diff options
76 files changed, 8593 insertions, 111 deletions
@@ -528,6 +528,10 @@ KBUILD_CFLAGS += -g KBUILD_AFLAGS += -gdwarf-2 endif +ifdef CONFIG_FTRACE +KBUILD_CFLAGS += -pg +endif + # We trigger additional mismatches with less inlining ifdef CONFIG_DEBUG_SECTION_MISMATCH KBUILD_CFLAGS += $(call cc-option, -fno-inline-functions-called-once) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3934e2659407..a5e9912e2d37 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -105,11 +105,13 @@ config ARCH_NO_VIRT_TO_BUS config PPC bool default y + select HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE select HAVE_IDE - select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_LMB + select HAVE_OPROFILE config EARLY_PRINTK bool diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 2346d271fbfd..f3f5e2641432 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -12,6 +12,18 @@ CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC endif +ifdef CONFIG_FTRACE +# Do not trace early boot code +CFLAGS_REMOVE_cputable.o = -pg +CFLAGS_REMOVE_prom_init.o = -pg + +ifdef CONFIG_DYNAMIC_FTRACE +# dynamic ftrace setup. +CFLAGS_REMOVE_ftrace.o = -pg +endif + +endif + obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ init_task.o process.o systbl.o idle.o \ @@ -78,6 +90,8 @@ obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o + obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o ifneq ($(CONFIG_PPC_INDIRECT_IO),y) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 0c8614d9875c..0e6221889ca9 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -1035,3 +1035,133 @@ machine_check_in_rtas: /* XXX load up BATs and panic */ #endif /* CONFIG_PPC_RTAS */ + +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +_GLOBAL(mcount) +_GLOBAL(_mcount) + stwu r1,-48(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + mflr r3 + stw r7, 28(r1) + mfcr r5 + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + stw r3, 44(r1) + stw r5, 8(r1) + .globl mcount_call +mcount_call: + bl ftrace_stub + nop + lwz r6, 8(r1) + lwz r0, 44(r1) + lwz r3, 12(r1) + mtctr r0 + lwz r4, 16(r1) + mtcr r6 + lwz r5, 20(r1) + lwz r6, 24(r1) + lwz r0, 52(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + mtlr r0 + lwz r9, 36(r1) + lwz r10,40(r1) + addi r1, r1, 48 + bctr + +_GLOBAL(ftrace_caller) + /* Based off of objdump optput from glibc */ + stwu r1,-48(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + mflr r3 + lwz r4, 52(r1) + mfcr r5 + stw r7, 28(r1) + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + stw r3, 44(r1) + stw r5, 8(r1) +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop + lwz r6, 8(r1) + lwz r0, 44(r1) + lwz r3, 12(r1) + mtctr r0 + lwz r4, 16(r1) + mtcr r6 + lwz r5, 20(r1) + lwz r6, 24(r1) + lwz r0, 52(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + mtlr r0 + lwz r9, 36(r1) + lwz r10,40(r1) + addi r1, r1, 48 + bctr +#else +_GLOBAL(mcount) +_GLOBAL(_mcount) + stwu r1,-48(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + mflr r3 + lwz r4, 52(r1) + mfcr r5 + stw r7, 28(r1) + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + stw r3, 44(r1) + stw r5, 8(r1) + + LOAD_REG_ADDR(r5, ftrace_trace_function) +#if 0 + mtctr r3 + mr r1, r5 + bctrl +#endif + lwz r5,0(r5) +#if 1 + mtctr r5 + bctrl +#else + bl ftrace_stub +#endif + nop + + lwz r6, 8(r1) + lwz r0, 44(r1) + lwz r3, 12(r1) + mtctr r0 + lwz r4, 16(r1) + mtcr r6 + lwz r5, 20(r1) + lwz r6, 24(r1) + lwz r0, 52(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + mtlr r0 + lwz r9, 36(r1) + lwz r10,40(r1) + addi r1, r1, 48 + bctr +#endif + +_GLOBAL(ftrace_stub) + blr + +#endif /* CONFIG_MCOUNT */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index c0db5b769e55..2c4d9e056ead 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -870,3 +870,65 @@ _GLOBAL(enter_prom) ld r0,16(r1) mtlr r0 blr + +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +_GLOBAL(mcount) +_GLOBAL(_mcount) + /* Taken from output of objdump from lib64/glibc */ + mflr r3 + stdu r1, -112(r1) + std r3, 128(r1) + .globl mcount_call +mcount_call: + bl ftrace_stub + nop + ld r0, 128(r1) + mtlr r0 + addi r1, r1, 112 + blr + +_GLOBAL(ftrace_caller) + /* Taken from output of objdump from lib64/glibc */ + mflr r3 + ld r11, 0(r1) + stdu r1, -112(r1) + std r3, 128(r1) + ld r4, 16(r11) +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop + ld r0, 128(r1) + mtlr r0 + addi r1, r1, 112 +_GLOBAL(ftrace_stub) + blr +#else +_GLOBAL(mcount) + blr + +_GLOBAL(_mcount) + /* Taken from output of objdump from lib64/glibc */ + mflr r3 + ld r11, 0(r1) + stdu r1, -112(r1) + std r3, 128(r1) + ld r4, 16(r11) + + + LOAD_REG_ADDR(r5,ftrace_trace_function) + ld r5,0(r5) + ld r5,0(r5) + mtctr r5 + bctrl + + nop + ld r0, 128(r1) + mtlr r0 + addi r1, r1, 112 +_GLOBAL(ftrace_stub) + blr + +#endif +#endif diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c new file mode 100644 index 000000000000..5a4993fefa45 --- /dev/null +++ b/arch/powerpc/kernel/ftrace.c @@ -0,0 +1,165 @@ +/* + * Code for replacing ftrace calls with jumps. + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * + * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box. + * + */ + +#include <linux/spinlock.h> +#include <linux/hardirq.h> +#include <linux/ftrace.h> +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/list.h> + +#include <asm/cacheflush.h> + +#define CALL_BACK 4 + +static unsigned int ftrace_nop = 0x60000000; + +#ifdef CONFIG_PPC32 +# define GET_ADDR(addr) addr +#else +/* PowerPC64's functions are data that points to the functions */ +# define GET_ADDR(addr) *(unsigned long *)addr +#endif + +notrace int ftrace_ip_converted(unsigned long ip) +{ + unsigned int save; + + ip -= CALL_BACK; + save = *(unsigned int *)ip; + + return save == ftrace_nop; +} + +static unsigned int notrace ftrace_calc_offset(long ip, long addr) +{ + return (int)((addr + CALL_BACK) - ip); +} + +notrace unsigned char *ftrace_nop_replace(void) +{ + return (char *)&ftrace_nop; +} + +notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + static unsigned int op; + + addr = GET_ADDR(addr); + + /* Set to "bl addr" */ + op = 0x48000001 | (ftrace_calc_offset(ip, addr) & 0x03fffffe); + + /* + * No locking needed, this must be called via kstop_machine + * which in essence is like running on a uniprocessor machine. + */ + return (unsigned char *)&op; +} + +#ifdef CONFIG_PPC64 +# define _ASM_ALIGN " .align 3 " +# define _ASM_PTR " .llong " +#else +# define _ASM_ALIGN " .align 2 " +# define _ASM_PTR " .long " +#endif + +notrace int +ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code) +{ + unsigned replaced; + unsigned old = *(unsigned *)old_code; + unsigned new = *(unsigned *)new_code; + int faulted = 0; + + /* move the IP back to the start of the call */ + ip -= CALL_BACK; + + /* + * Note: Due to modules and __init, code can + * disappear and change, we need to protect against faulting + * as well as code changing. + * + * No real locking needed, this code is run through + * kstop_machine. + */ + asm volatile ( + "1: lwz %1, 0(%2)\n" + " cmpw %1, %5\n" + " bne 2f\n" + " stwu %3, 0(%2)\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: li %0, 1\n" + " b 2b\n" + ".previous\n" + ".section __ex_table,\"a\"\n" + _ASM_ALIGN "\n" + _ASM_PTR "1b, 3b\n" + ".previous" + : "=r"(faulted), "=r"(replaced) + : "r"(ip), "r"(new), + "0"(faulted), "r"(old) + : "memory"); + + if (replaced != old && replaced != new) + faulted = 2; + + if (!faulted) + flush_icache_range(ip, ip + 8); + + return faulted; +} + +notrace int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char old[4], *new; + int ret; + + ip += CALL_BACK; + + memcpy(old, &ftrace_call, 4); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + + return ret; +} + +notrace int ftrace_mcount_set(unsigned long *data) +{ + unsigned long ip = (long)(&mcount_call); + unsigned long *addr = data; + unsigned char old[4], *new; + + /* ip is at the location, but modify code will subtact this */ + ip += CALL_BACK; + + /* + * Replace the mcount stub with a pointer to the + * ip recorder function. + */ + memcpy(old, &mcount_call, 4); + new = ftrace_call_replace(ip, *addr); + *addr = ftrace_modify_code(ip, old, new); + + return 0; +} + +int __init ftrace_dyn_arch_init(void *data) +{ + /* This is running in kstop_machine */ + + ftrace_mcount_set(data); + + return 0; +} + diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c index e31aca9208eb..1882bf419fa6 100644 --- a/arch/powerpc/kernel/io.c +++ b/arch/powerpc/kernel/io.c @@ -120,7 +120,8 @@ EXPORT_SYMBOL(_outsl_ns); #define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0) -void _memset_io(volatile void __iomem *addr, int c, unsigned long n) +notrace void +_memset_io(volatile void __iomem *addr, int c, unsigned long n) { void *p = (void __force *)addr; u32 lc = c; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index bcc249d90c4d..dcc946e67099 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -98,7 +98,7 @@ EXPORT_SYMBOL(irq_desc); int distribute_irqs = 1; -static inline unsigned long get_hard_enabled(void) +static inline notrace unsigned long get_hard_enabled(void) { unsigned long enabled; @@ -108,13 +108,13 @@ static inline unsigned long get_hard_enabled(void) return enabled; } -static inline void set_soft_enabled(unsigned long enable) +static inline notrace void set_soft_enabled(unsigned long enable) { __asm__ __volatile__("stb %0,%1(13)" : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled))); } -void raw_local_irq_restore(unsigned long en) +notrace void raw_local_irq_restore(unsigned long en) { /* * get_paca()->soft_enabled = en; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 5112a4aa801d..22f8e2bacd32 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -47,6 +47,11 @@ #include <asm/kgdb.h> #endif +#ifdef CONFIG_FTRACE +extern void _mcount(void); +EXPORT_SYMBOL(_mcount); +#endif + extern void bootx_init(unsigned long r4, unsigned long phys); int boot_cpuid; @@ -81,7 +86,7 @@ int ucache_bsize; * from the address that it was linked at, so we must use RELOC/PTRRELOC * to access static data (including strings). -- paulus */ -unsigned long __init early_init(unsigned long dt_ptr) +notrace unsigned long __init early_init(unsigned long dt_ptr) { unsigned long offset = reloc_offset(); struct cpu_spec *spec; @@ -111,7 +116,7 @@ unsigned long __init early_init(unsigned long dt_ptr) * This is called very early on the boot process, after a minimal * MMU environment has been set up but before MMU_init is called. */ -void __init machine_init(unsigned long dt_ptr, unsigned long phys) +notrace void __init machine_init(unsigned long dt_ptr, unsigned long phys) { /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); @@ -133,7 +138,7 @@ void __init machine_init(unsigned long dt_ptr, unsigned long phys) #ifdef CONFIG_BOOKE_WDT /* Checks wdt=x and wdt_period=xx command-line option */ -int __init early_parse_wdt(char *p) +notrace int __init early_parse_wdt(char *p) { if (p && strncmp(p, "0", 1) != 0) booke_wdt_enabled = 1; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 098fd96a394a..277bf18cbbcc 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -85,6 +85,11 @@ struct ppc64_caches ppc64_caches = { }; EXPORT_SYMBOL_GPL(ppc64_caches); +#ifdef CONFIG_FTRACE +extern void _mcount(void); +EXPORT_SYMBOL(_mcount); +#endif + /* * These are used in binfmt_elf.c to put aux entries on the stack * for each elf executable being started. diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index 4d72c8f72159..89774177b209 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -1,5 +1,10 @@ CFLAGS_bootx_init.o += -fPIC +ifdef CONFIG_FTRACE +# Do not trace early boot code +CFLAGS_REMOVE_bootx_init.o = -pg +endif + obj-y += pic.o setup.o time.o feature.o pci.o \ sleep.o low_i2c.o cache.o pfunc_core.o \ pfunc_base.o diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig index eb36f3b746b8..fca9246470b1 100644 --- a/arch/sparc64/Kconfig +++ b/arch/sparc64/Kconfig @@ -11,6 +11,8 @@ config SPARC config SPARC64 bool default y + select HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE select HAVE_IDE select HAVE_LMB select HAVE_ARCH_KGDB diff --git a/arch/sparc64/Kconfig.debug b/arch/sparc64/Kconfig.debug index 6a4d28a4076d..d6d32d178fc8 100644 --- a/arch/sparc64/Kconfig.debug +++ b/arch/sparc64/Kconfig.debug @@ -33,7 +33,7 @@ config DEBUG_PAGEALLOC config MCOUNT bool - depends on STACK_DEBUG + depends on STACK_DEBUG || FTRACE default y config FRAME_POINTER diff --git a/arch/sparc64/kernel/Makefile b/arch/sparc64/kernel/Makefile index ec4f5ebb1ca6..418b5782096e 100644 --- a/arch/sparc64/kernel/Makefile +++ b/arch/sparc64/kernel/Makefile @@ -14,6 +14,7 @@ obj-y := process.o setup.o cpu.o idprom.o \ power.o sbus.o sparc64_ksyms.o chmc.o \ visemul.o prom.o of_device.o hvapi.o sstate.o mdesc.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_PCI) += ebus.o pci_common.o \ pci_psycho.o pci_sabre.o pci_schizo.o \ diff --git a/arch/sparc64/kernel/ftrace.c b/arch/sparc64/kernel/ftrace.c new file mode 100644 index 000000000000..f449e6df6c4a --- /dev/null +++ b/arch/sparc64/kernel/ftrace.c @@ -0,0 +1,99 @@ +#include <linux/spinlock.h> +#include <linux/hardirq.h> +#include <linux/ftrace.h> +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/list.h> + +static const u32 ftrace_nop = 0x01000000; + +notrace int ftrace_ip_converted(unsigned long ip) +{ + u32 insn = *(u32 *) ip; + + return (insn == ftrace_nop); +} + +notrace unsigned char *ftrace_nop_replace(void) +{ + return (char *)&ftrace_nop; +} + +notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + static u32 call; + s32 off; + + off = ((s32)addr - (s32)ip); + call = 0x40000000 | ((u32)off >> 2); + + return (unsigned char *) &call; +} + +notrace int +ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code) +{ + u32 old = *(u32 *)old_code; + u32 new = *(u32 *)new_code; + u32 replaced; + int faulted; + + __asm__ __volatile__( + "1: cas [%[ip]], %[old], %[new]\n" + " flush %[ip]\n" + " mov 0, %[faulted]\n" + "2:\n" + " .section .fixup,#alloc,#execinstr\n" + " .align 4\n" + "3: sethi %%hi(2b), %[faulted]\n" + " jmpl %[faulted] + %%lo(2b), %%g0\n" + " mov 1, %[faulted]\n" + " .previous\n" + " .section __ex_table,\"a\"\n" + " .align 4\n" + " .word 1b, 3b\n" + " .previous\n" + : "=r" (replaced), [faulted] "=r" (faulted) + : [new] "0" (new), [old] "r" (old), [ip] "r" (ip) + : "memory"); + + if (replaced != old && replaced != new) + faulted = 2; + + return faulted; +} + +notrace int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char old[4], *new; + + memcpy(old, &ftrace_call, 4); + new = ftrace_call_replace(ip, (unsigned long)func); + return ftrace_modify_code(ip, old, new); +} + +notrace int ftrace_mcount_set(unsigned long *data) +{ + unsigned long ip = (long)(&mcount_call); + unsigned long *addr = data; + unsigned char old[4], *new; + + /* + * Replace the mcount stub with a pointer to the + * ip recorder function. + */ + memcpy(old, &mcount_call, 4); + new = ftrace_call_replace(ip, *addr); + *addr = ftrace_modify_code(ip, old, new); + + return 0; +} + + +int __init ftrace_dyn_arch_init(void *data) +{ + ftrace_mcount_set(data); + return 0; +} diff --git a/arch/sparc64/lib/mcount.S b/arch/sparc64/lib/mcount.S index 9e4534b485c7..7735a7a60533 100644 --- a/arch/sparc64/lib/mcount.S +++ b/arch/sparc64/lib/mcount.S @@ -28,10 +28,13 @@ ovstack: .skip OVSTACKSIZE #endif .text - .align 32 - .globl mcount, _mcount -mcount: + .align 32 + .globl _mcount + .type _mcount,#function + .globl mcount + .type mcount,#function _mcount: +mcount: #ifdef CONFIG_STACK_DEBUG /* * Check whether %sp is dangerously low. @@ -55,6 +58,53 @@ _mcount: or %g3, %lo(panicstring), %o0 call prom_halt nop +1: +#endif +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE + mov %o7, %o0 + .globl mcount_call +mcount_call: + call ftrace_stub + mov %o0, %o7 +#else + sethi %hi(ftrace_trace_function), %g1 + sethi %hi(ftrace_stub), %g2 + ldx [%g1 + %lo(ftrace_trace_function)], %g1 + or %g2, %lo(ftrace_stub), %g2 + cmp %g1, %g2 + be,pn %icc, 1f + mov %i7, %o1 + jmpl %g1, %g0 + mov %o7, %o0 + /* not reached */ +1: #endif -1: retl +#endif + retl nop + .size _mcount,.-_mcount + .size mcount,.-mcount + +#ifdef CONFIG_FTRACE + .globl ftrace_stub + .type ftrace_stub,#function +ftrace_stub: + retl + nop + .size ftrace_stub,.-ftrace_stub +#ifdef CONFIG_DYNAMIC_FTRACE + .globl ftrace_caller + .type ftrace_caller,#function +ftrace_caller: + mov %i7, %o1 + mov %o7, %o0 + .globl ftrace_call +ftrace_call: + call ftrace_stub + mov %o0, %o7 + retl + nop + .size ftrace_caller,.-ftrace_caller +#endif +#endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e0edaaa6920a..400135148555 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,6 +23,8 @@ config X86 select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 18363374d51a..f395fd537c5c 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -172,6 +172,14 @@ config IOMMU_LEAK Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. +config PAGE_FAULT_HANDLERS + bool "Custom page fault handlers" + depends on DEBUG_KERNEL + help + Allow the use of custom page fault handlers. A kernel module may + register a function that is called on every page fault. Custom + handlers are used by some debugging and reverse engineering tools. + # # IO delay types: # diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 77807d4769c9..5ff67208d4ae 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -6,6 +6,13 @@ extra-y := head_$(BITS).o head$(BITS).o init_task.o vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) +ifdef CONFIG_FTRACE +# Do not profile debug utilities +CFLAGS_REMOVE_tsc_64.o = -pg +CFLAGS_REMOVE_tsc_32.o = -pg +CFLAGS_REMOVE_rtc.o = -pg +endif + # # vsyscalls (which work on the user stack) should have # no stack-protector checks: @@ -56,6 +63,7 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-$(CONFIG_X86_LOCAL_APIC) += apic_$(BITS).o nmi_$(BITS).o obj-$(CONFIG_X86_IO_APIC) += io_apic_$(BITS).o obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 65c7857a90dd..2763cb37b553 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1,6 +1,6 @@ #include <linux/module.h> #include <linux/sched.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/list.h> #include <linux/kprobes.h> #include <linux/mm.h> @@ -143,7 +143,7 @@ static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = { #ifdef CONFIG_X86_64 extern char __vsyscall_0; -static inline const unsigned char*const * find_nop_table(void) +const unsigned char *const *find_nop_table(void) { return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || boot_cpu_data.x86 < 6 ? k8_nops : p6_nops; @@ -162,7 +162,7 @@ static const struct nop { { -1, NULL } }; -static const unsigned char*const * find_nop_table(void) +const unsigned char *const *find_nop_table(void) { const unsigned char *const *noptable = intel_nops; int i; @@ -279,7 +279,7 @@ struct smp_alt_module { struct list_head next; }; static LIST_HEAD(smp_alt_modules); -static DEFINE_SPINLOCK(smp_alt); +static DEFINE_MUTEX(smp_alt); static int smp_mode = 1; /* protected by smp_alt */ void alternatives_smp_module_add(struct module *mod, char *name, @@ -312,12 +312,12 @@ void alternatives_smp_module_add(struct module *mod, char *name, __func__, smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); - spin_lock(&smp_alt); + mutex_lock(&smp_alt); list_add_tail(&smp->next, &smp_alt_modules); if (boot_cpu_has(X86_FEATURE_UP)) alternatives_smp_unlock(smp->locks, smp->locks_end, smp->text, smp->text_end); - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); } void alternatives_smp_module_del(struct module *mod) @@ -327,17 +327,17 @@ void alternatives_smp_module_del(struct module *mod) if (smp_alt_once || noreplace_smp) return; - spin_lock(&smp_alt); + mutex_lock(&smp_alt); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; list_del(&item->next); - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); DPRINTK("%s: %s\n", __func__, item->name); kfree(item); return; } - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); } void alternatives_smp_switch(int smp) @@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp) return; BUG_ON(!smp && (num_online_cpus() > 1)); - spin_lock(&smp_alt); + mutex_lock(&smp_alt); /* * Avoid unnecessary switches because it forces JIT based VMs to @@ -383,7 +383,7 @@ void alternatives_smp_switch(int smp) mod->text, mod->text_end); } smp_mode = smp; - spin_unlock(&smp_alt); + mutex_unlock(&smp_alt); } #endif diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index c778e4fa55a2..04ea83ccb979 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1110,6 +1110,74 @@ ENDPROC(xen_failsafe_callback) #endif /* CONFIG_XEN */ +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE + +ENTRY(mcount) + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + +.globl mcount_call +mcount_call: + call ftrace_stub + + popl %edx + popl %ecx + popl %eax + + ret +END(mcount) + +ENTRY(ftrace_caller) + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + popl %edx + popl %ecx + popl %eax + +.globl ftrace_stub +ftrace_stub: + ret +END(ftrace_caller) + +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(mcount) + cmpl $ftrace_stub, ftrace_trace_function + jnz trace +.globl ftrace_stub +ftrace_stub: + ret + + /* taken from glibc */ +trace: + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + + call *ftrace_trace_function + + popl %edx + popl %ecx + popl %eax + + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FTRACE */ + .section .rodata,"a" #include "syscall_table_32.S" diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 556a8df522a7..fe25e5febca3 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -54,6 +54,108 @@ .code64 +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(mcount) + + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + +.globl mcount_call +mcount_call: + call ftrace_stub + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + + retq +END(mcount) + +ENTRY(ftrace_caller) + + /* taken from glibc */ + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + movq 8(%rbp), %rsi + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + +.globl ftrace_stub +ftrace_stub: + retq +END(ftrace_caller) + +#else /* ! CONFIG_DYNAMIC_FTRACE */ +ENTRY(mcount) + cmpq $ftrace_stub, ftrace_trace_function + jnz trace +.globl ftrace_stub +ftrace_stub: + retq + +trace: + /* taken from glibc */ + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + movq 8(%rbp), %rsi + + call *ftrace_trace_function + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FTRACE */ + #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c new file mode 100644 index 000000000000..498608c015fb --- /dev/null +++ b/arch/x86/kernel/ftrace.c @@ -0,0 +1,159 @@ +/* + * Code for replacing ftrace calls with jumps. + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * + * Thanks goes to Ingo Molnar, for suggesting the idea. + * Mathieu Desnoyers, for suggesting postponing the modifications. + * Arjan van de Ven, for keeping me straight, and explaining to me + * the dangers of modifying code on the run. + */ + +#include <linux/spinlock.h> +#include <linux/hardirq.h> +#include <linux/ftrace.h> +#include <linux/percpu.h> +#include <linux/init.h> +#include <linux/list.h> + +#include <asm/alternative.h> + +#define CALL_BACK 5 + +/* Long is fine, even if it is only 4 bytes ;-) */ +static long *ftrace_nop; + +union ftrace_code_union { + char code[5]; + struct { + char e8; + int offset; + } __attribute__((packed)); +}; + +notrace int ftrace_ip_converted(unsigned long ip) +{ + unsigned long save; + + ip -= CALL_BACK; + save = *(long *)ip; + + return save == *ftrace_nop; +} + +static int notrace ftrace_calc_offset(long ip, long addr) +{ + return (int)(addr - ip); +} + +notrace unsigned char *ftrace_nop_replace(void) +{ + return (char *)ftrace_nop; +} + +notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + static union ftrace_code_union calc; + + calc.e8 = 0xe8; + calc.offset = ftrace_calc_offset(ip, addr); + + /* + * No locking needed, this must be called via kstop_machine + * which in essence is like running on a uniprocessor machine. + */ + return calc.code; +} + +notrace int +ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code) +{ + unsigned replaced; + unsigned old = *(unsigned *)old_code; /* 4 bytes */ + unsigned new = *(unsigned *)new_code; /* 4 bytes */ + unsigned char newch = new_code[4]; + int faulted = 0; + + /* move the IP back to the start of the call */ + ip -= CALL_BACK; + + /* + * Note: Due to modules and __init, code can + * disappear and change, we need to protect against faulting + * as well as code changing. + * + * No real locking needed, this code is run through + * kstop_machine. + */ + asm volatile ( + "1: lock\n" + " cmpxchg %3, (%2)\n" + " jnz 2f\n" + " movb %b4, 4(%2)\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: movl $1, %0\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : "=r"(faulted), "=a"(replaced) + : "r"(ip), "r"(new), "r"(newch), + "0"(faulted), "a"(old) + : "memory"); + sync_core(); + + if (replaced != old && replaced != new) + faulted = 2; + + return faulted; +} + +notrace int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char old[5], *new; + int ret; + + ip += CALL_BACK; + + memcpy(old, &ftrace_call, 5); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + + return ret; +} + +notrace int ftrace_mcount_set(unsigned long *data) +{ + unsigned long ip = (long)(&mcount_call); + unsigned long *addr = data; + unsigned char old[5], *new; + + /* ip is at the location, but modify code will subtact this */ + ip += CALL_BACK; + + /* + * Replace the mcount stub with a pointer to the + * ip recorder function. + */ + memcpy(old, &mcount_call, 5); + new = ftrace_call_replace(ip, *addr); + *addr = ftrace_modify_code(ip, old, new); + + return 0; +} + +int __init ftrace_dyn_arch_init(void *data) +{ + const unsigned char *const *noptable = find_nop_table(); + + /* This is running in kstop_machine */ + + ftrace_mcount_set(data); + + ftrace_nop = (unsigned long *)noptable[CALL_BACK]; + + return 0; +} + diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index deb43785e923..29999dbb754c 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -1,7 +1,14 @@ +#include <linux/ftrace.h> #include <linux/module.h> + #include <asm/checksum.h> -#include <asm/desc.h> #include <asm/pgtable.h> +#include <asm/desc.h> + +#ifdef CONFIG_FTRACE +/* mcount is defined in assembly */ +EXPORT_SYMBOL(mcount); +#endif /* Networking helper routines. */ EXPORT_SYMBOL(csum_partial_copy_generic); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index d0b234c9fc31..88923fd7a6fc 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -11,6 +11,8 @@ #include <linux/delay.h> #include <linux/init.h> #include <linux/numa.h> +#include <linux/ftrace.h> + #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> @@ -107,6 +109,8 @@ NORET_TYPE void machine_kexec(struct kimage *image) unsigned long page_list[PAGES_NR]; void *control_page; + tracer_disable(); + /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 576a03db4511..1558fdc174f9 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -11,6 +11,8 @@ #include <linux/string.h> #include <linux/reboot.h> #include <linux/numa.h> +#include <linux/ftrace.h> + #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -184,6 +186,8 @@ NORET_TYPE void machine_kexec(struct kimage *image) unsigned long page_list[PAGES_NR]; void *control_page; + tracer_disable(); + /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index e2db9ac5c61c..347a7aba8b16 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -185,7 +185,10 @@ void cpu_idle(void) local_irq_disable(); __get_cpu_var(irq_stat).idle_timestamp = jiffies; + /* Don't trace irqs off for idle */ + stop_critical_timings(); idle(); + start_critical_timings(); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c6eb5c91e5f6..ea090e6cfe39 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -165,7 +165,10 @@ void cpu_idle(void) */ local_irq_disable(); enter_idle(); + /* Don't trace irqs off for idle */ + stop_critical_timings(); idle(); + start_critical_timings(); /* In many cases the interrupt that ended idle has already called exit_idle. But some idle loops can be woken up without interrupt. */ diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 61efa2f7d564..4063dfa2a02d 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -42,7 +42,8 @@ #include <asm/topology.h> #include <asm/vgtod.h> -#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) +#define __vsyscall(nr) \ + __attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace #define __syscall_clobber "r11","cx","memory" /* diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index f6c05d0410fb..122885bc5f3b 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -1,15 +1,22 @@ /* Exports for assembly files. All C exports should go in the respective C files. */ +#include <linux/ftrace.h> #include <linux/module.h> -#include <net/checksum.h> #include <linux/smp.h> +#include <net/checksum.h> + #include <asm/processor.h> -#include <asm/uaccess.h> #include <asm/pgtable.h> +#include <asm/uaccess.h> #include <asm/desc.h> +#ifdef CONFIG_FTRACE +/* mcount is defined in assembly */ +EXPORT_SYMBOL(mcount); +#endif + EXPORT_SYMBOL(kernel_thread); EXPORT_SYMBOL(__get_user_1); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 76f60f52a885..84aa2883fe15 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_SMP) := msr-on-cpu.o lib-y := delay_$(BITS).o +lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o lib-y += memcpy_$(BITS).o diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S new file mode 100644 index 000000000000..650b11e00ecc --- /dev/null +++ b/arch/x86/lib/thunk_32.S @@ -0,0 +1,47 @@ +/* + * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash) + * Copyright 2008 by Steven Rostedt, Red Hat, Inc + * (inspired by Andi Kleen's thunk_64.S) + * Subject to the GNU public license, v.2. No warranty of any kind. + */ + + #include <linux/linkage.h> + +#define ARCH_TRACE_IRQS_ON \ + pushl %eax; \ + pushl %ecx; \ + pushl %edx; \ + call trace_hardirqs_on; \ + popl %edx; \ + popl %ecx; \ + popl %eax; + +#define ARCH_TRACE_IRQS_OFF \ + pushl %eax; \ + pushl %ecx; \ + pushl %edx; \ + call trace_hardirqs_off; \ + popl %edx; \ + popl %ecx; \ + popl %eax; + +#ifdef CONFIG_TRACE_IRQFLAGS + /* put return address in eax (arg1) */ + .macro thunk_ra name,func + .globl \name +\name: + pushl %eax + pushl %ecx + pushl %edx + /* Place EIP in the arg1 */ + movl 3*4(%esp), %eax + call \func + popl %edx + popl %ecx + popl %eax + ret + .endm + + thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller + thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller +#endif diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index e009251d4e9f..bf9a7d5a5428 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -2,6 +2,7 @@ * Save registers before calling assembly functions. This avoids * disturbance of register allocation in some inline assembly constructs. * Copyright 2001,2002 by Andi Kleen, SuSE Labs. + * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc. * Subject to the GNU public license, v.2. No warranty of any kind. */ @@ -42,8 +43,22 @@ #endif #ifdef CONFIG_TRACE_IRQFLAGS - thunk trace_hardirqs_on_thunk,trace_hardirqs_on - thunk trace_hardirqs_off_thunk,trace_hardirqs_off + /* put return address in rdi (arg1) */ + .macro thunk_ra name,func + .globl \name +\name: + CFI_STARTPROC + SAVE_ARGS + /* SAVE_ARGS pushs 9 elements */ + /* the next element would be the rip */ + movq 9*8(%rsp), %rdi + call \func + jmp restore + CFI_ENDPROC + .endm + + thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller + thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8bcb6f40ccb6..42394b353c6a 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -49,6 +49,60 @@ #define PF_RSVD (1<<3) #define PF_INSTR (1<<4) +#ifdef CONFIG_PAGE_FAULT_HANDLERS +static HLIST_HEAD(pf_handlers); /* protected by RCU */ +static DEFINE_SPINLOCK(pf_handlers_writer); + +void register_page_fault_handler(struct pf_handler *new_pfh) +{ + unsigned long flags; + spin_lock_irqsave(&pf_handlers_writer, flags); + hlist_add_head_rcu(&new_pfh->hlist, &pf_handlers); + spin_unlock_irqrestore(&pf_handlers_writer, flags); +} +EXPORT_SYMBOL_GPL(register_page_fault_handler); + +/** + * unregister_page_fault_handler: + * The caller must ensure @old_pfh is not in use anymore before freeing it. + * This function does not guarantee it. The list of handlers is protected by + * RCU, so you can do this by e.g. calling synchronize_rcu(). + */ +void unregister_page_fault_handler(struct pf_handler *old_pfh) +{ + unsigned long flags; + spin_lock_irqsave(&pf_handlers_writer, flags); + hlist_del_rcu(&old_pfh->hlist); + spin_unlock_irqrestore(&pf_handlers_writer, flags); +} +EXPORT_SYMBOL_GPL(unregister_page_fault_handler); +#endif + +/* returns non-zero if do_page_fault() should return */ +static int handle_custom_pf(struct pt_regs *regs, unsigned long error_code, + unsigned long address) +{ +#ifdef CONFIG_PAGE_FAULT_HANDLERS + int ret = 0; + struct pf_handler *cur; + struct hlist_node *ncur; + + if (hlist_empty(&pf_handlers)) + return 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(cur, ncur, &pf_handlers, hlist) { + ret = cur->handler(regs, error_code, address); + if (ret) + break; + } + rcu_read_unlock(); + return ret; +#else + return 0; +#endif +} + static inline int notify_page_fault(struct pt_regs *regs) { #ifdef CONFIG_KPROBES @@ -606,6 +660,8 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) if (notify_page_fault(regs)) return; + if (handle_custom_pf(regs, error_code, address)) + return; /* * We fault-in kernel-space virtual memory on-demand. The diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ec30d10154b6..f96eca21ad8f 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -710,6 +710,8 @@ void mark_rodata_ro(void) unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; +#ifndef CONFIG_DYNAMIC_FTRACE + /* Dynamic tracing modifies the kernel text section */ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); @@ -722,6 +724,8 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif +#endif /* CONFIG_DYNAMIC_FTRACE */ + start += size; size = (unsigned long)__end_rodata - start; set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 156e6d7b0e32..a5fd2e06f5c9 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -766,6 +766,13 @@ EXPORT_SYMBOL_GPL(rodata_test_data); void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata); + unsigned long rodata_start = + ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; + +#ifdef CONFIG_DYNAMIC_FTRACE + /* Dynamic tracing modifies the kernel text section */ + start = rodata_start; +#endif printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -775,8 +782,7 @@ void mark_rodata_ro(void) * The rodata section (but not the kernel text!) should also be * not-executable. */ - start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; - set_memory_nx(start, (end - start) >> PAGE_SHIFT); + set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT); rodata_test(); diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index efa2ba7c6005..1ef0f90813d6 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -23,7 +23,7 @@ #define gtod vdso_vsyscall_gtod_data -static long vdso_fallback_gettime(long clock, struct timespec *ts) +notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; asm("syscall" : "=a" (ret) : @@ -31,7 +31,7 @@ static long vdso_fallback_gettime(long clock, struct timespec *ts) return ret; } -static inline long vgetns(void) +notrace static inline long vgetns(void) { long v; cycles_t (*vread)(void); @@ -40,7 +40,7 @@ static inline long vgetns(void) return (v * gtod->clock.mult) >> gtod->clock.shift; } -static noinline int do_realtime(struct timespec *ts) +notrace static noinline int do_realtime(struct timespec *ts) { unsigned long seq, ns; do { @@ -54,7 +54,8 @@ static noinline int do_realtime(struct timespec *ts) } /* Copy of the version in kernel/time.c which we cannot directly access */ -static void vset_normalized_timespec(struct timespec *ts, long sec, long nsec) +notrace static void +vset_normalized_timespec(struct timespec *ts, long sec, long nsec) { while (nsec >= NSEC_PER_SEC) { nsec -= NSEC_PER_SEC; @@ -68,7 +69,7 @@ static void vset_normalized_timespec(struct timespec *ts, long sec, long nsec) ts->tv_nsec = nsec; } -static noinline int do_monotonic(struct timespec *ts) +notrace static noinline int do_monotonic(struct timespec *ts) { unsigned long seq, ns, secs; do { @@ -82,7 +83,7 @@ static noinline int do_monotonic(struct timespec *ts) return 0; } -int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) +notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) { if (likely(gtod->sysctl_enabled && gtod->clock.vread)) switch (clock) { @@ -96,7 +97,7 @@ int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) int clock_gettime(clockid_t, struct timespec *) __attribute__((weak, alias("__vdso_clock_gettime"))); -int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) +notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) { long ret; if (likely(gtod->sysctl_enabled && gtod->clock.vread)) { diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c index c8097f17f8a9..9fbc6b20026b 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/vdso/vgetcpu.c @@ -13,7 +13,8 @@ #include <asm/vgtod.h> #include "vextern.h" -long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) +notrace long +__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) { unsigned int p; diff --git a/include/asm-powerpc/hw_irq.h b/include/asm-powerpc/hw_irq.h index ad8c9f7fd0e3..f75a5fc64d2e 100644 --- a/include/asm-powerpc/hw_irq.h +++ b/include/asm-powerpc/hw_irq.h @@ -59,6 +59,11 @@ extern void iseries_handle_interrupts(void); get_paca()->hard_enabled = 0; \ } while(0) +static inline int irqs_disabled_flags(unsigned long flags) +{ + return flags == 0; +} + #else #if defined(CONFIG_BOOKE) @@ -113,6 +118,11 @@ static inline void local_irq_save_ptr(unsigned long *flags) #define hard_irq_enable() local_irq_enable() #define hard_irq_disable() local_irq_disable() +static inline int irqs_disabled_flags(unsigned long flags) +{ + return (flags & MSR_EE) == 0; +} + #endif /* CONFIG_PPC64 */ /* diff --git a/include/asm-x86/alternative.h b/include/asm-x86/alternative.h index 1f6a9ca10126..f6aa18eadf71 100644 --- a/include/asm-x86/alternative.h +++ b/include/asm-x86/alternative.h @@ -72,6 +72,8 @@ static inline void alternatives_smp_module_del(struct module *mod) {} static inline void alternatives_smp_switch(int smp) {} #endif /* CONFIG_SMP */ +const unsigned char *const *find_nop_table(void); + /* * Alternative instructions for different CPU types or capabilities. * diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h index c242527f970e..24d71b1eb189 100644 --- a/include/asm-x86/irqflags.h +++ b/include/asm-x86/irqflags.h @@ -179,8 +179,6 @@ static inline void trace_hardirqs_fixup(void) * have a reliable stack. x86_64 only. */ #define SWAPGS_UNSAFE_STACK swapgs -#define ARCH_TRACE_IRQS_ON call trace_hardirqs_on_thunk -#define ARCH_TRACE_IRQS_OFF call trace_hardirqs_off_thunk #define ARCH_LOCKDEP_SYS_EXIT call lockdep_sys_exit_thunk #define ARCH_LOCKDEP_SYS_EXIT_IRQ \ TRACE_IRQS_ON; \ @@ -192,24 +190,6 @@ static inline void trace_hardirqs_fixup(void) TRACE_IRQS_OFF; #else -#define ARCH_TRACE_IRQS_ON \ - pushl %eax; \ - pushl %ecx; \ - pushl %edx; \ - call trace_hardirqs_on; \ - popl %edx; \ - popl %ecx; \ - popl %eax; - -#define ARCH_TRACE_IRQS_OFF \ - pushl %eax; \ - pushl %ecx; \ - pushl %edx; \ - call trace_hardirqs_off; \ - popl %edx; \ - popl %ecx; \ - popl %eax; - #define ARCH_LOCKDEP_SYS_EXIT \ pushl %eax; \ pushl %ecx; \ @@ -223,8 +203,8 @@ static inline void trace_hardirqs_fixup(void) #endif #ifdef CONFIG_TRACE_IRQFLAGS -# define TRACE_IRQS_ON ARCH_TRACE_IRQS_ON -# define TRACE_IRQS_OFF ARCH_TRACE_IRQS_OFF +# define TRACE_IRQS_ON call trace_hardirqs_on_thunk; +# define TRACE_IRQS_OFF call trace_hardirqs_off_thunk; #else # define TRACE_IRQS_ON # define TRACE_IRQS_OFF diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h index 96651bb59ba1..a80f2d6cc737 100644 --- a/include/asm-x86/kdebug.h +++ b/include/asm-x86/kdebug.h @@ -35,4 +35,13 @@ extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); +struct pf_handler { + struct hlist_node hlist; + int (*handler)(struct pt_regs *regs, unsigned long error_code, + unsigned long address); +}; + +extern void register_page_fault_handler(struct pf_handler *new_pfh); +extern void unregister_page_fault_handler(struct pf_handler *old_pfh); + #endif diff --git a/include/asm-x86/vsyscall.h b/include/asm-x86/vsyscall.h index 17b3700949bf..6b66ff905af0 100644 --- a/include/asm-x86/vsyscall.h +++ b/include/asm-x86/vsyscall.h @@ -24,7 +24,8 @@ enum vsyscall_num { ((unused, __section__ (".vsyscall_gtod_data"),aligned(16))) #define __section_vsyscall_clock __attribute__ \ ((unused, __section__ (".vsyscall_clock"),aligned(16))) -#define __vsyscall_fn __attribute__ ((unused,__section__(".vsyscall_fn"))) +#define __vsyscall_fn \ + __attribute__ ((unused, __section__(".vsyscall_fn"))) notrace #define VGETCPU_RDTSCP 1 #define VGETCPU_LSL 2 diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h new file mode 100644 index 000000000000..922e23d0196f --- /dev/null +++ b/include/linux/ftrace.h @@ -0,0 +1,132 @@ +#ifndef _LINUX_FTRACE_H +#define _LINUX_FTRACE_H + +#ifdef CONFIG_FTRACE + +#include <linux/linkage.h> +#include <linux/fs.h> + +extern int ftrace_enabled; +extern int +ftrace_enable_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); + +typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); + +struct ftrace_ops { + ftrace_func_t func; + struct ftrace_ops *next; +}; + +/* + * The ftrace_ops must be a static and should also + * be read_mostly. These functions do modify read_mostly variables + * so use them sparely. Never free an ftrace_op or modify the + * next pointer after it has been registered. Even after unregistering + * it, the next pointer may still be used internally. + */ +int register_ftrace_function(struct ftrace_ops *ops); +int unregister_ftrace_function(struct ftrace_ops *ops); +void clear_ftrace_function(void); + +extern void ftrace_stub(unsigned long a0, unsigned long a1); +extern void mcount(void); + +#else /* !CONFIG_FTRACE */ +# define register_ftrace_function(ops) do { } while (0) +# define unregister_ftrace_function(ops) do { } while (0) +# define clear_ftrace_function(ops) do { } while (0) +#endif /* CONFIG_FTRACE */ + +#ifdef CONFIG_DYNAMIC_FTRACE +# define FTRACE_HASHBITS 10 +# define FTRACE_HASHSIZE (1<<FTRACE_HASHBITS) + +enum { + FTRACE_FL_FREE = (1 << 0), + FTRACE_FL_FAILED = (1 << 1), + FTRACE_FL_FILTER = (1 << 2), + FTRACE_FL_ENABLED = (1 << 3), +}; + +struct dyn_ftrace { + struct hlist_node node; + unsigned long ip; + unsigned long flags; +}; + +int ftrace_force_update(void); +void ftrace_set_filter(unsigned char *buf, int len, int reset); + +/* defined in arch */ +extern int ftrace_ip_converted(unsigned long ip); +extern unsigned char *ftrace_nop_replace(void); +extern unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr); +extern int ftrace_dyn_arch_init(void *data); +extern int ftrace_mcount_set(unsigned long *data); +extern int ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code); +extern int ftrace_update_ftrace_func(ftrace_func_t func); +extern void ftrace_caller(void); +extern void ftrace_call(void); +extern void mcount_call(void); +#else +# define ftrace_force_update() ({ 0; }) +# define ftrace_set_filter(buf, len, reset) do { } while (0) +#endif + +/* totally disable ftrace - can not re-enable after this */ +void ftrace_kill(void); + +static inline void tracer_disable(void) +{ +#ifdef CONFIG_FTRACE + ftrace_enabled = 0; +#endif +} + +#ifdef CONFIG_FRAME_POINTER +/* TODO: need to fix this for ARM */ +# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1)) +# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2)) +# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3)) +# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4)) +# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5)) +# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6)) +#else +# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +# define CALLER_ADDR1 0UL +# define CALLER_ADDR2 0UL +# define CALLER_ADDR3 0UL +# define CALLER_ADDR4 0UL +# define CALLER_ADDR5 0UL +# define CALLER_ADDR6 0UL +#endif + +#ifdef CONFIG_IRQSOFF_TRACER + extern void time_hardirqs_on(unsigned long a0, unsigned long a1); + extern void time_hardirqs_off(unsigned long a0, unsigned long a1); +#else +# define time_hardirqs_on(a0, a1) do { } while (0) +# define time_hardirqs_off(a0, a1) do { } while (0) +#endif + +#ifdef CONFIG_PREEMPT_TRACER + extern void trace_preempt_on(unsigned long a0, unsigned long a1); + extern void trace_preempt_off(unsigned long a0, unsigned long a1); +#else +# define trace_preempt_on(a0, a1) do { } while (0) +# define trace_preempt_off(a0, a1) do { } while (0) +#endif + +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +extern void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); +#else +static inline void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } +#endif + +#endif /* _LINUX_FTRACE_H */ diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index e600c4e9b8c5..2b1c2e58566e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -12,10 +12,10 @@ #define _LINUX_TRACE_IRQFLAGS_H #ifdef CONFIG_TRACE_IRQFLAGS - extern void trace_hardirqs_on(void); - extern void trace_hardirqs_off(void); extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); + extern void trace_hardirqs_on(void); + extern void trace_hardirqs_off(void); # define trace_hardirq_context(p) ((p)->hardirq_context) # define trace_softirq_context(p) ((p)->softirq_context) # define trace_hardirqs_enabled(p) ((p)->hardirqs_enabled) @@ -41,6 +41,15 @@ # define INIT_TRACE_IRQFLAGS #endif +#if defined(CONFIG_IRQSOFF_TRACER) || \ + defined(CONFIG_PREEMPT_TRACER) + extern void stop_critical_timings(void); + extern void start_critical_timings(void); +#else +# define stop_critical_timings() do { } while (0) +# define start_critical_timings() do { } while (0) +#endif + #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT #include <asm/irqflags.h> diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 2119610b24f8..14f329c64ba8 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -3,6 +3,8 @@ #include <asm/linkage.h> +#define notrace __attribute__((no_instrument_function)) + #ifdef __cplusplus #define CPP_ASMLINKAGE extern "C" #else diff --git a/include/linux/marker.h b/include/linux/marker.h index 430f6adf9762..1290653f9241 100644 --- a/include/linux/marker.h +++ b/include/linux/marker.h @@ -44,8 +44,8 @@ struct marker { */ char state; /* Marker state. */ char ptype; /* probe type : 0 : single, 1 : multi */ - void (*call)(const struct marker *mdata, /* Probe wrapper */ - void *call_private, const char *fmt, ...); + /* Probe wrapper */ + void (*call)(const struct marker *mdata, void *call_private, ...); struct marker_probe_closure single; struct marker_probe_closure *multi; } __attribute__((aligned(8))); @@ -58,8 +58,12 @@ struct marker { * Make sure the alignment of the structure in the __markers section will * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. + * + * The "generic" argument controls which marker enabling mechanism must be used. + * If generic is true, a variable read is used. + * If generic is false, immediate values are used. */ -#define __trace_mark(name, call_private, format, args...) \ +#define __trace_mark(generic, name, call_private, format, args...) \ do { \ static const char __mstrtab_##name[] \ __attribute__((section("__markers_strings"))) \ @@ -72,15 +76,14 @@ struct marker { __mark_check_format(format, ## args); \ if (unlikely(__mark_##name.state)) { \ (*__mark_##name.call) \ - (&__mark_##name, call_private, \ - format, ## args); \ + (&__mark_##name, call_private, ## args);\ } \ } while (0) extern void marker_update_probe_range(struct marker *begin, struct marker *end); #else /* !CONFIG_MARKERS */ -#define __trace_mark(name, call_private, format, args...) \ +#define __trace_mark(generic, name, call_private, format, args...) \ __mark_check_format(format, ## args) static inline void marker_update_probe_range(struct marker *begin, struct marker *end) @@ -88,15 +91,30 @@ static inline void marker_update_probe_range(struct marker *begin, #endif /* CONFIG_MARKERS */ /** - * trace_mark - Marker + * trace_mark - Marker using code patching * @name: marker name, not quoted. * @format: format string * @args...: variable argument list * - * Places a marker. + * Places a marker using optimized code patching technique (imv_read()) + * to be enabled when immediate values are present. */ #define trace_mark(name, format, args...) \ - __trace_mark(name, NULL, format, ## args) + __trace_mark(0, name, NULL, format, ## args) + +/** + * _trace_mark - Marker using variable read + * @name: marker name, not quoted. + * @format: format string + * @args...: variable argument list + * + * Places a marker using a standard memory read (_imv_read()) to be + * enabled. Should be used for markers in code paths where instruction + * modification based enabling is not welcome. (__init and __exit functions, + * lockdep, some traps, printk). + */ +#define _trace_mark(name, format, args...) \ + __trace_mark(1, name, NULL, format, ## args) /** * MARK_NOARGS - Format string for a marker with no argument. @@ -117,9 +135,9 @@ static inline void __printf(1, 2) ___mark_check_format(const char *fmt, ...) extern marker_probe_func __mark_empty_function; extern void marker_probe_cb(const struct marker *mdata, - void *call_private, const char *fmt, ...); + void *call_private, ...); extern void marker_probe_cb_noarg(const struct marker *mdata, - void *call_private, const char *fmt, ...); + void *call_private, ...); /* * Connect a probe to a marker. diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 23f0c54175cd..72b1a10a59b6 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -10,7 +10,7 @@ #include <linux/linkage.h> #include <linux/list.h> -#ifdef CONFIG_DEBUG_PREEMPT +#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER) extern void add_preempt_count(int val); extern void sub_preempt_count(int val); #else @@ -52,6 +52,34 @@ do { \ preempt_check_resched(); \ } while (0) +/* For debugging and tracer internals only! */ +#define add_preempt_count_notrace(val) \ + do { preempt_count() += (val); } while (0) +#define sub_preempt_count_notrace(val) \ + do { preempt_count() -= (val); } while (0) +#define inc_preempt_count_notrace() add_preempt_count_notrace(1) +#define dec_preempt_count_notrace() sub_preempt_count_notrace(1) + +#define preempt_disable_notrace() \ +do { \ + inc_preempt_count_notrace(); \ + barrier(); \ +} while (0) + +#define preempt_enable_no_resched_notrace() \ +do { \ + barrier(); \ + dec_preempt_count_notrace(); \ +} while (0) + +/* preempt_check_resched is OK to trace */ +#define preempt_enable_notrace() \ +do { \ + preempt_enable_no_resched_notrace(); \ + barrier(); \ + preempt_check_resched(); \ +} while (0) + #else #define preempt_disable() do { } while (0) @@ -59,6 +87,10 @@ do { \ #define preempt_enable() do { } while (0) #define preempt_check_resched() do { } while (0) +#define preempt_disable_notrace() do { } while (0) +#define preempt_enable_no_resched_notrace() do { } while (0) +#define preempt_enable_notrace() do { } while (0) + #endif #ifdef CONFIG_PREEMPT_NOTIFIERS diff --git a/include/linux/sched.h b/include/linux/sched.h index c5d3f847ca8d..aa609858aef0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -246,6 +246,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern void init_idle_bootup_task(struct task_struct *idle); +extern int runqueue_is_locked(void); + extern cpumask_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) extern int select_nohz_load_balancer(int cpu); @@ -2131,6 +2133,18 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) } #endif +#ifdef CONFIG_TRACING +extern void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3); +#else +static inline void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ +} +#endif + extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask); extern long sched_getaffinity(pid_t pid, cpumask_t *mask); @@ -2225,6 +2239,8 @@ static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p) } #endif /* CONFIG_MM_OWNER */ +#define TASK_STATE_TO_CHAR_STR "RSDTtZX" + #endif /* __KERNEL__ */ #endif diff --git a/include/linux/writeback.h b/include/linux/writeback.h index f462439cc288..bd91987c065f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -105,6 +105,8 @@ extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; +extern unsigned long determine_dirtyable_memory(void); + extern int dirty_ratio_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/Makefile b/kernel/Makefile index 1c9938addb9d..ca2433e84873 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,6 +11,18 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o +CFLAGS_REMOVE_sched.o = -pg -mno-spe + +ifdef CONFIG_FTRACE +# Do not trace debug files and internal ftrace files +CFLAGS_REMOVE_lockdep.o = -pg +CFLAGS_REMOVE_lockdep_proc.o = -pg +CFLAGS_REMOVE_mutex-debug.o = -pg +CFLAGS_REMOVE_rtmutex-debug.o = -pg +CFLAGS_REMOVE_cgroup-debug.o = -pg +CFLAGS_REMOVE_sched_clock.o = -pg +endif + obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ @@ -69,6 +81,8 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_MARKERS) += marker.o obj-$(CONFIG_LATENCYTOP) += latencytop.o +obj-$(CONFIG_FTRACE) += trace/ +obj-$(CONFIG_TRACING) += trace/ ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/fork.c b/kernel/fork.c index 19908b26cf80..d66d676dc362 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -909,7 +909,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, rt_mutex_init_task(p); -#ifdef CONFIG_TRACE_IRQFLAGS +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_LOCKDEP) DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 81a4e4a3f087..65548eff029e 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -39,6 +39,7 @@ #include <linux/irqflags.h> #include <linux/utsname.h> #include <linux/hash.h> +#include <linux/ftrace.h> #include <asm/sections.h> @@ -81,6 +82,8 @@ static int graph_lock(void) __raw_spin_unlock(&lockdep_lock); return 0; } + /* prevent any recursions within lockdep from causing deadlocks */ + current->lockdep_recursion++; return 1; } @@ -89,6 +92,7 @@ static inline int graph_unlock(void) if (debug_locks && !