diff options
33 files changed, 1161 insertions, 196 deletions
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt index 753f4de4b17..35a78bc6651 100644 --- a/Documentation/ftrace.txt +++ b/Documentation/ftrace.txt @@ -324,7 +324,7 @@ output. To see what is available, simply cat the file: cat /debug/tracing/trace_options print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \ - noblock nostacktrace nosched-tree + noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj To disable one of the options, echo in the option prepended with "no". @@ -378,6 +378,20 @@ Here are the available options: When a trace is recorded, so is the stack of functions. This allows for back traces of trace sites. + userstacktrace - This option changes the trace. + It records a stacktrace of the current userspace thread. + + sym-userobj - when user stacktrace are enabled, look up which object the + address belongs to, and print a relative address + This is especially useful when ASLR is on, otherwise you don't + get a chance to resolve the address to object/file/line after the app is no + longer running + + The lookup is performed when you read trace,trace_pipe,latency_trace. Example: + + a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0 +x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] + sched-tree - TBD (any users??) diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt index 5bbbe209622..cde23b4a12a 100644 --- a/Documentation/tracers/mmiotrace.txt +++ b/Documentation/tracers/mmiotrace.txt @@ -37,7 +37,7 @@ $ echo mmiotrace > /debug/tracing/current_tracer $ cat /debug/tracing/trace_pipe > mydump.txt & Start X or whatever. $ echo "X is up" > /debug/tracing/trace_marker -$ echo none > /debug/tracing/current_tracer +$ echo nop > /debug/tracing/current_tracer Check for lost events. @@ -66,7 +66,7 @@ which action. It is recommended to place descriptive markers about what you do. Shut down mmiotrace (requires root privileges): -$ echo none > /debug/tracing/current_tracer +$ echo nop > /debug/tracing/current_tracer The 'cat' process exits. If it does not, kill it by issuing 'fg' command and pressing ctrl+c. @@ -81,7 +81,9 @@ are: $ cat /debug/tracing/trace_entries gives you a number. Approximately double this number and write it back, for instance: +$ echo 0 > /debug/tracing/tracing_enabled $ echo 128000 > /debug/tracing/trace_entries +$ echo 1 > /debug/tracing/tracing_enabled Then start again from the top. If you are doing a trace for a driver project, e.g. Nouveau, you should also diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index b298f7a631e..e5f2ae8362f 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -7,7 +7,19 @@ #ifndef __ASSEMBLY__ extern void _mcount(void); -#endif + +#ifdef CONFIG_DYNAMIC_FTRACE +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* reloction of mcount call site is the same as the address */ + return addr; +} + +struct dyn_arch_ftrace { + struct module *mod; +}; +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index e5f14b13ccf..08454880a2c 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -34,11 +34,19 @@ struct mod_arch_specific { #ifdef __powerpc64__ unsigned int stubs_section; /* Index of stubs section in module */ unsigned int toc_section; /* What section is the TOC? */ -#else +#ifdef CONFIG_DYNAMIC_FTRACE + unsigned long toc; + unsigned long tramp; +#endif + +#else /* powerpc64 */ /* Indices of PLT sections within module. */ unsigned int core_plt_section; unsigned int init_plt_section; +#ifdef CONFIG_DYNAMIC_FTRACE + unsigned long tramp; #endif +#endif /* powerpc64 */ /* List of BUG addresses, source line numbers and filenames */ struct list_head bug_list; @@ -68,6 +76,12 @@ struct mod_arch_specific { # endif /* MODULE */ #endif +#ifdef CONFIG_DYNAMIC_FTRACE +# ifdef MODULE + asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous"); +# endif /* MODULE */ +#endif + struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index f4b006ed0ab..3271cd698e4 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -9,22 +9,30 @@ #include <linux/spinlock.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> +#include <linux/module.h> #include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/list.h> #include <asm/cacheflush.h> +#include <asm/code-patching.h> #include <asm/ftrace.h> +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(fmt , ...) do { } while (0) +#endif -static unsigned int ftrace_nop = 0x60000000; +static unsigned int ftrace_nop = PPC_NOP_INSTR; #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 +# define GET_ADDR(addr) (*(unsigned long *)addr) #endif @@ -33,12 +41,12 @@ static unsigned int ftrace_calc_offset(long ip, long addr) return (int)(addr - ip); } -unsigned char *ftrace_nop_replace(void) +static unsigned char *ftrace_nop_replace(void) { return (char *)&ftrace_nop; } -unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) { static unsigned int op; @@ -68,49 +76,434 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) # define _ASM_PTR " .long " #endif -int +static 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; + unsigned char replaced[MCOUNT_INSN_SIZE]; /* * Note: Due to modules and __init, code can * disappear and change, we need to protect against faulting - * as well as code changing. + * as well as code changing. We do this by using the + * probe_kernel_* functions. * * No real locking needed, this code is run through - * kstop_machine. + * kstop_machine, or before SMP starts. */ - 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; + + /* read the text we want to modify */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + + /* replace the text with the new text */ + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) + return -EPERM; + + flush_icache_range(ip, ip + 8); + + return 0; +} + +/* + * Helper functions that are the same for both PPC64 and PPC32. + */ +static int test_24bit_addr(unsigned long ip, unsigned long addr) +{ + long diff; + + /* + * Can we get to addr from ip in 24 bits? + * (26 really, since we mulitply by 4 for 4 byte alignment) + */ + diff = addr - ip; + + /* + * Return true if diff is less than 1 << 25 + * and greater than -1 << 26. + */ + return (diff < (1 << 25)) && (diff > (-1 << 26)); +} + +static int is_bl_op(unsigned int op) +{ + return (op & 0xfc000003) == 0x48000001; +} + +static int test_offset(unsigned long offset) +{ + return (offset + 0x2000000 > 0x3ffffff) || ((offset & 3) != 0); +} + +static unsigned long find_bl_target(unsigned long ip, unsigned int op) +{ + static int offset; + + offset = (op & 0x03fffffc); + /* make it signed */ + if (offset & 0x02000000) + offset |= 0xfe000000; + + return ip + (long)offset; +} + +static unsigned int branch_offset(unsigned long offset) +{ + /* return "bl ip+offset" */ + return 0x48000001 | (offset & 0x03fffffc); +} + +#ifdef CONFIG_PPC64 +static int +__ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE * 2]; + unsigned int *op = (unsigned *)&replaced; + unsigned char jmp[8]; + unsigned long *ptr = (unsigned long *)&jmp; + unsigned long ip = rec->ip; + unsigned long tramp; + int offset; + + /* read where this goes */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(*op)) { + printk(KERN_ERR "Not expected bl: opcode is %x\n", *op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, *op); + + /* + * On PPC64 the trampoline looks like: + * 0x3d, 0x82, 0x00, 0x00, addis r12,r2, <high> + * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, <low> + * Where the bytes 2,3,6 and 7 make up the 32bit offset + * to the TOC that holds the pointer. + * to jump to. + * 0xf8, 0x41, 0x00, 0x28, std r2,40(r1) + * 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12) + * The actually address is 32 bytes from the offset + * into the TOC. + * 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12) + */ + + DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc); + + /* Find where the trampoline jumps to */ + if (probe_kernel_read(jmp, (void *)tramp, 8)) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x", + (unsigned)(*ptr >> 32), + (unsigned)*ptr); + + offset = (unsigned)jmp[2] << 24 | + (unsigned)jmp[3] << 16 | + (unsigned)jmp[6] << 8 | + (unsigned)jmp[7]; + + DEBUGP(" %x ", offset); + + /* get the address this jumps too */ + tramp = mod->arch.toc + offset + 32; + DEBUGP("toc: %lx", tramp); + + if (probe_kernel_read(jmp, (void *)tramp, 8)) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x\n", + (unsigned)(*ptr >> 32), + (unsigned)*ptr); + + /* This should match what was called */ + if (*ptr != GET_ADDR(addr)) { + printk(KERN_ERR "addr does not match %lx\n", *ptr); + return -EINVAL; + } + + /* + * We want to nop the line, but the next line is + * 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1) + * This needs to be turned to a nop too. + */ + if (probe_kernel_read(replaced, (void *)(ip+4), MCOUNT_INSN_SIZE)) + return -EFAULT; + + if (*op != 0xe8410028) { + printk(KERN_ERR "Next line is not ld! (%08x)\n", *op); + return -EINVAL; + } + + /* + * Milton Miller pointed out that we can not blindly do nops. + * If a task was preempted when calling a trace function, + * the nops will remove the way to restore the TOC in r2 + * and the r2 TOC will get corrupted. + */ + + /* + * Replace: + * bl <tramp> <==== will be replaced with "b 1f" + * ld r2,40(r1) + * 1: + */ + op[0] = 0x48000008; /* b +8 */ + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} + +#else /* !PPC64 */ +static int +__ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + unsigned int *op = (unsigned *)&replaced; + unsigned char jmp[8]; + unsigned int *ptr = (unsigned int *)&jmp; + unsigned long ip = rec->ip; + unsigned long tramp; + int offset; + + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(*op)) { + printk(KERN_ERR "Not expected bl: opcode is %x\n", *op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, *op); + + /* + * On PPC32 the trampoline looks like: + * lis r11,sym@ha + * addi r11,r11,sym@l + * mtctr r11 + * bctr + */ + + DEBUGP("ip:%lx jumps to %lx", ip, tramp); + + /* Find where the trampoline jumps to */ + if (probe_kernel_read(jmp, (void *)tramp, 8)) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x ", ptr[0], ptr[1]); + + tramp = (ptr[1] & 0xffff) | + ((ptr[0] & 0xffff) << 16); + if (tramp & 0x8000) + tramp -= 0x10000; + + DEBUGP(" %x ", tramp); + + if (tramp != addr) { + printk(KERN_ERR + "Trampoline location %08lx does not match addr\n", + tramp); + return -EINVAL; + } + + op[0] = PPC_NOP_INSTR; + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} +#endif /* PPC64 */ + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + unsigned long ip = rec->ip; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ftrace_call_replace(ip, addr); + new = ftrace_nop_replace(); + return ftrace_modify_code(ip, old, new); + } + + /* + * Out of range jumps are called from modules. + * We should either already have a pointer to the module + * or it has been passed in. + */ + if (!rec->arch.mod) { + if (!mod) { + printk(KERN_ERR "No module loaded addr=%lx\n", + addr); + return -EFAULT; + } + rec->arch.mod = mod; + } else if (mod) { + if (mod != rec->arch.mod) { + printk(KERN_ERR + "Record mod %p not equal to passed in mod %p\n", + rec->arch.mod, mod); + return -EINVAL; + } + /* nothing to do if mod == rec->arch.mod */ + } else + mod = rec->arch.mod; + + return __ftrace_make_nop(mod, rec, addr); + +} + +#ifdef CONFIG_PPC64 +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE * 2]; + unsigned int *op = (unsigned *)&replaced; + unsigned long ip = rec->ip; + unsigned long offset; + + /* read where this goes */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE * 2)) + return -EFAULT; + + /* + * It should be pointing to two nops or + * b +8; ld r2,40(r1) + */ + if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) && + ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) { + printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]); + return -EINVAL; + } + + /* If we never set up a trampoline to ftrace_caller, then bail */ + if (!rec->arch.mod->arch.tramp) { + printk(KERN_ERR "No ftrace trampoline\n"); + return -EINVAL; + } + + /* now calculate a jump to the ftrace caller trampoline */ + offset = rec->arch.mod->arch.tramp - ip; + + if (test_offset(offset)) { + printk(KERN_ERR "REL24 %li out of range!\n", + (long int)offset); + return -EINVAL; + } + + /* Set to "bl addr" */ + op[0] = branch_offset(offset); + /* ld r2,40(r1) */ + op[1] = 0xe8410028; + + DEBUGP("write to %lx\n", rec->ip); + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE * 2)) + return -EPERM; + + return 0; +} +#else +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + unsigned int *op = (unsigned *)&replaced; + unsigned long ip = rec->ip; + unsigned long offset; + + /* read where this goes */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* It should be pointing to a nop */ + if (op[0] != PPC_NOP_INSTR) { + printk(KERN_ERR "Expected NOP but have %x\n", op[0]); + return -EINVAL; + } + + /* If we never set up a trampoline to ftrace_caller, then bail */ + if (!rec->arch.mod->arch.tramp) { + printk(KERN_ERR "No ftrace trampoline\n"); + return -EINVAL; + } + + /* now calculate a jump to the ftrace caller trampoline */ + offset = rec->arch.mod->arch.tramp - ip; + + if (test_offset(offset)) { + printk(KERN_ERR "REL24 %li out of range!