From ae63b31e4d0e2ec09c569306ea46f664508ef717 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 3 May 2012 23:09:03 -0400 Subject: tracing: Separate out trace events from global variables The trace events for ftrace are all defined via global variables. The arrays of events and event systems are linked to a global list. This prevents multiple users of the event system (what to enable and what not to). By adding descriptors to represent the event/file relation, as well as to which trace_array descriptor they are associated with, allows for more than one set of events to be defined. Once the trace events files have a link between the trace event and the trace_array they are associated with, we can create multiple trace_arrays that can record separate events in separate buffers. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4f1dade56981..932931897b8d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -189,6 +189,8 @@ unsigned long long ns2usecs(cycle_t nsec) */ static struct trace_array global_trace; +LIST_HEAD(ftrace_trace_arrays); + static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); int filter_current_check_discard(struct ring_buffer *buffer, @@ -5359,6 +5361,12 @@ __init static int tracer_alloc_buffers(void) register_die_notifier(&trace_die_notifier); + global_trace.flags = TRACE_ARRAY_FL_GLOBAL; + + INIT_LIST_HEAD(&global_trace.systems); + INIT_LIST_HEAD(&global_trace.events); + list_add(&global_trace.list, &ftrace_trace_arrays); + while (trace_boot_options) { char *option; -- cgit v1.2.3 From ae3b5093ad6004b52e2825f3db1ad8200a2724d8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 23 Jan 2013 15:22:59 -0500 Subject: tracing: Use RING_BUFFER_ALL_CPUS for TRACE_PIPE_ALL_CPU Both RING_BUFFER_ALL_CPUS and TRACE_PIPE_ALL_CPU are defined as -1 and used to say that all the ring buffers are to be modified or read (instead of just a single cpu, which would be >= 0). There's no reason to keep TRACE_PIPE_ALL_CPU as it is also started to be used for more than what it was created for, and now that the ring buffer code added a generic RING_BUFFER_ALL_CPUS define, we can clean up the trace code to use that instead and remove the TRACE_PIPE_ALL_CPU macro. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 28 ++++++++++++++-------------- kernel/trace/trace.h | 2 -- kernel/trace/trace_kdb.c | 4 ++-- 3 files changed, 16 insertions(+), 18 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 932931897b8d..59953aa28845 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -287,13 +287,13 @@ static DEFINE_PER_CPU(struct mutex, cpu_access_lock); static inline void trace_access_lock(int cpu) { - if (cpu == TRACE_PIPE_ALL_CPU) { + if (cpu == RING_BUFFER_ALL_CPUS) { /* gain it for accessing the whole ring buffer. */ down_write(&all_cpu_access_lock); } else { /* gain it for accessing a cpu ring buffer. */ - /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */ + /* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */ down_read(&all_cpu_access_lock); /* Secondly block other access to this @cpu ring buffer. */ @@ -303,7 +303,7 @@ static inline void trace_access_lock(int cpu) static inline void trace_access_unlock(int cpu) { - if (cpu == TRACE_PIPE_ALL_CPU) { + if (cpu == RING_BUFFER_ALL_CPUS) { up_write(&all_cpu_access_lock); } else { mutex_unlock(&per_cpu(cpu_access_lock, cpu)); @@ -1823,7 +1823,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, * If we are in a per_cpu trace file, don't bother by iterating over * all cpu and peek directly. */ - if (cpu_file > TRACE_PIPE_ALL_CPU) { + if (cpu_file > RING_BUFFER_ALL_CPUS) { if (ring_buffer_empty_cpu(buffer, cpu_file)) return NULL; ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events); @@ -1983,7 +1983,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) iter->cpu = 0; iter->idx = -1; - if (cpu_file == TRACE_PIPE_ALL_CPU) { + if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) tracing_iter_reset(iter, cpu); } else @@ -2291,7 +2291,7 @@ int trace_empty(struct trace_iterator *iter) int cpu; /* If we are looking at one CPU buffer, only check that one */ - if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { cpu = iter->cpu_file; buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { @@ -2533,7 +2533,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (!iter->snapshot) tracing_stop(); - if (iter->cpu_file == TRACE_PIPE_ALL_CPU) { + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = ring_buffer_read_prepare(iter->tr->buffer, cpu); @@ -2617,7 +2617,7 @@ static int tracing_open(struct inode *inode, struct file *file) (file->f_flags & O_TRUNC)) { long cpu = (long) inode->i_private; - if (cpu == TRACE_PIPE_ALL_CPU) + if (cpu == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(&global_trace); else tracing_reset(&global_trace, cpu); @@ -5035,7 +5035,7 @@ static __init int tracer_init_debugfs(void) NULL, &tracing_cpumask_fops); trace_create_file("trace", 0644, d_tracer, - (void *) TRACE_PIPE_ALL_CPU, &tracing_fops); + (void *) RING_BUFFER_ALL_CPUS, &tracing_fops); trace_create_file("available_tracers", 0444, d_tracer, &global_trace, &show_traces_fops); @@ -5055,7 +5055,7 @@ static __init int tracer_init_debugfs(void) NULL, &tracing_readme_fops); trace_create_file("trace_pipe", 0444, d_tracer, - (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops); + (void *) RING_BUFFER_ALL_CPUS, &tracing_pipe_fops); trace_create_file("buffer_size_kb", 0644, d_tracer, (void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops); @@ -5085,7 +5085,7 @@ static __init int