diff options
28 files changed, 856 insertions, 518 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 1d28812..51138b3 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -778,6 +778,13 @@ and is between 256 and 4096 characters. It is defined in the file by the set_ftrace_notrace file in the debugfs tracing directory. + ftrace_graph_filter=[function-list] + [FTRACE] Limit the top level callers functions traced + by the function graph tracer at boot up. + function-list is a comma separated list of functions + that can be changed at run time by the + set_graph_function file in the debugfs tracing directory. + gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad support via parallel port (up to 5 devices per port) diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt index 7003e10..641a1ef 100644 --- a/Documentation/trace/ftrace-design.txt +++ b/Documentation/trace/ftrace-design.txt @@ -213,10 +213,19 @@ If you can't trace NMI functions, then skip this option. <details to be filled> -HAVE_FTRACE_SYSCALLS +HAVE_SYSCALL_TRACEPOINTS --------------------- -<details to be filled> +You need very few things to get the syscalls tracing in an arch. + +- Have a NR_syscalls variable in <asm/unistd.h> that provides the number + of syscalls supported by the arch. +- Implement arch_syscall_addr() that resolves a syscall address from a + syscall number. +- Support the TIF_SYSCALL_TRACEPOINT thread flags +- Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace + in the ptrace syscalls tracing path. +- Tag this arch as HAVE_SYSCALL_TRACEPOINTS. HAVE_FTRACE_MCOUNT_RECORD @@ -379,6 +379,7 @@ export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn --exc PHONY += scripts_basic scripts_basic: $(Q)$(MAKE) $(build)=scripts/basic + $(Q)rm -f .tmp_quiet_recordmcount # To avoid any implicit rule to kick in, define an empty command. scripts/basic/%: scripts_basic ; diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index f5fe34d..5a82bc6 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -203,73 +203,10 @@ out: #ifdef CONFIG_FTRACE_SYSCALLS -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; extern unsigned int sys_call_table[]; -static struct syscall_metadata **syscalls_metadata; - -struct syscall_metadata *syscall_nr_to_meta(int nr) -{ - if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) - return NULL; - - return syscalls_metadata[nr]; -} - -int syscall_name_to_nr(char *name) -{ - int i; - - if (!syscalls_metadata) - return -1; - for (i = 0; i < NR_syscalls; i++) - if (syscalls_metadata[i]) - if (!strcmp(syscalls_metadata[i]->name, name)) - return i; - return -1; -} - -void set_syscall_enter_id(int num, int id) -{ - syscalls_metadata[num]->enter_id = id; -} - -void set_syscall_exit_id(int num, int id) +unsigned long __init arch_syscall_addr(int nr) { - syscalls_metadata[num]->exit_id = id; -} - -static struct syscall_metadata *find_syscall_meta(unsigned long syscall) -{ - struct syscall_metadata *start; - struct syscall_metadata *stop; - char str[KSYM_SYMBOL_LEN]; - - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; - kallsyms_lookup(syscall, NULL, NULL, NULL, str); - - for ( ; start < stop; start++) { - if (start->name && !strcmp(start->name + 3, str + 3)) - return start; - } - return NULL; -} - -static int __init arch_init_ftrace_syscalls(void) -{ - struct syscall_metadata *meta; - int i; - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls, - GFP_KERNEL); - if (!syscalls_metadata) - return -ENOMEM; - for (i = 0; i < NR_syscalls; i++) { - meta = find_syscall_meta((unsigned long)sys_call_table[i]); - syscalls_metadata[i] = meta; - } - return 0; + return (unsigned long)sys_call_table[nr]; } -arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index c097e7d..7d52e9d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1185,17 +1185,14 @@ END(ftrace_graph_caller) .globl return_to_handler return_to_handler: - pushl $0 pushl %eax - pushl %ecx pushl %edx movl %ebp, %eax call ftrace_return_to_handler - movl %eax, 0xc(%esp) + movl %eax, %ecx popl %edx - popl %ecx popl %eax - ret + jmp *%ecx #endif .section .rodata,"a" diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index b5c061f..bd5bbdd 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -155,11 +155,11 @@ GLOBAL(return_to_handler) call ftrace_return_to_handler - movq %rax, 16(%rsp) + movq %rax, %rdi movq 8(%rsp), %rdx movq (%rsp), %rax - addq $16, %rsp - retq + addq $24, %rsp + jmp *%rdi #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 9dbb527..5a1b975 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -9,6 +9,8 @@ * the dangers of modifying code on the run. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/spinlock.h> #include <linux/hardirq.h> #include <linux/uaccess.h> @@ -336,15 +338,15 @@ int __init ftrace_dyn_arch_init(void *data) switch (faulted) { case 0: - pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n"); + pr_info("converting mcount calls to 0f 1f 44 00 00\n"); memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE); break; case 1: - pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n"); + pr_info("converting mcount calls to 66 66 66 66 90\n"); memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE); break; case 2: - pr_info("ftrace: converting mcount calls to jmp . + 5\n"); + pr_info("converting mcount calls to jmp . + 5\n"); memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE); break; } @@ -468,82 +470,10 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, #ifdef CONFIG_FTRACE_SYSCALLS -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; extern unsigned long *sys_call_table; -static struct syscall_metadata **syscalls_metadata; - -static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) -{ - struct syscall_metadata *start; - struct syscall_metadata *stop; - char str[KSYM_SYMBOL_LEN]; - - - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; - kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str); - - for ( ; start < stop; start++) { - if (start->name && !strcmp(start->name, str)) - return start; - } - return NULL; -} - -struct syscall_metadata *syscall_nr_to_meta(int nr) -{ - if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) - return NULL; - - return syscalls_metadata[nr]; -} - -int syscall_name_to_nr(char *name) +unsigned long __init arch_syscall_addr(int nr) { - int i; - - if (!syscalls_metadata) - return -1; - - for (i = 0; i < NR_syscalls; i++) { - if (syscalls_metadata[i]) { - if (!strcmp(syscalls_metadata[i]->name, name)) - return i; - } - } - return -1; -} - -void set_syscall_enter_id(int num, int id) -{ - syscalls_metadata[num]->enter_id = id; -} - -void set_syscall_exit_id(int num, int id) -{ - syscalls_metadata[num]->exit_id = id; -} - -static int __init arch_init_ftrace_syscalls(void) -{ - int i; - struct syscall_metadata *meta; - unsigned long **psys_syscall_table = &sys_call_table; - - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * - NR_syscalls, GFP_KERNEL); - if (!syscalls_metadata) { - WARN_ON(1); - return -ENOMEM; - } - - for (i = 0; i < NR_syscalls; i++) { - meta = find_syscall_meta(psys_syscall_table[i]); - syscalls_metadata[i] = meta; - } - return 0; + return (unsigned long)(&sys_call_table)[nr]; } -arch_initcall(arch_init_ftrace_syscalls); #endif diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 427fd1b..8565d94 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -1,12 +1,13 @@ /* * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi> */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/io.h> #include <linux/mmiotrace.h> -#define MODULE_NAME "testmmiotrace" - static unsigned long mmio_address; module_param(mmio_address, ulong, 0); MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB " @@ -30,7 +31,7 @@ static unsigned v32(unsigned i) static void do_write_test(void __iomem *p) { unsigned int i; - pr_info(MODULE_NAME ": write test.