diff options
Diffstat (limited to 'arch')
44 files changed, 1239 insertions, 41 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b786e68914d..3845e5c8a34 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -14,6 +14,8 @@ config ARM select HAVE_OPROFILE select HAVE_KPROBES if (!XIP_KERNEL) select HAVE_KRETPROBES if (HAVE_KPROBES) + select HAVE_FTRACE if (!XIP_KERNEL) + select HAVE_DYNAMIC_FTRACE if (HAVE_FTRACE) help The ARM series is a line of low-power-consumption RISC chip designs licensed by ARM Ltd and targeted at embedded applications and diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index de9d9ee5095..95baac4939e 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -69,6 +69,12 @@ SEDFLAGS = s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/ targets := vmlinux vmlinux.lds piggy.gz piggy.o font.o font.c \ head.o misc.o $(OBJS) + +ifeq ($(CONFIG_FTRACE),y) +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) +endif + EXTRA_CFLAGS := -fpic -fno-builtin EXTRA_AFLAGS := diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index ad455ff5aeb..eb9092ca800 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -4,6 +4,10 @@ AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) +ifdef CONFIG_DYNAMIC_FTRACE +CFLAGS_REMOVE_ftrace.o = -pg +endif + # Object file lists. obj-y := compat.o entry-armv.o entry-common.o irq.o \ @@ -18,6 +22,7 @@ obj-$(CONFIG_ARTHUR) += arthur.o obj-$(CONFIG_ISA_DMA) += dma-isa.o obj-$(CONFIG_PCI) += bios32.o isa.o obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_KPROBES) += kprobes.o kprobes-decode.o obj-$(CONFIG_ATAGS_PROC) += atags.o diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index 688b7b1ee41..3b132215cbf 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -48,6 +48,11 @@ extern void __aeabi_ulcmp(void); extern void fpundefinstr(void); extern void fp_enter(void); +#ifdef CONFIG_FTRACE +extern void mcount(void); +EXPORT_SYMBOL(mcount); +#endif + /* * This has a special calling convention; it doesn't * modify any of the usual registers, except for LR. diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 597ed00a08d..8f79a4789ed 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -99,6 +99,53 @@ ENTRY(ret_from_fork) #undef CALL #define CALL(x) .long x +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(mcount) + stmdb sp!, {r0-r3, lr} + mov r0, lr + + .globl mcount_call +mcount_call: + bl ftrace_stub + ldmia sp!, {r0-r3, pc} + +ENTRY(ftrace_caller) + stmdb sp!, {r0-r3, lr} + ldr r1, [fp, #-4] + mov r0, lr + + .globl ftrace_call +ftrace_call: + bl ftrace_stub + ldmia sp!, {r0-r3, pc} + +#else + +ENTRY(mcount) + stmdb sp!, {r0-r3, lr} + ldr r0, =ftrace_trace_function + ldr r2, [r0] + adr r0, ftrace_stub + cmp r0, r2 + bne trace + ldmia sp!, {r0-r3, pc} + +trace: + ldr r1, [fp, #-4] + mov r0, lr + mov lr, pc + mov pc, r2 + ldmia sp!, {r0-r3, pc} + +#endif /* CONFIG_DYNAMIC_FTRACE */ + + .globl ftrace_stub +ftrace_stub: + mov pc, lr + +#endif /* CONFIG_FTRACE */ + /*============================================================================= * SWI handler *----------------------------------------------------------------------------- diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c new file mode 100644 index 00000000000..22f3d6e309f --- /dev/null +++ b/arch/arm/kernel/ftrace.c @@ -0,0 +1,118 @@ +/* + * Dynamic function tracing support. + * + * Copyright (C) 2008 Abhishek Sagar <sagar.abhishek@gmail.com> + * + * For licencing details, see COPYING. + * + * Defines low-level handling of mcount calls when the kernel + * is compiled with the -pg flag. When using dynamic ftrace, the + * mcount call-sites get patched lazily with NOP till they are + * enabled. All code mutation routines here take effect atomically. + */ + +#include <linux/ftrace.h> +#include <asm/cacheflush.h> + +#define INSN_SIZE 4 +#define PC_OFFSET 8 +#define BL_OPCODE 0xeb000000 +#define BL_OFFSET_MASK 0x00ffffff + +static unsigned long bl_insn; +static const unsigned long NOP = 0xe1a00000; /* mov r0, r0 */ + +unsigned char *ftrace_nop_replace(void) +{ + return (char *)&NOP; +} + +/* construct a branch (BL) instruction to addr */ +unsigned char *ftrace_call_replace(unsigned long pc, unsigned long addr) +{ + long offset; + + offset = (long)addr - (long)(pc - INSN_SIZE + PC_OFFSET); + if (unlikely(offset < -33554432 || offset > 33554428)) { + /* Can't generate branches that far (from ARM ARM). Ftrace + * doesn't generate branches outside of core kernel text. + */ + WARN_ON_ONCE(1); + return NULL; + } + offset = (offset >> 2) & BL_OFFSET_MASK; + bl_insn = BL_OPCODE | offset; + return (unsigned char *)&bl_insn; +} + +int ftrace_modify_code(unsigned long pc, unsigned char *old_code, + unsigned char *new_code) +{ + unsigned long err = 0, replaced = 0, old, new; + + old = *(unsigned long *)old_code; + new = *(unsigned long *)new_code; + pc -= INSN_SIZE; + + __asm__ __volatile__ ( + "1: ldr %1, [%2] \n" + " cmp %1, %4 \n" + "2: streq %3, [%2] \n" + " cmpne %1, %3 \n" + " movne %0, #2 \n" + "3:\n" + + ".section .fixup, \"ax\"\n" + "4: mov %0, #1 \n" + " b 3b \n" + ".previous\n" + + ".section __ex_table, \"a\"\n" + " .long 1b, 4b \n" + " .long 2b, 4b \n" + ".previous\n" + + : "=r"(err), "=r"(replaced) + : "r"(pc), "r"(new), "r"(old), "0"(err), "1"(replaced) + : "memory"); + + if (!err && (replaced == old)) + flush_icache_range(pc, pc + INSN_SIZE); + + return err; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + int ret; + unsigned long pc, old; + unsigned char *new; + + pc = (unsigned long)&ftrace_call; + pc += INSN_SIZE; + memcpy(&old, &ftrace_call, INSN_SIZE); + new = ftrace_call_replace(pc, (unsigned long)func); + ret = ftrace_modify_code(pc, (unsigned char *)&old, new); + return ret; +} + +int ftrace_mcount_set(unsigned long *data) +{ + unsigned long pc, old; + unsigned long *addr = data; + unsigned char *new; + + pc = (unsigned long)&mcount_call; + pc += INSN_SIZE; + memcpy(&old, &mcount_call, INSN_SIZE); + new = ftrace_call_replace(pc, *addr); + *addr = ftrace_modify_code(pc, (unsigned char *)&old, new); + return 0; +} + +/* run from kstop_machine */ +int __init ftrace_dyn_arch_init(void *data) +{ + ftrace_mcount_set(data); + return 0; +} diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 5593dd20721..5ee39e10c8d 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -274,7 +274,7 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, * for kretprobe handlers which should normally be interested in r0 only * anyway. */ -static void __attribute__((naked)) __kprobes kretprobe_trampoline(void) +void __naked __kprobes kretprobe_trampoline(void) { __asm__ __volatile__ ( "stmdb sp!, {r0 - r11} \n\t" diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3934e265940..a5e9912e2d3 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 2346d271fbf..f3f5e264143 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 0c8614d9875..3b1dd29d9f9 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -1035,3 +1035,126 @@ 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) + lwz r5,0(r5) + + mtctr r5 + bctrl + + 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 c0db5b769e5..2c4d9e056ea 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 00000000000..e12c593ab9c --- /dev/null +++ b/arch/powerpc/kernel/ftrace.c @@ -0,0 +1,161 @@ +/* + * 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 + +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; + + /* + * It would be nice to just use create_function_call, but that will + * update the code itself. Here we need to just return the + * instruction that is going to be modified, without modifying the + * code. + */ + addr = GET_ADDR(addr); + + /* Set to "bl addr" */ + op = 0x48000001 | (ftrace_calc_offset(ip, addr) & 0x03fffffc); + + /* + * 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 e31aca9208e..1882bf419fa 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 bcc249d90c4..dcc946e6709 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/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index d3ac631cbd2..a8d02506468 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -42,6 +42,7 @@ #include <asm/div64.h> #include <asm/signal.h> #include <asm/dcr.h> +#include <asm/ftrace.h> #ifdef CONFIG_PPC32 extern void transfer_to_handler(void); @@ -67,6 +68,10 @@ EXPORT_SYMBOL(single_step_exception); EXPORT_SYMBOL(sys_sigreturn); #endif +#ifdef CONFIG_FTRACE +EXPORT_SYMBOL(_mcount); +#endif + EXPORT_SYMBOL(strcpy); EXPORT_SYMBOL(strncpy); EXPORT_SYMBOL(strcat); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 5112a4aa801..19e8fcb9cea 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -81,7 +81,7 @@ 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 +111,7 @@ 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 +133,7 @@ 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/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index 4d72c8f7215..89774177b20 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 eb36f3b746b..fca9246470b 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 6a4d28a4076..d6d32d178fc 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 ec4f5ebb1ca..418b5782096 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 00000000000..c17373195b1 --- /dev/null +++ b/arch/sparc64/kernel/ftrace.c @@ -0,0 +1,92 @@ +#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 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 9e4534b485c..7735a7a6053 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 52e18e6d2ba..b0937c03af3 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 18363374d51..f395fd537c5 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 5e618c3b472..739d49acd2f 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 65c7857a90d..2763cb37b55 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 c778e4fa55a..04ea83ccb97 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 556a8df522a..fe25e5febca 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 00000000000..55828149e01 --- /dev/null +++ b/arch/x86/kernel/ftrace.c @@ -0,0 +1,149 @@ +/* + * 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)); +}; + +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), "c"(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 deb43785e92..29999dbb754 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 d0b234c9fc3..88923fd7a6f 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 576a03db451..1558fdc174f 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 e2db9ac5c61..347a7aba8b1 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 c6eb5c91e5f..ea090e6cfe3 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 61efa2f7d56..4063dfa2a02 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 f6c05d0410f..122885bc5f3 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 76f60f52a88..84aa2883fe1 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 00000000000..650b11e00ec --- /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 e009251d4e9..bf9a7d5a542 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 8bcb6f40ccb..42394b353c6 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 ec30d10154b..f96eca21ad8 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 156e6d7b0e3..a5fd2e06f5c 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 efa2ba7c600..1ef0f90813d 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 c8097f17f8a..9fbc6b20026 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; |