diff --git a/[refs] b/[refs]
index 354b17e34a55..fac4fb2342d8 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
---
-refs/heads/master: 2f841ed13b9f10037e25ddf417d01700ecd886d0
+refs/heads/master: 1ccb53a4f3d0bfd65889fcfe988d829633641f49
diff --git a/trunk/Documentation/DocBook/sh.tmpl b/trunk/Documentation/DocBook/sh.tmpl
index 4a38f604fa66..d858d92cf6d9 100644
--- a/trunk/Documentation/DocBook/sh.tmpl
+++ b/trunk/Documentation/DocBook/sh.tmpl
@@ -79,6 +79,10 @@
+
+ Clock Framework Extensions
+!Iinclude/linux/sh_clk.h
+
Machine Specific Interfaces
diff --git a/trunk/Documentation/edac.txt b/trunk/Documentation/edac.txt
index 9ee774de57cd..0b875e8da969 100644
--- a/trunk/Documentation/edac.txt
+++ b/trunk/Documentation/edac.txt
@@ -196,7 +196,7 @@ csrow3.
The representation of the above is reflected in the directory tree
in EDAC's sysfs interface. Starting in directory
/sys/devices/system/edac/mc each memory controller will be represented
-by its own 'mcX' directory, where 'X' is the index of the MC.
+by its own 'mcX' directory, where 'X" is the index of the MC.
..../edac/mc/
@@ -207,7 +207,7 @@ by its own 'mcX' directory, where 'X' is the index of the MC.
....
Under each 'mcX' directory each 'csrowX' is again represented by a
-'csrowX', where 'X' is the csrow index:
+'csrowX', where 'X" is the csrow index:
.../mc/mc0/
@@ -232,7 +232,7 @@ EDAC control and attribute files.
In 'mcX' directories are EDAC control and attribute files for
-this 'X' instance of the memory controllers:
+this 'X" instance of the memory controllers:
Counter reset control file:
@@ -343,7 +343,7 @@ Sdram memory scrubbing rate:
'csrowX' DIRECTORIES
In the 'csrowX' directories are EDAC control and attribute files for
-this 'X' instance of csrow:
+this 'X" instance of csrow:
Total Uncorrectable Errors count attribute file:
diff --git a/trunk/Documentation/fb/00-INDEX b/trunk/Documentation/fb/00-INDEX
index 30a70542e823..a618fd99c9f0 100644
--- a/trunk/Documentation/fb/00-INDEX
+++ b/trunk/Documentation/fb/00-INDEX
@@ -4,41 +4,33 @@ please mail me.
Geert Uytterhoeven
00-INDEX
- - this file.
+ - this file
arkfb.txt
- info on the fbdev driver for ARK Logic chips.
aty128fb.txt
- info on the ATI Rage128 frame buffer driver.
cirrusfb.txt
- info on the driver for Cirrus Logic chipsets.
-cmap_xfbdev.txt
- - an introduction to fbdev's cmap structures.
deferred_io.txt
- an introduction to deferred IO.
-efifb.txt
- - info on the EFI platform driver for Intel based Apple computers.
-ep93xx-fb.txt
- - info on the driver for EP93xx LCD controller.
fbcon.txt
- intro to and usage guide for the framebuffer console (fbcon).
framebuffer.txt
- introduction to frame buffer devices.
-gxfb.txt
- - info on the framebuffer driver for AMD Geode GX2 based processors.
+imacfb.txt
+ - info on the generic EFI platform driver for Intel based Macs.
intel810.txt
- documentation for the Intel 810/815 framebuffer driver.
intelfb.txt
- docs for Intel 830M/845G/852GM/855GM/865G/915G/945G fb driver.
internals.txt
- quick overview of frame buffer device internals.
-lxfb.txt
- - info on the framebuffer driver for AMD Geode LX based processors.
matroxfb.txt
- info on the Matrox framebuffer driver for Alpha, Intel and PPC.
-metronomefb.txt
- - info on the driver for the Metronome display controller.
modedb.txt
- info on the video mode database.
+matroxfb.txt
+ - info on the Matrox frame buffer driver.
pvr2fb.txt
- info on the PowerVR 2 frame buffer driver.
pxafb.txt
@@ -47,23 +39,13 @@ s3fb.txt
- info on the fbdev driver for S3 Trio/Virge chips.
sa1100fb.txt
- information about the driver for the SA-1100 LCD controller.
-sh7760fb.txt
- - info on the SH7760/SH7763 integrated LCDC Framebuffer driver.
sisfb.txt
- info on the framebuffer device driver for various SiS chips.
sstfb.txt
- info on the frame buffer driver for 3dfx' Voodoo Graphics boards.
tgafb.txt
- - info on the TGA (DECChip 21030) frame buffer driver.
-tridentfb.txt
- info on the framebuffer driver for some Trident chip based cards.
-uvesafb.txt
- - info on the userspace VESA (VBE2+ compliant) frame buffer device.
+ - info on the TGA (DECChip 21030) frame buffer driver
vesafb.txt
- - info on the VESA frame buffer device.
-viafb.modes
- - list of modes for VIA Integration Graphic Chip.
-viafb.txt
- - info on the VIA Integration Graphic Chip console framebuffer driver.
+ - info on the VESA frame buffer device
vt8623fb.txt
- info on the fb driver for the graphics core in VIA VT8623 chipsets.
diff --git a/trunk/Documentation/kernel-parameters.txt b/trunk/Documentation/kernel-parameters.txt
index cdd2a6e8a3b7..92e83e53148f 100644
--- a/trunk/Documentation/kernel-parameters.txt
+++ b/trunk/Documentation/kernel-parameters.txt
@@ -2385,11 +2385,6 @@ and is between 256 and 4096 characters. It is defined in the file
improve throughput, but will also increase the
amount of memory reserved for use by the client.
- swapaccount[=0|1]
- [KNL] Enable accounting of swap in memory resource
- controller if no parameter or 1 is given or disable
- it if 0 is given (See Documentation/cgroups/memory.txt)
-
swiotlb= [IA-64] Number of I/O TLB slabs
switches= [HW,M68k]
diff --git a/trunk/Documentation/networking/ip-sysctl.txt b/trunk/Documentation/networking/ip-sysctl.txt
index 3c5e465296e1..fe95105992c5 100644
--- a/trunk/Documentation/networking/ip-sysctl.txt
+++ b/trunk/Documentation/networking/ip-sysctl.txt
@@ -144,7 +144,6 @@ tcp_adv_win_scale - INTEGER
Count buffering overhead as bytes/2^tcp_adv_win_scale
(if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
if it is <= 0.
- Possible values are [-31, 31], inclusive.
Default: 2
tcp_allowed_congestion_control - STRING
diff --git a/trunk/Documentation/sh/clk.txt b/trunk/Documentation/sh/clk.txt
new file mode 100644
index 000000000000..114b595cfa97
--- /dev/null
+++ b/trunk/Documentation/sh/clk.txt
@@ -0,0 +1,32 @@
+Clock framework on SuperH architecture
+
+The framework on SH extends existing API by the function clk_set_rate_ex,
+which prototype is as follows:
+
+ clk_set_rate_ex (struct clk *clk, unsigned long rate, int algo_id)
+
+The algo_id parameter is used to specify algorithm used to recalculate clocks,
+adjanced to clock, specified as first argument. It is assumed that algo_id==0
+means no changes to adjanced clock
+
+Internally, the clk_set_rate_ex forwards request to clk->ops->set_rate method,
+if it is present in ops structure. The method should set the clock rate and adjust
+all needed clocks according to the passed algo_id.
+Exact values for algo_id are machine-dependent. For the sh7722, the following
+values are defined:
+
+ NO_CHANGE = 0,
+ IUS_N1_N1, /* I:U = N:1, U:Sh = N:1 */
+ IUS_322, /* I:U:Sh = 3:2:2 */
+ IUS_522, /* I:U:Sh = 5:2:2 */
+ IUS_N11, /* I:U:Sh = N:1:1 */
+ SB_N1, /* Sh:B = N:1 */
+ SB3_N1, /* Sh:B3 = N:1 */
+ SB3_32, /* Sh:B3 = 3:2 */
+ SB3_43, /* Sh:B3 = 4:3 */
+ SB3_54, /* Sh:B3 = 5:4 */
+ BP_N1, /* B:P = N:1 */
+ IP_N1 /* I:P = N:1 */
+
+Each of these constants means relation between clocks that can be set via the FRQCR
+register
diff --git a/trunk/MAINTAINERS b/trunk/MAINTAINERS
index b3be8b3d0437..a92c994ba935 100644
--- a/trunk/MAINTAINERS
+++ b/trunk/MAINTAINERS
@@ -1359,7 +1359,7 @@ F: include/net/bluetooth/
BONDING DRIVER
M: Jay Vosburgh
-L: netdev@vger.kernel.org
+L: bonding-devel@lists.sourceforge.net
W: http://sourceforge.net/projects/bonding/
S: Supported
F: drivers/net/bonding/
@@ -2444,12 +2444,10 @@ F: drivers/net/wan/sdla.c
FRAMEBUFFER LAYER
L: linux-fbdev@vger.kernel.org
W: http://linux-fbdev.sourceforge.net/
-Q: http://patchwork.kernel.org/project/linux-fbdev/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/fbdev-2.6.git
S: Orphan
F: Documentation/fb/
-F: drivers/video/
-F: include/video/
+F: drivers/video/fb*
F: include/linux/fb.h
FREESCALE DMA DRIVER
@@ -5839,8 +5837,6 @@ M: Chris Metcalf
W: http://www.tilera.com/scm/
S: Supported
F: arch/tile/
-F: drivers/char/hvc_tile.c
-F: drivers/net/tile/
TLAN NETWORK DRIVER
M: Samuel Chessman
diff --git a/trunk/Makefile b/trunk/Makefile
index 9e3c89030f5c..b31d21377e4c 100644
--- a/trunk/Makefile
+++ b/trunk/Makefile
@@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 37
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc3
NAME = Flesh-Eating Bats with Fangs
# *DOCUMENTATION*
diff --git a/trunk/arch/arm/Kconfig b/trunk/arch/arm/Kconfig
index 49778bb43782..db524e75c4a2 100644
--- a/trunk/arch/arm/Kconfig
+++ b/trunk/arch/arm/Kconfig
@@ -14,7 +14,6 @@ config ARM
select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL)
- select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
select HAVE_GENERIC_DMA_COHERENT
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZO
@@ -1206,11 +1205,10 @@ config SMP
depends on EXPERIMENTAL
depends on GENERIC_CLOCKEVENTS
depends on REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP || \
- MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
- ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \
- ARCH_MSM_SCORPIONMP
+ MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
+ ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4
select USE_GENERIC_SMP_HELPERS
- select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP
+ select HAVE_ARM_SCU
help
This enables support for systems with more than one CPU. If you have
a system with only one CPU, like most personal computers, say N. If
@@ -1285,7 +1283,6 @@ config NR_CPUS
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
depends on SMP && HOTPLUG && EXPERIMENTAL
- depends on !ARCH_MSM
help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu.
@@ -1294,7 +1291,7 @@ config LOCAL_TIMERS
bool "Use local timer interrupts"
depends on SMP
default y
- select HAVE_ARM_TWD if !ARCH_MSM_SCORPIONMP
+ select HAVE_ARM_TWD
help
Enable support for local timers on SMP platforms, rather then the
legacy IPI broadcast method. Local timers allows the system
diff --git a/trunk/arch/arm/Kconfig.debug b/trunk/arch/arm/Kconfig.debug
index eac62085f5b2..2fd0b99afc4b 100644
--- a/trunk/arch/arm/Kconfig.debug
+++ b/trunk/arch/arm/Kconfig.debug
@@ -23,7 +23,7 @@ config STRICT_DEVMEM
config FRAME_POINTER
bool
depends on !THUMB2_KERNEL
- default y if !ARM_UNWIND || FUNCTION_GRAPH_TRACER
+ default y if !ARM_UNWIND
help
If you say N here, the resulting kernel will be slightly smaller and
faster. However, if neither FRAME_POINTER nor ARM_UNWIND are enabled,
diff --git a/trunk/arch/arm/boot/compressed/head.S b/trunk/arch/arm/boot/compressed/head.S
index 9be21ba648cd..6825c34646d4 100644
--- a/trunk/arch/arm/boot/compressed/head.S
+++ b/trunk/arch/arm/boot/compressed/head.S
@@ -1084,6 +1084,6 @@ memdump: mov r12, r0
reloc_end:
.align
- .section ".stack", "aw", %nobits
+ .section ".stack", "w"
user_stack: .space 4096
user_stack_end:
diff --git a/trunk/arch/arm/boot/compressed/vmlinux.lds.in b/trunk/arch/arm/boot/compressed/vmlinux.lds.in
index 366a924019ac..d08168941bd6 100644
--- a/trunk/arch/arm/boot/compressed/vmlinux.lds.in
+++ b/trunk/arch/arm/boot/compressed/vmlinux.lds.in
@@ -57,7 +57,7 @@ SECTIONS
.bss : { *(.bss) }
_end = .;
- .stack : { *(.stack) }
+ .stack (NOLOAD) : { *(.stack) }
.stab 0 : { *(.stab) }
.stabstr 0 : { *(.stabstr) }
diff --git a/trunk/arch/arm/include/asm/assembler.h b/trunk/arch/arm/include/asm/assembler.h
index 749bb6622404..062b58c029ab 100644
--- a/trunk/arch/arm/include/asm/assembler.h
+++ b/trunk/arch/arm/include/asm/assembler.h
@@ -238,7 +238,7 @@
@ Slightly optimised to avoid incrementing the pointer twice
usraccoff \instr, \reg, \ptr, \inc, 0, \cond, \abort
.if \rept == 2
- usraccoff \instr, \reg, \ptr, \inc, \inc, \cond, \abort
+ usraccoff \instr, \reg, \ptr, \inc, 4, \cond, \abort
.endif
add\cond \ptr, #\rept * \inc
diff --git a/trunk/arch/arm/include/asm/hw_breakpoint.h b/trunk/arch/arm/include/asm/hw_breakpoint.h
index f389b2704d82..4d8ae9d67abe 100644
--- a/trunk/arch/arm/include/asm/hw_breakpoint.h
+++ b/trunk/arch/arm/include/asm/hw_breakpoint.h
@@ -20,8 +20,8 @@ struct arch_hw_breakpoint_ctrl {
struct arch_hw_breakpoint {
u32 address;
u32 trigger;
- struct arch_hw_breakpoint_ctrl step_ctrl;
- struct arch_hw_breakpoint_ctrl ctrl;
+ struct perf_event *suspended_wp;
+ struct arch_hw_breakpoint_ctrl ctrl;
};
static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
diff --git a/trunk/arch/arm/include/asm/mmu.h b/trunk/arch/arm/include/asm/mmu.h
index b4ffe9d5b526..68870c776671 100644
--- a/trunk/arch/arm/include/asm/mmu.h
+++ b/trunk/arch/arm/include/asm/mmu.h
@@ -13,10 +13,6 @@ typedef struct {
#ifdef CONFIG_CPU_HAS_ASID
#define ASID(mm) ((mm)->context.id & 255)
-
-/* init_mm.context.id_lock should be initialized. */
-#define INIT_MM_CONTEXT(name) \
- .context.id_lock = __SPIN_LOCK_UNLOCKED(name.context.id_lock),
#else
#define ASID(mm) (0)
#endif
diff --git a/trunk/arch/arm/include/asm/pgtable.h b/trunk/arch/arm/include/asm/pgtable.h
index 53d1d5deb111..b155414192da 100644
--- a/trunk/arch/arm/include/asm/pgtable.h
+++ b/trunk/arch/arm/include/asm/pgtable.h
@@ -374,9 +374,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
-/* we don't need complex calculations here as the pmd is folded into the pgd */
-#define pmd_addr_end(addr,end) (end)
-
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
diff --git a/trunk/arch/arm/include/asm/system.h b/trunk/arch/arm/include/asm/system.h
index ec4327a4653d..1120f18a6b17 100644
--- a/trunk/arch/arm/include/asm/system.h
+++ b/trunk/arch/arm/include/asm/system.h
@@ -63,11 +63,6 @@
#include
#define __exception __attribute__((section(".exception.text")))
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-#define __exception_irq_entry __irq_entry
-#else
-#define __exception_irq_entry __exception
-#endif
struct thread_info;
struct task_struct;
diff --git a/trunk/arch/arm/include/asm/traps.h b/trunk/arch/arm/include/asm/traps.h
index 124475afb007..491960bf4260 100644
--- a/trunk/arch/arm/include/asm/traps.h
+++ b/trunk/arch/arm/include/asm/traps.h
@@ -15,32 +15,13 @@ struct undef_hook {
void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- extern char __irqentry_text_start[];
- extern char __irqentry_text_end[];
-
- return ptr >= (unsigned long)&__irqentry_text_start &&
- ptr < (unsigned long)&__irqentry_text_end;
-}
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- return 0;
-}
-#endif
-
static inline int in_exception_text(unsigned long ptr)
{
extern char __exception_text_start[];
extern char __exception_text_end[];
- int in;
-
- in = ptr >= (unsigned long)&__exception_text_start &&
- ptr < (unsigned long)&__exception_text_end;
- return in ? : __in_irqentry_text(ptr);
+ return ptr >= (unsigned long)&__exception_text_start &&
+ ptr < (unsigned long)&__exception_text_end;
}
extern void __init early_trap_init(void);
diff --git a/trunk/arch/arm/kernel/Makefile b/trunk/arch/arm/kernel/Makefile
index 679851a9f589..5b9b268f4fbb 100644
--- a/trunk/arch/arm/kernel/Makefile
+++ b/trunk/arch/arm/kernel/Makefile
@@ -5,7 +5,7 @@
CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET)
AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET)
-ifdef CONFIG_FUNCTION_TRACER
+ifdef CONFIG_DYNAMIC_FTRACE
CFLAGS_REMOVE_ftrace.o = -pg
endif
@@ -33,7 +33,6 @@ obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o
obj-$(CONFIG_HAVE_ARM_TWD) += smp_twd.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o
obj-$(CONFIG_KPROBES) += kprobes.o kprobes-decode.o
obj-$(CONFIG_ATAGS_PROC) += atags.o
diff --git a/trunk/arch/arm/kernel/entry-armv.S b/trunk/arch/arm/kernel/entry-armv.S
index 34bbef0d2e7e..c09e3573c5de 100644
--- a/trunk/arch/arm/kernel/entry-armv.S
+++ b/trunk/arch/arm/kernel/entry-armv.S
@@ -198,7 +198,6 @@ __dabt_svc:
@
@ set desired IRQ state, then call main handler
@
- debug_entry r1
msr cpsr_c, r9
mov r2, sp
bl do_DataAbort
@@ -325,7 +324,6 @@ __pabt_svc:
#else
bl CPU_PABORT_HANDLER
#endif
- debug_entry r1
msr cpsr_c, r9 @ Maybe enable interrupts
mov r2, sp @ regs
bl do_PrefetchAbort @ call abort handler
@@ -441,7 +439,6 @@ __dabt_usr:
@
@ IRQs on, then call the main handler
@
- debug_entry r1
enable_irq
mov r2, sp
adr lr, BSYM(ret_from_exception)
@@ -706,7 +703,6 @@ __pabt_usr:
#else
bl CPU_PABORT_HANDLER
#endif
- debug_entry r1
enable_irq @ Enable interrupts
mov r2, sp @ regs
bl do_PrefetchAbort @ call abort handler
diff --git a/trunk/arch/arm/kernel/entry-common.S b/trunk/arch/arm/kernel/entry-common.S
index aae802ee12f8..8bfa98757cd2 100644
--- a/trunk/arch/arm/kernel/entry-common.S
+++ b/trunk/arch/arm/kernel/entry-common.S
@@ -141,170 +141,98 @@ ENDPROC(ret_from_fork)
#endif
#endif
-.macro __mcount suffix
- mcount_enter
- ldr r0, =ftrace_trace_function
- ldr r2, [r0]
- adr r0, .Lftrace_stub
- cmp r0, r2
- bne 1f
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- ldr r1, =ftrace_graph_return
- ldr r2, [r1]
- cmp r0, r2
- bne ftrace_graph_caller\suffix
-
- ldr r1, =ftrace_graph_entry
- ldr r2, [r1]
- ldr r0, =ftrace_graph_entry_stub
- cmp r0, r2
- bne ftrace_graph_caller\suffix
-#endif
-
- mcount_exit
-
-1: mcount_get_lr r1 @ lr of instrumented func
- mov r0, lr @ instrumented function
- sub r0, r0, #MCOUNT_INSN_SIZE
- adr lr, BSYM(2f)
- mov pc, r2
-2: mcount_exit
-.endm
-
-.macro __ftrace_caller suffix
- mcount_enter
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(__gnu_mcount_nc)
+ mov ip, lr
+ ldmia sp!, {lr}
+ mov pc, ip
+ENDPROC(__gnu_mcount_nc)
- mcount_get_lr r1 @ lr of instrumented func
- mov r0, lr @ instrumented function
+ENTRY(ftrace_caller)
+ stmdb sp!, {r0-r3, lr}
+ mov r0, lr
sub r0, r0, #MCOUNT_INSN_SIZE
+ ldr r1, [sp, #20]
- .globl ftrace_call\suffix
-ftrace_call\suffix:
+ .global ftrace_call
+ftrace_call:
bl ftrace_stub
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- .globl ftrace_graph_call\suffix
-ftrace_graph_call\suffix:
- mov r0, r0
-#endif
-
- mcount_exit
-.endm
-
-.macro __ftrace_graph_caller
- sub r0, fp, #4 @ &lr of instrumented routine (&parent)
-#ifdef CONFIG_DYNAMIC_FTRACE
- @ called from __ftrace_caller, saved in mcount_enter
- ldr r1, [sp, #16] @ instrumented routine (func)
-#else
- @ called from __mcount, untouched in lr
- mov r1, lr @ instrumented routine (func)
-#endif
- sub r1, r1, #MCOUNT_INSN_SIZE
- mov r2, fp @ frame pointer
- bl prepare_ftrace_return
- mcount_exit
-.endm
+ ldmia sp!, {r0-r3, ip, lr}
+ mov pc, ip
+ENDPROC(ftrace_caller)
#ifdef CONFIG_OLD_MCOUNT
-/*
- * mcount
- */
-
-.macro mcount_enter
- stmdb sp!, {r0-r3, lr}
-.endm
-
-.macro mcount_get_lr reg
- ldr \reg, [fp, #-4]
-.endm
-
-.macro mcount_exit
- ldr lr, [fp, #-4]
- ldmia sp!, {r0-r3, pc}
-.endm
-
ENTRY(mcount)
-#ifdef CONFIG_DYNAMIC_FTRACE
stmdb sp!, {lr}
ldr lr, [fp, #-4]
ldmia sp!, {pc}
-#else
- __mcount _old
-#endif
ENDPROC(mcount)
-#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(ftrace_caller_old)
- __ftrace_caller _old
-ENDPROC(ftrace_caller_old)
-#endif
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller_old)
- __ftrace_graph_caller
-ENDPROC(ftrace_graph_caller_old)
-#endif
+ stmdb sp!, {r0-r3, lr}
+ ldr r1, [fp, #-4]
+ mov r0, lr
+ sub r0, r0, #MCOUNT_INSN_SIZE
-.purgem mcount_enter
-.purgem mcount_get_lr
-.purgem mcount_exit
+ .globl ftrace_call_old
+ftrace_call_old:
+ bl ftrace_stub
+ ldr lr, [fp, #-4] @ restore lr
+ ldmia sp!, {r0-r3, pc}
+ENDPROC(ftrace_caller_old)
#endif
-/*
- * __gnu_mcount_nc
- */
+#else
-.macro mcount_enter
+ENTRY(__gnu_mcount_nc)
stmdb sp!, {r0-r3, lr}
-.endm
-
-.macro mcount_get_lr reg
- ldr \reg, [sp, #20]
-.endm
-
-.macro mcount_exit
+ ldr r0, =ftrace_trace_function
+ ldr r2, [r0]
+ adr r0, .Lftrace_stub
+ cmp r0, r2
+ bne gnu_trace
ldmia sp!, {r0-r3, ip, lr}
mov pc, ip
-.endm
-ENTRY(__gnu_mcount_nc)
-#ifdef CONFIG_DYNAMIC_FTRACE
- mov ip, lr
- ldmia sp!, {lr}
+gnu_trace:
+ ldr r1, [sp, #20] @ lr of instrumented routine
+ mov r0, lr
+ sub r0, r0, #MCOUNT_INSN_SIZE
+ adr lr, BSYM(1f)
+ mov pc, r2
+1:
+ ldmia sp!, {r0-r3, ip, lr}
mov pc, ip
-#else
- __mcount
-#endif
ENDPROC(__gnu_mcount_nc)
-#ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(ftrace_caller)
- __ftrace_caller
-ENDPROC(ftrace_caller)
-#endif
+#ifdef CONFIG_OLD_MCOUNT
+/*
+ * This is under an ifdef in order to force link-time errors for people trying
+ * to build with !FRAME_POINTER with a GCC which doesn't use the new-style
+ * mcount.
+ */
+ENTRY(mcount)
+ stmdb sp!, {r0-r3, lr}
+ ldr r0, =ftrace_trace_function
+ ldr r2, [r0]
+ adr r0, ftrace_stub
+ cmp r0, r2
+ bne trace
+ ldr lr, [fp, #-4] @ restore lr
+ ldmia sp!, {r0-r3, pc}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
- __ftrace_graph_caller
-ENDPROC(ftrace_graph_caller)
+trace:
+ ldr r1, [fp, #-4] @ lr of instrumented routine
+ mov r0, lr
+ sub r0, r0, #MCOUNT_INSN_SIZE
+ mov lr, pc
+ mov pc, r2
+ ldr lr, [fp, #-4] @ restore lr
+ ldmia sp!, {r0-r3, pc}
+ENDPROC(mcount)
#endif
-.purgem mcount_enter
-.purgem mcount_get_lr
-.purgem mcount_exit
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- .globl return_to_handler
-return_to_handler:
- stmdb sp!, {r0-r3}
- mov r0, fp @ frame pointer
- bl ftrace_return_to_handler
- mov lr, r0 @ r0 has real ret addr
- ldmia sp!, {r0-r3}
- mov pc, lr
-#endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
ENTRY(ftrace_stub)
.Lftrace_stub:
diff --git a/trunk/arch/arm/kernel/entry-header.S b/trunk/arch/arm/kernel/entry-header.S
index ae9464900168..d93f976fb389 100644
--- a/trunk/arch/arm/kernel/entry-header.S
+++ b/trunk/arch/arm/kernel/entry-header.S
@@ -165,25 +165,6 @@
.endm
#endif /* !CONFIG_THUMB2_KERNEL */
- @
- @ Debug exceptions are taken as prefetch or data aborts.