__raw_spin_is_locked(&lockdep_lock)) return DEBUG_LOCKS_WARN_ON(1); + current->lockdep_recursion--; __raw_spin_unlock(&lockdep_lock); return 0; } @@ -982,7 +986,7 @@ check_noncircular(struct lock_class *source, unsigned int depth) return 1; } -#ifdef CONFIG_TRACE_IRQFLAGS +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) /* * Forwards and backwards subgraph searching, for the purposes of * proving that two subgraphs can be connected by a new dependency @@ -1680,7 +1684,7 @@ valid_state(struct task_struct *curr, struct held_lock *this, static int mark_lock(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit new_bit); -#ifdef CONFIG_TRACE_IRQFLAGS +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) /* * print irq inversion bug: @@ -2013,11 +2017,13 @@ void early_boot_irqs_on(void) /* * Hardirqs will be enabled: */ -void trace_hardirqs_on(void) +void trace_hardirqs_on_caller(unsigned long a0) { struct task_struct *curr = current; unsigned long ip; + time_hardirqs_on(CALLER_ADDR0, a0); + if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2055,16 +2061,23 @@ void trace_hardirqs_on(void) curr->hardirq_enable_event = ++curr->irq_events; debug_atomic_inc(&hardirqs_on_events); } +EXPORT_SYMBOL(trace_hardirqs_on_caller); +void trace_hardirqs_on(void) +{ + trace_hardirqs_on_caller(CALLER_ADDR0); +} EXPORT_SYMBOL(trace_hardirqs_on); /* * Hardirqs were disabled: */ -void trace_hardirqs_off(void) +void trace_hardirqs_off_caller(unsigned long a0) { struct task_struct *curr = current; + time_hardirqs_off(CALLER_ADDR0, a0); + if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2082,7 +2095,12 @@ void trace_hardirqs_off(void) } else debug_atomic_inc(&redundant_hardirqs_off); } +EXPORT_SYMBOL(trace_hardirqs_off_caller); +void trace_hardirqs_off(void) +{ + trace_hardirqs_off_caller(CALLER_ADDR0); +} EXPORT_SYMBOL(trace_hardirqs_off); /* @@ -2246,7 +2264,7 @@ static inline int separate_irq_context(struct task_struct *curr, * Mark a lock with a usage bit, and validate the state transition: */ static int mark_lock(struct task_struct *curr, struct held_lock *this, - enum lock_usage_bit new_bit) + enum lock_usage_bit new_bit) { unsigned int new_mask = 1 << new_bit, ret = 1; @@ -2686,7 +2704,7 @@ static void check_flags(unsigned long flags) * and also avoid lockdep recursion: */ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, unsigned long ip) + int trylock, int read, int check, unsigned long ip) { unsigned long flags; @@ -2708,7 +2726,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, EXPORT_SYMBOL_GPL(lock_acquire); -void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) +void lock_release(struct lockdep_map *lock, int nested, + unsigned long ip) { unsigned long flags; diff --git a/kernel/marker.c b/kernel/marker.c index b5a9fe1d50d5..1abfb923b761 100644 --- a/kernel/marker.c +++ b/kernel/marker.c @@ -55,8 +55,8 @@ static DEFINE_MUTEX(markers_mutex); struct marker_entry { struct hlist_node hlist; char *format; - void (*call)(const struct marker *mdata, /* Probe wrapper */ - void *call_private, const char *fmt, ...); + /* Probe wrapper */ + void (*call)(const struct marker *mdata, void *call_private, ...); struct marker_probe_closure single; struct marker_probe_closure *multi; int refcount; /* Number of times armed. 0 if disarmed. */ @@ -91,15 +91,13 @@ EXPORT_SYMBOL_GPL(__mark_empty_function); * marker_probe_cb Callback that prepares the variable argument list for probes. * @mdata: pointer of type struct marker * @call_private: caller site private data - * @fmt: format string * @...: Variable argument list. * * Since we do not use "typical" pointer based RCU in the 1 argument case, we * need to put a full smp_rmb() in this branch. This is why we do not use * rcu_dereference() for the pointer read. */ -void marker_probe_cb(const struct marker *mdata, void *call_private, - const char *fmt, ...) +void marker_probe_cb(const struct marker *mdata, void *call_private, ...) { va_list args; char ptype; @@ -120,8 +118,9 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, /* Must read the ptr before private data. They are not data * dependant, so we put an explicit smp_rmb() here. */ smp_rmb(); - va_start(args, fmt); - func(mdata->single.probe_private, call_private, fmt, &args); + va_start(args, call_private); + func(mdata->single.probe_private, call_private, mdata->format, + &args); va_end(args); } else { struct marker_probe_closure *multi; @@ -136,9 +135,9 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, smp_read_barrier_depends(); multi = mdata->multi; for (i = 0; multi[i].func; i++) { - va_start(args, fmt); - multi[i].func(multi[i].probe_private, call_private, fmt, - &args); + va_start(args, call_private); + multi[i].func(multi[i].probe_private, call_private, + mdata->format, &args); va_end(args); } } @@ -150,13 +149,11 @@ EXPORT_SYMBOL_GPL(marker_probe_cb); * marker_probe_cb Callback that does not prepare the variable argument list. * @mdata: pointer of type struct marker * @call_private: caller site private data - * @fmt: format string * @...: Variable argument list. * * Should be connected to markers "MARK_NOARGS". */ -void marker_probe_cb_noarg(const struct marker *mdata, - void *call_private, const char *fmt, ...) +void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) { va_list args; /* not initialized */ char ptype; @@ -172,7 +169,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, /* Must read the ptr before private data. They are not data * dependant, so we put an explicit smp_rmb() here. */ smp_rmb(); - func(mdata->single.probe_private, call_private, fmt, &args); + func(mdata->single.probe_private, call_private, mdata->format, + &args); } else { struct marker_probe_closure *multi; int i; @@ -186,8 +184,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, smp_read_barrier_depends(); multi = mdata->multi; for (i = 0; multi[i].func; i++) - multi[i].func(multi[i].probe_private, call_private, fmt, - &args); + multi[i].func(multi[i].probe_private, call_private, + mdata->format, &args); } preempt_enable(); } diff --git a/kernel/printk.c b/kernel/printk.c index 8fb01c32aa3b..ae7d5b9e535d 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1041,7 +1041,9 @@ void release_console_sem(void) _log_end = log_end; con_start = log_end; /* Flush */ spin_unlock(&logbuf_lock); + stop_critical_timings(); /* don't trace print latency */ call_console_drivers(_con_start, _log_end); + start_critical_timings(); local_irq_restore(flags); } console_locked = 0; diff --git a/kernel/sched.c b/kernel/sched.c index 3aaa5c8cb421..2a7ad35ea79b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -70,6 +70,7 @@ #include <linux/bootmem.h> #include <linux/debugfs.h> #include <linux/ctype.h> +#include <linux/ftrace.h> #include <asm/tlb.h> #include <asm/irq_regs.h> @@ -607,6 +608,24 @@ static inline void update_rq_clock(struct rq *rq) # define const_debug static const #endif +/** + * runqueue_is_locked + * + * Returns true if the current cpu runqueue is locked. + * This interface allows printk to be called with the runqueue lock + * held and know whether or not it is OK to wake up the klogd. + */ +int runqueue_is_locked(void) +{ + int cpu = get_cpu(); + struct rq *rq = cpu_rq(cpu); + int ret; + + ret = spin_is_locked(&rq->lock); + put_cpu(); + return ret; +} + /* * Debugging: various feature bits */ @@ -2149,6 +2168,9 @@ out_activate: success = 1; out_running: + trace_mark(kernel_sched_wakeup, + "pid %d state %ld ## rq %p task %p rq->curr %p", + p->pid, p->state, rq, p, rq->curr); check_preempt_curr(rq, p); p->state = TASK_RUNNING; @@ -2279,6 +2301,9 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) p->sched_class->task_new(rq, p); inc_nr_running(p, rq); } + trace_mark(kernel_sched_wakeup_new, + "pid %d state %ld ## rq %p task %p rq->curr %p", + p->pid, p->state, rq, p, rq->curr); check_preempt_curr(rq, p); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) @@ -2451,6 +2476,11 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm, *oldmm; prepare_task_switch(rq, prev, next); + trace_mark(kernel_sched_schedule, + "prev_pid %d next_pid %d prev_state %ld " + "## rq %p prev %p next %p", + prev->pid, next->pid, prev->state, + rq, prev, next); mm = next->mm; oldmm = prev->active_mm; /* @@ -4021,26 +4051,44 @@ void scheduler_tick(void) #endif } -#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT) +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + +static inline unsigned long get_parent_ip(unsigned long addr) +{ + if (in_lock_functions(addr)) { + addr = CALLER_ADDR2; + if (in_lock_functions(addr)) + addr = CALLER_ADDR3; + } + return addr; +} void __kprobes add_preempt_count(int val) { +#ifdef CONFIG_DEBUG_PREEMPT /* * Underflow? */ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) return; +#endif preempt_count() += val; +#ifdef CONFIG_DEBUG_PREEMPT /* * Spinlock count overflowing soon? */ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); +#endif + if (preempt_count() == val) + trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); } EXPORT_SYMBOL(add_preempt_count); void __kprobes sub_preempt_count(int val) { +#ifdef CONFIG_DEBUG_PREEMPT /* * Underflow? */ @@ -4052,7 +4100,10 @@ void __kprobes sub_preempt_count(int val) if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK))) return; +#endif + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); preempt_count() -= val; } EXPORT_SYMBOL(sub_preempt_count); @@ -5384,7 +5435,7 @@ out_unlock: return retval; } -static const char stat_nam[] = "RSDTtZX"; +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; void sched_show_task(struct task_struct *p) { diff --git a/kernel/semaphore.c b/kernel/semaphore.c index 5c2942e768cd..1a064adab658 100644 --- a/kernel/semaphore.c +++ b/kernel/semaphore.c @@ -31,6 +31,7 @@ #include <linux/sched.h> #include <linux/semaphore.h> #include <linux/spinlock.h> +#include <linux/ftrace.h> static noinline void __down(struct semaphore *sem); static noinline int __down_interruptible(struct semaphore *sem); @@ -53,6 +54,7 @@ void down(struct semaphore *sem) { unsigned long flags; + ftrace_special(sem->count, 0, __LINE__); spin_lock_irqsave(&sem->lock, flags); if (likely(sem->count > 0)) sem->count--; diff --git a/kernel/spinlock.c b/kernel/spinlock.c index ae28c8245123..a1fb54c93cdd 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -436,7 +436,7 @@ int __lockfunc _spin_trylock_bh(spinlock_t *lock) } EXPORT_SYMBOL(_spin_trylock_bh); -int in_lock_functions(unsigned long addr) +notrace int in_lock_functions(unsigned long addr) { /* Linker adds these: start and end of __lockfunc functions */ extern char __lock_text_start[], __lock_text_end[]; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 29116652dca8..efaf7c5500e9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -46,6 +46,7 @@ #include <linux/nfs_fs.h> #include <linux/acpi.h> #include <linux/reboot.h> +#include <linux/ftrace.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -455,6 +456,16 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, +#ifdef CONFIG_FTRACE + { + .ctl_name = CTL_UNNUMBERED, + .procname = "ftrace_enabled", + .data = &ftrace_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &ftrace_enable_sysctl, + }, +#endif #ifdef CONFIG_KMOD { .ctl_name = KERN_MODPROBE, diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig new file mode 100644 index 000000000000..263e9e6bbd60 --- /dev/null +++ b/kernel/trace/Kconfig @@ -0,0 +1,135 @@ +# +# Architectures that offer an FTRACE implementation should select HAVE_FTRACE: +# +config HAVE_FTRACE + bool + +config HAVE_DYNAMIC_FTRACE + bool + +config TRACER_MAX_TRACE + bool + +config TRACING + bool + select DEBUG_FS + select STACKTRACE + +config FTRACE + bool "Kernel Function Tracer" + depends on HAVE_FTRACE + select FRAME_POINTER + select TRACING + select CONTEXT_SWITCH_TRACER + help + Enable the kernel to trace every kernel function. This is done + by using a compiler feature to insert a small, 5-byte No-Operation + instruction to the beginning of every kernel function, which NOP + sequence is then dynamically patched into a tracer call when + tracing is enabled by the administrator. If it's runtime disabled + (the bootup default), then the overhead of the instructions is very + small and not measurable even in micro-benchmarks. + +config IRQSOFF_TRACER + bool "Interrupts-off Latency Tracer" + default n + depends on TRACE_IRQFLAGS_SUPPORT + depends on GENERIC_TIME + depends on HAVE_FTRACE + select TRACE_IRQFLAGS + select TRACING + select TRACER_MAX_TRACE + help + This option measures the time spent in irqs-off critical + sections, with microsecond accuracy. + + The default measurement method is a maximum search, which is + disabled by default and can be runtime (re-)started + via: + + echo 0 > /debugfs/tracing/tracing_max_latency + + (Note that kernel size and overhead increases with this option + enabled. This option and the preempt-off timing option can be + used together or separately.) + +config PREEMPT_TRACER + bool "Preemption-off Latency Tracer" + default n + depends on GENERIC_TIME + depends on PREEMPT + depends on HAVE_FTRACE + select TRACING + select TRACER_MAX_TRACE + help + This option measures the time spent in preemption off critical + sections, with microsecond accuracy. + + The default measurement method is a maximum search, which is + disabled by default and can be runtime (re-)started + via: + + echo 0 > /debugfs/tracing/tracing_max_latency + + (Note that kernel size and overhead increases with this option + enabled. This option and the irqs-off timing option can be + used together or separately.) + +config SYSPROF_TRACER + bool "Sysprof Tracer" + depends on X86 + select TRACING + help + This tracer provides the trace needed by the 'Sysprof' userspace + tool. + +config SCHED_TRACER + bool "Scheduling Latency Tracer" + depends on HAVE_FTRACE + select TRACING + select CONTEXT_SWITCH_TRACER + select TRACER_MAX_TRACE + help + This tracer tracks the latency of the highest priority task + to be scheduled in, starting from the point it has woken up. + +config CONTEXT_SWITCH_TRACER + bool "Trace process context switches" + depends on HAVE_FTRACE + select TRACING + select MARKERS + help + This tracer gets called from the context switch and records + all switching of tasks. + +config DYNAMIC_FTRACE + bool "enable/disable ftrace tracepoints dynamically" + depends on FTRACE + depends on HAVE_DYNAMIC_FTRACE + default y + help + This option will modify all the calls to ftrace dynamically + (will patch them out of the binary image and replaces them + with a No-Op instruction) as they are called. A table is + created to dynamically enable them again. + + This way a CONFIG_FTRACE kernel is slightly larger, but otherwise + has native performance as long as no tracing is active. + + The changes to the code are done by a kernel thread that + wakes up once a second and checks to see if any ftrace calls + were made. If so, it runs stop_machine (stops all CPUS) + and modifies the code to jump over the call to ftrace. + +config FTRACE_SELFTEST + bool + +config FTRACE_STARTUP_TEST + bool "Perform a startup test on ftrace" + depends on TRACING + select FTRACE_SELFTEST + help + This option performs a series of startup tests on ftrace. On bootup + a series of tests are made to verify that the tracer is + functioning properly. It will do tests on all the configured + tracers of ftrace. diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile new file mode 100644 index 000000000000..7aec123ec1d8 --- /dev/null +++ b/kernel/trace/Makefile @@ -0,0 +1,23 @@ + +# Do not instrument the tracer itself: + +ifdef CONFIG_FTRACE +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) + +# selftest needs instrumentation +CFLAGS_trace_selftest_dynamic.o = -pg +obj-y += trace_selftest_dynamic.o +endif + +obj-$(CONFIG_FTRACE) += libftrace.o + +obj-$(CONFIG_TRACING) += trace.o +obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o +obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o +obj-$(CONFIG_FTRACE) += trace_functions.o +obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o +obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o +obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o + +libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c new file mode 100644 index 000000000000..89bd9a6f52ec --- /dev/null +++ b/kernel/trace/ftrace.c @@ -0,0 +1,1398 @@ +/* + * Infrastructure for profiling code inserted by 'gcc -pg'. + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2004-2008 Ingo Molnar <mingo@redhat.com> + * + * Originally ported from the -rt patch by: + * Copyright (C) 2007 Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Based on code in the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ + +#include <linux/stop_machine.h> +#include <linux/clocksource.h> +#include <linux/kallsyms.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/hardirq.h> +#include <linux/kthread.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/sysctl.h> +#include <linux/ctype.h> +#include <linux/hash.h> +#include <linux/list.h> + +#include "trace.h" + +/* ftrace_enabled is a method to turn ftrace on or off */ +int ftrace_enabled __read_mostly; +static int last_ftrace_enabled; + +/* + * ftrace_disabled is set when an anomaly is discovered. + * ftrace_disabled is much stronger than ftrace_enabled. + */ +static int ftrace_disabled __read_mostly; + +static DEFINE_SPINLOCK(ftrace_lock); +static DEFINE_MUTEX(ftrace_sysctl_lock); + +static struct ftrace_ops ftrace_list_end __read_mostly = +{ + .func = ftrace_stub, +}; + +static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; +ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; + +void ftrace_list_func(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_ops *op = ftrace_list; + + /* in case someone actually ports this to alpha! */ + read_barrier_depends(); + + while (op != &ftrace_list_end) { + /* silly alpha */ + read_barrier_depends(); + op->func(ip, parent_ip); + op = op->next; + }; +} + +/** + * clear_ftrace_function - reset the ftrace function + * + * This NULLs the ftrace function and in essence stops + * tracing. There may be lag + */ +void clear_ftrace_function(void) +{ + ftrace_trace_function = ftrace_stub; +} + +static int __register_ftrace_function(struct ftrace_ops *ops) +{ + /* Should never be called by interrupts */ + spin_lock(&ftrace_lock); + + ops->next = ftrace_list; + /* + * We are entering ops into the ftrace_list but another + * CPU might be walking that list. We need to make sure + * the ops->next pointer is valid before another CPU sees + * the ops pointer included into the ftrace_list. + */ + smp_wmb(); + ftrace_list = ops; + + if (ftrace_enabled) { + /* + * For one func, simply call it directly. + * For more than one func, call the chain. + */ + if (ops->next == &ftrace_list_end) + ftrace_trace_function = ops->func; + else + ftrace_trace_function = ftrace_list_func; + } + + spin_unlock(&ftrace_lock); + + return 0; +} + +static int __unregister_ftrace_function(struct ftrace_ops *ops) +{ + struct ftrace_ops **p; + int ret = 0; + + spin_lock(&ftrace_lock); + + /* + * If we are removing the last function, then simply point + * to the ftrace_stub. + */ + if (ftrace_list == ops && ops->next == &ftrace_list_end) { + ftrace_trace_function = ftrace_stub; + ftrace_list = &ftrace_list_end; + goto out; + } + + for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next) + if (*p == ops) + break; + + if (*p != ops) { + ret = -1; + goto out; + } + + *p = (*p)->next; + + if (ftrace_enabled) { + /* If we only have one func left, then call that directly */ + if (ftrace_list == &ftrace_list_end || + ftrace_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_list->func; + } + + out: + spin_unlock(&ftrace_lock); + + return ret; +} + +#ifdef CONFIG_DYNAMIC_FTRACE + +static struct task_struct *ftraced_task; +static DECLARE_WAIT_QUEUE_HEAD(ftraced_waiters); +static unsigned long ftraced_iteration_counter; + +enum { + FTRACE_ENABLE_CALLS = (1 << 0), + FTRACE_DISABLE_CALLS = (1 << 1), + FTRACE_UPDATE_TRACE_FUNC = (1 << 2), + FTRACE_ENABLE_MCOUNT = (1 << 3), + FTRACE_DISABLE_MCOUNT = (1 << 4), +}; + +static int ftrace_filtered; + +static struct hlist_head ftrace_hash[FTRACE_HASHSIZE]; + +static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu); + +static DEFINE_SPINLOCK(ftrace_shutdown_lock); +static DEFINE_MUTEX(ftraced_lock); +static DEFINE_MUTEX(ftrace_filter_lock); + +struct ftrace_page { + struct ftrace_page *next; + unsigned long index; + struct dyn_ftrace records[]; +}; + +#define ENTRIES_PER_PAGE \ + ((PAGE_SIZE - sizeof(struct ftrace_page)) / sizeof(struct dyn_ftrace)) + +/* estimate from running different kernels */ +#define NR_TO_INIT 10000 + +static struct ftrace_page *ftrace_pages_start; +static struct ftrace_page *ftrace_pages; + +static int ftraced_trigger; +static int ftraced_suspend; + +static int ftrace_record_suspend; + +static struct dyn_ftrace *ftrace_free_records; + +static inline int +ftrace_ip_in_hash(unsigned long ip, unsigned long key) +{ + struct dyn_ftrace *p; + struct hlist_node *t; + int found = 0; + + hlist_for_each_entry(p, t, &ftrace_hash[key], node) { + if (p->ip == ip) { + found = 1; + break; + } + } + + return found; +} + +static inline void +ftrace_add_hash(struct dyn_ftrace *node, unsigned long key) +{ + hlist_add_head(&node->node, &ftrace_hash[key]); +} + +static void ftrace_free_rec(struct dyn_ftrace *rec) +{ + /* no locking, only called from kstop_machine */ + + rec->ip = (unsigned long)ftrace_free_records; + ftrace_free_records = rec; + rec->flags |= FTRACE_FL_FREE; +} + +static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) +{ + struct dyn_ftrace *rec; + + /* First check for freed records */ + if (ftrace_free_records) { + rec = ftrace_free_records; + + if (unlikely(!(rec->flags & FTRACE_FL_FREE))) { + WARN_ON_ONCE(1); + ftrace_free_records = NULL; + ftrace_disabled = 1; + ftrace_enabled = 0; + return NULL; + } + + ftrace_free_records = (void *)rec->ip; + memset(rec, 0, sizeof(*rec)); + return rec; + } + + if (ftrace_pages->index == ENTRIES_PER_PAGE) { + if (!ftrace_pages->next) + return NULL; + ftrace_pages = ftrace_pages->next; + } + + return &ftrace_pages->records[ftrace_pages->index++]; +} + +static void +ftrace_record_ip(unsigned long ip) +{ + struct dyn_ftrace *node; + unsigned long flags; + unsigned long key; + int resched; + int atomic; + int cpu; + + if (!ftrace_enabled || ftrace_disabled) + return; + + resched = need_resched(); + preempt_disable_notrace(); + + /* + * We simply need to protect against recursion. + * Use the the raw version of smp_processor_id and not + * __get_cpu_var which can call debug hooks that can + * cause a recursive crash here. + */ + cpu = raw_smp_processor_id(); + per_cpu(ftrace_shutdown_disable_cpu, cpu)++; + if (per_cpu(ftrace_shutdown_disable_cpu, cpu) != 1) + goto out; + + if (unlikely(ftrace_record_suspend)) + goto out; + + key = hash_long(ip, FTRACE_HASHBITS); + + WARN_ON_ONCE(key >= FTRACE_HASHSIZE); + + if (ftrace_ip_in_hash(ip, key)) + goto out; + + atomic = irqs_disabled(); + + spin_lock_irqsave(&ftrace_shutdown_lock, flags); + + /* This ip may have hit the hash before the lock */ + if (ftrace_ip_in_hash(ip, key)) + goto out_unlock; + + /* + * There's a slight race that the ftraced will update the + * hash and reset here. If it is already converted, skip it. + */ + if (ftrace_ip_converted(ip)) + goto out_unlock; + + node = ftrace_alloc_dyn_node(ip); + if (!node) + goto out_unlock; + + node->ip = ip; + + ftrace_add_hash(node, key); + + ftraced_trigger = 1; + + out_unlock: + spin_unlock_irqrestore(&ftrace_shutdown_lock, flags); + out: + per_cpu(ftrace_shutdown_disable_cpu, cpu)--; + + /* prevent recursion with scheduler */ + if (resched) + preempt_enable_no_resched_notrace(); + else + preempt_enable_notrace(); +} + +#define FTRACE_ADDR ((long)(ftrace_caller)) +#define MCOUNT_ADDR ((long)(mcount)) + +static void +__ftrace_replace_code(struct dyn_ftrace *rec, + unsigned char *old, unsigned char *new, int enable) +{ + unsigned long ip; + int failed; + + ip = rec->ip; + + if (ftrace_filtered && enable) { + unsigned long fl; + /* + * If filtering is on: + * + * If this record is set to be filtered and + * is enabled then do nothing. + * + * If this record is set to be filtered and + * it is not enabled, enable it. + * + * If this record is not set to be filtered + * and it is not enabled do nothing. + * + * If this record is not set to be filtered and + * it is enabled, disable it. + */ + fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED); + + if ((fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) || + (fl == 0)) + return; + + /* + * If it is enabled disable it, + * otherwise enable it! + */ + if (fl == FTRACE_FL_ENABLED) { + /* swap new and old */ + new = old; + old = ftrace_call_replace(ip, FTRACE_ADDR); + rec->flags &= ~FTRACE_FL_ENABLED; + } else { + new = ftrace_call_replace(ip, FTRACE_ADDR); + rec->flags |= FTRACE_FL_ENABLED; + } + } else { + + if (enable) + new = ftrace_call_replace(ip, FTRACE_ADDR); + else + old = ftrace_call_replace(ip, FTRACE_ADDR); + + if (enable) { + if (rec->flags & FTRACE_FL_ENABLED) + return; + rec->flags |= FTRACE_FL_ENABLED; + } else { + if (!