\n", + (long int)offset); + return -EINVAL; + } + + /* Set to "bl addr" */ + op[0] = branch_offset(offset); + + DEBUGP("write to %lx\n", rec->ip); + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} +#endif /* CONFIG_PPC64 */ + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + unsigned long ip = rec->ip; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ftrace_nop_replace(); + new = ftrace_call_replace(ip, addr); + return ftrace_modify_code(ip, old, new); + } + + /* + * Out of range jumps are called from modules. + * Being that we are converting from nop, it had better + * already have a module defined. + */ + if (!rec->arch.mod) { + printk(KERN_ERR "No module loaded\n"); + return -EINVAL; + } + + return __ftrace_make_call(rec, addr); } int ftrace_update_ftrace_func(ftrace_func_t func) @@ -128,10 +521,10 @@ int ftrace_update_ftrace_func(ftrace_func_t func) int __init ftrace_dyn_arch_init(void *data) { - /* This is running in kstop_machine */ + /* caller expects data to be zero */ + unsigned long *p = data; - ftrace_mcount_set(data); + *p = 0; return 0; } - diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 31982d05d81..88d9c1d5e5f 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -69,10 +69,15 @@ void cpu_idle(void) smp_mb(); local_irq_disable(); + /* Don't trace irqs off for idle */ + stop_critical_timings(); + /* check again after disabling irqs */ if (!need_resched() && !cpu_should_die()) ppc_md.power_save(); + start_critical_timings(); + local_irq_enable(); set_thread_flag(TIF_POLLING_NRFLAG); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 2df91a03462..f832773fc28 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/ftrace.h> #include <linux/cache.h> #include <linux/bug.h> #include <linux/sort.h> @@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num) r_addend = rela[i].r_addend; } +#ifdef CONFIG_DYNAMIC_FTRACE + _count_relocs++; /* add one for ftrace_caller */ +#endif return _count_relocs; } @@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, return -ENOEXEC; } } +#ifdef CONFIG_DYNAMIC_FTRACE + module->arch.tramp = + do_plt_call(module->module_core, + (unsigned long)ftrace_caller, + sechdrs, module); +#endif return 0; } diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 1af2377e499..8992b031a7b 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -20,6 +20,7 @@ #include <linux/moduleloader.h> #include <linux/err.h> #include <linux/vmalloc.h> +#include <linux/ftrace.h> #include <linux/bug.h> #include <asm/module.h> #include <asm/firmware.h> @@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, } } +#ifdef CONFIG_DYNAMIC_FTRACE + /* make the trampoline to the ftrace_caller */ + relocs++; +#endif + DEBUGP("Looks like a total of %lu stubs, max\n", relocs); return relocs * sizeof(struct ppc64_stub_entry); } @@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } } +#ifdef CONFIG_DYNAMIC_FTRACE + me->arch.toc = my_r2(sechdrs, me); + me->arch.tramp = stub_for_addr(sechdrs, + (unsigned long)ftrace_caller, + me); +#endif + return 0; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7a146baaa99..e49a4fd718f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -36,6 +36,7 @@ config X86 select HAVE_ARCH_TRACEHOOK select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS + select USER_STACKTRACE_SUPPORT config ARCH_DEFCONFIG string diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 2bb43b433e0..754a3e082f9 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -29,7 +29,6 @@ struct dyn_arch_ftrace { #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_RET_TRACER -#define FTRACE_RET_STACK_SIZE 20 #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e90e81ef6ab..0921b4018c1 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -40,36 +40,8 @@ struct thread_info { */ __u8 supervisor_stack[0]; #endif - -#ifdef CONFIG_FUNCTION_RET_TRACER - /* Index of current stored adress in ret_stack */ - int curr_ret_stack; - /* Stack of return addresses for return function tracing */ - struct ftrace_ret_stack ret_stack[FTRACE_RET_STACK_SIZE]; - /* - * Number of functions that haven't been traced - * because of depth overrun. - */ - atomic_t trace_overrun; -#endif }; -#ifdef CONFIG_FUNCTION_RET_TRACER -#define INIT_THREAD_INFO(tsk) \ -{ \ - .task = &tsk, \ - .exec_domain = &default_exec_domain, \ - .flags = 0, \ - .cpu = 0, \ - .preempt_count = 1, \ - .addr_limit = KERNEL_DS, \ - .restart_block = { \ - .fn = do_no_restart_syscall, \ - }, \ - .curr_ret_stack = -1,\ - .trace_overrun = ATOMIC_INIT(0) \ -} -#else #define INIT_THREAD_INFO(tsk) \ { \ .task = &tsk, \ @@ -82,7 +54,6 @@ struct thread_info { .fn = do_no_restart_syscall, \ }, \ } -#endif #define init_thread_info (init_thread_union.thread_info) #define init_stack (init_thread_union.stack) diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 356bb1eb6e9..bb137f7297e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -350,19 +350,21 @@ static int push_return_trace(unsigned long ret, unsigned long long time, unsigned long func) { int index; - struct thread_info *ti = current_thread_info(); + + if (!current->ret_stack) + return -EBUSY; /* The return trace stack is full */ - if (ti->curr_ret_stack == FTRACE_RET_STACK_SIZE - 1) { - atomic_inc(&ti->trace_overrun); + if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { + atomic_inc(¤t->trace_overrun); return -EBUSY; } - index = ++ti->curr_ret_stack; + index = ++current->curr_ret_stack; barrier(); - ti->ret_stack[index].ret = ret; - ti->ret_stack[index].func = func; - ti->ret_stack[index].calltime = time; + current->ret_stack[index].ret = ret; + current->ret_stack[index].func = func; + current->ret_stack[index].calltime = time; return 0; } @@ -373,13 +375,12 @@ static void pop_return_trace(unsigned long *ret, unsigned long long *time, { int index; - struct thread_info *ti = current_thread_info(); - index = ti->curr_ret_stack; - *ret = ti->ret_stack[index].ret; - *func = ti->ret_stack[index].func; - *time = ti->ret_stack[index].calltime; - *overrun = atomic_read(&ti->trace_overrun); - ti->curr_ret_stack--; + index = current->curr_ret_stack; + *ret = current->ret_stack[index].ret; + *func = current->ret_stack[index].func; + *time = current->ret_stack[index].calltime; + *overrun = atomic_read(¤t->trace_overrun); + current->curr_ret_stack--; } /* diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index a03e7f6d90c..10786af9554 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/stacktrace.h> #include <linux/module.h> +#include <linux/uaccess.h> #include <asm/stacktrace.h> static void save_stack_warning(void *data, char *msg) @@ -83,3 +84,66 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); + +/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ + +struct stack_frame { + const void __user *next_fp; + unsigned long ret_addr; +}; + +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; +} + +static inline void __save_stack_trace_user(struct stack_trace *trace) +{ + const struct pt_regs *regs = task_pt_regs(current); + const void __user *fp = (const void __user *)regs->bp; + + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = regs->ip; + + while (trace->nr_entries < trace->max_entries) { + struct stack_frame frame; + + frame.next_fp = NULL; + frame.ret_addr = 0; + if (!copy_stack_frame(fp, &frame)) + break; + if ((unsigned long)fp < regs->sp) + break; + if (frame.ret_addr) { + trace->entries[trace->nr_entries++] = + frame.ret_addr; + } + if (fp == frame.next_fp) + break; + fp = frame.next_fp; + } +} + +void