- @ We must disable preemption during the handler so that
- @ we can access the debug registers safely.
- @
- .macro debug_entry, fsr
-#if defined(CONFIG_HAVE_HW_BREAKPOINT) && defined(CONFIG_PREEMPT)
- ldr r4, =0x40f @ mask out fsr.fs
- and r5, r4, \fsr
- cmp r5, #2 @ debug exception
- bne 1f
- get_thread_info r10
- ldr r6, [r10, #TI_PREEMPT] @ get preempt count
- add r11, r6, #1 @ increment it
- str r11, [r10, #TI_PREEMPT]
-1:
-#endif
- .endm
-
/*
* These are the registers used in the syscall handler, and allow us to
* have in theory up to 7 arguments to a function - r0 to r6.
diff --git a/trunk/arch/arm/kernel/ftrace.c b/trunk/arch/arm/kernel/ftrace.c
index c0062ad1e847..971ac8c36ea7 100644
--- a/trunk/arch/arm/kernel/ftrace.c
+++ b/trunk/arch/arm/kernel/ftrace.c
@@ -24,7 +24,6 @@
#define NOP 0xe8bd4000 /* pop {lr} */
#endif
-#ifdef CONFIG_DYNAMIC_FTRACE
#ifdef CONFIG_OLD_MCOUNT
#define OLD_MCOUNT_ADDR ((unsigned long) mcount)
#define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
@@ -60,9 +59,9 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
}
#endif
+/* construct a branch (BL) instruction to addr */
#ifdef CONFIG_THUMB2_KERNEL
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
- bool link)
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
{
unsigned long s, j1, j2, i1, i2, imm10, imm11;
unsigned long first, second;
@@ -84,22 +83,15 @@ static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
j2 = (!i2) ^ s;
first = 0xf000 | (s << 10) | imm10;
- second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11;
- if (link)
- second |= 1 << 14;
+ second = 0xd000 | (j1 << 13) | (j2 << 11) | imm11;
return (second << 16) | first;
}
#else
-static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
- bool link)
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
{
- unsigned long opcode = 0xea000000;
long offset;
- if (link)
- opcode |= 1 << 24;
-
offset = (long)addr - (long)(pc + 8);
if (unlikely(offset < -33554432 || offset > 33554428)) {
/* Can't generate branches that far (from ARM ARM). Ftrace
@@ -111,15 +103,10 @@ static unsigned long ftrace_gen_branch(unsigned long pc, unsigned long addr,
offset = (offset >> 2) & 0x00ffffff;
- return opcode | offset;
+ return 0xeb000000 | offset;
}
#endif
-static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
-{
- return ftrace_gen_branch(pc, addr, true);
-}
-
static int ftrace_modify_code(unsigned long pc, unsigned long old,
unsigned long new)
{
@@ -206,83 +193,3 @@ int __init ftrace_dyn_arch_init(void *data)
return 0;
}
-#endif /* CONFIG_DYNAMIC_FTRACE */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
- unsigned long frame_pointer)
-{
- unsigned long return_hooker = (unsigned long) &return_to_handler;
- struct ftrace_graph_ent trace;
- unsigned long old;
- int err;
-
- if (unlikely(atomic_read(¤t->tracing_graph_pause)))
- return;
-
- old = *parent;
- *parent = return_hooker;
-
- err = ftrace_push_return_trace(old, self_addr, &trace.depth,
- frame_pointer);
- if (err == -EBUSY) {
- *parent = old;
- return;
- }
-
- trace.func = self_addr;
-
- /* Only trace if the calling function expects to */
- if (!ftrace_graph_entry(&trace)) {
- current->curr_ret_stack--;
- *parent = old;
- }
-}
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-extern unsigned long ftrace_graph_call;
-extern unsigned long ftrace_graph_call_old;
-extern void ftrace_graph_caller_old(void);
-
-static int __ftrace_modify_caller(unsigned long *callsite,
- void (*func) (void), bool enable)
-{
- unsigned long caller_fn = (unsigned long) func;
- unsigned long pc = (unsigned long) callsite;
- unsigned long branch = ftrace_gen_branch(pc, caller_fn, false);
- unsigned long nop = 0xe1a00000; /* mov r0, r0 */
- unsigned long old = enable ? nop : branch;
- unsigned long new = enable ? branch : nop;
-
- return ftrace_modify_code(pc, old, new);
-}
-
-static int ftrace_modify_graph_caller(bool enable)
-{
- int ret;
-
- ret = __ftrace_modify_caller(&ftrace_graph_call,
- ftrace_graph_caller,
- enable);
-
-#ifdef CONFIG_OLD_MCOUNT
- if (!ret)
- ret = __ftrace_modify_caller(&ftrace_graph_call_old,
- ftrace_graph_caller_old,
- enable);
-#endif
-
- return ret;
-}
-
-int ftrace_enable_ftrace_graph_caller(void)
-{
- return ftrace_modify_graph_caller(true);
-}
-
-int ftrace_disable_ftrace_graph_caller(void)
-{
- return ftrace_modify_graph_caller(false);
-}
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/trunk/arch/arm/kernel/hw_breakpoint.c b/trunk/arch/arm/kernel/hw_breakpoint.c
index c9f3f0467570..21e3a4ab3b8c 100644
--- a/trunk/arch/arm/kernel/hw_breakpoint.c
+++ b/trunk/arch/arm/kernel/hw_breakpoint.c
@@ -24,7 +24,6 @@
#define pr_fmt(fmt) "hw-breakpoint: " fmt
#include
-#include
#include
#include
#include
@@ -45,7 +44,6 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
/* Number of BRP/WRP registers on this CPU. */
static int core_num_brps;
-static int core_num_reserved_brps;
static int core_num_wrps;
/* Debug architecture version. */
@@ -54,6 +52,87 @@ static u8 debug_arch;
/* Maximum supported watchpoint length. */
static u8 max_watchpoint_len;
+/* Determine number of BRP registers available. */
+static int get_num_brps(void)
+{
+ u32 didr;
+ ARM_DBG_READ(c0, 0, didr);
+ return ((didr >> 24) & 0xf) + 1;
+}
+
+/* Determine number of WRP registers available. */
+static int get_num_wrps(void)
+{
+ /*
+ * FIXME: When a watchpoint fires, the only way to work out which
+ * watchpoint it was is by disassembling the faulting instruction
+ * and working out the address of the memory access.
+ *
+ * Furthermore, we can only do this if the watchpoint was precise
+ * since imprecise watchpoints prevent us from calculating register
+ * based addresses.
+ *
+ * For the time being, we only report 1 watchpoint register so we
+ * always know which watchpoint fired. In the future we can either
+ * add a disassembler and address generation emulator, or we can
+ * insert a check to see if the DFAR is set on watchpoint exception
+ * entry [the ARM ARM states that the DFAR is UNKNOWN, but
+ * experience shows that it is set on some implementations].
+ */
+
+#if 0
+ u32 didr, wrps;
+ ARM_DBG_READ(c0, 0, didr);
+ return ((didr >> 28) & 0xf) + 1;
+#endif
+
+ return 1;
+}
+
+int hw_breakpoint_slots(int type)
+{
+ /*
+ * We can be called early, so don't rely on
+ * our static variables being initialised.
+ */
+ switch (type) {
+ case TYPE_INST:
+ return get_num_brps();
+ case TYPE_DATA:
+ return get_num_wrps();
+ default:
+ pr_warning("unknown slot type: %d\n", type);
+ return 0;
+ }
+}
+
+/* Determine debug architecture. */
+static u8 get_debug_arch(void)
+{
+ u32 didr;
+
+ /* Do we implement the extended CPUID interface? */
+ if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
+ pr_warning("CPUID feature registers not supported. "
+ "Assuming v6 debug is present.\n");
+ return ARM_DEBUG_ARCH_V6;
+ }
+
+ ARM_DBG_READ(c0, 0, didr);
+ return (didr >> 16) & 0xf;
+}
+
+/* Does this core support mismatch breakpoints? */
+static int core_has_mismatch_bps(void)
+{
+ return debug_arch >= ARM_DEBUG_ARCH_V7_ECP14 && core_num_brps > 1;
+}
+
+u8 arch_get_debug_arch(void)
+{
+ return debug_arch;
+}
+
#define READ_WB_REG_CASE(OP2, M, VAL) \
case ((OP2 << 4) + M): \
ARM_DBG_READ(c ## M, OP2, VAL); \
@@ -131,94 +210,6 @@ static void write_wb_reg(int n, u32 val)
isb();
}
-/* Determine debug architecture. */
-static u8 get_debug_arch(void)
-{
- u32 didr;
-
- /* Do we implement the extended CPUID interface? */
- if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
- pr_warning("CPUID feature registers not supported. "
- "Assuming v6 debug is present.\n");
- return ARM_DEBUG_ARCH_V6;
- }
-
- ARM_DBG_READ(c0, 0, didr);
- return (didr >> 16) & 0xf;
-}
-
-u8 arch_get_debug_arch(void)
-{
- return debug_arch;
-}
-
-/* Determine number of BRP register available. */
-static int get_num_brp_resources(void)
-{
- u32 didr;
- ARM_DBG_READ(c0, 0, didr);
- return ((didr >> 24) & 0xf) + 1;
-}
-
-/* Does this core support mismatch breakpoints? */
-static int core_has_mismatch_brps(void)
-{
- return (get_debug_arch() >= ARM_DEBUG_ARCH_V7_ECP14 &&
- get_num_brp_resources() > 1);
-}
-
-/* Determine number of usable WRPs available. */
-static int get_num_wrps(void)
-{
- /*
- * FIXME: When a watchpoint fires, the only way to work out which
- * watchpoint it was is by disassembling the faulting instruction
- * and working out the address of the memory access.
- *
- * Furthermore, we can only do this if the watchpoint was precise
- * since imprecise watchpoints prevent us from calculating register
- * based addresses.
- *
- * Providing we have more than 1 breakpoint register, we only report
- * a single watchpoint register for the time being. This way, we always
- * know which watchpoint fired. In the future we can either add a
- * disassembler and address generation emulator, or we can insert a
- * check to see if the DFAR is set on watchpoint exception entry
- * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows
- * that it is set on some implementations].
- */
-
-#if 0
- int wrps;
- u32 didr;
- ARM_DBG_READ(c0, 0, didr);
- wrps = ((didr >> 28) & 0xf) + 1;
-#endif
- int wrps = 1;
-
- if (core_has_mismatch_brps() && wrps >= get_num_brp_resources())
- wrps = get_num_brp_resources() - 1;
-
- return wrps;
-}
-
-/* We reserve one breakpoint for each watchpoint. */
-static int get_num_reserved_brps(void)
-{
- if (core_has_mismatch_brps())
- return get_num_wrps();
- return 0;
-}
-
-/* Determine number of usable BRPs available. */
-static int get_num_brps(void)
-{
- int brps = get_num_brp_resources();
- if (core_has_mismatch_brps())
- brps -= get_num_reserved_brps();
- return brps;
-}
-
/*
* In order to access the breakpoint/watchpoint control registers,
* we must be running in debug monitor mode. Unfortunately, we can
@@ -239,12 +230,8 @@ static int enable_monitor_mode(void)
goto out;
}
- /* If monitor mode is already enabled, just return. */
- if (dscr & ARM_DSCR_MDBGEN)
- goto out;
-
/* Write to the corresponding DSCR. */
- switch (get_debug_arch()) {
+ switch (debug_arch) {
case ARM_DEBUG_ARCH_V6:
case ARM_DEBUG_ARCH_V6_1:
ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
@@ -259,30 +246,15 @@ static int enable_monitor_mode(void)
/* Check that the write made it through. */
ARM_DBG_READ(c1, 0, dscr);
- if (!(dscr & ARM_DSCR_MDBGEN))
+ if (WARN_ONCE(!(dscr & ARM_DSCR_MDBGEN),
+ "failed to enable monitor mode.")) {
ret = -EPERM;
+ }
out:
return ret;
}
-int hw_breakpoint_slots(int type)
-{
- /*
- * We can be called early, so don't rely on
- * our static variables being initialised.
- */
- switch (type) {
- case TYPE_INST:
- return get_num_brps();
- case TYPE_DATA:
- return get_num_wrps();
- default:
- pr_warning("unknown slot type: %d\n", type);
- return 0;
- }
-}
-
/*
* Check if 8-bit byte-address select is available.
* This clobbers WRP 0.
@@ -296,6 +268,9 @@ static u8 get_max_wp_len(void)
if (debug_arch < ARM_DEBUG_ARCH_V7_ECP14)
goto out;
+ if (enable_monitor_mode())
+ goto out;
+
memset(&ctrl, 0, sizeof(ctrl));
ctrl.len = ARM_BREAKPOINT_LEN_8;
ctrl_reg = encode_ctrl_reg(ctrl);
@@ -314,6 +289,23 @@ u8 arch_get_max_wp_len(void)
return max_watchpoint_len;
}
+/*
+ * Handler for reactivating a suspended watchpoint when the single
+ * step `mismatch' breakpoint is triggered.
+ */
+static void wp_single_step_handler(struct perf_event *bp, int unused,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ perf_event_enable(counter_arch_bp(bp)->suspended_wp);
+ unregister_hw_breakpoint(bp);
+}
+
+static int bp_is_single_step(struct perf_event *bp)
+{
+ return bp->overflow_handler == wp_single_step_handler;
+}
+
/*
* Install a perf counter breakpoint.
*/
@@ -322,41 +314,30 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
struct perf_event **slot, **slots;
int i, max_slots, ctrl_base, val_base, ret = 0;
- u32 addr, ctrl;
/* Ensure that we are in monitor mode and halting mode is disabled. */
ret = enable_monitor_mode();
if (ret)
goto out;
- addr = info->address;
- ctrl = encode_ctrl_reg(info->ctrl) | 0x1;
-
if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
/* Breakpoint */
ctrl_base = ARM_BASE_BCR;
val_base = ARM_BASE_BVR;
- slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
- max_slots = core_num_brps;
- if (info->step_ctrl.enabled) {
- /* Override the breakpoint data with the step data. */
- addr = info->trigger & ~0x3;
- ctrl = encode_ctrl_reg(info->step_ctrl);
+ slots = __get_cpu_var(bp_on_reg);
+ max_slots = core_num_brps - 1;
+
+ if (bp_is_single_step(bp)) {
+ info->ctrl.mismatch = 1;
+ i = max_slots;
+ slots[i] = bp;
+ goto setup;
}
} else {
/* Watchpoint */
- if (info->step_ctrl.enabled) {
- /* Install into the reserved breakpoint region. */
- ctrl_base = ARM_BASE_BCR + core_num_brps;
- val_base = ARM_BASE_BVR + core_num_brps;
- /* Override the watchpoint data with the step data. */
- addr = info->trigger & ~0x3;
- ctrl = encode_ctrl_reg(info->step_ctrl);
- } else {
- ctrl_base = ARM_BASE_WCR;
- val_base = ARM_BASE_WVR;
- }
- slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+ ctrl_base = ARM_BASE_WCR;
+ val_base = ARM_BASE_WVR;
+ slots = __get_cpu_var(wp_on_reg);
max_slots = core_num_wrps;
}
@@ -374,11 +355,12 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
goto out;
}
+setup:
/* Setup the address register. */
- write_wb_reg(val_base + i, addr);
+ write_wb_reg(val_base + i, info->address);
/* Setup the control register. */
- write_wb_reg(ctrl_base + i, ctrl);
+ write_wb_reg(ctrl_base + i, encode_ctrl_reg(info->ctrl) | 0x1);
out:
return ret;
@@ -393,15 +375,18 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
/* Breakpoint */
base = ARM_BASE_BCR;
- slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
- max_slots = core_num_brps;
+ slots = __get_cpu_var(bp_on_reg);
+ max_slots = core_num_brps - 1;
+
+ if (bp_is_single_step(bp)) {
+ i = max_slots;
+ slots[i] = NULL;
+ goto reset;
+ }
} else {
/* Watchpoint */
- if (info->step_ctrl.enabled)
- base = ARM_BASE_BCR + core_num_brps;
- else
- base = ARM_BASE_WCR;
- slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+ base = ARM_BASE_WCR;
+ slots = __get_cpu_var(wp_on_reg);
max_slots = core_num_wrps;
}
@@ -418,6 +403,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
return;
+reset:
/* Reset the control register. */
write_wb_reg(base + i, 0);
}
@@ -551,23 +537,12 @@ static int arch_build_bp_info(struct perf_event *bp)
return -EINVAL;
}
- /*
- * Breakpoints must be of length 2 (thumb) or 4 (ARM) bytes.
- * Watchpoints can be of length 1, 2, 4 or 8 bytes if supported
- * by the hardware and must be aligned to the appropriate number of
- * bytes.
- */
- if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
- info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
- info->ctrl.len != ARM_BREAKPOINT_LEN_4)
- return -EINVAL;
-
/* Address */
info->address = bp->attr.bp_addr;
/* Privilege */
info->ctrl.privilege = ARM_BREAKPOINT_USER;
- if (arch_check_bp_in_kernelspace(bp))
+ if (arch_check_bp_in_kernelspace(bp) && !bp_is_single_step(bp))
info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
/* Enabled? */
@@ -586,7 +561,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
{
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
int ret = 0;
- u32 offset, alignment_mask = 0x3;
+ u32 bytelen, max_len, offset, alignment_mask = 0x3;
/* Build the arch_hw_breakpoint. */
ret = arch_build_bp_info(bp);
@@ -596,85 +571,84 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
/* Check address alignment. */
if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
alignment_mask = 0x7;
- offset = info->address & alignment_mask;
- switch (offset) {
- case 0:
- /* Aligned */
- break;
- case 1:
- /* Allow single byte watchpoint. */
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
- break;
- case 2:
- /* Allow halfword watchpoints and breakpoints. */
- if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
- break;
- default:
- ret = -EINVAL;
- goto out;
- }
+ if (info->address & alignment_mask) {
+ /*
+ * Try to fix the alignment. This may result in a length
+ * that is too large, so we must check for that.
+ */
+ bytelen = get_hbp_len(info->ctrl.len);
+ max_len = info->ctrl.type == ARM_BREAKPOINT_EXECUTE ? 4 :
+ max_watchpoint_len;
+
+ if (max_len >= 8)
+ offset = info->address & 0x7;
+ else
+ offset = info->address & 0x3;
+
+ if (bytelen > (1 << ((max_len - (offset + 1)) >> 1))) {
+ ret = -EFBIG;
+ goto out;
+ }
- info->address &= ~alignment_mask;
- info->ctrl.len <<= offset;
+ info->ctrl.len <<= offset;
+ info->address &= ~offset;
+
+ pr_debug("breakpoint alignment fixup: length = 0x%x, "
+ "address = 0x%x\n", info->ctrl.len, info->address);
+ }
/*
* Currently we rely on an overflow handler to take
* care of single-stepping the breakpoint when it fires.
* In the case of userspace breakpoints on a core with V7 debug,
- * we can use the mismatch feature as a poor-man's hardware
- * single-step, but this only works for per-task breakpoints.
+ * we can use the mismatch feature as a poor-man's hardware single-step.
*/
if (WARN_ONCE(!bp->overflow_handler &&
- (arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps()
- || !bp->hw.bp_target),
+ (arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_bps()),
"overflow handler required but none found")) {
ret = -EINVAL;
+ goto out;
}
out:
return ret;
}
-/*
- * Enable/disable single-stepping over the breakpoint bp at address addr.
- */
-static void enable_single_step(struct perf_event *bp, u32 addr)
+static void update_mismatch_flag(int idx, int flag)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+ struct perf_event *bp = __get_cpu_var(bp_on_reg[idx]);
+ struct arch_hw_breakpoint *info;
- arch_uninstall_hw_breakpoint(bp);
- info->step_ctrl.mismatch = 1;
- info->step_ctrl.len = ARM_BREAKPOINT_LEN_4;
- info->step_ctrl.type = ARM_BREAKPOINT_EXECUTE;
- info->step_ctrl.privilege = info->ctrl.privilege;
- info->step_ctrl.enabled = 1;
- info->trigger = addr;
- arch_install_hw_breakpoint(bp);
-}
+ if (bp == NULL)
+ return;
-static void disable_single_step(struct perf_event *bp)
-{
- arch_uninstall_hw_breakpoint(bp);
- counter_arch_bp(bp)->step_ctrl.enabled = 0;
- arch_install_hw_breakpoint(bp);
+ info = counter_arch_bp(bp);
+
+ /* Update the mismatch field to enter/exit `single-step' mode */
+ if (!bp->overflow_handler && info->ctrl.mismatch != flag) {
+ info->ctrl.mismatch = flag;
+ write_wb_reg(ARM_BASE_BCR + idx, encode_ctrl_reg(info->ctrl) | 0x1);
+ }
}
static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
{
int i;
- struct perf_event *wp, **slots;
+ struct perf_event *bp, **slots = __get_cpu_var(wp_on_reg);
struct arch_hw_breakpoint *info;
-
- slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+ struct perf_event_attr attr;
/* Without a disassembler, we can only handle 1 watchpoint. */
BUG_ON(core_num_wrps > 1);
+ hw_breakpoint_init(&attr);
+ attr.bp_addr = regs->ARM_pc & ~0x3;
+ attr.bp_len = HW_BREAKPOINT_LEN_4;
+ attr.bp_type = HW_BREAKPOINT_X;
+
for (i = 0; i < core_num_wrps; ++i) {
rcu_read_lock();
- wp = slots[i];
-
- if (wp == NULL) {
+ if (slots[i] == NULL) {
rcu_read_unlock();
continue;
}
@@ -684,51 +658,24 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
* single watchpoint, we can set the trigger to the lowest
* possible faulting address.
*/
- info = counter_arch_bp(wp);
- info->trigger = wp->attr.bp_addr;
+ info = counter_arch_bp(slots[i]);
+ info->trigger = slots[i]->attr.bp_addr;
pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
- perf_bp_event(wp, regs);
+ perf_bp_event(slots[i], regs);
/*
* If no overflow handler is present, insert a temporary
* mismatch breakpoint so we can single-step over the
* watchpoint trigger.
*/
- if (!wp->overflow_handler)
- enable_single_step(wp, instruction_pointer(regs));
-
- rcu_read_unlock();
- }
-}
-
-static void watchpoint_single_step_handler(unsigned long pc)
-{
- int i;
- struct perf_event *wp, **slots;
- struct arch_hw_breakpoint *info;
-
- slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
-
- for (i = 0; i < core_num_reserved_brps; ++i) {
- rcu_read_lock();
-
- wp = slots[i];
-
- if (wp == NULL)
- goto unlock;
-
- info = counter_arch_bp(wp);
- if (!info->step_ctrl.enabled)
- goto unlock;
-
- /*
- * Restore the original watchpoint if we've completed the
- * single-step.
- */
- if (info->trigger != pc)
- disable_single_step(wp);
+ if (!slots[i]->overflow_handler) {
+ bp = register_user_hw_breakpoint(&attr,
+ wp_single_step_handler,
+ current);
+ counter_arch_bp(bp)->suspended_wp = slots[i];
+ perf_event_disable(slots[i]);
+ }
-unlock:
rcu_read_unlock();
}
}
@@ -736,69 +683,62 @@ static void watchpoint_single_step_handler(unsigned long pc)
static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
{
int i;
+ int mismatch;
u32 ctrl_reg, val, addr;
- struct perf_event *bp, **slots;
+ struct perf_event *bp, **slots = __get_cpu_var(bp_on_reg);
struct arch_hw_breakpoint *info;
struct arch_hw_breakpoint_ctrl ctrl;
- slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
-
/* The exception entry code places the amended lr in the PC. */
addr = regs->ARM_pc;
- /* Check the currently installed breakpoints first. */
for (i = 0; i < core_num_brps; ++i) {
rcu_read_lock();
bp = slots[i];
- if (bp == NULL)
- goto unlock;
+ if (bp == NULL) {
+ rcu_read_unlock();
+ continue;
+ }
- info = counter_arch_bp(bp);
+ mismatch = 0;
/* Check if the breakpoint value matches. */
val = read_wb_reg(ARM_BASE_BVR + i);
if (val != (addr & ~0x3))
- goto mismatch;
+ goto unlock;
/* Possible match, check the byte address select to confirm. */
ctrl_reg = read_wb_reg(ARM_BASE_BCR + i);
decode_ctrl_reg(ctrl_reg, &ctrl);
if ((1 << (addr & 0x3)) & ctrl.len) {
+ mismatch = 1;
+ info = counter_arch_bp(bp);
info->trigger = addr;
+ }
+
+unlock:
+ if ((mismatch && !info->ctrl.mismatch) || bp_is_single_step(bp)) {
pr_debug("breakpoint fired: address = 0x%x\n", addr);
perf_bp_event(bp, regs);
- if (!bp->overflow_handler)
- enable_single_step(bp, addr);
- goto unlock;
}
-mismatch:
- /* If we're stepping a breakpoint, it can now be restored. */
- if (info->step_ctrl.enabled)
- disable_single_step(bp);
-unlock:
+ update_mismatch_flag(i, mismatch);
rcu_read_unlock();
}
-
- /* Handle any pending watchpoint single-step breakpoints. */
- watchpoint_single_step_handler(addr);
}
/*
* Called from either the Data Abort Handler [watchpoint] or the
- * Prefetch Abort Handler [breakpoint] with preemption disabled.
+ * Prefetch Abort Handler [breakpoint].
*/
static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
- int ret = 0;
+ int ret = 1; /* Unhandled fault. */
u32 dscr;
- /* We must be called with preemption disabled. */
- WARN_ON(preemptible());
-
/* We only handle watchpoints and hardware breakpoints. */
ARM_DBG_READ(c1, 0, dscr);
@@ -813,47 +753,25 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
watchpoint_handler(addr, regs);
break;
default:
- ret = 1; /* Unhandled fault. */
+ goto out;
}
- /*
- * Re-enable preemption after it was disabled in the
- * low-level exception handling code.
