From e5e25cf47b0bdd1f7e9b8bb6368ee48e16de0c87 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 18 Sep 2009 00:54:43 +0200 Subject: tracing: Factorize the events profile accounting Factorize the events enabling accounting in a common tracing core helper. This reduces the size of the profile_enable() and profile_disable() callbacks for each trace events. Signed-off-by: Frederic Weisbecker Acked-by: Steven Rostedt Acked-by: Li Zefan Cc: Peter Zijlstra Cc: Jason Baron Cc: Masami Hiramatsu Cc: Ingo Molnar --- kernel/trace/trace_event_profile.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index 55a25c933d1..df4a74efd50 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -8,6 +8,14 @@ #include #include "trace.h" +static int ftrace_profile_enable_event(struct ftrace_event_call *event) +{ + if (atomic_inc_return(&event->profile_count)) + return 0; + + return event->profile_enable(); +} + int ftrace_profile_enable(int event_id) { struct ftrace_event_call *event; @@ -17,7 +25,7 @@ int ftrace_profile_enable(int event_id) list_for_each_entry(event, &ftrace_events, list) { if (event->id == event_id && event->profile_enable && try_module_get(event->mod)) { - ret = event->profile_enable(event); + ret = ftrace_profile_enable_event(event); break; } } @@ -26,6 +34,14 @@ int ftrace_profile_enable(int event_id) return ret; } +static void ftrace_profile_disable_event(struct ftrace_event_call *event) +{ + if (!atomic_add_negative(-1, &event->profile_count)) + return; + + event->profile_disable(); +} + void ftrace_profile_disable(int event_id) { struct ftrace_event_call *event; @@ -33,7 +49,7 @@ void ftrace_profile_disable(int event_id) mutex_lock(&event_mutex); list_for_each_entry(event, &ftrace_events, list) { if (event->id == event_id) { - event->profile_disable(event); + ftrace_profile_disable_event(event); module_put(event->mod); break; } -- cgit v1.2.3 From 20ab4425a77a1f34028cc6ce57053c22c184ba5f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 18 Sep 2009 06:10:28 +0200 Subject: tracing: Allocate the ftrace event profile buffer dynamically Currently the trace event profile buffer is allocated in the stack. But this may be too much for the stack, as the events can have large statically defined field size and can also grow with dynamic arrays. Allocate two per cpu buffer for all profiled events. The first cpu buffer is used to host every non-nmi context traces. It is protected by disabling the interrupts while writing and committing the trace. The second buffer is reserved for nmi. So that there is no race between them and the first buffer. The whole write/commit section is rcu protected because we release these buffers while deactivating the last profiling trace event. v2: Move the buffers from trace_event to be global, as pointed by Steven Rostedt. v3: Fix the syscall events to handle the profiling buffer races by disabling interrupts, now that the buffers are globals. Suggested-by: Steven Rostedt Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Li Zefan Cc: Jason Baron Cc: Masami Hiramatsu Cc: Ingo Molnar --- kernel/trace/trace_event_profile.c | 61 +++++++++++++++++++++++- kernel/trace/trace_syscalls.c | 97 ++++++++++++++++++++++++++++++-------- 2 files changed, 138 insertions(+), 20 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index df4a74efd50..3aaa77c3309 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -8,12 +8,52 @@ #include #include "trace.h" +/* + * We can't use a size but a type in alloc_percpu() + * So let's create a dummy type that matches the desired size + */ +typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t; + +char *trace_profile_buf; +char *trace_profile_buf_nmi; + +/* Count the events in use (per event id, not per instance) */ +static int total_profile_count; + static int ftrace_profile_enable_event(struct ftrace_event_call *event) { + char *buf; + int ret = -ENOMEM; + if (atomic_inc_return(&event->profile_count)) return 0; - return event->profile_enable(); + if (!total_profile_count++) { + buf = (char *)alloc_percpu(profile_buf_t); + if (!buf) + goto fail_buf; + + rcu_assign_pointer(trace_profile_buf, buf); + + buf = (char *)alloc_percpu(profile_buf_t); + if (!buf) + goto fail_buf_nmi; + + rcu_assign_pointer(trace_profile_buf_nmi, buf); + } + + ret = event->profile_enable(); + if (!ret) + return 0; + + kfree(trace_profile_buf_nmi); +fail_buf_nmi: + kfree(trace_profile_buf); +fail_buf: + total_profile_count--; + atomic_dec(&event->profile_count); + + return ret; } int ftrace_profile_enable(int event_id) @@ -36,10 +76,29 @@ int ftrace_profile_enable(int event_id) static void ftrace_profile_disable_event(struct ftrace_event_call *event) { + char *buf, *nmi_buf; + if (!atomic_add_negative(-1, &event->profile_count)) return; event->profile_disable(); + + if (!