(rec->flags & FTRACE_FL_ENABLED)) + return; + rec->flags &= ~FTRACE_FL_ENABLED; + } + } + + failed = ftrace_modify_code(ip, old, new); + if (failed) { + unsigned long key; + /* It is possible that the function hasn't been converted yet */ + key = hash_long(ip, FTRACE_HASHBITS); + if (!ftrace_ip_in_hash(ip, key)) { + rec->flags |= FTRACE_FL_FAILED; + ftrace_free_rec(rec); + } + + } +} + +static void ftrace_replace_code(int enable) +{ + unsigned char *new = NULL, *old = NULL; + struct dyn_ftrace *rec; + struct ftrace_page *pg; + int i; + + if (enable) + old = ftrace_nop_replace(); + else + new = ftrace_nop_replace(); + + for (pg = ftrace_pages_start; pg; pg = pg->next) { + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + + /* don't modify code that has already faulted */ + if (rec->flags & FTRACE_FL_FAILED) + continue; + + __ftrace_replace_code(rec, old, new, enable); + } + } +} + +static void ftrace_shutdown_replenish(void) +{ + if (ftrace_pages->next) + return; + + /* allocate another page */ + ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL); +} + +static void +ftrace_code_disable(struct dyn_ftrace *rec) +{ + unsigned long ip; + unsigned char *nop, *call; + int failed; + + ip = rec->ip; + + nop = ftrace_nop_replace(); + call = ftrace_call_replace(ip, MCOUNT_ADDR); + + failed = ftrace_modify_code(ip, call, nop); + if (failed) { + rec->flags |= FTRACE_FL_FAILED; + ftrace_free_rec(rec); + } +} + +static int __ftrace_modify_code(void *data) +{ + unsigned long addr; + int *command = data; + + if (*command & FTRACE_ENABLE_CALLS) + ftrace_replace_code(1); + else if (*command & FTRACE_DISABLE_CALLS) + ftrace_replace_code(0); + + if (*command & FTRACE_UPDATE_TRACE_FUNC) + ftrace_update_ftrace_func(ftrace_trace_function); + + if (*command & FTRACE_ENABLE_MCOUNT) { + addr = (unsigned long)ftrace_record_ip; + ftrace_mcount_set(&addr); + } else if (*command & FTRACE_DISABLE_MCOUNT) { + addr = (unsigned long)ftrace_stub; + ftrace_mcount_set(&addr); + } + + return 0; +} + +static void ftrace_run_update_code(int command) +{ + stop_machine_run(__ftrace_modify_code, &command, NR_CPUS); +} + +static ftrace_func_t saved_ftrace_func; + +static void ftrace_startup(void) +{ + int command = 0; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + ftraced_suspend++; + if (ftraced_suspend == 1) + command |= FTRACE_ENABLE_CALLS; + + if (saved_ftrace_func != ftrace_trace_function) { + saved_ftrace_func = ftrace_trace_function; + command |= FTRACE_UPDATE_TRACE_FUNC; + } + + if (!command || !ftrace_enabled) + goto out; + + ftrace_run_update_code(command); + out: + mutex_unlock(&ftraced_lock); +} + +static void ftrace_shutdown(void) +{ + int command = 0; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + ftraced_suspend--; + if (!ftraced_suspend) + command |= FTRACE_DISABLE_CALLS; + + if (saved_ftrace_func != ftrace_trace_function) { + saved_ftrace_func = ftrace_trace_function; + command |= FTRACE_UPDATE_TRACE_FUNC; + } + + if (!command || !ftrace_enabled) + goto out; + + ftrace_run_update_code(command); + out: + mutex_unlock(&ftraced_lock); +} + +static void ftrace_startup_sysctl(void) +{ + int command = FTRACE_ENABLE_MCOUNT; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + /* Force update next time */ + saved_ftrace_func = NULL; + /* ftraced_suspend is true if we want ftrace running */ + if (ftraced_suspend) + command |= FTRACE_ENABLE_CALLS; + + ftrace_run_update_code(command); + mutex_unlock(&ftraced_lock); +} + +static void ftrace_shutdown_sysctl(void) +{ + int command = FTRACE_DISABLE_MCOUNT; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + /* ftraced_suspend is true if ftrace is running */ + if (ftraced_suspend) + command |= FTRACE_DISABLE_CALLS; + + ftrace_run_update_code(command); + mutex_unlock(&ftraced_lock); +} + +static cycle_t ftrace_update_time; +static unsigned long ftrace_update_cnt; +unsigned long ftrace_update_tot_cnt; + +static int __ftrace_update_code(void *ignore) +{ + struct dyn_ftrace *p; + struct hlist_head head; + struct hlist_node *t; + int save_ftrace_enabled; + cycle_t start, stop; + int i; + + /* Don't be recording funcs now */ + save_ftrace_enabled = ftrace_enabled; + ftrace_enabled = 0; + + start = ftrace_now(raw_smp_processor_id()); + ftrace_update_cnt = 0; + + /* No locks needed, the machine is stopped! */ + for (i = 0; i < FTRACE_HASHSIZE; i++) { + if (hlist_empty(&ftrace_hash[i])) + continue; + + head = ftrace_hash[i]; + INIT_HLIST_HEAD(&ftrace_hash[i]); + + /* all CPUS are stopped, we are safe to modify code */ + hlist_for_each_entry(p, t, &head, node) { + ftrace_code_disable(p); + ftrace_update_cnt++; + } + + } + + stop = ftrace_now(raw_smp_processor_id()); + ftrace_update_time = stop - start; + ftrace_update_tot_cnt += ftrace_update_cnt; + + ftrace_enabled = save_ftrace_enabled; + + return 0; +} + +static void ftrace_update_code(void) +{ + if (unlikely(ftrace_disabled)) + return; + + stop_machine_run(__ftrace_update_code, NULL, NR_CPUS); +} + +static int ftraced(void *ignore) +{ + unsigned long usecs; + + while (!kthread_should_stop()) { + + set_current_state(TASK_INTERRUPTIBLE); + + /* check once a second */ + schedule_timeout(HZ); + + if (unlikely(ftrace_disabled)) + continue; + + mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftraced_lock); + if (ftrace_enabled && ftraced_trigger && !ftraced_suspend) { + ftrace_record_suspend++; + ftrace_update_code(); + usecs = nsecs_to_usecs(ftrace_update_time); + if (ftrace_update_tot_cnt > 100000) { + ftrace_update_tot_cnt = 0; + pr_info("hm, dftrace overflow: %lu change%s" + " (%lu total) in %lu usec%s\n", + ftrace_update_cnt, + ftrace_update_cnt != 1 ? "s" : "", + ftrace_update_tot_cnt, + usecs, usecs != 1 ? "s" : ""); + ftrace_disabled = 1; + WARN_ON_ONCE(1); + } + ftraced_trigger = 0; + ftrace_record_suspend--; + } + ftraced_iteration_counter++; + mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_sysctl_lock); + + wake_up_interruptible(&ftraced_waiters); + + ftrace_shutdown_replenish(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +static int __init ftrace_dyn_table_alloc(void) +{ + struct ftrace_page *pg; + int cnt; + int i; + + /* allocate a few pages */ + ftrace_pages_start = (void *)get_zeroed_page(GFP_KERNEL); + if (!ftrace_pages_start) + return -1; + + /* + * Allocate a few more pages. + * + * TODO: have some parser search vmlinux before + * final linking to find all calls to ftrace. + * Then we can: + * a) know how many pages to allocate. + * and/or + * b) set up the table then. + * + * The dynamic code is still necessary for + * modules. + */ + + pg = ftrace_pages = ftrace_pages_start; + + cnt = NR_TO_INIT / ENTRIES_PER_PAGE; + + for (i = 0; i < cnt; i++) { + pg->next = (void *)get_zeroed_page(GFP_KERNEL); + + /* If we fail, we'll try later anyway */ + if (!pg->next) + break; + + pg = pg->next; + } + + return 0; +} + +enum { + FTRACE_ITER_FILTER = (1 << 0), + FTRACE_ITER_CONT = (1 << 1), +}; + +#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ + +struct ftrace_iterator { + loff_t pos; + struct ftrace_page *pg; + unsigned idx; + unsigned flags; + unsigned char buffer[FTRACE_BUFF_MAX+1]; + unsigned buffer_idx; + unsigned filtered; +}; + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + struct dyn_ftrace *rec = NULL; + + (*pos)++; + + retry: + if (iter->idx >= iter->pg->index) { + if (iter->pg->next) { + iter->pg = iter->pg->next; + iter->idx = 0; + goto retry; + } + } else { + rec = &iter->pg->records[iter->idx++]; + if ((rec->flags & FTRACE_FL_FAILED) || + ((iter->flags & FTRACE_ITER_FILTER) && + !(rec->flags & FTRACE_FL_FILTER))) { + rec = NULL; + goto retry; + } + } + + iter->pos = *pos; + + return rec; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + void *p = NULL; + loff_t l = -1; + + if (*pos != iter->pos) { + for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l)) + ; + } else { + l = *pos; + p = t_next(m, p, &l); + } + + return p; +} + +static void t_stop(struct seq_file *m, void *p) +{ +} + +static int t_show(struct seq_file *m, void *v) +{ + struct dyn_ftrace *rec = v; + char str[KSYM_SYMBOL_LEN]; + + if (!rec) + return 0; + + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + + seq_printf(m, "%s\n", str); + + return 0; +} + +static struct seq_operations show_ftrace_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int +ftrace_avail_open(struct inode *inode, struct file *file) +{ + struct ftrace_iterator *iter; + int ret; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + iter->pg = ftrace_pages_start; + iter->pos = -1; + + ret = seq_open(file, &show_ftrace_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + + m->private = iter; + } else { + kfree(iter); + } + + return ret; +} + +int ftrace_avail_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + struct ftrace_iterator *iter = m->private; + + seq_release(inode, file); + kfree(iter); + + return 0; +} + +static void ftrace_filter_reset(void) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec; + unsigned i; + + /* keep kstop machine from running */ + preempt_disable(); + ftrace_filtered = 0; + pg = ftrace_pages_start; + while (pg) { + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + if (rec->flags & FTRACE_FL_FAILED) + continue; + rec->flags &= ~FTRACE_FL_FILTER; + } + pg = pg->next; + } + preempt_enable(); +} + +static int +ftrace_filter_open(struct inode *inode, struct file *file) +{ + struct ftrace_iterator *iter; + int ret = 0; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + mutex_lock(&ftrace_filter_lock); + if ((file->f_mode & FMODE_WRITE) && + !(file->f_flags & O_APPEND)) + ftrace_filter_reset(); + + if (file->f_mode & FMODE_READ) { + iter->pg = ftrace_pages_start; + iter->pos = -1; + iter->flags = FTRACE_ITER_FILTER; + + ret = seq_open(file, &show_ftrace_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = iter; + } else + kfree(iter); + } else + file->private_data = iter; + mutex_unlock(&ftrace_filter_lock); + + return ret; +} + +static ssize_t +ftrace_filter_read(struct file *file, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + if (file->f_mode & FMODE_READ) + return seq_read(file, ubuf, cnt, ppos); + else + return -EPERM; +} + +static loff_t +ftrace_filter_lseek(struct file *file, loff_t offset, int origin) +{ + loff_t ret; + + if (file->f_mode & FMODE_READ) + ret = seq_lseek(file, offset, origin); + else + file->f_pos = ret = 1; + + return ret; +} + +enum { + MATCH_FULL, + MATCH_FRONT_ONLY, + MATCH_MIDDLE_ONLY, + MATCH_END_ONLY, +}; + +static void +ftrace_match(unsigned char *buff, int len) +{ + char str[KSYM_SYMBOL_LEN]; + char *search = NULL; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int type = MATCH_FULL; + unsigned i, match = 0, search_len = 0; + + for (i = 0; i < len; i++) { + if (buff[i] == '*') { + if (!i) { + search = buff + i + 1; + type = MATCH_END_ONLY; + search_len = len - (i + 1); + } else { + if (type == MATCH_END_ONLY) { + type = MATCH_MIDDLE_ONLY; + } else { + match = i; + type = MATCH_FRONT_ONLY; + } + buff[i] = 0; + break; + } + } + } + + /* keep kstop machine from running */ + preempt_disable(); + ftrace_filtered = 1; + pg = ftrace_pages_start; + while (pg) { + for (i = 0; i < pg->index; i++) { + int matched = 0; + char *ptr; + + rec = &pg->records[i]; + if (rec->flags & FTRACE_FL_FAILED) + continue; + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + switch (type) { + case MATCH_FULL: + if (strcmp(str, buff) == 0) + matched = 1; + break; + case MATCH_FRONT_ONLY: + if (memcmp(str, buff, match) == 0) + matched = 1; + break; + case MATCH_MIDDLE_ONLY: + if (strstr(str, search)) + matched = 1; + break; + case MATCH_END_ONLY: + ptr = strstr(str, search); + if (ptr && (ptr[search_len] == 0)) + matched = 1; + break; + } + if (matched) + rec->flags |= FTRACE_FL_FILTER; + } + pg = pg->next; + } + preempt_enable(); +} + +static ssize_t +ftrace_filter_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ftrace_iterator *iter; + char ch; + size_t read = 0; + ssize_t ret; + + if (!cnt || cnt < 0) + return 0; + + mutex_lock(&ftrace_filter_lock); + + if (file->f_mode & FMODE_READ) { + struct seq_file *m = file->private_data; + iter = m->private; + } else + iter = file->private_data; + + if (!*ppos) { + iter->flags &= ~FTRACE_ITER_CONT; + iter->buffer_idx = 0; + } + + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + + if (!(iter->flags & ~FTRACE_ITER_CONT)) { + /* skip white space */ + while (cnt && isspace(ch)) { + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + + if (isspace(ch)) { + file->f_pos += read; + ret = read; + goto out; + } + + iter->buffer_idx = 0; + } + + while (cnt && !isspace(ch)) { + if (iter->buffer_idx < FTRACE_BUFF_MAX) + iter->buffer[iter->buffer_idx++] = ch; + else { + ret = -EINVAL; + goto out; + } + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + if (isspace(ch)) { + iter->filtered++; + iter->buffer[iter->buffer_idx] = 0; + ftrace_match(iter->buffer, iter->buffer_idx); + iter->buffer_idx = 0; + } else + iter->flags |= FTRACE_ITER_CONT; + + + file->f_pos += read; + + ret = read; + out: + mutex_unlock(&ftrace_filter_lock); + + return ret; +} + +/** + * ftrace_set_filter - set a function to filter on in ftrace + * @buf - the string that holds the function filter text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled. + * If @buf is NULL and reset is set, all functions will be enabled for tracing. + */ +void ftrace_set_filter(unsigned char *buf, int len, int reset) +{ + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftrace_filter_lock); + if (reset) + ftrace_filter_reset(); + if (buf) + ftrace_match(buf, len); + mutex_unlock(&ftrace_filter_lock); +} + +static int +ftrace_filter_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + struct ftrace_iterator *iter; + + mutex_lock(&ftrace_filter_lock); + if (file->f_mode & FMODE_READ) { + iter = m->private; + + seq_release(inode, file); + } else + iter = file->private_data; + + if (iter->buffer_idx) { + iter->filtered++; + iter->buffer[iter->buffer_idx] = 0; + ftrace_match(iter->buffer, iter->buffer_idx); + } + + mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftraced_lock); + if (iter->filtered && ftraced_suspend && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_sysctl_lock); + + kfree(iter); + mutex_unlock(&ftrace_filter_lock); + return 0; +} + +static struct file_operations ftrace_avail_fops = { + .open = ftrace_avail_open, + .read = seq_read, + .llseek = seq_lseek, + .release = ftrace_avail_release, +}; + +static struct file_operations ftrace_filter_fops = { + .open = ftrace_filter_open, + .read = ftrace_filter_read, + .write = ftrace_filter_write, + .llseek = ftrace_filter_lseek, + .release = ftrace_filter_release, +}; + +/** + * ftrace_force_update - force an update to all recording ftrace functions + * + * The ftrace dynamic update daemon only wakes up once a second. + * There may be cases where an update needs to be done immediately + * for tests or internal kernel tracing to begin. This function + * wakes the daemon to do an update and will not return until the + * update is complete. + */ +int ftrace_force_update(void) +{ + unsigned long last_counter; + DECLARE_WAITQUEUE(wait, current); + int ret = 0; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + mutex_lock(&ftraced_lock); + last_counter = ftraced_iteration_counter; + + set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&ftraced_waiters, &wait); + + if (unlikely(!ftraced_task)) { + ret = -ENODEV; + goto out; + } + + do { + mutex_unlock(&ftraced_lock); + wake_up_process(ftraced_task); + schedule(); + mutex_lock(&ftraced_lock); + if (signal_pending(current)) { + ret = -EINTR; + break; + } + set_current_state(TASK_INTERRUPTIBLE); + } while (last_counter == ftraced_iteration_counter); + + out: + mutex_unlock(&ftraced_lock); + remove_wait_queue(&ftraced_waiters, &wait); + set_current_state(TASK_RUNNING); + + return ret; +} + +static void ftrace_force_shutdown(void) +{ + struct task_struct *task; + int command = FTRACE_DISABLE_CALLS | FTRACE_UPDATE_TRACE_FUNC; + + mutex_lock(&ftraced_lock); + task = ftraced_task; + ftraced_task = NULL; + ftraced_suspend = -1; + ftrace_run_update_code(command); + mutex_unlock(&ftraced_lock); + + if (task) + kthread_stop(task); +} + +static __init int ftrace_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("available_filter_functions", 0444, + d_tracer, NULL, &ftrace_avail_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'available_filter_functions' entry\n"); + + entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer, + NULL, &ftrace_filter_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'set_ftrace_filter' entry\n"); + return 0; +} + +fs_initcall(ftrace_init_debugfs); + +static int __init ftrace_dynamic_init(void) +{ + struct task_struct *p; + unsigned long addr; + int ret; + + addr = (unsigned long)ftrace_record_ip; + + stop_machine_run(ftrace_dyn_arch_init, &addr, NR_CPUS); + + /* ftrace_dyn_arch_init places the return code in addr */ + if (addr) { + ret = (int)addr; + goto failed; + } + + ret = ftrace_dyn_table_alloc(); + if (ret) + goto failed; + + p = kthread_run(ftraced, NULL, "ftraced"); + if (IS_ERR(p)) { + ret = -1; + goto failed; + } + + last_ftrace_enabled = ftrace_enabled = 1; + ftraced_task = p; + + return 0; + + failed: + ftrace_disabled = 1; + return ret; +} + +core_initcall(ftrace_dynamic_init); +#else +# define ftrace_startup() do { } while (0) +# define ftrace_shutdown() do { } while (0) +# define ftrace_startup_sysctl() do { } while (0) +# define ftrace_shutdown_sysctl() do { } while (0) +# define ftrace_force_shutdown() do { } while (0) +#endif /* CONFIG_DYNAMIC_FTRACE */ + +/** + * ftrace_kill - totally shutdown ftrace + * + * This is a safety measure. If something was detected that seems + * wrong, calling this function will keep ftrace from doing + * any more modifications, and updates. + * used when something went wrong. + */ +void ftrace_kill(void) +{ + mutex_lock(&ftrace_sysctl_lock); + ftrace_disabled = 1; + ftrace_enabled = 0; + + clear_ftrace_function(); + mutex_unlock(&ftrace_sysctl_lock); + + /* Try to totally disable ftrace */ + ftrace_force_shutdown(); +} + +/** + * register_ftrace_function - register a function for profiling + * @ops - ops structure that holds the function for profiling. + * + * Register a function to be called by all functions in the + * kernel. + * + * Note: @ops->func and all the functions it calls must be labeled + * with "notrace", otherwise it will go into a + * recursive loop. + */ +int register_ftrace_function(struct ftrace_ops *ops) +{ + int ret; + + if (unlikely(ftrace_disabled)) + return -1; + + mutex_lock(&ftrace_sysctl_lock); + ret = __register_ftrace_function(ops); + ftrace_startup(); + mutex_unlock(&ftrace_sysctl_lock); + + return ret; +} + +/** + * unregister_ftrace_function - unresgister a function for profiling. + * @ops - ops structure that holds the function to unregister + * + * Unregister a function that was added to be called by ftrace profiling. + */ +int unregister_ftrace_function(struct ftrace_ops *ops) +{ + int ret; + + mutex_lock(&ftrace_sysctl_lock); + ret = __unregister_ftrace_function(ops); + ftrace_shutdown(); + mutex_unlock(&ftrace_sysctl_lock); + + return ret; +} + +int +ftrace_enable_sysctl(struct ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + mutex_lock(&ftrace_sysctl_lock); + + ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + + if (ret || !write || (last_ftrace_enabled == ftrace_enabled)) + goto out; + + last_ftrace_enabled = ftrace_enabled; + + if (ftrace_enabled) { + + ftrace_startup_sysctl(); + + /* we are starting ftrace again */ + if (ftrace_list != &ftrace_list_end) { + if (ftrace_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_list->func; + else + ftrace_trace_function = ftrace_list_func; + } + + } else { + /* stopping ftrace calls (just send to ftrace_stub) */ + ftrace_trace_function = ftrace_stub; + + ftrace_shutdown_sysctl(); + } + + out: + mutex_unlock(&ftrace_sysctl_lock); + return ret; +} diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c new file mode 100644 index 000000000000..95b7c48a9a1d --- /dev/null +++ b/kernel/trace/trace.c @@ -0,0 +1,3034 @@ +/* + * ring buffer based function tracer + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * Originally taken from the RT patch by: + * Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Based on code from the latency_tracer, that is: + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/utsrelease.h> +#include <linux/kallsyms.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/pagemap.h> +#include <linux/hardirq.h> +#include <linux/linkage.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/poll.h> +#include <linux/gfp.h> +#include <linux/fs.h> +#include <linux/writeback.h> + +#include <linux/stacktrace.h> + +#include "trace.h" + +unsigned long __read_mostly tracing_max_latency = (cycle_t)ULONG_MAX; +unsigned long __read_mostly tracing_thresh; + +static unsigned long __read_mostly tracing_nr_buffers; +static cpumask_t __read_mostly tracing_buffer_mask; + +#define for_each_tracing_cpu(cpu) \ + for_each_cpu_mask(cpu, tracing_buffer_mask) + +/* dummy trace to disable tracing */ +static struct tracer no_tracer __read_mostly = { + .name = "none", +}; + +static int trace_alloc_page(void); +static int trace_free_page(void); + +static int tracing_disabled = 1; + +static unsigned long tracing_pages_allocated; + +long +ns2usecs(cycle_t nsec) +{ + nsec += 500; + do_div(nsec, 1000); + return nsec; +} + +cycle_t ftrace_now(int cpu) +{ + return cpu_clock(cpu); +} + +/* + * The global_trace is the descriptor that holds the tracing + * buffers for the live tracing. For each CPU, it contains + * a link list of pages that will store trace entries. The + * page descriptor of the pages in the memory is used to hold + * the link list by linking the lru item in the page descriptor + * to each of the pages in the buffer per CPU. + * + * For each active CPU there is a data field that holds the + * pages for the buffer for that CPU. Each CPU has the same number + * of pages allocated for its buffer. + */ +static struct trace_array global_trace; + +static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); + +/* + * The max_tr is used to snapshot the global_trace when a maximum + * latency is reached. Some tracers will use this to store a maximum + * trace while it continues examining live traces. + * + * The buffers for the max_tr are set up the same as the global_trace. + * When a snapshot is taken, the link list of the max_tr is swapped + * with the link list of the global_trace and the buffers are reset for + * the global_trace so the tracing can continue. + */ +static struct trace_array max_tr; + +static DEFINE_PER_CPU(struct trace_array_cpu, max_data); + +/* tracer_enabled is used to toggle activation of a tracer */ +static int tracer_enabled = 1; + +/* + * trace_nr_entries is the number of entries that is allocated + * for a buffer. Note, the number of entries is always rounded + * to ENTRIES_PER_PAGE. + */ +static unsigned long trace_nr_entries = 65536UL; + +/* trace_types holds a link list of available tracers. */ +static struct tracer *trace_types __read_mostly; + +/* current_trace points to the tracer that is currently active */ +static struct tracer *current_trace __read_mostly; + +/* + * max_tracer_type_len is used to simplify the allocating of + * buffers to read userspace tracer names. We keep track of + * the longest tracer name registered. + */ +static int max_tracer_type_len; + +/* + * trace_types_lock is used to protect the trace_types list. + * This lock is also used to keep user access serialized. + * Accesses from userspace will grab this lock while userspace + * activities happen inside the kernel. + */ +static DEFINE_MUTEX(trace_types_lock); + +/* trace_wait is a waitqueue for tasks blocked on trace_poll */ +static DECLARE_WAIT_QUEUE_HEAD(trace_wait); + +/* trace_flags holds iter_ctrl options */ +unsigned long trace_flags = TRACE_ITER_PRINT_PARENT; + +/** + * trace_wake_up - wake up tasks waiting for trace input + * + * Simply wakes up any task that is blocked on the trace_wait + * queue. These is used with trace_poll for tasks polling the trace. + */ +void trace_wake_up(void) +{ + /* + * The runqueue_is_locked() can fail, but this is the best we + * have for now: + */ + if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked()) + wake_up(&trace_wait); +} + +#define ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(struct trace_entry)) + +static int __init set_nr_entries(char *str) +{ + unsigned long nr_entries; + int ret; + + if (!str) + return 0; + ret = strict_strtoul(str, 0, &nr_entries); + /* nr_entries can not be zero */ + if (ret < 0 || nr_entries == 0) + return 0; + trace_nr_entries = nr_entries; + return 1; +} +__setup("trace_entries=", set_nr_entries); + +unsigned long nsecs_to_usecs(unsigned long nsecs) +{ + return nsecs / 1000; +} + +/* + * trace_flag_type is an enumeration that holds different + * states when a trace occurs. These are: + * IRQS_OFF - interrupts were disabled + * NEED_RESCED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler + */ +enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, + TRACE_FLAG_NEED_RESCHED = 0x02, + TRACE_FLAG_HARDIRQ = 0x04, + TRACE_FLAG_SOFTIRQ = 0x08, +}; + +/* + * TRACE_ITER_SYM_MASK masks the options in trace_flags that + * control the output of kernel symbols. + */ +#define TRACE_ITER_SYM_MASK \ + (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR) + +/* These must match the bit postions in trace_iterator_flags */ +static const char *trace_options[] = { + "print-parent", + "sym-offset", + "sym-addr", + "verbose", + "raw", + "hex", + "bin", + "block", + "stacktrace", + "sched-tree", + NULL +}; + +/* + * ftrace_max_lock is used to protect the swapping of buffers + * when taking a max snapshot. The buffers themselves are + * protected by per_cpu spinlocks. But the action of the swap + * needs its own lock. + * + * This is defined as a raw_spinlock_t in order to help + * with performance when lockdep debugging is enabled. + */ +static raw_spinlock_t ftrace_max_lock = + (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + +/* + * Copy the new maximum trace into the separate maximum-trace + * structure. (this way the maximum trace is permanently saved, + * for later retrieval via /debugfs/tracing/latency_trace) + */ +static void +__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_array_cpu *data = tr->data[cpu]; + + max_tr.cpu = cpu; + max_tr.time_start = data->preempt_timestamp; + + data = max_tr.data[cpu]; + data->saved_latency = tracing_max_latency; + + memcpy(data->comm, tsk->comm, TASK_COMM_LEN); + data->pid = tsk->pid; + data->uid = tsk->uid; + data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; + data->policy = tsk->policy; + data->rt_priority = tsk->rt_priority; + + /* record this tasks comm */ + tracing_record_cmdline(current); +} + +/** + * check_pages - integrity check of trace buffers + * + * As a safty measure we check to make sure the data pages have not + * been corrupted. TODO: configure to disable this because it adds + * a bit of overhead. + */ +void check_pages(struct trace_array_cpu *data) +{ + struct page *page, *tmp; + + BUG_ON(data->trace_pages.next->prev != &data->trace_pages); + BUG_ON(data->trace_pages.prev->next != &data->trace_pages); + + list_for_each_entry_safe(page, tmp, &data->trace_pages, lru) { + BUG_ON(page->lru.next->prev != &page->lru); + BUG_ON(page->lru.prev->next != &page->lru); + } +} + +/** + * head_page - page address of the first page in per_cpu buffer. + * + * head_page returns the page address of the first page in + * a per_cpu buffer. This also preforms various consistency + * checks to make sure the buffer has not been corrupted. + */ +void *head_page(struct trace_array_cpu *data) +{ + struct page *page; + + check_pages(data); + if (list_empty(&data->trace_pages)) + return NULL; + + page = list_entry(data->trace_pages.next, struct page, lru); + BUG_ON(&page->lru == &data->trace_pages); + + return page_address(page); +} + +/** + * trace_seq_printf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +int +trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +{ + int len = (PAGE_SIZE - 1) - s->len; + va_list ap; + int ret; + + if (!len) + return 0; + + va_start(ap, fmt); + ret = vsnprintf(s->buffer + s->len, len, fmt, ap); + va_end(ap); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) + return 0; + + s->len += ret; + + return len; +} + +/** + * trace_seq_puts - trace sequence printing of simple string + * @s: trace sequence descriptor + * @str: simple string to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple string + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + */ +static int +trace_seq_puts(struct trace_seq *s, const char *str) +{ + int len = strlen(str); + + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, str, len); + s->len += len; + + return len; +} + +static int +trace_seq_putc(struct trace_seq *s, unsigned char c) +{ + if (s->len >= (PAGE_SIZE - 1)) + return 0; + + s->buffer[s->len++] = c; + + return 1; +} + +static int +trace_seq_putmem(struct trace_seq *s, void *mem, size_t len) +{ + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, mem, len); + s->len += len; + + return len; +} + +#define HEX_CHARS 17 +static const char hex2asc[] = "0123456789abcdef"; + +static int +trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) +{ + unsigned char hex[HEX_CHARS]; + unsigned char *data = mem; + unsigned char byte; + int i, j; + + BUG_ON(len >= HEX_CHARS); + +#ifdef __BIG_ENDIAN + for (i = 0, j = 0; i < len; i++) { +#else + for (i = len-1, j = 0; i >= 0; i--) { +#endif + byte = data[i]; + + hex[j++] = hex2asc[byte & 0x0f]; + hex[j++] = hex2asc[byte >> 4]; + } + hex[j++] = ' '; + + return trace_seq_putmem(s, hex, j); +} + +static void +trace_seq_reset(struct trace_seq *s) +{ + s->len = 0; + s->readpos = 0; +} + +ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) +{ + int len; + int ret; + + if (s->len <= s->readpos) + return -EBUSY; + + len = s->len - s->readpos; + if (cnt > len) + cnt = len; + ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); + if (ret) + return -EFAULT; + + s->readpos += len; + return cnt; +} + +static void +trace_print_seq(struct seq_file *m, struct trace_seq *s) +{ + int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len; + + s->buffer[len] = 0; + seq_puts(m, s->buffer); + + trace_seq_reset(s); +} + +/* + * flip the trace buffers between two trace descriptors. + * This usually is the buffers between the global_trace and + * the max_tr to record a snapshot of a current trace. + * + * The ftrace_max_lock must be held. + */ +static void +flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2) +{ + struct list_head flip_pages; + + INIT_LIST_HEAD(&flip_pages); + + memcpy(&tr1->trace_head_idx, &tr2->trace_head_idx, + sizeof(struct trace_array_cpu) - + offsetof(struct trace_array_cpu, trace_head_idx)); + + check_pages(tr1); + check_pages(tr2); + list_splice_init(&tr1->trace_pages, &flip_pages); + list_splice_init(&tr2->trace_pages, &tr1->trace_pages); + list_splice_init(&flip_pages, &tr2->trace_pages); + BUG_ON(!list_empty(&flip_pages)); + check_pages(tr1); + check_pages(tr2); +} + +/** + * update_max_tr - snapshot all trace buffers from global_trace to max_tr + * @tr: tracer + * @tsk: the task with the latency + * @cpu: The cpu that initiated the trace. + * + * Flip the buffers between the @tr and the max_tr and record information + * about which task was the cause of this latency. + */ +void +update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_array_cpu *data; + int i; + + WARN_ON_ONCE(!irqs_disabled()); + __raw_spin_lock(&ftrace_max_lock); + /* clear out all the previous traces */ + for_each_tracing_cpu(i) { + data = tr->data[i]; + flip_trace(max_tr.data[i], data); + tracing_reset(data); + } + + __update_max_tr(tr, tsk, cpu); + __raw_spin_unlock(&ftrace_max_lock); +} + +/** + * update_max_tr_single - only copy one trace over, and reset the rest + * @tr - tracer + * @tsk - task with the latency + * @cpu - the cpu of the buffer to copy. + * + * Flip the trace of a single CPU buffer between the @tr and the max_tr. + */ +void +update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_array_cpu *data = tr->data[cpu]; + int i; + + WARN_ON_ONCE(!irqs_disabled()); + __raw_spin_lock(&ftrace_max_lock); + for_each_tracing_cpu(i) + tracing_reset(max_tr.data[i]); + + flip_trace(max_tr.data[cpu], data); + tracing_reset(data); + + __update_max_tr(tr, tsk, cpu); + __raw_spin_unlock(&ftrace_max_lock); +} + +/** + * register_tracer - register a tracer with the ftrace system. + * @type - the plugin for the tracer + * + * Register a new plugin tracer. + */ +int register_tracer(struct tracer *type) +{ + struct tracer *t; + int len; + int ret = 0; + + if (!type->name) { + pr_info("Tracer must have a name\n"); + return -1; + } + + mutex_lock(&trace_types_lock); + for (t = trace_types; t; t = t->next) { + if (strcmp(type->name, t->name) == 0) { + /* already found */ + pr_info("Trace %s already registered\n", + type->name); + ret = -1; + goto out; + } + } + +#ifdef CONFIG_FTRACE_STARTUP_TEST + if (type->selftest) { + struct tracer *saved_tracer = current_trace; + struct trace_array_cpu *data; + struct trace_array *tr = &global_trace; + int saved_ctrl = tr->ctrl; + int i; + /* + * Run a selftest on this tracer. + * Here we reset the trace buffer, and set the current + * tracer to be this tracer. The tracer can then run some + * internal tracing to verify that everything is in order. + * If we fail, we do not register this tracer. + */ + for_each_tracing_cpu(i) { + data = tr->data[i]; + if (!head_page(data)) + continue; + tracing_reset(data); + } + current_trace = type; + tr->ctrl = 0; + /* the test is responsible for initializing and enabling */ + pr_info("Testing tracer %s: ", type->name); + ret = type->selftest(type, tr); + /* the test is responsible for resetting too */ + current_trace = saved_tracer; + tr->ctrl = saved_ctrl; + if (ret) { + printk(KERN_CONT "FAILED!