- */
- preempt_enable();
-
+ ret = 0;
+out:
return ret;
}
/*
* One-time initialisation.
*/
-static void reset_ctrl_regs(void *unused)
+static void __init reset_ctrl_regs(void *unused)
{
int i;
- /*
- * v7 debug contains save and restore registers so that debug state
- * can be maintained across low-power modes without leaving
- * the debug logic powered up. It is IMPLEMENTATION DEFINED whether
- * we can write to the debug registers out of reset, so we must
- * unlock the OS Lock Access Register to avoid taking undefined
- * instruction exceptions later on.
- */
- if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) {
- /*
- * Unconditionally clear the lock by writing a value
- * other than 0xC5ACCE55 to the access register.
- */
- asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0));
- isb();
- }
-
if (enable_monitor_mode())
return;
- /* We must also reset any reserved registers. */
- for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) {
+ for (i = 0; i < core_num_brps; ++i) {
write_wb_reg(ARM_BASE_BCR + i, 0UL);
write_wb_reg(ARM_BASE_BVR + i, 0UL);
}
@@ -864,57 +782,45 @@ static void reset_ctrl_regs(void *unused)
}
}
-static int __cpuinit dbg_reset_notify(struct notifier_block *self,
- unsigned long action, void *cpu)
-{
- if (action == CPU_ONLINE)
- smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1);
- return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata dbg_reset_nb = {
- .notifier_call = dbg_reset_notify,
-};
-
static int __init arch_hw_breakpoint_init(void)
{
+ int ret = 0;
u32 dscr;
debug_arch = get_debug_arch();
if (debug_arch > ARM_DEBUG_ARCH_V7_ECP14) {
pr_info("debug architecture 0x%x unsupported.\n", debug_arch);
- return 0;
+ ret = -ENODEV;
+ goto out;
}
/* Determine how many BRPs/WRPs are available. */
core_num_brps = get_num_brps();
- core_num_reserved_brps = get_num_reserved_brps();
core_num_wrps = get_num_wrps();
pr_info("found %d breakpoint and %d watchpoint registers.\n",
- core_num_brps + core_num_reserved_brps, core_num_wrps);
+ core_num_brps, core_num_wrps);
- if (core_num_reserved_brps)
- pr_info("%d breakpoint(s) reserved for watchpoint "
- "single-step.\n", core_num_reserved_brps);
+ if (core_has_mismatch_bps())
+ pr_info("1 breakpoint reserved for watchpoint single-step.\n");
ARM_DBG_READ(c1, 0, dscr);
if (dscr & ARM_DSCR_HDBGEN) {
pr_warning("halting debug mode enabled. Assuming maximum "
"watchpoint size of 4 bytes.");
} else {
+ /* Work out the maximum supported watchpoint length. */
+ max_watchpoint_len = get_max_wp_len();
+ pr_info("maximum watchpoint size is %u bytes.\n",
+ max_watchpoint_len);
+
/*
* Reset the breakpoint resources. We assume that a halting
* debugger will leave the world in a nice state for us.
*/
smp_call_function(reset_ctrl_regs, NULL, 1);
reset_ctrl_regs(NULL);
-
- /* Work out the maximum supported watchpoint length. */
- max_watchpoint_len = get_max_wp_len();
- pr_info("maximum watchpoint size is %u bytes.\n",
- max_watchpoint_len);
}
/* Register debug fault handler. */
@@ -923,9 +829,8 @@ static int __init arch_hw_breakpoint_init(void)
hook_ifault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
"breakpoint debug exception");
- /* Register hotplug notifier. */
- register_cpu_notifier(&dbg_reset_nb);
- return 0;
+out:
+ return ret;
}
arch_initcall(arch_hw_breakpoint_init);
diff --git a/trunk/arch/arm/kernel/irq.c b/trunk/arch/arm/kernel/irq.c
index 6d616333340f..36ad3be4692a 100644
--- a/trunk/arch/arm/kernel/irq.c
+++ b/trunk/arch/arm/kernel/irq.c
@@ -35,7 +35,6 @@
#include
#include
#include
-#include
#include
#include
@@ -106,8 +105,7 @@ int show_interrupts(struct seq_file *p, void *v)
* come via this function. Instead, they should provide their
* own 'handler'
*/
-asmlinkage void __exception_irq_entry
-asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
+asmlinkage void __exception asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
diff --git a/trunk/arch/arm/kernel/perf_event.c b/trunk/arch/arm/kernel/perf_event.c
index 624e2a5de2b3..07a50357492a 100644
--- a/trunk/arch/arm/kernel/perf_event.c
+++ b/trunk/arch/arm/kernel/perf_event.c
@@ -4,7 +4,9 @@
* ARM performance counter support.
*
* Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
- * Copyright (C) 2010 ARM Ltd., Will Deacon
+ *
+ * ARMv7 support: Jean Pihet
+ * 2010 (c) MontaVista Software, LLC.
*
* This code is based on the sparc64 perf event code, which is in turn based
* on the x86 code. Callchain code is based on the ARM OProfile backtrace
@@ -32,7 +34,7 @@ static struct platform_device *pmu_device;
* Hardware lock to serialize accesses to PMU registers. Needed for the
* read/modify/write sequences.
*/
-static DEFINE_RAW_SPINLOCK(pmu_lock);
+DEFINE_SPINLOCK(pmu_lock);
/*
* ARMv6 supports a maximum of 3 events, starting from index 1. If we add
@@ -65,25 +67,31 @@ struct cpu_hw_events {
*/
unsigned long active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
};
-static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+
+/* PMU names. */
+static const char *arm_pmu_names[] = {
+ [ARM_PERF_PMU_ID_XSCALE1] = "xscale1",
+ [ARM_PERF_PMU_ID_XSCALE2] = "xscale2",
+ [ARM_PERF_PMU_ID_V6] = "v6",
+ [ARM_PERF_PMU_ID_V6MP] = "v6mpcore",
+ [ARM_PERF_PMU_ID_CA8] = "ARMv7 Cortex-A8",
+ [ARM_PERF_PMU_ID_CA9] = "ARMv7 Cortex-A9",
+};
struct arm_pmu {
enum arm_perf_pmu_ids id;
- const char *name;
irqreturn_t (*handle_irq)(int irq_num, void *dev);
void (*enable)(struct hw_perf_event *evt, int idx);
void (*disable)(struct hw_perf_event *evt, int idx);
+ int (*event_map)(int evt);
+ u64 (*raw_event)(u64);
int (*get_event_idx)(struct cpu_hw_events *cpuc,
struct hw_perf_event *hwc);
u32 (*read_counter)(int idx);
void (*write_counter)(int idx, u32 val);
void (*start)(void);
void (*stop)(void);
- const unsigned (*cache_map)[PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX];
- const unsigned (*event_map)[PERF_COUNT_HW_MAX];
- u32 raw_event_mask;
int num_events;
u64 max_period;
};
@@ -128,6 +136,10 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
#define CACHE_OP_UNSUPPORTED 0xFFFF
+static unsigned armpmu_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX];
+
static int
armpmu_map_cache_event(u64 config)
{
@@ -145,7 +157,7 @@ armpmu_map_cache_event(u64 config)
if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
return -EINVAL;
- ret = (int)(*armpmu->cache_map)[cache_type][cache_op][cache_result];
+ ret = (int)armpmu_perf_cache_map[cache_type][cache_op][cache_result];
if (ret == CACHE_OP_UNSUPPORTED)
return -ENOENT;
@@ -153,19 +165,6 @@ armpmu_map_cache_event(u64 config)
return ret;
}
-static int
-armpmu_map_event(u64 config)
-{
- int mapping = (*armpmu->event_map)[config];
- return mapping == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : mapping;
-}
-
-static int
-armpmu_map_raw_event(u64 config)
-{
- return (int)(config & armpmu->raw_event_mask);
-}
-
static int
armpmu_event_set_period(struct perf_event *event,
struct hw_perf_event *hwc,
@@ -459,11 +458,11 @@ __hw_perf_event_init(struct perf_event *event)
/* Decode the generic type into an ARM event identifier. */
if (PERF_TYPE_HARDWARE == event->attr.type) {
- mapping = armpmu_map_event(event->attr.config);
+ mapping = armpmu->event_map(event->attr.config);
} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
mapping = armpmu_map_cache_event(event->attr.config);
} else if (PERF_TYPE_RAW == event->attr.type) {
- mapping = armpmu_map_raw_event(event->attr.config);
+ mapping = armpmu->raw_event(event->attr.config);
} else {
pr_debug("event type %x not supported\n", event->attr.type);
return -EOPNOTSUPP;
@@ -604,10 +603,2366 @@ static struct pmu pmu = {
.read = armpmu_read,
};
-/* Include the PMU-specific implementations. */
-#include "perf_event_xscale.c"
-#include "perf_event_v6.c"
-#include "perf_event_v7.c"
+/*
+ * ARMv6 Performance counter handling code.
+ *
+ * ARMv6 has 2 configurable performance counters and a single cycle counter.
+ * They all share a single reset bit but can be written to zero so we can use
+ * that for a reset.
+ *
+ * The counters can't be individually enabled or disabled so when we remove
+ * one event and replace it with another we could get spurious counts from the
+ * wrong event. However, we can take advantage of the fact that the
+ * performance counters can export events to the event bus, and the event bus
+ * itself can be monitored. This requires that we *don't* export the events to
+ * the event bus. The procedure for disabling a configurable counter is:
+ * - change the counter to count the ETMEXTOUT[0] signal (0x20). This
+ * effectively stops the counter from counting.
+ * - disable the counter's interrupt generation (each counter has it's
+ * own interrupt enable bit).
+ * Once stopped, the counter value can be written as 0 to reset.
+ *
+ * To enable a counter:
+ * - enable the counter's interrupt generation.
+ * - set the new event type.
+ *
+ * Note: the dedicated cycle counter only counts cycles and can't be
+ * enabled/disabled independently of the others. When we want to disable the
+ * cycle counter, we have to just disable the interrupt reporting and start
+ * ignoring that counter. When re-enabling, we have to reset the value and
+ * enable the interrupt.
+ */
+
+enum armv6_perf_types {
+ ARMV6_PERFCTR_ICACHE_MISS = 0x0,
+ ARMV6_PERFCTR_IBUF_STALL = 0x1,
+ ARMV6_PERFCTR_DDEP_STALL = 0x2,
+ ARMV6_PERFCTR_ITLB_MISS = 0x3,
+ ARMV6_PERFCTR_DTLB_MISS = 0x4,
+ ARMV6_PERFCTR_BR_EXEC = 0x5,
+ ARMV6_PERFCTR_BR_MISPREDICT = 0x6,
+ ARMV6_PERFCTR_INSTR_EXEC = 0x7,
+ ARMV6_PERFCTR_DCACHE_HIT = 0x9,
+ ARMV6_PERFCTR_DCACHE_ACCESS = 0xA,
+ ARMV6_PERFCTR_DCACHE_MISS = 0xB,
+ ARMV6_PERFCTR_DCACHE_WBACK = 0xC,
+ ARMV6_PERFCTR_SW_PC_CHANGE = 0xD,
+ ARMV6_PERFCTR_MAIN_TLB_MISS = 0xF,
+ ARMV6_PERFCTR_EXPL_D_ACCESS = 0x10,
+ ARMV6_PERFCTR_LSU_FULL_STALL = 0x11,
+ ARMV6_PERFCTR_WBUF_DRAINED = 0x12,
+ ARMV6_PERFCTR_CPU_CYCLES = 0xFF,
+ ARMV6_PERFCTR_NOP = 0x20,
+};
+
+enum armv6_counters {
+ ARMV6_CYCLE_COUNTER = 1,
+ ARMV6_COUNTER0,
+ ARMV6_COUNTER1,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT,
+ [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(L1D)] = {
+ /*
+ * The performance counters don't differentiate between read
+ * and write accesses/misses so this isn't strictly correct,
+ * but it's the best we can do. Writes and reads get
+ * combined.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(DTLB)] = {
+ /*
+ * The ARM performance counters can count micro DTLB misses,
+ * micro ITLB misses and main TLB misses. There isn't an event
+ * for TLB misses, so use the micro misses here and if users
+ * want the main TLB misses they can use a raw counter.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+};
+
+enum armv6mpcore_perf_types {
+ ARMV6MPCORE_PERFCTR_ICACHE_MISS = 0x0,
+ ARMV6MPCORE_PERFCTR_IBUF_STALL = 0x1,
+ ARMV6MPCORE_PERFCTR_DDEP_STALL = 0x2,
+ ARMV6MPCORE_PERFCTR_ITLB_MISS = 0x3,
+ ARMV6MPCORE_PERFCTR_DTLB_MISS = 0x4,
+ ARMV6MPCORE_PERFCTR_BR_EXEC = 0x5,
+ ARMV6MPCORE_PERFCTR_BR_NOTPREDICT = 0x6,
+ ARMV6MPCORE_PERFCTR_BR_MISPREDICT = 0x7,
+ ARMV6MPCORE_PERFCTR_INSTR_EXEC = 0x8,
+ ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
+ ARMV6MPCORE_PERFCTR_DCACHE_RDMISS = 0xB,
+ ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
+ ARMV6MPCORE_PERFCTR_DCACHE_WRMISS = 0xD,
+ ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
+ ARMV6MPCORE_PERFCTR_SW_PC_CHANGE = 0xF,
+ ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS = 0x10,
+ ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
+ ARMV6MPCORE_PERFCTR_LSU_FULL_STALL = 0x12,
+ ARMV6MPCORE_PERFCTR_WBUF_DRAINED = 0x13,
+ ARMV6MPCORE_PERFCTR_CPU_CYCLES = 0xFF,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
+ [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] =
+ ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
+ [C(RESULT_MISS)] =
+ ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] =
+ ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
+ [C(RESULT_MISS)] =
+ ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(DTLB)] = {
+ /*
+ * The ARM performance counters can count micro DTLB misses,
+ * micro ITLB misses and main TLB misses. There isn't an event
+ * for TLB misses, so use the micro misses here and if users
+ * want the main TLB misses they can use a raw counter.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+};
+
+static inline unsigned long
+armv6_pmcr_read(void)
+{
+ u32 val;
+ asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r"(val));
+ return val;
+}
+
+static inline void
+armv6_pmcr_write(unsigned long val)
+{
+ asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r"(val));
+}
+
+#define ARMV6_PMCR_ENABLE (1 << 0)
+#define ARMV6_PMCR_CTR01_RESET (1 << 1)
+#define ARMV6_PMCR_CCOUNT_RESET (1 << 2)
+#define ARMV6_PMCR_CCOUNT_DIV (1 << 3)
+#define ARMV6_PMCR_COUNT0_IEN (1 << 4)
+#define ARMV6_PMCR_COUNT1_IEN (1 << 5)
+#define ARMV6_PMCR_CCOUNT_IEN (1 << 6)
+#define ARMV6_PMCR_COUNT0_OVERFLOW (1 << 8)
+#define ARMV6_PMCR_COUNT1_OVERFLOW (1 << 9)
+#define ARMV6_PMCR_CCOUNT_OVERFLOW (1 << 10)
+#define ARMV6_PMCR_EVT_COUNT0_SHIFT 20
+#define ARMV6_PMCR_EVT_COUNT0_MASK (0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
+#define ARMV6_PMCR_EVT_COUNT1_SHIFT 12
+#define ARMV6_PMCR_EVT_COUNT1_MASK (0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)
+
+#define ARMV6_PMCR_OVERFLOWED_MASK \
+ (ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
+ ARMV6_PMCR_CCOUNT_OVERFLOW)
+
+static inline int
+armv6_pmcr_has_overflowed(unsigned long pmcr)
+{
+ return (pmcr & ARMV6_PMCR_OVERFLOWED_MASK);
+}
+
+static inline int
+armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
+ enum armv6_counters counter)
+{
+ int ret = 0;
+
+ if (ARMV6_CYCLE_COUNTER == counter)
+ ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
+ else if (ARMV6_COUNTER0 == counter)
+ ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
+ else if (ARMV6_COUNTER1 == counter)
+ ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
+ else
+ WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+ return ret;
+}
+
+static inline u32
+armv6pmu_read_counter(int counter)
+{
+ unsigned long value = 0;
+
+ if (ARMV6_CYCLE_COUNTER == counter)
+ asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r"(value));
+ else if (ARMV6_COUNTER0 == counter)
+ asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r"(value));
+ else if (ARMV6_COUNTER1 == counter)
+ asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r"(value));
+ else
+ WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+ return value;
+}
+
+static inline void
+armv6pmu_write_counter(int counter,
+ u32 value)
+{
+ if (ARMV6_CYCLE_COUNTER == counter)
+ asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r"(value));
+ else if (ARMV6_COUNTER0 == counter)
+ asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r"(value));
+ else if (ARMV6_COUNTER1 == counter)
+ asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r"(value));
+ else
+ WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+}
+
+void
+armv6pmu_enable_event(struct hw_perf_event *hwc,
+ int idx)
+{
+ unsigned long val, mask, evt, flags;
+
+ if (ARMV6_CYCLE_COUNTER == idx) {
+ mask = 0;
+ evt = ARMV6_PMCR_CCOUNT_IEN;
+ } else if (ARMV6_COUNTER0 == idx) {
+ mask = ARMV6_PMCR_EVT_COUNT0_MASK;
+ evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
+ ARMV6_PMCR_COUNT0_IEN;
+ } else if (ARMV6_COUNTER1 == idx) {
+ mask = ARMV6_PMCR_EVT_COUNT1_MASK;
+ evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
+ ARMV6_PMCR_COUNT1_IEN;
+ } else {
+ WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+ return;
+ }
+
+ /*
+ * Mask out the current event and set the counter to count the event
+ * that we're interested in.
+ */
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = armv6_pmcr_read();
+ val &= ~mask;
+ val |= evt;
+ armv6_pmcr_write(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static irqreturn_t
+armv6pmu_handle_irq(int irq_num,
+ void *dev)
+{
+ unsigned long pmcr = armv6_pmcr_read();
+ struct perf_sample_data data;
+ struct cpu_hw_events *cpuc;
+ struct pt_regs *regs;
+ int idx;
+
+ if (!armv6_pmcr_has_overflowed(pmcr))
+ return IRQ_NONE;
+
+ regs = get_irq_regs();
+
+ /*
+ * The interrupts are cleared by writing the overflow flags back to
+ * the control register. All of the other bits don't have any effect
+ * if they are rewritten, so write the whole value back.
+ */
+ armv6_pmcr_write(pmcr);
+
+ perf_sample_data_init(&data, 0);
+
+ cpuc = &__get_cpu_var(cpu_hw_events);
+ for (idx = 0; idx <= armpmu->num_events; ++idx) {
+ struct perf_event *event = cpuc->events[idx];
+ struct hw_perf_event *hwc;
+
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ /*
+ * We have a single interrupt for all counters. Check that
+ * each counter has overflowed before we process it.
+ */
+ if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
+ continue;
+
+ hwc = &event->hw;
+ armpmu_event_update(event, hwc, idx);
+ data.period = event->hw.last_period;
+ if (!armpmu_event_set_period(event, hwc, idx))
+ continue;
+
+ if (perf_event_overflow(event, 0, &data, regs))
+ armpmu->disable(hwc, idx);
+ }
+
+ /*
+ * Handle the pending perf events.
+ *
+ * Note: this call *must* be run with interrupts disabled. For
+ * platforms that can have the PMU interrupts raised as an NMI, this
+ * will not work.
+ */
+ irq_work_run();
+
+ return IRQ_HANDLED;
+}
+
+static void
+armv6pmu_start(void)
+{
+ unsigned long flags, val;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = armv6_pmcr_read();
+ val |= ARMV6_PMCR_ENABLE;
+ armv6_pmcr_write(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+void
+armv6pmu_stop(void)
+{
+ unsigned long flags, val;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = armv6_pmcr_read();
+ val &= ~ARMV6_PMCR_ENABLE;
+ armv6_pmcr_write(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline int
+armv6pmu_event_map(int config)
+{
+ int mapping = armv6_perf_map[config];
+ if (HW_OP_UNSUPPORTED == mapping)
+ mapping = -EOPNOTSUPP;
+ return mapping;
+}
+
+static inline int
+armv6mpcore_pmu_event_map(int config)
+{
+ int mapping = armv6mpcore_perf_map[config];
+ if (HW_OP_UNSUPPORTED == mapping)
+ mapping = -EOPNOTSUPP;
+ return mapping;
+}
+
+static u64
+armv6pmu_raw_event(u64 config)
+{
+ return config & 0xff;
+}
+
+static int
+armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
+ struct hw_perf_event *event)
+{
+ /* Always place a cycle counter into the cycle counter. */
+ if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) {
+ if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
+ return -EAGAIN;
+
+ return ARMV6_CYCLE_COUNTER;
+ } else {
+ /*
+ * For anything other than a cycle counter, try and use
+ * counter0 and counter1.
+ */
+ if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask)) {
+ return ARMV6_COUNTER1;
+ }
+
+ if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask)) {
+ return ARMV6_COUNTER0;
+ }
+
+ /* The counters are all in use. */
+ return -EAGAIN;
+ }
+}
+
+static void
+armv6pmu_disable_event(struct hw_perf_event *hwc,
+ int idx)
+{
+ unsigned long val, mask, evt, flags;
+
+ if (ARMV6_CYCLE_COUNTER == idx) {
+ mask = ARMV6_PMCR_CCOUNT_IEN;
+ evt = 0;
+ } else if (ARMV6_COUNTER0 == idx) {
+ mask = ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
+ evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
+ } else if (ARMV6_COUNTER1 == idx) {
+ mask = ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
+ evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
+ } else {
+ WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+ return;
+ }
+
+ /*
+ * Mask out the current event and set the counter to count the number
+ * of ETM bus signal assertion cycles. The external reporting should
+ * be disabled and so this should never increment.
+ */
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = armv6_pmcr_read();
+ val &= ~mask;
+ val |= evt;
+ armv6_pmcr_write(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
+ int idx)
+{
+ unsigned long val, mask, flags, evt = 0;
+
+ if (ARMV6_CYCLE_COUNTER == idx) {
+ mask = ARMV6_PMCR_CCOUNT_IEN;
+ } else if (ARMV6_COUNTER0 == idx) {
+ mask = ARMV6_PMCR_COUNT0_IEN;
+ } else if (ARMV6_COUNTER1 == idx) {
+ mask = ARMV6_PMCR_COUNT1_IEN;
+ } else {
+ WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+ return;
+ }
+
+ /*
+ * Unlike UP ARMv6, we don't have a way of stopping the counters. We
+ * simply disable the interrupt reporting.
+ */
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = armv6_pmcr_read();
+ val &= ~mask;
+ val |= evt;
+ armv6_pmcr_write(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static const struct arm_pmu armv6pmu = {
+ .id = ARM_PERF_PMU_ID_V6,
+ .handle_irq = armv6pmu_handle_irq,
+ .enable = armv6pmu_enable_event,
+ .disable = armv6pmu_disable_event,
+ .event_map = armv6pmu_event_map,
+ .raw_event = armv6pmu_raw_event,
+ .read_counter = armv6pmu_read_counter,
+ .write_counter = armv6pmu_write_counter,
+ .get_event_idx = armv6pmu_get_event_idx,
+ .start = armv6pmu_start,
+ .stop = armv6pmu_stop,
+ .num_events = 3,
+ .max_period = (1LLU << 32) - 1,
+};
+
+/*
+ * ARMv6mpcore is almost identical to single core ARMv6 with the exception
+ * that some of the events have different enumerations and that there is no
+ * *hack* to stop the programmable counters. To stop the counters we simply
+ * disable the interrupt reporting and update the event. When unthrottling we
+ * reset the period and enable the interrupt reporting.
+ */
+static const struct arm_pmu armv6mpcore_pmu = {
+ .id = ARM_PERF_PMU_ID_V6MP,
+ .handle_irq = armv6pmu_handle_irq,
+ .enable = armv6pmu_enable_event,
+ .disable = armv6mpcore_pmu_disable_event,
+ .event_map = armv6mpcore_pmu_event_map,
+ .raw_event = armv6pmu_raw_event,
+ .read_counter = armv6pmu_read_counter,
+ .write_counter = armv6pmu_write_counter,
+ .get_event_idx = armv6pmu_get_event_idx,
+ .start = armv6pmu_start,
+ .stop = armv6pmu_stop,
+ .num_events = 3,
+ .max_period = (1LLU << 32) - 1,
+};
+
+/*
+ * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code.
+ *
+ * Copied from ARMv6 code, with the low level code inspired
+ * by the ARMv7 Oprofile code.
+ *
+ * Cortex-A8 has up to 4 configurable performance counters and
+ * a single cycle counter.
+ * Cortex-A9 has up to 31 configurable performance counters and
+ * a single cycle counter.
+ *
+ * All counters can be enabled/disabled and IRQ masked separately. The cycle
+ * counter and all 4 performance counters together can be reset separately.
+ */
+
+/* Common ARMv7 event types */
+enum armv7_perf_types {
+ ARMV7_PERFCTR_PMNC_SW_INCR = 0x00,
+ ARMV7_PERFCTR_IFETCH_MISS = 0x01,
+ ARMV7_PERFCTR_ITLB_MISS = 0x02,
+ ARMV7_PERFCTR_DCACHE_REFILL = 0x03,
+ ARMV7_PERFCTR_DCACHE_ACCESS = 0x04,
+ ARMV7_PERFCTR_DTLB_REFILL = 0x05,
+ ARMV7_PERFCTR_DREAD = 0x06,
+ ARMV7_PERFCTR_DWRITE = 0x07,
+
+ ARMV7_PERFCTR_EXC_TAKEN = 0x09,
+ ARMV7_PERFCTR_EXC_EXECUTED = 0x0A,
+ ARMV7_PERFCTR_CID_WRITE = 0x0B,
+ /* ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
+ * It counts:
+ * - all branch instructions,
+ * - instructions that explicitly write the PC,
+ * - exception generating instructions.