\n"); + pr_info("write test.\n"); mmiotrace_printk("Write test.\n"); for (i = 0; i < 256; i++) @@ -47,7 +48,7 @@ static void do_read_test(void __iomem *p) { unsigned int i; unsigned errs[3] = { 0 }; - pr_info(MODULE_NAME ": read test.\n"); + pr_info("read test.\n"); mmiotrace_printk("Read test.\n"); for (i = 0; i < 256; i++) @@ -68,7 +69,7 @@ static void do_read_test(void __iomem *p) static void do_read_far_test(void __iomem *p) { - pr_info(MODULE_NAME ": read far test.\n"); + pr_info("read far test.\n"); mmiotrace_printk("Read far test.\n"); ioread32(p + read_far); @@ -78,7 +79,7 @@ static void do_test(unsigned long size) { void __iomem *p = ioremap_nocache(mmio_address, size); if (!p) { - pr_err(MODULE_NAME ": could not ioremap, aborting.\n"); + pr_err("could not ioremap, aborting.\n"); return; } mmiotrace_printk("ioremap returned %p.\n", p); @@ -94,24 +95,22 @@ static int __init init(void) unsigned long size = (read_far) ? (8 << 20) : (16 << 10); if (mmio_address == 0) { - pr_err(MODULE_NAME ": you have to use the module argument " - "mmio_address.\n"); - pr_err(MODULE_NAME ": DO NOT LOAD THIS MODULE UNLESS" - " YOU REALLY KNOW WHAT YOU ARE DOING!\n"); + pr_err("you have to use the module argument mmio_address.\n"); + pr_err("DO NOT LOAD THIS MODULE UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!\n"); return -ENXIO; } - pr_warning(MODULE_NAME ": WARNING: mapping %lu kB @ 0x%08lx in PCI " - "address space, and writing 16 kB of rubbish in there.\n", - size >> 10, mmio_address); + pr_warning("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, " + "and writing 16 kB of rubbish in there.\n", + size >> 10, mmio_address); do_test(size); - pr_info(MODULE_NAME ": All done.\n"); + pr_info("All done.\n"); return 0; } static void __exit cleanup(void) { - pr_debug(MODULE_NAME ": unloaded.\n"); + pr_debug("unloaded.\n"); } module_init(init); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index a3ed7cb..73dcf80 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -79,6 +79,7 @@ #define noinline __attribute__((noinline)) #define __attribute_const__ __attribute__((__const__)) #define __maybe_unused __attribute__((unused)) +#define __always_unused __attribute__((unused)) #define __gcc_header(x) #x #define _gcc_header(x) __gcc_header(linux/compiler-gcc##x.h) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 59f2089..acbd654 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -218,6 +218,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # define __maybe_unused /* unimplemented */ #endif +#ifndef __always_unused +# define __always_unused /* unimplemented */ +#endif + #ifndef noinline #define noinline #endif diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h index 813be59..2ea1dd1 100644 --- a/include/linux/smp_lock.h +++ b/include/linux/smp_lock.h @@ -24,8 +24,21 @@ static inline int reacquire_kernel_lock(struct task_struct *task) return 0; } -extern void __lockfunc lock_kernel(void) __acquires(kernel_lock); -extern void __lockfunc unlock_kernel(void) __releases(kernel_lock); +extern void __lockfunc +_lock_kernel(const char *func, const char *file, int line) +__acquires(kernel_lock); + +extern void __lockfunc +_unlock_kernel(const char *func, const char *file, int line) +__releases(kernel_lock); + +#define lock_kernel() do { \ + _lock_kernel(__func__, __FILE__, __LINE__); \ +} while (0) + +#define unlock_kernel() do { \ + _unlock_kernel(__func__, __FILE__, __LINE__); \ +} while (0) /* * Various legacy drivers don't really need the BKL in a specific @@ -41,8 +54,8 @@ static inline void cycle_kernel_lock(void) #else -#define lock_kernel() do { } while(0) -#define unlock_kernel() do { } while(0) +#define lock_kernel() +#define unlock_kernel() #define release_kernel_lock(task) do { } while(0) #define cycle_kernel_lock() do { } while(0) #define reacquire_kernel_lock(task) 0 diff --git a/include/trace/events/bkl.h b/include/trace/events/bkl.h new file mode 100644 index 0000000..8abd620 --- /dev/null +++ b/include/trace/events/bkl.h @@ -0,0 +1,61 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM bkl + +#if !defined(_TRACE_BKL_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_BKL_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(lock_kernel, + + TP_PROTO(const char *func, const char *file, int line), + + TP_ARGS(func, file, line), + + TP_STRUCT__entry( + __field( int, lock_depth ) + __field_ext( const char *, func, FILTER_PTR_STRING ) + __field_ext( const char *, file, FILTER_PTR_STRING ) + __field( int, line ) + ), + + TP_fast_assign( + /* We want to record the lock_depth after lock is acquired */ + __entry->lock_depth = current->lock_depth + 1; + __entry->func = func; + __entry->file = file; + __entry->line = line; + ), + + TP_printk("depth: %d, %s:%d %s()", __entry->lock_depth, + __entry->file, __entry->line, __entry->func) +); + +TRACE_EVENT(unlock_kernel, + + TP_PROTO(const char *func, const char *file, int line), + + TP_ARGS(func, file, line), + + TP_STRUCT__entry( + __field(int, lock_depth) + __field(const char *, func) + __field(const char *, file) + __field(int, line) + ), + + TP_fast_assign( + __entry->lock_depth = current->lock_depth; + __entry->func = func; + __entry->file = file; + __entry->line = line; + ), + + TP_printk("depth: %d, %s:%d %s()", __entry->lock_depth, + __entry->file, __entry->line, __entry->func) +); + +#endif /* _TRACE_BKL_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h index 397dff2..fb726ac 100644 --- a/include/trace/events/syscalls.h +++ b/include/trace/events/syscalls.h @@ -1,5 +1,6 @@ #undef TRACE_SYSTEM -#define TRACE_SYSTEM syscalls +#define TRACE_SYSTEM raw_syscalls +#define TRACE_INCLUDE_FILE syscalls #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_EVENTS_SYSCALLS_H diff --git a/include/trace/power.h b/include/trace/power.h deleted file mode 100644 index ef20466..0000000 --- a/include/trace/power.h +++ /dev/null @@ -1,32 +0,0 @@ -#ifndef _TRACE_POWER_H -#define _TRACE_POWER_H - -#include <linux/ktime.h> -#include <linux/tracepoint.h> - -enum { - POWER_NONE = 0, - POWER_CSTATE = 1, - POWER_PSTATE = 2, -}; - -struct power_trace { - ktime_t stamp; - ktime_t end; - int type; - int state; -}; - -DECLARE_TRACE(power_start, - TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state), - TP_ARGS(it, type, state)); - -DECLARE_TRACE(power_mark, - TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state), - TP_ARGS(it, type, state)); - -DECLARE_TRACE(power_end, - TP_PROTO(struct power_trace *it), - TP_ARGS(it)); - -#endif /* _TRACE_POWER_H */ diff --git a/include/trace/syscall.h b/include/trace/syscall.h index 5dc283b..e972f0a 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -33,7 +33,7 @@ struct syscall_metadata { }; #ifdef CONFIG_FTRACE_SYSCALLS -extern struct