save_stack_trace_user(struct stack_trace *trace) +{ + /* + * Trace user stack if we are not a kernel thread + */ + if (current->mm) { + __save_stack_trace_user(trace); + } + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} + diff --git a/fs/seq_file.c b/fs/seq_file.c index eba2eabcd2b..f03220d7891 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -357,7 +357,18 @@ int seq_printf(struct seq_file *m, const char *f, ...) } EXPORT_SYMBOL(seq_printf); -static char *mangle_path(char *s, char *p, char *esc) +/** + * mangle_path - mangle and copy path to buffer beginning + * @s: buffer start + * @p: beginning of path in above buffer + * @esc: set of characters that need escaping + * + * Copy the path from @p to @s, replacing each occurrence of character from + * @esc with usual octal escape. + * Returns pointer past last written character in @s, or NULL in case of + * failure. + */ +char *mangle_path(char *s, char *p, char *esc) { while (s <= p) { char c = *p++; @@ -376,6 +387,7 @@ static char *mangle_path(char *s, char *p, char *esc) } return NULL; } +EXPORT_SYMBOL_GPL(mangle_path); /* * return the absolute path of 'dentry' residing in mount 'mnt'. diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 3b46ae46493..eba835a2c2c 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -46,16 +46,21 @@ #endif #ifdef CONFIG_TRACE_BRANCH_PROFILING -#define LIKELY_PROFILE() VMLINUX_SYMBOL(__start_likely_profile) = .; \ - *(_ftrace_likely) \ - VMLINUX_SYMBOL(__stop_likely_profile) = .; \ - VMLINUX_SYMBOL(__start_unlikely_profile) = .; \ - *(_ftrace_unlikely) \ - VMLINUX_SYMBOL(__stop_unlikely_profile) = .; +#define LIKELY_PROFILE() VMLINUX_SYMBOL(__start_annotated_branch_profile) = .; \ + *(_ftrace_annotated_branch) \ + VMLINUX_SYMBOL(__stop_annotated_branch_profile) = .; #else #define LIKELY_PROFILE() #endif +#ifdef CONFIG_PROFILE_ALL_BRANCHES +#define BRANCH_PROFILE() VMLINUX_SYMBOL(__start_branch_profile) = .; \ + *(_ftrace_branch) \ + VMLINUX_SYMBOL(__stop_branch_profile) = .; +#else +#define BRANCH_PROFILE() +#endif + /* .data section */ #define DATA_DATA \ *(.data) \ @@ -75,7 +80,8 @@ VMLINUX_SYMBOL(__start___tracepoints) = .; \ *(__tracepoints) \ VMLINUX_SYMBOL(__stop___tracepoints) = .; \ - LIKELY_PROFILE() + LIKELY_PROFILE() \ + BRANCH_PROFILE() #define RO_DATA(align) \ . = ALIGN((align)); \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c7d804a7a4d..ea7c6be354b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -63,8 +63,16 @@ struct ftrace_branch_data { const char *func; const char *file; unsigned line; - unsigned long correct; - unsigned long incorrect; + union { + struct { + unsigned long correct; + unsigned long incorrect; + }; + struct { + unsigned long miss; + unsigned long hit; + }; + }; }; /* @@ -77,34 +85,18 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) -#define likely_check(x) ({ \ +#define __branch_check__(x, expect) ({ \ int ______r; \ static struct ftrace_branch_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_likely"))) \ + __attribute__((section("_ftrace_annotated_branch"))) \ ______f = { \ .func = __func__, \ .file = __FILE__, \ .line = __LINE__, \ }; \ - ______f.line = __LINE__; \ ______r = likely_notrace(x); \ - ftrace_likely_update(&______f, ______r, 1); \ - ______r; \ - }) -#define unlikely_check(x) ({ \ - int ______r; \ - static struct ftrace_branch_data \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_unlikely"))) \ - ______f = { \ - .func = __func__, \ - .file = __FILE__, \ - .line = __LINE__, \ - }; \ - ______f.line = __LINE__; \ - ______r = unlikely_notrace(x); \ - ftrace_likely_update(&______f, ______r, 0); \ + ftrace_likely_update(&______f, ______r, expect); \ ______r; \ }) @@ -114,11 +106,37 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); * written by Daniel Walker. */ # ifndef likely -# define likely(x) (__builtin_constant_p(x) ? !!(x) : likely_check(x)) +# define likely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 1)) # endif # ifndef unlikely -# define unlikely(x) (__builtin_constant_p(x) ? !!(x) : unlikely_check(x)) +# define unlikely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0)) # endif + +#ifdef CONFIG_PROFILE_ALL_BRANCHES +/* + * "Define 'is'", Bill Clinton + * "Define 'if'", Steven Rostedt + */ +#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) : \ + ({ \ + int ______r; \ + static struct ftrace_branch_data \ + __attribute__((__aligned__(4))) \ + __attribute__((section("_ftrace_branch"))) \ + ______f = { \ + .func = __func__, \ + .file = __FILE__, \ + .line = __LINE__, \ + }; \ + ______r = !!(cond); \ + if (______r) \ + ______f.hit++; \ + else \ + ______f.miss++; \ + ______r; \ + })) +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ + #else # define likely(x) __builtin_expect(!!(x), 1) # define unlikely(x) __builtin_expect(!!(x), 0) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f7ba4ea5e12..7854d87b97b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -257,6 +257,7 @@ extern int ftrace_dump_on_oops; extern void tracing_start(void); extern void tracing_stop(void); +extern void ftrace_off_permanent(void); extern void ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); @@ -290,6 +291,7 @@ ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0))); static inline void tracing_start(void) { } static inline void tracing_stop(void) { } +static inline void ftrace_off_permanent(void) { } static inline int ftrace_printk(const char *fmt, ...) { @@ -323,6 +325,8 @@ struct ftrace_retfunc { }; #ifdef CONFIG_FUNCTION_RET_TRACER +#define FTRACE_RETFUNC_DEPTH 50 +#define FTRACE_RETSTACK_ALLOC_SIZE 32 /* Type of a callback handler of tracing return function */ typedef void (*trace_function_return_t)(struct ftrace_retfunc *); @@ -330,6 +334,12 @@ extern int register_ftrace_return(trace_function_return_t func); /* The current handler in use */ extern trace_function_return_t ftrace_function_return; extern void unregister_ftrace_return(void); + +extern void ftrace_retfunc_init_task(struct task_struct *t); +extern void ftrace_retfunc_exit_task(struct task_struct *t); +#else +static inline void ftrace_retfunc_init_task(struct task_struct *t) { } +static inline void ftrace_retfunc_exit_task(struct task_struct *t) { } #endif #endif /* _LINUX_FTRACE_H */ diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index e097c2e6b6d..3bb87a753fa 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -122,6 +122,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts); void tracing_on(void); void tracing_off(void); +void tracing_off_permanent(void); enum ring_buffer_flags { RB_FL_OVERWRITE = 1 << 0, diff --git a/include/linux/sched.h b/include/linux/sched.h index c8e0db46420..bee1e93c95a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1352,6 +1352,17 @@ struct task_struct { unsigned long default_timer_slack_ns; struct list_head *scm_work_list; +#ifdef CONFIG_FUNCTION_RET_TRACER + /* Index of current stored adress in ret_stack */ + int