+ */
+ ARMV7_PERFCTR_PC_WRITE = 0x0C,
+ ARMV7_PERFCTR_PC_IMM_BRANCH = 0x0D,
+ ARMV7_PERFCTR_UNALIGNED_ACCESS = 0x0F,
+ ARMV7_PERFCTR_PC_BRANCH_MIS_PRED = 0x10,
+ ARMV7_PERFCTR_CLOCK_CYCLES = 0x11,
+
+ ARMV7_PERFCTR_PC_BRANCH_MIS_USED = 0x12,
+
+ ARMV7_PERFCTR_CPU_CYCLES = 0xFF
+};
+
+/* ARMv7 Cortex-A8 specific event types */
+enum armv7_a8_perf_types {
+ ARMV7_PERFCTR_INSTR_EXECUTED = 0x08,
+
+ ARMV7_PERFCTR_PC_PROC_RETURN = 0x0E,
+
+ ARMV7_PERFCTR_WRITE_BUFFER_FULL = 0x40,
+ ARMV7_PERFCTR_L2_STORE_MERGED = 0x41,
+ ARMV7_PERFCTR_L2_STORE_BUFF = 0x42,
+ ARMV7_PERFCTR_L2_ACCESS = 0x43,
+ ARMV7_PERFCTR_L2_CACH_MISS = 0x44,
+ ARMV7_PERFCTR_AXI_READ_CYCLES = 0x45,
+ ARMV7_PERFCTR_AXI_WRITE_CYCLES = 0x46,
+ ARMV7_PERFCTR_MEMORY_REPLAY = 0x47,
+ ARMV7_PERFCTR_UNALIGNED_ACCESS_REPLAY = 0x48,
+ ARMV7_PERFCTR_L1_DATA_MISS = 0x49,
+ ARMV7_PERFCTR_L1_INST_MISS = 0x4A,
+ ARMV7_PERFCTR_L1_DATA_COLORING = 0x4B,
+ ARMV7_PERFCTR_L1_NEON_DATA = 0x4C,
+ ARMV7_PERFCTR_L1_NEON_CACH_DATA = 0x4D,
+ ARMV7_PERFCTR_L2_NEON = 0x4E,
+ ARMV7_PERFCTR_L2_NEON_HIT = 0x4F,
+ ARMV7_PERFCTR_L1_INST = 0x50,
+ ARMV7_PERFCTR_PC_RETURN_MIS_PRED = 0x51,
+ ARMV7_PERFCTR_PC_BRANCH_FAILED = 0x52,
+ ARMV7_PERFCTR_PC_BRANCH_TAKEN = 0x53,
+ ARMV7_PERFCTR_PC_BRANCH_EXECUTED = 0x54,
+ ARMV7_PERFCTR_OP_EXECUTED = 0x55,
+ ARMV7_PERFCTR_CYCLES_INST_STALL = 0x56,
+ ARMV7_PERFCTR_CYCLES_INST = 0x57,
+ ARMV7_PERFCTR_CYCLES_NEON_DATA_STALL = 0x58,
+ ARMV7_PERFCTR_CYCLES_NEON_INST_STALL = 0x59,
+ ARMV7_PERFCTR_NEON_CYCLES = 0x5A,
+
+ ARMV7_PERFCTR_PMU0_EVENTS = 0x70,
+ ARMV7_PERFCTR_PMU1_EVENTS = 0x71,
+ ARMV7_PERFCTR_PMU_EVENTS = 0x72,
+};
+
+/* ARMv7 Cortex-A9 specific event types */
+enum armv7_a9_perf_types {
+ ARMV7_PERFCTR_JAVA_HW_BYTECODE_EXEC = 0x40,
+ ARMV7_PERFCTR_JAVA_SW_BYTECODE_EXEC = 0x41,
+ ARMV7_PERFCTR_JAZELLE_BRANCH_EXEC = 0x42,
+
+ ARMV7_PERFCTR_COHERENT_LINE_MISS = 0x50,
+ ARMV7_PERFCTR_COHERENT_LINE_HIT = 0x51,
+
+ ARMV7_PERFCTR_ICACHE_DEP_STALL_CYCLES = 0x60,
+ ARMV7_PERFCTR_DCACHE_DEP_STALL_CYCLES = 0x61,
+ ARMV7_PERFCTR_TLB_MISS_DEP_STALL_CYCLES = 0x62,
+ ARMV7_PERFCTR_STREX_EXECUTED_PASSED = 0x63,
+ ARMV7_PERFCTR_STREX_EXECUTED_FAILED = 0x64,
+ ARMV7_PERFCTR_DATA_EVICTION = 0x65,
+ ARMV7_PERFCTR_ISSUE_STAGE_NO_INST = 0x66,
+ ARMV7_PERFCTR_ISSUE_STAGE_EMPTY = 0x67,
+ ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE = 0x68,
+
+ ARMV7_PERFCTR_PREDICTABLE_FUNCT_RETURNS = 0x6E,
+
+ ARMV7_PERFCTR_MAIN_UNIT_EXECUTED_INST = 0x70,
+ ARMV7_PERFCTR_SECOND_UNIT_EXECUTED_INST = 0x71,
+ ARMV7_PERFCTR_LD_ST_UNIT_EXECUTED_INST = 0x72,
+ ARMV7_PERFCTR_FP_EXECUTED_INST = 0x73,
+ ARMV7_PERFCTR_NEON_EXECUTED_INST = 0x74,
+
+ ARMV7_PERFCTR_PLD_FULL_DEP_STALL_CYCLES = 0x80,
+ ARMV7_PERFCTR_DATA_WR_DEP_STALL_CYCLES = 0x81,
+ ARMV7_PERFCTR_ITLB_MISS_DEP_STALL_CYCLES = 0x82,
+ ARMV7_PERFCTR_DTLB_MISS_DEP_STALL_CYCLES = 0x83,
+ ARMV7_PERFCTR_MICRO_ITLB_MISS_DEP_STALL_CYCLES = 0x84,
+ ARMV7_PERFCTR_MICRO_DTLB_MISS_DEP_STALL_CYCLES = 0x85,
+ ARMV7_PERFCTR_DMB_DEP_STALL_CYCLES = 0x86,
+
+ ARMV7_PERFCTR_INTGR_CLK_ENABLED_CYCLES = 0x8A,
+ ARMV7_PERFCTR_DATA_ENGINE_CLK_EN_CYCLES = 0x8B,
+
+ ARMV7_PERFCTR_ISB_INST = 0x90,
+ ARMV7_PERFCTR_DSB_INST = 0x91,
+ ARMV7_PERFCTR_DMB_INST = 0x92,
+ ARMV7_PERFCTR_EXT_INTERRUPTS = 0x93,
+
+ ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_COMPLETED = 0xA0,
+ ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_SKIPPED = 0xA1,
+ ARMV7_PERFCTR_PLE_FIFO_FLUSH = 0xA2,
+ ARMV7_PERFCTR_PLE_RQST_COMPLETED = 0xA3,
+ ARMV7_PERFCTR_PLE_FIFO_OVERFLOW = 0xA4,
+ ARMV7_PERFCTR_PLE_RQST_PROG = 0xA5
+};
+
+/*
+ * Cortex-A8 HW events mapping
+ *
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(L1D)] = {
+ /*
+ * The performance counters don't differentiate between read
+ * and write accesses/misses so this isn't strictly correct,
+ * but it's the best we can do. Writes and reads get
+ * combined.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_INST,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_INST_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_INST,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_INST_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_ACCESS,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACH_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_ACCESS,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACH_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(DTLB)] = {
+ /*
+ * Only ITLB misses and DTLB refills are supported.
+ * If users want the DTLB refills misses a raw counter
+ * must be used.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
+ [C(RESULT_MISS)]
+ = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
+ [C(RESULT_MISS)]
+ = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+};
+
+/*
+ * Cortex-A9 HW events mapping
+ */
+static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] =
+ ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_COHERENT_LINE_HIT,
+ [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_COHERENT_LINE_MISS,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(L1D)] = {
+ /*
+ * The performance counters don't differentiate between read
+ * and write accesses/misses so this isn't strictly correct,
+ * but it's the best we can do. Writes and reads get
+ * combined.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(DTLB)] = {
+ /*
+ * Only ITLB misses and DTLB refills are supported.
+ * If users want the DTLB refills misses a raw counter
+ * must be used.
+ */
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
+ [C(RESULT_MISS)]
+ = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
+ [C(RESULT_MISS)]
+ = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+};
+
+/*
+ * Perf Events counters
+ */
+enum armv7_counters {
+ ARMV7_CYCLE_COUNTER = 1, /* Cycle counter */
+ ARMV7_COUNTER0 = 2, /* First event counter */
+};
+
+/*
+ * The cycle counter is ARMV7_CYCLE_COUNTER.
+ * The first event counter is ARMV7_COUNTER0.
+ * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
+ */
+#define ARMV7_COUNTER_LAST (ARMV7_COUNTER0 + armpmu->num_events - 1)
+
+/*
+ * ARMv7 low level PMNC access
+ */
+
+/*
+ * Per-CPU PMNC: config reg
+ */
+#define ARMV7_PMNC_E (1 << 0) /* Enable all counters */
+#define ARMV7_PMNC_P (1 << 1) /* Reset all counters */
+#define ARMV7_PMNC_C (1 << 2) /* Cycle counter reset */
+#define ARMV7_PMNC_D (1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV7_PMNC_X (1 << 4) /* Export to ETM */
+#define ARMV7_PMNC_DP (1 << 5) /* Disable CCNT if non-invasive debug*/
+#define ARMV7_PMNC_N_SHIFT 11 /* Number of counters supported */
+#define ARMV7_PMNC_N_MASK 0x1f
+#define ARMV7_PMNC_MASK 0x3f /* Mask for writable bits */
+
+/*
+ * Available counters
+ */
+#define ARMV7_CNT0 0 /* First event counter */
+#define ARMV7_CCNT 31 /* Cycle counter */
+
+/* Perf Event to low level counters mapping */
+#define ARMV7_EVENT_CNT_TO_CNTx (ARMV7_COUNTER0 - ARMV7_CNT0)
+
+/*
+ * CNTENS: counters enable reg
+ */
+#define ARMV7_CNTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_CNTENS_C (1 << ARMV7_CCNT)
+
+/*
+ * CNTENC: counters disable reg
+ */
+#define ARMV7_CNTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_CNTENC_C (1 << ARMV7_CCNT)
+
+/*
+ * INTENS: counters overflow interrupt enable reg
+ */
+#define ARMV7_INTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_INTENS_C (1 << ARMV7_CCNT)
+
+/*
+ * INTENC: counters overflow interrupt disable reg
+ */
+#define ARMV7_INTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_INTENC_C (1 << ARMV7_CCNT)
+
+/*
+ * EVTSEL: Event selection reg
+ */
+#define ARMV7_EVTSEL_MASK 0xff /* Mask for writable bits */
+
+/*
+ * SELECT: Counter selection reg
+ */
+#define ARMV7_SELECT_MASK 0x1f /* Mask for writable bits */
+
+/*
+ * FLAG: counters overflow flag status reg
+ */
+#define ARMV7_FLAG_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_FLAG_C (1 << ARMV7_CCNT)
+#define ARMV7_FLAG_MASK 0xffffffff /* Mask for writable bits */
+#define ARMV7_OVERFLOWED_MASK ARMV7_FLAG_MASK
+
+static inline unsigned long armv7_pmnc_read(void)
+{
+ u32 val;
+ asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
+ return val;
+}
+
+static inline void armv7_pmnc_write(unsigned long val)
+{
+ val &= ARMV7_PMNC_MASK;
+ asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
+}
+
+static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
+{
+ return pmnc & ARMV7_OVERFLOWED_MASK;
+}
+
+static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
+ enum armv7_counters counter)
+{
+ int ret = 0;
+
+ if (counter == ARMV7_CYCLE_COUNTER)
+ ret = pmnc & ARMV7_FLAG_C;
+ else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
+ ret = pmnc & ARMV7_FLAG_P(counter);
+ else
+ pr_err("CPU%u checking wrong counter %d overflow status\n",
+ smp_processor_id(), counter);
+
+ return ret;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int idx)
+{
+ u32 val;
+
+ if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
+ pr_err("CPU%u selecting wrong PMNC counter"
+ " %d\n", smp_processor_id(), idx);
+ return -1;
+ }
+
+ val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
+ asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+ return idx;
+}
+
+static inline u32 armv7pmu_read_counter(int idx)
+{
+ unsigned long value = 0;
+
+ if (idx == ARMV7_CYCLE_COUNTER)
+ asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
+ else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
+ if (armv7_pmnc_select_counter(idx) == idx)
+ asm volatile("mrc p15, 0, %0, c9, c13, 2"
+ : "=r" (value));
+ } else
+ pr_err("CPU%u reading wrong counter %d\n",
+ smp_processor_id(), idx);
+
+ return value;
+}
+
+static inline void armv7pmu_write_counter(int idx, u32 value)
+{
+ if (idx == ARMV7_CYCLE_COUNTER)
+ asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+ else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
+ if (armv7_pmnc_select_counter(idx) == idx)
+ asm volatile("mcr p15, 0, %0, c9, c13, 2"
+ : : "r" (value));
+ } else
+ pr_err("CPU%u writing wrong counter %d\n",
+ smp_processor_id(), idx);
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
+{
+ if (armv7_pmnc_select_counter(idx) == idx) {
+ val &= ARMV7_EVTSEL_MASK;
+ asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+ }
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
+{
+ u32 val;
+
+ if ((idx != ARMV7_CYCLE_COUNTER) &&
+ ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+ pr_err("CPU%u enabling wrong PMNC counter"
+ " %d\n", smp_processor_id(), idx);
+ return -1;
+ }
+
+ if (idx == ARMV7_CYCLE_COUNTER)
+ val = ARMV7_CNTENS_C;
+ else
+ val = ARMV7_CNTENS_P(idx);
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+ return idx;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
+{
+ u32 val;
+
+
+ if ((idx != ARMV7_CYCLE_COUNTER) &&
+ ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+ pr_err("CPU%u disabling wrong PMNC counter"
+ " %d\n", smp_processor_id(), idx);
+ return -1;
+ }
+
+ if (idx == ARMV7_CYCLE_COUNTER)
+ val = ARMV7_CNTENC_C;
+ else
+ val = ARMV7_CNTENC_P(idx);
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+ return idx;
+}
+
+static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
+{
+ u32 val;
+
+ if ((idx != ARMV7_CYCLE_COUNTER) &&
+ ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+ pr_err("CPU%u enabling wrong PMNC counter"
+ " interrupt enable %d\n", smp_processor_id(), idx);
+ return -1;
+ }
+
+ if (idx == ARMV7_CYCLE_COUNTER)
+ val = ARMV7_INTENS_C;
+ else
+ val = ARMV7_INTENS_P(idx);
+
+ asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
+
+ return idx;
+}
+
+static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
+{
+ u32 val;
+
+ if ((idx != ARMV7_CYCLE_COUNTER) &&
+ ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+ pr_err("CPU%u disabling wrong PMNC counter"
+ " interrupt enable %d\n", smp_processor_id(), idx);
+ return -1;
+ }
+
+ if (idx == ARMV7_CYCLE_COUNTER)
+ val = ARMV7_INTENC_C;
+ else
+ val = ARMV7_INTENC_P(idx);
+
+ asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
+
+ return idx;
+}
+
+static inline u32 armv7_pmnc_getreset_flags(void)
+{
+ u32 val;
+
+ /* Read */
+ asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+
+ /* Write to clear flags */
+ val &= ARMV7_FLAG_MASK;
+ asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val));
+
+ return val;
+}
+
+#ifdef DEBUG
+static void armv7_pmnc_dump_regs(void)
+{
+ u32 val;
+ unsigned int cnt;
+
+ printk(KERN_INFO "PMNC registers dump:\n");
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+ printk(KERN_INFO "PMNC =0x%08x\n", val);
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
+ printk(KERN_INFO "CNTENS=0x%08x\n", val);
+
+ asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
+ printk(KERN_INFO "INTENS=0x%08x\n", val);
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+ printk(KERN_INFO "FLAGS =0x%08x\n", val);
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
+ printk(KERN_INFO "SELECT=0x%08x\n", val);
+
+ asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+ printk(KERN_INFO "CCNT =0x%08x\n", val);
+
+ for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
+ armv7_pmnc_select_counter(cnt);
+ asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+ printk(KERN_INFO "CNT[%d] count =0x%08x\n",
+ cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+ asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
+ printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
+ cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+ }
+}
+#endif
+
+void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+ unsigned long flags;
+
+ /*
+ * Enable counter and interrupt, and set the counter to count
+ * the event that we're interested in.
+ */
+ spin_lock_irqsave(&pmu_lock, flags);
+
+ /*
+ * Disable counter
+ */
+ armv7_pmnc_disable_counter(idx);
+
+ /*
+ * Set event (if destined for PMNx counters)
+ * We don't need to set the event if it's a cycle count
+ */
+ if (idx != ARMV7_CYCLE_COUNTER)
+ armv7_pmnc_write_evtsel(idx, hwc->config_base);
+
+ /*
+ * Enable interrupt for this counter
+ */
+ armv7_pmnc_enable_intens(idx);
+
+ /*
+ * Enable counter
+ */
+ armv7_pmnc_enable_counter(idx);
+
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+ unsigned long flags;
+
+ /*
+ * Disable counter and interrupt
+ */
+ spin_lock_irqsave(&pmu_lock, flags);
+
+ /*
+ * Disable counter
+ */
+ armv7_pmnc_disable_counter(idx);
+
+ /*
+ * Disable interrupt for this counter
+ */
+ armv7_pmnc_disable_intens(idx);
+
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
+{
+ unsigned long pmnc;
+ struct perf_sample_data data;
+ struct cpu_hw_events *cpuc;
+ struct pt_regs *regs;
+ int idx;
+
+ /*
+ * Get and reset the IRQ flags
+ */
+ pmnc = armv7_pmnc_getreset_flags();
+
+ /*
+ * Did an overflow occur?
+ */
+ if (!armv7_pmnc_has_overflowed(pmnc))
+ return IRQ_NONE;
+
+ /*
+ * Handle the counter(s) overflow(s)
+ */
+ regs = get_irq_regs();
+
+ perf_sample_data_init(&data, 0);
+
+ cpuc = &__get_cpu_var(cpu_hw_events);
+ for (idx = 0; idx <= armpmu->num_events; ++idx) {
+ struct perf_event *event = cpuc->events[idx];
+ struct hw_perf_event *hwc;
+
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ /*
+ * We have a single interrupt for all counters. Check that
+ * each counter has overflowed before we process it.
+ */
+ if (!armv7_pmnc_counter_has_overflowed(pmnc, idx))
+ continue;
+
+ hwc = &event->hw;
+ armpmu_event_update(event, hwc, idx);
+ data.period = event->hw.last_period;
+ if (!armpmu_event_set_period(event, hwc, idx))
+ continue;
+
+ if (perf_event_overflow(event, 0, &data, regs))
+ armpmu->disable(hwc, idx);
+ }
+
+ /*
+ * Handle the pending perf events.
+ *
+ * Note: this call *must* be run with interrupts disabled. For
+ * platforms that can have the PMU interrupts raised as an NMI, this
+ * will not work.
+ */
+ irq_work_run();
+
+ return IRQ_HANDLED;
+}
+
+static void armv7pmu_start(void)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ /* Enable all counters */
+ armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void armv7pmu_stop(void)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ /* Disable all counters */
+ armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline int armv7_a8_pmu_event_map(int config)
+{
+ int mapping = armv7_a8_perf_map[config];
+ if (HW_OP_UNSUPPORTED == mapping)
+ mapping = -EOPNOTSUPP;
+ return mapping;
+}
+
+static inline int armv7_a9_pmu_event_map(int config)
+{
+ int mapping = armv7_a9_perf_map[config];
+ if (HW_OP_UNSUPPORTED == mapping)
+ mapping = -EOPNOTSUPP;
+ return mapping;
+}
+
+static u64 armv7pmu_raw_event(u64 config)
+{
+ return config & 0xff;
+}
+
+static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
+ struct hw_perf_event *event)
+{
+ int idx;
+
+ /* Always place a cycle counter into the cycle counter. */
+ if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
+ if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
+ return -EAGAIN;
+
+ return ARMV7_CYCLE_COUNTER;
+ } else {
+ /*
+ * For anything other than a cycle counter, try and use
+ * the events counters
+ */
+ for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
+ if (!test_and_set_bit(idx, cpuc->used_mask))
+ return idx;
+ }
+
+ /* The counters are all in use. */
+ return -EAGAIN;
+ }
+}
+
+static struct arm_pmu armv7pmu = {
+ .handle_irq = armv7pmu_handle_irq,
+ .enable = armv7pmu_enable_event,
+ .disable = armv7pmu_disable_event,
+ .raw_event = armv7pmu_raw_event,
+ .read_counter = armv7pmu_read_counter,
+ .write_counter = armv7pmu_write_counter,
+ .get_event_idx = armv7pmu_get_event_idx,
+ .start = armv7pmu_start,
+ .stop = armv7pmu_stop,
+ .max_period = (1LLU << 32) - 1,
+};
+
+static u32 __init armv7_reset_read_pmnc(void)
+{
+ u32 nb_cnt;
+
+ /* Initialize & Reset PMNC: C and P bits */
+ armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
+
+ /* Read the nb of CNTx counters supported from PMNC */
+ nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+
+ /* Add the CPU cycles counter and return */
+ return nb_cnt + 1;
+}
+
+/*
+ * ARMv5 [xscale] Performance counter handling code.
+ *
+ * Based on xscale OProfile code.
+ *
+ * There are two variants of the xscale PMU that we support:
+ * - xscale1pmu: 2 event counters and a cycle counter
+ * - xscale2pmu: 4 event counters and a cycle counter
+ * The two variants share event definitions, but have different
+ * PMU structures.
+ */
+
+enum xscale_perf_types {
+ XSCALE_PERFCTR_ICACHE_MISS = 0x00,
+ XSCALE_PERFCTR_ICACHE_NO_DELIVER = 0x01,
+ XSCALE_PERFCTR_DATA_STALL = 0x02,
+ XSCALE_PERFCTR_ITLB_MISS = 0x03,
+ XSCALE_PERFCTR_DTLB_MISS = 0x04,
+ XSCALE_PERFCTR_BRANCH = 0x05,
+ XSCALE_PERFCTR_BRANCH_MISS = 0x06,
+ XSCALE_PERFCTR_INSTRUCTION = 0x07,
+ XSCALE_PERFCTR_DCACHE_FULL_STALL = 0x08,
+ XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG = 0x09,
+ XSCALE_PERFCTR_DCACHE_ACCESS = 0x0A,
+ XSCALE_PERFCTR_DCACHE_MISS = 0x0B,
+ XSCALE_PERFCTR_DCACHE_WRITE_BACK = 0x0C,
+ XSCALE_PERFCTR_PC_CHANGED = 0x0D,
+ XSCALE_PERFCTR_BCU_REQUEST = 0x10,
+ XSCALE_PERFCTR_BCU_FULL = 0x11,
+ XSCALE_PERFCTR_BCU_DRAIN = 0x12,
+ XSCALE_PERFCTR_BCU_ECC_NO_ELOG = 0x14,
+ XSCALE_PERFCTR_BCU_1_BIT_ERR = 0x15,
+ XSCALE_PERFCTR_RMW = 0x16,
+ /* XSCALE_PERFCTR_CCNT is not hardware defined */
+ XSCALE_PERFCTR_CCNT = 0xFE,
+ XSCALE_PERFCTR_UNUSED = 0xFF,
+};
+
+enum xscale_counters {
+ XSCALE_CYCLE_COUNTER = 1,
+ XSCALE_COUNTER0,
+ XSCALE_COUNTER1,
+ XSCALE_COUNTER2,
+ XSCALE_COUNTER3,
+};
+
+static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = XSCALE_PERFCTR_CCNT,
+ [PERF_COUNT_HW_INSTRUCTIONS] = XSCALE_PERFCTR_INSTRUCTION,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH,
+ [PERF_COUNT_HW_BRANCH_MISSES] = XSCALE_PERFCTR_BRANCH_MISS,
+ [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
+};
+
+#define XSCALE_PMU_ENABLE 0x001
+#define XSCALE_PMN_RESET 0x002
+#define XSCALE_CCNT_RESET 0x004
+#define XSCALE_PMU_RESET (CCNT_RESET | PMN_RESET)
+#define XSCALE_PMU_CNT64 0x008
+
+static inline int
+xscalepmu_event_map(int config)
+{
+ int mapping = xscale_perf_map[config];
+ if (HW_OP_UNSUPPORTED == mapping)
+ mapping = -EOPNOTSUPP;
+ return mapping;
+}
+
+static u64
+xscalepmu_raw_event(u64 config)
+{
+ return config & 0xff;
+}
+
+#define XSCALE1_OVERFLOWED_MASK 0x700
+#define XSCALE1_CCOUNT_OVERFLOW 0x400
+#define XSCALE1_COUNT0_OVERFLOW 0x100
+#define XSCALE1_COUNT1_OVERFLOW 0x200
+#define XSCALE1_CCOUNT_INT_EN 0x040
+#define XSCALE1_COUNT0_INT_EN 0x010
+#define XSCALE1_COUNT1_INT_EN 0x020
+#define XSCALE1_COUNT0_EVT_SHFT 12
+#define XSCALE1_COUNT0_EVT_MASK (0xff << XSCALE1_COUNT0_EVT_SHFT)
+#define XSCALE1_COUNT1_EVT_SHFT 20
+#define XSCALE1_COUNT1_EVT_MASK (0xff << XSCALE1_COUNT1_EVT_SHFT)
+
+static inline u32
+xscale1pmu_read_pmnc(void)
+{
+ u32 val;
+ asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val));
+ return val;
+}
+
+static inline void
+xscale1pmu_write_pmnc(u32 val)
+{
+ /* upper 4bits and 7, 11 are write-as-0 */
+ val &= 0xffff77f;
+ asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val));
+}
+
+static inline int
+xscale1_pmnc_counter_has_overflowed(unsigned long pmnc,
+ enum xscale_counters counter)
+{
+ int ret = 0;
+
+ switch (counter) {
+ case XSCALE_CYCLE_COUNTER:
+ ret = pmnc & XSCALE1_CCOUNT_OVERFLOW;
+ break;
+ case XSCALE_COUNTER0:
+ ret = pmnc & XSCALE1_COUNT0_OVERFLOW;
+ break;
+ case XSCALE_COUNTER1:
+ ret = pmnc & XSCALE1_COUNT1_OVERFLOW;
+ break;
+ default:
+ WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+ }
+
+ return ret;
+}
+
+static irqreturn_t
+xscale1pmu_handle_irq(int irq_num, void *dev)
+{
+ unsigned long pmnc;
+ struct perf_sample_data data;
+ struct cpu_hw_events *cpuc;
+ struct pt_regs *regs;
+ int idx;
+
+ /*
+ * NOTE: there's an A stepping erratum that states if an overflow
+ * bit already exists and another occurs, the previous
+ * Overflow bit gets cleared. There's no workaround.