syscall_metadata *syscall_nr_to_meta(int nr); +extern unsigned long arch_syscall_addr(int nr); extern int syscall_name_to_nr(char *name); void set_syscall_enter_id(int num, int id); void set_syscall_exit_id(int num, int id); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 5240d75..1494e85 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1014,9 +1014,9 @@ int __kprobes register_kretprobe(struct kretprobe *rp) /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { #ifdef CONFIG_PREEMPT - rp->maxactive = max(10, 2 * NR_CPUS); + rp->maxactive = max(10, 2 * num_possible_cpus()); #else - rp->maxactive = NR_CPUS; + rp->maxactive = num_possible_cpus(); #endif } spin_lock_init(&rp->lock); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6dc4e5e..e51a1bc 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -60,6 +60,13 @@ static int last_ftrace_enabled; /* Quick disabling of function tracer. */ int function_trace_stop; +/* List for set_ftrace_pid's pids. */ +LIST_HEAD(ftrace_pids); +struct ftrace_pid { + struct list_head list; + struct pid *pid; +}; + /* * ftrace_disabled is set when an anomaly is discovered. * ftrace_disabled is much stronger than ftrace_enabled. @@ -78,6 +85,10 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static int ftrace_set_func(unsigned long *array, int *idx, char *buffer); +#endif + static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) { struct ftrace_ops *op = ftrace_list; @@ -155,7 +166,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) else func = ftrace_list_func; - if (ftrace_pid_trace) { + if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); func = ftrace_pid_func; } @@ -203,7 +214,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_list->next == &ftrace_list_end) { ftrace_func_t func = ftrace_list->func; - if (ftrace_pid_trace) { + if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); func = ftrace_pid_func; } @@ -231,7 +242,7 @@ static void ftrace_update_pid_func(void) func = __ftrace_trace_function; #endif - if (ftrace_pid_trace) { + if (!list_empty(&ftrace_pids)) { set_ftrace_pid_function(func); func = ftrace_pid_func; } else { @@ -821,8 +832,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) } #endif /* CONFIG_FUNCTION_PROFILER */ -/* set when tracing only a pid */ -struct pid *ftrace_pid_trace; static struct pid * const ftrace_swapper_pid = &init_struct_pid; #ifdef CONFIG_DYNAMIC_FTRACE @@ -1261,12 +1270,34 @@ static int ftrace_update_code(struct module *mod) ftrace_new_addrs = p->newlist; p->flags = 0L; - /* convert record (i.e, patch mcount-call with NOP) */ - if (ftrace_code_disable(mod, p)) { - p->flags |= FTRACE_FL_CONVERTED; - ftrace_update_cnt++; - } else + /* + * Do the initial record convertion from mcount jump + * to the NOP instructions. + */ + if (!ftrace_code_disable(mod, p)) { ftrace_free_rec(p); + continue; + } + + p->flags |= FTRACE_FL_CONVERTED; + ftrace_update_cnt++; + + /* + * If the tracing is enabled, go ahead and enable the record. + * + * The reason not to enable the record immediatelly is the + * inherent check of ftrace_make_nop/ftrace_make_call for + * correct previous instructions. Making first the NOP + * conversion puts the module to the correct state, thus + * passing the ftrace_make_call check. + */ + if (ftrace_start_up) { + int failed = __ftrace_replace_code(p, 1); + if (failed) { + ftrace_bug(failed, p->ip); + ftrace_free_rec(p); + } + } } stop = ftrace_now(raw_smp_processor_id()); @@ -1656,60 +1687,6 @@ ftrace_regex_lseek(struct file *file, loff_t offset, int origin) return ret; } -enum { - MATCH_FULL, - MATCH_FRONT_ONLY, - MATCH_MIDDLE_ONLY, - MATCH_END_ONLY, -}; - -/* - * (static function - no need for kernel doc) - * - * Pass in a buffer containing a glob and this function will - * set search to point to the search part of the buffer and - * return the type of search it is (see enum above). - * This does modify buff. - * - * Returns enum type. - * search returns the pointer to use for comparison. - * not returns 1 if buff started with a '!' - * 0 otherwise. - */ -static int -ftrace_setup_glob(char *buff, int len, char **search, int *not) -{ - int type = MATCH_FULL; - int i; - - if (buff[0] == '!') { - *not = 1; - buff++; - len--; - } else - *not = 0; - - *search = buff; - - for (i = 0; i < len; i++) { - if (buff[i] == '*') { - if (!i) { - *search = buff + 1; - type = MATCH_END_ONLY; - } else { - if (type == MATCH_END_ONLY) - type = MATCH_MIDDLE_ONLY; - else - type = MATCH_FRONT_ONLY; - buff[i] = 0; - break; - } - } - } - - return type; -} - static int ftrace_match(char *str, char *regex, int len, int type) { int matched = 0; @@ -1758,7 +1735,7 @@ static void ftrace_match_records(char *buff, int len, int enable) int not; flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - type = ftrace_setup_glob(buff, len, &search, ¬); + type = filter_parse_regex(buff, len, &search, ¬); search_len = strlen(search); @@ -1826,7 +1803,7 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable) } if (strlen(buff)) { - type = ftrace_setup_glob(buff, strlen(buff), &search, ¬); + type = filter_parse_regex(buff, strlen(buff), &search, ¬); search_len = strlen(search); } @@ -1991,7 +1968,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, int count = 0; char *search; - type = ftrace_setup_glob(glob, strlen(glob), &search, ¬); + type = filter_parse_regex(glob, strlen(glob), &search, ¬); len = strlen(search); /* we do not support '!' for function probes */ @@ -2068,7 +2045,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, else if (glob) { int not; - type = ftrace_setup_glob(glob, strlen(glob), &search, ¬); + type = filter_parse_regex(glob, strlen(glob), &search, ¬); len = strlen(search); /* we do not support '!' for function probes */ @@ -2312,6 +2289,32 @@ static int __init set_ftrace_filter(char *str) } __setup("ftrace_filter=", set_ftrace_filter); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; +static int __init set_graph_function(char *str) +{ + strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); + return 1; +} +__setup("ftrace_graph_filter=", set_graph_function); + +static void __init set_ftrace_early_graph(char *buf) +{ + int ret; + char *func; + + while (buf) { + func = strsep(&buf, ","); + /* we allow only one expression at a time */ + ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, + func); + if (ret) + printk(KERN_DEBUG "ftrace: function %s not " + "traceable\n", func); + } +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + static void __init set_ftrace_early_filter(char *buf, int enable) { char *func; @@ -2328,6 +2331,10 @@ static void __init set_ftrace_early_filters(void) set_ftrace_early_filter(ftrace_filter_buf, 1); if (ftrace_notrace_buf[0]) set_ftrace_early_filter(ftrace_notrace_buf, 0); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (ftrace_graph_buf[0]) + set_ftrace_early_graph(ftrace_graph_buf); +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ } static int @@ -2513,7 +2520,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) return -ENODEV; /* decode regex */ - type = ftrace_setup_glob(buffer, strlen(buffer), &search, ¬); + type = filter_parse_regex(buffer, strlen(buffer), &search, ¬); if (not) return -EINVAL; @@ -2624,7 +2631,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) return 0; } -static int ftrace_convert_nops(struct