--total_profile_count) { + buf = trace_profile_buf; + rcu_assign_pointer(trace_profile_buf, NULL); + + nmi_buf = trace_profile_buf_nmi; + rcu_assign_pointer(trace_profile_buf_nmi, NULL); + + /* + * Ensure every events in profiling have finished before + * releasing the buffers + */ + synchronize_sched(); + + free_percpu(buf); + free_percpu(nmi_buf); + } } void ftrace_profile_disable(int event_id) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 8712ce3c6a0..7a3550cf259 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -384,10 +384,13 @@ static int sys_prof_refcount_exit; static void prof_syscall_enter(struct pt_regs *regs, long id) { - struct syscall_trace_enter *rec; struct syscall_metadata *sys_data; + struct syscall_trace_enter *rec; + unsigned long flags; + char *raw_data; int syscall_nr; int size; + int cpu; syscall_nr = syscall_get_nr(current, regs); if (!test_bit(syscall_nr, enabled_prof_enter_syscalls)) @@ -402,20 +405,38 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) size = ALIGN(size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - do { - char raw_data[size]; + if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, + "profile buffer not large enough")) + return; + + /* Protect the per cpu buffer, begin the rcu read side */ + local_irq_save(flags); - /* zero the dead bytes from align to not leak stack to user */ - *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; + cpu = smp_processor_id(); + + if (in_nmi()) + raw_data = rcu_dereference(trace_profile_buf_nmi); + else + raw_data = rcu_dereference(trace_profile_buf); + + if (!raw_data) + goto end; - rec = (struct syscall_trace_enter *) raw_data; - tracing_generic_entry_update(&rec->ent, 0, 0); - rec->ent.type = sys_data->enter_id; - rec->nr = syscall_nr; - syscall_get_arguments(current, regs, 0, sys_data->nb_args, - (unsigned long *)&rec->args); - perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size); - } while(0); + raw_data = per_cpu_ptr(raw_data, cpu); + + /* zero the dead bytes from align to not leak stack to user */ + *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; + + rec = (struct syscall_trace_enter *) raw_data; + tracing_generic_entry_update(&rec->ent, 0, 0); + rec->ent.type = sys_data->enter_id; + rec->nr = syscall_nr; + syscall_get_arguments(current, regs, 0, sys_data->nb_args, + (unsigned long *)&rec->args); + perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size); + +end: + local_irq_restore(flags); } int reg_prof_syscall_enter(char *name) @@ -460,8 +481,12 @@ void unreg_prof_syscall_enter(char *name) static void prof_syscall_exit(struct pt_regs *regs, long ret) { struct syscall_metadata *sys_data; - struct syscall_trace_exit rec; + struct syscall_trace_exit *rec; + unsigned long flags; int syscall_nr; + char *raw_data; + int size; + int cpu; syscall_nr = syscall_get_nr(current, regs); if (!test_bit(syscall_nr, enabled_prof_exit_syscalls)) @@ -471,12 +496,46 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) if (!sys_data) return; - tracing_generic_entry_update(&rec.ent, 0, 0); - rec.ent.type = sys_data->exit_id; - rec.nr = syscall_nr; - rec.ret = syscall_get_return_value(current, regs); + /* We can probably do that at build time */ + size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64)); + size -= sizeof(u32); - perf_tpcounter_event(sys_data->exit_id, 0, 1, &rec, sizeof(rec)); + /* + * Impossible, but be paranoid with the future + * How to put this check outside runtime? + */ + if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE, + "exit event has grown above profile buffer size")) + return; + + /* Protect the per cpu buffer, begin the rcu read side */ + local_irq_save(flags); + cpu = smp_processor_id(); + + if (in_nmi()) + raw_data = rcu_dereference(trace_profile_buf_nmi); + else + raw_data = rcu_dereference(trace_profile_buf); + + if (!raw_data) + goto end; + + raw_data = per_cpu_ptr(raw_data, cpu); + + /* zero the dead bytes from align to not leak stack to user */ + *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL; + + rec = (struct syscall_trace_exit *)raw_data; + + tracing_generic_entry_update(&rec->ent, 0, 0); + rec->ent.type = sys_data->exit_id; + rec->nr = syscall_nr; + rec->ret = syscall_get_return_value(current, regs); + + perf_tpcounter_event(sys_data->exit_id, 0, 1, rec, size); + +end: + local_irq_restore(flags); } int reg_prof_syscall_exit(char *name) -- cgit v1.2.3 From fc5377668c3d808e1d53c4aee152c836f55c3490 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Sep 2009 19:35:28 +0200 Subject: tracing: Remove markers Now that the last users of markers have migrated to the event tracer we can kill off the (now orphan) support code. Signed-off-by: Christoph Hellwig Acked-by: Mathieu Desnoyers Cc: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <20090917173527.GA1699@lst.de> Signed-off-by: Ingo Molnar --- kernel/trace/trace_printk.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 687699d365a..2547d8813cf 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 6161352142d5fed4cd753b32e5ccde66e705b14e Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 17 Sep 2009 16:11:28 +0200 Subject: tracing, perf: Convert the power tracer into an event tracer This patch converts the existing power tracer into an event tracer, so that power events (C states and frequency changes) can be tracked via "perf". This also removes the perl script that was used to demo the tracer; its functionality is being replaced entirely with timechart. Signed-off-by: Arjan van de Ven Acked-by: Peter Zijlstra Cc: Paul Mackerras Cc: Frederic Weisbecker LKML-Reference: <20090912130542.6d314860@infradead.org> Signed-off-by: Ingo Molnar --- kernel/trace/Makefile | 2 +- kernel/trace/power-traces.c | 20 ++++ kernel/trace/trace.h | 3 - kernel/trace/trace_entries.h | 17 ---- kernel/trace/trace_power.c | 218 ------------------------------------------- 5 files changed, 21 insertions(+), 239 deletions(-) create mode 100644 kernel/trace/power-traces.c delete mode 100644 kernel/trace/trace_power.c (limited to 'kernel/trace') diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 844164dca90..26f03ac07c2 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -42,7 +42,6 @@ obj-$(CONFIG_BOOT_TRACER) += trace_boot.