+ * Fixed in B stepping or later.
+ */
+ pmnc = xscale1pmu_read_pmnc();
+
+ /*
+ * Write the value back to clear the overflow flags. Overflow
+ * flags remain in pmnc for use below. We also disable the PMU
+ * while we process the interrupt.
+ */
+ xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
+
+ if (!(pmnc & XSCALE1_OVERFLOWED_MASK))
+ return IRQ_NONE;
+
+ regs = get_irq_regs();
+
+ perf_sample_data_init(&data, 0);
+
+ cpuc = &__get_cpu_var(cpu_hw_events);
+ for (idx = 0; idx <= armpmu->num_events; ++idx) {
+ struct perf_event *event = cpuc->events[idx];
+ struct hw_perf_event *hwc;
+
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
+ continue;
+
+ hwc = &event->hw;
+ armpmu_event_update(event, hwc, idx);
+ data.period = event->hw.last_period;
+ if (!armpmu_event_set_period(event, hwc, idx))
+ continue;
+
+ if (perf_event_overflow(event, 0, &data, regs))
+ armpmu->disable(hwc, idx);
+ }
+
+ irq_work_run();
+
+ /*
+ * Re-enable the PMU.
+ */
+ pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE;
+ xscale1pmu_write_pmnc(pmnc);
+
+ return IRQ_HANDLED;
+}
+
+static void
+xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+ unsigned long val, mask, evt, flags;
+
+ switch (idx) {
+ case XSCALE_CYCLE_COUNTER:
+ mask = 0;
+ evt = XSCALE1_CCOUNT_INT_EN;
+ break;
+ case XSCALE_COUNTER0:
+ mask = XSCALE1_COUNT0_EVT_MASK;
+ evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) |
+ XSCALE1_COUNT0_INT_EN;
+ break;
+ case XSCALE_COUNTER1:
+ mask = XSCALE1_COUNT1_EVT_MASK;
+ evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) |
+ XSCALE1_COUNT1_INT_EN;
+ break;
+ default:
+ WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+ return;
+ }
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = xscale1pmu_read_pmnc();
+ val &= ~mask;
+ val |= evt;
+ xscale1pmu_write_pmnc(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+ unsigned long val, mask, evt, flags;
+
+ switch (idx) {
+ case XSCALE_CYCLE_COUNTER:
+ mask = XSCALE1_CCOUNT_INT_EN;
+ evt = 0;
+ break;
+ case XSCALE_COUNTER0:
+ mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK;
+ evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT;
+ break;
+ case XSCALE_COUNTER1:
+ mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK;
+ evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT;
+ break;
+ default:
+ WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+ return;
+ }
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = xscale1pmu_read_pmnc();
+ val &= ~mask;
+ val |= evt;
+ xscale1pmu_write_pmnc(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
+ struct hw_perf_event *event)
+{
+ if (XSCALE_PERFCTR_CCNT == event->config_base) {
+ if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask))
+ return -EAGAIN;
+
+ return XSCALE_CYCLE_COUNTER;
+ } else {
+ if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask)) {
+ return XSCALE_COUNTER1;
+ }
+
+ if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask)) {
+ return XSCALE_COUNTER0;
+ }
+
+ return -EAGAIN;
+ }
+}
+
+static void
+xscale1pmu_start(void)
+{
+ unsigned long flags, val;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = xscale1pmu_read_pmnc();
+ val |= XSCALE_PMU_ENABLE;
+ xscale1pmu_write_pmnc(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale1pmu_stop(void)
+{
+ unsigned long flags, val;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = xscale1pmu_read_pmnc();
+ val &= ~XSCALE_PMU_ENABLE;
+ xscale1pmu_write_pmnc(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline u32
+xscale1pmu_read_counter(int counter)
+{
+ u32 val = 0;
+
+ switch (counter) {
+ case XSCALE_CYCLE_COUNTER:
+ asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val));
+ break;
+ case XSCALE_COUNTER0:
+ asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val));
+ break;
+ case XSCALE_COUNTER1:
+ asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val));
+ break;
+ }
+
+ return val;
+}
+
+static inline void
+xscale1pmu_write_counter(int counter, u32 val)
+{
+ switch (counter) {
+ case XSCALE_CYCLE_COUNTER:
+ asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val));
+ break;
+ case XSCALE_COUNTER0:
+ asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val));
+ break;
+ case XSCALE_COUNTER1:
+ asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val));
+ break;
+ }
+}
+
+static const struct arm_pmu xscale1pmu = {
+ .id = ARM_PERF_PMU_ID_XSCALE1,
+ .handle_irq = xscale1pmu_handle_irq,
+ .enable = xscale1pmu_enable_event,
+ .disable = xscale1pmu_disable_event,
+ .event_map = xscalepmu_event_map,
+ .raw_event = xscalepmu_raw_event,
+ .read_counter = xscale1pmu_read_counter,
+ .write_counter = xscale1pmu_write_counter,
+ .get_event_idx = xscale1pmu_get_event_idx,
+ .start = xscale1pmu_start,
+ .stop = xscale1pmu_stop,
+ .num_events = 3,
+ .max_period = (1LLU << 32) - 1,
+};
+
+#define XSCALE2_OVERFLOWED_MASK 0x01f
+#define XSCALE2_CCOUNT_OVERFLOW 0x001
+#define XSCALE2_COUNT0_OVERFLOW 0x002
+#define XSCALE2_COUNT1_OVERFLOW 0x004
+#define XSCALE2_COUNT2_OVERFLOW 0x008
+#define XSCALE2_COUNT3_OVERFLOW 0x010
+#define XSCALE2_CCOUNT_INT_EN 0x001
+#define XSCALE2_COUNT0_INT_EN 0x002
+#define XSCALE2_COUNT1_INT_EN 0x004
+#define XSCALE2_COUNT2_INT_EN 0x008
+#define XSCALE2_COUNT3_INT_EN 0x010
+#define XSCALE2_COUNT0_EVT_SHFT 0
+#define XSCALE2_COUNT0_EVT_MASK (0xff << XSCALE2_COUNT0_EVT_SHFT)
+#define XSCALE2_COUNT1_EVT_SHFT 8
+#define XSCALE2_COUNT1_EVT_MASK (0xff << XSCALE2_COUNT1_EVT_SHFT)
+#define XSCALE2_COUNT2_EVT_SHFT 16
+#define XSCALE2_COUNT2_EVT_MASK (0xff << XSCALE2_COUNT2_EVT_SHFT)
+#define XSCALE2_COUNT3_EVT_SHFT 24
+#define XSCALE2_COUNT3_EVT_MASK (0xff << XSCALE2_COUNT3_EVT_SHFT)
+
+static inline u32
+xscale2pmu_read_pmnc(void)
+{
+ u32 val;
+ asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val));
+ /* bits 1-2 and 4-23 are read-unpredictable */
+ return val & 0xff000009;
+}
+
+static inline void
+xscale2pmu_write_pmnc(u32 val)
+{
+ /* bits 4-23 are write-as-0, 24-31 are write ignored */
+ val &= 0xf;
+ asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val));
+}
+
+static inline u32
+xscale2pmu_read_overflow_flags(void)
+{
+ u32 val;
+ asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val));
+ return val;
+}
+
+static inline void
+xscale2pmu_write_overflow_flags(u32 val)
+{
+ asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val));
+}
+
+static inline u32
+xscale2pmu_read_event_select(void)
+{
+ u32 val;
+ asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val));
+ return val;
+}
+
+static inline void
+xscale2pmu_write_event_select(u32 val)
+{
+ asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val));
+}
+
+static inline u32
+xscale2pmu_read_int_enable(void)
+{
+ u32 val;
+ asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val));
+ return val;
+}
+
+static void
+xscale2pmu_write_int_enable(u32 val)
+{
+ asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val));
+}
+
+static inline int
+xscale2_pmnc_counter_has_overflowed(unsigned long of_flags,
+ enum xscale_counters counter)
+{
+ int ret = 0;
+
+ switch (counter) {
+ case XSCALE_CYCLE_COUNTER:
+ ret = of_flags & XSCALE2_CCOUNT_OVERFLOW;
+ break;
+ case XSCALE_COUNTER0:
+ ret = of_flags & XSCALE2_COUNT0_OVERFLOW;
+ break;
+ case XSCALE_COUNTER1:
+ ret = of_flags & XSCALE2_COUNT1_OVERFLOW;
+ break;
+ case XSCALE_COUNTER2:
+ ret = of_flags & XSCALE2_COUNT2_OVERFLOW;
+ break;
+ case XSCALE_COUNTER3:
+ ret = of_flags & XSCALE2_COUNT3_OVERFLOW;
+ break;
+ default:
+ WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+ }
+
+ return ret;
+}
+
+static irqreturn_t
+xscale2pmu_handle_irq(int irq_num, void *dev)
+{
+ unsigned long pmnc, of_flags;
+ struct perf_sample_data data;
+ struct cpu_hw_events *cpuc;
+ struct pt_regs *regs;
+ int idx;
+
+ /* Disable the PMU. */
+ pmnc = xscale2pmu_read_pmnc();
+ xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
+
+ /* Check the overflow flag register. */
+ of_flags = xscale2pmu_read_overflow_flags();
+ if (!(of_flags & XSCALE2_OVERFLOWED_MASK))
+ return IRQ_NONE;
+
+ /* Clear the overflow bits. */
+ xscale2pmu_write_overflow_flags(of_flags);
+
+ regs = get_irq_regs();
+
+ perf_sample_data_init(&data, 0);
+
+ cpuc = &__get_cpu_var(cpu_hw_events);
+ for (idx = 0; idx <= armpmu->num_events; ++idx) {
+ struct perf_event *event = cpuc->events[idx];
+ struct hw_perf_event *hwc;
+
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
+ continue;
+
+ hwc = &event->hw;
+ armpmu_event_update(event, hwc, idx);
+ data.period = event->hw.last_period;
+ if (!armpmu_event_set_period(event, hwc, idx))
+ continue;
+
+ if (perf_event_overflow(event, 0, &data, regs))
+ armpmu->disable(hwc, idx);
+ }
+
+ irq_work_run();
+
+ /*
+ * Re-enable the PMU.
+ */
+ pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE;
+ xscale2pmu_write_pmnc(pmnc);
+
+ return IRQ_HANDLED;
+}
+
+static void
+xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+ unsigned long flags, ien, evtsel;
+
+ ien = xscale2pmu_read_int_enable();
+ evtsel = xscale2pmu_read_event_select();
+
+ switch (idx) {
+ case XSCALE_CYCLE_COUNTER:
+ ien |= XSCALE2_CCOUNT_INT_EN;
+ break;
+ case XSCALE_COUNTER0:
+ ien |= XSCALE2_COUNT0_INT_EN;
+ evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
+ evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT;
+ break;
+ case XSCALE_COUNTER1:
+ ien |= XSCALE2_COUNT1_INT_EN;
+ evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
+ evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT;
+ break;
+ case XSCALE_COUNTER2:
+ ien |= XSCALE2_COUNT2_INT_EN;
+ evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
+ evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT;
+ break;
+ case XSCALE_COUNTER3:
+ ien |= XSCALE2_COUNT3_INT_EN;
+ evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
+ evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT;
+ break;
+ default:
+ WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+ return;
+ }
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ xscale2pmu_write_event_select(evtsel);
+ xscale2pmu_write_int_enable(ien);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+ unsigned long flags, ien, evtsel;
+
+ ien = xscale2pmu_read_int_enable();
+ evtsel = xscale2pmu_read_event_select();
+
+ switch (idx) {
+ case XSCALE_CYCLE_COUNTER:
+ ien &= ~XSCALE2_CCOUNT_INT_EN;
+ break;
+ case XSCALE_COUNTER0:
+ ien &= ~XSCALE2_COUNT0_INT_EN;
+ evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
+ evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
+ break;
+ case XSCALE_COUNTER1:
+ ien &= ~XSCALE2_COUNT1_INT_EN;
+ evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
+ evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
+ break;
+ case XSCALE_COUNTER2:
+ ien &= ~XSCALE2_COUNT2_INT_EN;
+ evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
+ evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
+ break;
+ case XSCALE_COUNTER3:
+ ien &= ~XSCALE2_COUNT3_INT_EN;
+ evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
+ evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
+ break;
+ default:
+ WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+ return;
+ }
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ xscale2pmu_write_event_select(evtsel);
+ xscale2pmu_write_int_enable(ien);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
+ struct hw_perf_event *event)
+{
+ int idx = xscale1pmu_get_event_idx(cpuc, event);
+ if (idx >= 0)
+ goto out;
+
+ if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask))
+ idx = XSCALE_COUNTER3;
+ else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask))
+ idx = XSCALE_COUNTER2;
+out:
+ return idx;
+}
+
+static void
+xscale2pmu_start(void)
+{
+ unsigned long flags, val;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
+ val |= XSCALE_PMU_ENABLE;
+ xscale2pmu_write_pmnc(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale2pmu_stop(void)
+{
+ unsigned long flags, val;
+
+ spin_lock_irqsave(&pmu_lock, flags);
+ val = xscale2pmu_read_pmnc();
+ val &= ~XSCALE_PMU_ENABLE;
+ xscale2pmu_write_pmnc(val);
+ spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline u32
+xscale2pmu_read_counter(int counter)
+{
+ u32 val = 0;
+
+ switch (counter) {
+ case XSCALE_CYCLE_COUNTER:
+ asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val));
+ break;
+ case XSCALE_COUNTER0:
+ asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val));
+ break;
+ case XSCALE_COUNTER1:
+ asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val));
+ break;
+ case XSCALE_COUNTER2:
+ asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val));
+ break;
+ case XSCALE_COUNTER3:
+ asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val));
+ break;
+ }
+
+ return val;
+}
+
+static inline void
+xscale2pmu_write_counter(int counter, u32 val)
+{
+ switch (counter) {
+ case XSCALE_CYCLE_COUNTER:
+ asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val));
+ break;
+ case XSCALE_COUNTER0:
+ asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val));
+ break;
+ case XSCALE_COUNTER1:
+ asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val));
+ break;
+ case XSCALE_COUNTER2:
+ asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val));
+ break;
+ case XSCALE_COUNTER3:
+ asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val));
+ break;
+ }
+}
+
+static const struct arm_pmu xscale2pmu = {
+ .id = ARM_PERF_PMU_ID_XSCALE2,
+ .handle_irq = xscale2pmu_handle_irq,
+ .enable = xscale2pmu_enable_event,
+ .disable = xscale2pmu_disable_event,
+ .event_map = xscalepmu_event_map,
+ .raw_event = xscalepmu_raw_event,
+ .read_counter = xscale2pmu_read_counter,
+ .write_counter = xscale2pmu_write_counter,
+ .get_event_idx = xscale2pmu_get_event_idx,
+ .start = xscale2pmu_start,
+ .stop = xscale2pmu_stop,
+ .num_events = 5,
+ .max_period = (1LLU << 32) - 1,
+};
static int __init
init_hw_perf_events(void)
@@ -622,16 +2977,37 @@ init_hw_perf_events(void)
case 0xB360: /* ARM1136 */
case 0xB560: /* ARM1156 */
case 0xB760: /* ARM1176 */
- armpmu = armv6pmu_init();
+ armpmu = &armv6pmu;
+ memcpy(armpmu_perf_cache_map, armv6_perf_cache_map,
+ sizeof(armv6_perf_cache_map));
break;
case 0xB020: /* ARM11mpcore */
- armpmu = armv6mpcore_pmu_init();
+ armpmu = &armv6mpcore_pmu;
+ memcpy(armpmu_perf_cache_map,
+ armv6mpcore_perf_cache_map,
+ sizeof(armv6mpcore_perf_cache_map));
break;
case 0xC080: /* Cortex-A8 */
- armpmu = armv7_a8_pmu_init();
+ armv7pmu.id = ARM_PERF_PMU_ID_CA8;
+ memcpy(armpmu_perf_cache_map, armv7_a8_perf_cache_map,
+ sizeof(armv7_a8_perf_cache_map));
+ armv7pmu.event_map = armv7_a8_pmu_event_map;
+ armpmu = &armv7pmu;
+
+ /* Reset PMNC and read the nb of CNTx counters
+ supported */
+ armv7pmu.num_events = armv7_reset_read_pmnc();
break;
case 0xC090: /* Cortex-A9 */
- armpmu = armv7_a9_pmu_init();
+ armv7pmu.id = ARM_PERF_PMU_ID_CA9;
+ memcpy(armpmu_perf_cache_map, armv7_a9_perf_cache_map,
+ sizeof(armv7_a9_perf_cache_map));
+ armv7pmu.event_map = armv7_a9_pmu_event_map;
+ armpmu = &armv7pmu;
+
+ /* Reset PMNC and read the nb of CNTx counters
+ supported */
+ armv7pmu.num_events = armv7_reset_read_pmnc();
break;
}
/* Intel CPUs [xscale]. */
@@ -639,17 +3015,21 @@ init_hw_perf_events(void)
part_number = (cpuid >> 13) & 0x7;
switch (part_number) {
case 1:
- armpmu = xscale1pmu_init();
+ armpmu = &xscale1pmu;
+ memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
+ sizeof(xscale_perf_cache_map));
break;
case 2:
- armpmu = xscale2pmu_init();
+ armpmu = &xscale2pmu;
+ memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
+ sizeof(xscale_perf_cache_map));
break;
}
}
if (armpmu) {
pr_info("enabled with %s PMU driver, %d counters available\n",
- armpmu->name, armpmu->num_events);
+ arm_pmu_names[armpmu->id], armpmu->num_events);
} else {
pr_info("no hardware support available\n");
}
@@ -673,17 +3053,17 @@ arch_initcall(init_hw_perf_events);
* This code has been adapted from the ARM OProfile support.
*/
struct frame_tail {
- struct frame_tail __user *fp;
- unsigned long sp;
- unsigned long lr;
+ struct frame_tail *fp;
+ unsigned long sp;
+ unsigned long lr;
} __attribute__((packed));
/*
* Get the return address for a single stackframe and return a pointer to the
* next frame tail.
*/
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
+static struct frame_tail *
+user_backtrace(struct frame_tail *tail,
struct perf_callchain_entry *entry)
{
struct frame_tail buftail;
@@ -709,10 +3089,10 @@ user_backtrace(struct frame_tail __user *tail,
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
{
- struct frame_tail __user *tail;
+ struct frame_tail *tail;
- tail = (struct frame_tail __user *)regs->ARM_fp - 1;
+ tail = (struct frame_tail *)regs->ARM_fp - 1;
while (tail && !((unsigned long)tail & 0x3))
tail = user_backtrace(tail, entry);
diff --git a/trunk/arch/arm/kernel/perf_event_v6.c b/trunk/arch/arm/kernel/perf_event_v6.c
deleted file mode 100644
index c058bfc8532b..000000000000
--- a/trunk/arch/arm/kernel/perf_event_v6.c
+++ /dev/null
@@ -1,672 +0,0 @@
-/*
- * ARMv6 Performance counter handling code.
- *
- * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
- *
- * ARMv6 has 2 configurable performance counters and a single cycle counter.
- * They all share a single reset bit but can be written to zero so we can use
- * that for a reset.
- *
- * The counters can't be individually enabled or disabled so when we remove
- * one event and replace it with another we could get spurious counts from the
- * wrong event. However, we can take advantage of the fact that the
- * performance counters can export events to the event bus, and the event bus
- * itself can be monitored. This requires that we *don't* export the events to
- * the event bus. The procedure for disabling a configurable counter is:
- * - change the counter to count the ETMEXTOUT[0] signal (0x20). This
- * effectively stops the counter from counting.
- * - disable the counter's interrupt generation (each counter has it's
- * own interrupt enable bit).
- * Once stopped, the counter value can be written as 0 to reset.
- *
- * To enable a counter:
- * - enable the counter's interrupt generation.
- * - set the new event type.
- *
- * Note: the dedicated cycle counter only counts cycles and can't be
- * enabled/disabled independently of the others. When we want to disable the
- * cycle counter, we have to just disable the interrupt reporting and start
- * ignoring that counter. When re-enabling, we have to reset the value and
- * enable the interrupt.
- */
-
-#ifdef CONFIG_CPU_V6
-enum armv6_perf_types {
- ARMV6_PERFCTR_ICACHE_MISS = 0x0,
- ARMV6_PERFCTR_IBUF_STALL = 0x1,
- ARMV6_PERFCTR_DDEP_STALL = 0x2,
- ARMV6_PERFCTR_ITLB_MISS = 0x3,
- ARMV6_PERFCTR_DTLB_MISS = 0x4,
- ARMV6_PERFCTR_BR_EXEC = 0x5,
- ARMV6_PERFCTR_BR_MISPREDICT = 0x6,
- ARMV6_PERFCTR_INSTR_EXEC = 0x7,
- ARMV6_PERFCTR_DCACHE_HIT = 0x9,
- ARMV6_PERFCTR_DCACHE_ACCESS = 0xA,
- ARMV6_PERFCTR_DCACHE_MISS = 0xB,
- ARMV6_PERFCTR_DCACHE_WBACK = 0xC,
- ARMV6_PERFCTR_SW_PC_CHANGE = 0xD,
- ARMV6_PERFCTR_MAIN_TLB_MISS = 0xF,
- ARMV6_PERFCTR_EXPL_D_ACCESS = 0x10,
- ARMV6_PERFCTR_LSU_FULL_STALL = 0x11,
- ARMV6_PERFCTR_WBUF_DRAINED = 0x12,
- ARMV6_PERFCTR_CPU_CYCLES = 0xFF,
- ARMV6_PERFCTR_NOP = 0x20,
-};
-
-enum armv6_counters {
- ARMV6_CYCLE_COUNTER = 1,
- ARMV6_COUNTER0,
- ARMV6_COUNTER1,
-};
-
-/*
- * The hardware events that we support. We do support cache operations but
- * we have harvard caches and no way to combine instruction and data
- * accesses/misses in hardware.
- */
-static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC,
- [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT,
- [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
-};
-
-static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
- [C(L1D)] = {
- /*
- * The performance counters don't differentiate between read
- * and write accesses/misses so this isn't strictly correct,
- * but it's the best we can do. Writes and reads get
- * combined.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- /*
- * The ARM performance counters can count micro DTLB misses,
- * micro ITLB misses and main TLB misses. There isn't an event
- * for TLB misses, so use the micro misses here and if users
- * want the main TLB misses they can use a raw counter.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
-};
-
-enum armv6mpcore_perf_types {
- ARMV6MPCORE_PERFCTR_ICACHE_MISS = 0x0,
- ARMV6MPCORE_PERFCTR_IBUF_STALL = 0x1,
- ARMV6MPCORE_PERFCTR_DDEP_STALL = 0x2,
- ARMV6MPCORE_PERFCTR_ITLB_MISS = 0x3,
- ARMV6MPCORE_PERFCTR_DTLB_MISS = 0x4,
- ARMV6MPCORE_PERFCTR_BR_EXEC = 0x5,
- ARMV6MPCORE_PERFCTR_BR_NOTPREDICT = 0x6,
- ARMV6MPCORE_PERFCTR_BR_MISPREDICT = 0x7,
- ARMV6MPCORE_PERFCTR_INSTR_EXEC = 0x8,
- ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
- ARMV6MPCORE_PERFCTR_DCACHE_RDMISS = 0xB,
- ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
- ARMV6MPCORE_PERFCTR_DCACHE_WRMISS = 0xD,
- ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
- ARMV6MPCORE_PERFCTR_SW_PC_CHANGE = 0xF,
- ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS = 0x10,
- ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
- ARMV6MPCORE_PERFCTR_LSU_FULL_STALL = 0x12,
- ARMV6MPCORE_PERFCTR_WBUF_DRAINED = 0x13,
- ARMV6MPCORE_PERFCTR_CPU_CYCLES = 0xFF,
-};
-
-/*
- * The hardware events that we support. We do support cache operations but
- * we have harvard caches and no way to combine instruction and data
- * accesses/misses in hardware.
- */
-static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
- [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
- [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
-};
-
-static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
- [C(L1D)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
- [C(RESULT_MISS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
- [C(RESULT_MISS)] =
- ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- /*
- * The ARM performance counters can count micro DTLB misses,
- * micro ITLB misses and main TLB misses. There isn't an event
- * for TLB misses, so use the micro misses here and if users
- * want the main TLB misses they can use a raw counter.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
-};
-
-static inline unsigned long
-armv6_pmcr_read(void)
-{
- u32 val;
- asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r"(val));
- return val;
-}
-
-static inline void
-armv6_pmcr_write(unsigned long val)
-{
- asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r"(val));
-}
-
-#define ARMV6_PMCR_ENABLE (1 << 0)
-#define ARMV6_PMCR_CTR01_RESET (1 << 1)
-#define ARMV6_PMCR_CCOUNT_RESET (1 << 2)
-#define ARMV6_PMCR_CCOUNT_DIV (1 << 3)
-#define ARMV6_PMCR_COUNT0_IEN (1 << 4)
-#define ARMV6_PMCR_COUNT1_IEN (1 << 5)
-#define ARMV6_PMCR_CCOUNT_IEN (1 << 6)
-#define ARMV6_PMCR_COUNT0_OVERFLOW (1 << 8)
-#define ARMV6_PMCR_COUNT1_OVERFLOW (1 << 9)
-#define ARMV6_PMCR_CCOUNT_OVERFLOW (1 << 10)
-#define ARMV6_PMCR_EVT_COUNT0_SHIFT 20
-#define ARMV6_PMCR_EVT_COUNT0_MASK (0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
-#define ARMV6_PMCR_EVT_COUNT1_SHIFT 12
-#define ARMV6_PMCR_EVT_COUNT1_MASK (0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)
-
-#define ARMV6_PMCR_OVERFLOWED_MASK \
- (ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
- ARMV6_PMCR_CCOUNT_OVERFLOW)
-
-static inline int
-armv6_pmcr_has_overflowed(unsigned long pmcr)
-{
- return pmcr & ARMV6_PMCR_OVERFLOWED_MASK;
-}
-
-static inline int
-armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
- enum armv6_counters counter)
-{
- int ret = 0;
-
- if (ARMV6_CYCLE_COUNTER == counter)
- ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
- else if (ARMV6_COUNTER0 == counter)
- ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
- else if (ARMV6_COUNTER1 == counter)
- ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
- else
- WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-
- return ret;
-}
-
-static inline u32
-armv6pmu_read_counter(int counter)
-{
- unsigned long value = 0;
-
- if (ARMV6_CYCLE_COUNTER == counter)
- asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r"(value));
- else if (ARMV6_COUNTER0 == counter)
- asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r"(value));
- else if (ARMV6_COUNTER1 == counter)
- asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r"(value));
- else
- WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-
- return value;
-}
-
-static inline void
-armv6pmu_write_counter(int counter,
- u32 value)
-{
- if (ARMV6_CYCLE_COUNTER == counter)
- asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r"(value));
- else if (ARMV6_COUNTER0 == counter)
- asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r"(value));
- else if (ARMV6_COUNTER1 == counter)
- asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r"(value));
- else
- WARN_ONCE(1, "invalid counter number (%d)\n", counter);
-}
-
-static void
-armv6pmu_enable_event(struct hw_perf_event *hwc,
- int idx)
-{
- unsigned long val, mask, evt, flags;
-
- if (ARMV6_CYCLE_COUNTER == idx) {
- mask = 0;
- evt = ARMV6_PMCR_CCOUNT_IEN;
- } else if (ARMV6_COUNTER0 == idx) {
- mask = ARMV6_PMCR_EVT_COUNT0_MASK;
- evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
- ARMV6_PMCR_COUNT0_IEN;
- } else if (ARMV6_COUNTER1 == idx) {
- mask = ARMV6_PMCR_EVT_COUNT1_MASK;
- evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
- ARMV6_PMCR_COUNT1_IEN;
- } else {
- WARN_ONCE(1, "invalid counter number (%d)\n", idx);
- return;
- }
-
- /*
- * Mask out the current event and set the counter to count the event
- * that we're interested in.