module *mod, +static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) { @@ -2684,7 +2691,7 @@ static void ftrace_init_module(struct module *mod, { if (ftrace_disabled || start == end) return; - ftrace_convert_nops(mod, start, end); + ftrace_process_locs(mod, start, end); } static int ftrace_module_notify(struct notifier_block *self, @@ -2745,7 +2752,7 @@ void __init ftrace_init(void) last_ftrace_enabled = ftrace_enabled = 1; - ret = ftrace_convert_nops(NULL, + ret = ftrace_process_locs(NULL, __start_mcount_loc, __stop_mcount_loc); @@ -2778,23 +2785,6 @@ static inline void ftrace_startup_enable(int command) { } # define ftrace_shutdown_sysctl() do { } while (0) #endif /* CONFIG_DYNAMIC_FTRACE */ -static ssize_t -ftrace_pid_read(struct file *file, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - int r; - - if (ftrace_pid_trace == ftrace_swapper_pid) - r = sprintf(buf, "swapper tasks\n"); - else if (ftrace_pid_trace) - r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace)); - else - r = sprintf(buf, "no pid\n"); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - static void clear_ftrace_swapper(void) { struct task_struct *p; @@ -2845,14 +2835,12 @@ static void set_ftrace_pid(struct pid *pid) rcu_read_unlock(); } -static void clear_ftrace_pid_task(struct pid **pid) +static void clear_ftrace_pid_task(struct pid *pid) { - if (*pid == ftrace_swapper_pid) + if (pid == ftrace_swapper_pid) clear_ftrace_swapper(); else - clear_ftrace_pid(*pid); - - *pid = NULL; + clear_ftrace_pid(pid); } static void set_ftrace_pid_task(struct pid *pid) @@ -2863,74 +2851,184 @@ static void set_ftrace_pid_task(struct pid *pid) set_ftrace_pid(pid); } -static ssize_t -ftrace_pid_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +static int ftrace_pid_add(int p) { struct pid *pid; - char buf[64]; - long val; - int ret; + struct ftrace_pid *fpid; + int ret = -EINVAL; - if (cnt >= sizeof(buf)) - return -EINVAL; + mutex_lock(&ftrace_lock); - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; + if (!p) + pid = ftrace_swapper_pid; + else + pid = find_get_pid(p); - buf[cnt] = 0; + if (!pid) + goto out; - ret = strict_strtol(buf, 10, &val); - if (ret < 0) - return ret; + ret = 0; - mutex_lock(&ftrace_lock); - if (val < 0) { - /* disable pid tracing */ - if (!ftrace_pid_trace) - goto out; + list_for_each_entry(fpid, &ftrace_pids, list) + if (fpid->pid == pid) + goto out_put; - clear_ftrace_pid_task(&ftrace_pid_trace); + ret = -ENOMEM; - } else { - /* swapper task is special */ - if (!val) { - pid = ftrace_swapper_pid; - if (pid == ftrace_pid_trace) - goto out; - } else { - pid = find_get_pid(val); + fpid = kmalloc(sizeof(*fpid), GFP_KERNEL); + if (!fpid) + goto out_put; - if (pid == ftrace_pid_trace) { - put_pid(pid); - goto out; - } - } + list_add(&fpid->list, &ftrace_pids); + fpid->pid = pid; - if (ftrace_pid_trace) - clear_ftrace_pid_task(&ftrace_pid_trace); + set_ftrace_pid_task(pid); - if (!pid) - goto out; + ftrace_update_pid_func(); + ftrace_startup_enable(0); + + mutex_unlock(&ftrace_lock); + return 0; + +out_put: + if (pid != ftrace_swapper_pid) + put_pid(pid); - ftrace_pid_trace = pid; +out: + mutex_unlock(&ftrace_lock); + return ret; +} + +static void ftrace_pid_reset(void) +{ + struct ftrace_pid *fpid, *safe; - set_ftrace_pid_task(ftrace_pid_trace); + mutex_lock(&ftrace_lock); + list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) { + struct pid *pid = fpid->pid; + + clear_ftrace_pid_task(pid); + + list_del(&fpid->list); + kfree(fpid); } - /* update the function call */ ftrace_update_pid_func(); ftrace_startup_enable(0); - out: mutex_unlock(&ftrace_lock); +} - return cnt; +static void *fpid_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&ftrace_lock); + + if (list_empty(&ftrace_pids) && (!*pos)) + return (void *) 1; + + return seq_list_start(&ftrace_pids, *pos); +} + +static void *fpid_next(struct seq_file *m, void *v, loff_t *pos) +{ + if (v == (void *)1) + return NULL; + + return seq_list_next(v, &ftrace_pids, pos); +} + +static void fpid_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&ftrace_lock); +} + +static int fpid_show(struct seq_file *m, void *v) +{ + const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list); + + if (v == (void *)1) { + seq_printf(m, "no pid\n"); + return 0; + } + + if (fpid->pid == ftrace_swapper_pid) + seq_printf(m, "swapper tasks\n"); + else + seq_printf(m, "%u\n", pid_vnr(fpid->pid)); + + return 0; +} + +static const struct seq_operations ftrace_pid_sops = { + .start = fpid_start, + .next = fpid_next, + .stop = fpid_stop, + .show = fpid_show, +}; + +static int +ftrace_pid_open(struct inode *inode, struct file *file) +{ + int ret = 0; + + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + ftrace_pid_reset(); + + if (file->f_mode & FMODE_READ) + ret = seq_open(file, &ftrace_pid_sops); + + return ret; +} + +static ssize_t +ftrace_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64], *tmp; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + /* + * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid" + * to clean the filter quietly. + */ + tmp = strstrip(buf); + if (strlen(tmp) == 0) + return 1; + + ret = strict_strtol(tmp, 10, &val); + if (ret < 0) + return ret; + + ret = ftrace_pid_add(val); + + return ret ? ret : cnt; +} + +static int +ftrace_pid_release(struct inode *inode, struct file *file) +{ + if (file->f_mode & FMODE_READ) + seq_release(inode, file); + + return 0; } static const struct file_operations ftrace_pid_fops = { - .read = ftrace_pid_read, - .write = ftrace_pid_write, + .open = ftrace_pid_open, + .write = ftrace_pid_write, + .read = seq_read, + .llseek = seq_lseek, + .release = ftrace_pid_release, }; static __init int ftrace_init_debugfs(void) @@ -3293,4 +3391,3 @@ void ftrace_graph_stop(void) ftrace_stop(); } #endif - diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 5dd017f..a72c6e0 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1787,9 +1787,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, static struct ring_buffer_event * rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long length, unsigned long tail, - struct buffer_page *commit_page, struct buffer_page *tail_page, u64 *ts) { + struct buffer_page *commit_page = cpu_buffer->commit_page; struct ring_buffer *buffer = cpu_buffer->buffer; struct buffer_page *next_page; int ret; @@ -1892,13 +1892,10 @@ static struct ring_buffer_event * __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, unsigned type, unsigned long length, u64 *ts) { - struct buffer_page *tail_page, *commit_page; + struct buffer_page *tail_page; struct ring_buffer_event *event; unsigned long tail, write; - commit_page = cpu_buffer->commit_page; - /* we just need to protect against interrupts */ - barrier(); tail_page = cpu_buffer->tail_page; write = local_add_return(length, &tail_page->write); @@ -1909,7 +1906,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (write > BUF_PAGE_SIZE) return rb_move_tail(cpu_buffer, length, tail, - commit_page, tail_page, ts); + tail_page, ts); /* We reserved something on the buffer */ diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 573d3cc..b2477ca 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -35,6 +35,28 @@ static int disable_reader; module_param(disable_reader, uint, 0644); MODULE_PARM_DESC(disable_reader, "only