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o -obj-$(CONFIG_POWER_TRACER) += trace_power.o obj-$(CONFIG_KMEMTRACE) += kmemtrace.o obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o @@ -54,5 +53,6 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o +obj-$(CONFIG_EVENT_TRACING) += power-traces.o libftrace-y := ftrace.o diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c new file mode 100644 index 00000000000..e06c6e3d56a --- /dev/null +++ b/kernel/trace/power-traces.c @@ -0,0 +1,20 @@ +/* + * Power trace points + * + * Copyright (C) 2009 Arjan van de Ven + */ + +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL_GPL(power_start); +EXPORT_TRACEPOINT_SYMBOL_GPL(power_end); +EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency); + diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 86bcff94791..405cb850b75 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #include @@ -37,7 +36,6 @@ enum trace_type { TRACE_HW_BRANCHES, TRACE_KMEM_ALLOC, TRACE_KMEM_FREE, - TRACE_POWER, TRACE_BLK, __TRACE_LAST_TYPE, @@ -207,7 +205,6 @@ extern void __ftrace_bad_type(void); IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ TRACE_GRAPH_RET); \ IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\ - IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \ IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \ TRACE_KMEM_ALLOC); \ IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index a431748ddd6..ead3d724599 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -330,23 +330,6 @@ FTRACE_ENTRY(hw_branch, hw_branch_entry, F_printk("from: %llx to: %llx", __entry->from, __entry->to) ); -FTRACE_ENTRY(power, trace_power, - - TRACE_POWER, - - F_STRUCT( - __field_struct( struct power_trace, state_data ) - __field_desc( s64, state_data, stamp ) - __field_desc( s64, state_data, end ) - __field_desc( int, state_data, type ) - __field_desc( int, state_data, state ) - ), - - F_printk("%llx->%llx type:%u state:%u", - __entry->stamp, __entry->end, - __entry->type, __entry->state) -); - FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry, TRACE_KMEM_ALLOC, diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c deleted file mode 100644 index fe1a00f1445..00000000000 --- a/kernel/trace/trace_power.c +++ /dev/null @@ -1,218 +0,0 @@ -/* - * ring buffer based C-state tracer - * - * Arjan van de Ven - * Copyright (C) 2008 Intel Corporation - * - * Much is borrowed from trace_boot.c which is - * Copyright (C) 2008 Frederic Weisbecker - * - */ - -#include -#include -#include -#include -#include - -#include "trace.h" -#include "trace_output.h" - -static struct trace_array *power_trace; -static int __read_mostly trace_power_enabled; - -static void probe_power_start(struct power_trace *it, unsigned int type, - unsigned int level) -{ - if (!trace_power_enabled) - return; - - memset(it, 0, sizeof(struct power_trace)); - it->state = level; - it->type = type; - it->stamp = ktime_get(); -} - - -static void probe_power_end(struct power_trace *it) -{ - struct ftrace_event_call *call = &event_power; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct trace_power *entry; - struct trace_array_cpu *data; - struct trace_array *tr = power_trace; - - if (!trace_power_enabled) - return; - - buffer = tr->buffer; - - preempt_disable(); - it->end = ktime_get(); - data = tr->data[smp_processor_id()]; - - event = trace_buffer_lock_reserve(buffer, TRACE_POWER, - sizeof(*entry), 0, 0); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->state_data = *it; - if (!filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - out: - preempt_enable(); -} - -static void probe_power_mark(struct power_trace *it, unsigned int type, - unsigned int level) -{ - struct ftrace_event_call *call = &event_power; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct trace_power *entry; - struct trace_array_cpu *data; - struct trace_array *tr = power_trace; - - if (!trace_power_enabled) - return; - - buffer = tr->buffer; - - memset(it, 0, sizeof(struct power_trace)); - it->state = level; - it->type = type; - it->stamp = ktime_get(); - preempt_disable(); - it->end = it->stamp; - data = tr->data[smp_processor_id()]; - - event = trace_buffer_lock_reserve(buffer, TRACE_POWER, - sizeof(*entry), 0, 0); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->state_data = *it; - if (!filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - out: - preempt_enable(); -} - -static int tracing_power_register(void) -{ - int ret; - - ret = register_trace_power_start(probe_power_start); - if (ret) { - pr_info("power trace: Couldn't activate tracepoint" - " probe to trace_power_start\n"); - return ret; - } - ret = register_trace_power_end(probe_power_end); - if (ret) { - pr_info("power trace: Couldn't activate tracepoint" - " probe to trace_power_end\n"); - goto fail_start; - } - ret = register_trace_power_mark(probe_power_mark); - if (ret) { - pr_info("power trace: Couldn't activate tracepoint" - " probe to trace_power_mark\n"); - goto fail_end; - } - return ret; -fail_end: - unregister_trace_power_end(probe_power_end); -fail_start: - unregister_trace_power_start(probe_power_start); - return ret; -} - -static void start_power_trace(struct trace_array *tr) -{ - trace_power_enabled = 1; -} - -static void stop_power_trace(struct trace_array *tr) -{ - trace_power_enabled = 0; -} - -static void power_trace_reset(struct trace_array *tr) -{ - trace_power_enabled = 0; - unregister_trace_power_start(probe_power_start); - unregister_trace_power_end(probe_power_end); - unregister_trace_power_mark(probe_power_mark); -} - - -static int power_trace_init(struct trace_array *tr) -{ - power_trace = tr; - - trace_power_enabled = 1; - tracing_power_register(); - - tracing_reset_online_cpus(tr); - return 0; -} - -static enum print_line_t power_print_line(struct trace_iterator *iter) -{ - int ret = 0; - struct trace_entry *entry = iter->ent; - struct trace_power *field ; - struct power_trace *it; - struct trace_seq *s = &iter->seq; - struct timespec stamp; - struct timespec duration; - - trace_assign_type(field, entry); - it = &field->state_data; - stamp = ktime_to_timespec(it->stamp); - duration = ktime_to_timespec(ktime_sub(it->end, it->stamp)); - - if (entry->type == TRACE_POWER) { - if (it->type == POWER_CSTATE) - ret = trace_seq_printf(s, "[%5ld.%09ld] CSTATE: Going to C%i on cpu %i for %ld.%09ld\n", - stamp.tv_sec, - stamp.tv_nsec, - it->state, iter->cpu, - duration.tv_sec, - duration.tv_nsec); - if (it->type == POWER_PSTATE) - ret = trace_seq_printf(s, "[%5ld.%09ld] PSTATE: Going to P%i on cpu %i\n", - stamp.tv_sec, - stamp.tv_nsec, - it->state, iter->cpu); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - return TRACE_TYPE_HANDLED; - } - return TRACE_TYPE_UNHANDLED; -} - -static void power_print_header(struct seq_file *s) -{ - seq_puts(s, "# TIMESTAMP STATE EVENT\n"); - seq_puts(s, "# | | |\n"); -} - -static struct tracer power_tracer __read_mostly = -{ - .name = "power", - .init = power_trace_init, - .start = start_power_trace, - .stop = stop_power_trace, - .reset = power_trace_reset, - .print_line = power_print_line, - .print_header = power_print_header, -}; - -static int init_power_trace(void) -{ - return register_tracer(&power_tracer); -} -device_initcall(init_power_trace); -- cgit v1.2.3 From a4ec5e0c2681b8cf99ddabf118705847f7460f19 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 18 Sep 2009 14:06:28 +0800 Subject: function-graph: use ftrace_graph_funcs directly No need to store ftrace_graph_funcs in file->private. Acked-by: Frederic Weisbecker Signed-off-by: Li Zefan LKML-Reference: <4AB32364.7020602@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 23 ++++------------------- 1 file changed, 4 insertions(+), 19 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index cc615f84751..c71e91bf737 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2414,11 +2414,9 @@ unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly; static void * __g_next(struct seq_file *m, loff_t *pos) { - unsigned long *array = m->private; - if (*pos >= ftrace_graph_count) return NULL; - return &array[*pos]; + return &ftrace_graph_funcs[*pos]; } static void * @@ -2482,16 +2480,10 @@ ftrace_graph_open(struct inode *inode, struct file *file) ftrace_graph_count = 0; memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs)); } + mutex_unlock(&graph_lock); - if (file->f_mode & FMODE_READ) { + if (file->f_mode & FMODE_READ) ret = seq_open(file, &ftrace_graph_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = ftrace_graph_funcs; - } - } else - file->private_data = ftrace_graph_funcs; - mutex_unlock(&graph_lock); return ret; } @@ -2560,7 +2552,6 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; - unsigned long *array; size_t read = 0; ssize_t ret; @@ -2574,12 +2565,6 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, goto out; } - if (file->f_mode & FMODE_READ) { - struct seq_file *m = file->private_data; - array = m->private; - } else - array = file->private_data; - if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) { ret = -ENOMEM; goto out; @@ -2591,7 +2576,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, parser.buffer[parser.idx] = 0; /* we allow only one expression at a time */ - ret = ftrace_set_func(array, &ftrace_graph_count, + ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, parser.buffer); if (ret) goto out; -- cgit v1.2.3 From ee6c2c1bd15e60a442d1861b66285f112ce4f25c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 18 Sep 2009 14:06:47 +0800 Subject: tracing: remove max_tracer_type_len Limit the length of a tracer's name within 100 chars, and then we don't have to play with max_tracer_type_len. Acked-by: Frederic Weisbecker Signed-off-by: Li Zefan LKML-Reference: <4AB32377.9020601@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 49 ++++++++++++++++--------------------------------- 1 file changed, 16 insertions(+), 33 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index fd52a19dd17..861308072d2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -125,13 +125,13 @@ int ftrace_dump_on_oops; static int tracing_set_tracer(const char *buf); -#define BOOTUP_TRACER_SIZE 100 -static char bootup_tracer_buf[BOOTUP_TRACER_SIZE] __initdata; +#define MAX_TRACER_SIZE 100 +static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; static int __init set_ftrace(char *str) { - strncpy(bootup_tracer_buf, str, BOOTUP_TRACER_SIZE); + strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ ring_buffer_expanded = 1; @@ -241,13 +241,6 @@ static struct tracer *trace_types __read_mostly; /* current_trace points to the tracer that is currently active */ static struct tracer *current_trace __read_mostly; -/* - * max_tracer_type_len is used to simplify the allocating of - * buffers to read userspace tracer names. We keep track of - * the longest tracer name registered. - */ -static int