/Kconfig | 5 - trunk/arch/sh/cchips/hd6446x/hd64461.c | 2 +- trunk/arch/sh/configs/ap325rxa_defconfig | 37 +- trunk/arch/sh/configs/cayman_defconfig | 71 +- trunk/arch/sh/configs/dreamcast_defconfig | 39 +- trunk/arch/sh/configs/edosk7705_defconfig | 29 +- trunk/arch/sh/configs/edosk7760_defconfig | 32 +- trunk/arch/sh/configs/espt_defconfig | 39 +- trunk/arch/sh/configs/hp6xx_defconfig | 35 +- trunk/arch/sh/configs/landisk_defconfig | 48 +- trunk/arch/sh/configs/lboxre2_defconfig | 44 +- trunk/arch/sh/configs/magicpanelr2_defconfig | 30 +- trunk/arch/sh/configs/microdev_defconfig | 36 +- trunk/arch/sh/configs/migor_defconfig | 36 +- trunk/arch/sh/configs/polaris_defconfig | 30 +- trunk/arch/sh/configs/r7780mp_defconfig | 38 +- trunk/arch/sh/configs/r7785rp_defconfig | 38 +- trunk/arch/sh/configs/rsk7201_defconfig | 37 +- trunk/arch/sh/configs/rsk7203_defconfig | 40 +- trunk/arch/sh/configs/rts7751r2d1_defconfig | 43 +- .../arch/sh/configs/rts7751r2dplus_defconfig | 130 +- trunk/arch/sh/configs/sdk7780_defconfig | 38 +- trunk/arch/sh/configs/se7206_defconfig | 35 +- trunk/arch/sh/configs/se7343_defconfig | 42 +- trunk/arch/sh/configs/se7619_defconfig | 35 +- trunk/arch/sh/configs/se7705_defconfig | 34 +- trunk/arch/sh/configs/se7712_defconfig | 30 +- trunk/arch/sh/configs/se7721_defconfig | 33 +- trunk/arch/sh/configs/se7722_defconfig | 38 +- trunk/arch/sh/configs/se7724_defconfig | 1552 ++++ trunk/arch/sh/configs/se7750_defconfig | 34 +- trunk/arch/sh/configs/se7751_defconfig | 34 +- trunk/arch/sh/configs/se7780_defconfig | 38 +- trunk/arch/sh/configs/sh03_defconfig | 43 +- trunk/arch/sh/configs/sh7710voipgw_defconfig | 35 +- .../arch/sh/configs/sh7724_generic_defconfig | 707 ++ trunk/arch/sh/configs/sh7763rdp_defconfig | 35 +- .../arch/sh/configs/sh7770_generic_defconfig | 700 ++ .../arch/sh/configs/sh7785lcr_32bit_defconfig | 37 +- trunk/arch/sh/configs/sh7785lcr_defconfig | 6 +- trunk/arch/sh/configs/shmin_defconfig | 31 +- trunk/arch/sh/configs/shx3_defconfig | 32 +- trunk/arch/sh/configs/snapgear_defconfig | 40 +- trunk/arch/sh/configs/systemh_defconfig | 39 +- trunk/arch/sh/configs/titan_defconfig | 40 +- trunk/arch/sh/configs/ul2_defconfig | 37 +- trunk/arch/sh/configs/urquell_defconfig | 39 +- trunk/arch/sh/drivers/dma/Kconfig | 3 +- trunk/arch/sh/drivers/pci/Kconfig | 18 - trunk/arch/sh/drivers/pci/Makefile | 28 +- .../pci/{ops-cayman.c => fixups-cayman.c} | 12 - trunk/arch/sh/drivers/pci/fixups-dreamcast.c | 9 +- .../pci/{ops-landisk.c => fixups-landisk.c} | 33 - trunk/arch/sh/drivers/pci/fixups-lboxre2.c | 41 - trunk/arch/sh/drivers/pci/fixups-r7780rp.c | 41 +- trunk/arch/sh/drivers/pci/fixups-rts7751r2d.c | 48 +- trunk/arch/sh/drivers/pci/fixups-sdk7780.c | 63 +- trunk/arch/sh/drivers/pci/fixups-se7751.c | 111 + trunk/arch/sh/drivers/pci/fixups-se7780.c | 60 - trunk/arch/sh/drivers/pci/fixups-sh7785lcr.c | 46 - trunk/arch/sh/drivers/pci/fixups-snapgear.c | 38 + .../pci/{ops-titan.c => fixups-titan.c} | 39 - trunk/arch/sh/drivers/pci/ops-dreamcast.c | 107 +- trunk/arch/sh/drivers/pci/ops-lboxre2.c | 63 - trunk/arch/sh/drivers/pci/ops-r7780rp.c | 68 - trunk/arch/sh/drivers/pci/ops-rts7751r2d.c | 74 - trunk/arch/sh/drivers/pci/ops-sdk7780.c | 73 - trunk/arch/sh/drivers/pci/ops-se7780.c | 96 - trunk/arch/sh/drivers/pci/ops-sh03.c | 45 - trunk/arch/sh/drivers/pci/ops-sh4.c | 79 +- trunk/arch/sh/drivers/pci/ops-sh5.c | 25 - trunk/arch/sh/drivers/pci/ops-sh7785lcr.c | 66 - trunk/arch/sh/drivers/pci/ops-snapgear.c | 94 - trunk/arch/sh/drivers/pci/pci-auto.c | 545 -- trunk/arch/sh/drivers/pci/pci-dreamcast.c | 102 + trunk/arch/sh/drivers/pci/pci-sh4.h | 19 +- trunk/arch/sh/drivers/pci/pci-sh5.c | 55 +- trunk/arch/sh/drivers/pci/pci-sh5.h | 3 - trunk/arch/sh/drivers/pci/pci-sh7751.c | 215 +- trunk/arch/sh/drivers/pci/pci-sh7751.h | 12 +- trunk/arch/sh/drivers/pci/pci-sh7780.c | 224 +- trunk/arch/sh/drivers/pci/pci-sh7780.h | 16 +- trunk/arch/sh/drivers/pci/pci.c | 279 +- trunk/arch/sh/include/asm/atomic-llsc.h | 27 + trunk/arch/sh/include/asm/atomic.h | 6 +- trunk/arch/sh/include/asm/bitsperlong.h | 1 + trunk/arch/sh/include/asm/cacheflush.h | 2 - trunk/arch/sh/include/asm/clock.h | 113 +- trunk/arch/sh/include/asm/cmpxchg-llsc.h | 2 +- trunk/arch/sh/include/asm/device.h | 2 + trunk/arch/sh/include/asm/hd64461.h | 148 +- trunk/arch/sh/include/asm/io.h | 22 +- trunk/arch/sh/include/asm/irq.h | 3 +- trunk/arch/sh/include/asm/kprobes.h | 2 +- trunk/arch/sh/include/asm/machvec.h | 3 + trunk/arch/sh/include/asm/mman.h | 2 +- trunk/arch/sh/include/asm/page.h | 2 +- trunk/arch/sh/include/asm/pci.h | 118 +- trunk/arch/sh/include/asm/pgtable.h | 4 + trunk/arch/sh/include/asm/processor.h | 23 +- trunk/arch/sh/include/asm/ptrace.h | 5 + trunk/arch/sh/include/asm/rtc.h | 11 + trunk/arch/sh/include/asm/signal.h | 2 +- trunk/arch/sh/include/asm/spinlock.h | 2 +- trunk/arch/sh/include/asm/swab.h | 12 +- trunk/arch/sh/include/asm/system_32.h | 2 +- trunk/arch/sh/include/asm/timer.h | 44 - trunk/arch/sh/include/asm/types.h | 4 +- trunk/arch/sh/include/asm/ubc.h | 11 + trunk/arch/sh/include/asm/unaligned-sh4a.h | 10 +- trunk/arch/sh/include/asm/unistd_32.h | 3 +- trunk/arch/sh/include/asm/unistd_64.h | 3 +- trunk/arch/sh/include/cpu-sh2a/cpu/ubc.h | 29 +- trunk/arch/sh/include/cpu-sh3/cpu/timer.h | 67 - trunk/arch/sh/include/cpu-sh4/cpu/cache.h | 2 + trunk/arch/sh/include/cpu-sh4/cpu/freq.h | 18 + trunk/arch/sh/include/cpu-sh4/cpu/sh7722.h | 14 + trunk/arch/sh/include/cpu-sh4/cpu/sh7723.h | 14 + trunk/arch/sh/include/cpu-sh4/cpu/sh7724.h | 269 + trunk/arch/sh/include/cpu-sh4/cpu/sh7785.h | 25 + trunk/arch/sh/include/cpu-sh4/cpu/timer.h | 60 - trunk/arch/sh/include/cpu-sh5/cpu/irq.h | 1 - .../sh/include/mach-common/mach/sh7785lcr.h | 10 +- .../arch/sh/include/mach-dreamcast/mach/pci.h | 2 + trunk/arch/sh/include/mach-se/mach/se7724.h | 67 + trunk/arch/sh/kernel/Makefile_32 | 6 +- trunk/arch/sh/kernel/Makefile_64 | 9 +- trunk/arch/sh/kernel/cpu/Makefile | 1 + trunk/arch/sh/kernel/cpu/clock-cpg.c | 256 + trunk/arch/sh/kernel/cpu/clock.c | 606 +- trunk/arch/sh/kernel/cpu/init.c | 7 + trunk/arch/sh/kernel/cpu/irq/imask.c | 68 +- trunk/arch/sh/kernel/cpu/irq/intc-sh5.c | 36 +- trunk/arch/sh/kernel/cpu/irq/ipr.c | 9 + trunk/arch/sh/kernel/cpu/sh2/clock-sh7619.c | 16 +- trunk/arch/sh/kernel/cpu/sh2/setup-sh7619.c | 84 + trunk/arch/sh/kernel/cpu/sh2a/clock-sh7201.c | 14 +- trunk/arch/sh/kernel/cpu/sh2a/clock-sh7203.c | 15 +- trunk/arch/sh/kernel/cpu/sh2a/clock-sh7206.c | 12 +- trunk/arch/sh/kernel/cpu/sh2a/setup-mxg.c | 111 +- trunk/arch/sh/kernel/cpu/sh2a/setup-sh7201.c | 115 + trunk/arch/sh/kernel/cpu/sh2a/setup-sh7203.c | 154 + trunk/arch/sh/kernel/cpu/sh2a/setup-sh7206.c | 187 + trunk/arch/sh/kernel/cpu/sh3/clock-sh3.c | 12 +- trunk/arch/sh/kernel/cpu/sh3/clock-sh7705.c | 12 +- trunk/arch/sh/kernel/cpu/sh3/clock-sh7706.c | 12 +- trunk/arch/sh/kernel/cpu/sh3/clock-sh7709.c | 12 +- trunk/arch/sh/kernel/cpu/sh3/clock-sh7710.c | 12 +- trunk/arch/sh/kernel/cpu/sh3/clock-sh7712.c | 8 +- trunk/arch/sh/kernel/cpu/sh3/setup-sh7705.c | 108 + trunk/arch/sh/kernel/cpu/sh3/setup-sh770x.c | 108 + trunk/arch/sh/kernel/cpu/sh3/setup-sh7710.c | 108 + trunk/arch/sh/kernel/cpu/sh3/setup-sh7720.c | 270 + trunk/arch/sh/kernel/cpu/sh4/clock-sh4-202.c | 43 +- trunk/arch/sh/kernel/cpu/sh4/clock-sh4.c | 12 +- trunk/arch/sh/kernel/cpu/sh4/probe.c | 130 +- trunk/arch/sh/kernel/cpu/sh4/setup-sh4-202.c | 164 +- trunk/arch/sh/kernel/cpu/sh4/setup-sh7750.c | 187 + trunk/arch/sh/kernel/cpu/sh4/setup-sh7760.c | 140 +- trunk/arch/sh/kernel/cpu/sh4a/Makefile | 9 +- trunk/arch/sh/kernel/cpu/sh4a/clock-sh7343.c | 211 + trunk/arch/sh/kernel/cpu/sh4a/clock-sh7366.c | 211 + trunk/arch/sh/kernel/cpu/sh4a/clock-sh7722.c | 923 +-- trunk/arch/sh/kernel/cpu/sh4a/clock-sh7723.c | 222 + trunk/arch/sh/kernel/cpu/sh4a/clock-sh7724.c | 242 + trunk/arch/sh/kernel/cpu/sh4a/clock-sh7763.c | 46 +- trunk/arch/sh/kernel/cpu/sh4a/clock-sh7770.c | 12 +- trunk/arch/sh/kernel/cpu/sh4a/clock-sh7780.c | 43 +- trunk/arch/sh/kernel/cpu/sh4a/clock-sh7785.c | 208 +- trunk/arch/sh/kernel/cpu/sh4a/clock-sh7786.c | 47 +- trunk/arch/sh/kernel/cpu/sh4a/clock-shx3.c | 41 +- trunk/arch/sh/kernel/cpu/sh4a/pinmux-sh7724.c | 2230 ++++++ trunk/arch/sh/kernel/cpu/sh4a/setup-sh7343.c | 122 +- trunk/arch/sh/kernel/cpu/sh4a/setup-sh7366.c | 119 +- trunk/arch/sh/kernel/cpu/sh4a/setup-sh7722.c | 123 +- trunk/arch/sh/kernel/cpu/sh4a/setup-sh7723.c | 231 +- trunk/arch/sh/kernel/cpu/sh4a/setup-sh7724.c | 786 ++ trunk/arch/sh/kernel/cpu/sh4a/setup-sh7763.c | 204 + trunk/arch/sh/kernel/cpu/sh4a/setup-sh7770.c | 546 ++ trunk/arch/sh/kernel/cpu/sh4a/setup-sh7780.c | 204 + trunk/arch/sh/kernel/cpu/sh4a/setup-sh7785.c | 210 + trunk/arch/sh/kernel/cpu/sh4a/setup-sh7786.c | 393 + trunk/arch/sh/kernel/cpu/sh4a/setup-shx3.c | 209 +- trunk/arch/sh/kernel/cpu/sh5/Makefile | 3 + trunk/arch/sh/kernel/cpu/sh5/clock-sh5.c | 14 +- trunk/arch/sh/kernel/cpu/sh5/entry.S | 65 +- trunk/arch/sh/kernel/cpu/sh5/setup-sh5.c | 195 + trunk/arch/sh/kernel/io.c | 1 + trunk/arch/sh/kernel/io_trapped.c | 2 +- trunk/arch/sh/kernel/irq.c | 77 +- trunk/arch/sh/kernel/kgdb.c | 4 +- .../timer-broadcast.c => localtimer.c} | 0 trunk/arch/sh/kernel/machvec.c | 1 + trunk/arch/sh/kernel/module.c | 4 +- trunk/arch/sh/kernel/process_32.c | 4 +- trunk/arch/sh/kernel/ptrace_32.c | 8 + trunk/arch/sh/kernel/setup.c | 26 +- trunk/arch/sh/kernel/sh_ksyms_32.c | 9 - trunk/arch/sh/kernel/sh_ksyms_64.c | 2 + trunk/arch/sh/kernel/syscalls_32.S | 3 +- trunk/arch/sh/kernel/syscalls_64.S | 1 + trunk/arch/sh/kernel/time.c | 125 + trunk/arch/sh/kernel/time_32.c | 240 - trunk/arch/sh/kernel/time_64.c | 363 - trunk/arch/sh/kernel/timers/Makefile | 11 - trunk/arch/sh/kernel/timers/timer-cmt.c | 188 - trunk/arch/sh/kernel/timers/timer-mtu2.c | 202 - trunk/arch/sh/kernel/timers/timer-tmu.c | 297 - trunk/arch/sh/kernel/timers/timer.c | 55 - trunk/arch/sh/kernel/traps.c | 6 +- trunk/arch/sh/kernel/traps_32.c | 15 +- trunk/arch/sh/kernel/traps_64.c | 35 +- trunk/arch/sh/kernel/vmlinux.lds.S | 179 +- trunk/arch/sh/kernel/vmlinux_32.lds.S | 154 - trunk/arch/sh/kernel/vmlinux_64.lds.S | 163 - trunk/arch/sh/lib64/.gitignore | 1 - trunk/arch/sh/lib64/dbg.c | 182 - trunk/arch/sh/lib64/panic.c | 43 - trunk/arch/sh/lib64/sdivsi3.S | 6 +- trunk/arch/sh/lib64/udelay.c | 2 +- trunk/arch/sh/mm/Kconfig | 31 +- trunk/arch/sh/mm/cache-sh5.c | 8 +- trunk/arch/sh/mm/init.c | 3 - trunk/arch/sh/mm/ioremap_32.c | 14 +- trunk/arch/sh/mm/ioremap_64.c | 266 +- trunk/arch/sh/mm/mmap.c | 136 +- trunk/arch/sh/oprofile/common.c | 1 + trunk/arch/sh/tools/mach-types | 1 + trunk/arch/sparc/include/asm/atomic_32.h | 2 +- trunk/arch/sparc/include/asm/atomic_64.h | 2 +- trunk/arch/sparc/include/asm/bitsperlong.h | 13 + trunk/arch/sparc/include/asm/mman.h | 2 +- trunk/arch/sparc/include/asm/page_32.h | 2 +- trunk/arch/sparc/include/asm/page_64.h | 2 +- trunk/arch/sparc/include/asm/signal.h | 2 +- trunk/arch/sparc/include/asm/thread_info_64.h | 4 +- trunk/arch/sparc/include/asm/types.h | 4 - trunk/arch/sparc/include/asm/uaccess_32.h | 3 + trunk/arch/sparc/include/asm/uaccess_64.h | 2 +- trunk/arch/sparc/kernel/irq_64.c | 12 +- trunk/arch/sparc/kernel/module.c | 2 - trunk/arch/sparc/mm/extable.c | 29 + trunk/arch/um/drivers/ubd_kern.c | 36 +- trunk/arch/um/include/asm/page.h | 2 +- trunk/arch/um/include/asm/pgtable.h | 7 +- trunk/arch/um/include/asm/suspend.h | 4 - trunk/arch/um/sys-i386/Makefile | 2 +- trunk/arch/um/sys-x86_64/Makefile | 4 +- trunk/arch/um/sys-x86_64/um_module.c | 21 - trunk/arch/x86/Kbuild | 16 + trunk/arch/x86/Kconfig | 99 +- trunk/arch/x86/Kconfig.debug | 20 +- trunk/arch/x86/Makefile | 19 +- trunk/arch/x86/boot/.gitignore | 2 + trunk/arch/x86/boot/Makefile | 29 +- trunk/arch/x86/boot/a20.c | 9 +- trunk/arch/x86/boot/apm.c | 76 +- trunk/arch/x86/boot/bioscall.S | 82 + trunk/arch/x86/boot/boot.h | 48 + trunk/arch/x86/boot/compressed/.gitignore | 3 + trunk/arch/x86/boot/compressed/Makefile | 54 +- trunk/arch/x86/boot/compressed/head_32.S | 194 +- trunk/arch/x86/boot/compressed/head_64.S | 169 +- trunk/arch/x86/boot/compressed/misc.c | 12 +- trunk/arch/x86/boot/compressed/mkpiggy.c | 97 + .../{vmlinux_64.lds => vmlinux.lds.S} | 29 +- trunk/arch/x86/boot/compressed/vmlinux.scr | 10 - trunk/arch/x86/boot/compressed/vmlinux_32.lds | 43 - trunk/arch/x86/boot/edd.c | 71 +- trunk/arch/x86/boot/header.S | 30 +- trunk/arch/x86/boot/main.c | 39 +- trunk/arch/x86/boot/mca.c | 27 +- trunk/arch/x86/boot/memory.c | 79 +- trunk/arch/x86/boot/regs.c | 29 + trunk/arch/x86/boot/setup.ld | 6 + trunk/arch/x86/boot/tty.c | 52 +- trunk/arch/x86/boot/video-bios.c | 27 +- trunk/arch/x86/boot/video-vesa.c | 137 +- trunk/arch/x86/boot/video-vga.c | 95 +- trunk/arch/x86/boot/video.c | 42 +- trunk/arch/x86/boot/video.h | 14 - trunk/arch/x86/configs/i386_defconfig | 148 +- trunk/arch/x86/configs/x86_64_defconfig | 151 +- trunk/arch/x86/crypto/Makefile | 2 + trunk/arch/x86/crypto/aesni-intel_glue.c | 267 +- trunk/arch/x86/crypto/fpu.c | 166 + trunk/arch/x86/ia32/ia32entry.S | 4 +- trunk/arch/x86/include/asm/alternative.h | 59 +- trunk/arch/x86/include/asm/amd_iommu.h | 2 + trunk/arch/x86/include/asm/amd_iommu_types.h | 55 +- trunk/arch/x86/include/asm/apic.h | 33 +- trunk/arch/x86/include/asm/apicdef.h | 8 +- trunk/arch/x86/include/asm/atomic_32.h | 238 +- trunk/arch/x86/include/asm/atomic_64.h | 2 +- trunk/arch/x86/include/asm/bitsperlong.h | 13 + trunk/arch/x86/include/asm/boot.h | 15 + trunk/arch/x86/include/asm/bootparam.h | 3 +- trunk/arch/x86/include/asm/cpu_debug.h | 101 +- trunk/arch/x86/include/asm/cpufeature.h | 9 +- trunk/arch/x86/include/asm/ds.h | 82 +- trunk/arch/x86/include/asm/entry_arch.h | 13 +- trunk/arch/x86/include/asm/hardirq.h | 4 +- trunk/arch/x86/include/asm/hw_irq.h | 29 +- trunk/arch/x86/include/asm/i387.h | 43 +- trunk/arch/x86/include/asm/i8259.h | 4 - .../arch/x86/include/asm/intel_arch_perfmon.h | 31 - trunk/arch/x86/include/asm/io_apic.h | 9 +- trunk/arch/x86/include/asm/iomap.h | 5 + trunk/arch/x86/include/asm/irq_remapping.h | 2 +- trunk/arch/x86/include/asm/irq_vectors.h | 26 +- trunk/arch/x86/include/asm/k8.h | 13 + trunk/arch/x86/include/asm/kvm.h | 1 + trunk/arch/x86/include/asm/kvm_host.h | 45 +- trunk/arch/x86/include/asm/kvm_x86_emulate.h | 6 + trunk/arch/x86/include/asm/lguest.h | 7 +- trunk/arch/x86/include/asm/lguest_hcall.h | 15 +- trunk/arch/x86/include/asm/mce.h | 88 +- trunk/arch/x86/include/asm/microcode.h | 25 +- trunk/arch/x86/include/asm/mman.h | 2 +- trunk/arch/x86/include/asm/mpspec.h | 15 +- trunk/arch/x86/include/asm/msr-index.h | 8 +- trunk/arch/x86/include/asm/msr.h | 23 + trunk/arch/x86/include/asm/nmi.h | 2 +- trunk/arch/x86/include/asm/numa_64.h | 10 +- trunk/arch/x86/include/asm/page.h | 2 +- trunk/arch/x86/include/asm/page_32_types.h | 4 - trunk/arch/x86/include/asm/page_64_types.h | 22 +- trunk/arch/x86/include/asm/page_types.h | 6 + trunk/arch/x86/include/asm/paravirt.h | 22 +- trunk/arch/x86/include/asm/perf_counter.h | 100 + trunk/arch/x86/include/asm/pgtable.h | 4 + trunk/arch/x86/include/asm/pgtable_32_types.h | 4 + trunk/arch/x86/include/asm/pgtable_64.h | 6 - trunk/arch/x86/include/asm/pgtable_64_types.h | 8 +- trunk/arch/x86/include/asm/pgtable_types.h | 1 - trunk/arch/x86/include/asm/processor.h | 47 +- trunk/arch/x86/include/asm/ptrace.h | 9 +- .../arch/x86/include/asm/required-features.h | 8 +- trunk/arch/x86/include/asm/setup.h | 1 - trunk/arch/x86/include/asm/signal.h | 2 +- trunk/arch/x86/include/asm/smp.h | 2 +- trunk/arch/x86/include/asm/sparsemem.h | 2 +- trunk/arch/x86/include/asm/svm.h | 1 + trunk/arch/x86/include/asm/syscalls.h | 45 +- trunk/arch/x86/include/asm/termios.h | 1 + trunk/arch/x86/include/asm/thread_info.h | 4 +- trunk/arch/x86/include/asm/tlbflush.h | 10 +- trunk/arch/x86/include/asm/topology.h | 3 +- trunk/arch/x86/include/asm/traps.h | 5 +- trunk/arch/x86/include/asm/types.h | 6 - trunk/arch/x86/include/asm/unistd_32.h | 2 + trunk/arch/x86/include/asm/unistd_64.h | 5 +- trunk/arch/x86/include/asm/uv/uv_bau.h | 2 +- trunk/arch/x86/include/asm/uv/uv_hub.h | 6 +- trunk/arch/x86/include/asm/vmx.h | 1 + trunk/arch/x86/kernel/Makefile | 5 +- trunk/arch/x86/kernel/acpi/boot.c | 156 +- trunk/arch/x86/kernel/acpi/realmode/Makefile | 2 +- .../arch/x86/kernel/acpi/realmode/bioscall.S | 1 + trunk/arch/x86/kernel/acpi/realmode/regs.c | 1 + trunk/arch/x86/kernel/acpi/sleep.c | 2 +- trunk/arch/x86/kernel/amd_iommu.c | 500 +- trunk/arch/x86/kernel/amd_iommu_init.c | 273 +- trunk/arch/x86/kernel/apic/apic.c | 318 +- trunk/arch/x86/kernel/apic/apic_flat_64.c | 4 +- trunk/arch/x86/kernel/apic/es7000_32.c | 2 +- trunk/arch/x86/kernel/apic/io_apic.c | 910 ++- trunk/arch/x86/kernel/apic/nmi.c | 4 +- trunk/arch/x86/kernel/apic/probe_32.c | 1 - trunk/arch/x86/kernel/apic/probe_64.c | 2 +- trunk/arch/x86/kernel/apic/summit_32.c | 7 - trunk/arch/x86/kernel/apic/x2apic_cluster.c | 2 +- trunk/arch/x86/kernel/apic/x2apic_uv_x.c | 20 +- trunk/arch/x86/kernel/apm_32.c | 14 +- trunk/arch/x86/kernel/asm-offsets_32.c | 2 + trunk/arch/x86/kernel/asm-offsets_64.c | 1 + trunk/arch/x86/kernel/cpu/Makefile | 12 +- trunk/arch/x86/kernel/cpu/amd.c | 12 +- trunk/arch/x86/kernel/cpu/common.c | 25 +- trunk/arch/x86/kernel/cpu/cpu_debug.c | 431 +- trunk/arch/x86/kernel/cpu/cpufreq/Kconfig | 9 +- .../x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 8 +- .../arch/x86/kernel/cpu/cpufreq/powernow-k7.c | 2 +- .../arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 15 +- .../kernel/cpu/cpufreq/speedstep-centrino.c | 2 +- trunk/arch/x86/kernel/cpu/intel.c | 6 +- trunk/arch/x86/kernel/cpu/intel_cacheinfo.c | 153 +- trunk/arch/x86/kernel/cpu/mcheck/Makefile | 10 +- trunk/arch/x86/kernel/cpu/mcheck/k7.c | 42 +- trunk/arch/x86/kernel/cpu/mcheck/mce-inject.c | 127 + .../arch/x86/kernel/cpu/mcheck/mce-internal.h | 15 + .../arch/x86/kernel/cpu/mcheck/mce-severity.c | 218 + trunk/arch/x86/kernel/cpu/mcheck/mce.c | 1964 +++++ trunk/arch/x86/kernel/cpu/mcheck/mce.h | 26 +- trunk/arch/x86/kernel/cpu/mcheck/mce_32.c | 76 - trunk/arch/x86/kernel/cpu/mcheck/mce_64.c | 1187 --- trunk/arch/x86/kernel/cpu/mcheck/mce_amd_64.c | 203 +- trunk/arch/x86/kernel/cpu/mcheck/mce_intel.c | 74 + .../arch/x86/kernel/cpu/mcheck/mce_intel_64.c | 66 +- trunk/arch/x86/kernel/cpu/mcheck/non-fatal.c | 57 +- trunk/arch/x86/kernel/cpu/mcheck/p4.c | 86 +- trunk/arch/x86/kernel/cpu/mcheck/p5.c | 48 +- trunk/arch/x86/kernel/cpu/mcheck/p6.c | 26 +- .../arch/x86/kernel/cpu/mcheck/therm_throt.c | 73 +- trunk/arch/x86/kernel/cpu/mcheck/threshold.c | 2 +- trunk/arch/x86/kernel/cpu/mcheck/winchip.c | 17 +- trunk/arch/x86/kernel/cpu/mtrr/cleanup.c | 4 +- trunk/arch/x86/kernel/cpu/mtrr/generic.c | 24 +- trunk/arch/x86/kernel/cpu/mtrr/main.c | 2 +- trunk/arch/x86/kernel/cpu/mtrr/mtrr.h | 15 - trunk/arch/x86/kernel/cpu/mtrr/state.c | 6 +- trunk/arch/x86/kernel/cpu/perf_counter.c | 1711 +++++ trunk/arch/x86/kernel/cpu/perfctr-watchdog.c | 4 +- trunk/arch/x86/kernel/ds.c | 921 ++- trunk/arch/x86/kernel/ds_selftest.c | 408 + trunk/arch/x86/kernel/ds_selftest.h | 15 + trunk/arch/x86/kernel/dumpstack.h | 1 - trunk/arch/x86/kernel/e820.c | 46 +- trunk/arch/x86/kernel/early-quirks.c | 2 + trunk/arch/x86/kernel/entry_64.S | 40 +- trunk/arch/x86/kernel/head_32.S | 7 - trunk/arch/x86/kernel/irq.c | 47 +- .../x86/kernel/{irqinit_32.c => irqinit.c} | 155 +- trunk/arch/x86/kernel/irqinit_64.c | 177 - trunk/arch/x86/kernel/kgdb.c | 2 +- trunk/arch/x86/kernel/kvm.c | 6 +- trunk/arch/x86/kernel/microcode_amd.c | 70 +- trunk/arch/x86/kernel/microcode_core.c | 329 +- trunk/arch/x86/kernel/microcode_intel.c | 90 +- .../arch/x86/kernel/{module_64.c => module.c} | 82 +- trunk/arch/x86/kernel/module_32.c | 152 - trunk/arch/x86/kernel/mpparse.c | 34 +- trunk/arch/x86/kernel/paravirt.c | 56 +- trunk/arch/x86/kernel/pci-calgary_64.c | 54 +- trunk/arch/x86/kernel/pci-gart_64.c | 55 +- trunk/arch/x86/kernel/pci-swiotlb.c | 2 +- trunk/arch/x86/kernel/process.c | 20 +- trunk/arch/x86/kernel/process_32.c | 20 +- trunk/arch/x86/kernel/process_64.c | 20 +- trunk/arch/x86/kernel/ptrace.c | 284 +- trunk/arch/x86/kernel/quirks.c | 37 + trunk/arch/x86/kernel/reboot.c | 9 + trunk/arch/x86/kernel/setup.c | 55 +- trunk/arch/x86/kernel/setup_percpu.c | 8 + trunk/arch/x86/kernel/signal.c | 7 +- trunk/arch/x86/kernel/smp.c | 51 +- trunk/arch/x86/kernel/smpboot.c | 24 +- trunk/arch/x86/kernel/stacktrace.c | 2 +- trunk/arch/x86/kernel/syscall_table_32.S | 2 + trunk/arch/x86/kernel/tlb_uv.c | 17 +- trunk/arch/x86/kernel/traps.c | 26 +- trunk/arch/x86/kernel/tsc.c | 19 +- trunk/arch/x86/kernel/tsc_sync.c | 14 +- trunk/arch/x86/kernel/vm86_32.c | 13 +- trunk/arch/x86/kernel/vmi_32.c | 20 +- trunk/arch/x86/kernel/vmlinux.lds.S | 432 +- trunk/arch/x86/kernel/vmlinux_32.lds.S | 229 - trunk/arch/x86/kernel/vmlinux_64.lds.S | 298 - trunk/arch/x86/kernel/vsyscall_64.c | 8 - trunk/arch/x86/kvm/Kconfig | 6 + trunk/arch/x86/kvm/Makefile | 2 +- trunk/arch/x86/kvm/i8254.c | 109 +- trunk/arch/x86/kvm/i8254.h | 12 +- trunk/arch/x86/kvm/irq.c | 7 + trunk/arch/x86/kvm/kvm_timer.h | 18 + trunk/arch/x86/kvm/lapic.c | 251 +- trunk/arch/x86/kvm/lapic.h | 12 +- trunk/arch/x86/kvm/mmu.c | 194 +- trunk/arch/x86/kvm/mmu.h | 5 + trunk/arch/x86/kvm/paging_tmpl.h | 16 +- trunk/arch/x86/kvm/svm.c | 415 +- trunk/arch/x86/kvm/timer.c | 46 + trunk/arch/x86/kvm/vmx.c | 721 +- trunk/arch/x86/kvm/x86.c | 409 +- trunk/arch/x86/kvm/x86.h | 14 +- trunk/arch/x86/kvm/x86_emulate.c | 141 +- trunk/arch/x86/lguest/Kconfig | 1 - trunk/arch/x86/lguest/Makefile | 1 + trunk/arch/x86/lguest/boot.c | 193 +- trunk/arch/x86/lguest/i386_head.S | 60 +- trunk/arch/x86/lib/Makefile | 2 +- trunk/arch/x86/lib/msr-on-cpu.c | 97 - trunk/arch/x86/lib/msr.c | 183 + trunk/arch/x86/mm/dump_pagetables.c | 7 +- trunk/arch/x86/mm/fault.c | 69 +- trunk/arch/x86/mm/highmem_32.c | 2 - trunk/arch/x86/mm/init.c | 78 +- trunk/arch/x86/mm/init_32.c | 71 +- trunk/arch/x86/mm/init_64.c | 47 +- trunk/arch/x86/mm/iomap_32.c | 1 - trunk/arch/x86/mm/kmmio.c | 104 +- trunk/arch/x86/mm/memtest.c | 17 +- trunk/arch/x86/mm/mmio-mod.c | 2 + trunk/arch/x86/mm/numa_64.c | 33 +- trunk/arch/x86/mm/pageattr.c | 14 - trunk/arch/x86/mm/srat_64.c | 98 +- trunk/arch/x86/oprofile/nmi_int.c | 34 +- trunk/arch/x86/oprofile/op_model_ppro.c | 10 +- trunk/arch/x86/pci/irq.c | 84 +- trunk/arch/x86/pci/mmconfig-shared.c | 6 +- trunk/arch/x86/power/Makefile | 2 +- trunk/arch/x86/power/{cpu_64.c => cpu.c} | 165 +- trunk/arch/x86/power/cpu_32.c | 148 - trunk/arch/x86/vdso/vdso32-setup.c | 6 +- trunk/arch/x86/vdso/vma.c | 8 +- trunk/arch/x86/xen/enlighten.c | 65 +- trunk/arch/x86/xen/mmu.c | 23 +- trunk/arch/x86/xen/setup.c | 6 +- trunk/arch/x86/xen/xen-ops.h | 1 - trunk/arch/xtensa/include/asm/atomic.h | 2 +- trunk/arch/xtensa/include/asm/bitsperlong.h | 1 + trunk/arch/xtensa/include/asm/page.h | 2 +- trunk/arch/xtensa/kernel/module.c | 2 - trunk/block/Kconfig | 11 +- trunk/block/as-iosched.c | 24 +- trunk/block/blk-barrier.c | 27 +- trunk/block/blk-core.c | 878 ++- trunk/block/blk-exec.c | 1 - trunk/block/blk-integrity.c | 2 +- trunk/block/blk-ioc.c | 12 +- trunk/block/blk-map.c | 25 +- trunk/block/blk-merge.c | 71 +- trunk/block/blk-settings.c | 269 +- trunk/block/blk-sysfs.c | 65 +- trunk/block/blk-tag.c | 17 +- trunk/block/blk-timeout.c | 22 +- trunk/block/blk.h | 51 +- trunk/block/bsg.c | 11 +- trunk/block/cfq-iosched.c | 38 +- trunk/block/compat_ioctl.c | 6 +- trunk/block/deadline-iosched.c | 2 +- trunk/block/elevator.c | 193 +- trunk/block/genhd.c | 11 + trunk/block/ioctl.c | 12 +- trunk/block/scsi_ioctl.c | 13 +- trunk/crypto/Kconfig | 10 + trunk/crypto/algboss.c | 18 +- trunk/crypto/api.c | 14 +- trunk/crypto/cryptd.c | 14 +- trunk/crypto/internal.h | 3 - trunk/crypto/pcompress.c | 1 + trunk/crypto/tcrypt.c | 183 +- trunk/crypto/testmgr.c | 470 +- trunk/crypto/testmgr.h | 645 +- trunk/crypto/zlib.c | 24 +- trunk/drivers/acpi/pci_irq.c | 5 +- trunk/drivers/acpi/processor_core.c | 2 +- trunk/drivers/ata/ahci.c | 159 +- trunk/drivers/ata/ata_piix.c | 20 +- trunk/drivers/ata/libata-core.c | 11 +- trunk/drivers/ata/libata-scsi.c | 2 +- trunk/drivers/ata/libata-sff.c | 20 +- trunk/drivers/ata/pata_ali.c | 17 +- trunk/drivers/ata/pata_efar.c | 17 +- trunk/drivers/ata/pata_legacy.c | 2 + trunk/drivers/ata/pata_netcell.c | 2 +- trunk/drivers/ata/sata_nv.c | 131 +- trunk/drivers/ata/sata_sil.c | 2 +- trunk/drivers/ata/sata_sx4.c | 11 +- trunk/drivers/base/firmware_class.c | 129 +- trunk/drivers/base/platform.c | 36 +- trunk/drivers/base/power/main.c | 94 +- trunk/drivers/base/sys.c | 16 + trunk/drivers/block/DAC960.c | 10 +- trunk/drivers/block/Kconfig | 4 +- trunk/drivers/block/amiflop.c | 54 +- trunk/drivers/block/ataflop.c | 66 +- trunk/drivers/block/brd.c | 7 +- trunk/drivers/block/cciss.c | 927 ++- trunk/drivers/block/cciss.h | 34 +- trunk/drivers/block/cciss_cmd.h | 2 + trunk/drivers/block/cciss_scsi.c | 109 +- trunk/drivers/block/cpqarray.c | 20 +- trunk/drivers/block/floppy.c | 85 +- trunk/drivers/block/hd.c | 106 +- trunk/drivers/block/loop.c | 37 +- trunk/drivers/block/mg_disk.c | 537 +- trunk/drivers/block/nbd.c | 23 +- trunk/drivers/block/paride/pcd.c | 29 +- trunk/drivers/block/paride/pd.c | 22 +- trunk/drivers/block/paride/pf.c | 47 +- trunk/drivers/block/pktcdvd.c | 8 +- trunk/drivers/block/ps3disk.c | 24 +- trunk/drivers/block/sunvdc.c | 14 +- trunk/drivers/block/swim.c | 48 +- trunk/drivers/block/swim3.c | 107 +- trunk/drivers/block/sx8.c | 17 +- trunk/drivers/block/ub.c | 54 +- trunk/drivers/block/viodasd.c | 12 +- trunk/drivers/block/virtio_blk.c | 120 +- trunk/drivers/block/xd.c | 41 +- trunk/drivers/block/xen-blkfront.c | 34 +- trunk/drivers/block/xsysace.c | 46 +- trunk/drivers/block/z2ram.c | 19 +- trunk/drivers/bluetooth/hci_ldisc.c | 5 +- trunk/drivers/cdrom/cdrom.c | 4 +- trunk/drivers/cdrom/gdrom.c | 36 +- trunk/drivers/cdrom/viocd.c | 33 +- trunk/drivers/char/Kconfig | 15 +- trunk/drivers/char/Makefile | 1 + trunk/drivers/char/agp/intel-agp.c | 16 +- trunk/drivers/char/bfin_jtag_comm.c | 365 + trunk/drivers/char/cyclades.c | 290 +- trunk/drivers/char/epca.c | 17 +- trunk/drivers/char/hpet.c | 4 +- trunk/drivers/char/hw_random/Kconfig | 2 +- trunk/drivers/char/hw_random/omap-rng.c | 2 +- trunk/drivers/char/hw_random/timeriomem-rng.c | 26 +- trunk/drivers/char/hw_random/via-rng.c | 15 +- trunk/drivers/char/hw_random/virtio-rng.c | 30 +- trunk/drivers/char/ip2/i2lib.c | 4 +- trunk/drivers/char/ip2/ip2main.c | 4 +- trunk/drivers/char/isicom.c | 19 +- trunk/drivers/char/istallion.c | 8 +- trunk/drivers/char/mem.c | 2 + trunk/drivers/char/moxa.c | 5 + trunk/drivers/char/mxser.c | 14 +- trunk/drivers/char/n_hdlc.c | 4 +- trunk/drivers/char/n_tty.c | 29 +- trunk/drivers/char/pcmcia/synclink_cs.c | 11 +- trunk/drivers/char/pty.c | 11 +- trunk/drivers/char/raw.c | 2 +- trunk/drivers/char/rocket.c | 19 +- trunk/drivers/char/selection.c | 2 +- trunk/drivers/char/stallion.c | 6 +- trunk/drivers/char/synclink.c | 9 +- trunk/drivers/char/synclink_gt.c | 86 +- trunk/drivers/char/synclinkmp.c | 9 +- trunk/drivers/char/sysrq.c | 2 + trunk/drivers/char/tty_audit.c | 10 +- trunk/drivers/char/tty_io.c | 122 +- trunk/drivers/char/tty_ioctl.c | 88 +- trunk/drivers/char/tty_ldisc.c | 549 +- trunk/drivers/char/tty_port.c | 47 +- trunk/drivers/char/virtio_console.c | 26 +- trunk/drivers/char/vt.c | 8 +- trunk/drivers/clocksource/Makefile | 2 + trunk/drivers/clocksource/sh_cmt.c | 116 +- trunk/drivers/clocksource/sh_mtu2.c | 357 + trunk/drivers/clocksource/sh_tmu.c | 461 ++ trunk/drivers/cpufreq/cpufreq.c | 2 +- trunk/drivers/crypto/Kconfig | 2 +- trunk/drivers/crypto/hifn_795x.c | 8 +- trunk/drivers/crypto/padlock-aes.c | 13 + trunk/drivers/crypto/talitos.c | 713 +- trunk/drivers/edac/Kconfig | 26 +- trunk/drivers/edac/Makefile | 7 + trunk/drivers/edac/amd64_edac.c | 3354 ++++++++ trunk/drivers/edac/amd64_edac.h | 644 ++ trunk/drivers/edac/amd64_edac_dbg.c | 255 + trunk/drivers/edac/amd64_edac_err_types.c | 161 + trunk/drivers/edac/amd64_edac_inj.c | 185 + trunk/drivers/edac/edac_core.h | 9 +- trunk/drivers/firmware/dmi_scan.c | 1 + trunk/drivers/gpio/Kconfig | 2 +- trunk/drivers/gpu/drm/drm_bufs.c | 3 +- trunk/drivers/gpu/drm/drm_crtc.c | 7 +- trunk/drivers/gpu/drm/drm_crtc_helper.c | 109 +- trunk/drivers/gpu/drm/drm_edid.c | 79 +- trunk/drivers/gpu/drm/drm_gem.c | 2 +- trunk/drivers/gpu/drm/drm_hashtab.c | 4 + trunk/drivers/gpu/drm/drm_irq.c | 8 +- trunk/drivers/gpu/drm/drm_mm.c | 165 +- trunk/drivers/gpu/drm/drm_modes.c | 18 +- trunk/drivers/gpu/drm/drm_stub.c | 17 +- trunk/drivers/gpu/drm/drm_sysfs.c | 7 +- trunk/drivers/gpu/drm/i915/i915_dma.c | 79 +- trunk/drivers/gpu/drm/i915/i915_drv.h | 48 +- trunk/drivers/gpu/drm/i915/i915_gem.c | 156 +- trunk/drivers/gpu/drm/i915/i915_gem_tiling.c | 152 + trunk/drivers/gpu/drm/i915/i915_irq.c | 190 +- trunk/drivers/gpu/drm/i915/i915_reg.h | 616 +- trunk/drivers/gpu/drm/i915/i915_suspend.c | 20 + trunk/drivers/gpu/drm/i915/intel_bios.c | 86 +- trunk/drivers/gpu/drm/i915/intel_bios.h | 101 +- trunk/drivers/gpu/drm/i915/intel_crt.c | 82 +- trunk/drivers/gpu/drm/i915/intel_display.c | 645 +- trunk/drivers/gpu/drm/i915/intel_dvo.c | 1 + trunk/drivers/gpu/drm/i915/intel_fb.c | 26 +- trunk/drivers/gpu/drm/i915/intel_hdmi.c | 34 +- trunk/drivers/gpu/drm/i915/intel_lvds.c | 159 +- trunk/drivers/gpu/drm/i915/intel_sdvo.c | 111 +- trunk/drivers/gpu/drm/i915/intel_tv.c | 4 + trunk/drivers/gpu/drm/radeon/r600_cp.c | 42 +- trunk/drivers/gpu/drm/radeon/radeon_cp.c | 6 +- trunk/drivers/gpu/drm/radeon/radeon_drv.h | 6 +- trunk/drivers/gpu/drm/via/via_dmablit.c | 6 +- trunk/drivers/i2c/busses/Kconfig | 2 +- trunk/drivers/i2c/busses/i2c-bfin-twi.c | 59 +- trunk/drivers/i2c/busses/i2c-ocores.c | 5 + trunk/drivers/i2c/busses/i2c-omap.c | 39 +- trunk/drivers/i2c/busses/i2c-s3c2410.c | 48 +- trunk/drivers/i2c/busses/i2c-sh7760.c | 2 +- trunk/drivers/ide/alim15x3.c | 10 +- trunk/drivers/ide/at91_ide.c | 7 +- trunk/drivers/ide/au1xxx-ide.c | 8 +- trunk/drivers/ide/buddha.c | 9 +- trunk/drivers/ide/cmd640.c | 7 +- trunk/drivers/ide/cs5520.c | 4 +- trunk/drivers/ide/delkin_cb.c | 6 +- trunk/drivers/ide/falconide.c | 9 +- trunk/drivers/ide/gayle.c | 9 +- trunk/drivers/ide/hpt366.c | 25 +- trunk/drivers/ide/icside.c | 77 +- trunk/drivers/ide/ide-4drives.c | 6 +- trunk/drivers/ide/ide-atapi.c | 185 +- trunk/drivers/ide/ide-cd.c | 152 +- trunk/drivers/ide/ide-cd.h | 4 - trunk/drivers/ide/ide-cs.c | 6 +- trunk/drivers/ide/ide-disk.c | 86 +- trunk/drivers/ide/ide-dma.c | 23 +- trunk/drivers/ide/ide-eh.c | 14 +- trunk/drivers/ide/ide-floppy.c | 32 +- trunk/drivers/ide/ide-gd.c | 14 + trunk/drivers/ide/ide-generic.c | 7 +- trunk/drivers/ide/ide-h8300.c | 10 +- trunk/drivers/ide/ide-io.c | 134 +- trunk/drivers/ide/ide-ioctls.c | 1 - trunk/drivers/ide/ide-iops.c | 26 +- trunk/drivers/ide/ide-legacy.c | 7 +- trunk/drivers/ide/ide-lib.c | 2 +- trunk/drivers/ide/ide-park.c | 7 +- trunk/drivers/ide/ide-pm.c | 38 +- trunk/drivers/ide/ide-pnp.c | 6 +- trunk/drivers/ide/ide-probe.c | 95 +- trunk/drivers/ide/ide-tape.c | 822 +- trunk/drivers/ide/ide-taskfile.c | 23 +- trunk/drivers/ide/ide.c | 10 + trunk/drivers/ide/ide_platform.c | 9 +- trunk/drivers/ide/macide.c | 9 +- trunk/drivers/ide/palm_bk3710.c | 6 +- trunk/drivers/ide/pdc202xx_new.c | 26 - trunk/drivers/ide/pdc202xx_old.c | 106 +- trunk/drivers/ide/pmac.c | 13 +- trunk/drivers/ide/q40ide.c | 11 +- trunk/drivers/ide/rapide.c | 8 +- trunk/drivers/ide/scc_pata.c | 6 +- trunk/drivers/ide/setup-pci.c | 85 +- trunk/drivers/ide/sgiioc4.c | 7 +- trunk/drivers/ide/siimage.c | 4 +- trunk/drivers/ide/sl82c105.c | 9 +- trunk/drivers/ide/tc86c001.c | 2 +- trunk/drivers/ide/tx4938ide.c | 5 +- trunk/drivers/ide/tx4939ide.c | 7 +- trunk/drivers/ieee1394/dv1394.c | 5 +- trunk/drivers/ieee1394/ieee1394_core.h | 6 +- .../drivers/infiniband/ulp/iser/iscsi_iser.c | 10 +- trunk/drivers/input/serio/Kconfig | 2 +- trunk/drivers/lguest/Kconfig | 2 +- trunk/drivers/lguest/core.c | 30 +- trunk/drivers/lguest/hypercalls.c | 14 + trunk/drivers/lguest/interrupts_and_traps.c | 57 +- trunk/drivers/lguest/lg.h | 28 +- trunk/drivers/lguest/lguest_device.c | 41 +- trunk/drivers/lguest/lguest_user.c | 127 +- trunk/drivers/lguest/page_tables.c | 396 +- trunk/drivers/lguest/segments.c | 2 +- trunk/drivers/md/bitmap.c | 4 +- trunk/drivers/md/dm-exception-store.c | 2 +- trunk/drivers/md/dm-log.c | 3 +- trunk/drivers/md/dm-snap-persistent.c | 2 +- trunk/drivers/md/dm-table.c | 38 +- trunk/drivers/md/dm.c | 8 +- trunk/drivers/md/linear.c | 2 +- trunk/drivers/md/md.c | 2 +- trunk/drivers/md/multipath.c | 4 +- trunk/drivers/md/raid0.c | 2 +- trunk/drivers/md/raid1.c | 4 +- trunk/drivers/md/raid10.c | 8 +- trunk/drivers/md/raid5.c | 32 +- trunk/drivers/media/video/ivtv/ivtv-queue.c | 3 +- trunk/drivers/memstick/core/mspro_block.c | 19 +- trunk/drivers/message/fusion/mptbase.c | 1571 ++-- trunk/drivers/message/fusion/mptbase.h | 180 +- trunk/drivers/message/fusion/mptctl.c | 692 +- trunk/drivers/message/fusion/mptdebug.h | 3 + trunk/drivers/message/fusion/mptfc.c | 15 +- trunk/drivers/message/fusion/mptsas.c | 3154 ++++++-- trunk/drivers/message/fusion/mptsas.h | 41 +- trunk/drivers/message/fusion/mptscsih.c | 1329 ++-- trunk/drivers/message/fusion/mptscsih.h | 7 +- trunk/drivers/message/fusion/mptspi.c | 71 +- trunk/drivers/message/i2o/i2o_block.c | 43 +- trunk/drivers/mmc/card/block.c | 12 +- trunk/drivers/mmc/card/queue.c | 11 +- trunk/drivers/mmc/host/atmel-mci.c | 12 +- trunk/drivers/mmc/host/mvsdio.c | 35 + trunk/drivers/mmc/host/mxcmmc.c | 47 +- trunk/drivers/mmc/host/omap.c | 2 +- trunk/drivers/mmc/host/omap_hsmmc.c | 2 +- trunk/drivers/mmc/host/sdhci-of.c | 9 +- trunk/drivers/mtd/mtd_blkdevs.c | 43 +- trunk/drivers/mtd/nand/davinci_nand.c | 7 +- trunk/drivers/net/Kconfig | 11 + trunk/drivers/net/Makefile | 1 + trunk/drivers/net/bnx2.c | 193 +- trunk/drivers/net/bnx2.h | 18 + trunk/drivers/net/cnic.c | 2717 +++++++ trunk/drivers/net/cnic.h | 299 + trunk/drivers/net/cnic_defs.h | 580 ++ trunk/drivers/net/cnic_if.h | 299 + trunk/drivers/net/r8169.c | 11 +- trunk/drivers/net/virtio_net.c | 45 +- trunk/drivers/of/Kconfig | 8 +- trunk/drivers/parisc/iosapic.c | 6 +- trunk/drivers/parport/parport_pc.c | 1802 +++-- trunk/drivers/pci/hotplug/ibmphp_core.c | 54 +- trunk/drivers/pci/htirq.c | 4 +- trunk/drivers/pci/intel-iommu.c | 9 - trunk/drivers/pci/intr_remapping.c | 54 +- trunk/drivers/pci/probe.c | 2 + trunk/drivers/pnp/pnpacpi/rsparser.c | 2 +- trunk/drivers/pnp/resource.c | 18 + trunk/drivers/rtc/Kconfig | 2 +- trunk/drivers/s390/block/dasd.c | 71 +- trunk/drivers/s390/block/dasd_diag.c | 6 +- trunk/drivers/s390/block/dasd_eckd.c | 50 +- trunk/drivers/s390/block/dasd_fba.c | 29 +- trunk/drivers/s390/block/dasd_int.h | 3 +- trunk/drivers/s390/block/dcssblk.c | 6 +- trunk/drivers/s390/block/xpram.c | 2 +- trunk/drivers/s390/char/con3270.c | 38 +- trunk/drivers/s390/char/tape_34xx.c | 2 +- trunk/drivers/s390/char/tape_3590.c | 2 +- trunk/drivers/s390/char/tape_block.c | 26 +- trunk/drivers/s390/char/tty3270.c | 57 +- trunk/drivers/s390/cio/cio.c | 6 +- trunk/drivers/s390/cio/device_ops.c | 24 +- trunk/drivers/s390/cio/qdio_main.c | 46 +- trunk/drivers/s390/cio/qdio_perf.c | 12 - trunk/drivers/s390/cio/qdio_perf.h | 10 +- trunk/drivers/s390/kvm/kvm_virtio.c | 43 +- trunk/drivers/s390/scsi/zfcp_ccw.c | 30 +- trunk/drivers/s390/scsi/zfcp_dbf.c | 10 +- trunk/drivers/s390/scsi/zfcp_def.h | 7 - trunk/drivers/s390/scsi/zfcp_erp.c | 8 +- trunk/drivers/s390/scsi/zfcp_ext.h | 1 + trunk/drivers/s390/scsi/zfcp_fc.c | 7 +- trunk/drivers/s390/scsi/zfcp_fsf.c | 29 +- trunk/drivers/s390/scsi/zfcp_scsi.c | 13 +- trunk/drivers/sbus/char/jsflash.c | 26 +- trunk/drivers/scsi/Kconfig | 31 +- trunk/drivers/scsi/Makefile | 3 +- trunk/drivers/scsi/NCR_D700.c | 2 +- .../drivers/scsi/bnx2i/57xx_iscsi_constants.h | 155 + trunk/drivers/scsi/bnx2i/57xx_iscsi_hsi.h | 1509 ++++ trunk/drivers/scsi/bnx2i/Kconfig | 7 + trunk/drivers/scsi/bnx2i/Makefile | 3 + trunk/drivers/scsi/bnx2i/bnx2i.h | 771 ++ trunk/drivers/scsi/bnx2i/bnx2i_hwi.c | 2405 ++++++ trunk/drivers/scsi/bnx2i/bnx2i_init.c | 438 ++ trunk/drivers/scsi/bnx2i/bnx2i_iscsi.c | 2064 +++++ trunk/drivers/scsi/bnx2i/bnx2i_sysfs.c | 142 + trunk/drivers/scsi/cxgb3i/cxgb3i.h | 1 - trunk/drivers/scsi/cxgb3i/cxgb3i_iscsi.c | 26 +- trunk/drivers/scsi/cxgb3i/cxgb3i_offload.c | 23 +- trunk/drivers/scsi/cxgb3i/cxgb3i_offload.h | 3 +- .../scsi/device_handler/scsi_dh_rdac.c | 6 + trunk/drivers/scsi/eata.c | 24 +- trunk/drivers/scsi/fcoe/fcoe.c | 95 +- trunk/drivers/scsi/fcoe/fcoe.h | 1 + trunk/drivers/scsi/fcoe/libfcoe.c | 21 +- trunk/drivers/scsi/fnic/fnic_main.c | 1 + trunk/drivers/scsi/gdth_proc.c | 5 +- trunk/drivers/scsi/ibmvscsi/ibmvfc.c | 434 +- trunk/drivers/scsi/ibmvscsi/ibmvfc.h | 40 +- trunk/drivers/scsi/ibmvscsi/ibmvscsi.c | 463 +- trunk/drivers/scsi/ibmvscsi/ibmvscsi.h | 4 + trunk/drivers/scsi/ibmvscsi/viosrp.h | 68 +- trunk/drivers/scsi/ipr.c | 5 +- trunk/drivers/scsi/libfc/fc_exch.c | 4 + trunk/drivers/scsi/libfc/fc_fcp.c | 2 +- trunk/drivers/scsi/libfc/fc_rport.c | 6 +- trunk/drivers/scsi/libiscsi.c | 468 +- trunk/drivers/scsi/libiscsi_tcp.c | 18 +- trunk/drivers/scsi/libsas/sas_expander.c | 16 +- trunk/drivers/scsi/libsas/sas_host_smp.c | 49 +- trunk/drivers/scsi/lpfc/lpfc.h | 123 +- trunk/drivers/scsi/lpfc/lpfc_attr.c | 250 +- trunk/drivers/scsi/lpfc/lpfc_crtn.h | 63 +- trunk/drivers/scsi/lpfc/lpfc_ct.c | 15 +- trunk/drivers/scsi/lpfc/lpfc_debugfs.c | 21 +- trunk/drivers/scsi/lpfc/lpfc_disc.h | 1 + trunk/drivers/scsi/lpfc/lpfc_els.c | 275 +- trunk/drivers/scsi/lpfc/lpfc_hbadisc.c | 1365 +++- trunk/drivers/scsi/lpfc/lpfc_hw.h | 142 +- trunk/drivers/scsi/lpfc/lpfc_hw4.h | 2141 ++++++ trunk/drivers/scsi/lpfc/lpfc_init.c | 6044 +++++++++++++-- trunk/drivers/scsi/lpfc/lpfc_logmsg.h | 54 +- trunk/drivers/scsi/lpfc/lpfc_mbox.c | 674 +- trunk/drivers/scsi/lpfc/lpfc_mem.c | 206 +- trunk/drivers/scsi/lpfc/lpfc_nportdisc.c | 51 +- trunk/drivers/scsi/lpfc/lpfc_scsi.c | 952 ++- trunk/drivers/scsi/lpfc/lpfc_scsi.h | 2 + trunk/drivers/scsi/lpfc/lpfc_sli.c | 6831 +++++++++++++++-- trunk/drivers/scsi/lpfc/lpfc_sli.h | 29 +- trunk/drivers/scsi/lpfc/lpfc_sli4.h | 467 ++ trunk/drivers/scsi/lpfc/lpfc_version.h | 2 +- trunk/drivers/scsi/lpfc/lpfc_vport.c | 62 +- trunk/drivers/scsi/mpt2sas/mpt2sas_base.h | 5 +- trunk/drivers/scsi/mpt2sas/mpt2sas_ctl.c | 32 +- trunk/drivers/scsi/mpt2sas/mpt2sas_scsih.c | 363 +- .../drivers/scsi/mpt2sas/mpt2sas_transport.c | 59 +- trunk/drivers/scsi/mvsas.c | 3222 -------- trunk/drivers/scsi/mvsas/Kconfig | 42 + trunk/drivers/scsi/mvsas/Makefile | 32 + trunk/drivers/scsi/mvsas/mv_64xx.c | 793 ++ trunk/drivers/scsi/mvsas/mv_64xx.h | 151 + trunk/drivers/scsi/mvsas/mv_94xx.c | 672 ++ trunk/drivers/scsi/mvsas/mv_94xx.h | 222 + trunk/drivers/scsi/mvsas/mv_chips.h | 280 + trunk/drivers/scsi/mvsas/mv_defs.h | 502 ++ trunk/drivers/scsi/mvsas/mv_init.c | 703 ++ trunk/drivers/scsi/mvsas/mv_sas.c | 2154 ++++++ trunk/drivers/scsi/mvsas/mv_sas.h | 406 + trunk/drivers/scsi/osd/Kbuild | 25 - trunk/drivers/scsi/osd/Makefile | 37 - trunk/drivers/scsi/osd/osd_initiator.c | 155 +- trunk/drivers/scsi/osd/osd_uld.c | 66 +- trunk/drivers/scsi/qla1280.c | 387 +- trunk/drivers/scsi/qla1280.h | 3 +- trunk/drivers/scsi/qla2xxx/qla_attr.c | 227 +- trunk/drivers/scsi/qla2xxx/qla_dbg.c | 13 +- trunk/drivers/scsi/qla2xxx/qla_def.h | 45 +- trunk/drivers/scsi/qla2xxx/qla_fw.h | 6 +- trunk/drivers/scsi/qla2xxx/qla_gbl.h | 43 +- trunk/drivers/scsi/qla2xxx/qla_gs.c | 5 +- trunk/drivers/scsi/qla2xxx/qla_init.c | 206 +- trunk/drivers/scsi/qla2xxx/qla_iocb.c | 55 +- trunk/drivers/scsi/qla2xxx/qla_isr.c | 240 +- trunk/drivers/scsi/qla2xxx/qla_mbx.c | 244 +- trunk/drivers/scsi/qla2xxx/qla_mid.c | 118 +- trunk/drivers/scsi/qla2xxx/qla_os.c | 294 +- trunk/drivers/scsi/qla2xxx/qla_sup.c | 47 +- trunk/drivers/scsi/qla2xxx/qla_version.h | 2 +- trunk/drivers/scsi/scsi.c | 4 +- trunk/drivers/scsi/scsi_debug.c | 2 +- trunk/drivers/scsi/scsi_error.c | 21 +- trunk/drivers/scsi/scsi_lib.c | 101 +- trunk/drivers/scsi/scsi_scan.c | 4 +- trunk/drivers/scsi/scsi_tgt_lib.c | 2 +- trunk/drivers/scsi/scsi_transport_iscsi.c | 173 +- trunk/drivers/scsi/scsi_transport_sas.c | 4 +- trunk/drivers/scsi/sd.c | 71 +- trunk/drivers/scsi/sd_dif.c | 2 +- trunk/drivers/scsi/sg.c | 18 +- trunk/drivers/scsi/sr.c | 17 +- trunk/drivers/scsi/st.c | 8 +- trunk/drivers/scsi/sym53c8xx_2/sym_glue.c | 66 +- trunk/drivers/scsi/sym53c8xx_2/sym_hipd.c | 49 +- trunk/drivers/scsi/sym53c8xx_2/sym_hipd.h | 2 + trunk/drivers/scsi/u14-34f.c | 22 +- trunk/drivers/serial/8250.c | 7 + trunk/drivers/serial/8250_pci.c | 3 + trunk/drivers/serial/Kconfig | 8 + trunk/drivers/serial/Makefile | 1 + trunk/drivers/serial/bfin_5xx.c | 77 +- trunk/drivers/serial/bfin_sport_uart.c | 58 +- trunk/drivers/serial/icom.c | 20 +- trunk/drivers/serial/imx.c | 294 +- trunk/drivers/serial/jsm/jsm.h | 1 + trunk/drivers/serial/jsm/jsm_tty.c | 14 +- trunk/drivers/serial/sh-sci.c | 388 +- trunk/drivers/serial/sh-sci.h | 42 +- trunk/drivers/serial/timbuart.c | 526 ++ trunk/drivers/serial/timbuart.h | 58 + trunk/drivers/sh/intc.c | 11 +- trunk/drivers/spi/Kconfig | 2 +- trunk/drivers/ssb/embedded.c | 1 + trunk/drivers/usb/Kconfig | 1 + trunk/drivers/usb/class/cdc-acm.c | 442 +- trunk/drivers/usb/class/cdc-acm.h | 5 +- trunk/drivers/usb/core/inode.c | 5 + trunk/drivers/usb/serial/belkin_sa.c | 6 +- trunk/drivers/usb/serial/ch341.c | 46 +- trunk/drivers/usb/serial/console.c | 6 +- trunk/drivers/usb/serial/cp210x.c | 253 +- trunk/drivers/usb/serial/cyberjack.c | 6 +- trunk/drivers/usb/serial/cypress_m8.c | 81 +- trunk/drivers/usb/serial/digi_acceleport.c | 75 +- trunk/drivers/usb/serial/empeg.c | 6 +- trunk/drivers/usb/serial/ftdi_sio.c | 149 +- trunk/drivers/usb/serial/garmin_gps.c | 3 +- trunk/drivers/usb/serial/generic.c | 3 +- trunk/drivers/usb/serial/io_edgeport.c | 10 +- trunk/drivers/usb/serial/io_ti.c | 3 +- trunk/drivers/usb/serial/ipaq.c | 6 +- trunk/drivers/usb/serial/ipw.c | 18 +- trunk/drivers/usb/serial/ir-usb.c | 6 +- trunk/drivers/usb/serial/iuu_phoenix.c | 102 +- trunk/drivers/usb/serial/keyspan.c | 13 +- trunk/drivers/usb/serial/keyspan.h | 8 +- trunk/drivers/usb/serial/keyspan_pda.c | 48 +- trunk/drivers/usb/serial/kl5kusb105.c | 6 +- trunk/drivers/usb/serial/kobil_sct.c | 9 +- trunk/drivers/usb/serial/mct_u232.c | 37 +- trunk/drivers/usb/serial/mos7720.c | 3 +- trunk/drivers/usb/serial/mos7840.c | 48 +- trunk/drivers/usb/serial/navman.c | 3 +- trunk/drivers/usb/serial/omninet.c | 6 +- trunk/drivers/usb/serial/opticon.c | 3 +- trunk/drivers/usb/serial/option.c | 68 +- trunk/drivers/usb/serial/oti6858.c | 57 +- trunk/drivers/usb/serial/pl2303.c | 79 +- trunk/drivers/usb/serial/sierra.c | 351 +- trunk/drivers/usb/serial/spcp8x5.c | 85 +- trunk/drivers/usb/serial/symbolserial.c | 3 +- trunk/drivers/usb/serial/ti_usb_3410_5052.c | 6 +- trunk/drivers/usb/serial/usb-serial.c | 144 +- trunk/drivers/usb/serial/visor.c | 6 +- trunk/drivers/usb/serial/whiteheat.c | 33 +- trunk/drivers/usb/storage/scsiglue.c | 4 +- trunk/drivers/video/Kconfig | 2 +- trunk/drivers/video/aty/aty128fb.c | 2 +- trunk/drivers/video/console/vgacon.c | 5 +- trunk/drivers/video/cyber2000fb.c | 9 +- trunk/drivers/video/hitfb.c | 4 +- trunk/drivers/video/uvesafb.c | 10 +- trunk/drivers/virtio/virtio.c | 29 +- trunk/drivers/virtio/virtio_balloon.c | 27 +- trunk/drivers/virtio/virtio_pci.c | 307 +- trunk/drivers/virtio/virtio_ring.c | 102 +- trunk/drivers/xen/Kconfig | 20 + trunk/drivers/xen/Makefile | 4 +- trunk/drivers/xen/events.c | 20 +- trunk/drivers/xen/evtchn.c | 507 ++ trunk/drivers/xen/manage.c | 25 +- trunk/drivers/xen/sys-hypervisor.c | 445 ++ trunk/drivers/xen/xenbus/xenbus_probe.c | 61 +- trunk/drivers/xen/xenbus/xenbus_xs.c | 2 + trunk/drivers/xen/xenfs/super.c | 19 +- trunk/fs/Kconfig | 10 + trunk/fs/adfs/adfs.h | 4 +- trunk/fs/adfs/dir.c | 10 +- trunk/fs/adfs/dir_f.c | 17 + trunk/fs/adfs/dir_fplus.c | 17 + trunk/fs/adfs/file.c | 2 +- trunk/fs/adfs/inode.c | 4 +- trunk/fs/adfs/map.c | 2 +- trunk/fs/adfs/super.c | 4 + trunk/fs/affs/affs.h | 1 + trunk/fs/affs/dir.c | 2 +- trunk/fs/affs/file.c | 14 +- trunk/fs/affs/super.c | 54 +- trunk/fs/afs/mntpt.c | 2 +- trunk/fs/afs/super.c | 4 + trunk/fs/autofs/dirhash.c | 5 +- trunk/fs/autofs4/autofs_i.h | 6 +- trunk/fs/autofs4/dev-ioctl.c | 195 +- trunk/fs/autofs4/expire.c | 15 +- trunk/fs/autofs4/root.c | 7 +- trunk/fs/autofs4/waitq.c | 22 +- trunk/fs/befs/linuxvfs.c | 5 +- trunk/fs/bfs/dir.c | 8 +- trunk/fs/bfs/inode.c | 52 +- trunk/fs/bio.c | 29 +- trunk/fs/block_dev.c | 31 +- trunk/fs/btrfs/Makefile | 4 +- trunk/fs/btrfs/acl.c | 5 - trunk/fs/btrfs/async-thread.c | 2 +- trunk/fs/btrfs/btrfs_inode.h | 4 +- trunk/fs/btrfs/compression.c | 6 +- trunk/fs/btrfs/crc32c.h | 29 - trunk/fs/btrfs/ctree.c | 698 +- trunk/fs/btrfs/ctree.h | 330 +- trunk/fs/btrfs/delayed-ref.c | 509 +- trunk/fs/btrfs/delayed-ref.h | 85 +- trunk/fs/btrfs/disk-io.c | 164 +- trunk/fs/btrfs/export.c | 4 +- trunk/fs/btrfs/extent-tree.c | 2713 ++++--- trunk/fs/btrfs/extent_io.c | 18 +- trunk/fs/btrfs/file.c | 78 +- trunk/fs/btrfs/free-space-cache.c | 10 +- trunk/fs/btrfs/free-space-cache.h | 1 + trunk/fs/btrfs/hash.h | 4 +- trunk/fs/btrfs/inode.c | 166 +- trunk/fs/btrfs/ioctl.c | 197 +- trunk/fs/btrfs/print-tree.c | 155 +- trunk/fs/btrfs/relocation.c | 3711 +++++++++ trunk/fs/btrfs/root-tree.c | 17 +- trunk/fs/btrfs/super.c | 64 +- trunk/fs/btrfs/transaction.c | 410 +- trunk/fs/btrfs/transaction.h | 12 +- trunk/fs/btrfs/tree-log.c | 103 +- trunk/fs/btrfs/volumes.c | 70 +- trunk/fs/btrfs/volumes.h | 12 +- trunk/fs/buffer.c | 10 +- trunk/fs/cachefiles/interface.c | 4 +- trunk/fs/char_dev.c | 14 +- trunk/fs/cifs/CHANGES | 11 + trunk/fs/cifs/README | 16 +- trunk/fs/cifs/cifs_dfs_ref.c | 2 +- trunk/fs/cifs/cifs_spnego.c | 6 +- trunk/fs/cifs/cifsacl.c | 178 +- trunk/fs/cifs/cifsfs.c | 8 +- trunk/fs/cifs/cifsfs.h | 4 +- trunk/fs/cifs/cifsproto.h | 10 +- trunk/fs/cifs/cifssmb.c | 7 +- trunk/fs/cifs/connect.c | 34 +- trunk/fs/cifs/file.c | 2 +- trunk/fs/cifs/inode.c | 19 +- trunk/fs/cifs/netmisc.c | 24 +- trunk/fs/cifs/readdir.c | 44 +- trunk/fs/coda/file.c | 9 +- trunk/fs/compat.c | 8 +- trunk/fs/configfs/configfs_internal.h | 3 + trunk/fs/configfs/dir.c | 196 +- trunk/fs/configfs/inode.c | 38 + trunk/fs/dcache.c | 7 +- trunk/fs/devpts/inode.c | 4 +- trunk/fs/direct-io.c | 2 +- trunk/fs/dlm/dir.c | 7 +- trunk/fs/dlm/lockspace.c | 17 +- trunk/fs/dlm/lowcomms.c | 22 +- trunk/fs/dlm/lowcomms.h | 3 +- trunk/fs/dlm/member.c | 19 +- trunk/fs/dlm/requestqueue.c | 2 +- trunk/fs/ecryptfs/super.c | 5 + trunk/fs/eventfd.c | 3 + trunk/fs/exec.c | 19 +- trunk/fs/exofs/common.h | 6 - trunk/fs/exofs/inode.c | 8 +- trunk/fs/exofs/osd.c | 30 +- trunk/fs/exofs/super.c | 25 +- trunk/fs/ext2/Makefile | 2 +- trunk/fs/ext2/dir.c | 2 +- trunk/fs/ext2/ext2.h | 3 - trunk/fs/ext2/file.c | 4 +- trunk/fs/ext2/fsync.c | 50 - trunk/fs/ext2/inode.c | 11 +- trunk/fs/ext2/super.c | 61 +- trunk/fs/ext3/balloc.c | 3 +- trunk/fs/ext3/ialloc.c | 3 +- trunk/fs/ext3/inode.c | 1 - trunk/fs/ext3/resize.c | 2 - trunk/fs/ext3/super.c | 39 +- trunk/fs/ext3/xattr.c | 1 - trunk/fs/ext4/Makefile | 4 +- trunk/fs/ext4/balloc.c | 28 +- trunk/fs/ext4/block_validity.c | 244 + trunk/fs/ext4/dir.c | 3 +- trunk/fs/ext4/ext4.h | 354 +- trunk/fs/ext4/ext4_i.h | 140 - trunk/fs/ext4/ext4_sb.h | 161 - trunk/fs/ext4/extents.c | 85 +- trunk/fs/ext4/group.h | 29 - trunk/fs/ext4/ialloc.c | 73 +- trunk/fs/ext4/inode.c | 593 +- trunk/fs/ext4/mballoc.c | 166 +- trunk/fs/ext4/mballoc.h | 1 - trunk/fs/ext4/namei.c | 27 +- trunk/fs/ext4/namei.h | 8 - trunk/fs/ext4/resize.c | 36 +- trunk/fs/ext4/super.c | 849 +- trunk/fs/fat/dir.c | 16 +- trunk/fs/fat/fat.h | 6 + trunk/fs/fat/fatent.c | 13 +- trunk/fs/fat/file.c | 14 +- trunk/fs/fat/inode.c | 31 +- trunk/fs/fat/namei_msdos.c | 4 +- trunk/fs/fat/namei_vfat.c | 4 +- trunk/fs/file_table.c | 40 +- trunk/fs/freevxfs/vxfs_super.c | 4 + trunk/fs/fs-writeback.c | 92 +- trunk/fs/fuse/Makefile | 1 + trunk/fs/fuse/cuse.c | 610 ++ trunk/fs/fuse/dev.c | 15 +- trunk/fs/fuse/dir.c | 33 +- trunk/fs/fuse/file.c | 346 +- trunk/fs/fuse/fuse_i.h | 47 +- trunk/fs/fuse/inode.c | 118 +- trunk/fs/gfs2/Kconfig | 1 + trunk/fs/gfs2/Makefile | 5 +- trunk/fs/gfs2/{ops_address.c => aops.c} | 21 +- trunk/fs/gfs2/bmap.c | 15 +- trunk/fs/gfs2/{ops_dentry.c => dentry.c} | 0 trunk/fs/gfs2/dir.c | 11 +- trunk/fs/gfs2/eattr.c | 14 +- trunk/fs/gfs2/{ops_export.c => export.c} | 0 trunk/fs/gfs2/{ops_file.c => file.c} | 36 +- trunk/fs/gfs2/glock.c | 33 +- trunk/fs/gfs2/glops.c | 20 +- trunk/fs/gfs2/incore.h | 27 +- trunk/fs/gfs2/inode.c | 150 +- trunk/fs/gfs2/inode.h | 52 +- trunk/fs/gfs2/log.c | 17 +- trunk/fs/gfs2/lops.c | 17 +- trunk/fs/gfs2/main.c | 8 + trunk/fs/gfs2/meta_io.c | 105 +- trunk/fs/gfs2/mount.c | 185 - trunk/fs/gfs2/ops_address.h | 23 - trunk/fs/gfs2/ops_fstype.c | 74 +- trunk/fs/gfs2/ops_inode.c | 146 + trunk/fs/gfs2/ops_super.c | 723 -- trunk/fs/gfs2/quota.c | 1 - trunk/fs/gfs2/recovery.c | 102 +- trunk/fs/gfs2/recovery.h | 2 +- trunk/fs/gfs2/rgrp.c | 152 +- trunk/fs/gfs2/rgrp.h | 47 +- trunk/fs/gfs2/super.c | 890 ++- trunk/fs/gfs2/sys.c | 245 +- trunk/fs/gfs2/trace_gfs2.h | 407 + trunk/fs/gfs2/trans.c | 9 +- trunk/fs/hfs/super.c | 23 +- trunk/fs/hfsplus/super.c | 25 +- trunk/fs/hpfs/super.c | 12 + trunk/fs/hugetlbfs/inode.c | 2 + trunk/fs/inode.c | 44 +- trunk/fs/internal.h | 17 + trunk/fs/ioctl.c | 14 +- trunk/fs/isofs/inode.c | 5 + trunk/fs/jbd/commit.c | 6 +- trunk/fs/jbd2/journal.c | 8 +- trunk/fs/jffs2/fs.c | 18 +- trunk/fs/jffs2/os-linux.h | 1 - trunk/fs/jffs2/super.c | 26 + trunk/fs/jfs/jfs_imap.c | 1 + trunk/fs/jfs/super.c | 31 +- trunk/fs/libfs.c | 25 + trunk/fs/minix/dir.c | 2 +- trunk/fs/minix/file.c | 20 +- trunk/fs/minix/inode.c | 37 +- trunk/fs/minix/minix.h | 2 - trunk/fs/mpage.c | 6 +- trunk/fs/namei.c | 135 +- trunk/fs/namespace.c | 327 +- trunk/fs/ncpfs/inode.c | 4 + trunk/fs/nfs/namespace.c | 2 +- trunk/fs/nfs/super.c | 2 + trunk/fs/nfsd/export.c | 78 +- trunk/fs/nfsd/vfs.c | 68 +- trunk/fs/nilfs2/cpfile.c | 6 +- trunk/fs/nilfs2/sb.h | 1 + trunk/fs/nilfs2/super.c | 256 +- trunk/fs/nilfs2/the_nilfs.c | 115 +- trunk/fs/nilfs2/the_nilfs.h | 23 +- trunk/fs/notify/Kconfig | 13 + trunk/fs/notify/Makefile | 2 + trunk/fs/notify/dnotify/Kconfig | 1 + trunk/fs/notify/dnotify/dnotify.c | 464 +- trunk/fs/notify/fsnotify.c | 186 + trunk/fs/notify/fsnotify.h | 34 + trunk/fs/notify/group.c | 254 + trunk/fs/notify/inode_mark.c | 426 + trunk/fs/notify/inotify/Kconfig | 20 +- trunk/fs/notify/inotify/Makefile | 2 +- trunk/fs/notify/inotify/inotify.c | 20 + trunk/fs/notify/inotify/inotify.h | 21 + trunk/fs/notify/inotify/inotify_fsnotify.c | 138 + trunk/fs/notify/inotify/inotify_user.c | 837 +- trunk/fs/notify/notification.c | 411 + trunk/fs/ntfs/super.c | 60 +- trunk/fs/ocfs2/cluster/heartbeat.c | 2 +- trunk/fs/ocfs2/super.c | 24 +- trunk/fs/omfs/file.c | 17 +- trunk/fs/open.c | 4 +- trunk/fs/partitions/check.c | 52 +- trunk/fs/partitions/ibm.c | 2 +- trunk/fs/partitions/msdos.c | 4 +- trunk/fs/pipe.c | 14 + trunk/fs/proc/base.c | 6 + trunk/fs/proc/internal.h | 25 + trunk/fs/proc/loadavg.c | 18 +- trunk/fs/proc/proc_devtree.c | 1 + trunk/fs/qnx4/Makefile | 2 +- trunk/fs/qnx4/bitmap.c | 7 +- trunk/fs/qnx4/dir.c | 9 +- trunk/fs/qnx4/file.c | 5 +- trunk/fs/qnx4/fsync.c | 169 - trunk/fs/qnx4/inode.c | 58 +- trunk/fs/qnx4/namei.c | 13 +- trunk/fs/qnx4/qnx4.h | 57 + trunk/fs/qnx4/truncate.c | 6 +- trunk/fs/quota/quota.c | 25 +- trunk/fs/read_write.c | 7 +- trunk/fs/reiserfs/dir.c | 10 +- trunk/fs/reiserfs/super.c | 33 +- trunk/fs/reiserfs/xattr.c | 3 +- trunk/fs/smbfs/inode.c | 4 + trunk/fs/splice.c | 338 +- trunk/fs/squashfs/super.c | 4 + trunk/fs/super.c | 192 +- trunk/fs/sync.c | 117 +- trunk/fs/sysv/dir.c | 2 +- trunk/fs/sysv/file.c | 17 +- trunk/fs/sysv/inode.c | 75 +- trunk/fs/sysv/sysv.h | 1 - trunk/fs/ubifs/super.c | 17 +- trunk/fs/udf/Makefile | 2 +- trunk/fs/udf/dir.c | 2 +- trunk/fs/udf/file.c | 2 +- trunk/fs/udf/fsync.c | 52 - trunk/fs/udf/super.c | 13 +- trunk/fs/udf/udfdecl.h | 3 - trunk/fs/ufs/dir.c | 2 +- trunk/fs/ufs/file.c | 23 +- trunk/fs/ufs/super.c | 65 +- trunk/fs/ufs/ufs.h | 1 - trunk/fs/xattr.c | 4 +- trunk/fs/xfs/Kconfig | 1 + trunk/fs/xfs/Makefile | 5 +- trunk/fs/xfs/linux-2.6/xfs_acl.c | 523 ++ trunk/fs/xfs/linux-2.6/xfs_buf.c | 2 +- trunk/fs/xfs/linux-2.6/xfs_ioctl.c | 25 +- trunk/fs/xfs/linux-2.6/xfs_iops.c | 53 +- trunk/fs/xfs/linux-2.6/xfs_lrw.c | 1 - trunk/fs/xfs/linux-2.6/xfs_quotaops.c | 4 +- trunk/fs/xfs/linux-2.6/xfs_super.c | 61 +- trunk/fs/xfs/linux-2.6/xfs_sync.c | 479 +- trunk/fs/xfs/linux-2.6/xfs_sync.h | 19 +- trunk/fs/xfs/linux-2.6/xfs_xattr.c | 67 +- trunk/fs/xfs/quota/xfs_dquot.c | 5 +- trunk/fs/xfs/quota/xfs_dquot.h | 1 - trunk/fs/xfs/quota/xfs_dquot_item.c | 1 - trunk/fs/xfs/quota/xfs_qm.c | 168 +- trunk/fs/xfs/quota/xfs_qm.h | 21 - trunk/fs/xfs/quota/xfs_qm_bhv.c | 77 +- trunk/fs/xfs/quota/xfs_qm_stats.c | 1 - trunk/fs/xfs/quota/xfs_qm_syscalls.c | 113 +- trunk/fs/xfs/quota/xfs_trans_dquot.c | 66 +- trunk/fs/xfs/xfs_acl.c | 874 --- trunk/fs/xfs/xfs_acl.h | 97 +- trunk/fs/xfs/xfs_ag.h | 2 + trunk/fs/xfs/xfs_arch.h | 32 - trunk/fs/xfs/xfs_attr.c | 13 +- trunk/fs/xfs/xfs_bmap.c | 34 +- trunk/fs/xfs/xfs_bmap_btree.c | 4 +- trunk/fs/xfs/xfs_filestream.c | 6 +- trunk/fs/xfs/xfs_fs.h | 11 +- trunk/fs/xfs/xfs_iget.c | 8 +- trunk/fs/xfs/xfs_inode.c | 1 - trunk/fs/xfs/xfs_inode.h | 6 + trunk/fs/xfs/xfs_iomap.c | 13 +- trunk/fs/xfs/xfs_log_recover.c | 38 +- trunk/fs/xfs/xfs_mount.c | 105 +- trunk/fs/xfs/xfs_mount.h | 84 +- trunk/fs/xfs/xfs_qmops.c | 152 - trunk/fs/xfs/xfs_quota.h | 129 +- trunk/fs/xfs/xfs_rename.c | 3 +- trunk/fs/xfs/xfs_rw.c | 1 - trunk/fs/xfs/xfs_trans.c | 17 +- trunk/fs/xfs/xfs_utils.c | 2 +- trunk/fs/xfs/xfs_vnodeops.c | 114 +- trunk/fs/xfs/xfs_vnodeops.h | 1 + trunk/include/Kbuild | 1 + trunk/include/asm-generic/Kbuild | 22 + trunk/include/asm-generic/Kbuild.asm | 1 + trunk/include/asm-generic/atomic-long.h | 258 + trunk/include/asm-generic/atomic.h | 321 +- trunk/include/asm-generic/auxvec.h | 8 + trunk/include/asm-generic/bitops.h | 24 +- trunk/include/asm-generic/bitops/atomic.h | 1 + trunk/include/asm-generic/bitsperlong.h | 32 + trunk/include/asm-generic/bugs.h | 10 + trunk/include/asm-generic/cache.h | 12 + trunk/include/asm-generic/cacheflush.h | 30 + trunk/include/asm-generic/checksum.h | 79 + trunk/include/asm-generic/current.h | 9 + trunk/include/asm-generic/delay.h | 9 + trunk/include/asm-generic/dma.h | 15 + trunk/include/asm-generic/fb.h | 12 + trunk/include/asm-generic/getorder.h | 24 + trunk/include/asm-generic/hardirq.h | 34 + trunk/include/asm-generic/hw_irq.h | 9 + trunk/include/asm-generic/int-l64.h | 2 + trunk/include/asm-generic/int-ll64.h | 2 + trunk/include/asm-generic/io.h | 300 + trunk/include/asm-generic/ioctls.h | 110 + trunk/include/asm-generic/ipcbuf.h | 34 + trunk/include/asm-generic/irq.h | 18 + trunk/include/asm-generic/irqflags.h | 72 + trunk/include/asm-generic/kmap_types.h | 32 + trunk/include/asm-generic/linkage.h | 8 + trunk/include/asm-generic/mman-common.h | 41 + trunk/include/asm-generic/mman.h | 51 +- trunk/include/asm-generic/mmu.h | 15 + trunk/include/asm-generic/mmu_context.h | 45 + trunk/include/asm-generic/module.h | 22 + trunk/include/asm-generic/msgbuf.h | 47 + trunk/include/asm-generic/mutex.h | 9 + trunk/include/asm-generic/page.h | 109 +- trunk/include/asm-generic/param.h | 24 + trunk/include/asm-generic/parport.h | 23 + trunk/include/asm-generic/pci.h | 8 + trunk/include/asm-generic/pgalloc.h | 12 + trunk/include/asm-generic/pgtable.h | 21 +- trunk/include/asm-generic/posix_types.h | 165 + trunk/include/asm-generic/rtc.h | 2 +- trunk/include/asm-generic/scatterlist.h | 43 + trunk/include/asm-generic/segment.h | 9 + trunk/include/asm-generic/sembuf.h | 38 + trunk/include/asm-generic/serial.h | 13 + trunk/include/asm-generic/setup.h | 6 + trunk/include/asm-generic/shmbuf.h | 59 + trunk/include/asm-generic/shmparam.h | 6 + trunk/include/asm-generic/signal-defs.h | 28 + trunk/include/asm-generic/signal.h | 137 +- trunk/include/asm-generic/socket.h | 63 + trunk/include/asm-generic/sockios.h | 13 + trunk/include/asm-generic/spinlock.h | 11 + trunk/include/asm-generic/stat.h | 72 + trunk/include/asm-generic/string.h | 10 + trunk/include/asm-generic/swab.h | 18 + trunk/include/asm-generic/syscalls.h | 60 + trunk/include/asm-generic/system.h | 161 + trunk/include/asm-generic/termbits.h | 198 + trunk/include/asm-generic/termios-base.h | 77 + trunk/include/asm-generic/termios.h | 105 +- trunk/include/asm-generic/timex.h | 22 + trunk/include/asm-generic/tlbflush.h | 18 + trunk/include/asm-generic/types.h | 42 + trunk/include/asm-generic/uaccess-unaligned.h | 26 + trunk/include/asm-generic/uaccess.h | 333 +- trunk/include/asm-generic/ucontext.h | 12 + trunk/include/asm-generic/unaligned.h | 30 + trunk/include/asm-generic/unistd.h | 854 +++ trunk/include/asm-generic/user.h | 8 + trunk/include/asm-generic/vga.h | 24 + trunk/include/asm-generic/vmlinux.lds.h | 2 +- trunk/include/drm/drmP.h | 126 +- trunk/include/drm/drm_crtc.h | 3 + trunk/include/drm/drm_crtc_helper.h | 2 + trunk/include/drm/drm_hashtab.h | 2 + trunk/include/drm/drm_mm.h | 90 + trunk/include/drm/drm_pciids.h | 9 + trunk/include/linux/Kbuild | 2 +- trunk/include/linux/acpi.h | 2 +- trunk/include/linux/amba/serial.h | 1 + trunk/include/linux/atmel-mci.h | 2 + trunk/include/linux/bio.h | 10 +- trunk/include/linux/blkdev.h | 247 +- trunk/include/linux/blktrace_api.h | 45 +- trunk/include/linux/cdev.h | 2 + trunk/include/linux/clocksource.h | 10 +- trunk/include/linux/compat.h | 2 + trunk/include/linux/compiler.h | 5 + trunk/include/linux/cpumask.h | 15 + trunk/include/linux/cramfs_fs.h | 3 +- trunk/include/linux/cyclades.h | 37 +- trunk/include/linux/dcache.h | 11 +- trunk/include/linux/device-mapper.h | 2 +- trunk/include/linux/device.h | 5 - trunk/include/linux/dlm.h | 4 +- trunk/include/linux/dma-debug.h | 7 + trunk/include/linux/dmar.h | 3 + trunk/include/linux/dnotify.h | 29 +- trunk/include/linux/elevator.h | 4 +- trunk/include/linux/fs.h | 29 +- trunk/include/linux/fsnotify.h | 199 +- trunk/include/linux/fsnotify_backend.h | 387 + trunk/include/linux/ftrace.h | 17 +- trunk/include/linux/ftrace_event.h | 172 + trunk/include/linux/fuse.h | 31 + trunk/include/linux/futex.h | 6 + trunk/include/linux/genhd.h | 2 + trunk/include/linux/gfp.h | 3 + trunk/include/linux/i2c-ocores.h | 2 + trunk/include/linux/ide.h | 73 +- trunk/include/linux/if_ether.h | 1 + trunk/include/linux/ima.h | 11 +- trunk/include/linux/init_task.h | 15 +- trunk/include/linux/interrupt.h | 8 +- trunk/include/linux/iocontext.h | 6 +- trunk/include/linux/irq.h | 74 +- trunk/include/linux/kernel_stat.h | 5 + trunk/include/linux/kmemleak.h | 96 + trunk/include/linux/kmemtrace.h | 25 + trunk/include/linux/kvm.h | 46 +- trunk/include/linux/kvm_host.h | 21 +- trunk/include/linux/kvm_types.h | 27 + trunk/include/linux/lguest.h | 4 + trunk/include/linux/lguest_launcher.h | 3 +- trunk/include/linux/loop.h | 3 +- trunk/include/linux/lsm_audit.h | 111 + trunk/include/linux/magic.h | 3 + trunk/include/linux/mg_disk.h | 206 - trunk/include/linux/mm.h | 11 +- trunk/include/linux/mmiotrace.h | 2 + trunk/include/linux/module.h | 9 + trunk/include/linux/moduleparam.h | 40 +- trunk/include/linux/mount.h | 25 +- trunk/include/linux/mutex.h | 1 + trunk/include/linux/namei.h | 5 +- trunk/include/linux/nfsd/export.h | 6 +- trunk/include/linux/page_cgroup.h | 18 +- trunk/include/linux/pci_ids.h | 14 + trunk/include/linux/percpu.h | 5 + trunk/include/linux/perf_counter.h | 709 ++ trunk/include/linux/pipe_fs_i.h | 1 + trunk/include/linux/pm.h | 11 +- trunk/include/linux/pnp.h | 2 + trunk/include/linux/prctl.h | 3 + trunk/include/linux/proc_fs.h | 24 - trunk/include/linux/ptrace.h | 10 - trunk/include/linux/qnx4_fs.h | 61 - trunk/include/linux/quotaops.h | 20 +- trunk/include/linux/rational.h | 19 + trunk/include/linux/rculist.h | 30 +- trunk/include/linux/rcutree.h | 9 +- trunk/include/linux/reiserfs_fs_sb.h | 2 + trunk/include/linux/ring_buffer.h | 66 +- trunk/include/linux/sched.h | 79 +- trunk/include/linux/security.h | 2 + trunk/include/linux/serial.h | 116 +- trunk/include/linux/serial_core.h | 6 +- trunk/include/linux/serial_sci.h | 3 +- trunk/include/linux/sh_cmt.h | 13 - trunk/include/linux/sh_timer.h | 13 + trunk/include/linux/signal.h | 2 + trunk/include/linux/slab.h | 4 + trunk/include/linux/slab_def.h | 2 +- trunk/include/linux/slob_def.h | 5 + trunk/include/linux/slub_def.h | 4 +- trunk/include/linux/spinlock_up.h | 1 + trunk/include/linux/splice.h | 3 +- trunk/include/linux/suspend.h | 18 +- trunk/include/linux/swiotlb.h | 3 +- trunk/include/linux/syscalls.h | 5 + trunk/include/linux/thread_info.h | 3 +- trunk/include/linux/time.h | 15 + trunk/include/linux/trace_seq.h | 92 + trunk/include/linux/tracehook.h | 11 +- trunk/include/linux/tracepoint.h | 8 +- trunk/include/linux/tty.h | 18 +- trunk/include/linux/tty_driver.h | 6 +- trunk/include/linux/usb/serial.h | 10 +- trunk/include/linux/virtio.h | 15 +- trunk/include/linux/virtio_blk.h | 12 + trunk/include/linux/virtio_config.h | 49 +- trunk/include/linux/virtio_pci.h | 10 +- trunk/include/linux/virtio_ring.h | 8 +- trunk/include/linux/wait.h | 2 - trunk/include/linux/writeback.h | 1 - trunk/include/scsi/fc/fc_fip.h | 7 - trunk/include/scsi/iscsi_if.h | 49 +- trunk/include/scsi/libfc.h | 1 + trunk/include/scsi/libiscsi.h | 8 +- trunk/include/scsi/osd_attributes.h | 74 +- trunk/include/scsi/osd_initiator.h | 14 +- trunk/include/scsi/osd_protocol.h | 8 + trunk/include/scsi/scsi_cmnd.h | 2 +- trunk/include/scsi/scsi_transport_iscsi.h | 8 +- trunk/include/sound/asound.h | 1 + trunk/include/sound/core.h | 11 +- trunk/include/sound/driver.h | 1 - trunk/include/sound/pcm.h | 76 +- trunk/include/sound/soc-dai.h | 30 +- trunk/include/sound/soc-dapm.h | 24 +- trunk/include/sound/soc.h | 34 +- trunk/include/sound/wm9081.h | 25 + trunk/include/trace/block.h | 76 - trunk/include/trace/define_trace.h | 75 + trunk/include/trace/events/block.h | 493 ++ trunk/include/trace/events/irq.h | 145 + trunk/include/trace/events/kmem.h | 231 + trunk/include/trace/events/lockdep.h | 96 + .../{sched_event_types.h => events/sched.h} | 29 +- trunk/include/trace/events/skb.h | 40 + trunk/include/trace/events/workqueue.h | 100 + trunk/include/trace/ftrace.h | 591 ++ trunk/include/trace/irq.h | 9 - trunk/include/trace/irq_event_types.h | 55 - trunk/include/trace/kmemtrace.h | 63 - trunk/include/trace/lockdep.h | 9 - trunk/include/trace/lockdep_event_types.h | 44 - trunk/include/trace/sched.h | 9 - trunk/include/trace/skb.h | 11 - trunk/include/trace/trace_event_types.h | 5 - trunk/include/trace/trace_events.h | 5 - trunk/include/trace/workqueue.h | 25 - trunk/include/xen/Kbuild | 1 + trunk/include/xen/events.h | 3 + trunk/include/xen/evtchn.h | 88 + trunk/include/xen/interface/version.h | 3 + trunk/include/xen/xenbus.h | 3 +- trunk/init/Kconfig | 41 +- trunk/init/main.c | 53 +- trunk/ipc/sem.c | 4 +- trunk/ipc/shm.c | 10 +- trunk/kernel/Makefile | 2 + trunk/kernel/async.c | 15 +- trunk/kernel/audit_tree.c | 6 +- trunk/kernel/cgroup.c | 3 + trunk/kernel/compat.c | 11 + trunk/kernel/cpuset.c | 2 +- trunk/kernel/cred.c | 4 +- trunk/kernel/exit.c | 23 +- trunk/kernel/fork.c | 33 +- trunk/kernel/futex.c | 1194 ++- trunk/kernel/irq/Makefile | 2 +- trunk/kernel/irq/chip.c | 12 +- trunk/kernel/irq/handle.c | 74 +- trunk/kernel/irq/internals.h | 5 +- trunk/kernel/irq/manage.c | 17 +- trunk/kernel/irq/migration.c | 14 +- trunk/kernel/irq/numa_migrate.c | 38 +- trunk/kernel/kexec.c | 14 +- trunk/kernel/kthread.c | 5 +- trunk/kernel/lockdep.c | 16 +- trunk/kernel/module.c | 90 +- trunk/kernel/mutex.c | 31 +- trunk/kernel/params.c | 46 +- trunk/kernel/perf_counter.c | 4339 +++++++++++ trunk/kernel/power/Kconfig | 4 + trunk/kernel/power/Makefile | 5 +- trunk/kernel/power/{disk.c => hibernate.c} | 34 +- trunk/kernel/power/hibernate_nvs.c | 135 + trunk/kernel/power/main.c | 521 -- trunk/kernel/power/power.h | 25 +- trunk/kernel/power/snapshot.c | 80 +- trunk/kernel/power/suspend.c | 300 + trunk/kernel/power/suspend_test.c | 187 + trunk/kernel/power/swsusp.c | 198 - trunk/kernel/profile.c | 6 - trunk/kernel/ptrace.c | 21 +- trunk/kernel/rcupreempt.c | 8 +- trunk/kernel/rcutree.c | 25 +- trunk/kernel/rcutree_trace.c | 64 +- trunk/kernel/rtmutex.c | 248 +- trunk/kernel/rtmutex_common.h | 8 + trunk/kernel/sched.c | 445 +- trunk/kernel/sched_cpupri.c | 8 +- trunk/kernel/sched_fair.c | 13 +- trunk/kernel/sched_idletask.c | 3 +- trunk/kernel/sched_rt.c | 2 +- trunk/kernel/signal.c | 71 +- trunk/kernel/slow-work.c | 4 +- trunk/kernel/smp.c | 2 +- trunk/kernel/softirq.c | 9 +- trunk/kernel/sys.c | 7 + trunk/kernel/sys_ni.c | 3 + trunk/kernel/sysctl.c | 49 +- trunk/kernel/time/clocksource.c | 3 - trunk/kernel/time/timekeeping.c | 9 +- trunk/kernel/timer.c | 90 +- trunk/kernel/trace/Kconfig | 143 +- trunk/kernel/trace/Makefile | 20 +- trunk/kernel/trace/blktrace.c | 285 +- trunk/kernel/trace/events.c | 14 - trunk/kernel/trace/ftrace.c | 801 +- trunk/kernel/trace/kmemtrace.c | 10 +- trunk/kernel/trace/ring_buffer.c | 777 +- trunk/kernel/trace/ring_buffer_benchmark.c | 416 + trunk/kernel/trace/trace.c | 383 +- trunk/kernel/trace/trace.h | 243 +- trunk/kernel/trace/trace_boot.c | 5 +- trunk/kernel/trace/trace_branch.c | 8 +- trunk/kernel/trace/trace_event_profile.c | 24 +- trunk/kernel/trace/trace_event_types.h | 12 +- trunk/kernel/trace/trace_events.c | 839 +- trunk/kernel/trace/trace_events_filter.c | 1204 ++- trunk/kernel/trace/trace_events_stage_1.h | 39 - trunk/kernel/trace/trace_events_stage_2.h | 176 - trunk/kernel/trace/trace_events_stage_3.h | 281 - trunk/kernel/trace/trace_export.c | 110 +- trunk/kernel/trace/trace_functions_graph.c | 31 +- trunk/kernel/trace/trace_hw_branches.c | 203 +- trunk/kernel/trace/trace_mmiotrace.c | 6 +- trunk/kernel/trace/trace_output.c | 240 +- trunk/kernel/trace/trace_output.h | 34 +- trunk/kernel/trace/trace_power.c | 8 +- trunk/kernel/trace/trace_printk.c | 6 +- trunk/kernel/trace/trace_sched_switch.c | 12 +- trunk/kernel/trace/trace_sched_wakeup.c | 8 +- trunk/kernel/trace/trace_selftest.c | 58 + trunk/kernel/trace/trace_stack.c | 15 +- trunk/kernel/trace/trace_stat.c | 208 +- trunk/kernel/trace/trace_stat.h | 2 +- trunk/kernel/trace/trace_sysprof.c | 6 +- trunk/kernel/trace/trace_workqueue.c | 25 +- trunk/kernel/wait.c | 2 +- trunk/kernel/workqueue.c | 11 +- trunk/lib/Kconfig | 3 + trunk/lib/Kconfig.debug | 32 + trunk/lib/Makefile | 3 + trunk/lib/checksum.c | 193 + trunk/lib/cpumask.c | 23 +- trunk/lib/dma-debug.c | 432 +- trunk/lib/extable.c | 21 +- trunk/lib/rational.c | 62 + trunk/lib/swiotlb.c | 119 +- trunk/lib/vsprintf.c | 56 +- trunk/mm/Kconfig | 19 + trunk/mm/Makefile | 2 + trunk/mm/bootmem.c | 12 + trunk/mm/bounce.c | 9 +- trunk/mm/kmemleak-test.c | 111 + trunk/mm/kmemleak.c | 1498 ++++ trunk/mm/maccess.c | 2 +- trunk/mm/mlock.c | 51 +- trunk/mm/mmap.c | 8 + trunk/mm/mprotect.c | 2 + trunk/mm/nommu.c | 3 + trunk/mm/page_alloc.c | 80 +- trunk/mm/page_cgroup.c | 17 +- trunk/mm/percpu.c | 141 +- trunk/mm/shmem.c | 2 +- trunk/mm/slab.c | 158 +- trunk/mm/slob.c | 9 +- trunk/mm/slub.c | 40 +- trunk/mm/util.c | 11 +- trunk/mm/vmalloc.c | 33 +- trunk/mm/vmscan.c | 4 +- trunk/net/9p/trans_virtio.c | 6 +- trunk/net/core/drop_monitor.c | 2 +- trunk/net/core/net-traces.c | 4 +- trunk/net/core/skbuff.c | 2 +- trunk/net/sched/cls_cgroup.c | 3 + trunk/samples/Kconfig | 6 + trunk/samples/Makefile | 2 +- trunk/samples/trace_events/Makefile | 6 + .../trace_events/trace-events-sample.c | 52 + .../trace_events/trace-events-sample.h | 129 + trunk/scripts/Makefile.lib | 28 +- trunk/scripts/bin_size | 10 - trunk/scripts/checksyscalls.sh | 92 +- trunk/scripts/kernel-doc | 22 + trunk/scripts/mod/file2alias.c | 2 +- trunk/scripts/recordmcount.pl | 19 +- trunk/security/Kconfig | 22 +- trunk/security/Makefile | 3 + trunk/security/commoncap.c | 32 + trunk/security/inode.c | 2 +- trunk/security/integrity/ima/ima_audit.c | 32 +- trunk/security/integrity/ima/ima_crypto.c | 4 +- trunk/security/integrity/ima/ima_fs.c | 12 +- trunk/security/integrity/ima/ima_iint.c | 2 +- trunk/security/integrity/ima/ima_init.c | 4 +- trunk/security/integrity/ima/ima_main.c | 86 +- trunk/security/integrity/ima/ima_policy.c | 48 +- trunk/security/lsm_audit.c | 386 + trunk/security/root_plug.c | 12 - trunk/security/security.c | 3 - trunk/security/selinux/avc.c | 2 +- trunk/security/selinux/hooks.c | 24 +- trunk/security/selinux/include/security.h | 7 +- trunk/security/selinux/nlmsgtab.c | 2 + trunk/security/selinux/selinuxfs.c | 8 +- trunk/security/selinux/ss/services.c | 30 +- trunk/security/smack/smack.h | 108 +- trunk/security/smack/smack_access.c | 143 +- trunk/security/smack/smack_lsm.c | 405 +- trunk/security/smack/smackfs.c | 76 +- trunk/security/tomoyo/common.c | 119 +- trunk/security/tomoyo/common.h | 134 +- trunk/security/tomoyo/domain.c | 240 +- trunk/security/tomoyo/file.c | 156 +- trunk/security/tomoyo/realpath.c | 23 +- trunk/security/tomoyo/tomoyo.c | 4 + trunk/security/tomoyo/tomoyo.h | 13 +- trunk/sound/aoa/fabrics/layout.c | 8 +- trunk/sound/aoa/soundbus/i2sbus/core.c | 8 +- trunk/sound/core/Kconfig | 2 + trunk/sound/core/init.c | 61 +- trunk/sound/core/jack.c | 2 +- trunk/sound/core/oss/pcm_oss.c | 5 +- trunk/sound/core/pcm_lib.c | 92 +- trunk/sound/core/pcm_native.c | 23 +- trunk/sound/core/seq/Kconfig | 16 + trunk/sound/core/seq/Makefile | 18 +- trunk/sound/drivers/opl3/Makefile | 10 +- trunk/sound/drivers/opl4/Makefile | 10 +- trunk/sound/isa/Kconfig | 7 +- trunk/sound/isa/es1688/es1688.c | 2 +- trunk/sound/isa/gus/gusextreme.c | 2 +- trunk/sound/isa/sb/Makefile | 10 +- trunk/sound/isa/sc6000.c | 134 +- trunk/sound/mips/sgio2audio.c | 3 +- trunk/sound/oss/Kconfig | 2 +- trunk/sound/oss/sh_dac_audio.c | 85 +- trunk/sound/parisc/harmony.c | 4 +- trunk/sound/pci/Kconfig | 27 +- trunk/sound/pci/Makefile | 2 + trunk/sound/pci/au88x0/au88x0_core.c | 10 +- trunk/sound/pci/bt87x.c | 2 + trunk/sound/pci/ca0106/ca0106_main.c | 1 - trunk/sound/pci/ca0106/ca0106_mixer.c | 10 +- trunk/sound/pci/ctxfi/Makefile | 5 + trunk/sound/pci/ctxfi/ct20k1reg.h | 636 ++ trunk/sound/pci/ctxfi/ct20k2reg.h | 85 + trunk/sound/pci/ctxfi/ctamixer.c | 488 ++ trunk/sound/pci/ctxfi/ctamixer.h | 96 + trunk/sound/pci/ctxfi/ctatc.c | 1619 ++++ trunk/sound/pci/ctxfi/ctatc.h | 147 + trunk/sound/pci/ctxfi/ctdaio.c | 769 ++ trunk/sound/pci/ctxfi/ctdaio.h | 122 + trunk/sound/pci/ctxfi/cthardware.c | 91 + trunk/sound/pci/ctxfi/cthardware.h | 196 + trunk/sound/pci/ctxfi/cthw20k1.c | 2248 ++++++ trunk/sound/pci/ctxfi/cthw20k1.h | 26 + trunk/sound/pci/ctxfi/cthw20k2.c | 2137 ++++++ trunk/sound/pci/ctxfi/cthw20k2.h | 26 + trunk/sound/pci/ctxfi/ctimap.c | 112 + trunk/sound/pci/ctxfi/ctimap.h | 40 + trunk/sound/pci/ctxfi/ctmixer.c | 1123 +++ trunk/sound/pci/ctxfi/ctmixer.h | 67 + trunk/sound/pci/ctxfi/ctpcm.c | 426 + trunk/sound/pci/ctxfi/ctpcm.h | 27 + trunk/sound/pci/ctxfi/ctresource.c | 301 + trunk/sound/pci/ctxfi/ctresource.h | 72 + trunk/sound/pci/ctxfi/ctsrc.c | 886 +++ trunk/sound/pci/ctxfi/ctsrc.h | 149 + trunk/sound/pci/ctxfi/cttimer.c | 441 ++ trunk/sound/pci/ctxfi/cttimer.h | 29 + trunk/sound/pci/ctxfi/ctvmem.c | 250 + trunk/sound/pci/ctxfi/ctvmem.h | 61 + trunk/sound/pci/ctxfi/xfi.c | 142 + trunk/sound/pci/emu10k1/Makefile | 10 +- trunk/sound/pci/emu10k1/emu10k1x.c | 1 - trunk/sound/pci/emu10k1/emupcm.c | 2 +- trunk/sound/pci/hda/Kconfig | 13 + trunk/sound/pci/hda/Makefile | 4 + trunk/sound/pci/hda/hda_beep.c | 55 +- trunk/sound/pci/hda/hda_beep.h | 5 +- trunk/sound/pci/hda/hda_codec.c | 239 +- trunk/sound/pci/hda/hda_codec.h | 13 +- trunk/sound/pci/hda/hda_hwdep.c | 9 +- trunk/sound/pci/hda/hda_intel.c | 197 +- trunk/sound/pci/hda/hda_proc.c | 8 +- trunk/sound/pci/hda/patch_ca0110.c | 573 ++ trunk/sound/pci/hda/patch_nvhdmi.c | 279 +- trunk/sound/pci/hda/patch_realtek.c | 2334 +++--- trunk/sound/pci/hda/patch_sigmatel.c | 278 +- trunk/sound/pci/hda/patch_via.c | 111 +- trunk/sound/pci/ice1712/Makefile | 2 +- trunk/sound/pci/ice1712/ice1712.h | 12 +- trunk/sound/pci/ice1712/ice1724.c | 96 +- trunk/sound/pci/ice1712/maya44.c | 779 ++ trunk/sound/pci/ice1712/maya44.h | 10 + trunk/sound/pci/lx6464es/Makefile | 2 + trunk/sound/pci/lx6464es/lx6464es.c | 1159 +++ trunk/sound/pci/lx6464es/lx6464es.h | 114 + trunk/sound/pci/lx6464es/lx_core.c | 1444 ++++ trunk/sound/pci/lx6464es/lx_core.h | 242 + trunk/sound/pci/lx6464es/lx_defs.h | 376 + trunk/sound/pci/oxygen/oxygen_pcm.c | 6 +- trunk/sound/pci/oxygen/virtuoso.c | 64 +- trunk/sound/pci/riptide/riptide.c | 347 +- trunk/sound/pci/rme9652/hdsp.c | 11 +- trunk/sound/pci/rme9652/hdspm.c | 4 +- trunk/sound/ppc/awacs.c | 54 +- trunk/sound/ppc/beep.c | 2 +- trunk/sound/ppc/burgundy.c | 26 +- trunk/sound/ppc/daca.c | 2 +- trunk/sound/ppc/keywest.c | 10 +- trunk/sound/ppc/pmac.c | 12 +- trunk/sound/ppc/snd_ps3.c | 777 +- trunk/sound/ppc/tumbler.c | 16 +- trunk/sound/soc/Kconfig | 2 + trunk/sound/soc/Makefile | 2 + trunk/sound/soc/atmel/Kconfig | 8 + trunk/sound/soc/atmel/Makefile | 1 + trunk/sound/soc/atmel/playpaq_wm8510.c | 2 +- trunk/sound/soc/atmel/snd-soc-afeb9260.c | 203 + trunk/sound/soc/blackfin/bf5xx-ac97.c | 9 + trunk/sound/soc/blackfin/bf5xx-sport.c | 4 +- trunk/sound/soc/codecs/Kconfig | 24 + trunk/sound/soc/codecs/Makefile | 12 + trunk/sound/soc/codecs/ac97.c | 4 +- trunk/sound/soc/codecs/ad1980.c | 4 +- trunk/sound/soc/codecs/cs4270.c | 105 +- trunk/sound/soc/codecs/spdif_transciever.c | 71 + trunk/sound/soc/codecs/spdif_transciever.h | 17 + trunk/sound/soc/codecs/ssm2602.c | 33 +- trunk/sound/soc/codecs/stac9766.c | 463 ++ trunk/sound/soc/codecs/stac9766.h | 21 + trunk/sound/soc/codecs/tlv320aic23.c | 16 +- trunk/sound/soc/codecs/twl4030.c | 1116 ++- trunk/sound/soc/codecs/twl4030.h | 43 +- trunk/sound/soc/codecs/uda134x.c | 4 +- trunk/sound/soc/codecs/wm8350.c | 2 +- trunk/sound/soc/codecs/wm8350.h | 1 + trunk/sound/soc/codecs/wm8400.c | 8 +- trunk/sound/soc/codecs/wm8510.c | 2 +- trunk/sound/soc/codecs/wm8580.c | 4 +- trunk/sound/soc/codecs/wm8731.c | 4 +- trunk/sound/soc/codecs/wm8753.c | 6 +- trunk/sound/soc/codecs/wm8900.c | 6 +- trunk/sound/soc/codecs/wm8903.c | 119 +- trunk/sound/soc/codecs/wm8940.c | 955 +++ trunk/sound/soc/codecs/wm8940.h | 104 + trunk/sound/soc/codecs/wm8960.c | 969 +++ trunk/sound/soc/codecs/wm8960.h | 127 + trunk/sound/soc/codecs/wm8988.c | 1097 +++ trunk/sound/soc/codecs/wm8988.h | 60 + trunk/sound/soc/codecs/wm8990.c | 2 +- trunk/sound/soc/codecs/wm9081.c | 1534 ++++ trunk/sound/soc/codecs/wm9081.h | 787 ++ trunk/sound/soc/codecs/wm9705.c | 4 +- trunk/sound/soc/codecs/wm9712.c | 8 +- trunk/sound/soc/codecs/wm9713.c | 48 +- trunk/sound/soc/fsl/Kconfig | 32 +- trunk/sound/soc/fsl/Makefile | 7 + trunk/sound/soc/fsl/efika-audio-fabric.c | 90 + trunk/sound/soc/fsl/fsl_ssi.c | 11 +- trunk/sound/soc/fsl/mpc5200_dma.c | 564 ++ trunk/sound/soc/fsl/mpc5200_dma.h | 80 + trunk/sound/soc/fsl/mpc5200_psc_ac97.c | 329 + trunk/sound/soc/fsl/mpc5200_psc_ac97.h | 15 + trunk/sound/soc/fsl/mpc5200_psc_i2s.c | 754 +- trunk/sound/soc/fsl/mpc5200_psc_i2s.h | 12 + trunk/sound/soc/fsl/pcm030-audio-fabric.c | 90 + trunk/sound/soc/omap/Kconfig | 8 + trunk/sound/soc/omap/Makefile | 2 + trunk/sound/soc/omap/n810.c | 7 +- trunk/sound/soc/omap/omap-mcbsp.c | 43 +- trunk/sound/soc/omap/omap-pcm.c | 9 +- trunk/sound/soc/omap/omap2evm.c | 2 +- trunk/sound/soc/omap/omap3beagle.c | 28 +- trunk/sound/soc/omap/omap3evm.c | 147 + trunk/sound/soc/omap/omap3pandora.c | 4 +- trunk/sound/soc/omap/overo.c | 2 +- trunk/sound/soc/omap/sdp3430.c | 94 +- trunk/sound/soc/pxa/Kconfig | 13 +- trunk/sound/soc/pxa/Makefile | 2 + trunk/sound/soc/pxa/em-x270.c | 9 +- trunk/sound/soc/pxa/imote2.c | 114 + trunk/sound/soc/pxa/magician.c | 13 +- trunk/sound/soc/pxa/pxa-ssp.c | 218 +- trunk/sound/soc/pxa/pxa2xx-i2s.c | 39 +- trunk/sound/soc/s3c24xx/neo1973_wm8753.c | 16 +- trunk/sound/soc/s3c24xx/s3c-i2s-v2.c | 91 +- trunk/sound/soc/s3c24xx/s3c2412-i2s.c | 2 +- trunk/sound/soc/s3c24xx/s3c64xx-i2s.c | 157 +- trunk/sound/soc/s3c24xx/s3c64xx-i2s.h | 6 +- trunk/sound/soc/s6000/Kconfig | 19 + trunk/sound/soc/s6000/Makefile | 11 + trunk/sound/soc/s6000/s6000-i2s.c | 629 ++ trunk/sound/soc/s6000/s6000-i2s.h | 25 + trunk/sound/soc/s6000/s6000-pcm.c | 497 ++ trunk/sound/soc/s6000/s6000-pcm.h | 35 + trunk/sound/soc/s6000/s6105-ipcam.c | 244 + trunk/sound/soc/sh/ssi.c | 2 +- trunk/sound/soc/soc-core.c | 165 +- trunk/sound/soc/soc-dapm.c | 427 +- trunk/sound/soc/txx9/Kconfig | 29 + trunk/sound/soc/txx9/Makefile | 11 + trunk/sound/soc/txx9/txx9aclc-ac97.c | 255 + trunk/sound/soc/txx9/txx9aclc-generic.c | 98 + trunk/sound/soc/txx9/txx9aclc.c | 430 ++ trunk/sound/soc/txx9/txx9aclc.h | 83 + trunk/sound/synth/Makefile | 12 +- trunk/sound/synth/emux/Makefile | 12 +- trunk/sound/usb/caiaq/audio.c | 88 +- trunk/sound/usb/caiaq/device.c | 109 +- trunk/sound/usb/caiaq/device.h | 1 - trunk/sound/usb/caiaq/midi.c | 24 +- trunk/sound/usb/usbaudio.c | 39 +- trunk/sound/usb/usbquirks.h | 43 + trunk/tools/perf/.gitignore | 16 + trunk/tools/perf/Documentation/Makefile | 300 + trunk/tools/perf/Documentation/asciidoc.conf | 91 + .../tools/perf/Documentation/manpage-1.72.xsl | 14 + .../tools/perf/Documentation/manpage-base.xsl | 35 + .../Documentation/manpage-bold-literal.xsl | 17 + .../perf/Documentation/manpage-normal.xsl | 13 + .../Documentation/manpage-suppress-sp.xsl | 21 + .../perf/Documentation/perf-annotate.txt | 29 + trunk/tools/perf/Documentation/perf-help.txt | 38 + trunk/tools/perf/Documentation/perf-list.txt | 25 + .../tools/perf/Documentation/perf-record.txt | 42 + .../tools/perf/Documentation/perf-report.txt | 26 + trunk/tools/perf/Documentation/perf-stat.txt | 66 + trunk/tools/perf/Documentation/perf-top.txt | 39 + trunk/tools/perf/Documentation/perf.txt | 24 + trunk/tools/perf/Makefile | 929 +++ trunk/tools/perf/builtin-annotate.c | 1356 ++++ trunk/tools/perf/builtin-help.c | 461 ++ trunk/tools/perf/builtin-list.c | 20 + trunk/tools/perf/builtin-record.c | 585 ++ trunk/tools/perf/builtin-report.c | 1316 ++++ trunk/tools/perf/builtin-stat.c | 367 + trunk/tools/perf/builtin-top.c | 736 ++ trunk/tools/perf/builtin.h | 26 + trunk/tools/perf/command-list.txt | 10 + trunk/tools/perf/design.txt | 457 ++ trunk/tools/perf/perf.c | 428 ++ trunk/tools/perf/perf.h | 68 + trunk/tools/perf/util/PERF-VERSION-GEN | 42 + trunk/tools/perf/util/abspath.c | 117 + trunk/tools/perf/util/alias.c | 77 + trunk/tools/perf/util/cache.h | 119 + trunk/tools/perf/util/color.c | 241 + trunk/tools/perf/util/color.h | 36 + trunk/tools/perf/util/config.c | 873 +++ trunk/tools/perf/util/ctype.c | 26 + trunk/tools/perf/util/environment.c | 9 + trunk/tools/perf/util/exec_cmd.c | 165 + trunk/tools/perf/util/exec_cmd.h | 13 + trunk/tools/perf/util/generate-cmdlist.sh | 24 + trunk/tools/perf/util/help.c | 367 + trunk/tools/perf/util/help.h | 29 + trunk/tools/perf/util/levenshtein.c | 84 + trunk/tools/perf/util/levenshtein.h | 8 + trunk/tools/perf/util/list.h | 603 ++ trunk/tools/perf/util/pager.c | 99 + trunk/tools/perf/util/parse-events.c | 316 + trunk/tools/perf/util/parse-events.h | 17 + trunk/tools/perf/util/parse-options.c | 508 ++ trunk/tools/perf/util/parse-options.h | 174 + trunk/tools/perf/util/path.c | 353 + trunk/tools/perf/util/quote.c | 481 ++ trunk/tools/perf/util/quote.h | 68 + trunk/tools/perf/util/rbtree.c | 383 + trunk/tools/perf/util/rbtree.h | 171 + trunk/tools/perf/util/run-command.c | 395 + trunk/tools/perf/util/run-command.h | 93 + trunk/tools/perf/util/sigchain.c | 52 + trunk/tools/perf/util/sigchain.h | 11 + trunk/tools/perf/util/strbuf.c | 359 + trunk/tools/perf/util/strbuf.h | 137 + trunk/tools/perf/util/string.c | 34 + trunk/tools/perf/util/string.h | 8 + trunk/tools/perf/util/symbol.c | 641 ++ trunk/tools/perf/util/symbol.h | 47 + trunk/tools/perf/util/usage.c | 80 + trunk/tools/perf/util/util.h | 410 + trunk/tools/perf/util/wrapper.c | 206 + trunk/virt/kvm/ioapic.c | 153 +- trunk/virt/kvm/ioapic.h | 27 +- trunk/virt/kvm/iommu.c | 27 +- trunk/virt/kvm/irq_comm.c | 111 +- trunk/virt/kvm/kvm_main.c | 680 +- 2549 files changed, 208611 insertions(+), 58115 deletions(-) create mode 100644 trunk/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss create mode 100644 trunk/Documentation/ABI/testing/sysfs-devices-cache_disable create mode 100644 trunk/Documentation/DocBook/tracepoint.tmpl create mode 100644 trunk/Documentation/filesystems/debugfs.txt create mode 100644 trunk/Documentation/futex-requeue-pi.txt create mode 100644 trunk/Documentation/kmemleak.txt create mode 100644 trunk/Documentation/sound/alsa/README.maya44 create mode 100644 trunk/Documentation/trace/events.txt create mode 100644 trunk/Documentation/trace/power.txt create mode 100644 trunk/arch/alpha/include/asm/bitsperlong.h delete mode 100644 trunk/arch/alpha/include/asm/suspend.h create mode 100644 trunk/arch/arm/include/asm/bitsperlong.h delete mode 100644 trunk/arch/arm/include/asm/suspend.h create mode 100644 trunk/arch/avr32/boards/atngw100/Kconfig_mrmt create mode 100644 trunk/arch/avr32/boards/atngw100/mrmt.c create mode 100644 trunk/arch/avr32/configs/atngw100_mrmt_defconfig create mode 100644 trunk/arch/avr32/include/asm/bitsperlong.h create mode 100644 trunk/arch/blackfin/include/asm/bitsperlong.h create mode 100644 trunk/arch/cris/include/asm/bitsperlong.h create mode 100644 trunk/arch/frv/include/asm/bitsperlong.h create mode 100644 trunk/arch/frv/include/asm/syscall.h create mode 100644 trunk/arch/h8300/include/asm/bitsperlong.h create mode 100644 trunk/arch/ia64/include/asm/bitsperlong.h delete mode 100644 trunk/arch/ia64/include/asm/suspend.h create mode 100644 trunk/arch/m32r/include/asm/bitsperlong.h create mode 100644 trunk/arch/m68k/include/asm/bitsperlong.h delete mode 100644 trunk/arch/m68k/include/asm/suspend.h create mode 100644 trunk/arch/microblaze/configs/mmu_defconfig create mode 100644 trunk/arch/microblaze/include/asm/bitsperlong.h create mode 100644 trunk/arch/microblaze/include/asm/mmu_context_mm.h create mode 100644 trunk/arch/microblaze/include/asm/mmu_context_no.h create mode 100644 trunk/arch/microblaze/kernel/entry.S create mode 100644 trunk/arch/microblaze/kernel/misc.S create mode 100644 trunk/arch/microblaze/lib/uaccess_old.S create mode 100644 trunk/arch/microblaze/mm/fault.c create mode 100644 trunk/arch/microblaze/mm/mmu_context.c create mode 100644 trunk/arch/microblaze/mm/pgtable.c create mode 100644 trunk/arch/mips/include/asm/bitsperlong.h delete mode 100644 trunk/arch/mips/include/asm/suspend.h create mode 100644 trunk/arch/mips/lib/delay.c create mode 100644 trunk/arch/mn10300/include/asm/bitsperlong.h create mode 100644 trunk/arch/parisc/include/asm/bitsperlong.h create mode 100644 trunk/arch/powerpc/include/asm/bitsperlong.h create mode 100644 trunk/arch/powerpc/include/asm/perf_counter.h create mode 100644 trunk/arch/powerpc/kernel/perf_counter.c create mode 100644 trunk/arch/powerpc/kernel/power4-pmu.c create mode 100644 trunk/arch/powerpc/kernel/power5+-pmu.c create mode 100644 trunk/arch/powerpc/kernel/power5-pmu.c create mode 100644 trunk/arch/powerpc/kernel/power6-pmu.c create mode 100644 trunk/arch/powerpc/kernel/power7-pmu.c create mode 100644 trunk/arch/powerpc/kernel/ppc970-pmu.c create mode 100644 trunk/arch/s390/include/asm/bitsperlong.h delete mode 100644 trunk/arch/s390/include/asm/cpu.h create mode 100644 trunk/arch/s390/include/asm/seccomp.h delete mode 100644 trunk/arch/s390/include/asm/suspend.h create mode 100644 trunk/arch/s390/kernel/ftrace.c create mode 100644 trunk/arch/s390/kernel/sclp.S create mode 100644 trunk/arch/s390/mm/maccess.c