run producer"); +static int write_iteration = 50; +module_param(write_iteration, uint, 0644); +MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings"); + +static int producer_nice = 19; +static int consumer_nice = 19; + +static int producer_fifo = -1; +static int consumer_fifo = -1; + +module_param(producer_nice, uint, 0644); +MODULE_PARM_DESC(producer_nice, "nice prio for producer"); + +module_param(consumer_nice, uint, 0644); +MODULE_PARM_DESC(consumer_nice, "nice prio for consumer"); + +module_param(producer_fifo, uint, 0644); +MODULE_PARM_DESC(producer_fifo, "fifo prio for producer"); + +module_param(consumer_fifo, uint, 0644); +MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer"); + static int read_events; static int kill_test; @@ -208,15 +230,18 @@ static void ring_buffer_producer(void) do { struct ring_buffer_event *event; int *entry; - - event = ring_buffer_lock_reserve(buffer, 10); - if (!event) { - missed++; - } else { - hit++; - entry = ring_buffer_event_data(event); - *entry = smp_processor_id(); - ring_buffer_unlock_commit(buffer, event); + int i; + + for (i = 0; i < write_iteration; i++) { + event = ring_buffer_lock_reserve(buffer, 10); + if (!event) { + missed++; + } else { + hit++; + entry = ring_buffer_event_data(event); + *entry = smp_processor_id(); + ring_buffer_unlock_commit(buffer, event); + } } do_gettimeofday(&end_tv); @@ -263,6 +288,27 @@ static void ring_buffer_producer(void) if (kill_test) trace_printk("ERROR!\n"); + + if (!disable_reader) { + if (consumer_fifo < 0) + trace_printk("Running Consumer at nice: %d\n", + consumer_nice); + else + trace_printk("Running Consumer at SCHED_FIFO %d\n", + consumer_fifo); + } + if (producer_fifo < 0) + trace_printk("Running Producer at nice: %d\n", + producer_nice); + else + trace_printk("Running Producer at SCHED_FIFO %d\n", + producer_fifo); + + /* Let the user know that the test is running at low priority */ + if (producer_fifo < 0 && consumer_fifo < 0 && + producer_nice == 19 && consumer_nice == 19) + trace_printk("WARNING!!! This test is running at lowest priority.\n"); + trace_printk("Time: %lld (usecs)\n", time); trace_printk("Overruns: %lld\n", overruns); if (disable_reader) @@ -392,6 +438,27 @@ static int __init ring_buffer_benchmark_init(void) if (IS_ERR(producer)) goto out_kill; + /* + * Run them as low-prio background tasks by default: + */ + if (!disable_reader) { + if (consumer_fifo >= 0) { + struct sched_param param = { + .sched_priority = consumer_fifo + }; + sched_setscheduler(consumer, SCHED_FIFO, ¶m); + } else + set_user_nice(consumer, consumer_nice); + } + + if (producer_fifo >= 0) { + struct sched_param param = { + .sched_priority = consumer_fifo + }; + sched_setscheduler(producer, SCHED_FIFO, ¶m); + } else + set_user_nice(producer, producer_nice); + return 0; out_kill: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 12b49ca..874f289 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -129,7 +129,7 @@ static int tracing_set_tracer(const char *buf); static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; -static int __init set_ftrace(char *str) +static int __init set_cmdline_ftrace(char *str) { strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; @@ -137,7 +137,7 @@ static int __init set_ftrace(char *str) ring_buffer_expanded = 1; return 1; } -__setup("ftrace=", set_ftrace); +__setup("ftrace=", set_cmdline_ftrace); static int __init set_ftrace_dump_on_oops(char *str) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 405cb85..acef8b4 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -483,10 +483,6 @@ static inline int ftrace_graph_addr(unsigned long addr) return 0; } #else -static inline int ftrace_trace_addr(unsigned long addr) -{ - return 1; -} static inline int ftrace_graph_addr(unsigned long addr) { return 1; @@ -500,12 +496,12 @@ print_graph_function(struct trace_iterator *iter) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -extern struct pid *ftrace_pid_trace; +extern struct list_head ftrace_pids; #ifdef CONFIG_FUNCTION_TRACER static inline int ftrace_trace_task(struct task_struct *task) { - if (!ftrace_pid_trace) + if (list_empty(&ftrace_pids)) return 1; return test_tsk_trace_trace(task); @@ -699,22 +695,40 @@ struct event_subsystem { }; struct filter_pred; +struct regex; typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event, int val1, int val2); +typedef int (*regex_match_func)(char *str, struct regex *r, int len); + +enum regex_type { + MATCH_FULL, + MATCH_FRONT_ONLY, + MATCH_MIDDLE_ONLY, + MATCH_END_ONLY, +}; + +struct regex { + char pattern[MAX_FILTER_STR_VAL]; + int len; + int field_len; + regex_match_func match; +}; + struct filter_pred { - filter_pred_fn_t fn; - u64 val; - char str_val[MAX_FILTER_STR_VAL]; - int str_len; - char *field_name; - int offset; - int not; - int op; - int pop_n; + filter_pred_fn_t fn; + u64 val; + struct regex regex; + char *field_name; + int offset; + int not; + int op; + int pop_n; }; +extern enum regex_type +filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s); extern int apply_event_filter(struct ftrace_event_call *call, diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 20c5f92..878c03f 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -20,6 +20,8 @@ #include <linux/ktime.h> #include <linux/trace_clock.h> +#include "trace.h" + /* * trace_clock_local(): the simplest and least coherent tracing clock. * @@ -28,17 +30,17 @@ */ u64 notrace trace_clock_local(void) { - unsigned long flags; u64 clock; + int resched; /* * sched_clock() is an architecture implemented, fast, scalable, * lockless clock. It is not guaranteed to be coherent across * CPUs, nor across CPU idle events. */ - raw_local_irq_save(flags); + resched = ftrace_preempt_disable(); clock = sched_clock(); - raw_local_irq_restore(flags); + ftrace_preempt_enable(resched); return clock; } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index d128f65..5e9ffc3 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -878,9 +878,9 @@ event_subsystem_dir(const char *name, struct dentry *d_events) "'%s/filter' entry\n", name); } - entry = trace_create_file("enable", 0644, system->entry, - (void *)system->name, - &ftrace_system_enable_fops); + trace_create_file("enable", 0644, system->entry, + (void *)system->name, + &ftrace_system_enable_fops); return system->entry; } @@ -892,7 +892,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, const struct file_operations *filter, const struct file_operations *format) { - struct dentry *entry; int ret; /* @@ -910,12 +909,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, } if (call->regfunc) - entry = trace_create_file("enable", 0644, call->dir, call, - enable); + trace_create_file("enable", 0644, call->dir, call, + enable); if (call->id && call->profile_enable) - entry = trace_create_file("id", 0444, call->dir, call, - id); + trace_create_file("id", 0444, call->dir, call, + id); if (call->define_fields) { ret = call->define_fields(call); @@ -924,16 +923,16 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, " events/%s\n", call->name); return ret; } - entry = trace_create_file("filter", 0644, call->dir, call, - filter); + trace_create_file("filter", 0644, call->dir, call, + filter); } /* A trace may not want to export its format */ if (!call->show_format) return 0; - entry = trace_create_file("format", 0444, call->dir, call, - format); + trace_create_file("format", 0444, call->dir, call, + format); return 0; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 98a6cc5..9267201 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -18,8 +18,6 @@ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com> */ -#include <linux/debugfs.h> -#include <linux/uaccess.