\n"); + goto out; + } + /* Only reset on passing, to avoid touching corrupted buffers */ + for_each_tracing_cpu(i) { + data = tr->data[i]; + if (!head_page(data)) + continue; + tracing_reset(data); + } + printk(KERN_CONT "PASSED\n"); + } +#endif + + type->next = trace_types; + trace_types = type; + len = strlen(type->name); + if (len > max_tracer_type_len) + max_tracer_type_len = len; + + out: + mutex_unlock(&trace_types_lock); + + return ret; +} + +void unregister_tracer(struct tracer *type) +{ + struct tracer **t; + int len; + + mutex_lock(&trace_types_lock); + for (t = &trace_types; *t; t = &(*t)->next) { + if (*t == type) + goto found; + } + pr_info("Trace %s not registered\n", type->name); + goto out; + + found: + *t = (*t)->next; + if (strlen(type->name) != max_tracer_type_len) + goto out; + + max_tracer_type_len = 0; + for (t = &trace_types; *t; t = &(*t)->next) { + len = strlen((*t)->name); + if (len > max_tracer_type_len) + max_tracer_type_len = len; + } + out: + mutex_unlock(&trace_types_lock); +} + +void tracing_reset(struct trace_array_cpu *data) +{ + data->trace_idx = 0; + data->overrun = 0; + data->trace_head = data->trace_tail = head_page(data); + data->trace_head_idx = 0; + data->trace_tail_idx = 0; +} + +#define SAVED_CMDLINES 128 +static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; +static unsigned map_cmdline_to_pid[SAVED_CMDLINES]; +static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN]; +static int cmdline_idx; +static DEFINE_SPINLOCK(trace_cmdline_lock); + +/* trace in all context switches */ +atomic_t trace_record_cmdline_enabled __read_mostly; + +/* temporary disable recording */ +atomic_t trace_record_cmdline_disabled __read_mostly; + +static void trace_init_cmdlines(void) +{ + memset(&map_pid_to_cmdline, -1, sizeof(map_pid_to_cmdline)); + memset(&map_cmdline_to_pid, -1, sizeof(map_cmdline_to_pid)); + cmdline_idx = 0; +} + +void trace_stop_cmdline_recording(void); + +static void trace_save_cmdline(struct task_struct *tsk) +{ + unsigned map; + unsigned idx; + + if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) + return; + + /* + * It's not the end of the world if we don't get + * the lock, but we also don't want to spin + * nor do we want to disable interrupts, + * so if we miss here, then better luck next time. + */ + if (!spin_trylock(&trace_cmdline_lock)) + return; + + idx = map_pid_to_cmdline[tsk->pid]; + if (idx >= SAVED_CMDLINES) { + idx = (cmdline_idx + 1) % SAVED_CMDLINES; + + map = map_cmdline_to_pid[idx]; + if (map <= PID_MAX_DEFAULT) + map_pid_to_cmdline[map] = (unsigned)-1; + + map_pid_to_cmdline[tsk->pid] = idx; + + cmdline_idx = idx; + } + + memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN); + + spin_unlock(&trace_cmdline_lock); +} + +static char *trace_find_cmdline(int pid) +{ + char *cmdline = "<...>"; + unsigned map; + + if (!pid) + return "<idle>"; + + if (pid > PID_MAX_DEFAULT) + goto out; + + map = map_pid_to_cmdline[pid]; + if (map >= SAVED_CMDLINES) + goto out; + + cmdline = saved_cmdlines[map]; + + out: + return cmdline; +} + +void tracing_record_cmdline(struct task_struct *tsk) +{ + if (atomic_read(&trace_record_cmdline_disabled)) + return; + + trace_save_cmdline(tsk); +} + +static inline struct list_head * +trace_next_list(struct trace_array_cpu *data, struct list_head *next) +{ + /* + * Roundrobin - but skip the head (which is not a real page): + */ + next = next->next; + if (unlikely(next == &data->trace_pages)) + next = next->next; + BUG_ON(next == &data->trace_pages); + + return next; +} + +static inline void * +trace_next_page(struct trace_array_cpu *data, void *addr) +{ + struct list_head *next; + struct page *page; + + page = virt_to_page(addr); + + next = trace_next_list(data, &page->lru); + page = list_entry(next, struct page, lru); + + return page_address(page); +} + +static inline struct trace_entry * +tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data) +{ + unsigned long idx, idx_next; + struct trace_entry *entry; + + data->trace_idx++; + idx = data->trace_head_idx; + idx_next = idx + 1; + + BUG_ON(idx * TRACE_ENTRY_SIZE >= PAGE_SIZE); + + entry = data->trace_head + idx * TRACE_ENTRY_SIZE; + + if (unlikely(idx_next >= ENTRIES_PER_PAGE)) { + data->trace_head = trace_next_page(data, data->trace_head); + idx_next = 0; + } + + if (data->trace_head == data->trace_tail && + idx_next == data->trace_tail_idx) { + /* overrun */ + data->overrun++; + data->trace_tail_idx++; + if (data->trace_tail_idx >= ENTRIES_PER_PAGE) { + data->trace_tail = + trace_next_page(data, data->trace_tail); + data->trace_tail_idx = 0; + } + } + + data->trace_head_idx = idx_next; + + return entry; +} + +static inline void +tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags) +{ + struct task_struct *tsk = current; + unsigned long pc; + + pc = preempt_count(); + + entry->preempt_count = pc & 0xff; + entry->pid = (tsk) ? tsk->pid : 0; + entry->t = ftrace_now(raw_smp_processor_id()); + entry->flags = (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | + (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); +} + +void +trace_function(struct trace_array *tr, struct trace_array_cpu *data, + unsigned long ip, unsigned long parent_ip, unsigned long flags) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_FN; + entry->fn.ip = ip; + entry->fn.parent_ip = parent_ip; + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); +} + +void +ftrace(struct trace_array *tr, struct trace_array_cpu *data, + unsigned long ip, unsigned long parent_ip, unsigned long flags) +{ + if (likely(!atomic_read(&data->disabled))) + trace_function(tr, data, ip, parent_ip, flags); +} + +void __trace_stack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, + int skip) +{ + struct trace_entry *entry; + struct stack_trace trace; + + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; + + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_STACK; + + memset(&entry->stack, 0, sizeof(entry->stack)); + + trace.nr_entries = 0; + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.skip = skip; + trace.entries = entry->stack.caller; + + save_stack_trace(&trace); +} + +void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ + struct trace_array_cpu *data = __data; + struct trace_array *tr = __tr; + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, 0); + entry->type = TRACE_SPECIAL; + entry->special.arg1 = arg1; + entry->special.arg2 = arg2; + entry->special.arg3 = arg3; + __trace_stack(tr, data, irq_flags, 4); + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); + + trace_wake_up(); +} + +void +tracing_sched_switch_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *prev, + struct task_struct *next, + unsigned long flags) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_CTX; + entry->ctx.prev_pid = prev->pid; + entry->ctx.prev_prio = prev->prio; + entry->ctx.prev_state = prev->state; + entry->ctx.next_pid = next->pid; + entry->ctx.next_prio = next->prio; + entry->ctx.next_state = next->state; + __trace_stack(tr, data, flags, 5); + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); +} + +void +tracing_sched_wakeup_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *wakee, + struct task_struct *curr, + unsigned long flags) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_WAKE; + entry->ctx.prev_pid = curr->pid; + entry->ctx.prev_prio = curr->prio; + entry->ctx.prev_state = curr->state; + entry->ctx.next_pid = wakee->pid; + entry->ctx.next_prio = wakee->prio; + entry->ctx.next_state = wakee->state; + __trace_stack(tr, data, flags, 6); + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); + + trace_wake_up(); +} + +#ifdef CONFIG_FTRACE +static void +function_trace_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + if (unlikely(!tracer_enabled)) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + trace_function(tr, data, ip, parent_ip, flags); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = function_trace_call, +}; + +void tracing_start_function_trace(void) +{ + register_ftrace_function(&trace_ops); +} + +void tracing_stop_function_trace(void) +{ + unregister_ftrace_function(&trace_ops); +} +#endif + +enum trace_file_type { + TRACE_FILE_LAT_FMT = 1, +}; + +static struct trace_entry * +trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data, + struct trace_iterator *iter, int cpu) +{ + struct page *page; + struct trace_entry *array; + + if (iter->next_idx[cpu] >= tr->entries || + iter->next_idx[cpu] >= data->trace_idx || + (data->trace_head == data->trace_tail && + data->trace_head_idx == data->trace_tail_idx)) + return NULL; + + if (!iter->next_page[cpu]) { + /* Initialize the iterator for this cpu trace buffer */ + WARN_ON(!data->trace_tail); + page = virt_to_page(data->trace_tail); + iter->next_page[cpu] = &page->lru; + iter->next_page_idx[cpu] = data->trace_tail_idx; + } + + page = list_entry(iter->next_page[cpu], struct page, lru); + BUG_ON(&data->trace_pages == &page->lru); + + array = page_address(page); + + WARN_ON(iter->next_page_idx[cpu] >= ENTRIES_PER_PAGE); + return &array[iter->next_page_idx[cpu]]; +} + +static struct trace_entry * +find_next_entry(struct trace_iterator *iter, int *ent_cpu) +{ + struct trace_array *tr = iter->tr; + struct trace_entry *ent, *next = NULL; + int next_cpu = -1; + int cpu; + + for_each_tracing_cpu(cpu) { + if (!head_page(tr->data[cpu])) + continue; + ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu); + /* + * Pick the entry with the smallest timestamp: + */ + if (ent && (!next || ent->t < next->t)) { + next = ent; + next_cpu = cpu; + } + } + + if (ent_cpu) + *ent_cpu = next_cpu; + + return next; +} + +static void trace_iterator_increment(struct trace_iterator *iter) +{ + iter->idx++; + iter->next_idx[iter->cpu]++; + iter->next_page_idx[iter->cpu]++; + + if (iter->next_page_idx[iter->cpu] >= ENTRIES_PER_PAGE) { + struct trace_array_cpu *data = iter->tr->data[iter->cpu]; + + iter->next_page_idx[iter->cpu] = 0; + iter->next_page[iter->cpu] = + trace_next_list(data, iter->next_page[iter->cpu]); + } +} + +static void trace_consume(struct trace_iterator *iter) +{ + struct trace_array_cpu *data = iter->tr->data[iter->cpu]; + + data->trace_tail_idx++; + if (data->trace_tail_idx >= ENTRIES_PER_PAGE) { + data->trace_tail = trace_next_page(data, data->trace_tail); + data->trace_tail_idx = 0; + } + + /* Check if we empty it, then reset the index */ + if (data->trace_head == data->trace_tail && + data->trace_head_idx == data->trace_tail_idx) + data->trace_idx = 0; +} + +static void *find_next_entry_inc(struct trace_iterator *iter) +{ + struct trace_entry *next; + int next_cpu = -1; + + next = find_next_entry(iter, &next_cpu); + + iter->prev_ent = iter->ent; + iter->prev_cpu = iter->cpu; + + iter->ent = next; + iter->cpu = next_cpu; + + if (next) + trace_iterator_increment(iter); + + return next ? iter : NULL; +} + +static void *s_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct trace_iterator *iter = m->private; + void *last_ent = iter->ent; + int i = (int)*pos; + void *ent; + + (*pos)++; + + /* can't go backwards */ + if (iter->idx > i) + return NULL; + + if (iter->idx < 0) + ent = find_next_entry_inc(iter); + else + ent = iter; + + while (ent && iter->idx < i) + ent = find_next_entry_inc(iter); + + iter->pos = *pos; + + if (last_ent && !ent) + seq_puts(m, "\n\nvim:ft=help\n"); + + return ent; +} + +static void *s_start(struct seq_file *m, loff_t *pos) +{ + struct trace_iterator *iter = m->private; + void *p = NULL; + loff_t l = 0; + int i; + + mutex_lock(&trace_types_lock); + + if (!current_trace || current_trace != iter->trace) { + mutex_unlock(&trace_types_lock); + return NULL; + } + + atomic_inc(&trace_record_cmdline_disabled); + + /* let the tracer grab locks here if needed */ + if (current_trace->start) + current_trace->start(iter); + + if (*pos != iter->pos) { + iter->ent = NULL; + iter->cpu = 0; + iter->idx = -1; + iter->prev_ent = NULL; + iter->prev_cpu = -1; + + for_each_tracing_cpu(i) { + iter->next_idx[i] = 0; + iter->next_page[i] = NULL; + } + + for (p = iter; p && l < *pos; p = s_next(m, p, &l)) + ; + + } else { + l = *pos - 1; + p = s_next(m, p, &l); + } + + return p; +} + +static void s_stop(struct seq_file *m, void *p) +{ + struct trace_iterator *iter = m->private; + + atomic_dec(&trace_record_cmdline_disabled); + + /* let the tracer release locks here if needed */ + if (current_trace && current_trace == iter->trace && iter->trace->stop) + iter->trace->stop(iter); + + mutex_unlock(&trace_types_lock); +} + +static int +seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + + kallsyms_lookup(address, NULL, NULL, NULL, str); + + return trace_seq_printf(s, fmt, str); +#endif + return 1; +} + +static int +seq_print_sym_offset(struct trace_seq *s, const char *fmt, + unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + + sprint_symbol(str, address); + return trace_seq_printf(s, fmt, str); +#endif + return 1; +} + +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + +static int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) +{ + int ret; + + if (!ip) + return trace_seq_printf(s, "0"); + + if (sym_flags & TRACE_ITER_SYM_OFFSET) + ret = seq_print_sym_offset(s, "%s", ip); + else + ret = seq_print_sym_short(s, "%s", ip); + + if (!ret) + return 0; + + if (sym_flags & TRACE_ITER_SYM_ADDR) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +static void print_lat_help_header(struct seq_file *m) +{ + seq_puts(m, "# _------=> CPU# \n"); + seq_puts(m, "# / _-----=> irqs-off \n"); + seq_puts(m, "# | / _----=> need-resched \n"); + seq_puts(m, "# || / _---=> hardirq/softirq \n"); + seq_puts(m, "# ||| / _--=> preempt-depth \n"); + seq_puts(m, "# |||| / \n"); + seq_puts(m, "# ||||| delay \n"); + seq_puts(m, "# cmd pid ||||| time | caller \n"); + seq_puts(m, "# \\ / ||||| \\ | / \n"); +} + +static void print_func_help_header(struct seq_file *m) +{ + seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | | |\n"); +} + + +static void +print_trace_header(struct seq_file *m, struct trace_iterator *iter) +{ + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_array *tr = iter->tr; + struct trace_array_cpu *data = tr->data[tr->cpu]; + struct tracer *type = current_trace; + unsigned long total = 0; + unsigned long entries = 0; + int cpu; + const char *name = "preemption"; + + if (type) + name = type->name; + + for_each_tracing_cpu(cpu) { + if (head_page(tr->data[cpu])) { + total += tr->data[cpu]->trace_idx; + if (tr->data[cpu]->trace_idx > tr->entries) + entries += tr->entries; + else + entries += tr->data[cpu]->trace_idx; + } + } + + seq_printf(m, "%s latency trace v1.1.5 on %s\n", + name, UTS_RELEASE); + seq_puts(m, "-----------------------------------" + "---------------------------------\n"); + seq_printf(m, " latency: %lu us, #%lu/%lu, CPU#%d |" + " (M:%s VP:%d, KP:%d, SP:%d HP:%d", + nsecs_to_usecs(data->saved_latency), + entries, + total, + tr->cpu, +#if defined(CONFIG_PREEMPT_NONE) + "server", +#elif defined(CONFIG_PREEMPT_VOLUNTARY) + "desktop", +#elif defined(CONFIG_PREEMPT_DESKTOP) + "preempt", +#else + "unknown", +#endif + /* These are reserved for later use */ + 0, 0, 0, 0); +#ifdef CONFIG_SMP + seq_printf(m, " #P:%d)\n", num_online_cpus()); +#else + seq_puts(m, ")\n"); +#endif + seq_puts(m, " -----------------\n"); + seq_printf(m, " | task: %.16s-%d " + "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", + data->comm, data->pid, data->uid, data->nice, + data->policy, data->rt_priority); + seq_puts(m, " -----------------\n"); + + if (data->critical_start) { + seq_puts(m, " => started at: "); + seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags); + trace_print_seq(m, &iter->seq); + seq_puts(m, "\n => ended at: "); + seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); + trace_print_seq(m, &iter->seq); + seq_puts(m, "\n"); + } + + seq_puts(m, "\n"); +} + +static void +lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) +{ + int hardirq, softirq; + char *comm; + + comm = trace_find_cmdline(entry->pid); + + trace_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid); + trace_seq_printf(s, "%d", cpu); + trace_seq_printf(s, "%c%c", + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.', + ((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.')); + + hardirq = entry->flags & TRACE_FLAG_HARDIRQ; + softirq = entry->flags & TRACE_FLAG_SOFTIRQ; + if (hardirq && softirq) { + trace_seq_putc(s, 'H'); + } else { + if (hardirq) { + trace_seq_putc(s, 'h'); + } else { + if (softirq) + trace_seq_putc(s, 's'); + else + trace_seq_putc(s, '.'); + } + } + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_puts(s, "."); +} + +unsigned long preempt_mark_thresh = 100; + +static void +lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs, + unsigned long rel_usecs) +{ + trace_seq_printf(s, " %4lldus", abs_usecs); + if (rel_usecs > preempt_mark_thresh) + trace_seq_puts(s, "!: "); + else if (rel_usecs > 1) + trace_seq_puts(s, "+: "); + else + trace_seq_puts(s, " : "); +} + +static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + +static int +print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) +{ + struct trace_seq *s = &iter->seq; + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_entry *next_entry = find_next_entry(iter, NULL); + unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); + struct trace_entry *entry = iter->ent; + unsigned long abs_usecs; + unsigned long rel_usecs; + char *comm; + int S, T; + int i; + unsigned state; + + if (!next_entry) + next_entry = entry; + rel_usecs = ns2usecs(next_entry->t - entry->t); + abs_usecs = ns2usecs(entry->t - iter->tr->time_start); + + if (verbose) { + comm = trace_find_cmdline(entry->pid); + trace_seq_printf(s, "%16s %5d %d %d %08x %08x [%08lx]" + " %ld.%03ldms (+%ld.%03ldms): ", + comm, + entry->pid, cpu, entry->flags, + entry->preempt_count, trace_idx, + ns2usecs(entry->t), + abs_usecs/1000, + abs_usecs % 1000, rel_usecs/1000, + rel_usecs % 1000); + } else { + lat_print_generic(s, entry, cpu); + lat_print_timestamp(s, abs_usecs, rel_usecs); + } + switch (entry->type) { + case TRACE_FN: + seq_print_ip_sym(s, entry->fn.ip, sym_flags); + trace_seq_puts(s, " ("); + seq_print_ip_sym(s, entry->fn.parent_ip, sym_flags); + trace_seq_puts(s, ")\n"); + break; + case TRACE_CTX: + case TRACE_WAKE: + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + + state = entry->ctx.prev_state ? __ffs(entry->ctx.prev_state) + 1 : 0; + S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X'; + comm = trace_find_cmdline(entry->ctx.next_pid); + trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n", + entry->ctx.prev_pid, + entry->ctx.prev_prio, + S, entry->type == TRACE_CTX ? "==>" : " +", + entry->ctx.next_pid, + entry->ctx.next_prio, + T, comm); + break; + case TRACE_SPECIAL: + trace_seq_printf(s, "# %ld %ld %ld\n", + entry->special.arg1, + entry->special.arg2, + entry->special.arg3); + break; + case TRACE_STACK: + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + if (i) + trace_seq_puts(s, " <= "); + seq_print_ip_sym(s, entry->stack.caller[i], sym_flags); + } + trace_seq_puts(s, "\n"); + break; + default: + trace_seq_printf(s, "Unknown type %d\n", entry->type); + } + return 1; +} + +static int print_trace_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_entry *entry; + unsigned long usec_rem; + unsigned long long t; + unsigned long secs; + char *comm; + int ret; + int S, T; + int i; + + entry = iter->ent; + + comm = trace_find_cmdline(iter->ent->pid); + + t = ns2usecs(entry->t); + usec_rem = do_div(t, 1000000ULL); + secs = (unsigned long)t; + + ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); + if (!ret) + return 0; + ret = trace_seq_printf(s, "[%02d] ", iter->cpu); + if (!ret) + return 0; + ret = trace_seq_printf(s, "%5lu.%06lu: ", secs, usec_rem); + if (!ret) + return 0; + + switch (entry->type) { + case TRACE_FN: + ret = seq_print_ip_sym(s, entry->fn.ip, sym_flags); + if (!ret) + return 0; + if ((sym_flags & TRACE_ITER_PRINT_PARENT) && + entry->fn.parent_ip) { + ret = trace_seq_printf(s, " <-"); + if (!ret) + return 0; + ret = seq_print_ip_sym(s, entry->fn.parent_ip, + sym_flags); + if (!ret) + return 0; + } + ret = trace_seq_printf(s, "\n"); + if (!ret) + return 0; + break; + case TRACE_CTX: + case TRACE_WAKE: + S = entry->ctx.prev_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.prev_state] : 'X'; + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + ret = trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c\n", + entry->ctx.prev_pid, + entry->ctx.prev_prio, + S, + entry->type == TRACE_CTX ? "==>" : " +", + entry->ctx.next_pid, + entry->ctx.next_prio, + T); + if (!ret) + return 0; + break; + case TRACE_SPECIAL: + ret = trace_seq_printf(s, "# %ld %ld %ld\n", + entry->special.arg1, + entry->special.arg2, + entry->special.arg3); + if (!ret) + return 0; + break; + case TRACE_STACK: + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + if (i) { + ret = trace_seq_puts(s, " <= "); + if (!ret) + return 0; + } + ret = seq_print_ip_sym(s, entry->stack.caller[i], + sym_flags); + if (!ret) + return 0; + } + ret = trace_seq_puts(s, "\n"); + if (!ret) + return 0; + break; + } + return 1; +} + +static int print_raw_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry; + int ret; + int S, T; + + entry = iter->ent; + + ret = trace_seq_printf(s, "%d %d %llu ", + entry->pid, iter->cpu, entry->t); + if (!ret) + return 0; + + switch (entry->type) { + case TRACE_FN: + ret = trace_seq_printf(s, "%x %x\n", + entry->fn.ip, entry->fn.parent_ip); + if (!ret) + return 0; + break; + case TRACE_CTX: + case TRACE_WAKE: + S = entry->ctx.prev_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.prev_state] : 'X'; + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + if (entry->type == TRACE_WAKE) + S = '+'; + ret = trace_seq_printf(s, "%d %d %c %d %d %c\n", + entry->ctx.prev_pid, + entry->ctx.prev_prio, + S, + entry->ctx.next_pid, + entry->ctx.next_prio, + T); + if (!ret) + return 0; + break; + case TRACE_SPECIAL: + case TRACE_STACK: + ret = trace_seq_printf(s, "# %ld %ld %ld\n", + entry->special.arg1, + entry->special.arg2, + entry->special.arg3); + if (!ret) + return 0; + break; + } + return 1; +} + +#define SEQ_PUT_FIELD_RET(s, x) \ +do { \ + if (!trace_seq_putmem(s, &(x), sizeof(x))) \ + return 0; \ +} while (0) + +#define SEQ_PUT_HEX_FIELD_RET(s, x) \ +do { \ + if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ + return 0; \ +} while (0) + +static int print_hex_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + unsigned char newline = '\n'; + struct trace_entry *entry; + int S, T; + + entry = iter->ent; + + SEQ_PUT_HEX_FIELD_RET(s, entry->pid); + SEQ_PUT_HEX_FIELD_RET(s, iter->cpu); + SEQ_PUT_HEX_FIELD_RET(s, entry->t); + + switch (entry->type) { + case TRACE_FN: + SEQ_PUT_HEX_FIELD_RET(s, entry->fn.ip); + SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip); + break; + case TRACE_CTX: + case TRACE_WAKE: + S = entry->ctx.prev_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.prev_state] : 'X'; + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + if (entry->type == TRACE_WAKE) + S = '+'; + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_pid); + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_prio); + SEQ_PUT_HEX_FIELD_RET(s, S); + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_pid); + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_prio); + SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip); + SEQ_PUT_HEX_FIELD_RET(s, T); + break; + case TRACE_SPECIAL: + case TRACE_STACK: + SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg1); + SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg2); + SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg3); + break; + } + SEQ_PUT_FIELD_RET(s, newline); + + return 1; +} + +static int print_bin_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry; + + entry = iter->ent; + + SEQ_PUT_FIELD_RET(s, entry->pid); + SEQ_PUT_FIELD_RET(s, entry->cpu); + SEQ_PUT_FIELD_RET(s, entry->t); + + switch (entry->type) { + case TRACE_FN: + SEQ_PUT_FIELD_RET(s, entry->fn.ip); + SEQ_PUT_FIELD_RET(s, entry->fn.parent_ip); + break; + case TRACE_CTX: + SEQ_PUT_FIELD_RET(s, entry->ctx.prev_pid); + SEQ_PUT_FIELD_RET(s, entry->ctx.prev_prio); + SEQ_PUT_FIELD_RET(s, entry->ctx.prev_state); + SEQ_PUT_FIELD_RET(s, entry->ctx.next_pid); + SEQ_PUT_FIELD_RET(s, entry->ctx.next_prio); + SEQ_PUT_FIELD_RET(s, entry->ctx.next_state); + break; + case TRACE_SPECIAL: + case TRACE_STACK: + SEQ_PUT_FIELD_RET(s, entry->special.arg1); + SEQ_PUT_FIELD_RET(s, entry->special.arg2); + SEQ_PUT_FIELD_RET(s, entry->special.arg3); + break; + } + return 1; +} + +static int trace_empty(struct trace_iterator *iter) +{ + struct trace_array_cpu *data; + int cpu; + + for_each_tracing_cpu(cpu) { + data = iter->tr->data[cpu]; + + if (head_page(data) && data->trace_idx && + (data->trace_tail != data->trace_head || + data->trace_tail_idx != data->trace_head_idx)) + return 0; + } + return 1; +} + +static int print_trace_line(struct trace_iterator *iter) +{ + if (iter->trace && iter->trace->print_line) + return iter->trace->print_line(iter); + + if (trace_flags & TRACE_ITER_BIN) + return print_bin_fmt(iter); + + if (trace_flags & TRACE_ITER_HEX) + return print_hex_fmt(iter); + + if (trace_flags & TRACE_ITER_RAW) + return print_raw_fmt(iter); + + if (iter->iter_flags & TRACE_FILE_LAT_FMT) + return print_lat_fmt(iter, iter->idx, iter->cpu); + + return print_trace_fmt(iter); +} + +static int s_show(struct seq_file *m, void *v) +{ + struct trace_iterator *iter = v; + + if (iter->ent == NULL) { + if (iter->tr) { + seq_printf(m, "# tracer: %s\n", iter->trace->name); + seq_puts(m, "#\n"); + } + if (iter->iter_flags & TRACE_FILE_LAT_FMT) { + /* print nothing if the buffers are empty */ + if (trace_empty(iter)) + return 0; + print_trace_header(m, iter); + if (!