max_tracer_type_len; - /* * trace_types_lock is used to protect the trace_types list. * This lock is also used to keep user access serialized. @@ -619,7 +612,6 @@ __releases(kernel_lock) __acquires(kernel_lock) { struct tracer *t; - int len; int ret = 0; if (!type->name) { @@ -627,6 +619,11 @@ __acquires(kernel_lock) return -1; } + if (strlen(type->name) > MAX_TRACER_SIZE) { + pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE); + return -1; + } + /* * When this gets called we hold the BKL which means that * preemption is disabled. Various trace selftests however @@ -641,7 +638,7 @@ __acquires(kernel_lock) for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ - pr_info("Trace %s already registered\n", + pr_info("Tracer %s already registered\n", type->name); ret = -1; goto out; @@ -692,9 +689,6 @@ __acquires(kernel_lock) type->next = trace_types; trace_types = type; - len = strlen(type->name); - if (len > max_tracer_type_len) - max_tracer_type_len = len; out: tracing_selftest_running = false; @@ -703,7 +697,7 @@ __acquires(kernel_lock) if (ret || !default_bootup_tracer) goto out_unlock; - if (strncmp(default_bootup_tracer, type->name, BOOTUP_TRACER_SIZE)) + if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE)) goto out_unlock; printk(KERN_INFO "Starting tracer '%s'\n", type->name); @@ -725,14 +719,13 @@ __acquires(kernel_lock) void unregister_tracer(struct tracer *type) { struct tracer **t; - int len; mutex_lock(&trace_types_lock); for (t = &trace_types; *t; t = &(*t)->next) { if (*t == type) goto found; } - pr_info("Trace %s not registered\n", type->name); + pr_info("Tracer %s not registered\n", type->name); goto out; found: @@ -745,17 +738,7 @@ void unregister_tracer(struct tracer *type) current_trace->stop(&global_trace); current_trace = &nop_trace; } - - if (strlen(type->name) != max_tracer_type_len) - goto out; - - max_tracer_type_len = 0; - for (t = &trace_types; *t; t = &(*t)->next) { - len = strlen((*t)->name); - if (len > max_tracer_type_len) - max_tracer_type_len = len; - } - out: +out: mutex_unlock(&trace_types_lock); } @@ -2604,7 +2587,7 @@ static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - char buf[max_tracer_type_len+2]; + char buf[MAX_TRACER_SIZE+2]; int r; mutex_lock(&trace_types_lock); @@ -2754,15 +2737,15 @@ static ssize_t tracing_set_trace_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - char buf[max_tracer_type_len+1]; + char buf[MAX_TRACER_SIZE+1]; int i; size_t ret; int err; ret = cnt; - if (cnt > max_tracer_type_len) - cnt = max_tracer_type_len; + if (cnt > MAX_TRACER_SIZE) + cnt = MAX_TRACER_SIZE; if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; -- cgit v1.2.3 From 30bd39cd6244ffe3258c9203405286ef77b1c4eb Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 18 Sep 2009 14:07:05 +0800 Subject: tracing/events: use list_for_entry_continue Simplify s_next() and t_next(). Acked-by: Frederic Weisbecker Signed-off-by: Li Zefan LKML-Reference: <4AB32389.1030005@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 49 ++++++++++++++------------------------------- 1 file changed, 15 insertions(+), 34 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 56c260b83a9..6f03c8a1105 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -271,42 +271,32 @@ ftrace_event_write(struct file *file, const char __user *ubuf, static void * t_next(struct seq_file *m, void *v, loff_t *pos) { - struct list_head *list = m->private; - struct ftrace_event_call *call; + struct ftrace_event_call *call = v; (*pos)++; - for (;;) { - if (list == &ftrace_events) - return NULL; - - call = list_entry(list, struct ftrace_event_call, list); - + list_for_each_entry_continue(call, &ftrace_events, list) { /* * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ if (call->regfunc) - break; - - list = list->next; + return call; } - m->private = list->next; - - return call; + return NULL; } static void *t_start(struct seq_file *m, loff_t *pos) { - struct ftrace_event_call *call = NULL; + struct ftrace_event_call *call; loff_t l; mutex_lock(&event_mutex); - m->private = ftrace_events.next; + call = list_entry(&ftrace_events, struct ftrace_event_call, list); for (l = 0; l <= *pos; ) { - call = t_next(m, NULL, &l); + call = t_next(m, call, &l); if (!call) break; } @@ -316,37 +306,28 @@ static void *t_start(struct seq_file *m, loff_t *pos) static void * s_next(struct seq_file *m, void *v, loff_t *pos) { - struct list_head *list = m->private; - struct ftrace_event_call *call; + struct ftrace_event_call *call = v; (*pos)++; - retry: - if (list == &ftrace_events) - return NULL; - - call = list_entry(list, struct ftrace_event_call, list); - - if (!call->enabled) { - list = list->next; - goto retry; + list_for_each_entry_continue(call, &ftrace_events, list) { + if (call->enabled) + return call; } - m->private = list->next; - - return call; + return NULL; } static void *s_start(struct seq_file *m, loff_t *pos) { - struct ftrace_event_call *call = NULL; + struct ftrace_event_call *call; loff_t l; mutex_lock(&event_mutex); - m->private = ftrace_events.next; + call = list_entry(&ftrace_events, struct ftrace_event_call, list); for (l = 0; l <= *pos; ) { - call = s_next(m, NULL, &l); + call = s_next(m, call, &l); if (!call) break; } -- cgit v1.2.3 From a0f320f48799f67329fcb1b26ff0451c304e1dde Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Sun, 20 Sep 2009 16:31:16 +0530 Subject: includecheck fix: kernel/trace, ring_buffer.c fix the following 'make includecheck' warning: kernel/trace/ring_buffer.c: trace.h is included more than once. Signed-off-by: Jaswinder Singh Rajput Cc: Steven Rostedt Cc: Ingo Molnar Cc: Sam Ravnborg LKML-Reference: <1247068617.4382.107.camel@ht.satnam> --- kernel/trace/ring_buffer.