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/mutex.h> @@ -197,9 +195,9 @@ static int filter_pred_string(struct filter_pred *pred, void *event, char *addr = (char *)(event + pred->offset); int cmp, match; - cmp = strncmp(addr, pred->str_val, pred->str_len); + cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len); - match = (!cmp) ^ pred->not; + match = cmp ^ pred->not; return match; } @@ -211,9 +209,9 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event, char **addr = (char **)(event + pred->offset); int cmp, match; - cmp = strncmp(*addr, pred->str_val, pred->str_len); + cmp = pred->regex.match(*addr, &pred->regex, pred->regex.field_len); - match = (!cmp) ^ pred->not; + match = cmp ^ pred->not; return match; } @@ -237,9 +235,9 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event, char *addr = (char *)(event + str_loc); int cmp, match; - cmp = strncmp(addr, pred->str_val, str_len); + cmp = pred->regex.match(addr, &pred->regex, str_len); - match = (!cmp) ^ pred->not; + match = cmp ^ pred->not; return match; } @@ -250,6 +248,124 @@ static int filter_pred_none(struct filter_pred *pred, void *event, return 0; } +/* Basic regex callbacks */ +static int regex_match_full(char *str, struct regex *r, int len) +{ + if (strncmp(str, r->pattern, len) == 0) + return 1; + return 0; +} + +static int regex_match_front(char *str, struct regex *r, int len) +{ + if (strncmp(str, r->pattern, len) == 0) + return 1; + return 0; +} + +static int regex_match_middle(char *str, struct regex *r, int len) +{ + if (strstr(str, r->pattern)) + return 1; + return 0; +} + +static int regex_match_end(char *str, struct regex *r, int len) +{ + char *ptr = strstr(str, r->pattern); + + if (ptr && (ptr[r->len] == 0)) + return 1; + return 0; +} + +/** + * filter_parse_regex - parse a basic regex + * @buff: the raw regex + * @len: length of the regex + * @search: will point to the beginning of the string to compare + * @not: tell whether the match will have to be inverted + * + * This passes in a buffer containing a regex and this function will + * set search to point to the search part of the buffer and + * return the type of search it is (see enum above). + * This does modify buff. + * + * Returns enum type. + * search returns the pointer to use for comparison. + * not returns 1 if buff started with a '!' + * 0 otherwise. + */ +enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) +{ + int type = MATCH_FULL; + int i; + + if (buff[0] == '!') { + *not = 1; + buff++; + len--; + } else + *not = 0; + + *search = buff; + + for (i = 0; i < len; i++) { + if (buff[i] == '*') { + if (!i) { + *search = buff + 1; + type = MATCH_END_ONLY; + } else { + if (type == MATCH_END_ONLY) + type = MATCH_MIDDLE_ONLY; + else + type = MATCH_FRONT_ONLY; + buff[i] = 0; + break; + } + } + } + + return type; +} + +static int filter_build_regex(struct filter_pred *pred) +{ + struct regex *r = &pred->regex; + char *search, *dup; + enum regex_type type; + int not; + + type = filter_parse_regex(r->pattern, r->len, &search, ¬); + dup = kstrdup(search, GFP_KERNEL); + if (!dup) + return -ENOMEM; + + strcpy(r->pattern, dup); + kfree(dup); + + r->len = strlen(r->pattern); + + switch (type) { + case MATCH_FULL: + r->match = regex_match_full; + break; + case MATCH_FRONT_ONLY: + r->match = regex_match_front; + break; + case MATCH_MIDDLE_ONLY: + r->match = regex_match_middle; + break; + case MATCH_END_ONLY: + r->match = regex_match_end; + break; + } + + pred->not ^= not; + + return 0; +} + /* return 1 if event matches, 0 otherwise (discard) */ int filter_match_preds(struct ftrace_event_call *call, void *rec) { @@ -396,7 +512,7 @@ static void filter_clear_pred(struct filter_pred *pred) { kfree(pred->field_name); pred->field_name = NULL; - pred->str_len = 0; + pred->regex.len = 0; } static int filter_set_pred(struct filter_pred *dest, @@ -660,21 +776,24 @@ static int filter_add_pred(struct filter_parse_state *ps, } if (is_string_field(field)) { - pred->str_len = field->size; + ret = filter_build_regex(pred); + if (ret) + return ret; - if (field->filter_type == FILTER_STATIC_STRING) + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; - else if (field->filter_type == FILTER_DYN_STRING) - fn = filter_pred_strloc; + pred->regex.field_len = field->size; + } else if (field->filter_type == FILTER_DYN_STRING) + fn = filter_pred_strloc; else { fn = filter_pred_pchar; - pred->str_len = strlen(pred->str_val); + pred->regex.field_len = strlen(pred->regex.pattern); } } else { if (field->is_signed) - ret = strict_strtoll(pred->str_val, 0, &val); + ret = strict_strtoll(pred->regex.pattern, 0, &val); else - ret = strict_strtoull(pred->str_val, 0, &val); + ret = strict_strtoull(pred->regex.pattern, 0, &val); if (ret) { parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0); return -EINVAL; @@ -1045,8 +1164,8 @@ static struct filter_pred *create_pred(int op, char *operand1, char *operand2) return NULL; } - strcpy(pred->str_val, operand2); - pred->str_len = strlen(operand2); + strcpy(pred->regex.pattern, operand2); + pred->regex.len = strlen(pred->regex.pattern); pred->op = op; diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 9753fcc..c74848d 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -48,11 +48,11 @@ struct ____ftrace_##name { \ tstruct \ }; \ -static void __used ____ftrace_check_##name(void) \ +static void __always_unused ____ftrace_check_##name(void) \ { \ struct ____ftrace_##name *__entry = NULL; \ \ - /* force cmpile-time check on F_printk() */ \ + /* force compile-time check on F_printk() */ \ printk(print); \ } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 527e17e..ddee9c5 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -14,6 +14,69 @@ static int sys_refcount_exit; static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); +extern unsigned long __start_syscalls_metadata[]; +extern unsigned long __stop_syscalls_metadata[]; + +static struct syscall_metadata **syscalls_metadata; + +static struct syscall_metadata *find_syscall_meta(unsigned long syscall) +{ + struct syscall_metadata *start; + struct syscall_metadata *stop; + char str[KSYM_SYMBOL_LEN]; + + + start = (struct syscall_metadata *)__start_syscalls_metadata; + stop = (struct syscall_metadata *)__stop_syscalls_metadata; + kallsyms_lookup(syscall, NULL, NULL, NULL, str); + + for ( ; start < stop; start++) { + /* + * Only compare after the "sys" prefix. Archs that use + * syscall wrappers may have syscalls symbols aliases prefixed + * with "SyS" instead of "sys", leading to an unwanted + * mismatch. + */ + if (start->name && !strcmp(start->name + 3, str + 3)) + return start; + } + return NULL; +} + +static struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + +int syscall_name_to_nr(char *name) +{ + int i; + + if (!syscalls_metadata) + return -1; + + for (i = 0; i < NR_syscalls; i++) { + if (syscalls_metadata[i]) { + if (!strcmp(syscalls_metadata[i]->name, name)) + return