curr_ret_stack; + /* Stack of return addresses for return function tracing */ + struct ftrace_ret_stack *ret_stack; + /* + * Number of functions that haven't been traced + * because of depth overrun. + */ + atomic_t trace_overrun; +#endif }; /* @@ -2006,18 +2017,6 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct { *task_thread_info(p) = *task_thread_info(org); task_thread_info(p)->task = p; - -#ifdef CONFIG_FUNCTION_RET_TRACER - /* - * When fork() creates a child process, this function is called. - * But the child task may not inherit the return adresses traced - * by the return function tracer because it will directly execute - * in userspace and will not return to kernel functions its parent - * used. - */ - task_thread_info(p)->curr_ret_stack = -1; - atomic_set(&task_thread_info(p)->trace_overrun, 0); -#endif } static inline unsigned long *end_of_stack(struct task_struct *p) diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index dc50bcc282a..b3dfa72f13b 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -34,6 +34,7 @@ struct seq_operations { #define SEQ_SKIP 1 +char *mangle_path(char *s, char *p, char *esc); int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); loff_t seq_lseek(struct file *, loff_t, int); diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index b106fd8e0d5..1a8cecc4f38 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -15,9 +15,17 @@ extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); extern void print_stack_trace(struct stack_trace *trace, int spaces); + +#ifdef CONFIG_USER_STACKTRACE_SUPPORT +extern void save_stack_trace_user(struct stack_trace *trace); +#else +# define save_stack_trace_user(trace) do { } while (0) +#endif + #else # define save_stack_trace(trace) do { } while (0) # define save_stack_trace_tsk(tsk, trace) do { } while (0) +# define save_stack_trace_user(trace) do { } while (0) # define print_stack_trace(trace, spaces) do { } while (0) #endif diff --git a/init/main.c b/init/main.c index e810196bf2f..79213c0785d 100644 --- a/init/main.c +++ b/init/main.c @@ -723,7 +723,7 @@ int do_one_initcall(initcall_t fn) disable_boot_trace(); rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - ret.duration = (unsigned long long) delta.tv64 >> 10; + ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10; trace_boot_ret(&ret, fn); printk("initcall %pF returned %d after %Ld usecs\n", fn, ret.result, ret.duration); diff --git a/kernel/exit.c b/kernel/exit.c index 35c8ec2ba03..e5ae36ebe8a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1127,7 +1127,6 @@ NORET_TYPE void do_exit(long code) preempt_disable(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; - schedule(); BUG(); /* Avoid "noreturn function does return". */ diff --git a/kernel/fork.c b/kernel/fork.c index ac62f43ee43..d6e1a3205f6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -47,6 +47,7 @@ #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> +#include <linux/ftrace.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/acct.h> @@ -139,6 +140,7 @@ void free_task(struct task_struct *tsk) prop_local_destroy_single(&tsk->dirties); free_thread_info(tsk->stack); rt_mutex_debug_task_free(tsk); + ftrace_retfunc_exit_task(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); @@ -1269,6 +1271,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, total_forks++; spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); + ftrace_retfunc_init_task(p); proc_fork_connector(p); cgroup_post_fork(p); return p; diff --git a/kernel/sched.c b/kernel/sched.c index 4de56108c86..388d9db044a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5901,6 +5901,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) * The idle tasks have their own, simple scheduling class: */ idle->sched_class = &idle_sched_class; + ftrace_retfunc_init_task(idle); } /* diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index b8378fad29a..9cbf7761f49 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -3,6 +3,9 @@ # select HAVE_FUNCTION_TRACER: # +config USER_STACKTRACE_SUPPORT + bool + config NOP_TRACER bool @@ -166,14 +169,29 @@ config TRACE_BRANCH_PROFILING This tracer profiles all the the likely and unlikely macros in the kernel. It will display the results in: - /debugfs/tracing/profile_likely - /debugfs/tracing/profile_unlikely + /debugfs/tracing/profile_annotated_branch Note: this will add a significant overhead, only turn this on if you need to profile the system's use of these macros. Say N if unsure. +config PROFILE_ALL_BRANCHES + bool "Profile all if conditionals" + depends on TRACE_BRANCH_PROFILING + help + This tracer profiles all branch conditions. Every if () + taken in the kernel is recorded whether it hit or miss. + The results will be displayed in: + + /debugfs/tracing/profile_branch + + This configuration, when enabled, will impose a great overhead + on the system. This should only be enabled when the system + is to be analyzed + + Say N if unsure. + config TRACING_BRANCHES bool help diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f212da48668..53042f118f2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1498,10 +1498,77 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, #ifdef CONFIG_FUNCTION_RET_TRACER +static atomic_t ftrace_retfunc_active; + /* The callback that hooks the return of a function */ trace_function_return_t ftrace_function_return = (trace_function_return_t)ftrace_stub; + +/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */ +static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) +{ + int i; + int ret = 0; + unsigned long flags; + int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE; + struct task_struct *g, *t; + + for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) { + ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack_list[i]) { + start = 0; + end = i; + ret = -ENOMEM; + goto free; + } + } + + read_lock_irqsave(&tasklist_lock, flags); + do_each_thread(g, t) { + if (start == end) { + ret = -EAGAIN; + goto unlock; + } + + if (t->ret_stack == NULL) { + t->ret_stack = ret_stack_list[start++]; + t->curr_ret_stack = -1; + atomic_set(&t->trace_overrun, 0); + } + } while_each_thread(g, t); + +unlock: + read_unlock_irqrestore(&tasklist_lock, flags); +free: + for (i = start; i < end; i++) + kfree(ret_stack_list[i]); + return ret; +} + +/* Allocate a return stack for each task */ +static int start_return_tracing(void) +{ + struct ftrace_ret_stack **ret_stack_list; + int ret; + + ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE * + sizeof(struct ftrace_ret_stack *), + GFP_KERNEL); + + if (!ret_stack_list) + return -ENOMEM; + + do { + ret = alloc_retstack_tasklist(ret_stack_list); + } while (ret == -EAGAIN); + + kfree(ret_stack_list); + return ret; +} + int register_ftrace_return(trace_function_return_t func) { int ret = 0; @@ -1516,7 +1583,12 @@ int register_ftrace_return(trace_function_return_t func) ret = -EBUSY; goto out; } - + atomic_inc(&ftrace_retfunc_active); + ret = start_return_tracing(); + if (ret) { + atomic_dec(&ftrace_retfunc_active); + goto out; + } ftrace_tracing_type = FTRACE_TYPE_RETURN; ftrace_function_return = func; ftrace_startup(); @@ -1530,6 +1602,7 @@ void unregister_ftrace_return(void) { mutex_lock(&ftrace_sysctl_lock); + atomic_dec(&ftrace_retfunc_active); ftrace_function_return = (trace_function_return_t)ftrace_stub; ftrace_shutdown(); /* Restore normal tracing type */ @@ -1537,6 +1610,32 @@ void unregister_ftrace_return(void) mutex_unlock(&ftrace_sysctl_lock); } + +/* Allocate a return stack for newly created task */ +void ftrace_retfunc_init_task(struct task_struct *t) +{ + if (atomic_read(&ftrace_retfunc_active)) { + t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!t->ret_stack) + return; + t->curr_ret_stack = -1; + atomic_set(&t->trace_overrun, 0); + } else + t->ret_stack = NULL; +} + +void ftrace_retfunc_exit_task(struct task_struct *t) +{ + struct ftrace_ret_stack *ret_stack = t->ret_stack; + + t->ret_stack = NULL; + /* NULL must become visible to IRQs before we free it: */ + barrier(); + + kfree(ret_stack); +} #endif diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 85ced143c2c..e206951603c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -18,8 +18,46 @@ #include "trace.h" -/* Global flag to disable all recording to ring buffers */ -static int ring_buffers_off __read_mostly; +/* + * A fast way to enable or disable all ring buffers is to + * call tracing_on or tracing_off. Turning off the ring buffers + * prevents all ring buffers from being recorded to. + * Turning this switch on, makes it OK to write to the + * ring buffer, if the ring buffer is enabled itself. + * + * There's three layers that must be on in order to write + * to the ring buffer. + * + * 1) This global flag must be set. + * 2) The ring buffer must be enabled for recording. + * 3) The per cpu buffer must be enabled for recording. + * + * In case of an anomaly, this global flag has a bit set that + * will permantly disable all ring buffers. + */ + +/* + * Global flag to disable all recording to ring buffers + * This has two bits: ON, DISABLED + * + * ON DISABLED + * ---- ---------- + * 0 0 : ring buffers are off + * 1 0 : ring buffers are on + * X 1 : ring buffers are permanently disabled + */ + +enum { + RB_BUFFERS_ON_BIT = 0, + RB_BUFFERS_DISABLED_BIT = 1, +}; + +enum { + RB_BUFFERS_ON = 1 << RB_BUFFERS_ON_BIT, + RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT, +}; + +static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; /** * tracing_on - enable all tracing buffers @@ -29,7 +67,7 @@ static int ring_buffers_off __read_mostly; */ void tracing_on(void) { - ring_buffers_off = 0; + set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); } /** @@ -42,7 +80,18 @@ void tracing_on(void) */ void tracing_off(void) { - ring_buffers_off = 1; + clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); +} + +/** + * tracing_off_permanent - permanently disable ring buffers + * + * This function, once called, will disable all ring buffers + * permanenty. + */ +void tracing_off_permanent(void) +{ + set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags); } #include "trace.h" @@ -1185,7 +1234,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, struct ring_buffer_event *event; int cpu, resched; - if (ring_buffers_off) + if (ring_buffer_flags != RB_BUFFERS_ON) return NULL; if (atomic_read(&buffer->record_disabled)) @@ -1297,7 +1346,7 @@ int ring_buffer_write(struct ring_buffer *buffer, int ret = -EBUSY; int cpu, resched; - if (ring_buffers_off) + if (ring_buffer_flags != RB_BUFFERS_ON) return -EBUSY; if (atomic_read(&buffer->record_disabled)) @@ -2178,12 +2227,14 @@ static ssize_t rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - int *p = filp->private_data; + long *p = filp->private_data; char buf[64]; int r; - /* !ring_buffers_off == tracing_on */ - r = sprintf(buf, "%d\n", !*p); + if (test_bit(RB_BUFFERS_DISABLED_BIT, p)) + r = sprintf(buf, "permanently disabled\n"); + else + r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p)); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } @@ -2192,7 +2243,7 @@ static ssize_t rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - int *p = filp->private_data; + long *p = filp->private_data; char buf[64]; long val; int ret; @@ -2209,8 +2260,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - /* !ring_buffers_off == tracing_on */ - *p = !val; + if (val) + set_bit(RB_BUFFERS_ON_BIT, p); + else + clear_bit(RB_BUFFERS_ON_BIT, p); (*ppos)++; @@ -2232,7 +2285,7 @@ static __init int rb_init_debugfs(void) d_tracer = tracing_init_dentry(); entry = debugfs_create_file("tracing_on", 0644, d_tracer, - &ring_buffers_off, &rb_simple_fops); + &ring_buffer_flags, &rb_simple_fops); if (!entry) pr_warning("Could not create debugfs 'tracing_on' entry\n"); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4ee6f037522..a45b59e53fb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -30,6 +30,7 @@ #include <linux/gfp.h> #include <linux/fs.h> #include <linux/kprobes.h> +#include <linux/seq_file.h> #include <linux/writeback.h> #include <linux/stacktrace.h> @@ -275,6 +276,8 @@ static const char *trace_options[] = { "ftrace_preempt", "branch", "annotate", + "userstacktrace", + "sym-userobj", NULL }; @@ -421,6 +424,28 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) return trace_seq_putmem(s, hex, j); } +static int +trace_seq_path(struct trace_seq *s, struct path *path) +{ + unsigned char *p; + + if (s->len >= (PAGE_SIZE - 1)) + return 0; + p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); + if (!IS_ERR(p)) { + p = mangle_path(s->buffer + s->len, p, "\n"); + if (p) { + s->len = p - s->buffer; + return 1; + } + } else { + s->buffer[s->len++] = '?'; + return 1; + } + + return 0; +} + static void trace_seq_reset(struct trace_seq *s) { @@ -661,6 +686,21 @@ static int trace_stop_count; static DEFINE_SPINLOCK(tracing_start_lock); /** + * ftrace_off_permanent - disable all ftrace code permanently + * + * This should only be called when a serious anomally has + * been detected. This will turn off the function tracing, + * ring buffers, and other tracing utilites. It takes no + * locks and can be called from any context. + */ +void ftrace_off_permanent(void) +{ + tracing_disabled = 1; + ftrace_stop(); + tracing_off_permanent(); +} + +/** * tracing_start - quick start of the tracer * * If tracing is enabled but was stopped by tracing_stop, @@ -801,6 +841,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; + entry->tgid = (tsk) ? tsk->tgid : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -918,6 +959,44 @@ void __trace_stack(struct trace_array *tr, ftrace_trace_stack(tr, data, flags, skip, preempt_count()); } +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, int pc) +{ + struct ring_buffer_event *event; + struct userstack_entry *entry; + struct stack_trace trace; + unsigned long irq_flags; + + if (!