create mode 100644 trunk/arch/sh/boards/mach-cayman/panic.c create mode 100644 trunk/arch/sh/boards/mach-se/7724/Makefile create mode 100644 trunk/arch/sh/boards/mach-se/7724/irq.c create mode 100644 trunk/arch/sh/boards/mach-se/7724/setup.c delete mode 100644 trunk/arch/sh/boards/mach-se/7751/pci.c delete mode 100644 trunk/arch/sh/boot/compressed/Makefile_32 delete mode 100644 trunk/arch/sh/boot/compressed/Makefile_64 delete mode 100644 trunk/arch/sh/boot/compressed/vmlinux_64.lds create mode 100644 trunk/arch/sh/configs/se7724_defconfig create mode 100644 trunk/arch/sh/configs/sh7724_generic_defconfig create mode 100644 trunk/arch/sh/configs/sh7770_generic_defconfig rename trunk/arch/sh/drivers/pci/{ops-cayman.c => fixups-cayman.c} (88%) rename trunk/arch/sh/drivers/pci/{ops-landisk.c => fixups-landisk.c} (51%) delete mode 100644 trunk/arch/sh/drivers/pci/fixups-lboxre2.c create mode 100644 trunk/arch/sh/drivers/pci/fixups-se7751.c delete mode 100644 trunk/arch/sh/drivers/pci/fixups-se7780.c delete mode 100644 trunk/arch/sh/drivers/pci/fixups-sh7785lcr.c create mode 100644 trunk/arch/sh/drivers/pci/fixups-snapgear.c rename trunk/arch/sh/drivers/pci/{ops-titan.c => fixups-titan.c} (50%) delete mode 100644 trunk/arch/sh/drivers/pci/ops-lboxre2.c delete mode 100644 trunk/arch/sh/drivers/pci/ops-r7780rp.c delete mode 100644 trunk/arch/sh/drivers/pci/ops-rts7751r2d.c delete mode 100644 trunk/arch/sh/drivers/pci/ops-sdk7780.c delete mode 100644 trunk/arch/sh/drivers/pci/ops-se7780.c delete mode 100644 trunk/arch/sh/drivers/pci/ops-sh03.c delete mode 100644 trunk/arch/sh/drivers/pci/ops-sh7785lcr.c delete mode 100644 trunk/arch/sh/drivers/pci/ops-snapgear.c delete mode 100644 trunk/arch/sh/drivers/pci/pci-auto.c create mode 100644 trunk/arch/sh/drivers/pci/pci-dreamcast.c create mode 100644 trunk/arch/sh/include/asm/bitsperlong.h delete mode 100644 trunk/arch/sh/include/asm/timer.h delete mode 100644 trunk/arch/sh/include/cpu-sh3/cpu/timer.h create mode 100644 trunk/arch/sh/include/cpu-sh4/cpu/sh7724.h delete mode 100644 trunk/arch/sh/include/cpu-sh4/cpu/timer.h create mode 100644 trunk/arch/sh/include/mach-se/mach/se7724.h create mode 100644 trunk/arch/sh/kernel/cpu/clock-cpg.c create mode 100644 trunk/arch/sh/kernel/cpu/sh4a/clock-sh7343.c create mode 100644 trunk/arch/sh/kernel/cpu/sh4a/clock-sh7366.c create mode 100644 trunk/arch/sh/kernel/cpu/sh4a/clock-sh7723.c create mode 100644 trunk/arch/sh/kernel/cpu/sh4a/clock-sh7724.c create mode 100644 trunk/arch/sh/kernel/cpu/sh4a/pinmux-sh7724.c create mode 100644 trunk/arch/sh/kernel/cpu/sh4a/setup-sh7724.c create mode 100644 trunk/arch/sh/kernel/cpu/sh5/setup-sh5.c rename trunk/arch/sh/kernel/{timers/timer-broadcast.c => localtimer.c} (100%) create mode 100644 trunk/arch/sh/kernel/time.c delete mode 100644 trunk/arch/sh/kernel/time_32.c delete mode 100644 trunk/arch/sh/kernel/time_64.c delete mode 100644 trunk/arch/sh/kernel/timers/Makefile delete mode 100644 trunk/arch/sh/kernel/timers/timer-cmt.c delete mode 100644 trunk/arch/sh/kernel/timers/timer-mtu2.c delete mode 100644 trunk/arch/sh/kernel/timers/timer-tmu.c delete mode 100644 trunk/arch/sh/kernel/timers/timer.c delete mode 100644 trunk/arch/sh/kernel/vmlinux_32.lds.S delete mode 100644 trunk/arch/sh/kernel/vmlinux_64.lds.S delete mode 100644 trunk/arch/sh/lib64/.gitignore create mode 100644 trunk/arch/sparc/include/asm/bitsperlong.h delete mode 100644 trunk/arch/um/include/asm/suspend.h delete mode 100644 trunk/arch/um/sys-x86_64/um_module.c create mode 100644 trunk/arch/x86/Kbuild create mode 100644 trunk/arch/x86/boot/bioscall.S create mode 100644 trunk/arch/x86/boot/compressed/mkpiggy.c rename trunk/arch/x86/boot/compressed/{vmlinux_64.lds => vmlinux.lds.S} (57%) delete mode 100644 trunk/arch/x86/boot/compressed/vmlinux.scr delete mode 100644 trunk/arch/x86/boot/compressed/vmlinux_32.lds create mode 100644 trunk/arch/x86/boot/regs.c create mode 100644 trunk/arch/x86/crypto/fpu.c create mode 100644 trunk/arch/x86/include/asm/bitsperlong.h delete mode 100644 trunk/arch/x86/include/asm/intel_arch_perfmon.h create mode 100644 trunk/arch/x86/include/asm/perf_counter.h create mode 100644 trunk/arch/x86/kernel/acpi/realmode/bioscall.S create mode 100644 trunk/arch/x86/kernel/acpi/realmode/regs.c create mode 100644 trunk/arch/x86/kernel/cpu/mcheck/mce-inject.c create mode 100644 trunk/arch/x86/kernel/cpu/mcheck/mce-internal.h create mode 100644 trunk/arch/x86/kernel/cpu/mcheck/mce-severity.c create mode 100644 trunk/arch/x86/kernel/cpu/mcheck/mce.c delete mode 100644 trunk/arch/x86/kernel/cpu/mcheck/mce_32.c delete mode 100644 trunk/arch/x86/kernel/cpu/mcheck/mce_64.c create mode 100644 trunk/arch/x86/kernel/cpu/mcheck/mce_intel.c create mode 100644 trunk/arch/x86/kernel/cpu/perf_counter.c create mode 100644 trunk/arch/x86/kernel/ds_selftest.c create mode 100644 trunk/arch/x86/kernel/ds_selftest.h rename trunk/arch/x86/kernel/{irqinit_32.c => irqinit.c} (67%) delete mode 100644 trunk/arch/x86/kernel/irqinit_64.c rename trunk/arch/x86/kernel/{module_64.c => module.c} (74%) delete mode 100644 trunk/arch/x86/kernel/module_32.c delete mode 100644 trunk/arch/x86/kernel/vmlinux_32.lds.S delete mode 100644 trunk/arch/x86/kernel/vmlinux_64.lds.S create mode 100644 trunk/arch/x86/kvm/kvm_timer.h create mode 100644 trunk/arch/x86/kvm/timer.c delete mode 100644 trunk/arch/x86/lib/msr-on-cpu.c create mode 100644 trunk/arch/x86/lib/msr.c rename trunk/arch/x86/power/{cpu_64.c => cpu.c} (62%) delete mode 100644 trunk/arch/x86/power/cpu_32.c create mode 100644 trunk/arch/xtensa/include/asm/bitsperlong.h create mode 100644 trunk/drivers/char/bfin_jtag_comm.c create mode 100644 trunk/drivers/clocksource/sh_mtu2.c create mode 100644 trunk/drivers/clocksource/sh_tmu.c create mode 100644 trunk/drivers/edac/amd64_edac.c create mode 100644 trunk/drivers/edac/amd64_edac.h create mode 100644 trunk/drivers/edac/amd64_edac_dbg.c create mode 100644 trunk/drivers/edac/amd64_edac_err_types.c create mode 100644 trunk/drivers/edac/amd64_edac_inj.c create mode 100644 trunk/drivers/net/cnic.c create mode 100644 trunk/drivers/net/cnic.h create mode 100644 trunk/drivers/net/cnic_defs.h create mode 100644 trunk/drivers/net/cnic_if.h create mode 100644 trunk/drivers/scsi/bnx2i/57xx_iscsi_constants.h create mode 100644 trunk/drivers/scsi/bnx2i/57xx_iscsi_hsi.h create mode 100644 trunk/drivers/scsi/bnx2i/Kconfig create mode 100644 trunk/drivers/scsi/bnx2i/Makefile create mode 100644 trunk/drivers/scsi/bnx2i/bnx2i.h create mode 100644 trunk/drivers/scsi/bnx2i/bnx2i_hwi.c create mode 100644 trunk/drivers/scsi/bnx2i/bnx2i_init.c create mode 100644 trunk/drivers/scsi/bnx2i/bnx2i_iscsi.c create mode 100644 trunk/drivers/scsi/bnx2i/bnx2i_sysfs.c create mode 100644 trunk/drivers/scsi/lpfc/lpfc_hw4.h create mode 100644 trunk/drivers/scsi/lpfc/lpfc_sli4.h delete mode 100644 trunk/drivers/scsi/mvsas.c create mode 100644 trunk/drivers/scsi/mvsas/Kconfig create mode 100644 trunk/drivers/scsi/mvsas/Makefile create mode 100644 trunk/drivers/scsi/mvsas/mv_64xx.c create mode 100644 trunk/drivers/scsi/mvsas/mv_64xx.h create mode 100644 trunk/drivers/scsi/mvsas/mv_94xx.c create mode 100644 trunk/drivers/scsi/mvsas/mv_94xx.h create mode 100644 trunk/drivers/scsi/mvsas/mv_chips.h create mode 100644 trunk/drivers/scsi/mvsas/mv_defs.h create mode 100644 trunk/drivers/scsi/mvsas/mv_init.c create mode 100644 trunk/drivers/scsi/mvsas/mv_sas.c create mode 100644 trunk/drivers/scsi/mvsas/mv_sas.h delete mode 100755 trunk/drivers/scsi/osd/Makefile create mode 100644 trunk/drivers/serial/timbuart.c create mode 100644 trunk/drivers/serial/timbuart.h create mode 100644 trunk/drivers/xen/evtchn.c create mode 100644 trunk/drivers/xen/sys-hypervisor.c delete mode 100644 trunk/fs/btrfs/crc32c.h create mode 100644 trunk/fs/btrfs/relocation.c delete mode 100644 trunk/fs/ext2/fsync.c create mode 100644 trunk/fs/ext4/block_validity.c delete mode 100644 trunk/fs/ext4/ext4_i.h delete mode 100644 trunk/fs/ext4/ext4_sb.h delete mode 100644 trunk/fs/ext4/group.h delete mode 100644 trunk/fs/ext4/namei.h create mode 100644 trunk/fs/fuse/cuse.c rename trunk/fs/gfs2/{ops_address.c => aops.c} (98%) rename trunk/fs/gfs2/{ops_dentry.c => dentry.c} (100%) rename trunk/fs/gfs2/{ops_export.c => export.c} (100%) rename trunk/fs/gfs2/{ops_file.c => file.c} (97%) delete mode 100644 trunk/fs/gfs2/mount.c delete mode 100644 trunk/fs/gfs2/ops_address.h delete mode 100644 trunk/fs/gfs2/ops_super.c create mode 100644 trunk/fs/gfs2/trace_gfs2.h create mode 100644 trunk/fs/notify/fsnotify.c create mode 100644 trunk/fs/notify/fsnotify.h create mode 100644 trunk/fs/notify/group.c create mode 100644 trunk/fs/notify/inode_mark.c create mode 100644 trunk/fs/notify/inotify/inotify.h create mode 100644 trunk/fs/notify/inotify/inotify_fsnotify.c create mode 100644 trunk/fs/notify/notification.c delete mode 100644 trunk/fs/qnx4/fsync.c create mode 100644 trunk/fs/qnx4/qnx4.h delete mode 100644 trunk/fs/udf/fsync.c create mode 100644 trunk/fs/xfs/linux-2.6/xfs_acl.c delete mode 100644 trunk/fs/xfs/xfs_acl.c delete mode 100644 trunk/fs/xfs/xfs_qmops.c create mode 100644 trunk/include/asm-generic/atomic-long.h create mode 100644 trunk/include/asm-generic/auxvec.h create mode 100644 trunk/include/asm-generic/bitsperlong.h create mode 100644 trunk/include/asm-generic/bugs.h create mode 100644 trunk/include/asm-generic/cache.h create mode 100644 trunk/include/asm-generic/cacheflush.h create mode 100644 trunk/include/asm-generic/checksum.h create mode 100644 trunk/include/asm-generic/current.h create mode 100644 trunk/include/asm-generic/delay.h create mode 100644 trunk/include/asm-generic/dma.h create mode 100644 trunk/include/asm-generic/fb.h create mode 100644 trunk/include/asm-generic/getorder.h create mode 100644 trunk/include/asm-generic/hardirq.h create mode 100644 trunk/include/asm-generic/hw_irq.h create mode 100644 trunk/include/asm-generic/io.h create mode 100644 trunk/include/asm-generic/ioctls.h create mode 100644 trunk/include/asm-generic/ipcbuf.h create mode 100644 trunk/include/asm-generic/irq.h create mode 100644 trunk/include/asm-generic/irqflags.h create mode 100644 trunk/include/asm-generic/kmap_types.h create mode 100644 trunk/include/asm-generic/linkage.h create mode 100644 trunk/include/asm-generic/mman-common.h create mode 100644 trunk/include/asm-generic/mmu.h create mode 100644 trunk/include/asm-generic/mmu_context.h create mode 100644 trunk/include/asm-generic/module.h create mode 100644 trunk/include/asm-generic/msgbuf.h create mode 100644 trunk/include/asm-generic/mutex.h create mode 100644 trunk/include/asm-generic/param.h create mode 100644 trunk/include/asm-generic/parport.h create mode 100644 trunk/include/asm-generic/pgalloc.h create mode 100644 trunk/include/asm-generic/posix_types.h create mode 100644 trunk/include/asm-generic/scatterlist.h create mode 100644 trunk/include/asm-generic/segment.h create mode 100644 trunk/include/asm-generic/sembuf.h create mode 100644 trunk/include/asm-generic/serial.h create mode 100644 trunk/include/asm-generic/setup.h create mode 100644 trunk/include/asm-generic/shmbuf.h create mode 100644 trunk/include/asm-generic/shmparam.h create mode 100644 trunk/include/asm-generic/signal-defs.h create mode 100644 trunk/include/asm-generic/socket.h create mode 100644 trunk/include/asm-generic/sockios.h create mode 100644 trunk/include/asm-generic/spinlock.h create mode 100644 trunk/include/asm-generic/stat.h create mode 100644 trunk/include/asm-generic/string.h create mode 100644 trunk/include/asm-generic/swab.h create mode 100644 trunk/include/asm-generic/syscalls.h create mode 100644 trunk/include/asm-generic/system.h create mode 100644 trunk/include/asm-generic/termbits.h create mode 100644 trunk/include/asm-generic/termios-base.h create mode 100644 trunk/include/asm-generic/timex.h create mode 100644 trunk/include/asm-generic/tlbflush.h create mode 100644 trunk/include/asm-generic/types.h create mode 100644 trunk/include/asm-generic/uaccess-unaligned.h create mode 100644 trunk/include/asm-generic/ucontext.h create mode 100644 trunk/include/asm-generic/unaligned.h create mode 100644 trunk/include/asm-generic/unistd.h create mode 100644 trunk/include/asm-generic/user.h create mode 100644 trunk/include/asm-generic/vga.h create mode 100644 trunk/include/drm/drm_mm.h create mode 100644 trunk/include/linux/fsnotify_backend.h create mode 100644 trunk/include/linux/ftrace_event.h create mode 100644 trunk/include/linux/kmemleak.h create mode 100644 trunk/include/linux/kmemtrace.h create mode 100644 trunk/include/linux/lsm_audit.h delete mode 100644 trunk/include/linux/mg_disk.h create mode 100644 trunk/include/linux/perf_counter.h create mode 100644 trunk/include/linux/rational.h delete mode 100644 trunk/include/linux/sh_cmt.h create mode 100644 trunk/include/linux/sh_timer.h create mode 100644 trunk/include/linux/trace_seq.h delete mode 100644 trunk/include/sound/driver.h create mode 100644 trunk/include/sound/wm9081.h delete mode 100644 trunk/include/trace/block.h create mode 100644 trunk/include/trace/define_trace.h create mode 100644 trunk/include/trace/events/block.h create mode 100644 trunk/include/trace/events/irq.h create mode 100644 trunk/include/trace/events/kmem.h create mode 100644 trunk/include/trace/events/lockdep.h rename trunk/include/trace/{sched_event_types.h => events/sched.h} (91%) create mode 100644 trunk/include/trace/events/skb.h create mode 100644 trunk/include/trace/events/workqueue.h create mode 100644 trunk/include/trace/ftrace.h delete mode 100644 trunk/include/trace/irq.h delete mode 100644 trunk/include/trace/irq_event_types.h delete mode 100644 trunk/include/trace/kmemtrace.h delete mode 100644 trunk/include/trace/lockdep.h delete mode 100644 trunk/include/trace/lockdep_event_types.h delete mode 100644 trunk/include/trace/sched.h delete mode 100644 trunk/include/trace/skb.h delete mode 100644 trunk/include/trace/trace_event_types.h delete mode 100644 trunk/include/trace/trace_events.h delete mode 100644 trunk/include/trace/workqueue.h create mode 100644 trunk/include/xen/Kbuild create mode 100644 trunk/include/xen/evtchn.h create mode 100644 trunk/kernel/perf_counter.c rename trunk/kernel/power/{disk.c => hibernate.c} (96%) create mode 100644 trunk/kernel/power/hibernate_nvs.c create mode 100644 trunk/kernel/power/suspend.c create mode 100644 trunk/kernel/power/suspend_test.c delete mode 100644 trunk/kernel/trace/events.c create mode 100644 trunk/kernel/trace/ring_buffer_benchmark.c delete mode 100644 trunk/kernel/trace/trace_events_stage_1.h delete mode 100644 trunk/kernel/trace/trace_events_stage_2.h delete mode 100644 trunk/kernel/trace/trace_events_stage_3.h create mode 100644 trunk/lib/checksum.c create mode 100644 trunk/lib/rational.c create mode 100644 trunk/mm/kmemleak-test.c create mode 100644 trunk/mm/kmemleak.c create mode 100644 trunk/samples/trace_events/Makefile create mode 100644 trunk/samples/trace_events/trace-events-sample.c create mode 100644 trunk/samples/trace_events/trace-events-sample.h delete mode 100644 trunk/scripts/bin_size create mode 100644 trunk/security/lsm_audit.c create mode 100644 trunk/sound/core/seq/Kconfig create mode 100644 trunk/sound/pci/ctxfi/Makefile create mode 100644 trunk/sound/pci/ctxfi/ct20k1reg.h create mode 100644 trunk/sound/pci/ctxfi/ct20k2reg.h create mode 100644 trunk/sound/pci/ctxfi/ctamixer.c create mode 100644 trunk/sound/pci/ctxfi/ctamixer.h create mode 100644 trunk/sound/pci/ctxfi/ctatc.c create mode 100644 trunk/sound/pci/ctxfi/ctatc.h create mode 100644 trunk/sound/pci/ctxfi/ctdaio.c create mode 100644 trunk/sound/pci/ctxfi/ctdaio.h create mode 100644 trunk/sound/pci/ctxfi/cthardware.c create mode 100644 trunk/sound/pci/ctxfi/cthardware.h create mode 100644 trunk/sound/pci/ctxfi/cthw20k1.c create mode 100644 trunk/sound/pci/ctxfi/cthw20k1.h create mode 100644 trunk/sound/pci/ctxfi/cthw20k2.c create mode 100644 trunk/sound/pci/ctxfi/cthw20k2.h create mode 100644 trunk/sound/pci/ctxfi/ctimap.c create mode 100644 trunk/sound/pci/ctxfi/ctimap.h create mode 100644 trunk/sound/pci/ctxfi/ctmixer.c create mode 100644 trunk/sound/pci/ctxfi/ctmixer.h create mode 100644 trunk/sound/pci/ctxfi/ctpcm.c create mode 100644 trunk/sound/pci/ctxfi/ctpcm.h create mode 100644 trunk/sound/pci/ctxfi/ctresource.c create mode 100644 trunk/sound/pci/ctxfi/ctresource.h create mode 100644 trunk/sound/pci/ctxfi/ctsrc.c create mode 100644 trunk/sound/pci/ctxfi/ctsrc.h create mode 100644 trunk/sound/pci/ctxfi/cttimer.c create mode 100644 trunk/sound/pci/ctxfi/cttimer.h create mode 100644 trunk/sound/pci/ctxfi/ctvmem.c create mode 100644 trunk/sound/pci/ctxfi/ctvmem.h create mode 100644 trunk/sound/pci/ctxfi/xfi.c create mode 100644 trunk/sound/pci/hda/patch_ca0110.c create mode 100644 trunk/sound/pci/ice1712/maya44.c create mode 100644 trunk/sound/pci/ice1712/maya44.h create mode 100644 trunk/sound/pci/lx6464es/Makefile create mode 100644 trunk/sound/pci/lx6464es/lx6464es.c create mode 100644 trunk/sound/pci/lx6464es/lx6464es.h create mode 100644 trunk/sound/pci/lx6464es/lx_core.c create mode 100644 trunk/sound/pci/lx6464es/lx_core.h create mode 100644 trunk/sound/pci/lx6464es/lx_defs.h create mode 100644 trunk/sound/soc/atmel/snd-soc-afeb9260.c create mode 100644 trunk/sound/soc/codecs/spdif_transciever.c create mode 100644 trunk/sound/soc/codecs/spdif_transciever.h create mode 100644 trunk/sound/soc/codecs/stac9766.c create mode 100644 trunk/sound/soc/codecs/stac9766.h create mode 100644 trunk/sound/soc/codecs/wm8940.c create mode 100644 trunk/sound/soc/codecs/wm8940.h create mode 100644 trunk/sound/soc/codecs/wm8960.c create mode 100644 trunk/sound/soc/codecs/wm8960.h create mode 100644 trunk/sound/soc/codecs/wm8988.c create mode 100644 trunk/sound/soc/codecs/wm8988.h create mode 100644 trunk/sound/soc/codecs/wm9081.c create mode 100644 trunk/sound/soc/codecs/wm9081.h create mode 100644 trunk/sound/soc/fsl/efika-audio-fabric.c create mode 100644 trunk/sound/soc/fsl/mpc5200_dma.c create mode 100644 trunk/sound/soc/fsl/mpc5200_dma.h create mode 100644 trunk/sound/soc/fsl/mpc5200_psc_ac97.c create mode 100644 trunk/sound/soc/fsl/mpc5200_psc_ac97.h create mode 100644 trunk/sound/soc/fsl/mpc5200_psc_i2s.h create mode 100644 trunk/sound/soc/fsl/pcm030-audio-fabric.c create mode 100644 trunk/sound/soc/omap/omap3evm.c create mode 100644 trunk/sound/soc/pxa/imote2.c create mode 100644 trunk/sound/soc/s6000/Kconfig create mode 100644 trunk/sound/soc/s6000/Makefile create mode 100644 trunk/sound/soc/s6000/s6000-i2s.c create mode 100644 trunk/sound/soc/s6000/s6000-i2s.h create mode 100644 trunk/sound/soc/s6000/s6000-pcm.c create mode 100644 trunk/sound/soc/s6000/s6000-pcm.h create mode 100644 trunk/sound/soc/s6000/s6105-ipcam.c create mode 100644 trunk/sound/soc/txx9/Kconfig create mode 100644 trunk/sound/soc/txx9/Makefile create mode 100644 trunk/sound/soc/txx9/txx9aclc-ac97.c create mode 100644 trunk/sound/soc/txx9/txx9aclc-generic.c create mode 100644 trunk/sound/soc/txx9/txx9aclc.c create mode 100644 trunk/sound/soc/txx9/txx9aclc.h create mode 100644 trunk/tools/perf/.gitignore create mode 100644 trunk/tools/perf/Documentation/Makefile create mode 100644 trunk/tools/perf/Documentation/asciidoc.conf create mode 100644 trunk/tools/perf/Documentation/manpage-1.72.xsl create mode 100644 trunk/tools/perf/Documentation/manpage-base.xsl create mode 100644 trunk/tools/perf/Documentation/manpage-bold-literal.xsl create mode 100644 trunk/tools/perf/Documentation/manpage-normal.xsl create mode 100644 trunk/tools/perf/Documentation/manpage-suppress-sp.xsl create mode 100644 trunk/tools/perf/Documentation/perf-annotate.txt create mode 100644 trunk/tools/perf/Documentation/perf-help.txt create mode 100644 trunk/tools/perf/Documentation/perf-list.txt create mode 100644 trunk/tools/perf/Documentation/perf-record.txt create mode 100644 trunk/tools/perf/Documentation/perf-report.txt create mode 100644 trunk/tools/perf/Documentation/perf-stat.txt create mode 100644 trunk/tools/perf/Documentation/perf-top.txt create mode 100644 trunk/tools/perf/Documentation/perf.txt create mode 100644 trunk/tools/perf/Makefile create mode 100644 trunk/tools/perf/builtin-annotate.c create mode 100644 trunk/tools/perf/builtin-help.c create mode 100644 trunk/tools/perf/builtin-list.c create mode 100644 trunk/tools/perf/builtin-record.c create mode 100644 trunk/tools/perf/builtin-report.c create mode 100644 trunk/tools/perf/builtin-stat.c create mode 100644 trunk/tools/perf/builtin-top.c create mode 100644 trunk/tools/perf/builtin.h create mode 100644 trunk/tools/perf/command-list.txt create mode 100644 trunk/tools/perf/design.txt create mode 100644 trunk/tools/perf/perf.c create mode 100644 trunk/tools/perf/perf.h create mode 100755 trunk/tools/perf/util/PERF-VERSION-GEN create mode 100644 trunk/tools/perf/util/abspath.c create mode 100644 trunk/tools/perf/util/alias.c create mode 100644 trunk/tools/perf/util/cache.h create mode 100644 trunk/tools/perf/util/color.c create mode 100644 trunk/tools/perf/util/color.h create mode 100644 trunk/tools/perf/util/config.c create mode 100644 trunk/tools/perf/util/ctype.c create mode 100644 trunk/tools/perf/util/environment.c create mode 100644 trunk/tools/perf/util/exec_cmd.c create mode 100644 trunk/tools/perf/util/exec_cmd.h create mode 100755 trunk/tools/perf/util/generate-cmdlist.sh create mode 100644 trunk/tools/perf/util/help.c create mode 100644 trunk/tools/perf/util/help.h create mode 100644 trunk/tools/perf/util/levenshtein.c create mode 100644 trunk/tools/perf/util/levenshtein.h create mode 100644 trunk/tools/perf/util/list.h create mode 100644 trunk/tools/perf/util/pager.c create mode 100644 trunk/tools/perf/util/parse-events.c create mode 100644 trunk/tools/perf/util/parse-events.h create mode 100644 trunk/tools/perf/util/parse-options.c create mode 100644 trunk/tools/perf/util/parse-options.h create mode 100644 trunk/tools/perf/util/path.c create mode 100644 trunk/tools/perf/util/quote.c create mode 100644 trunk/tools/perf/util/quote.h create mode 100644 trunk/tools/perf/util/rbtree.c create mode 100644 trunk/tools/perf/util/rbtree.h create mode 100644 trunk/tools/perf/util/run-command.c create mode 100644 trunk/tools/perf/util/run-command.h create mode 100644 trunk/tools/perf/util/sigchain.c create mode 100644 trunk/tools/perf/util/sigchain.h create mode 100644 trunk/tools/perf/util/strbuf.c create mode 100644 trunk/tools/perf/util/strbuf.h create mode 100644 trunk/tools/perf/util/string.c create mode 100644 trunk/tools/perf/util/string.h create mode 100644 trunk/tools/perf/util/symbol.c create mode 100644 trunk/tools/perf/util/symbol.h create mode 100644 trunk/tools/perf/util/usage.c create mode 100644 trunk/tools/perf/util/util.h create mode 100644 trunk/tools/perf/util/wrapper.c diff --git a/[refs] b/[refs] index 1d7d82275220..9d65ae1a1b60 100644 --- a/[refs] +++ b/[refs] @@ -1,2 +1,2 @@ --- -refs/heads/master: ce53895a5d24e0ee19fb92f56c17323fb4c9ab27 +refs/heads/master: 2cf4d4514d5b43c1f3b64bd0ec8b9853bde8f1dc diff --git a/trunk/Documentation/ABI/testing/sysfs-block b/trunk/Documentation/ABI/testing/sysfs-block index 44f52a4f5903..cbbd3e069945 100644 --- a/trunk/Documentation/ABI/testing/sysfs-block +++ b/trunk/Documentation/ABI/testing/sysfs-block @@ -60,3 +60,62 @@ Description: Indicates whether the block layer should automatically generate checksums for write requests bound for devices that support receiving integrity metadata. + +What: /sys/block//alignment_offset +Date: April 2009 +Contact: Martin K. Petersen +Description: + Storage devices may report a physical block size that is + bigger than the logical block size (for instance a drive + with 4KB physical sectors exposing 512-byte logical + blocks to the operating system). This parameter + indicates how many bytes the beginning of the device is + offset from the disk's natural alignment. + +What: /sys/block///alignment_offset +Date: April 2009 +Contact: Martin K. Petersen +Description: + Storage devices may report a physical block size that is + bigger than the logical block size (for instance a drive + with 4KB physical sectors exposing 512-byte logical + blocks to the operating system). This parameter + indicates how many bytes the beginning of the partition + is offset from the disk's natural alignment. + +What: /sys/block//queue/logical_block_size +Date: May 2009 +Contact: Martin K. Petersen +Description: + This is the smallest unit the storage device can + address. It is typically 512 bytes. + +What: /sys/block//queue/physical_block_size +Date: May 2009 +Contact: Martin K. Petersen +Description: + This is the smallest unit the storage device can write + without resorting to read-modify-write operation. It is + usually the same as the logical block size but may be + bigger. One example is SATA drives with 4KB sectors + that expose a 512-byte logical block size to the + operating system. + +What: /sys/block//queue/minimum_io_size +Date: April 2009 +Contact: Martin K. Petersen +Description: + Storage devices may report a preferred minimum I/O size, + which is the smallest request the device can perform + without incurring a read-modify-write penalty. For disk + drives this is often the physical block size. For RAID + arrays it is often the stripe chunk size. + +What: /sys/block//queue/optimal_io_size +Date: April 2009 +Contact: Martin K. Petersen +Description: + Storage devices may report an optimal I/O size, which is + the device's preferred unit of receiving I/O. This is + rarely reported for disk drives. For RAID devices it is + usually the stripe width or the internal block size. diff --git a/trunk/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/trunk/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss new file mode 100644 index 000000000000..0a92a7c93a62 --- /dev/null +++ b/trunk/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss @@ -0,0 +1,33 @@ +Where: /sys/bus/pci/devices//ccissX/cXdY/model +Date: March 2009 +Kernel Version: 2.6.30 +Contact: iss_storagedev@hp.com +Description: Displays the SCSI INQUIRY page 0 model for logical drive + Y of controller X. + +Where: /sys/bus/pci/devices//ccissX/cXdY/rev +Date: March 2009 +Kernel Version: 2.6.30 +Contact: iss_storagedev@hp.com +Description: Displays the SCSI INQUIRY page 0 revision for logical + drive Y of controller X. + +Where: /sys/bus/pci/devices//ccissX/cXdY/unique_id +Date: March 2009 +Kernel Version: 2.6.30 +Contact: iss_storagedev@hp.com +Description: Displays the SCSI INQUIRY page 83 serial number for logical + drive Y of controller X. + +Where: /sys/bus/pci/devices//ccissX/cXdY/vendor +Date: March 2009 +Kernel Version: 2.6.30 +Contact: iss_storagedev@hp.com +Description: Displays the SCSI INQUIRY page 0 vendor for logical drive + Y of controller X. + +Where: /sys/bus/pci/devices//ccissX/cXdY/block:cciss!cXdY +Date: March 2009 +Kernel Version: 2.6.30 +Contact: iss_storagedev@hp.com +Description: A symbolic link to /sys/block/cciss!cXdY diff --git a/trunk/Documentation/ABI/testing/sysfs-devices-cache_disable b/trunk/Documentation/ABI/testing/sysfs-devices-cache_disable new file mode 100644 index 000000000000..175bb4f70512 --- /dev/null +++ b/trunk/Documentation/ABI/testing/sysfs-devices-cache_disable @@ -0,0 +1,18 @@ +What: /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X +Date: August 2008 +KernelVersion: 2.6.27 +Contact: mark.langsdorf@amd.com +Description: These files exist in every cpu's cache index directories. + There are currently 2 cache_disable_# files in each + directory. Reading from these files on a supported + processor will return that cache disable index value + for that processor and node. Writing to one of these + files will cause the specificed cache index to be disabled. + + Currently, only AMD Family 10h Processors support cache index + disable, and only for their L3 caches. See the BIOS and + Kernel Developer's Guide at + http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf + for formatting information and other details on the + cache index disable. +Users: joachim.deguara@amd.com diff --git a/trunk/Documentation/Changes b/trunk/Documentation/Changes index b95082be4d5e..d21b3b5aa543 100644 --- a/trunk/Documentation/Changes +++ b/trunk/Documentation/Changes @@ -48,6 +48,7 @@ o procps 3.2.0 # ps --version o oprofile 0.9 # oprofiled --version o udev 081 # udevinfo -V o grub 0.93 # grub --version +o mcelog 0.6 Kernel compilation ================== @@ -276,6 +277,16 @@ before running exportfs or mountd. It is recommended that all NFS services be protected from the internet-at-large by a firewall where that is possible. +mcelog +------ + +In Linux 2.6.31+ the i386 kernel needs to run the mcelog utility +as a regular cronjob similar to the x86-64 kernel to process and log +machine check events when CONFIG_X86_NEW_MCE is enabled. Machine check +events are errors reported by the CPU. Processing them is strongly encouraged. +All x86-64 kernels since 2.6.4 require the mcelog utility to +process machine checks. + Getting updated software ======================== @@ -365,6 +376,10 @@ FUSE ---- o +mcelog +------ +o + Networking ********** diff --git a/trunk/Documentation/DMA-API.txt b/trunk/Documentation/DMA-API.txt index d9aa43d78bcc..25fb8bcf32a2 100644 --- a/trunk/Documentation/DMA-API.txt +++ b/trunk/Documentation/DMA-API.txt @@ -704,12 +704,24 @@ this directory the following files can currently be found: The current number of free dma_debug_entries in the allocator. + dma-api/driver-filter + You can write a name of a driver into this file + to limit the debug output to requests from that + particular driver. Write an empty string to + that file to disable the filter and see + all errors again. + If you have this code compiled into your kernel it will be enabled by default. If you want to boot without the bookkeeping anyway you can provide 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging. Notice that you can not enable it again at runtime. You have to reboot to do so. +If you want to see debug messages only for a special device driver you can +specify the dma_debug_driver= parameter. This will enable the +driver filter at boot time. The debug code will only print errors for that +driver afterwards. This filter can be disabled or changed later using debugfs. + When the code disables itself at runtime this is most likely because it ran out of dma_debug_entries. These entries are preallocated at boot. The number of preallocated entries is defined per architecture. If it is too low for you diff --git a/trunk/Documentation/DocBook/Makefile b/trunk/Documentation/DocBook/Makefile index b1eb661e6302..9632444f6c62 100644 --- a/trunk/Documentation/DocBook/Makefile +++ b/trunk/Documentation/DocBook/Makefile @@ -13,7 +13,8 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \ gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \ genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \ mac80211.xml debugobjects.xml sh.xml regulator.xml \ - alsa-driver-api.xml writing-an-alsa-driver.xml + alsa-driver-api.xml writing-an-alsa-driver.xml \ + tracepoint.xml ### # The build process is as follows (targets): diff --git a/trunk/Documentation/DocBook/tracepoint.tmpl b/trunk/Documentation/DocBook/tracepoint.tmpl new file mode 100644 index 000000000000..b0756d0fd579 --- /dev/null +++ b/trunk/Documentation/DocBook/tracepoint.tmpl @@ -0,0 +1,89 @@ + + + + + + The Linux Kernel Tracepoint API + + + + Jason + Baron + +
+ jbaron@redhat.com +
+ + + + + + + This documentation 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. + + + + This program 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 General Public License for more details. + + + + You should have received a copy of the GNU General Public + License along with this program; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, + MA 02111-1307 USA + + + + For more details see the file COPYING in the source + distribution of Linux. + + + + + + + Introduction + + Tracepoints are static probe points that are located in strategic points + throughout the kernel. 'Probes' register/unregister with tracepoints + via a callback mechanism. The 'probes' are strictly typed functions that + are passed a unique set of parameters defined by each tracepoint. + + + + From this simple callback mechanism, 'probes' can be used to profile, debug, + and understand kernel behavior. There are a number of tools that provide a + framework for using 'probes'. These tools include Systemtap, ftrace, and + LTTng. + + + + Tracepoints are defined in a number of header files via various macros. Thus, + the purpose of this document is to provide a clear accounting of the available + tracepoints. The intention is to understand not only what tracepoints are + available but also to understand where future tracepoints might be added. + + + + The API presented has functions of the form: + trace_tracepointname(function parameters). These are the + tracepoints callbacks that are found throughout the code. Registering and + unregistering probes with these callback sites is covered in the + Documentation/trace/* directory. + + + + + IRQ +!Iinclude/trace/events/irq.h + + + diff --git a/trunk/Documentation/RCU/trace.txt b/trunk/Documentation/RCU/trace.txt index 068848240a8b..02cced183b2d 100644 --- a/trunk/Documentation/RCU/trace.txt +++ b/trunk/Documentation/RCU/trace.txt @@ -192,23 +192,24 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy). The output of "cat rcu/rcudata" looks as follows: rcu: - 0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10 - 1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10 - 2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10 - 3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10 - 4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10 - 5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10 - 6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10 - 7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10 +rcu: + 0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10 + 1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10 + 2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10 + 3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10 + 4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10 + 5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10 + 6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10 + 7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10 rcu_bh: - 0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10 - 1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10 - 2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10 - 3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10 - 4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10 - 5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10 - 6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10 - 7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10 + 0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10 + 1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10 + 2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 + 3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10 + 4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 + 5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 + 6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 + 7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 The first section lists the rcu_data structures for rcu, the second for rcu_bh. Each section has one line per CPU, or eight for this 8-CPU system. @@ -253,12 +254,6 @@ o "pqc" indicates which grace period the last-observed quiescent o "qp" indicates that RCU still expects a quiescent state from this CPU. -o "rpfq" is the number of rcu_pending() calls on this CPU required - to induce this CPU to invoke force_quiescent_state(). - -o "rp" is low-order four hex digits of the count of how many times - rcu_pending() has been invoked on this CPU. - o "dt" is the current value of the dyntick counter that is incremented when entering or leaving dynticks idle state, either by the scheduler or by irq. The number after the "/" is the interrupt @@ -305,6 +300,9 @@ o "b" is the batch limit for this CPU. If more than this number of RCU callbacks is ready to invoke, then the remainder will be deferred. +There is also an rcu/rcudata.csv file with the same information in +comma-separated-variable spreadsheet format. + The output of "cat rcu/rcugp" looks as follows: @@ -411,3 +409,63 @@ o Each element of the form "1/1 0:127 ^0" represents one struct For example, the first entry at the lowest level shows "^0", indicating that it corresponds to bit zero in the first entry at the middle level. + + +The output of "cat rcu/rcu_pending" looks as follows: + +rcu: + 0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741 + 1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792 + 2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629 + 3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723 + 4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110 + 5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456 + 6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834 + 7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888 +rcu_bh: + 0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314 + 1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180 + 2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936 + 3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863 + 4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671 + 5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235 + 6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921 + 7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542 + +As always, this is once again split into "rcu" and "rcu_bh" portions. +The fields are as follows: + +o "np" is the number of times that __rcu_pending() has been invoked + for the corresponding flavor of RCU. + +o "qsp" is the number of times that the RCU was waiting for a + quiescent state from this CPU. + +o "cbr" is the number of times that this CPU had RCU callbacks + that had passed through a grace period, and were thus ready + to be invoked. + +o "cng" is the number of times that this CPU needed another + grace period while RCU was idle. + +o "gpc" is the number of times that an old grace period had + completed, but this CPU was not yet aware of it. + +o "gps" is the number of times that a new grace period had started, + but this CPU was not yet aware of it. + +o "nf" is the number of times that this CPU suspected that the + current grace period had run for too long, and thus needed to + be forced. + + Please note that "forcing" consists of sending resched IPIs + to holdout CPUs. If that CPU really still is in an old RCU + read-side critical section, then we really do have to wait for it. + The assumption behing "forcing" is that the CPU is not still in + an old RCU read-side critical section, but has not yet responded + for some other reason. + +o "nn" is the number of times that this CPU needed nothing. Alert + readers will note that the rcu "nn" number for a given CPU very + closely matches the rcu_bh "np" number for that same CPU. This + is due to short-circuit evaluation in rcu_pending(). diff --git a/trunk/Documentation/Smack.txt b/trunk/Documentation/Smack.txt index 629c92e99783..34614b4c708e 100644 --- a/trunk/Documentation/Smack.txt +++ b/trunk/Documentation/Smack.txt @@ -184,8 +184,9 @@ length. Single character labels using special characters, that being anything other than a letter or digit, are reserved for use by the Smack development team. Smack labels are unstructured, case sensitive, and the only operation ever performed on them is comparison for equality. Smack labels cannot -contain unprintable characters or the "/" (slash) character. Smack labels -cannot begin with a '-', which is reserved for special options. +contain unprintable characters, the "/" (slash), the "\" (backslash), the "'" +(quote) and '"' (double-quote) characters. +Smack labels cannot begin with a '-', which is reserved for special options. There are some predefined labels: @@ -523,3 +524,18 @@ Smack supports some mount options: These mount options apply to all file system types. +Smack auditing + +If you want Smack auditing of security events, you need to set CONFIG_AUDIT +in your kernel configuration. +By default, all denied events will be audited. You can change this behavior by +writing a single character to the /smack/logging file : +0 : no logging +1 : log denied (default) +2 : log accepted +3 : log denied & accepted + +Events are logged as 'key=value' pairs, for each event you at least will get +the subjet, the object, the rights requested, the action, the kernel function +that triggered the event, plus other pairs depending on the type of event +audited. diff --git a/trunk/Documentation/SubmittingPatches b/trunk/Documentation/SubmittingPatches index f309d3c6221c..6c456835c1fd 100644 --- a/trunk/Documentation/SubmittingPatches +++ b/trunk/Documentation/SubmittingPatches @@ -91,6 +91,10 @@ Be as specific as possible. The WORST descriptions possible include things like "update driver X", "bug fix for driver X", or "this patch includes updates for subsystem X. Please apply." +The maintainer will thank you if you write your patch description in a +form which can be easily pulled into Linux's source code management +system, git, as a "commit log". See #15, below. + If your description starts to get long, that's a sign that you probably need to split up your patch. See #3, next. @@ -405,7 +409,14 @@ person it names. This tag documents that potentially interested parties have been included in the discussion -14) Using Tested-by: and Reviewed-by: +14) Using Reported-by:, Tested-by: and Reviewed-by: + +If this patch fixes a problem reported by somebody else, consider adding a +Reported-by: tag to credit the reporter for their contribution. Please +note that this tag should not be added without the reporter's permission, +especially if the problem was not reported in a public forum. That said, +if we diligently credit our bug reporters, they will, hopefully, be +inspired to help us again in the future. A Tested-by: tag indicates that the patch has been successfully tested (in some environment) by the person named. This tag informs maintainers that @@ -444,7 +455,7 @@ offer a Reviewed-by tag for a patch. This tag serves to give credit to reviewers and to inform maintainers of the degree of review which has been done on the patch. Reviewed-by: tags, when supplied by reviewers known to understand the subject area and to perform thorough reviews, will normally -increase the liklihood of your patch getting into the kernel. +increase the likelihood of your patch getting into the kernel. 15) The canonical patch format @@ -485,12 +496,33 @@ phrase" should not be a filename. Do not use the same "summary phrase" for every patch in a whole patch series (where a "patch series" is an ordered sequence of multiple, related patches). -Bear in mind that the "summary phrase" of your email becomes -a globally-unique identifier for that patch. It propagates -all the way into the git changelog. The "summary phrase" may -later be used in developer discussions which refer to the patch. -People will want to google for the "summary phrase" to read -discussion regarding that patch. +Bear in mind that the "summary phrase" of your email becomes a +globally-unique identifier for that patch. It propagates all the way +into the git changelog. The "summary phrase" may later be used in +developer discussions which refer to the patch. People will want to +google for the "summary phrase" to read discussion regarding that +patch. It will also be the only thing that people may quickly see +when, two or three months later, they are going through perhaps +thousands of patches using tools such as "gitk" or "git log +--oneline". + +For these reasons, the "summary" must be no more than 70-75 +characters, and it must describe both what the patch changes, as well +as why the patch might be necessary. It is challenging to be both +succinct and descriptive, but that is what a well-written summary +should do. + +The "summary phrase" may be prefixed by tags enclosed in square +brackets: "Subject: [PATCH tag] ". The tags are not +considered part of the summary phrase, but describe how the patch +should be treated. Common tags might include a version descriptor if +the multiple versions of the patch have been sent out in response to +comments (i.e., "v1, v2, v3"), or "RFC" to indicate a request for +comments. If there are four patches in a patch series the individual +patches may be numbered like this: 1/4, 2/4, 3/4, 4/4. This assures +that developers understand the order in which the patches should be +applied and that they have reviewed or applied all of the patches in +the patch series. A couple of example Subjects: @@ -510,19 +542,31 @@ the patch author in the changelog. The explanation body will be committed to the permanent source changelog, so should make sense to a competent reader who has long since forgotten the immediate details of the discussion that might -have led to this patch. +have led to this patch. Including symptoms of the failure which the +patch addresses (kernel log messages, oops messages, etc.) is +especially useful for people who might be searching the commit logs +looking for the applicable patch. If a patch fixes a compile failure, +it may not be necessary to include _all_ of the compile failures; just +enough that it is likely that someone searching for the patch can find +it. As in the "summary phrase", it is important to be both succinct as +well as descriptive. The "---" marker line serves the essential purpose of marking for patch handling tools where the changelog message ends. One good use for the additional comments after the "---" marker is for -a diffstat, to show what files have changed, and the number of inserted -and deleted lines per file. A diffstat is especially useful on bigger -patches. Other comments relevant only to the moment or the maintainer, -not suitable for the permanent changelog, should also go here. -Use diffstat options "-p 1 -w 70" so that filenames are listed from the -top of the kernel source tree and don't use too much horizontal space -(easily fit in 80 columns, maybe with some indentation). +a diffstat, to show what files have changed, and the number of +inserted and deleted lines per file. A diffstat is especially useful +on bigger patches. Other comments relevant only to the moment or the +maintainer, not suitable for the permanent changelog, should also go +here. A good example of such comments might be "patch changelogs" +which describe what has changed between the v1 and v2 version of the +patch. + +If you are going to include a diffstat after the "---" marker, please +use diffstat options "-p 1 -w 70" so that filenames are listed from +the top of the kernel source tree and don't use too much horizontal +space (easily fit in 80 columns, maybe with some indentation). See more details on the proper patch format in the following references. diff --git a/trunk/Documentation/block/biodoc.txt b/trunk/Documentation/block/biodoc.txt index 6fab97ea7e6b..8d2158a1c6aa 100644 --- a/trunk/Documentation/block/biodoc.txt +++ b/trunk/Documentation/block/biodoc.txt @@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address do not have a corresponding kernel virtual address space mapping) and low-memory pages. -Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion +Note: Please refer to Documentation/DMA-mapping.txt for a discussion on PCI high mem DMA aspects and mapping of scatter gather lists, and support for 64 bit PCI. diff --git a/trunk/Documentation/development-process/5.Posting b/trunk/Documentation/development-process/5.Posting index dd48132a74dd..f622c1e9f0f9 100644 --- a/trunk/Documentation/development-process/5.Posting +++ b/trunk/Documentation/development-process/5.Posting @@ -119,7 +119,7 @@ which takes quite a bit of time and thought after the "real work" has been done. When done properly, though, it is time well spent. -5.4: PATCH FORMATTING +5.4: PATCH FORMATTING AND CHANGELOGS So now you have a perfect series of patches for posting, but the work is not done quite yet. Each patch needs to be formatted into a message which @@ -146,8 +146,33 @@ that end, each patch will be composed of the following: - One or more tag lines, with, at a minimum, one Signed-off-by: line from the author of the patch. Tags will be described in more detail below. -The above three items should, normally, be the text used when committing -the change to a revision control system. They are followed by: +The items above, together, form the changelog for the patch. Writing good +changelogs is a crucial but often-neglected art; it's worth spending +another moment discussing this issue. When writing a changelog, you should +bear in mind that a number of different people will be reading your words. +These include subsystem maintainers and reviewers who need to decide +whether the patch should be included, distributors and other maintainers +trying to decide whether a patch should be backported to other kernels, bug +hunters wondering whether the patch is responsible for a problem they are +chasing, users who want to know how the kernel has changed, and more. A +good changelog conveys the needed information to all of these people in the +most direct and concise way possible. + +To that end, the summary line should describe the effects of and motivation +for the change as well as possible given the one-line constraint. The +detailed description can then amplify on those topics and provide any +needed additional information. If the patch fixes a bug, cite the commit +which introduced the bug if possible. If a problem is associated with +specific log or compiler output, include that output to help others +searching for a solution to the same problem. If the change is meant to +support other changes coming in later patch, say so. If internal APIs are +changed, detail those changes and how other developers should respond. In +general, the more you can put yourself into the shoes of everybody who will +be reading your changelog, the better that changelog (and the kernel as a +whole) will be. + +Needless to say, the changelog should be the text used when committing the +change to a revision control system. It will be followed by: - The patch itself, in the unified ("-u") patch format. Using the "-p" option to diff will associate function names with changes, making the diff --git a/trunk/Documentation/feature-removal-schedule.txt b/trunk/Documentation/feature-removal-schedule.txt index de491a3e2313..ec9ef5d0d7b3 100644 --- a/trunk/Documentation/feature-removal-schedule.txt +++ b/trunk/Documentation/feature-removal-schedule.txt @@ -437,3 +437,13 @@ Why: Superseded by tdfxfb. I2C/DDC support used to live in a separate driver but this caused driver conflicts. Who: Jean Delvare Krzysztof Helt + +---------------------------- + +What: CONFIG_X86_OLD_MCE +When: 2.6.32 +Why: Remove the old legacy 32bit machine check code. This has been + superseded by the newer machine check code from the 64bit port, + but the old version has been kept around for easier testing. Note this + doesn't impact the old P5 and WinChip machine check handlers. +Who: Andi Kleen diff --git a/trunk/Documentation/filesystems/debugfs.txt b/trunk/Documentation/filesystems/debugfs.txt new file mode 100644 index 000000000000..ed52af60c2d8 --- /dev/null +++ b/trunk/Documentation/filesystems/debugfs.txt @@ -0,0 +1,158 @@ +Copyright 2009 Jonathan Corbet + +Debugfs exists as a simple way for kernel developers to make information +available to user space. Unlike /proc, which is only meant for information +about a process, or sysfs, which has strict one-value-per-file rules, +debugfs has no rules at all. Developers can put any information they want +there. The debugfs filesystem is also intended to not serve as a stable +ABI to user space; in theory, there are no stability constraints placed on +files exported there. The real world is not always so simple, though [1]; +even debugfs interfaces are best designed with the idea that they will need +to be maintained forever. + +Debugfs is typically mounted with a command like: + + mount -t debugfs none /sys/kernel/debug + +(Or an equivalent /etc/fstab line). + +Note that the debugfs API is exported GPL-only to modules. + +Code using debugfs should include . Then, the first order +of business will be to create at least one directory to hold a set of +debugfs files: + + struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); + +This call, if successful, will make a directory called name underneath the +indicated parent directory. If parent is NULL, the directory will be +created in the debugfs root. On success, the return value is a struct +dentry pointer which can be used to create files in the directory (and to +clean it up at the end). A NULL return value indicates that something went +wrong. If ERR_PTR(-ENODEV) is returned, that is an indication that the +kernel has been built without debugfs support and none of the functions +described below will work. + +The most general way to create a file within a debugfs directory is with: + + struct dentry *debugfs_create_file(const char *name, mode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops); + +Here, name is the name of the file to create, mode describes the access +permissions the file should have, parent indicates the directory which +should hold the file, data will be stored in the i_private field of the +resulting inode structure, and fops is a set of file operations which +implement the file's behavior. At a minimum, the read() and/or write() +operations should be provided; others can be included as needed. Again, +the return value will be a dentry pointer to the created file, NULL for +error, or ERR_PTR(-ENODEV) if debugfs support is missing. + +In a number of cases, the creation of a set of file operations is not +actually necessary; the debugfs code provides a number of helper functions +for simple situations. Files containing a single integer value can be +created with any of: + + struct dentry *debugfs_create_u8(const char *name, mode_t mode, + struct dentry *parent, u8 *value); + struct dentry *debugfs_create_u16(const char *name, mode_t mode, + struct dentry *parent, u16 *value); + struct dentry *debugfs_create_u32(const char *name, mode_t mode, + struct dentry *parent, u32 *value); + struct dentry *debugfs_create_u64(const char *name, mode_t mode, + struct dentry *parent, u64 *value); + +These files support both reading and writing the given value; if a specific +file should not be written to, simply set the mode bits accordingly. The +values in these files are in decimal; if hexadecimal is more appropriate, +the following functions can be used instead: + + struct dentry *debugfs_create_x8(const char *name, mode_t mode, + struct dentry *parent, u8 *value); + struct dentry *debugfs_create_x16(const char *name, mode_t mode, + struct dentry *parent, u16 *value); + struct dentry *debugfs_create_x32(const char *name, mode_t mode, + struct dentry *parent, u32 *value); + +Note that there is no debugfs_create_x64(). + +These functions are useful as long as the developer knows the size of the +value to be exported. Some types can have different widths on different +architectures, though, complicating the situation somewhat. There is a +function meant to help out in one special case: + + struct dentry *debugfs_create_size_t(const char *name, mode_t mode, + struct dentry *parent, + size_t *value); + +As might be expected, this function will create a debugfs file to represent +a variable of type size_t. + +Boolean values can be placed in debugfs with: + + struct dentry *debugfs_create_bool(const char *name, mode_t mode, + struct dentry *parent, u32 *value); + +A read on the resulting file will yield either Y (for non-zero values) or +N, followed by a newline. If written to, it will accept either upper- or +lower-case values, or 1 or 0. Any other input will be silently ignored. + +Finally, a block of arbitrary binary data can be exported with: + + struct debugfs_blob_wrapper { + void *data; + unsigned long size; + }; + + struct dentry *debugfs_create_blob(const char *name, mode_t mode, + struct dentry *parent, + struct debugfs_blob_wrapper *blob); + +A read of this file will return the data pointed to by the +debugfs_blob_wrapper structure. Some drivers use "blobs" as a simple way +to return several lines of (static) formatted text output. This function +can be used to export binary information, but there does not appear to be +any code which does so in the mainline. Note that all files created with +debugfs_create_blob() are read-only. + +There are a couple of other directory-oriented helper functions: + + struct dentry *debugfs_rename(struct dentry *old_dir, + struct dentry *old_dentry, + struct dentry *new_dir, + const char *new_name); + + struct dentry *debugfs_create_symlink(const char *name, + struct dentry *parent, + const char *target); + +A call to debugfs_rename() will give a new name to an existing debugfs +file, possibly in a different directory. The new_name must not exist prior +to the call; the return value is old_dentry with updated information. +Symbolic links can be created with debugfs_create_symlink(). + +There is one important thing that all debugfs users must take into account: +there is no automatic cleanup of any directories created in debugfs. If a +module is unloaded without explicitly removing debugfs entries, the result +will be a lot of stale pointers and no end of highly antisocial behavior. +So all debugfs users - at least those which can be built as modules - must +be prepared to remove all files and directories they create there. A file +can be removed with: + + void debugfs_remove(struct dentry *dentry); + +The dentry value can be NULL, in which case nothing will be removed. + +Once upon a time, debugfs users were required to remember the dentry +pointer for every debugfs file they created so that all files could be +cleaned up. We live in more civilized times now, though, and debugfs users +can call: + + void debugfs_remove_recursive(struct dentry *dentry); + +If this function is passed a pointer for the dentry corresponding to the +top-level directory, the entire hierarchy below that directory will be +removed. + +Notes: + [1] http://lwn.net/Articles/309298/ diff --git a/trunk/Documentation/filesystems/gfs2-glocks.txt b/trunk/Documentation/filesystems/gfs2-glocks.txt index 4dae9a3840bf..0494f78d87e4 100644 --- a/trunk/Documentation/filesystems/gfs2-glocks.txt +++ b/trunk/Documentation/filesystems/gfs2-glocks.txt @@ -60,7 +60,7 @@ go_lock | Called for the first local holder of a lock go_unlock | Called on the final local unlock of a lock go_dump | Called to print content of object for debugfs file, or on | error to dump glock to the log. -go_type; | The type of the glock, LM_TYPE_..... +go_type | The type of the glock, LM_TYPE_..... go_min_hold_time | The minimum hold time The minimum hold time for each lock is the time after a remote lock diff --git a/trunk/Documentation/filesystems/gfs2.txt b/trunk/Documentation/filesystems/gfs2.txt index 593004b6bbab..5e3ab8f3beff 100644 --- a/trunk/Documentation/filesystems/gfs2.txt +++ b/trunk/Documentation/filesystems/gfs2.txt @@ -11,18 +11,15 @@ their I/O so file system consistency is maintained. One of the nifty features of GFS is perfect consistency -- changes made to the file system on one machine show up immediately on all other machines in the cluster. -GFS uses interchangable inter-node locking mechanisms. Different lock -modules can plug into GFS and each file system selects the appropriate -lock module at mount time. Lock modules include: +GFS uses interchangable inter-node locking mechanisms, the currently +supported mechanisms are: lock_nolock -- allows gfs to be used as a local file system lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking The dlm is found at linux/fs/dlm/ -In addition to interfacing with an external locking manager, a gfs lock -module is responsible for interacting with external cluster management -systems. Lock_dlm depends on user space cluster management systems found +Lock_dlm depends on user space cluster management systems found at the URL above. To use gfs as a local file system, no external clustering systems are @@ -31,13 +28,19 @@ needed, simply: $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device $ mount -t gfs2 /dev/block_device /dir -GFS2 is not on-disk compatible with previous versions of GFS. +If you are using Fedora, you need to install the gfs2-utils package +and, for lock_dlm, you will also need to install the cman package +and write a cluster.conf as per the documentation. + +GFS2 is not on-disk compatible with previous versions of GFS, but it +is pretty close. The following man pages can be found at the URL above: - gfs2_fsck to repair a filesystem + fsck.gfs2 to repair a filesystem gfs2_grow to expand a filesystem online gfs2_jadd to add journals to a filesystem online gfs2_tool to manipulate, examine and tune a filesystem gfs2_quota to examine and change quota values in a filesystem + gfs2_convert to convert a gfs filesystem to gfs2 in-place mount.gfs2 to help mount(8) mount a filesystem mkfs.gfs2 to make a filesystem diff --git a/trunk/Documentation/futex-requeue-pi.txt b/trunk/Documentation/futex-requeue-pi.txt new file mode 100644 index 000000000000..9dc1ff4fd536 --- /dev/null +++ b/trunk/Documentation/futex-requeue-pi.txt @@ -0,0 +1,131 @@ +Futex Requeue PI +---------------- + +Requeueing of tasks from a non-PI futex to a PI futex requires +special handling in order to ensure the underlying rt_mutex is never +left without an owner if it has waiters; doing so would break the PI +boosting logic [see rt-mutex-desgin.txt] For the purposes of +brevity, this action will be referred to as "requeue_pi" throughout +this document. Priority inheritance is abbreviated throughout as +"PI". + +Motivation +---------- + +Without requeue_pi, the glibc implementation of +pthread_cond_broadcast() must resort to waking all the tasks waiting +on a pthread_condvar and letting them try to sort out which task +gets to run first in classic thundering-herd formation. An ideal +implementation would wake the highest-priority waiter, and leave the +rest to the natural wakeup inherent in unlocking the mutex +associated with the condvar. + +Consider the simplified glibc calls: + +/* caller must lock mutex */ +pthread_cond_wait(cond, mutex) +{ + lock(cond->__data.__lock); + unlock(mutex); + do { + unlock(cond->__data.__lock); + futex_wait(cond->__data.__futex); + lock(cond->__data.__lock); + } while(...) + unlock(cond->__data.__lock); + lock(mutex); +} + +pthread_cond_broadcast(cond) +{ + lock(cond->__data.__lock); + unlock(cond->__data.__lock); + futex_requeue(cond->data.__futex, cond->mutex); +} + +Once pthread_cond_broadcast() requeues the tasks, the cond->mutex +has waiters. Note that pthread_cond_wait() attempts to lock the +mutex only after it has returned to user space. This will leave the +underlying rt_mutex with waiters, and no owner, breaking the +previously mentioned PI-boosting algorithms. + +In order to support PI-aware pthread_condvar's, the kernel needs to +be able to requeue tasks to PI futexes. This support implies that +upon a successful futex_wait system call, the caller would return to +user space already holding the PI futex. The glibc implementation +would be modified as follows: + + +/* caller must lock mutex */ +pthread_cond_wait_pi(cond, mutex) +{ + lock(cond->__data.__lock); + unlock(mutex); + do { + unlock(cond->__data.__lock); + futex_wait_requeue_pi(cond->__data.__futex); + lock(cond->__data.__lock); + } while(...) + unlock(cond->__data.__lock); + /* the kernel acquired the the mutex for us */ +} + +pthread_cond_broadcast_pi(cond) +{ + lock(cond->__data.__lock); + unlock(cond->__data.__lock); + futex_requeue_pi(cond->data.__futex, cond->mutex); +} + +The actual glibc implementation will likely test for PI and make the +necessary changes inside the existing calls rather than creating new +calls for the PI cases. Similar changes are needed for +pthread_cond_timedwait() and pthread_cond_signal(). + +Implementation +-------------- + +In order to ensure the rt_mutex has an owner if it has waiters, it +is necessary for both the requeue code, as well as the waiting code, +to be able to acquire the rt_mutex before returning to user space. +The requeue code cannot simply wake the waiter and leave it to +acquire the rt_mutex as it would open a race window between the +requeue call returning to user space and the waiter waking and +starting to run. This is especially true in the uncontended case. + +The solution involves two new rt_mutex helper routines, +rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which +allow the requeue code to acquire an uncontended rt_mutex on behalf +of the waiter and to enqueue the waiter on a contended rt_mutex. +Two new system calls provide the kernel<->user interface to +requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI. + +FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait() +and pthread_cond_timedwait()) to block on the initial futex and wait +to be requeued to a PI-aware futex. The implementation is the +result of a high-speed collision between futex_wait() and +futex_lock_pi(), with some extra logic to check for the additional +wake-up scenarios. + +FUTEX_REQUEUE_CMP_PI is called by the waker +(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and +possibly wake the waiting tasks. Internally, this system call is +still handled by futex_requeue (by passing requeue_pi=1). Before +requeueing, futex_requeue() attempts to acquire the requeue target +PI futex on behalf of the top waiter. If it can, this waiter is +woken. futex_requeue() then proceeds to requeue the remaining +nr_wake+nr_requeue tasks to the PI futex, calling +rt_mutex_start_proxy_lock() prior to each requeue to prepare the +task as a waiter on the underlying rt_mutex. It is possible that +the lock can be acquired at this stage as well, if so, the next +waiter is woken to finish the acquisition of the lock. + +FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but +their sum is all that really matters. futex_requeue() will wake or +requeue up to nr_wake + nr_requeue tasks. It will wake only as many +tasks as it can acquire the lock for, which in the majority of cases +should be 0 as good programming practice dictates that the caller of +either pthread_cond_broadcast() or pthread_cond_signal() acquire the +mutex prior to making the call. FUTEX_REQUEUE_PI requires that +nr_wake=1. nr_requeue should be INT_MAX for broadcast and 0 for +signal. diff --git a/trunk/Documentation/i2c/busses/i2c-ocores b/trunk/Documentation/i2c/busses/i2c-ocores index cfcebb10d14e..c269aaa2f26a 100644 --- a/trunk/Documentation/i2c/busses/i2c-ocores +++ b/trunk/Documentation/i2c/busses/i2c-ocores @@ -20,6 +20,8 @@ platform_device with the base address and interrupt number. The dev.platform_data of the device should also point to a struct ocores_i2c_platform_data (see linux/i2c-ocores.h) describing the distance between registers and the input clock speed. +There is also a possibility to attach a list of i2c_board_info which +the i2c-ocores driver will add to the bus upon creation. E.G. something like: @@ -36,9 +38,24 @@ static struct resource ocores_resources[] = { }, }; +/* optional board info */ +struct i2c_board_info ocores_i2c_board_info[] = { + { + I2C_BOARD_INFO("tsc2003", 0x48), + .platform_data = &tsc2003_platform_data, + .irq = TSC_IRQ + }, + { + I2C_BOARD_INFO("adv7180", 0x42 >> 1), + .irq = ADV_IRQ + } +}; + static struct ocores_i2c_platform_data myi2c_data = { .regstep = 2, /* two bytes between registers */ .clock_khz = 50000, /* input clock of 50MHz */ + .devices = ocores_i2c_board_info, /* optional table of devices */ + .num_devices = ARRAY_SIZE(ocores_i2c_board_info), /* table size */ }; static struct platform_device myi2c = { diff --git a/trunk/Documentation/ide/ide.txt b/trunk/Documentation/ide/ide.txt index 0c78f4b1d9d9..e77bebfa7b0d 100644 --- a/trunk/Documentation/ide/ide.txt +++ b/trunk/Documentation/ide/ide.txt @@ -216,6 +216,8 @@ Other kernel parameters for ide_core are: * "noflush=[interface_number.device_number]" to disable flush requests +* "nohpa=[interface_number.device_number]" to disable Host Protected Area + * "noprobe=[interface_number.device_number]" to skip probing * "nowerr=[interface_number.device_number]" to ignore the WRERR_STAT bit diff --git a/trunk/Documentation/kernel-parameters.txt b/trunk/Documentation/kernel-parameters.txt index fd5cac013037..0bf8a882ee9e 100644 --- a/trunk/Documentation/kernel-parameters.txt +++ b/trunk/Documentation/kernel-parameters.txt @@ -56,7 +56,6 @@ parameter is applicable: ISAPNP ISA PnP code is enabled. ISDN Appropriate ISDN support is enabled. JOY Appropriate joystick support is enabled. - KMEMTRACE kmemtrace is enabled. LIBATA Libata driver is enabled LP Printer support is enabled. LOOP Loopback device support is enabled. @@ -329,11 +328,6 @@ and is between 256 and 4096 characters. It is defined in the file flushed before they will be reused, which is a lot of faster - amd_iommu_size= [HW,X86-64] - Define the size of the aperture for the AMD IOMMU - driver. Possible values are: - '32M', '64M' (default), '128M', '256M', '512M', '1G' - amijoy.map= [HW,JOY] Amiga joystick support Map of devices attached to JOY0DAT and JOY1DAT Format: , @@ -646,6 +640,13 @@ and is between 256 and 4096 characters. It is defined in the file DMA-API debugging code disables itself because the architectural default is too low. + dma_debug_driver= + With this option the DMA-API debugging driver + filter feature can be enabled at boot time. Just + pass the driver to filter for as the parameter. + The filter can be disabled or changed to another + driver later using sysfs. + dscc4.setup= [NET] dtc3181e= [HW,SCSI] @@ -752,12 +753,25 @@ and is between 256 and 4096 characters. It is defined in the file ia64_pal_cache_flush instead of SAL_CACHE_FLUSH. ftrace=[tracer] - [ftrace] will set and start the specified tracer + [FTRACE] will set and start the specified tracer as early as possible in order to facilitate early boot debugging. ftrace_dump_on_oops - [ftrace] will dump the trace buffers on oops. + [FTRACE] will dump the trace buffers on oops. + + ftrace_filter=[function-list] + [FTRACE] Limit the functions traced by the function + tracer at boot up. function-list is a comma separated + list of functions. This list can be changed at run + time by the set_ftrace_filter file in the debugfs + tracing directory. + + ftrace_notrace=[function-list] + [FTRACE] Do not trace the functions specified in + function-list. This list can be changed at run time + by the set_ftrace_notrace file in the debugfs + tracing directory. gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad @@ -873,11 +887,8 @@ and is between 256 and 4096 characters. It is defined in the file ide-core.nodma= [HW] (E)IDE subsystem Format: =0.0 to prevent dma on hda, =0.1 hdb =1.0 hdc - .vlb_clock .pci_clock .noflush .noprobe .nowerr .cdrom - .chs .ignore_cable are additional options - See Documentation/ide/ide.txt. - - idebus= [HW] (E)IDE subsystem - VLB/PCI bus speed + .vlb_clock .pci_clock .noflush .nohpa .noprobe .nowerr + .cdrom .chs .ignore_cable are additional options See Documentation/ide/ide.txt. ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem @@ -914,6 +925,12 @@ and is between 256 and 4096 characters. It is defined in the file Formt: { "sha1" | "md5" } default: "sha1" + ima_tcb [IMA] + Load a policy which meets the needs of the Trusted + Computing Base. This means IMA will measure all + programs exec'd, files mmap'd for exec, and all files + opened for read by uid=0. + in2000= [HW,SCSI] See header of drivers/scsi/in2000.c. @@ -1054,15 +1071,6 @@ and is between 256 and 4096 characters. It is defined in the file use the HighMem zone if it exists, and the Normal zone if it does not. - kmemtrace.enable= [KNL,KMEMTRACE] Format: { yes | no } - Controls whether kmemtrace is enabled - at boot-time. - - kmemtrace.subbufs=n [KNL,KMEMTRACE] Overrides the number of - subbufs kmemtrace's relay channel has. Set this - higher than default (KMEMTRACE_N_SUBBUFS in code) if - you experience buffer overruns. - kgdboc= [HW] kgdb over consoles. Requires a tty driver that supports console polling. (only serial suported for now) @@ -1072,6 +1080,10 @@ and is between 256 and 4096 characters. It is defined in the file Configure the RouterBoard 532 series on-chip Ethernet adapter MAC address. + kmemleak= [KNL] Boot-time kmemleak enable/disable + Valid arguments: on, off + Default: on + kstack=N [X86] Print N words from the kernel stack in oops dumps. @@ -1575,6 +1587,9 @@ and is between 256 and 4096 characters. It is defined in the file noinitrd [RAM] Tells the kernel not to load any configured initial RAM disk. + nointremap [X86-64, Intel-IOMMU] Do not enable interrupt + remapping. + nointroute [IA-64] nojitter [IA64] Disables jitter checking for ITC timers. @@ -1660,6 +1675,14 @@ and is between 256 and 4096 characters. It is defined in the file oprofile.timer= [HW] Use timer interrupt instead of performance counters + oprofile.cpu_type= Force an oprofile cpu type + This might be useful if you have an older oprofile + userland or if you want common events. + Format: { archperfmon } + archperfmon: [X86] Force use of architectural + perfmon on Intel CPUs instead of the + CPU specific event set. + osst= [HW,SCSI] SCSI Tape Driver Format: , See also Documentation/scsi/st.txt. diff --git a/trunk/Documentation/kmemleak.txt b/trunk/Documentation/kmemleak.txt new file mode 100644 index 000000000000..0112da3b9ab8 --- /dev/null +++ b/trunk/Documentation/kmemleak.txt @@ -0,0 +1,142 @@ +Kernel Memory Leak Detector +=========================== + +Introduction +------------ + +Kmemleak provides a way of detecting possible kernel memory leaks in a +way similar to a tracing garbage collector +(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors), +with the difference that the orphan objects are not freed but only +reported via /sys/kernel/debug/kmemleak. A similar method is used by the +Valgrind tool (memcheck --leak-check) to detect the memory leaks in +user-space applications. + +Usage +----- + +CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel +thread scans the memory every 10 minutes (by default) and prints any new +unreferenced objects found. To trigger an intermediate scan and display +all the possible memory leaks: + + # mount -t debugfs nodev /sys/kernel/debug/ + # cat /sys/kernel/debug/kmemleak + +Note that the orphan objects are listed in the order they were allocated +and one object at the beginning of the list may cause other subsequent +objects to be reported as orphan. + +Memory scanning parameters can be modified at run-time by writing to the +/sys/kernel/debug/kmemleak file. The following parameters are supported: + + off - disable kmemleak (irreversible) + stack=on - enable the task stacks scanning + stack=off - disable the tasks stacks scanning + scan=on - start the automatic memory scanning thread + scan=off - stop the automatic memory scanning thread + scan= - set the automatic memory scanning period in seconds (0 + to disable it) + +Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on +the kernel command line. + +Basic Algorithm +--------------- + +The memory allocations via kmalloc, vmalloc, kmem_cache_alloc and +friends are traced and the pointers, together with additional +information like size and stack trace, are stored in a prio search tree. +The corresponding freeing function calls are tracked and the pointers +removed from the kmemleak data structures. + +An allocated block of memory is considered orphan if no pointer to its +start address or to any location inside the block can be found by +scanning the memory (including saved registers). This means that there +might be no way for the kernel to pass the address of the allocated +block to a freeing function and therefore the block is considered a +memory leak. + +The scanning algorithm steps: + + 1. mark all objects as white (remaining white objects will later be + considered orphan) + 2. scan the memory starting with the data section and stacks, checking + the values against the addresses stored in the prio search tree. If + a pointer to a white object is found, the object is added to the + gray list + 3. scan the gray objects for matching addresses (some white objects + can become gray and added at the end of the gray list) until the + gray set is finished + 4. the remaining white objects are considered orphan and reported via + /sys/kernel/debug/kmemleak + +Some allocated memory blocks have pointers stored in the kernel's +internal data structures and they cannot be detected as orphans. To +avoid this, kmemleak can also store the number of values pointing to an +address inside the block address range that need to be found so that the +block is not considered a leak. One example is __vmalloc(). + +Kmemleak API +------------ + +See the include/linux/kmemleak.h header for the functions prototype. + +kmemleak_init - initialize kmemleak +kmemleak_alloc - notify of a memory block allocation +kmemleak_free - notify of a memory block freeing +kmemleak_not_leak - mark an object as not a leak +kmemleak_ignore - do not scan or report an object as leak +kmemleak_scan_area - add scan areas inside a memory block +kmemleak_no_scan - do not scan a memory block +kmemleak_erase - erase an old value in a pointer variable +kmemleak_alloc_recursive - as kmemleak_alloc but checks the recursiveness +kmemleak_free_recursive - as kmemleak_free but checks the recursiveness + +Dealing with false positives/negatives +-------------------------------------- + +The false negatives are real memory leaks (orphan objects) but not +reported by kmemleak because values found during the memory scanning +point to such objects. To reduce the number of false negatives, kmemleak +provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and +kmemleak_erase functions (see above). The task stacks also increase the +amount of false negatives and their scanning is not enabled by default. + +The false positives are objects wrongly reported as being memory leaks +(orphan). For objects known not to be leaks, kmemleak provides the +kmemleak_not_leak function. The kmemleak_ignore could also be used if +the memory block is known not to contain other pointers and it will no +longer be scanned. + +Some of the reported leaks are only transient, especially on SMP +systems, because of pointers temporarily stored in CPU registers or +stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing +the minimum age of an object to be reported as a memory leak. + +Limitations and Drawbacks +------------------------- + +The main drawback is the reduced performance of memory allocation and +freeing. To avoid other penalties, the memory scanning is only performed +when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is +intended for debugging purposes where the performance might not be the +most important requirement. + +To keep the algorithm simple, kmemleak scans for values pointing to any +address inside a block's address range. This may lead to an increased +number of false negatives. However, it is likely that a real memory leak +will eventually become visible. + +Another source of false negatives is the data stored in non-pointer +values. In a future version, kmemleak could only scan the pointer +members in the allocated structures. This feature would solve many of +the false negative cases described above. + +The tool can report false positives. These are cases where an allocated +block doesn't need to be freed (some cases in the init_call functions), +the pointer is calculated by other methods than the usual container_of +macro or the pointer is stored in a location not scanned by kmemleak. + +Page allocations and ioremap are not tracked. Only the ARM and x86 +architectures are currently supported. diff --git a/trunk/Documentation/lguest/Makefile b/trunk/Documentation/lguest/Makefile index 1f4f9e888bd1..28c8cdfcafd8 100644 --- a/trunk/Documentation/lguest/Makefile +++ b/trunk/Documentation/lguest/Makefile @@ -1,6 +1,5 @@ # This creates the demonstration utility "lguest" which runs a Linux guest. -CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE -LDLIBS:=-lz +CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE all: lguest diff --git a/trunk/Documentation/lguest/lguest.c b/trunk/Documentation/lguest/lguest.c index d36fcc0f2715..9ebcd6ef361b 100644 --- a/trunk/Documentation/lguest/lguest.c +++ b/trunk/Documentation/lguest/lguest.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -59,7 +60,6 @@ typedef uint8_t u8; /*:*/ #define PAGE_PRESENT 0x7 /* Present, RW, Execute */ -#define NET_PEERNUM 1 #define BRIDGE_PFX "bridge:" #ifndef SIOCBRADDIF #define SIOCBRADDIF 0x89a2 /* add interface to bridge */ @@ -76,19 +76,12 @@ static bool verbose; do { if (verbose) printf(args); } while(0) /*:*/ -/* File descriptors for the Waker. */ -struct { - int pipe[2]; - int lguest_fd; -} waker_fds; - /* The pointer to the start of guest memory. */ static void *guest_base; /* The maximum guest physical address allowed, and maximum possible. */ static unsigned long guest_limit, guest_max; -/* The pipe for signal hander to write to. */ -static int timeoutpipe[2]; -static unsigned int timeout_usec = 500; +/* The /dev/lguest file descriptor. */ +static int lguest_fd; /* a per-cpu variable indicating whose vcpu is currently running */ static unsigned int __thread cpu_id; @@ -96,11 +89,6 @@ static unsigned int __thread cpu_id; /* This is our list of devices. */ struct device_list { - /* Summary information about the devices in our list: ready to pass to - * select() to ask which need servicing.