From ac483c446b67870444c9eeaf8325d3d2af9b91bc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 2 Jan 2012 10:04:14 +0100 Subject: ftrace: Change filter/notrace set functions to return exit code Currently the ftrace_set_filter and ftrace_set_notrace functions do not return any return code. So there's no way for ftrace_ops user to tell wether the filter was correctly applied. The set_ftrace_filter interface returns error in case the filter did not match: # echo krava > set_ftrace_filter bash: echo: write error: Invalid argument Changing both ftrace_set_filter and ftrace_set_notrace functions to return zero if the filter was applied correctly or -E* values in case of error. Link: http://lkml.kernel.org/r/1325495060-6402-2-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 683d559a0eef..e2e0597c0845 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3146,8 +3146,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_lock(&ftrace_regex_lock); if (reset) ftrace_filter_reset(hash); - if (buf) - ftrace_match_records(hash, buf, len); + if (buf && !ftrace_match_records(hash, buf, len)) { + ret = -EINVAL; + goto out_regex_unlock; + } mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); @@ -3157,6 +3159,7 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_unlock(&ftrace_lock); + out_regex_unlock: mutex_unlock(&ftrace_regex_lock); free_ftrace_hash(hash); @@ -3173,10 +3176,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. */ -void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, +int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) { - ftrace_set_regex(ops, buf, len, reset, 1); + return ftrace_set_regex(ops, buf, len, reset, 1); } EXPORT_SYMBOL_GPL(ftrace_set_filter); @@ -3191,10 +3194,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter); * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. */ -void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, +int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) { - ftrace_set_regex(ops, buf, len, reset, 0); + return ftrace_set_regex(ops, buf, len, reset, 0); } EXPORT_SYMBOL_GPL(ftrace_set_notrace); /** -- cgit v1.3-14-g43fede From 1e42e83fde5537266c1d1e7fd8c010b3028d50fc Mon Sep 17 00:00:00 2001 From: Geunsik Lim Date: Wed, 8 Feb 2012 19:05:36 +0900 Subject: ftrace: sched_switch plugin is deprecated Actually, sched_switch function tracer is merged into wakeup/wakeup_rt Update 'mini-HOWTO' for ftrace(Kernel function tracer). If we want to trace "sched:sched_switch" to trace sched_switch func, We may utilize event option.(e.g: trace-cmd list -e | grep sched) This patch is based on Linux-3.3.rc2-SMP-PREEMPT Link: http://lkml.kernel.org/r/1328695537-15081-1-git-send-email-geunsik.lim@gmail.com Cc: Randy Dunlap Signed-off-by: Geunsik Lim Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a3f1bc5d2a00..10d5503f0d04 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2764,12 +2764,12 @@ static const char readme_msg[] = "tracing mini-HOWTO:\n\n" "# mount -t debugfs nodev /sys/kernel/debug\n\n" "# cat /sys/kernel/debug/tracing/available_tracers\n" - "wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n" + "wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n" "# cat /sys/kernel/debug/tracing/current_tracer\n" "nop\n" - "# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n" + "# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n" "# cat /sys/kernel/debug/tracing/current_tracer\n" - "sched_switch\n" + "wakeup\n" "# cat /sys/kernel/debug/tracing/trace_options\n" "noprint-parent nosym-offset nosym-addr noverbose\n" "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n" -- cgit v1.3-14-g43fede From 47b0edcb599ea6eb9ef16d3a08932a0e01485293 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Tue, 29 Nov 2011 22:08:00 +0100 Subject: tracing/trivial: Use kcalloc instead of kzalloc to allocate array The advantage of kcalloc is, that will prevent integer overflows which could result from the multiplication of number of elements and size and it is also a bit nicer to read. The semantic patch that makes this change is available in https://lkml.org/lkml/2011/11/25/107 Link: http://lkml.kernel.org/r/1322600880.1534.347.camel@localhost.localdomain Signed-off-by: Thomas Meyer Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 2 +- kernel/trace/trace_events_filter.c | 7 +++---- kernel/trace/trace_syscalls.c | 4 ++-- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e2e0597c0845..d1499e910fe8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1129,7 +1129,7 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits) return NULL; size = 1 << size_bits; - hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL); + hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL); if (!hash->buckets) { kfree(hash); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 24aee7127451..76afaee99dbc 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -685,7 +685,7 @@ find_event_field(struct ftrace_event_call *call, char *name) static int __alloc_pred_stack(struct pred_stack *stack, int n_preds) { - stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL); + stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL); if (!stack->preds) return -ENOMEM; stack->index = n_preds; @@ -826,8 +826,7 @@ static int __alloc_preds(struct event_filter *filter, int n_preds) if (filter->preds) __free_preds(filter); - filter->preds = - kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL); + filter->preds = kcalloc(n_preds, sizeof(*filter->preds), GFP_KERNEL); if (!filter->preds) return -ENOMEM; @@ -1486,7 +1485,7 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root) children = count_leafs(preds, &preds[root->left]); children += count_leafs(preds, &preds[root->right]); - root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL); + root->ops = kcalloc(children, sizeof(*root->ops), GFP_KERNEL); if (!root->ops) return -ENOMEM; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index cb654542c1a1..43500153dd1e 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -468,8 +468,8 @@ int __init init_ftrace_syscalls(void) unsigned long addr; int i; - syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * - NR_syscalls, GFP_KERNEL); + syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata), + GFP_KERNEL); if (!syscalls_metadata) { WARN_ON(1); return -ENOMEM; -- cgit v1.3-14-g43fede From e404b321dbb2d6e438522b7dce9c1d0c6a8c5275 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Sun, 19 Feb 2012 14:16:07 +0300 Subject: tracing: Don't print an extra separator of flags If __print_flags() is used after another __print_*() function, the temp seq_file buffer will not be empty on entry, and the delimiter will be printed even though there's just one field. We get something like: |S instead of just: S This is because the length of the temp seq buffer is used to determine if the delimiter is printed or not. But this algorithm fails when the seq buffer is not empty on entry, and the delimiter will be printed because it thinks that a previous field was already printed. Link: http://lkml.kernel.org/r/1329650167-480655-1-git-send-email-avagin@openvz.org Signed-off-by: Andrew Vagin Cc: Ingo Molnar Cc: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/trace_output.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 0d6ff3555942..3efd718984fb 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -300,7 +300,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long mask; const char *str; const char *ret = p->buffer + p->len; - int i; + int i, first = 1; for (i = 0; flag_array[i].name && flags; i++) { @@ -310,8 +310,10 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim, str = flag_array[i].name; flags &= ~mask; - if (p->len && delim) + if (!first && delim) trace_seq_puts(p, delim); + else + first = 0; trace_seq_puts(p, str); } -- cgit v1.3-14-g43fede From 5b34926114e39e12005031269613d2b13194aeba Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 20 Feb 2012 20:37:32 -0500 Subject: tracing: Don't use p->len field to determine output in __print_*() functions If more than one __print_*() function is used in a tracepoint (__print_flags(), __print_symbols(), etc), then the temp seq buffer will not be zero on entry. Using the temp seq buffer's length to know if data has been printed or not in the current function is incorrect and may produce incorrect results. Currently, no in-tree tracepoint causes this bug, but new ones may be created. Cc: Andrew Vagin Signed-off-by: Steven Rostedt --- kernel/trace/trace_output.