i; + } + } + return -1; +} + +void set_syscall_enter_id(int num, int id) +{ + syscalls_metadata[num]->enter_id = id; +} + +void set_syscall_exit_id(int num, int id) +{ + syscalls_metadata[num]->exit_id = id; +} + enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags) { @@ -375,6 +438,29 @@ struct trace_event event_syscall_exit = { .trace = print_syscall_exit, }; +int __init init_ftrace_syscalls(void) +{ + struct syscall_metadata *meta; + unsigned long addr; + int i; + + syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * + NR_syscalls, GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return -ENOMEM; + } + + for (i = 0; i < NR_syscalls; i++) { + addr = arch_syscall_addr(i); + meta = find_syscall_meta(addr); + syscalls_metadata[i] = meta; + } + + return 0; +} +core_initcall(init_ftrace_syscalls); + #ifdef CONFIG_EVENT_PROFILE static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls); diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c index 39f1029..4ebfa5a 100644 --- a/lib/kernel_lock.c +++ b/lib/kernel_lock.c @@ -5,10 +5,13 @@ * relegated to obsolescence, but used by various less * important (or lazy) subsystems. */ -#include <linux/smp_lock.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/semaphore.h> +#include <linux/smp_lock.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/bkl.h> /* * The 'big kernel lock' @@ -113,21 +116,26 @@ static inline void __unlock_kernel(void) * This cannot happen asynchronously, so we only need to * worry about other CPU's. */ -void __lockfunc lock_kernel(void) +void __lockfunc _lock_kernel(const char *func, const char *file, int line) { - int depth = current->lock_depth+1; + int depth = current->lock_depth + 1; + + trace_lock_kernel(func, file, line); + if (likely(!depth)) __lock_kernel(); current->lock_depth = depth; } -void __lockfunc unlock_kernel(void) +void __lockfunc _unlock_kernel(const char *func, const char *file, int line) { BUG_ON(current->lock_depth < 0); if (likely(--current->lock_depth < 0)) __unlock_kernel(); + + trace_unlock_kernel(func, file, line); } -EXPORT_SYMBOL(lock_kernel); -EXPORT_SYMBOL(unlock_kernel); +EXPORT_SYMBOL(_lock_kernel); +EXPORT_SYMBOL(_unlock_kernel); diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 090d300..f0d1445 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -6,77 +6,93 @@ # all the offsets to the calls to mcount. # # -# What we want to end up with is a section in vmlinux called -# __mcount_loc that contains a list of pointers to all the -# call sites in the kernel that call mcount. Later on boot up, the kernel -# will read this list, save the locations and turn them into nops. -# When tracing or profiling is later enabled, these locations will then -# be converted back to pointers to some function. +# What we want to end up with this is that each object file will have a +# section called __mcount_loc that will hold the list of pointers to mcount +# callers. After final linking, the vmlinux will have within .init.data the +# list of all callers to mcount between __start_mcount_loc and __stop_mcount_loc. +# Later on boot up, the kernel will read this list, save the locations and turn +# them into nops. When tracing or profiling is later enabled, these locations +# will then be converted back to pointers to some function. # # This is no easy feat. This script is called just after the original # object is compiled and before it is linked. # -# The references to the call sites are offsets from the section of text -# that the call site is in. Hence, all functions in a section that -# has a call site to mcount, will have the offset from the beginning of -# the section and not the beginning of the function. +# When parse this object file using 'objdump', the references to the call +# sites are offsets from the section that the call site is in. Hence, all +# functions in a section that has a call site to mcount, will have the +# offset from the beginning of the section and not the beginning of the +# function. +# +# But where this section will reside finally in vmlinx is undetermined at +# this point. So we can't use this kind of offsets to record the final +# address of this call site. +# +# The trick is to change the call offset referring the start of a section to +# referring a function symbol in this section. During the link step, 'ld' will +# compute the final address according to the information we record. # -# The trick is to find a way to record the beginning of the section. -# The way we do this is to look at the first function in the section -# which will also be the location of that section after final link. # e.g. # # .section ".sched.text", "ax" -# .globl my_func -# my_func: # [...] -# call mcount (offset: 0x5) +# func1: +# [...] +# call mcount (offset: 0x10) # [...] # ret -# other_func: +# .globl fun2 +# func2: (offset: 0x20) # [...] -# call mcount (offset: 0x1b) +# [...] +# ret +# func3: +# [...] +# call mcount (offset: 0x30) # [...] # # Both relocation offsets for the mcounts in the above example will be -# offset from .sched.text. If we make another file called tmp.s with: +# offset from .sched.text. If we choose global symbol func2 as a reference and +# make another file called tmp.s with the new offsets: # # .section __mcount_loc -# .quad my_func + 0x5 -# .quad my_func + 0x1b +# .quad func2 - 0x10 +# .quad func2 + 0x10 # -# We can then compile this tmp.s into tmp.o, and link it to the original +# We can then compile this tmp.s into tmp.o, and link it back to the original # object. # -# But this gets hard if my_func is not globl (a static function). -# In such a case we have: +# In our algorithm, we will choose the first global function we meet in this +# section as the reference. But this gets hard if there is no global functions +# in this section. In such a case we have to select a local one. E.g. func1: # # .section ".sched.text", "ax" -# my_func: +# func1: # [...] -# call mcount (offset: 0x5) +# call mcount (offset: 0x10) # [...] # ret -# other_func: +# func2: # [...] -# call mcount (offset: 0x1b) +# call mcount (offset: 0x20) # [...] +# .section "other.section" # # If we make the tmp.s the same as above, when we link together with -# the original object, we will end up with two symbols for my_func: +# the original object, we will end up with two symbols for func1: # one local, one global. After final compile, we will end up with -# an undefined reference to my_func. +# an undefined reference to func1 or a wrong reference to another global +# func1 in other files. # # Since local objects can reference local variables, we need to find # a way to make tmp.o reference the local objects of the original object -# file after it is linked together. To do this, we convert the my_func +# file after it is linked together. To do this, we convert func1 # into a global symbol before linking tmp.o. Then after we link tmp.o -# we will only have a single symbol for my_func that is global. -# We can convert my_func back into a local symbol and we are done. +# we will only have a single symbol for func1 that is global. +# We can convert func1 back into a local symbol and we are done. # # Here are the steps we take: # -# 1) Record all the local symbols by using 'nm' +# 1) Record all the local and weak symbols by using 'nm' # 2) Use objdump to find all the call site offsets and sections for # mcount. # 3) Compile the list into its own object. @@ -86,10 +102,8 @@ # 6) Link together this new object with the list object. # 7) Convert the local functions back to local symbols and rename # the result as the original object. -# End. # 8) Link the object with the list object. # 9) Move the result back to the original object. -# End. # use strict; @@ -99,7 +113,7 @@ $P =~ s@.