*/ - fd_set infds; - int max_infd; - /* Counter to assign interrupt numbers. */ unsigned int next_irq; @@ -126,22 +114,21 @@ struct device /* The linked-list pointer. */ struct device *next; - /* The this device's descriptor, as mapped into the Guest. */ + /* The device's descriptor, as mapped into the Guest. */ struct lguest_device_desc *desc; + /* We can't trust desc values once Guest has booted: we use these. */ + unsigned int feature_len; + unsigned int num_vq; + /* The name of this device, for --verbose. */ const char *name; - /* If handle_input is set, it wants to be called when this file - * descriptor is ready. */ - int fd; - bool (*handle_input)(int fd, struct device *me); - /* Any queues attached to this device */ struct virtqueue *vq; - /* Handle status being finalized (ie. feature bits stable). */ - void (*ready)(struct device *me); + /* Is it operational */ + bool running; /* Device-specific data. */ void *priv; @@ -164,22 +151,28 @@ struct virtqueue /* Last available index we saw. */ u16 last_avail_idx; - /* The routine to call when the Guest pings us, or timeout. */ - void (*handle_output)(int fd, struct virtqueue *me, bool timeout); + /* How many are used since we sent last irq? */ + unsigned int pending_used; - /* Outstanding buffers */ - unsigned int inflight; + /* Eventfd where Guest notifications arrive. */ + int eventfd; - /* Is this blocked awaiting a timer? */ - bool blocked; + /* Function for the thread which is servicing this virtqueue. */ + void (*service)(struct virtqueue *vq); + pid_t thread; }; /* Remember the arguments to the program so we can "reboot" */ static char **main_args; -/* Since guest is UP and we don't run at the same time, we don't need barriers. - * But I include them in the code in case others copy it. */ -#define wmb() +/* The original tty settings to restore on exit. */ +static struct termios orig_term; + +/* We have to be careful with barriers: our devices are all run in separate + * threads and so we need to make sure that changes visible to the Guest happen + * in precise order. */ +#define wmb() __asm__ __volatile__("" : : : "memory") +#define mb() __asm__ __volatile__("" : : : "memory") /* Convert an iovec element to the given type. * @@ -245,7 +238,7 @@ static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len) static u8 *get_feature_bits(struct device *dev) { return (u8 *)(dev->desc + 1) - + dev->desc->num_vq * sizeof(struct lguest_vqconfig); + + dev->num_vq * sizeof(struct lguest_vqconfig); } /*L:100 The Launcher code itself takes us out into userspace, that scary place @@ -505,99 +498,19 @@ static void concat(char *dst, char *args[]) * saw the arguments it expects when we looked at initialize() in lguest_user.c: * the base of Guest "physical" memory, the top physical page to allow and the * entry point for the Guest. */ -static int tell_kernel(unsigned long start) +static void tell_kernel(unsigned long start) { unsigned long args[] = { LHREQ_INITIALIZE, (unsigned long)guest_base, guest_limit / getpagesize(), start }; - int fd; - verbose("Guest: %p - %p (%#lx)\n", guest_base, guest_base + guest_limit, guest_limit); - fd = open_or_die("/dev/lguest", O_RDWR); - if (write(fd, args, sizeof(args)) < 0) + lguest_fd = open_or_die("/dev/lguest", O_RDWR); + if (write(lguest_fd, args, sizeof(args)) < 0) err(1, "Writing to /dev/lguest"); - - /* We return the /dev/lguest file descriptor to control this Guest */ - return fd; } /*:*/ -static void add_device_fd(int fd) -{ - FD_SET(fd, &devices.infds); - if (fd > devices.max_infd) - devices.max_infd = fd; -} - -/*L:200 - * The Waker. - * - * With console, block and network devices, we can have lots of input which we - * need to process. We could try to tell the kernel what file descriptors to - * watch, but handing a file descriptor mask through to the kernel is fairly - * icky. - * - * Instead, we clone off a thread which watches the file descriptors and writes - * the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host - * stop running the Guest. This causes the Launcher to return from the - * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset - * the LHREQ_BREAK and wake us up again. - * - * This, of course, is merely a different *kind* of icky. - * - * Given my well-known antipathy to threads, I'd prefer to use processes. But - * it's easier to share Guest memory with threads, and trivial to share the - * devices.infds as the Launcher changes it. - */ -static int waker(void *unused) -{ - /* Close the write end of the pipe: only the Launcher has it open. */ - close(waker_fds.pipe[1]); - - for (;;) { - fd_set rfds = devices.infds; - unsigned long args[] = { LHREQ_BREAK, 1 }; - unsigned int maxfd = devices.max_infd; - - /* We also listen to the pipe from the Launcher. */ - FD_SET(waker_fds.pipe[0], &rfds); - if (waker_fds.pipe[0] > maxfd) - maxfd = waker_fds.pipe[0]; - - /* Wait until input is ready from one of the devices. */ - select(maxfd+1, &rfds, NULL, NULL, NULL); - - /* Message from Launcher? */ - if (FD_ISSET(waker_fds.pipe[0], &rfds)) { - char c; - /* If this fails, then assume Launcher has exited. - * Don't do anything on exit: we're just a thread! */ - if (read(waker_fds.pipe[0], &c, 1) != 1) - _exit(0); - continue; - } - - /* Send LHREQ_BREAK command to snap the Launcher out of it. */ - pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id); - } - return 0; -} - -/* This routine just sets up a pipe to the Waker process. */ -static void setup_waker(int lguest_fd) -{ - /* This pipe is closed when Launcher dies, telling Waker. */ - if (pipe(waker_fds.pipe) != 0) - err(1, "Creating pipe for Waker"); - - /* Waker also needs to know the lguest fd */ - waker_fds.lguest_fd = lguest_fd; - - if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1) - err(1, "Creating Waker"); -} - /* * Device Handling. * @@ -623,49 +536,90 @@ static void *_check_pointer(unsigned long addr, unsigned int size, /* Each buffer in the virtqueues is actually a chain of descriptors. This * function returns the next descriptor in the chain, or vq->vring.num if we're * at the end. */ -static unsigned next_desc(struct virtqueue *vq, unsigned int i) +static unsigned next_desc(struct vring_desc *desc, + unsigned int i, unsigned int max) { unsigned int next; /* If this descriptor says it doesn't chain, we're done. */ - if (!(vq->vring.desc[i].flags & VRING_DESC_F_NEXT)) - return vq->vring.num; + if (!(desc[i].flags & VRING_DESC_F_NEXT)) + return max; /* Check they're not leading us off end of descriptors. */ - next = vq->vring.desc[i].next; + next = desc[i].next; /* Make sure compiler knows to grab that: we don't want it changing! */ wmb(); - if (next >= vq->vring.num) + if (next >= max) errx(1, "Desc next is %u", next); return next; } +/* This actually sends the interrupt for this virtqueue */ +static void trigger_irq(struct virtqueue *vq) +{ + unsigned long buf[] = { LHREQ_IRQ, vq->config.irq }; + + /* Don't inform them if nothing used. */ + if (!vq->pending_used) + return; + vq->pending_used = 0; + + /* If they don't want an interrupt, don't send one, unless empty. */ + if ((vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) + && lg_last_avail(vq) != vq->vring.avail->idx) + return; + + /* Send the Guest an interrupt tell them we used something up. */ + if (write(lguest_fd, buf, sizeof(buf)) != 0) + err(1, "Triggering irq %i", vq->config.irq); +} + /* This looks in the virtqueue and for the first available buffer, and converts * it to an iovec for convenient access. Since descriptors consist of some * number of output then some number of input descriptors, it's actually two * iovecs, but we pack them into one and note how many of each there were. * - * This function returns the descriptor number found, or vq->vring.num (which - * is never a valid descriptor number) if none was found. */ -static unsigned get_vq_desc(struct virtqueue *vq, - struct iovec iov[], - unsigned int *out_num, unsigned int *in_num) + * This function returns the descriptor number found. */ +static unsigned wait_for_vq_desc(struct virtqueue *vq, + struct iovec iov[], + unsigned int *out_num, unsigned int *in_num) { - unsigned int i, head; - u16 last_avail; + unsigned int i, head, max; + struct vring_desc *desc; + u16 last_avail = lg_last_avail(vq); + + while (last_avail == vq->vring.avail->idx) { + u64 event; + + /* OK, tell Guest about progress up to now. */ + trigger_irq(vq); + + /* OK, now we need to know about added descriptors. */ + vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; + + /* They could have slipped one in as we were doing that: make + * sure it's written, then check again. */ + mb(); + if (last_avail != vq->vring.avail->idx) { + vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; + break; + } + + /* Nothing new? Wait for eventfd to tell us they refilled. */ + if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event)) + errx(1, "Event read failed?"); + + /* We don't need to be notified again. */ + vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; + } /* Check it isn't doing very strange things with descriptor numbers. */ - last_avail = lg_last_avail(vq); if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) errx(1, "Guest moved used index from %u to %u", last_avail, vq->vring.avail->idx); - /* If there's nothing new since last we looked, return invalid. */ - if (vq->vring.avail->idx == last_avail) - return vq->vring.num; - /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ head = vq->vring.avail->ring[last_avail % vq->vring.num]; @@ -678,15 +632,28 @@ static unsigned get_vq_desc(struct virtqueue *vq, /* When we start there are none of either input nor output. */ *out_num = *in_num = 0; + max = vq->vring.num; + desc = vq->vring.desc; i = head; + + /* If this is an indirect entry, then this buffer contains a descriptor + * table which we handle as if it's any normal descriptor chain. */ + if (desc[i].flags & VRING_DESC_F_INDIRECT) { + if (desc[i].len % sizeof(struct vring_desc)) + errx(1, "Invalid size for indirect buffer table"); + + max = desc[i].len / sizeof(struct vring_desc); + desc = check_pointer(desc[i].addr, desc[i].len); + i = 0; + } + do { /* Grab the first descriptor, and check it's OK. */ - iov[*out_num + *in_num].iov_len = vq->vring.desc[i].len; + iov[*out_num + *in_num].iov_len = desc[i].len; iov[*out_num + *in_num].iov_base - = check_pointer(vq->vring.desc[i].addr, - vq->vring.desc[i].len); + = check_pointer(desc[i].addr, desc[i].len); /* If this is an input descriptor, increment that count. */ - if (vq->vring.desc[i].flags & VRING_DESC_F_WRITE) + if (desc[i].flags & VRING_DESC_F_WRITE) (*in_num)++; else { /* If it's an output descriptor, they're all supposed @@ -697,11 +664,10 @@ static unsigned get_vq_desc(struct virtqueue *vq, } /* If we've got too many, that implies a descriptor loop. */ - if (*out_num + *in_num > vq->vring.num) + if (*out_num + *in_num > max) errx(1, "Looped descriptor"); - } while ((i = next_desc(vq, i)) != vq->vring.num); + } while ((i = next_desc(desc, i, max)) != max); - vq->inflight++; return head; } @@ -719,44 +685,20 @@ static void add_used(struct virtqueue *vq, unsigned int head, int len) /* Make sure buffer is written before we update index. */ wmb(); vq->vring.used->idx++; - vq->inflight--; -} - -/* This actually sends the interrupt for this virtqueue */ -static void trigger_irq(int fd, struct virtqueue *vq) -{ - unsigned long buf[] = { LHREQ_IRQ, vq->config.irq }; - - /* If they don't want an interrupt, don't send one, unless empty. */ - if ((vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) - && vq->inflight) - return; - - /* Send the Guest an interrupt tell them we used something up. */ - if (write(fd, buf, sizeof(buf)) != 0) - err(1, "Triggering irq %i", vq->config.irq); + vq->pending_used++; } /* And here's the combo meal deal. Supersize me! */ -static void add_used_and_trigger(int fd, struct virtqueue *vq, - unsigned int head, int len) +static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len) { add_used(vq, head, len); - trigger_irq(fd, vq); + trigger_irq(vq); } /* * The Console * - * Here is the input terminal setting we save, and the routine to restore them - * on exit so the user gets their terminal back. */ -static struct termios orig_term; -static void restore_term(void) -{ - tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); -} - -/* We associate some data with the console for our exit hack. */ + * We associate some data with the console for our exit hack. */ struct console_abort { /* How many times have they hit ^C? */ @@ -766,276 +708,275 @@ struct console_abort }; /* This is the routine which handles console input (ie. stdin). */ -static bool handle_console_input(int fd, struct device *dev) +static void console_input(struct virtqueue *vq) { int len; unsigned int head, in_num, out_num; - struct iovec iov[dev->vq->vring.num]; - struct console_abort *abort = dev->priv; - - /* First we need a console buffer from the Guests's input virtqueue. */ - head = get_vq_desc(dev->vq, iov, &out_num, &in_num); - - /* If they're not ready for input, stop listening to this file - * descriptor. We'll start again once they add an input buffer. */ - if (head == dev->vq->vring.num) - return false; + struct console_abort *abort = vq->dev->priv; + struct iovec iov[vq->vring.num]; + /* Make sure there's a descriptor waiting. */ + head = wait_for_vq_desc(vq, iov, &out_num, &in_num); if (out_num) errx(1, "Output buffers in console in queue?"); - /* This is why we convert to iovecs: the readv() call uses them, and so - * it reads straight into the Guest's buffer. */ - len = readv(dev->fd, iov, in_num); + /* Read it in. */ + len = readv(STDIN_FILENO, iov, in_num); if (len <= 0) { - /* This implies that the console is closed, is /dev/null, or - * something went terribly wrong. */ + /* Ran out of input? */ warnx("Failed to get console input, ignoring console."); - /* Put the input terminal back. */ - restore_term(); - /* Remove callback from input vq, so it doesn't restart us. */ - dev->vq->handle_output = NULL; - /* Stop listening to this fd: don't call us again. */ - return false; + /* For simplicity, dying threads kill the whole Launcher. So + * just nap here. */ + for (;;) + pause(); } - /* Tell the Guest about the new input. */ - add_used_and_trigger(fd, dev->vq, head, len); + add_used_and_trigger(vq, head, len); /* Three ^C within one second? Exit. * - * This is such a hack, but works surprisingly well. Each ^C has to be - * in a buffer by itself, so they can't be too fast. But we check that - * we get three within about a second, so they can't be too slow. */ - if (len == 1 && ((char *)iov[0].iov_base)[0] == 3) { - if (!abort->count++) - gettimeofday(&abort->start, NULL); - else if (abort->count == 3) { - struct timeval now; - gettimeofday(&now, NULL); - if (now.tv_sec <= abort->start.tv_sec+1) { - unsigned long args[] = { LHREQ_BREAK, 0 }; - /* Close the fd so Waker will know it has to - * exit. */ - close(waker_fds.pipe[1]); - /* Just in case Waker is blocked in BREAK, send - * unbreak now. */ - write(fd, args, sizeof(args)); - exit(2); - } - abort->count = 0; - } - } else - /* Any other key resets the abort counter. */ + * This is such a hack, but works surprisingly well. Each ^C has to + * be in a buffer by itself, so they can't be too fast. But we check + * that we get three within about a second, so they can't be too + * slow. */ + if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) { abort->count = 0; + return; + } - /* Everything went OK! */ - return true; + abort->count++; + if (abort->count == 1) + gettimeofday(&abort->start, NULL); + else if (abort->count == 3) { + struct timeval now; + gettimeofday(&now, NULL); + /* Kill all Launcher processes with SIGINT, like normal ^C */ + if (now.tv_sec <= abort->start.tv_sec+1) + kill(0, SIGINT); + abort->count = 0; + } } -/* Handling output for console is simple: we just get all the output buffers - * and write them to stdout. */ -static void handle_console_output(int fd, struct virtqueue *vq, bool timeout) +/* This is the routine which handles console output (ie. stdout). */ +static void console_output(struct virtqueue *vq) { unsigned int head, out, in; - int len; struct iovec iov[vq->vring.num]; - /* Keep getting output buffers from the Guest until we run out. */ - while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) { - if (in) - errx(1, "Input buffers in output queue?"); - len = writev(STDOUT_FILENO, iov, out); - add_used_and_trigger(fd, vq, head, len); + head = wait_for_vq_desc(vq, iov, &out, &in); + if (in) + errx(1, "Input buffers in console output queue?"); + while (!iov_empty(iov, out)) { + int len = writev(STDOUT_FILENO, iov, out); + if (len <= 0) + err(1, "Write to stdout gave %i", len); + iov_consume(iov, out, len); } -} - -/* This is called when we no longer want to hear about Guest changes to a - * virtqueue. This is more efficient in high-traffic cases, but it means we - * have to set a timer to check if any more changes have occurred. */ -static void block_vq(struct virtqueue *vq) -{ - struct itimerval itm; - - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - vq->blocked = true; - - itm.it_interval.tv_sec = 0; - itm.it_interval.tv_usec = 0; - itm.it_value.tv_sec = 0; - itm.it_value.tv_usec = timeout_usec; - - setitimer(ITIMER_REAL, &itm, NULL); + add_used(vq, head, 0); } /* * The Network * * Handling output for network is also simple: we get all the output buffers - * and write them (ignoring the first element) to this device's file descriptor - * (/dev/net/tun). + * and write them to /dev/net/tun. */ -static void handle_net_output(int fd, struct virtqueue *vq, bool timeout) +struct net_info { + int tunfd; +}; + +static void net_output(struct virtqueue *vq) { - unsigned int head, out, in, num = 0; - int len; + struct net_info *net_info = vq->dev->priv; + unsigned int head, out, in; struct iovec iov[vq->vring.num]; - static int last_timeout_num; - - /* Keep getting output buffers from the Guest until we run out. */ - while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) { - if (in) - errx(1, "Input buffers in output queue?"); - len = writev(vq->dev->fd, iov, out); - if (len < 0) - err(1, "Writing network packet to tun"); - add_used_and_trigger(fd, vq, head, len); - num++; - } - /* Block further kicks and set up a timer if we saw anything. */ - if (!timeout && num) - block_vq(vq); - - /* We never quite know how long should we wait before we check the - * queue again for more packets. We start at 500 microseconds, and if - * we get fewer packets than last time, we assume we made the timeout - * too small and increase it by 10 microseconds. Otherwise, we drop it - * by one microsecond every time. It seems to work well enough. */ - if (timeout) { - if (num < last_timeout_num) - timeout_usec += 10; - else if (timeout_usec > 1) - timeout_usec--; - last_timeout_num = num; - } + head = wait_for_vq_desc(vq, iov, &out, &in); + if (in) + errx(1, "Input buffers in net output queue?"); + if (writev(net_info->tunfd, iov, out) < 0) + errx(1, "Write to tun failed?"); + add_used(vq, head, 0); +} + +/* Will reading from this file descriptor block? */ +static bool will_block(int fd) +{ + fd_set fdset; + struct timeval zero = { 0, 0 }; + FD_ZERO(&fdset); + FD_SET(fd, &fdset); + return select(fd+1, &fdset, NULL, NULL, &zero) != 1; } -/* This is where we handle a packet coming in from the tun device to our +/* This is where we handle packets coming in from the tun device to our * Guest. */ -static bool handle_tun_input(int fd, struct device *dev) +static void net_input(struct virtqueue *vq) { - unsigned int head, in_num, out_num; int len; - struct iovec iov[dev->vq->vring.num]; - - /* First we need a network buffer from the Guests's recv virtqueue. */ - head = get_vq_desc(dev->vq, iov, &out_num, &in_num); - if (head == dev->vq->vring.num) { - /* Now, it's expected that if we try to send a packet too - * early, the Guest won't be ready yet. Wait until the device - * status says it's ready. */ - /* FIXME: Actually want DRIVER_ACTIVE here. */ - - /* Now tell it we want to know if new things appear. */ - dev->vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; - wmb(); - - /* We'll turn this back on if input buffers are registered. */ - return false; - } else if (out_num) - errx(1, "Output buffers in network recv queue?"); - - /* Read the packet from the device directly into the Guest's buffer. */ - len = readv(dev->fd, iov, in_num); - if (len <= 0) - err(1, "reading network"); + unsigned int head, out, in; + struct iovec iov[vq->vring.num]; + struct net_info *net_info = vq->dev->priv; - /* Tell the Guest about the new packet. */ - add_used_and_trigger(fd, dev->vq, head, len); + head = wait_for_vq_desc(vq, iov, &out, &in); + if (out) + errx(1, "Output buffers in net input queue?"); - verbose("tun input packet len %i [%02x %02x] (%s)\n", len, - ((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1], - head != dev->vq->vring.num ? "sent" : "discarded"); + /* Deliver interrupt now, since we're about to sleep. */ + if (vq->pending_used && will_block(net_info->tunfd)) + trigger_irq(vq); - /* All good. */ - return true; + len = readv(net_info->tunfd, iov, in); + if (len <= 0) + err(1, "Failed to read from tun."); + add_used(vq, head, len); } -/*L:215 This is the callback attached to the network and console input - * virtqueues: it ensures we try again, in case we stopped console or net - * delivery because Guest didn't have any buffers. */ -static void enable_fd(int fd, struct virtqueue *vq, bool timeout) +/* This is the helper to create threads. */ +static int do_thread(void *_vq) { - add_device_fd(vq->dev->fd); - /* Snap the Waker out of its select loop. */ - write(waker_fds.pipe[1], "", 1); + struct virtqueue *vq = _vq; + + for (;;) + vq->service(vq); + return 0; } -static void net_enable_fd(int fd, struct virtqueue *vq, bool timeout) +/* When a child dies, we kill our entire process group with SIGTERM. This + * also has the side effect that the shell restores the console for us! */ +static void kill_launcher(int signal) { - /* We don't need to know again when Guest refills receive buffer. */ - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - enable_fd(fd, vq, timeout); + kill(0, SIGTERM); } -/* When the Guest tells us they updated the status field, we handle it. */ -static void update_device_status(struct device *dev) +static void reset_device(struct device *dev) { struct virtqueue *vq; - /* This is a reset. */ - if (dev->desc->status == 0) { - verbose("Resetting device %s\n", dev->name); + verbose("Resetting device %s\n", dev->name); - /* Clear any features they've acked. */ - memset(get_feature_bits(dev) + dev->desc->feature_len, 0, - dev->desc->feature_len); + /* Clear any features they've acked. */ + memset(get_feature_bits(dev) + dev->feature_len, 0, dev->feature_len); - /* Zero out the virtqueues. */ - for (vq = dev->vq; vq; vq = vq->next) { - memset(vq->vring.desc, 0, - vring_size(vq->config.num, LGUEST_VRING_ALIGN)); - lg_last_avail(vq) = 0; + /* We're going to be explicitly killing threads, so ignore them. */ + signal(SIGCHLD, SIG_IGN); + + /* Zero out the virtqueues, get rid of their threads */ + for (vq = dev->vq; vq; vq = vq->next) { + if (vq->thread != (pid_t)-1) { + kill(vq->thread, SIGTERM); + waitpid(vq->thread, NULL, 0); + vq->thread = (pid_t)-1; } - } else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) { + memset(vq->vring.desc, 0, + vring_size(vq->config.num, LGUEST_VRING_ALIGN)); + lg_last_avail(vq) = 0; + } + dev->running = false; + + /* Now we care if threads die. */ + signal(SIGCHLD, (void *)kill_launcher); +} + +static void create_thread(struct virtqueue *vq) +{ + /* Create stack for thread and run it. Since stack grows + * upwards, we point the stack pointer to the end of this + * region. */ + char *stack = malloc(32768); + unsigned long args[] = { LHREQ_EVENTFD, + vq->config.pfn*getpagesize(), 0 }; + + /* Create a zero-initialized eventfd. */ + vq->eventfd = eventfd(0, 0); + if (vq->eventfd < 0) + err(1, "Creating eventfd"); + args[2] = vq->eventfd; + + /* Attach an eventfd to this virtqueue: it will go off + * when the Guest does an LHCALL_NOTIFY for this vq. */ + if (write(lguest_fd, &args, sizeof(args)) != 0) + err(1, "Attaching eventfd"); + + /* CLONE_VM: because it has to access the Guest memory, and + * SIGCHLD so we get a signal if it dies. */ + vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq); + if (vq->thread == (pid_t)-1) + err(1, "Creating clone"); + /* We close our local copy, now the child has it. */ + close(vq->eventfd); +} + +static void start_device(struct device *dev) +{ + unsigned int i; + struct virtqueue *vq; + + verbose("Device %s OK: offered", dev->name); + for (i = 0; i < dev->feature_len; i++) + verbose(" %02x", get_feature_bits(dev)[i]); + verbose(", accepted"); + for (i = 0; i < dev->feature_len; i++) + verbose(" %02x", get_feature_bits(dev) + [dev->feature_len+i]); + + for (vq = dev->vq; vq; vq = vq->next) { + if (vq->service) + create_thread(vq); + } + dev->running = true; +} + +static void cleanup_devices(void) +{ + struct device *dev; + + for (dev = devices.dev; dev; dev = dev->next) + reset_device(dev); + + /* If we saved off the original terminal settings, restore them now. */ + if (orig_term.c_lflag & (ISIG|ICANON|ECHO)) + tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); +} + +/* When the Guest tells us they updated the status field, we handle it. */ +static void update_device_status(struct device *dev) +{ + /* A zero status is a reset, otherwise it's a set of flags. */ + if (dev->desc->status == 0) + reset_device(dev); + else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) { warnx("Device %s configuration FAILED", dev->name); + if (dev->running) + reset_device(dev); } else if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK) { - unsigned int i; - - verbose("Device %s OK: offered", dev->name); - for (i = 0; i < dev->desc->feature_len; i++) - verbose(" %02x", get_feature_bits(dev)[i]); - verbose(", accepted"); - for (i = 0; i < dev->desc->feature_len; i++) - verbose(" %02x", get_feature_bits(dev) - [dev->desc->feature_len+i]); - - if (dev->ready) - dev->ready(dev); + if (!dev->running) + start_device(dev); } } /* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */ -static void handle_output(int fd, unsigned long addr) +static void handle_output(unsigned long addr) { struct device *i; - struct virtqueue *vq; - /* Check each device and virtqueue. */ + /* Check each device. */ for (i = devices.dev; i; i = i->next) { + struct virtqueue *vq; + /* Notifications to device descriptors update device status. */ if (from_guest_phys(addr) == i->desc) { update_device_status(i); return; } - /* Notifications to virtqueues mean output has occurred. */ + /* Devices *can* be used before status is set to DRIVER_OK. */ for (vq = i->vq; vq; vq = vq->next) { - if (vq->config.pfn != addr/getpagesize()) + if (addr != vq->config.pfn*getpagesize()) continue; - - /* Guest should acknowledge (and set features!) before - * using the device. */ - if (i->desc->status == 0) { - warnx("%s gave early output", i->name); - return; - } - - if (strcmp(vq->dev->name, "console") != 0) - verbose("Output to %s\n", vq->dev->name); - if (vq->handle_output) - vq->handle_output(fd, vq, false); + if (i->running) + errx(1, "Notification on running %s", i->name); + start_device(i); return; } } @@ -1049,71 +990,6 @@ static void handle_output(int fd, unsigned long addr) strnlen(from_guest_phys(addr), guest_limit - addr)); } -static void handle_timeout(int fd) -{ - char buf[32]; - struct device *i; - struct virtqueue *vq; - - /* Clear the pipe */ - read(timeoutpipe[0], buf, sizeof(buf)); - - /* Check each device and virtqueue: flush blocked ones. */ - for (i = devices.dev; i; i = i->next) { - for (vq = i->vq; vq; vq = vq->next) { - if (!vq->blocked) - continue; - - vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; - vq->blocked = false; - if (vq->handle_output) - vq->handle_output(fd, vq, true); - } - } -} - -/* This is called when the Waker wakes us up: check for incoming file - * descriptors. */ -static void handle_input(int fd) -{ - /* select() wants a zeroed timeval to mean "don't wait". */ - struct timeval poll = { .tv_sec = 0, .tv_usec = 0 }; - - for (;;) { - struct device *i; - fd_set fds = devices.infds; - int num; - - num = select(devices.max_infd+1, &fds, NULL, NULL, &poll); - /* Could get interrupted */ - if (num < 0) - continue; - /* If nothing is ready, we're done. */ - if (num == 0) - break; - - /* Otherwise, call the device(s) which have readable file - * descriptors and a method of handling them. */ - for (i = devices.dev; i; i = i->next) { - if (i->handle_input && FD_ISSET(i->fd, &fds)) { - if (i->handle_input(fd, i)) - continue; - - /* If handle_input() returns false, it means we - * should no longer service it. Networking and - * console do this when there's no input - * buffers to deliver into. Console also uses - * it when it discovers that stdin is closed. */ - FD_CLR(i->fd, &devices.infds); - } - } - - /* Is this the timeout fd? */ - if (FD_ISSET(timeoutpipe[0], &fds)) - handle_timeout(fd); - } -} - /*L:190 * Device Setup * @@ -1129,8 +1005,8 @@ static void handle_input(int fd) static u8 *device_config(const struct device *dev) { return (void *)(dev->desc + 1) - + dev->desc->num_vq * sizeof(struct lguest_vqconfig) - + dev->desc->feature_len * 2; + + dev->num_vq * sizeof(struct lguest_vqconfig) + + dev->feature_len * 2; } /* This routine allocates a new "struct lguest_device_desc" from descriptor @@ -1159,7 +1035,7 @@ static struct lguest_device_desc *new_dev_desc(u16 type) /* Each device descriptor is followed by the description of its virtqueues. We * specify how many descriptors the virtqueue is to have. */ static void add_virtqueue(struct device *dev, unsigned int num_descs, - void (*handle_output)(int, struct virtqueue *, bool)) + void (*service)(struct virtqueue *)) { unsigned int pages; struct virtqueue **i, *vq = malloc(sizeof(*vq)); @@ -1174,8 +1050,8 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, vq->next = NULL; vq->last_avail_idx = 0; vq->dev = dev; - vq->inflight = 0; - vq->blocked = false; + vq->service = service; + vq->thread = (pid_t)-1; /* Initialize the configuration. */ vq->config.num = num_descs; @@ -1191,6 +1067,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, * yet, otherwise we'd be overwriting them. */ assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0); memcpy(device_config(dev), &vq->config, sizeof(vq->config)); + dev->num_vq++; dev->desc->num_vq++; verbose("Virtqueue page %#lx\n", to_guest_phys(p)); @@ -1199,15 +1076,6 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, * second. */ for (i = &dev->vq; *i; i = &(*i)->next); *i = vq; - - /* Set the routine to call when the Guest does something to this - * virtqueue. */ - vq->handle_output = handle_output; - - /* As an optimization, set the advisory "Don't Notify Me" flag if we - * don't have a handler */ - if (!handle_output) - vq->vring.used->flags = VRING_USED_F_NO_NOTIFY; } /* The first half of the feature bitmask is for us to advertise features. The @@ -1219,7 +1087,7 @@ static void add_feature(struct device *dev, unsigned bit) /* We can't extend the feature bits once we've added config bytes */ if (dev->desc->feature_len <= bit / CHAR_BIT) { assert(dev->desc->config_len == 0); - dev->desc->feature_len = (bit / CHAR_BIT) + 1; + dev->feature_len = dev->desc->feature_len = (bit/CHAR_BIT) + 1; } features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT)); @@ -1243,22 +1111,17 @@ static void set_config(struct device *dev, unsigned len, const void *conf) * calling new_dev_desc() to allocate the descriptor and device memory. * * See what I mean about userspace being boring? */ -static struct device *new_device(const char *name, u16 type, int fd, - bool (*handle_input)(int, struct device *)) +static struct device *new_device(const char *name, u16 type) { struct device *dev = malloc(sizeof(*dev)); /* Now we populate the fields one at a time. */ - dev->fd = fd; - /* If we have an input handler for this file descriptor, then we add it - * to the device_list's fdset and maxfd. */ - if (handle_input) - add_device_fd(dev->fd); dev->desc = new_dev_desc(type); - dev->handle_input = handle_input; dev->name = name; dev->vq = NULL; - dev->ready = NULL; + dev->feature_len = 0; + dev->num_vq = 0; + dev->running = false; /* Append to device list. Prepending to a single-linked list is * easier, but the user expects the devices to be arranged on the bus @@ -1286,13 +1149,10 @@ static void setup_console(void) * raw input stream to the Guest. */ term.c_lflag &= ~(ISIG|ICANON|ECHO); tcsetattr(STDIN_FILENO, TCSANOW, &term); - /* If we exit gracefully, the original settings will be - * restored so the user can see what they're typing. */ - atexit(restore_term); } - dev = new_device("console", VIRTIO_ID_CONSOLE, - STDIN_FILENO, handle_console_input); + dev = new_device("console", VIRTIO_ID_CONSOLE); + /* We store the console state in dev->priv, and initialize it. */ dev->priv = malloc(sizeof(struct console_abort)); ((struct console_abort *)dev->priv)->count = 0; @@ -1301,31 +1161,13 @@ static void setup_console(void) * they put something the input queue, we make sure we're listening to * stdin. When they put something in the output queue, we write it to * stdout. */ - add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd); - add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output); + add_virtqueue(dev, VIRTQUEUE_NUM, console_input); + add_virtqueue(dev, VIRTQUEUE_NUM, console_output); - verbose("device %u: console\n", devices.device_num++); + verbose("device %u: console\n", ++devices.device_num); } /*:*/ -static void timeout_alarm(int sig) -{ - write(timeoutpipe[1], "", 1); -} - -static void setup_timeout(void) -{ - if (pipe(timeoutpipe) != 0) - err(1, "Creating timeout pipe"); - - if (fcntl(timeoutpipe[1], F_SETFL, - fcntl(timeoutpipe[1], F_GETFL) | O_NONBLOCK) != 0) - err(1, "Making timeout pipe nonblocking"); - - add_device_fd(timeoutpipe[0]); - signal(SIGALRM, timeout_alarm); -} - /*M:010 Inter-guest networking is an interesting area. Simplest is to have a * --sharenet= option which opens or creates a named pipe. This can be * used to send packets to another guest in a 1:1 manner. @@ -1447,21 +1289,23 @@ static int get_tun_device(char tapif[IFNAMSIZ]) static void setup_tun_net(char *arg) { struct device *dev; - int netfd, ipfd; + struct net_info *net_info = malloc(sizeof(*net_info)); + int ipfd; u32 ip = INADDR_ANY; bool bridging = false; char tapif[IFNAMSIZ], *p; struct virtio_net_config conf; - netfd = get_tun_device(tapif); + net_info->tunfd = get_tun_device(tapif); /* First we create a new network device. */ - dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input); + dev = new_device("net", VIRTIO_ID_NET); + dev->priv = net_info; /* Network devices need a receive and a send queue, just like * console. */ - add_virtqueue(dev, VIRTQUEUE_NUM, net_enable_fd); - add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output); + add_virtqueue(dev, VIRTQUEUE_NUM, net_input); + add_virtqueue(dev, VIRTQUEUE_NUM, net_output); /* We need a socket to perform the magic network ioctls to bring up the * tap interface, connect to the bridge etc. Any socket will do! */ @@ -1502,6 +1346,8 @@ static void setup_tun_net(char *arg) add_feature(dev, VIRTIO_NET_F_HOST_TSO4); add_feature(dev, VIRTIO_NET_F_HOST_TSO6); add_feature(dev, VIRTIO_NET_F_HOST_ECN); + /* We handle indirect ring entries */ + add_feature(dev, VIRTIO_RING_F_INDIRECT_DESC); set_config(dev, sizeof(conf), &conf); /* We don't need the socket any more; setup is done. */ @@ -1550,20 +1396,18 @@ struct vblk_info * Remember that the block device is handled by a separate I/O thread. We head * straight into the core of that thread here: */ -static bool service_io(struct device *dev) +static void blk_request(struct virtqueue *vq) { - struct vblk_info *vblk = dev->priv; + struct vblk_info *vblk = vq->dev->priv; unsigned int head, out_num, in_num, wlen; int ret; u8 *in; struct virtio_blk_outhdr *out; - struct iovec iov[dev->vq->vring.num]; + struct iovec iov[vq->vring.num]; off64_t off; - /* See if there's a request waiting. If not, nothing to do. */ - head = get_vq_desc(dev->vq, iov, &out_num, &in_num); - if (head == dev->vq->vring.num) - return false; + /* Get the next request. */ + head = wait_for_vq_desc(vq, iov, &out_num, &in_num); /* Every block request should contain at least one output buffer * (detailing the location on disk and the type of request) and one @@ -1637,83 +1481,21 @@ static bool service_io(struct device *dev) if (out->type & VIRTIO_BLK_T_BARRIER) fdatasync(vblk->fd); - /* We can't trigger an IRQ, because we're not the Launcher. It does - * that when we tell it we're done. */ - add_used(dev->vq, head, wlen); - return true; -} - -/* This is the thread which actually services the I/O. */ -static int io_thread(void *_dev) -{ - struct device *dev = _dev; - struct vblk_info *vblk = dev->priv; - char c; - - /* Close other side of workpipe so we get 0 read when main dies. */ - close(vblk->workpipe[1]); - /* Close the other side of the done_fd pipe. */ - close(dev->fd); - - /* When this read fails, it means Launcher died, so we follow. */ - while (read(vblk->workpipe[0], &c, 1) == 1) { - /* We acknowledge each request immediately to reduce latency, - * rather than waiting until we've done them all. I haven't - * measured to see if it makes any difference. - * - * That would be an interesting test, wouldn't it? You could - * also try having more than one I/O thread. */ - while (service_io(dev)) - write(vblk->done_fd, &c, 1); - } - return 0; -} - -/* Now we've seen the I/O thread, we return to the Launcher to see what happens - * when that thread tells us it's completed some I/O. */ -static bool handle_io_finish(int fd, struct device *dev) -{ - char c; - - /* If the I/O thread died, presumably it printed the error, so we - * simply exit. */ - if (read(dev->fd, &c, 1) != 1) - exit(1); - - /* It did some work, so trigger the irq. */ - trigger_irq(fd, dev->vq); - return true; -} - -/* When the Guest submits some I/O, we just need to wake the I/O thread. */ -static void handle_virtblk_output(int fd, struct virtqueue *vq, bool timeout) -{ - struct vblk_info *vblk = vq->dev->priv; - char c = 0; - - /* Wake up I/O thread and tell it to go to work! */ - if (write(vblk->workpipe[1], &c, 1) != 1) - /* Presumably it indicated why it died. */ - exit(1); + add_used(vq, head, wlen); } /*L:198 This actually sets up a virtual block device. */ static void setup_block_file(const char *filename) { - int p[2]; struct device *dev; struct vblk_info *vblk; - void *stack; struct virtio_blk_config conf; - /* This is the pipe the I/O thread will use to tell us I/O is done. */ - pipe(p); - /* The device responds to return from I/O thread. */ - dev = new_device("block", VIRTIO_ID_BLOCK, p[0], handle_io_finish); + dev = new_device("block", VIRTIO_ID_BLOCK); /* The device has one virtqueue, where the Guest places requests. */ - add_virtqueue(dev, VIRTQUEUE_NUM, handle_virtblk_output); + add_virtqueue(dev, VIRTQUEUE_NUM, blk_request); /* Allocate the room for our own bookkeeping */ vblk = dev->priv = malloc(sizeof(*vblk)); @@ -1735,49 +1517,29 @@ static void setup_block_file(const char *filename) set_config(dev, sizeof(conf), &conf); - /* The I/O thread writes to this end of the pipe when done. */ - vblk->done_fd = p[1]; - - /* This is the second pipe, which is how we tell the I/O thread about - * more work. */ - pipe(vblk->workpipe); - - /* Create stack for thread and run it. Since stack grows upwards, we - * point the stack pointer to the end of this region. */ - stack = malloc(32768); - /* SIGCHLD - We dont "wait" for our cloned thread, so prevent it from - * becoming a zombie. */ - if (clone(io_thread, stack + 32768, CLONE_VM | SIGCHLD, dev) == -1) - err(1, "Creating clone"); - - /* We don't need to keep the I/O thread's end of the pipes open. */ - close(vblk->done_fd); - close(vblk->workpipe[0]); - verbose("device %u: virtblock %llu sectors\n", - devices.device_num, le64_to_cpu(conf.capacity)); + ++devices.device_num, le64_to_cpu(conf.capacity)); } +struct rng_info { + int rfd; +}; + /* Our random number generator device reads from /dev/random into the Guest's * input buffers. The usual case is that the Guest doesn't want random numbers * and so has no buffers although /dev/random is still readable, whereas * console is the reverse. * * The same logic applies, however. */ -static bool handle_rng_input(int fd, struct device *dev) +static void rng_input(struct virtqueue *vq) { int len; unsigned int head, in_num, out_num, totlen = 0; - struct iovec iov[dev->vq->vring.num]; + struct rng_info *rng_info = vq->dev->priv; + struct iovec iov[vq->vring.num]; /* First we need a buffer from the Guests's virtqueue. */ - head = get_vq_desc(dev->vq, iov, &out_num, &in_num); - - /* If they're not ready for input, stop listening to this file - * descriptor. We'll start again once they add an input buffer. */ - if (head == dev->vq->vring.num) - return false; - + head = wait_for_vq_desc(vq, iov, &out_num, &in_num); if (out_num) errx(1, "Output buffers in rng?"); @@ -1785,7 +1547,7 @@ static bool handle_rng_input(int fd, struct device *dev) * it reads straight into the Guest's buffer. We loop to make sure we * fill it. */ while (!iov_empty(iov, in_num)) { - len = readv(dev->fd, iov, in_num); + len = readv(rng_info->rfd, iov, in_num); if (len <= 0) err(1, "Read from /dev/random gave %i", len); iov_consume(iov, in_num, len); @@ -1793,25 +1555,23 @@ static bool handle_rng_input(int fd, struct device *dev) } /* Tell the Guest about the new input. */ - add_used_and_trigger(fd, dev->vq, head, totlen); - - /* Everything went OK! */ - return true; + add_used(vq, head, totlen); } /* And this creates a "hardware" random number device for the Guest. */ static void setup_rng(void) { struct device *dev; - int fd; + struct rng_info *rng_info = malloc(sizeof(*rng_info)); - fd = open_or_die("/dev/random", O_RDONLY); + rng_info->rfd = open_or_die("/dev/random", O_RDONLY); /* The device responds to return from I/O thread. */ - dev = new_device("rng", VIRTIO_ID_RNG, fd, handle_rng_input); + dev = new_device("rng", VIRTIO_ID_RNG); + dev->priv = rng_info; /* The device has one virtqueue, where the Guest places inbufs. */ - add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd); + add_virtqueue(dev, VIRTQUEUE_NUM, rng_input); verbose("device %u: rng\n", devices.device_num++); } @@ -1827,17 +1587,18 @@ static void __attribute__((noreturn)) restart_guest(void) for (i = 3; i < FD_SETSIZE; i++) close(i); - /* The exec automatically gets rid of the I/O and Waker threads. */ + /* Reset all the devices (kills all threads). */ + cleanup_devices(); + execv(main_args[0], main_args); err(1, "Could not exec %s", main_args[0]); } /*L:220 Finally we reach the core of the Launcher which runs the Guest, serves * its input and output, and finally, lays it to rest. */ -static void __attribute__((noreturn)) run_guest(int lguest_fd) +static void __attribute__((noreturn)) run_guest(void) { for (;;) { - unsigned long args[] = { LHREQ_BREAK, 0 }; unsigned long notify_addr; int readval; @@ -1848,8 +1609,7 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd) /* One unsigned long means the Guest did HCALL_NOTIFY */ if (readval == sizeof(notify_addr)) { verbose("Notify on address %#lx\n", notify_addr); - handle_output(lguest_fd, notify_addr); - continue; + handle_output(notify_addr); /* ENOENT means the Guest died. Reading tells us why. */ } else if (errno == ENOENT) { char reason[1024] = { 0 }; @@ -1858,19 +1618,9 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd) /* ERESTART means that we need to reboot the guest */ } else if (errno == ERESTART) { restart_guest(); - /* EAGAIN means a signal (timeout). - * Anything else means a bug or incompatible change. */ - } else if (errno != EAGAIN) + /* Anything else means a bug or incompatible change. */ + } else err(1, "Running guest failed"); - - /* Only service input on thread for CPU 0. */ - if (cpu_id != 0) - continue; - - /* Service input, then unset the BREAK to release the Waker. */ - handle_input(lguest_fd); - if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0) - err(1, "Resetting break"); } } /*L:240 @@ -1904,8 +1654,8 @@ int main(int argc, char *argv[]) /* Memory, top-level pagetable, code startpoint and size of the * (optional) initrd. */ unsigned long mem = 0, start, initrd_size = 0; - /* Two temporaries and the /dev/lguest file descriptor. */ - int i, c, lguest_fd; + /* Two temporaries. */ + int i, c; /* The boot information for the Guest. */ struct boot_params *boot; /* If they specify an initrd file to load. */ @@ -1913,18 +1663,10 @@ int main(int argc, char *argv[]) /* Save the args: we "reboot" by execing ourselves again. */ main_args = argv; - /* We don't "wait" for the children, so prevent them from becoming - * zombies. */ - signal(SIGCHLD, SIG_IGN); - /* First we initialize the device list. Since console and network - * device receive input from a file descriptor, we keep an fdset - * (infds) and the maximum fd number (max_infd) with the head of the - * list. We also keep a pointer to the last device. Finally, we keep - * the next interrupt number to use for devices (1: remember that 0 is - * used by the timer). */ - FD_ZERO(&devices.infds); - devices.max_infd = -1; + /* First we initialize the device list. We keep a pointer to the last + * device, and the next interrupt number to use for devices (1: + * remember that 0 is used by the timer). */ devices.lastdev = NULL; devices.next_irq = 1; @@ -1982,9 +1724,6 @@ int main(int argc, char *argv[]) /* We always have a console device */ setup_console(); - /* We can timeout waiting for Guest network transmit. */ - setup_timeout(); - /* Now we load the kernel */ start = load_kernel(open_or_die(argv[optind+1], O_RDONLY)); @@ -2023,15 +1762,16 @@ int main(int argc, char *argv[]) /* We tell the kernel to initialize the Guest: this returns the open * /dev/lguest file descriptor. */ - lguest_fd = tell_kernel(start); + tell_kernel(start); + + /* Ensure that we terminate if a child dies. */ + signal(SIGCHLD, kill_launcher); - /* We clone off a thread, which wakes the Launcher whenever one of the - * input file descriptors needs attention. We call this the Waker, and - * we'll cover it in a moment. */ - setup_waker(lguest_fd); + /* If we exit via err(), this kills all the threads, restores tty. */ + atexit(cleanup_devices); /* Finally, run the Guest. This doesn't return. */ - run_guest(lguest_fd); + run_guest(); } /*:*/ diff --git a/trunk/Documentation/lguest/lguest.txt b/trunk/Documentation/lguest/lguest.txt index 28c747362f95..efb3a6a045a2 100644 --- a/trunk/Documentation/lguest/lguest.txt +++ b/trunk/Documentation/lguest/lguest.txt @@ -37,7 +37,6 @@ Running Lguest: "Paravirtualized guest support" = Y "Lguest guest support" = Y "High Memory Support" = off/4GB - "PAE (Physical Address Extension) Support" = N "Alignment value to which kernel should be aligned" = 0x100000 (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and CONFIG_PHYSICAL_ALIGN=0x100000) diff --git a/trunk/Documentation/memory-barriers.txt b/trunk/Documentation/memory-barriers.txt index f5b7127f54ac..7f5809eddee6 100644 --- a/trunk/Documentation/memory-barriers.txt +++ b/trunk/Documentation/memory-barriers.txt @@ -31,6 +31,7 @@ Contents: - Locking functions. - Interrupt disabling functions. + - Sleep and wake-up functions. - Miscellaneous functions. (*) Inter-CPU locking barrier effects. @@ -1217,6 +1218,132 @@ barriers are required in such a situation, they must be provided from some other means. +SLEEP AND WAKE-UP FUNCTIONS +--------------------------- + +Sleeping and waking on an event flagged in global data can be viewed as an +interaction between two pieces of data: the task state of the task waiting for +the event and the global data used to indicate the event. To make sure that +these appear to happen in the right order, the primitives to begin the process +of going to sleep, and the primitives to initiate a wake up imply certain +barriers. + +Firstly, the sleeper normally follows something like this sequence of events: + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (event_indicated) + break; + schedule(); + } + +A general memory barrier is interpolated automatically by set_current_state() +after it has altered the task state: + + CPU 1 + =============================== + set_current_state(); + set_mb(); + STORE current->state + + LOAD event_indicated + +set_current_state() may be wrapped by: + + prepare_to_wait(); + prepare_to_wait_exclusive(); + +which therefore also imply a general memory barrier after setting the state. +The whole sequence above is available in various canned forms, all of which +interpolate the memory barrier in the right place: + + wait_event(); + wait_event_interruptible(); + wait_event_interruptible_exclusive(); + wait_event_interruptible_timeout(); + wait_event_killable(); + wait_event_timeout(); + wait_on_bit(); + wait_on_bit_lock(); + + +Secondly, code that performs a wake up normally follows something like this: + + event_indicated = 1; + wake_up(&event_wait_queue); + +or: + + event_indicated = 1; + wake_up_process(event_daemon); + +A write memory barrier is implied by wake_up() and co. if and only if they wake +something up. The barrier occurs before the task state is cleared, and so sits +between the STORE to indicate the event and the STORE to set TASK_RUNNING: + + CPU 1 CPU 2 + =============================== =============================== + set_current_state(); STORE event_indicated + set_mb(); wake_up(); + STORE current->state + STORE current->state + LOAD event_indicated + +The available waker functions include: + + complete(); + wake_up(); + wake_up_all(); + wake_up_bit(); + wake_up_interruptible(); + wake_up_interruptible_all(); + wake_up_interruptible_nr(); + wake_up_interruptible_poll(); + wake_up_interruptible_sync(); + wake_up_interruptible_sync_poll(); + wake_up_locked(); + wake_up_locked_poll(); + wake_up_nr(); + wake_up_poll(); + wake_up_process(); + + +[!] Note that the memory barriers implied by the sleeper and the waker do _not_ +order multiple stores before the wake-up with respect to loads of those stored +values after the sleeper has called set_current_state(). For instance, if the +sleeper does: + + set_current_state(TASK_INTERRUPTIBLE); + if (event_indicated) + break; + __set_current_state(TASK_RUNNING); + do_something(my_data); + +and the waker does: + + my_data = value; + event_indicated = 1; + wake_up(&event_wait_queue); + +there's no guarantee that the change to event_indicated will be perceived by +the sleeper as coming after the change to my_data. In such a circumstance, the +code on both sides must interpolate its own memory barriers between the +separate data accesses. Thus the above sleeper ought to do: + + set_current_state(TASK_INTERRUPTIBLE); + if (event_indicated) { + smp_rmb(); + do_something(my_data); + } + +and the waker should do: + + my_data = value; + smp_wmb(); + event_indicated = 1; + wake_up(&event_wait_queue); + + MISCELLANEOUS FUNCTIONS ----------------------- @@ -1366,7 +1493,7 @@ WHERE ARE MEMORY BARRIERS NEEDED? Under normal operation, memory operation reordering is generally not going to be a problem as a single-threaded linear piece of code will still appear to -work correctly, even if it's in an SMP kernel. There are, however, three +work correctly, even if it's in an SMP kernel. There are, however, four circumstances in which reordering definitely _could_ be a problem: (*) Interprocessor interaction. diff --git a/trunk/Documentation/power/devices.txt b/trunk/Documentation/power/devices.txt index 421e7d00ffd0..c9abbd86bc18 100644 --- a/trunk/Documentation/power/devices.txt +++ b/trunk/Documentation/power/devices.txt @@ -75,9 +75,6 @@ may need to apply in domain-specific ways to their devices: struct bus_type { ... int (*suspend)(struct device *dev, pm_message_t state); - int (*suspend_late)(struct device *dev, pm_message_t state); - - int (*resume_early)(struct device *dev); int (*resume)(struct device *dev); }; @@ -226,20 +223,7 @@ The phases are seen by driver notifications issued in this order: This call should handle parts of device suspend logic that require sleeping. It probably does work to quiesce the device which hasn't - been abstracted into class.suspend() or bus.suspend_late(). - - 3 bus.suspend_late(dev, message) is called with IRQs disabled, and - with only one CPU active. Until the bus.resume_early() phase - completes (see later), IRQs are not enabled again. This method - won't be exposed by all busses; for message based busses like USB, - I2C, or SPI, device interactions normally require IRQs. This bus - call may be morphed into a driver call with bus-specific parameters. - - This call might save low level hardware state that might otherwise - be lost in the upcoming low power state, and actually put the - device into a low power state ... so that in some cases the device - may stay partly usable until this late. This "late" call may also - help when coping with hardware that behaves badly. + been abstracted into class.suspend(). The pm_message_t parameter is currently used to refine those semantics (described later). @@ -351,19 +335,11 @@ devices processing each phase's calls before the next phase begins. The phases are seen by driver notifications issued in this order: - 1 bus.resume_early(dev) is called with IRQs disabled, and with - only one CPU active. As with bus.suspend_late(), this method - won't be supported on busses that require IRQs in order to - interact with devices. - - This reverses the effects of bus.suspend_late(). - - 2 bus.resume(dev) is called next. This may be morphed into a device - driver call with bus-specific parameters; implementations may sleep. - - This reverses the effects of bus.suspend(). + 1 bus.resume(dev) reverses the effects of bus.suspend(). This may + be morphed into a device driver call with bus-specific parameters; + implementations may sleep. - 3 class.resume(dev) is called for devices associated with a class + 2 class.resume(dev) is called for devices associated with a class that has such a method. Implementations may sleep. This reverses the effects of class.suspend(), and would usually diff --git a/trunk/Documentation/scheduler/sched-rt-group.txt b/trunk/Documentation/scheduler/sched-rt-group.txt index 5ba4d3fc625a..1df7f9cdab05 100644 --- a/trunk/Documentation/scheduler/sched-rt-group.txt +++ b/trunk/Documentation/scheduler/sched-rt-group.txt @@ -4,6 +4,7 @@ CONTENTS ======== +0. WARNING 1. Overview 1.1 The problem 1.2 The solution @@ -14,6 +15,23 @@ CONTENTS 3. Future plans +0. WARNING +========== + + Fiddling with these settings can result in an unstable system, the knobs are + root only and assumes root knows what he is doing. + +Most notable: + + * very small values in sched_rt_period_us can result in an unstable + system when the period is smaller than either the available hrtimer + resolution, or the time it takes to handle the budget refresh itself. + + * very small values in sched_rt_runtime_us can result in an unstable + system when the runtime is so small the system has difficulty making + forward progress (NOTE: the migration thread and kstopmachine both + are real-time processes). + 1. Overview =========== @@ -169,7 +187,7 @@ get their allocated time. Implementing SCHED_EDF might take a while to complete. Priority Inheritance is the biggest challenge as the current linux PI infrastructure is geared towards -the limited static priority levels 0-139. With deadline scheduling you need to +the limited static priority levels 0-99. With deadline scheduling you need to do deadline inheritance (since priority is inversely proportional to the deadline delta (deadline - now). diff --git a/trunk/Documentation/sound/alsa/ALSA-Configuration.txt b/trunk/Documentation/sound/alsa/ALSA-Configuration.txt index 012858d2b119..5c08d96f407c 100644 --- a/trunk/Documentation/sound/alsa/ALSA-Configuration.txt +++ b/trunk/Documentation/sound/alsa/ALSA-Configuration.txt @@ -460,6 +460,25 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. The power-management is supported. + Module snd-ctxfi + ---------------- + + Module for Creative Sound Blaster X-Fi boards (20k1 / 20k2 chips) + * Creative Sound Blaster X-Fi Titanium Fatal1ty Champion Series + * Creative Sound Blaster X-Fi Titanium Fatal1ty Professional Series + * Creative Sound Blaster X-Fi Titanium Professional Audio + * Creative Sound Blaster X-Fi Titanium + * Creative Sound Blaster X-Fi Elite Pro + * Creative Sound Blaster X-Fi Platinum + * Creative Sound Blaster X-Fi Fatal1ty + * Creative Sound Blaster X-Fi XtremeGamer + * Creative Sound Blaster X-Fi XtremeMusic + + reference_rate - reference sample rate, 44100 or 48000 (default) + multiple - multiple to ref. sample rate, 1 or 2 (default) + + This module supports multiple cards. + Module snd-darla20 ------------------ @@ -925,6 +944,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. * Onkyo SE-90PCI * Onkyo SE-200PCI * ESI Juli@ + * ESI Maya44 * Hercules Fortissimo IV * EGO-SYS WaveTerminal 192M @@ -933,7 +953,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. prodigy71xt, prodigy71hifi, prodigyhd2, prodigy192, juli, aureon51, aureon71, universe, ap192, k8x800, phase22, phase28, ms300, av710, se200pci, se90pci, - fortissimo4, sn25p, WT192M + fortissimo4, sn25p, WT192M, maya44 This module supports multiple cards and autoprobe. @@ -1093,6 +1113,13 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. This module supports multiple cards. The driver requires the firmware loader support on kernel. + Module snd-lx6464es + ------------------- + + Module for Digigram LX6464ES boards + + This module supports multiple cards. + Module snd-maestro3 ------------------- @@ -1543,13 +1570,15 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. Module snd-sc6000 ----------------- - Module for Gallant SC-6000 soundcard. + Module for Gallant SC-6000 soundcard and later models: SC-6600 + and SC-7000. port - Port # (0x220 or 0x240) mss_port - MSS Port # (0x530 or 0xe80) irq - IRQ # (5,7,9,10,11) mpu_irq - MPU-401 IRQ # (5,7,9,10) ,0 - no MPU-401 irq dma - DMA # (1,3,0) + joystick - Enable gameport - 0 = disable (default), 1 = enable This module supports multiple cards. @@ -1859,7 +1888,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. ------------------- Module for sound cards based on the Asus AV100/AV200 chips, - i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), and Essence STX. + i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), Essence ST + (Deluxe) and Essence STX. This module supports autoprobe and multiple cards. diff --git a/trunk/Documentation/sound/alsa/HD-Audio-Models.txt b/trunk/Documentation/sound/alsa/HD-Audio-Models.txt index 322869fc8a9e..de8e10a94103 100644 --- a/trunk/Documentation/sound/alsa/HD-Audio-Models.txt +++ b/trunk/Documentation/sound/alsa/HD-Audio-Models.txt @@ -36,6 +36,7 @@ ALC260 acer Acer TravelMate will Will laptops (PB V7900) replacer Replacer 672V + favorit100 Maxdata Favorit 100XS basic fixed pin assignment (old default model) test for testing/debugging purpose, almost all controls can adjusted. Appearing only when compiled with @@ -85,10 +86,11 @@ ALC269 eeepc-p703 ASUS Eeepc P703 P900A eeepc-p901 ASUS Eeepc P901 S101 fujitsu FSC Amilo + lifebook Fujitsu Lifebook S6420 auto auto-config reading BIOS (default) -ALC662/663 -========== +ALC662/663/272 +============== 3stack-dig 3-stack (2-channel) with SPDIF 3stack-6ch 3-stack (6-channel) 3stack-6ch-dig 3-stack (6-channel) with SPDIF @@ -107,6 +109,9 @@ ALC662/663 asus-mode4 ASUS asus-mode5 ASUS asus-mode6 ASUS + dell Dell with ALC272 + dell-zm1 Dell ZM1 with ALC272 + samsung-nc10 Samsung NC10 mini notebook auto auto-config reading BIOS (default) ALC882/885 @@ -118,6 +123,7 @@ ALC882/885 asus-a7j ASUS A7J asus-a7m ASUS A7M macpro MacPro support + mb5 Macbook 5,1 mbp3 Macbook Pro rev3 imac24 iMac 24'' with jack detection w2jc ASUS W2JC @@ -133,10 +139,12 @@ ALC883/888 acer Acer laptops (Travelmate 3012WTMi, Aspire 5600, etc) acer-aspire Acer Aspire 9810 acer-aspire-4930g Acer Aspire 4930G + acer-aspire-8930g Acer Aspire 8930G medion Medion Laptops medion-md2 Medion MD2 targa-dig Targa/MSI - targa-2ch-dig Targs/MSI with 2-channel + targa-2ch-dig Targa/MSI with 2-channel + targa-8ch-dig Targa/MSI with 8-channel (MSI GX620) laptop-eapd 3-jack with SPDIF I/O and EAPD (Clevo M540JE, M550JE) lenovo-101e Lenovo 101E lenovo-nb0763 Lenovo NB0763 @@ -150,6 +158,9 @@ ALC883/888 fujitsu-pi2515 Fujitsu AMILO Pi2515 fujitsu-xa3530 Fujitsu AMILO XA3530 3stack-6ch-intel Intel DG33* boards + asus-p5q ASUS P5Q-EM boards + mb31 MacBook 3,1 + sony-vaio-tt Sony VAIO TT auto auto-config reading BIOS (default) ALC861/660 @@ -348,6 +359,7 @@ STAC92HD71B* hp-m4 HP mini 1000 hp-dv5 HP dv series hp-hdx HP HDX series + hp-dv4-1222nr HP dv4-1222nr (with LED support) auto BIOS setup (default) STAC92HD73* diff --git a/trunk/Documentation/sound/alsa/Procfile.txt b/trunk/Documentation/sound/alsa/Procfile.txt index cfac20cf9e33..381908d8ca42 100644 --- a/trunk/Documentation/sound/alsa/Procfile.txt +++ b/trunk/Documentation/sound/alsa/Procfile.txt @@ -88,26 +88,34 @@ card*/pcm*/info substreams, etc. card*/pcm*/xrun_debug - This file appears when CONFIG_SND_DEBUG=y. - This shows the status of xrun (= buffer overrun/xrun) debug of - ALSA PCM middle layer, as an integer from 0 to 2. The value - can be changed by writing to this file, such as - - # cat 2 > /proc/asound/card0/pcm0p/xrun_debug - - When this value is greater than 0, the driver will show the - messages to kernel log when an xrun is detected. The debug - message is shown also when the invalid H/W pointer is detected - at the update of periods (usually called from the interrupt + This file appears when CONFIG_SND_DEBUG=y and + CONFIG_PCM_XRUN_DEBUG=y. + This shows the status of xrun (= buffer overrun/xrun) and + invalid PCM position debug/check of ALSA PCM middle layer. + It takes an integer value, can be changed by writing to this + file, such as + + # cat 5 > /proc/asound/card0/pcm0p/xrun_debug + + The value consists of the following bit flags: + bit 0 = Enable XRUN/jiffies debug messages + bit 1 = Show stack trace at XRUN / jiffies check + bit 2 = Enable additional jiffies check + + When the bit 0 is set, the driver will show the messages to + kernel log when an xrun is detected. The debug message is + shown also when the invalid H/W pointer is detected at the + update of periods (usually called from the interrupt handler). - When this value is greater than 1, the driver will show the - stack trace additionally. This may help the debugging. + When the bit 1 is set, the driver will show the stack trace + additionally. This may help the debugging. - Since 2.6.30, this option also enables the hwptr check using + Since 2.6.30, this option can enable the hwptr check using jiffies. This detects spontaneous invalid pointer callback values, but can be lead to too much corrections for a (mostly buggy) hardware that doesn't give smooth pointer updates. + This feature is enabled via the bit 2. card*/pcm*/sub*/info The general information of this PCM sub-stream. diff --git a/trunk/Documentation/sound/alsa/README.maya44 b/trunk/Documentation/sound/alsa/README.maya44 new file mode 100644 index 000000000000..0e41576fa13e --- /dev/null +++ b/trunk/Documentation/sound/alsa/README.maya44 @@ -0,0 +1,163 @@ +NOTE: The following is the original document of Rainer's patch that the +current maya44 code based on. Some contents might be obsoleted, but I +keep here as reference -- tiwai + +---------------------------------------------------------------- + +STATE OF DEVELOPMENT: + +This driver is being developed on the initiative of Piotr Makowski (oponek@gmail.com) and financed by Lars Bergmann. +Development is carried out by Rainer Zimmermann (mail@lightshed.de). + +ESI provided a sample Maya44 card for the development work. + +However, unfortunately it has turned out difficult to get detailed programming information, so I (Rainer Zimmermann) had to find out some card-specific information by experiment and conjecture. Some information (in particular, several GPIO bits) is still missing. + +This is the first testing version of the Maya44 driver released to the alsa-devel mailing list (Feb 5, 2008). + + +The following functions work, as tested by Rainer Zimmermann and Piotr Makowski: + +- playback and capture at all sampling rates +- input/output level +- crossmixing +- line/mic switch +- phantom power switch +- analogue monitor a.k.a bypass + + +The following functions *should* work, but are not fully tested: + +- Channel 3+4 analogue - S/PDIF input switching +- S/PDIF output +- all inputs/outputs on the M/IO/DIO extension card +- internal/external clock selection + + +*In particular, we would appreciate testing of these functions by anyone who has access to an M/IO/DIO extension card.* + + +Things that do not seem to work: + +- The level meters ("multi track") in 'alsamixer' do not seem to react to signals in (if this is a bug, it would probably be in the existing ICE1724 code). + +- Ardour 2.1 seems to work only via JACK, not using ALSA directly or via OSS. This still needs to be tracked down. + + +DRIVER DETAILS: + +the following files were added: + +pci/ice1724/maya44.c - Maya44 specific code +pci/ice1724/maya44.h +pci/ice1724/ice1724.patch +pci/ice1724/ice1724.h.patch - PROPOSED patch to ice1724.h (see SAMPLING RATES) +i2c/other/wm8776.c - low-level access routines for Wolfson WM8776 codecs +include/wm8776.h + + +Note that the wm8776.c code is meant to be card-independent and does not actually register the codec with the ALSA infrastructure. +This is done in maya44.c, mainly because some of the WM8776 controls are used in Maya44-specific ways, and should be named appropriately. + + +the following files were created in pci/ice1724, simply #including the corresponding file from the alsa-kernel tree: + +wtm.h +vt1720_mobo.h +revo.h +prodigy192.h +pontis.h +phase.h +maya44.h +juli.h +aureon.h +amp.h +envy24ht.h +se.h +prodigy_hifi.h + + +*I hope this is the correct way to do things.* + + +SAMPLING RATES: + +The Maya44 card (or more exactly, the Wolfson WM8776 codecs) allow a maximum sampling rate of 192 kHz for playback and 92 kHz for capture. + +As the ICE1724 chip only allows one global sampling rate, this is handled as follows: + +* setting the sampling rate on any open PCM device on the maya44 card will always set the *global* sampling rate for all playback and capture channels. + +* In the current state of the driver, setting rates of up to 192 kHz is permitted even for capture devices. + +*AVOID CAPTURING AT RATES ABOVE 96kHz*, even though it may appear to work. The codec cannot actually capture at such rates, meaning poor quality. + + +I propose some additional code for limiting the sampling rate when setting on a capture pcm device. However because of the global sampling rate, this logic would be somewhat problematic. + +The proposed code (currently deactivated) is in ice1712.h.patch, ice1724.c and maya44.c (in pci/ice1712). + + +SOUND DEVICES: + +PCM devices correspond to inputs/outputs as follows (assuming Maya44 is card #0): + +hw:0,0 input - stereo, analog input 1+2 +hw:0,0 output - stereo, analog output 1+2 +hw:0,1 input - stereo, analog input 3+4 OR S/PDIF input +hw:0,1 output - stereo, analog output 3+4 (and SPDIF out) + + +NAMING OF MIXER CONTROLS: + +(for more information about the signal flow, please refer to the block diagram on p.24 of the ESI Maya44 manual, or in the ESI windows software). + + +PCM: (digital) output level for channel 1+2 +PCM 1: same for channel 3+4 + +Mic Phantom+48V: switch for +48V phantom power for electrostatic microphones on input 1/2. + Make sure this is not turned on while any other source is connected to input 1/2. + It might damage the source and/or the maya44 card. + +Mic/Line input: if switch is is on, input jack 1/2 is microphone input (mono), otherwise line input (stereo). + +Bypass: analogue bypass from ADC input to output for channel 1+2. Same as "Monitor" in the windows driver. +Bypass 1: same for channel 3+4. + +Crossmix: cross-mixer from channels 1+2 to channels 3+4 +Crossmix 1: cross-mixer from channels 3+4 to channels 1+2 + +IEC958 Output: switch for S/PDIF output. + This is not supported by the ESI windows driver. + S/PDIF should output the same signal as channel 3+4. [untested!] + + +Digitial output selectors: + + These switches allow a direct digital routing from the ADCs to the DACs. + Each switch determines where the digital input data to one of the DACs comes from. + They are not supported by the ESI windows driver. + For normal operation, they should all be set to "PCM out". + +H/W: Output source channel 1 +H/W 1: Output source channel 2 +H/W 2: Output source channel 3 +H/W 3: Output source channel 4 + +H/W 4 ... H/W 9: unknown function, left in to enable testing. + Possibly some of these control S/PDIF output(s). + If these turn out to be unused, they will go away in later driver versions. + +Selectable values for each of the digital output selectors are: + "PCM out" -> DAC output of the corresponding channel (default setting) + "Input 1"... + "Input 4" -> direct routing from ADC output of the selected input channel + + +-------- + +Feb 14, 2008 +Rainer Zimmermann +mail@lightshed.de + diff --git a/trunk/Documentation/sound/alsa/soc/dapm.txt b/trunk/Documentation/sound/alsa/soc/dapm.txt index 9e6763264a2e..9ac842be9b4f 100644 --- a/trunk/Documentation/sound/alsa/soc/dapm.txt +++ b/trunk/Documentation/sound/alsa/soc/dapm.txt @@ -62,6 +62,7 @@ Audio DAPM widgets fall into a number of types:- o Mic - Mic (and optional Jack) o Line - Line Input/Output (and optional Jack) o Speaker - Speaker + o Supply - Power or clock supply widget used by other widgets. o Pre - Special PRE widget (exec before all others) o Post - Special POST widget (exec after all others) diff --git a/trunk/Documentation/sysctl/kernel.txt b/trunk/Documentation/sysctl/kernel.txt index f11ca7979fa6..322a00bb99d9 100644 --- a/trunk/Documentation/sysctl/kernel.txt +++ b/trunk/Documentation/sysctl/kernel.txt @@ -32,6 +32,7 @@ show up in /proc/sys/kernel: - kstack_depth_to_print [ X86 only ] - l2cr [ PPC only ] - modprobe ==> Documentation/debugging-modules.txt +- modules_disabled - msgmax - msgmnb - msgmni @@ -184,6 +185,16 @@ kernel stack. ============================================================== +modules_disabled: + +A toggle value indicating if modules are allowed to be loaded +in an otherwise modular kernel. This toggle defaults to off +(0), but can be set true (1). Once true, modules can be +neither loaded nor unloaded, and the toggle cannot be set back +to false. + +============================================================== + osrelease, ostype & version: # cat osrelease diff --git a/trunk/Documentation/trace/events.txt b/trunk/Documentation/trace/events.txt new file mode 100644 index 000000000000..f157d7594ea7 --- /dev/null +++ b/trunk/Documentation/trace/events.txt @@ -0,0 +1,90 @@ + Event Tracing + + Documentation written by Theodore Ts'o + Updated by Li Zefan + +1. Introduction +=============== + +Tracepoints (see Documentation/trace/tracepoints.txt) can be used +without creating custom kernel modules to register probe functions +using the event tracing infrastructure. + +Not all tracepoints can be traced using the event tracing system; +the kernel developer must provide code snippets which define how the +tracing information is saved into the tracing buffer, and how the +tracing information should be printed. + +2. Using Event Tracing +====================== + +2.1 Via the 'set_event' interface +--------------------------------- + +The events which are available for tracing can be found in the file +/debug/tracing/available_events. + +To enable a particular event, such as 'sched_wakeup', simply echo it +to /debug/tracing/set_event. For example: + + # echo sched_wakeup >> /debug/tracing/set_event + +[ Note: '>>' is necessary, otherwise it will firstly disable + all the events. ] + +To disable an event, echo the event name to the set_event file prefixed +with an exclamation point: + + # echo '!sched_wakeup' >> /debug/tracing/set_event + +To disable all events, echo an empty line to the set_event file: + + # echo > /debug/tracing/set_event + +To enable all events, echo '*:*' or '*:' to the set_event file: + + # echo *:* > /debug/tracing/set_event + +The events are organized into subsystems, such as ext4, irq, sched, +etc., and a full event name looks like this: :. The +subsystem name is optional, but it is displayed in the available_events +file. All of the events in a subsystem can be specified via the syntax +":*"; for example, to enable all irq events, you can use the +command: + + # echo 'irq:*' > /debug/tracing/set_event + +2.2 Via the 'enable' toggle +--------------------------- + +The events available are also listed in /debug/tracing/events/ hierarchy +of directories. + +To enable event 'sched_wakeup': + + # echo 1 > /debug/tracing/events/sched/sched_wakeup/enable + +To disable it: + + # echo 0 > /debug/tracing/events/sched/sched_wakeup/enable + +To enable all events in sched subsystem: + + # echo 1 > /debug/tracing/events/sched/enable + +To eanble all events: + + # echo 1 > /debug/tracing/events/enable + +When reading one of these enable files, there are four results: + + 0 - all events this file affects are disabled + 1 - all events this file affects are enabled + X - there is a mixture of events enabled and disabled + ? - this file does not affect any event + +3. Defining an event-enabled tracepoint +======================================= + +See The example provided in samples/trace_events + diff --git a/trunk/Documentation/trace/ftrace.txt b/trunk/Documentation/trace/ftrace.txt index fd9a3e693813..2a82d8602944 100644 --- a/trunk/Documentation/trace/ftrace.txt +++ b/trunk/Documentation/trace/ftrace.txt @@ -179,7 +179,7 @@ Here is the list of current tracers that may be configured. Function call tracer to trace all kernel functions. - "function_graph_tracer" + "function_graph" Similar to the function tracer except that the function tracer probes the functions on their entry @@ -518,9 +518,18 @@ priority with zero (0) being the highest priority and the nice values starting at 100 (nice -20). Below is a quick chart to map the kernel priority to user land priorities. - Kernel priority: 0 to 99 ==> user RT priority 99 to 0 - Kernel priority: 100 to 139 ==> user nice -20 to 19 - Kernel priority: 140 ==> idle task priority + Kernel Space User Space + =============================================================== + 0(high) to 98(low) user RT priority 99(high) to 1(low) + with SCHED_RR or SCHED_FIFO + --------------------------------------------------------------- + 99 sched_priority is not used in scheduling + decisions(it must be specified as 0) + --------------------------------------------------------------- + 100(high) to 139(low) user nice -20(high) to 19(low) + --------------------------------------------------------------- + 140 idle task priority + --------------------------------------------------------------- The task states are: diff --git a/trunk/Documentation/trace/power.txt b/trunk/Documentation/trace/power.txt new file mode 100644 index 000000000000..cd805e16dc27 --- /dev/null +++ b/trunk/Documentation/trace/power.txt @@ -0,0 +1,17 @@ +The power tracer collects detailed information about C-state and P-state +transitions, instead of just looking at the high-level "average" +information. + +There is a helper script found in scrips/tracing/power.pl in the kernel +sources which can be used to parse this information and create a +Scalable Vector Graphics (SVG) picture from the trace data. + +To use this tracer: + + echo 0 > /sys/kernel/debug/tracing/tracing_enabled + echo power > /sys/kernel/debug/tracing/current_tracer + echo 1 > /sys/kernel/debug/tracing/tracing_enabled + sleep 1 + echo 0 > /sys/kernel/debug/tracing/tracing_enabled + cat /sys/kernel/debug/tracing/trace | \ + perl scripts/tracing/power.pl > out.sv diff --git a/trunk/Documentation/x86/boot.txt b/trunk/Documentation/x86/boot.txt index e0203662f9e9..8da3a795083f 100644 --- a/trunk/Documentation/x86/boot.txt +++ b/trunk/Documentation/x86/boot.txt @@ -50,6 +50,10 @@ Protocol 2.08: (Kernel 2.6.26) Added crc32 checksum and ELF format Protocol 2.09: (Kernel 2.6.26) Added a field of 64-bit physical pointer to single linked list of struct setup_data. +Protocol 2.10: (Kernel 2.6.31) Added a protocol for relaxed alignment + beyond the kernel_alignment added, new init_size and + pref_address fields. Added extended boot loader IDs. + **** MEMORY LAYOUT The traditional memory map for the kernel loader, used for Image or @@ -168,12 +172,13 @@ Offset Proto Name Meaning 021C/4 2.00+ ramdisk_size initrd size (set by boot loader) 0220/4 2.00+ bootsect_kludge DO NOT USE - for bootsect.S use only 0224/2 2.01+ heap_end_ptr Free memory after setup end -0226/2 N/A pad1 Unused +0226/1 2.02+(3 ext_loader_ver Extended boot loader version +0227/1 2.02+(3 ext_loader_type Extended boot loader ID 0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line 022C/4 2.03+ ramdisk_max Highest legal initrd address 0230/4 2.05+ kernel_alignment Physical addr alignment required for kernel 0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not -0235/1 N/A pad2 Unused +0235/1 2.10+ min_alignment Minimum alignment, as a power of two 0236/2 N/A pad3 Unused 0238/4 2.06+ cmdline_size Maximum size of the kernel command line 023C/4 2.07+ hardware_subarch Hardware subarchitecture @@ -182,6 +187,8 @@ Offset Proto Name Meaning 024C/4 2.08+ payload_length Length of kernel payload 0250/8 2.09+ setup_data 64-bit physical pointer to linked list of struct setup_data +0258/8 2.10+ pref_address Preferred loading address +0260/4 2.10+ init_size Linear memory required during initialization (1) For backwards compatibility, if the setup_sects field contains 0, the real value is 4. @@ -190,6 +197,8 @@ Offset Proto Name Meaning field are unusable, which means the size of a bzImage kernel cannot be determined. +(3) Ignored, but safe to set, for boot protocols 2.02-2.09. + If the "HdrS" (0x53726448) magic number is not found at offset 0x202, the boot protocol version is "old". Loading an old kernel, the following parameters should be assumed: @@ -343,18 +352,32 @@ Protocol: 2.00+ 0xTV here, where T is an identifier for the boot loader and V is a version number. Otherwise, enter 0xFF here. + For boot loader IDs above T = 0xD, write T = 0xE to this field and + write the extended ID minus 0x10 to the ext_loader_type field. + Similarly, the ext_loader_ver field can be used to provide more than + four bits for the bootloader version. + + For example, for T = 0x15, V = 0x234, write: + + type_of_loader <- 0xE4 + ext_loader_type <- 0x05 + ext_loader_ver <- 0x23 + Assigned boot loader ids: 0 LILO (0x00 reserved for pre-2.00 bootloader) 1 Loadlin 2 bootsect-loader (0x20, all other values reserved) - 3 SYSLINUX - 4 EtherBoot + 3 Syslinux + 4 Etherboot/gPXE 5 ELILO 7 GRUB - 8 U-BOOT + 8 U-Boot 9 Xen A Gujin B Qemu + C Arcturus Networks uCbootloader + E Extended (see ext_loader_type) + F Special (0xFF = undefined) Please contact if you need a bootloader ID value assigned. @@ -453,6 +476,35 @@ Protocol: 2.01+ Set this field to the offset (from the beginning of the real-mode code) of the end of the setup stack/heap, minus 0x0200. +Field name: ext_loader_ver +Type: write (optional) +Offset/size: 0x226/1 +Protocol: 2.02+ + + This field is used as an extension of the version number in the + type_of_loader field. The total version number is considered to be + (type_of_loader & 0x0f) + (ext_loader_ver << 4). + + The use of this field is boot loader specific. If not written, it + is zero. + + Kernels prior to 2.6.31 did not recognize this field, but it is safe + to write for protocol version 2.02 or higher. + +Field name: ext_loader_type +Type: write (obligatory if (type_of_loader & 0xf0) == 0xe0) +Offset/size: 0x227/1 +Protocol: 2.02+ + + This field is used as an extension of the type number in + type_of_loader field. If the type in type_of_loader is 0xE, then + the actual type is (ext_loader_type + 0x10). + + This field is ignored if the type in type_of_loader is not 0xE. + + Kernels prior to 2.6.31 did not recognize this field, but it is safe + to write for protocol version 2.02 or higher. + Field name: cmd_line_ptr Type: write (obligatory) Offset/size: 0x228/4 @@ -482,11 +534,19 @@ Protocol: 2.03+ 0x37FFFFFF, you can start your ramdisk at 0x37FE0000.) Field name: kernel_alignment -Type: read (reloc) +Type: read/modify (reloc) Offset/size: 0x230/4 -Protocol: 2.05+ +Protocol: 2.05+ (read), 2.10+ (modify) + + Alignment unit required by the kernel (if relocatable_kernel is + true.) A relocatable kernel that is loaded at an alignment + incompatible with the value in this field will be realigned during + kernel initialization. - Alignment unit required by the kernel (if relocatable_kernel is true.) + Starting with protocol version 2.10, this reflects the kernel + alignment preferred for optimal performance; it is possible for the + loader to modify this field to permit a lesser alignment. See the + min_alignment and pref_address field below. Field name: relocatable_kernel Type: read (reloc) @@ -498,6 +558,22 @@ Protocol: 2.05+ After loading, the boot loader must set the code32_start field to point to the loaded code, or to a boot loader hook. +Field name: min_alignment +Type: read (reloc) +Offset/size: 0x235/1 +Protocol: 2.10+ + + This field, if nonzero, indicates as a power of two the minimum + alignment required, as opposed to preferred, by the kernel to boot. + If a boot loader makes use of this field, it should update the + kernel_alignment field with the alignment unit desired; typically: + + kernel_alignment = 1 << min_alignment + + There may be a considerable performance cost with an excessively + misaligned kernel. Therefore, a loader should typically try each + power-of-two alignment from kernel_alignment down to this alignment. + Field name: cmdline_size Type: read Offset/size: 0x238/4 @@ -582,6 +658,36 @@ Protocol: 2.09+ sure to consider the case where the linked list already contains entries. +Field name: pref_address +Type: read (reloc) +Offset/size: 0x258/8 +Protocol: 2.10+ + + This field, if nonzero, represents a preferred load address for the + kernel. A relocating bootloader should attempt to load at this + address if possible. + + A non-relocatable kernel will unconditionally move itself and to run + at this address. + +Field name: init_size +Type: read +Offset/size: 0x25c/4 + + This field indicates the amount of linear contiguous memory starting + at the kernel runtime start address that the kernel needs before it + is capable of examining its memory map. This is not the same thing + as the total amount of memory the kernel needs to boot, but it can + be used by a relocating boot loader to help select a safe load + address for the kernel. + + The kernel runtime start address is determined by the following algorithm: + + if (relocatable_kernel) + runtime_start = align_up(load_address, kernel_alignment) + else + runtime_start = pref_address + **** THE IMAGE CHECKSUM diff --git a/trunk/Documentation/x86/x86_64/boot-options.txt b/trunk/Documentation/x86/x86_64/boot-options.txt index 34c13040a718..29a6ff8bc7d3 100644 --- a/trunk/Documentation/x86/x86_64/boot-options.txt +++ b/trunk/Documentation/x86/x86_64/boot-options.txt @@ -5,21 +5,51 @@ only the AMD64 specific ones are listed here. Machine check - mce=off disable machine check - mce=bootlog Enable logging of machine checks left over from booting. - Disabled by default on AMD because some BIOS leave bogus ones. - If your BIOS doesn't do that it's a good idea to enable though - to make sure you log even machine check events that result - in a reboot. On Intel systems it is enabled by default. + Please see Documentation/x86/x86_64/machinecheck for sysfs runtime tunables. + + mce=off + Disable machine check + mce=no_cmci + Disable CMCI(Corrected Machine Check Interrupt) that + Intel processor supports. Usually this disablement is + not recommended, but it might be handy if your hardware + is misbehaving. + Note that you'll get more problems without CMCI than with + due to the shared banks, i.e. you might get duplicated + error logs. + mce=dont_log_ce + Don't make logs for corrected errors. All events reported + as corrected are silently cleared by OS. + This option will be useful if you have no interest in any + of corrected errors. + mce=ignore_ce + Disable features for corrected errors, e.g. polling timer + and CMCI. All events reported as corrected are not cleared + by OS and remained in its error banks. + Usually this disablement is not recommended, however if + there is an agent checking/clearing corrected errors + (e.g. BIOS or hardware monitoring applications), conflicting + with OS's error handling, and you cannot deactivate the agent, + then this option will be a help. + mce=bootlog + Enable logging of machine checks left over from booting. + Disabled by default on AMD because some BIOS leave bogus ones. + If your BIOS doesn't do that it's a good idea to enable though + to make sure you log even machine check events that result + in a reboot. On Intel systems it is enabled by default. mce=nobootlog Disable boot machine check logging. - mce=tolerancelevel (number) + mce=tolerancelevel[,monarchtimeout] (number,number) + tolerance levels: 0: always panic on uncorrected errors, log corrected errors 1: panic or SIGBUS on uncorrected errors, log corrected errors 2: SIGBUS or log uncorrected errors, log corrected errors 3: never panic or SIGBUS, log all errors (for testing only) Default is 1 Can be also set using sysfs which is preferable. + monarchtimeout: + Sets the time in us to wait for other CPUs on machine checks. 