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 3efd718984fb..c5a01873567d 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -319,7 +319,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim, /* check for left over flags */ if (flags) { - if (p->len && delim) + if (!first && delim) trace_seq_puts(p, delim); trace_seq_printf(p, "0x%lx", flags); } @@ -346,7 +346,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, break; } - if (!p->len) + if (ret == (const char *)(p->buffer + p->len)) trace_seq_printf(p, "0x%lx", val); trace_seq_putc(p, 0); @@ -372,7 +372,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, break; } - if (!p->len) + if (ret == (const char *)(p->buffer + p->len)) trace_seq_printf(p, "0x%llx", val); trace_seq_putc(p, 0); -- cgit v1.3-14-g43fede From e248491ac283b516958ca9ab62c8e74b6718bca8 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:48 +0100 Subject: ftrace: Add enable/disable ftrace_ops control interface Adding a way to temporarily enable/disable ftrace_ops. The change follows the same way as 'global' ftrace_ops are done. Introducing 2 global ftrace_ops - control_ops and ftrace_control_list which take over all ftrace_ops registered with FTRACE_OPS_FL_CONTROL flag. In addition new per cpu flag called 'disabled' is also added to ftrace_ops to provide the control information for each cpu. When ftrace_ops with FTRACE_OPS_FL_CONTROL is registered, it is set as disabled for all cpus. The ftrace_control_list contains all the registered 'control' ftrace_ops. The control_ops provides function which iterates ftrace_control_list and does the check for 'disabled' flag on current cpu. Adding 3 inline functions: ftrace_function_local_disable/ftrace_function_local_enable - enable/disable the ftrace_ops on current cpu ftrace_function_local_disabled - get disabled ftrace_ops::disabled value for current cpu Link: http://lkml.kernel.org/r/1329317514-8131-2-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 66 +++++++++++++++++++++++++++++ kernel/trace/ftrace.c | 111 +++++++++++++++++++++++++++++++++++++++++++++---- kernel/trace/trace.h | 2 + 3 files changed, 172 insertions(+), 7 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f33fb3b041c6..64a309d2fbd6 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -31,16 +31,33 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); +/* + * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are + * set in the flags member. + * + * ENABLED - set/unset when ftrace_ops is registered/unregistered + * GLOBAL - set manualy by ftrace_ops user to denote the ftrace_ops + * is part of the global tracers sharing the same filter + * via set_ftrace_* debugfs files. + * DYNAMIC - set when ftrace_ops is registered to denote dynamically + * allocated ftrace_ops which need special care + * CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops + * could be controled by following calls: + * ftrace_function_local_enable + * ftrace_function_local_disable + */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, FTRACE_OPS_FL_GLOBAL = 1 << 1, FTRACE_OPS_FL_DYNAMIC = 1 << 2, + FTRACE_OPS_FL_CONTROL = 1 << 3, }; struct ftrace_ops { ftrace_func_t func; struct ftrace_ops *next; unsigned long flags; + int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE struct ftrace_hash *notrace_hash; struct ftrace_hash *filter_hash; @@ -97,6 +114,55 @@ int register_ftrace_function(struct ftrace_ops *ops); int unregister_ftrace_function(struct ftrace_ops *ops); void clear_ftrace_function(void); +/** + * ftrace_function_local_enable - enable controlled ftrace_ops on current cpu + * + * This function enables tracing on current cpu by decreasing + * the per cpu control variable. + * It must be called with preemption disabled and only on ftrace_ops + * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. + */ +static inline void ftrace_function_local_enable(struct ftrace_ops *ops) +{ + if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL))) + return; + + (*this_cpu_ptr(ops->disabled))--; +} + +/** + * ftrace_function_local_disable - enable controlled ftrace_ops on current cpu + * + * This function enables tracing on current cpu by decreasing + * the per cpu control variable. + * It must be called with preemption disabled and only on ftrace_ops + * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. + */ +static inline void ftrace_function_local_disable(struct ftrace_ops *ops) +{ + if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL))) + return; + + (*this_cpu_ptr(ops->disabled))++; +} + +/** + * ftrace_function_local_disabled - returns ftrace_ops disabled value + * on current cpu + * + * This function returns value of ftrace_ops::disabled on current cpu. + * It must be called with preemption disabled and only on ftrace_ops + * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. + */ +static inline int ftrace_function_local_disabled(struct ftrace_ops *ops) +{ + WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)); + return *this_cpu_ptr(ops->disabled); +} + extern void ftrace_stub(unsigned long a0, unsigned long a1); #else /* !CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d1499e910fe8..f615f974d90e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -62,6 +62,8 @@ #define FTRACE_HASH_DEFAULT_BITS 10 #define FTRACE_HASH_MAX_BITS 12 +#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL) + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; @@ -89,12 +91,14 @@ static struct ftrace_ops ftrace_list_end __read_mostly = { }; static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; +static struct ftrace_ops control_ops; static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); @@ -168,6 +172,32 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) } #endif +static void control_ops_disable_all(struct ftrace_ops *ops) +{ + int cpu; + + for_each_possible_cpu(cpu) + *per_cpu_ptr(ops->disabled, cpu) = 1; +} + +static int control_ops_alloc(struct ftrace_ops *ops) +{ + int __percpu *disabled; + + disabled = alloc_percpu(int); + if (!disabled) + return -ENOMEM; + + ops->disabled = disabled; + control_ops_disable_all(ops); + return 0; +} + +static void control_ops_free(struct ftrace_ops *ops) +{ + free_percpu(ops->disabled); +} + static void update_global_ops(void) { ftrace_func_t func; @@ -259,6 +289,26 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) return 0; } +static void add_ftrace_list_ops(struct ftrace_ops **list, + struct ftrace_ops *main_ops, + struct ftrace_ops *ops) +{ + int first = *list == &ftrace_list_end; + add_ftrace_ops(list, ops); + if (first) + add_ftrace_ops(&ftrace_ops_list, main_ops); +} + +static int remove_ftrace_list_ops(struct ftrace_ops **list, + struct ftrace_ops *main_ops, + struct ftrace_ops *ops) +{ + int ret = remove_ftrace_ops(list, ops); + if (!ret && *list == &ftrace_list_end) + ret = remove_ftrace_ops(&ftrace_ops_list, main_ops); + return ret; +} + static int __register_ftrace_function(struct ftrace_ops *ops) { if (ftrace_disabled) @@ -270,15 +320,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) return -EBUSY; + /* We don't support both control and global flags set. */ + if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) + return -EINVAL; + if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; if (ops->flags & FTRACE_OPS_FL_GLOBAL) { - int first = ftrace_global_list == &ftrace_list_end; - add_ftrace_ops(&ftrace_global_list, ops); + add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops); ops->flags |= FTRACE_OPS_FL_ENABLED; - if (first) - add_ftrace_ops(&ftrace_ops_list, &global_ops); + } else if (ops->flags & FTRACE_OPS_FL_CONTROL) { + if (control_ops_alloc(ops)) + return -ENOMEM; + add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops); } else add_ftrace_ops(&ftrace_ops_list, ops); @@ -302,11 +357,23 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) return -EINVAL; if (ops->flags & FTRACE_OPS_FL_GLOBAL) { - ret = remove_ftrace_ops(&ftrace_global_list, ops); - if (!ret && ftrace_global_list == &ftrace_list_end) - ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops); + ret = remove_ftrace_list_ops(&ftrace_global_list, + &global_ops, ops); if (!ret) ops->flags &= ~FTRACE_OPS_FL_ENABLED; + } else if (ops->flags & FTRACE_OPS_FL_CONTROL) { + ret = remove_ftrace_list_ops(&ftrace_control_list, + &control_ops, ops); + if (!ret) { + /* + * The ftrace_ops is now removed from the list, + * so there'll be no new users. We must ensure + * all current users are done before we free + * the control data. + */ + synchronize_sched(); + control_ops_free(ops); + } } else ret = remove_ftrace_ops(&ftrace_ops_list, ops); @@ -3873,6 +3940,36 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) #endif /* CONFIG_DYNAMIC_FTRACE */ +static void +ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_ops *op; + + if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) + return; + + /* + * Some of the ops may be dynamically allocated, + * they must be freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + trace_recursion_set(TRACE_CONTROL_BIT); + op = rcu_dereference_raw(ftrace_control_list); + while (op != &ftrace_list_end) { + if (!ftrace_function_local_disabled(op) && + ftrace_ops_test(op, ip)) + op->func(ip, parent_ip); + + op = rcu_dereference_raw(op->next); + }; + trace_recursion_clear(TRACE_CONTROL_BIT); + preempt_enable_notrace(); +} + +static struct ftrace_ops control_ops = { + .func = ftrace_ops_control_func, +}; + static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b93ecbadad6d..55c6ea00f28a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -288,6 +288,8 @@ struct tracer { /* for function tracing recursion */ #define TRACE_INTERNAL_BIT (1<<11) #define TRACE_GLOBAL_BIT (1<<12) +#define TRACE_CONTROL_BIT (1<<13) + /* * Abuse of the trace_recursion. * As we need a way to maintain state if we are tracing the function -- cgit v1.3-14-g43fede From ceec0b6fc7cd43b38a40c2d40223f9cd0616f0cd Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:49 +0100 Subject: ftrace, perf: Add open/close tracepoint perf registration actions Adding TRACE_REG_PERF_OPEN and TRACE_REG_PERF_CLOSE to differentiate register/unregister from open/close actions. The register/unregister actions are invoked for the first/last tracepoint user when opening/closing the event. The open/close actions are invoked for each tracepoint user when opening/closing the event. Link: http://lkml.kernel.org/r/1329317514-8131-3-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 6 ++- kernel/trace/trace_event_perf.c | 116 ++++++++++++++++++++++++++-------------- kernel/trace/trace_events.c | 10 ++-- kernel/trace/trace_kprobe.c | 6 ++- kernel/trace/trace_syscalls.c | 14 +++-- 5 files changed, 101 insertions(+), 51 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index c3da42dd22ba..195e3606ddd7 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -146,6 +146,8 @@ enum trace_reg { TRACE_REG_UNREGISTER, TRACE_REG_PERF_REGISTER, TRACE_REG_PERF_UNREGISTER, + TRACE_REG_PERF_OPEN, + TRACE_REG_PERF_CLOSE, }; struct ftrace_event_call; @@ -157,7 +159,7 @@ struct ftrace_event_class { void *perf_probe; #endif int (*reg)(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); int (*define_fields)(struct ftrace_event_call *); struct list_head *(*get_fields)(struct ftrace_event_call *); struct list_head fields; @@ -165,7 +167,7 @@ struct ftrace_event_class { }; extern int ftrace_event_reg(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); enum { TRACE_EVENT_FL_ENABLED_BIT, diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 19a359d5e6d5..0cfcc37f63de 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -44,23 +44,17 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event, return 0; } -static int perf_trace_event_init(struct ftrace_event_call *tp_event, - struct perf_event *p_event) +static int perf_trace_event_reg(struct ftrace_event_call *tp_event, + struct perf_event *p_event) { struct hlist_head __percpu *list; - int ret; + int ret = -ENOMEM; int cpu; - ret = perf_trace_event_perm(tp_event, p_event); - if (ret) - return ret; - p_event->tp_event = tp_event; if (tp_event->perf_refcount++ > 0) return 0; - ret = -ENOMEM; - list = alloc_percpu(struct hlist_head); if (!list) goto fail; @@ -83,7 +77,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event, } } - ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER); + ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL); if (ret) goto fail; @@ -108,6 +102,69 @@ fail: return ret; } +static void perf_trace_event_unreg(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + int i; + + if (--tp_event->perf_refcount > 0) + goto out; + + tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL); + + /* + * Ensure our callback won't be called anymore. The buffers + * will be freed after that. + */ + tracepoint_synchronize_unregister(); + + free_percpu(tp_event->perf_events); + tp_event->perf_events = NULL; + + if (!--total_ref_count) { + for (i = 0; i < PERF_NR_CONTEXTS; i++) { + free_percpu(perf_trace_buf[i]); + perf_trace_buf[i] = NULL; + } + } +out: + module_put(tp_event->mod); +} + +static int perf_trace_event_open(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event); +} + +static void perf_trace_event_close(struct perf_event *p_event) +{ + struct ftrace_event_call *tp_event = p_event->tp_event; + tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event); +} + +static int perf_trace_event_init(struct ftrace_event_call *tp_event, + struct perf_event *p_event) +{ + int ret; + + ret = perf_trace_event_perm(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_reg(tp_event, p_event); + if (ret) + return ret; + + ret = perf_trace_event_open(p_event); + if (ret) { + perf_trace_event_unreg(p_event); + return ret; + } + + return 0; +} + int perf_trace_init(struct perf_event *p_event) { struct ftrace_event_call *tp_event; @@ -130,6 +187,14 @@ int perf_trace_init(struct perf_event *p_event) return ret; } +void perf_trace_destroy(struct perf_event *p_event) +{ + mutex_lock(&event_mutex); + perf_trace_event_close(p_event); + perf_trace_event_unreg(p_event); + mutex_unlock(&event_mutex); +} + int perf_trace_add(struct perf_event *p_event, int flags) { struct ftrace_event_call *tp_event = p_event->tp_event; @@ -154,37 +219,6 @@ void perf_trace_del(struct perf_event *p_event, int flags) hlist_del_rcu(&p_event->hlist_entry); } -void perf_trace_destroy(struct perf_event *p_event) -{ - struct ftrace_event_call *tp_event = p_event->tp_event; - int i; - - mutex_lock(&event_mutex); - if (--tp_event->perf_refcount > 0) - goto out; - - tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER); - - /* - * Ensure our callback won't be called anymore. The buffers - * will be freed after that. - */ - tracepoint_synchronize_unregister(); - - free_percpu(tp_event->perf_events); - tp_event->perf_events = NULL; - - if (!--total_ref_count) { - for (i = 0; i < PERF_NR_CONTEXTS; i++) { - free_percpu(perf_trace_buf[i]); - perf_trace_buf[i] = NULL; - } - } -out: - module_put(tp_event->mod); - mutex_unlock(&event_mutex); -} - __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, struct pt_regs *regs, int *rctxp) { diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c212a7f934ec..5138fea37908 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -147,7 +147,8 @@ int trace_event_raw_init(struct ftrace_event_call *call) } EXPORT_SYMBOL_GPL(trace_event_raw_init); -int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type) +int ftrace_event_reg(struct ftrace_event_call *call, + enum trace_reg type, void *data) { switch (type) { case TRACE_REG_REGISTER: @@ -170,6 +171,9 @@ int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type) call->class->perf_probe, call); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + return 0; #endif } return 0; @@ -209,7 +213,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, tracing_stop_cmdline_record(); call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD; } - call->class->reg(call, TRACE_REG_UNREGISTER); + call->class->reg(call, TRACE_REG_UNREGISTER, NULL); } break; case 1: @@ -218,7 +222,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, tracing_start_cmdline_record(); call->flags |= TRACE_EVENT_FL_RECORDED_CMD; } - ret = call->class->reg(call, TRACE_REG_REGISTER); + ret = call->class->reg(call, TRACE_REG_REGISTER, NULL); if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 00d527c945a4..5667f8958cc9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1892,7 +1892,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, #endif /* CONFIG_PERF_EVENTS */ static __kprobes -int kprobe_register(struct ftrace_event_call *event, enum trace_reg type) +int kprobe_register(struct ftrace_event_call *event, + enum trace_reg type, void *data) { struct trace_probe *tp = (struct trace_probe *)event->data; @@ -1909,6 +1910,9 @@ int kprobe_register(struct ftrace_event_call *event, enum trace_reg type) case TRACE_REG_PERF_UNREGISTER: disable_trace_probe(tp, TP_FLAG_PROFILE); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + return 0; #endif } return 0; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 43500153dd1e..e23515f51ed4 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -17,9 +17,9 @@ static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); static int syscall_enter_register(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); static int syscall_exit_register(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); static int syscall_enter_define_fields(struct ftrace_event_call *call); static int syscall_exit_define_fields(struct ftrace_event_call *call); @@ -649,7 +649,7 @@ void perf_sysexit_disable(struct ftrace_event_call *call) #endif /* CONFIG_PERF_EVENTS */ static int syscall_enter_register(struct ftrace_event_call *event, - enum trace_reg type) + enum trace_reg type, void *data) { switch (type) { case TRACE_REG_REGISTER: @@ -664,13 +664,16 @@ static int syscall_enter_register(struct ftrace_event_call *event, case TRACE_REG_PERF_UNREGISTER: perf_sysenter_disable(event); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + return 0; #endif } return 0; } static int syscall_exit_register(struct ftrace_event_call *event, - enum trace_reg type) + enum trace_reg type, void *data) { switch (type) { case TRACE_REG_REGISTER: @@ -685,6 +688,9 @@ static int syscall_exit_register(struct ftrace_event_call *event, case TRACE_REG_PERF_UNREGISTER: perf_sysexit_disable(event); return 0; + case TRACE_REG_PERF_OPEN: + case TRACE_REG_PERF_CLOSE: + return 0; #endif } return 0; -- cgit v1.3-14-g43fede From 489c75c3b333dfda4c8d2b7ad1b00e5da024bfa7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:50 +0100 Subject: ftrace, perf: Add add/del tracepoint perf registration actions Adding TRACE_REG_PERF_ADD and TRACE_REG_PERF_DEL to handle perf event schedule in/out actions. The add action is invoked for when the perf event is scheduled in, while the del action is invoked when the event is scheduled out. Link: http://lkml.kernel.org/r/1329317514-8131-4-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 ++ kernel/trace/trace_event_perf.c | 4 +++- kernel/trace/trace_events.c | 2 ++ kernel/trace/trace_kprobe.c | 2 ++ kernel/trace/trace_syscalls.c | 4 ++++ 5 files changed, 13 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 195e3606ddd7..2bf677cb2d6f 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -148,6 +148,8 @@ enum trace_reg { TRACE_REG_PERF_UNREGISTER, TRACE_REG_PERF_OPEN, TRACE_REG_PERF_CLOSE, + TRACE_REG_PERF_ADD, + TRACE_REG_PERF_DEL, }; struct ftrace_event_call; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0cfcc37f63de..d72af0b03822 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -211,12 +211,14 @@ int perf_trace_add(struct perf_event *p_event, int flags) list = this_cpu_ptr(pcpu_list); hlist_add_head_rcu(&p_event->hlist_entry, list); - return 0; + return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event); } void perf_trace_del(struct perf_event *p_event, int flags) { + struct ftrace_event_call *tp_event = p_event->tp_event; hlist_del_rcu(&p_event->hlist_entry); + tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event); } __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 5138fea37908..079a93ae8a9d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -173,6 +173,8 @@ int ftrace_event_reg(struct ftrace_event_call *call, return 0; case TRACE_REG_PERF_OPEN: case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: return 0; #endif } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5667f8958cc9..580a05ec926b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1912,6 +1912,8 @@ int kprobe_register(struct ftrace_event_call *event, return 0; case TRACE_REG_PERF_OPEN: case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: return 0; #endif } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index e23515f51ed4..96fc73369099 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -666,6 +666,8 @@ static int syscall_enter_register(struct ftrace_event_call *event, return 0; case TRACE_REG_PERF_OPEN: case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: return 0; #endif } @@ -690,6 +692,8 @@ static int syscall_exit_register(struct ftrace_event_call *event, return 0; case TRACE_REG_PERF_OPEN: case TRACE_REG_PERF_CLOSE: + case TRACE_REG_PERF_ADD: + case TRACE_REG_PERF_DEL: return 0; #endif } -- cgit v1.3-14-g43fede From e59a0bff3ecf389951e3c9378ddfd00f6448bfaa Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:51 +0100 Subject: ftrace: Add FTRACE_ENTRY_REG macro to allow event registration Adding FTRACE_ENTRY_REG macro so particular ftrace entries could specify registration function and thus become accesible via perf. This will be used in upcomming patch for function trace. Link: http://lkml.kernel.org/r/1329317514-8131-5-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 4 ++++ kernel/trace/trace_export.c | 18 ++++++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 55c6ea00f28a..638476af8d7b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -68,6 +68,10 @@ enum trace_type { #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) + #include "trace_entries.h" /* diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index bbeec31e0ae3..f74de861cde9 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -18,6 +18,14 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace +/* + * The FTRACE_ENTRY_REG macro allows ftrace entry to define register + * function and thus become accesible via perf. + */ +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) + /* not needed for this file */ #undef __field_struct #define __field_struct(type, item) @@ -152,13 +160,14 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #undef F_printk #define F_printk(fmt, args...) #fmt ", " __stringify(args) -#undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ +#undef FTRACE_ENTRY_REG +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn)\ \ struct ftrace_event_class event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ .define_fields = ftrace_define_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ + .reg = regfn, \ }; \ \ struct ftrace_event_call __used event_##call = { \ @@ -170,4 +179,9 @@ struct ftrace_event_call __used event_##call = { \ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; +#undef FTRACE_ENTRY +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ + FTRACE_ENTRY_REG(call, struct_name, etype, \ + PARAMS(tstruct), PARAMS(print), NULL) + #include "trace_entries.h" -- cgit v1.3-14-g43fede From ced39002f5ea736b716ae233fb68b26d59783912 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:52 +0100 Subject: ftrace, perf: Add support to use function tracepoint in perf Adding perf registration support for the ftrace function event, so it is now possible to register it via perf interface. The perf_event struct statically contains ftrace_ops as a handle for function tracer. The function tracer is registered/unregistered in open/close actions. To be efficient, we enable/disable ftrace_ops each time the traced process is scheduled in/out (via TRACE_REG_PERF_(ADD|DELL) handlers). This way tracing is enabled only when the process is running. Intentionally using this way instead of the event's hw state PERF_HES_STOPPED, which would not disable the ftrace_ops. It is now possible to use function trace within perf commands like: perf record -e ftrace:function ls perf stat -e ftrace:function ls Allowed only for root. Link: http://lkml.kernel.org/r/1329317514-8131-6-git-send-email-jolsa@redhat.com Acked-by: Frederic Weisbecker Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- include/linux/perf_event.h | 3 ++ kernel/trace/trace.h | 11 ++++++ kernel/trace/trace_entries.h | 6 ++- kernel/trace/trace_event_perf.c | 86 +++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace_export.c | 5 +++ 5 files changed, 109 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 412b790f5da6..92a056f6d18d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -859,6 +859,9 @@ struct perf_event { #ifdef CONFIG_EVENT_TRACING struct ftrace_event_call *tp_event; struct event_filter *filter; +#ifdef CONFIG_FUNCTION_TRACER + struct ftrace_ops ftrace_ops; +#endif #endif #ifdef CONFIG_CGROUP_PERF diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 638476af8d7b..76a1c5094bbf 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -595,6 +595,8 @@ static inline int ftrace_trace_task(struct task_struct *task) static inline int ftrace_is_dead(void) { return 0; } #endif +int ftrace_event_is_function(struct ftrace_event_call *call); + /* * struct trace_parser - servers for reading the user input separated by spaces * @cont: set if the input is not complete - no final space char was found @@ -832,4 +834,13 @@ extern const char *__stop___trace_bprintk_fmt[]; FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" +#ifdef CONFIG_PERF_EVENTS +#ifdef CONFIG_FUNCTION_TRACER +int perf_ftrace_event_register(struct ftrace_event_call *call, + enum trace_reg type, void *data); +#else +#define perf_ftrace_event_register NULL +#endif /* CONFIG_FUNCTION_TRACER */ +#endif /* CONFIG_PERF_EVENTS */ + #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 93365907f219..47db7eda0531 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -55,7 +55,7 @@ /* * Function trace entry - function address and parent function address: */ -FTRACE_ENTRY(function, ftrace_entry, +FTRACE_ENTRY_REG(function, ftrace_entry, TRACE_FN, @@ -64,7 +64,9 @@ FTRACE_ENTRY(function, ftrace_entry, __field( unsigned long, parent_ip ) ), - F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip) + F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip), + + perf_ftrace_event_register ); /* Function call entry */ diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index d72af0b03822..fdeeb5c49627 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -24,6 +24,11 @@ static int total_ref_count; static int perf_trace_event_perm(struct ftrace_event_call *tp_event, struct perf_event *p_event) { + /* The ftrace function trace is allowed only for root. */ + if (ftrace_event_is_function(tp_event) && + perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* No tracing, just counting, so no obvious leak */ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) return 0; @@ -250,3 +255,84 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, return raw_data; } EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); + +#ifdef CONFIG_FUNCTION_TRACER +static void +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_entry *entry; + struct hlist_head *head; + struct pt_regs regs; + int rctx; + +#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \ + sizeof(u64)) - sizeof(u32)) + + BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE); + + perf_fetch_caller_regs(®s); + + entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx); + if (!entry) + return; + + entry->ip = ip; + entry->parent_ip = parent_ip; + + head = this_cpu_ptr(event_function.perf_events); + perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, + 1, ®s, head); + +#undef ENTRY_SIZE +} + +static int perf_ftrace_function_register(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + + ops->flags |= FTRACE_OPS_FL_CONTROL; + ops->func = perf_ftrace_function_call; + return register_ftrace_function(ops); +} + +static int perf_ftrace_function_unregister(struct perf_event *event) +{ + struct ftrace_ops *ops = &event->ftrace_ops; + return unregister_ftrace_function(ops); +} + +static void perf_ftrace_function_enable(struct perf_event *event) +{ + ftrace_function_local_enable(&event->ftrace_ops); +} + +static void perf_ftrace_function_disable(struct perf_event *event) +{ + ftrace_function_local_disable(&event->ftrace_ops); +} + +int perf_ftrace_event_register(struct ftrace_event_call *call, + enum trace_reg type, void *data) +{ + switch (type) { + case TRACE_REG_REGISTER: + case TRACE_REG_UNREGISTER: + break; + case TRACE_REG_PERF_REGISTER: + case TRACE_REG_PERF_UNREGISTER: + return 0; + case TRACE_REG_PERF_OPEN: + return perf_ftrace_function_register(data); + case TRACE_REG_PERF_CLOSE: + return perf_ftrace_function_unregister(data); + case TRACE_REG_PERF_ADD: + perf_ftrace_function_enable(data); + return 0; + case TRACE_REG_PERF_DEL: + perf_ftrace_function_disable(data); + return 0; + } + + return -EINVAL; +} +#endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index f74de861cde9..a3dbee6d04cd 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -184,4 +184,9 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; FTRACE_ENTRY_REG(call, struct_name, etype, \ PARAMS(tstruct), PARAMS(print), NULL) +int ftrace_event_is_function(struct ftrace_event_call *call) +{ + return call == &event_function; +} + #include "trace_entries.h" -- cgit v1.3-14-g43fede From 02aa3162edaa166a01d193f80ccde890be8b55da Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:53 +0100 Subject: ftrace: Allow to specify filter field type for ftrace events Adding FILTER_TRACE_FN event field type for function tracepoint event, so it can be properly recognized within filtering code. Currently all fields of ftrace subsystem events share the common field type FILTER_OTHER. Since the function trace fields need special care within the filtering code we need to recognize it properly, hence adding the FILTER_TRACE_FN event type. Adding filter parameter to the FTRACE_ENTRY macro, to specify the filter field type for the event. Link: http://lkml.kernel.org/r/1329317514-8131-7-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 1 + kernel/trace/trace.h | 23 +++++++++-------- kernel/trace/trace_entries.h | 48 +++++++++++++++++++++++++---------- kernel/trace/trace_events_filter.c | 7 +++++- kernel/trace/trace_export.c | 51 +++++++++++++++++++++----------------- 5 files changed, 83 insertions(+), 47 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 2bf677cb2d6f..dd478fc8f9f5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -245,6 +245,7 @@ enum { FILTER_STATIC_STRING, FILTER_DYN_STRING, FILTER_PTR_STRING, + FILTER_TRACE_FN, }; #define EVENT_STORAGE_SIZE 128 diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 76a1c5094bbf..29f93cd434a5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -56,21 +56,23 @@ enum trace_type { #define F_STRUCT(args...) args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ - struct struct_name { \ - struct trace_entry ent; \ - tstruct \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ + struct struct_name { \ + struct trace_entry ent; \ + tstruct \ } #undef TP_ARGS #define TP_ARGS(args...) args #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ + filter, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) #include "trace_entries.h" @@ -826,12 +828,13 @@ extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ __attribute__((__aligned__(4))) event_##call; #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) #include "trace_entries.h" #ifdef CONFIG_PERF_EVENTS diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 47db7eda0531..d91eb0541b3a 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -66,6 +66,8 @@ FTRACE_ENTRY_REG(function, ftrace_entry, F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip), + FILTER_TRACE_FN, + perf_ftrace_event_register ); @@ -80,7 +82,9 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry, __field_desc( int, graph_ent, depth ) ), - F_printk("--> %lx (%d)", __entry->func, __entry->depth) + F_printk("--> %lx (%d)", __entry->func, __entry->depth), + + FILTER_OTHER ); /* Function return entry */ @@ -100,7 +104,9 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry, F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d", __entry->func, __entry->depth, __entry->calltime, __entry->rettime, - __entry->depth) + __entry->depth), + + FILTER_OTHER ); /* @@ -129,8 +135,9 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry, F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu - ) + __entry->next_cpu), + + FILTER_OTHER ); /* @@ -148,8 +155,9 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu - ) + __entry->next_cpu), + + FILTER_OTHER ); /* @@ -171,7 +179,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry, "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", __entry->caller[0], __entry->caller[1], __entry->caller[2], __entry->caller[3], __entry->caller[4], __entry->caller[5], - __entry->caller[6], __entry->caller[7]) + __entry->caller[6], __entry->caller[7]), + + FILTER_OTHER ); FTRACE_ENTRY(user_stack, userstack_entry, @@ -187,7 +197,9 @@ FTRACE_ENTRY(user_stack, userstack_entry, "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", __entry->caller[0], __entry->caller[1], __entry->caller[2], __entry->caller[3], __entry->caller[4], __entry->caller[5], - __entry->caller[6], __entry->caller[7]) + __entry->caller[6], __entry->caller[7]), + + FILTER_OTHER ); /* @@ -204,7 +216,9 @@ FTRACE_ENTRY(bprint, bprint_entry, ), F_printk("%08lx fmt:%p", - __entry->ip, __entry->fmt) + __entry->ip, __entry->fmt), + + FILTER_OTHER ); FTRACE_ENTRY(print, print_entry, @@ -217,7 +231,9 @@ FTRACE_ENTRY(print, print_entry, ), F_printk("%08lx %s", - __entry->ip, __entry->buf) + __entry->ip, __entry->buf), + + FILTER_OTHER ); FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, @@ -236,7 +252,9 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, F_printk("%lx %lx %lx %d %x %x", (unsigned long)__entry->phys, __entry->value, __entry->pc, - __entry->map_id, __entry->opcode, __entry->width) + __entry->map_id, __entry->opcode, __entry->width), + + FILTER_OTHER ); FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, @@ -254,7 +272,9 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, F_printk("%lx %lx %lx %d %x", (unsigned long)__entry->phys, __entry->virt, __entry->len, - __entry->map_id, __entry->opcode) + __entry->map_id, __entry->opcode), + + FILTER_OTHER ); @@ -274,6 +294,8 @@ FTRACE_ENTRY(branch, trace_branch, F_printk("%u:%s:%s (%u)", __entry->line, - __entry->func, __entry->file, __entry->correct) + __entry->func, __entry->file, __entry->correct), + + FILTER_OTHER ); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 76afaee99dbc..3da3d0ec3584 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -899,6 +899,11 @@ int filter_assign_type(const char *type) return FILTER_OTHER; } +static bool is_function_field(struct ftrace_event_field *field) +{ + return field->filter_type == FILTER_TRACE_FN; +} + static bool is_string_field(struct ftrace_event_field *field) { return field->filter_type == FILTER_DYN_STRING || @@ -986,7 +991,7 @@ static int init_pred(struct filter_parse_state *ps, fn = filter_pred_strloc; else fn = filter_pred_pchar; - } else { + } else if (!is_function_field(field)) { if (field->is_signed) ret = strict_strtoll(pred->regex.pattern, 0, &val); else diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index a3dbee6d04cd..7b46c9bd22ae 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -23,8 +23,10 @@ * function and thus become accesible via perf. */ #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ + filter, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) /* not needed for this file */ #undef __field_struct @@ -52,21 +54,22 @@ #define F_printk(fmt, args...) fmt, args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ -struct ____ftrace_##name { \ - tstruct \ -}; \ -static void __always_unused ____ftrace_check_##name(void) \ -{ \ - struct ____ftrace_##name *__entry = NULL; \ - \ - /* force compile-time check on F_printk() */ \ - printk(print); \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +struct ____ftrace_##name { \ + tstruct \ +}; \ +static void __always_unused ____ftrace_check_##name(void) \ +{ \ + struct ____ftrace_##name *__entry = NULL; \ + \ + /* force compile-time check on F_printk() */ \ + printk(print); \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ + filter) #include "trace_entries.h" @@ -75,7 +78,7 @@ static void __always_unused ____ftrace_check_##name(void) \ ret = trace_define_field(event_call, #type, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ if (ret) \ return ret; @@ -85,7 +88,7 @@ static void __always_unused ____ftrace_check_##name(void) \ offsetof(typeof(field), \ container.item), \ sizeof(field.container.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ if (ret) \ return ret; @@ -99,7 +102,7 @@ static void __always_unused ____ftrace_check_##name(void) \ ret = trace_define_field(event_call, event_storage, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ mutex_unlock(&event_storage_mutex); \ if (ret) \ return ret; \ @@ -112,7 +115,7 @@ static void __always_unused ____ftrace_check_##name(void) \ offsetof(typeof(field), \ container.item), \ sizeof(field.container.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), filter_type); \ if (ret) \ return ret; @@ -120,17 +123,18 @@ static void __always_unused ____ftrace_check_##name(void) \ #define __dynamic_array(type, item) \ ret = trace_define_field(event_call, #type, #item, \ offsetof(typeof(field), item), \ - 0, is_signed_type(type), FILTER_OTHER);\ + 0, is_signed_type(type), filter_type);\ if (ret) \ return ret; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ int \ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ { \ struct struct_name field; \ int ret; \ + int filter_type = filter; \ \ tstruct; \ \ @@ -161,7 +165,8 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #define F_printk(fmt, args...) #fmt ", " __stringify(args) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn)\ +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ + regfn) \ \ struct ftrace_event_class event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ @@ -180,9 +185,9 @@ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \ FTRACE_ENTRY_REG(call, struct_name, etype, \ - PARAMS(tstruct), PARAMS(print), NULL) + PARAMS(tstruct), PARAMS(print), filter, NULL) int ftrace_event_is_function(struct ftrace_event_call *call) { -- cgit v1.3-14-g43fede From 5500fa51199aee770ce53718853732600543619e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 15 Feb 2012 15:51:54 +0100 Subject: ftrace, perf: Add filter support for function trace event Adding support to filter function trace event via perf interface. It is now possible to use filter interface in the perf tool like: perf record -e ftrace:function --filter="(ip == mm_*)" ls The filter syntax is restricted to the the 'ip' field only, and following operators are accepted '==' '!