*/@@g; my $V = '0.1'; -if ($#ARGV < 7) { +if ($#ARGV != 10) { print "usage: $P arch bits objdump objcopy cc ld nm rm mv is_module inputfile\n"; print "version: $V\n"; exit(1); @@ -109,7 +123,7 @@ my ($arch, $bits, $objdump, $objcopy, $cc, $ld, $nm, $rm, $mv, $is_module, $inputfile) = @ARGV; # This file refers to mcount and shouldn't be ftraced, so lets' ignore it -if ($inputfile eq "kernel/trace/ftrace.o") { +if ($inputfile =~ m,kernel/trace/ftrace\.o$,) { exit(0); } @@ -119,6 +133,7 @@ my %text_sections = ( ".sched.text" => 1, ".spinlock.text" => 1, ".irqentry.text" => 1, + ".text.unlikely" => 1, ); $objdump = "objdump" if ((length $objdump) == 0); @@ -137,13 +152,47 @@ 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 $local_regex; # Match a local function (return function) +my $weak_regex; # Match a weak function (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 $section_type; # Section header plus possible alignment command +my $can_use_local = 0; # If we can use local function references + +# Shut up recordmcount if user has older objcopy +my $quiet_recordmcount = ".tmp_quiet_recordmcount"; +my $print_warning = 1; +$print_warning = 0 if ( -f $quiet_recordmcount); + +## +# check_objcopy - whether objcopy supports --globalize-symbols +# +# --globalize-symbols came out in 2.17, we must test the version +# of objcopy, and if it is less than 2.17, then we can not +# record local functions. +sub check_objcopy +{ + open (IN, "$objcopy --version |") or die "error running $objcopy"; + while (<IN>) { + if (/objcopy.*\s(\d+)\.(\d+)/) { + $can_use_local = 1 if ($1 > 2 || ($1 == 2 && $2 >= 17)); + last; + } + } + close (IN); + + if (!$can_use_local && $print_warning) { + print STDERR "WARNING: could not find objcopy version or version " . + "is less than 2.17.\n" . + "\tLocal function references are disabled.\n"; + open (QUIET, ">$quiet_recordmcount"); + printf QUIET "Disables the warning from recordmcount.pl\n"; + close QUIET; + } +} if ($arch eq "x86") { if ($bits == 64) { @@ -157,7 +206,8 @@ 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+)"; +$local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\S+)"; +$weak_regex = "^[0-9a-fA-F]+\\s+([wW])\\s+(\\S+)"; $section_regex = "Disassembly of section\\s+(\\S+):"; $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$"; @@ -206,7 +256,7 @@ if ($arch eq "x86_64") { $cc .= " -m32"; } elsif ($arch eq "powerpc") { - $nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; + $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$"; @@ -278,44 +328,17 @@ if ($filename =~ m,^(.*)(\.\S),) { my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s"; my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o"; -# -# --globalize-symbols came out in 2.17, we must test the version -# of objcopy, and if it is less than 2.17, then we can not -# record local functions. -my $use_locals = 01; -my $local_warn_once = 0; -my $found_version = 0; - -open (IN, "$objcopy --version |") || die "error running $objcopy"; -while (<IN>) { - if (/objcopy.*\s(\d+)\.(\d+)/) { - my $major = $1; - my $minor = $2; - - $found_version = 1; - if ($major < 2 || - ($major == 2 && $minor < 17)) { - $use_locals = 0; - } - last; - } -} -close (IN); - -if (!$found_version) { - print STDERR "WARNING: could not find objcopy version.\n" . - "\tDisabling local function references.\n"; -} +check_objcopy(); # # Step 1: find all the local (static functions) and weak symbols. -# 't' is local, 'w/W' is weak (we never use a weak function) +# 't' is local, 'w/W' is weak # open (IN, "$nm $inputfile|") || die "error running $nm"; while (<IN>) { - if (/$nm_regex/) { + if (/$local_regex/) { $locals{$1} = 1; - } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) { + } elsif (/$weak_regex/) { $weak{$2} = $1; } } @@ -333,26 +356,20 @@ my $offset = 0; # offset of ref_func to section beginning # sub update_funcs { - return if ($#offsets < 0); - - defined($ref_func) || die "No function to reference"; + return unless ($ref_func and @offsets); - # A section only had a weak function, to represent it. - # Unfortunately, a weak function may be overwritten by another - # function of the same name, making all these offsets incorrect. - # To be safe, we simply print a warning and bail. + # Sanity check on weak function. A weak function may be overwritten by + # another function of the same name, making all these offsets incorrect. if (defined $weak{$ref_func}) { - print STDERR - "$inputfile: WARNING: referencing weak function" . + die "$inputfile: ERROR: referencing weak function" . " $ref_func for mcount\n"; - return; } # is this function static? If so, note this fact. if (defined $locals{$ref_func}) { # only use locals if objcopy supports globalize-symbols - if (!$use_locals) { + if (!$can_use_local) { return; } $convert{$ref_func} = 1; @@ -378,9 +395,27 @@ open(IN, "$objdump -hdr $inputfile|") || die "error running $objdump"; my $text; + +# read headers first my $read_headers = 1; while (<IN>) { + + if ($read_headers && /$mcount_section/) { + # + # Somehow the make process can execute this script on an + # object twice. If it does, we would duplicate the mcount + # section and it will cause the function tracer self test + # to fail. Check if the mcount section exists, and if it does, + # warn and exit. + # + print STDERR "ERROR: $mcount_section already in $inputfile\n" . + "\tThis may be an indication that your build is corrupted.\n" . + "\tDelete $inputfile and try again. If the same object file\n" . + "\tstill causes an issue, then disable CONFIG_DYNAMIC_FTRACE.\n"; + exit(-1); + } + # is it a section? if (/$section_regex/) { $read_headers = 0; @@ -392,7 +427,7 @@ while (<IN>) { $read_function = 0; } # print out any recorded offsets - update_funcs() if (defined($ref_func)); + update_funcs(); # reset all markers and arrays $text_found = 0; @@ -421,21 +456,7 @@ while (<IN>) { $offset = hex $1; } } - } elsif ($read_headers && /$mcount_section/) { - # - # Somehow the make process can execute this script on an - # object twice. If it does, we would duplicate the mcount - # section and it will cause the function tracer self test - # to fail. Check if the mcount section exists, and if it does, - # warn and exit. - # - print STDERR "ERROR: $mcount_section already in $inputfile\n" . - "\tThis may be an indication that your build is corrupted.\n" . - "\tDelete $inputfile and try again. If the same object file\n" . - "\tstill causes an issue, then disable CONFIG_DYNAMIC_FTRACE.\n"; - exit(-1); } - # is this a call site to mcount? If so, record it to print later if ($text_found && /$mcount_regex/) { $offsets[$#offsets + 1] = hex $1; @@ -443,7 +464,7 @@ while (<IN>) { } # dump out anymore offsets that may have been found -update_funcs() if (defined($ref_func)); +update_funcs(); # If we did not find any mcount callers, we are done (do nothing). if (!$opened) { |