0 + to disable. nomce (for compatibility with i386): same as mce=off @@ -150,11 +180,6 @@ NUMA Otherwise, the remaining system RAM is allocated to an additional node. - numa=hotadd=percent - Only allow hotadd memory to preallocate page structures upto - percent of already available memory. - numa=hotadd=0 will disable hotadd memory. - ACPI acpi=off Don't enable ACPI diff --git a/trunk/Documentation/x86/x86_64/machinecheck b/trunk/Documentation/x86/x86_64/machinecheck index a05e58e7b159..b1fb30273286 100644 --- a/trunk/Documentation/x86/x86_64/machinecheck +++ b/trunk/Documentation/x86/x86_64/machinecheck @@ -41,7 +41,9 @@ check_interval the polling interval. When the poller stops finding MCEs, it triggers an exponential backoff (poll less often) on the polling interval. The check_interval variable is both the initial and - maximum polling interval. + maximum polling interval. 0 means no polling for corrected machine + check errors (but some corrected errors might be still reported + in other ways) tolerant Tolerance level. When a machine check exception occurs for a non @@ -67,6 +69,10 @@ trigger Program to run when a machine check event is detected. This is an alternative to running mcelog regularly from cron and allows to detect events faster. +monarch_timeout + How long to wait for the other CPUs to machine check too on a + exception. 0 to disable waiting for other CPUs. + Unit: us TBD document entries for AMD threshold interrupt configuration diff --git a/trunk/Documentation/x86/x86_64/mm.txt b/trunk/Documentation/x86/x86_64/mm.txt index 29b52b14d0b4..d6498e3cd713 100644 --- a/trunk/Documentation/x86/x86_64/mm.txt +++ b/trunk/Documentation/x86/x86_64/mm.txt @@ -6,10 +6,11 @@ Virtual memory map with 4 level page tables: 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm hole caused by [48:63] sign extension ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole -ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory -ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole -ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space -ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB) +ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory +ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole +ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space +ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole +ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) ... unused hole ... ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space diff --git a/trunk/MAINTAINERS b/trunk/MAINTAINERS index aed47f2d11a7..0765bb6aa3cb 100644 --- a/trunk/MAINTAINERS +++ b/trunk/MAINTAINERS @@ -71,7 +71,7 @@ P: Person M: Mail patches to L: Mailing list that is relevant to this area W: Web-page with status/info -T: SCM tree type and location. Type is one of: git, hg, quilt. +T: SCM tree type and location. Type is one of: git, hg, quilt, stgit. S: Status, one of the following: Supported: Someone is actually paid to look after this. @@ -159,7 +159,8 @@ F: drivers/net/r8169.c 8250/16?50 (AND CLONE UARTS) SERIAL DRIVER L: linux-serial@vger.kernel.org W: http://serial.sourceforge.net -S: Orphan +M: alan@lxorguk.ukuu.org.uk +S: Odd Fixes F: drivers/serial/8250* F: include/linux/serial_8250.h @@ -1808,10 +1809,10 @@ F: drivers/char/epca* F: drivers/char/digi* DIRECTORY NOTIFICATION (DNOTIFY) -P: Stephen Rothwell -M: sfr@canb.auug.org.au +P: Eric Paris +M: eparis@parisplace.org L: linux-kernel@vger.kernel.org -S: Supported +S: Maintained F: Documentation/filesystems/dnotify.txt F: fs/notify/dnotify/ F: include/linux/dnotify.h @@ -1985,6 +1986,16 @@ F: Documentation/edac.txt F: drivers/edac/edac_* F: include/linux/edac.h +EDAC-AMD64 +P: Doug Thompson +M: dougthompson@xmission.com +P: Borislav Petkov +M: borislav.petkov@amd.com +L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) +W: bluesmoke.sourceforge.net +S: Supported +F: drivers/edac/amd64_edac* + EDAC-E752X P: Mark Gross M: mark.gross@intel.com @@ -2854,6 +2865,8 @@ P: John McCutchan M: john@johnmccutchan.com P: Robert Love M: rlove@rlove.org +P: Eric Paris +M: eparis@parisplace.org L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/inotify.txt @@ -3357,6 +3370,16 @@ F: drivers/serial/kgdboc.c F: include/linux/kgdb.h F: kernel/kgdb.c +KMEMLEAK +P: Catalin Marinas +M: catalin.marinas@arm.com +L: linux-kernel@vger.kernel.org +S: Maintained +F: Documentation/kmemleak.txt +F: include/linux/kmemleak.h +F: mm/kmemleak.c +F: mm/kmemleak-test.c + KMEMTRACE P: Eduard - Gabriel Munteanu M: eduard.munteanu@linux360.ro @@ -4462,6 +4485,16 @@ S: Maintained F: include/linux/delayacct.h F: kernel/delayacct.c +PERFORMANCE COUNTER SUBSYSTEM +P: Peter Zijlstra +M: a.p.zijlstra@chello.nl +P: Paul Mackerras +M: paulus@samba.org +P: Ingo Molnar +M: mingo@elte.hu +L: linux-kernel@vger.kernel.org +S: Supported + PERSONALITY HANDLING P: Christoph Hellwig M: hch@infradead.org @@ -4644,7 +4677,8 @@ F: drivers/pcmcia/pxa2xx* F: drivers/spi/pxa2xx* F: drivers/usb/gadget/pxa2* F: include/sound/pxa2xx-lib.h -F: sound/soc/pxa/pxa2xx* +F: sound/arm/pxa* +F: sound/soc/pxa PXA168 SUPPORT P: Eric Miao @@ -5371,11 +5405,12 @@ P: Liam Girdwood M: lrg@slimlogic.co.uk P: Mark Brown M: broonie@opensource.wolfsonmicro.com -T: git git://opensource.wolfsonmicro.com/linux-2.6-asoc +T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound-2.6.git L: alsa-devel@alsa-project.org (subscribers-only) W: http://alsa-project.org/main/index.php/ASoC S: Supported F: sound/soc/ +F: include/sound/soc* SPARC + UltraSPARC (sparc/sparc64) P: David S. Miller @@ -5684,6 +5719,7 @@ P: Alan Cox M: alan@lxorguk.ukuu.org.uk L: linux-kernel@vger.kernel.org S: Maintained +T: stgit http://zeniv.linux.org.uk/~alan/ttydev/ TULIP NETWORK DRIVERS P: Grant Grundler diff --git a/trunk/Makefile b/trunk/Makefile index 610d1c332c45..03373bb703ca 100644 --- a/trunk/Makefile +++ b/trunk/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 30 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* @@ -533,7 +533,7 @@ endif include $(srctree)/arch/$(SRCARCH)/Makefile -ifneq (CONFIG_FRAME_WARN,0) +ifneq ($(CONFIG_FRAME_WARN),0) KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN}) endif diff --git a/trunk/arch/alpha/include/asm/atomic.h b/trunk/arch/alpha/include/asm/atomic.h index 62b363584b2b..610dff44d94b 100644 --- a/trunk/arch/alpha/include/asm/atomic.h +++ b/trunk/arch/alpha/include/asm/atomic.h @@ -256,5 +256,5 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) #define smp_mb__before_atomic_inc() smp_mb() #define smp_mb__after_atomic_inc() smp_mb() -#include +#include #endif /* _ALPHA_ATOMIC_H */ diff --git a/trunk/arch/alpha/include/asm/bitsperlong.h b/trunk/arch/alpha/include/asm/bitsperlong.h new file mode 100644 index 000000000000..ad57f7868203 --- /dev/null +++ b/trunk/arch/alpha/include/asm/bitsperlong.h @@ -0,0 +1,8 @@ +#ifndef __ASM_ALPHA_BITSPERLONG_H +#define __ASM_ALPHA_BITSPERLONG_H + +#define __BITS_PER_LONG 64 + +#include + +#endif /* __ASM_ALPHA_BITSPERLONG_H */ diff --git a/trunk/arch/alpha/include/asm/page.h b/trunk/arch/alpha/include/asm/page.h index 0995f9d13417..07af062544fb 100644 --- a/trunk/arch/alpha/include/asm/page.h +++ b/trunk/arch/alpha/include/asm/page.h @@ -93,6 +93,6 @@ typedef struct page *pgtable_t; VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #include -#include +#include #endif /* _ALPHA_PAGE_H */ diff --git a/trunk/arch/alpha/include/asm/signal.h b/trunk/arch/alpha/include/asm/signal.h index 13c2305d35ef..a9388300abb1 100644 --- a/trunk/arch/alpha/include/asm/signal.h +++ b/trunk/arch/alpha/include/asm/signal.h @@ -111,7 +111,7 @@ typedef unsigned long sigset_t; #define SIG_UNBLOCK 2 /* for unblocking signals */ #define SIG_SETMASK 3 /* for setting the signal mask */ -#include +#include #ifdef __KERNEL__ struct osf_sigaction { diff --git a/trunk/arch/alpha/include/asm/suspend.h b/trunk/arch/alpha/include/asm/suspend.h deleted file mode 100644 index c7042d575851..000000000000 --- a/trunk/arch/alpha/include/asm/suspend.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ALPHA_SUSPEND_H -#define __ALPHA_SUSPEND_H - -/* Dummy include. */ - -#endif /* __ALPHA_SUSPEND_H */ diff --git a/trunk/arch/alpha/include/asm/types.h b/trunk/arch/alpha/include/asm/types.h index f072f344497e..bd621ecd1eb3 100644 --- a/trunk/arch/alpha/include/asm/types.h +++ b/trunk/arch/alpha/include/asm/types.h @@ -25,9 +25,6 @@ typedef unsigned int umode_t; * These aren't exported outside the kernel to avoid name space clashes */ #ifdef __KERNEL__ - -#define BITS_PER_LONG 64 - #ifndef __ASSEMBLY__ typedef u64 dma_addr_t; diff --git a/trunk/arch/alpha/kernel/osf_sys.c b/trunk/arch/alpha/kernel/osf_sys.c index 42ee05981e71..9a3334ae282e 100644 --- a/trunk/arch/alpha/kernel/osf_sys.c +++ b/trunk/arch/alpha/kernel/osf_sys.c @@ -371,8 +371,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path, int retval = -EINVAL; char *name; - lock_kernel(); - name = getname(path); retval = PTR_ERR(name); if (IS_ERR(name)) @@ -392,7 +390,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path, } putname(name); out: - unlock_kernel(); return retval; } diff --git a/trunk/arch/alpha/kernel/sys_dp264.c b/trunk/arch/alpha/kernel/sys_dp264.c index 9c9d1fd4155f..5bd5259324b7 100644 --- a/trunk/arch/alpha/kernel/sys_dp264.c +++ b/trunk/arch/alpha/kernel/sys_dp264.c @@ -176,22 +176,26 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } } -static void +static int dp264_set_affinity(unsigned int irq, const struct cpumask *affinity) { spin_lock(&dp264_irq_lock); cpu_set_irq_affinity(irq, *affinity); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); + + return 0; } -static void +static int clipper_set_affinity(unsigned int irq, const struct cpumask *affinity) { spin_lock(&dp264_irq_lock); cpu_set_irq_affinity(irq - 16, *affinity); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); + + return 0; } static struct hw_interrupt_type dp264_irq_type = { diff --git a/trunk/arch/alpha/kernel/sys_titan.c b/trunk/arch/alpha/kernel/sys_titan.c index 27f840a4ad3d..8dd239ebdb9e 100644 --- a/trunk/arch/alpha/kernel/sys_titan.c +++ b/trunk/arch/alpha/kernel/sys_titan.c @@ -157,13 +157,15 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } -static void +static int titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) { spin_lock(&titan_irq_lock); titan_cpu_set_irq_affinity(irq - 16, *affinity); titan_update_irq_hw(titan_cached_irq_mask); spin_unlock(&titan_irq_lock); + + return 0; } static void diff --git a/trunk/arch/alpha/mm/extable.c b/trunk/arch/alpha/mm/extable.c index 62dc379d301a..813c9b63c0e1 100644 --- a/trunk/arch/alpha/mm/extable.c +++ b/trunk/arch/alpha/mm/extable.c @@ -48,6 +48,27 @@ void sort_extable(struct exception_table_entry *start, cmp_ex, swap_ex); } +#ifdef CONFIG_MODULES +/* + * Any entry referring to the module init will be at the beginning or + * the end. + */ +void trim_init_extable(struct module *m) +{ + /*trim the beginning*/ + while (m->num_exentries && + within_module_init(ex_to_addr(&m->extable[0]), m)) { + m->extable++; + m->num_exentries--; + } + /*trim the end*/ + while (m->num_exentries && + within_module_init(ex_to_addr(&m->extable[m->num_exentries-1]), + m)) + m->num_exentries--; +} +#endif /* CONFIG_MODULES */ + const struct exception_table_entry * search_extable(const struct exception_table_entry *first, const struct exception_table_entry *last, diff --git a/trunk/arch/arm/common/gic.c b/trunk/arch/arm/common/gic.c index 3e1714c6523f..664c7b8b1ba8 100644 --- a/trunk/arch/arm/common/gic.c +++ b/trunk/arch/arm/common/gic.c @@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq) } #ifdef CONFIG_SMP -static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) +static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) { void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3); unsigned int shift = (irq % 4) * 8; @@ -122,6 +122,8 @@ static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) val |= 1 << (cpu + shift); writel(val, reg); spin_unlock(&irq_controller_lock); + + return 0; } #endif diff --git a/trunk/arch/arm/include/asm/atomic.h b/trunk/arch/arm/include/asm/atomic.h index 16b52f397983..9e07fe507029 100644 --- a/trunk/arch/arm/include/asm/atomic.h +++ b/trunk/arch/arm/include/asm/atomic.h @@ -249,6 +249,6 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #define smp_mb__before_atomic_inc() smp_mb() #define smp_mb__after_atomic_inc() smp_mb() -#include +#include #endif #endif diff --git a/trunk/arch/arm/include/asm/bitsperlong.h b/trunk/arch/arm/include/asm/bitsperlong.h new file mode 100644 index 000000000000..6dc0bb0c13b2 --- /dev/null +++ b/trunk/arch/arm/include/asm/bitsperlong.h @@ -0,0 +1 @@ +#include diff --git a/trunk/arch/arm/include/asm/cache.h b/trunk/arch/arm/include/asm/cache.h index cb7a9e97fd7e..feaa75f0013e 100644 --- a/trunk/arch/arm/include/asm/cache.h +++ b/trunk/arch/arm/include/asm/cache.h @@ -7,4 +7,20 @@ #define L1_CACHE_SHIFT 5 #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) +/* + * Memory returned by kmalloc() may be used for DMA, so we must make + * sure that all such allocations are cache aligned. Otherwise, + * unrelated code may cause parts of the buffer to be read into the + * cache before the transfer is done, causing old data to be seen by + * the CPU. + */ +#define ARCH_KMALLOC_MINALIGN L1_CACHE_BYTES + +/* + * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers. + */ +#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) +#define ARCH_SLAB_MINALIGN 8 +#endif + #endif diff --git a/trunk/arch/arm/include/asm/mman.h b/trunk/arch/arm/include/asm/mman.h index 54570d2e95b7..fc26976d8e3a 100644 --- a/trunk/arch/arm/include/asm/mman.h +++ b/trunk/arch/arm/include/asm/mman.h @@ -1,7 +1,7 @@ #ifndef __ARM_MMAN_H__ #define __ARM_MMAN_H__ -#include +#include #define MAP_GROWSDOWN 0x0100 /* stack-like segment */ #define MAP_DENYWRITE 0x0800 /* ETXTBSY */ diff --git a/trunk/arch/arm/include/asm/page.h b/trunk/arch/arm/include/asm/page.h index e6eb8a67b807..be962c1349c4 100644 --- a/trunk/arch/arm/include/asm/page.h +++ b/trunk/arch/arm/include/asm/page.h @@ -202,13 +202,6 @@ typedef struct page *pgtable_t; (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -/* - * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers. - */ -#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) -#define ARCH_SLAB_MINALIGN 8 -#endif - -#include +#include #endif diff --git a/trunk/arch/arm/include/asm/signal.h b/trunk/arch/arm/include/asm/signal.h index d0fb487aba4f..43ba0fb1c8ad 100644 --- a/trunk/arch/arm/include/asm/signal.h +++ b/trunk/arch/arm/include/asm/signal.h @@ -111,7 +111,7 @@ typedef unsigned long sigset_t; #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 -#include +#include #ifdef __KERNEL__ struct old_sigaction { diff --git a/trunk/arch/arm/include/asm/suspend.h b/trunk/arch/arm/include/asm/suspend.h deleted file mode 100644 index cf0d0bdee74d..000000000000 --- a/trunk/arch/arm/include/asm/suspend.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef _ASMARM_SUSPEND_H -#define _ASMARM_SUSPEND_H - -#endif diff --git a/trunk/arch/arm/mach-mx2/clock_imx21.c b/trunk/arch/arm/mach-mx2/clock_imx21.c index fa2b292d7b3c..0850fb88ec15 100644 --- a/trunk/arch/arm/mach-mx2/clock_imx21.c +++ b/trunk/arch/arm/mach-mx2/clock_imx21.c @@ -915,7 +915,7 @@ static struct clk clko_clk = { .con_id = n, \ .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { /* It's unlikely that any driver wants one of them directly: _REGISTER_CLOCK(NULL, "ckih", ckih_clk) _REGISTER_CLOCK(NULL, "ckil", ckil_clk) diff --git a/trunk/arch/arm/mach-mx2/clock_imx27.c b/trunk/arch/arm/mach-mx2/clock_imx27.c index 3f7280c490f0..2c971442f3f2 100644 --- a/trunk/arch/arm/mach-mx2/clock_imx27.c +++ b/trunk/arch/arm/mach-mx2/clock_imx27.c @@ -621,7 +621,7 @@ DEFINE_CLOCK1(csi_clk, 0, 0, 0, parent, &csi_clk1, &per4_clk); .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { _REGISTER_CLOCK("imx-uart.0", NULL, uart1_clk) _REGISTER_CLOCK("imx-uart.1", NULL, uart2_clk) _REGISTER_CLOCK("imx-uart.2", NULL, uart3_clk) diff --git a/trunk/arch/arm/mach-mx3/clock-imx35.c b/trunk/arch/arm/mach-mx3/clock-imx35.c index 0d76521cb491..577ee83d1f60 100644 --- a/trunk/arch/arm/mach-mx3/clock-imx35.c +++ b/trunk/arch/arm/mach-mx3/clock-imx35.c @@ -381,7 +381,7 @@ DEFINE_CLOCK(gpu2d_clk, 0, CCM_CGR3, 4, NULL, NULL); .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { _REGISTER_CLOCK(NULL, "asrc", asrc_clk) _REGISTER_CLOCK(NULL, "ata", ata_clk) _REGISTER_CLOCK(NULL, "audmux", audmux_clk) diff --git a/trunk/arch/arm/mach-mx3/clock.c b/trunk/arch/arm/mach-mx3/clock.c index 217d114b177a..8b14239724c9 100644 --- a/trunk/arch/arm/mach-mx3/clock.c +++ b/trunk/arch/arm/mach-mx3/clock.c @@ -516,7 +516,7 @@ DEFINE_CLOCK(ipg_clk, 0, NULL, 0, ipg_get_rate, NULL, &ahb_clk); .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { _REGISTER_CLOCK(NULL, "emi", emi_clk) _REGISTER_CLOCK(NULL, "cspi", cspi1_clk) _REGISTER_CLOCK(NULL, "cspi", cspi2_clk) diff --git a/trunk/arch/arm/mach-pxa/devices.c b/trunk/arch/arm/mach-pxa/devices.c index d3c3b7b025ae..ecc08f360b68 100644 --- a/trunk/arch/arm/mach-pxa/devices.c +++ b/trunk/arch/arm/mach-pxa/devices.c @@ -72,7 +72,10 @@ void __init pxa_set_mci_info(struct pxamci_platform_data *info) } -static struct pxa2xx_udc_mach_info pxa_udc_info; +static struct pxa2xx_udc_mach_info pxa_udc_info = { + .gpio_pullup = -1, + .gpio_vbus = -1, +}; void __init pxa_set_udc_info(struct pxa2xx_udc_mach_info *info) { diff --git a/trunk/arch/arm/mach-pxa/imote2.c b/trunk/arch/arm/mach-pxa/imote2.c index be7be72dace1..961807dc6467 100644 --- a/trunk/arch/arm/mach-pxa/imote2.c +++ b/trunk/arch/arm/mach-pxa/imote2.c @@ -439,7 +439,7 @@ static struct platform_device imote2_flash_device = { */ static struct i2c_board_info __initdata imote2_i2c_board_info[] = { { /* UCAM sensor board */ - .type = "max1238", + .type = "max1239", .addr = 0x35, }, { /* ITS400 Sensor board only */ .type = "max1363", diff --git a/trunk/arch/arm/mm/proc-v7.S b/trunk/arch/arm/mm/proc-v7.S index 4f8486475a79..180a08d03a03 100644 --- a/trunk/arch/arm/mm/proc-v7.S +++ b/trunk/arch/arm/mm/proc-v7.S @@ -190,23 +190,37 @@ __v7_setup: stmia r12, {r0-r5, r7, r9, r11, lr} bl v7_flush_dcache_all ldmia r12, {r0-r5, r7, r9, r11, lr} + + mrc p15, 0, r0, c0, c0, 0 @ read main ID register + and r10, r0, #0xff000000 @ ARM? + teq r10, #0x41000000 + bne 2f + and r5, r0, #0x00f00000 @ variant + and r6, r0, #0x0000000f @ revision + orr r0, r6, r5, lsr #20-4 @ combine variant and revision + #ifdef CONFIG_ARM_ERRATA_430973 - mrc p15, 0, r10, c1, c0, 1 @ read aux control register - orr r10, r10, #(1 << 6) @ set IBE to 1 - mcr p15, 0, r10, c1, c0, 1 @ write aux control register + teq r5, #0x00100000 @ only present in r1p* + mrceq p15, 0, r10, c1, c0, 1 @ read aux control register + orreq r10, r10, #(1 << 6) @ set IBE to 1 + mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_458693 - mrc p15, 0, r10, c1, c0, 1 @ read aux control register - orr r10, r10, #(1 << 5) @ set L1NEON to 1 - orr r10, r10, #(1 << 9) @ set PLDNOP to 1 - mcr p15, 0, r10, c1, c0, 1 @ write aux control register + teq r0, #0x20 @ only present in r2p0 + mrceq p15, 0, r10, c1, c0, 1 @ read aux control register + orreq r10, r10, #(1 << 5) @ set L1NEON to 1 + orreq r10, r10, #(1 << 9) @ set PLDNOP to 1 + mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_460075 - mrc p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register - orr r10, r10, #(1 << 22) @ set the Write Allocate disable bit - mcr p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register + teq r0, #0x20 @ only present in r2p0 + mrceq p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register + tsteq r10, #1 << 22 + orreq r10, r10, #(1 << 22) @ set the Write Allocate disable bit + mcreq p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register #endif - mov r10, #0 + +2: mov r10, #0 #ifdef HARVARD_CACHE mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate #endif diff --git a/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h b/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h index 90af4d9bc19e..4adec9b154dd 100644 --- a/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h +++ b/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h @@ -20,11 +20,16 @@ #define ASMARM_ARCH_UART_H #define IMXUART_HAVE_RTSCTS (1<<0) +#define IMXUART_IRDA (1<<1) struct imxuart_platform_data { int (*init)(struct platform_device *pdev); void (*exit)(struct platform_device *pdev); unsigned int flags; + void (*irda_enable)(int enable); + unsigned int irda_inv_rx:1; + unsigned int irda_inv_tx:1; + unsigned short transceiver_delay; }; #endif diff --git a/trunk/arch/arm/plat-omap/mailbox.c b/trunk/arch/arm/plat-omap/mailbox.c index 0abfbaa59871..40424edae939 100644 --- a/trunk/arch/arm/plat-omap/mailbox.c +++ b/trunk/arch/arm/plat-omap/mailbox.c @@ -147,24 +147,40 @@ static int __mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void *arg) return ret; } +struct omap_msg_tx_data { + mbox_msg_t msg; + void *arg; +}; + +static void omap_msg_tx_end_io(struct request *rq, int error) +{ + kfree(rq->special); + __blk_put_request(rq->q, rq); +} + int omap_mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void* arg) { + struct omap_msg_tx_data *tx_data; struct request *rq; struct request_queue *q = mbox->txq->queue; - int ret = 0; + + tx_data = kmalloc(sizeof(*tx_data), GFP_ATOMIC); + if (unlikely(!tx_data)) + return -ENOMEM; rq = blk_get_request(q, WRITE, GFP_ATOMIC); if (unlikely(!rq)) { - ret = -ENOMEM; - goto fail; + kfree(tx_data); + return -ENOMEM; } - rq->data = (void *)msg; - blk_insert_request(q, rq, 0, arg); + tx_data->msg = msg; + tx_data->arg = arg; + rq->end_io = omap_msg_tx_end_io; + blk_insert_request(q, rq, 0, tx_data); schedule_work(&mbox->txq->work); - fail: - return ret; + return 0; } EXPORT_SYMBOL(omap_mbox_msg_send); @@ -178,22 +194,28 @@ static void mbox_tx_work(struct work_struct *work) struct request_queue *q = mbox->txq->queue; while (1) { + struct omap_msg_tx_data *tx_data; + spin_lock(q->queue_lock); - rq = elv_next_request(q); + rq = blk_fetch_request(q); spin_unlock(q->queue_lock); if (!rq) break; - ret = __mbox_msg_send(mbox, (mbox_msg_t) rq->data, rq->special); + tx_data = rq->special; + + ret = __mbox_msg_send(mbox, tx_data->msg, tx_data->arg); if (ret) { enable_mbox_irq(mbox, IRQ_TX); + spin_lock(q->queue_lock); + blk_requeue_request(q, rq); + spin_unlock(q->queue_lock); return; } spin_lock(q->queue_lock); - if (__blk_end_request(rq, 0, 0)) - BUG(); + __blk_end_request_all(rq, 0); spin_unlock(q->queue_lock); } } @@ -218,16 +240,13 @@ static void mbox_rx_work(struct work_struct *work) while (1) { spin_lock_irqsave(q->queue_lock, flags); - rq = elv_next_request(q); + rq = blk_fetch_request(q); spin_unlock_irqrestore(q->queue_lock, flags); if (!rq) break; - msg = (mbox_msg_t) rq->data; - - if (blk_end_request(rq, 0, 0)) - BUG(); - + msg = (mbox_msg_t)rq->special; + blk_end_request_all(rq, 0); mbox->rxq->callback((void *)msg); } } @@ -264,7 +283,6 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox) goto nomem; msg = mbox_fifo_read(mbox); - rq->data = (void *)msg; if (unlikely(mbox_seq_test(mbox, msg))) { pr_info("mbox: Illegal seq bit!(%08x)\n", msg); @@ -272,7 +290,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox) mbox->err_notify(); } - blk_insert_request(q, rq, 0, NULL); + blk_insert_request(q, rq, 0, (void *)msg); if (mbox->ops->type == OMAP_MBOX_TYPE1) break; } @@ -329,16 +347,15 @@ omap_mbox_read(struct device *dev, struct device_attribute *attr, char *buf) while (1) { spin_lock_irqsave(q->queue_lock, flags); - rq = elv_next_request(q); + rq = blk_fetch_request(q); spin_unlock_irqrestore(q->queue_lock, flags); if (!rq) break; - *p = (mbox_msg_t) rq->data; + *p = (mbox_msg_t)rq->special; - if (blk_end_request(rq, 0, 0)) - BUG(); + blk_end_request_all(rq, 0); if (unlikely(mbox_seq_test(mbox, *p))) { pr_info("mbox: Illegal seq bit!(%08x) ignored\n", *p); diff --git a/trunk/arch/avr32/boards/atngw100/Kconfig b/trunk/arch/avr32/boards/atngw100/Kconfig index b3f99477bbeb..be27a0218ab4 100644 --- a/trunk/arch/avr32/boards/atngw100/Kconfig +++ b/trunk/arch/avr32/boards/atngw100/Kconfig @@ -2,8 +2,15 @@ if BOARD_ATNGW100 +choice + prompt "Select an NGW100 add-on board to support" + default BOARD_ATNGW100_ADDON_NONE + +config BOARD_ATNGW100_ADDON_NONE + bool "None" + config BOARD_ATNGW100_EVKLCD10X - bool "Add support for EVKLCD10X addon board" + bool "EVKLCD10X addon board" help This enables support for the EVKLCD100 (QVGA) or EVKLCD101 (VGA) addon board for the NGW100. By enabling this the LCD controller and @@ -14,7 +21,19 @@ config BOARD_ATNGW100_EVKLCD10X The MCI pins can be reenabled by editing the "add device function" but this may break the setup for other displays that use these pins. - Choose 'Y' here if you have a EVKLCD100/101 connected to the NGW100. +config BOARD_ATNGW100_MRMT + bool "Mediama RMT1/2 add-on board" + help + This enables support for the Mediama RMT1 or RMT2 board. + RMT provides LCD support, AC97 codec and other + optional peripherals to the Atmel NGW100. + + This choice disables the detect pin and the write-protect pin for the + MCI platform device, since it conflicts with the LCD platform device. + The MCI pins can be reenabled by editing the "add device function" but + this may break the setup for other displays that use these pins. + +endchoice choice prompt "LCD panel resolution on EVKLCD10X" @@ -32,4 +51,8 @@ config BOARD_ATNGW100_EVKLCD10X_POW_QVGA endchoice +if BOARD_ATNGW100_MRMT +source "arch/avr32/boards/atngw100/Kconfig_mrmt" +endif + endif # BOARD_ATNGW100 diff --git a/trunk/arch/avr32/boards/atngw100/Kconfig_mrmt b/trunk/arch/avr32/boards/atngw100/Kconfig_mrmt new file mode 100644 index 000000000000..9a199a207f3c --- /dev/null +++ b/trunk/arch/avr32/boards/atngw100/Kconfig_mrmt @@ -0,0 +1,80 @@ +# RMT for NGW100 customization + +choice + prompt "RMT Version" + help + Select the RMTx board version. + +config BOARD_MRMT_REV1 + bool "RMT1" +config BOARD_MRMT_REV2 + bool "RMT2" + +endchoice + +config BOARD_MRMT_AC97 + bool "Enable AC97 CODEC" + help + Enable the UCB1400 AC97 CODEC driver. + +choice + prompt "Touchscreen Driver" + default BOARD_MRMT_ADS7846_TS + +config BOARD_MRMT_UCB1400_TS + bool "Use UCB1400 Touchscreen" + +config BOARD_MRMT_ADS7846_TS + bool "Use ADS7846 Touchscreen" + +endchoice + +choice + prompt "RMTx LCD Selection" + default BOARD_MRMT_LCD_DISABLE + +config BOARD_MRMT_LCD_DISABLE + bool "LCD Disabled" + +config BOARD_MRMT_LCD_LQ043T3DX0X + bool "Sharp LQ043T3DX0x or compatible" + help + If using RMT2, be sure to load the resistor pack selectors accordingly + +if BOARD_MRMT_REV2 +config BOARD_MRMT_LCD_KWH043GM08 + bool "Formike KWH043GM08 or compatible" + help + Be sure to load the RMT2 resistor pack selectors accordingly +endif + +endchoice + +if !BOARD_MRMT_LCD_DISABLE +config BOARD_MRMT_BL_PWM + bool "Use PWM control for LCD Backlight" + help + Use PWM driver for controlling LCD Backlight. + Otherwise, LCD Backlight is always on. +endif + +config BOARD_MRMT_RTC_I2C + bool "Use External RTC on I2C Bus" + help + RMT1 has an optional RTC device on the I2C bus. + It is a SII S35390A. Be sure to select the + matching RTC driver. + +choice + prompt "Wireless Module on ttyS2" + default BOARD_MRMT_WIRELESS_ZB + +config BOARD_MRMT_WIRELESS_ZB + bool "Use ZigBee/802.15.4 Module" + +config BOARD_MRMT_WIRELESS_BT + bool "Use Bluetooth (HCI) Module" + +config BOARD_MRMT_WIRELESS_NONE + bool "Not Installed" +endchoice diff --git a/trunk/arch/avr32/boards/atngw100/Makefile b/trunk/arch/avr32/boards/atngw100/Makefile index 6376f5322e4d..f4ebe42a8254 100644 --- a/trunk/arch/avr32/boards/atngw100/Makefile +++ b/trunk/arch/avr32/boards/atngw100/Makefile @@ -1,2 +1,3 @@ obj-y += setup.o flash.o obj-$(CONFIG_BOARD_ATNGW100_EVKLCD10X) += evklcd10x.o +obj-$(CONFIG_BOARD_ATNGW100_MRMT) += mrmt.o diff --git a/trunk/arch/avr32/boards/atngw100/mrmt.c b/trunk/arch/avr32/boards/atngw100/mrmt.c new file mode 100644 index 000000000000..bf78e516a85f --- /dev/null +++ b/trunk/arch/avr32/boards/atngw100/mrmt.c @@ -0,0 +1,373 @@ +/* + * Board-specific setup code for Remote Media Terminal 1 (RMT1) + * add-on board for the ATNGW100 Network Gateway + * + * Copyright (C) 2008 Mediama Technologies + * Based on ATNGW100 Network Gateway (Copyright (C) Atmel) + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include + +#include
); if section is defined, else just show +# the command. + +[macros] +(?su)[\\]?(?Plinkperf):(?P\S*?)\[(?P.*?)\]= + +[attributes] +asterisk=* +plus=+ +caret=^ +startsb=[ +endsb=] +tilde=~ + +ifdef::backend-docbook[] +[linkperf-inlinemacro] +{0%{target}} +{0#} +{0#{target}{0}} +{0#} +endif::backend-docbook[] + +ifdef::backend-docbook[] +ifndef::perf-asciidoc-no-roff[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +# v1.72 breaks with this because it replaces dots not in roff requests. +[listingblock] +{title} + +ifdef::doctype-manpage[] + .ft C +endif::doctype-manpage[] +| +ifdef::doctype-manpage[] + .ft +endif::doctype-manpage[] + +{title#} +endif::perf-asciidoc-no-roff[] + +ifdef::perf-asciidoc-no-roff[] +ifdef::doctype-manpage[] +# The following two small workarounds insert a simple paragraph after screen +[listingblock] +{title} + +| + +{title#} + +[verseblock] +{title} +{title%} +{title#} +| + +{title#} +{title%} +endif::doctype-manpage[] +endif::perf-asciidoc-no-roff[] +endif::backend-docbook[] + +ifdef::doctype-manpage[] +ifdef::backend-docbook[] +[header] +template::[header-declarations] + + +{mantitle} +{manvolnum} +perf +{perf_version} +perf Manual + + + {manname} + {manpurpose} + +endif::backend-docbook[] +endif::doctype-manpage[] + +ifdef::backend-xhtml11[] +[linkperf-inlinemacro] +{target}{0?({0})} +endif::backend-xhtml11[] diff --git a/trunk/tools/perf/Documentation/manpage-1.72.xsl b/trunk/tools/perf/Documentation/manpage-1.72.xsl new file mode 100644 index 000000000000..b4d315cb8c47 --- /dev/null +++ b/trunk/tools/perf/Documentation/manpage-1.72.xsl @@ -0,0 +1,14 @@ + + + + + + +▓ +⌂ + + diff --git a/trunk/tools/perf/Documentation/manpage-base.xsl b/trunk/tools/perf/Documentation/manpage-base.xsl new file mode 100644 index 000000000000..a264fa616093 --- /dev/null +++ b/trunk/tools/perf/Documentation/manpage-base.xsl @@ -0,0 +1,35 @@ + + + + + + + + + + + + + + sp + + + + + + + + br + + + diff --git a/trunk/tools/perf/Documentation/manpage-bold-literal.xsl b/trunk/tools/perf/Documentation/manpage-bold-literal.xsl new file mode 100644 index 000000000000..608eb5df6281 --- /dev/null +++ b/trunk/tools/perf/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ + + + + + + + fB + + + fR + + + diff --git a/trunk/tools/perf/Documentation/manpage-normal.xsl b/trunk/tools/perf/Documentation/manpage-normal.xsl new file mode 100644 index 000000000000..a48f5b11f3dc --- /dev/null +++ b/trunk/tools/perf/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ + + + + + + +\ +. + + diff --git a/trunk/tools/perf/Documentation/manpage-suppress-sp.xsl b/trunk/tools/perf/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 000000000000..a63c7632a87d --- /dev/null +++ b/trunk/tools/perf/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ + + + + + + + + + + + + + + + diff --git a/trunk/tools/perf/Documentation/perf-annotate.txt b/trunk/tools/perf/Documentation/perf-annotate.txt new file mode 100644 index 000000000000..c9dcade06831 --- /dev/null +++ b/trunk/tools/perf/Documentation/perf-annotate.txt @@ -0,0 +1,29 @@ +perf-annotate(1) +============== + +NAME +---- +perf-annotate - Read perf.data (created by perf record) and display annotated code + +SYNOPSIS +-------- +[verse] +'perf annotate' [-i | --input=file] symbol_name + +DESCRIPTION +----------- +This command reads the input file and displays an annotated version of the +code. If the object file has debug symbols then the source code will be +displayed alongside assembly code. + +If there is no debug info in the object, then annotated assembly is displayed. + +OPTIONS +------- +-i:: +--input=:: + Input file name. (default: perf.data) + +SEE ALSO +-------- +linkperf:perf-record[1] diff --git a/trunk/tools/perf/Documentation/perf-help.txt b/trunk/tools/perf/Documentation/perf-help.txt new file mode 100644 index 000000000000..514391818d1f --- /dev/null +++ b/trunk/tools/perf/Documentation/perf-help.txt @@ -0,0 +1,38 @@ +perf-help(1) +============ + +NAME +---- +perf-help - display help information about perf + +SYNOPSIS +-------- +'perf help' [-a|--all] [COMMAND] + +DESCRIPTION +----------- + +With no options and no COMMAND given, the synopsis of the 'perf' +command and a list of the most commonly used perf commands are printed +on the standard output. + +If the option '--all' or '-a' is given, then all available commands are +printed on the standard output. + +If a perf command is named, a manual page for that command is brought +up. The 'man' program is used by default for this purpose, but this +can be overridden by other options or configuration variables. + +Note that `perf --help ...` is identical to `perf help ...` because the +former is internally converted into the latter. + +OPTIONS +------- +-a:: +--all:: + Prints all the available commands on the standard output. This + option supersedes any other option. + +PERF +---- +Part of the linkperf:perf[1] suite diff --git a/trunk/tools/perf/Documentation/perf-list.txt b/trunk/tools/perf/Documentation/perf-list.txt new file mode 100644 index 000000000000..8290b9422668 --- /dev/null +++ b/trunk/tools/perf/Documentation/perf-list.txt @@ -0,0 +1,25 @@ +perf-list(1) +============ + +NAME +---- +perf-list - List all symbolic event types + +SYNOPSIS +-------- +[verse] +'perf list' + +DESCRIPTION +----------- +This command displays the symbolic event types which can be selected in the +various perf commands with the -e option. + +OPTIONS +------- +None + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-top[1], +linkperf:perf-record[1] diff --git a/trunk/tools/perf/Documentation/perf-record.txt b/trunk/tools/perf/Documentation/perf-record.txt new file mode 100644 index 000000000000..1dbc1eeb4c01 --- /dev/null +++ b/trunk/tools/perf/Documentation/perf-record.txt @@ -0,0 +1,42 @@ +perf-record(1) +============== + +NAME +---- +perf-record - Run a command and record its profile into perf.data + +SYNOPSIS +-------- +[verse] +'perf record' [-e | --event=EVENT] [-l] [-a] +'perf record' [-e | --event=EVENT] [-l] [-a] -- [] + +DESCRIPTION +----------- +This command runs a command and gathers a performance counter profile +from it, into perf.data - without displaying anything. + +This file can then be inspected later on, using 'perf report'. + + +OPTIONS +------- +...:: + Any command you can specify in a shell. + +-e:: +--event=:: + Select the PMU event. Selection can be a symbolic event name + (use 'perf list' to list all events) or a raw PMU + event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + +-a:: + system-wide collection + +-l:: + scale counter values + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/trunk/tools/perf/Documentation/perf-report.txt b/trunk/tools/perf/Documentation/perf-report.txt new file mode 100644 index 000000000000..52d3fc6846a9 --- /dev/null +++ b/trunk/tools/perf/Documentation/perf-report.txt @@ -0,0 +1,26 @@ +perf-report(1) +============== + +NAME +---- +perf-report - Read perf.data (created by perf record) and display the profile + +SYNOPSIS +-------- +[verse] +'perf report' [-i | --input=file] + +DESCRIPTION +----------- +This command displays the performance counter profile information recorded +via perf report. + +OPTIONS +------- +-i:: +--input=:: + Input file name. (default: perf.data) + +SEE ALSO +-------- +linkperf:perf-stat[1] diff --git a/trunk/tools/perf/Documentation/perf-stat.txt b/trunk/tools/perf/Documentation/perf-stat.txt new file mode 100644 index 000000000000..c368a72721d7 --- /dev/null +++ b/trunk/tools/perf/Documentation/perf-stat.txt @@ -0,0 +1,66 @@ +perf-stat(1) +============ + +NAME +---- +perf-stat - Run a command and gather performance counter statistics + +SYNOPSIS +-------- +[verse] +'perf stat' [-e | --event=EVENT] [-l] [-a] +'perf stat' [-e | --event=EVENT] [-l] [-a] -- [] + +DESCRIPTION +----------- +This command runs a command and gathers performance counter statistics +from it. + + +OPTIONS +------- +...:: + Any command you can specify in a shell. + + +-e:: +--event=:: + Select the PMU event. Selection can be a symbolic event name + (use 'perf list' to list all events) or a raw PMU + event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + +-i:: +--inherit:: + child tasks inherit counters +-p:: +--pid=:: + stat events on existing pid + +-a:: + system-wide collection + +-l:: + scale counter values + +EXAMPLES +-------- + +$ perf stat -- make -j + + Performance counter stats for 'make -j': + + 8117.370256 task clock ticks # 11.281 CPU utilization factor + 678 context switches # 0.000 M/sec + 133 CPU migrations # 0.000 M/sec + 235724 pagefaults # 0.029 M/sec + 24821162526 CPU cycles # 3057.784 M/sec + 18687303457 instructions # 2302.138 M/sec + 172158895 cache references # 21.209 M/sec + 27075259 cache misses # 3.335 M/sec + + Wall-clock time elapsed: 719.554352 msecs + +SEE ALSO +-------- +linkperf:perf-top[1], linkperf:perf-list[1] diff --git a/trunk/tools/perf/Documentation/perf-top.txt b/trunk/tools/perf/Documentation/perf-top.txt new file mode 100644 index 000000000000..539d01289725 --- /dev/null +++ b/trunk/tools/perf/Documentation/perf-top.txt @@ -0,0 +1,39 @@ +perf-top(1) +=========== + +NAME +---- +perf-top - Run a command and profile it + +SYNOPSIS +-------- +[verse] +'perf top' [-e | --event=EVENT] [-l] [-a] + +DESCRIPTION +----------- +This command runs a command and gathers a performance counter profile +from it. + + +OPTIONS +------- +...:: + Any command you can specify in a shell. + +-e:: +--event=:: + Select the PMU event. Selection can be a symbolic event name + (use 'perf list' to list all events) or a raw PMU + event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + +-a:: + system-wide collection + +-l:: + scale counter values + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/trunk/tools/perf/Documentation/perf.txt b/trunk/tools/perf/Documentation/perf.txt new file mode 100644 index 000000000000..69c832557199 --- /dev/null +++ b/trunk/tools/perf/Documentation/perf.txt @@ -0,0 +1,24 @@ +perf(1) +======= + +NAME +---- +perf - Performance analysis tools for Linux + +SYNOPSIS +-------- +[verse] +'perf' [--version] [--help] COMMAND [ARGS] + +DESCRIPTION +----------- +Performance counters for Linux are are a new kernel-based subsystem +that provide a framework for all things performance analysis. It +covers hardware level (CPU/PMU, Performance Monitoring Unit) features +and software features (software counters, tracepoints) as well. + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-top[1], +linkperf:perf-record[1], linkperf:perf-report[1], +linkperf:perf-list[1] diff --git a/trunk/tools/perf/Makefile b/trunk/tools/perf/Makefile new file mode 100644 index 000000000000..0cbd5d6874ec --- /dev/null +++ b/trunk/tools/perf/Makefile @@ -0,0 +1,929 @@ +# The default target of this Makefile is... +all:: + +# Define V=1 to have a more verbose compile. +# +# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf() +# or vsnprintf() return -1 instead of number of characters which would +# have been written to the final string if enough space had been available. +# +# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds +# when attempting to read from an fopen'ed directory. +# +# Define NO_OPENSSL environment variable if you do not have OpenSSL. +# This also implies MOZILLA_SHA1. +# +# Define CURLDIR=/foo/bar if your curl header and library files are in +# /foo/bar/include and /foo/bar/lib directories. +# +# Define EXPATDIR=/foo/bar if your expat header and library files are in +# /foo/bar/include and /foo/bar/lib directories. +# +# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent. +# +# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks +# d_type in struct dirent (latest Cygwin -- will be fixed soonish). +# +# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.) +# do not support the 'size specifiers' introduced by C99, namely ll, hh, +# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t). +# some C compilers supported these specifiers prior to C99 as an extension. +# +# Define NO_STRCASESTR if you don't have strcasestr. +# +# Define NO_MEMMEM if you don't have memmem. +# +# Define NO_STRTOUMAX if you don't have strtoumax in the C library. +# If your compiler also does not support long long or does not have +# strtoull, define NO_STRTOULL. +# +# Define NO_SETENV if you don't have setenv in the C library. +# +# Define NO_UNSETENV if you don't have unsetenv in the C library. +# +# Define NO_MKDTEMP if you don't have mkdtemp in the C library. +# +# Define NO_SYS_SELECT_H if you don't have sys/select.h. +# +# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link. +# Enable it on Windows. By default, symrefs are still used. +# +# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability +# tests. These tests take up a significant amount of the total test time +# but are not needed unless you plan to talk to SVN repos. +# +# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink +# installed in /sw, but don't want PERF to link against any libraries +# installed there. If defined you may specify your own (or Fink's) +# include directories and library directories by defining CFLAGS +# and LDFLAGS appropriately. +# +# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X, +# have DarwinPorts installed in /opt/local, but don't want PERF to +# link against any libraries installed there. If defined you may +# specify your own (or DarwinPort's) include directories and +# library directories by defining CFLAGS and LDFLAGS appropriately. +# +# Define PPC_SHA1 environment variable when running make to make use of +# a bundled SHA1 routine optimized for PowerPC. +# +# Define ARM_SHA1 environment variable when running make to make use of +# a bundled SHA1 routine optimized for ARM. +# +# Define MOZILLA_SHA1 environment variable when running make to make use of +# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast +# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default +# choice) has very fast version optimized for i586. +# +# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin). +# +# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin). +# +# Define NEEDS_SOCKET if linking with libc is not enough (SunOS, +# Patrick Mauritz). +# +# Define NO_MMAP if you want to avoid mmap. +# +# Define NO_PTHREADS if you do not have or do not want to use Pthreads. +# +# Define NO_PREAD if you have a problem with pread() system call (e.g. +# cygwin.dll before v1.5.22). +# +# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is +# generally faster on your platform than accessing the working directory. +# +# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support +# the executable mode bit, but doesn't really do so. +# +# Define NO_IPV6 if you lack IPv6 support and getaddrinfo(). +# +# Define NO_SOCKADDR_STORAGE if your platform does not have struct +# sockaddr_storage. +# +# Define NO_ICONV if your libc does not properly support iconv. +# +# Define OLD_ICONV if your library has an old iconv(), where the second +# (input buffer pointer) parameter is declared with type (const char **). +# +# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound. +# +# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib" +# that tells runtime paths to dynamic libraries; +# "-Wl,-rpath=/path/lib" is used instead. +# +# Define USE_NSEC below if you want perf to care about sub-second file mtimes +# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and +# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely +# randomly break unless your underlying filesystem supports those sub-second +# times (my ext3 doesn't). +# +# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of +# "st_ctim" +# +# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec" +# available. This automatically turns USE_NSEC off. +# +# Define USE_STDEV below if you want perf to care about the underlying device +# change being considered an inode change from the update-index perspective. +# +# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks +# field that counts the on-disk footprint in 512-byte blocks. +# +# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8 +# +# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72. +# +# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's +# MakeMaker (e.g. using ActiveState under Cygwin). +# +# Define NO_PERL if you do not want Perl scripts or libraries at all. +# +# Define INTERNAL_QSORT to use Git's implementation of qsort(), which +# is a simplified version of the merge sort used in glibc. This is +# recommended if Git triggers O(n^2) behavior in your platform's qsort(). +# +# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call +# your external grep (e.g., if your system lacks grep, if its grep is +# broken, or spawning external process is slower than built-in grep perf has). + +PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE + @$(SHELL_PATH) util/PERF-VERSION-GEN +-include PERF-VERSION-FILE + +uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') +uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') +uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not') +uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') +uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not') +uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not') + +# CFLAGS and LDFLAGS are for the users to override from the command line. + +CFLAGS = -ggdb3 -Wall -Werror -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -O6 +LDFLAGS = -lpthread -lrt -lelf +ALL_CFLAGS = $(CFLAGS) +ALL_LDFLAGS = $(LDFLAGS) +STRIP ?= strip + +# Among the variables below, these: +# perfexecdir +# template_dir +# mandir +# infodir +# htmldir +# ETC_PERFCONFIG (but not sysconfdir) +# can be specified as a relative path some/where/else; +# this is interpreted as relative to $(prefix) and "perf" at +# runtime figures out where they are based on the path to the executable. +# This can help installing the suite in a relocatable way. + +prefix = $(HOME) +bindir_relative = bin +bindir = $(prefix)/$(bindir_relative) +mandir = share/man +infodir = share/info +perfexecdir = libexec/perf-core +sharedir = $(prefix)/share +template_dir = share/perf-core/templates +htmldir = share/doc/perf-doc +ifeq ($(prefix),/usr) +sysconfdir = /etc +ETC_PERFCONFIG = $(sysconfdir)/perfconfig +else +sysconfdir = $(prefix)/etc +ETC_PERFCONFIG = etc/perfconfig +endif +lib = lib +# DESTDIR= + +export prefix bindir sharedir sysconfdir + +CC = gcc +AR = ar +RM = rm -f +TAR = tar +FIND = find +INSTALL = install +RPMBUILD = rpmbuild +PTHREAD_LIBS = -lpthread + +# sparse is architecture-neutral, which means that we need to tell it +# explicitly what architecture to check for. Fix this up for yours.. +SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ + + + +### --- END CONFIGURATION SECTION --- + +# Those must not be GNU-specific; they are shared with perl/ which may +# be built by a different compiler. (Note that this is an artifact now +# but it still might be nice to keep that distinction.) +BASIC_CFLAGS = +BASIC_LDFLAGS = + +# Guard against environment variables +BUILTIN_OBJS = +BUILT_INS = +COMPAT_CFLAGS = +COMPAT_OBJS = +LIB_H = +LIB_OBJS = +SCRIPT_PERL = +SCRIPT_SH = +TEST_PROGRAMS = + +# +# No scripts right now: +# + +# SCRIPT_SH += perf-am.sh + +# +# No Perl scripts right now: +# + +# SCRIPT_PERL += perf-add--interactive.perl + +SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \ + $(patsubst %.perl,%,$(SCRIPT_PERL)) + +# Empty... +EXTRA_PROGRAMS = + +# ... and all the rest that could be moved out of bindir to perfexecdir +PROGRAMS += $(EXTRA_PROGRAMS) + +# +# Single 'perf' binary right now: +# +PROGRAMS += perf + +# List built-in command $C whose implementation cmd_$C() is not in +# builtin-$C.o but is linked in as part of some other command. +# +# None right now: +# +# BUILT_INS += perf-init $X + +# what 'all' will build and 'install' will install, in perfexecdir +ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) + +# what 'all' will build but not install in perfexecdir +OTHER_PROGRAMS = perf$X + +# Set paths to tools early so that they can be used for version tests. +ifndef SHELL_PATH + SHELL_PATH = /bin/sh +endif +ifndef PERL_PATH + PERL_PATH = /usr/bin/perl +endif + +export PERL_PATH + +LIB_FILE=libperf.a + +LIB_H += ../../include/linux/perf_counter.h +LIB_H += perf.h +LIB_H += util/list.h +LIB_H += util/rbtree.h +LIB_H += util/levenshtein.h +LIB_H += util/parse-options.h +LIB_H += util/parse-events.h +LIB_H += util/quote.h +LIB_H += util/util.h +LIB_H += util/help.h +LIB_H += util/strbuf.h +LIB_H += util/string.h +LIB_H += util/run-command.h +LIB_H += util/sigchain.h +LIB_H += util/symbol.h +LIB_H += util/color.h + +LIB_OBJS += util/abspath.o +LIB_OBJS += util/alias.o +LIB_OBJS += util/config.o +LIB_OBJS += util/ctype.o +LIB_OBJS += util/environment.o +LIB_OBJS += util/exec_cmd.o +LIB_OBJS += util/help.o +LIB_OBJS += util/levenshtein.o +LIB_OBJS += util/parse-options.o +LIB_OBJS += util/parse-events.o +LIB_OBJS += util/path.o +LIB_OBJS += util/rbtree.o +LIB_OBJS += util/run-command.o +LIB_OBJS += util/quote.o +LIB_OBJS += util/strbuf.o +LIB_OBJS += util/string.o +LIB_OBJS += util/usage.o +LIB_OBJS += util/wrapper.o +LIB_OBJS += util/sigchain.o +LIB_OBJS += util/symbol.o +LIB_OBJS += util/color.o +LIB_OBJS += util/pager.o + +BUILTIN_OBJS += builtin-annotate.o +BUILTIN_OBJS += builtin-help.o +BUILTIN_OBJS += builtin-list.o +BUILTIN_OBJS += builtin-record.o +BUILTIN_OBJS += builtin-report.o +BUILTIN_OBJS += builtin-stat.o +BUILTIN_OBJS += builtin-top.o + +PERFLIBS = $(LIB_FILE) +EXTLIBS = + +# +# Platform specific tweaks +# + +# We choose to avoid "if .. else if .. else .. endif endif" +# because maintaining the nesting to match is a pain. If +# we had "elif" things would have been much nicer... + +-include config.mak.autogen +-include config.mak + +ifeq ($(uname_S),Darwin) + ifndef NO_FINK + ifeq ($(shell test -d /sw/lib && echo y),y) + BASIC_CFLAGS += -I/sw/include + BASIC_LDFLAGS += -L/sw/lib + endif + endif + ifndef NO_DARWIN_PORTS + ifeq ($(shell test -d /opt/local/lib && echo y),y) + BASIC_CFLAGS += -I/opt/local/include + BASIC_LDFLAGS += -L/opt/local/lib + endif + endif + PTHREAD_LIBS = +endif + +ifndef CC_LD_DYNPATH + ifdef NO_R_TO_GCC_LINKER + # Some gcc does not accept and pass -R to the linker to specify + # the runtime dynamic library path. + CC_LD_DYNPATH = -Wl,-rpath, + else + CC_LD_DYNPATH = -R + endif +endif + +ifdef ZLIB_PATH + BASIC_CFLAGS += -I$(ZLIB_PATH)/include + EXTLIBS += -L$(ZLIB_PATH)/$(lib) $(CC_LD_DYNPATH)$(ZLIB_PATH)/$(lib) +endif +EXTLIBS += -lz + +ifdef NEEDS_SOCKET + EXTLIBS += -lsocket +endif +ifdef NEEDS_NSL + EXTLIBS += -lnsl +endif +ifdef NO_D_TYPE_IN_DIRENT + BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT +endif +ifdef NO_D_INO_IN_DIRENT + BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT +endif +ifdef NO_ST_BLOCKS_IN_STRUCT_STAT + BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT +endif +ifdef USE_NSEC + BASIC_CFLAGS += -DUSE_NSEC +endif +ifdef USE_ST_TIMESPEC + BASIC_CFLAGS += -DUSE_ST_TIMESPEC +endif +ifdef NO_NSEC + BASIC_CFLAGS += -DNO_NSEC +endif +ifdef NO_C99_FORMAT + BASIC_CFLAGS += -DNO_C99_FORMAT +endif +ifdef SNPRINTF_RETURNS_BOGUS + COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS + COMPAT_OBJS += compat/snprintf.o +endif +ifdef FREAD_READS_DIRECTORIES + COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES + COMPAT_OBJS += compat/fopen.o +endif +ifdef NO_SYMLINK_HEAD + BASIC_CFLAGS += -DNO_SYMLINK_HEAD +endif +ifdef NO_STRCASESTR + COMPAT_CFLAGS += -DNO_STRCASESTR + COMPAT_OBJS += compat/strcasestr.o +endif +ifdef NO_STRTOUMAX + COMPAT_CFLAGS += -DNO_STRTOUMAX + COMPAT_OBJS += compat/strtoumax.o +endif +ifdef NO_STRTOULL + COMPAT_CFLAGS += -DNO_STRTOULL +endif +ifdef NO_SETENV + COMPAT_CFLAGS += -DNO_SETENV + COMPAT_OBJS += compat/setenv.o +endif +ifdef NO_MKDTEMP + COMPAT_CFLAGS += -DNO_MKDTEMP + COMPAT_OBJS += compat/mkdtemp.o +endif +ifdef NO_UNSETENV + COMPAT_CFLAGS += -DNO_UNSETENV + COMPAT_OBJS += compat/unsetenv.o +endif +ifdef NO_SYS_SELECT_H + BASIC_CFLAGS += -DNO_SYS_SELECT_H +endif +ifdef NO_MMAP + COMPAT_CFLAGS += -DNO_MMAP + COMPAT_OBJS += compat/mmap.o +else + ifdef USE_WIN32_MMAP + COMPAT_CFLAGS += -DUSE_WIN32_MMAP + COMPAT_OBJS += compat/win32mmap.o + endif +endif +ifdef NO_PREAD + COMPAT_CFLAGS += -DNO_PREAD + COMPAT_OBJS += compat/pread.o +endif +ifdef NO_FAST_WORKING_DIRECTORY + BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY +endif +ifdef NO_TRUSTABLE_FILEMODE + BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE +endif +ifdef NO_IPV6 + BASIC_CFLAGS += -DNO_IPV6 +endif +ifdef NO_UINTMAX_T + BASIC_CFLAGS += -Duintmax_t=uint32_t +endif +ifdef NO_SOCKADDR_STORAGE +ifdef NO_IPV6 + BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in +else + BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6 +endif +endif +ifdef NO_INET_NTOP + LIB_OBJS += compat/inet_ntop.o +endif +ifdef NO_INET_PTON + LIB_OBJS += compat/inet_pton.o +endif + +ifdef NO_ICONV + BASIC_CFLAGS += -DNO_ICONV +endif + +ifdef OLD_ICONV + BASIC_CFLAGS += -DOLD_ICONV +endif + +ifdef NO_DEFLATE_BOUND + BASIC_CFLAGS += -DNO_DEFLATE_BOUND +endif + +ifdef PPC_SHA1 + SHA1_HEADER = "ppc/sha1.h" + LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o +else +ifdef ARM_SHA1 + SHA1_HEADER = "arm/sha1.h" + LIB_OBJS += arm/sha1.o arm/sha1_arm.o +else +ifdef MOZILLA_SHA1 + SHA1_HEADER = "mozilla-sha1/sha1.h" + LIB_OBJS += mozilla-sha1/sha1.o +else + SHA1_HEADER = + EXTLIBS += $(LIB_4_CRYPTO) +endif +endif +endif +ifdef NO_PERL_MAKEMAKER + export NO_PERL_MAKEMAKER +endif +ifdef NO_HSTRERROR + COMPAT_CFLAGS += -DNO_HSTRERROR + COMPAT_OBJS += compat/hstrerror.o +endif +ifdef NO_MEMMEM + COMPAT_CFLAGS += -DNO_MEMMEM + COMPAT_OBJS += compat/memmem.o +endif +ifdef INTERNAL_QSORT + COMPAT_CFLAGS += -DINTERNAL_QSORT + COMPAT_OBJS += compat/qsort.o +endif +ifdef RUNTIME_PREFIX + COMPAT_CFLAGS += -DRUNTIME_PREFIX +endif + +ifdef DIR_HAS_BSD_GROUP_SEMANTICS + COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS +endif +ifdef NO_EXTERNAL_GREP + BASIC_CFLAGS += -DNO_EXTERNAL_GREP +endif + +ifeq ($(PERL_PATH),) +NO_PERL=NoThanks +endif + +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) +PRINT_DIR = --no-print-directory +else # "make -w" +NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) +ifndef V + QUIET_CC = @echo ' ' CC $@; + QUIET_AR = @echo ' ' AR $@; + QUIET_LINK = @echo ' ' LINK $@; + QUIET_BUILT_IN = @echo ' ' BUILTIN $@; + QUIET_GEN = @echo ' ' GEN $@; + QUIET_SUBDIR0 = +@subdir= + QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \ + $(MAKE) $(PRINT_DIR) -C $$subdir + export V + export QUIET_GEN + export QUIET_BUILT_IN +endif +endif + +ifdef ASCIIDOC8 + export ASCIIDOC8 +endif + +# Shell quote (do not use $(call) to accommodate ancient setups); + +SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER)) +ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) + +DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) +bindir_SQ = $(subst ','\'',$(bindir)) +bindir_relative_SQ = $(subst ','\'',$(bindir_relative)) +mandir_SQ = $(subst ','\'',$(mandir)) +infodir_SQ = $(subst ','\'',$(infodir)) +perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) +template_dir_SQ = $(subst ','\'',$(template_dir)) +htmldir_SQ = $(subst ','\'',$(htmldir)) +prefix_SQ = $(subst ','\'',$(prefix)) + +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) + +LIBS = $(PERFLIBS) $(EXTLIBS) + +BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \ + $(COMPAT_CFLAGS) +LIB_OBJS += $(COMPAT_OBJS) + +ALL_CFLAGS += $(BASIC_CFLAGS) +ALL_LDFLAGS += $(BASIC_LDFLAGS) + +export TAR INSTALL DESTDIR SHELL_PATH + + +### Build rules + +SHELL = $(SHELL_PATH) + +all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS +ifneq (,$X) + $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';) +endif + +all:: + +please_set_SHELL_PATH_to_a_more_modern_shell: + @$$(:) + +shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell + +strip: $(PROGRAMS) perf$X + $(STRIP) $(STRIP_OPTS) $(PROGRAMS) perf$X + +perf.o: perf.c common-cmds.h PERF-CFLAGS + $(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \ + '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ + $(ALL_CFLAGS) -c $(filter %.c,$^) + +perf$X: perf.o $(BUILTIN_OBJS) $(PERFLIBS) + $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ perf.o \ + $(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS) + +builtin-help.o: builtin-help.c common-cmds.h PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \ + '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ + '-DPERF_MAN_PATH="$(mandir_SQ)"' \ + '-DPERF_INFO_PATH="$(infodir_SQ)"' $< + +$(BUILT_INS): perf$X + $(QUIET_BUILT_IN)$(RM) $@ && \ + ln perf$X $@ 2>/dev/null || \ + ln -s perf$X $@ 2>/dev/null || \ + cp perf$X $@ + +common-cmds.h: util/generate-cmdlist.sh command-list.txt + +common-cmds.h: $(wildcard Documentation/perf-*.txt) + $(QUIET_GEN)util/generate-cmdlist.sh > $@+ && mv $@+ $@ + +$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh + $(QUIET_GEN)$(RM) $@ $@+ && \ + sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \ + -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \ + -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \ + -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \ + -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ + $@.sh >$@+ && \ + chmod +x $@+ && \ + mv $@+ $@ + +configure: configure.ac + $(QUIET_GEN)$(RM) $@ $<+ && \ + sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \ + $< > $<+ && \ + autoconf -o $@ $<+ && \ + $(RM) $<+ + +# These can record PERF_VERSION +perf.o perf.spec \ + $(patsubst %.sh,%,$(SCRIPT_SH)) \ + $(patsubst %.perl,%,$(SCRIPT_PERL)) \ + : PERF-VERSION-FILE + +%.o: %.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $< +%.s: %.c PERF-CFLAGS + $(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $< +%.o: %.S + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $< + +util/exec_cmd.o: util/exec_cmd.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \ + '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ + '-DBINDIR="$(bindir_relative_SQ)"' \ + '-DPREFIX="$(prefix_SQ)"' \ + $< + +builtin-init-db.o: builtin-init-db.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $< + +util/config.o: util/config.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +perf-%$X: %.o $(PERFLIBS) + $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) + +$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) +$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) +builtin-revert.o wt-status.o: wt-status.h + +$(LIB_FILE): $(LIB_OBJS) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS) + +doc: + $(MAKE) -C Documentation all + +man: + $(MAKE) -C Documentation man + +html: + $(MAKE) -C Documentation html + +info: + $(MAKE) -C Documentation info + +pdf: + $(MAKE) -C Documentation pdf + +TAGS: + $(RM) TAGS + $(FIND) . -name '*.[hcS]' -print | xargs etags -a + +tags: + $(RM) tags + $(FIND) . -name '*.[hcS]' -print | xargs ctags -a + +cscope: + $(RM) cscope* + $(FIND) . -name '*.[hcS]' -print | xargs cscope -b + +### Detect prefix changes +TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\ + $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ) + +PERF-CFLAGS: .FORCE-PERF-CFLAGS + @FLAGS='$(TRACK_CFLAGS)'; \ + if test x"$$FLAGS" != x"`cat PERF-CFLAGS 2>/dev/null`" ; then \ + echo 1>&2 " * new build flags or prefix"; \ + echo "$$FLAGS" >PERF-CFLAGS; \ + fi + +# We need to apply sq twice, once to protect from the shell +# that runs PERF-BUILD-OPTIONS, and then again to protect it +# and the first level quoting from the shell that runs "echo". +PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS + @echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@ + @echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@ + @echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@ + @echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@ + +### Testing rules + +# +# None right now: +# +# TEST_PROGRAMS += test-something$X + +all:: $(TEST_PROGRAMS) + +# GNU make supports exporting all variables by "export" without parameters. +# However, the environment gets quite big, and some programs have problems +# with that. + +export NO_SVN_TESTS + +check: common-cmds.h + if sparse; \ + then \ + for i in *.c */*.c; \ + do \ + sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \ + done; \ + else \ + echo 2>&1 "Did you mean 'make test'?"; \ + exit 1; \ + fi + +remove-dashes: + ./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS) + +### Installation rules + +ifneq ($(filter /%,$(firstword $(template_dir))),) +template_instdir = $(template_dir) +else +template_instdir = $(prefix)/$(template_dir) +endif +export template_instdir + +ifneq ($(filter /%,$(firstword $(perfexecdir))),) +perfexec_instdir = $(perfexecdir) +else +perfexec_instdir = $(prefix)/$(perfexecdir) +endif +perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) +export perfexec_instdir + +install: all + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)' +ifdef BUILT_INS + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' + $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' +ifneq (,$X) + $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';) +endif +endif + +install-doc: + $(MAKE) -C Documentation install + +install-man: + $(MAKE) -C Documentation install-man + +install-html: + $(MAKE) -C Documentation install-html + +install-info: + $(MAKE) -C Documentation install-info + +install-pdf: + $(MAKE) -C Documentation install-pdf + +quick-install-doc: + $(MAKE) -C Documentation quick-install + +quick-install-man: + $(MAKE) -C Documentation quick-install-man + +quick-install-html: + $(MAKE) -C Documentation quick-install-html + + +### Maintainer's dist rules +# +# None right now +# +# +# perf.spec: perf.spec.in +# sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+ +# mv $@+ $@ +# +# PERF_TARNAME=perf-$(PERF_VERSION) +# dist: perf.spec perf-archive$(X) configure +# ./perf-archive --format=tar \ +# --prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar +# @mkdir -p $(PERF_TARNAME) +# @cp perf.spec configure $(PERF_TARNAME) +# @echo $(PERF_VERSION) > $(PERF_TARNAME)/version +# $(TAR) rf $(PERF_TARNAME).tar \ +# $(PERF_TARNAME)/perf.spec \ +# $(PERF_TARNAME)/configure \ +# $(PERF_TARNAME)/version +# @$(RM) -r $(PERF_TARNAME) +# gzip -f -9 $(PERF_TARNAME).tar +# +# htmldocs = perf-htmldocs-$(PERF_VERSION) +# manpages = perf-manpages-$(PERF_VERSION) +# dist-doc: +# $(RM) -r .doc-tmp-dir +# mkdir .doc-tmp-dir +# $(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc +# cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar . +# gzip -n -9 -f $(htmldocs).tar +# : +# $(RM) -r .doc-tmp-dir +# mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7 +# $(MAKE) -C Documentation DESTDIR=./ \ +# man1dir=../.doc-tmp-dir/man1 \ +# man5dir=../.doc-tmp-dir/man5 \ +# man7dir=../.doc-tmp-dir/man7 \ +# install +# cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar . +# gzip -n -9 -f $(manpages).tar +# $(RM) -r .doc-tmp-dir +# +# rpm: dist +# $(RPMBUILD) -ta $(PERF_TARNAME).tar.gz + +### Cleaning rules + +distclean: clean +# $(RM) configure + +clean: + $(RM) *.o */*.o $(LIB_FILE) + $(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X + $(RM) $(TEST_PROGRAMS) + $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags cscope* + $(RM) -r autom4te.cache + $(RM) config.log config.mak.autogen config.mak.append config.status config.cache + $(RM) -r $(PERF_TARNAME) .doc-tmp-dir + $(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz + $(RM) $(htmldocs).tar.gz $(manpages).tar.gz + $(MAKE) -C Documentation/ clean + $(RM) PERF-VERSION-FILE PERF-CFLAGS PERF-BUILD-OPTIONS + +.PHONY: all install clean strip +.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell +.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS +.PHONY: .FORCE-PERF-BUILD-OPTIONS + +### Make sure built-ins do not have dups and listed in perf.c +# +check-builtins:: + ./check-builtins.sh + +### Test suite coverage testing +# +# None right now +# +# .PHONY: coverage coverage-clean coverage-build coverage-report +# +# coverage: +# $(MAKE) coverage-build +# $(MAKE) coverage-report +# +# coverage-clean: +# rm -f *.gcda *.gcno +# +# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs +# COVERAGE_LDFLAGS = $(CFLAGS) -O0 -lgcov +# +# coverage-build: coverage-clean +# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all +# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \ +# -j1 test +# +# coverage-report: +# gcov -b *.c */*.c +# grep '^function.*called 0 ' *.c.gcov */*.c.gcov \ +# | sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \ +# | tee coverage-untested-functions diff --git a/trunk/tools/perf/builtin-annotate.c b/trunk/tools/perf/builtin-annotate.c new file mode 100644 index 000000000000..b1ed5f766cb3 --- /dev/null +++ b/trunk/tools/perf/builtin-annotate.c @@ -0,0 +1,1356 @@ +/* + * builtin-annotate.c + * + * Builtin annotate command: Analyze the perf.data input file, + * look up and read DSOs and symbol information and display + * a histogram of results, along various sorting keys. + */ +#include "builtin.h" + +#include "util/util.h" + +#include "util/color.h" +#include "util/list.h" +#include "util/cache.h" +#include "util/rbtree.h" +#include "util/symbol.h" +#include "util/string.h" + +#include "perf.h" + +#include "util/parse-options.h" +#include "util/parse-events.h" + +#define SHOW_KERNEL 1 +#define SHOW_USER 2 +#define SHOW_HV 4 + +static char const *input_name = "perf.data"; +static char *vmlinux = "vmlinux"; + +static char default_sort_order[] = "comm,symbol"; +static char *sort_order = default_sort_order; + +static int input; +static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; + +static int dump_trace = 0; +#define dprintf(x...) do { if (dump_trace) printf(x); } while (0) + +static int verbose; + +static unsigned long page_size; +static unsigned long mmap_window = 32; + +struct ip_event { + struct perf_event_header header; + __u64 ip; + __u32 pid, tid; +}; + +struct mmap_event { + struct perf_event_header header; + __u32 pid, tid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; +}; + +struct comm_event { + struct perf_event_header header; + __u32 pid, tid; + char comm[16]; +}; + +struct fork_event { + struct perf_event_header header; + __u32 pid, ppid; +}; + +struct period_event { + struct perf_event_header header; + __u64 time; + __u64 id; + __u64 sample_period; +}; + +typedef union event_union { + struct perf_event_header header; + struct ip_event ip; + struct mmap_event mmap; + struct comm_event comm; + struct fork_event fork; + struct period_event period; +} event_t; + +static LIST_HEAD(dsos); +static struct dso *kernel_dso; +static struct dso *vdso; + + +static void dsos__add(struct dso *dso) +{ + list_add_tail(&dso->node, &dsos); +} + +static struct dso *dsos__find(const char *name) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + if (strcmp(pos->name, name) == 0) + return pos; + return NULL; +} + +static struct dso *dsos__findnew(const char *name) +{ + struct dso *dso = dsos__find(name); + int nr; + + if (dso) + return dso; + + dso = dso__new(name, 0); + if (!dso) + goto out_delete_dso; + + nr = dso__load(dso, NULL, verbose); + if (nr < 0) { + if (verbose) + fprintf(stderr, "Failed to open: %s\n", name); + goto out_delete_dso; + } + if (!nr && verbose) { + fprintf(stderr, + "No symbols found in: %s, maybe install a debug package?\n", + name); + } + + dsos__add(dso); + + return dso; + +out_delete_dso: + dso__delete(dso); + return NULL; +} + +static void dsos__fprintf(FILE *fp) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + dso__fprintf(pos, fp); +} + +static struct symbol *vdso__find_symbol(struct dso *dso, __u64 ip) +{ + return dso__find_symbol(kernel_dso, ip); +} + +static int load_kernel(void) +{ + int err; + + kernel_dso = dso__new("[kernel]", 0); + if (!kernel_dso) + return -1; + + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); + if (err) { + dso__delete(kernel_dso); + kernel_dso = NULL; + } else + dsos__add(kernel_dso); + + vdso = dso__new("[vdso]", 0); + if (!vdso) + return -1; + + vdso->find_symbol = vdso__find_symbol; + + dsos__add(vdso); + + return err; +} + +struct map { + struct list_head node; + __u64 start; + __u64 end; + __u64 pgoff; + __u64 (*map_ip)(struct map *, __u64); + struct dso *dso; +}; + +static __u64 map__map_ip(struct map *map, __u64 ip) +{ + return ip - map->start + map->pgoff; +} + +static __u64 vdso__map_ip(struct map *map, __u64 ip) +{ + return ip; +} + +static struct map *map__new(struct mmap_event *event) +{ + struct map *self = malloc(sizeof(*self)); + + if (self != NULL) { + const char *filename = event->filename; + + self->start = event->start; + self->end = event->start + event->len; + self->pgoff = event->pgoff; + + self->dso = dsos__findnew(filename); + if (self->dso == NULL) + goto out_delete; + + if (self->dso == vdso) + self->map_ip = vdso__map_ip; + else + self->map_ip = map__map_ip; + } + return self; +out_delete: + free(self); + return NULL; +} + +static struct map *map__clone(struct map *self) +{ + struct map *map = malloc(sizeof(*self)); + + if (!map) + return NULL; + + memcpy(map, self, sizeof(*self)); + + return map; +} + +static int map__overlap(struct map *l, struct map *r) +{ + if (l->start > r->start) { + struct map *t = l; + l = r; + r = t; + } + + if (l->end > r->start) + return 1; + + return 0; +} + +static size_t map__fprintf(struct map *self, FILE *fp) +{ + return fprintf(fp, " %Lx-%Lx %Lx %s\n", + self->start, self->end, self->pgoff, self->dso->name); +} + + +struct thread { + struct rb_node rb_node; + struct list_head maps; + pid_t pid; + char *comm; +}; + +static struct thread *thread__new(pid_t pid) +{ + struct thread *self = malloc(sizeof(*self)); + + if (self != NULL) { + self->pid = pid; + self->comm = malloc(32); + if (self->comm) + snprintf(self->comm, 32, ":%d", self->pid); + INIT_LIST_HEAD(&self->maps); + } + + return self; +} + +static int thread__set_comm(struct thread *self, const char *comm) +{ + if (self->comm) + free(self->comm); + self->comm = strdup(comm); + return self->comm ? 0 : -ENOMEM; +} + +static size_t thread__fprintf(struct thread *self, FILE *fp) +{ + struct map *pos; + size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm); + + list_for_each_entry(pos, &self->maps, node) + ret += map__fprintf(pos, fp); + + return ret; +} + + +static struct rb_root threads; +static struct thread *last_match; + +static struct thread *threads__findnew(pid_t pid) +{ + struct rb_node **p = &threads.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + /* + * Font-end cache - PID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: + */ + if (last_match && last_match->pid == pid) + return last_match; + + while (*p != NULL) { + parent = *p; + th = rb_entry(parent, struct thread, rb_node); + + if (th->pid == pid) { + last_match = th; + return th; + } + + if (pid < th->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + th = thread__new(pid); + if (th != NULL) { + rb_link_node(&th->rb_node, parent, p); + rb_insert_color(&th->rb_node, &threads); + last_match = th; + } + + return th; +} + +static void thread__insert_map(struct thread *self, struct map *map) +{ + struct map *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &self->maps, node) { + if (map__overlap(pos, map)) { + list_del_init(&pos->node); + /* XXX leaks dsos */ + free(pos); + } + } + + list_add_tail(&map->node, &self->maps); +} + +static int thread__fork(struct thread *self, struct thread *parent) +{ + struct map *map; + + if (self->comm) + free(self->comm); + self->comm = strdup(parent->comm); + if (!self->comm) + return -ENOMEM; + + list_for_each_entry(map, &parent->maps, node) { + struct map *new = map__clone(map); + if (!new) + return -ENOMEM; + thread__insert_map(self, new); + } + + return 0; +} + +static struct map *thread__find_map(struct thread *self, __u64 ip) +{ + struct map *pos; + + if (self == NULL) + return NULL; + + list_for_each_entry(pos, &self->maps, node) + if (ip >= pos->start && ip <= pos->end) + return pos; + + return NULL; +} + +static size_t threads__fprintf(FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + + for (nd = rb_first(&threads); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); + + ret += thread__fprintf(pos, fp); + } + + return ret; +} + +/* + * histogram, sorted on item, collects counts + */ + +static struct rb_root hist; + +struct hist_entry { + struct rb_node rb_node; + + struct thread *thread; + struct map *map; + struct dso *dso; + struct symbol *sym; + __u64 ip; + char level; + + uint32_t count; +}; + +/* + * configurable sorting bits + */ + +struct sort_entry { + struct list_head list; + + char *header; + + int64_t (*cmp)(struct hist_entry *, struct hist_entry *); + int64_t (*collapse)(struct hist_entry *, struct hist_entry *); + size_t (*print)(FILE *fp, struct hist_entry *); +}; + +/* --sort pid */ + +static int64_t +sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static size_t +sort__thread_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid); +} + +static struct sort_entry sort_thread = { + .header = " Command: Pid", + .cmp = sort__thread_cmp, + .print = sort__thread_print, +}; + +/* --sort comm */ + +static int64_t +sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static int64_t +sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) +{ + char *comm_l = left->thread->comm; + char *comm_r = right->thread->comm; + + if (!comm_l || !comm_r) { + if (!comm_l && !comm_r) + return 0; + else if (!comm_l) + return -1; + else + return 1; + } + + return strcmp(comm_l, comm_r); +} + +static size_t +sort__comm_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s", self->thread->comm); +} + +static struct sort_entry sort_comm = { + .header = " Command", + .cmp = sort__comm_cmp, + .collapse = sort__comm_collapse, + .print = sort__comm_print, +}; + +/* --sort dso */ + +static int64_t +sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct dso *dso_l = left->dso; + struct dso *dso_r = right->dso; + + if (!dso_l || !dso_r) { + if (!dso_l && !dso_r) + return 0; + else if (!dso_l) + return -1; + else + return 1; + } + + return strcmp(dso_l->name, dso_r->name); +} + +static size_t +sort__dso_print(FILE *fp, struct hist_entry *self) +{ + if (self->dso) + return fprintf(fp, "%-25s", self->dso->name); + + return fprintf(fp, "%016llx ", (__u64)self->ip); +} + +static struct sort_entry sort_dso = { + .header = "Shared Object ", + .cmp = sort__dso_cmp, + .print = sort__dso_print, +}; + +/* --sort symbol */ + +static int64_t +sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) +{ + __u64 ip_l, ip_r; + + if (left->sym == right->sym) + return 0; + + ip_l = left->sym ? left->sym->start : left->ip; + ip_r = right->sym ? right->sym->start : right->ip; + + return (int64_t)(ip_r - ip_l); +} + +static size_t +sort__sym_print(FILE *fp, struct hist_entry *self) +{ + size_t ret = 0; + + if (verbose) + ret += fprintf(fp, "%#018llx ", (__u64)self->ip); + + if (self->sym) { + ret += fprintf(fp, "[%c] %s", + self->dso == kernel_dso ? 'k' : '.', self->sym->name); + } else { + ret += fprintf(fp, "%#016llx", (__u64)self->ip); + } + + return ret; +} + +static struct sort_entry sort_sym = { + .header = "Symbol", + .cmp = sort__sym_cmp, + .print = sort__sym_print, +}; + +static int sort__need_collapse = 0; + +struct sort_dimension { + char *name; + struct sort_entry *entry; + int taken; +}; + +static struct sort_dimension sort_dimensions[] = { + { .name = "pid", .entry = &sort_thread, }, + { .name = "comm", .entry = &sort_comm, }, + { .name = "dso", .entry = &sort_dso, }, + { .name = "symbol", .entry = &sort_sym, }, +}; + +static LIST_HEAD(hist_entry__sort_list); + +static int sort_dimension__add(char *tok) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { + struct sort_dimension *sd = &sort_dimensions[i]; + + if (sd->taken) + continue; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sd->entry->collapse) + sort__need_collapse = 1; + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; + + return 0; + } + + return -ESRCH; +} + +static int64_t +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + cmp = se->cmp(left, right); + if (cmp) + break; + } + + return cmp; +} + +static int64_t +hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + int64_t (*f)(struct hist_entry *, struct hist_entry *); + + f = se->collapse ?: se->cmp; + + cmp = f(left, right); + if (cmp) + break; + } + + return cmp; +} + +/* + * collect histogram counts + */ +static void hist_hit(struct hist_entry *he, __u64 ip) +{ + unsigned int sym_size, offset; + struct symbol *sym = he->sym; + + he->count++; + + if (!sym || !sym->hist) + return; + + sym_size = sym->end - sym->start; + offset = ip - sym->start; + + if (offset >= sym_size) + return; + + sym->hist_sum++; + sym->hist[offset]++; + + if (verbose >= 3) + printf("%p %s: count++ [ip: %p, %08Lx] => %Ld\n", + (void *)(unsigned long)he->sym->start, + he->sym->name, + (void *)(unsigned long)ip, ip - he->sym->start, + sym->hist[offset]); +} + +static int +hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, + struct symbol *sym, __u64 ip, char level) +{ + struct rb_node **p = &hist.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *he; + struct hist_entry entry = { + .thread = thread, + .map = map, + .dso = dso, + .sym = sym, + .ip = ip, + .level = level, + .count = 1, + }; + int cmp; + + while (*p != NULL) { + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__cmp(&entry, he); + + if (!cmp) { + hist_hit(he, ip); + + return 0; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + he = malloc(sizeof(*he)); + if (!he) + return -ENOMEM; + *he = entry; + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &hist); + + return 0; +} + +static void hist_entry__free(struct hist_entry *he) +{ + free(he); +} + +/* + * collapse the histogram + */ + +static struct rb_root collapse_hists; + +static void collapse__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &collapse_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + int64_t cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__collapse(iter, he); + + if (!cmp) { + iter->count += he->count; + hist_entry__free(he); + return; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &collapse_hists); +} + +static void collapse__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + + if (!sort__need_collapse) + return; + + next = rb_first(&hist); + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, &hist); + collapse__insert_entry(n); + } +} + +/* + * reverse the map, sort on count. + */ + +static struct rb_root output_hists; + +static void output__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &output_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + if (he->count > iter->count) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &output_hists); +} + +static void output__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + struct rb_root *tree = &hist; + + if (sort__need_collapse) + tree = &collapse_hists; + + next = rb_first(tree); + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, tree); + output__insert_entry(n); + } +} + +static void register_idle_thread(void) +{ + struct thread *thread = threads__findnew(0); + + if (thread == NULL || + thread__set_comm(thread, "[idle]")) { + fprintf(stderr, "problem inserting idle task.\n"); + exit(-1); + } +} + +static unsigned long total = 0, + total_mmap = 0, + total_comm = 0, + total_fork = 0, + total_unknown = 0; + +static int +process_overflow_event(event_t *event, unsigned long offset, unsigned long head) +{ + char level; + int show = 0; + struct dso *dso = NULL; + struct thread *thread = threads__findnew(event->ip.pid); + __u64 ip = event->ip.ip; + struct map *map = NULL; + + dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.misc, + event->ip.pid, + (void *)(long)ip); + + dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid); + + if (thread == NULL) { + fprintf(stderr, "problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + if (event->header.misc & PERF_EVENT_MISC_KERNEL) { + show = SHOW_KERNEL; + level = 'k'; + + dso = kernel_dso; + + dprintf(" ...... dso: %s\n", dso->name); + + } else if (event->header.misc & PERF_EVENT_MISC_USER) { + + show = SHOW_USER; + level = '.'; + + map = thread__find_map(thread, ip); + if (map != NULL) { + ip = map->map_ip(map, ip); + dso = map->dso; + } else { + /* + * If this is outside of all known maps, + * and is a negative address, try to look it + * up in the kernel dso, as it might be a + * vsyscall (which executes in user-mode): + */ + if ((long long)ip < 0) + dso = kernel_dso; + } + dprintf(" ...... dso: %s\n", dso ? dso->name : ""); + + } else { + show = SHOW_HV; + level = 'H'; + dprintf(" ...... dso: [hypervisor]\n"); + } + + if (show & show_mask) { + struct symbol *sym = NULL; + + if (dso) + sym = dso->find_symbol(dso, ip); + + if (hist_entry__add(thread, map, dso, sym, ip, level)) { + fprintf(stderr, + "problem incrementing symbol count, skipping event\n"); + return -1; + } + } + total++; + + return 0; +} + +static int +process_mmap_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->mmap.pid); + struct map *map = map__new(&event->mmap); + + dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->mmap.pid, + (void *)(long)event->mmap.start, + (void *)(long)event->mmap.len, + (void *)(long)event->mmap.pgoff, + event->mmap.filename); + + if (thread == NULL || map == NULL) { + dprintf("problem processing PERF_EVENT_MMAP, skipping event.\n"); + return 0; + } + + thread__insert_map(thread, map); + total_mmap++; + + return 0; +} + +static int +process_comm_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->comm.pid); + + dprintf("%p [%p]: PERF_EVENT_COMM: %s:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->comm.comm, event->comm.pid); + + if (thread == NULL || + thread__set_comm(thread, event->comm.comm)) { + dprintf("problem processing PERF_EVENT_COMM, skipping event.