=' '||', ending up with the filter strings like: ip == f1[, ]f2 ... || ip != f3[, ]f4 ... with comma ',' or space ' ' as a function separator. If the space ' ' is used as a separator, the right side of the assignment needs to be enclosed in double quotes '"', e.g.: perf record -e ftrace:function --filter '(ip == do_execve,sys_*,ext*)' ls perf record -e ftrace:function --filter '(ip == "do_execve,sys_*,ext*")' ls perf record -e ftrace:function --filter '(ip == "do_execve sys_* ext*")' ls The '==' operator adds trace filter with same effect as would be added via set_ftrace_filter file. The '!=' operator adds trace filter with same effect as would be added via set_ftrace_notrace file. The right side of the '!=', '==' operators is list of functions or regexp. to be added to filter separated by space. The '||' operator is used for connecting multiple filter definitions together. It is possible to have more than one '==' and '!=' operators within one filter string. Link: http://lkml.kernel.org/r/1329317514-8131-8-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 7 +- kernel/trace/ftrace.c | 6 ++ kernel/trace/trace.h | 2 - kernel/trace/trace_event_perf.c | 4 +- kernel/trace/trace_events_filter.c | 165 +++++++++++++++++++++++++++++++++++-- 5 files changed, 172 insertions(+), 12 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 64a309d2fbd6..72a6cabb4d5b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -250,6 +250,7 @@ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); void ftrace_set_global_filter(unsigned char *buf, int len, int reset); void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); +void ftrace_free_filter(struct ftrace_ops *ops); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); @@ -380,9 +381,6 @@ extern void ftrace_enable_daemon(void); #else static inline int skip_trace(unsigned long ip) { return 0; } static inline int ftrace_force_update(void) { return 0; } -static inline void ftrace_set_filter(unsigned char *buf, int len, int reset) -{ -} static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } static inline void ftrace_release_mod(struct module *mod) {} @@ -406,6 +404,9 @@ static inline int ftrace_text_reserved(void *start, void *end) */ #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) +#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) +#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) +#define ftrace_free_filter(ops) do { } while (0) static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { return -ENODEV; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f615f974d90e..867bd1dd2dd0 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1186,6 +1186,12 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); } +void ftrace_free_filter(struct ftrace_ops *ops) +{ + free_ftrace_hash(ops->filter_hash); + free_ftrace_hash(ops->notrace_hash); +} + static struct ftrace_hash *alloc_ftrace_hash(int size_bits) { struct ftrace_hash *hash; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 29f93cd434a5..54faec790bc1 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -776,9 +776,7 @@ struct filter_pred { u64 val; struct regex regex; unsigned short *ops; -#ifdef CONFIG_FTRACE_STARTUP_TEST struct ftrace_event_field *field; -#endif int offset; int not; int op; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index fdeeb5c49627..fee3752ae8f6 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -298,7 +298,9 @@ static int perf_ftrace_function_register(struct perf_event *event) static int perf_ftrace_function_unregister(struct perf_event *event) { struct ftrace_ops *ops = &event->ftrace_ops; - return unregister_ftrace_function(ops); + int ret = unregister_ftrace_function(ops); + ftrace_free_filter(ops); + return ret; } static void perf_ftrace_function_enable(struct perf_event *event) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 3da3d0ec3584..431dba8b7542 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -81,6 +81,7 @@ enum { FILT_ERR_TOO_MANY_PREDS, FILT_ERR_MISSING_FIELD, FILT_ERR_INVALID_FILTER, + FILT_ERR_IP_FIELD_ONLY, }; static char *err_text[] = { @@ -96,6 +97,7 @@ static char *err_text[] = { "Too many terms in predicate expression", "Missing field name and/or value", "Meaningless filter expression", + "Only 'ip' field is supported for function trace", }; struct opstack_op { @@ -991,7 +993,12 @@ static int init_pred(struct filter_parse_state *ps, fn = filter_pred_strloc; else fn = filter_pred_pchar; - } else if (!is_function_field(field)) { + } else if (is_function_field(field)) { + if (strcmp(field->name, "ip")) { + parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0); + return -EINVAL; + } + } else { if (field->is_signed) ret = strict_strtoll(pred->regex.pattern, 0, &val); else @@ -1338,10 +1345,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps, strcpy(pred.regex.pattern, operand2); pred.regex.len = strlen(pred.regex.pattern); - -#ifdef CONFIG_FTRACE_STARTUP_TEST pred.field = field; -#endif return init_pred(ps, field, &pred) ? NULL : &pred; } @@ -1954,6 +1958,148 @@ void ftrace_profile_free_filter(struct perf_event *event) __free_filter(filter); } +struct function_filter_data { + struct ftrace_ops *ops; + int first_filter; + int first_notrace; +}; + +#ifdef CONFIG_FUNCTION_TRACER +static char ** +ftrace_function_filter_re(char *buf, int len, int *count) +{ + char *str, *sep, **re; + + str = kstrndup(buf, len, GFP_KERNEL); + if (!str) + return NULL; + + /* + * The argv_split function takes white space + * as a separator, so convert ',' into spaces. + */ + while ((sep = strchr(str, ','))) + *sep = ' '; + + re = argv_split(GFP_KERNEL, str, count); + kfree(str); + return re; +} + +static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter, + int reset, char *re, int len) +{ + int ret; + + if (filter) + ret = ftrace_set_filter(ops, re, len, reset); + else + ret = ftrace_set_notrace(ops, re, len, reset); + + return ret; +} + +static int __ftrace_function_set_filter(int filter, char *buf, int len, + struct function_filter_data *data) +{ + int i, re_cnt, ret; + int *reset; + char **re; + + reset = filter ? &data->first_filter : &data->first_notrace; + + /* + * The 'ip' field could have multiple filters set, separated + * either by space or comma. We first cut the filter and apply + * all pieces separatelly. + */ + re = ftrace_function_filter_re(buf, len, &re_cnt); + if (!re) + return -EINVAL; + + for (i = 0; i < re_cnt; i++) { + ret = ftrace_function_set_regexp(data->ops, filter, *reset, + re[i], strlen(re[i])); + if (ret) + break; + + if (*reset) + *reset = 0; + } + + argv_free(re); + return ret; +} + +static int ftrace_function_check_pred(struct filter_pred *pred, int leaf) +{ + struct ftrace_event_field *field = pred->field; + + if (leaf) { + /* + * Check the leaf predicate for function trace, verify: + * - only '==' and '!=' is used + * - the 'ip' field is used + */ + if ((pred->op != OP_EQ) && (pred->op != OP_NE)) + return -EINVAL; + + if (strcmp(field->name, "ip")) + return -EINVAL; + } else { + /* + * Check the non leaf predicate for function trace, verify: + * - only '||' is used + */ + if (pred->op != OP_OR) + return -EINVAL; + } + + return 0; +} + +static int ftrace_function_set_filter_cb(enum move_type move, + struct filter_pred *pred, + int *err, void *data) +{ + /* Checking the node is valid for function trace. */ + if ((move != MOVE_DOWN) || + (pred->left != FILTER_PRED_INVALID)) { + *err = ftrace_function_check_pred(pred, 0); + } else { + *err = ftrace_function_check_pred(pred, 1); + if (*err) + return WALK_PRED_ABORT; + + *err = __ftrace_function_set_filter(pred->op == OP_EQ, + pred->regex.pattern, + pred->regex.len, + data); + } + + return (*err) ? WALK_PRED_ABORT : WALK_PRED_DEFAULT; +} + +static int ftrace_function_set_filter(struct perf_event *event, + struct event_filter *filter) +{ + struct function_filter_data data = { + .first_filter = 1, + .first_notrace = 1, + .ops = &event->ftrace_ops, + }; + + return walk_pred_tree(filter->preds, filter->root, + ftrace_function_set_filter_cb, &data); +} +#else +static int ftrace_function_set_filter(struct perf_event *event, + struct event_filter *filter) +{ + return -ENODEV; +} +#endif /* CONFIG_FUNCTION_TRACER */ + int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str) { @@ -1974,9 +2120,16 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, goto out_unlock; err = create_filter(call, filter_str, false, &filter); - if (!err) - event->filter = filter; + if (err) + goto free_filter; + + if (ftrace_event_is_function(call)) + err = ftrace_function_set_filter(event, filter); else + event->filter = filter; + +free_filter: + if (err || ftrace_event_is_function(call)) __free_filter(filter); out_unlock: -- cgit v1.3-14-g43fede From 499e547057f5bba5cd6f87ebe59b05d0c59da905 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 22 Feb 2012 15:50:28 -0500 Subject: tracing/ring-buffer: Only have tracing_on disable tracing buffers As the ring-buffer code is being used by other facilities in the kernel, having tracing_on file disable *all* buffers is not a desired affect. It should only disable the ftrace buffers that are being used. Move the code into the trace.c file and use the buffer disabling for tracing_on() and tracing_off(). This way only the ftrace buffers will be affected by them and other kernel utilities will not be confused to why their output suddenly stopped. Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 3 + kernel/trace/ring_buffer.c | 157 +++++++++++++++++--------------------------- kernel/trace/trace.c | 107 ++++++++++++++++++++++++++++++ kernel/trace/trace.h | 1 + 4 files changed, 171 insertions(+), 97 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 67be0376d8e3..7be2e88f23fd 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -151,6 +151,9 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_disable(struct ring_buffer *buffer); void ring_buffer_record_enable(struct ring_buffer *buffer); +void ring_buffer_record_off(struct ring_buffer *buffer); +void ring_buffer_record_on(struct ring_buffer *buffer); +int ring_buffer_record_is_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f5b7b5c1195b..cf8d11e91efd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -154,33 +154,10 @@ enum { static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; -#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) - -/** - * tracing_on - enable all tracing buffers - * - * This function enables all tracing buffers that may have been - * disabled with tracing_off. - */ -void tracing_on(void) -{ - set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); -} -EXPORT_SYMBOL_GPL(tracing_on); +/* Used for individual buffers (after the counter) */ +#define RB_BUFFER_OFF (1 << 20) -/** - * tracing_off - turn off all tracing buffers - * - * This function stops all tracing buffers from recording data. - * It does not disable any overhead the tracers themselves may - * be causing. This function simply causes all recording to - * the ring buffers to fail. - */ -void tracing_off(void) -{ - clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); -} -EXPORT_SYMBOL_GPL(tracing_off); +#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) /** * tracing_off_permanent - permanently disable ring buffers @@ -193,15 +170,6 @@ void tracing_off_permanent(void) set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags); } -/** - * tracing_is_on - show state of ring buffers enabled - */ -int tracing_is_on(void) -{ - return ring_buffer_flags == RB_BUFFERS_ON; -} -EXPORT_SYMBOL_GPL(tracing_is_on); - #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array)) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) @@ -2618,6 +2586,63 @@ void ring_buffer_record_enable(struct ring_buffer *buffer) } EXPORT_SYMBOL_GPL(ring_buffer_record_enable); +/** + * ring_buffer_record_off - stop all writes into the buffer + * @buffer: The ring buffer to stop writes to. + * + * This prevents all writes to the buffer. Any attempt to write + * to the buffer after this will fail and return NULL. + * + * This is different than ring_buffer_record_disable() as + * it works like an on/off switch, where as the disable() verison + * must be paired with a enable(). + */ +void ring_buffer_record_off(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd | RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_off); + +/** + * ring_buffer_record_on - restart writes into the buffer + * @buffer: The ring buffer to start writes to. + * + * This enables all writes to the buffer that was disabled by + * ring_buffer_record_off(). + * + * This is different than ring_buffer_record_enable() as + * it works like an on/off switch, where as the enable() verison + * must be paired with a disable(). + */ +void ring_buffer_record_on(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd & ~RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_on); + +/** + * ring_buffer_record_is_on - return true if the ring buffer can write + * @buffer: The ring buffer to see if write is enabled + * + * Returns true if the ring buffer is in a state that it accepts writes. + */ +int ring_buffer_record_is_on(struct ring_buffer *buffer) +{ + return !atomic_read(&buffer->record_disabled); +} + /** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. @@ -4039,68 +4064,6 @@ int ring_buffer_read_page(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_read_page); -#ifdef CONFIG_TRACING -static ssize_t -rb_simple_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long *p = filp->private_data; - char buf[64]; - int r; - - 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); -} - -static ssize_t -rb_simple_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long *p = filp->private_data; - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - if (val) - set_bit(RB_BUFFERS_ON_BIT, p); - else - clear_bit(RB_BUFFERS_ON_BIT, p); - - (*ppos)++; - - return cnt; -} - -static const struct file_operations rb_simple_fops = { - .open = tracing_open_generic, - .read = rb_simple_read, - .write = rb_simple_write, - .llseek = default_llseek, -}; - - -static __init int rb_init_debugfs(void) -{ - struct dentry *d_tracer; - - d_tracer = tracing_init_dentry(); - - trace_create_file("tracing_on", 0644, d_tracer, - &ring_buffer_flags, &rb_simple_fops); - - return 0; -} - -fs_initcall(rb_init_debugfs); -#endif - #ifdef CONFIG_HOTPLUG_CPU static int rb_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 10d5503f0d04..f3c13d63d064 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -351,6 +351,59 @@ static void wakeup_work_handler(struct work_struct *work) static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); +/** + * tracing_on - enable tracing buffers + * + * This function enables tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 0; +} +EXPORT_SYMBOL_GPL(tracing_on); + +/** + * tracing_off - turn off tracing buffers + * + * This function stops the tracing buffers from recording data. + * It does not disable any overhead the tracers themselves may + * be causing. This function simply causes all recording to + * the ring buffers to fail. + */ +void tracing_off(void) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 1; +} +EXPORT_SYMBOL_GPL(tracing_off); + +/** + * tracing_is_on - show state of ring buffers enabled + */ +int tracing_is_on(void) +{ + if (global_trace.buffer) + return ring_buffer_record_is_on(global_trace.buffer); + return !global_trace.buffer_disabled; +} +EXPORT_SYMBOL_GPL(tracing_is_on); + /** * trace_wake_up - wake up tasks waiting for trace input * @@ -4567,6 +4620,55 @@ static __init void create_trace_options_dir(void) create_trace_option_core_file(trace_options[i], i); } +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ring_buffer *buffer = filp->private_data; + char buf[64]; + int r; + + if (buffer) + r = ring_buffer_record_is_on(buffer); + else + r = 0; + + r = sprintf(buf, "%d\n", r); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +rb_simple_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ring_buffer *buffer = filp->private_data; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (buffer) { + if (val) + ring_buffer_record_on(buffer); + else + ring_buffer_record_off(buffer); + } + + (*ppos)++; + + return cnt; +} + +static const struct file_operations rb_simple_fops = { + .open = tracing_open_generic, + .read = rb_simple_read, + .write = rb_simple_write, + .llseek = default_llseek, +}; + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; @@ -4626,6 +4728,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("trace_clock", 0644, d_tracer, NULL, &trace_clock_fops); + trace_create_file("tracing_on", 0644, d_tracer, + global_trace.buffer, &rb_simple_fops); + #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); @@ -4863,6 +4968,8 @@ __init static int tracer_alloc_buffers(void) goto out_free_cpumask; } global_trace.entries = ring_buffer_size(global_trace.buffer); + if (global_trace.buffer_disabled) + tracing_off(); #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 54faec790bc1..ce887c0eca56 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -154,6 +154,7 @@ struct trace_array { struct ring_buffer *buffer; unsigned long entries; int cpu; + int buffer_disabled; cycle_t time_start; struct task_struct *waiter; struct trace_array_cpu *data[NR_CPUS]; -- cgit v1.3-14-g43fede From 8c9cf542b8a66c231747a550573d910daf17f0e9 Mon Sep 17 00:00:00 2001 From: Gerlando Falauto Date: Mon, 27 Feb 2012 09:08:21 +0100 Subject: tracing: Do not select FRAME_POINTER on PPC On PowerPC, FUNCTION_TRACER selects FRAME_POINTER, even though the architecture does not support it. This causes the following warning: warning: (LOCKDEP && FAULT_INJECTION_STACKTRACE_FILTER && LATENCYTOP && FUNCTION_TRACER && KMEMCHECK) selects FRAME_POINTER which has unmet direct dependencies (DEBUG_KERNEL && (CRIS || M68K || FRV || UML || AVR32 || SUPERH || BLACKFIN || MN10300) || ARCH_WANT_FRAME_POINTERS) So remove the warning by adding the extra condition "if !PPC" to FUNCTION_TRACER for FRAME_POINTER selection Link: http://lkml.kernel.org/r/1330330101-8618-1-git-send-email-gerlando.falauto@keymile.com Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Gerlando Falauto Signed-off-by: Steven Rostedt --- kernel/trace/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index cd3134510f3d..a1d2849f2473 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -141,7 +141,7 @@ if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE + select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER -- cgit v1.3-14-g43fede From b892e5c89787716b95a8e55d77d25a1c0748df10 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 1 Mar 2012 22:06:48 -0500 Subject: tracing: Keep NMI watchdog from triggering when dumping trace As ftrace_dump() (called by ftrace_dump_on_oops) disables interrupts as it dumps its output to the console, it can keep interrupts disabled for long periods of time. This is likely to trigger the NMI watchdog, and it can disrupt the output of critical data. Add a touch_nmi_watchdog() to each event that is written to the screen to keep the NMI watchdog from affecting the output. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f3c13d63d064..3a19c354edd6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include "trace.h" @@ -4903,6 +4904,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); } + touch_nmi_watchdog(); trace_printk_seq(&iter.seq); } -- cgit v1.3-14-g43fede From db6544e0075d192e5ad16eda8689c55fa9c6f8f4 Mon Sep 17 00:00:00 2001 From: Rajesh Bhagat Date: Fri, 17 Feb 2012 13:59:15 +0530 Subject: ftrace: Fix function_graph for archs that test ftrace_trace_function When CONFIG_DYNAMIC_FTRACE is not set, some archs (ARM) test the variable function_trace_function to determine if it should call the function tracer. If it is not set to ftrace_stub, then it will call the function and return, and not call the function graph tracer. But some of these archs (ARM) do not have the assembly code to test if function tracing is enabled or not (quick stop of tracing) and it calls the helper routine ftrace_test_stop_func() instead. If function tracer is enabled and then disabled, the variable ftrace_trace_function is still set to the helper routine ftrace_test_stop_func(), and not to ftrace_stub. This will prevent the function graph tracer from ever running. Output before patch /debug/tracing # echo function > current_tracer /debug/tracing # echo function_graph > current_tracer /debug/tracing # cat trace Output after patch /debug/tracing # echo function > current_tracer /debug/tracing # echo function_graph > current_tracer /debug/tracing # cat trace 0) ! 253.375 us | } /* irq_enter */ 0) | generic_handle_irq() { 0) | handle_fasteoi_irq() { 0) 9.208 us | _raw_spin_lock(); 0) | handle_irq_event() { 0) | handle_irq_event_percpu() { Signed-off-by: Rajesh Bhagat Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 867bd1dd2dd0..0fa92f677c92 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -249,7 +249,8 @@ static void update_ftrace_function(void) #else __ftrace_trace_function = func; #endif - ftrace_trace_function = ftrace_test_stop_func; + ftrace_trace_function = + (func == ftrace_stub) ? func : ftrace_test_stop_func; #endif } -- cgit v1.3-14-g43fede From fa73dc9400516945bcbae8d98c23393bcefe1440 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 28 Feb 2012 11:02:46 +0000 Subject: tracing: Fix build breakage without CONFIG_PERF_EVENTS Today's -next fails to build for me: CC kernel/trace/trace_export.o In file included from kernel/trace/trace_export.c:197: kernel/trace/trace_entries.h:58: error: 'perf_ftrace_event_register' undeclared here (not in a function) make[2]: *** [kernel/trace/trace_export.o] Error 1 make[1]: *** [kernel/trace] Error 2 make: *** [kernel] Error 2 because as of ced390 (ftrace, perf: Add support to use function tracepoint in perf) perf_trace_event_register() is declared in trace.h only if CONFIG_PERF_EVENTS is enabled but I don't have that set. Ensure that we always have a definition of perf_trace_event_register() by making the definition unconditional. Link: http://lkml.kernel.org/r/1330426967-17067-1-git-send-email-broonie@opensource.wolfsonmicro.com Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jiri Olsa Signed-off-by: Mark Brown Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ce887c0eca56..95059f091a24 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -836,13 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[]; filter) #include "trace_entries.h" -#ifdef CONFIG_PERF_EVENTS #ifdef CONFIG_FUNCTION_TRACER int perf_ftrace_event_register(struct ftrace_event_call *call, enum trace_reg type, void *data); #else #define perf_ftrace_event_register NULL #endif /* CONFIG_FUNCTION_TRACER */ -#endif /* CONFIG_PERF_EVENTS */ #endif /* _LINUX_KERNEL_TRACE_H */ -- cgit v1.3-14-g43fede From 38eff2892628fa5c4fc8962a17b7296f42833ebe Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 14 Mar 2012 21:51:10 -0400 Subject: constify path argument of trace_seq_path() Signed-off-by: Al Viro --- include/linux/trace_seq.h | 4 ++-- kernel/trace/trace_output.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 7dadc3df0c77..a32d86ec8bf2 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -44,7 +44,7 @@ extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len); extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len); extern void *trace_seq_reserve(struct trace_seq *s, size_t len); -extern int trace_seq_path(struct trace_seq *s, struct path *path); +extern int trace_seq_path(struct trace_seq *s, const struct path *path); #else /* CONFIG_TRACING */ static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...) @@ -88,7 +88,7 @@ static inline void *trace_seq_reserve(struct trace_seq *s, size_t len) { return NULL; } -static inline int trace_seq_path(struct trace_seq *s, struct path *path) +static inline int trace_seq_path(struct trace_seq *s, const struct path *path) { return 0; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 0d6ff3555942..690987198ad7 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -264,7 +264,7 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len) return ret; } -int trace_seq_path(struct trace_seq *s, struct path *path) +int trace_seq_path(struct trace_seq *s, const struct path *path) { unsigned char *p; -- cgit v1.3-14-g43fede From 01de982abf8c9e10fc3089e10585cd2cc914bdab Mon Sep 17 00:00:00 2001 From: Wolfgang Mauerer Date: Thu, 22 Mar 2012 11:18:20 +0100 Subject: tracing: Fix ftrace stack trace entries 8 hex characters tell only half the tale for 64 bit CPUs, so use the appropriate length. Link: http://lkml.kernel.org/r/1332411501-8059-2-git-send-email-wolfgang.mauerer@siemens.com Cc: stable@vger.kernel.org Signed-off-by: Wolfgang Mauerer Signed-off-by: Steven Rostedt --- kernel/trace/trace_entries.h | 16 ++++++++++++---- kernel/trace/trace_export.c | 2 +- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 93365907f219..205dcac89206 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -156,6 +156,12 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, #define FTRACE_STACK_ENTRIES 8 +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + FTRACE_ENTRY(kernel_stack, stack_entry, TRACE_STACK, @@ -165,8 +171,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry, __dynamic_array(unsigned long, caller ) ), - F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" - "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n", __entry->caller[0], __entry->caller[1], __entry->caller[2], __entry->caller[3], __entry->caller[4], __entry->caller[5], __entry->caller[6], __entry->caller[7]) @@ -181,8 +188,9 @@ FTRACE_ENTRY(user_stack, userstack_entry, __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) ), - F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" - "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n", + F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n" + "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n", __entry->caller[0], __entry->caller[1], __entry->caller[2], __entry->caller[3], __entry->caller[4], __entry->caller[5], __entry->caller[6], __entry->caller[7]) diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index bbeec31e0ae3..ad4000c71be0 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -150,7 +150,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #define __dynamic_array(type, item) #undef F_printk -#define F_printk(fmt, args...) #fmt ", " __stringify(args) +#define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ -- cgit v1.3-14-g43fede From 12b5da349a8b94c9dbc3430a6bc42eabd9eaf50b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 27 Mar 2012 10:43:28 -0400 Subject: tracing: Fix ent_size in trace output When reading the trace file, the records of each of the per_cpu buffers are examined to find the next event to print out. At the point of looking at the event, the size of the event is recorded. But if the first event is chosen, the other events in the other CPU buffers will reset the event size that is stored in the iterator descriptor, causing the event size passed to the output functions to be incorrect. In most cases this is not a problem, but for the case of stack traces, it is. With the change to the stack tracing to record a dynamic number of back traces, the output depends on the size of the entry instead of the fixed 8 back traces. When the entry size is not correct, the back traces would not be fully printed. Note, reading from the per-cpu trace files were not affected. Reported-by: Thomas Gleixner Tested-by: Thomas Gleixner Cc: stable@vger.kernel.org Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3a19c354edd6..ed7b5d1e12f4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1698,6 +1698,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, int cpu_file = iter->cpu_file; u64 next_ts = 0, ts; int next_cpu = -1; + int next_size = 0; int cpu; /* @@ -1729,9 +1730,12 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, next_cpu = cpu; next_ts = ts; next_lost = lost_events; + next_size = iter->ent_size; } } + iter->ent_size = next_size; + if (ent_cpu) *ent_cpu = next_cpu; -- cgit v1.3-14-g43fede