(trace_flags & TRACE_ITER_VERBOSE)) + print_lat_help_header(m); + } else { + if (!(trace_flags & TRACE_ITER_VERBOSE)) + print_func_help_header(m); + } + } else { + print_trace_line(iter); + trace_print_seq(m, &iter->seq); + } + + return 0; +} + +static struct seq_operations tracer_seq_ops = { + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show, +}; + +static struct trace_iterator * +__tracing_open(struct inode *inode, struct file *file, int *ret) +{ + struct trace_iterator *iter; + + if (tracing_disabled) { + *ret = -ENODEV; + return NULL; + } + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) { + *ret = -ENOMEM; + goto out; + } + + mutex_lock(&trace_types_lock); + if (current_trace && current_trace->print_max) + iter->tr = &max_tr; + else + iter->tr = inode->i_private; + iter->trace = current_trace; + iter->pos = -1; + + /* TODO stop tracer */ + *ret = seq_open(file, &tracer_seq_ops); + if (!*ret) { + struct seq_file *m = file->private_data; + m->private = iter; + + /* stop the trace while dumping */ + if (iter->tr->ctrl) + tracer_enabled = 0; + + if (iter->trace && iter->trace->open) + iter->trace->open(iter); + } else { + kfree(iter); + iter = NULL; + } + mutex_unlock(&trace_types_lock); + + out: + return iter; +} + +int tracing_open_generic(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + filp->private_data = inode->i_private; + return 0; +} + +int tracing_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + struct trace_iterator *iter = m->private; + + mutex_lock(&trace_types_lock); + if (iter->trace && iter->trace->close) + iter->trace->close(iter); + + /* reenable tracing if it was previously enabled */ + if (iter->tr->ctrl) + tracer_enabled = 1; + mutex_unlock(&trace_types_lock); + + seq_release(inode, file); + kfree(iter); + return 0; +} + +static int tracing_open(struct inode *inode, struct file *file) +{ + int ret; + + __tracing_open(inode, file, &ret); + + return ret; +} + +static int tracing_lt_open(struct inode *inode, struct file *file) +{ + struct trace_iterator *iter; + int ret; + + iter = __tracing_open(inode, file, &ret); + + if (!ret) + iter->iter_flags |= TRACE_FILE_LAT_FMT; + + return ret; +} + + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct tracer *t = m->private; + + (*pos)++; + + if (t) + t = t->next; + + m->private = t; + + return t; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + struct tracer *t = m->private; + loff_t l = 0; + + mutex_lock(&trace_types_lock); + for (; t && l < *pos; t = t_next(m, t, &l)) + ; + + return t; +} + +static void t_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&trace_types_lock); +} + +static int t_show(struct seq_file *m, void *v) +{ + struct tracer *t = v; + + if (!t) + return 0; + + seq_printf(m, "%s", t->name); + if (t->next) + seq_putc(m, ' '); + else + seq_putc(m, '\n'); + + return 0; +} + +static struct seq_operations show_traces_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int show_traces_open(struct inode *inode, struct file *file) +{ + int ret; + + if (tracing_disabled) + return -ENODEV; + + ret = seq_open(file, &show_traces_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = trace_types; + } + + return ret; +} + +static struct file_operations tracing_fops = { + .open = tracing_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_release, +}; + +static struct file_operations tracing_lt_fops = { + .open = tracing_lt_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_release, +}; + +static struct file_operations show_traces_fops = { + .open = show_traces_open, + .read = seq_read, + .release = seq_release, +}; + +/* + * Only trace on a CPU if the bitmask is set: + */ +static cpumask_t tracing_cpumask = CPU_MASK_ALL; + +/* + * When tracing/tracing_cpu_mask is modified then this holds + * the new bitmask we are about to install: + */ +static cpumask_t tracing_cpumask_new; + +/* + * The tracer itself will not take this lock, but still we want + * to provide a consistent cpumask to user-space: + */ +static DEFINE_MUTEX(tracing_cpumask_update_lock); + +/* + * Temporary storage for the character representation of the + * CPU bitmask (and one more byte for the newline): + */ +static char mask_str[NR_CPUS + 1]; + +static ssize_t +tracing_cpumask_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + int len; + + mutex_lock(&tracing_cpumask_update_lock); + + len = cpumask_scnprintf(mask_str, count, tracing_cpumask); + if (count - len < 2) { + count = -EINVAL; + goto out_err; + } + len += sprintf(mask_str + len, "\n"); + count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1); + +out_err: + mutex_unlock(&tracing_cpumask_update_lock); + + return count; +} + +static ssize_t +tracing_cpumask_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + int err, cpu; + + mutex_lock(&tracing_cpumask_update_lock); + err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); + if (err) + goto err_unlock; + + raw_local_irq_disable(); + __raw_spin_lock(&ftrace_max_lock); + for_each_tracing_cpu(cpu) { + /* + * Increase/decrease the disabled counter if we are + * about to flip a bit in the cpumask: + */ + if (cpu_isset(cpu, tracing_cpumask) && + !cpu_isset(cpu, tracing_cpumask_new)) { + atomic_inc(&global_trace.data[cpu]->disabled); + } + if (!cpu_isset(cpu, tracing_cpumask) && + cpu_isset(cpu, tracing_cpumask_new)) { + atomic_dec(&global_trace.data[cpu]->disabled); + } + } + __raw_spin_unlock(&ftrace_max_lock); + raw_local_irq_enable(); + + tracing_cpumask = tracing_cpumask_new; + + mutex_unlock(&tracing_cpumask_update_lock); + + return count; + +err_unlock: + mutex_unlock(&tracing_cpumask_update_lock); + + return err; +} + +static struct file_operations tracing_cpumask_fops = { + .open = tracing_open_generic, + .read = tracing_cpumask_read, + .write = tracing_cpumask_write, +}; + +static ssize_t +tracing_iter_ctrl_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char *buf; + int r = 0; + int len = 0; + int i; + + /* calulate max size */ + for (i = 0; trace_options[i]; i++) { + len += strlen(trace_options[i]); + len += 3; /* "no" and space */ + } + + /* +2 for \n and \0 */ + buf = kmalloc(len + 2, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + for (i = 0; trace_options[i]; i++) { + if (trace_flags & (1 << i)) + r += sprintf(buf + r, "%s ", trace_options[i]); + else + r += sprintf(buf + r, "no%s ", trace_options[i]); + } + + r += sprintf(buf + r, "\n"); + WARN_ON(r >= len + 2); + + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + + kfree(buf); + + return r; +} + +static ssize_t +tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp = buf; + int neg = 0; + int i; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (strncmp(buf, "no", 2) == 0) { + neg = 1; + cmp += 2; + } + + for (i = 0; trace_options[i]; i++) { + int len = strlen(trace_options[i]); + + if (strncmp(cmp, trace_options[i], len) == 0) { + if (neg) + trace_flags &= ~(1 << i); + else + trace_flags |= (1 << i); + break; + } + } + /* + * If no option could be set, return an error: + */ + if (!trace_options[i]) + return -EINVAL; + + filp->f_pos += cnt; + + return cnt; +} + +static struct file_operations tracing_iter_fops = { + .open = tracing_open_generic, + .read = tracing_iter_ctrl_read, + .write = tracing_iter_ctrl_write, +}; + +static const char readme_msg[] = + "tracing mini-HOWTO:\n\n" + "# mkdir /debug\n" + "# mount -t debugfs nodev /debug\n\n" + "# cat /debug/tracing/available_tracers\n" + "wakeup preemptirqsoff preemptoff irqsoff ftrace sched_switch none\n\n" + "# cat /debug/tracing/current_tracer\n" + "none\n" + "# echo sched_switch > /debug/tracing/current_tracer\n" + "# cat /debug/tracing/current_tracer\n" + "sched_switch\n" + "# cat /debug/tracing/iter_ctrl\n" + "noprint-parent nosym-offset nosym-addr noverbose\n" + "# echo print-parent > /debug/tracing/iter_ctrl\n" + "# echo 1 > /debug/tracing/tracing_enabled\n" + "# cat /debug/tracing/trace > /tmp/trace.txt\n" + "echo 0 > /debug/tracing/tracing_enabled\n" +; + +static ssize_t +tracing_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static struct file_operations tracing_readme_fops = { + .open = tracing_open_generic, + .read = tracing_readme_read, +}; + +static ssize_t +tracing_ctrl_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r; + + r = sprintf(buf, "%ld\n", tr->ctrl); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_ctrl_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + val = !!val; + + mutex_lock(&trace_types_lock); + if (tr->ctrl ^ val) { + if (val) + tracer_enabled = 1; + else + tracer_enabled = 0; + + tr->ctrl = val; + + if (current_trace && current_trace->ctrl_update) + current_trace->ctrl_update(tr); + } + mutex_unlock(&trace_types_lock); + + filp->f_pos += cnt; + + return cnt; +} + +static ssize_t +tracing_set_trace_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[max_tracer_type_len+2]; + int r; + + mutex_lock(&trace_types_lock); + if (current_trace) + r = sprintf(buf, "%s\n", current_trace->name); + else + r = sprintf(buf, "\n"); + mutex_unlock(&trace_types_lock); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_set_trace_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = &global_trace; + struct tracer *t; + char buf[max_tracer_type_len+1]; + int i; + + if (cnt > max_tracer_type_len) + cnt = max_tracer_type_len; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + /* strip ending whitespace. */ + for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) + buf[i] = 0; + + mutex_lock(&trace_types_lock); + for (t = trace_types; t; t = t->next) { + if (strcmp(t->name, buf) == 0) + break; + } + if (!t || t == current_trace) + goto out; + + if (current_trace && current_trace->reset) + current_trace->reset(tr); + + current_trace = t; + if (t->init) + t->init(tr); + + out: + mutex_unlock(&trace_types_lock); + + filp->f_pos += cnt; + + return cnt; +} + +static ssize_t +tracing_max_lat_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long *ptr = filp->private_data; + char buf[64]; + int r; + + r = snprintf(buf, sizeof(buf), "%ld\n", + *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr)); + if (r > sizeof(buf)) + r = sizeof(buf); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_max_lat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + long *ptr = filp->private_data; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + *ptr = val * 1000; + + return cnt; +} + +static atomic_t tracing_reader; + +static int tracing_open_pipe(struct inode *inode, struct file *filp) +{ + struct trace_iterator *iter; + + if (tracing_disabled) + return -ENODEV; + + /* We only allow for reader of the pipe */ + if (atomic_inc_return(&tracing_reader) != 1) { + atomic_dec(&tracing_reader); + return -EBUSY; + } + + /* create a buffer to store the information to pass to userspace */ + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + mutex_lock(&trace_types_lock); + iter->tr = &global_trace; + iter->trace = current_trace; + filp->private_data = iter; + + if (iter->trace->pipe_open) + iter->trace->pipe_open(iter); + mutex_unlock(&trace_types_lock); + + return 0; +} + +static int tracing_release_pipe(struct inode *inode, struct file *file) +{ + struct trace_iterator *iter = file->private_data; + + kfree(iter); + atomic_dec(&tracing_reader); + + return 0; +} + +static unsigned int +tracing_poll_pipe(struct file *filp, poll_table *poll_table) +{ + struct trace_iterator *iter = filp->private_data; + + if (trace_flags & TRACE_ITER_BLOCK) { + /* + * Always select as readable when in blocking mode + */ + return POLLIN | POLLRDNORM; + } else { + if (!trace_empty(iter)) + return POLLIN | POLLRDNORM; + poll_wait(filp, &trace_wait, poll_table); + if (!trace_empty(iter)) + return POLLIN | POLLRDNORM; + + return 0; + } +} + +/* + * Consumer reader. + */ +static ssize_t +tracing_read_pipe(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_iterator *iter = filp->private_data; + struct trace_array_cpu *data; + static cpumask_t mask; + unsigned long flags; +#ifdef CONFIG_FTRACE + int ftrace_save; +#endif + int cpu; + ssize_t sret; + + /* return any leftover data */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (sret != -EBUSY) + return sret; + sret = 0; + + trace_seq_reset(&iter->seq); + + mutex_lock(&trace_types_lock); + if (iter->trace->read) { + sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); + if (sret) + goto out; + } + + while (trace_empty(iter)) { + + if ((filp->f_flags & O_NONBLOCK)) { + sret = -EAGAIN; + goto out; + } + + /* + * This is a make-shift waitqueue. The reason we don't use + * an actual wait queue is because: + * 1) we only ever have one waiter + * 2) the tracing, traces all functions, we don't want + * the overhead of calling wake_up and friends + * (and tracing them too) + * Anyway, this is really very primitive wakeup. + */ + set_current_state(TASK_INTERRUPTIBLE); + iter->tr->waiter = current; + + mutex_unlock(&trace_types_lock); + + /* sleep for 100 msecs, and try again. */ + schedule_timeout(HZ/10); + + mutex_lock(&trace_types_lock); + + iter->tr->waiter = NULL; + + if (signal_pending(current)) { + sret = -EINTR; + goto out; + } + + if (iter->trace != current_trace) + goto out; + + /* + * We block until we read something and tracing is disabled. + * We still block if tracing is disabled, but we have never + * read anything. This allows a user to cat this file, and + * then enable tracing. But after we have read something, + * we give an EOF when tracing is again disabled. + * + * iter->pos will be 0 if we haven't read anything. + */ + if (!tracer_enabled && iter->pos) + break; + + continue; + } + + /* stop when tracing is finished */ + if (trace_empty(iter)) + goto out; + + if (cnt >= PAGE_SIZE) + cnt = PAGE_SIZE - 1; + + /* reset all but tr, trace, and overruns */ + memset(&iter->seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + iter->pos = -1; + + /* + * We need to stop all tracing on all CPUS to read the + * the next buffer. This is a bit expensive, but is + * not done often. We fill all what we can read, + * and then release the locks again. + */ + + cpus_clear(mask); + local_irq_save(flags); +#ifdef CONFIG_FTRACE + ftrace_save = ftrace_enabled; + ftrace_enabled = 0; +#endif + smp_wmb(); + for_each_tracing_cpu(cpu) { + data = iter->tr->data[cpu]; + + if (!head_page(data) || !data->trace_idx) + continue; + + atomic_inc(&data->disabled); + cpu_set(cpu, mask); + } + + for_each_cpu_mask(cpu, mask) { + data = iter->tr->data[cpu]; + __raw_spin_lock(&data->lock); + + if (data->overrun > iter->last_overrun[cpu]) + iter->overrun[cpu] += + data->overrun - iter->last_overrun[cpu]; + iter->last_overrun[cpu] = data->overrun; + } + + while (find_next_entry_inc(iter) != NULL) { + int ret; + int len = iter->seq.len; + + ret = print_trace_line(iter); + if (!ret) { + /* don't print partial lines */ + iter->seq.len = len; + break; + } + + trace_consume(iter); + + if (iter->seq.len >= cnt) + break; + } + + for_each_cpu_mask(cpu, mask) { + data = iter->tr->data[cpu]; + __raw_spin_unlock(&data->lock); + } + + for_each_cpu_mask(cpu, mask) { + data = iter->tr->data[cpu]; + atomic_dec(&data->disabled); + } +#ifdef CONFIG_FTRACE + ftrace_enabled = ftrace_save; +#endif + local_irq_restore(flags); + + /* Now copy what we have to the user */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (iter->seq.readpos >= iter->seq.len) + trace_seq_reset(&iter->seq); + if (sret == -EBUSY) + sret = 0; + +out: + mutex_unlock(&trace_types_lock); + + return sret; +} + +static ssize_t +tracing_entries_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r; + + r = sprintf(buf, "%lu\n", tr->entries); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_entries_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long val; + char buf[64]; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + /* must have at least 1 entry */ + if (!val) + return -EINVAL; + + mutex_lock(&trace_types_lock); + + if (current_trace != &no_tracer) { + cnt = -EBUSY; + pr_info("ftrace: set current_tracer to none" + " before modifying buffer size\n"); + goto out; + } + + if (val > global_trace.entries) { + long pages_requested; + unsigned long freeable_pages; + + /* make sure we have enough memory before mapping */ + pages_requested = + (val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE; + + /* account for each buffer (and max_tr) */ + pages_requested *= tracing_nr_buffers * 2; + + /* Check for overflow */ + if (pages_requested < 0) { + cnt = -ENOMEM; + goto out; + } + + freeable_pages = determine_dirtyable_memory(); + + /* we only allow to request 1/4 of useable memory */ + if (pages_requested > + ((freeable_pages + tracing_pages_allocated) / 4)) { + cnt = -ENOMEM; + goto out; + } + + while (global_trace.entries < val) { + if (trace_alloc_page()) { + cnt = -ENOMEM; + goto out; + } + /* double check that we don't go over the known pages */ + if (tracing_pages_allocated > pages_requested) + break; + } + + } else { + /* include the number of entries in val (inc of page entries) */ + while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1)) + trace_free_page(); + } + + filp->f_pos += cnt; + + out: + max_tr.entries = global_trace.entries; + mutex_unlock(&trace_types_lock); + + return cnt; +} + +static struct file_operations tracing_max_lat_fops = { + .open = tracing_open_generic, + .read = tracing_max_lat_read, + .write = tracing_max_lat_write, +}; + +static struct file_operations tracing_ctrl_fops = { + .open = tracing_open_generic, + .read = tracing_ctrl_read, + .write = tracing_ctrl_write, +}; + +static struct file_operations set_tracer_fops = { + .open = tracing_open_generic, + .read = tracing_set_trace_read, + .write = tracing_set_trace_write, +}; + +static struct file_operations tracing_pipe_fops = { + .open = tracing_open_pipe, + .poll = tracing_poll_pipe, + .read = tracing_read_pipe, + .release = tracing_release_pipe, +}; + +static struct file_operations tracing_entries_fops = { + .open = tracing_open_generic, + .read = tracing_entries_read, + .write = tracing_entries_write, +}; + +#ifdef CONFIG_DYNAMIC_FTRACE + +static ssize_t +tracing_read_long(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long *p = filp->private_data; + char buf[64]; + int r; + + r = sprintf(buf, "%ld\n", *p); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static struct file_operations tracing_read_long_fops = { + .open = tracing_open_generic, + .read = tracing_read_long, +}; +#endif + +static struct dentry *d_tracer; + +struct dentry *tracing_init_dentry(void) +{ + static int once; + + if (d_tracer) + return d_tracer; + + d_tracer = debugfs_create_dir("tracing", NULL); + + if (!d_tracer && !once) { + once = 1; + pr_warning("Could not create debugfs directory 'tracing'\n"); + return NULL; + } + + return d_tracer; +} + +#ifdef CONFIG_FTRACE_SELFTEST +/* Let selftest have access to static functions in this file */ +#include "trace_selftest.c" +#endif + +static __init void tracer_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("tracing_enabled", 0644, d_tracer, + &global_trace, &tracing_ctrl_fops); + if (!entry) + pr_warning("Could not create debugfs 'tracing_enabled' entry\n"); + + entry = debugfs_create_file("iter_ctrl", 0644, d_tracer, + NULL, &tracing_iter_fops); + if (!entry) + pr_warning("Could not create debugfs 'iter_ctrl' entry\n"); + + entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer, + NULL, &tracing_cpumask_fops); + if (!entry) + pr_warning("Could not create debugfs 'tracing_cpumask' entry\n"); + + entry = debugfs_create_file("latency_trace", 0444, d_tracer, + &global_trace, &tracing_lt_fops); + if (!entry) + pr_warning("Could not create debugfs 'latency_trace' entry\n"); + + entry = debugfs_create_file("trace", 0444, d_tracer, + &global_trace, &tracing_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace' entry\n"); + + entry = debugfs_create_file("available_tracers", 0444, d_tracer, + &global_trace, &show_traces_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace' entry\n"); + + entry = debugfs_create_file("current_tracer", 0444, d_tracer, + &global_trace, &set_tracer_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace' entry\n"); + + entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer, + &tracing_max_latency, + &tracing_max_lat_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_max_latency' entry\n"); + + entry = debugfs_create_file("tracing_thresh", 0644, d_tracer, + &tracing_thresh, &tracing_max_lat_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_threash' entry\n"); + entry = debugfs_create_file("README", 0644, d_tracer, + NULL, &tracing_readme_fops); + if (!entry) + pr_warning("Could not create debugfs 'README' entry\n"); + + entry = debugfs_create_file("trace_pipe", 0644, d_tracer, + NULL, &tracing_pipe_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_threash' entry\n"); + + entry = debugfs_create_file("trace_entries", 0644, d_tracer, + &global_trace, &tracing_entries_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_threash' entry\n"); + +#ifdef CONFIG_DYNAMIC_FTRACE + entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer, + &ftrace_update_tot_cnt, + &tracing_read_long_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'dyn_ftrace_total_info' entry\n"); +#endif +#ifdef CONFIG_SYSPROF_TRACER + init_tracer_sysprof_debugfs(d_tracer); +#endif +} + +static int trace_alloc_page(void) +{ + struct trace_array_cpu *data; + struct page *page, *tmp; + LIST_HEAD(pages); + void *array; + unsigned pages_allocated = 0; + int i; + + /* first allocate a page for each CPU */ + for_each_tracing_cpu(i) { + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_pages; + } + + pages_allocated++; + page = virt_to_page(array); + list_add(&page->lru, &pages); + +/* Only allocate if we are actually using the max trace */ +#ifdef CONFIG_TRACER_MAX_TRACE + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_pages; + } + pages_allocated++; + page = virt_to_page(array); + list_add(&page->lru, &pages); +#endif + } + + /* Now that we successfully allocate a page per CPU, add them */ + for_each_tracing_cpu(i) { + data = global_trace.data[i]; + page = list_entry(pages.next, struct page, lru); + list_del_init(&page->lru); + list_add_tail(&page->lru, &data->trace_pages); + ClearPageLRU(page); + +#ifdef CONFIG_TRACER_MAX_TRACE + data = max_tr.data[i]; + page = list_entry(pages.next, struct page, lru); + list_del_init(&page->lru); + list_add_tail(&page->lru, &data->trace_pages); + SetPageLRU(page); +#endif + } + tracing_pages_allocated += pages_allocated; + global_trace.entries += ENTRIES_PER_PAGE; + + return 0; + + free_pages: + list_for_each_entry_safe(page, tmp, &pages, lru) { + list_del_init(&page->lru); + __free_page(page); + } + return -ENOMEM; +} + +static int trace_free_page(void) +{ + struct trace_array_cpu *data; + struct page *page; + struct list_head *p; + int i; + int ret = 0; + + /* free one page from each buffer */ + for_each_tracing_cpu(i) { + data = global_trace.data[i]; + p = data->trace_pages.next; + if (p == &data->trace_pages) { + /* should never happen */ + WARN_ON(1); + tracing_disabled = 1; + ret = -1; + break; + } + page = list_entry(p, struct page, lru); + ClearPageLRU(page); + list_del(&page->lru); + tracing_pages_allocated--; + tracing_pages_allocated--; + __free_page(page); + + tracing_reset(data); + +#ifdef CONFIG_TRACER_MAX_TRACE + data = max_tr.data[i]; + p = data->trace_pages.next; + if (p == &data->trace_pages) { + /* should never happen */ + WARN_ON(1); + tracing_disabled = 1; + ret = -1; + break; + } + page = list_entry(p, struct page, lru); + ClearPageLRU(page); + list_del(&page->lru); + __free_page(page); + + tracing_reset(data); +#endif + } + global_trace.entries -= ENTRIES_PER_PAGE; + + return ret; +} + +__init static int tracer_alloc_buffers(void) +{ + struct trace_array_cpu *data; + void *array; + struct page *page; + int pages = 0; + int ret = -ENOMEM; + int i; + + global_trace.ctrl = tracer_enabled; + + /* TODO: make the number of buffers hot pluggable with CPUS */ + tracing_nr_buffers = num_possible_cpus(); + tracing_buffer_mask = cpu_possible_map; + + /* Allocate the first page for all buffers */ + for_each_tracing_cpu(i) { + data = global_trace.data[i] = &per_cpu(global_trace_cpu, i); + max_tr.data[i] = &per_cpu(max_data, i); + + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_buffers; + } + + /* set the array to the list */ + INIT_LIST_HEAD(&data->trace_pages); + page = virt_to_page(array); + list_add(&page->lru, &data->trace_pages); + /* use the LRU flag to differentiate the two buffers */ + ClearPageLRU(page); + + data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + +/* Only allocate if we are actually using the max trace */ +#ifdef CONFIG_TRACER_MAX_TRACE + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_buffers; + } + + INIT_LIST_HEAD(&max_tr.data[i]->trace_pages); + page = virt_to_page(array); + list_add(&page->lru, &max_tr.data[i]->trace_pages); + SetPageLRU(page); +#endif + } + + /* + * Since we allocate by orders of pages, we may be able to + * round up a bit. + */ + global_trace.entries = ENTRIES_PER_PAGE; + pages++; + + while (global_trace.entries < trace_nr_entries) { + if (trace_alloc_page()) + break; + pages++; + } + max_tr.entries = global_trace.entries; + + pr_info("tracer: %d pages allocated for %ld", + pages, trace_nr_entries); + pr_info(" entries of %ld bytes\n", (long)TRACE_ENTRY_SIZE); + pr_info(" actual entries %ld\n", global_trace.entries); + + tracer_init_debugfs(); + + trace_init_cmdlines(); + + register_tracer(&no_tracer); + current_trace = &no_tracer; + + /* All seems OK, enable tracing */ + tracing_disabled = 0; + + return 0; + + free_buffers: + for (i-- ; i >= 0; i--) { + struct page *page, *tmp; + struct trace_array_cpu *data = global_trace.data[i]; + + if (data) { + list_for_each_entry_safe(page, tmp, + &data->trace_pages, lru) { + list_del_init(&page->lru); + __free_page(page); + } + } + +#ifdef CONFIG_TRACER_MAX_TRACE + data = max_tr.data[i]; + if (data) { + list_for_each_entry_safe(page, tmp, + &data->trace_pages, lru) { + list_del_init(&page->lru); + __free_page(page); + } + } +#endif + } + return ret; +} +fs_initcall(tracer_alloc_buffers); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h new file mode 100644 index 000000000000..b7f85d9c80d7 --- /dev/null +++ b/kernel/trace/trace.h @@ -0,0 +1,319 @@ +#ifndef _LINUX_KERNEL_TRACE_H +#define _LINUX_KERNEL_TRACE_H + +#include <linux/fs.h> +#include <asm/atomic.h> +#include <linux/sched.h> +#include <linux/clocksource.h> + +enum trace_type { + __TRACE_FIRST_TYPE = 0, + + TRACE_FN, + TRACE_CTX, + TRACE_WAKE, + TRACE_STACK, + TRACE_SPECIAL, + + __TRACE_LAST_TYPE +}; + +/* + * Function trace entry - function address and parent function addres: + */ +struct ftrace_entry { + unsigned long ip; + unsigned long parent_ip; +}; + +/* + * Context switch trace entry - which task (and prio) we switched from/to: + */ +struct ctx_switch_entry { + unsigned int prev_pid; + unsigned char prev_prio; + unsigned char prev_state; + unsigned int next_pid; + unsigned char next_prio; + unsigned char next_state; +}; + +/* + * Special (free-form) trace entry: + */ +struct special_entry { + unsigned long arg1; + unsigned long arg2; + unsigned long arg3; +}; + +/* + * Stack-trace entry: + */ + +#define FTRACE_STACK_ENTRIES 8 + +struct stack_entry { + unsigned long caller[FTRACE_STACK_ENTRIES]; +}; + +/* + * The trace entry - the most basic unit of tracing. This is what + * is printed in the end as a single line in the trace output, such as: + * + * bash-15816 [01] 235.197585: idle_cpu <- irq_enter + */ +struct trace_entry { + char type; + char cpu; + char flags; + char preempt_count; + int pid; + cycle_t t; + union { + struct ftrace_entry fn; + struct ctx_switch_entry ctx; + struct special_entry special; + struct stack_entry stack; + }; +}; + +#define TRACE_ENTRY_SIZE sizeof(struct trace_entry) + +/* + * The CPU trace array - it consists of thousands of trace entries + * plus some other descriptor data: (for example which task started + * the trace, etc.) + */ +struct trace_array_cpu { + struct list_head trace_pages; + atomic_t disabled; + raw_spinlock_t lock; + struct lock_class_key lock_key; + + /* these fields get copied into max-trace: */ + unsigned trace_head_idx; + unsigned trace_tail_idx; + void *trace_head; /* producer */ + void *trace_tail; /* consumer */ + unsigned long trace_idx; + unsigned long overrun; + unsigned long saved_latency; + unsigned long critical_start; + unsigned long critical_end; + unsigned long critical_sequence; + unsigned long nice; + unsigned long policy; + unsigned long rt_priority; + cycle_t preempt_timestamp; + pid_t pid; + uid_t uid; + char comm[TASK_COMM_LEN]; +}; + +struct trace_iterator; + +/* + * The trace array - an array of per-CPU trace arrays. This is the + * highest level data structure that individual tracers deal with. + * They have on/off state as well: + */ +struct trace_array { + unsigned long entries; + long ctrl; + int cpu; + cycle_t time_start; + struct task_struct *waiter; + struct trace_array_cpu *data[NR_CPUS]; +}; + +/* + * A specific tracer, represented by methods that operate on a trace array: + */ +struct tracer { + const char *name; + void (*init)(struct trace_array *tr); + void (*reset)(struct trace_array *tr); + void (*open)(struct trace_iterator *iter); + void (*pipe_open)(struct trace_iterator *iter); + void (*close)(struct trace_iterator *iter); + void (*start)(struct trace_iterator *iter); + void (*stop)(struct trace_iterator *iter); + ssize_t (*read)(struct trace_iterator *iter, + struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos); + void (*ctrl_update)(struct trace_array *tr); +#ifdef CONFIG_FTRACE_STARTUP_TEST + int (*selftest)(struct tracer *trace, + struct trace_array *tr); +#endif + int (*print_line)(struct trace_iterator *iter); + struct tracer *next; + int print_max; +}; + +struct trace_seq { + unsigned char buffer[PAGE_SIZE]; + unsigned int len; + unsigned int readpos; +}; + +/* + * Trace iterator - used by printout routines who present trace + * results to users and which routines might sleep, etc: + */ +struct trace_iterator { + struct trace_array *tr; + struct tracer *trace; + void *private; + long last_overrun[NR_CPUS]; + long overrun[NR_CPUS]; + + /* The below is zeroed out in pipe_read */ + struct trace_seq seq; + struct trace_entry *ent; + int cpu; + + struct trace_entry *prev_ent; + int prev_cpu; + + unsigned long iter_flags; + loff_t pos; + unsigned long next_idx[NR_CPUS]; + struct list_head *next_page[NR_CPUS]; + unsigned next_page_idx[NR_CPUS]; + long idx; +}; + +void tracing_reset(struct trace_array_cpu *data); +int tracing_open_generic(struct inode *inode, struct file *filp); +struct dentry *tracing_init_dentry(void); +void init_tracer_sysprof_debugfs(struct dentry *d_tracer); + +void ftrace(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long ip, + unsigned long parent_ip, + unsigned long flags); +void tracing_sched_switch_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *prev, + struct task_struct *next, + unsigned long flags); +void tracing_record_cmdline(struct task_struct *tsk); + +void tracing_sched_wakeup_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *wakee, + struct task_struct *cur, + unsigned long flags); +void trace_special(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long arg1, + unsigned long arg2, + unsigned long arg3); +void trace_function(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long ip, + unsigned long parent_ip, + unsigned long flags); + +void tracing_start_function_trace(void); +void tracing_stop_function_trace(void); +int register_tracer(struct tracer *type); +void unregister_tracer(struct tracer *type); + +extern unsigned long nsecs_to_usecs(unsigned long nsecs); + +extern unsigned long tracing_max_latency; +extern unsigned long tracing_thresh; + +extern atomic_t trace_record_cmdline_enabled; + +void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); +void update_max_tr_single(struct trace_array *tr, + struct task_struct *tsk, int cpu); + +extern cycle_t ftrace_now(int cpu); + +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +typedef void +(*tracer_switch_func_t)(void *private, + void *__rq, + struct task_struct *prev, + struct task_struct *next); + +struct tracer_switch_ops { + tracer_switch_func_t func; + void *private; + struct tracer_switch_ops *next; +}; + +#endif /* CONFIG_CONTEXT_SWITCH_TRACER */ + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_update_tot_cnt; +#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func +extern int DYN_FTRACE_TEST_NAME(void); +#endif + +#ifdef CONFIG_FTRACE_STARTUP_TEST +#ifdef CONFIG_FTRACE +extern int trace_selftest_startup_function(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_IRQSOFF_TRACER +extern int trace_selftest_startup_irqsoff(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_PREEMPT_TRACER +extern int trace_selftest_startup_preemptoff(struct tracer *trace, + struct trace_array *tr); +#endif +#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER) +extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_SCHED_TRACER +extern int trace_selftest_startup_wakeup(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +extern int trace_selftest_startup_sched_switch(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_SYSPROF_TRACER +extern int trace_selftest_startup_sysprof(struct tracer *trace, + struct trace_array *tr); +#endif +#endif /* CONFIG_FTRACE_STARTUP_TEST */ + +extern void *head_page(struct trace_array_cpu *data); +extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...); +extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, + size_t cnt); +extern long ns2usecs(cycle_t nsec); + +extern unsigned long trace_flags; + +/* + * trace_iterator_flags is an enumeration that defines bit + * positions into trace_flags that controls the output. + * + * NOTE: These bits must match the trace_options array in + * trace.c. + */ +enum trace_iterator_flags { + TRACE_ITER_PRINT_PARENT = 0x01, + TRACE_ITER_SYM_OFFSET = 0x02, + TRACE_ITER_SYM_ADDR = 0x04, + TRACE_ITER_VERBOSE = 0x08, + TRACE_ITER_RAW = 0x10, + TRACE_ITER_HEX = 0x20, + TRACE_ITER_BIN = 0x40, + TRACE_ITER_BLOCK = 0x80, + TRACE_ITER_STACKTRACE = 0x100, + TRACE_ITER_SCHED_TREE = 0x200, +}; + +#endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c new file mode 100644 index 000000000000..0a084656d7cf --- /dev/null +++ b/kernel/trace/trace_functions.c @@ -0,0 +1,78 @@ +/* + * ring buffer based function tracer + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * Based on code from the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/fs.h> + +#include "trace.h" + +static void function_reset(struct trace_array *tr) +{ + int cpu; + + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); +} + +static void start_function_trace(struct trace_array *tr) +{ + function_reset(tr); + atomic_inc(&trace_record_cmdline_enabled); + tracing_start_function_trace(); +} + +static void stop_function_trace(struct trace_array *tr) +{ + tracing_stop_function_trace(); + atomic_dec(&trace_record_cmdline_enabled); +} + +static void function_trace_init(struct trace_array *tr) +{ + if (tr->ctrl) + start_function_trace(tr); +} + +static void function_trace_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_function_trace(tr); +} + +static void function_trace_ctrl_update(struct trace_array *tr) +{ + if (tr->ctrl) + start_function_trace(tr); + else + stop_function_trace(tr); +} + +static struct tracer function_trace __read_mostly = +{ + .name = "ftrace", + .init = function_trace_init, + .reset = function_trace_reset, + .ctrl_update = function_trace_ctrl_update, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_function, +#endif +}; + +static __init int init_function_trace(void) +{ + return register_tracer(&function_trace); +} + +device_initcall(init_function_trace); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c new file mode 100644 index 000000000000..761f3ec66c50 --- /dev/null +++ b/kernel/trace/trace_irqsoff.c @@ -0,0 +1,502 @@ +/* + * trace irqs off criticall timings + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * From code in the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/kallsyms.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/ftrace.h> +#include <linux/fs.h> + +#include "trace.h" + +static struct trace_array *irqsoff_trace __read_mostly; +static int tracer_enabled __read_mostly; + +static DEFINE_PER_CPU(int, tracing_cpu); + +static DEFINE_SPINLOCK(max_trace_lock); + +enum { + TRACER_IRQS_OFF = (1 << 1), + TRACER_PREEMPT_OFF = (1 << 2), +}; + +static int trace_type __read_mostly; + +#ifdef CONFIG_PREEMPT_TRACER +static inline int +preempt_trace(void) +{ + return ((trace_type & TRACER_PREEMPT_OFF) && preempt_count()); +} +#else +# define preempt_trace() (0) +#endif + +#ifdef CONFIG_IRQSOFF_TRACER +static inline int +irq_trace(void) +{ + return ((trace_type & TRACER_IRQS_OFF) && + irqs_disabled()); +} +#else +# define irq_trace() (0) +#endif + +/* + * Sequence count - we record it when starting a measurement and + * skip the latency if the sequence has changed - some other section + * did a maximum and could disturb our measurement with serial console + * printouts, etc. Truly coinciding maximum latencies should be rare + * and what happens together happens separately as well, so this doesnt + * decrease the validity of the maximum found: + */ +static __cacheline_aligned_in_smp unsigned long max_sequence; + +#ifdef CONFIG_FTRACE +/* + * irqsoff uses its own tracer function to keep the overhead down: + */ +static void +irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + /* + * Does not matter if we preempt. We test the flags + * afterward, to see if irqs are disabled or not. + * If we preempt and get a false positive, the flags + * test will fail. + */ + cpu = raw_smp_processor_id(); + if (likely(!per_cpu(tracing_cpu, cpu))) + return; + + local_save_flags(flags); + /* slight chance to get a false positive on tracing_cpu */ + if (!irqs_disabled_flags(flags)) + return; + + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + trace_function(tr, data, ip, parent_ip, flags); + + atomic_dec(&data->disabled); +} + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = irqsoff_tracer_call, +}; +#endif /* CONFIG_FTRACE */ + +/* + * Should this new latency be reported/recorded? + */ +static int report_latency(cycle_t delta) +{ + if (tracing_thresh) { + if (delta < tracing_thresh) + return 0; + } else { + if (delta <= tracing_max_latency) + return 0; + } + return 1; +} + +static void +check_critical_timing(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long parent_ip, + int cpu) +{ + unsigned long latency, t0, t1; + cycle_t T0, T1, delta; + unsigned long flags; + + /* + * usecs conversion is slow so we try to delay the conversion + * as long as possible: + */ + T0 = data->preempt_timestamp; + T1 = ftrace_now(cpu); + delta = T1-T0; + + local_save_flags(flags); + + if (!report_latency(delta)) + goto out; + + spin_lock_irqsave(&max_trace_lock, flags); + + /* check if we are still the max latency */ + if (!report_latency(delta)) + goto out_unlock; + + trace_function(tr, data, CALLER_ADDR0, parent_ip, flags); + + latency = nsecs_to_usecs(delta); + + if (data->critical_sequence != max_sequence) + goto out_unlock; + + tracing_max_latency = delta; + t0 = nsecs_to_usecs(T0); + t1 = nsecs_to_usecs(T1); + + data->critical_end = parent_ip; + + update_max_tr_single(tr, current, cpu); + + if (!runqueue_is_locked()) { + if (tracing_thresh) { + printk(KERN_INFO "(%16s-%-5d|#%d): %lu us critical" + " section violates %lu us threshold.\n", + current->comm, current->pid, + raw_smp_processor_id(), + latency, nsecs_to_usecs(tracing_thresh)); + } else { + printk(KERN_INFO "(%16s-%-5d|#%d): new %lu us" + " maximum-latency critical section.\n", + current->comm, current->pid, + raw_smp_processor_id(), + latency); + } + } + + max_sequence++; + +out_unlock: + spin_unlock_irqrestore(&max_trace_lock, flags); + +out: + data->critical_sequence = max_sequence; + data->preempt_timestamp = ftrace_now(cpu); + tracing_reset(data); + trace_function(tr, data, CALLER_ADDR0, parent_ip, flags); +} + +static inline void +start_critical_timing(unsigned long ip, unsigned long parent_ip) +{ + int cpu; + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + + if (likely(!tracer_enabled)) + return; + + cpu = raw_smp_processor_id(); + + if (per_cpu(tracing_cpu, cpu)) + return; + + data = tr->data[cpu]; + + if (unlikely(!data) || atomic_read(&data->disabled)) + return; + + atomic_inc(&data->disabled); + + data->critical_sequence = max_sequence; + data->preempt_timestamp = ftrace_now(cpu); + data->critical_start = parent_ip ? : ip; + tracing_reset(data); + + local_save_flags(flags); + + trace_function(tr, data, ip, parent_ip, flags); + + per_cpu(tracing_cpu, cpu) = 1; + + atomic_dec(&data->disabled); +} + +static inline void +stop_critical_timing(unsigned long ip, unsigned long parent_ip) +{ + int cpu; + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + + cpu = raw_smp_processor_id(); + /* Always clear the tracing cpu on stopping the trace */ + if (unlikely(per_cpu(tracing_cpu, cpu))) + per_cpu(tracing_cpu, cpu) = 0; + else + return; + + if (!tracer_enabled) + return; + + data = tr->data[cpu]; + + if (unlikely(!data) || unlikely(!head_page(data)) || + !data->critical_start || atomic_read(&data->disabled)) + return; + + atomic_inc(&data->disabled); + + local_save_flags(flags); + trace_function(tr, data, ip, parent_ip, flags); + check_critical_timing(tr, data, parent_ip ? : ip, cpu); + data->critical_start = 0; + atomic_dec(&data->disabled); +} + +/* start and stop critical timings used to for stoppage (in idle) */ +void start_critical_timings(void) +{ + if (preempt_trace() || irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} + +void stop_critical_timings(void) +{ + if (preempt_trace() || irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} + +#ifdef CONFIG_IRQSOFF_TRACER +#ifdef CONFIG_PROVE_LOCKING +void time_hardirqs_on(unsigned long a0, unsigned long a1) +{ + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); +} + +void time_hardirqs_off(unsigned long a0, unsigned long a1) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); +} + +#else /* !CONFIG_PROVE_LOCKING */ + +/* + * Stubs: + */ + +void early_boot_irqs_off(void) +{ +} + +void early_boot_irqs_on(void) +{ +} + +void trace_softirqs_on(unsigned long ip) +{ +} + +void trace_softirqs_off(unsigned long ip) +{ +} + +inline void print_irqtrace_events(struct task_struct *curr) +{ +} + +/* + * We are only interested in hardirq on/off events: + */ +void trace_hardirqs_on(void) +{ + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} +EXPORT_SYMBOL(trace_hardirqs_on); + +void trace_hardirqs_off(void) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} +EXPORT_SYMBOL(trace_hardirqs_off); + +void trace_hardirqs_on_caller(unsigned long caller_addr) +{ + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, caller_addr); +} +EXPORT_SYMBOL(trace_hardirqs_on_caller); + +void trace_hardirqs_off_caller(unsigned long caller_addr) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, caller_addr); +} +EXPORT_SYMBOL(trace_hardirqs_off_caller); + +#endif /* CONFIG_PROVE_LOCKING */ +#endif /* CONFIG_IRQSOFF_TRACER */ + +#ifdef CONFIG_PREEMPT_TRACER +void trace_preempt_on(unsigned long a0, unsigned long a1) +{ + stop_critical_timing(a0, a1); +} + +void trace_preempt_off(unsigned long a0, unsigned long a1) +{ + start_critical_timing(a0, a1); +} +#endif /* CONFIG_PREEMPT_TRACER */ + +static void start_irqsoff_tracer(struct trace_array *tr) +{ + register_ftrace_function(&trace_ops); + tracer_enabled = 1; +} + +static void stop_irqsoff_tracer(struct trace_array *tr) +{ + tracer_enabled = 0; + unregister_ftrace_function(&trace_ops); +} + +static void __irqsoff_tracer_init(struct trace_array *tr) +{ + irqsoff_trace = tr; + /* make sure that the tracer is visible */ + smp_wmb(); + + if (tr->ctrl) + start_irqsoff_tracer(tr); +} + +static void irqsoff_tracer_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_irqsoff_tracer(tr); +} + +static void irqsoff_tracer_ctrl_update(struct trace_array *tr) +{ + if (tr->ctrl) + start_irqsoff_tracer(tr); + else + stop_irqsoff_tracer(tr); +} + +static void irqsoff_tracer_open(struct trace_iterator *iter) +{ + /* stop the trace while dumping */ + if (iter->tr->ctrl) + stop_irqsoff_tracer(iter->tr); +} + +static void irqsoff_tracer_close(struct trace_iterator *iter) +{ + if (iter->tr->ctrl) + start_irqsoff_tracer(iter->tr); +} + +#ifdef CONFIG_IRQSOFF_TRACER +static void irqsoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_IRQS_OFF; + + __irqsoff_tracer_init(tr); +} +static struct tracer irqsoff_tracer __read_mostly = +{ + .name = "irqsoff", + .init = irqsoff_tracer_init, + .reset = irqsoff_tracer_reset, + .open = irqsoff_tracer_open, + .close = irqsoff_tracer_close, + .ctrl_update = irqsoff_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_irqsoff, +#endif +}; +# define register_irqsoff(trace) register_tracer(&trace) +#else +# define register_irqsoff(trace) do { } while (0) +#endif + +#ifdef CONFIG_PREEMPT_TRACER +static void preemptoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_PREEMPT_OFF; + + __irqsoff_tracer_init(tr); +} + +static struct tracer preemptoff_tracer __read_mostly = +{ + .name = "preemptoff", + .init = preemptoff_tracer_init, + .reset = irqsoff_tracer_reset, + .open = irqsoff_tracer_open, + .close = irqsoff_tracer_close, + .ctrl_update = irqsoff_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_preemptoff, +#endif +}; +# define register_preemptoff(trace) register_tracer(&trace) +#else +# define register_preemptoff(trace) do { } while (0) +#endif + +#if defined(CONFIG_IRQSOFF_TRACER) && \ + defined(CONFIG_PREEMPT_TRACER) + +static void preemptirqsoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF; + + __irqsoff_tracer_init(tr); +} + +static struct tracer preemptirqsoff_tracer __read_mostly = +{ + .name = "preemptirqsoff", + .init = preemptirqsoff_tracer_init, + .reset = irqsoff_tracer_reset, + .open = irqsoff_tracer_open, + .close = irqsoff_tracer_close, + .ctrl_update = irqsoff_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_preemptirqsoff, +#endif +}; + +# define register_preemptirqsoff(trace) register_tracer(&trace) +#else +# define register_preemptirqsoff(trace) do { } while (0) +#endif + +__init static int init_irqsoff_tracer(void) +{ + register_irqsoff(irqsoff_tracer); + register_preemptoff(preemptoff_tracer); + register_preemptirqsoff(preemptirqsoff_tracer); + + return 0; +} +device_initcall(init_irqsoff_tracer); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c new file mode 100644 index 000000000000..d25ffa5eaf2b --- /dev/null +++ b/kernel/trace/trace_sched_switch.c @@ -0,0 +1,301 @@ +/* + * trace context switch + * + * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com> + * + */ +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/marker.h> +#include <linux/ftrace.h> + +#include "trace.h" + +static struct trace_array *ctx_trace; +static int __read_mostly tracer_enabled; +static atomic_t sched_ref; + +static void +sched_switch_func(void *private, void *__rq, struct task_struct *prev, + struct task_struct *next) +{ + struct trace_array **ptr = private; + struct trace_array *tr = *ptr; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + if (!tracer_enabled) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + tracing_sched_switch_trace(tr, data, prev, next, flags); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static notrace void +sched_switch_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct task_struct *prev; + struct task_struct *next; + struct rq *__rq; + + if (!atomic_read(&sched_ref)) + return; + + /* skip prev_pid %d next_pid %d prev_state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, int); + (void)va_arg(*args, long); + __rq = va_arg(*args, typeof(__rq)); + prev = va_arg(*args, typeof(prev)); + next = va_arg(*args, typeof(next)); + + tracing_record_cmdline(prev); + + /* + * If tracer_switch_func only points to the local + * switch func, it still needs the ptr passed to it. + */ + sched_switch_func(probe_data, __rq, prev, next); +} + +static void +wakeup_func(void *private, void *__rq, struct task_struct *wakee, struct + task_struct *curr) +{ + struct trace_array **ptr = private; + struct trace_array *tr = *ptr; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + if (!tracer_enabled) + return; + + tracing_record_cmdline(curr); + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + tracing_sched_wakeup_trace(tr, data, wakee, curr, flags); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static notrace void +wake_up_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct task_struct *curr; + struct task_struct *task; + struct rq *__rq; + + if (likely(!tracer_enabled)) + return; + + /* Skip pid %d state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, long); + /* now get the meat: "rq %p task %p rq->curr %p" */ + __rq = va_arg(*args, typeof(__rq)); + task = va_arg(*args, typeof(task)); + curr = va_arg(*args, typeof(curr)); + + tracing_record_cmdline(task); + tracing_record_cmdline(curr); + + wakeup_func(probe_data, __rq, task, curr); +} + +void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ + struct trace_array *tr = ctx_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + if (!tracer_enabled) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + __trace_special(tr, data, arg1, arg2, arg3); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static void sched_switch_reset(struct trace_array *tr) +{ + int cpu; + + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); +} + +static int tracing_sched_register(void) +{ + int ret; + + ret = marker_probe_register("kernel_sched_wakeup", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &ctx_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup\n"); + return ret; + } + + ret = marker_probe_register("kernel_sched_wakeup_new", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &ctx_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup_new\n"); + goto fail_deprobe; + } + + ret = marker_probe_register("kernel_sched_schedule", + "prev_pid %d next_pid %d prev_state %ld " + "## rq %p prev %p next %p", + sched_switch_callback, + &ctx_trace); + if (ret) { + pr_info("sched trace: Couldn't add marker" + " probe to kernel_sched_schedule\n"); + goto fail_deprobe_wake_new; + } + + return ret; +fail_deprobe_wake_new: + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &ctx_trace); +fail_deprobe: + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &ctx_trace); + return ret; +} + +static void tracing_sched_unregister(void) +{ + marker_probe_unregister("kernel_sched_schedule", + sched_switch_callback, + &ctx_trace); + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &ctx_trace); + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &ctx_trace); +} + +void tracing_start_sched_switch(void) +{ + long ref; + + ref = atomic_inc_return(&sched_ref); + if (ref == 1) + tracing_sched_register(); +} + +void tracing_stop_sched_switch(void) +{ + long ref; + + ref = atomic_dec_and_test(&sched_ref); + if (ref) + tracing_sched_unregister(); +} + +static void start_sched_trace(struct trace_array *tr) +{ + sched_switch_reset(tr); + atomic_inc(&trace_record_cmdline_enabled); + tracer_enabled = 1; + tracing_start_sched_switch(); +} + +static void stop_sched_trace(struct trace_array *tr) +{ + tracing_stop_sched_switch(); + atomic_dec(&trace_record_cmdline_enabled); + tracer_enabled = 0; +} + +static void sched_switch_trace_init(struct trace_array *tr) +{ + ctx_trace = tr; + + if (tr->ctrl) + start_sched_trace(tr); +} + +static void sched_switch_trace_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_sched_trace(tr); +} + +static void sched_switch_trace_ctrl_update(struct trace_array *tr) +{ + /* When starting a new trace, reset the buffers */ + if (tr->ctrl) + start_sched_trace(tr); + else + stop_sched_trace(tr); +} + +static struct tracer sched_switch_trace __read_mostly = +{ + .name = "sched_switch", + .init = sched_switch_trace_init, + .reset = sched_switch_trace_reset, + .ctrl_update = sched_switch_trace_ctrl_update, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_sched_switch, +#endif +}; + +__init static int init_sched_switch_trace(void) +{ + int ret = 0; + + if (atomic_read(&sched_ref)) + ret = tracing_sched_register(); + if (ret) { + pr_info("error registering scheduler trace\n"); + return ret; + } + return register_tracer(&sched_switch_trace); +} +device_initcall(init_sched_switch_trace); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c new file mode 100644 index 000000000000..5d2fb48e47f8 --- /dev/null +++ b/kernel/trace/trace_sched_wakeup.c @@ -0,0 +1,382 @@ +/* + * trace task wakeup timings + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * Based on code from the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/marker.h> + +#include "trace.h" + +static struct trace_array *wakeup_trace; +static int __read_mostly tracer_enabled; + +static struct task_struct *wakeup_task; +static int wakeup_cpu; +static unsigned wakeup_prio = -1; + +static DEFINE_SPINLOCK(wakeup_lock); + +static void __wakeup_reset(struct trace_array *tr); + +/* + * Should this new latency be reported/recorded? + */ +static int report_latency(cycle_t delta) +{ + if (tracing_thresh) { + if (delta < tracing_thresh) + return 0; + } else { + if (delta <= tracing_max_latency) + return 0; + } + return 1; +} + +static void notrace +wakeup_sched_switch(void *private, void *rq, struct task_struct *prev, + struct task_struct *next) +{ + unsigned long latency = 0, t0 = 0, t1 = 0; + struct trace_array **ptr = private; + struct trace_array *tr = *ptr; + struct trace_array_cpu *data; + cycle_t T0, T1, delta; + unsigned long flags; + long disabled; + int cpu; + + if (unlikely(!tracer_enabled)) + return; + + /* + * When