\n"); + return -1; + } + total_comm++; + + return 0; +} + +static int +process_fork_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->fork.pid); + struct thread *parent = threads__findnew(event->fork.ppid); + + dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->fork.pid, event->fork.ppid); + + if (!thread || !parent || thread__fork(thread, parent)) { + dprintf("problem processing PERF_EVENT_FORK, skipping event.\n"); + return -1; + } + total_fork++; + + return 0; +} + +static int +process_period_event(event_t *event, unsigned long offset, unsigned long head) +{ + dprintf("%p [%p]: PERF_EVENT_PERIOD: time:%Ld, id:%Ld: period:%Ld\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->period.time, + event->period.id, + event->period.sample_period); + + return 0; +} + +static int +process_event(event_t *event, unsigned long offset, unsigned long head) +{ + if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) + return process_overflow_event(event, offset, head); + + switch (event->header.type) { + case PERF_EVENT_MMAP: + return process_mmap_event(event, offset, head); + + case PERF_EVENT_COMM: + return process_comm_event(event, offset, head); + + case PERF_EVENT_FORK: + return process_fork_event(event, offset, head); + + case PERF_EVENT_PERIOD: + return process_period_event(event, offset, head); + /* + * We dont process them right now but they are fine: + */ + + case PERF_EVENT_THROTTLE: + case PERF_EVENT_UNTHROTTLE: + return 0; + + default: + return -1; + } + + return 0; +} + +static int +parse_line(FILE *file, struct symbol *sym, __u64 start, __u64 len) +{ + char *line = NULL, *tmp, *tmp2; + unsigned int offset; + size_t line_len; + __u64 line_ip; + int ret; + char *c; + + if (getline(&line, &line_len, file) < 0) + return -1; + if (!line) + return -1; + + c = strchr(line, '\n'); + if (c) + *c = 0; + + line_ip = -1; + offset = 0; + ret = -2; + + /* + * Strip leading spaces: + */ + tmp = line; + while (*tmp) { + if (*tmp != ' ') + break; + tmp++; + } + + if (*tmp) { + /* + * Parse hexa addresses followed by ':' + */ + line_ip = strtoull(tmp, &tmp2, 16); + if (*tmp2 != ':') + line_ip = -1; + } + + if (line_ip != -1) { + unsigned int hits = 0; + double percent = 0.0; + char *color = PERF_COLOR_NORMAL; + + offset = line_ip - start; + if (offset < len) + hits = sym->hist[offset]; + + if (sym->hist_sum) + percent = 100.0 * hits / sym->hist_sum; + + /* + * We color high-overhead entries in red, mid-overhead + * entries in green - and keep the low overhead places + * normal: + */ + if (percent >= 5.0) + color = PERF_COLOR_RED; + else { + if (percent > 0.5) + color = PERF_COLOR_GREEN; + } + + color_fprintf(stdout, color, " %7.2f", percent); + printf(" : "); + color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", line); + } else { + if (!*line) + printf(" :\n"); + else + printf(" : %s\n", line); + } + + return 0; +} + +static void annotate_sym(struct dso *dso, struct symbol *sym) +{ + char *filename = dso->name; + __u64 start, end, len; + char command[PATH_MAX*2]; + FILE *file; + + if (!filename) + return; + if (dso == kernel_dso) + filename = vmlinux; + + printf("\n------------------------------------------------\n"); + printf(" Percent | Source code & Disassembly of %s\n", filename); + printf("------------------------------------------------\n"); + + if (verbose >= 2) + printf("annotating [%p] %30s : [%p] %30s\n", dso, dso->name, sym, sym->name); + + start = sym->obj_start; + if (!start) + start = sym->start; + + end = start + sym->end - sym->start + 1; + len = sym->end - sym->start; + + sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s", (__u64)start, (__u64)end, filename); + + if (verbose >= 3) + printf("doing: %s\n", command); + + file = popen(command, "r"); + if (!file) + return; + + while (!feof(file)) { + if (parse_line(file, sym, start, len) < 0) + break; + } + + pclose(file); +} + +static void find_annotations(void) +{ + struct rb_node *nd; + struct dso *dso; + int count = 0; + + list_for_each_entry(dso, &dsos, node) { + + for (nd = rb_first(&dso->syms); nd; nd = rb_next(nd)) { + struct symbol *sym = rb_entry(nd, struct symbol, rb_node); + + if (sym->hist) { + annotate_sym(dso, sym); + count++; + } + } + } + + if (!count) + printf(" Error: symbol '%s' not present amongst the samples.\n", sym_hist_filter); +} + +static int __cmd_annotate(void) +{ + int ret, rc = EXIT_FAILURE; + unsigned long offset = 0; + unsigned long head = 0; + struct stat stat; + event_t *event; + uint32_t size; + char *buf; + + register_idle_thread(); + + input = open(input_name, O_RDONLY); + if (input < 0) { + perror("failed to open file"); + exit(-1); + } + + ret = fstat(input, &stat); + if (ret < 0) { + perror("failed to stat file"); + exit(-1); + } + + if (!stat.st_size) { + fprintf(stderr, "zero-sized file, nothing to do!\n"); + exit(0); + } + + if (load_kernel() < 0) { + perror("failed to load kernel symbols"); + return EXIT_FAILURE; + } + +remap: + buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, + MAP_SHARED, input, offset); + if (buf == MAP_FAILED) { + perror("failed to mmap file"); + exit(-1); + } + +more: + event = (event_t *)(buf + head); + + size = event->header.size; + if (!size) + size = 8; + + if (head + event->header.size >= page_size * mmap_window) { + unsigned long shift = page_size * (head / page_size); + int ret; + + ret = munmap(buf, page_size * mmap_window); + assert(ret == 0); + + offset += shift; + head -= shift; + goto remap; + } + + size = event->header.size; + + dprintf("%p [%p]: event: %d\n", + (void *)(offset + head), + (void *)(long)event->header.size, + event->header.type); + + if (!size || process_event(event, offset, head) < 0) { + + dprintf("%p [%p]: skipping unknown header type: %d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.type); + + total_unknown++; + + /* + * assume we lost track of the stream, check alignment, and + * increment a single u64 in the hope to catch on again 'soon'. + */ + + if (unlikely(head & 7)) + head &= ~7ULL; + + size = 8; + } + + head += size; + + if (offset + head < stat.st_size) + goto more; + + rc = EXIT_SUCCESS; + close(input); + + dprintf(" IP events: %10ld\n", total); + dprintf(" mmap events: %10ld\n", total_mmap); + dprintf(" comm events: %10ld\n", total_comm); + dprintf(" fork events: %10ld\n", total_fork); + dprintf(" unknown events: %10ld\n", total_unknown); + + if (dump_trace) + return 0; + + if (verbose >= 3) + threads__fprintf(stdout); + + if (verbose >= 2) + dsos__fprintf(stdout); + + collapse__resort(); + output__resort(); + + find_annotations(); + + return rc; +} + +static const char * const annotate_usage[] = { + "perf annotate [] ", + NULL +}; + +static const struct option options[] = { + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_STRING('s', "symbol", &sym_hist_filter, "symbol", + "symbol to annotate"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"), + OPT_END() +}; + +static void setup_sorting(void) +{ + char *tmp, *tok, *str = strdup(sort_order); + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + if (sort_dimension__add(tok) < 0) { + error("Unknown --sort key: `%s'", tok); + usage_with_options(annotate_usage, options); + } + } + + free(str); +} + +int cmd_annotate(int argc, const char **argv, const char *prefix) +{ + symbol__init(); + + page_size = getpagesize(); + + argc = parse_options(argc, argv, options, annotate_usage, 0); + + setup_sorting(); + + if (argc) { + /* + * Special case: if there's an argument left then assume tha + * it's a symbol filter: + */ + if (argc > 1) + usage_with_options(annotate_usage, options); + + sym_hist_filter = argv[0]; + } + + if (!sym_hist_filter) + usage_with_options(annotate_usage, options); + + setup_pager(); + + return __cmd_annotate(); +} diff --git a/trunk/tools/perf/builtin-help.c b/trunk/tools/perf/builtin-help.c new file mode 100644 index 000000000000..0f32dc3f3c4c --- /dev/null +++ b/trunk/tools/perf/builtin-help.c @@ -0,0 +1,461 @@ +/* + * builtin-help.c + * + * Builtin help command + */ +#include "util/cache.h" +#include "builtin.h" +#include "util/exec_cmd.h" +#include "common-cmds.h" +#include "util/parse-options.h" +#include "util/run-command.h" +#include "util/help.h" + +static struct man_viewer_list { + struct man_viewer_list *next; + char name[FLEX_ARRAY]; +} *man_viewer_list; + +static struct man_viewer_info_list { + struct man_viewer_info_list *next; + const char *info; + char name[FLEX_ARRAY]; +} *man_viewer_info_list; + +enum help_format { + HELP_FORMAT_MAN, + HELP_FORMAT_INFO, + HELP_FORMAT_WEB, +}; + +static int show_all = 0; +static enum help_format help_format = HELP_FORMAT_MAN; +static struct option builtin_help_options[] = { + OPT_BOOLEAN('a', "all", &show_all, "print all available commands"), + OPT_SET_INT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN), + OPT_SET_INT('w', "web", &help_format, "show manual in web browser", + HELP_FORMAT_WEB), + OPT_SET_INT('i', "info", &help_format, "show info page", + HELP_FORMAT_INFO), + OPT_END(), +}; + +static const char * const builtin_help_usage[] = { + "perf help [--all] [--man|--web|--info] [command]", + NULL +}; + +static enum help_format parse_help_format(const char *format) +{ + if (!strcmp(format, "man")) + return HELP_FORMAT_MAN; + if (!strcmp(format, "info")) + return HELP_FORMAT_INFO; + if (!strcmp(format, "web") || !strcmp(format, "html")) + return HELP_FORMAT_WEB; + die("unrecognized help format '%s'", format); +} + +static const char *get_man_viewer_info(const char *name) +{ + struct man_viewer_info_list *viewer; + + for (viewer = man_viewer_info_list; viewer; viewer = viewer->next) + { + if (!strcasecmp(name, viewer->name)) + return viewer->info; + } + return NULL; +} + +static int check_emacsclient_version(void) +{ + struct strbuf buffer = STRBUF_INIT; + struct child_process ec_process; + const char *argv_ec[] = { "emacsclient", "--version", NULL }; + int version; + + /* emacsclient prints its version number on stderr */ + memset(&ec_process, 0, sizeof(ec_process)); + ec_process.argv = argv_ec; + ec_process.err = -1; + ec_process.stdout_to_stderr = 1; + if (start_command(&ec_process)) { + fprintf(stderr, "Failed to start emacsclient.\n"); + return -1; + } + strbuf_read(&buffer, ec_process.err, 20); + close(ec_process.err); + + /* + * Don't bother checking return value, because "emacsclient --version" + * seems to always exits with code 1. + */ + finish_command(&ec_process); + + if (prefixcmp(buffer.buf, "emacsclient")) { + fprintf(stderr, "Failed to parse emacsclient version.\n"); + strbuf_release(&buffer); + return -1; + } + + strbuf_remove(&buffer, 0, strlen("emacsclient")); + version = atoi(buffer.buf); + + if (version < 22) { + fprintf(stderr, + "emacsclient version '%d' too old (< 22).\n", + version); + strbuf_release(&buffer); + return -1; + } + + strbuf_release(&buffer); + return 0; +} + +static void exec_woman_emacs(const char* path, const char *page) +{ + if (!check_emacsclient_version()) { + /* This works only with emacsclient version >= 22. */ + struct strbuf man_page = STRBUF_INIT; + + if (!path) + path = "emacsclient"; + strbuf_addf(&man_page, "(woman \"%s\")", page); + execlp(path, "emacsclient", "-e", man_page.buf, NULL); + warning("failed to exec '%s': %s", path, strerror(errno)); + } +} + +static void exec_man_konqueror(const char* path, const char *page) +{ + const char *display = getenv("DISPLAY"); + if (display && *display) { + struct strbuf man_page = STRBUF_INIT; + const char *filename = "kfmclient"; + + /* It's simpler to launch konqueror using kfmclient. */ + if (path) { + const char *file = strrchr(path, '/'); + if (file && !strcmp(file + 1, "konqueror")) { + char *new = strdup(path); + char *dest = strrchr(new, '/'); + + /* strlen("konqueror") == strlen("kfmclient") */ + strcpy(dest + 1, "kfmclient"); + path = new; + } + if (file) + filename = file; + } else + path = "kfmclient"; + strbuf_addf(&man_page, "man:%s(1)", page); + execlp(path, filename, "newTab", man_page.buf, NULL); + warning("failed to exec '%s': %s", path, strerror(errno)); + } +} + +static void exec_man_man(const char* path, const char *page) +{ + if (!path) + path = "man"; + execlp(path, "man", page, NULL); + warning("failed to exec '%s': %s", path, strerror(errno)); +} + +static void exec_man_cmd(const char *cmd, const char *page) +{ + struct strbuf shell_cmd = STRBUF_INIT; + strbuf_addf(&shell_cmd, "%s %s", cmd, page); + execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL); + warning("failed to exec '%s': %s", cmd, strerror(errno)); +} + +static void add_man_viewer(const char *name) +{ + struct man_viewer_list **p = &man_viewer_list; + size_t len = strlen(name); + + while (*p) + p = &((*p)->next); + *p = calloc(1, (sizeof(**p) + len + 1)); + strncpy((*p)->name, name, len); +} + +static int supported_man_viewer(const char *name, size_t len) +{ + return (!strncasecmp("man", name, len) || + !strncasecmp("woman", name, len) || + !strncasecmp("konqueror", name, len)); +} + +static void do_add_man_viewer_info(const char *name, + size_t len, + const char *value) +{ + struct man_viewer_info_list *new = calloc(1, sizeof(*new) + len + 1); + + strncpy(new->name, name, len); + new->info = strdup(value); + new->next = man_viewer_info_list; + man_viewer_info_list = new; +} + +static int add_man_viewer_path(const char *name, + size_t len, + const char *value) +{ + if (supported_man_viewer(name, len)) + do_add_man_viewer_info(name, len, value); + else + warning("'%s': path for unsupported man viewer.\n" + "Please consider using 'man..cmd' instead.", + name); + + return 0; +} + +static int add_man_viewer_cmd(const char *name, + size_t len, + const char *value) +{ + if (supported_man_viewer(name, len)) + warning("'%s': cmd for supported man viewer.\n" + "Please consider using 'man..path' instead.", + name); + else + do_add_man_viewer_info(name, len, value); + + return 0; +} + +static int add_man_viewer_info(const char *var, const char *value) +{ + const char *name = var + 4; + const char *subkey = strrchr(name, '.'); + + if (!subkey) + return error("Config with no key for man viewer: %s", name); + + if (!strcmp(subkey, ".path")) { + if (!value) + return config_error_nonbool(var); + return add_man_viewer_path(name, subkey - name, value); + } + if (!strcmp(subkey, ".cmd")) { + if (!value) + return config_error_nonbool(var); + return add_man_viewer_cmd(name, subkey - name, value); + } + + warning("'%s': unsupported man viewer sub key.", subkey); + return 0; +} + +static int perf_help_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "help.format")) { + if (!value) + return config_error_nonbool(var); + help_format = parse_help_format(value); + return 0; + } + if (!strcmp(var, "man.viewer")) { + if (!value) + return config_error_nonbool(var); + add_man_viewer(value); + return 0; + } + if (!prefixcmp(var, "man.")) + return add_man_viewer_info(var, value); + + return perf_default_config(var, value, cb); +} + +static struct cmdnames main_cmds, other_cmds; + +void list_common_cmds_help(void) +{ + int i, longest = 0; + + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + if (longest < strlen(common_cmds[i].name)) + longest = strlen(common_cmds[i].name); + } + + puts(" The most commonly used perf commands are:"); + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + printf(" %s ", common_cmds[i].name); + mput_char(' ', longest - strlen(common_cmds[i].name)); + puts(common_cmds[i].help); + } +} + +static int is_perf_command(const char *s) +{ + return is_in_cmdlist(&main_cmds, s) || + is_in_cmdlist(&other_cmds, s); +} + +static const char *prepend(const char *prefix, const char *cmd) +{ + size_t pre_len = strlen(prefix); + size_t cmd_len = strlen(cmd); + char *p = malloc(pre_len + cmd_len + 1); + memcpy(p, prefix, pre_len); + strcpy(p + pre_len, cmd); + return p; +} + +static const char *cmd_to_page(const char *perf_cmd) +{ + if (!perf_cmd) + return "perf"; + else if (!prefixcmp(perf_cmd, "perf")) + return perf_cmd; + else if (is_perf_command(perf_cmd)) + return prepend("perf-", perf_cmd); + else + return prepend("perf-", perf_cmd); +} + +static void setup_man_path(void) +{ + struct strbuf new_path = STRBUF_INIT; + const char *old_path = getenv("MANPATH"); + + /* We should always put ':' after our path. If there is no + * old_path, the ':' at the end will let 'man' to try + * system-wide paths after ours to find the manual page. If + * there is old_path, we need ':' as delimiter. */ + strbuf_addstr(&new_path, system_path(PERF_MAN_PATH)); + strbuf_addch(&new_path, ':'); + if (old_path) + strbuf_addstr(&new_path, old_path); + + setenv("MANPATH", new_path.buf, 1); + + strbuf_release(&new_path); +} + +static void exec_viewer(const char *name, const char *page) +{ + const char *info = get_man_viewer_info(name); + + if (!strcasecmp(name, "man")) + exec_man_man(info, page); + else if (!strcasecmp(name, "woman")) + exec_woman_emacs(info, page); + else if (!strcasecmp(name, "konqueror")) + exec_man_konqueror(info, page); + else if (info) + exec_man_cmd(info, page); + else + warning("'%s': unknown man viewer.", name); +} + +static void show_man_page(const char *perf_cmd) +{ + struct man_viewer_list *viewer; + const char *page = cmd_to_page(perf_cmd); + const char *fallback = getenv("PERF_MAN_VIEWER"); + + setup_man_path(); + for (viewer = man_viewer_list; viewer; viewer = viewer->next) + { + exec_viewer(viewer->name, page); /* will return when unable */ + } + if (fallback) + exec_viewer(fallback, page); + exec_viewer("man", page); + die("no man viewer handled the request"); +} + +static void show_info_page(const char *perf_cmd) +{ + const char *page = cmd_to_page(perf_cmd); + setenv("INFOPATH", system_path(PERF_INFO_PATH), 1); + execlp("info", "info", "perfman", page, NULL); +} + +static void get_html_page_path(struct strbuf *page_path, const char *page) +{ + struct stat st; + const char *html_path = system_path(PERF_HTML_PATH); + + /* Check that we have a perf documentation directory. */ + if (stat(mkpath("%s/perf.html", html_path), &st) + || !S_ISREG(st.st_mode)) + die("'%s': not a documentation directory.", html_path); + + strbuf_init(page_path, 0); + strbuf_addf(page_path, "%s/%s.html", html_path, page); +} + +/* + * If open_html is not defined in a platform-specific way (see for + * example compat/mingw.h), we use the script web--browse to display + * HTML. + */ +#ifndef open_html +static void open_html(const char *path) +{ + execl_perf_cmd("web--browse", "-c", "help.browser", path, NULL); +} +#endif + +static void show_html_page(const char *perf_cmd) +{ + const char *page = cmd_to_page(perf_cmd); + struct strbuf page_path; /* it leaks but we exec bellow */ + + get_html_page_path(&page_path, page); + + open_html(page_path.buf); +} + +int cmd_help(int argc, const char **argv, const char *prefix) +{ + const char *alias; + load_command_list("perf-", &main_cmds, &other_cmds); + + perf_config(perf_help_config, NULL); + + argc = parse_options(argc, argv, builtin_help_options, + builtin_help_usage, 0); + + if (show_all) { + printf("\n usage: %s\n\n", perf_usage_string); + list_commands("perf commands", &main_cmds, &other_cmds); + printf(" %s\n\n", perf_more_info_string); + return 0; + } + + if (!argv[0]) { + printf("\n usage: %s\n\n", perf_usage_string); + list_common_cmds_help(); + printf("\n %s\n\n", perf_more_info_string); + return 0; + } + + alias = alias_lookup(argv[0]); + if (alias && !is_perf_command(argv[0])) { + printf("`perf %s' is aliased to `%s'\n", argv[0], alias); + return 0; + } + + switch (help_format) { + case HELP_FORMAT_MAN: + show_man_page(argv[0]); + break; + case HELP_FORMAT_INFO: + show_info_page(argv[0]); + break; + case HELP_FORMAT_WEB: + show_html_page(argv[0]); + break; + } + + return 0; +} diff --git a/trunk/tools/perf/builtin-list.c b/trunk/tools/perf/builtin-list.c new file mode 100644 index 000000000000..fe60e37c96ef --- /dev/null +++ b/trunk/tools/perf/builtin-list.c @@ -0,0 +1,20 @@ +/* + * builtin-list.c + * + * Builtin list command: list all event types + * + * Copyright (C) 2009, Thomas Gleixner + * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar + */ +#include "builtin.h" + +#include "perf.h" + +#include "util/parse-options.h" +#include "util/parse-events.h" + +int cmd_list(int argc, const char **argv, const char *prefix) +{ + print_events(); + return 0; +} diff --git a/trunk/tools/perf/builtin-record.c b/trunk/tools/perf/builtin-record.c new file mode 100644 index 000000000000..0f5771f615da --- /dev/null +++ b/trunk/tools/perf/builtin-record.c @@ -0,0 +1,585 @@ +/* + * builtin-record.c + * + * Builtin record command: Record the profile of a workload + * (or a CPU, or a PID) into the perf.data output file - for + * later analysis via perf report. + */ +#include "builtin.h" + +#include "perf.h" + +#include "util/util.h" +#include "util/parse-options.h" +#include "util/parse-events.h" +#include "util/string.h" + +#include +#include + +#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1) +#define __ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) + +static int fd[MAX_NR_CPUS][MAX_COUNTERS]; + +static long default_interval = 100000; + +static int nr_cpus = 0; +static unsigned int page_size; +static unsigned int mmap_pages = 128; +static int freq = 0; +static int output; +static const char *output_name = "perf.data"; +static int group = 0; +static unsigned int realtime_prio = 0; +static int system_wide = 0; +static pid_t target_pid = -1; +static int inherit = 1; +static int force = 0; +static int append_file = 0; +static int verbose = 0; + +static long samples; +static struct timeval last_read; +static struct timeval this_read; + +static __u64 bytes_written; + +static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; + +static int nr_poll; +static int nr_cpu; + +struct mmap_event { + struct perf_event_header header; + __u32 pid; + __u32 tid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; +}; + +struct comm_event { + struct perf_event_header header; + __u32 pid; + __u32 tid; + char comm[16]; +}; + + +struct mmap_data { + int counter; + void *base; + unsigned int mask; + unsigned int prev; +}; + +static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; + +static unsigned int mmap_read_head(struct mmap_data *md) +{ + struct perf_counter_mmap_page *pc = md->base; + int head; + + head = pc->data_head; + rmb(); + + return head; +} + +static void mmap_read(struct mmap_data *md) +{ + unsigned int head = mmap_read_head(md); + unsigned int old = md->prev; + unsigned char *data = md->base + page_size; + unsigned long size; + void *buf; + int diff; + + gettimeofday(&this_read, NULL); + + /* + * If we're further behind than half the buffer, there's a chance + * the writer will bite our tail and mess up the samples under us. + * + * If we somehow ended up ahead of the head, we got messed up. + * + * In either case, truncate and restart at head. + */ + diff = head - old; + if (diff > md->mask / 2 || diff < 0) { + struct timeval iv; + unsigned long msecs; + + timersub(&this_read, &last_read, &iv); + msecs = iv.tv_sec*1000 + iv.tv_usec/1000; + + fprintf(stderr, "WARNING: failed to keep up with mmap data." + " Last read %lu msecs ago.\n", msecs); + + /* + * head points to a known good entry, start there. + */ + old = head; + } + + last_read = this_read; + + if (old != head) + samples++; + + size = head - old; + + if ((old & md->mask) + size != (head & md->mask)) { + buf = &data[old & md->mask]; + size = md->mask + 1 - (old & md->mask); + old += size; + + while (size) { + int ret = write(output, buf, size); + + if (ret < 0) + die("failed to write"); + + size -= ret; + buf += ret; + + bytes_written += ret; + } + } + + buf = &data[old & md->mask]; + size = head - old; + old += size; + + while (size) { + int ret = write(output, buf, size); + + if (ret < 0) + die("failed to write"); + + size -= ret; + buf += ret; + + bytes_written += ret; + } + + md->prev = old; +} + +static volatile int done = 0; +static volatile int signr = -1; + +static void sig_handler(int sig) +{ + done = 1; + signr = sig; +} + +static void sig_atexit(void) +{ + if (signr == -1) + return; + + signal(signr, SIG_DFL); + kill(getpid(), signr); +} + +static void pid_synthesize_comm_event(pid_t pid, int full) +{ + struct comm_event comm_ev; + char filename[PATH_MAX]; + char bf[BUFSIZ]; + int fd, ret; + size_t size; + char *field, *sep; + DIR *tasks; + struct dirent dirent, *next; + + snprintf(filename, sizeof(filename), "/proc/%d/stat", pid); + + fd = open(filename, O_RDONLY); + if (fd < 0) { + fprintf(stderr, "couldn't open %s\n", filename); + exit(EXIT_FAILURE); + } + if (read(fd, bf, sizeof(bf)) < 0) { + fprintf(stderr, "couldn't read %s\n", filename); + exit(EXIT_FAILURE); + } + close(fd); + + /* 9027 (cat) R 6747 9027 6747 34816 9027 ... */ + memset(&comm_ev, 0, sizeof(comm_ev)); + field = strchr(bf, '('); + if (field == NULL) + goto out_failure; + sep = strchr(++field, ')'); + if (sep == NULL) + goto out_failure; + size = sep - field; + memcpy(comm_ev.comm, field, size++); + + comm_ev.pid = pid; + comm_ev.header.type = PERF_EVENT_COMM; + size = ALIGN(size, sizeof(__u64)); + comm_ev.header.size = sizeof(comm_ev) - (sizeof(comm_ev.comm) - size); + + if (!full) { + comm_ev.tid = pid; + + ret = write(output, &comm_ev, comm_ev.header.size); + if (ret < 0) { + perror("failed to write"); + exit(-1); + } + return; + } + + snprintf(filename, sizeof(filename), "/proc/%d/task", pid); + + tasks = opendir(filename); + while (!readdir_r(tasks, &dirent, &next) && next) { + char *end; + pid = strtol(dirent.d_name, &end, 10); + if (*end) + continue; + + comm_ev.tid = pid; + + ret = write(output, &comm_ev, comm_ev.header.size); + if (ret < 0) { + perror("failed to write"); + exit(-1); + } + } + closedir(tasks); + return; + +out_failure: + fprintf(stderr, "couldn't get COMM and pgid, malformed %s\n", + filename); + exit(EXIT_FAILURE); +} + +static void pid_synthesize_mmap_samples(pid_t pid) +{ + char filename[PATH_MAX]; + FILE *fp; + + snprintf(filename, sizeof(filename), "/proc/%d/maps", pid); + + fp = fopen(filename, "r"); + if (fp == NULL) { + fprintf(stderr, "couldn't open %s\n", filename); + exit(EXIT_FAILURE); + } + while (1) { + char bf[BUFSIZ], *pbf = bf; + struct mmap_event mmap_ev = { + .header.type = PERF_EVENT_MMAP, + }; + int n; + size_t size; + if (fgets(bf, sizeof(bf), fp) == NULL) + break; + + /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ + n = hex2u64(pbf, &mmap_ev.start); + if (n < 0) + continue; + pbf += n + 1; + n = hex2u64(pbf, &mmap_ev.len); + if (n < 0) + continue; + pbf += n + 3; + if (*pbf == 'x') { /* vm_exec */ + char *execname = strrchr(bf, ' '); + + if (execname == NULL || execname[1] != '/') + continue; + + execname += 1; + size = strlen(execname); + execname[size - 1] = '\0'; /* Remove \n */ + memcpy(mmap_ev.filename, execname, size); + size = ALIGN(size, sizeof(__u64)); + mmap_ev.len -= mmap_ev.start; + mmap_ev.header.size = (sizeof(mmap_ev) - + (sizeof(mmap_ev.filename) - size)); + mmap_ev.pid = pid; + mmap_ev.tid = pid; + + if (write(output, &mmap_ev, mmap_ev.header.size) < 0) { + perror("failed to write"); + exit(-1); + } + } + } + + fclose(fp); +} + +static void synthesize_samples(void) +{ + DIR *proc; + struct dirent dirent, *next; + + proc = opendir("/proc"); + + while (!readdir_r(proc, &dirent, &next) && next) { + char *end; + pid_t pid; + + pid = strtol(dirent.d_name, &end, 10); + if (*end) /* only interested in proper numerical dirents */ + continue; + + pid_synthesize_comm_event(pid, 1); + pid_synthesize_mmap_samples(pid); + } + + closedir(proc); +} + +static int group_fd; + +static void create_counter(int counter, int cpu, pid_t pid) +{ + struct perf_counter_attr *attr = attrs + counter; + int track = 1; + + attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + if (freq) { + attr->sample_type |= PERF_SAMPLE_PERIOD; + attr->freq = 1; + attr->sample_freq = freq; + } + attr->mmap = track; + attr->comm = track; + attr->inherit = (cpu < 0) && inherit; + attr->disabled = 1; + + track = 0; /* only the first counter needs these */ + +try_again: + fd[nr_cpu][counter] = sys_perf_counter_open(attr, pid, cpu, group_fd, 0); + + if (fd[nr_cpu][counter] < 0) { + int err = errno; + + if (err == EPERM) + die("Permission error - are you root?\n"); + + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[nr_cpu][counter], strerror(err)); + die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n"); + exit(-1); + } + + assert(fd[nr_cpu][counter] >= 0); + fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK); + + /* + * First counter acts as the group leader: + */ + if (group && group_fd == -1) + group_fd = fd[nr_cpu][counter]; + + event_array[nr_poll].fd = fd[nr_cpu][counter]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[nr_cpu][counter].counter = counter; + mmap_array[nr_cpu][counter].prev = 0; + mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1; + mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ, MAP_SHARED, fd[nr_cpu][counter], 0); + if (mmap_array[nr_cpu][counter].base == MAP_FAILED) { + error("failed to mmap with %d (%s)\n", errno, strerror(errno)); + exit(-1); + } + + ioctl(fd[nr_cpu][counter], PERF_COUNTER_IOC_ENABLE); +} + +static void open_counters(int cpu, pid_t pid) +{ + int counter; + + if (pid > 0) { + pid_synthesize_comm_event(pid, 0); + pid_synthesize_mmap_samples(pid); + } + + group_fd = -1; + for (counter = 0; counter < nr_counters; counter++) + create_counter(counter, cpu, pid); + + nr_cpu++; +} + +static int __cmd_record(int argc, const char **argv) +{ + int i, counter; + struct stat st; + pid_t pid; + int flags; + int ret; + + page_size = sysconf(_SC_PAGE_SIZE); + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + assert(nr_cpus <= MAX_NR_CPUS); + assert(nr_cpus >= 0); + + if (!stat(output_name, &st) && !force && !append_file) { + fprintf(stderr, "Error, output file %s exists, use -A to append or -f to overwrite.\n", + output_name); + exit(-1); + } + + flags = O_CREAT|O_RDWR; + if (append_file) + flags |= O_APPEND; + else + flags |= O_TRUNC; + + output = open(output_name, flags, S_IRUSR|S_IWUSR); + if (output < 0) { + perror("failed to create output file"); + exit(-1); + } + + if (!system_wide) { + open_counters(-1, target_pid != -1 ? target_pid : getpid()); + } else for (i = 0; i < nr_cpus; i++) + open_counters(i, target_pid); + + atexit(sig_atexit); + signal(SIGCHLD, sig_handler); + signal(SIGINT, sig_handler); + + if (target_pid == -1 && argc) { + pid = fork(); + if (pid < 0) + perror("failed to fork"); + + if (!pid) { + if (execvp(argv[0], (char **)argv)) { + perror(argv[0]); + exit(-1); + } + } + } + + if (realtime_prio) { + struct sched_param param; + + param.sched_priority = realtime_prio; + if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { + printf("Could not set realtime priority.\n"); + exit(-1); + } + } + + if (system_wide) + synthesize_samples(); + + while (!done) { + int hits = samples; + + for (i = 0; i < nr_cpu; i++) { + for (counter = 0; counter < nr_counters; counter++) + mmap_read(&mmap_array[i][counter]); + } + + if (hits == samples) + ret = poll(event_array, nr_poll, 100); + } + + /* + * Approximate RIP event size: 24 bytes. + */ + fprintf(stderr, + "[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n", + (double)bytes_written / 1024.0 / 1024.0, + output_name, + bytes_written / 24); + + return 0; +} + +static const char * const record_usage[] = { + "perf record [] []", + "perf record [] -- []", + NULL +}; + +static const struct option options[] = { + OPT_CALLBACK('e', "event", NULL, "event", + "event selector. use 'perf list' to list available events", + parse_events), + OPT_INTEGER('p', "pid", &target_pid, + "record events on existing pid"), + OPT_INTEGER('r', "realtime", &realtime_prio, + "collect data with this RT SCHED_FIFO priority"), + OPT_BOOLEAN('a', "all-cpus", &system_wide, + "system-wide collection from all CPUs"), + OPT_BOOLEAN('A', "append", &append_file, + "append to the output file to do incremental profiling"), + OPT_BOOLEAN('f', "force", &force, + "overwrite existing data file"), + OPT_LONG('c', "count", &default_interval, + "event period to sample"), + OPT_STRING('o', "output", &output_name, "file", + "output file name"), + OPT_BOOLEAN('i', "inherit", &inherit, + "child tasks inherit counters"), + OPT_INTEGER('F', "freq", &freq, + "profile at this frequency"), + OPT_INTEGER('m', "mmap-pages", &mmap_pages, + "number of mmap data pages"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_END() +}; + +int cmd_record(int argc, const char **argv, const char *prefix) +{ + int counter; + + argc = parse_options(argc, argv, options, record_usage, 0); + if (!argc && target_pid == -1 && !system_wide) + usage_with_options(record_usage, options); + + if (!nr_counters) { + nr_counters = 1; + attrs[0].type = PERF_TYPE_HARDWARE; + attrs[0].config = PERF_COUNT_HW_CPU_CYCLES; + } + + for (counter = 0; counter < nr_counters; counter++) { + if (attrs[counter].sample_period) + continue; + + attrs[counter].sample_period = default_interval; + } + + return __cmd_record(argc, argv); +} diff --git a/trunk/tools/perf/builtin-report.c b/trunk/tools/perf/builtin-report.c new file mode 100644 index 000000000000..82fa93b4db99 --- /dev/null +++ b/trunk/tools/perf/builtin-report.c @@ -0,0 +1,1316 @@ +/* + * builtin-report.c + * + * Builtin report command: Analyze the perf.data input file, + * look up and read DSOs and symbol information and display + * a histogram of results, along various sorting keys. + */ +#include "builtin.h" + +#include "util/util.h" + +#include "util/color.h" +#include "util/list.h" +#include "util/cache.h" +#include "util/rbtree.h" +#include "util/symbol.h" +#include "util/string.h" + +#include "perf.h" + +#include "util/parse-options.h" +#include "util/parse-events.h" + +#define SHOW_KERNEL 1 +#define SHOW_USER 2 +#define SHOW_HV 4 + +static char const *input_name = "perf.data"; +static char *vmlinux = NULL; + +static char default_sort_order[] = "comm,dso"; +static char *sort_order = default_sort_order; + +static int input; +static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; + +static int dump_trace = 0; +#define dprintf(x...) do { if (dump_trace) printf(x); } while (0) + +static int verbose; +static int full_paths; + +static unsigned long page_size; +static unsigned long mmap_window = 32; + +struct ip_event { + struct perf_event_header header; + __u64 ip; + __u32 pid, tid; + __u64 period; +}; + +struct mmap_event { + struct perf_event_header header; + __u32 pid, tid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; +}; + +struct comm_event { + struct perf_event_header header; + __u32 pid, tid; + char comm[16]; +}; + +struct fork_event { + struct perf_event_header header; + __u32 pid, ppid; +}; + +struct period_event { + struct perf_event_header header; + __u64 time; + __u64 id; + __u64 sample_period; +}; + +typedef union event_union { + struct perf_event_header header; + struct ip_event ip; + struct mmap_event mmap; + struct comm_event comm; + struct fork_event fork; + struct period_event period; +} event_t; + +static LIST_HEAD(dsos); +static struct dso *kernel_dso; +static struct dso *vdso; + +static void dsos__add(struct dso *dso) +{ + list_add_tail(&dso->node, &dsos); +} + +static struct dso *dsos__find(const char *name) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + if (strcmp(pos->name, name) == 0) + return pos; + return NULL; +} + +static struct dso *dsos__findnew(const char *name) +{ + struct dso *dso = dsos__find(name); + int nr; + + if (dso) + return dso; + + dso = dso__new(name, 0); + if (!dso) + goto out_delete_dso; + + nr = dso__load(dso, NULL, verbose); + if (nr < 0) { + if (verbose) + fprintf(stderr, "Failed to open: %s\n", name); + goto out_delete_dso; + } + if (!nr && verbose) { + fprintf(stderr, + "No symbols found in: %s, maybe install a debug package?\n", + name); + } + + dsos__add(dso); + + return dso; + +out_delete_dso: + dso__delete(dso); + return NULL; +} + +static void dsos__fprintf(FILE *fp) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + dso__fprintf(pos, fp); +} + +static struct symbol *vdso__find_symbol(struct dso *dso, __u64 ip) +{ + return dso__find_symbol(kernel_dso, ip); +} + +static int load_kernel(void) +{ + int err; + + kernel_dso = dso__new("[kernel]", 0); + if (!kernel_dso) + return -1; + + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); + if (err) { + dso__delete(kernel_dso); + kernel_dso = NULL; + } else + dsos__add(kernel_dso); + + vdso = dso__new("[vdso]", 0); + if (!vdso) + return -1; + + vdso->find_symbol = vdso__find_symbol; + + dsos__add(vdso); + + return err; +} + +static char __cwd[PATH_MAX]; +static char *cwd = __cwd; +static int cwdlen; + +static int strcommon(const char *pathname) +{ + int n = 0; + + while (pathname[n] == cwd[n] && n < cwdlen) + ++n; + + return n; +} + +struct map { + struct list_head node; + __u64 start; + __u64 end; + __u64 pgoff; + __u64 (*map_ip)(struct map *, __u64); + struct dso *dso; +}; + +static __u64 map__map_ip(struct map *map, __u64 ip) +{ + return ip - map->start + map->pgoff; +} + +static __u64 vdso__map_ip(struct map *map, __u64 ip) +{ + return ip; +} + +static inline int is_anon_memory(const char *filename) +{ + return strcmp(filename, "//anon") == 0; +} + +static struct map *map__new(struct mmap_event *event) +{ + struct map *self = malloc(sizeof(*self)); + + if (self != NULL) { + const char *filename = event->filename; + char newfilename[PATH_MAX]; + int anon; + + if (cwd) { + int n = strcommon(filename); + + if (n == cwdlen) { + snprintf(newfilename, sizeof(newfilename), + ".%s", filename + n); + filename = newfilename; + } + } + + anon = is_anon_memory(filename); + + if (anon) { + snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid); + filename = newfilename; + } + + self->start = event->start; + self->end = event->start + event->len; + self->pgoff = event->pgoff; + + self->dso = dsos__findnew(filename); + if (self->dso == NULL) + goto out_delete; + + if (self->dso == vdso || anon) + self->map_ip = vdso__map_ip; + else + self->map_ip = map__map_ip; + } + return self; +out_delete: + free(self); + return NULL; +} + +static struct map *map__clone(struct map *self) +{ + struct map *map = malloc(sizeof(*self)); + + if (!map) + return NULL; + + memcpy(map, self, sizeof(*self)); + + return map; +} + +static int map__overlap(struct map *l, struct map *r) +{ + if (l->start > r->start) { + struct map *t = l; + l = r; + r = t; + } + + if (l->end > r->start) + return 1; + + return 0; +} + +static size_t map__fprintf(struct map *self, FILE *fp) +{ + return fprintf(fp, " %Lx-%Lx %Lx %s\n", + self->start, self->end, self->pgoff, self->dso->name); +} + + +struct thread { + struct rb_node rb_node; + struct list_head maps; + pid_t pid; + char *comm; +}; + +static struct thread *thread__new(pid_t pid) +{ + struct thread *self = malloc(sizeof(*self)); + + if (self != NULL) { + self->pid = pid; + self->comm = malloc(32); + if (self->comm) + snprintf(self->comm, 32, ":%d", self->pid); + INIT_LIST_HEAD(&self->maps); + } + + return self; +} + +static int thread__set_comm(struct thread *self, const char *comm) +{ + if (self->comm) + free(self->comm); + self->comm = strdup(comm); + return self->comm ? 0 : -ENOMEM; +} + +static size_t thread__fprintf(struct thread *self, FILE *fp) +{ + struct map *pos; + size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm); + + list_for_each_entry(pos, &self->maps, node) + ret += map__fprintf(pos, fp); + + return ret; +} + + +static struct rb_root threads; +static struct thread *last_match; + +static struct thread *threads__findnew(pid_t pid) +{ + struct rb_node **p = &threads.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + /* + * Font-end cache - PID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: + */ + if (last_match && last_match->pid == pid) + return last_match; + + while (*p != NULL) { + parent = *p; + th = rb_entry(parent, struct thread, rb_node); + + if (th->pid == pid) { + last_match = th; + return th; + } + + if (pid < th->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + th = thread__new(pid); + if (th != NULL) { + rb_link_node(&th->rb_node, parent, p); + rb_insert_color(&th->rb_node, &threads); + last_match = th; + } + + return th; +} + +static void thread__insert_map(struct thread *self, struct map *map) +{ + struct map *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &self->maps, node) { + if (map__overlap(pos, map)) { + list_del_init(&pos->node); + /* XXX leaks dsos */ + free(pos); + } + } + + list_add_tail(&map->node, &self->maps); +} + +static int thread__fork(struct thread *self, struct thread *parent) +{ + struct map *map; + + if (self->comm) + free(self->comm); + self->comm = strdup(parent->comm); + if (!self->comm) + return -ENOMEM; + + list_for_each_entry(map, &parent->maps, node) { + struct map *new = map__clone(map); + if (!new) + return -ENOMEM; + thread__insert_map(self, new); + } + + return 0; +} + +static struct map *thread__find_map(struct thread *self, __u64 ip) +{ + struct map *pos; + + if (self == NULL) + return NULL; + + list_for_each_entry(pos, &self->maps, node) + if (ip >= pos->start && ip <= pos->end) + return pos; + + return NULL; +} + +static size_t threads__fprintf(FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + + for (nd = rb_first(&threads); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); + + ret += thread__fprintf(pos, fp); + } + + return ret; +} + +/* + * histogram, sorted on item, collects counts + */ + +static struct rb_root hist; + +struct hist_entry { + struct rb_node rb_node; + + struct thread *thread; + struct map *map; + struct dso *dso; + struct symbol *sym; + __u64 ip; + char level; + + __u64 count; +}; + +/* + * configurable sorting bits + */ + +struct sort_entry { + struct list_head list; + + char *header; + + int64_t (*cmp)(struct hist_entry *, struct hist_entry *); + int64_t (*collapse)(struct hist_entry *, struct hist_entry *); + size_t (*print)(FILE *fp, struct hist_entry *); +}; + +/* --sort pid */ + +static int64_t +sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static size_t +sort__thread_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid); +} + +static struct sort_entry sort_thread = { + .header = " Command: Pid", + .cmp = sort__thread_cmp, + .print = sort__thread_print, +}; + +/* --sort comm */ + +static int64_t +sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static int64_t +sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) +{ + char *comm_l = left->thread->comm; + char *comm_r = right->thread->comm; + + if (!comm_l || !comm_r) { + if (!comm_l && !comm_r) + return 0; + else if (!comm_l) + return -1; + else + return 1; + } + + return strcmp(comm_l, comm_r); +} + +static size_t +sort__comm_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s", self->thread->comm); +} + +static struct sort_entry sort_comm = { + .header = " Command", + .cmp = sort__comm_cmp, + .collapse = sort__comm_collapse, + .print = sort__comm_print, +}; + +/* --sort dso */ + +static int64_t +sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct dso *dso_l = left->dso; + struct dso *dso_r = right->dso; + + if (!dso_l || !dso_r) { + if (!dso_l && !dso_r) + return 0; + else if (!dso_l) + return -1; + else + return 1; + } + + return strcmp(dso_l->name, dso_r->name); +} + +static size_t +sort__dso_print(FILE *fp, struct hist_entry *self) +{ + if (self->dso) + return fprintf(fp, "%-25s", self->dso->name); + + return fprintf(fp, "%016llx ", (__u64)self->ip); +} + +static struct sort_entry sort_dso = { + .header = "Shared Object ", + .cmp = sort__dso_cmp, + .print = sort__dso_print, +}; + +/* --sort symbol */ + +static int64_t +sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) +{ + __u64 ip_l, ip_r; + + if (left->sym == right->sym) + return 0; + + ip_l = left->sym ? left->sym->start : left->ip; + ip_r = right->sym ? right->sym->start : right->ip; + + return (int64_t)(ip_r - ip_l); +} + +static size_t +sort__sym_print(FILE *fp, struct hist_entry *self) +{ + size_t ret = 0; + + if (verbose) + ret += fprintf(fp, "%#018llx ", (__u64)self->ip); + + if (self->sym) { + ret += fprintf(fp, "[%c] %s", + self->dso == kernel_dso ? 'k' : '.', self->sym->name); + } else { + ret += fprintf(fp, "%#016llx", (__u64)self->ip); + } + + return ret; +} + +static struct sort_entry sort_sym = { + .header = "Symbol", + .cmp = sort__sym_cmp, + .print = sort__sym_print, +}; + +static int sort__need_collapse = 0; + +struct sort_dimension { + char *name; + struct sort_entry *entry; + int taken; +}; + +static struct sort_dimension sort_dimensions[] = { + { .name = "pid", .entry = &sort_thread, }, + { .name = "comm", .entry = &sort_comm, }, + { .name = "dso", .entry = &sort_dso, }, + { .name = "symbol", .entry = &sort_sym, }, +}; + +static LIST_HEAD(hist_entry__sort_list); + +static int sort_dimension__add(char *tok) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { + struct sort_dimension *sd = &sort_dimensions[i]; + + if (sd->taken) + continue; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sd->entry->collapse) + sort__need_collapse = 1; + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; + + return 0; + } + + return -ESRCH; +} + +static int64_t +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + cmp = se->cmp(left, right); + if (cmp) + break; + } + + return cmp; +} + +static int64_t +hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + int64_t (*f)(struct hist_entry *, struct hist_entry *); + + f = se->collapse ?: se->cmp; + + cmp = f(left, right); + if (cmp) + break; + } + + return cmp; +} + +static size_t +hist_entry__fprintf(FILE *fp, struct hist_entry *self, __u64 total_samples) +{ + struct sort_entry *se; + size_t ret; + + if (total_samples) { + double percent = self->count * 100.0 / total_samples; + char *color = PERF_COLOR_NORMAL; + + /* + * We color high-overhead entries in red, mid-overhead + * entries in green - and keep the low overhead places + * normal: + */ + if (percent >= 5.0) { + color = PERF_COLOR_RED; + } else { + if (percent >= 0.5) + color = PERF_COLOR_GREEN; + } + + ret = color_fprintf(fp, color, " %6.2f%%", + (self->count * 100.0) / total_samples); + } else + ret = fprintf(fp, "%12Ld ", self->count); + + list_for_each_entry(se, &hist_entry__sort_list, list) { + fprintf(fp, " "); + ret += se->print(fp, self); + } + + ret += fprintf(fp, "\n"); + + return ret; +} + +/* + * collect histogram counts + */ + +static int +hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, + struct symbol *sym, __u64 ip, char level, __u64 count) +{ + struct rb_node **p = &hist.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *he; + struct hist_entry entry = { + .thread = thread, + .map = map, + .dso = dso, + .sym = sym, + .ip = ip, + .level = level, + .count = count, + }; + int cmp; + + while (*p != NULL) { + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__cmp(&entry, he); + + if (!cmp) { + he->count += count; + return 0; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + he = malloc(sizeof(*he)); + if (!he) + return -ENOMEM; + *he = entry; + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &hist); + + return 0; +} + +static void hist_entry__free(struct hist_entry *he) +{ + free(he); +} + +/* + * collapse the histogram + */ + +static struct rb_root collapse_hists; + +static void collapse__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &collapse_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + int64_t cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__collapse(iter, he); + + if (!cmp) { + iter->count += he->count; + hist_entry__free(he); + return; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &collapse_hists); +} + +static void collapse__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + + if (!sort__need_collapse) + return; + + next = rb_first(&hist); + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, &hist); + collapse__insert_entry(n); + } +} + +/* + * reverse the map, sort on count. + */ + +static struct rb_root output_hists; + +static void output__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &output_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + if (he->count > iter->count) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &output_hists); +} + +static void output__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + struct rb_root *tree = &hist; + + if (sort__need_collapse) + tree = &collapse_hists; + + next = rb_first(tree); + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, tree); + output__insert_entry(n); + } +} + +static size_t output__fprintf(FILE *fp, __u64 total_samples) +{ + struct hist_entry *pos; + struct sort_entry *se; + struct rb_node *nd; + size_t ret = 0; + + fprintf(fp, "\n"); + fprintf(fp, "#\n"); + fprintf(fp, "# (%Ld samples)\n", (__u64)total_samples); + fprintf(fp, "#\n"); + + fprintf(fp, "# Overhead"); + list_for_each_entry(se, &hist_entry__sort_list, list) + fprintf(fp, " %s", se->header); + fprintf(fp, "\n"); + + fprintf(fp, "# ........"); + list_for_each_entry(se, &hist_entry__sort_list, list) { + int i; + + fprintf(fp, " "); + for (i = 0; i < strlen(se->header); i++) + fprintf(fp, "."); + } + fprintf(fp, "\n"); + + fprintf(fp, "#\n"); + + for (nd = rb_first(&output_hists); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node); + ret += hist_entry__fprintf(fp, pos, total_samples); + } + + if (!strcmp(sort_order, default_sort_order)) { + fprintf(fp, "#\n"); + fprintf(fp, "# (For more details, try: perf report --sort comm,dso,symbol)\n"); + fprintf(fp, "#\n"); + } + fprintf(fp, "\n"); + + return ret; +} + +static void register_idle_thread(void) +{ + struct thread *thread = threads__findnew(0); + + if (thread == NULL || + thread__set_comm(thread, "[idle]")) { + fprintf(stderr, "problem inserting idle task.\n"); + exit(-1); + } +} + +static unsigned long total = 0, + total_mmap = 0, + total_comm = 0, + total_fork = 0, + total_unknown = 0; + +static int +process_overflow_event(event_t *event, unsigned long offset, unsigned long head) +{ + char level; + int show = 0; + struct dso *dso = NULL; + struct thread *thread = threads__findnew(event->ip.pid); + __u64 ip = event->ip.ip; + __u64 period = 1; + struct map *map = NULL; + + if (event->header.type & PERF_SAMPLE_PERIOD) + period = event->ip.period; + + dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.misc, + event->ip.pid, + (void *)(long)ip, + (long long)period); + + dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid); + + if (thread == NULL) { + fprintf(stderr, "problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + if (event->header.misc & PERF_EVENT_MISC_KERNEL) { + show = SHOW_KERNEL; + level = 'k'; + + dso = kernel_dso; + + dprintf(" ...... dso: %s\n", dso->name); + + } else if (event->header.misc & PERF_EVENT_MISC_USER) { + + show = SHOW_USER; + level = '.'; + + map = thread__find_map(thread, ip); + if (map != NULL) { + ip = map->map_ip(map, ip); + dso = map->dso; + } else { + /* + * If this is outside of all known maps, + * and is a negative address, try to look it + * up in the kernel dso, as it might be a + * vsyscall (which executes in user-mode): + */ + if ((long long)ip < 0) + dso = kernel_dso; + } + dprintf(" ...... dso: %s\n", dso ? dso->name : ""); + + } else { + show = SHOW_HV; + level = 'H'; + dprintf(" ...... dso: [hypervisor]\n"); + } + + if (show & show_mask) { + struct symbol *sym = NULL; + + if (dso) + sym = dso->find_symbol(dso, ip); + + if (hist_entry__add(thread, map, dso, sym, ip, level, period)) { + fprintf(stderr, + "problem incrementing symbol count, skipping event\n"); + return -1; + } + } + total += period; + + return 0; +} + +static int +process_mmap_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->mmap.pid); + struct map *map = map__new(&event->mmap); + + dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->mmap.pid, + (void *)(long)event->mmap.start, + (void *)(long)event->mmap.len, + (void *)(long)event->mmap.pgoff, + event->mmap.filename); + + if (thread == NULL || map == NULL) { + dprintf("problem processing PERF_EVENT_MMAP, skipping event.\n"); + return 0; + } + + thread__insert_map(thread, map); + total_mmap++; + + return 0; +} + +static int +process_comm_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->comm.pid); + + dprintf("%p [%p]: PERF_EVENT_COMM: %s:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->comm.comm, event->comm.pid); + + if (thread == NULL || + thread__set_comm(thread, event->comm.comm)) { + dprintf("problem processing PERF_EVENT_COMM, skipping event.\n"); + return -1; + } + total_comm++; + + return 0; +} + +static int +process_fork_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->fork.pid); + struct thread *parent = threads__findnew(event->fork.ppid); + + dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->fork.pid, event->fork.ppid); + + if (!thread || !parent || thread__fork(thread, parent)) { + dprintf("problem processing PERF_EVENT_FORK, skipping event.\n"); + return -1; + } + total_fork++; + + return 0; +} + +static int +process_period_event(event_t *event, unsigned long offset, unsigned long head) +{ + dprintf("%p [%p]: PERF_EVENT_PERIOD: time:%Ld, id:%Ld: period:%Ld\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->period.time, + event->period.id, + event->period.sample_period); + + return 0; +} + +static int +process_event(event_t *event, unsigned long offset, unsigned long head) +{ + if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) + return process_overflow_event(event, offset, head); + + switch (event->header.type) { + case PERF_EVENT_MMAP: + return process_mmap_event(event, offset, head); + + case PERF_EVENT_COMM: + return process_comm_event(event, offset, head); + + case PERF_EVENT_FORK: + return process_fork_event(event, offset, head); + + case PERF_EVENT_PERIOD: + return process_period_event(event, offset, head); + /* + * We dont process them right now but they are fine: + */ + + case PERF_EVENT_THROTTLE: + case PERF_EVENT_UNTHROTTLE: + return 0; + + default: + return -1; + } + + return 0; +} + +static int __cmd_report(void) +{ + int ret, rc = EXIT_FAILURE; + unsigned long offset = 0; + unsigned long head = 0; + struct stat stat; + event_t *event; + uint32_t size; + char *buf; + + register_idle_thread(); + + input = open(input_name, O_RDONLY); + if (input < 0) { + fprintf(stderr, " failed to open file: %s", input_name); + if (!strcmp(input_name, "perf.data")) + fprintf(stderr, " (try 'perf record' first)"); + fprintf(stderr, "\n"); + exit(-1); + } + + ret = fstat(input, &stat); + if (ret < 0) { + perror("failed to stat file"); + exit(-1); + } + + if (!stat.st_size) { + fprintf(stderr, "zero-sized file, nothing to do!\n"); + exit(0); + } + + if (load_kernel() < 0) { + perror("failed to load kernel symbols"); + return EXIT_FAILURE; + } + + if (!full_paths) { + if (getcwd(__cwd, sizeof(__cwd)) == NULL) { + perror("failed to get the current directory"); + return EXIT_FAILURE; + } + cwdlen = strlen(cwd); + } else { + cwd = NULL; + cwdlen = 0; + } +remap: + buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, + MAP_SHARED, input, offset); + if (buf == MAP_FAILED) { + perror("failed to mmap file"); + exit(-1); + } + +more: + event = (event_t *)(buf + head); + + size = event->header.size; + if (!size) + size = 8; + + if (head + event->header.size >= page_size * mmap_window) { + unsigned long shift = page_size * (head / page_size); + int ret; + + ret = munmap(buf, page_size * mmap_window); + assert(ret == 0); + + offset += shift; + head -= shift; + goto remap; + } + + size = event->header.size; + + dprintf("%p [%p]: event: %d\n", + (void *)(offset + head), + (void *)(long)event->header.size, + event->header.type); + + if (!size || process_event(event, offset, head) < 0) { + + dprintf("%p [%p]: skipping unknown header type: %d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.type); + + total_unknown++; + + /* + * assume we lost track of the stream, check alignment, and + * increment a single u64 in the hope to catch on again 'soon'. + */ + + if (unlikely(head & 7)) + head &= ~7ULL; + + size = 8; + } + + head += size; + + if (offset + head < stat.st_size) + goto more; + + rc = EXIT_SUCCESS; + close(input); + + dprintf(" IP events: %10ld\n", total); + dprintf(" mmap events: %10ld\n", total_mmap); + dprintf(" comm events: %10ld\n", total_comm); + dprintf(" fork events: %10ld\n", total_fork); + dprintf(" unknown events: %10ld\n", total_unknown); + + if (dump_trace) + return 0; + + if (verbose >= 3) + threads__fprintf(stdout); + + if (verbose >= 2) + dsos__fprintf(stdout); + + collapse__resort(); + output__resort(); + output__fprintf(stdout, total); + + return rc; +} + +static const char * const report_usage[] = { + "perf report [] ", + NULL +}; + +static const struct option options[] = { + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"), + OPT_STRING('s', "sort", &sort_order, "key[,key2...]", + "sort by key(s): pid, comm, dso, symbol. Default: pid,symbol"), + OPT_BOOLEAN('P', "full-paths", &full_paths, + "Don't shorten the pathnames taking into account the cwd"), + OPT_END() +}; + +static void setup_sorting(void) +{ + char *tmp, *tok, *str = strdup(sort_order); + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + if (sort_dimension__add(tok) < 0) { + error("Unknown --sort key: `%s'", tok); + usage_with_options(report_usage, options); + } + } + + free(str); +} + +int cmd_report(int argc, const char **argv, const char *prefix) +{ + symbol__init(); + + page_size = getpagesize(); + + argc = parse_options(argc, argv, options, report_usage, 0); + + setup_sorting(); + + /* + * Any (unrecognized) arguments left? + */ + if (argc) + usage_with_options(report_usage, options); + + setup_pager(); + + return __cmd_report(); +} diff --git a/trunk/tools/perf/builtin-stat.c b/trunk/tools/perf/builtin-stat.c new file mode 100644 index 000000000000..c43e4a97dc42 --- /dev/null +++ b/trunk/tools/perf/builtin-stat.c @@ -0,0 +1,367 @@ +/* + * builtin-stat.c + * + * Builtin stat command: Give a precise performance counters summary + * overview about any workload, CPU or specific PID. + * + * Sample output: + + $ perf stat ~/hackbench 10 + Time: 0.104 + + Performance counter stats for '/home/mingo/hackbench': + + 1255.538611 task clock ticks # 10.143 CPU utilization factor + 54011 context switches # 0.043 M/sec + 385 CPU migrations # 0.000 M/sec + 17755 pagefaults # 0.014 M/sec + 3808323185 CPU cycles # 3033.219 M/sec + 1575111190 instructions # 1254.530 M/sec + 17367895 cache references # 13.833 M/sec + 7674421 cache misses # 6.112 M/sec + + Wall-clock time elapsed: 123.786620 msecs + + * + * Copyright (C) 2008, Red Hat Inc, Ingo Molnar + * + * Improvements and fixes by: + * + * Arjan van de Ven + * Yanmin Zhang + * Wu Fengguang + * Mike Galbraith + * Paul Mackerras + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "perf.h" +#include "builtin.h" +#include "util/util.h" +#include "util/parse-options.h" +#include "util/parse-events.h" + +#include + +static struct perf_counter_attr default_attrs[MAX_COUNTERS] = { + + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES}, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, + + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + +}; + +static int system_wide = 0; +static int inherit = 1; +static int verbose = 0; + +static int fd[MAX_NR_CPUS][MAX_COUNTERS]; + +static int target_pid = -1; +static int nr_cpus = 0; +static unsigned int page_size; + +static int scale = 1; + +static const unsigned int default_count[] = { + 1000000, + 1000000, + 10000, + 10000, + 1000000, + 10000, +}; + +static __u64 event_res[MAX_COUNTERS][3]; +static __u64 event_scaled[MAX_COUNTERS]; + +static __u64 runtime_nsecs; +static __u64 walltime_nsecs; +static __u64 runtime_cycles; + +static void create_perf_stat_counter(int counter) +{ + struct perf_counter_attr *attr = attrs + counter; + + if (scale) + attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + + if (system_wide) { + int cpu; + for (cpu = 0; cpu < nr_cpus; cpu ++) { + fd[cpu][counter] = sys_perf_counter_open(attr, -1, cpu, -1, 0); + if (fd[cpu][counter] < 0 && verbose) { + printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[cpu][counter], strerror(errno)); + } + } + } else { + attr->inherit = inherit; + attr->disabled = 1; + + fd[0][counter] = sys_perf_counter_open(attr, 0, -1, -1, 0); + if (fd[0][counter] < 0 && verbose) { + printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[0][counter], strerror(errno)); + } + } +} + +/* + * Does the counter have nsecs as a unit? + */ +static inline int nsec_counter(int counter) +{ + if (attrs[counter].type != PERF_TYPE_SOFTWARE) + return 0; + + if (attrs[counter].config == PERF_COUNT_SW_CPU_CLOCK) + return 1; + + if (attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) + return 1; + + return 0; +} + +/* + * Read out the results of a single counter: + */ +static void read_counter(int counter) +{ + __u64 *count, single_count[3]; + ssize_t res; + int cpu, nv; + int scaled; + + count = event_res[counter]; + + count[0] = count[1] = count[2] = 0; + + nv = scale ? 3 : 1; + for (cpu = 0; cpu < nr_cpus; cpu ++) { + if (fd[cpu][counter] < 0) + continue; + + res = read(fd[cpu][counter], single_count, nv * sizeof(__u64)); + assert(res == nv * sizeof(__u64)); + + count[0] += single_count[0]; + if (scale) { + count[1] += single_count[1]; + count[2] += single_count[2]; + } + } + + scaled = 0; + if (scale) { + if (count[2] == 0) { + event_scaled[counter] = -1; + count[0] = 0; + return; + } + + if (count[2] < count[1]) { + event_scaled[counter] = 1; + count[0] = (unsigned long long) + ((double)count[0] * count[1] / count[2] + 0.5); + } + } + /* + * Save the full runtime - to allow normalization during printout: + */ + if (attrs[counter].type == PERF_TYPE_SOFTWARE && + attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) + runtime_nsecs = count[0]; + if (attrs[counter].type == PERF_TYPE_HARDWARE && + attrs[counter].config == PERF_COUNT_HW_CPU_CYCLES) + runtime_cycles = count[0]; +} + +/* + * Print out the results of a single counter: + */ +static void print_counter(int counter) +{ + __u64 *count; + int scaled; + + count = event_res[counter]; + scaled = event_scaled[counter]; + + if (scaled == -1) { + fprintf(stderr, " %14s %-20s\n", + "", event_name(counter)); + return; + } + + if (nsec_counter(counter)) { + double msecs = (double)count[0] / 1000000; + + fprintf(stderr, " %14.6f %-20s", + msecs, event_name(counter)); + if (attrs[counter].type == PERF_TYPE_SOFTWARE && + attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) { + + if (walltime_nsecs) + fprintf(stderr, " # %11.3f CPU utilization factor", + (double)count[0] / (double)walltime_nsecs); + } + } else { + fprintf(stderr, " %14Ld %-20s", + count[0], event_name(counter)); + if (runtime_nsecs) + fprintf(stderr, " # %11.3f M/sec", + (double)count[0]/runtime_nsecs*1000.0); + if (runtime_cycles && + attrs[counter].type == PERF_TYPE_HARDWARE && + attrs[counter].config == PERF_COUNT_HW_INSTRUCTIONS) { + + fprintf(stderr, " # %1.3f per cycle", + (double)count[0] / (double)runtime_cycles); + } + } + if (scaled) + fprintf(stderr, " (scaled from %.2f%%)", + (double) count[2] / count[1] * 100); + fprintf(stderr, "\n"); +} + +static int do_perf_stat(int argc, const char **argv) +{ + unsigned long long t0, t1; + int counter; + int status; + int pid; + int i; + + if (!system_wide) + nr_cpus = 1; + + for (counter = 0; counter < nr_counters; counter++) + create_perf_stat_counter(counter); + + /* + * Enable counters and exec the command: + */ + t0 = rdclock(); + prctl(PR_TASK_PERF_COUNTERS_ENABLE); + + if ((pid = fork()) < 0) + perror("failed to fork"); + + if (!pid) { + if (execvp(argv[0], (char **)argv)) { + perror(argv[0]); + exit(-1); + } + } + + while (wait(&status) >= 0) + ; + + prctl(PR_TASK_PERF_COUNTERS_DISABLE); + t1 = rdclock(); + + walltime_nsecs = t1 - t0; + + fflush(stdout); + + fprintf(stderr, "\n"); + fprintf(stderr, " Performance counter stats for \'%s", argv[0]); + + for (i = 1; i < argc; i++) + fprintf(stderr, " %s", argv[i]); + + fprintf(stderr, "\':\n"); + fprintf(stderr, "\n"); + + for (counter = 0; counter < nr_counters; counter++) + read_counter(counter); + + for (counter = 0; counter < nr_counters; counter++) + print_counter(counter); + + + fprintf(stderr, "\n"); + fprintf(stderr, " Wall-clock time elapsed: %12.6f msecs\n", + (double)(t1-t0)/1e6); + fprintf(stderr, "\n"); + + return 0; +} + +static volatile int signr = -1; + +static void skip_signal(int signo) +{ + signr = signo; +} + +static void sig_atexit(void) +{ + if (signr == -1) + return; + + signal(signr, SIG_DFL); + kill(getpid(), signr); +} + +static const char * const stat_usage[] = { + "perf stat [] ", + NULL +}; + +static const struct option options[] = { + OPT_CALLBACK('e', "event", NULL, "event", + "event selector. use 'perf list' to list available events", + parse_events), + OPT_BOOLEAN('i', "inherit", &inherit, + "child tasks inherit counters"), + OPT_INTEGER('p', "pid", &target_pid, + "stat events on existing pid"), + OPT_BOOLEAN('a', "all-cpus", &system_wide, + "system-wide collection from all CPUs"), + OPT_BOOLEAN('S', "scale", &scale, + "scale/normalize counters"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_END() +}; + +int cmd_stat(int argc, const char **argv, const char *prefix) +{ + page_size = sysconf(_SC_PAGE_SIZE); + + memcpy(attrs, default_attrs, sizeof(attrs)); + + argc = parse_options(argc, argv, options, stat_usage, 0); + if (!argc) + usage_with_options(stat_usage, options); + + if (!nr_counters) + nr_counters = 8; + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + assert(nr_cpus <= MAX_NR_CPUS); + assert(nr_cpus >= 0); + + /* + * We dont want to block the signals - that would cause + * child tasks to inherit that and Ctrl-C would not work. + * What we want is for Ctrl-C to work in the exec()-ed + * task, but being ignored by perf stat itself: + */ + atexit(sig_atexit); + signal(SIGINT, skip_signal); + signal(SIGALRM, skip_signal); + signal(SIGABRT, skip_signal); + + return do_perf_stat(argc, argv); +} diff --git a/trunk/tools/perf/builtin-top.c b/trunk/tools/perf/builtin-top.c new file mode 100644 index 000000000000..fe338d3c5d7e --- /dev/null +++ b/trunk/tools/perf/builtin-top.c @@ -0,0 +1,736 @@ +/* + * builtin-top.c + * + * Builtin top command: Display a continuously updated profile of + * any workload, CPU or specific PID. + * + * Copyright (C) 2008, Red Hat Inc, Ingo Molnar + * + * Improvements and fixes by: + * + * Arjan van de Ven + * Yanmin Zhang + * Wu Fengguang + * Mike Galbraith + * Paul Mackerras + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include "builtin.h" + +#include "perf.h" + +#include "util/symbol.h" +#include "util/color.h" +#include "util/util.h" +#include "util/rbtree.h" +#include "util/parse-options.h" +#include "util/parse-events.h" + +#include +#include + +#include + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +static int fd[MAX_NR_CPUS][MAX_COUNTERS]; + +static int system_wide = 0; + +static int default_interval = 100000; + +static __u64 count_filter = 5; +static int print_entries = 15; + +static int target_pid = -1; +static int profile_cpu = -1; +static int nr_cpus = 0; +static unsigned int realtime_prio = 0; +static int group = 0; +static unsigned int page_size; +static unsigned int mmap_pages = 16; +static int freq = 0; +static int verbose = 0; + +static char *sym_filter; +static unsigned long filter_start; +static unsigned long filter_end; + +static int delay_secs = 2; +static int zero; +static int dump_symtab; + +/* + * Symbols + */ + +static __u64 min_ip; +static __u64 max_ip = -1ll; + +struct sym_entry { + struct rb_node rb_node; + struct list_head node; + unsigned long count[MAX_COUNTERS]; + unsigned long snap_count; + double weight; + int skip; +}; + +struct sym_entry *sym_filter_entry; + +struct dso *kernel_dso; + +/* + * Symbols will be added here in record_ip and will get out + * after decayed. + */ +static LIST_HEAD(active_symbols); +static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER; + +/* + * Ordering weight: count-1 * count-2 * ... / count-n + */ +static double sym_weight(const struct sym_entry *sym) +{ + double weight = sym->snap_count; + int counter; + + for (counter = 1; counter < nr_counters-1; counter++) + weight *= sym->count[counter]; + + weight /= (sym->count[counter] + 1); + + return weight; +} + +static long samples; +static long userspace_samples; +static const char CONSOLE_CLEAR[] = ""; + +static void __list_insert_active_sym(struct sym_entry *syme) +{ + list_add(&syme->node, &active_symbols); +} + +static void list_remove_active_sym(struct sym_entry *syme) +{ + pthread_mutex_lock(&active_symbols_lock); + list_del_init(&syme->node); + pthread_mutex_unlock(&active_symbols_lock); +} + +static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se) +{ + struct rb_node **p = &tree->rb_node; + struct rb_node *parent = NULL; + struct sym_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct sym_entry, rb_node); + + if (se->weight > iter->weight) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&se->rb_node, parent, p); + rb_insert_color(&se->rb_node, tree); +} + +static void print_sym_table(void) +{ + int printed = 0, j; + int counter; + float samples_per_sec = samples/delay_secs; + float ksamples_per_sec = (samples-userspace_samples)/delay_secs; + float sum_ksamples = 0.0; + struct sym_entry *syme, *n; + struct rb_root tmp = RB_ROOT; + struct rb_node *nd; + + samples = userspace_samples = 0; + + /* Sort the active symbols */ + pthread_mutex_lock(&active_symbols_lock); + syme = list_entry(active_symbols.next, struct sym_entry, node); + pthread_mutex_unlock(&active_symbols_lock); + + list_for_each_entry_safe_from(syme, n, &active_symbols, node) { + syme->snap_count = syme->count[0]; + if (syme->snap_count != 0) { + syme->weight = sym_weight(syme); + rb_insert_active_sym(&tmp, syme); + sum_ksamples += syme->snap_count; + + for (j = 0; j < nr_counters; j++) + syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8; + } else + list_remove_active_sym(syme); + } + + puts(CONSOLE_CLEAR); + + printf( +"------------------------------------------------------------------------------\n"); + printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% [", + samples_per_sec, + 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec))); + + if (nr_counters == 1) { + printf("%Ld", attrs[0].sample_period); + if (freq) + printf("Hz "); + else + printf(" "); + } + + for (counter = 0; counter < nr_counters; counter++) { + if (counter) + printf("/"); + + printf("%s", event_name(counter)); + } + + printf( "], "); + + if (target_pid != -1) + printf(" (target_pid: %d", target_pid); + else + printf(" (all"); + + if (profile_cpu != -1) + printf(", cpu: %d)\n", profile_cpu); + else { + if (target_pid != -1) + printf(")\n"); + else + printf(", %d CPUs)\n", nr_cpus); + } + + printf("------------------------------------------------------------------------------\n\n"); + + if (nr_counters == 1) + printf(" samples pcnt"); + else + printf(" weight samples pcnt"); + + printf(" RIP kernel function\n" + " ______ _______ _____ ________________ _______________\n\n" + ); + + for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) { + struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node); + struct symbol *sym = (struct symbol *)(syme + 1); + char *color = PERF_COLOR_NORMAL; + double pcnt; + + if (++printed > print_entries || syme->snap_count < count_filter) + continue; + + pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) / + sum_ksamples)); + + /* + * We color high-overhead entries in red, mid-overhead + * entries in green - and keep the low overhead places + * normal: + */ + if (pcnt >= 5.0) { + color = PERF_COLOR_RED; + } else { + if (pcnt >= 0.5) + color = PERF_COLOR_GREEN; + } + + if (nr_counters == 1) + printf("%20.2f - ", syme->weight); + else + printf("%9.1f %10ld - ", syme->weight, syme->snap_count); + + color_fprintf(stdout, color, "%4.1f%%", pcnt); + printf(" - %016llx : %s\n", sym->start, sym->name); + } +} + +static void *display_thread(void *arg) +{ + struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; + int delay_msecs = delay_secs * 1000; + + printf("PerfTop refresh period: %d seconds\n", delay_secs); + + do { + print_sym_table(); + } while (!poll(&stdin_poll, 1, delay_msecs) == 1); + + printf("key pressed - exiting.\n"); + exit(0); + + return NULL; +} + +static int symbol_filter(struct dso *self, struct symbol *sym) +{ + static int filter_match; + struct sym_entry *syme; + const char *name = sym->name; + + if (!strcmp(name, "_text") || + !strcmp(name, "_etext") || + !strcmp(name, "_sinittext") || + !strncmp("init_module", name, 11) || + !strncmp("cleanup_module", name, 14) || + strstr(name, "_text_start") || + strstr(name, "_text_end")) + return 1; + + syme = dso__sym_priv(self, sym); + /* Tag samples to be skipped. */ + if (!strcmp("default_idle", name) || + !strcmp("cpu_idle", name) || + !strcmp("enter_idle", name) || + !strcmp("exit_idle", name) || + !strcmp("mwait_idle", name)) + syme->skip = 1; + + if (filter_match == 1) { + filter_end = sym->start; + filter_match = -1; + if (filter_end - filter_start > 10000) { + fprintf(stderr, + "hm, too large filter symbol <%s> - skipping.\n", + sym_filter); + fprintf(stderr, "symbol filter start: %016lx\n", + filter_start); + fprintf(stderr, " end: %016lx\n", + filter_end); + filter_end = filter_start = 0; + sym_filter = NULL; + sleep(1); + } + } + + if (filter_match == 0 && sym_filter && !strcmp(name, sym_filter)) { + filter_match = 1; + filter_start = sym->start; + } + + + return 0; +} + +static int parse_symbols(void) +{ + struct rb_node *node; + struct symbol *sym; + + kernel_dso = dso__new("[kernel]", sizeof(struct sym_entry)); + if (kernel_dso == NULL) + return -1; + + if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1) != 0) + goto out_delete_dso; + + node = rb_first(&kernel_dso->syms); + sym = rb_entry(node, struct symbol, rb_node); + min_ip = sym->start; + + node = rb_last(&kernel_dso->syms); + sym = rb_entry(node, struct symbol, rb_node); + max_ip = sym->end; + + if (dump_symtab) + dso__fprintf(kernel_dso, stderr); + + return 0; + +out_delete_dso: + dso__delete(kernel_dso); + kernel_dso = NULL; + return -1; +} + +#define TRACE_COUNT 3 + +/* + * Binary search in the histogram table and record the hit: + */ +static void record_ip(__u64 ip, int counter) +{ + struct symbol *sym = dso__find_symbol(kernel_dso, ip); + + if (sym != NULL) { + struct sym_entry *syme = dso__sym_priv(kernel_dso, sym); + + if (!syme->skip) { + syme->count[counter]++; + pthread_mutex_lock(&active_symbols_lock); + if (list_empty(&syme->node) || !syme->node.next) + __list_insert_active_sym(syme); + pthread_mutex_unlock(&active_symbols_lock); + return; + } + } + + samples--; +} + +static void process_event(__u64 ip, int counter) +{ + samples++; + + if (ip < min_ip || ip > max_ip) { + userspace_samples++; + return; + } + + record_ip(ip, counter); +} + +struct mmap_data { + int counter; + void *base; + unsigned int mask; + unsigned int prev; +}; + +static unsigned int mmap_read_head(struct mmap_data *md) +{ + struct perf_counter_mmap_page *pc = md->base; + int head; + + head = pc->data_head; + rmb(); + + return head; +} + +struct timeval last_read, this_read; + +static void mmap_read_counter(struct mmap_data *md) +{ + unsigned int head = mmap_read_head(md); + unsigned int old = md->prev; + unsigned char *data = md->base + page_size; + int diff; + + gettimeofday(&this_read, NULL); + + /* + * If we're further behind than half the buffer, there's a chance + * the writer will bite our tail and mess up the samples under us. + * + * If we somehow ended up ahead of the head, we got messed up. + * + * In either case, truncate and restart at head. + */ + diff = head - old; + if (diff > md->mask / 2 || diff < 0) { + struct timeval iv; + unsigned long msecs; + + timersub(&this_read, &last_read, &iv); + msecs = iv.tv_sec*1000 + iv.tv_usec/1000; + + fprintf(stderr, "WARNING: failed to keep up with mmap data." + " Last read %lu msecs ago.\n", msecs); + + /* + * head points to a known good entry, start there. + */ + old = head; + } + + last_read = this_read; + + for (; old != head;) { + struct ip_event { + struct perf_event_header header; + __u64 ip; + __u32 pid, target_pid; + }; + struct mmap_event { + struct perf_event_header header; + __u32 pid, target_pid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; + }; + + typedef union event_union { + struct perf_event_header header; + struct ip_event ip; + struct mmap_event mmap; + } event_t; + + event_t *event = (event_t *)&data[old & md->mask]; + + event_t event_copy; + + size_t size = event->header.size; + + /* + * Event straddles the mmap boundary -- header should always + * be inside due to u64 alignment of output. + */ + if ((old & md->mask) + size != ((old + size) & md->mask)) { + unsigned int offset = old; + unsigned int len = min(sizeof(*event), size), cpy; + void *dst = &event_copy; + + do { + cpy = min(md->mask + 1 - (offset & md->mask), len); + memcpy(dst, &data[offset & md->mask], cpy); + offset += cpy; + dst += cpy; + len -= cpy; + } while (len); + + event = &event_copy; + } + + old += size; + + if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) { + if (event->header.type & PERF_SAMPLE_IP) + process_event(event->ip.ip, md->counter); + } + } + + md->prev = old; +} + +static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; +static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; + +static void mmap_read(void) +{ + int i, counter; + + for (i = 0; i < nr_cpus; i++) { + for (counter = 0; counter < nr_counters; counter++) + mmap_read_counter(&mmap_array[i][counter]); + } +} + +int nr_poll; +int group_fd; + +static void start_counter(int i, int counter) +{ + struct perf_counter_attr *attr; + unsigned int cpu; + + cpu = profile_cpu; + if (target_pid == -1 && profile_cpu == -1) + cpu = i; + + attr = attrs + counter; + + attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + attr->freq = freq; + +try_again: + fd[i][counter] = sys_perf_counter_open(attr, target_pid, cpu, group_fd, 0); + + if (fd[i][counter] < 0) { + int err = errno; + + if (err == EPERM) + die("No permission - are you root?\n"); + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[i][counter], strerror(err)); + die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n"); + exit(-1); + } + assert(fd[i][counter] >= 0); + fcntl(fd[i][counter], F_SETFL, O_NONBLOCK); + + /* + * First counter acts as the group leader: + */ + if (group && group_fd == -1) + group_fd = fd[i][counter]; + + event_array[nr_poll].fd = fd[i][counter]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[i][counter].counter = counter; + mmap_array[i][counter].prev = 0; + mmap_array[i][counter].mask = mmap_pages*page_size - 1; + mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ, MAP_SHARED, fd[i][counter], 0); + if (mmap_array[i][counter].base == MAP_FAILED) + die("failed to mmap with %d (%s)\n", errno, strerror(errno)); +} + +static int __cmd_top(void) +{ + pthread_t thread; + int i, counter; + int ret; + + for (i = 0; i < nr_cpus; i++) { + group_fd = -1; + for (counter = 0; counter < nr_counters; counter++) + start_counter(i, counter); + } + + /* Wait for a minimal set of events before starting the snapshot */ + poll(event_array, nr_poll, 100); + + mmap_read(); + + if (pthread_create(&thread, NULL, display_thread, NULL)) { + printf("Could not create display thread.\n"); + exit(-1); + } + + if (realtime_prio) { + struct sched_param param; + + param.sched_priority = realtime_prio; + if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { + printf("Could not set realtime priority.