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6eef38923b0..d4ff0197054 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -201,8 +201,6 @@ int tracing_is_on(void) } EXPORT_SYMBOL_GPL(tracing_is_on); -#include "trace.h" - #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) -- cgit v1.2.3 From 05bafda856092de0705de239c846777bddb94974 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 20 Sep 2009 12:34:38 +0200 Subject: tracing: Export trace_profile_buf symbols ERROR: "trace_profile_buf_nmi" [fs/jbd2/jbd2.ko] undefined! ERROR: "trace_profile_buf" [fs/jbd2/jbd2.ko] undefined! ERROR: "trace_profile_buf_nmi" [fs/ext4/ext4.ko] undefined! ERROR: "trace_profile_buf" [fs/ext4/ext4.ko] undefined! ERROR: "trace_profile_buf_nmi" [arch/x86/kvm/kvm.ko] undefined! ERROR: "trace_profile_buf" [arch/x86/kvm/kvm.ko] undefined! Signed-off-by: Peter Zijlstra Acked-by: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <1253442878.7542.3.camel@laptop> [ fixed whitespace noise and checkpatch complaint ] Signed-off-by: Ingo Molnar --- kernel/trace/trace_event_profile.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index 3aaa77c3309..dd44b876886 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -15,7 +15,10 @@ typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t; char *trace_profile_buf; -char *trace_profile_buf_nmi; +EXPORT_SYMBOL_GPL(trace_profile_buf); + +char *trace_profile_buf_nmi; +EXPORT_SYMBOL_GPL(trace_profile_buf_nmi); /* Count the events in use (per event id, not per instance) */ static int total_profile_count; -- cgit v1.2.3 From 89f19f04dc72363d912fd007a399cb10310eff6e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 19 Sep 2009 11:55:44 -0700 Subject: sched: Fix raciness in runqueue_is_locked() runqueue_is_locked() is unavoidably racy due to a poor interface design. It does cpu = get_cpu() ret = some_perpcu_thing(cpu); put_cpu(cpu); return ret; Its return value is unreliable. Fix. Signed-off-by: Andrew Morton Acked-by: Steven Rostedt Cc: Peter Zijlstra LKML-Reference: <200909191855.n8JItiko022148@imap1.linux-foundation.org> Signed-off-by: Ingo Molnar --- kernel/trace/trace.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index fd52a19dd17..420232a1fbb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -275,12 +275,18 @@ static DEFINE_SPINLOCK(tracing_start_lock); */ void trace_wake_up(void) { + int cpu; + + if (trace_flags & TRACE_ITER_BLOCK) + return; /* * The runqueue_is_locked() can fail, but this is the best we * have for now: */ - if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked()) + cpu = get_cpu(); + if (!runqueue_is_locked(cpu)) wake_up(&trace_wait); + put_cpu(); } static int __init set_buf_size(char *str) -- cgit v1.2.3 From cdd6c482c9ff9c55475ee7392ec8f672eddb7be6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 21 Sep 2009 12:02:48 +0200 Subject: perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian Acked-by: Peter Zijlstra Acked-by: Paul Mackerras Reviewed-by: Arjan van de Ven Cc: Mike Galbraith Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Benjamin Herrenschmidt Cc: David Howells Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/trace/trace_syscalls.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 8712ce3c6a0..233f3483ac8 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -2,7 +2,7 @@ #include #include #include -#include +#include #include #include "trace_output.h" @@ -414,7 +414,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size); + perf_tp_event(sys_data->enter_id, 0, 1, rec, size); } while(0); } @@ -476,7 +476,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret) rec.nr = syscall_nr; rec.ret = syscall_get_return_value(current, regs); - perf_tpcounter_event(sys_data->exit_id, 0, 1, &rec, sizeof(rec)); + perf_tp_event(sys_data->exit_id, 0, 1, &rec, sizeof(rec)); } int reg_prof_syscall_exit(char *name) -- cgit v1.2.3 From 2944fcbe03d65a704f07e43efe14adb0d226fd09 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-Koenig Date: Wed, 5 Aug 2009 22:06:42 +0200 Subject: trivial: Fix duplicated word "options" in comment this was introduced in 5e0a093 (tracing: fix config options to not show when automatically selected) Signed-off-by: Uwe Kleine-Koenig Cc: Steven Rostedt Cc: trivial@kernel.org Signed-off-by: Jiri Kosina --- 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 e7163460440..b416512ad17 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -83,7 +83,7 @@ config RING_BUFFER_ALLOW_SWAP # This allows those options to appear when no other tracer is selected. But the # options do not appear when something else selects it. We need the two options # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the -# hidding of the automatic options options. +# hidding of the automatic options. config TRACING bool -- cgit v1.2.3 From a419aef8b858a2bdb98df60336063d28df4b272f Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 18 Aug 2009 11:18:35 -0700 Subject: trivial: remove unnecessary semicolons Signed-off-by: Joe Perches Signed-off-by: Jiri Kosina --- kernel/trace/trace_hw_branches.