we start a new trace, we set wakeup_task to NULL + * and then set tracer_enabled = 1. We want to make sure + * that another CPU does not see the tracer_enabled = 1 + * and the wakeup_task with an older task, that might + * actually be the same as next. + */ + smp_rmb(); + + if (next != wakeup_task) + return; + + /* The task we are waitng for is waking up */ + data = tr->data[wakeup_cpu]; + + /* disable local data, not wakeup_cpu data */ + cpu = raw_smp_processor_id(); + disabled = atomic_inc_return(&tr->data[cpu]->disabled); + if (likely(disabled != 1)) + goto out; + + spin_lock_irqsave(&wakeup_lock, flags); + + /* We could race with grabbing wakeup_lock */ + if (unlikely(!tracer_enabled || next != wakeup_task)) + goto out_unlock; + + trace_function(tr, data, CALLER_ADDR1, CALLER_ADDR2, flags); + + /* + * usecs conversion is slow so we try to delay the conversion + * as long as possible: + */ + T0 = data->preempt_timestamp; + T1 = ftrace_now(cpu); + delta = T1-T0; + + if (!report_latency(delta)) + goto out_unlock; + + latency = nsecs_to_usecs(delta); + + tracing_max_latency = delta; + t0 = nsecs_to_usecs(T0); + t1 = nsecs_to_usecs(T1); + + update_max_tr(tr, wakeup_task, wakeup_cpu); + +out_unlock: + __wakeup_reset(tr); + spin_unlock_irqrestore(&wakeup_lock, flags); +out: + atomic_dec(&tr->data[cpu]->disabled); +} + +static notrace void +sched_switch_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct task_struct *prev; + struct task_struct *next; + struct rq *__rq; + + /* skip prev_pid %d next_pid %d prev_state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, int); + (void)va_arg(*args, long); + __rq = va_arg(*args, typeof(__rq)); + prev = va_arg(*args, typeof(prev)); + next = va_arg(*args, typeof(next)); + + tracing_record_cmdline(prev); + + /* + * If tracer_switch_func only points to the local + * switch func, it still needs the ptr passed to it. + */ + wakeup_sched_switch(probe_data, __rq, prev, next); +} + +static void __wakeup_reset(struct trace_array *tr) +{ + struct trace_array_cpu *data; + int cpu; + + assert_spin_locked(&wakeup_lock); + + for_each_possible_cpu(cpu) { + data = tr->data[cpu]; + tracing_reset(data); + } + + wakeup_cpu = -1; + wakeup_prio = -1; + + if (wakeup_task) + put_task_struct(wakeup_task); + + wakeup_task = NULL; +} + +static void wakeup_reset(struct trace_array *tr) +{ + unsigned long flags; + + spin_lock_irqsave(&wakeup_lock, flags); + __wakeup_reset(tr); + spin_unlock_irqrestore(&wakeup_lock, flags); +} + +static void +wakeup_check_start(struct trace_array *tr, struct task_struct *p, + struct task_struct *curr) +{ + int cpu = smp_processor_id(); + unsigned long flags; + long disabled; + + if (likely(!rt_task(p)) || + p->prio >= wakeup_prio || + p->prio >= curr->prio) + return; + + disabled = atomic_inc_return(&tr->data[cpu]->disabled); + if (unlikely(disabled != 1)) + goto out; + + /* interrupts should be off from try_to_wake_up */ + spin_lock(&wakeup_lock); + + /* check for races. */ + if (!tracer_enabled || p->prio >= wakeup_prio) + goto out_locked; + + /* reset the trace */ + __wakeup_reset(tr); + + wakeup_cpu = task_cpu(p); + wakeup_prio = p->prio; + + wakeup_task = p; + get_task_struct(wakeup_task); + + local_save_flags(flags); + + tr->data[wakeup_cpu]->preempt_timestamp = ftrace_now(cpu); + trace_function(tr, tr->data[wakeup_cpu], + CALLER_ADDR1, CALLER_ADDR2, flags); + +out_locked: + spin_unlock(&wakeup_lock); +out: + atomic_dec(&tr->data[cpu]->disabled); +} + +static notrace void +wake_up_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct trace_array **ptr = probe_data; + struct trace_array *tr = *ptr; + struct task_struct *curr; + struct task_struct *task; + struct rq *__rq; + + if (likely(!tracer_enabled)) + return; + + /* Skip pid %d state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, long); + /* now get the meat: "rq %p task %p rq->curr %p" */ + __rq = va_arg(*args, typeof(__rq)); + task = va_arg(*args, typeof(task)); + curr = va_arg(*args, typeof(curr)); + + tracing_record_cmdline(task); + tracing_record_cmdline(curr); + + wakeup_check_start(tr, task, curr); +} + +static void start_wakeup_tracer(struct trace_array *tr) +{ + int ret; + + ret = marker_probe_register("kernel_sched_wakeup", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &wakeup_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup\n"); + return; + } + + ret = marker_probe_register("kernel_sched_wakeup_new", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &wakeup_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup_new\n"); + goto fail_deprobe; + } + + ret = marker_probe_register("kernel_sched_schedule", + "prev_pid %d next_pid %d prev_state %ld " + "## rq %p prev %p next %p", + sched_switch_callback, + &wakeup_trace); + if (ret) { + pr_info("sched trace: Couldn't add marker" + " probe to kernel_sched_schedule\n"); + goto fail_deprobe_wake_new; + } + + wakeup_reset(tr); + + /* + * Don't let the tracer_enabled = 1 show up before + * the wakeup_task is reset. This may be overkill since + * wakeup_reset does a spin_unlock after setting the + * wakeup_task to NULL, but I want to be safe. + * This is a slow path anyway. + */ + smp_wmb(); + + tracer_enabled = 1; + + return; +fail_deprobe_wake_new: + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &wakeup_trace); +fail_deprobe: + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &wakeup_trace); +} + +static void stop_wakeup_tracer(struct trace_array *tr) +{ + tracer_enabled = 0; + marker_probe_unregister("kernel_sched_schedule", + sched_switch_callback, + &wakeup_trace); + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &wakeup_trace); + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &wakeup_trace); +} + +static void wakeup_tracer_init(struct trace_array *tr) +{ + wakeup_trace = tr; + + if (tr->ctrl) + start_wakeup_tracer(tr); +} + +static void wakeup_tracer_reset(struct trace_array *tr) +{ + if (tr->ctrl) { + stop_wakeup_tracer(tr); + /* make sure we put back any tasks we are tracing */ + wakeup_reset(tr); + } +} + +static void wakeup_tracer_ctrl_update(struct trace_array *tr) +{ + if (tr->ctrl) + start_wakeup_tracer(tr); + else + stop_wakeup_tracer(tr); +} + +static void wakeup_tracer_open(struct trace_iterator *iter) +{ + /* stop the trace while dumping */ + if (iter->tr->ctrl) + stop_wakeup_tracer(iter->tr); +} + +static void wakeup_tracer_close(struct trace_iterator *iter) +{ + /* forget about any processes we were recording */ + if (iter->tr->ctrl) + start_wakeup_tracer(iter->tr); +} + +static struct tracer wakeup_tracer __read_mostly = +{ + .name = "wakeup", + .init = wakeup_tracer_init, + .reset = wakeup_tracer_reset, + .open = wakeup_tracer_open, + .close = wakeup_tracer_close, + .ctrl_update = wakeup_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_wakeup, +#endif +}; + +__init static int init_wakeup_tracer(void) +{ + int ret; + + ret = register_tracer(&wakeup_tracer); + if (ret) + return ret; + + return 0; +} +device_initcall(init_wakeup_tracer); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c new file mode 100644 index 000000000000..5588ecc40985 --- /dev/null +++ b/kernel/trace/trace_selftest.c @@ -0,0 +1,562 @@ +/* Include in trace.c */ + +#include <linux/kthread.h> +#include <linux/delay.h> + +static inline int trace_valid_entry(struct trace_entry *entry) +{ + switch (entry->type) { + case TRACE_FN: + case TRACE_CTX: + case TRACE_WAKE: + case TRACE_STACK: + case TRACE_SPECIAL: + return 1; + } + return 0; +} + +static int +trace_test_buffer_cpu(struct trace_array *tr, struct trace_array_cpu *data) +{ + struct trace_entry *entries; + struct page *page; + int idx = 0; + int i; + + BUG_ON(list_empty(&data->trace_pages)); + page = list_entry(data->trace_pages.next, struct page, lru); + entries = page_address(page); + + if (head_page(data) != entries) + goto failed; + + /* + * The starting trace buffer always has valid elements, + * if any element exists. + */ + entries = head_page(data); + + for (i = 0; i < tr->entries; i++) { + + if (i < data->trace_idx && !trace_valid_entry(&entries[idx])) { + printk(KERN_CONT ".. invalid entry %d ", + entries[idx].type); + goto failed; + } + + idx++; + if (idx >= ENTRIES_PER_PAGE) { + page = virt_to_page(entries); + if (page->lru.next == &data->trace_pages) { + if (i != tr->entries - 1) { + printk(KERN_CONT ".. entries buffer mismatch"); + goto failed; + } + } else { + page = list_entry(page->lru.next, struct page, lru); + entries = page_address(page); + } + idx = 0; + } + } + + page = virt_to_page(entries); + if (page->lru.next != &data->trace_pages) { + printk(KERN_CONT ".. too many entries"); + goto failed; + } + + return 0; + + failed: + /* disable tracing */ + tracing_disabled = 1; + printk(KERN_CONT ".. corrupted trace buffer .. "); + return -1; +} + +/* + * Test the trace buffer to see if all the elements + * are still sane. + */ +static int trace_test_buffer(struct trace_array *tr, unsigned long *count) +{ + unsigned long flags, cnt = 0; + int cpu, ret = 0; + + /* Don't allow flipping of max traces now */ + raw_local_irq_save(flags); + __raw_spin_lock(&ftrace_max_lock); + for_each_possible_cpu(cpu) { + if (!head_page(tr->data[cpu])) + continue; + + cnt += tr->data[cpu]->trace_idx; + + ret = trace_test_buffer_cpu(tr, tr->data[cpu]); + if (ret) + break; + } + __raw_spin_unlock(&ftrace_max_lock); + raw_local_irq_restore(flags); + + if (count) + *count = cnt; + + return ret; +} + +#ifdef CONFIG_FTRACE + +#ifdef CONFIG_DYNAMIC_FTRACE + +#define __STR(x) #x +#define STR(x) __STR(x) + +/* Test dynamic code modification and ftrace filters */ +int trace_selftest_startup_dynamic_tracing(struct tracer *trace, + struct trace_array *tr, + int (*func)(void)) +{ + unsigned long count; + int ret; + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + + /* The ftrace test PASSED */ + printk(KERN_CONT "PASSED\n"); + pr_info("Testing dynamic ftrace: "); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* passed in by parameter to fool gcc from optimizing */ + func(); + + /* update the records */ + ret = ftrace_force_update(); + if (ret) { + printk(KERN_CONT ".. ftraced failed .. "); + return ret; + } + + /* + * Some archs *cough*PowerPC*cough* add charachters to the + * start of the function names. We simply put a '*' to + * accomodate them. + */ + func_name = "*" STR(DYN_FTRACE_TEST_NAME); + + /* filter only on our function */ + ftrace_set_filter(func_name, strlen(func_name), 1); + + /* enable tracing */ + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + + /* we should have nothing in the buffer */ + ret = trace_test_buffer(tr, &count); + if (ret) + goto out; + + if (count) { + ret = -1; + printk(KERN_CONT ".. filter did not filter .. "); + goto out; + } + + /* call our function again */ + func(); + + /* sleep again */ + msleep(100); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + ftrace_enabled = 0; + + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + /* we should only have one item */ + if (!ret && count != 1) { + printk(KERN_CONT ".. filter failed count=%ld ..", count); + ret = -1; + goto out; + } + out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + /* Enable tracing on all functions again */ + ftrace_set_filter(NULL, 0, 1); + + return ret; +} +#else +# define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; }) +#endif /* CONFIG_DYNAMIC_FTRACE */ +/* + * Simple verification test of ftrace function tracer. + * Enable ftrace, sleep 1/10 second, and then read the trace + * buffer to see if all is in order. + */ +int +trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + + /* make sure msleep has been recorded */ + msleep(1); + + /* force the recorded functions to be traced */ + ret = ftrace_force_update(); + if (ret) { + printk(KERN_CONT ".. ftraced failed .. "); + return ret; + } + + /* start the tracing */ + ftrace_enabled = 1; + tracer_enabled = 1; + + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + ftrace_enabled = 0; + + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + ret = trace_selftest_startup_dynamic_tracing(trace, tr, + DYN_FTRACE_TEST_NAME); + + out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + /* kill ftrace totally if we failed */ + if (ret) + ftrace_kill(); + + return ret; +} +#endif /* CONFIG_FTRACE */ + +#ifdef CONFIG_IRQSOFF_TRACER +int +trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* reset the max latency */ + tracing_max_latency = 0; + /* disable interrupts for a bit */ + local_irq_disable(); + udelay(100); + local_irq_enable(); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (!ret) + ret = trace_test_buffer(&max_tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + tracing_max_latency = save_max; + + return ret; +} +#endif /* CONFIG_IRQSOFF_TRACER */ + +#ifdef CONFIG_PREEMPT_TRACER +int +trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* reset the max latency */ + tracing_max_latency = 0; + /* disable preemption for a bit */ + preempt_disable(); + udelay(100); + preempt_enable(); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (!ret) + ret = trace_test_buffer(&max_tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + tracing_max_latency = save_max; + + return ret; +} +#endif /* CONFIG_PREEMPT_TRACER */ + +#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER) +int +trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + + /* reset the max latency */ + tracing_max_latency = 0; + + /* disable preemption and interrupts for a bit */ + preempt_disable(); + local_irq_disable(); + udelay(100); + preempt_enable(); + /* reverse the order of preempt vs irqs */ + local_irq_enable(); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (ret) + goto out; + + ret = trace_test_buffer(&max_tr, &count); + if (ret) + goto out; + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + /* do the test by disabling interrupts first this time */ + tracing_max_latency = 0; + tr->ctrl = 1; + trace->ctrl_update(tr); + preempt_disable(); + local_irq_disable(); + udelay(100); + preempt_enable(); + /* reverse the order of preempt vs irqs */ + local_irq_enable(); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (ret) + goto out; + + ret = trace_test_buffer(&max_tr, &count); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + out: + trace->reset(tr); + tracing_max_latency = save_max; + + return ret; +} +#endif /* CONFIG_IRQSOFF_TRACER && CONFIG_PREEMPT_TRACER */ + +#ifdef CONFIG_SCHED_TRACER +static int trace_wakeup_test_thread(void *data) +{ + /* Make this a RT thread, doesn't need to be too high */ + struct sched_param param = { .sched_priority = 5 }; + struct completion *x = data; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + + /* Make it know we have a new prio */ + complete(x); + + /* now go to sleep and let the test wake us up */ + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + + /* we are awake, now wait to disappear */ + while (!kthread_should_stop()) { + /* + * This is an RT task, do short sleeps to let + * others run. + */ + msleep(100); + } + + return 0; +} + +int +trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + struct task_struct *p; + struct completion isrt; + unsigned long count; + int ret; + + init_completion(&isrt); + + /* create a high prio thread */ + p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test"); + if (IS_ERR(p)) { + printk(KERN_CONT "Failed to create ftrace wakeup test thread "); + return -1; + } + + /* make sure the thread is running at an RT prio */ + wait_for_completion(&isrt); + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* reset the max latency */ + tracing_max_latency = 0; + + /* sleep to let the RT thread sleep too */ + msleep(100); + + /* + * Yes this is slightly racy. It is possible that for some + * strange reason that the RT thread we created, did not + * call schedule for 100ms after doing the completion, + * and we do a wakeup on a task that already is awake. + * But that is extremely unlikely, and the worst thing that + * happens in such a case, is that we disable tracing. + * Honestly, if this race does happen something is horrible + * wrong with the system. + */ + + wake_up_process(p); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (!ret) + ret = trace_test_buffer(&max_tr, &count); + + + trace->reset(tr); + + tracing_max_latency = save_max; + + /* kill the thread */ + kthread_stop(p); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + return ret; +} +#endif /* CONFIG_SCHED_TRACER */ + +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +int +trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + return ret; +} +#endif /* CONFIG_CONTEXT_SWITCH_TRACER */ + +#ifdef CONFIG_SYSPROF_TRACER +int +trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + return ret; +} +#endif /* CONFIG_SYSPROF_TRACER */ diff --git a/kernel/trace/trace_selftest_dynamic.c b/kernel/trace/trace_selftest_dynamic.c new file mode 100644 index 000000000000..54dd77cce5bf --- /dev/null +++ b/kernel/trace/trace_selftest_dynamic.c @@ -0,0 +1,7 @@ +#include "trace.h" + +int DYN_FTRACE_TEST_NAME(void) +{ + /* used to call mcount */ + return 0; +} diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c new file mode 100644 index 000000000000..2301e1e7c606 --- /dev/null +++ b/kernel/trace/trace_sysprof.c @@ -0,0 +1,363 @@ +/* + * trace stack traces + * + * Copyright (C) 2004-2008, Soeren Sandmann + * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + */ +#include <linux/kallsyms.h> +#include <linux/debugfs.h> +#include <linux/hrtimer.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/module.h> +#include <linux/irq.h> +#include <linux/fs.h> + +#include <asm/stacktrace.h> + +#include "trace.h" + +static struct trace_array *sysprof_trace; +static int __read_mostly tracer_enabled; + +/* + * 1 msec sample interval by default: + */ +static unsigned long sample_period = 1000000; +static const unsigned int sample_max_depth = 512; + +static DEFINE_MUTEX(sample_timer_lock); +/* + * Per CPU hrtimers that do the profiling: + */ +static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer); + +struct stack_frame { + const void __user *next_fp; + unsigned long return_address; +}; + +static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) +{ + int ret; + + if (!access_ok(VERIFY_READ, fp, sizeof(*frame))) + return 0; + + ret = 1; + pagefault_disable(); + if (__copy_from_user_inatomic(frame, fp, sizeof(*frame))) + ret = 0; + pagefault_enable(); + + return ret; +} + +struct backtrace_info { + struct trace_array_cpu *data; + struct trace_array *tr; + int pos; +}; + +static void +backtrace_warning_symbol(void *data, char *msg, unsigned long symbol) +{ + /* Ignore warnings */ +} + +static void backtrace_warning(void *data, char *msg) +{ + /* Ignore warnings */ +} + +static int backtrace_stack(void *data, char *name) +{ + /* Don't bother with IRQ stacks for now */ + return -1; +} + +static void backtrace_address(void *data, unsigned long addr, int reliable) +{ + struct backtrace_info *info = data; + + if (info->pos < sample_max_depth && reliable) { + __trace_special(info->tr, info->data, 1, addr, 0); + + info->pos++; + } +} + +const static struct stacktrace_ops backtrace_ops = { + .warning = backtrace_warning, + .warning_symbol = backtrace_warning_symbol, + .stack = backtrace_stack, + .address = backtrace_address, +}; + +static int +trace_kernel(struct pt_regs *regs, struct trace_array *tr, + struct trace_array_cpu *data) +{ + struct backtrace_info info; + unsigned long bp; + char *stack; + + info.tr = tr; + info.data = data; + info.pos = 1; + + __trace_special(info.tr, info.data, 1, regs->ip, 0); + + stack = ((char *)regs + sizeof(struct pt_regs)); +#ifdef CONFIG_FRAME_POINTER + bp = regs->bp; +#else + bp = 0; +#endif + + dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, &info); + + return info.pos; +} + +static void timer_notify(struct pt_regs *regs, int cpu) +{ + struct trace_array_cpu *data; + struct stack_frame frame; + struct trace_array *tr; + const void __user *fp; + int is_user; + int i; + + if (!regs) + return; + + tr = sysprof_trace; + data = tr->data[cpu]; + is_user = user_mode(regs); + + if (!current || current->pid == 0) + return; + + if (is_user && current->state != TASK_RUNNING) + return; + + __trace_special(tr, data, 0, 0, current->pid); + + if (!is_user) + i = trace_kernel(regs, tr, data); + else + i = 0; + + /* + * Trace user stack if we are not a kernel thread + */ + if (current->mm && i < sample_max_depth) { + regs = (struct pt_regs *)current->thread.sp0 - 1; + + fp = (void __user *)regs->bp; + + __trace_special(tr, data, 2, regs->ip, 0); + + while (i < sample_max_depth) { + frame.next_fp = 0; + frame.return_address = 0; + if (!copy_stack_frame(fp, &frame)) + break; + if ((unsigned long)fp < regs->sp) + break; + + __trace_special(tr, data, 2, frame.return_address, + (unsigned long)fp); + fp = frame.next_fp; + + i++; + } + + } + + /* + * Special trace entry if we overflow the max depth: + */ + if (i == sample_max_depth) + __trace_special(tr, data, -1, -1, -1); + + __trace_special(tr, data, 3, current->pid, i); +} + +static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer) +{ + /* trace here */ + timer_notify(get_irq_regs(), smp_processor_id()); + + hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); + + return HRTIMER_RESTART; +} + +static void start_stack_timer(int cpu) +{ + struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu); + + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = stack_trace_timer_fn; + hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; + + hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL); +} + +static void start_stack_timers(void) +{ + cpumask_t saved_mask = current->cpus_allowed; + int cpu; + + for_each_online_cpu(cpu) { + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); + start_stack_timer(cpu); + } + set_cpus_allowed_ptr(current, &saved_mask); +} + +static void stop_stack_timer(int cpu) +{ + struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu); + + hrtimer_cancel(hrtimer); +} + +static void stop_stack_timers(void) +{ + int cpu; + + for_each_online_cpu(cpu) + stop_stack_timer(cpu); +} + +static void stack_reset(struct trace_array *tr) +{ + int cpu; + + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); +} + +static void start_stack_trace(struct trace_array *tr) +{ + mutex_lock(&sample_timer_lock); + stack_reset(tr); + start_stack_timers(); + tracer_enabled = 1; + mutex_unlock(&sample_timer_lock); +} + +static void stop_stack_trace(struct trace_array *tr) +{ + mutex_lock(&sample_timer_lock); + stop_stack_timers(); + tracer_enabled = 0; + mutex_unlock(&sample_timer_lock); +} + +static void stack_trace_init(struct trace_array *tr) +{ + sysprof_trace = tr; + + if (tr->ctrl) + start_stack_trace(tr); +} + +static void stack_trace_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_stack_trace(tr); +} + +static void stack_trace_ctrl_update(struct trace_array *tr) +{ + /* When starting a new trace, reset the buffers */ + if (tr->ctrl) + start_stack_trace(tr); + else + stop_stack_trace(tr); +} + +static struct tracer stack_trace __read_mostly = +{ + .name = "sysprof", + .init = stack_trace_init, + .reset = stack_trace_reset, + .ctrl_update = stack_trace_ctrl_update, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_sysprof, +#endif +}; + +__init static int init_stack_trace(void) +{ + return register_tracer(&stack_trace); +} +device_initcall(init_stack_trace); + +#define MAX_LONG_DIGITS 22 + +static ssize_t +sysprof_sample_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_LONG_DIGITS]; + int r; + + r = sprintf(buf, "%ld\n", nsecs_to_usecs(sample_period)); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +sysprof_sample_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_LONG_DIGITS]; + unsigned long val; + + if (cnt > MAX_LONG_DIGITS-1) + cnt = MAX_LONG_DIGITS-1; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + val = simple_strtoul(buf, NULL, 10); + /* + * Enforce a minimum sample period of 100 usecs: + */ + if (val < 100) + val = 100; + + mutex_lock(&sample_timer_lock); + stop_stack_timers(); + sample_period = val * 1000; + start_stack_timers(); + mutex_unlock(&sample_timer_lock); + + return cnt; +} + +static struct file_operations sysprof_sample_fops = { + .read = sysprof_sample_read, + .write = sysprof_sample_write, +}; + +void init_tracer_sysprof_debugfs(struct dentry *d_tracer) +{ + struct dentry *entry; + + entry = debugfs_create_file("sysprof_sample_period", 0644, + d_tracer, NULL, &sysprof_sample_fops); + if (entry) + return; + pr_warning("Could not create debugfs 'dyn_ftrace_total_info' entry\n"); +} diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d2099f41aa1e..d8b6279a9b42 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -634,6 +634,8 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. +source kernel/trace/Kconfig + config PROVIDE_OHCI1394_DMA_INIT bool "Remote debugging over FireWire early on boot" depends on PCI && X86 diff --git a/lib/Makefile b/lib/Makefile index 74b0cfb1fcc3..4b836a53c08f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -8,6 +8,15 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o prio_heap.o ratelimit.o +ifdef CONFIG_FTRACE +# Do not profile string.o, since it may be used in early boot or vdso +CFLAGS_REMOVE_string.o = -pg +# Also do not profile any debug utilities +CFLAGS_REMOVE_spinlock_debug.o = -pg +CFLAGS_REMOVE_list_debug.o = -pg +CFLAGS_REMOVE_debugobjects.o = -pg +endif + lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 6c90fb90e19c..3b4dc098181e 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -7,7 +7,7 @@ #include <linux/kallsyms.h> #include <linux/sched.h> -unsigned int debug_smp_processor_id(void) +notrace unsigned int debug_smp_processor_id(void) { unsigned long preempt_count = preempt_count(); int this_cpu = raw_smp_processor_id(); @@ -37,7 +37,7 @@ unsigned int debug_smp_processor_id(void) /* * Avoid recursion: */ - preempt_disable(); + preempt_disable_notrace(); if (!printk_ratelimit()) goto out_enable; @@ -49,7 +49,7 @@ unsigned int debug_smp_processor_id(void) dump_stack(); out_enable: - preempt_enable_no_resched(); + preempt_enable_no_resched_notrace(); out: return this_cpu; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 789b6adbef37..b38f700825fc 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -126,8 +126,6 @@ static void background_writeout(unsigned long _min_pages); static struct prop_descriptor vm_completions; static struct prop_descriptor vm_dirties; -static unsigned long determine_dirtyable_memory(void); - /* * couple the period to the dirty_ratio: * @@ -347,7 +345,13 @@ static unsigned long highmem_dirtyable_memory(unsigned long total) #endif } -static unsigned long determine_dirtyable_memory(void) +/** + * determine_dirtyable_memory - amount of memory that may be used + * + * Returns the numebr of pages that can currently be freed and used + * by the kernel for direct mappings. + */ +unsigned long determine_dirtyable_memory(void) { unsigned long x; diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 8e440233c27d..ea48b82a3707 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -96,7 +96,8 @@ basename_flags = -D"KBUILD_BASENAME=KBUILD_STR($(call name-fix,$(basetarget)))" modname_flags = $(if $(filter 1,$(words $(modname))),\ -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))") -_c_flags = $(KBUILD_CFLAGS) $(ccflags-y) $(CFLAGS_$(basetarget).o) +orig_c_flags = $(KBUILD_CFLAGS) $(ccflags-y) $(CFLAGS_$(basetarget).o) +_c_flags = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(orig_c_flags)) _a_flags = $(KBUILD_AFLAGS) $(asflags-y) $(AFLAGS_$(basetarget).o) _cpp_flags = $(KBUILD_CPPFLAGS) $(cppflags-y) $(CPPFLAGS_$(@F)) |