\n"); + exit(-1); + } + } + + while (1) { + int hits = samples; + + mmap_read(); + + if (hits == samples) + ret = poll(event_array, nr_poll, 100); + } + + return 0; +} + +static const char * const top_usage[] = { + "perf top []", + NULL +}; + +static const struct option options[] = { + OPT_CALLBACK('e', "event", NULL, "event", + "event selector. use 'perf list' to list available events", + parse_events), + OPT_INTEGER('c', "count", &default_interval, + "event period to sample"), + OPT_INTEGER('p', "pid", &target_pid, + "profile events on existing pid"), + OPT_BOOLEAN('a', "all-cpus", &system_wide, + "system-wide collection from all CPUs"), + OPT_INTEGER('C', "CPU", &profile_cpu, + "CPU to profile on"), + OPT_INTEGER('m', "mmap-pages", &mmap_pages, + "number of mmap data pages"), + OPT_INTEGER('r', "realtime", &realtime_prio, + "collect data with this RT SCHED_FIFO priority"), + OPT_INTEGER('d', "delay", &delay_secs, + "number of seconds to delay between refreshes"), + OPT_BOOLEAN('D', "dump-symtab", &dump_symtab, + "dump the symbol table used for profiling"), + OPT_INTEGER('f', "count-filter", &count_filter, + "only display functions with more events than this"), + OPT_BOOLEAN('g', "group", &group, + "put the counters into a counter group"), + OPT_STRING('s', "sym-filter", &sym_filter, "pattern", + "only display symbols matchig this pattern"), + OPT_BOOLEAN('z', "zero", &group, + "zero history across updates"), + OPT_INTEGER('F', "freq", &freq, + "profile at this frequency"), + OPT_INTEGER('E', "entries", &print_entries, + "display this many functions"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_END() +}; + +int cmd_top(int argc, const char **argv, const char *prefix) +{ + int counter; + + page_size = sysconf(_SC_PAGE_SIZE); + + argc = parse_options(argc, argv, options, top_usage, 0); + if (argc) + usage_with_options(top_usage, options); + + if (freq) { + default_interval = freq; + freq = 1; + } + + /* CPU and PID are mutually exclusive */ + if (target_pid != -1 && profile_cpu != -1) { + printf("WARNING: PID switch overriding CPU\n"); + sleep(1); + profile_cpu = -1; + } + + if (!nr_counters) + nr_counters = 1; + + if (delay_secs < 1) + delay_secs = 1; + + parse_symbols(); + + /* + * Fill in the ones not specifically initialized via -c: + */ + for (counter = 0; counter < nr_counters; counter++) { + if (attrs[counter].sample_period) + continue; + + attrs[counter].sample_period = default_interval; + } + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + assert(nr_cpus <= MAX_NR_CPUS); + assert(nr_cpus >= 0); + + if (target_pid != -1 || profile_cpu != -1) + nr_cpus = 1; + + return __cmd_top(); +} diff --git a/trunk/tools/perf/builtin.h b/trunk/tools/perf/builtin.h new file mode 100644 index 000000000000..51d168230ee7 --- /dev/null +++ b/trunk/tools/perf/builtin.h @@ -0,0 +1,26 @@ +#ifndef BUILTIN_H +#define BUILTIN_H + +#include "util/util.h" +#include "util/strbuf.h" + +extern const char perf_version_string[]; +extern const char perf_usage_string[]; +extern const char perf_more_info_string[]; + +extern void list_common_cmds_help(void); +extern const char *help_unknown_cmd(const char *cmd); +extern void prune_packed_objects(int); +extern int read_line_with_nul(char *buf, int size, FILE *file); +extern int check_pager_config(const char *cmd); + +extern int cmd_annotate(int argc, const char **argv, const char *prefix); +extern int cmd_help(int argc, const char **argv, const char *prefix); +extern int cmd_record(int argc, const char **argv, const char *prefix); +extern int cmd_report(int argc, const char **argv, const char *prefix); +extern int cmd_stat(int argc, const char **argv, const char *prefix); +extern int cmd_top(int argc, const char **argv, const char *prefix); +extern int cmd_version(int argc, const char **argv, const char *prefix); +extern int cmd_list(int argc, const char **argv, const char *prefix); + +#endif diff --git a/trunk/tools/perf/command-list.txt b/trunk/tools/perf/command-list.txt new file mode 100644 index 000000000000..eebce30afbc0 --- /dev/null +++ b/trunk/tools/perf/command-list.txt @@ -0,0 +1,10 @@ +# +# List of known perf commands. +# command name category [deprecated] [common] +# +perf-annotate mainporcelain common +perf-list mainporcelain common +perf-record mainporcelain common +perf-report mainporcelain common +perf-stat mainporcelain common +perf-top mainporcelain common diff --git a/trunk/tools/perf/design.txt b/trunk/tools/perf/design.txt new file mode 100644 index 000000000000..f71e0d245cba --- /dev/null +++ b/trunk/tools/perf/design.txt @@ -0,0 +1,457 @@ + +Performance Counters for Linux +------------------------------ + +Performance counters are special hardware registers available on most modern +CPUs. These registers count the number of certain types of hw events: such +as instructions executed, cachemisses suffered, or branches mis-predicted - +without slowing down the kernel or applications. These registers can also +trigger interrupts when a threshold number of events have passed - and can +thus be used to profile the code that runs on that CPU. + +The Linux Performance Counter subsystem provides an abstraction of these +hardware capabilities. It provides per task and per CPU counters, counter +groups, and it provides event capabilities on top of those. It +provides "virtual" 64-bit counters, regardless of the width of the +underlying hardware counters. + +Performance counters are accessed via special file descriptors. +There's one file descriptor per virtual counter used. + +The special file descriptor is opened via the perf_counter_open() +system call: + + int sys_perf_counter_open(struct perf_counter_hw_event *hw_event_uptr, + pid_t pid, int cpu, int group_fd, + unsigned long flags); + +The syscall returns the new fd. The fd can be used via the normal +VFS system calls: read() can be used to read the counter, fcntl() +can be used to set the blocking mode, etc. + +Multiple counters can be kept open at a time, and the counters +can be poll()ed. + +When creating a new counter fd, 'perf_counter_hw_event' is: + +struct perf_counter_hw_event { + /* + * The MSB of the config word signifies if the rest contains cpu + * specific (raw) counter configuration data, if unset, the next + * 7 bits are an event type and the rest of the bits are the event + * identifier. + */ + __u64 config; + + __u64 irq_period; + __u32 record_type; + __u32 read_format; + + __u64 disabled : 1, /* off by default */ + inherit : 1, /* children inherit it */ + pinned : 1, /* must always be on PMU */ + exclusive : 1, /* only group on PMU */ + exclude_user : 1, /* don't count user */ + exclude_kernel : 1, /* ditto kernel */ + exclude_hv : 1, /* ditto hypervisor */ + exclude_idle : 1, /* don't count when idle */ + mmap : 1, /* include mmap data */ + munmap : 1, /* include munmap data */ + comm : 1, /* include comm data */ + + __reserved_1 : 52; + + __u32 extra_config_len; + __u32 wakeup_events; /* wakeup every n events */ + + __u64 __reserved_2; + __u64 __reserved_3; +}; + +The 'config' field specifies what the counter should count. It +is divided into 3 bit-fields: + +raw_type: 1 bit (most significant bit) 0x8000_0000_0000_0000 +type: 7 bits (next most significant) 0x7f00_0000_0000_0000 +event_id: 56 bits (least significant) 0x00ff_ffff_ffff_ffff + +If 'raw_type' is 1, then the counter will count a hardware event +specified by the remaining 63 bits of event_config. The encoding is +machine-specific. + +If 'raw_type' is 0, then the 'type' field says what kind of counter +this is, with the following encoding: + +enum perf_event_types { + PERF_TYPE_HARDWARE = 0, + PERF_TYPE_SOFTWARE = 1, + PERF_TYPE_TRACEPOINT = 2, +}; + +A counter of PERF_TYPE_HARDWARE will count the hardware event +specified by 'event_id': + +/* + * Generalized performance counter event types, used by the hw_event.event_id + * parameter of the sys_perf_counter_open() syscall: + */ +enum hw_event_ids { + /* + * Common hardware events, generalized by the kernel: + */ + PERF_COUNT_HW_CPU_CYCLES = 0, + PERF_COUNT_HW_INSTRUCTIONS = 1, + PERF_COUNT_HW_CACHE_REFERENCES = 2, + PERF_COUNT_HW_CACHE_MISSES = 3, + PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, + PERF_COUNT_HW_BRANCH_MISSES = 5, + PERF_COUNT_HW_BUS_CYCLES = 6, +}; + +These are standardized types of events that work relatively uniformly +on all CPUs that implement Performance Counters support under Linux, +although there may be variations (e.g., different CPUs might count +cache references and misses at different levels of the cache hierarchy). +If a CPU is not able to count the selected event, then the system call +will return -EINVAL. + +More hw_event_types are supported as well, but they are CPU-specific +and accessed as raw events. For example, to count "External bus +cycles while bus lock signal asserted" events on Intel Core CPUs, pass +in a 0x4064 event_id value and set hw_event.raw_type to 1. + +A counter of type PERF_TYPE_SOFTWARE will count one of the available +software events, selected by 'event_id': + +/* + * Special "software" counters provided by the kernel, even if the hardware + * does not support performance counters. These counters measure various + * physical and sw events of the kernel (and allow the profiling of them as + * well): + */ +enum sw_event_ids { + PERF_COUNT_SW_CPU_CLOCK = 0, + PERF_COUNT_SW_TASK_CLOCK = 1, + PERF_COUNT_SW_PAGE_FAULTS = 2, + PERF_COUNT_SW_CONTEXT_SWITCHES = 3, + PERF_COUNT_SW_CPU_MIGRATIONS = 4, + PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, + PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, +}; + +Counters of the type PERF_TYPE_TRACEPOINT are available when the ftrace event +tracer is available, and event_id values can be obtained from +/debug/tracing/events/*/*/id + + +Counters come in two flavours: counting counters and sampling +counters. A "counting" counter is one that is used for counting the +number of events that occur, and is characterised by having +irq_period = 0. + + +A read() on a counter returns the current value of the counter and possible +additional values as specified by 'read_format', each value is a u64 (8 bytes) +in size. + +/* + * Bits that can be set in hw_event.read_format to request that + * reads on the counter should return the indicated quantities, + * in increasing order of bit value, after the counter value. + */ +enum perf_counter_read_format { + PERF_FORMAT_TOTAL_TIME_ENABLED = 1, + PERF_FORMAT_TOTAL_TIME_RUNNING = 2, +}; + +Using these additional values one can establish the overcommit ratio for a +particular counter allowing one to take the round-robin scheduling effect +into account. + + +A "sampling" counter is one that is set up to generate an interrupt +every N events, where N is given by 'irq_period'. A sampling counter +has irq_period > 0. The record_type controls what data is recorded on each +interrupt: + +/* + * Bits that can be set in hw_event.record_type to request information + * in the overflow packets. + */ +enum perf_counter_record_format { + PERF_RECORD_IP = 1U << 0, + PERF_RECORD_TID = 1U << 1, + PERF_RECORD_TIME = 1U << 2, + PERF_RECORD_ADDR = 1U << 3, + PERF_RECORD_GROUP = 1U << 4, + PERF_RECORD_CALLCHAIN = 1U << 5, +}; + +Such (and other) events will be recorded in a ring-buffer, which is +available to user-space using mmap() (see below). + +The 'disabled' bit specifies whether the counter starts out disabled +or enabled. If it is initially disabled, it can be enabled by ioctl +or prctl (see below). + +The 'inherit' bit, if set, specifies that this counter should count +events on descendant tasks as well as the task specified. This only +applies to new descendents, not to any existing descendents at the +time the counter is created (nor to any new descendents of existing +descendents). + +The 'pinned' bit, if set, specifies that the counter should always be +on the CPU if at all possible. It only applies to hardware counters +and only to group leaders. If a pinned counter cannot be put onto the +CPU (e.g. because there are not enough hardware counters or because of +a conflict with some other event), then the counter goes into an +'error' state, where reads return end-of-file (i.e. read() returns 0) +until the counter is subsequently enabled or disabled. + +The 'exclusive' bit, if set, specifies that when this counter's group +is on the CPU, it should be the only group using the CPU's counters. +In future, this will allow sophisticated monitoring programs to supply +extra configuration information via 'extra_config_len' to exploit +advanced features of the CPU's Performance Monitor Unit (PMU) that are +not otherwise accessible and that might disrupt other hardware +counters. + +The 'exclude_user', 'exclude_kernel' and 'exclude_hv' bits provide a +way to request that counting of events be restricted to times when the +CPU is in user, kernel and/or hypervisor mode. + +The 'mmap' and 'munmap' bits allow recording of PROT_EXEC mmap/munmap +operations, these can be used to relate userspace IP addresses to actual +code, even after the mapping (or even the whole process) is gone, +these events are recorded in the ring-buffer (see below). + +The 'comm' bit allows tracking of process comm data on process creation. +This too is recorded in the ring-buffer (see below). + +The 'pid' parameter to the perf_counter_open() system call allows the +counter to be specific to a task: + + pid == 0: if the pid parameter is zero, the counter is attached to the + current task. + + pid > 0: the counter is attached to a specific task (if the current task + has sufficient privilege to do so) + + pid < 0: all tasks are counted (per cpu counters) + +The 'cpu' parameter allows a counter to be made specific to a CPU: + + cpu >= 0: the counter is restricted to a specific CPU + cpu == -1: the counter counts on all CPUs + +(Note: the combination of 'pid == -1' and 'cpu == -1' is not valid.) + +A 'pid > 0' and 'cpu == -1' counter is a per task counter that counts +events of that task and 'follows' that task to whatever CPU the task +gets schedule to. Per task counters can be created by any user, for +their own tasks. + +A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts +all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege. + +The 'flags' parameter is currently unused and must be zero. + +The 'group_fd' parameter allows counter "groups" to be set up. A +counter group has one counter which is the group "leader". The leader +is created first, with group_fd = -1 in the perf_counter_open call +that creates it. The rest of the group members are created +subsequently, with group_fd giving the fd of the group leader. +(A single counter on its own is created with group_fd = -1 and is +considered to be a group with only 1 member.) + +A counter group is scheduled onto the CPU as a unit, that is, it will +only be put onto the CPU if all of the counters in the group can be +put onto the CPU. This means that the values of the member counters +can be meaningfully compared, added, divided (to get ratios), etc., +with each other, since they have counted events for the same set of +executed instructions. + + +Like stated, asynchronous events, like counter overflow or PROT_EXEC mmap +tracking are logged into a ring-buffer. This ring-buffer is created and +accessed through mmap(). + +The mmap size should be 1+2^n pages, where the first page is a meta-data page +(struct perf_counter_mmap_page) that contains various bits of information such +as where the ring-buffer head is. + +/* + * Structure of the page that can be mapped via mmap + */ +struct perf_counter_mmap_page { + __u32 version; /* version number of this structure */ + __u32 compat_version; /* lowest version this is compat with */ + + /* + * Bits needed to read the hw counters in user-space. + * + * u32 seq; + * s64 count; + * + * do { + * seq = pc->lock; + * + * barrier() + * if (pc->index) { + * count = pmc_read(pc->index - 1); + * count += pc->offset; + * } else + * goto regular_read; + * + * barrier(); + * } while (pc->lock != seq); + * + * NOTE: for obvious reason this only works on self-monitoring + * processes. + */ + __u32 lock; /* seqlock for synchronization */ + __u32 index; /* hardware counter identifier */ + __s64 offset; /* add to hardware counter value */ + + /* + * Control data for the mmap() data buffer. + * + * User-space reading this value should issue an rmb(), on SMP capable + * platforms, after reading this value -- see perf_counter_wakeup(). + */ + __u32 data_head; /* head in the data section */ +}; + +NOTE: the hw-counter userspace bits are arch specific and are currently only + implemented on powerpc. + +The following 2^n pages are the ring-buffer which contains events of the form: + +#define PERF_EVENT_MISC_KERNEL (1 << 0) +#define PERF_EVENT_MISC_USER (1 << 1) +#define PERF_EVENT_MISC_OVERFLOW (1 << 2) + +struct perf_event_header { + __u32 type; + __u16 misc; + __u16 size; +}; + +enum perf_event_type { + + /* + * The MMAP events record the PROT_EXEC mappings so that we can + * correlate userspace IPs to code. They have the following structure: + * + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * u64 addr; + * u64 len; + * u64 pgoff; + * char filename[]; + * }; + */ + PERF_EVENT_MMAP = 1, + PERF_EVENT_MUNMAP = 2, + + /* + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * char comm[]; + * }; + */ + PERF_EVENT_COMM = 3, + + /* + * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field + * will be PERF_RECORD_* + * + * struct { + * struct perf_event_header header; + * + * { u64 ip; } && PERF_RECORD_IP + * { u32 pid, tid; } && PERF_RECORD_TID + * { u64 time; } && PERF_RECORD_TIME + * { u64 addr; } && PERF_RECORD_ADDR + * + * { u64 nr; + * { u64 event, val; } cnt[nr]; } && PERF_RECORD_GROUP + * + * { u16 nr, + * hv, + * kernel, + * user; + * u64 ips[nr]; } && PERF_RECORD_CALLCHAIN + * }; + */ +}; + +NOTE: PERF_RECORD_CALLCHAIN is arch specific and currently only implemented + on x86. + +Notification of new events is possible through poll()/select()/epoll() and +fcntl() managing signals. + +Normally a notification is generated for every page filled, however one can +additionally set perf_counter_hw_event.wakeup_events to generate one every +so many counter overflow events. + +Future work will include a splice() interface to the ring-buffer. + + +Counters can be enabled and disabled in two ways: via ioctl and via +prctl. When a counter is disabled, it doesn't count or generate +events but does continue to exist and maintain its count value. + +An individual counter or counter group can be enabled with + + ioctl(fd, PERF_COUNTER_IOC_ENABLE); + +or disabled with + + ioctl(fd, PERF_COUNTER_IOC_DISABLE); + +Enabling or disabling the leader of a group enables or disables the +whole group; that is, while the group leader is disabled, none of the +counters in the group will count. Enabling or disabling a member of a +group other than the leader only affects that counter - disabling an +non-leader stops that counter from counting but doesn't affect any +other counter. + +Additionally, non-inherited overflow counters can use + + ioctl(fd, PERF_COUNTER_IOC_REFRESH, nr); + +to enable a counter for 'nr' events, after which it gets disabled again. + +A process can enable or disable all the counter groups that are +attached to it, using prctl: + + prctl(PR_TASK_PERF_COUNTERS_ENABLE); + + prctl(PR_TASK_PERF_COUNTERS_DISABLE); + +This applies to all counters on the current process, whether created +by this process or by another, and doesn't affect any counters that +this process has created on other processes. It only enables or +disables the group leaders, not any other members in the groups. + + +Arch requirements +----------------- + +If your architecture does not have hardware performance metrics, you can +still use the generic software counters based on hrtimers for sampling. + +So to start with, in order to add HAVE_PERF_COUNTERS to your Kconfig, you +will need at least this: + - asm/perf_counter.h - a basic stub will suffice at first + - support for atomic64 types (and associated helper functions) + - set_perf_counter_pending() implemented + +If your architecture does have hardware capabilities, you can override the +weak stub hw_perf_counter_init() to register hardware counters. diff --git a/trunk/tools/perf/perf.c b/trunk/tools/perf/perf.c new file mode 100644 index 000000000000..4eb725933703 --- /dev/null +++ b/trunk/tools/perf/perf.c @@ -0,0 +1,428 @@ +/* + * perf.c + * + * Performance analysis utility. + * + * This is the main hub from which the sub-commands (perf stat, + * perf top, perf record, perf report, etc.) are started. + */ +#include "builtin.h" + +#include "util/exec_cmd.h" +#include "util/cache.h" +#include "util/quote.h" +#include "util/run-command.h" + +const char perf_usage_string[] = + "perf [--version] [--help] COMMAND [ARGS]"; + +const char perf_more_info_string[] = + "See 'perf help COMMAND' for more information on a specific command."; + +static int use_pager = -1; +struct pager_config { + const char *cmd; + int val; +}; + +static int pager_command_config(const char *var, const char *value, void *data) +{ + struct pager_config *c = data; + if (!prefixcmp(var, "pager.") && !strcmp(var + 6, c->cmd)) + c->val = perf_config_bool(var, value); + return 0; +} + +/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */ +int check_pager_config(const char *cmd) +{ + struct pager_config c; + c.cmd = cmd; + c.val = -1; + perf_config(pager_command_config, &c); + return c.val; +} + +static void commit_pager_choice(void) { + switch (use_pager) { + case 0: + setenv("PERF_PAGER", "cat", 1); + break; + case 1: + /* setup_pager(); */ + break; + default: + break; + } +} + +static int handle_options(const char*** argv, int* argc, int* envchanged) +{ + int handled = 0; + + while (*argc > 0) { + const char *cmd = (*argv)[0]; + if (cmd[0] != '-') + break; + + /* + * For legacy reasons, the "version" and "help" + * commands can be written with "--" prepended + * to make them look like flags. + */ + if (!strcmp(cmd, "--help") || !strcmp(cmd, "--version")) + break; + + /* + * Check remaining flags. + */ + if (!prefixcmp(cmd, "--exec-path")) { + cmd += 11; + if (*cmd == '=') + perf_set_argv_exec_path(cmd + 1); + else { + puts(perf_exec_path()); + exit(0); + } + } else if (!strcmp(cmd, "--html-path")) { + puts(system_path(PERF_HTML_PATH)); + exit(0); + } else if (!strcmp(cmd, "-p") || !strcmp(cmd, "--paginate")) { + use_pager = 1; + } else if (!strcmp(cmd, "--no-pager")) { + use_pager = 0; + if (envchanged) + *envchanged = 1; + } else if (!strcmp(cmd, "--perf-dir")) { + if (*argc < 2) { + fprintf(stderr, "No directory given for --perf-dir.\n" ); + usage(perf_usage_string); + } + setenv(PERF_DIR_ENVIRONMENT, (*argv)[1], 1); + if (envchanged) + *envchanged = 1; + (*argv)++; + (*argc)--; + handled++; + } else if (!prefixcmp(cmd, "--perf-dir=")) { + setenv(PERF_DIR_ENVIRONMENT, cmd + 10, 1); + if (envchanged) + *envchanged = 1; + } else if (!strcmp(cmd, "--work-tree")) { + if (*argc < 2) { + fprintf(stderr, "No directory given for --work-tree.\n" ); + usage(perf_usage_string); + } + setenv(PERF_WORK_TREE_ENVIRONMENT, (*argv)[1], 1); + if (envchanged) + *envchanged = 1; + (*argv)++; + (*argc)--; + } else if (!prefixcmp(cmd, "--work-tree=")) { + setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + 12, 1); + if (envchanged) + *envchanged = 1; + } else { + fprintf(stderr, "Unknown option: %s\n", cmd); + usage(perf_usage_string); + } + + (*argv)++; + (*argc)--; + handled++; + } + return handled; +} + +static int handle_alias(int *argcp, const char ***argv) +{ + int envchanged = 0, ret = 0, saved_errno = errno; + int count, option_count; + const char** new_argv; + const char *alias_command; + char *alias_string; + + alias_command = (*argv)[0]; + alias_string = alias_lookup(alias_command); + if (alias_string) { + if (alias_string[0] == '!') { + if (*argcp > 1) { + struct strbuf buf; + + strbuf_init(&buf, PATH_MAX); + strbuf_addstr(&buf, alias_string); + sq_quote_argv(&buf, (*argv) + 1, PATH_MAX); + free(alias_string); + alias_string = buf.buf; + } + ret = system(alias_string + 1); + if (ret >= 0 && WIFEXITED(ret) && + WEXITSTATUS(ret) != 127) + exit(WEXITSTATUS(ret)); + die("Failed to run '%s' when expanding alias '%s'", + alias_string + 1, alias_command); + } + count = split_cmdline(alias_string, &new_argv); + if (count < 0) + die("Bad alias.%s string", alias_command); + option_count = handle_options(&new_argv, &count, &envchanged); + if (envchanged) + die("alias '%s' changes environment variables\n" + "You can use '!perf' in the alias to do this.", + alias_command); + memmove(new_argv - option_count, new_argv, + count * sizeof(char *)); + new_argv -= option_count; + + if (count < 1) + die("empty alias for %s", alias_command); + + if (!strcmp(alias_command, new_argv[0])) + die("recursive alias: %s", alias_command); + + new_argv = realloc(new_argv, sizeof(char*) * + (count + *argcp + 1)); + /* insert after command name */ + memcpy(new_argv + count, *argv + 1, sizeof(char*) * *argcp); + new_argv[count+*argcp] = NULL; + + *argv = new_argv; + *argcp += count - 1; + + ret = 1; + } + + errno = saved_errno; + + return ret; +} + +const char perf_version_string[] = PERF_VERSION; + +#define RUN_SETUP (1<<0) +#define USE_PAGER (1<<1) +/* + * require working tree to be present -- anything uses this needs + * RUN_SETUP for reading from the configuration file. + */ +#define NEED_WORK_TREE (1<<2) + +struct cmd_struct { + const char *cmd; + int (*fn)(int, const char **, const char *); + int option; +}; + +static int run_builtin(struct cmd_struct *p, int argc, const char **argv) +{ + int status; + struct stat st; + const char *prefix; + + prefix = NULL; + if (p->option & RUN_SETUP) + prefix = NULL; /* setup_perf_directory(); */ + + if (use_pager == -1 && p->option & RUN_SETUP) + use_pager = check_pager_config(p->cmd); + if (use_pager == -1 && p->option & USE_PAGER) + use_pager = 1; + commit_pager_choice(); + + if (p->option & NEED_WORK_TREE) + /* setup_work_tree() */; + + status = p->fn(argc, argv, prefix); + if (status) + return status & 0xff; + + /* Somebody closed stdout? */ + if (fstat(fileno(stdout), &st)) + return 0; + /* Ignore write errors for pipes and sockets.. */ + if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode)) + return 0; + + /* Check for ENOSPC and EIO errors.. */ + if (fflush(stdout)) + die("write failure on standard output: %s", strerror(errno)); + if (ferror(stdout)) + die("unknown write failure on standard output"); + if (fclose(stdout)) + die("close failed on standard output: %s", strerror(errno)); + return 0; +} + +static void handle_internal_command(int argc, const char **argv) +{ + const char *cmd = argv[0]; + static struct cmd_struct commands[] = { + { "help", cmd_help, 0 }, + { "list", cmd_list, 0 }, + { "record", cmd_record, 0 }, + { "report", cmd_report, 0 }, + { "stat", cmd_stat, 0 }, + { "top", cmd_top, 0 }, + { "annotate", cmd_annotate, 0 }, + { "version", cmd_version, 0 }, + }; + int i; + static const char ext[] = STRIP_EXTENSION; + + if (sizeof(ext) > 1) { + i = strlen(argv[0]) - strlen(ext); + if (i > 0 && !strcmp(argv[0] + i, ext)) { + char *argv0 = strdup(argv[0]); + argv[0] = cmd = argv0; + argv0[i] = '\0'; + } + } + + /* Turn "perf cmd --help" into "perf help cmd" */ + if (argc > 1 && !strcmp(argv[1], "--help")) { + argv[1] = argv[0]; + argv[0] = cmd = "help"; + } + + for (i = 0; i < ARRAY_SIZE(commands); i++) { + struct cmd_struct *p = commands+i; + if (strcmp(p->cmd, cmd)) + continue; + exit(run_builtin(p, argc, argv)); + } +} + +static void execv_dashed_external(const char **argv) +{ + struct strbuf cmd = STRBUF_INIT; + const char *tmp; + int status; + + strbuf_addf(&cmd, "perf-%s", argv[0]); + + /* + * argv[0] must be the perf command, but the argv array + * belongs to the caller, and may be reused in + * subsequent loop iterations. Save argv[0] and + * restore it on error. + */ + tmp = argv[0]; + argv[0] = cmd.buf; + + /* + * if we fail because the command is not found, it is + * OK to return. Otherwise, we just pass along the status code. + */ + status = run_command_v_opt(argv, 0); + if (status != -ERR_RUN_COMMAND_EXEC) { + if (IS_RUN_COMMAND_ERR(status)) + die("unable to run '%s'", argv[0]); + exit(-status); + } + errno = ENOENT; /* as if we called execvp */ + + argv[0] = tmp; + + strbuf_release(&cmd); +} + +static int run_argv(int *argcp, const char ***argv) +{ + int done_alias = 0; + + while (1) { + /* See if it's an internal command */ + handle_internal_command(*argcp, *argv); + + /* .. then try the external ones */ + execv_dashed_external(*argv); + + /* It could be an alias -- this works around the insanity + * of overriding "perf log" with "perf show" by having + * alias.log = show + */ + if (done_alias || !handle_alias(argcp, argv)) + break; + done_alias = 1; + } + + return done_alias; +} + + +int main(int argc, const char **argv) +{ + const char *cmd; + + cmd = perf_extract_argv0_path(argv[0]); + if (!cmd) + cmd = "perf-help"; + + /* + * "perf-xxxx" is the same as "perf xxxx", but we obviously: + * + * - cannot take flags in between the "perf" and the "xxxx". + * - cannot execute it externally (since it would just do + * the same thing over again) + * + * So we just directly call the internal command handler, and + * die if that one cannot handle it. + */ + if (!prefixcmp(cmd, "perf-")) { + cmd += 5; + argv[0] = cmd; + handle_internal_command(argc, argv); + die("cannot handle %s internally", cmd); + } + + /* Look for flags.. */ + argv++; + argc--; + handle_options(&argv, &argc, NULL); + commit_pager_choice(); + if (argc > 0) { + if (!prefixcmp(argv[0], "--")) + argv[0] += 2; + } else { + /* The user didn't specify a command; give them help */ + printf("\n usage: %s\n\n", perf_usage_string); + list_common_cmds_help(); + printf("\n %s\n\n", perf_more_info_string); + exit(1); + } + cmd = argv[0]; + + /* + * We use PATH to find perf commands, but we prepend some higher + * precidence paths: the "--exec-path" option, the PERF_EXEC_PATH + * environment, and the $(perfexecdir) from the Makefile at build + * time. + */ + setup_path(); + + while (1) { + static int done_help = 0; + static int was_alias = 0; + + was_alias = run_argv(&argc, &argv); + if (errno != ENOENT) + break; + + if (was_alias) { + fprintf(stderr, "Expansion of alias '%s' failed; " + "'%s' is not a perf-command\n", + cmd, argv[0]); + exit(1); + } + if (!done_help) { + cmd = argv[0] = help_unknown_cmd(cmd); + done_help = 1; + } else + break; + } + + fprintf(stderr, "Failed to run command '%s': %s\n", + cmd, strerror(errno)); + + return 1; +} diff --git a/trunk/tools/perf/perf.h b/trunk/tools/perf/perf.h new file mode 100644 index 000000000000..87a1aca4a424 --- /dev/null +++ b/trunk/tools/perf/perf.h @@ -0,0 +1,68 @@ +#ifndef _PERF_PERF_H +#define _PERF_PERF_H + +#if defined(__x86_64__) || defined(__i386__) +#include "../../arch/x86/include/asm/unistd.h" +#define rmb() asm volatile("lfence" ::: "memory") +#define cpu_relax() asm volatile("rep; nop" ::: "memory"); +#endif + +#ifdef __powerpc__ +#include "../../arch/powerpc/include/asm/unistd.h" +#define rmb() asm volatile ("sync" ::: "memory") +#define cpu_relax() asm volatile ("" ::: "memory"); +#endif + +#include +#include +#include +#include + +#include "../../include/linux/perf_counter.h" + +/* + * prctl(PR_TASK_PERF_COUNTERS_DISABLE) will (cheaply) disable all + * counters in the current task. + */ +#define PR_TASK_PERF_COUNTERS_DISABLE 31 +#define PR_TASK_PERF_COUNTERS_ENABLE 32 + +#ifndef NSEC_PER_SEC +# define NSEC_PER_SEC 1000000000ULL +#endif + +static inline unsigned long long rdclock(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ULL + ts.tv_nsec; +} + +/* + * Pick up some kernel type conventions: + */ +#define __user +#define asmlinkage + +#define unlikely(x) __builtin_expect(!!(x), 0) +#define min(x, y) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + (void) (&_min1 == &_min2); \ + _min1 < _min2 ? _min1 : _min2; }) + +static inline int +sys_perf_counter_open(struct perf_counter_attr *attr, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + attr->size = sizeof(*attr); + return syscall(__NR_perf_counter_open, attr, pid, cpu, + group_fd, flags); +} + +#define MAX_COUNTERS 256 +#define MAX_NR_CPUS 256 + +#endif diff --git a/trunk/tools/perf/util/PERF-VERSION-GEN b/trunk/tools/perf/util/PERF-VERSION-GEN new file mode 100755 index 000000000000..c561d1538c03 --- /dev/null +++ b/trunk/tools/perf/util/PERF-VERSION-GEN @@ -0,0 +1,42 @@ +#!/bin/sh + +GVF=PERF-VERSION-FILE +DEF_VER=v0.0.1.PERF + +LF=' +' + +# First see if there is a version file (included in release tarballs), +# then try git-describe, then default. +if test -f version +then + VN=$(cat version) || VN="$DEF_VER" +elif test -d .git -o -f .git && + VN=$(git describe --abbrev=4 HEAD 2>/dev/null) && + case "$VN" in + *$LF*) (exit 1) ;; + v[0-9]*) + git update-index -q --refresh + test -z "$(git diff-index --name-only HEAD --)" || + VN="$VN-dirty" ;; + esac +then + VN=$(echo "$VN" | sed -e 's/-/./g'); +else + VN="$DEF_VER" +fi + +VN=$(expr "$VN" : v*'\(.*\)') + +if test -r $GVF +then + VC=$(sed -e 's/^PERF_VERSION = //' <$GVF) +else + VC=unset +fi +test "$VN" = "$VC" || { + echo >&2 "PERF_VERSION = $VN" + echo "PERF_VERSION = $VN" >$GVF +} + + diff --git a/trunk/tools/perf/util/abspath.c b/trunk/tools/perf/util/abspath.c new file mode 100644 index 000000000000..61d33b81fc97 --- /dev/null +++ b/trunk/tools/perf/util/abspath.c @@ -0,0 +1,117 @@ +#include "cache.h" + +/* + * Do not use this for inspecting *tracked* content. When path is a + * symlink to a directory, we do not want to say it is a directory when + * dealing with tracked content in the working tree. + */ +static int is_directory(const char *path) +{ + struct stat st; + return (!stat(path, &st) && S_ISDIR(st.st_mode)); +} + +/* We allow "recursive" symbolic links. Only within reason, though. */ +#define MAXDEPTH 5 + +const char *make_absolute_path(const char *path) +{ + static char bufs[2][PATH_MAX + 1], *buf = bufs[0], *next_buf = bufs[1]; + char cwd[1024] = ""; + int buf_index = 1, len; + + int depth = MAXDEPTH; + char *last_elem = NULL; + struct stat st; + + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die ("Too long path: %.*s", 60, path); + + while (depth--) { + if (!is_directory(buf)) { + char *last_slash = strrchr(buf, '/'); + if (last_slash) { + *last_slash = '\0'; + last_elem = xstrdup(last_slash + 1); + } else { + last_elem = xstrdup(buf); + *buf = '\0'; + } + } + + if (*buf) { + if (!*cwd && !getcwd(cwd, sizeof(cwd))) + die ("Could not get current working directory"); + + if (chdir(buf)) + die ("Could not switch to '%s'", buf); + } + if (!getcwd(buf, PATH_MAX)) + die ("Could not get current working directory"); + + if (last_elem) { + int len = strlen(buf); + if (len + strlen(last_elem) + 2 > PATH_MAX) + die ("Too long path name: '%s/%s'", + buf, last_elem); + buf[len] = '/'; + strcpy(buf + len + 1, last_elem); + free(last_elem); + last_elem = NULL; + } + + if (!lstat(buf, &st) && S_ISLNK(st.st_mode)) { + len = readlink(buf, next_buf, PATH_MAX); + if (len < 0) + die ("Invalid symlink: %s", buf); + if (PATH_MAX <= len) + die("symbolic link too long: %s", buf); + next_buf[len] = '\0'; + buf = next_buf; + buf_index = 1 - buf_index; + next_buf = bufs[buf_index]; + } else + break; + } + + if (*cwd && chdir(cwd)) + die ("Could not change back to '%s'", cwd); + + return buf; +} + +static const char *get_pwd_cwd(void) +{ + static char cwd[PATH_MAX + 1]; + char *pwd; + struct stat cwd_stat, pwd_stat; + if (getcwd(cwd, PATH_MAX) == NULL) + return NULL; + pwd = getenv("PWD"); + if (pwd && strcmp(pwd, cwd)) { + stat(cwd, &cwd_stat); + if (!stat(pwd, &pwd_stat) && + pwd_stat.st_dev == cwd_stat.st_dev && + pwd_stat.st_ino == cwd_stat.st_ino) { + strlcpy(cwd, pwd, PATH_MAX); + } + } + return cwd; +} + +const char *make_nonrelative_path(const char *path) +{ + static char buf[PATH_MAX + 1]; + + if (is_absolute_path(path)) { + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } else { + const char *cwd = get_pwd_cwd(); + if (!cwd) + die("Cannot determine the current working directory"); + if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } + return buf; +} diff --git a/trunk/tools/perf/util/alias.c b/trunk/tools/perf/util/alias.c new file mode 100644 index 000000000000..9b3dd2b428df --- /dev/null +++ b/trunk/tools/perf/util/alias.c @@ -0,0 +1,77 @@ +#include "cache.h" + +static const char *alias_key; +static char *alias_val; + +static int alias_lookup_cb(const char *k, const char *v, void *cb) +{ + if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) { + if (!v) + return config_error_nonbool(k); + alias_val = strdup(v); + return 0; + } + return 0; +} + +char *alias_lookup(const char *alias) +{ + alias_key = alias; + alias_val = NULL; + perf_config(alias_lookup_cb, NULL); + return alias_val; +} + +int split_cmdline(char *cmdline, const char ***argv) +{ + int src, dst, count = 0, size = 16; + char quoted = 0; + + *argv = malloc(sizeof(char*) * size); + + /* split alias_string */ + (*argv)[count++] = cmdline; + for (src = dst = 0; cmdline[src];) { + char c = cmdline[src]; + if (!quoted && isspace(c)) { + cmdline[dst++] = 0; + while (cmdline[++src] + && isspace(cmdline[src])) + ; /* skip */ + if (count >= size) { + size += 16; + *argv = realloc(*argv, sizeof(char*) * size); + } + (*argv)[count++] = cmdline + dst; + } else if (!quoted && (c == '\'' || c == '"')) { + quoted = c; + src++; + } else if (c == quoted) { + quoted = 0; + src++; + } else { + if (c == '\\' && quoted != '\'') { + src++; + c = cmdline[src]; + if (!c) { + free(*argv); + *argv = NULL; + return error("cmdline ends with \\"); + } + } + cmdline[dst++] = c; + src++; + } + } + + cmdline[dst] = 0; + + if (quoted) { + free(*argv); + *argv = NULL; + return error("unclosed quote"); + } + + return count; +} + diff --git a/trunk/tools/perf/util/cache.h b/trunk/tools/perf/util/cache.h new file mode 100644 index 000000000000..393d6146d13b --- /dev/null +++ b/trunk/tools/perf/util/cache.h @@ -0,0 +1,119 @@ +#ifndef CACHE_H +#define CACHE_H + +#include "util.h" +#include "strbuf.h" + +#define PERF_DIR_ENVIRONMENT "PERF_DIR" +#define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE" +#define DEFAULT_PERF_DIR_ENVIRONMENT ".perf" +#define DB_ENVIRONMENT "PERF_OBJECT_DIRECTORY" +#define INDEX_ENVIRONMENT "PERF_INDEX_FILE" +#define GRAFT_ENVIRONMENT "PERF_GRAFT_FILE" +#define TEMPLATE_DIR_ENVIRONMENT "PERF_TEMPLATE_DIR" +#define CONFIG_ENVIRONMENT "PERF_CONFIG" +#define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH" +#define CEILING_DIRECTORIES_ENVIRONMENT "PERF_CEILING_DIRECTORIES" +#define PERFATTRIBUTES_FILE ".perfattributes" +#define INFOATTRIBUTES_FILE "info/attributes" +#define ATTRIBUTE_MACRO_PREFIX "[attr]" + +typedef int (*config_fn_t)(const char *, const char *, void *); +extern int perf_default_config(const char *, const char *, void *); +extern int perf_config_from_file(config_fn_t fn, const char *, void *); +extern int perf_config(config_fn_t fn, void *); +extern int perf_parse_ulong(const char *, unsigned long *); +extern int perf_config_int(const char *, const char *); +extern unsigned long perf_config_ulong(const char *, const char *); +extern int perf_config_bool_or_int(const char *, const char *, int *); +extern int perf_config_bool(const char *, const char *); +extern int perf_config_string(const char **, const char *, const char *); +extern int perf_config_set(const char *, const char *); +extern int perf_config_set_multivar(const char *, const char *, const char *, int); +extern int perf_config_rename_section(const char *, const char *); +extern const char *perf_etc_perfconfig(void); +extern int check_repository_format_version(const char *var, const char *value, void *cb); +extern int perf_config_system(void); +extern int perf_config_global(void); +extern int config_error_nonbool(const char *); +extern const char *config_exclusive_filename; + +#define MAX_PERFNAME (1000) +extern char perf_default_email[MAX_PERFNAME]; +extern char perf_default_name[MAX_PERFNAME]; +extern int user_ident_explicitly_given; + +extern const char *perf_log_output_encoding; +extern const char *perf_mailmap_file; + +/* IO helper functions */ +extern void maybe_flush_or_die(FILE *, const char *); +extern int copy_fd(int ifd, int ofd); +extern int copy_file(const char *dst, const char *src, int mode); +extern ssize_t read_in_full(int fd, void *buf, size_t count); +extern ssize_t write_in_full(int fd, const void *buf, size_t count); +extern void write_or_die(int fd, const void *buf, size_t count); +extern int write_or_whine(int fd, const void *buf, size_t count, const char *msg); +extern int write_or_whine_pipe(int fd, const void *buf, size_t count, const char *msg); +extern void fsync_or_die(int fd, const char *); + +/* pager.c */ +extern void setup_pager(void); +extern const char *pager_program; +extern int pager_in_use(void); +extern int pager_use_color; + +extern const char *editor_program; +extern const char *excludes_file; + +char *alias_lookup(const char *alias); +int split_cmdline(char *cmdline, const char ***argv); + +#define alloc_nr(x) (((x)+16)*3/2) + +/* + * Realloc the buffer pointed at by variable 'x' so that it can hold + * at least 'nr' entries; the number of entries currently allocated + * is 'alloc', using the standard growing factor alloc_nr() macro. + * + * DO NOT USE any expression with side-effect for 'x' or 'alloc'. + */ +#define ALLOC_GROW(x, nr, alloc) \ + do { \ + if ((nr) > alloc) { \ + if (alloc_nr(alloc) < (nr)) \ + alloc = (nr); \ + else \ + alloc = alloc_nr(alloc); \ + x = xrealloc((x), alloc * sizeof(*(x))); \ + } \ + } while(0) + + +static inline int is_absolute_path(const char *path) +{ + return path[0] == '/'; +} + +const char *make_absolute_path(const char *path); +const char *make_nonrelative_path(const char *path); +const char *make_relative_path(const char *abs, const char *base); +int normalize_path_copy(char *dst, const char *src); +int longest_ancestor_length(const char *path, const char *prefix_list); +char *strip_path_suffix(const char *path, const char *suffix); + +extern char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +/* perf_mkstemp() - create tmp file honoring TMPDIR variable */ +extern int perf_mkstemp(char *path, size_t len, const char *template); + +extern char *mksnpath(char *buf, size_t n, const char *fmt, ...) + __attribute__((format (printf, 3, 4))); +extern char *perf_snpath(char *buf, size_t n, const char *fmt, ...) + __attribute__((format (printf, 3, 4))); +extern char *perf_pathdup(const char *fmt, ...) + __attribute__((format (printf, 1, 2))); + +extern size_t strlcpy(char *dest, const char *src, size_t size); + +#endif /* CACHE_H */ diff --git a/trunk/tools/perf/util/color.c b/trunk/tools/perf/util/color.c new file mode 100644 index 000000000000..9a8c20ccc53e --- /dev/null +++ b/trunk/tools/perf/util/color.c @@ -0,0 +1,241 @@ +#include "cache.h" +#include "color.h" + +int perf_use_color_default = -1; + +static int parse_color(const char *name, int len) +{ + static const char * const color_names[] = { + "normal", "black", "red", "green", "yellow", + "blue", "magenta", "cyan", "white" + }; + char *end; + int i; + for (i = 0; i < ARRAY_SIZE(color_names); i++) { + const char *str = color_names[i]; + if (!strncasecmp(name, str, len) && !str[len]) + return i - 1; + } + i = strtol(name, &end, 10); + if (end - name == len && i >= -1 && i <= 255) + return i; + return -2; +} + +static int parse_attr(const char *name, int len) +{ + static const int attr_values[] = { 1, 2, 4, 5, 7 }; + static const char * const attr_names[] = { + "bold", "dim", "ul", "blink", "reverse" + }; + int i; + for (i = 0; i < ARRAY_SIZE(attr_names); i++) { + const char *str = attr_names[i]; + if (!strncasecmp(name, str, len) && !str[len]) + return attr_values[i]; + } + return -1; +} + +void color_parse(const char *value, const char *var, char *dst) +{ + color_parse_mem(value, strlen(value), var, dst); +} + +void color_parse_mem(const char *value, int value_len, const char *var, + char *dst) +{ + const char *ptr = value; + int len = value_len; + int attr = -1; + int fg = -2; + int bg = -2; + + if (!strncasecmp(value, "reset", len)) { + strcpy(dst, PERF_COLOR_RESET); + return; + } + + /* [fg [bg]] [attr] */ + while (len > 0) { + const char *word = ptr; + int val, wordlen = 0; + + while (len > 0 && !isspace(word[wordlen])) { + wordlen++; + len--; + } + + ptr = word + wordlen; + while (len > 0 && isspace(*ptr)) { + ptr++; + len--; + } + + val = parse_color(word, wordlen); + if (val >= -1) { + if (fg == -2) { + fg = val; + continue; + } + if (bg == -2) { + bg = val; + continue; + } + goto bad; + } + val = parse_attr(word, wordlen); + if (val < 0 || attr != -1) + goto bad; + attr = val; + } + + if (attr >= 0 || fg >= 0 || bg >= 0) { + int sep = 0; + + *dst++ = '\033'; + *dst++ = '['; + if (attr >= 0) { + *dst++ = '0' + attr; + sep++; + } + if (fg >= 0) { + if (sep++) + *dst++ = ';'; + if (fg < 8) { + *dst++ = '3'; + *dst++ = '0' + fg; + } else { + dst += sprintf(dst, "38;5;%d", fg); + } + } + if (bg >= 0) { + if (sep++) + *dst++ = ';'; + if (bg < 8) { + *dst++ = '4'; + *dst++ = '0' + bg; + } else { + dst += sprintf(dst, "48;5;%d", bg); + } + } + *dst++ = 'm'; + } + *dst = 0; + return; +bad: + die("bad color value '%.*s' for variable '%s'", value_len, value, var); +} + +int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) +{ + if (value) { + if (!strcasecmp(value, "never")) + return 0; + if (!strcasecmp(value, "always")) + return 1; + if (!strcasecmp(value, "auto")) + goto auto_color; + } + + /* Missing or explicit false to turn off colorization */ + if (!perf_config_bool(var, value)) + return 0; + + /* any normal truth value defaults to 'auto' */ + auto_color: + if (stdout_is_tty < 0) + stdout_is_tty = isatty(1); + if (stdout_is_tty || (pager_in_use() && pager_use_color)) { + char *term = getenv("TERM"); + if (term && strcmp(term, "dumb")) + return 1; + } + return 0; +} + +int perf_color_default_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "color.ui")) { + perf_use_color_default = perf_config_colorbool(var, value, -1); + return 0; + } + + return perf_default_config(var, value, cb); +} + +static int color_vfprintf(FILE *fp, const char *color, const char *fmt, + va_list args, const char *trail) +{ + int r = 0; + + /* + * Auto-detect: + */ + if (perf_use_color_default < 0) { + if (isatty(1) || pager_in_use()) + perf_use_color_default = 1; + else + perf_use_color_default = 0; + } + + if (perf_use_color_default && *color) + r += fprintf(fp, "%s", color); + r += vfprintf(fp, fmt, args); + if (perf_use_color_default && *color) + r += fprintf(fp, "%s", PERF_COLOR_RESET); + if (trail) + r += fprintf(fp, "%s", trail); + return r; +} + + + +int color_fprintf(FILE *fp, const char *color, const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = color_vfprintf(fp, color, fmt, args, NULL); + va_end(args); + return r; +} + +int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...) +{ + va_list args; + int r; + va_start(args, fmt); + r = color_vfprintf(fp, color, fmt, args, "\n"); + va_end(args); + return r; +} + +/* + * This function splits the buffer by newlines and colors the lines individually. + * + * Returns 0 on success. + */ +int color_fwrite_lines(FILE *fp, const char *color, + size_t count, const char *buf) +{ + if (!*color) + return fwrite(buf, count, 1, fp) != 1; + while (count) { + char *p = memchr(buf, '\n', count); + if (p != buf && (fputs(color, fp) < 0 || + fwrite(buf, p ? p - buf : count, 1, fp) != 1 || + fputs(PERF_COLOR_RESET, fp) < 0)) + return -1; + if (!p) + return 0; + if (fputc('\n', fp) < 0) + return -1; + count -= p + 1 - buf; + buf = p + 1; + } + return 0; +} + + diff --git a/trunk/tools/perf/util/color.h b/trunk/tools/perf/util/color.h new file mode 100644 index 000000000000..5abfd379582b --- /dev/null +++ b/trunk/tools/perf/util/color.h @@ -0,0 +1,36 @@ +#ifndef COLOR_H +#define COLOR_H + +/* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ +#define COLOR_MAXLEN 24 + +#define PERF_COLOR_NORMAL "" +#define PERF_COLOR_RESET "\033[m" +#define PERF_COLOR_BOLD "\033[1m" +#define PERF_COLOR_RED "\033[31m" +#define PERF_COLOR_GREEN "\033[32m" +#define PERF_COLOR_YELLOW "\033[33m" +#define PERF_COLOR_BLUE "\033[34m" +#define PERF_COLOR_MAGENTA "\033[35m" +#define PERF_COLOR_CYAN "\033[36m" +#define PERF_COLOR_BG_RED "\033[41m" + +/* + * This variable stores the value of color.ui + */ +extern int perf_use_color_default; + + +/* + * Use this instead of perf_default_config if you need the value of color.ui. + */ +int perf_color_default_config(const char *var, const char *value, void *cb); + +int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty); +void color_parse(const char *value, const char *var, char *dst); +void color_parse_mem(const char *value, int len, const char *var, char *dst); +int color_fprintf(FILE *fp, const char *color, const char *fmt, ...); +int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); +int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); + +#endif /* COLOR_H */ diff --git a/trunk/tools/perf/util/config.c b/trunk/tools/perf/util/config.c new file mode 100644 index 000000000000..3dd13faa6a27 --- /dev/null +++ b/trunk/tools/perf/util/config.c @@ -0,0 +1,873 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + * Copyright (C) Johannes Schindelin, 2005 + * + */ +#include "util.h" +#include "cache.h" +#include "exec_cmd.h" + +#define MAXNAME (256) + +static FILE *config_file; +static const char *config_file_name; +static int config_linenr; +static int config_file_eof; + +const char *config_exclusive_filename = NULL; + +static int get_next_char(void) +{ + int c; + FILE *f; + + c = '\n'; + if ((f = config_file) != NULL) { + c = fgetc(f); + if (c == '\r') { + /* DOS like systems */ + c = fgetc(f); + if (c != '\n') { + ungetc(c, f); + c = '\r'; + } + } + if (c == '\n') + config_linenr++; + if (c == EOF) { + config_file_eof = 1; + c = '\n'; + } + } + return c; +} + +static char *parse_value(void) +{ + static char value[1024]; + int quote = 0, comment = 0, len = 0, space = 0; + + for (;;) { + int c = get_next_char(); + if (len >= sizeof(value) - 1) + return NULL; + if (c == '\n') { + if (quote) + return NULL; + value[len] = 0; + return value; + } + if (comment) + continue; + if (isspace(c) && !quote) { + space = 1; + continue; + } + if (!quote) { + if (c == ';' || c == '#') { + comment = 1; + continue; + } + } + if (space) { + if (len) + value[len++] = ' '; + space = 0; + } + if (c == '\\') { + c = get_next_char(); + switch (c) { + case '\n': + continue; + case 't': + c = '\t'; + break; + case 'b': + c = '\b'; + break; + case 'n': + c = '\n'; + break; + /* Some characters escape as themselves */ + case '\\': case '"': + break; + /* Reject unknown escape sequences */ + default: + return NULL; + } + value[len++] = c; + continue; + } + if (c == '"') { + quote = 1-quote; + continue; + } + value[len++] = c; + } +} + +static inline int iskeychar(int c) +{ + return isalnum(c) || c == '-'; +} + +static int get_value(config_fn_t fn, void *data, char *name, unsigned int len) +{ + int c; + char *value; + + /* Get the full name */ + for (;;) { + c = get_next_char(); + if (config_file_eof) + break; + if (!iskeychar(c)) + break; + name[len++] = tolower(c); + if (len >= MAXNAME) + return -1; + } + name[len] = 0; + while (c == ' ' || c == '\t') + c = get_next_char(); + + value = NULL; + if (c != '\n') { + if (c != '=') + return -1; + value = parse_value(); + if (!value) + return -1; + } + return fn(name, value, data); +} + +static int get_extended_base_var(char *name, int baselen, int c) +{ + do { + if (c == '\n') + return -1; + c = get_next_char(); + } while (isspace(c)); + + /* We require the format to be '[base "extension"]' */ + if (c != '"') + return -1; + name[baselen++] = '.'; + + for (;;) { + int c = get_next_char(); + if (c == '\n') + return -1; + if (c == '"') + break; + if (c == '\\') { + c = get_next_char(); + if (c == '\n') + return -1; + } + name[baselen++] = c; + if (baselen > MAXNAME / 2) + return -1; + } + + /* Final ']' */ + if (get_next_char() != ']') + return -1; + return baselen; +} + +static int get_base_var(char *name) +{ + int baselen = 0; + + for (;;) { + int c = get_next_char(); + if (config_file_eof) + return -1; + if (c == ']') + return baselen; + if (isspace(c)) + return get_extended_base_var(name, baselen, c); + if (!iskeychar(c) && c != '.') + return -1; + if (baselen > MAXNAME / 2) + return -1; + name[baselen++] = tolower(c); + } +} + +static int perf_parse_file(config_fn_t fn, void *data) +{ + int comment = 0; + int baselen = 0; + static char var[MAXNAME]; + + /* U+FEFF Byte Order Mark in UTF8 */ + static const unsigned char *utf8_bom = (unsigned char *) "\xef\xbb\xbf"; + const unsigned char *bomptr = utf8_bom; + + for (;;) { + int c = get_next_char(); + if (bomptr && *bomptr) { + /* We are at the file beginning; skip UTF8-encoded BOM + * if present. Sane editors won't put this in on their + * own, but e.g. Windows Notepad will do it happily. */ + if ((unsigned char) c == *bomptr) { + bomptr++; + continue; + } else { + /* Do not tolerate partial BOM. */ + if (bomptr != utf8_bom) + break; + /* No BOM at file beginning. Cool. */ + bomptr = NULL; + } + } + if (c == '\n') { + if (config_file_eof) + return 0; + comment = 0; + continue; + } + if (comment || isspace(c)) + continue; + if (c == '#' || c == ';') { + comment = 1; + continue; + } + if (c == '[') { + baselen = get_base_var(var); + if (baselen <= 0) + break; + var[baselen++] = '.'; + var[baselen] = 0; + continue; + } + if (!isalpha(c)) + break; + var[baselen] = tolower(c); + if (get_value(fn, data, var, baselen+1) < 0) + break; + } + die("bad config file line %d in %s", config_linenr, config_file_name); +} + +static int parse_unit_factor(const char *end, unsigned long *val) +{ + if (!*end) + return 1; + else if (!strcasecmp(end, "k")) { + *val *= 1024; + return 1; + } + else if (!strcasecmp(end, "m")) { + *val *= 1024 * 1024; + return 1; + } + else if (!strcasecmp(end, "g")) { + *val *= 1024 * 1024 * 1024; + return 1; + } + return 0; +} + +static int perf_parse_long(const char *value, long *ret) +{ + if (value && *value) { + char *end; + long val = strtol(value, &end, 0); + unsigned long factor = 1; + if (!parse_unit_factor(end, &factor)) + return 0; + *ret = val * factor; + return 1; + } + return 0; +} + +int perf_parse_ulong(const char *value, unsigned long *ret) +{ + if (value && *value) { + char *end; + unsigned long val = strtoul(value, &end, 0); + if (!parse_unit_factor(end, &val)) + return 0; + *ret = val; + return 1; + } + return 0; +} + +static void die_bad_config(const char *name) +{ + if (config_file_name) + die("bad config value for '%s' in %s", name, config_file_name); + die("bad config value for '%s'", name); +} + +int perf_config_int(const char *name, const char *value) +{ + long ret = 0; + if (!perf_parse_long(value, &ret)) + die_bad_config(name); + return ret; +} + +unsigned long perf_config_ulong(const char *name, const char *value) +{ + unsigned long ret; + if (!perf_parse_ulong(value, &ret)) + die_bad_config(name); + return ret; +} + +int perf_config_bool_or_int(const char *name, const char *value, int *is_bool) +{ + *is_bool = 1; + if (!value) + return 1; + if (!*value) + return 0; + if (!strcasecmp(value, "true") || !strcasecmp(value, "yes") || !strcasecmp(value, "on")) + return 1; + if (!strcasecmp(value, "false") || !strcasecmp(value, "no") || !strcasecmp(value, "off")) + return 0; + *is_bool = 0; + return perf_config_int(name, value); +} + +int perf_config_bool(const char *name, const char *value) +{ + int discard; + return !!perf_config_bool_or_int(name, value, &discard); +} + +int perf_config_string(const char **dest, const char *var, const char *value) +{ + if (!value) + return config_error_nonbool(var); + *dest = strdup(value); + return 0; +} + +static int perf_default_core_config(const char *var, const char *value) +{ + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} + +int perf_default_config(const char *var, const char *value, void *dummy) +{ + if (!prefixcmp(var, "core.")) + return perf_default_core_config(var, value); + + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} + +int perf_config_from_file(config_fn_t fn, const char *filename, void *data) +{ + int ret; + FILE *f = fopen(filename, "r"); + + ret = -1; + if (f) { + config_file = f; + config_file_name = filename; + config_linenr = 1; + config_file_eof = 0; + ret = perf_parse_file(fn, data); + fclose(f); + config_file_name = NULL; + } + return ret; +} + +const char *perf_etc_perfconfig(void) +{ + static const char *system_wide; + if (!system_wide) + system_wide = system_path(ETC_PERFCONFIG); + return system_wide; +} + +static int perf_env_bool(const char *k, int def) +{ + const char *v = getenv(k); + return v ? perf_config_bool(k, v) : def; +} + +int perf_config_system(void) +{ + return !perf_env_bool("PERF_CONFIG_NOSYSTEM", 0); +} + +int perf_config_global(void) +{ + return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0); +} + +int perf_config(config_fn_t fn, void *data) +{ + int ret = 0, found = 0; + char *repo_config = NULL; + const char *home = NULL; + + /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ + if (config_exclusive_filename) + return perf_config_from_file(fn, config_exclusive_filename, data); + if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) { + ret += perf_config_from_file(fn, perf_etc_perfconfig(), + data); + found += 1; + } + + home = getenv("HOME"); + if (perf_config_global() && home) { + char *user_config = strdup(mkpath("%s/.perfconfig", home)); + if (!access(user_config, R_OK)) { + ret += perf_config_from_file(fn, user_config, data); + found += 1; + } + free(user_config); + } + + repo_config = perf_pathdup("config"); + if (!access(repo_config, R_OK)) { + ret += perf_config_from_file(fn, repo_config, data); + found += 1; + } + free(repo_config); + if (found == 0) + return -1; + return ret; +} + +/* + * Find all the stuff for perf_config_set() below. + */ + +#define MAX_MATCHES 512 + +static struct { + int baselen; + char* key; + int do_not_match; + regex_t* value_regex; + int multi_replace; + size_t offset[MAX_MATCHES]; + enum { START, SECTION_SEEN, SECTION_END_SEEN, KEY_SEEN } state; + int seen; +} store; + +static int matches(const char* key, const char* value) +{ + return !strcmp(key, store.key) && + (store.value_regex == NULL || + (store.do_not_match ^ + !regexec(store.value_regex, value, 0, NULL, 0))); +} + +static int store_aux(const char* key, const char* value, void *cb) +{ + const char *ep; + size_t section_len; + + switch (store.state) { + case KEY_SEEN: + if (matches(key, value)) { + if (store.seen == 1 && store.multi_replace == 0) { + warning("%s has multiple values", key); + } else if (store.seen >= MAX_MATCHES) { + error("too many matches for %s", key); + return 1; + } + + store.offset[store.seen] = ftell(config_file); + store.seen++; + } + break; + case SECTION_SEEN: + /* + * What we are looking for is in store.key (both + * section and var), and its section part is baselen + * long. We found key (again, both section and var). + * We would want to know if this key is in the same + * section as what we are looking for. We already + * know we are in the same section as what should + * hold store.key. + */ + ep = strrchr(key, '.'); + section_len = ep - key; + + if ((section_len != store.baselen) || + memcmp(key, store.key, section_len+1)) { + store.state = SECTION_END_SEEN; + break; + } + + /* + * Do not increment matches: this is no match, but we + * just made sure we are in the desired section. + */ + store.offset[store.seen] = ftell(config_file); + /* fallthru */ + case SECTION_END_SEEN: + case START: + if (matches(key, value)) { + store.offset[store.seen] = ftell(config_file); + store.state = KEY_SEEN; + store.seen++; + } else { + if (strrchr(key, '.') - key == store.baselen && + !strncmp(key, store.key, store.baselen)) { + store.state = SECTION_SEEN; + store.offset[store.seen] = ftell(config_file); + } + } + } + return 0; +} + +static int store_write_section(int fd, const char* key) +{ + const char *dot; + int i, success; + struct strbuf sb = STRBUF_INIT; + + dot = memchr(key, '.', store.baselen); + if (dot) { + strbuf_addf(&sb, "[%.*s \"", (int)(dot - key), key); + for (i = dot - key + 1; i < store.baselen; i++) { + if (key[i] == '"' || key[i] == '\\') + strbuf_addch(&sb, '\\'); + strbuf_addch(&sb, key[i]); + } + strbuf_addstr(&sb, "\"]\n"); + } else { + strbuf_addf(&sb, "[%.*s]\n", store.baselen, key); + } + + success = write_in_full(fd, sb.buf, sb.len) == sb.len; + strbuf_release(&sb); + + return success; +} + +static int store_write_pair(int fd, const char* key, const char* value) +{ + int i, success; + int length = strlen(key + store.baselen + 1); + const char *quote = ""; + struct strbuf sb = STRBUF_INIT; + + /* + * Check to see if the value needs to be surrounded with a dq pair. + * Note that problematic characters are always backslash-quoted; this + * check is about not losing leading or trailing SP and strings that + * follow beginning-of-comment characters (i.e. ';' and '#') by the + * configuration parser. + */ + if (value[0] == ' ') + quote = "\""; + for (i = 0; value[i]; i++) + if (value[i] == ';' || value[i] == '#') + quote = "\""; + if (i && value[i - 1] == ' ') + quote = "\""; + + strbuf_addf(&sb, "\t%.*s = %s", + length, key + store.baselen + 1, quote); + + for (i = 0; value[i]; i++) + switch (value[i]) { + case '\n': + strbuf_addstr(&sb, "\\n"); + break; + case '\t': + strbuf_addstr(&sb, "\\t"); + break; + case '"': + case '\\': + strbuf_addch(&sb, '\\'); + default: + strbuf_addch(&sb, value[i]); + break; + } + strbuf_addf(&sb, "%s\n", quote); + + success = write_in_full(fd, sb.buf, sb.len) == sb.len; + strbuf_release(&sb); + + return success; +} + +static ssize_t find_beginning_of_line(const char* contents, size_t size, + size_t offset_, int* found_bracket) +{ + size_t equal_offset = size, bracket_offset = size; + ssize_t offset; + +contline: + for (offset = offset_-2; offset > 0 + && contents[offset] != '\n'; offset--) + switch (contents[offset]) { + case '=': equal_offset = offset; break; + case ']': bracket_offset = offset; break; + } + if (offset > 0 && contents[offset-1] == '\\') { + offset_ = offset; + goto contline; + } + if (bracket_offset < equal_offset) { + *found_bracket = 1; + offset = bracket_offset+1; + } else + offset++; + + return offset; +} + +int perf_config_set(const char* key, const char* value) +{ + return perf_config_set_multivar(key, value, NULL, 0); +} + +/* + * If value==NULL, unset in (remove from) config, + * if value_regex!=NULL, disregard key/value pairs where value does not match. + * if multi_replace==0, nothing, or only one matching key/value is replaced, + * else all matching key/values (regardless how many) are removed, + * before the new pair is written. + * + * Returns 0 on success. + * + * This function does this: + * + * - it locks the config file by creating ".perf/config.lock" + * + * - it then parses the config using store_aux() as validator to find + * the position on the key/value pair to replace. If it is to be unset, + * it must be found exactly once. + * + * - the config file is mmap()ed and the part before the match (if any) is + * written to the lock file, then the changed part and the rest. + * + * - the config file is removed and the lock file rename()d to it. + * + */ +int perf_config_set_multivar(const char* key, const char* value, + const char* value_regex, int multi_replace) +{ + int i, dot; + int fd = -1, in_fd; + int ret = 0; + char* config_filename; + const char* last_dot = strrchr(key, '.'); + + if (config_exclusive_filename) + config_filename = strdup(config_exclusive_filename); + else + config_filename = perf_pathdup("config"); + + /* + * Since "key" actually contains the section name and the real + * key name separated by a dot, we have to know where the dot is. + */ + + if (last_dot == NULL) { + error("key does not contain a section: %s", key); + ret = 2; + goto out_free; + } + store.baselen = last_dot - key; + + store.multi_replace = multi_replace; + + /* + * Validate the key and while at it, lower case it for matching. + */ + store.key = malloc(strlen(key) + 1); + dot = 0; + for (i = 0; key[i]; i++) { + unsigned char c = key[i]; + if (c == '.') + dot = 1; + /* Leave the extended basename untouched.. */ + if (!dot || i > store.baselen) { + if (!iskeychar(c) || (i == store.baselen+1 && !isalpha(c))) { + error("invalid key: %s", key); + free(store.key); + ret = 1; + goto out_free; + } + c = tolower(c); + } else if (c == '\n') { + error("invalid key (newline): %s", key); + free(store.key); + ret = 1; + goto out_free; + } + store.key[i] = c; + } + store.key[i] = 0; + + /* + * If .perf/config does not exist yet, write a minimal version. + */ + in_fd = open(config_filename, O_RDONLY); + if ( in_fd < 0 ) { + free(store.key); + + if ( ENOENT != errno ) { + error("opening %s: %s", config_filename, + strerror(errno)); + ret = 3; /* same as "invalid config file" */ + goto out_free; + } + /* if nothing to unset, error out */ + if (value == NULL) { + ret = 5; + goto out_free; + } + + store.key = (char*)key; + if (!store_write_section(fd, key) || + !store_write_pair(fd, key, value)) + goto write_err_out; + } else { + struct stat st; + char* contents; + size_t contents_sz, copy_begin, copy_end; + int i, new_line = 0; + + if (value_regex == NULL) + store.value_regex = NULL; + else { + if (value_regex[0] == '!') { + store.do_not_match = 1; + value_regex++; + } else + store.do_not_match = 0; + + store.value_regex = (regex_t*)malloc(sizeof(regex_t)); + if (regcomp(store.value_regex, value_regex, + REG_EXTENDED)) { + error("invalid pattern: %s", value_regex); + free(store.value_regex); + ret = 6; + goto out_free; + } + } + + store.offset[0] = 0; + store.state = START; + store.seen = 0; + + /* + * After this, store.offset will contain the *end* offset + * of the last match, or remain at 0 if no match was found. + * As a side effect, we make sure to transform only a valid + * existing config file. + */ + if (perf_config_from_file(store_aux, config_filename, NULL)) { + error("invalid config file %s", config_filename); + free(store.key); + if (store.value_regex != NULL) { + regfree(store.value_regex); + free(store.value_regex); + } + ret = 3; + goto out_free; + } + + free(store.key); + if (store.value_regex != NULL) { + regfree(store.value_regex); + free(store.value_regex); + } + + /* if nothing to unset, or too many matches, error out */ + if ((store.seen == 0 && value == NULL) || + (store.seen > 1 && multi_replace == 0)) { + ret = 5; + goto out_free; + } + + fstat(in_fd, &st); + contents_sz = xsize_t(st.st_size); + contents = mmap(NULL, contents_sz, PROT_READ, + MAP_PRIVATE, in_fd, 0); + close(in_fd); + + if (store.seen == 0) + store.seen = 1; + + for (i = 0, copy_begin = 0; i < store.seen; i++) { + if (store.offset[i] == 0) { + store.offset[i] = copy_end = contents_sz; + } else if (store.state != KEY_SEEN) { + copy_end = store.offset[i]; + } else + copy_end = find_beginning_of_line( + contents, contents_sz, + store.offset[i]-2, &new_line); + + if (copy_end > 0 && contents[copy_end-1] != '\n') + new_line = 1; + + /* write the first part of the config */ + if (copy_end > copy_begin) { + if (write_in_full(fd, contents + copy_begin, + copy_end - copy_begin) < + copy_end - copy_begin) + goto write_err_out; + if (new_line && + write_in_full(fd, "\n", 1) != 1) + goto write_err_out; + } + copy_begin = store.offset[i]; + } + + /* write the pair (value == NULL means unset) */ + if (value != NULL) { + if (store.state == START) { + if (!store_write_section(fd, key)) + goto write_err_out; + } + if (!store_write_pair(fd, key, value)) + goto write_err_out; + } + + /* write the rest of the config */ + if (copy_begin < contents_sz) + if (write_in_full(fd, contents + copy_begin, + contents_sz - copy_begin) < + contents_sz - copy_begin) + goto write_err_out; + + munmap(contents, contents_sz); + } + + ret = 0; + +out_free: + free(config_filename); + return ret; + +write_err_out: + goto out_free; + +} + +/* + * Call this to report error for your variable that should not + * get a boolean value (i.e. "[my] var" means "true"). + */ +int config_error_nonbool(const char *var) +{ + return error("Missing value for '%s'", var); +} diff --git a/trunk/tools/perf/util/ctype.c b/trunk/tools/perf/util/ctype.c new file mode 100644 index 000000000000..b90ec004f29c --- /dev/null +++ b/trunk/tools/perf/util/ctype.c @@ -0,0 +1,26 @@ +/* + * Sane locale-independent, ASCII ctype. + * + * No surprises, and works with signed and unsigned chars. + */ +#include "cache.h" + +enum { + S = GIT_SPACE, + A = GIT_ALPHA, + D = GIT_DIGIT, + G = GIT_GLOB_SPECIAL, /* *, ?, [, \\ */ + R = GIT_REGEX_SPECIAL, /* $, (, ), +, ., ^, {, | * */ +}; + +unsigned char sane_ctype[256] = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, S, S, 0, 0, S, 0, 0, /* 0.. 15 */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16.. 31 */ + S, 0, 0, 0, R, 0, 0, 0, R, R, G, R, 0, 0, R, 0, /* 32.. 47 */ + D, D, D, D, D, D, D, D, D, D, 0, 0, 0, 0, 0, G, /* 48.. 63 */ + 0, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 64.. 79 */ + A, A, A, A, A, A, A, A, A, A, A, G, G, 0, R, 0, /* 80.. 95 */ + 0, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 96..111 */ + A, A, A, A, A, A, A, A, A, A, A, R, R, 0, 0, 0, /* 112..127 */ + /* Nothing in the 128.. range */ +}; diff --git a/trunk/tools/perf/util/environment.c b/trunk/tools/perf/util/environment.c new file mode 100644 index 000000000000..275b0ee345f5 --- /dev/null +++ b/trunk/tools/perf/util/environment.c @@ -0,0 +1,9 @@ +/* + * We put all the perf config variables in this same object + * file, so that programs can link against the config parser + * without having to link against all the rest of perf. + */ +#include "cache.h" + +const char *pager_program; +int pager_use_color = 1; diff --git a/trunk/tools/perf/util/exec_cmd.c b/trunk/tools/perf/util/exec_cmd.c new file mode 100644 index 000000000000..d39292263153 --- /dev/null +++ b/trunk/tools/perf/util/exec_cmd.c @@ -0,0 +1,165 @@ +#include "cache.h" +#include "exec_cmd.h" +#include "quote.h" +#define MAX_ARGS 32 + +extern char **environ; +static const char *argv_exec_path; +static const char *argv0_path; + +const char *system_path(const char *path) +{ +#ifdef RUNTIME_PREFIX + static const char *prefix; +#else + static const char *prefix = PREFIX; +#endif + struct strbuf d = STRBUF_INIT; + + if (is_absolute_path(path)) + return path; + +#ifdef RUNTIME_PREFIX + assert(argv0_path); + assert(is_absolute_path(argv0_path)); + + if (!prefix && + !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) && + !(prefix = strip_path_suffix(argv0_path, BINDIR)) && + !(prefix = strip_path_suffix(argv0_path, "perf"))) { + prefix = PREFIX; + fprintf(stderr, "RUNTIME_PREFIX requested, " + "but prefix computation failed. " + "Using static fallback '%s'.\n", prefix); + } +#endif + + strbuf_addf(&d, "%s/%s", prefix, path); + path = strbuf_detach(&d, NULL); + return path; +} + +const char *perf_extract_argv0_path(const char *argv0) +{ + const char *slash; + + if (!argv0 || !*argv0) + return NULL; + slash = argv0 + strlen(argv0); + + while (argv0 <= slash && !is_dir_sep(*slash)) + slash--; + + if (slash >= argv0) { + argv0_path = strndup(argv0, slash - argv0); + return slash + 1; + } + + return argv0; +} + +void perf_set_argv_exec_path(const char *exec_path) +{ + argv_exec_path = exec_path; + /* + * Propagate this setting to external programs. + */ + setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1); +} + + +/* Returns the highest-priority, location to look for perf programs. */ +const char *perf_exec_path(void) +{ + const char *env; + + if (argv_exec_path) + return argv_exec_path; + + env = getenv(EXEC_PATH_ENVIRONMENT); + if (env && *env) { + return env; + } + + return system_path(PERF_EXEC_PATH); +} + +static void add_path(struct strbuf *out, const char *path) +{ + if (path && *path) { + if (is_absolute_path(path)) + strbuf_addstr(out, path); + else + strbuf_addstr(out, make_nonrelative_path(path)); + + strbuf_addch(out, PATH_SEP); + } +} + +void setup_path(void) +{ + const char *old_path = getenv("PATH"); + struct strbuf new_path = STRBUF_INIT; + + add_path(&new_path, perf_exec_path()); + add_path(&new_path, argv0_path); + + if (old_path) + strbuf_addstr(&new_path, old_path); + else + strbuf_addstr(&new_path, "/usr/local/bin:/usr/bin:/bin"); + + setenv("PATH", new_path.buf, 1); + + strbuf_release(&new_path); +} + +const char **prepare_perf_cmd(const char **argv) +{ + int argc; + const char **nargv; + + for (argc = 0; argv[argc]; argc++) + ; /* just counting */ + nargv = malloc(sizeof(*nargv) * (argc + 2)); + + nargv[0] = "perf"; + for (argc = 0; argv[argc]; argc++) + nargv[argc + 1] = argv[argc]; + nargv[argc + 1] = NULL; + return nargv; +} + +int execv_perf_cmd(const char **argv) { + const char **nargv = prepare_perf_cmd(argv); + + /* execvp() can only ever return if it fails */ + execvp("perf", (char **)nargv); + + free(nargv); + return -1; +} + + +int execl_perf_cmd(const char *cmd,...) +{ + int argc; + const char *argv[MAX_ARGS + 1]; + const char *arg; + va_list param; + + va_start(param, cmd); + argv[0] = cmd; + argc = 1; + while (argc < MAX_ARGS) { + arg = argv[argc++] = va_arg(param, char *); + if (!arg) + break; + } + va_end(param); + if (MAX_ARGS <= argc) + return error("too many args to run %s", cmd); + + argv[argc] = NULL; + return execv_perf_cmd(argv); +} diff --git a/trunk/tools/perf/util/exec_cmd.h b/trunk/tools/perf/util/exec_cmd.h new file mode 100644 index 000000000000..effe25eb1545 --- /dev/null +++ b/trunk/tools/perf/util/exec_cmd.h @@ -0,0 +1,13 @@ +#ifndef PERF_EXEC_CMD_H +#define PERF_EXEC_CMD_H + +extern void perf_set_argv_exec_path(const char *exec_path); +extern const char *perf_extract_argv0_path(const char *path); +extern const char *perf_exec_path(void); +extern void setup_path(void); +extern const char **prepare_perf_cmd(const char **argv); +extern int execv_perf_cmd(const char **argv); /* NULL terminated */ +extern int execl_perf_cmd(const char *cmd, ...); +extern const char *system_path(const char *path); + +#endif /* PERF_EXEC_CMD_H */ diff --git a/trunk/tools/perf/util/generate-cmdlist.sh b/trunk/tools/perf/util/generate-cmdlist.sh new file mode 100755 index 000000000000..f06f6fd148f8 --- /dev/null +++ b/trunk/tools/perf/util/generate-cmdlist.sh @@ -0,0 +1,24 @@ +#!/bin/sh + +echo "/* Automatically generated by $0 */ +struct cmdname_help +{ + char name[16]; + char help[80]; +}; + +static struct cmdname_help common_cmds[] = {" + +sed -n -e 's/^perf-\([^ ]*\)[ ].* common.*/\1/p' command-list.txt | +sort | +while read cmd +do + sed -n ' + /^NAME/,/perf-'"$cmd"'/H + ${ + x + s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/perf-$cmd.txt" +done +echo "};" diff --git a/trunk/tools/perf/util/help.c b/trunk/tools/perf/util/help.c new file mode 100644 index 000000000000..6653f7dd1d78 --- /dev/null +++ b/trunk/tools/perf/util/help.c @@ -0,0 +1,367 @@ +#include "cache.h" +#include "../builtin.h" +#include "exec_cmd.h" +#include "levenshtein.h" +#include "help.h" + +/* most GUI terminals set COLUMNS (although some don't export it) */ +static int term_columns(void) +{ + char *col_string = getenv("COLUMNS"); + int n_cols; + + if (col_string && (n_cols = atoi(col_string)) > 0) + return n_cols; + +#ifdef TIOCGWINSZ + { + struct winsize ws; + if (!ioctl(1, TIOCGWINSZ, &ws)) { + if (ws.ws_col) + return ws.ws_col; + } + } +#endif + + return 80; +} + +void add_cmdname(struct cmdnames *cmds, const char *name, int len) +{ + struct cmdname *ent = malloc(sizeof(*ent) + len + 1); + + ent->len = len; + memcpy(ent->name, name, len); + ent->name[len] = 0; + + ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc); + cmds->names[cmds->cnt++] = ent; +} + +static void clean_cmdnames(struct cmdnames *cmds) +{ + int i; + for (i = 0; i < cmds->cnt; ++i) + free(cmds->names[i]); + free(cmds->names); + cmds->cnt = 0; + cmds->alloc = 0; +} + +static int cmdname_compare(const void *a_, const void *b_) +{ + struct cmdname *a = *(struct cmdname **)a_; + struct cmdname *b = *(struct cmdname **)b_; + return strcmp(a->name, b->name); +} + +static void uniq(struct cmdnames *cmds) +{ + int i, j; + + if (!cmds->cnt) + return; + + for (i = j = 1; i < cmds->cnt; i++) + if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) + cmds->names[j++] = cmds->names[i]; + + cmds->cnt = j; +} + +void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) +{ + int ci, cj, ei; + int cmp; + + ci = cj = ei = 0; + while (ci < cmds->cnt && ei < excludes->cnt) { + cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name); + if (cmp < 0) + cmds->names[cj++] = cmds->names[ci++]; + else if (cmp == 0) + ci++, ei++; + else if (cmp > 0) + ei++; + } + + while (ci < cmds->cnt) + cmds->names[cj++] = cmds->names[ci++]; + + cmds->cnt = cj; +} + +static void pretty_print_string_list(struct cmdnames *cmds, int longest) +{ + int cols = 1, rows; + int space = longest + 1; /* min 1 SP between words */ + int max_cols = term_columns() - 1; /* don't print *on* the edge */ + int i, j; + + if (space < max_cols) + cols = max_cols / space; + rows = (cmds->cnt + cols - 1) / cols; + + for (i = 0; i < rows; i++) { + printf(" "); + + for (j = 0; j < cols; j++) { + int n = j * rows + i; + int size = space; + if (n >= cmds->cnt) + break; + if (j == cols-1 || n + rows >= cmds->cnt) + size = 1; + printf("%-*s", size, cmds->names[n]->name); + } + putchar('\n'); + } +} + +static int is_executable(const char *name) +{ + struct stat st; + + if (stat(name, &st) || /* stat, not lstat */ + !S_ISREG(st.st_mode)) + return 0; + +#ifdef __MINGW32__ + /* cannot trust the executable bit, peek into the file instead */ + char buf[3] = { 0 }; + int n; + int fd = open(name, O_RDONLY); + st.st_mode &= ~S_IXUSR; + if (fd >= 0) { + n = read(fd, buf, 2); + if (n == 2) + /* DOS executables start with "MZ" */ + if (!strcmp(buf, "#!") || !strcmp(buf, "MZ")) + st.st_mode |= S_IXUSR; + close(fd); + } +#endif + return st.st_mode & S_IXUSR; +} + +static void list_commands_in_dir(struct cmdnames *cmds, + const char *path, + const char *prefix) +{ + int prefix_len; + DIR *dir = opendir(path); + struct dirent *de; + struct strbuf buf = STRBUF_INIT; + int len; + + if (!dir) + return; + if (!prefix) + prefix = "perf-"; + prefix_len = strlen(prefix); + + strbuf_addf(&buf, "%s/", path); + len = buf.len; + + while ((de = readdir(dir)) != NULL) { + int entlen; + + if (prefixcmp(de->d_name, prefix)) + continue; + + strbuf_setlen(&buf, len); + strbuf_addstr(&buf, de->d_name); + if (!is_executable(buf.buf)) + continue; + + entlen = strlen(de->d_name) - prefix_len; + if (has_extension(de->d_name, ".exe")) + entlen -= 4; + + add_cmdname(cmds, de->d_name + prefix_len, entlen); + } + closedir(dir); + strbuf_release(&buf); +} + +void load_command_list(const char *prefix, + struct cmdnames *main_cmds, + struct cmdnames *other_cmds) +{ + const char *env_path = getenv("PATH"); + const char *exec_path = perf_exec_path(); + + if (exec_path) { + list_commands_in_dir(main_cmds, exec_path, prefix); + qsort(main_cmds->names, main_cmds->cnt, + sizeof(*main_cmds->names), cmdname_compare); + uniq(main_cmds); + } + + if (env_path) { + char *paths, *path, *colon; + path = paths = strdup(env_path); + while (1) { + if ((colon = strchr(path, PATH_SEP))) + *colon = 0; + if (!exec_path || strcmp(path, exec_path)) + list_commands_in_dir(other_cmds, path, prefix); + + if (!colon) + break; + path = colon + 1; + } + free(paths); + + qsort(other_cmds->names, other_cmds->cnt, + sizeof(*other_cmds->names), cmdname_compare); + uniq(other_cmds); + } + exclude_cmds(other_cmds, main_cmds); +} + +void list_commands(const char *title, struct cmdnames *main_cmds, + struct cmdnames *other_cmds) +{ + int i, longest = 0; + + for (i = 0; i < main_cmds->cnt; i++) + if (longest < main_cmds->names[i]->len) + longest = main_cmds->names[i]->len; + for (i = 0; i < other_cmds->cnt; i++) + if (longest < other_cmds->names[i]->len) + longest = other_cmds->names[i]->len; + + if (main_cmds->cnt) { + const char *exec_path = perf_exec_path(); + printf("available %s in '%s'\n", title, exec_path); + printf("----------------"); + mput_char('-', strlen(title) + strlen(exec_path)); + putchar('\n'); + pretty_print_string_list(main_cmds, longest); + putchar('\n'); + } + + if (other_cmds->cnt) { + printf("%s available from elsewhere on your $PATH\n", title); + printf("---------------------------------------"); + mput_char('-', strlen(title)); + putchar('\n'); + pretty_print_string_list(other_cmds, longest); + putchar('\n'); + } +} + +int is_in_cmdlist(struct cmdnames *c, const char *s) +{ + int i; + for (i = 0; i < c->cnt; i++) + if (!strcmp(s, c->names[i]->name)) + return 1; + return 0; +} + +static int autocorrect; +static struct cmdnames aliases; + +static int perf_unknown_cmd_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "help.autocorrect")) + autocorrect = perf_config_int(var,value); + /* Also use aliases for command lookup */ + if (!prefixcmp(var, "alias.")) + add_cmdname(&aliases, var + 6, strlen(var + 6)); + + return perf_default_config(var, value, cb); +} + +static int levenshtein_compare(const void *p1, const void *p2) +{ + const struct cmdname *const *c1 = p1, *const *c2 = p2; + const char *s1 = (*c1)->name, *s2 = (*c2)->name; + int l1 = (*c1)->len; + int l2 = (*c2)->len; + return l1 != l2 ? l1 - l2 : strcmp(s1, s2); +} + +static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) +{ + int i; + ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc); + + for (i = 0; i < old->cnt; i++) + cmds->names[cmds->cnt++] = old->names[i]; + free(old->names); + old->cnt = 0; + old->names = NULL; +} + +const char *help_unknown_cmd(const char *cmd) +{ + int i, n = 0, best_similarity = 0; + struct cmdnames main_cmds, other_cmds; + + memset(&main_cmds, 0, sizeof(main_cmds)); + memset(&other_cmds, 0, sizeof(main_cmds)); + memset(&aliases, 0, sizeof(aliases)); + + perf_config(perf_unknown_cmd_config, NULL); + + load_command_list("perf-", &main_cmds, &other_cmds); + + add_cmd_list(&main_cmds, &aliases); + add_cmd_list(&main_cmds, &other_cmds); + qsort(main_cmds.names, main_cmds.cnt, + sizeof(main_cmds.names), cmdname_compare); + uniq(&main_cmds); + + if (main_cmds.cnt) { + /* This reuses cmdname->len for similarity index */ + for (i = 0; i < main_cmds.cnt; ++i) + main_cmds.names[i]->len = + levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4); + + qsort(main_cmds.names, main_cmds.cnt, + sizeof(*main_cmds.names), levenshtein_compare); + + best_similarity = main_cmds.names[0]->len; + n = 1; + while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len) + ++n; + } + + if (autocorrect && n == 1) { + const char *assumed = main_cmds.names[0]->name; + + main_cmds.names[0] = NULL; + clean_cmdnames(&main_cmds); + fprintf(stderr, "WARNING: You called a Git program named '%s', " + "which does not exist.\n" + "Continuing under the assumption that you meant '%s'\n", + cmd, assumed); + if (autocorrect > 0) { + fprintf(stderr, "in %0.1f seconds automatically...\n", + (float)autocorrect/10.0); + poll(NULL, 0, autocorrect * 100); + } + return assumed; + } + + fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd); + + if (main_cmds.cnt && best_similarity < 6) { + fprintf(stderr, "\nDid you mean %s?\n", + n < 2 ? "this": "one of these"); + + for (i = 0; i < n; i++) + fprintf(stderr, "\t%s\n", main_cmds.names[i]->name); + } + + exit(1); +} + +int cmd_version(int argc, const char **argv, const char *prefix) +{ + printf("perf version %s\n", perf_version_string); + return 0; +} diff --git a/trunk/tools/perf/util/help.h b/trunk/tools/perf/util/help.h new file mode 100644 index 000000000000..56bc15406ffc --- /dev/null +++ b/trunk/tools/perf/util/help.h @@ -0,0 +1,29 @@ +#ifndef HELP_H +#define HELP_H + +struct cmdnames { + int alloc; + int cnt; + struct cmdname { + size_t len; /* also used for similarity index in help.c */ + char name[FLEX_ARRAY]; + } **names; +}; + +static inline void mput_char(char c, unsigned int num) +{ + while(num--) + putchar(c); +} + +void load_command_list(const char *prefix, + struct cmdnames *main_cmds, + struct cmdnames *other_cmds); +void add_cmdname(struct cmdnames *cmds, const char *name, int len); +/* Here we require that excludes is a sorted list. */ +void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes); +int is_in_cmdlist(struct cmdnames *c, const char *s); +void list_commands(const char *title, struct cmdnames *main_cmds, + struct cmdnames *other_cmds); + +#endif /* HELP_H */ diff --git a/trunk/tools/perf/util/levenshtein.c b/trunk/tools/perf/util/levenshtein.c new file mode 100644 index 000000000000..e521d1516df6 --- /dev/null +++ b/trunk/tools/perf/util/levenshtein.c @@ -0,0 +1,84 @@ +#include "cache.h" +#include "levenshtein.h" + +/* + * This function implements the Damerau-Levenshtein algorithm to + * calculate a distance between strings. + * + * Basically, it says how many letters need to be swapped, substituted, + * deleted from, or added to string1, at least, to get string2. + * + * The idea is to build a distance matrix for the substrings of both + * strings. To avoid a large space complexity, only the last three rows + * are kept in memory (if swaps had the same or higher cost as one deletion + * plus one insertion, only two rows would be needed). + * + * At any stage, "i + 1" denotes the length of the current substring of + * string1 that the distance is calculated for. + * + * row2 holds the current row, row1 the previous row (i.e. for the substring + * of string1 of length "i"), and row0 the row before that. + * + * In other words, at the start of the big loop, row2[j + 1] contains the + * Damerau-Levenshtein distance between the substring of string1 of length + * "i" and the substring of string2 of length "j + 1". + * + * All the big loop does is determine the partial minimum-cost paths. + * + * It does so by calculating the costs of the path ending in characters + * i (in string1) and j (in string2), respectively, given that the last + * operation is a substition, a swap, a deletion, or an insertion. + * + * This implementation allows the costs to be weighted: + * + * - w (as in "sWap") + * - s (as in "Substitution") + * - a (for insertion, AKA "Add") + * - d (as in "Deletion") + * + * Note that this algorithm calculates a distance _iff_ d == a. + */ +int levenshtein(const char *string1, const char *string2, + int w, int s, int a, int d) +{ + int len1 = strlen(string1), len2 = strlen(string2); + int *row0 = malloc(sizeof(int) * (len2 + 1)); + int *row1 = malloc(sizeof(int) * (len2 + 1)); + int *row2 = malloc(sizeof(int) * (len2 + 1)); + int i, j; + + for (j = 0; j <= len2; j++) + row1[j] = j * a; + for (i = 0; i < len1; i++) { + int *dummy; + + row2[0] = (i + 1) * d; + for (j = 0; j < len2; j++) { + /* substitution */ + row2[j + 1] = row1[j] + s * (string1[i] != string2[j]); + /* swap */ + if (i > 0 && j > 0 && string1[i - 1] == string2[j] && + string1[i] == string2[j - 1] && + row2[j + 1] > row0[j - 1] + w) + row2[j + 1] = row0[j - 1] + w; + /* deletion */ + if (row2[j + 1] > row1[j + 1] + d) + row2[j + 1] = row1[j + 1] + d; + /* insertion */ + if (row2[j + 1] > row2[j] + a) + row2[j + 1] = row2[j] + a; + } + + dummy = row0; + row0 = row1; + row1 = row2; + row2 = dummy; + } + + i = row1[len2]; + free(row0); + free(row1); + free(row2); + + return i; +} diff --git a/trunk/tools/perf/util/levenshtein.h b/trunk/tools/perf/util/levenshtein.h new file mode 100644 index 000000000000..0173abeef52c --- /dev/null +++ b/trunk/tools/perf/util/levenshtein.h @@ -0,0 +1,8 @@ +#ifndef LEVENSHTEIN_H +#define LEVENSHTEIN_H + +int levenshtein(const char *string1, const char *string2, + int swap_penalty, int substition_penalty, + int insertion_penalty, int deletion_penalty); + +#endif diff --git a/trunk/tools/perf/util/list.h b/trunk/tools/perf/util/list.h new file mode 100644 index 000000000000..e2548e8072cf --- /dev/null +++ b/trunk/tools/perf/util/list.h @@ -0,0 +1,603 @@ +#ifndef _LINUX_LIST_H +#define _LINUX_LIST_H +/* + Copyright (C) Cast of dozens, comes from the Linux kernel + + This program is free software; you can redistribute it and/or modify it + under the terms of version 2 of the GNU General Public License as + published by the Free Software Foundation. +*/ + +#include + +/* + * These are non-NULL pointers that will result in page faults + * under normal circumstances, used to verify that nobody uses + * non-initialized list entries. + */ +#define LIST_POISON1 ((void *)0x00100100) +#define LIST_POISON2 ((void *)0x00200200) + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + const typeof( ((type *)0)->member ) *__mptr = (ptr); \ + (type *)( (char *)__mptr - offsetof(type,member) );}) + +/* + * Simple doubly linked list implementation. + * + * Some of the internal functions ("__xxx") are useful when + * manipulating whole lists rather than single entries, as + * sometimes we already know the next/prev entries and we can + * generate better code by using them directly rather than + * using the generic single-entry routines. + */ + +struct list_head { + struct list_head *next, *prev; +}; + +#define LIST_HEAD_INIT(name) { &(name), &(name) } + +#define LIST_HEAD(name) \ + struct list_head name = LIST_HEAD_INIT(name) + +static inline void INIT_LIST_HEAD(struct list_head *list) +{ + list->next = list; + list->prev = list; +} + +/* + * Insert a new entry between two known consecutive entries. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next) +{ + next->prev = new; + new->next = next; + new->prev = prev; + prev->next = new; +} + +/** + * list_add - add a new entry + * @new: new entry to be added + * @head: list head to add it after + * + * Insert a new entry after the specified head. + * This is good for implementing stacks. + */ +static inline void list_add(struct list_head *new, struct list_head *head) +{ + __list_add(new, head, head->next); +} + +/** + * list_add_tail - add a new entry + * @new: new entry to be added + * @head: list head to add it before + * + * Insert a new entry before the specified head. + * This is useful for implementing queues. + */ +static inline void list_add_tail(struct list_head *new, struct list_head *head) +{ + __list_add(new, head->prev, head); +} + +/* + * Delete a list entry by making the prev/next entries + * point to each other. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_del(struct list_head * prev, struct list_head * next) +{ + next->prev = prev; + prev->next = next; +} + +/** + * list_del - deletes entry from list. + * @entry: the element to delete from the list. + * Note: list_empty on entry does not return true after this, the entry is + * in an undefined state. + */ +static inline void list_del(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->next = LIST_POISON1; + entry->prev = LIST_POISON2; +} + +/** + * list_del_range - deletes range of entries from list. + * @beging: first element in the range to delete from the list. + * @beging: first element in the range to delete from the list. + * Note: list_empty on the range of entries does not return true after this, + * the entries is in an undefined state. + */ +static inline void list_del_range(struct list_head *begin, + struct list_head *end) +{ + begin->prev->next = end->next; + end->next->prev = begin->prev; +} + +/** + * list_replace - replace old entry by new one + * @old : the element to be replaced + * @new : the new element to insert + * Note: if 'old' was empty, it will be overwritten. + */ +static inline void list_replace(struct list_head *old, + struct list_head *new) +{ + new->next = old->next; + new->next->prev = new; + new->prev = old->prev; + new->prev->next = new; +} + +static inline void list_replace_init(struct list_head *old, + struct list_head *new) +{ + list_replace(old, new); + INIT_LIST_HEAD(old); +} + +/** + * list_del_init - deletes entry from list and reinitialize it. + * @entry: the element to delete from the list. + */ +static inline void list_del_init(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + INIT_LIST_HEAD(entry); +} + +/** + * list_move - delete from one list and add as another's head + * @list: the entry to move + * @head: the head that will precede our entry + */ +static inline void list_move(struct list_head *list, struct list_head *head) +{ + __list_del(list->prev, list->next); + list_add(list, head); +} + +/** + * list_move_tail - delete from one list and add as another's tail + * @list: the entry to move + * @head: the head that will follow our entry + */ +static inline void list_move_tail(struct list_head *list, + struct list_head *head) +{ + __list_del(list->prev, list->next); + list_add_tail(list, head); +} + +/** + * list_is_last - tests whether @list is the last entry in list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_last(const struct list_head *list, + const struct list_head *head) +{ + return list->next == head; +} + +/** + * list_empty - tests whether a list is empty + * @head: the list to test. + */ +static inline int list_empty(const struct list_head *head) +{ + return head->next == head; +} + +/** + * list_empty_careful - tests whether a list is empty and not being modified + * @head: the list to test + * + * Description: + * tests whether a list is empty _and_ checks that no other CPU might be + * in the process of modifying either member (next or prev) + * + * NOTE: using list_empty_careful() without synchronization + * can only be safe if the only activity that can happen + * to the list entry is list_del_init(). Eg. it cannot be used + * if another CPU could re-list_add() it. + */ +static inline int list_empty_careful(const struct list_head *head) +{ + struct list_head *next = head->next; + return (next == head) && (next == head->prev); +} + +static inline void __list_splice(struct list_head *list, + struct list_head *head) +{ + struct list_head *first = list->next; + struct list_head *last = list->prev; + struct list_head *at = head->next; + + first->prev = head; + head->next = first; + + last->next = at; + at->prev = last; +} + +/** + * list_splice - join two lists + * @list: the new list to add. + * @head: the place to add it in the first list. + */ +static inline void list_splice(struct list_head *list, struct list_head *head) +{ + if (!list_empty(list)) + __list_splice(list, head); +} + +/** + * list_splice_init - join two lists and reinitialise the emptied list. + * @list: the new list to add. + * @head: the place to add it in the first list. + * + * The list at @list is reinitialised + */ +static inline void list_splice_init(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) { + __list_splice(list, head); + INIT_LIST_HEAD(list); + } +} + +/** + * list_entry - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_struct within the struct. + */ +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) + +/** + * list_first_entry - get the first element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_struct within the struct. + * + * Note, that list is expected to be not empty. + */ +#define list_first_entry(ptr, type, member) \ + list_entry((ptr)->next, type, member) + +/** + * list_for_each - iterate over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each(pos, head) \ + for (pos = (head)->next; pos != (head); \ + pos = pos->next) + +/** + * __list_for_each - iterate over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + * + * This variant differs from list_for_each() in that it's the + * simplest possible list iteration code, no prefetching is done. + * Use this for code that knows the list to be very short (empty + * or 1 entry) most of the time. + */ +#define __list_for_each(pos, head) \ + for (pos = (head)->next; pos != (head); pos = pos->next) + +/** + * list_for_each_prev - iterate over a list backwards + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each_prev(pos, head) \ + for (pos = (head)->prev; pos != (head); \ + pos = pos->prev) + +/** + * list_for_each_safe - iterate over a list safe against removal of list entry + * @pos: the &struct list_head to use as a loop cursor. + * @n: another &struct list_head to use as temporary storage + * @head: the head for your list. + */ +#define list_for_each_safe(pos, n, head) \ + for (pos = (head)->next, n = pos->next; pos != (head); \ + pos = n, n = pos->next) + +/** + * list_for_each_entry - iterate over list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry(pos, head, member) \ + for (pos = list_entry((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + +/** + * list_for_each_entry_reverse - iterate backwards over list of given type. + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_reverse(pos, head, member) \ + for (pos = list_entry((head)->prev, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry(pos->member.prev, typeof(*pos), member)) + +/** + * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue + * @pos: the type * to use as a start point + * @head: the head of the list + * @member: the name of the list_struct within the struct. + * + * Prepares a pos entry for use as a start point in list_for_each_entry_continue. + */ +#define list_prepare_entry(pos, head, member) \ + ((pos) ? : list_entry(head, typeof(*pos), member)) + +/** + * list_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define list_for_each_entry_continue(pos, head, member) \ + for (pos = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + +/** + * list_for_each_entry_from - iterate over list of given type from the current point + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate over list of given type, continuing from current position. + */ +#define list_for_each_entry_from(pos, head, member) \ + for (; &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + +/** + * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_safe(pos, n, head, member) \ + for (pos = list_entry((head)->next, typeof(*pos), member), \ + n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + +/** + * list_for_each_entry_safe_continue + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate over list of given type, continuing after current point, + * safe against removal of list entry. + */ +#define list_for_each_entry_safe_continue(pos, n, head, member) \ + for (pos = list_entry(pos->member.next, typeof(*pos), member), \ + n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + +/** + * list_for_each_entry_safe_from + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate over list of given type from current point, safe against + * removal of list entry. + */ +#define list_for_each_entry_safe_from(pos, n, head, member) \ + for (n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + +/** + * list_for_each_entry_safe_reverse + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate backwards over list of given type, safe against removal + * of list entry. + */ +#define list_for_each_entry_safe_reverse(pos, n, head, member) \ + for (pos = list_entry((head)->prev, typeof(*pos), member), \ + n = list_entry(pos->member.prev, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.prev, typeof(*n), member)) + +/* + * Double linked lists with a single pointer list head. + * Mostly useful for hash tables where the two pointer list head is + * too wasteful. + * You lose the ability to access the tail in O(1). + */ + +struct hlist_head { + struct hlist_node *first; +}; + +struct hlist_node { + struct hlist_node *next, **pprev; +}; + +#define HLIST_HEAD_INIT { .first = NULL } +#define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } +#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) +static inline void INIT_HLIST_NODE(struct hlist_node *h) +{ + h->next = NULL; + h->pprev = NULL; +} + +static inline int hlist_unhashed(const struct hlist_node *h) +{ + return !h->pprev; +} + +static inline int hlist_empty(const struct hlist_head *h) +{ + return !h->first; +} + +static inline void __hlist_del(struct hlist_node *n) +{ + struct hlist_node *next = n->next; + struct hlist_node **pprev = n->pprev; + *pprev = next; + if (next) + next->pprev = pprev; +} + +static inline void hlist_del(struct hlist_node *n) +{ + __hlist_del(n); + n->next = LIST_POISON1; + n->pprev = LIST_POISON2; +} + +static inline void hlist_del_init(struct hlist_node *n) +{ + if (!hlist_unhashed(n)) { + __hlist_del(n); + INIT_HLIST_NODE(n); + } +} + +static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) +{ + struct hlist_node *first = h->first; + n->next = first; + if (first) + first->pprev = &n->next; + h->first = n; + n->pprev = &h->first; +} + +/* next must be != NULL */ +static inline void hlist_add_before(struct hlist_node *n, + struct hlist_node *next) +{ + n->pprev = next->pprev; + n->next = next; + next->pprev = &n->next; + *(n->pprev) = n; +} + +static inline void hlist_add_after(struct hlist_node *n, + struct hlist_node *next) +{ + next->next = n->next; + n->next = next; + next->pprev = &n->next; + + if(next->next) + next->next->pprev = &next->next; +} + +#define hlist_entry(ptr, type, member) container_of(ptr,type,member) + +#define hlist_for_each(pos, head) \ + for (pos = (head)->first; pos; \ + pos = pos->next) + +#define hlist_for_each_safe(pos, n, head) \ + for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ + pos = n) + +/** + * hlist_for_each_entry - iterate over list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry(tpos, pos, head, member) \ + for (pos = (head)->first; \ + pos && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_for_each_entry_continue - iterate over a hlist continuing after current point + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_continue(tpos, pos, member) \ + for (pos = (pos)->next; \ + pos && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_for_each_entry_from - iterate over a hlist continuing from current point + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_from(tpos, pos, member) \ + for (; pos && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @n: another &struct hlist_node to use as temporary storage + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_safe(tpos, pos, n, head, member) \ + for (pos = (head)->first; \ + pos && ({ n = pos->next; 1; }) && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = n) + +#endif diff --git a/trunk/tools/perf/util/pager.c b/trunk/tools/perf/util/pager.c new file mode 100644 index 000000000000..a28bccae5458 --- /dev/null +++ b/trunk/tools/perf/util/pager.c @@ -0,0 +1,99 @@ +#include "cache.h" +#include "run-command.h" +#include "sigchain.h" + +/* + * This is split up from the rest of git so that we can do + * something different on Windows. + */ + +static int spawned_pager; + +#ifndef __MINGW32__ +static void pager_preexec(void) +{ + /* + * Work around bug in "less" by not starting it until we + * have real input + */ + fd_set in; + + FD_ZERO(&in); + FD_SET(0, &in); + select(1, &in, NULL, &in, NULL); + + setenv("LESS", "FRSX", 0); +} +#endif + +static const char *pager_argv[] = { "sh", "-c", NULL, NULL }; +static struct child_process pager_process; + +static void wait_for_pager(void) +{ + fflush(stdout); + fflush(stderr); + /* signal EOF to pager */ + close(1); + close(2); + finish_command(&pager_process); +} + +static void wait_for_pager_signal(int signo) +{ + wait_for_pager(); + sigchain_pop(signo); + raise(signo); +} + +void setup_pager(void) +{ + const char *pager = getenv("PERF_PAGER"); + + if (!isatty(1)) + return; + if (!pager) { + if (!pager_program) + perf_config(perf_default_config, NULL); + pager = pager_program; + } + if (!pager) + pager = getenv("PAGER"); + if (!pager) + pager = "less"; + else if (!*pager || !strcmp(pager, "cat")) + return; + + spawned_pager = 1; /* means we are emitting to terminal */ + + /* spawn the pager */ + pager_argv[2] = pager; + pager_process.argv = pager_argv; + pager_process.in = -1; +#ifndef __MINGW32__ + pager_process.preexec_cb = pager_preexec; +#endif + if (start_command(&pager_process)) + return; + + /* original process continues, but writes to the pipe */ + dup2(pager_process.in, 1); + if (isatty(2)) + dup2(pager_process.in, 2); + close(pager_process.in); + + /* this makes sure that the parent terminates after the pager */ + sigchain_push_common(wait_for_pager_signal); + atexit(wait_for_pager); +} + +int pager_in_use(void) +{ + const char *env; + + if (spawned_pager) + return 1; + + env = getenv("PERF_PAGER_IN_USE"); + return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0; +} diff --git a/trunk/tools/perf/util/parse-events.c b/trunk/tools/perf/util/parse-events.c new file mode 100644 index 000000000000..5a72586e1df0 --- /dev/null +++ b/trunk/tools/perf/util/parse-events.c @@ -0,0 +1,316 @@ + +#include "../perf.h" +#include "util.h" +#include "parse-options.h" +#include "parse-events.h" +#include "exec_cmd.h" +#include "string.h" + +extern char *strcasestr(const char *haystack, const char *needle); + +int nr_counters; + +struct perf_counter_attr attrs[MAX_COUNTERS]; + +struct event_symbol { + __u8 type; + __u64 config; + char *symbol; +}; + +#define C(x, y) .type = PERF_TYPE_##x, .config = PERF_COUNT_##y +#define CR(x, y) .type = PERF_TYPE_##x, .config = y + +static struct event_symbol event_symbols[] = { + { C(HARDWARE, HW_CPU_CYCLES), "cpu-cycles", }, + { C(HARDWARE, HW_CPU_CYCLES), "cycles", }, + { C(HARDWARE, HW_INSTRUCTIONS), "instructions", }, + { C(HARDWARE, HW_CACHE_REFERENCES), "cache-references", }, + { C(HARDWARE, HW_CACHE_MISSES), "cache-misses", }, + { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branch-instructions", }, + { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branches", }, + { C(HARDWARE, HW_BRANCH_MISSES), "branch-misses", }, + { C(HARDWARE, HW_BUS_CYCLES), "bus-cycles", }, + + { C(SOFTWARE, SW_CPU_CLOCK), "cpu-clock", }, + { C(SOFTWARE, SW_TASK_CLOCK), "task-clock", }, + { C(SOFTWARE, SW_PAGE_FAULTS), "page-faults", }, + { C(SOFTWARE, SW_PAGE_FAULTS), "faults", }, + { C(SOFTWARE, SW_PAGE_FAULTS_MIN), "minor-faults", }, + { C(SOFTWARE, SW_PAGE_FAULTS_MAJ), "major-faults", }, + { C(SOFTWARE, SW_CONTEXT_SWITCHES), "context-switches", }, + { C(SOFTWARE, SW_CONTEXT_SWITCHES), "cs", }, + { C(SOFTWARE, SW_CPU_MIGRATIONS), "cpu-migrations", }, + { C(SOFTWARE, SW_CPU_MIGRATIONS), "migrations", }, +}; + +#define __PERF_COUNTER_FIELD(config, name) \ + ((config & PERF_COUNTER_##name##_MASK) >> PERF_COUNTER_##name##_SHIFT) + +#define PERF_COUNTER_RAW(config) __PERF_COUNTER_FIELD(config, RAW) +#define PERF_COUNTER_CONFIG(config) __PERF_COUNTER_FIELD(config, CONFIG) +#define PERF_COUNTER_TYPE(config) __PERF_COUNTER_FIELD(config, TYPE) +#define PERF_COUNTER_ID(config) __PERF_COUNTER_FIELD(config, EVENT) + +static char *hw_event_names[] = { + "cycles", + "instructions", + "cache-references", + "cache-misses", + "branches", + "branch-misses", + "bus-cycles", +}; + +static char *sw_event_names[] = { + "cpu-clock-ticks", + "task-clock-ticks", + "page-faults", + "context-switches", + "CPU-migrations", + "minor-faults", + "major-faults", +}; + +#define MAX_ALIASES 8 + +static char *hw_cache [][MAX_ALIASES] = { + { "L1-data" , "l1-d", "l1d" }, + { "L1-instruction" , "l1-i", "l1i" }, + { "L2" , "l2" }, + { "Data-TLB" , "dtlb", "d-tlb" }, + { "Instruction-TLB" , "itlb", "i-tlb" }, + { "Branch" , "bpu" , "btb", "bpc" }, +}; + +static char *hw_cache_op [][MAX_ALIASES] = { + { "Load" , "read" }, + { "Store" , "write" }, + { "Prefetch" , "speculative-read", "speculative-load" }, +}; + +static char *hw_cache_result [][MAX_ALIASES] = { + { "Reference" , "ops", "access" }, + { "Miss" }, +}; + +char *event_name(int counter) +{ + __u64 config = attrs[counter].config; + int type = attrs[counter].type; + static char buf[32]; + + if (attrs[counter].type == PERF_TYPE_RAW) { + sprintf(buf, "raw 0x%llx", config); + return buf; + } + + switch (type) { + case PERF_TYPE_HARDWARE: + if (config < PERF_COUNT_HW_MAX) + return hw_event_names[config]; + return "unknown-hardware"; + + case PERF_TYPE_HW_CACHE: { + __u8 cache_type, cache_op, cache_result; + static char name[100]; + + cache_type = (config >> 0) & 0xff; + if (cache_type > PERF_COUNT_HW_CACHE_MAX) + return "unknown-ext-hardware-cache-type"; + + cache_op = (config >> 8) & 0xff; + if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX) + return "unknown-ext-hardware-cache-op"; + + cache_result = (config >> 16) & 0xff; + if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX) + return "unknown-ext-hardware-cache-result"; + + sprintf(name, "%s-Cache-%s-%ses", + hw_cache[cache_type][0], + hw_cache_op[cache_op][0], + hw_cache_result[cache_result][0]); + + return name; + } + + case PERF_TYPE_SOFTWARE: + if (config < PERF_COUNT_SW_MAX) + return sw_event_names[config]; + return "unknown-software"; + + default: + break; + } + + return "unknown"; +} + +static int parse_aliases(const char *str, char *names[][MAX_ALIASES], int size) +{ + int i, j; + + for (i = 0; i < size; i++) { + for (j = 0; j < MAX_ALIASES; j++) { + if (!names[i][j]) + break; + if (strcasestr(str, names[i][j])) + return i; + } + } + + return -1; +} + +static int parse_generic_hw_symbols(const char *str, struct perf_counter_attr *attr) +{ + int cache_type = -1, cache_op = 0, cache_result = 0; + + cache_type = parse_aliases(str, hw_cache, PERF_COUNT_HW_CACHE_MAX); + /* + * No fallback - if we cannot get a clear cache type + * then bail out: + */ + if (cache_type == -1) + return -EINVAL; + + cache_op = parse_aliases(str, hw_cache_op, PERF_COUNT_HW_CACHE_OP_MAX); + /* + * Fall back to reads: + */ + if (cache_op == -1) + cache_op = PERF_COUNT_HW_CACHE_OP_READ; + + cache_result = parse_aliases(str, hw_cache_result, + PERF_COUNT_HW_CACHE_RESULT_MAX); + /* + * Fall back to accesses: + */ + if (cache_result == -1) + cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS; + + attr->config = cache_type | (cache_op << 8) | (cache_result << 16); + attr->type = PERF_TYPE_HW_CACHE; + + return 0; +} + +/* + * Each event can have multiple symbolic names. + * Symbolic names are (almost) exactly matched. + */ +static int parse_event_symbols(const char *str, struct perf_counter_attr *attr) +{ + __u64 config, id; + int type; + unsigned int i; + const char *sep, *pstr; + + if (str[0] == 'r' && hex2u64(str + 1, &config) > 0) { + attr->type = PERF_TYPE_RAW; + attr->config = config; + + return 0; + } + + pstr = str; + sep = strchr(pstr, ':'); + if (sep) { + type = atoi(pstr); + pstr = sep + 1; + id = atoi(pstr); + sep = strchr(pstr, ':'); + if (sep) { + pstr = sep + 1; + if (strchr(pstr, 'k')) + attr->exclude_user = 1; + if (strchr(pstr, 'u')) + attr->exclude_kernel = 1; + } + attr->type = type; + attr->config = id; + + return 0; + } + + for (i = 0; i < ARRAY_SIZE(event_symbols); i++) { + if (!strncmp(str, event_symbols[i].symbol, + strlen(event_symbols[i].symbol))) { + + attr->type = event_symbols[i].type; + attr->config = event_symbols[i].config; + + return 0; + } + } + + return parse_generic_hw_symbols(str, attr); +} + +int parse_events(const struct option *opt, const char *str, int unset) +{ + struct perf_counter_attr attr; + int ret; + + memset(&attr, 0, sizeof(attr)); +again: + if (nr_counters == MAX_COUNTERS) + return -1; + + ret = parse_event_symbols(str, &attr); + if (ret < 0) + return ret; + + attrs[nr_counters] = attr; + nr_counters++; + + str = strstr(str, ","); + if (str) { + str++; + goto again; + } + + return 0; +} + +static const char * const event_type_descriptors[] = { + "", + "Hardware event", + "Software event", + "Tracepoint event", + "Hardware cache event", +}; + +/* + * Print the help text for the event symbols: + */ +void print_events(void) +{ + struct event_symbol *syms = event_symbols; + unsigned int i, type, prev_type = -1; + + fprintf(stderr, "\n"); + fprintf(stderr, "List of pre-defined events (to be used in -e):\n"); + + for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { + type = syms->type + 1; + if (type > ARRAY_SIZE(event_type_descriptors)) + type = 0; + + if (type != prev_type) + fprintf(stderr, "\n"); + + fprintf(stderr, " %-30s [%s]\n", syms->symbol, + event_type_descriptors[type]); + + prev_type = type; + } + + fprintf(stderr, "\n"); + fprintf(stderr, " %-30s [raw hardware event descriptor]\n", + "rNNN"); + fprintf(stderr, "\n"); + + exit(129); +} diff --git a/trunk/tools/perf/util/parse-events.h b/trunk/tools/perf/util/parse-events.h new file mode 100644 index 000000000000..e3d552908e60 --- /dev/null +++ b/trunk/tools/perf/util/parse-events.h @@ -0,0 +1,17 @@ + +/* + * Parse symbolic events/counts passed in as options: + */ + +extern int nr_counters; + +extern struct perf_counter_attr attrs[MAX_COUNTERS]; + +extern char *event_name(int ctr); + +extern int parse_events(const struct option *opt, const char *str, int unset); + +#define EVENTS_HELP_MAX (128*1024) + +extern void print_events(void); + diff --git a/trunk/tools/perf/util/parse-options.c b/trunk/tools/perf/util/parse-options.c new file mode 100644 index 000000000000..b3affb1658d2 --- /dev/null +++ b/trunk/tools/perf/util/parse-options.c @@ -0,0 +1,508 @@ +#include "util.h" +#include "parse-options.h" +#include "cache.h" + +#define OPT_SHORT 1 +#define OPT_UNSET 2 + +static int opterror(const struct option *opt, const char *reason, int flags) +{ + if (flags & OPT_SHORT) + return error("switch `%c' %s", opt->short_name, reason); + if (flags & OPT_UNSET) + return error("option `no-%s' %s", opt->long_name, reason); + return error("option `%s' %s", opt->long_name, reason); +} + +static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt, + int flags, const char **arg) +{ + if (p->opt) { + *arg = p->opt; + p->opt = NULL; + } else if (p->argc == 1 && (opt->flags & PARSE_OPT_LASTARG_DEFAULT)) { + *arg = (const char *)opt->defval; + } else if (p->argc > 1) { + p->argc--; + *arg = *++p->argv; + } else + return opterror(opt, "requires a value", flags); + return 0; +} + +static int get_value(struct parse_opt_ctx_t *p, + const struct option *opt, int flags) +{ + const char *s, *arg = NULL; + const int unset = flags & OPT_UNSET; + + if (unset && p->opt) + return opterror(opt, "takes no value", flags); + if (unset && (opt->flags & PARSE_OPT_NONEG)) + return opterror(opt, "isn't available", flags); + + if (!(flags & OPT_SHORT) && p->opt) { + switch (opt->type) { + case OPTION_CALLBACK: + if (!(opt->flags & PARSE_OPT_NOARG)) + break; + /* FALLTHROUGH */ + case OPTION_BOOLEAN: + case OPTION_BIT: + case OPTION_SET_INT: + case OPTION_SET_PTR: + return opterror(opt, "takes no value", flags); + default: + break; + } + } + + switch (opt->type) { + case OPTION_BIT: + if (unset) + *(int *)opt->value &= ~opt->defval; + else + *(int *)opt->value |= opt->defval; + return 0; + + case OPTION_BOOLEAN: + *(int *)opt->value = unset ? 0 : *(int *)opt->value + 1; + return 0; + + case OPTION_SET_INT: + *(int *)opt->value = unset ? 0 : opt->defval; + return 0; + + case OPTION_SET_PTR: + *(void **)opt->value = unset ? NULL : (void *)opt->defval; + return 0; + + case OPTION_STRING: + if (unset) + *(const char **)opt->value = NULL; + else if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + *(const char **)opt->value = (const char *)opt->defval; + else + return get_arg(p, opt, flags, (const char **)opt->value); + return 0; + + case OPTION_CALLBACK: + if (unset) + return (*opt->callback)(opt, NULL, 1) ? (-1) : 0; + if (opt->flags & PARSE_OPT_NOARG) + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; + if (get_arg(p, opt, flags, &arg)) + return -1; + return (*opt->callback)(opt, arg, 0) ? (-1) : 0; + + case OPTION_INTEGER: + if (unset) { + *(int *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(int *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + *(int *)opt->value = strtol(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + case OPTION_LONG: + if (unset) { + *(long *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(long *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + *(long *)opt->value = strtol(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + default: + die("should not happen, someone must be hit on the forehead"); + } +} + +static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options) +{ + for (; options->type != OPTION_END; options++) { + if (options->short_name == *p->opt) { + p->opt = p->opt[1] ? p->opt + 1 : NULL; + return get_value(p, options, OPT_SHORT); + } + } + return -2; +} + +static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg, + const struct option *options) +{ + const char *arg_end = strchr(arg, '='); + const struct option *abbrev_option = NULL, *ambiguous_option = NULL; + int abbrev_flags = 0, ambiguous_flags = 0; + + if (!arg_end) + arg_end = arg + strlen(arg); + + for (; options->type != OPTION_END; options++) { + const char *rest; + int flags = 0; + + if (!options->long_name) + continue; + + rest = skip_prefix(arg, options->long_name); + if (options->type == OPTION_ARGUMENT) { + if (!rest) + continue; + if (*rest == '=') + return opterror(options, "takes no value", flags); + if (*rest) + continue; + p->out[p->cpidx++] = arg - 2; + return 0; + } + if (!rest) { + /* abbreviated? */ + if (!strncmp(options->long_name, arg, arg_end - arg)) { +is_abbreviated: + if (abbrev_option) { + /* + * If this is abbreviated, it is + * ambiguous. So when there is no + * exact match later, we need to + * error out. + */ + ambiguous_option = abbrev_option; + ambiguous_flags = abbrev_flags; + } + if (!(flags & OPT_UNSET) && *arg_end) + p->opt = arg_end + 1; + abbrev_option = options; + abbrev_flags = flags; + continue; + } + /* negated and abbreviated very much? */ + if (!prefixcmp("no-", arg)) { + flags |= OPT_UNSET; + goto is_abbreviated; + } + /* negated? */ + if (strncmp(arg, "no-", 3)) + continue; + flags |= OPT_UNSET; + rest = skip_prefix(arg + 3, options->long_name); + /* abbreviated and negated? */ + if (!rest && !prefixcmp(options->long_name, arg + 3)) + goto is_abbreviated; + if (!rest) + continue; + } + if (*rest) { + if (*rest != '=') + continue; + p->opt = rest + 1; + } + return get_value(p, options, flags); + } + + if (ambiguous_option) + return error("Ambiguous option: %s " + "(could be --%s%s or --%s%s)", + arg, + (ambiguous_flags & OPT_UNSET) ? "no-" : "", + ambiguous_option->long_name, + (abbrev_flags & OPT_UNSET) ? "no-" : "", + abbrev_option->long_name); + if (abbrev_option) + return get_value(p, abbrev_option, abbrev_flags); + return -2; +} + +static void check_typos(const char *arg, const struct option *options) +{ + if (strlen(arg) < 3) + return; + + if (!prefixcmp(arg, "no-")) { + error ("did you mean `--%s` (with two dashes ?)", arg); + exit(129); + } + + for (; options->type != OPTION_END; options++) { + if (!options->long_name) + continue; + if (!prefixcmp(options->long_name, arg)) { + error ("did you mean `--%s` (with two dashes ?)", arg); + exit(129); + } + } +} + +void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags) +{ + memset(ctx, 0, sizeof(*ctx)); + ctx->argc = argc - 1; + ctx->argv = argv + 1; + ctx->out = argv; + ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0); + ctx->flags = flags; + if ((flags & PARSE_OPT_KEEP_UNKNOWN) && + (flags & PARSE_OPT_STOP_AT_NON_OPTION)) + die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together"); +} + +static int usage_with_options_internal(const char * const *, + const struct option *, int); + +int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]) +{ + int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP); + + /* we must reset ->opt, unknown short option leave it dangling */ + ctx->opt = NULL; + + for (; ctx->argc; ctx->argc--, ctx->argv++) { + const char *arg = ctx->argv[0]; + + if (*arg != '-' || !arg[1]) { + if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION) + break; + ctx->out[ctx->cpidx++] = ctx->argv[0]; + continue; + } + + if (arg[1] != '-') { + ctx->opt = arg + 1; + if (internal_help && *ctx->opt == 'h') + return parse_options_usage(usagestr, options); + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + goto unknown; + } + if (ctx->opt) + check_typos(arg + 1, options); + while (ctx->opt) { + if (internal_help && *ctx->opt == 'h') + return parse_options_usage(usagestr, options); + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + /* fake a short option thing to hide the fact that we may have + * started to parse aggregated stuff + * + * This is leaky, too bad. + */ + ctx->argv[0] = strdup(ctx->opt - 1); + *(char *)ctx->argv[0] = '-'; + goto unknown; + } + } + continue; + } + + if (!arg[2]) { /* "--" */ + if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) { + ctx->argc--; + ctx->argv++; + } + break; + } + + if (internal_help && !strcmp(arg + 2, "help-all")) + return usage_with_options_internal(usagestr, options, 1); + if (internal_help && !strcmp(arg + 2, "help")) + return parse_options_usage(usagestr, options); + switch (parse_long_opt(ctx, arg + 2, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + goto unknown; + } + continue; +unknown: + if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN)) + return PARSE_OPT_UNKNOWN; + ctx->out[ctx->cpidx++] = ctx->argv[0]; + ctx->opt = NULL; + } + return PARSE_OPT_DONE; +} + +int parse_options_end(struct parse_opt_ctx_t *ctx) +{ + memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out)); + ctx->out[ctx->cpidx + ctx->argc] = NULL; + return ctx->cpidx + ctx->argc; +} + +int parse_options(int argc, const char **argv, const struct option *options, + const char * const usagestr[], int flags) +{ + struct parse_opt_ctx_t ctx; + + parse_options_start(&ctx, argc, argv, flags); + switch (parse_options_step(&ctx, options, usagestr)) { + case PARSE_OPT_HELP: + exit(129); + case PARSE_OPT_DONE: + break; + default: /* PARSE_OPT_UNKNOWN */ + if (ctx.argv[0][1] == '-') { + error("unknown option `%s'", ctx.argv[0] + 2); + } else { + error("unknown switch `%c'", *ctx.opt); + } + usage_with_options(usagestr, options); + } + + return parse_options_end(&ctx); +} + +#define USAGE_OPTS_WIDTH 24 +#define USAGE_GAP 2 + +int usage_with_options_internal(const char * const *usagestr, + const struct option *opts, int full) +{ + if (!usagestr) + return PARSE_OPT_HELP; + + fprintf(stderr, "\n usage: %s\n", *usagestr++); + while (*usagestr && **usagestr) + fprintf(stderr, " or: %s\n", *usagestr++); + while (*usagestr) { + fprintf(stderr, "%s%s\n", + **usagestr ? " " : "", + *usagestr); + usagestr++; + } + + if (opts->type != OPTION_GROUP) + fputc('\n', stderr); + + for (; opts->type != OPTION_END; opts++) { + size_t pos; + int pad; + + if (opts->type == OPTION_GROUP) { + fputc('\n', stderr); + if (*opts->help) + fprintf(stderr, "%s\n", opts->help); + continue; + } + if (!full && (opts->flags & PARSE_OPT_HIDDEN)) + continue; + + pos = fprintf(stderr, " "); + if (opts->short_name) + pos += fprintf(stderr, "-%c", opts->short_name); + if (opts->long_name && opts->short_name) + pos += fprintf(stderr, ", "); + if (opts->long_name) + pos += fprintf(stderr, "--%s", opts->long_name); + + switch (opts->type) { + case OPTION_ARGUMENT: + break; + case OPTION_INTEGER: + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=]"); + else + pos += fprintf(stderr, "[]"); + else + pos += fprintf(stderr, " "); + break; + case OPTION_CALLBACK: + if (opts->flags & PARSE_OPT_NOARG) + break; + /* FALLTHROUGH */ + case OPTION_STRING: + if (opts->argh) { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<%s>]", opts->argh); + else + pos += fprintf(stderr, "[<%s>]", opts->argh); + else + pos += fprintf(stderr, " <%s>", opts->argh); + } else { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=...]"); + else + pos += fprintf(stderr, "[...]"); + else + pos += fprintf(stderr, " ..."); + } + break; + default: /* OPTION_{BIT,BOOLEAN,SET_INT,SET_PTR} */ + break; + } + + if (pos <= USAGE_OPTS_WIDTH) + pad = USAGE_OPTS_WIDTH - pos; + else { + fputc('\n', stderr); + pad = USAGE_OPTS_WIDTH; + } + fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); + } + fputc('\n', stderr); + + return PARSE_OPT_HELP; +} + +void usage_with_options(const char * const *usagestr, + const struct option *opts) +{ + usage_with_options_internal(usagestr, opts, 0); + exit(129); +} + +int parse_options_usage(const char * const *usagestr, + const struct option *opts) +{ + return usage_with_options_internal(usagestr, opts, 0); +} + + +int parse_opt_verbosity_cb(const struct option *opt, const char *arg, + int unset) +{ + int *target = opt->value; + + if (unset) + /* --no-quiet, --no-verbose */ + *target = 0; + else if (opt->short_name == 'v') { + if (*target >= 0) + (*target)++; + else + *target = 1; + } else { + if (*target <= 0) + (*target)--; + else + *target = -1; + } + return 0; +} diff --git a/trunk/tools/perf/util/parse-options.h b/trunk/tools/perf/util/parse-options.h new file mode 100644 index 000000000000..a1039a6ce0eb --- /dev/null +++ b/trunk/tools/perf/util/parse-options.h @@ -0,0 +1,174 @@ +#ifndef PARSE_OPTIONS_H +#define PARSE_OPTIONS_H + +enum parse_opt_type { + /* special types */ + OPTION_END, + OPTION_ARGUMENT, + OPTION_GROUP, + /* options with no arguments */ + OPTION_BIT, + OPTION_BOOLEAN, /* _INCR would have been a better name */ + OPTION_SET_INT, + OPTION_SET_PTR, + /* options with arguments (usually) */ + OPTION_STRING, + OPTION_INTEGER, + OPTION_LONG, + OPTION_CALLBACK, +}; + +enum parse_opt_flags { + PARSE_OPT_KEEP_DASHDASH = 1, + PARSE_OPT_STOP_AT_NON_OPTION = 2, + PARSE_OPT_KEEP_ARGV0 = 4, + PARSE_OPT_KEEP_UNKNOWN = 8, + PARSE_OPT_NO_INTERNAL_HELP = 16, +}; + +enum parse_opt_option_flags { + PARSE_OPT_OPTARG = 1, + PARSE_OPT_NOARG = 2, + PARSE_OPT_NONEG = 4, + PARSE_OPT_HIDDEN = 8, + PARSE_OPT_LASTARG_DEFAULT = 16, +}; + +struct option; +typedef int parse_opt_cb(const struct option *, const char *arg, int unset); + +/* + * `type`:: + * holds the type of the option, you must have an OPTION_END last in your + * array. + * + * `short_name`:: + * the character to use as a short option name, '\0' if none. + * + * `long_name`:: + * the long option name, without the leading dashes, NULL if none. + * + * `value`:: + * stores pointers to the values to be filled. + * + * `argh`:: + * token to explain the kind of argument this option wants. Keep it + * homogenous across the repository. + * + * `help`:: + * the short help associated to what the option does. + * Must never be NULL (except for OPTION_END). + * OPTION_GROUP uses this pointer to store the group header. + * + * `flags`:: + * mask of parse_opt_option_flags. + * PARSE_OPT_OPTARG: says that the argument is optionnal (not for BOOLEANs) + * PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs + * PARSE_OPT_NONEG: says that this option cannot be negated + * PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in + * the long one. + * + * `callback`:: + * pointer to the callback to use for OPTION_CALLBACK. + * + * `defval`:: + * default value to fill (*->value) with for PARSE_OPT_OPTARG. + * OPTION_{BIT,SET_INT,SET_PTR} store the {mask,integer,pointer} to put in + * the value when met. + * CALLBACKS can use it like they want. + */ +struct option { + enum parse_opt_type type; + int short_name; + const char *long_name; + void *value; + const char *argh; + const char *help; + + int flags; + parse_opt_cb *callback; + intptr_t defval; +}; + +#define OPT_END() { OPTION_END } +#define OPT_ARGUMENT(l, h) { OPTION_ARGUMENT, 0, (l), NULL, NULL, (h) } +#define OPT_GROUP(h) { OPTION_GROUP, 0, NULL, NULL, NULL, (h) } +#define OPT_BIT(s, l, v, h, b) { OPTION_BIT, (s), (l), (v), NULL, (h), 0, NULL, (b) } +#define OPT_BOOLEAN(s, l, v, h) { OPTION_BOOLEAN, (s), (l), (v), NULL, (h) } +#define OPT_SET_INT(s, l, v, h, i) { OPTION_SET_INT, (s), (l), (v), NULL, (h), 0, NULL, (i) } +#define OPT_SET_PTR(s, l, v, h, p) { OPTION_SET_PTR, (s), (l), (v), NULL, (h), 0, NULL, (p) } +#define OPT_INTEGER(s, l, v, h) { OPTION_INTEGER, (s), (l), (v), NULL, (h) } +#define OPT_LONG(s, l, v, h) { OPTION_LONG, (s), (l), (v), NULL, (h) } +#define OPT_STRING(s, l, v, a, h) { OPTION_STRING, (s), (l), (v), (a), (h) } +#define OPT_DATE(s, l, v, h) \ + { OPTION_CALLBACK, (s), (l), (v), "time",(h), 0, \ + parse_opt_approxidate_cb } +#define OPT_CALLBACK(s, l, v, a, h, f) \ + { OPTION_CALLBACK, (s), (l), (v), (a), (h), 0, (f) } + +/* parse_options() will filter out the processed options and leave the + * non-option argments in argv[]. + * Returns the number of arguments left in argv[]. + */ +extern int parse_options(int argc, const char **argv, + const struct option *options, + const char * const usagestr[], int flags); + +extern NORETURN void usage_with_options(const char * const *usagestr, + const struct option *options); + +/*----- incremantal advanced APIs -----*/ + +enum { + PARSE_OPT_HELP = -1, + PARSE_OPT_DONE, + PARSE_OPT_UNKNOWN, +}; + +/* + * It's okay for the caller to consume argv/argc in the usual way. + * Other fields of that structure are private to parse-options and should not + * be modified in any way. + */ +struct parse_opt_ctx_t { + const char **argv; + const char **out; + int argc, cpidx; + const char *opt; + int flags; +}; + +extern int parse_options_usage(const char * const *usagestr, + const struct option *opts); + +extern void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags); + +extern int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]); + +extern int parse_options_end(struct parse_opt_ctx_t *ctx); + + +/*----- some often used options -----*/ +extern int parse_opt_abbrev_cb(const struct option *, const char *, int); +extern int parse_opt_approxidate_cb(const struct option *, const char *, int); +extern int parse_opt_verbosity_cb(const struct option *, const char *, int); + +#define OPT__VERBOSE(var) OPT_BOOLEAN('v', "verbose", (var), "be verbose") +#define OPT__QUIET(var) OPT_BOOLEAN('q', "quiet", (var), "be quiet") +#define OPT__VERBOSITY(var) \ + { OPTION_CALLBACK, 'v', "verbose", (var), NULL, "be more verbose", \ + PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 }, \ + { OPTION_CALLBACK, 'q', "quiet", (var), NULL, "be more quiet", \ + PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 } +#define OPT__DRY_RUN(var) OPT_BOOLEAN('n', "dry-run", (var), "dry run") +#define OPT__ABBREV(var) \ + { OPTION_CALLBACK, 0, "abbrev", (var), "n", \ + "use digits to display SHA-1s", \ + PARSE_OPT_OPTARG, &parse_opt_abbrev_cb, 0 } + +extern const char *parse_options_fix_filename(const char *prefix, const char *file); + +#endif diff --git a/trunk/tools/perf/util/path.c b/trunk/tools/perf/util/path.c new file mode 100644 index 000000000000..a501a40dd2cb --- /dev/null +++ b/trunk/tools/perf/util/path.c @@ -0,0 +1,353 @@ +/* + * I'm tired of doing "vsnprintf()" etc just to open a + * file, so here's a "return static buffer with printf" + * interface for paths. + * + * It's obviously not thread-safe. Sue me. But it's quite + * useful for doing things like + * + * f = open(mkpath("%s/%s.perf", base, name), O_RDONLY); + * + * which is what it's designed for. + */ +#include "cache.h" + +static char bad_path[] = "/bad-path/"; +/* + * Two hacks: + */ + +static char *get_perf_dir(void) +{ + return "."; +} + +size_t strlcpy(char *dest, const char *src, size_t size) +{ + size_t ret = strlen(src); + + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + memcpy(dest, src, len); + dest[len] = '\0'; + } + return ret; +} + + +static char *get_pathname(void) +{ + static char pathname_array[4][PATH_MAX]; + static int index; + return pathname_array[3 & ++index]; +} + +static char *cleanup_path(char *path) +{ + /* Clean it up */ + if (!memcmp(path, "./", 2)) { + path += 2; + while (*path == '/') + path++; + } + return path; +} + +char *mksnpath(char *buf, size_t n, const char *fmt, ...) +{ + va_list args; + unsigned len; + + va_start(args, fmt); + len = vsnprintf(buf, n, fmt, args); + va_end(args); + if (len >= n) { + strlcpy(buf, bad_path, n); + return buf; + } + return cleanup_path(buf); +} + +static char *perf_vsnpath(char *buf, size_t n, const char *fmt, va_list args) +{ + const char *perf_dir = get_perf_dir(); + size_t len; + + len = strlen(perf_dir); + if (n < len + 1) + goto bad; + memcpy(buf, perf_dir, len); + if (len && !is_dir_sep(perf_dir[len-1])) + buf[len++] = '/'; + len += vsnprintf(buf + len, n - len, fmt, args); + if (len >= n) + goto bad; + return cleanup_path(buf); +bad: + strlcpy(buf, bad_path, n); + return buf; +} + +char *perf_snpath(char *buf, size_t n, const char *fmt, ...) +{ + va_list args; + va_start(args, fmt); + (void)perf_vsnpath(buf, n, fmt, args); + va_end(args); + return buf; +} + +char *perf_pathdup(const char *fmt, ...) +{ + char path[PATH_MAX]; + va_list args; + va_start(args, fmt); + (void)perf_vsnpath(path, sizeof(path), fmt, args); + va_end(args); + return xstrdup(path); +} + +char *mkpath(const char *fmt, ...) +{ + va_list args; + unsigned len; + char *pathname = get_pathname(); + + va_start(args, fmt); + len = vsnprintf(pathname, PATH_MAX, fmt, args); + va_end(args); + if (len >= PATH_MAX) + return bad_path; + return cleanup_path(pathname); +} + +char *perf_path(const char *fmt, ...) +{ + const char *perf_dir = get_perf_dir(); + char *pathname = get_pathname(); + va_list args; + unsigned len; + + len = strlen(perf_dir); + if (len > PATH_MAX-100) + return bad_path; + memcpy(pathname, perf_dir, len); + if (len && perf_dir[len-1] != '/') + pathname[len++] = '/'; + va_start(args, fmt); + len += vsnprintf(pathname + len, PATH_MAX - len, fmt, args); + va_end(args); + if (len >= PATH_MAX) + return bad_path; + return cleanup_path(pathname); +} + + +/* perf_mkstemp() - create tmp file honoring TMPDIR variable */ +int perf_mkstemp(char *path, size_t len, const char *template) +{ + const char *tmp; + size_t n; + + tmp = getenv("TMPDIR"); + if (!tmp) + tmp = "/tmp"; + n = snprintf(path, len, "%s/%s", tmp, template); + if (len <= n) { + errno = ENAMETOOLONG; + return -1; + } + return mkstemp(path); +} + + +const char *make_relative_path(const char *abs, const char *base) +{ + static char buf[PATH_MAX + 1]; + int baselen; + if (!base) + return abs; + baselen = strlen(base); + if (prefixcmp(abs, base)) + return abs; + if (abs[baselen] == '/') + baselen++; + else if (base[baselen - 1] != '/') + return abs; + strcpy(buf, abs + baselen); + return buf; +} + +/* + * It is okay if dst == src, but they should not overlap otherwise. + * + * Performs the following normalizations on src, storing the result in dst: + * - Ensures that components are separated by '/' (Windows only) + * - Squashes sequences of '/'. + * - Removes "." components. + * - Removes ".." components, and the components the precede them. + * Returns failure (non-zero) if a ".." component appears as first path + * component anytime during the normalization. Otherwise, returns success (0). + * + * Note that this function is purely textual. It does not follow symlinks, + * verify the existence of the path, or make any system calls. + */ +int normalize_path_copy(char *dst, const char *src) +{ + char *dst0; + + if (has_dos_drive_prefix(src)) { + *dst++ = *src++; + *dst++ = *src++; + } + dst0 = dst; + + if (is_dir_sep(*src)) { + *dst++ = '/'; + while (is_dir_sep(*src)) + src++; + } + + for (;;) { + char c = *src; + + /* + * A path component that begins with . could be + * special: + * (1) "." and ends -- ignore and terminate. + * (2) "./" -- ignore them, eat slash and continue. + * (3) ".." and ends -- strip one and terminate. + * (4) "../" -- strip one, eat slash and continue. + */ + if (c == '.') { + if (!src[1]) { + /* (1) */ + src++; + } else if (is_dir_sep(src[1])) { + /* (2) */ + src += 2; + while (is_dir_sep(*src)) + src++; + continue; + } else if (src[1] == '.') { + if (!src[2]) { + /* (3) */ + src += 2; + goto up_one; + } else if (is_dir_sep(src[2])) { + /* (4) */ + src += 3; + while (is_dir_sep(*src)) + src++; + goto up_one; + } + } + } + + /* copy up to the next '/', and eat all '/' */ + while ((c = *src++) != '\0' && !is_dir_sep(c)) + *dst++ = c; + if (is_dir_sep(c)) { + *dst++ = '/'; + while (is_dir_sep(c)) + c = *src++; + src--; + } else if (!c) + break; + continue; + + up_one: + /* + * dst0..dst is prefix portion, and dst[-1] is '/'; + * go up one level. + */ + dst--; /* go to trailing '/' */ + if (dst <= dst0) + return -1; + /* Windows: dst[-1] cannot be backslash anymore */ + while (dst0 < dst && dst[-1] != '/') + dst--; + } + *dst = '\0'; + return 0; +} + +/* + * path = Canonical absolute path + * prefix_list = Colon-separated list of absolute paths + * + * Determines, for each path in prefix_list, whether the "prefix" really + * is an ancestor directory of path. Returns the length of the longest + * ancestor directory, excluding any trailing slashes, or -1 if no prefix + * is an ancestor. (Note that this means 0 is returned if prefix_list is + * "/".) "/foo" is not considered an ancestor of "/foobar". Directories + * are not considered to be their own ancestors. path must be in a + * canonical form: empty components, or "." or ".." components are not + * allowed. prefix_list may be null, which is like "". + */ +int longest_ancestor_length(const char *path, const char *prefix_list) +{ + char buf[PATH_MAX+1]; + const char *ceil, *colon; + int len, max_len = -1; + + if (prefix_list == NULL || !strcmp(path, "/")) + return -1; + + for (colon = ceil = prefix_list; *colon; ceil = colon+1) { + for (colon = ceil; *colon && *colon != PATH_SEP; colon++); + len = colon - ceil; + if (len == 0 || len > PATH_MAX || !is_absolute_path(ceil)) + continue; + strlcpy(buf, ceil, len+1); + if (normalize_path_copy(buf, buf) < 0) + continue; + len = strlen(buf); + if (len > 0 && buf[len-1] == '/') + buf[--len] = '\0'; + + if (!strncmp(path, buf, len) && + path[len] == '/' && + len > max_len) { + max_len = len; + } + } + + return max_len; +} + +/* strip arbitrary amount of directory separators at end of path */ +static inline int chomp_trailing_dir_sep(const char *path, int len) +{ + while (len && is_dir_sep(path[len - 1])) + len--; + return len; +} + +/* + * If path ends with suffix (complete path components), returns the + * part before suffix (sans trailing directory separators). + * Otherwise returns NULL. + */ +char *strip_path_suffix(const char *path, const char *suffix) +{ + int path_len = strlen(path), suffix_len = strlen(suffix); + + while (suffix_len) { + if (!path_len) + return NULL; + + if (is_dir_sep(path[path_len - 1])) { + if (!is_dir_sep(suffix[suffix_len - 1])) + return NULL; + path_len = chomp_trailing_dir_sep(path, path_len); + suffix_len = chomp_trailing_dir_sep(suffix, suffix_len); + } + else if (path[--path_len] != suffix[--suffix_len]) + return NULL; + } + + if (path_len && !is_dir_sep(path[path_len - 1])) + return NULL; + return xstrndup(path, chomp_trailing_dir_sep(path, path_len)); +} diff --git a/trunk/tools/perf/util/quote.c b/trunk/tools/perf/util/quote.c new file mode 100644 index 000000000000..f18c5212bc92 --- /dev/null +++ b/trunk/tools/perf/util/quote.c @@ -0,0 +1,481 @@ +#include "cache.h" +#include "quote.h" + +int quote_path_fully = 1; + +/* Help to copy the thing properly quoted for the shell safety. + * any single quote is replaced with '\'', any exclamation point + * is replaced with '\!', and the whole thing is enclosed in a + * + * E.g. + * original sq_quote result + * name ==> name ==> 'name' + * a b ==> a b ==> 'a b' + * a'b ==> a'\''b ==> 'a'\''b' + * a!b ==> a'\!'b ==> 'a'\!'b' + */ +static inline int need_bs_quote(char c) +{ + return (c == '\'' || c == '!'); +} + +void sq_quote_buf(struct strbuf *dst, const char *src) +{ + char *to_free = NULL; + + if (dst->buf == src) + to_free = strbuf_detach(dst, NULL); + + strbuf_addch(dst, '\''); + while (*src) { + size_t len = strcspn(src, "'!"); + strbuf_add(dst, src, len); + src += len; + while (need_bs_quote(*src)) { + strbuf_addstr(dst, "'\\"); + strbuf_addch(dst, *src++); + strbuf_addch(dst, '\''); + } + } + strbuf_addch(dst, '\''); + free(to_free); +} + +void sq_quote_print(FILE *stream, const char *src) +{ + char c; + + fputc('\'', stream); + while ((c = *src++)) { + if (need_bs_quote(c)) { + fputs("'\\", stream); + fputc(c, stream); + fputc('\'', stream); + } else { + fputc(c, stream); + } + } + fputc('\'', stream); +} + +void sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen) +{ + int i; + + /* Copy into destination buffer. */ + strbuf_grow(dst, 255); + for (i = 0; argv[i]; ++i) { + strbuf_addch(dst, ' '); + sq_quote_buf(dst, argv[i]); + if (maxlen && dst->len > maxlen) + die("Too many or long arguments"); + } +} + +char *sq_dequote_step(char *arg, char **next) +{ + char *dst = arg; + char *src = arg; + char c; + + if (*src != '\'') + return NULL; + for (;;) { + c = *++src; + if (!c) + return NULL; + if (c != '\'') { + *dst++ = c; + continue; + } + /* We stepped out of sq */ + switch (*++src) { + case '\0': + *dst = 0; + if (next) + *next = NULL; + return arg; + case '\\': + c = *++src; + if (need_bs_quote(c) && *++src == '\'') { + *dst++ = c; + continue; + } + /* Fallthrough */ + default: + if (!next || !isspace(*src)) + return NULL; + do { + c = *++src; + } while (isspace(c)); + *dst = 0; + *next = src; + return arg; + } + } +} + +char *sq_dequote(char *arg) +{ + return sq_dequote_step(arg, NULL); +} + +int sq_dequote_to_argv(char *arg, const char ***argv, int *nr, int *alloc) +{ + char *next = arg; + + if (!*arg) + return 0; + do { + char *dequoted = sq_dequote_step(next, &next); + if (!dequoted) + return -1; + ALLOC_GROW(*argv, *nr + 1, *alloc); + (*argv)[(*nr)++] = dequoted; + } while (next); + + return 0; +} + +/* 1 means: quote as octal + * 0 means: quote as octal if (quote_path_fully) + * -1 means: never quote + * c: quote as "\\c" + */ +#define X8(x) x, x, x, x, x, x, x, x +#define X16(x) X8(x), X8(x) +static signed char const sq_lookup[256] = { + /* 0 1 2 3 4 5 6 7 */ + /* 0x00 */ 1, 1, 1, 1, 1, 1, 1, 'a', + /* 0x08 */ 'b', 't', 'n', 'v', 'f', 'r', 1, 1, + /* 0x10 */ X16(1), + /* 0x20 */ -1, -1, '"', -1, -1, -1, -1, -1, + /* 0x28 */ X16(-1), X16(-1), X16(-1), + /* 0x58 */ -1, -1, -1, -1,'\\', -1, -1, -1, + /* 0x60 */ X16(-1), X8(-1), + /* 0x78 */ -1, -1, -1, -1, -1, -1, -1, 1, + /* 0x80 */ /* set to 0 */ +}; + +static inline int sq_must_quote(char c) +{ + return sq_lookup[(unsigned char)c] + quote_path_fully > 0; +} + +/* returns the longest prefix not needing a quote up to maxlen if positive. + This stops at the first \0 because it's marked as a character needing an + escape */ +static size_t next_quote_pos(const char *s, ssize_t maxlen) +{ + size_t len; + if (maxlen < 0) { + for (len = 0; !sq_must_quote(s[len]); len++); + } else { + for (len = 0; len < maxlen && !sq_must_quote(s[len]); len++); + } + return len; +} + +/* + * C-style name quoting. + * + * (1) if sb and fp are both NULL, inspect the input name and counts the + * number of bytes that are needed to hold c_style quoted version of name, + * counting the double quotes around it but not terminating NUL, and + * returns it. + * However, if name does not need c_style quoting, it returns 0. + * + * (2) if sb or fp are not NULL, it emits the c_style quoted version + * of name, enclosed with double quotes if asked and needed only. + * Return value is the same as in (1). + */ +static size_t quote_c_style_counted(const char *name, ssize_t maxlen, + struct strbuf *sb, FILE *fp, int no_dq) +{ +#undef EMIT +#define EMIT(c) \ + do { \ + if (sb) strbuf_addch(sb, (c)); \ + if (fp) fputc((c), fp); \ + count++; \ + } while (0) +#define EMITBUF(s, l) \ + do { \ + int __ret; \ + if (sb) strbuf_add(sb, (s), (l)); \ + if (fp) __ret = fwrite((s), (l), 1, fp); \ + count += (l); \ + } while (0) + + size_t len, count = 0; + const char *p = name; + + for (;;) { + int ch; + + len = next_quote_pos(p, maxlen); + if (len == maxlen || !p[len]) + break; + + if (!no_dq && p == name) + EMIT('"'); + + EMITBUF(p, len); + EMIT('\\'); + p += len; + ch = (unsigned char)*p++; + if (sq_lookup[ch] >= ' ') { + EMIT(sq_lookup[ch]); + } else { + EMIT(((ch >> 6) & 03) + '0'); + EMIT(((ch >> 3) & 07) + '0'); + EMIT(((ch >> 0) & 07) + '0'); + } + } + + EMITBUF(p, len); + if (p == name) /* no ending quote needed */ + return 0; + + if (!no_dq) + EMIT('"'); + return count; +} + +size_t quote_c_style(const char *name, struct strbuf *sb, FILE *fp, int nodq) +{ + return quote_c_style_counted(name, -1, sb, fp, nodq); +} + +void quote_two_c_style(struct strbuf *sb, const char *prefix, const char *path, int nodq) +{ + if (quote_c_style(prefix, NULL, NULL, 0) || + quote_c_style(path, NULL, NULL, 0)) { + if (!nodq) + strbuf_addch(sb, '"'); + quote_c_style(prefix, sb, NULL, 1); + quote_c_style(path, sb, NULL, 1); + if (!nodq) + strbuf_addch(sb, '"'); + } else { + strbuf_addstr(sb, prefix); + strbuf_addstr(sb, path); + } +} + +void write_name_quoted(const char *name, FILE *fp, int terminator) +{ + if (terminator) { + quote_c_style(name, NULL, fp, 0); + } else { + fputs(name, fp); + } + fputc(terminator, fp); +} + +extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, + const char *name, FILE *fp, int terminator) +{ + int needquote = 0; + + if (terminator) { + needquote = next_quote_pos(pfx, pfxlen) < pfxlen + || name[next_quote_pos(name, -1)]; + } + if (needquote) { + fputc('"', fp); + quote_c_style_counted(pfx, pfxlen, NULL, fp, 1); + quote_c_style(name, NULL, fp, 1); + fputc('"', fp); + } else { + int ret; + + ret = fwrite(pfx, pfxlen, 1, fp); + fputs(name, fp); + } + fputc(terminator, fp); +} + +/* quote path as relative to the given prefix */ +char *quote_path_relative(const char *in, int len, + struct strbuf *out, const char *prefix) +{ + int needquote; + + if (len < 0) + len = strlen(in); + + /* "../" prefix itself does not need quoting, but "in" might. */ + needquote = next_quote_pos(in, len) < len; + strbuf_setlen(out, 0); + strbuf_grow(out, len); + + if (needquote) + strbuf_addch(out, '"'); + if (prefix) { + int off = 0; + while (prefix[off] && off < len && prefix[off] == in[off]) + if (prefix[off] == '/') { + prefix += off + 1; + in += off + 1; + len -= off + 1; + off = 0; + } else + off++; + + for (; *prefix; prefix++) + if (*prefix == '/') + strbuf_addstr(out, "../"); + } + + quote_c_style_counted (in, len, out, NULL, 1); + + if (needquote) + strbuf_addch(out, '"'); + if (!out->len) + strbuf_addstr(out, "./"); + + return out->buf; +} + +/* + * C-style name unquoting. + * + * Quoted should point at the opening double quote. + * + Returns 0 if it was able to unquote the string properly, and appends the + * result in the strbuf `sb'. + * + Returns -1 in case of error, and doesn't touch the strbuf. Though note + * that this function will allocate memory in the strbuf, so calling + * strbuf_release is mandatory whichever result unquote_c_style returns. + * + * Updates endp pointer to point at one past the ending double quote if given. + */ +int unquote_c_style(struct strbuf *sb, const char *quoted, const char **endp) +{ + size_t oldlen = sb->len, len; + int ch, ac; + + if (*quoted++ != '"') + return -1; + + for (;;) { + len = strcspn(quoted, "\"\\"); + strbuf_add(sb, quoted, len); + quoted += len; + + switch (*quoted++) { + case '"': + if (endp) + *endp = quoted; + return 0; + case '\\': + break; + default: + goto error; + } + + switch ((ch = *quoted++)) { + case 'a': ch = '\a'; break; + case 'b': ch = '\b'; break; + case 'f': ch = '\f'; break; + case 'n': ch = '\n'; break; + case 'r': ch = '\r'; break; + case 't': ch = '\t'; break; + case 'v': ch = '\v'; break; + + case '\\': case '"': + break; /* verbatim */ + + /* octal values with first digit over 4 overflow */ + case '0': case '1': case '2': case '3': + ac = ((ch - '0') << 6); + if ((ch = *quoted++) < '0' || '7' < ch) + goto error; + ac |= ((ch - '0') << 3); + if ((ch = *quoted++) < '0' || '7' < ch) + goto error; + ac |= (ch - '0'); + ch = ac; + break; + default: + goto error; + } + strbuf_addch(sb, ch); + } + + error: + strbuf_setlen(sb, oldlen); + return -1; +} + +/* quoting as a string literal for other languages */ + +void perl_quote_print(FILE *stream, const char *src) +{ + const char sq = '\''; + const char bq = '\\'; + char c; + + fputc(sq, stream); + while ((c = *src++)) { + if (c == sq || c == bq) + fputc(bq, stream); + fputc(c, stream); + } + fputc(sq, stream); +} + +void python_quote_print(FILE *stream, const char *src) +{ + const char sq = '\''; + const char bq = '\\'; + const char nl = '\n'; + char c; + + fputc(sq, stream); + while ((c = *src++)) { + if (c == nl) { + fputc(bq, stream); + fputc('n', stream); + continue; + } + if (c == sq || c == bq) + fputc(bq, stream); + fputc(c, stream); + } + fputc(sq, stream); +} + +void tcl_quote_print(FILE *stream, const char *src) +{ + char c; + + fputc('"', stream); + while ((c = *src++)) { + switch (c) { + case '[': case ']': + case '{': case '}': + case '$': case '\\': case '"': + fputc('\\', stream); + default: + fputc(c, stream); + break; + case '\f': + fputs("\\f", stream); + break; + case '\r': + fputs("\\r", stream); + break; + case '\n': + fputs("\\n", stream); + break; + case '\t': + fputs("\\t", stream); + break; + case '\v': + fputs("\\v", stream); + break; + } + } + fputc('"', stream); +} diff --git a/trunk/tools/perf/util/quote.h b/trunk/tools/perf/util/quote.h new file mode 100644 index 000000000000..5dfad89816db --- /dev/null +++ b/trunk/tools/perf/util/quote.h @@ -0,0 +1,68 @@ +#ifndef QUOTE_H +#define QUOTE_H + +#include +#include + +/* Help to copy the thing properly quoted for the shell safety. + * any single quote is replaced with '\'', any exclamation point + * is replaced with '\!', and the whole thing is enclosed in a + * single quote pair. + * + * For example, if you are passing the result to system() as an + * argument: + * + * sprintf(cmd, "foobar %s %s", sq_quote(arg0), sq_quote(arg1)) + * + * would be appropriate. If the system() is going to call ssh to + * run the command on the other side: + * + * sprintf(cmd, "git-diff-tree %s %s", sq_quote(arg0), sq_quote(arg1)); + * sprintf(rcmd, "ssh %s %s", sq_util/quote.host), sq_quote(cmd)); + * + * Note that the above examples leak memory! Remember to free result from + * sq_quote() in a real application. + * + * sq_quote_buf() writes to an existing buffer of specified size; it + * will return the number of characters that would have been written + * excluding the final null regardless of the buffer size. + */ + +extern void sq_quote_print(FILE *stream, const char *src); + +extern void sq_quote_buf(struct strbuf *, const char *src); +extern void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen); + +/* This unwraps what sq_quote() produces in place, but returns + * NULL if the input does not look like what sq_quote would have + * produced. + */ +extern char *sq_dequote(char *); + +/* + * Same as the above, but can be used to unwrap many arguments in the + * same string separated by space. "next" is changed to point to the + * next argument that should be passed as first parameter. When there + * is no more argument to be dequoted, "next" is updated to point to NULL. + */ +extern char *sq_dequote_step(char *arg, char **next); +extern int sq_dequote_to_argv(char *arg, const char ***argv, int *nr, int *alloc); + +extern int unquote_c_style(struct strbuf *, const char *quoted, const char **endp); +extern size_t quote_c_style(const char *name, struct strbuf *, FILE *, int no_dq); +extern void quote_two_c_style(struct strbuf *, const char *, const char *, int); + +extern void write_name_quoted(const char *name, FILE *, int terminator); +extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, + const char *name, FILE *, int terminator); + +/* quote path as relative to the given prefix */ +char *quote_path_relative(const char *in, int len, + struct strbuf *out, const char *prefix); + +/* quoting as a string literal for other languages */ +extern void perl_quote_print(FILE *stream, const char *src); +extern void python_quote_print(FILE *stream, const char *src); +extern void tcl_quote_print(FILE *stream, const char *src); + +#endif diff --git a/trunk/tools/perf/util/rbtree.c b/trunk/tools/perf/util/rbtree.c new file mode 100644 index 000000000000..b15ba9c7cb3f --- /dev/null +++ b/trunk/tools/perf/util/rbtree.c @@ -0,0 +1,383 @@ +/* + Red Black Trees + (C) 1999 Andrea Arcangeli + (C) 2002 David Woodhouse + + 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. + + This program 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 General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + linux/lib/rbtree.c +*/ + +#include "rbtree.h" + +static void __rb_rotate_left(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *right = node->rb_right; + struct rb_node *parent = rb_parent(node); + + if ((node->rb_right = right->rb_left)) + rb_set_parent(right->rb_left, node); + right->rb_left = node; + + rb_set_parent(right, parent); + + if (parent) + { + if (node == parent->rb_left) + parent->rb_left = right; + else + parent->rb_right = right; + } + else + root->rb_node = right; + rb_set_parent(node, right); +} + +static void __rb_rotate_right(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *left = node->rb_left; + struct rb_node *parent = rb_parent(node); + + if ((node->rb_left = left->rb_right)) + rb_set_parent(left->rb_right, node); + left->rb_right = node; + + rb_set_parent(left, parent); + + if (parent) + { + if (node == parent->rb_right) + parent->rb_right = left; + else + parent->rb_left = left; + } + else + root->rb_node = left; + rb_set_parent(node, left); +} + +void rb_insert_color(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *parent, *gparent; + + while ((parent = rb_parent(node)) && rb_is_red(parent)) + { + gparent = rb_parent(parent); + + if (parent == gparent->rb_left) + { + { + register struct rb_node *uncle = gparent->rb_right; + if (uncle && rb_is_red(uncle)) + { + rb_set_black(uncle); + rb_set_black(parent); + rb_set_red(gparent); + node = gparent; + continue; + } + } + + if (parent->rb_right == node) + { + register struct rb_node *tmp; + __rb_rotate_left(parent, root); + tmp = parent; + parent = node; + node = tmp; + } + + rb_set_black(parent); + rb_set_red(gparent); + __rb_rotate_right(gparent, root); + } else { + { + register struct rb_node *uncle = gparent->rb_left; + if (uncle && rb_is_red(uncle)) + { + rb_set_black(uncle); + rb_set_black(parent); + rb_set_red(gparent); + node = gparent; + continue; + } + } + + if (parent->rb_left == node) + { + register struct rb_node *tmp; + __rb_rotate_right(parent, root); + tmp = parent; + parent = node; + node = tmp; + } + + rb_set_black(parent); + rb_set_red(gparent); + __rb_rotate_left(gparent, root); + } + } + + rb_set_black(root->rb_node); +} + +static void __rb_erase_color(struct rb_node *node, struct rb_node *parent, + struct rb_root *root) +{ + struct rb_node *other; + + while ((!node || rb_is_black(node)) && node != root->rb_node) + { + if (parent->rb_left == node) + { + other = parent->rb_right; + if (rb_is_red(other)) + { + rb_set_black(other); + rb_set_red(parent); + __rb_rotate_left(parent, root); + other = parent->rb_right; + } + if ((!other->rb_left || rb_is_black(other->rb_left)) && + (!other->rb_right || rb_is_black(other->rb_right))) + { + rb_set_red(other); + node = parent; + parent = rb_parent(node); + } + else + { + if (!other->rb_right || rb_is_black(other->rb_right)) + { + rb_set_black(other->rb_left); + rb_set_red(other); + __rb_rotate_right(other, root); + other = parent->rb_right; + } + rb_set_color(other, rb_color(parent)); + rb_set_black(parent); + rb_set_black(other->rb_right); + __rb_rotate_left(parent, root); + node = root->rb_node; + break; + } + } + else + { + other = parent->rb_left; + if (rb_is_red(other)) + { + rb_set_black(other); + rb_set_red(parent); + __rb_rotate_right(parent, root); + other = parent->rb_left; + } + if ((!other->rb_left || rb_is_black(other->rb_left)) && + (!other->rb_right || rb_is_black(other->rb_right))) + { + rb_set_red(other); + node = parent; + parent = rb_parent(node); + } + else + { + if (!other->rb_left || rb_is_black(other->rb_left)) + { + rb_set_black(other->rb_right); + rb_set_red(other); + __rb_rotate_left(other, root); + other = parent->rb_left; + } + rb_set_color(other, rb_color(parent)); + rb_set_black(parent); + rb_set_black(other->rb_left); + __rb_rotate_right(parent, root); + node = root->rb_node; + break; + } + } + } + if (node) + rb_set_black(node); +} + +void rb_erase(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *child, *parent; + int color; + + if (!node->rb_left) + child = node->rb_right; + else if (!node->rb_right) + child = node->rb_left; + else + { + struct rb_node *old = node, *left; + + node = node->rb_right; + while ((left = node->rb_left) != NULL) + node = left; + child = node->rb_right; + parent = rb_parent(node); + color = rb_color(node); + + if (child) + rb_set_parent(child, parent); + if (parent == old) { + parent->rb_right = child; + parent = node; + } else + parent->rb_left = child; + + node->rb_parent_color = old->rb_parent_color; + node->rb_right = old->rb_right; + node->rb_left = old->rb_left; + + if (rb_parent(old)) + { + if (rb_parent(old)->rb_left == old) + rb_parent(old)->rb_left = node; + else + rb_parent(old)->rb_right = node; + } else + root->rb_node = node; + + rb_set_parent(old->rb_left, node); + if (old->rb_right) + rb_set_parent(old->rb_right, node); + goto color; + } + + parent = rb_parent(node); + color = rb_color(node); + + if (child) + rb_set_parent(child, parent); + if (parent) + { + if (parent->rb_left == node) + parent->rb_left = child; + else + parent->rb_right = child; + } + else + root->rb_node = child; + + color: + if (color == RB_BLACK) + __rb_erase_color(child, parent, root); +} + +/* + * This function returns the first node (in sort order) of the tree. + */ +struct rb_node *rb_first(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_left) + n = n->rb_left; + return n; +} + +struct rb_node *rb_last(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_right) + n = n->rb_right; + return n; +} + +struct rb_node *rb_next(const struct rb_node *node) +{ + struct rb_node *parent; + + if (rb_parent(node) == node) + return NULL; + + /* If we have a right-hand child, go down and then left as far + as we can. */ + if (node->rb_right) { + node = node->rb_right; + while (node->rb_left) + node=node->rb_left; + return (struct rb_node *)node; + } + + /* No right-hand children. Everything down and left is + smaller than us, so any 'next' node must be in the general + direction of our parent. Go up the tree; any time the + ancestor is a right-hand child of its parent, keep going + up. First time it's a left-hand child of its parent, said + parent is our 'next' node. */ + while ((parent = rb_parent(node)) && node == parent->rb_right) + node = parent; + + return parent; +} + +struct rb_node *rb_prev(const struct rb_node *node) +{ + struct rb_node *parent; + + if (rb_parent(node) == node) + return NULL; + + /* If we have a left-hand child, go down and then right as far + as we can. */ + if (node->rb_left) { + node = node->rb_left; + while (node->rb_right) + node=node->rb_right; + return (struct rb_node *)node; + } + + /* No left-hand children. Go up till we find an ancestor which + is a right-hand child of its parent */ + while ((parent = rb_parent(node)) && node == parent->rb_left) + node = parent; + + return parent; +} + +void rb_replace_node(struct rb_node *victim, struct rb_node *new, + struct rb_root *root) +{ + struct rb_node *parent = rb_parent(victim); + + /* Set the surrounding nodes to point to the replacement */ + if (parent) { + if (victim == parent->rb_left) + parent->rb_left = new; + else + parent->rb_right = new; + } else { + root->rb_node = new; + } + if (victim->rb_left) + rb_set_parent(victim->rb_left, new); + if (victim->rb_right) + rb_set_parent(victim->rb_right, new); + + /* Copy the pointers/colour from the victim to the replacement */ + *new = *victim; +} diff --git a/trunk/tools/perf/util/rbtree.h b/trunk/tools/perf/util/rbtree.h new file mode 100644 index 000000000000..6bdc488a47fb --- /dev/null +++ b/trunk/tools/perf/util/rbtree.h @@ -0,0 +1,171 @@ +/* + Red Black Trees + (C) 1999 Andrea Arcangeli + + 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. + + This program 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 General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + linux/include/linux/rbtree.h + + To use rbtrees you'll have to implement your own insert and search cores. + This will avoid us to use callbacks and to drop drammatically performances. + I know it's not the cleaner way, but in C (not in C++) to get + performances and genericity... + + Some example of insert and search follows here. The search is a plain + normal search over an ordered tree. The insert instead must be implemented + int two steps: as first thing the code must insert the element in + order as a red leaf in the tree, then the support library function + rb_insert_color() must be called. Such function will do the + not trivial work to rebalance the rbtree if necessary. + +----------------------------------------------------------------------- +static inline struct page * rb_search_page_cache(struct inode * inode, + unsigned long offset) +{ + struct rb_node * n = inode->i_rb_page_cache.rb_node; + struct page * page; + + while (n) + { + page = rb_entry(n, struct page, rb_page_cache); + + if (offset < page->offset) + n = n->rb_left; + else if (offset > page->offset) + n = n->rb_right; + else + return page; + } + return NULL; +} + +static inline struct page * __rb_insert_page_cache(struct inode * inode, + unsigned long offset, + struct rb_node * node) +{ + struct rb_node ** p = &inode->i_rb_page_cache.rb_node; + struct rb_node * parent = NULL; + struct page * page; + + while (*p) + { + parent = *p; + page = rb_entry(parent, struct page, rb_page_cache); + + if (offset < page->offset) + p = &(*p)->rb_left; + else if (offset > page->offset) + p = &(*p)->rb_right; + else + return page; + } + + rb_link_node(node, parent, p); + + return NULL; +} + +static inline struct page * rb_insert_page_cache(struct inode * inode, + unsigned long offset, + struct rb_node * node) +{ + struct page * ret; + if ((ret = __rb_insert_page_cache(inode, offset, node))) + goto out; + rb_insert_color(node, &inode->i_rb_page_cache); + out: + return ret; +} +----------------------------------------------------------------------- +*/ + +#ifndef _LINUX_RBTREE_H +#define _LINUX_RBTREE_H + +#include + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + const typeof( ((type *)0)->member ) *__mptr = (ptr); \ + (type *)( (char *)__mptr - offsetof(type,member) );}) + +struct rb_node +{ + unsigned long rb_parent_color; +#define RB_RED 0 +#define RB_BLACK 1 + struct rb_node *rb_right; + struct rb_node *rb_left; +} __attribute__((aligned(sizeof(long)))); + /* The alignment might seem pointless, but allegedly CRIS needs it */ + +struct rb_root +{ + struct rb_node *rb_node; +}; + + +#define rb_parent(r) ((struct rb_node *)((r)->rb_parent_color & ~3)) +#define rb_color(r) ((r)->rb_parent_color & 1) +#define rb_is_red(r) (!rb_color(r)) +#define rb_is_black(r) rb_color(r) +#define rb_set_red(r) do { (r)->rb_parent_color &= ~1; } while (0) +#define rb_set_black(r) do { (r)->rb_parent_color |= 1; } while (0) + +static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) +{ + rb->rb_parent_color = (rb->rb_parent_color & 3) | (unsigned long)p; +} +static inline void rb_set_color(struct rb_node *rb, int color) +{ + rb->rb_parent_color = (rb->rb_parent_color & ~1) | color; +} + +#define RB_ROOT (struct rb_root) { NULL, } +#define rb_entry(ptr, type, member) container_of(ptr, type, member) + +#define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL) +#define RB_EMPTY_NODE(node) (rb_parent(node) == node) +#define RB_CLEAR_NODE(node) (rb_set_parent(node, node)) + +extern void rb_insert_color(struct rb_node *, struct rb_root *); +extern void rb_erase(struct rb_node *, struct rb_root *); + +/* Find logical next and previous nodes in a tree */ +extern struct rb_node *rb_next(const struct rb_node *); +extern struct rb_node *rb_prev(const struct rb_node *); +extern struct rb_node *rb_first(const struct rb_root *); +extern struct rb_node *rb_last(const struct rb_root *); + +/* Fast replacement of a single node without remove/rebalance/add/rebalance */ +extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, + struct rb_root *root); + +static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, + struct rb_node ** rb_link) +{ + node->rb_parent_color = (unsigned long )parent; + node->rb_left = node->rb_right = NULL; + + *rb_link = node; +} + +#endif /* _LINUX_RBTREE_H */ diff --git a/trunk/tools/perf/util/run-command.c b/trunk/tools/perf/util/run-command.c new file mode 100644 index 000000000000..b2f5e854f40a --- /dev/null +++ b/trunk/tools/perf/util/run-command.c @@ -0,0 +1,395 @@ +#include "cache.h" +#include "run-command.h" +#include "exec_cmd.h" + +static inline void close_pair(int fd[2]) +{ + close(fd[0]); + close(fd[1]); +} + +static inline void dup_devnull(int to) +{ + int fd = open("/dev/null", O_RDWR); + dup2(fd, to); + close(fd); +} + +int start_command(struct child_process *cmd) +{ + int need_in, need_out, need_err; + int fdin[2], fdout[2], fderr[2]; + + /* + * In case of errors we must keep the promise to close FDs + * that have been passed in via ->in and ->out. + */ + + need_in = !cmd->no_stdin && cmd->in < 0; + if (need_in) { + if (pipe(fdin) < 0) { + if (cmd->out > 0) + close(cmd->out); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->in = fdin[1]; + } + + need_out = !cmd->no_stdout + && !cmd->stdout_to_stderr + && cmd->out < 0; + if (need_out) { + if (pipe(fdout) < 0) { + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->out = fdout[0]; + } + + need_err = !cmd->no_stderr && cmd->err < 0; + if (need_err) { + if (pipe(fderr) < 0) { + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + if (need_out) + close_pair(fdout); + else if (cmd->out) + close(cmd->out); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->err = fderr[0]; + } + +#ifndef __MINGW32__ + fflush(NULL); + cmd->pid = fork(); + if (!cmd->pid) { + if (cmd->no_stdin) + dup_devnull(0); + else if (need_in) { + dup2(fdin[0], 0); + close_pair(fdin); + } else if (cmd->in) { + dup2(cmd->in, 0); + close(cmd->in); + } + + if (cmd->no_stderr) + dup_devnull(2); + else if (need_err) { + dup2(fderr[1], 2); + close_pair(fderr); + } + + if (cmd->no_stdout) + dup_devnull(1); + else if (cmd->stdout_to_stderr) + dup2(2, 1); + else if (need_out) { + dup2(fdout[1], 1); + close_pair(fdout); + } else if (cmd->out > 1) { + dup2(cmd->out, 1); + close(cmd->out); + } + + if (cmd->dir && chdir(cmd->dir)) + die("exec %s: cd to %s failed (%s)", cmd->argv[0], + cmd->dir, strerror(errno)); + if (cmd->env) { + for (; *cmd->env; cmd->env++) { + if (strchr(*cmd->env, '=')) + putenv((char*)*cmd->env); + else + unsetenv(*cmd->env); + } + } + if (cmd->preexec_cb) + cmd->preexec_cb(); + if (cmd->perf_cmd) { + execv_perf_cmd(cmd->argv); + } else { + execvp(cmd->argv[0], (char *const*) cmd->argv); + } + exit(127); + } +#else + int s0 = -1, s1 = -1, s2 = -1; /* backups of stdin, stdout, stderr */ + const char **sargv = cmd->argv; + char **env = environ; + + if (cmd->no_stdin) { + s0 = dup(0); + dup_devnull(0); + } else if (need_in) { + s0 = dup(0); + dup2(fdin[0], 0); + } else if (cmd->in) { + s0 = dup(0); + dup2(cmd->in, 0); + } + + if (cmd->no_stderr) { + s2 = dup(2); + dup_devnull(2); + } else if (need_err) { + s2 = dup(2); + dup2(fderr[1], 2); + } + + if (cmd->no_stdout) { + s1 = dup(1); + dup_devnull(1); + } else if (cmd->stdout_to_stderr) { + s1 = dup(1); + dup2(2, 1); + } else if (need_out) { + s1 = dup(1); + dup2(fdout[1], 1); + } else if (cmd->out > 1) { + s1 = dup(1); + dup2(cmd->out, 1); + } + + if (cmd->dir) + die("chdir in start_command() not implemented"); + if (cmd->env) { + env = copy_environ(); + for (; *cmd->env; cmd->env++) + env = env_setenv(env, *cmd->env); + } + + if (cmd->perf_cmd) { + cmd->argv = prepare_perf_cmd(cmd->argv); + } + + cmd->pid = mingw_spawnvpe(cmd->argv[0], cmd->argv, env); + + if (cmd->env) + free_environ(env); + if (cmd->perf_cmd) + free(cmd->argv); + + cmd->argv = sargv; + if (s0 >= 0) + dup2(s0, 0), close(s0); + if (s1 >= 0) + dup2(s1, 1), close(s1); + if (s2 >= 0) + dup2(s2, 2), close(s2); +#endif + + if (cmd->pid < 0) { + int err = errno; + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + if (need_out) + close_pair(fdout); + else if (cmd->out) + close(cmd->out); + if (need_err) + close_pair(fderr); + return err == ENOENT ? + -ERR_RUN_COMMAND_EXEC : + -ERR_RUN_COMMAND_FORK; + } + + if (need_in) + close(fdin[0]); + else if (cmd->in) + close(cmd->in); + + if (need_out) + close(fdout[1]); + else if (cmd->out) + close(cmd->out); + + if (need_err) + close(fderr[1]); + + return 0; +} + +static int wait_or_whine(pid_t pid) +{ + for (;;) { + int status, code; + pid_t waiting = waitpid(pid, &status, 0); + + if (waiting < 0) { + if (errno == EINTR) + continue; + error("waitpid failed (%s)", strerror(errno)); + return -ERR_RUN_COMMAND_WAITPID; + } + if (waiting != pid) + return -ERR_RUN_COMMAND_WAITPID_WRONG_PID; + if (WIFSIGNALED(status)) + return -ERR_RUN_COMMAND_WAITPID_SIGNAL; + + if (!WIFEXITED(status)) + return -ERR_RUN_COMMAND_WAITPID_NOEXIT; + code = WEXITSTATUS(status); + switch (code) { + case 127: + return -ERR_RUN_COMMAND_EXEC; + case 0: + return 0; + default: + return -code; + } + } +} + +int finish_command(struct child_process *cmd) +{ + return wait_or_whine(cmd->pid); +} + +int run_command(struct child_process *cmd) +{ + int code = start_command(cmd); + if (code) + return code; + return finish_command(cmd); +} + +static void prepare_run_command_v_opt(struct child_process *cmd, + const char **argv, + int opt) +{ + memset(cmd, 0, sizeof(*cmd)); + cmd->argv = argv; + cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0; + cmd->perf_cmd = opt & RUN_PERF_CMD ? 