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c index ca7d7c4d0c2..23b63859130 100644 --- a/kernel/trace/trace_hw_branches.c +++ b/kernel/trace/trace_hw_branches.c @@ -155,7 +155,7 @@ static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) seq_print_ip_sym(seq, it->from, symflags) && trace_seq_printf(seq, "\n")) return TRACE_TYPE_HANDLED; - return TRACE_TYPE_PARTIAL_LINE;; + return TRACE_TYPE_PARTIAL_LINE; } return TRACE_TYPE_UNHANDLED; } -- cgit v1.2.3 From 3c235a337e205da0f614e456be72881483dcde6e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 22 Sep 2009 13:51:54 +0800 Subject: tracing: Fix off-by-one in trace_get_user() Leave the last slot for the tailing '\0'. Signed-off-by: Li Zefan Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Steven Rostedt LKML-Reference: <4AB865FA.5080801@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a35925d222b..ae17453dc0f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -415,7 +415,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, /* read the non-space input */ while (cnt && !isspace(ch)) { - if (parser->idx < parser->size) + if (parser->idx < parser->size - 1) parser->buffer[parser->idx++] = ch; else { ret = -EINVAL; -- cgit v1.2.3 From 4ba7978e98a3ff92cebfb0f31a02c309e3ffa1fe Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 22 Sep 2009 13:52:20 +0800 Subject: tracing: Check the return value of trace_get_user() Return immediately if trace_get_user() returned failure. Signed-off-by: Li Zefan Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Steven Rostedt LKML-Reference: <4AB86614.7020803@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 9 ++++----- kernel/trace/trace_events.c | 7 +++---- 2 files changed, 7 insertions(+), 9 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c71e91bf737..a8fe4782eba 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2202,7 +2202,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, struct trace_parser *parser; ssize_t ret, read; - if (!cnt || cnt < 0) + if (!cnt) return 0; mutex_lock(&ftrace_regex_lock); @@ -2216,7 +2216,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, parser = &iter->parser; read = trace_get_user(parser, ubuf, cnt, ppos); - if (trace_parser_loaded(parser) && + if (read >= 0 && trace_parser_loaded(parser) && !trace_parser_cont(parser)) { ret = ftrace_process_regex(parser->buffer, parser->idx, enable); @@ -2552,8 +2552,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; - size_t read = 0; - ssize_t ret; + ssize_t read, ret; if (!cnt || cnt < 0) return 0; @@ -2572,7 +2571,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, read = trace_get_user(&parser, ubuf, cnt, ppos); - if (trace_parser_loaded((&parser))) { + if (read >= 0 && trace_parser_loaded((&parser))) { parser.buffer[parser.idx] = 0; /* we allow only one expression at a time */ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6f03c8a1105..d128f65778e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -232,10 +232,9 @@ ftrace_event_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; - size_t read = 0; - ssize_t ret; + ssize_t read, ret; - if (!cnt || cnt < 0) + if (!cnt) return 0; ret = tracing_update_buffers(); @@ -247,7 +246,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf, read = trace_get_user(&parser, ubuf, cnt, ppos); - if (trace_parser_loaded((&parser))) { + if (read >= 0 && trace_parser_loaded((&parser))) { int set = 1; if (*parser.buffer == '!') -- cgit v1.2.3 From 1eb90f138b3fb4cc15f3acec94aa788e846269f7 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 22 Sep 2009 13:52:57 +0800 Subject: tracing: Fix failure path in ftrace_graph_write() Don't call trace_parser_put() on uninitialized trace_parser. Signed-off-by: Li Zefan Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Steven Rostedt LKML-Reference: <4AB86639.3000003@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a8fe4782eba..5c5cb9be8e8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2561,12 +2561,12 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) { ret = -EBUSY; - goto out; + goto out_unlock; } if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) { ret = -ENOMEM; - goto out; + goto out_unlock; } read = trace_get_user(&parser, ubuf, cnt, ppos); @@ -2578,12 +2578,14 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, parser.buffer); if (ret) - goto out; + goto out_free; } ret = read; - out: + +out_free: trace_parser_put(&parser); +out_unlock: mutex_unlock(&graph_lock); return ret; -- cgit v1.2.3 From 79fe249c8368be35c9ca05982e80c68e959505e1 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 22 Sep 2009 13:54:28 +0800 Subject: tracing: Fix failure path in ftrace_regex_open() Don't forget to free trace_parser if seq_open() returned failure. Signed-off-by: Li Zefan Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Steven Rostedt LKML-Reference: <4AB86694.4040803@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5c5cb9be8e8..e70af98bb99 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1621,8 +1621,10 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (!ret) { struct seq_file *m = file->private_data; m->private = iter; - } else + } else { + trace_parser_put(&iter->parser); kfree(iter); + } } else file->private_data = iter; mutex_unlock(&ftrace_regex_lock); -- cgit v1.2.3 From 88e9d34c727883d7d6f02cf1475b3ec98b8480c7 Mon Sep 17 00:00:00 2001 From: James Morris Date: Tue, 22 Sep 2009 16:43:43 -0700 Subject: seq_file: constify seq_operations Make all seq_operations structs const, to help mitigate against revectoring user-triggerable function pointers. This is derived from the grsecurity patch, although generated from scratch because it's simpler than extracting the changes from there. Signed-off-by: James Morris Acked-by: Serge Hallyn Acked-by: Casey Schaufler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/ftrace.c | 4 ++-- kernel/trace/trace.