(trace_flags & TRACE_ITER_USERSTACKTRACE)) + return; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_USER_STACK; + + memset(&entry->caller, 0, sizeof(entry->caller)); + + trace.nr_entries = 0; + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.skip = 0; + trace.entries = entry->caller; + + save_stack_trace_user(&trace); + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); +} + +void __trace_userstack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags) +{ + ftrace_trace_userstack(tr, data, flags, preempt_count()); +} + static void ftrace_trace_special(void *__tr, void *__data, unsigned long arg1, unsigned long arg2, unsigned long arg3, @@ -941,6 +1020,7 @@ ftrace_trace_special(void *__tr, void *__data, entry->arg3 = arg3; ring_buffer_unlock_commit(tr->buffer, event, irq_flags); ftrace_trace_stack(tr, data, irq_flags, 4, pc); + ftrace_trace_userstack(tr, data, irq_flags, pc); trace_wake_up(); } @@ -979,6 +1059,7 @@ tracing_sched_switch_trace(struct trace_array *tr, entry->next_cpu = task_cpu(next); ring_buffer_unlock_commit(tr->buffer, event, irq_flags); ftrace_trace_stack(tr, data, flags, 5, pc); + ftrace_trace_userstack(tr, data, flags, pc); } void @@ -1008,6 +1089,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_cpu = task_cpu(wakee); ring_buffer_unlock_commit(tr->buffer, event, irq_flags); ftrace_trace_stack(tr, data, flags, 6, pc); + ftrace_trace_userstack(tr, data, flags, pc); trace_wake_up(); } @@ -1387,6 +1469,78 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) return ret; } +static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags) +{ + struct file *file = NULL; + unsigned long vmstart = 0; + int ret = 1; + + if (mm) { + const struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, ip); + if (vma) { + file = vma->vm_file; + vmstart = vma->vm_start; + } + if (file) { + ret = trace_seq_path(s, &file->f_path); + if (ret) + ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart); + } + up_read(&mm->mmap_sem); + } + if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file)) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +static int +seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, + unsigned long sym_flags) +{ + struct mm_struct *mm = NULL; + int ret = 1; + unsigned int i; + + if (trace_flags & TRACE_ITER_SYM_USEROBJ) { + struct task_struct *task; + /* + * we do the lookup on the thread group leader, + * since individual threads might have already quit! + */ + rcu_read_lock(); + task = find_task_by_vpid(entry->ent.tgid); + if (task) + mm = get_task_mm(task); + rcu_read_unlock(); + } + + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + unsigned long ip = entry->caller[i]; + + if (ip == ULONG_MAX || !ret) + break; + if (i && ret) + ret = trace_seq_puts(s, " <- "); + if (!ip) { + if (ret) + ret = trace_seq_puts(s, "??"); + continue; + } + if (!ret) + break; + if (ret) + ret = seq_print_user_ip(s, mm, ip, sym_flags); + } + + if (mm) + mmput(mm); + return ret; +} + static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n"); @@ -1702,6 +1856,15 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) field->line); break; } + case TRACE_USER_STACK: { + struct userstack_entry *field; + + trace_assign_type(field, entry); + + seq_print_userip_objs(field, s, sym_flags); + trace_seq_putc(s, '\n'); + break; + } default: trace_seq_printf(s, "Unknown type %d\n", entry->type); } @@ -1853,6 +2016,19 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) field->line); break; } + case TRACE_USER_STACK: { + struct userstack_entry *field; + + trace_assign_type(field, entry); + + ret = seq_print_userip_objs(field, s, sym_flags); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + ret = trace_seq_putc(s, '\n'); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + break; + } } return TRACE_TYPE_HANDLED; } @@ -1912,6 +2088,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter) break; } case TRACE_SPECIAL: + case TRACE_USER_STACK: case TRACE_STACK: { struct special_entry *field; @@ -2000,6 +2177,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter) break; } case TRACE_SPECIAL: + case TRACE_USER_STACK: case TRACE_STACK: { struct special_entry *field; @@ -2054,6 +2232,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) break; } case TRACE_SPECIAL: + case TRACE_USER_STACK: case TRACE_STACK: { struct special_entry *field; @@ -3488,6 +3667,9 @@ void ftrace_dump(void) atomic_inc(&global_trace.data[cpu]->disabled); } + /* don't look at user memory in panic mode */ + trace_flags &= ~TRACE_ITER_SYM_USEROBJ; + printk(KERN_TRACE "Dumping ftrace buffer:\n"); iter.tr = &global_trace; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2cb12fd98f6..28c15c2ebc2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -26,6 +26,7 @@ enum trace_type { TRACE_BOOT_CALL, TRACE_BOOT_RET, TRACE_FN_RET, + TRACE_USER_STACK, __TRACE_LAST_TYPE }; @@ -42,6 +43,7 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; + int tgid; }; /* @@ -99,6 +101,11 @@ struct stack_entry { unsigned long caller[FTRACE_STACK_ENTRIES]; }; +struct userstack_entry { + struct trace_entry ent; + unsigned long caller[FTRACE_STACK_ENTRIES]; +}; + /* * ftrace_printk entry: */ @@ -240,6 +247,7 @@ extern void __ftrace_bad_type(void); IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \ IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \ IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \ + IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ IF_ASSIGN(var, ent, struct special_entry, 0); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ @@ -500,6 +508,8 @@ enum trace_iterator_flags { TRACE_ITER_PREEMPTONLY = 0x800, TRACE_ITER_BRANCH = 0x1000, TRACE_ITER_ANNOTATE = 0x2000, + TRACE_ITER_USERSTACKTRACE = 0x4000, + TRACE_ITER_SYM_USEROBJ = 0x8000 }; /* diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 23f9b02ce96..877ee88e6a7 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -185,12 +185,13 @@ EXPORT_SYMBOL(ftrace_likely_update); struct ftrace_pointer { void *start; void *stop; + int hit; }; static void * t_next(struct seq_file *m, void *v, loff_t *pos) { - struct ftrace_pointer *f = m->private; + const struct ftrace_pointer *f = m->private; struct ftrace_branch_data *p = v; (*pos)++; @@ -223,13 +224,17 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { + const struct ftrace_pointer *fp = m->private; struct ftrace_branch_data *p = v; const char *f; - unsigned long percent; + long percent; if (v == (void *)1) { - seq_printf(m, " correct incorrect %% " - " Function " + if (fp->hit) + seq_printf(m, " miss hit %% "); + else + seq_printf(m, " correct incorrect %% "); + seq_printf(m, " Function " " File Line\n" " ------- --------- - " " -------- " @@ -243,13 +248,20 @@ static int t_show(struct seq_file *m, void *v) f--; f++; + /* + * The miss is overlayed on correct, and hit on incorrect. + */ if (p->correct) { percent = p->incorrect * 100; percent /= p->correct + p->incorrect; } else - percent = p->incorrect ? 