- */
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = armv6_pmcr_read();
- val &= ~mask;
- val |= evt;
- armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static irqreturn_t
-armv6pmu_handle_irq(int irq_num,
- void *dev)
-{
- unsigned long pmcr = armv6_pmcr_read();
- struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- struct pt_regs *regs;
- int idx;
-
- if (!armv6_pmcr_has_overflowed(pmcr))
- return IRQ_NONE;
-
- regs = get_irq_regs();
-
- /*
- * The interrupts are cleared by writing the overflow flags back to
- * the control register. All of the other bits don't have any effect
- * if they are rewritten, so write the whole value back.
- */
- armv6_pmcr_write(pmcr);
-
- perf_sample_data_init(&data, 0);
-
- cpuc = &__get_cpu_var(cpu_hw_events);
- for (idx = 0; idx <= armpmu->num_events; ++idx) {
- struct perf_event *event = cpuc->events[idx];
- struct hw_perf_event *hwc;
-
- if (!test_bit(idx, cpuc->active_mask))
- continue;
-
- /*
- * We have a single interrupt for all counters. Check that
- * each counter has overflowed before we process it.
- */
- if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
- continue;
-
- hwc = &event->hw;
- armpmu_event_update(event, hwc, idx);
- data.period = event->hw.last_period;
- if (!armpmu_event_set_period(event, hwc, idx))
- continue;
-
- if (perf_event_overflow(event, 0, &data, regs))
- armpmu->disable(hwc, idx);
- }
-
- /*
- * Handle the pending perf events.
- *
- * Note: this call *must* be run with interrupts disabled. For
- * platforms that can have the PMU interrupts raised as an NMI, this
- * will not work.
- */
- irq_work_run();
-
- return IRQ_HANDLED;
-}
-
-static void
-armv6pmu_start(void)
-{
- unsigned long flags, val;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = armv6_pmcr_read();
- val |= ARMV6_PMCR_ENABLE;
- armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-armv6pmu_stop(void)
-{
- unsigned long flags, val;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = armv6_pmcr_read();
- val &= ~ARMV6_PMCR_ENABLE;
- armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static int
-armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
- struct hw_perf_event *event)
-{
- /* Always place a cycle counter into the cycle counter. */
- if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) {
- if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
- return -EAGAIN;
-
- return ARMV6_CYCLE_COUNTER;
- } else {
- /*
- * For anything other than a cycle counter, try and use
- * counter0 and counter1.
- */
- if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask))
- return ARMV6_COUNTER1;
-
- if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask))
- return ARMV6_COUNTER0;
-
- /* The counters are all in use. */
- return -EAGAIN;
- }
-}
-
-static void
-armv6pmu_disable_event(struct hw_perf_event *hwc,
- int idx)
-{
- unsigned long val, mask, evt, flags;
-
- if (ARMV6_CYCLE_COUNTER == idx) {
- mask = ARMV6_PMCR_CCOUNT_IEN;
- evt = 0;
- } else if (ARMV6_COUNTER0 == idx) {
- mask = ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
- evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
- } else if (ARMV6_COUNTER1 == idx) {
- mask = ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
- evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
- } else {
- WARN_ONCE(1, "invalid counter number (%d)\n", idx);
- return;
- }
-
- /*
- * Mask out the current event and set the counter to count the number
- * of ETM bus signal assertion cycles. The external reporting should
- * be disabled and so this should never increment.
- */
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = armv6_pmcr_read();
- val &= ~mask;
- val |= evt;
- armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
- int idx)
-{
- unsigned long val, mask, flags, evt = 0;
-
- if (ARMV6_CYCLE_COUNTER == idx) {
- mask = ARMV6_PMCR_CCOUNT_IEN;
- } else if (ARMV6_COUNTER0 == idx) {
- mask = ARMV6_PMCR_COUNT0_IEN;
- } else if (ARMV6_COUNTER1 == idx) {
- mask = ARMV6_PMCR_COUNT1_IEN;
- } else {
- WARN_ONCE(1, "invalid counter number (%d)\n", idx);
- return;
- }
-
- /*
- * Unlike UP ARMv6, we don't have a way of stopping the counters. We
- * simply disable the interrupt reporting.
- */
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = armv6_pmcr_read();
- val &= ~mask;
- val |= evt;
- armv6_pmcr_write(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static const struct arm_pmu armv6pmu = {
- .id = ARM_PERF_PMU_ID_V6,
- .name = "v6",
- .handle_irq = armv6pmu_handle_irq,
- .enable = armv6pmu_enable_event,
- .disable = armv6pmu_disable_event,
- .read_counter = armv6pmu_read_counter,
- .write_counter = armv6pmu_write_counter,
- .get_event_idx = armv6pmu_get_event_idx,
- .start = armv6pmu_start,
- .stop = armv6pmu_stop,
- .cache_map = &armv6_perf_cache_map,
- .event_map = &armv6_perf_map,
- .raw_event_mask = 0xFF,
- .num_events = 3,
- .max_period = (1LLU << 32) - 1,
-};
-
-static const struct arm_pmu *__init armv6pmu_init(void)
-{
- return &armv6pmu;
-}
-
-/*
- * ARMv6mpcore is almost identical to single core ARMv6 with the exception
- * that some of the events have different enumerations and that there is no
- * *hack* to stop the programmable counters. To stop the counters we simply
- * disable the interrupt reporting and update the event. When unthrottling we
- * reset the period and enable the interrupt reporting.
- */
-static const struct arm_pmu armv6mpcore_pmu = {
- .id = ARM_PERF_PMU_ID_V6MP,
- .name = "v6mpcore",
- .handle_irq = armv6pmu_handle_irq,
- .enable = armv6pmu_enable_event,
- .disable = armv6mpcore_pmu_disable_event,
- .read_counter = armv6pmu_read_counter,
- .write_counter = armv6pmu_write_counter,
- .get_event_idx = armv6pmu_get_event_idx,
- .start = armv6pmu_start,
- .stop = armv6pmu_stop,
- .cache_map = &armv6mpcore_perf_cache_map,
- .event_map = &armv6mpcore_perf_map,
- .raw_event_mask = 0xFF,
- .num_events = 3,
- .max_period = (1LLU << 32) - 1,
-};
-
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
-{
- return &armv6mpcore_pmu;
-}
-#else
-static const struct arm_pmu *__init armv6pmu_init(void)
-{
- return NULL;
-}
-
-static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
-{
- return NULL;
-}
-#endif /* CONFIG_CPU_V6 */
diff --git a/trunk/arch/arm/kernel/perf_event_v7.c b/trunk/arch/arm/kernel/perf_event_v7.c
deleted file mode 100644
index 2e1402556fa0..000000000000
--- a/trunk/arch/arm/kernel/perf_event_v7.c
+++ /dev/null
@@ -1,906 +0,0 @@
-/*
- * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code.
- *
- * ARMv7 support: Jean Pihet
- * 2010 (c) MontaVista Software, LLC.
- *
- * Copied from ARMv6 code, with the low level code inspired
- * by the ARMv7 Oprofile code.
- *
- * Cortex-A8 has up to 4 configurable performance counters and
- * a single cycle counter.
- * Cortex-A9 has up to 31 configurable performance counters and
- * a single cycle counter.
- *
- * All counters can be enabled/disabled and IRQ masked separately. The cycle
- * counter and all 4 performance counters together can be reset separately.
- */
-
-#ifdef CONFIG_CPU_V7
-/* Common ARMv7 event types */
-enum armv7_perf_types {
- ARMV7_PERFCTR_PMNC_SW_INCR = 0x00,
- ARMV7_PERFCTR_IFETCH_MISS = 0x01,
- ARMV7_PERFCTR_ITLB_MISS = 0x02,
- ARMV7_PERFCTR_DCACHE_REFILL = 0x03,
- ARMV7_PERFCTR_DCACHE_ACCESS = 0x04,
- ARMV7_PERFCTR_DTLB_REFILL = 0x05,
- ARMV7_PERFCTR_DREAD = 0x06,
- ARMV7_PERFCTR_DWRITE = 0x07,
-
- ARMV7_PERFCTR_EXC_TAKEN = 0x09,
- ARMV7_PERFCTR_EXC_EXECUTED = 0x0A,
- ARMV7_PERFCTR_CID_WRITE = 0x0B,
- /* ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
- * It counts:
- * - all branch instructions,
- * - instructions that explicitly write the PC,
- * - exception generating instructions.
- */
- ARMV7_PERFCTR_PC_WRITE = 0x0C,
- ARMV7_PERFCTR_PC_IMM_BRANCH = 0x0D,
- ARMV7_PERFCTR_UNALIGNED_ACCESS = 0x0F,
- ARMV7_PERFCTR_PC_BRANCH_MIS_PRED = 0x10,
- ARMV7_PERFCTR_CLOCK_CYCLES = 0x11,
-
- ARMV7_PERFCTR_PC_BRANCH_MIS_USED = 0x12,
-
- ARMV7_PERFCTR_CPU_CYCLES = 0xFF
-};
-
-/* ARMv7 Cortex-A8 specific event types */
-enum armv7_a8_perf_types {
- ARMV7_PERFCTR_INSTR_EXECUTED = 0x08,
-
- ARMV7_PERFCTR_PC_PROC_RETURN = 0x0E,
-
- ARMV7_PERFCTR_WRITE_BUFFER_FULL = 0x40,
- ARMV7_PERFCTR_L2_STORE_MERGED = 0x41,
- ARMV7_PERFCTR_L2_STORE_BUFF = 0x42,
- ARMV7_PERFCTR_L2_ACCESS = 0x43,
- ARMV7_PERFCTR_L2_CACH_MISS = 0x44,
- ARMV7_PERFCTR_AXI_READ_CYCLES = 0x45,
- ARMV7_PERFCTR_AXI_WRITE_CYCLES = 0x46,
- ARMV7_PERFCTR_MEMORY_REPLAY = 0x47,
- ARMV7_PERFCTR_UNALIGNED_ACCESS_REPLAY = 0x48,
- ARMV7_PERFCTR_L1_DATA_MISS = 0x49,
- ARMV7_PERFCTR_L1_INST_MISS = 0x4A,
- ARMV7_PERFCTR_L1_DATA_COLORING = 0x4B,
- ARMV7_PERFCTR_L1_NEON_DATA = 0x4C,
- ARMV7_PERFCTR_L1_NEON_CACH_DATA = 0x4D,
- ARMV7_PERFCTR_L2_NEON = 0x4E,
- ARMV7_PERFCTR_L2_NEON_HIT = 0x4F,
- ARMV7_PERFCTR_L1_INST = 0x50,
- ARMV7_PERFCTR_PC_RETURN_MIS_PRED = 0x51,
- ARMV7_PERFCTR_PC_BRANCH_FAILED = 0x52,
- ARMV7_PERFCTR_PC_BRANCH_TAKEN = 0x53,
- ARMV7_PERFCTR_PC_BRANCH_EXECUTED = 0x54,
- ARMV7_PERFCTR_OP_EXECUTED = 0x55,
- ARMV7_PERFCTR_CYCLES_INST_STALL = 0x56,
- ARMV7_PERFCTR_CYCLES_INST = 0x57,
- ARMV7_PERFCTR_CYCLES_NEON_DATA_STALL = 0x58,
- ARMV7_PERFCTR_CYCLES_NEON_INST_STALL = 0x59,
- ARMV7_PERFCTR_NEON_CYCLES = 0x5A,
-
- ARMV7_PERFCTR_PMU0_EVENTS = 0x70,
- ARMV7_PERFCTR_PMU1_EVENTS = 0x71,
- ARMV7_PERFCTR_PMU_EVENTS = 0x72,
-};
-
-/* ARMv7 Cortex-A9 specific event types */
-enum armv7_a9_perf_types {
- ARMV7_PERFCTR_JAVA_HW_BYTECODE_EXEC = 0x40,
- ARMV7_PERFCTR_JAVA_SW_BYTECODE_EXEC = 0x41,
- ARMV7_PERFCTR_JAZELLE_BRANCH_EXEC = 0x42,
-
- ARMV7_PERFCTR_COHERENT_LINE_MISS = 0x50,
- ARMV7_PERFCTR_COHERENT_LINE_HIT = 0x51,
-
- ARMV7_PERFCTR_ICACHE_DEP_STALL_CYCLES = 0x60,
- ARMV7_PERFCTR_DCACHE_DEP_STALL_CYCLES = 0x61,
- ARMV7_PERFCTR_TLB_MISS_DEP_STALL_CYCLES = 0x62,
- ARMV7_PERFCTR_STREX_EXECUTED_PASSED = 0x63,
- ARMV7_PERFCTR_STREX_EXECUTED_FAILED = 0x64,
- ARMV7_PERFCTR_DATA_EVICTION = 0x65,
- ARMV7_PERFCTR_ISSUE_STAGE_NO_INST = 0x66,
- ARMV7_PERFCTR_ISSUE_STAGE_EMPTY = 0x67,
- ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE = 0x68,
-
- ARMV7_PERFCTR_PREDICTABLE_FUNCT_RETURNS = 0x6E,
-
- ARMV7_PERFCTR_MAIN_UNIT_EXECUTED_INST = 0x70,
- ARMV7_PERFCTR_SECOND_UNIT_EXECUTED_INST = 0x71,
- ARMV7_PERFCTR_LD_ST_UNIT_EXECUTED_INST = 0x72,
- ARMV7_PERFCTR_FP_EXECUTED_INST = 0x73,
- ARMV7_PERFCTR_NEON_EXECUTED_INST = 0x74,
-
- ARMV7_PERFCTR_PLD_FULL_DEP_STALL_CYCLES = 0x80,
- ARMV7_PERFCTR_DATA_WR_DEP_STALL_CYCLES = 0x81,
- ARMV7_PERFCTR_ITLB_MISS_DEP_STALL_CYCLES = 0x82,
- ARMV7_PERFCTR_DTLB_MISS_DEP_STALL_CYCLES = 0x83,
- ARMV7_PERFCTR_MICRO_ITLB_MISS_DEP_STALL_CYCLES = 0x84,
- ARMV7_PERFCTR_MICRO_DTLB_MISS_DEP_STALL_CYCLES = 0x85,
- ARMV7_PERFCTR_DMB_DEP_STALL_CYCLES = 0x86,
-
- ARMV7_PERFCTR_INTGR_CLK_ENABLED_CYCLES = 0x8A,
- ARMV7_PERFCTR_DATA_ENGINE_CLK_EN_CYCLES = 0x8B,
-
- ARMV7_PERFCTR_ISB_INST = 0x90,
- ARMV7_PERFCTR_DSB_INST = 0x91,
- ARMV7_PERFCTR_DMB_INST = 0x92,
- ARMV7_PERFCTR_EXT_INTERRUPTS = 0x93,
-
- ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_COMPLETED = 0xA0,
- ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_SKIPPED = 0xA1,
- ARMV7_PERFCTR_PLE_FIFO_FLUSH = 0xA2,
- ARMV7_PERFCTR_PLE_RQST_COMPLETED = 0xA3,
- ARMV7_PERFCTR_PLE_FIFO_OVERFLOW = 0xA4,
- ARMV7_PERFCTR_PLE_RQST_PROG = 0xA5
-};
-
-/*
- * Cortex-A8 HW events mapping
- *
- * The hardware events that we support. We do support cache operations but
- * we have harvard caches and no way to combine instruction and data
- * accesses/misses in hardware.
- */
-static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED,
- [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
- [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES,
-};
-
-static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
- [C(L1D)] = {
- /*
- * The performance counters don't differentiate between read
- * and write accesses/misses so this isn't strictly correct,
- * but it's the best we can do. Writes and reads get
- * combined.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_INST,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_INST_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_INST,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_L1_INST_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_ACCESS,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACH_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_ACCESS,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACH_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- /*
- * Only ITLB misses and DTLB refills are supported.
- * If users want the DTLB refills misses a raw counter
- * must be used.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
- [C(RESULT_MISS)]
- = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
- [C(RESULT_MISS)]
- = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
-};
-
-/*
- * Cortex-A9 HW events mapping
- */
-static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] =
- ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
- [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_COHERENT_LINE_HIT,
- [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_COHERENT_LINE_MISS,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
- [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES,
-};
-
-static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
- [C(L1D)] = {
- /*
- * The performance counters don't differentiate between read
- * and write accesses/misses so this isn't strictly correct,
- * but it's the best we can do. Writes and reads get
- * combined.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DCACHE_REFILL,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_IFETCH_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- /*
- * Only ITLB misses and DTLB refills are supported.
- * If users want the DTLB refills misses a raw counter
- * must be used.
- */
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
- [C(RESULT_MISS)]
- = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_WRITE,
- [C(RESULT_MISS)]
- = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
-};
-
-/*
- * Perf Events counters
- */
-enum armv7_counters {
- ARMV7_CYCLE_COUNTER = 1, /* Cycle counter */
- ARMV7_COUNTER0 = 2, /* First event counter */
-};
-
-/*
- * The cycle counter is ARMV7_CYCLE_COUNTER.
- * The first event counter is ARMV7_COUNTER0.
- * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
- */
-#define ARMV7_COUNTER_LAST (ARMV7_COUNTER0 + armpmu->num_events - 1)
-
-/*
- * ARMv7 low level PMNC access
- */
-
-/*
- * Per-CPU PMNC: config reg
- */
-#define ARMV7_PMNC_E (1 << 0) /* Enable all counters */
-#define ARMV7_PMNC_P (1 << 1) /* Reset all counters */
-#define ARMV7_PMNC_C (1 << 2) /* Cycle counter reset */
-#define ARMV7_PMNC_D (1 << 3) /* CCNT counts every 64th cpu cycle */
-#define ARMV7_PMNC_X (1 << 4) /* Export to ETM */
-#define ARMV7_PMNC_DP (1 << 5) /* Disable CCNT if non-invasive debug*/
-#define ARMV7_PMNC_N_SHIFT 11 /* Number of counters supported */
-#define ARMV7_PMNC_N_MASK 0x1f
-#define ARMV7_PMNC_MASK 0x3f /* Mask for writable bits */
-
-/*
- * Available counters
- */
-#define ARMV7_CNT0 0 /* First event counter */
-#define ARMV7_CCNT 31 /* Cycle counter */
-
-/* Perf Event to low level counters mapping */
-#define ARMV7_EVENT_CNT_TO_CNTx (ARMV7_COUNTER0 - ARMV7_CNT0)
-
-/*
- * CNTENS: counters enable reg
- */
-#define ARMV7_CNTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENS_C (1 << ARMV7_CCNT)
-
-/*
- * CNTENC: counters disable reg
- */
-#define ARMV7_CNTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_CNTENC_C (1 << ARMV7_CCNT)
-
-/*
- * INTENS: counters overflow interrupt enable reg
- */
-#define ARMV7_INTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENS_C (1 << ARMV7_CCNT)
-
-/*
- * INTENC: counters overflow interrupt disable reg
- */
-#define ARMV7_INTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_INTENC_C (1 << ARMV7_CCNT)
-
-/*
- * EVTSEL: Event selection reg
- */
-#define ARMV7_EVTSEL_MASK 0xff /* Mask for writable bits */
-
-/*
- * SELECT: Counter selection reg
- */
-#define ARMV7_SELECT_MASK 0x1f /* Mask for writable bits */
-
-/*
- * FLAG: counters overflow flag status reg
- */
-#define ARMV7_FLAG_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
-#define ARMV7_FLAG_C (1 << ARMV7_CCNT)
-#define ARMV7_FLAG_MASK 0xffffffff /* Mask for writable bits */
-#define ARMV7_OVERFLOWED_MASK ARMV7_FLAG_MASK
-
-static inline unsigned long armv7_pmnc_read(void)
-{
- u32 val;
- asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
- return val;
-}
-
-static inline void armv7_pmnc_write(unsigned long val)
-{
- val &= ARMV7_PMNC_MASK;
- asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
-}
-
-static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
-{
- return pmnc & ARMV7_OVERFLOWED_MASK;
-}
-
-static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
- enum armv7_counters counter)
-{
- int ret = 0;
-
- if (counter == ARMV7_CYCLE_COUNTER)
- ret = pmnc & ARMV7_FLAG_C;
- else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
- ret = pmnc & ARMV7_FLAG_P(counter);
- else
- pr_err("CPU%u checking wrong counter %d overflow status\n",
- smp_processor_id(), counter);
-
- return ret;
-}
-
-static inline int armv7_pmnc_select_counter(unsigned int idx)
-{
- u32 val;
-
- if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
- pr_err("CPU%u selecting wrong PMNC counter"
- " %d\n", smp_processor_id(), idx);
- return -1;
- }
-
- val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
- asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
-
- return idx;
-}
-
-static inline u32 armv7pmu_read_counter(int idx)
-{
- unsigned long value = 0;
-
- if (idx == ARMV7_CYCLE_COUNTER)
- asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
- else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
- if (armv7_pmnc_select_counter(idx) == idx)
- asm volatile("mrc p15, 0, %0, c9, c13, 2"
- : "=r" (value));
- } else
- pr_err("CPU%u reading wrong counter %d\n",
- smp_processor_id(), idx);
-
- return value;
-}
-
-static inline void armv7pmu_write_counter(int idx, u32 value)
-{
- if (idx == ARMV7_CYCLE_COUNTER)
- asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
- else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
- if (armv7_pmnc_select_counter(idx) == idx)
- asm volatile("mcr p15, 0, %0, c9, c13, 2"
- : : "r" (value));
- } else
- pr_err("CPU%u writing wrong counter %d\n",
- smp_processor_id(), idx);
-}
-
-static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
-{
- if (armv7_pmnc_select_counter(idx) == idx) {
- val &= ARMV7_EVTSEL_MASK;
- asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
- }
-}
-
-static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
-{
- u32 val;
-
- if ((idx != ARMV7_CYCLE_COUNTER) &&
- ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
- pr_err("CPU%u enabling wrong PMNC counter"
- " %d\n", smp_processor_id(), idx);
- return -1;
- }
-
- if (idx == ARMV7_CYCLE_COUNTER)
- val = ARMV7_CNTENS_C;
- else
- val = ARMV7_CNTENS_P(idx);
-
- asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
-
- return idx;
-}
-
-static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
-{
- u32 val;
-
-
- if ((idx != ARMV7_CYCLE_COUNTER) &&
- ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
- pr_err("CPU%u disabling wrong PMNC counter"
- " %d\n", smp_processor_id(), idx);
- return -1;
- }
-
- if (idx == ARMV7_CYCLE_COUNTER)
- val = ARMV7_CNTENC_C;
- else
- val = ARMV7_CNTENC_P(idx);
-
- asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
-
- return idx;
-}
-
-static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
-{
- u32 val;
-
- if ((idx != ARMV7_CYCLE_COUNTER) &&
- ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
- pr_err("CPU%u enabling wrong PMNC counter"
- " interrupt enable %d\n", smp_processor_id(), idx);
- return -1;
- }
-
- if (idx == ARMV7_CYCLE_COUNTER)
- val = ARMV7_INTENS_C;
- else
- val = ARMV7_INTENS_P(idx);
-
- asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
-
- return idx;
-}
-
-static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
-{
- u32 val;
-
- if ((idx != ARMV7_CYCLE_COUNTER) &&
- ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
- pr_err("CPU%u disabling wrong PMNC counter"
- " interrupt enable %d\n", smp_processor_id(), idx);
- return -1;
- }
-
- if (idx == ARMV7_CYCLE_COUNTER)
- val = ARMV7_INTENC_C;
- else
- val = ARMV7_INTENC_P(idx);
-
- asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
-
- return idx;
-}
-
-static inline u32 armv7_pmnc_getreset_flags(void)
-{
- u32 val;
-
- /* Read */
- asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
-
- /* Write to clear flags */
- val &= ARMV7_FLAG_MASK;
- asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val));
-
- return val;
-}
-
-#ifdef DEBUG
-static void armv7_pmnc_dump_regs(void)
-{
- u32 val;
- unsigned int cnt;
-
- printk(KERN_INFO "PMNC registers dump:\n");
-
- asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
- printk(KERN_INFO "PMNC =0x%08x\n", val);
-
- asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
- printk(KERN_INFO "CNTENS=0x%08x\n", val);
-
- asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
- printk(KERN_INFO "INTENS=0x%08x\n", val);
-
- asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
- printk(KERN_INFO "FLAGS =0x%08x\n", val);
-
- asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
- printk(KERN_INFO "SELECT=0x%08x\n", val);
-
- asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
- printk(KERN_INFO "CCNT =0x%08x\n", val);
-
- for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
- armv7_pmnc_select_counter(cnt);
- asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
- printk(KERN_INFO "CNT[%d] count =0x%08x\n",
- cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
- asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
- printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
- cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
- }
-}
-#endif
-
-static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
- unsigned long flags;
-
- /*
- * Enable counter and interrupt, and set the counter to count
- * the event that we're interested in.