1 : 0; + cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0; +} + +int run_command_v_opt(const char **argv, int opt) +{ + struct child_process cmd; + prepare_run_command_v_opt(&cmd, argv, opt); + return run_command(&cmd); +} + +int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const char *const *env) +{ + struct child_process cmd; + prepare_run_command_v_opt(&cmd, argv, opt); + cmd.dir = dir; + cmd.env = env; + return run_command(&cmd); +} + +#ifdef __MINGW32__ +static __stdcall unsigned run_thread(void *data) +{ + struct async *async = data; + return async->proc(async->fd_for_proc, async->data); +} +#endif + +int start_async(struct async *async) +{ + int pipe_out[2]; + + if (pipe(pipe_out) < 0) + return error("cannot create pipe: %s", strerror(errno)); + async->out = pipe_out[0]; + +#ifndef __MINGW32__ + /* Flush stdio before fork() to avoid cloning buffers */ + fflush(NULL); + + async->pid = fork(); + if (async->pid < 0) { + error("fork (async) failed: %s", strerror(errno)); + close_pair(pipe_out); + return -1; + } + if (!async->pid) { + close(pipe_out[0]); + exit(!!async->proc(pipe_out[1], async->data)); + } + close(pipe_out[1]); +#else + async->fd_for_proc = pipe_out[1]; + async->tid = (HANDLE) _beginthreadex(NULL, 0, run_thread, async, 0, NULL); + if (!async->tid) { + error("cannot create thread: %s", strerror(errno)); + close_pair(pipe_out); + return -1; + } +#endif + return 0; +} + +int finish_async(struct async *async) +{ +#ifndef __MINGW32__ + int ret = 0; + + if (wait_or_whine(async->pid)) + ret = error("waitpid (async) failed"); +#else + DWORD ret = 0; + if (WaitForSingleObject(async->tid, INFINITE) != WAIT_OBJECT_0) + ret = error("waiting for thread failed: %lu", GetLastError()); + else if (!GetExitCodeThread(async->tid, &ret)) + ret = error("cannot get thread exit code: %lu", GetLastError()); + CloseHandle(async->tid); +#endif + return ret; +} + +int run_hook(const char *index_file, const char *name, ...) +{ + struct child_process hook; + const char **argv = NULL, *env[2]; + char index[PATH_MAX]; + va_list args; + int ret; + size_t i = 0, alloc = 0; + + if (access(perf_path("hooks/%s", name), X_OK) < 0) + return 0; + + va_start(args, name); + ALLOC_GROW(argv, i + 1, alloc); + argv[i++] = perf_path("hooks/%s", name); + while (argv[i-1]) { + ALLOC_GROW(argv, i + 1, alloc); + argv[i++] = va_arg(args, const char *); + } + va_end(args); + + memset(&hook, 0, sizeof(hook)); + hook.argv = argv; + hook.no_stdin = 1; + hook.stdout_to_stderr = 1; + if (index_file) { + snprintf(index, sizeof(index), "PERF_INDEX_FILE=%s", index_file); + env[0] = index; + env[1] = NULL; + hook.env = env; + } + + ret = start_command(&hook); + free(argv); + if (ret) { + warning("Could not spawn %s", argv[0]); + return ret; + } + ret = finish_command(&hook); + if (ret == -ERR_RUN_COMMAND_WAITPID_SIGNAL) + warning("%s exited due to uncaught signal", argv[0]); + + return ret; +} diff --git a/trunk/tools/perf/util/run-command.h b/trunk/tools/perf/util/run-command.h new file mode 100644 index 000000000000..328289f23669 --- /dev/null +++ b/trunk/tools/perf/util/run-command.h @@ -0,0 +1,93 @@ +#ifndef RUN_COMMAND_H +#define RUN_COMMAND_H + +enum { + ERR_RUN_COMMAND_FORK = 10000, + ERR_RUN_COMMAND_EXEC, + ERR_RUN_COMMAND_PIPE, + ERR_RUN_COMMAND_WAITPID, + ERR_RUN_COMMAND_WAITPID_WRONG_PID, + ERR_RUN_COMMAND_WAITPID_SIGNAL, + ERR_RUN_COMMAND_WAITPID_NOEXIT, +}; +#define IS_RUN_COMMAND_ERR(x) (-(x) >= ERR_RUN_COMMAND_FORK) + +struct child_process { + const char **argv; + pid_t pid; + /* + * Using .in, .out, .err: + * - Specify 0 for no redirections (child inherits stdin, stdout, + * stderr from parent). + * - Specify -1 to have a pipe allocated as follows: + * .in: returns the writable pipe end; parent writes to it, + * the readable pipe end becomes child's stdin + * .out, .err: returns the readable pipe end; parent reads from + * it, the writable pipe end becomes child's stdout/stderr + * The caller of start_command() must close the returned FDs + * after it has completed reading from/writing to it! + * - Specify > 0 to set a channel to a particular FD as follows: + * .in: a readable FD, becomes child's stdin + * .out: a writable FD, becomes child's stdout/stderr + * .err > 0 not supported + * The specified FD is closed by start_command(), even in case + * of errors! + */ + int in; + int out; + int err; + const char *dir; + const char *const *env; + unsigned no_stdin:1; + unsigned no_stdout:1; + unsigned no_stderr:1; + unsigned perf_cmd:1; /* if this is to be perf sub-command */ + unsigned stdout_to_stderr:1; + void (*preexec_cb)(void); +}; + +int start_command(struct child_process *); +int finish_command(struct child_process *); +int run_command(struct child_process *); + +extern int run_hook(const char *index_file, const char *name, ...); + +#define RUN_COMMAND_NO_STDIN 1 +#define RUN_PERF_CMD 2 /*If this is to be perf sub-command */ +#define RUN_COMMAND_STDOUT_TO_STDERR 4 +int run_command_v_opt(const char **argv, int opt); + +/* + * env (the environment) is to be formatted like environ: "VAR=VALUE". + * To unset an environment variable use just "VAR". + */ +int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const char *const *env); + +/* + * The purpose of the following functions is to feed a pipe by running + * a function asynchronously and providing output that the caller reads. + * + * It is expected that no synchronization and mutual exclusion between + * the caller and the feed function is necessary so that the function + * can run in a thread without interfering with the caller. + */ +struct async { + /* + * proc writes to fd and closes it; + * returns 0 on success, non-zero on failure + */ + int (*proc)(int fd, void *data); + void *data; + int out; /* caller reads from here and closes it */ +#ifndef __MINGW32__ + pid_t pid; +#else + HANDLE tid; + int fd_for_proc; +#endif +}; + +int start_async(struct async *async); +int finish_async(struct async *async); + +#endif diff --git a/trunk/tools/perf/util/sigchain.c b/trunk/tools/perf/util/sigchain.c new file mode 100644 index 000000000000..1118b99e57d3 --- /dev/null +++ b/trunk/tools/perf/util/sigchain.c @@ -0,0 +1,52 @@ +#include "sigchain.h" +#include "cache.h" + +#define SIGCHAIN_MAX_SIGNALS 32 + +struct sigchain_signal { + sigchain_fun *old; + int n; + int alloc; +}; +static struct sigchain_signal signals[SIGCHAIN_MAX_SIGNALS]; + +static void check_signum(int sig) +{ + if (sig < 1 || sig >= SIGCHAIN_MAX_SIGNALS) + die("BUG: signal out of range: %d", sig); +} + +int sigchain_push(int sig, sigchain_fun f) +{ + struct sigchain_signal *s = signals + sig; + check_signum(sig); + + ALLOC_GROW(s->old, s->n + 1, s->alloc); + s->old[s->n] = signal(sig, f); + if (s->old[s->n] == SIG_ERR) + return -1; + s->n++; + return 0; +} + +int sigchain_pop(int sig) +{ + struct sigchain_signal *s = signals + sig; + check_signum(sig); + if (s->n < 1) + return 0; + + if (signal(sig, s->old[s->n - 1]) == SIG_ERR) + return -1; + s->n--; + return 0; +} + +void sigchain_push_common(sigchain_fun f) +{ + sigchain_push(SIGINT, f); + sigchain_push(SIGHUP, f); + sigchain_push(SIGTERM, f); + sigchain_push(SIGQUIT, f); + sigchain_push(SIGPIPE, f); +} diff --git a/trunk/tools/perf/util/sigchain.h b/trunk/tools/perf/util/sigchain.h new file mode 100644 index 000000000000..618083bce0c6 --- /dev/null +++ b/trunk/tools/perf/util/sigchain.h @@ -0,0 +1,11 @@ +#ifndef SIGCHAIN_H +#define SIGCHAIN_H + +typedef void (*sigchain_fun)(int); + +int sigchain_push(int sig, sigchain_fun f); +int sigchain_pop(int sig); + +void sigchain_push_common(sigchain_fun f); + +#endif /* SIGCHAIN_H */ diff --git a/trunk/tools/perf/util/strbuf.c b/trunk/tools/perf/util/strbuf.c new file mode 100644 index 000000000000..eaba09306802 --- /dev/null +++ b/trunk/tools/perf/util/strbuf.c @@ -0,0 +1,359 @@ +#include "cache.h" + +int prefixcmp(const char *str, const char *prefix) +{ + for (; ; str++, prefix++) + if (!*prefix) + return 0; + else if (*str != *prefix) + return (unsigned char)*prefix - (unsigned char)*str; +} + +/* + * Used as the default ->buf value, so that people can always assume + * buf is non NULL and ->buf is NUL terminated even for a freshly + * initialized strbuf. + */ +char strbuf_slopbuf[1]; + +void strbuf_init(struct strbuf *sb, size_t hint) +{ + sb->alloc = sb->len = 0; + sb->buf = strbuf_slopbuf; + if (hint) + strbuf_grow(sb, hint); +} + +void strbuf_release(struct strbuf *sb) +{ + if (sb->alloc) { + free(sb->buf); + strbuf_init(sb, 0); + } +} + +char *strbuf_detach(struct strbuf *sb, size_t *sz) +{ + char *res = sb->alloc ? sb->buf : NULL; + if (sz) + *sz = sb->len; + strbuf_init(sb, 0); + return res; +} + +void strbuf_attach(struct strbuf *sb, void *buf, size_t len, size_t alloc) +{ + strbuf_release(sb); + sb->buf = buf; + sb->len = len; + sb->alloc = alloc; + strbuf_grow(sb, 0); + sb->buf[sb->len] = '\0'; +} + +void strbuf_grow(struct strbuf *sb, size_t extra) +{ + if (sb->len + extra + 1 <= sb->len) + die("you want to use way too much memory"); + if (!sb->alloc) + sb->buf = NULL; + ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); +} + +void strbuf_trim(struct strbuf *sb) +{ + char *b = sb->buf; + while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1])) + sb->len--; + while (sb->len > 0 && isspace(*b)) { + b++; + sb->len--; + } + memmove(sb->buf, b, sb->len); + sb->buf[sb->len] = '\0'; +} +void strbuf_rtrim(struct strbuf *sb) +{ + while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1])) + sb->len--; + sb->buf[sb->len] = '\0'; +} + +void strbuf_ltrim(struct strbuf *sb) +{ + char *b = sb->buf; + while (sb->len > 0 && isspace(*b)) { + b++; + sb->len--; + } + memmove(sb->buf, b, sb->len); + sb->buf[sb->len] = '\0'; +} + +void strbuf_tolower(struct strbuf *sb) +{ + int i; + for (i = 0; i < sb->len; i++) + sb->buf[i] = tolower(sb->buf[i]); +} + +struct strbuf **strbuf_split(const struct strbuf *sb, int delim) +{ + int alloc = 2, pos = 0; + char *n, *p; + struct strbuf **ret; + struct strbuf *t; + + ret = calloc(alloc, sizeof(struct strbuf *)); + p = n = sb->buf; + while (n < sb->buf + sb->len) { + int len; + n = memchr(n, delim, sb->len - (n - sb->buf)); + if (pos + 1 >= alloc) { + alloc = alloc * 2; + ret = realloc(ret, sizeof(struct strbuf *) * alloc); + } + if (!n) + n = sb->buf + sb->len - 1; + len = n - p + 1; + t = malloc(sizeof(struct strbuf)); + strbuf_init(t, len); + strbuf_add(t, p, len); + ret[pos] = t; + ret[++pos] = NULL; + p = ++n; + } + return ret; +} + +void strbuf_list_free(struct strbuf **sbs) +{ + struct strbuf **s = sbs; + + while (*s) { + strbuf_release(*s); + free(*s++); + } + free(sbs); +} + +int strbuf_cmp(const struct strbuf *a, const struct strbuf *b) +{ + int len = a->len < b->len ? a->len: b->len; + int cmp = memcmp(a->buf, b->buf, len); + if (cmp) + return cmp; + return a->len < b->len ? -1: a->len != b->len; +} + +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_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) +{ + strbuf_splice(sb, pos, 0, data, 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); + memcpy(sb->buf + sb->len, data, len); + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len) +{ + strbuf_grow(sb, len); + memcpy(sb->buf + sb->len, sb->buf + pos, len); + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_addf(struct strbuf *sb, const char *fmt, ...) +{ + int len; + va_list ap; + + if (!strbuf_avail(sb)) + strbuf_grow(sb, 64); + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len < 0) + die("your vsnprintf is broken"); + if (len > strbuf_avail(sb)) { + strbuf_grow(sb, len); + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len > strbuf_avail(sb)) { + die("this should not happen, your snprintf is broken"); + } + } + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, + void *context) +{ + for (;;) { + const char *percent; + size_t consumed; + + percent = strchrnul(format, '%'); + strbuf_add(sb, format, percent - format); + if (!*percent) + break; + format = percent + 1; + + consumed = fn(sb, format, context); + if (consumed) + format += consumed; + else + strbuf_addch(sb, '%'); + } +} + +size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, + void *context) +{ + struct strbuf_expand_dict_entry *e = context; + size_t len; + + for (; e->placeholder && (len = strlen(e->placeholder)); e++) { + if (!strncmp(placeholder, e->placeholder, len)) { + if (e->value) + strbuf_addstr(sb, e->value); + return len; + } + } + return 0; +} + +size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) +{ + size_t res; + size_t oldalloc = sb->alloc; + + strbuf_grow(sb, size); + res = fread(sb->buf + sb->len, 1, size, f); + if (res > 0) + strbuf_setlen(sb, sb->len + res); + else if (res < 0 && oldalloc == 0) + strbuf_release(sb); + return res; +} + +ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) +{ + size_t oldlen = sb->len; + size_t oldalloc = sb->alloc; + + strbuf_grow(sb, hint ? hint : 8192); + for (;;) { + ssize_t cnt; + + cnt = read(fd, sb->buf + sb->len, sb->alloc - sb->len - 1); + if (cnt < 0) { + if (oldalloc == 0) + strbuf_release(sb); + else + strbuf_setlen(sb, oldlen); + return -1; + } + if (!cnt) + break; + sb->len += cnt; + strbuf_grow(sb, 8192); + } + + sb->buf[sb->len] = '\0'; + return sb->len - oldlen; +} + +#define STRBUF_MAXLINK (2*PATH_MAX) + +int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint) +{ + size_t oldalloc = sb->alloc; + + if (hint < 32) + hint = 32; + + while (hint < STRBUF_MAXLINK) { + int len; + + strbuf_grow(sb, hint); + len = readlink(path, sb->buf, hint); + if (len < 0) { + if (errno != ERANGE) + break; + } else if (len < hint) { + strbuf_setlen(sb, len); + return 0; + } + + /* .. the buffer was too small - try again */ + hint *= 2; + } + if (oldalloc == 0) + strbuf_release(sb); + return -1; +} + +int strbuf_getline(struct strbuf *sb, FILE *fp, int term) +{ + int ch; + + strbuf_grow(sb, 0); + if (feof(fp)) + return EOF; + + strbuf_reset(sb); + while ((ch = fgetc(fp)) != EOF) { + if (ch == term) + break; + strbuf_grow(sb, 1); + sb->buf[sb->len++] = ch; + } + if (ch == EOF && sb->len == 0) + return EOF; + + sb->buf[sb->len] = '\0'; + return 0; +} + +int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint) +{ + int fd, len; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -1; + len = strbuf_read(sb, fd, hint); + close(fd); + if (len < 0) + return -1; + + return len; +} diff --git a/trunk/tools/perf/util/strbuf.h b/trunk/tools/perf/util/strbuf.h new file mode 100644 index 000000000000..9ee908a3ec5d --- /dev/null +++ b/trunk/tools/perf/util/strbuf.h @@ -0,0 +1,137 @@ +#ifndef STRBUF_H +#define STRBUF_H + +/* + * Strbuf's can be use in many ways: as a byte array, or to store arbitrary + * long, overflow safe strings. + * + * Strbufs has some invariants that are very important to keep in mind: + * + * 1. the ->buf member is always malloc-ed, hence strbuf's can be used to + * build complex strings/buffers whose final size isn't easily known. + * + * It is NOT legal to copy the ->buf pointer away. + * `strbuf_detach' is the operation that detachs a buffer from its shell + * while keeping the shell valid wrt its invariants. + * + * 2. the ->buf member is a byte array that has at least ->len + 1 bytes + * allocated. The extra byte is used to store a '\0', allowing the ->buf + * member to be a valid C-string. Every strbuf function ensure this + * invariant is preserved. + * + * Note that it is OK to "play" with the buffer directly if you work it + * that way: + * + * strbuf_grow(sb, SOME_SIZE); + * ... Here, the memory array starting at sb->buf, and of length + * ... strbuf_avail(sb) is all yours, and you are sure that + * ... strbuf_avail(sb) is at least SOME_SIZE. + * strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE); + * + * Of course, SOME_OTHER_SIZE must be smaller or equal to strbuf_avail(sb). + * + * Doing so is safe, though if it has to be done in many places, adding the + * missing API to the strbuf module is the way to go. + * + * XXX: do _not_ assume that the area that is yours is of size ->alloc - 1 + * even if it's true in the current implementation. Alloc is somehow a + * "private" member that should not be messed with. + */ + +#include + +extern char strbuf_slopbuf[]; +struct strbuf { + size_t alloc; + size_t len; + char *buf; +}; + +#define STRBUF_INIT { 0, 0, strbuf_slopbuf } + +/*----- strbuf life cycle -----*/ +extern void strbuf_init(struct strbuf *, size_t); +extern void strbuf_release(struct strbuf *); +extern char *strbuf_detach(struct strbuf *, size_t *); +extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); +static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) { + struct strbuf tmp = *a; + *a = *b; + *b = tmp; +} + +/*----- strbuf size related -----*/ +static inline size_t strbuf_avail(const struct strbuf *sb) { + return sb->alloc ? sb->alloc - sb->len - 1 : 0; +} + +extern void strbuf_grow(struct strbuf *, size_t); + +static inline void strbuf_setlen(struct strbuf *sb, size_t len) { + if (!sb->alloc) + strbuf_grow(sb, 0); + assert(len < sb->alloc); + sb->len = len; + sb->buf[len] = '\0'; +} +#define strbuf_reset(sb) strbuf_setlen(sb, 0) + +/*----- content related -----*/ +extern void strbuf_trim(struct strbuf *); +extern void strbuf_rtrim(struct strbuf *); +extern void strbuf_ltrim(struct strbuf *); +extern int strbuf_cmp(const struct strbuf *, const struct strbuf *); +extern void strbuf_tolower(struct strbuf *); + +extern struct strbuf **strbuf_split(const struct strbuf *, int delim); +extern void strbuf_list_free(struct strbuf **); + +/*----- add data in your buffer -----*/ +static inline void strbuf_addch(struct strbuf *sb, int c) { + strbuf_grow(sb, 1); + sb->buf[sb->len++] = c; + sb->buf[sb->len] = '\0'; +} + +extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t); +extern void strbuf_remove(struct strbuf *, size_t pos, size_t len); + +/* splice pos..pos+len with given data */ +extern void strbuf_splice(struct strbuf *, size_t pos, size_t len, + const void *, size_t); + +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)); +} +static inline void strbuf_addbuf(struct strbuf *sb, const struct strbuf *sb2) { + strbuf_add(sb, sb2->buf, sb2->len); +} +extern void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len); + +typedef size_t (*expand_fn_t) (struct strbuf *sb, const char *placeholder, void *context); +extern void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, void *context); +struct strbuf_expand_dict_entry { + const char *placeholder; + const char *value; +}; +extern size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, void *context); + +__attribute__((format(printf,2,3))) +extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); + +extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); +/* XXX: if read fails, any partial read is undone */ +extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); +extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint); +extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint); + +extern int strbuf_getline(struct strbuf *, FILE *, int); + +extern void stripspace(struct strbuf *buf, int skip_comments); +extern int launch_editor(const char *path, struct strbuf *buffer, const char *const *env); + +extern int strbuf_branchname(struct strbuf *sb, const char *name); +extern int strbuf_check_branch_ref(struct strbuf *sb, const char *name); + +#endif /* STRBUF_H */ diff --git a/trunk/tools/perf/util/string.c b/trunk/tools/perf/util/string.c new file mode 100644 index 000000000000..ec33c0c7f4e2 --- /dev/null +++ b/trunk/tools/perf/util/string.c @@ -0,0 +1,34 @@ +#include "string.h" + +static int hex(char ch) +{ + if ((ch >= '0') && (ch <= '9')) + return ch - '0'; + if ((ch >= 'a') && (ch <= 'f')) + return ch - 'a' + 10; + if ((ch >= 'A') && (ch <= 'F')) + return ch - 'A' + 10; + return -1; +} + +/* + * While we find nice hex chars, build a long_val. + * Return number of chars processed. + */ +int hex2u64(const char *ptr, __u64 *long_val) +{ + const char *p = ptr; + *long_val = 0; + + while (*p) { + const int hex_val = hex(*p); + + if (hex_val < 0) + break; + + *long_val = (*long_val << 4) | hex_val; + p++; + } + + return p - ptr; +} diff --git a/trunk/tools/perf/util/string.h b/trunk/tools/perf/util/string.h new file mode 100644 index 000000000000..72812c1c9a7a --- /dev/null +++ b/trunk/tools/perf/util/string.h @@ -0,0 +1,8 @@ +#ifndef _PERF_STRING_H_ +#define _PERF_STRING_H_ + +#include + +int hex2u64(const char *ptr, __u64 *val); + +#endif diff --git a/trunk/tools/perf/util/symbol.c b/trunk/tools/perf/util/symbol.c new file mode 100644 index 000000000000..49a55f813712 --- /dev/null +++ b/trunk/tools/perf/util/symbol.c @@ -0,0 +1,641 @@ +#include "util.h" +#include "../perf.h" +#include "string.h" +#include "symbol.h" + +#include +#include +#include + +const char *sym_hist_filter; + +static struct symbol *symbol__new(__u64 start, __u64 len, + const char *name, unsigned int priv_size, + __u64 obj_start, int verbose) +{ + size_t namelen = strlen(name) + 1; + struct symbol *self = calloc(1, priv_size + sizeof(*self) + namelen); + + if (!self) + return NULL; + + if (verbose >= 2) + printf("new symbol: %016Lx [%08lx]: %s, hist: %p, obj_start: %p\n", + (__u64)start, (unsigned long)len, name, self->hist, (void *)(unsigned long)obj_start); + + self->obj_start= obj_start; + self->hist = NULL; + self->hist_sum = 0; + + if (sym_hist_filter && !strcmp(name, sym_hist_filter)) + self->hist = calloc(sizeof(__u64), len); + + if (priv_size) { + memset(self, 0, priv_size); + self = ((void *)self) + priv_size; + } + self->start = start; + self->end = start + len - 1; + memcpy(self->name, name, namelen); + + return self; +} + +static void symbol__delete(struct symbol *self, unsigned int priv_size) +{ + free(((void *)self) - priv_size); +} + +static size_t symbol__fprintf(struct symbol *self, FILE *fp) +{ + return fprintf(fp, " %llx-%llx %s\n", + self->start, self->end, self->name); +} + +struct dso *dso__new(const char *name, unsigned int sym_priv_size) +{ + struct dso *self = malloc(sizeof(*self) + strlen(name) + 1); + + if (self != NULL) { + strcpy(self->name, name); + self->syms = RB_ROOT; + self->sym_priv_size = sym_priv_size; + self->find_symbol = dso__find_symbol; + } + + return self; +} + +static void dso__delete_symbols(struct dso *self) +{ + struct symbol *pos; + struct rb_node *next = rb_first(&self->syms); + + while (next) { + pos = rb_entry(next, struct symbol, rb_node); + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, &self->syms); + symbol__delete(pos, self->sym_priv_size); + } +} + +void dso__delete(struct dso *self) +{ + dso__delete_symbols(self); + free(self); +} + +static void dso__insert_symbol(struct dso *self, struct symbol *sym) +{ + struct rb_node **p = &self->syms.rb_node; + struct rb_node *parent = NULL; + const __u64 ip = sym->start; + struct symbol *s; + + while (*p != NULL) { + parent = *p; + s = rb_entry(parent, struct symbol, rb_node); + if (ip < s->start) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&sym->rb_node, parent, p); + rb_insert_color(&sym->rb_node, &self->syms); +} + +struct symbol *dso__find_symbol(struct dso *self, __u64 ip) +{ + struct rb_node *n; + + if (self == NULL) + return NULL; + + n = self->syms.rb_node; + + while (n) { + struct symbol *s = rb_entry(n, struct symbol, rb_node); + + if (ip < s->start) + n = n->rb_left; + else if (ip > s->end) + n = n->rb_right; + else + return s; + } + + return NULL; +} + +size_t dso__fprintf(struct dso *self, FILE *fp) +{ + size_t ret = fprintf(fp, "dso: %s\n", self->name); + + struct rb_node *nd; + for (nd = rb_first(&self->syms); nd; nd = rb_next(nd)) { + struct symbol *pos = rb_entry(nd, struct symbol, rb_node); + ret += symbol__fprintf(pos, fp); + } + + return ret; +} + +static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int verbose) +{ + struct rb_node *nd, *prevnd; + char *line = NULL; + size_t n; + FILE *file = fopen("/proc/kallsyms", "r"); + + if (file == NULL) + goto out_failure; + + while (!feof(file)) { + __u64 start; + struct symbol *sym; + int line_len, len; + char symbol_type; + + line_len = getline(&line, &n, file); + if (line_len < 0) + break; + + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + len = hex2u64(line, &start); + + len++; + if (len + 2 >= line_len) + continue; + + symbol_type = toupper(line[len]); + /* + * We're interested only in code ('T'ext) + */ + if (symbol_type != 'T' && symbol_type != 'W') + continue; + /* + * Well fix up the end later, when we have all sorted. + */ + sym = symbol__new(start, 0xdead, line + len + 2, + self->sym_priv_size, 0, verbose); + + if (sym == NULL) + goto out_delete_line; + + if (filter && filter(self, sym)) + symbol__delete(sym, self->sym_priv_size); + else + dso__insert_symbol(self, sym); + } + + /* + * Now that we have all sorted out, just set the ->end of all + * symbols + */ + prevnd = rb_first(&self->syms); + + if (prevnd == NULL) + goto out_delete_line; + + for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) { + struct symbol *prev = rb_entry(prevnd, struct symbol, rb_node), + *curr = rb_entry(nd, struct symbol, rb_node); + + prev->end = curr->start - 1; + prevnd = nd; + } + + free(line); + fclose(file); + + return 0; + +out_delete_line: + free(line); +out_failure: + return -1; +} + +static int dso__load_perf_map(struct dso *self, symbol_filter_t filter, int verbose) +{ + char *line = NULL; + size_t n; + FILE *file; + int nr_syms = 0; + + file = fopen(self->name, "r"); + if (file == NULL) + goto out_failure; + + while (!feof(file)) { + __u64 start, size; + struct symbol *sym; + int line_len, len; + + line_len = getline(&line, &n, file); + if (line_len < 0) + break; + + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + len = hex2u64(line, &start); + + len++; + if (len + 2 >= line_len) + continue; + + len += hex2u64(line + len, &size); + + len++; + if (len + 2 >= line_len) + continue; + + sym = symbol__new(start, size, line + len, + self->sym_priv_size, start, verbose); + + if (sym == NULL) + goto out_delete_line; + + if (filter && filter(self, sym)) + symbol__delete(sym, self->sym_priv_size); + else { + dso__insert_symbol(self, sym); + nr_syms++; + } + } + + free(line); + fclose(file); + + return nr_syms; + +out_delete_line: + free(line); +out_failure: + return -1; +} + +/** + * elf_symtab__for_each_symbol - iterate thru all the symbols + * + * @self: struct elf_symtab instance to iterate + * @index: uint32_t index + * @sym: GElf_Sym iterator + */ +#define elf_symtab__for_each_symbol(syms, nr_syms, index, sym) \ + for (index = 0, gelf_getsym(syms, index, &sym);\ + index < nr_syms; \ + index++, gelf_getsym(syms, index, &sym)) + +static inline uint8_t elf_sym__type(const GElf_Sym *sym) +{ + return GELF_ST_TYPE(sym->st_info); +} + +static inline int elf_sym__is_function(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_FUNC && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF && + sym->st_size != 0; +} + +static inline const char *elf_sym__name(const GElf_Sym *sym, + const Elf_Data *symstrs) +{ + return symstrs->d_buf + sym->st_name; +} + +static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, + GElf_Shdr *shp, const char *name, + size_t *index) +{ + Elf_Scn *sec = NULL; + size_t cnt = 1; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + char *str; + + gelf_getshdr(sec, shp); + str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); + if (!strcmp(name, str)) { + if (index) + *index = cnt; + break; + } + ++cnt; + } + + return sec; +} + +#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrel(reldata, idx, &pos_mem)) + +#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrela(reldata, idx, &pos_mem)) + +static int dso__synthesize_plt_symbols(struct dso *self, Elf *elf, + GElf_Ehdr *ehdr, Elf_Scn *scn_dynsym, + GElf_Shdr *shdr_dynsym, + size_t dynsym_idx, int verbose) +{ + uint32_t nr_rel_entries, idx; + GElf_Sym sym; + __u64 plt_offset; + GElf_Shdr shdr_plt; + struct symbol *f; + GElf_Shdr shdr_rel_plt; + Elf_Data *reldata, *syms, *symstrs; + Elf_Scn *scn_plt_rel, *scn_symstrs; + char sympltname[1024]; + int nr = 0, symidx; + + scn_plt_rel = elf_section_by_name(elf, ehdr, &shdr_rel_plt, + ".rela.plt", NULL); + if (scn_plt_rel == NULL) { + scn_plt_rel = elf_section_by_name(elf, ehdr, &shdr_rel_plt, + ".rel.plt", NULL); + if (scn_plt_rel == NULL) + return 0; + } + + if (shdr_rel_plt.sh_link != dynsym_idx) + return 0; + + if (elf_section_by_name(elf, ehdr, &shdr_plt, ".plt", NULL) == NULL) + return 0; + + /* + * Fetch the relocation section to find the indexes to the GOT + * and the symbols in the .dynsym they refer to. + */ + reldata = elf_getdata(scn_plt_rel, NULL); + if (reldata == NULL) + return -1; + + syms = elf_getdata(scn_dynsym, NULL); + if (syms == NULL) + return -1; + + scn_symstrs = elf_getscn(elf, shdr_dynsym->sh_link); + if (scn_symstrs == NULL) + return -1; + + symstrs = elf_getdata(scn_symstrs, NULL); + if (symstrs == NULL) + return -1; + + nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; + plt_offset = shdr_plt.sh_offset; + + if (shdr_rel_plt.sh_type == SHT_RELA) { + GElf_Rela pos_mem, *pos; + + elf_section__for_each_rela(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + sympltname, self->sym_priv_size, 0, verbose); + if (!f) + return -1; + + dso__insert_symbol(self, f); + ++nr; + } + } else if (shdr_rel_plt.sh_type == SHT_REL) { + GElf_Rel pos_mem, *pos; + elf_section__for_each_rel(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + sympltname, self->sym_priv_size, 0, verbose); + if (!f) + return -1; + + dso__insert_symbol(self, f); + ++nr; + } + } else { + /* + * TODO: There are still one more shdr_rel_plt.sh_type + * I have to investigate, but probably should be ignored. + */ + } + + return nr; +} + +static int dso__load_sym(struct dso *self, int fd, const char *name, + symbol_filter_t filter, int verbose) +{ + Elf_Data *symstrs; + uint32_t nr_syms; + int err = -1; + uint32_t index; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *syms; + GElf_Sym sym; + Elf_Scn *sec, *sec_dynsym; + Elf *elf; + size_t dynsym_idx; + int nr = 0; + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + if (verbose) + fprintf(stderr, "%s: cannot read %s ELF file.\n", + __func__, name); + goto out_close; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) { + if (verbose) + fprintf(stderr, "%s: cannot get elf header.\n", __func__); + goto out_elf_end; + } + + /* + * We need to check if we have a .dynsym, so that we can handle the + * .plt, synthesizing its symbols, that aren't on the symtabs (be it + * .dynsym or .symtab) + */ + sec_dynsym = elf_section_by_name(elf, &ehdr, &shdr, + ".dynsym", &dynsym_idx); + if (sec_dynsym != NULL) { + nr = dso__synthesize_plt_symbols(self, elf, &ehdr, + sec_dynsym, &shdr, + dynsym_idx, verbose); + if (nr < 0) + goto out_elf_end; + } + + /* + * But if we have a full .symtab (that is a superset of .dynsym) we + * should add the symbols not in the .dynsyn + */ + sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL); + if (sec == NULL) { + if (sec_dynsym == NULL) + goto out_elf_end; + + sec = sec_dynsym; + gelf_getshdr(sec, &shdr); + } + + syms = elf_getdata(sec, NULL); + if (syms == NULL) + goto out_elf_end; + + sec = elf_getscn(elf, shdr.sh_link); + if (sec == NULL) + goto out_elf_end; + + symstrs = elf_getdata(sec, NULL); + if (symstrs == NULL) + goto out_elf_end; + + nr_syms = shdr.sh_size / shdr.sh_entsize; + + memset(&sym, 0, sizeof(sym)); + + elf_symtab__for_each_symbol(syms, nr_syms, index, sym) { + struct symbol *f; + __u64 obj_start; + + if (!elf_sym__is_function(&sym)) + continue; + + sec = elf_getscn(elf, sym.st_shndx); + if (!sec) + goto out_elf_end; + + gelf_getshdr(sec, &shdr); + obj_start = sym.st_value; + + sym.st_value -= shdr.sh_addr - shdr.sh_offset; + + f = symbol__new(sym.st_value, sym.st_size, + elf_sym__name(&sym, symstrs), + self->sym_priv_size, obj_start, verbose); + if (!f) + goto out_elf_end; + + if (filter && filter(self, f)) + symbol__delete(f, self->sym_priv_size); + else { + dso__insert_symbol(self, f); + nr++; + } + } + + err = nr; +out_elf_end: + elf_end(elf); +out_close: + return err; +} + +int dso__load(struct dso *self, symbol_filter_t filter, int verbose) +{ + int size = strlen(self->name) + sizeof("/usr/lib/debug%s.debug"); + char *name = malloc(size); + int variant = 0; + int ret = -1; + int fd; + + if (!name) + return -1; + + if (strncmp(self->name, "/tmp/perf-", 10) == 0) + return dso__load_perf_map(self, filter, verbose); + +more: + do { + switch (variant) { + case 0: /* Fedora */ + snprintf(name, size, "/usr/lib/debug%s.debug", self->name); + break; + case 1: /* Ubuntu */ + snprintf(name, size, "/usr/lib/debug%s", self->name); + break; + case 2: /* Sane people */ + snprintf(name, size, "%s", self->name); + break; + + default: + goto out; + } + variant++; + + fd = open(name, O_RDONLY); + } while (fd < 0); + + ret = dso__load_sym(self, fd, name, filter, verbose); + close(fd); + + /* + * Some people seem to have debuginfo files _WITHOUT_ debug info!?!? + */ + if (!ret) + goto more; + +out: + free(name); + return ret; +} + +static int dso__load_vmlinux(struct dso *self, const char *vmlinux, + symbol_filter_t filter, int verbose) +{ + int err, fd = open(vmlinux, O_RDONLY); + + if (fd < 0) + return -1; + + err = dso__load_sym(self, fd, vmlinux, filter, verbose); + close(fd); + + return err; +} + +int dso__load_kernel(struct dso *self, const char *vmlinux, + symbol_filter_t filter, int verbose) +{ + int err = -1; + + if (vmlinux) + err = dso__load_vmlinux(self, vmlinux, filter, verbose); + + if (err) + err = dso__load_kallsyms(self, filter, verbose); + + return err; +} + +void symbol__init(void) +{ + elf_version(EV_CURRENT); +} diff --git a/trunk/tools/perf/util/symbol.h b/trunk/tools/perf/util/symbol.h new file mode 100644 index 000000000000..0d1292bd8270 --- /dev/null +++ b/trunk/tools/perf/util/symbol.h @@ -0,0 +1,47 @@ +#ifndef _PERF_SYMBOL_ +#define _PERF_SYMBOL_ 1 + +#include +#include "list.h" +#include "rbtree.h" + +struct symbol { + struct rb_node rb_node; + __u64 start; + __u64 end; + __u64 obj_start; + __u64 hist_sum; + __u64 *hist; + char name[0]; +}; + +struct dso { + struct list_head node; + struct rb_root syms; + unsigned int sym_priv_size; + struct symbol *(*find_symbol)(struct dso *, __u64 ip); + char name[0]; +}; + +const char *sym_hist_filter; + +typedef int (*symbol_filter_t)(struct dso *self, struct symbol *sym); + +struct dso *dso__new(const char *name, unsigned int sym_priv_size); +void dso__delete(struct dso *self); + +static inline void *dso__sym_priv(struct dso *self, struct symbol *sym) +{ + return ((void *)sym) - self->sym_priv_size; +} + +struct symbol *dso__find_symbol(struct dso *self, __u64 ip); + +int dso__load_kernel(struct dso *self, const char *vmlinux, + symbol_filter_t filter, int verbose); +int dso__load(struct dso *self, symbol_filter_t filter, int verbose); + +size_t dso__fprintf(struct dso *self, FILE *fp); + +void symbol__init(void); +#endif /* _PERF_SYMBOL_ */ diff --git a/trunk/tools/perf/util/usage.c b/trunk/tools/perf/util/usage.c new file mode 100644 index 000000000000..e16bf9a707e8 --- /dev/null +++ b/trunk/tools/perf/util/usage.c @@ -0,0 +1,80 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ +#include "util.h" + +static void report(const char *prefix, const char *err, va_list params) +{ + char msg[1024]; + vsnprintf(msg, sizeof(msg), err, params); + fprintf(stderr, " %s%s\n", prefix, msg); +} + +static NORETURN void usage_builtin(const char *err) +{ + fprintf(stderr, "\n Usage: %s\n", err); + exit(129); +} + +static NORETURN void die_builtin(const char *err, va_list params) +{ + report(" Fatal: ", err, params); + exit(128); +} + +static void error_builtin(const char *err, va_list params) +{ + report(" Error: ", err, params); +} + +static void warn_builtin(const char *warn, va_list params) +{ + report(" Warning: ", warn, params); +} + +/* If we are in a dlopen()ed .so write to a global variable would segfault + * (ugh), so keep things static. */ +static void (*usage_routine)(const char *err) NORETURN = usage_builtin; +static void (*die_routine)(const char *err, va_list params) NORETURN = die_builtin; +static void (*error_routine)(const char *err, va_list params) = error_builtin; +static void (*warn_routine)(const char *err, va_list params) = warn_builtin; + +void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN) +{ + die_routine = routine; +} + +void usage(const char *err) +{ + usage_routine(err); +} + +void die(const char *err, ...) +{ + va_list params; + + va_start(params, err); + die_routine(err, params); + va_end(params); +} + +int error(const char *err, ...) +{ + va_list params; + + va_start(params, err); + error_routine(err, params); + va_end(params); + return -1; +} + +void warning(const char *warn, ...) +{ + va_list params; + + va_start(params, warn); + warn_routine(warn, params); + va_end(params); +} diff --git a/trunk/tools/perf/util/util.h b/trunk/tools/perf/util/util.h new file mode 100644 index 000000000000..76590a16c271 --- /dev/null +++ b/trunk/tools/perf/util/util.h @@ -0,0 +1,410 @@ +#ifndef GIT_COMPAT_UTIL_H +#define GIT_COMPAT_UTIL_H + +#define _FILE_OFFSET_BITS 64 + +#ifndef FLEX_ARRAY +/* + * See if our compiler is known to support flexible array members. + */ +#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) +# define FLEX_ARRAY /* empty */ +#elif defined(__GNUC__) +# if (__GNUC__ >= 3) +# define FLEX_ARRAY /* empty */ +# else +# define FLEX_ARRAY 0 /* older GNU extension */ +# endif +#endif + +/* + * Otherwise, default to safer but a bit wasteful traditional style + */ +#ifndef FLEX_ARRAY +# define FLEX_ARRAY 1 +#endif +#endif + +#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) + +#ifdef __GNUC__ +#define TYPEOF(x) (__typeof__(x)) +#else +#define TYPEOF(x) +#endif + +#define MSB(x, bits) ((x) & TYPEOF(x)(~0ULL << (sizeof(x) * 8 - (bits)))) +#define HAS_MULTI_BITS(i) ((i) & ((i) - 1)) /* checks if an integer has more than 1 bit set */ + +/* Approximation of the length of the decimal representation of this type. */ +#define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1) + +#if !defined(__APPLE__) && !defined(__FreeBSD__) && !defined(__USLC__) && !defined(_M_UNIX) +#define _XOPEN_SOURCE 600 /* glibc2 and AIX 5.3L need 500, OpenBSD needs 600 for S_ISLNK() */ +#define _XOPEN_SOURCE_EXTENDED 1 /* AIX 5.3L needs this */ +#endif +#define _ALL_SOURCE 1 +#define _GNU_SOURCE 1 +#define _BSD_SOURCE 1 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#ifndef __MINGW32__ +#include +#include +#include +#include +#ifndef NO_SYS_SELECT_H +#include +#endif +#include +#include +#include +#include +#include +#include +#if defined(__CYGWIN__) +#undef _XOPEN_SOURCE +#include +#define _XOPEN_SOURCE 600 +#include "compat/cygwin.h" +#else +#undef _ALL_SOURCE /* AIX 5.3L defines a struct list with _ALL_SOURCE. */ +#include +#define _ALL_SOURCE 1 +#endif +#else /* __MINGW32__ */ +/* pull in Windows compatibility stuff */ +#include "compat/mingw.h" +#endif /* __MINGW32__ */ + +#ifndef NO_ICONV +#include +#endif + +#ifndef NO_OPENSSL +#include +#include +#endif + +/* On most systems would have given us this, but + * not on some systems (e.g. GNU/Hurd). + */ +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +#ifndef PRIuMAX +#define PRIuMAX "llu" +#endif + +#ifndef PRIu32 +#define PRIu32 "u" +#endif + +#ifndef PRIx32 +#define PRIx32 "x" +#endif + +#ifndef PATH_SEP +#define PATH_SEP ':' +#endif + +#ifndef STRIP_EXTENSION +#define STRIP_EXTENSION "" +#endif + +#ifndef has_dos_drive_prefix +#define has_dos_drive_prefix(path) 0 +#endif + +#ifndef is_dir_sep +#define is_dir_sep(c) ((c) == '/') +#endif + +#ifdef __GNUC__ +#define NORETURN __attribute__((__noreturn__)) +#else +#define NORETURN +#ifndef __attribute__ +#define __attribute__(x) +#endif +#endif + +/* General helper functions */ +extern void usage(const char *err) NORETURN; +extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); +extern int error(const char *err, ...) __attribute__((format (printf, 1, 2))); +extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); + +extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); + +extern int prefixcmp(const char *str, const char *prefix); +extern time_t tm_to_time_t(const struct tm *tm); + +static inline const char *skip_prefix(const char *str, const char *prefix) +{ + size_t len = strlen(prefix); + return strncmp(str, prefix, len) ? NULL : str + len; +} + +#if defined(NO_MMAP) || defined(USE_WIN32_MMAP) + +#ifndef PROT_READ +#define PROT_READ 1 +#define PROT_WRITE 2 +#define MAP_PRIVATE 1 +#define MAP_FAILED ((void*)-1) +#endif + +#define mmap git_mmap +#define munmap git_munmap +extern void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset); +extern int git_munmap(void *start, size_t length); + +#else /* NO_MMAP || USE_WIN32_MMAP */ + +#include + +#endif /* NO_MMAP || USE_WIN32_MMAP */ + +#ifdef NO_MMAP + +/* This value must be multiple of (pagesize * 2) */ +#define DEFAULT_PACKED_GIT_WINDOW_SIZE (1 * 1024 * 1024) + +#else /* NO_MMAP */ + +/* This value must be multiple of (pagesize * 2) */ +#define DEFAULT_PACKED_GIT_WINDOW_SIZE \ + (sizeof(void*) >= 8 \ + ? 1 * 1024 * 1024 * 1024 \ + : 32 * 1024 * 1024) + +#endif /* NO_MMAP */ + +#ifdef NO_ST_BLOCKS_IN_STRUCT_STAT +#define on_disk_bytes(st) ((st).st_size) +#else +#define on_disk_bytes(st) ((st).st_blocks * 512) +#endif + +#define DEFAULT_PACKED_GIT_LIMIT \ + ((1024L * 1024L) * (sizeof(void*) >= 8 ? 8192 : 256)) + +#ifdef NO_PREAD +#define pread git_pread +extern ssize_t git_pread(int fd, void *buf, size_t count, off_t offset); +#endif +/* + * Forward decl that will remind us if its twin in cache.h changes. + * This function is used in compat/pread.c. But we can't include + * cache.h there. + */ +extern ssize_t read_in_full(int fd, void *buf, size_t count); + +#ifdef NO_SETENV +#define setenv gitsetenv +extern int gitsetenv(const char *, const char *, int); +#endif + +#ifdef NO_MKDTEMP +#define mkdtemp gitmkdtemp +extern char *gitmkdtemp(char *); +#endif + +#ifdef NO_UNSETENV +#define unsetenv gitunsetenv +extern void gitunsetenv(const char *); +#endif + +#ifdef NO_STRCASESTR +#define strcasestr gitstrcasestr +extern char *gitstrcasestr(const char *haystack, const char *needle); +#endif + +#ifdef NO_STRLCPY +#define strlcpy gitstrlcpy +extern size_t gitstrlcpy(char *, const char *, size_t); +#endif + +#ifdef NO_STRTOUMAX +#define strtoumax gitstrtoumax +extern uintmax_t gitstrtoumax(const char *, char **, int); +#endif + +#ifdef NO_HSTRERROR +#define hstrerror githstrerror +extern const char *githstrerror(int herror); +#endif + +#ifdef NO_MEMMEM +#define memmem gitmemmem +void *gitmemmem(const void *haystack, size_t haystacklen, + const void *needle, size_t needlelen); +#endif + +#ifdef FREAD_READS_DIRECTORIES +#ifdef fopen +#undef fopen +#endif +#define fopen(a,b) git_fopen(a,b) +extern FILE *git_fopen(const char*, const char*); +#endif + +#ifdef SNPRINTF_RETURNS_BOGUS +#define snprintf git_snprintf +extern int git_snprintf(char *str, size_t maxsize, + const char *format, ...); +#define vsnprintf git_vsnprintf +extern int git_vsnprintf(char *str, size_t maxsize, + const char *format, va_list ap); +#endif + +#ifdef __GLIBC_PREREQ +#if __GLIBC_PREREQ(2, 1) +#define HAVE_STRCHRNUL +#endif +#endif + +#ifndef HAVE_STRCHRNUL +#define strchrnul gitstrchrnul +static inline char *gitstrchrnul(const char *s, int c) +{ + while (*s && *s != c) + s++; + return (char *)s; +} +#endif + +/* + * Wrappers: + */ +extern char *xstrdup(const char *str); +extern void *xmalloc(size_t size); +extern void *xmemdupz(const void *data, size_t len); +extern char *xstrndup(const char *str, size_t len); +extern void *xrealloc(void *ptr, size_t size); +extern void *xcalloc(size_t nmemb, size_t size); +extern void *xmmap(void *start, size_t length, int prot, int flags, int fd, off_t offset); +extern ssize_t xread(int fd, void *buf, size_t len); +extern ssize_t xwrite(int fd, const void *buf, size_t len); +extern int xdup(int fd); +extern FILE *xfdopen(int fd, const char *mode); +extern int xmkstemp(char *template); + +static inline size_t xsize_t(off_t len) +{ + return (size_t)len; +} + +static inline int has_extension(const char *filename, const char *ext) +{ + size_t len = strlen(filename); + size_t extlen = strlen(ext); + return len > extlen && !memcmp(filename + len - extlen, ext, extlen); +} + +/* Sane ctype - no locale, and works with signed chars */ +#undef isascii +#undef isspace +#undef isdigit +#undef isalpha +#undef isalnum +#undef tolower +#undef toupper +extern unsigned char sane_ctype[256]; +#define GIT_SPACE 0x01 +#define GIT_DIGIT 0x02 +#define GIT_ALPHA 0x04 +#define GIT_GLOB_SPECIAL 0x08 +#define GIT_REGEX_SPECIAL 0x10 +#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) +#define isascii(x) (((x) & ~0x7f) == 0) +#define isspace(x) sane_istest(x,GIT_SPACE) +#define isdigit(x) sane_istest(x,GIT_DIGIT) +#define isalpha(x) sane_istest(x,GIT_ALPHA) +#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) +#define is_glob_special(x) sane_istest(x,GIT_GLOB_SPECIAL) +#define is_regex_special(x) sane_istest(x,GIT_GLOB_SPECIAL | GIT_REGEX_SPECIAL) +#define tolower(x) sane_case((unsigned char)(x), 0x20) +#define toupper(x) sane_case((unsigned char)(x), 0) + +static inline int sane_case(int x, int high) +{ + if (sane_istest(x, GIT_ALPHA)) + x = (x & ~0x20) | high; + return x; +} + +static inline int strtoul_ui(char const *s, int base, unsigned int *result) +{ + unsigned long ul; + char *p; + + errno = 0; + ul = strtoul(s, &p, base); + if (errno || *p || p == s || (unsigned int) ul != ul) + return -1; + *result = ul; + return 0; +} + +static inline int strtol_i(char const *s, int base, int *result) +{ + long ul; + char *p; + + errno = 0; + ul = strtol(s, &p, base); + if (errno || *p || p == s || (int) ul != ul) + return -1; + *result = ul; + return 0; +} + +#ifdef INTERNAL_QSORT +void git_qsort(void *base, size_t nmemb, size_t size, + int(*compar)(const void *, const void *)); +#define qsort git_qsort +#endif + +#ifndef DIR_HAS_BSD_GROUP_SEMANTICS +# define FORCE_DIR_SET_GID S_ISGID +#else +# define FORCE_DIR_SET_GID 0 +#endif + +#ifdef NO_NSEC +#undef USE_NSEC +#define ST_CTIME_NSEC(st) 0 +#define ST_MTIME_NSEC(st) 0 +#else +#ifdef USE_ST_TIMESPEC +#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec)) +#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec)) +#else +#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec)) +#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec)) +#endif +#endif + +#endif diff --git a/trunk/tools/perf/util/wrapper.c b/trunk/tools/perf/util/wrapper.c new file mode 100644 index 000000000000..6350d65f6d9e --- /dev/null +++ b/trunk/tools/perf/util/wrapper.c @@ -0,0 +1,206 @@ +/* + * Various trivial helper wrappers around standard functions + */ +#include "cache.h" + +/* + * There's no pack memory to release - but stay close to the Git + * version so wrap this away: + */ +static inline void release_pack_memory(size_t size, int flag) +{ +} + +char *xstrdup(const char *str) +{ + char *ret = strdup(str); + if (!ret) { + release_pack_memory(strlen(str) + 1, -1); + ret = strdup(str); + if (!ret) + die("Out of memory, strdup failed"); + } + return ret; +} + +void *xmalloc(size_t size) +{ + void *ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) { + release_pack_memory(size, -1); + ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) + die("Out of memory, malloc failed"); + } +#ifdef XMALLOC_POISON + memset(ret, 0xA5, size); +#endif + return ret; +} + +/* + * xmemdupz() allocates (len + 1) bytes of memory, duplicates "len" bytes of + * "data" to the allocated memory, zero terminates the allocated memory, + * and returns a pointer to the allocated memory. If the allocation fails, + * the program dies. + */ +void *xmemdupz(const void *data, size_t len) +{ + char *p = xmalloc(len + 1); + memcpy(p, data, len); + p[len] = '\0'; + return p; +} + +char *xstrndup(const char *str, size_t len) +{ + char *p = memchr(str, '\0', len); + return xmemdupz(str, p ? p - str : len); +} + +void *xrealloc(void *ptr, size_t size) +{ + void *ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) { + release_pack_memory(size, -1); + ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) + die("Out of memory, realloc failed"); + } + return ret; +} + +void *xcalloc(size_t nmemb, size_t size) +{ + void *ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) { + release_pack_memory(nmemb * size, -1); + ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) + die("Out of memory, calloc failed"); + } + return ret; +} + +void *xmmap(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) { + if (!length) + return NULL; + release_pack_memory(length, fd); + ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) + die("Out of memory? mmap failed: %s", strerror(errno)); + } + return ret; +} + +/* + * xread() is the same a read(), but it automatically restarts read() + * operations with a recoverable error (EAGAIN and EINTR). xread() + * DOES NOT GUARANTEE that "len" bytes is read even if the data is available. + */ +ssize_t xread(int fd, void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = read(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +/* + * xwrite() is the same a write(), but it automatically restarts write() + * operations with a recoverable error (EAGAIN and EINTR). xwrite() DOES NOT + * GUARANTEE that "len" bytes is written even if the operation is successful. + */ +ssize_t xwrite(int fd, const void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = write(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +ssize_t read_in_full(int fd, void *buf, size_t count) +{ + char *p = buf; + ssize_t total = 0; + + while (count > 0) { + ssize_t loaded = xread(fd, p, count); + if (loaded <= 0) + return total ? total : loaded; + count -= loaded; + p += loaded; + total += loaded; + } + + return total; +} + +ssize_t write_in_full(int fd, const void *buf, size_t count) +{ + const char *p = buf; + ssize_t total = 0; + + while (count > 0) { + ssize_t written = xwrite(fd, p, count); + if (written < 0) + return -1; + if (!written) { + errno = ENOSPC; + return -1; + } + count -= written; + p += written; + total += written; + } + + return total; +} + +int xdup(int fd) +{ + int ret = dup(fd); + if (ret < 0) + die("dup failed: %s", strerror(errno)); + return ret; +} + +FILE *xfdopen(int fd, const char *mode) +{ + FILE *stream = fdopen(fd, mode); + if (stream == NULL) + die("Out of memory? fdopen failed: %s", strerror(errno)); + return stream; +} + +int xmkstemp(char *template) +{ + int fd; + + fd = mkstemp(template); + if (fd < 0) + die("Unable to create temporary file: %s", strerror(errno)); + return fd; +} diff --git a/trunk/virt/kvm/ioapic.c b/trunk/virt/kvm/ioapic.c index c3b99def9cbc..1eddae94bab3 100644 --- a/trunk/virt/kvm/ioapic.c +++ b/trunk/virt/kvm/ioapic.c @@ -85,7 +85,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) { - union ioapic_redir_entry *pent; + union kvm_ioapic_redirect_entry *pent; int injected = -1; pent = &ioapic->redirtbl[idx]; @@ -142,149 +142,40 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) } } -static int ioapic_inj_irq(struct kvm_ioapic *ioapic, - struct kvm_vcpu *vcpu, - u8 vector, u8 trig_mode, u8 delivery_mode) -{ - ioapic_debug("irq %d trig %d deliv %d\n", vector, trig_mode, - delivery_mode); - - ASSERT((delivery_mode == IOAPIC_FIXED) || - (delivery_mode == IOAPIC_LOWEST_PRIORITY)); - - return kvm_apic_set_irq(vcpu, vector, trig_mode); -} - -static void ioapic_inj_nmi(struct kvm_vcpu *vcpu) -{ - kvm_inject_nmi(vcpu); - kvm_vcpu_kick(vcpu); -} - -u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest, - u8 dest_mode) -{ - u32 mask = 0; - int i; - struct kvm *kvm = ioapic->kvm; - struct kvm_vcpu *vcpu; - - ioapic_debug("dest %d dest_mode %d\n", dest, dest_mode); - - if (dest_mode == 0) { /* Physical mode. */ - if (dest == 0xFF) { /* Broadcast. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i] && kvm->vcpus[i]->arch.apic) - mask |= 1 << i; - return mask; - } - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (kvm_apic_match_physical_addr(vcpu->arch.apic, dest)) { - if (vcpu->arch.apic) - mask = 1 << i; - break; - } - } - } else if (dest != 0) /* Logical mode, MDA non-zero. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (vcpu->arch.apic && - kvm_apic_match_logical_addr(vcpu->arch.apic, dest)) - mask |= 1 << vcpu->vcpu_id; - } - ioapic_debug("mask %x\n", mask); - return mask; -} - static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) { - u8 dest = ioapic->redirtbl[irq].fields.dest_id; - u8 dest_mode = ioapic->redirtbl[irq].fields.dest_mode; - u8 delivery_mode = ioapic->redirtbl[irq].fields.delivery_mode; - u8 vector = ioapic->redirtbl[irq].fields.vector; - u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode; - u32 deliver_bitmask; - struct kvm_vcpu *vcpu; - int vcpu_id, r = -1; + union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; + struct kvm_lapic_irq irqe; ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " "vector=%x trig_mode=%x\n", - dest, dest_mode, delivery_mode, vector, trig_mode); - - deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, dest, - dest_mode); - if (!deliver_bitmask) { - ioapic_debug("no target on destination\n"); - return 0; - } + entry->fields.dest, entry->fields.dest_mode, + entry->fields.delivery_mode, entry->fields.vector, + entry->fields.trig_mode); + + irqe.dest_id = entry->fields.dest_id; + irqe.vector = entry->fields.vector; + irqe.dest_mode = entry->fields.dest_mode; + irqe.trig_mode = entry->fields.trig_mode; + irqe.delivery_mode = entry->fields.delivery_mode << 8; + irqe.level = 1; + irqe.shorthand = 0; - switch (delivery_mode) { - case IOAPIC_LOWEST_PRIORITY: - vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector, - deliver_bitmask); #ifdef CONFIG_X86 - if (irq == 0) - vcpu = ioapic->kvm->vcpus[0]; -#endif - if (vcpu != NULL) - r = ioapic_inj_irq(ioapic, vcpu, vector, - trig_mode, delivery_mode); - else - ioapic_debug("null lowest prio vcpu: " - "mask=%x vector=%x delivery_mode=%x\n", - deliver_bitmask, vector, IOAPIC_LOWEST_PRIORITY); - break; - case IOAPIC_FIXED: -#ifdef CONFIG_X86 - if (irq == 0) - deliver_bitmask = 1; -#endif - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - if (r < 0) - r = 0; - r += ioapic_inj_irq(ioapic, vcpu, vector, - trig_mode, delivery_mode); - } - } - break; - case IOAPIC_NMI: - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - ioapic_inj_nmi(vcpu); - r = 1; - } - else - ioapic_debug("NMI to vcpu %d failed\n", - vcpu->vcpu_id); - } - break; - default: - printk(KERN_WARNING "Unsupported delivery mode %d\n", - delivery_mode); - break; + /* Always delivery PIT interrupt to vcpu 0 */ + if (irq == 0) { + irqe.dest_mode = 0; /* Physical mode. */ + irqe.dest_id = ioapic->kvm->vcpus[0]->vcpu_id; } - return r; +#endif + return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe); } int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) { u32 old_irr = ioapic->irr; u32 mask = 1 << irq; - union ioapic_redir_entry entry; + union kvm_ioapic_redirect_entry entry; int ret = 1; if (irq >= 0 && irq < IOAPIC_NUM_PINS) { @@ -305,7 +196,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin, int trigger_mode) { - union ioapic_redir_entry *ent; + union kvm_ioapic_redirect_entry *ent; ent = &ioapic->redirtbl[pin]; diff --git a/trunk/virt/kvm/ioapic.h b/trunk/virt/kvm/ioapic.h index a34bd5e6436b..7080b713c160 100644 --- a/trunk/virt/kvm/ioapic.h +++ b/trunk/virt/kvm/ioapic.h @@ -40,22 +40,7 @@ struct kvm_ioapic { u32 id; u32 irr; u32 pad; - union ioapic_redir_entry { - u64 bits; - struct { - u8 vector; - u8 delivery_mode:3; - u8 dest_mode:1; - u8 delivery_status:1; - u8 polarity:1; - u8 remote_irr:1; - u8 trig_mode:1; - u8 mask:1; - u8 reserve:7; - u8 reserved[4]; - u8 dest_id; - } fields; - } redirtbl[IOAPIC_NUM_PINS]; + union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); @@ -79,13 +64,13 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } -struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, - unsigned long bitmap); +int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, int dest, int dest_mode); +int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); -u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest, - u8 dest_mode); - +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq); #endif diff --git a/trunk/virt/kvm/iommu.c b/trunk/virt/kvm/iommu.c index 4c4037503600..15147583abd1 100644 --- a/trunk/virt/kvm/iommu.c +++ b/trunk/virt/kvm/iommu.c @@ -39,11 +39,16 @@ int kvm_iommu_map_pages(struct kvm *kvm, pfn_t pfn; int i, r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; + int flags; /* check if iommu exists and in use */ if (!domain) return 0; + flags = IOMMU_READ | IOMMU_WRITE; + if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY) + flags |= IOMMU_CACHE; + for (i = 0; i < npages; i++) { /* check if already mapped */ if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) @@ -53,8 +58,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, r = iommu_map_range(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn), - PAGE_SIZE, - IOMMU_READ | IOMMU_WRITE); + PAGE_SIZE, flags); if (r) { printk(KERN_ERR "kvm_iommu_map_address:" "iommu failed to map pfn=%lx\n", pfn); @@ -88,7 +92,7 @@ int kvm_assign_device(struct kvm *kvm, { struct pci_dev *pdev = NULL; struct iommu_domain *domain = kvm->arch.iommu_domain; - int r; + int r, last_flags; /* check if iommu exists and in use */ if (!domain) @@ -107,12 +111,29 @@ int kvm_assign_device(struct kvm *kvm, return r; } + last_flags = kvm->arch.iommu_flags; + if (iommu_domain_has_cap(kvm->arch.iommu_domain, + IOMMU_CAP_CACHE_COHERENCY)) + kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY; + + /* Check if need to update IOMMU page table for guest memory */ + if ((last_flags ^ kvm->arch.iommu_flags) == + KVM_IOMMU_CACHE_COHERENCY) { + kvm_iommu_unmap_memslots(kvm); + r = kvm_iommu_map_memslots(kvm); + if (r) + goto out_unmap; + } + printk(KERN_DEBUG "assign device: host bdf = %x:%x:%x\n", assigned_dev->host_busnr, PCI_SLOT(assigned_dev->host_devfn), PCI_FUNC(assigned_dev->host_devfn)); return 0; +out_unmap: + kvm_iommu_unmap_memslots(kvm); + return r; } int kvm_deassign_device(struct kvm *kvm, diff --git a/trunk/virt/kvm/irq_comm.c b/trunk/virt/kvm/irq_comm.c index 864ac5483baa..a8bd466d00cc 100644 --- a/trunk/virt/kvm/irq_comm.c +++ b/trunk/virt/kvm/irq_comm.c @@ -22,6 +22,9 @@ #include #include +#ifdef CONFIG_IA64 +#include +#endif #include "irq.h" @@ -43,57 +46,73 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); } -static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) +inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) { - int vcpu_id, r = -1; - struct kvm_vcpu *vcpu; - struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); - int dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK) - >> MSI_ADDR_DEST_ID_SHIFT; - int vector = (e->msi.data & MSI_DATA_VECTOR_MASK) - >> MSI_DATA_VECTOR_SHIFT; - int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT, - (unsigned long *)&e->msi.address_lo); - int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT, - (unsigned long *)&e->msi.data); - int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT, - (unsigned long *)&e->msi.data); - u32 deliver_bitmask; - - BUG_ON(!ioapic); - - deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, - dest_id, dest_mode); - /* IOAPIC delivery mode value is the same as MSI here */ - switch (delivery_mode) { - case IOAPIC_LOWEST_PRIORITY: - vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector, - deliver_bitmask); - if (vcpu != NULL) - r = kvm_apic_set_irq(vcpu, vector, trig_mode); - else - printk(KERN_INFO "kvm: null lowest priority vcpu!\n"); - break; - case IOAPIC_FIXED: - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - if (r < 0) - r = 0; - r += kvm_apic_set_irq(vcpu, vector, trig_mode); - } +#ifdef CONFIG_IA64 + return irq->delivery_mode == + (IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT); +#else + return irq->delivery_mode == APIC_DM_LOWEST; +#endif +} + +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq) +{ + int i, r = -1; + struct kvm_vcpu *vcpu, *lowest = NULL; + + if (irq->dest_mode == 0 && irq->dest_id == 0xff && + kvm_is_dm_lowest_prio(irq)) + printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); + + for (i = 0; i < KVM_MAX_VCPUS; i++) { + vcpu = kvm->vcpus[i]; + + if (!vcpu || !kvm_apic_present(vcpu)) + continue; + + if (!kvm_apic_match_dest(vcpu, src, irq->shorthand, + irq->dest_id, irq->dest_mode)) + continue; + + if (!kvm_is_dm_lowest_prio(irq)) { + if (r < 0) + r = 0; + r += kvm_apic_set_irq(vcpu, irq); + } else { + if (!lowest) + lowest = vcpu; + else if (kvm_apic_compare_prio(vcpu, lowest) < 0) + lowest = vcpu; } - break; - default: - break; } + + if (lowest) + r = kvm_apic_set_irq(lowest, irq); + return r; } +static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int level) +{ + struct kvm_lapic_irq irq; + + irq.dest_id = (e->msi.address_lo & + MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT; + irq.vector = (e->msi.data & + MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; + irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; + irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; + irq.delivery_mode = e->msi.data & 0x700; + irq.level = 1; + irq.shorthand = 0; + + /* TODO Deal with RH bit of MSI message address */ + return kvm_irq_delivery_to_apic(kvm, NULL, &irq); +} + /* This should be called with the kvm->lock mutex held * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) @@ -252,7 +271,7 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, delta = 8; break; case KVM_IRQCHIP_IOAPIC: - e->set = kvm_set_ioapic_irq; + e->set = kvm_set_ioapic_irq; break; default: goto out; diff --git a/trunk/virt/kvm/kvm_main.c b/trunk/virt/kvm/kvm_main.c index 1ecbe2391c8b..764554350ed8 100644 --- a/trunk/virt/kvm/kvm_main.c +++ b/trunk/virt/kvm/kvm_main.c @@ -41,6 +41,8 @@ #include #include #include +#include +#include #include #include @@ -60,9 +62,6 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static int msi2intx = 1; -module_param(msi2intx, bool, 0); - DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); @@ -95,38 +94,96 @@ static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *h return NULL; } +static int find_index_from_host_irq(struct kvm_assigned_dev_kernel + *assigned_dev, int irq) +{ + int i, index; + struct msix_entry *host_msix_entries; + + host_msix_entries = assigned_dev->host_msix_entries; + + index = -1; + for (i = 0; i < assigned_dev->entries_nr; i++) + if (irq == host_msix_entries[i].vector) { + index = i; + break; + } + if (index < 0) { + printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); + return 0; + } + + return index; +} + static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) { struct kvm_assigned_dev_kernel *assigned_dev; + struct kvm *kvm; + int irq, i; assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, interrupt_work); + kvm = assigned_dev->kvm; /* This is taken to safely inject irq inside the guest. When * the interrupt injection (or the ioapic code) uses a * finer-grained lock, update this */ - mutex_lock(&assigned_dev->kvm->lock); - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); - - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) { - enable_irq(assigned_dev->host_irq); - assigned_dev->host_irq_disabled = false; + mutex_lock(&kvm->lock); + spin_lock_irq(&assigned_dev->assigned_dev_lock); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + struct kvm_guest_msix_entry *guest_entries = + assigned_dev->guest_msix_entries; + for (i = 0; i < assigned_dev->entries_nr; i++) { + if (!(guest_entries[i].flags & + KVM_ASSIGNED_MSIX_PENDING)) + continue; + guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; + kvm_set_irq(assigned_dev->kvm, + assigned_dev->irq_source_id, + guest_entries[i].vector, 1); + irq = assigned_dev->host_msix_entries[i].vector; + if (irq != 0) + enable_irq(irq); + assigned_dev->host_irq_disabled = false; + } + } else { + kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, + assigned_dev->guest_irq, 1); + if (assigned_dev->irq_requested_type & + KVM_DEV_IRQ_GUEST_MSI) { + enable_irq(assigned_dev->host_irq); + assigned_dev->host_irq_disabled = false; + } } + + spin_unlock_irq(&assigned_dev->assigned_dev_lock); mutex_unlock(&assigned_dev->kvm->lock); } static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) { + unsigned long flags; struct kvm_assigned_dev_kernel *assigned_dev = (struct kvm_assigned_dev_kernel *) dev_id; + spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int index = find_index_from_host_irq(assigned_dev, irq); + if (index < 0) + goto out; + assigned_dev->guest_msix_entries[index].flags |= + KVM_ASSIGNED_MSIX_PENDING; + } + schedule_work(&assigned_dev->interrupt_work); disable_irq_nosync(irq); assigned_dev->host_irq_disabled = true; +out: + spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); return IRQ_HANDLED; } @@ -134,6 +191,7 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) { struct kvm_assigned_dev_kernel *dev; + unsigned long flags; if (kian->gsi == -1) return; @@ -146,28 +204,30 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) /* The guest irq may be shared so this ack may be * from another device. */ + spin_lock_irqsave(&dev->assigned_dev_lock, flags); if (dev->host_irq_disabled) { enable_irq(dev->host_irq); dev->host_irq_disabled = false; } + spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); } -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) +static void deassign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) { - if (!irqchip_in_kernel(kvm)) - return; - kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier); + assigned_dev->ack_notifier.gsi = -1; if (assigned_dev->irq_source_id != -1) kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); assigned_dev->irq_source_id = -1; + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); +} - if (!assigned_dev->irq_requested_type) - return; - +/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ +static void deassign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ /* * In kvm_free_device_irq, cancel_work_sync return true if: * 1. work is scheduled, and then cancelled. @@ -184,17 +244,64 @@ static void kvm_free_assigned_irq(struct kvm *kvm, * now, the kvm state is still legal for probably we also have to wait * interrupt_work done. */ - disable_irq_nosync(assigned_dev->host_irq); - cancel_work_sync(&assigned_dev->interrupt_work); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int i; + for (i = 0; i < assigned_dev->entries_nr; i++) + disable_irq_nosync(assigned_dev-> + host_msix_entries[i].vector); + + cancel_work_sync(&assigned_dev->interrupt_work); + + for (i = 0; i < assigned_dev->entries_nr; i++) + free_irq(assigned_dev->host_msix_entries[i].vector, + (void *)assigned_dev); + + assigned_dev->entries_nr = 0; + kfree(assigned_dev->host_msix_entries); + kfree(assigned_dev->guest_msix_entries); + pci_disable_msix(assigned_dev->dev); + } else { + /* Deal with MSI and INTx */ + disable_irq_nosync(assigned_dev->host_irq); + cancel_work_sync(&assigned_dev->interrupt_work); - free_irq(assigned_dev->host_irq, (void *)assigned_dev); + free_irq(assigned_dev->host_irq, (void *)assigned_dev); - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) - pci_disable_msi(assigned_dev->dev); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) + pci_disable_msi(assigned_dev->dev); + } - assigned_dev->irq_requested_type = 0; + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); } +static int kvm_deassign_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev, + unsigned long irq_requested_type) +{ + unsigned long guest_irq_type, host_irq_type; + + if (!irqchip_in_kernel(kvm)) + return -EINVAL; + /* no irq assignment to deassign */ + if (!assigned_dev->irq_requested_type) + return -ENXIO; + + host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; + guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; + + if (host_irq_type) + deassign_host_irq(kvm, assigned_dev); + if (guest_irq_type) + deassign_guest_irq(kvm, assigned_dev); + + return 0; +} + +static void kvm_free_assigned_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); +} static void kvm_free_assigned_device(struct kvm *kvm, struct kvm_assigned_dev_kernel @@ -226,190 +333,244 @@ void kvm_free_all_assigned_devices(struct kvm *kvm) } } -static int assigned_device_update_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *adev, - struct kvm_assigned_irq *airq) +static int assigned_device_enable_host_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) { - adev->guest_irq = airq->guest_irq; - adev->ack_notifier.gsi = airq->guest_irq; + dev->host_irq = dev->dev->irq; + /* Even though this is PCI, we don't want to use shared + * interrupts. Sharing host devices with guest-assigned devices + * on the same interrupt line is not a happy situation: there + * are going to be long delays in accepting, acking, etc. + */ + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, + 0, "kvm_assigned_intx_device", (void *)dev)) + return -EIO; + return 0; +} - if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_INTX) - return 0; +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_host_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int r; - if (irqchip_in_kernel(kvm)) { - if (!msi2intx && - (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)) { - free_irq(adev->host_irq, (void *)adev); - pci_disable_msi(adev->dev); - } + if (!dev->dev->msi_enabled) { + r = pci_enable_msi(dev->dev); + if (r) + return r; + } - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; + dev->host_irq = dev->dev->irq; + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, + "kvm_assigned_msi_device", (void *)dev)) { + pci_disable_msi(dev->dev); + return -EIO; + } - if (airq->host_irq) - adev->host_irq = airq->host_irq; - else - adev->host_irq = adev->dev->irq; + return 0; +} +#endif - /* Even though this is PCI, we don't want to use shared - * interrupts. Sharing host devices with guest-assigned devices - * on the same interrupt line is not a happy situation: there - * are going to be long delays in accepting, acking, etc. - */ - if (request_irq(adev->host_irq, kvm_assigned_dev_intr, - 0, "kvm_assigned_intx_device", (void *)adev)) - return -EIO; +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_host_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int i, r = -EINVAL; + + /* host_msix_entries and guest_msix_entries should have been + * initialized */ + if (dev->entries_nr == 0) + return r; + + r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + if (r) + return r; + + for (i = 0; i < dev->entries_nr; i++) { + r = request_irq(dev->host_msix_entries[i].vector, + kvm_assigned_dev_intr, 0, + "kvm_assigned_msix_device", + (void *)dev); + /* FIXME: free requested_irq's on failure */ + if (r) + return r; } - adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_INTX | - KVM_ASSIGNED_DEV_HOST_INTX; return 0; } -#ifdef CONFIG_X86 -static int assigned_device_update_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *adev, - struct kvm_assigned_irq *airq) +#endif + +static int assigned_device_enable_guest_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) { - int r; + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = irq->guest_irq; + return 0; +} - adev->guest_irq = airq->guest_irq; - if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) { - /* x86 don't care upper address of guest msi message addr */ - adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI; - adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX; - adev->ack_notifier.gsi = -1; - } else if (msi2intx) { - adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX; - adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI; - adev->ack_notifier.gsi = airq->guest_irq; - } else { - /* - * Guest require to disable device MSI, we disable MSI and - * re-enable INTx by default again. Notice it's only for - * non-msi2intx. - */ - assigned_device_update_intx(kvm, adev, airq); - return 0; +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_guest_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + return 0; +} +#endif +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_guest_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + return 0; +} +#endif + +static int assign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + __u32 host_irq_type) +{ + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) + return r; + + switch (host_irq_type) { + case KVM_DEV_IRQ_HOST_INTX: + r = assigned_device_enable_host_intx(kvm, dev); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_HOST_MSI: + r = assigned_device_enable_host_msi(kvm, dev); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_HOST_MSIX: + r = assigned_device_enable_host_msix(kvm, dev); + break; +#endif + default: + r = -EINVAL; } - if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) - return 0; + if (!r) + dev->irq_requested_type |= host_irq_type; - if (irqchip_in_kernel(kvm)) { - if (!msi2intx) { - if (adev->irq_requested_type & - KVM_ASSIGNED_DEV_HOST_INTX) - free_irq(adev->host_irq, (void *)adev); + return r; +} - r = pci_enable_msi(adev->dev); - if (r) - return r; - } +static int assign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq, + unsigned long guest_irq_type) +{ + int id; + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) + return r; - adev->host_irq = adev->dev->irq; - if (request_irq(adev->host_irq, kvm_assigned_dev_intr, 0, - "kvm_assigned_msi_device", (void *)adev)) - return -EIO; + id = kvm_request_irq_source_id(kvm); + if (id < 0) + return id; + + dev->irq_source_id = id; + + switch (guest_irq_type) { + case KVM_DEV_IRQ_GUEST_INTX: + r = assigned_device_enable_guest_intx(kvm, dev, irq); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_GUEST_MSI: + r = assigned_device_enable_guest_msi(kvm, dev, irq); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_GUEST_MSIX: + r = assigned_device_enable_guest_msix(kvm, dev, irq); + break; +#endif + default: + r = -EINVAL; } - if (!msi2intx) - adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_MSI; + if (!r) { + dev->irq_requested_type |= guest_irq_type; + kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); + } else + kvm_free_irq_source_id(kvm, dev->irq_source_id); - adev->irq_requested_type |= KVM_ASSIGNED_DEV_HOST_MSI; - return 0; + return r; } -#endif +/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, - struct kvm_assigned_irq - *assigned_irq) + struct kvm_assigned_irq *assigned_irq) { - int r = 0; + int r = -EINVAL; struct kvm_assigned_dev_kernel *match; - u32 current_flags = 0, changed_flags; + unsigned long host_irq_type, guest_irq_type; - mutex_lock(&kvm->lock); + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + if (!irqchip_in_kernel(kvm)) + return r; + + mutex_lock(&kvm->lock); + r = -ENODEV; match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, assigned_irq->assigned_dev_id); - if (!match) { - mutex_unlock(&kvm->lock); - return -EINVAL; - } - - if (!match->irq_requested_type) { - INIT_WORK(&match->interrupt_work, - kvm_assigned_dev_interrupt_work_handler); - if (irqchip_in_kernel(kvm)) { - /* Register ack nofitier */ - match->ack_notifier.gsi = -1; - match->ack_notifier.irq_acked = - kvm_assigned_dev_ack_irq; - kvm_register_irq_ack_notifier(kvm, - &match->ack_notifier); - - /* Request IRQ source ID */ - r = kvm_request_irq_source_id(kvm); - if (r < 0) - goto out_release; - else - match->irq_source_id = r; - -#ifdef CONFIG_X86 - /* Determine host device irq type, we can know the - * result from dev->msi_enabled */ - if (msi2intx) - pci_enable_msi(match->dev); -#endif - } - } + if (!match) + goto out; - if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) && - (match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI)) - current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI; + host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); + guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - changed_flags = assigned_irq->flags ^ current_flags; + r = -EINVAL; + /* can only assign one type at a time */ + if (hweight_long(host_irq_type) > 1) + goto out; + if (hweight_long(guest_irq_type) > 1) + goto out; + if (host_irq_type == 0 && guest_irq_type == 0) + goto out; - if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) || - (msi2intx && match->dev->msi_enabled)) { -#ifdef CONFIG_X86 - r = assigned_device_update_msi(kvm, match, assigned_irq); - if (r) { - printk(KERN_WARNING "kvm: failed to enable " - "MSI device!\n"); - goto out_release; - } -#else - r = -ENOTTY; -#endif - } else if (assigned_irq->host_irq == 0 && match->dev->irq == 0) { - /* Host device IRQ 0 means don't support INTx */ - if (!msi2intx) { - printk(KERN_WARNING - "kvm: wait device to enable MSI!\n"); - r = 0; - } else { - printk(KERN_WARNING - "kvm: failed to enable MSI device!\n"); - r = -ENOTTY; - goto out_release; - } - } else { - /* Non-sharing INTx mode */ - r = assigned_device_update_intx(kvm, match, assigned_irq); - if (r) { - printk(KERN_WARNING "kvm: failed to enable " - "INTx device!\n"); - goto out_release; - } - } + r = 0; + if (host_irq_type) + r = assign_host_irq(kvm, match, host_irq_type); + if (r) + goto out; + if (guest_irq_type) + r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); +out: mutex_unlock(&kvm->lock); return r; -out_release: +} + +static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, + struct kvm_assigned_irq + *assigned_irq) +{ + int r = -ENODEV; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + r = kvm_deassign_irq(kvm, match, assigned_irq->flags); +out: mutex_unlock(&kvm->lock); - kvm_free_assigned_device(kvm, match); return r; } @@ -427,7 +588,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, assigned_dev->assigned_dev_id); if (match) { /* device already assigned */ - r = -EINVAL; + r = -EEXIST; goto out; } @@ -464,8 +625,12 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, match->host_devfn = assigned_dev->devfn; match->flags = assigned_dev->flags; match->dev = dev; + spin_lock_init(&match->assigned_dev_lock); match->irq_source_id = -1; match->kvm = kvm; + match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; + INIT_WORK(&match->interrupt_work, + kvm_assigned_dev_interrupt_work_handler); list_add(&match->list, &kvm->arch.assigned_dev_head); @@ -878,6 +1043,8 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); +#else + kvm_arch_flush_shadow(kvm); #endif kvm_arch_destroy_vm(kvm); mmdrop(mm); @@ -919,9 +1086,8 @@ int __kvm_set_memory_region(struct kvm *kvm, { int r; gfn_t base_gfn; - unsigned long npages; - int largepages; - unsigned long i; + unsigned long npages, ugfn; + unsigned long largepages, i; struct kvm_memory_slot *memslot; struct kvm_memory_slot old, new; @@ -1010,6 +1176,14 @@ int __kvm_set_memory_region(struct kvm *kvm, new.lpage_info[0].write_count = 1; if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE) new.lpage_info[largepages-1].write_count = 1; + ugfn = new.userspace_addr >> PAGE_SHIFT; + /* + * If the gfn and userspace address are not aligned wrt each + * other, disable large page support for this slot + */ + if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1)) + for (i = 0; i < largepages; ++i) + new.lpage_info[i].write_count = 1; } /* Allocate page dirty bitmap if needed */ @@ -1043,8 +1217,10 @@ int __kvm_set_memory_region(struct kvm *kvm, kvm_free_physmem_slot(&old, npages ? &new : NULL); /* Slot deletion case: we have to update the current slot */ + spin_lock(&kvm->mmu_lock); if (!npages) *memslot = old; + spin_unlock(&kvm->mmu_lock); #ifdef CONFIG_DMAR /* map the pages in iommu page table */ r = kvm_iommu_map_pages(kvm, base_gfn, npages); @@ -1454,12 +1630,14 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) for (;;) { prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); - if (kvm_cpu_has_interrupt(vcpu) || - kvm_cpu_has_pending_timer(vcpu) || - kvm_arch_vcpu_runnable(vcpu)) { + if ((kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)) || + kvm_arch_vcpu_runnable(vcpu)) { set_bit(KVM_REQ_UNHALT, &vcpu->requests); break; } + if (kvm_cpu_has_pending_timer(vcpu)) + break; if (signal_pending(current)) break; @@ -1593,6 +1771,88 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } +#ifdef __KVM_HAVE_MSIX +static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, + struct kvm_assigned_msix_nr *entry_nr) +{ + int r = 0; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry_nr->assigned_dev_id); + if (!adev) { + r = -EINVAL; + goto msix_nr_out; + } + + if (adev->entries_nr == 0) { + adev->entries_nr = entry_nr->entry_nr; + if (adev->entries_nr == 0 || + adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { + r = -EINVAL; + goto msix_nr_out; + } + + adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * + entry_nr->entry_nr, + GFP_KERNEL); + if (!adev->host_msix_entries) { + r = -ENOMEM; + goto msix_nr_out; + } + adev->guest_msix_entries = kzalloc( + sizeof(struct kvm_guest_msix_entry) * + entry_nr->entry_nr, GFP_KERNEL); + if (!adev->guest_msix_entries) { + kfree(adev->host_msix_entries); + r = -ENOMEM; + goto msix_nr_out; + } + } else /* Not allowed set MSI-X number twice */ + r = -EINVAL; +msix_nr_out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, + struct kvm_assigned_msix_entry *entry) +{ + int r = 0, i; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry->assigned_dev_id); + + if (!adev) { + r = -EINVAL; + goto msix_entry_out; + } + + for (i = 0; i < adev->entries_nr; i++) + if (adev->guest_msix_entries[i].vector == 0 || + adev->guest_msix_entries[i].entry == entry->entry) { + adev->guest_msix_entries[i].entry = entry->entry; + adev->guest_msix_entries[i].vector = entry->gsi; + adev->host_msix_entries[i].entry = entry->entry; + break; + } + if (i == adev->entries_nr) { + r = -ENOSPC; + goto msix_entry_out; + } + +msix_entry_out: + mutex_unlock(&kvm->lock); + + return r; +} +#endif + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1864,6 +2124,11 @@ static long kvm_vm_ioctl(struct file *filp, break; } case KVM_ASSIGN_IRQ: { + r = -EOPNOTSUPP; + break; + } +#ifdef KVM_CAP_ASSIGN_DEV_IRQ + case KVM_ASSIGN_DEV_IRQ: { struct kvm_assigned_irq assigned_irq; r = -EFAULT; @@ -1874,6 +2139,18 @@ static long kvm_vm_ioctl(struct file *filp, goto out; break; } + case KVM_DEASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } +#endif #endif #ifdef KVM_CAP_DEVICE_DEASSIGNMENT case KVM_DEASSIGN_PCI_DEVICE: { @@ -1917,7 +2194,29 @@ static long kvm_vm_ioctl(struct file *filp, vfree(entries); break; } +#ifdef __KVM_HAVE_MSIX + case KVM_ASSIGN_SET_MSIX_NR: { + struct kvm_assigned_msix_nr entry_nr; + r = -EFAULT; + if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) + goto out; + r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); + if (r) + goto out; + break; + } + case KVM_ASSIGN_SET_MSIX_ENTRY: { + struct kvm_assigned_msix_entry entry; + r = -EFAULT; + if (copy_from_user(&entry, argp, sizeof entry)) + goto out; + r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); + if (r) + goto out; + break; + } #endif +#endif /* KVM_CAP_IRQ_ROUTING */ default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } @@ -2112,15 +2411,15 @@ EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot); static int kvm_reboot(struct notifier_block *notifier, unsigned long val, void *v) { - if (val == SYS_RESTART) { - /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - */ - printk(KERN_INFO "kvm: exiting hardware virtualization\n"); - kvm_rebooting = true; - on_each_cpu(hardware_disable, NULL, 1); - } + /* + * Some (well, at least mine) BIOSes hang on reboot if + * in vmx root mode. + * + * And Intel TXT required VMX off for all cpu when system shutdown. + */ + printk(KERN_INFO "kvm: exiting hardware virtualization\n"); + kvm_rebooting = true; + on_each_cpu(hardware_disable, NULL, 1); return NOTIFY_OK; } @@ -2301,7 +2600,7 @@ int kvm_init(void *opaque, unsigned int vcpu_size, bad_pfn = page_to_pfn(bad_page); - if (!alloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { r = -ENOMEM; goto out_free_0; } @@ -2353,9 +2652,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size, kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; -#ifndef CONFIG_X86 - msi2intx = 0; -#endif return 0;