100 : 0; + percent = p->incorrect ? 100 : -1; - seq_printf(m, "%8lu %8lu %3lu ", p->correct, p->incorrect, percent); + seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect); + if (percent < 0) + seq_printf(m, " X "); + else + seq_printf(m, "%3ld ", percent); seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line); return 0; } @@ -261,7 +273,7 @@ static struct seq_operations tracing_likely_seq_ops = { .show = t_show, }; -static int tracing_likely_open(struct inode *inode, struct file *file) +static int tracing_branch_open(struct inode *inode, struct file *file) { int ret; @@ -274,25 +286,30 @@ static int tracing_likely_open(struct inode *inode, struct file *file) return ret; } -static struct file_operations tracing_likely_fops = { - .open = tracing_likely_open, +static const struct file_operations tracing_branch_fops = { + .open = tracing_branch_open, .read = seq_read, .llseek = seq_lseek, }; -extern unsigned long __start_likely_profile[]; -extern unsigned long __stop_likely_profile[]; -extern unsigned long __start_unlikely_profile[]; -extern unsigned long __stop_unlikely_profile[]; +#ifdef CONFIG_PROFILE_ALL_BRANCHES +extern unsigned long __start_branch_profile[]; +extern unsigned long __stop_branch_profile[]; -static struct ftrace_pointer ftrace_likely_pos = { - .start = __start_likely_profile, - .stop = __stop_likely_profile, +static const struct ftrace_pointer ftrace_branch_pos = { + .start = __start_branch_profile, + .stop = __stop_branch_profile, + .hit = 1, }; -static struct ftrace_pointer ftrace_unlikely_pos = { - .start = __start_unlikely_profile, - .stop = __stop_unlikely_profile, +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ + +extern unsigned long __start_annotated_branch_profile[]; +extern unsigned long __stop_annotated_branch_profile[]; + +static const struct ftrace_pointer ftrace_annotated_branch_pos = { + .start = __start_annotated_branch_profile, + .stop = __stop_annotated_branch_profile, }; static __init int ftrace_branch_init(void) @@ -302,18 +319,21 @@ static __init int ftrace_branch_init(void) d_tracer = tracing_init_dentry(); - entry = debugfs_create_file("profile_likely", 0444, d_tracer, - &ftrace_likely_pos, - &tracing_likely_fops); + entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer, + (void *)&ftrace_annotated_branch_pos, + &tracing_branch_fops); if (!entry) - pr_warning("Could not create debugfs 'profile_likely' entry\n"); + pr_warning("Could not create debugfs " + "'profile_annotatet_branch' entry\n"); - entry = debugfs_create_file("profile_unlikely", 0444, d_tracer, - &ftrace_unlikely_pos, - &tracing_likely_fops); +#ifdef CONFIG_PROFILE_ALL_BRANCHES + entry = debugfs_create_file("profile_branch", 0444, d_tracer, + (void *)&ftrace_branch_pos, + &tracing_branch_fops); if (!entry) pr_warning("Could not create debugfs" - " 'profile_unlikely' entry\n"); + " 'profile_branch' entry\n"); +#endif return 0; } diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 433d650eda9..2a98a206acc 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -18,12 +18,14 @@ struct header_iter { static struct trace_array *mmio_trace_array; static bool overrun_detected; +static unsigned long prev_overruns; static void mmio_reset_data(struct trace_array *tr) { int cpu; overrun_detected = false; + prev_overruns = 0; tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) @@ -123,16 +125,12 @@ static void mmio_close(struct trace_iterator *iter) static unsigned long count_overruns(struct trace_iterator *iter) { - int cpu; unsigned long cnt = 0; -/* FIXME: */ -#if 0 - for_each_online_cpu(cpu) { - cnt += iter->overrun[cpu]; - iter->overrun[cpu] = 0; - } -#endif - (void)cpu; + unsigned long over = ring_buffer_overruns(iter->tr->buffer); + + if (over > prev_overruns) + cnt = over - prev_overruns; + prev_overruns = over; return cnt; } diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index eeac71c87c6..0197e2f6b54 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -130,11 +130,13 @@ my %weak; # List of weak functions my %convert; # List of local functions used that needs conversion my $type; +my $nm_regex; # Find the local functions (return function) my $section_regex; # Find the start of a section my $function_regex; # Find the name of a function # (return offset and func name) my $mcount_regex; # Find the call site to mcount (return offset) -my $alignment; # The .align value to use for $mcount_section +my $alignment; # The .align value to use for $mcount_section +my $section_type; # Section header plus possible alignment command if ($arch eq "x86") { if ($bits == 64) { @@ -144,9 +146,18 @@ if ($arch eq "x86") { } } +# +# We base the defaults off of i386, the other archs may +# feel free to change them in the below if statements. +# +$nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\S+)"; +$section_regex = "Disassembly of section\\s+(\\S+):"; +$function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:"; +$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$"; +$section_type = '@progbits'; +$type = ".long"; + if ($arch eq "x86_64") { - $section_regex = "Disassembly of section\\s+(\\S+):"; - $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$"; $type = ".quad"; $alignment = 8; @@ -158,10 +169,6 @@ if ($arch eq "x86_64") { $cc .= " -m64"; } elsif ($arch eq "i386") { - $section_regex = "Disassembly of section\\s+(\\S+):"; - $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:"; - $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$"; - $type = ".long"; $alignment = 4; # force flags for this arch @@ -170,6 +177,27 @@ if ($arch eq "x86_64") { $objcopy .= " -O elf32-i386"; $cc .= " -m32"; +} elsif ($arch eq "sh") { + $alignment = 2; + + # force flags for this arch + $ld .= " -m shlelf_linux"; + $objcopy .= " -O elf32-sh-linux"; + $cc .= " -m32"; + +} elsif ($arch eq "powerpc") { + $nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; + $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:"; + $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$"; + + if ($bits == 64) { + $type = ".quad"; + } + +} elsif ($arch eq "arm") { + $alignment = 2; + $section_type = '%progbits'; + } else { die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD"; } @@ -239,7 +267,7 @@ if (!$found_version) { # open (IN, "$nm $inputfile|") || die "error running $nm"; while (<IN>) { - if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) { + if (/$nm_regex/) { $locals{$1} = 1; } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) { $weak{$2} = $1; @@ -290,8 +318,8 @@ sub update_funcs if (!$opened) { open(FILE, ">$mcount_s") || die "can't create $mcount_s\n"; $opened = 1; - print FILE "\t.section $mcount_section,\"a\",\@progbits\n"; - print FILE "\t.align $alignment\n"; + print FILE "\t.section $mcount_section,\"a\",$section_type\n"; + print FILE "\t.align $alignment\n" if (defined($alignment)); } printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset; } |