- */
- raw_spin_lock_irqsave(&pmu_lock, flags);
-
- /*
- * Disable counter
- */
- armv7_pmnc_disable_counter(idx);
-
- /*
- * Set event (if destined for PMNx counters)
- * We don't need to set the event if it's a cycle count
- */
- if (idx != ARMV7_CYCLE_COUNTER)
- armv7_pmnc_write_evtsel(idx, hwc->config_base);
-
- /*
- * Enable interrupt for this counter
- */
- armv7_pmnc_enable_intens(idx);
-
- /*
- * Enable counter
- */
- armv7_pmnc_enable_counter(idx);
-
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
- unsigned long flags;
-
- /*
- * Disable counter and interrupt
- */
- raw_spin_lock_irqsave(&pmu_lock, flags);
-
- /*
- * Disable counter
- */
- armv7_pmnc_disable_counter(idx);
-
- /*
- * Disable interrupt for this counter
- */
- armv7_pmnc_disable_intens(idx);
-
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
-{
- unsigned long pmnc;
- struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- struct pt_regs *regs;
- int idx;
-
- /*
- * Get and reset the IRQ flags
- */
- pmnc = armv7_pmnc_getreset_flags();
-
- /*
- * Did an overflow occur?
- */
- if (!armv7_pmnc_has_overflowed(pmnc))
- return IRQ_NONE;
-
- /*
- * Handle the counter(s) overflow(s)
- */
- regs = get_irq_regs();
-
- perf_sample_data_init(&data, 0);
-
- cpuc = &__get_cpu_var(cpu_hw_events);
- for (idx = 0; idx <= armpmu->num_events; ++idx) {
- struct perf_event *event = cpuc->events[idx];
- struct hw_perf_event *hwc;
-
- if (!test_bit(idx, cpuc->active_mask))
- continue;
-
- /*
- * We have a single interrupt for all counters. Check that
- * each counter has overflowed before we process it.
- */
- if (!armv7_pmnc_counter_has_overflowed(pmnc, idx))
- continue;
-
- hwc = &event->hw;
- armpmu_event_update(event, hwc, idx);
- data.period = event->hw.last_period;
- if (!armpmu_event_set_period(event, hwc, idx))
- continue;
-
- if (perf_event_overflow(event, 0, &data, regs))
- armpmu->disable(hwc, idx);
- }
-
- /*
- * Handle the pending perf events.
- *
- * Note: this call *must* be run with interrupts disabled. For
- * platforms that can have the PMU interrupts raised as an NMI, this
- * will not work.
- */
- irq_work_run();
-
- return IRQ_HANDLED;
-}
-
-static void armv7pmu_start(void)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- /* Enable all counters */
- armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void armv7pmu_stop(void)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- /* Disable all counters */
- armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
- struct hw_perf_event *event)
-{
- int idx;
-
- /* Always place a cycle counter into the cycle counter. */
- if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
- if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
- return -EAGAIN;
-
- return ARMV7_CYCLE_COUNTER;
- } else {
- /*
- * For anything other than a cycle counter, try and use
- * the events counters
- */
- for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
- if (!test_and_set_bit(idx, cpuc->used_mask))
- return idx;
- }
-
- /* The counters are all in use. */
- return -EAGAIN;
- }
-}
-
-static struct arm_pmu armv7pmu = {
- .handle_irq = armv7pmu_handle_irq,
- .enable = armv7pmu_enable_event,
- .disable = armv7pmu_disable_event,
- .read_counter = armv7pmu_read_counter,
- .write_counter = armv7pmu_write_counter,
- .get_event_idx = armv7pmu_get_event_idx,
- .start = armv7pmu_start,
- .stop = armv7pmu_stop,
- .raw_event_mask = 0xFF,
- .max_period = (1LLU << 32) - 1,
-};
-
-static u32 __init armv7_reset_read_pmnc(void)
-{
- u32 nb_cnt;
-
- /* Initialize & Reset PMNC: C and P bits */
- armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
-
- /* Read the nb of CNTx counters supported from PMNC */
- nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
-
- /* Add the CPU cycles counter and return */
- return nb_cnt + 1;
-}
-
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
-{
- armv7pmu.id = ARM_PERF_PMU_ID_CA8;
- armv7pmu.name = "ARMv7 Cortex-A8";
- armv7pmu.cache_map = &armv7_a8_perf_cache_map;
- armv7pmu.event_map = &armv7_a8_perf_map;
- armv7pmu.num_events = armv7_reset_read_pmnc();
- return &armv7pmu;
-}
-
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
-{
- armv7pmu.id = ARM_PERF_PMU_ID_CA9;
- armv7pmu.name = "ARMv7 Cortex-A9";
- armv7pmu.cache_map = &armv7_a9_perf_cache_map;
- armv7pmu.event_map = &armv7_a9_perf_map;
- armv7pmu.num_events = armv7_reset_read_pmnc();
- return &armv7pmu;
-}
-#else
-static const struct arm_pmu *__init armv7_a8_pmu_init(void)
-{
- return NULL;
-}
-
-static const struct arm_pmu *__init armv7_a9_pmu_init(void)
-{
- return NULL;
-}
-#endif /* CONFIG_CPU_V7 */
diff --git a/trunk/arch/arm/kernel/perf_event_xscale.c b/trunk/arch/arm/kernel/perf_event_xscale.c
deleted file mode 100644
index 28cd3b025bc3..000000000000
--- a/trunk/arch/arm/kernel/perf_event_xscale.c
+++ /dev/null
@@ -1,807 +0,0 @@
-/*
- * ARMv5 [xscale] Performance counter handling code.
- *
- * Copyright (C) 2010, ARM Ltd., Will Deacon
- *
- * Based on the previous xscale OProfile code.
- *
- * There are two variants of the xscale PMU that we support:
- * - xscale1pmu: 2 event counters and a cycle counter
- * - xscale2pmu: 4 event counters and a cycle counter
- * The two variants share event definitions, but have different
- * PMU structures.
- */
-
-#ifdef CONFIG_CPU_XSCALE
-enum xscale_perf_types {
- XSCALE_PERFCTR_ICACHE_MISS = 0x00,
- XSCALE_PERFCTR_ICACHE_NO_DELIVER = 0x01,
- XSCALE_PERFCTR_DATA_STALL = 0x02,
- XSCALE_PERFCTR_ITLB_MISS = 0x03,
- XSCALE_PERFCTR_DTLB_MISS = 0x04,
- XSCALE_PERFCTR_BRANCH = 0x05,
- XSCALE_PERFCTR_BRANCH_MISS = 0x06,
- XSCALE_PERFCTR_INSTRUCTION = 0x07,
- XSCALE_PERFCTR_DCACHE_FULL_STALL = 0x08,
- XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG = 0x09,
- XSCALE_PERFCTR_DCACHE_ACCESS = 0x0A,
- XSCALE_PERFCTR_DCACHE_MISS = 0x0B,
- XSCALE_PERFCTR_DCACHE_WRITE_BACK = 0x0C,
- XSCALE_PERFCTR_PC_CHANGED = 0x0D,
- XSCALE_PERFCTR_BCU_REQUEST = 0x10,
- XSCALE_PERFCTR_BCU_FULL = 0x11,
- XSCALE_PERFCTR_BCU_DRAIN = 0x12,
- XSCALE_PERFCTR_BCU_ECC_NO_ELOG = 0x14,
- XSCALE_PERFCTR_BCU_1_BIT_ERR = 0x15,
- XSCALE_PERFCTR_RMW = 0x16,
- /* XSCALE_PERFCTR_CCNT is not hardware defined */
- XSCALE_PERFCTR_CCNT = 0xFE,
- XSCALE_PERFCTR_UNUSED = 0xFF,
-};
-
-enum xscale_counters {
- XSCALE_CYCLE_COUNTER = 1,
- XSCALE_COUNTER0,
- XSCALE_COUNTER1,
- XSCALE_COUNTER2,
- XSCALE_COUNTER3,
-};
-
-static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
- [PERF_COUNT_HW_CPU_CYCLES] = XSCALE_PERFCTR_CCNT,
- [PERF_COUNT_HW_INSTRUCTIONS] = XSCALE_PERFCTR_INSTRUCTION,
- [PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH,
- [PERF_COUNT_HW_BRANCH_MISSES] = XSCALE_PERFCTR_BRANCH_MISS,
- [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
-};
-
-static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
- [C(L1D)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(L1I)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(LL)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(DTLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(ITLB)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
- [C(BPU)] = {
- [C(OP_READ)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_WRITE)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- [C(OP_PREFETCH)] = {
- [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
- [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
- },
- },
-};
-
-#define XSCALE_PMU_ENABLE 0x001
-#define XSCALE_PMN_RESET 0x002
-#define XSCALE_CCNT_RESET 0x004
-#define XSCALE_PMU_RESET (CCNT_RESET | PMN_RESET)
-#define XSCALE_PMU_CNT64 0x008
-
-#define XSCALE1_OVERFLOWED_MASK 0x700
-#define XSCALE1_CCOUNT_OVERFLOW 0x400
-#define XSCALE1_COUNT0_OVERFLOW 0x100
-#define XSCALE1_COUNT1_OVERFLOW 0x200
-#define XSCALE1_CCOUNT_INT_EN 0x040
-#define XSCALE1_COUNT0_INT_EN 0x010
-#define XSCALE1_COUNT1_INT_EN 0x020
-#define XSCALE1_COUNT0_EVT_SHFT 12
-#define XSCALE1_COUNT0_EVT_MASK (0xff << XSCALE1_COUNT0_EVT_SHFT)
-#define XSCALE1_COUNT1_EVT_SHFT 20
-#define XSCALE1_COUNT1_EVT_MASK (0xff << XSCALE1_COUNT1_EVT_SHFT)
-
-static inline u32
-xscale1pmu_read_pmnc(void)
-{
- u32 val;
- asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val));
- return val;
-}
-
-static inline void
-xscale1pmu_write_pmnc(u32 val)
-{
- /* upper 4bits and 7, 11 are write-as-0 */
- val &= 0xffff77f;
- asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val));
-}
-
-static inline int
-xscale1_pmnc_counter_has_overflowed(unsigned long pmnc,
- enum xscale_counters counter)
-{
- int ret = 0;
-
- switch (counter) {
- case XSCALE_CYCLE_COUNTER:
- ret = pmnc & XSCALE1_CCOUNT_OVERFLOW;
- break;
- case XSCALE_COUNTER0:
- ret = pmnc & XSCALE1_COUNT0_OVERFLOW;
- break;
- case XSCALE_COUNTER1:
- ret = pmnc & XSCALE1_COUNT1_OVERFLOW;
- break;
- default:
- WARN_ONCE(1, "invalid counter number (%d)\n", counter);
- }
-
- return ret;
-}
-
-static irqreturn_t
-xscale1pmu_handle_irq(int irq_num, void *dev)
-{
- unsigned long pmnc;
- struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- struct pt_regs *regs;
- int idx;
-
- /*
- * NOTE: there's an A stepping erratum that states if an overflow
- * bit already exists and another occurs, the previous
- * Overflow bit gets cleared. There's no workaround.
- * Fixed in B stepping or later.
- */
- pmnc = xscale1pmu_read_pmnc();
-
- /*
- * Write the value back to clear the overflow flags. Overflow
- * flags remain in pmnc for use below. We also disable the PMU
- * while we process the interrupt.
- */
- xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
-
- if (!(pmnc & XSCALE1_OVERFLOWED_MASK))
- return IRQ_NONE;
-
- regs = get_irq_regs();
-
- perf_sample_data_init(&data, 0);
-
- cpuc = &__get_cpu_var(cpu_hw_events);
- for (idx = 0; idx <= armpmu->num_events; ++idx) {
- struct perf_event *event = cpuc->events[idx];
- struct hw_perf_event *hwc;
-
- if (!test_bit(idx, cpuc->active_mask))
- continue;
-
- if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
- continue;
-
- hwc = &event->hw;
- armpmu_event_update(event, hwc, idx);
- data.period = event->hw.last_period;
- if (!armpmu_event_set_period(event, hwc, idx))
- continue;
-
- if (perf_event_overflow(event, 0, &data, regs))
- armpmu->disable(hwc, idx);
- }
-
- irq_work_run();
-
- /*
- * Re-enable the PMU.
- */
- pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE;
- xscale1pmu_write_pmnc(pmnc);
-
- return IRQ_HANDLED;
-}
-
-static void
-xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
- unsigned long val, mask, evt, flags;
-
- switch (idx) {
- case XSCALE_CYCLE_COUNTER:
- mask = 0;
- evt = XSCALE1_CCOUNT_INT_EN;
- break;
- case XSCALE_COUNTER0:
- mask = XSCALE1_COUNT0_EVT_MASK;
- evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) |
- XSCALE1_COUNT0_INT_EN;
- break;
- case XSCALE_COUNTER1:
- mask = XSCALE1_COUNT1_EVT_MASK;
- evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) |
- XSCALE1_COUNT1_INT_EN;
- break;
- default:
- WARN_ONCE(1, "invalid counter number (%d)\n", idx);
- return;
- }
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = xscale1pmu_read_pmnc();
- val &= ~mask;
- val |= evt;
- xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
- unsigned long val, mask, evt, flags;
-
- switch (idx) {
- case XSCALE_CYCLE_COUNTER:
- mask = XSCALE1_CCOUNT_INT_EN;
- evt = 0;
- break;
- case XSCALE_COUNTER0:
- mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK;
- evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT;
- break;
- case XSCALE_COUNTER1:
- mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK;
- evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT;
- break;
- default:
- WARN_ONCE(1, "invalid counter number (%d)\n", idx);
- return;
- }
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = xscale1pmu_read_pmnc();
- val &= ~mask;
- val |= evt;
- xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static int
-xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
- struct hw_perf_event *event)
-{
- if (XSCALE_PERFCTR_CCNT == event->config_base) {
- if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask))
- return -EAGAIN;
-
- return XSCALE_CYCLE_COUNTER;
- } else {
- if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask))
- return XSCALE_COUNTER1;
-
- if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask))
- return XSCALE_COUNTER0;
-
- return -EAGAIN;
- }
-}
-
-static void
-xscale1pmu_start(void)
-{
- unsigned long flags, val;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = xscale1pmu_read_pmnc();
- val |= XSCALE_PMU_ENABLE;
- xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-xscale1pmu_stop(void)
-{
- unsigned long flags, val;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = xscale1pmu_read_pmnc();
- val &= ~XSCALE_PMU_ENABLE;
- xscale1pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static inline u32
-xscale1pmu_read_counter(int counter)
-{
- u32 val = 0;
-
- switch (counter) {
- case XSCALE_CYCLE_COUNTER:
- asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val));
- break;
- case XSCALE_COUNTER0:
- asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val));
- break;
- case XSCALE_COUNTER1:
- asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val));
- break;
- }
-
- return val;
-}
-
-static inline void
-xscale1pmu_write_counter(int counter, u32 val)
-{
- switch (counter) {
- case XSCALE_CYCLE_COUNTER:
- asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val));
- break;
- case XSCALE_COUNTER0:
- asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val));
- break;
- case XSCALE_COUNTER1:
- asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val));
- break;
- }
-}
-
-static const struct arm_pmu xscale1pmu = {
- .id = ARM_PERF_PMU_ID_XSCALE1,
- .name = "xscale1",
- .handle_irq = xscale1pmu_handle_irq,
- .enable = xscale1pmu_enable_event,
- .disable = xscale1pmu_disable_event,
- .read_counter = xscale1pmu_read_counter,
- .write_counter = xscale1pmu_write_counter,
- .get_event_idx = xscale1pmu_get_event_idx,
- .start = xscale1pmu_start,
- .stop = xscale1pmu_stop,
- .cache_map = &xscale_perf_cache_map,
- .event_map = &xscale_perf_map,
- .raw_event_mask = 0xFF,
- .num_events = 3,
- .max_period = (1LLU << 32) - 1,
-};
-
-static const struct arm_pmu *__init xscale1pmu_init(void)
-{
- return &xscale1pmu;
-}
-
-#define XSCALE2_OVERFLOWED_MASK 0x01f
-#define XSCALE2_CCOUNT_OVERFLOW 0x001
-#define XSCALE2_COUNT0_OVERFLOW 0x002
-#define XSCALE2_COUNT1_OVERFLOW 0x004
-#define XSCALE2_COUNT2_OVERFLOW 0x008
-#define XSCALE2_COUNT3_OVERFLOW 0x010
-#define XSCALE2_CCOUNT_INT_EN 0x001
-#define XSCALE2_COUNT0_INT_EN 0x002
-#define XSCALE2_COUNT1_INT_EN 0x004
-#define XSCALE2_COUNT2_INT_EN 0x008
-#define XSCALE2_COUNT3_INT_EN 0x010
-#define XSCALE2_COUNT0_EVT_SHFT 0
-#define XSCALE2_COUNT0_EVT_MASK (0xff << XSCALE2_COUNT0_EVT_SHFT)
-#define XSCALE2_COUNT1_EVT_SHFT 8
-#define XSCALE2_COUNT1_EVT_MASK (0xff << XSCALE2_COUNT1_EVT_SHFT)
-#define XSCALE2_COUNT2_EVT_SHFT 16
-#define XSCALE2_COUNT2_EVT_MASK (0xff << XSCALE2_COUNT2_EVT_SHFT)
-#define XSCALE2_COUNT3_EVT_SHFT 24
-#define XSCALE2_COUNT3_EVT_MASK (0xff << XSCALE2_COUNT3_EVT_SHFT)
-
-static inline u32
-xscale2pmu_read_pmnc(void)
-{
- u32 val;
- asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val));
- /* bits 1-2 and 4-23 are read-unpredictable */
- return val & 0xff000009;
-}
-
-static inline void
-xscale2pmu_write_pmnc(u32 val)
-{
- /* bits 4-23 are write-as-0, 24-31 are write ignored */
- val &= 0xf;
- asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val));
-}
-
-static inline u32
-xscale2pmu_read_overflow_flags(void)
-{
- u32 val;
- asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val));
- return val;
-}
-
-static inline void
-xscale2pmu_write_overflow_flags(u32 val)
-{
- asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val));
-}
-
-static inline u32
-xscale2pmu_read_event_select(void)
-{
- u32 val;
- asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val));
- return val;
-}
-
-static inline void
-xscale2pmu_write_event_select(u32 val)
-{
- asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val));
-}
-
-static inline u32
-xscale2pmu_read_int_enable(void)
-{
- u32 val;
- asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val));
- return val;
-}
-
-static void
-xscale2pmu_write_int_enable(u32 val)
-{
- asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val));
-}
-
-static inline int
-xscale2_pmnc_counter_has_overflowed(unsigned long of_flags,
- enum xscale_counters counter)
-{
- int ret = 0;
-
- switch (counter) {
- case XSCALE_CYCLE_COUNTER:
- ret = of_flags & XSCALE2_CCOUNT_OVERFLOW;
- break;
- case XSCALE_COUNTER0:
- ret = of_flags & XSCALE2_COUNT0_OVERFLOW;
- break;
- case XSCALE_COUNTER1:
- ret = of_flags & XSCALE2_COUNT1_OVERFLOW;
- break;
- case XSCALE_COUNTER2:
- ret = of_flags & XSCALE2_COUNT2_OVERFLOW;
- break;
- case XSCALE_COUNTER3:
- ret = of_flags & XSCALE2_COUNT3_OVERFLOW;
- break;
- default:
- WARN_ONCE(1, "invalid counter number (%d)\n", counter);
- }
-
- return ret;
-}
-
-static irqreturn_t
-xscale2pmu_handle_irq(int irq_num, void *dev)
-{
- unsigned long pmnc, of_flags;
- struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- struct pt_regs *regs;
- int idx;
-
- /* Disable the PMU. */
- pmnc = xscale2pmu_read_pmnc();
- xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
-
- /* Check the overflow flag register. */
- of_flags = xscale2pmu_read_overflow_flags();
- if (!(of_flags & XSCALE2_OVERFLOWED_MASK))
- return IRQ_NONE;
-
- /* Clear the overflow bits. */
- xscale2pmu_write_overflow_flags(of_flags);
-
- regs = get_irq_regs();
-
- perf_sample_data_init(&data, 0);
-
- cpuc = &__get_cpu_var(cpu_hw_events);
- for (idx = 0; idx <= armpmu->num_events; ++idx) {
- struct perf_event *event = cpuc->events[idx];
- struct hw_perf_event *hwc;
-
- if (!test_bit(idx, cpuc->active_mask))
- continue;
-
- if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
- continue;
-
- hwc = &event->hw;
- armpmu_event_update(event, hwc, idx);
- data.period = event->hw.last_period;
- if (!armpmu_event_set_period(event, hwc, idx))
- continue;
-
- if (perf_event_overflow(event, 0, &data, regs))
- armpmu->disable(hwc, idx);
- }
-
- irq_work_run();
-
- /*
- * Re-enable the PMU.
- */
- pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE;
- xscale2pmu_write_pmnc(pmnc);
-
- return IRQ_HANDLED;
-}
-
-static void
-xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
- unsigned long flags, ien, evtsel;
-
- ien = xscale2pmu_read_int_enable();
- evtsel = xscale2pmu_read_event_select();
-
- switch (idx) {
- case XSCALE_CYCLE_COUNTER:
- ien |= XSCALE2_CCOUNT_INT_EN;
- break;
- case XSCALE_COUNTER0:
- ien |= XSCALE2_COUNT0_INT_EN;
- evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
- evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT;
- break;
- case XSCALE_COUNTER1:
- ien |= XSCALE2_COUNT1_INT_EN;
- evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
- evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT;
- break;
- case XSCALE_COUNTER2:
- ien |= XSCALE2_COUNT2_INT_EN;
- evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
- evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT;
- break;
- case XSCALE_COUNTER3:
- ien |= XSCALE2_COUNT3_INT_EN;
- evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
- evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT;
- break;
- default:
- WARN_ONCE(1, "invalid counter number (%d)\n", idx);
- return;
- }
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- xscale2pmu_write_event_select(evtsel);
- xscale2pmu_write_int_enable(ien);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
- unsigned long flags, ien, evtsel;
-
- ien = xscale2pmu_read_int_enable();
- evtsel = xscale2pmu_read_event_select();
-
- switch (idx) {
- case XSCALE_CYCLE_COUNTER:
- ien &= ~XSCALE2_CCOUNT_INT_EN;
- break;
- case XSCALE_COUNTER0:
- ien &= ~XSCALE2_COUNT0_INT_EN;
- evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
- evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
- break;
- case XSCALE_COUNTER1:
- ien &= ~XSCALE2_COUNT1_INT_EN;
- evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
- evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
- break;
- case XSCALE_COUNTER2:
- ien &= ~XSCALE2_COUNT2_INT_EN;
- evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
- evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
- break;
- case XSCALE_COUNTER3:
- ien &= ~XSCALE2_COUNT3_INT_EN;
- evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
- evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
- break;
- default:
- WARN_ONCE(1, "invalid counter number (%d)\n", idx);
- return;
- }
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- xscale2pmu_write_event_select(evtsel);
- xscale2pmu_write_int_enable(ien);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static int
-xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
- struct hw_perf_event *event)
-{
- int idx = xscale1pmu_get_event_idx(cpuc, event);
- if (idx >= 0)
- goto out;
-
- if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask))
- idx = XSCALE_COUNTER3;
- else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask))
- idx = XSCALE_COUNTER2;
-out:
- return idx;
-}
-
-static void
-xscale2pmu_start(void)
-{
- unsigned long flags, val;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
- val |= XSCALE_PMU_ENABLE;
- xscale2pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static void
-xscale2pmu_stop(void)
-{
- unsigned long flags, val;
-
- raw_spin_lock_irqsave(&pmu_lock, flags);
- val = xscale2pmu_read_pmnc();
- val &= ~XSCALE_PMU_ENABLE;
- xscale2pmu_write_pmnc(val);
- raw_spin_unlock_irqrestore(&pmu_lock, flags);
-}
-
-static inline u32
-xscale2pmu_read_counter(int counter)
-{
- u32 val = 0;
-
- switch (counter) {
- case XSCALE_CYCLE_COUNTER:
- asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val));
- break;
- case XSCALE_COUNTER0:
- asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val));
- break;
- case XSCALE_COUNTER1:
- asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val));
- break;
- case XSCALE_COUNTER2:
- asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val));
- break;
- case XSCALE_COUNTER3:
- asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val));
- break;
- }
-
- return val;
-}
-
-static inline void
-xscale2pmu_write_counter(int counter, u32 val)
-{
- switch (counter) {
- case XSCALE_CYCLE_COUNTER:
- asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val));
- break;
- case XSCALE_COUNTER0:
- asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val));
- break;
- case XSCALE_COUNTER1:
- asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val));
- break;
- case XSCALE_COUNTER2:
- asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val));
- break;
- case XSCALE_COUNTER3:
- asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val));
- break;
- }
-}
-
-static const struct arm_pmu xscale2pmu = {
- .id = ARM_PERF_PMU_ID_XSCALE2,
- .name = "xscale2",
- .handle_irq = xscale2pmu_handle_irq,
- .enable = xscale2pmu_enable_event,
- .disable = xscale2pmu_disable_event,
- .read_counter = xscale2pmu_read_counter,
- .write_counter = xscale2pmu_write_counter,
- .get_event_idx = xscale2pmu_get_event_idx,
- .start = xscale2pmu_start,
- .stop = xscale2pmu_stop,
- .cache_map = &xscale_perf_cache_map,
- .event_map = &xscale_perf_map,
- .raw_event_mask = 0xFF,
- .num_events = 5,
- .max_period = (1LLU << 32) - 1,
-};
-
-static const struct arm_pmu *__init xscale2pmu_init(void)
-{
- return &xscale2pmu;
-}
-#else
-static const struct arm_pmu *__init xscale1pmu_init(void)
-{
- return NULL;
-}
-
-static const struct arm_pmu *__init xscale2pmu_init(void)
-{
- return NULL;
-}
-#endif /* CONFIG_CPU_XSCALE */
diff --git a/trunk/arch/arm/kernel/ptrace.c b/trunk/arch/arm/kernel/ptrace.c
index 19c6816db61e..3e97483abcf0 100644
--- a/trunk/arch/arm/kernel/ptrace.c
+++ b/trunk/arch/arm/kernel/ptrace.c
@@ -1060,8 +1060,8 @@ static int ptrace_sethbpregs(struct task_struct *tsk, long num,
goto out;
if ((gen_type & implied_type) != gen_type) {
- ret = -EINVAL;
- goto out;
+ ret = -EINVAL;
+ goto out;
}
attr.bp_len = gen_len;
diff --git a/trunk/arch/arm/kernel/smp.c b/trunk/arch/arm/kernel/smp.c
index bbca89872c18..8c1959590252 100644
--- a/trunk/arch/arm/kernel/smp.c
+++ b/trunk/arch/arm/kernel/smp.c
@@ -16,7 +16,6 @@
#include
#include
#include
-#include
#include
#include
#include
@@ -458,7 +457,7 @@ static void ipi_timer(void)
}
#ifdef CONFIG_LOCAL_TIMERS
-asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs)
+asmlinkage void __exception do_local_timer(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
int cpu = smp_processor_id();
@@ -545,7 +544,7 @@ static void ipi_cpu_stop(unsigned int cpu)
*
* Bit 0 - Inter-processor function call
*/
-asmlinkage void __exception_irq_entry do_IPI(struct pt_regs *regs)
+asmlinkage void __exception do_IPI(struct pt_regs *regs)
{
unsigned int cpu = smp_processor_id();
struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
diff --git a/trunk/arch/arm/kernel/vmlinux.lds.S b/trunk/arch/arm/kernel/vmlinux.lds.S
index 897c1a8f1694..cead8893b46b 100644
--- a/trunk/arch/arm/kernel/vmlinux.lds.S
+++ b/trunk/arch/arm/kernel/vmlinux.lds.S
@@ -101,7 +101,6 @@ SECTIONS
__exception_text_start = .;
*(.exception.text)
__exception_text_end = .;
- IRQENTRY_TEXT
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
diff --git a/trunk/arch/arm/lib/findbit.S b/trunk/arch/arm/lib/findbit.S
index 64f6bc1a9132..1e4cbd4e7be9 100644
--- a/trunk/arch/arm/lib/findbit.S
+++ b/trunk/arch/arm/lib/findbit.S
@@ -174,8 +174,8 @@ ENDPROC(_find_next_bit_be)
*/
.L_found:
#if __LINUX_ARM_ARCH__ >= 5
- rsb r0, r3, #0
- and r3, r3, r0
+ rsb r1, r3, #0
+ and r3, r3, r1
clz r3, r3
rsb r3, r3, #31
add r0, r2, r3
@@ -190,7 +190,5 @@ ENDPROC(_find_next_bit_be)
addeq r2, r2, #1
mov r0, r2
#endif
- cmp r1, r0 @ Clamp to maxbit
- movlo r0, r1
mov pc, lr
diff --git a/trunk/arch/arm/mach-aaec2000/include/mach/vmalloc.h b/trunk/arch/arm/mach-aaec2000/include/mach/vmalloc.h
index a6299e8321bd..cff4e0a996ce 100644
--- a/trunk/arch/arm/mach-aaec2000/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-aaec2000/include/mach/vmalloc.h
@@ -11,6 +11,6 @@
#ifndef __ASM_ARCH_VMALLOC_H
#define __ASM_ARCH_VMALLOC_H
-#define VMALLOC_END 0xd0000000UL
+#define VMALLOC_END 0xd0000000
#endif /* __ASM_ARCH_VMALLOC_H */
diff --git a/trunk/arch/arm/mach-bcmring/include/mach/vmalloc.h b/trunk/arch/arm/mach-bcmring/include/mach/vmalloc.h
index 7397bd7817d9..3db3a09fd398 100644
--- a/trunk/arch/arm/mach-bcmring/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-bcmring/include/mach/vmalloc.h
@@ -22,4 +22,4 @@
* 0xe0000000 to 0xefffffff. This gives us 256 MB of vm space and handles
* larger physical memory designs better.