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c71e91bf737..23df7771c93 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1520,7 +1520,7 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations show_ftrace_seq_ops = { +static const struct seq_operations show_ftrace_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, @@ -2459,7 +2459,7 @@ static int g_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations ftrace_graph_seq_ops = { +static const struct seq_operations ftrace_graph_seq_ops = { .start = g_start, .next = g_next, .stop = g_stop, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a35925d222b..6c0f6a8a22e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1949,7 +1949,7 @@ static int s_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations tracer_seq_ops = { +static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, .stop = s_stop, @@ -2163,7 +2163,7 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations show_traces_seq_ops = { +static const struct seq_operations show_traces_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, -- cgit v1.2.3 From 79f5599772ac2f138d7a75b8f3f06a93f09c75f7 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 15 Jun 2009 14:58:26 +0800 Subject: cpumask: use zalloc_cpumask_var() where possible Remove open-coded zalloc_cpumask_var() and zalloc_cpumask_var_node(). Signed-off-by: Li Zefan Signed-off-by: Rusty Russell --- kernel/trace/trace.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6c0f6a8a22e..411af37f4be 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1984,11 +1984,9 @@ __tracing_open(struct inode *inode, struct file *file) if (current_trace) *iter->trace = *current_trace; - if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) + if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; - cpumask_clear(iter->started); - if (current_trace && current_trace->print_max) iter->tr = &max_tr; else @@ -4389,7 +4387,7 @@ __init static int tracer_alloc_buffers(void) if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL)) goto out_free_buffer_mask; - if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL)) goto out_free_tracing_cpumask; /* To save memory, keep the ring buffer size to its minimum */ @@ -4400,7 +4398,6 @@ __init static int tracer_alloc_buffers(void) cpumask_copy(tracing_buffer_mask, cpu_possible_mask); cpumask_copy(tracing_cpumask, cpu_all_mask); - cpumask_clear(tracing_reader_cpumask); /* TODO: make the number of buffers hot pluggable with CPUS */ global_trace.buffer = ring_buffer_alloc(ring_buf_size, -- cgit v1.2.3 From 8d65af789f3e2cf4cfbdbf71a0f7a61ebcd41d38 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 23 Sep 2009 15:57:19 -0700 Subject: sysctl: remove "struct file *" argument of ->proc_handler It's unused. It isn't needed -- read or write flag is already passed and sysctl shouldn't care about the rest. It _was_ used in two places at arch/frv for some reason. Signed-off-by: Alexey Dobriyan Cc: David Howells Cc: "Eric W. Biederman" Cc: Al Viro Cc: Ralf Baechle Cc: Martin Schwidefsky Cc: Ingo Molnar Cc: "David S. Miller" Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/ftrace.c | 4 ++-- kernel/trace/trace_stack.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 23df7771c93..a142579765b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3015,7 +3015,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) int ftrace_enable_sysctl(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -3025,7 +3025,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, mutex_lock(&ftrace_lock); - ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0f6facb050a..8504ac71e4e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -296,14 +296,14 @@ static const struct file_operations stack_trace_fops = { int stack_trace_sysctl(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&stack_sysctl_mutex); - ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_stack_tracer_enabled == !!stack_tracer_enabled)) -- cgit v1.2.3 From 33974093c024f08caadd2fc71a83bd811ed1831d Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 28 Sep 2009 16:43:01 +0100 Subject: tracing: Fix infinite recursion in ftrace_update_pid_func() When CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST is enabled __ftrace_trace_function contains the current trace function, not ftrace_trace_function. In ftrace_update_pid_func() we currently incorrectly assign the value of ftrace_trace_function to __ftrace_trace_funcion before returning. Without this patch it is possible to execute an infinite recursion whereby ftrace_test_stop_func() calls __ftrace_trace_function, which was assigned ftrace_test_stop_func() in ftrace_update_pid_func(). Signed-off-by: Matt Fleming Acked-by: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <1254152581-18347-1-git-send-email-matt@console-pimps.org> Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 46592feab5a..3724756e41c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -225,7 +225,11 @@ static void ftrace_update_pid_func(void) if (ftrace_trace_function == ftrace_stub) return; +#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST func = ftrace_trace_function; +#else + func = __ftrace_trace_function; +#endif if (ftrace_pid_trace) { set_ftrace_pid_function(func); -- cgit v1.2.3