*/
-#define VMALLOC_END 0xf0000000UL
+#define VMALLOC_END 0xf0000000
diff --git a/trunk/arch/arm/mach-clps711x/include/mach/vmalloc.h b/trunk/arch/arm/mach-clps711x/include/mach/vmalloc.h
index 467b96137e47..30b3a287ed88 100644
--- a/trunk/arch/arm/mach-clps711x/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-clps711x/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#define VMALLOC_END 0xd0000000UL
+#define VMALLOC_END 0xd0000000
diff --git a/trunk/arch/arm/mach-davinci/dm355.c b/trunk/arch/arm/mach-davinci/dm355.c
index 2652af124acd..9be261beae7d 100644
--- a/trunk/arch/arm/mach-davinci/dm355.c
+++ b/trunk/arch/arm/mach-davinci/dm355.c
@@ -359,8 +359,8 @@ static struct clk_lookup dm355_clks[] = {
CLK(NULL, "uart1", &uart1_clk),
CLK(NULL, "uart2", &uart2_clk),
CLK("i2c_davinci.1", NULL, &i2c_clk),
- CLK("davinci-mcbsp.0", NULL, &asp0_clk),
- CLK("davinci-mcbsp.1", NULL, &asp1_clk),
+ CLK("davinci-asp.0", NULL, &asp0_clk),
+ CLK("davinci-asp.1", NULL, &asp1_clk),
CLK("davinci_mmc.0", NULL, &mmcsd0_clk),
CLK("davinci_mmc.1", NULL, &mmcsd1_clk),
CLK("spi_davinci.0", NULL, &spi0_clk),
@@ -664,7 +664,7 @@ static struct resource dm355_asp1_resources[] = {
};
static struct platform_device dm355_asp1_device = {
- .name = "davinci-mcbsp",
+ .name = "davinci-asp",
.id = 1,
.num_resources = ARRAY_SIZE(dm355_asp1_resources),
.resource = dm355_asp1_resources,
diff --git a/trunk/arch/arm/mach-davinci/dm365.c b/trunk/arch/arm/mach-davinci/dm365.c
index c466d710d3c1..a12065e87266 100644
--- a/trunk/arch/arm/mach-davinci/dm365.c
+++ b/trunk/arch/arm/mach-davinci/dm365.c
@@ -459,7 +459,7 @@ static struct clk_lookup dm365_clks[] = {
CLK(NULL, "usb", &usb_clk),
CLK("davinci_emac.1", NULL, &emac_clk),
CLK("davinci_voicecodec", NULL, &voicecodec_clk),
- CLK("davinci-mcbsp", NULL, &asp0_clk),
+ CLK("davinci-asp.0", NULL, &asp0_clk),
CLK(NULL, "rto", &rto_clk),
CLK(NULL, "mjcp", &mjcp_clk),
CLK(NULL, NULL, NULL),
@@ -922,8 +922,8 @@ static struct resource dm365_asp_resources[] = {
};
static struct platform_device dm365_asp_device = {
- .name = "davinci-mcbsp",
- .id = -1,
+ .name = "davinci-asp",
+ .id = 0,
.num_resources = ARRAY_SIZE(dm365_asp_resources),
.resource = dm365_asp_resources,
};
diff --git a/trunk/arch/arm/mach-davinci/dm644x.c b/trunk/arch/arm/mach-davinci/dm644x.c
index 9a2376b3137c..0608dd776a16 100644
--- a/trunk/arch/arm/mach-davinci/dm644x.c
+++ b/trunk/arch/arm/mach-davinci/dm644x.c
@@ -302,7 +302,7 @@ static struct clk_lookup dm644x_clks[] = {
CLK("davinci_emac.1", NULL, &emac_clk),
CLK("i2c_davinci.1", NULL, &i2c_clk),
CLK("palm_bk3710", NULL, &ide_clk),
- CLK("davinci-mcbsp", NULL, &asp_clk),
+ CLK("davinci-asp", NULL, &asp_clk),
CLK("davinci_mmc.0", NULL, &mmcsd_clk),
CLK(NULL, "spi", &spi_clk),
CLK(NULL, "gpio", &gpio_clk),
@@ -580,7 +580,7 @@ static struct resource dm644x_asp_resources[] = {
};
static struct platform_device dm644x_asp_device = {
- .name = "davinci-mcbsp",
+ .name = "davinci-asp",
.id = -1,
.num_resources = ARRAY_SIZE(dm644x_asp_resources),
.resource = dm644x_asp_resources,
diff --git a/trunk/arch/arm/mach-ebsa110/include/mach/vmalloc.h b/trunk/arch/arm/mach-ebsa110/include/mach/vmalloc.h
index ea141b7a3e03..60bde56fba4c 100644
--- a/trunk/arch/arm/mach-ebsa110/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-ebsa110/include/mach/vmalloc.h
@@ -7,4 +7,4 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
-#define VMALLOC_END 0xdf000000UL
+#define VMALLOC_END 0xdf000000
diff --git a/trunk/arch/arm/mach-footbridge/include/mach/vmalloc.h b/trunk/arch/arm/mach-footbridge/include/mach/vmalloc.h
index 40ba78e5782b..0ffbb7c85e59 100644
--- a/trunk/arch/arm/mach-footbridge/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-footbridge/include/mach/vmalloc.h
@@ -7,4 +7,4 @@
*/
-#define VMALLOC_END 0xf0000000UL
+#define VMALLOC_END 0xf0000000
diff --git a/trunk/arch/arm/mach-h720x/include/mach/vmalloc.h b/trunk/arch/arm/mach-h720x/include/mach/vmalloc.h
index 8520b4a4d4e6..a45915b88756 100644
--- a/trunk/arch/arm/mach-h720x/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-h720x/include/mach/vmalloc.h
@@ -5,6 +5,6 @@
#ifndef __ARCH_ARM_VMALLOC_H
#define __ARCH_ARM_VMALLOC_H
-#define VMALLOC_END 0xd0000000UL
+#define VMALLOC_END 0xd0000000
#endif
diff --git a/trunk/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c b/trunk/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c
index 7e1e9dc2c8fc..026263c665ca 100644
--- a/trunk/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c
+++ b/trunk/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c
@@ -250,6 +250,9 @@ static const struct imxuart_platform_data uart_pdata __initconst = {
.flags = IMXUART_HAVE_RTSCTS,
};
+#if defined(CONFIG_TOUCHSCREEN_ADS7846) \
+ || defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE)
+
#define ADS7846_PENDOWN (GPIO_PORTD | 25)
static void ads7846_dev_init(void)
@@ -270,7 +273,9 @@ static struct ads7846_platform_data ads7846_config __initdata = {
.get_pendown_state = ads7846_get_pendown_state,
.keep_vref_on = 1,
};
+#endif
+#if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE)
static struct spi_board_info eukrea_mbimx27_spi_board_info[] __initdata = {
[0] = {
.modalias = "ads7846",
@@ -289,6 +294,7 @@ static const struct spi_imx_master eukrea_mbimx27_spi0_data __initconst = {
.chipselect = eukrea_mbimx27_spi_cs,
.num_chipselect = ARRAY_SIZE(eukrea_mbimx27_spi_cs),
};
+#endif
static struct i2c_board_info eukrea_mbimx27_i2c_devices[] = {
{
diff --git a/trunk/arch/arm/mach-integrator/include/mach/vmalloc.h b/trunk/arch/arm/mach-integrator/include/mach/vmalloc.h
index 2f5a2bafb11f..e056e7cf5645 100644
--- a/trunk/arch/arm/mach-integrator/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-integrator/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#define VMALLOC_END 0xd0000000UL
+#define VMALLOC_END 0xd0000000
diff --git a/trunk/arch/arm/mach-msm/Kconfig b/trunk/arch/arm/mach-msm/Kconfig
index 31e5fd63ec9a..dbbcfeb919db 100644
--- a/trunk/arch/arm/mach-msm/Kconfig
+++ b/trunk/arch/arm/mach-msm/Kconfig
@@ -49,8 +49,6 @@ endchoice
config MSM_SOC_REV_A
bool
-config ARCH_MSM_SCORPIONMP
- bool
config ARCH_MSM_ARM11
bool
diff --git a/trunk/arch/arm/mach-msm/include/mach/vmalloc.h b/trunk/arch/arm/mach-msm/include/mach/vmalloc.h
index d138448eff16..31a32ad062dc 100644
--- a/trunk/arch/arm/mach-msm/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-msm/include/mach/vmalloc.h
@@ -16,7 +16,7 @@
#ifndef __ASM_ARCH_MSM_VMALLOC_H
#define __ASM_ARCH_MSM_VMALLOC_H
-#define VMALLOC_END 0xd0000000UL
+#define VMALLOC_END 0xd0000000
#endif
diff --git a/trunk/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h b/trunk/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h
index 788bdace1304..3eff39921d4d 100644
--- a/trunk/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h
+++ b/trunk/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h
@@ -65,7 +65,7 @@
*/
#define DDR_VIRT_BASE (MV78XX0_REGS_VIRT_BASE | 0x00000)
#define DDR_WINDOW_CPU0_BASE (DDR_VIRT_BASE | 0x1500)
-#define DDR_WINDOW_CPU1_BASE (DDR_VIRT_BASE | 0x1700)
+#define DDR_WINDOW_CPU1_BASE (DDR_VIRT_BASE | 0x1570)
#define DEV_BUS_PHYS_BASE (MV78XX0_REGS_PHYS_BASE | 0x10000)
#define DEV_BUS_VIRT_BASE (MV78XX0_REGS_VIRT_BASE | 0x10000)
diff --git a/trunk/arch/arm/mach-mx25/devices-imx25.h b/trunk/arch/arm/mach-mx25/devices-imx25.h
index d94d282fa676..93afa10b13cf 100644
--- a/trunk/arch/arm/mach-mx25/devices-imx25.h
+++ b/trunk/arch/arm/mach-mx25/devices-imx25.h
@@ -42,9 +42,9 @@ extern const struct imx_mxc_nand_data imx25_mxc_nand_data __initconst;
#define imx25_add_mxc_nand(pdata) \
imx_add_mxc_nand(&imx25_mxc_nand_data, pdata)
-extern const struct imx_spi_imx_data imx25_cspi_data[] __initconst;
+extern const struct imx_spi_imx_data imx25_spi_imx_data[] __initconst;
#define imx25_add_spi_imx(id, pdata) \
- imx_add_spi_imx(&imx25_cspi_data[id], pdata)
+ imx_add_spi_imx(&imx25_spi_imx_data[id], pdata)
#define imx25_add_spi_imx0(pdata) imx25_add_spi_imx(0, pdata)
#define imx25_add_spi_imx1(pdata) imx25_add_spi_imx(1, pdata)
#define imx25_add_spi_imx2(pdata) imx25_add_spi_imx(2, pdata)
diff --git a/trunk/arch/arm/mach-mx3/mach-pcm037_eet.c b/trunk/arch/arm/mach-mx3/mach-pcm037_eet.c
index fda56545d2fd..99e0894e07db 100644
--- a/trunk/arch/arm/mach-mx3/mach-pcm037_eet.c
+++ b/trunk/arch/arm/mach-mx3/mach-pcm037_eet.c
@@ -14,7 +14,6 @@
#include
#include
-#include
#include
@@ -60,12 +59,14 @@ static struct spi_board_info pcm037_spi_dev[] = {
};
/* Platform Data for MXC CSPI */
+#if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE)
static int pcm037_spi1_cs[] = {MXC_SPI_CS(1), IOMUX_TO_GPIO(MX31_PIN_KEY_COL7)};
static const struct spi_imx_master pcm037_spi1_pdata __initconst = {
.chipselect = pcm037_spi1_cs,
.num_chipselect = ARRAY_SIZE(pcm037_spi1_cs),
};
+#endif
/* GPIO-keys input device */
static struct gpio_keys_button pcm037_gpio_keys[] = {
@@ -170,7 +171,7 @@ static struct platform_device pcm037_gpio_keys_device = {
},
};
-static int __init eet_init_devices(void)
+static int eet_init_devices(void)
{
if (!machine_is_pcm037() || pcm037_variant() != PCM037_EET)
return 0;
diff --git a/trunk/arch/arm/mach-netx/include/mach/vmalloc.h b/trunk/arch/arm/mach-netx/include/mach/vmalloc.h
index 871f1ef7bff5..7cca3574308f 100644
--- a/trunk/arch/arm/mach-netx/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-netx/include/mach/vmalloc.h
@@ -16,4 +16,4 @@
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#define VMALLOC_END 0xd0000000UL
+#define VMALLOC_END 0xd0000000
diff --git a/trunk/arch/arm/mach-omap1/include/mach/vmalloc.h b/trunk/arch/arm/mach-omap1/include/mach/vmalloc.h
index 22ec4a479577..b001f67d695b 100644
--- a/trunk/arch/arm/mach-omap1/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-omap1/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#define VMALLOC_END 0xd8000000UL
+#define VMALLOC_END 0xd8000000
diff --git a/trunk/arch/arm/mach-omap2/include/mach/vmalloc.h b/trunk/arch/arm/mach-omap2/include/mach/vmalloc.h
index 866319947760..4da31e997efe 100644
--- a/trunk/arch/arm/mach-omap2/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-omap2/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#define VMALLOC_END 0xf8000000UL
+#define VMALLOC_END 0xf8000000
diff --git a/trunk/arch/arm/mach-omap2/pm24xx.c b/trunk/arch/arm/mach-omap2/pm24xx.c
index c85923e56b85..a40457d81927 100644
--- a/trunk/arch/arm/mach-omap2/pm24xx.c
+++ b/trunk/arch/arm/mach-omap2/pm24xx.c
@@ -30,7 +30,6 @@
#include
#include
#include
-#include
#include
#include
@@ -119,10 +118,6 @@ static void omap2_enter_full_retention(void)
if (omap_irq_pending())
goto no_sleep;
- /* Block console output in case it is on one of the OMAP UARTs */
- if (try_acquire_console_sem())
- goto no_sleep;
-
omap_uart_prepare_idle(0);
omap_uart_prepare_idle(1);
omap_uart_prepare_idle(2);
@@ -136,8 +131,6 @@ static void omap2_enter_full_retention(void)
omap_uart_resume_idle(1);
omap_uart_resume_idle(0);
- release_console_sem();
-
no_sleep:
if (omap2_pm_debug) {
unsigned long long tmp;
diff --git a/trunk/arch/arm/mach-omap2/pm34xx.c b/trunk/arch/arm/mach-omap2/pm34xx.c
index 0ec8a04b7473..75c0cd13ad8e 100644
--- a/trunk/arch/arm/mach-omap2/pm34xx.c
+++ b/trunk/arch/arm/mach-omap2/pm34xx.c
@@ -28,7 +28,6 @@
#include
#include
#include
-#include
#include
#include
@@ -386,12 +385,6 @@ void omap_sram_idle(void)
omap3_enable_io_chain();
}
- /* Block console output in case it is on one of the OMAP UARTs */
- if (per_next_state < PWRDM_POWER_ON ||
- core_next_state < PWRDM_POWER_ON)
- if (try_acquire_console_sem())
- goto console_still_active;
-
/* PER */
if (per_next_state < PWRDM_POWER_ON) {
omap_uart_prepare_idle(2);
@@ -470,9 +463,6 @@ void omap_sram_idle(void)
omap_uart_resume_idle(3);
}
- release_console_sem();
-
-console_still_active:
/* Disable IO-PAD and IO-CHAIN wakeup */
if (omap3_has_io_wakeup() &&
(per_next_state < PWRDM_POWER_ON ||
diff --git a/trunk/arch/arm/mach-omap2/serial.c b/trunk/arch/arm/mach-omap2/serial.c
index d17960a1be25..becf0e38ef7e 100644
--- a/trunk/arch/arm/mach-omap2/serial.c
+++ b/trunk/arch/arm/mach-omap2/serial.c
@@ -27,7 +27,6 @@
#include
#include
#include
-#include
#ifdef CONFIG_SERIAL_OMAP
#include
@@ -407,7 +406,7 @@ void omap_uart_resume_idle(int num)
struct omap_uart_state *uart;
list_for_each_entry(uart, &uart_list, node) {
- if (num == uart->num && uart->can_sleep) {
+ if (num == uart->num) {
omap_uart_enable_clocks(uart);
/* Check for IO pad wakeup */
@@ -808,8 +807,6 @@ void __init omap_serial_init_port(int port)
oh->dev_attr = uart;
- acquire_console_sem(); /* in case the earlycon is on the UART */
-
/*
* Because of early UART probing, UART did not get idled
* on init. Now that omap_device is ready, ensure full idle
@@ -834,8 +831,6 @@ void __init omap_serial_init_port(int port)
omap_uart_block_sleep(uart);
uart->timeout = DEFAULT_TIMEOUT;
- release_console_sem();
-
if ((cpu_is_omap34xx() && uart->padconf) ||
(uart->wk_en && uart->wk_mask)) {
device_init_wakeup(&od->pdev.dev, true);
diff --git a/trunk/arch/arm/mach-pnx4008/include/mach/vmalloc.h b/trunk/arch/arm/mach-pnx4008/include/mach/vmalloc.h
index 184913c71141..31b65ee07b0b 100644
--- a/trunk/arch/arm/mach-pnx4008/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-pnx4008/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
* The vmalloc() routines leaves a hole of 4kB between each vmalloced
* area for the same reason. ;)
*/
-#define VMALLOC_END 0xd0000000UL
+#define VMALLOC_END 0xd0000000
diff --git a/trunk/arch/arm/mach-rpc/include/mach/vmalloc.h b/trunk/arch/arm/mach-rpc/include/mach/vmalloc.h
index fb700228637a..3bcd86fadb81 100644
--- a/trunk/arch/arm/mach-rpc/include/mach/vmalloc.h
+++ b/trunk/arch/arm/mach-rpc/include/mach/vmalloc.h
@@ -7,4 +7,4 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
-#define VMALLOC_END 0xdc000000UL
+#define VMALLOC_END 0xdc000000
diff --git a/trunk/arch/arm/mach-s3c2410/h1940-bluetooth.c b/trunk/arch/arm/mach-s3c2410/h1940-bluetooth.c
index 6b86a722a7db..8aa2f1902a94 100644
--- a/trunk/arch/arm/mach-s3c2410/h1940-bluetooth.c
+++ b/trunk/arch/arm/mach-s3c2410/h1940-bluetooth.c
@@ -77,13 +77,13 @@ static int __devinit h1940bt_probe(struct platform_device *pdev)
/* Configures BT serial port GPIOs */
s3c_gpio_cfgpin(S3C2410_GPH(0), S3C2410_GPH0_nCTS0);
- s3c_gpio_setpull(S3C2410_GPH(0), S3C_GPIO_PULL_NONE);
+ s3c_gpio_cfgpull(S3C2410_GPH(0), S3C_GPIO_PULL_NONE);
s3c_gpio_cfgpin(S3C2410_GPH(1), S3C2410_GPIO_OUTPUT);
- s3c_gpio_setpull(S3C2410_GPH(1), S3C_GPIO_PULL_NONE);
+ s3c_gpio_cfgpull(S3C2410_GPH(1), S3C_GPIO_PULL_NONE);
s3c_gpio_cfgpin(S3C2410_GPH(2), S3C2410_GPH2_TXD0);
- s3c_gpio_setpull(S3C2410_GPH(2), S3C_GPIO_PULL_NONE);
+ s3c_gpio_cfgpull(S3C2410_GPH(2), S3C_GPIO_PULL_NONE);
s3c_gpio_cfgpin(S3C2410_GPH(3), S3C2410_GPH3_RXD0);
- s3c_gpio_setpull(S3C2410_GPH(3), S3C_GPIO_PULL_NONE);
+ s3c_gpio_cfgpull(S3C2410_GPH(3), S3C_GPIO_PULL_NONE);
rfk = rfkill_alloc(DRV_NAME, &pdev->dev, RFKILL_TYPE_BLUETOOTH,
diff --git a/trunk/arch/arm/mach-s3c2416/irq.c b/trunk/arch/arm/mach-s3c2416/irq.c
index 00174daf1526..084d121f368c 100644
--- a/trunk/arch/arm/mach-s3c2416/irq.c
+++ b/trunk/arch/arm/mach-s3c2416/irq.c
@@ -168,11 +168,12 @@ static struct irq_chip s3c2416_irq_dma = {
static void s3c2416_irq_demux_uart3(unsigned int irq, struct irq_desc *desc)
{
- s3c2416_irq_demux(IRQ_S3C2443_RX3, 3);
+ s3c2416_irq_demux(IRQ_S3C2443_UART3, 3);
}
#define INTMSK_UART3 (1UL << (IRQ_S3C2443_UART3 - IRQ_EINT0))
-#define SUBMSK_UART3 (0x7 << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0)))
+#define SUBMSK_UART3 (0xf << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0)))
+
static void s3c2416_irq_uart3_mask(unsigned int irqno)
{
diff --git a/trunk/arch/arm/mach-s3c2443/irq.c b/trunk/arch/arm/mach-s3c2443/irq.c
index 893424767ce1..0e0d693f3974 100644
--- a/trunk/arch/arm/mach-s3c2443/irq.c
+++ b/trunk/arch/arm/mach-s3c2443/irq.c
@@ -166,11 +166,12 @@ static struct irq_chip s3c2443_irq_dma = {
static void s3c2443_irq_demux_uart3(unsigned int irq, struct irq_desc *desc)
{
- s3c2443_irq_demux(IRQ_S3C2443_RX3, 3);
+ s3c2443_irq_demux(IRQ_S3C2443_UART3, 3);
}
#define INTMSK_UART3 (1UL << (IRQ_S3C2443_UART3 - IRQ_EINT0))
-#define SUBMSK_UART3 (0x7 << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0)))
+#define SUBMSK_UART3 (0xf << (IRQ_S3C2443_RX3 - S3C2410_IRQSUB(0)))
+
static void s3c2443_irq_uart3_mask(unsigned int irqno)
{
diff --git a/trunk/arch/arm/mach-s3c64xx/mach-mini6410.c b/trunk/arch/arm/mach-s3c64xx/mach-mini6410.c
index 89f35e02e883..249c62956471 100644
--- a/trunk/arch/arm/mach-s3c64xx/mach-mini6410.c
+++ b/trunk/arch/arm/mach-s3c64xx/mach-mini6410.c
@@ -45,7 +45,7 @@
#include