tracer_init_debugfs(void) #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_tracer, - (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops); + (void *) RING_BUFFER_ALL_CPUS, &snapshot_fops); #endif create_trace_options_dir(); @@ -5162,7 +5162,7 @@ void trace_init_global_iter(struct trace_iterator *iter) { iter->tr = &global_trace; iter->trace = current_trace; - iter->cpu_file = TRACE_PIPE_ALL_CPU; + iter->cpu_file = RING_BUFFER_ALL_CPUS; } static void @@ -5210,7 +5210,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) switch (oops_dump_mode) { case DUMP_ALL: - iter.cpu_file = TRACE_PIPE_ALL_CPU; + iter.cpu_file = RING_BUFFER_ALL_CPUS; break; case DUMP_ORIG: iter.cpu_file = raw_smp_processor_id(); @@ -5219,7 +5219,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) goto out_enable; default: printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); - iter.cpu_file = TRACE_PIPE_ALL_CPU; + iter.cpu_file = RING_BUFFER_ALL_CPUS; } printk(KERN_TRACE "Dumping ftrace buffer:\n"); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 037f7eb03d69..da09a037abcd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -453,8 +453,6 @@ static __always_inline void trace_clear_recursion(int bit) current->trace_recursion = val; } -#define TRACE_PIPE_ALL_CPU -1 - static inline struct ring_buffer_iter * trace_buffer_iter(struct trace_iterator *iter, int cpu) { diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 3c5c5dfea0b3..cc1dbdc5ee5d 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -43,7 +43,7 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) iter.iter_flags |= TRACE_FILE_LAT_FMT; iter.pos = -1; - if (cpu_file == TRACE_PIPE_ALL_CPU) { + if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter.buffer_iter[cpu] = ring_buffer_read_prepare(iter.tr->buffer, cpu); @@ -115,7 +115,7 @@ static int kdb_ftdump(int argc, const char **argv) !cpu_online(cpu_file)) return KDB_BADINT; } else { - cpu_file = TRACE_PIPE_ALL_CPU; + cpu_file = RING_BUFFER_ALL_CPUS; } kdb_trap_printk++; -- cgit v1.2.3 From 2b6080f28c7cc3efc8625ab71495aae89aeb63a0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 11 May 2012 13:29:49 -0400 Subject: tracing: Encapsulate global_trace and remove dependencies on global vars The global_trace variable in kernel/trace/trace.c has been kept 'static' and local to that file so that it would not be used too much outside of that file. This has paid off, even though there were lots of changes to make the trace_array structure more generic (not depending on global_trace). Removal of a lot of direct usages of global_trace is needed to be able to create more trace_arrays such that we can add multiple buffers. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 561 ++++++++++++++++++++++---------------- kernel/trace/trace.h | 21 +- kernel/trace/trace_irqsoff.c | 8 +- kernel/trace/trace_sched_wakeup.c | 8 +- 4 files changed, 358 insertions(+), 240 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 59953aa28845..91fe40905828 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1,7 +1,7 @@ /* * ring buffer based function tracer * - * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2007-2012 Steven Rostedt * Copyright (C) 2008 Ingo Molnar * * Originally taken from the RT patch by: @@ -251,9 +251,6 @@ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; /* trace_types holds a link list of available tracers. */ static struct tracer *trace_types __read_mostly; -/* current_trace points to the tracer that is currently active */ -static struct tracer *current_trace __read_mostly = &nop_trace; - /* * trace_types_lock is used to protect the trace_types list. */ @@ -350,9 +347,6 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; -static int trace_stop_count; -static DEFINE_RAW_SPINLOCK(tracing_start_lock); - /** * trace_wake_up - wake up tasks waiting for trace input * @@ -708,14 +702,14 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct ring_buffer *buf; - if (trace_stop_count) + if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); - if (!current_trace->allocated_snapshot) { + if (!tr->current_trace->allocated_snapshot) { /* Only the nop tracer should hit this when disabling */ - WARN_ON_ONCE(current_trace != &nop_trace); + WARN_ON_ONCE(tr->current_trace != &nop_trace); return; } @@ -742,11 +736,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) { int ret; - if (trace_stop_count) + if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); - if (WARN_ON_ONCE(!current_trace->allocated_snapshot)) + if (WARN_ON_ONCE(!tr->current_trace->allocated_snapshot)) return; arch_spin_lock(&ftrace_max_lock); @@ -853,8 +847,8 @@ int register_tracer(struct tracer *type) #ifdef CONFIG_FTRACE_STARTUP_TEST if (type->selftest && !tracing_selftest_disabled) { - struct tracer *saved_tracer = current_trace; struct trace_array *tr = &global_trace; + struct tracer *saved_tracer = tr->current_trace; /* * Run a selftest on this tracer. @@ -865,7 +859,7 @@ int register_tracer(struct tracer *type) */ tracing_reset_online_cpus(tr); - current_trace = type; + tr->current_trace = type; if (type->use_max_tr) { /* If we expanded the buffers, make sure the max is expanded too */ @@ -879,7 +873,7 @@ int register_tracer(struct tracer *type) pr_info("Testing tracer %s: ", type->name); ret = type->selftest(type, tr); /* the test is responsible for resetting too */ - current_trace = saved_tracer; + tr->current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); /* Add the warning after printing 'FAILED' */ @@ -997,7 +991,7 @@ static void trace_init_cmdlines(void) int is_tracing_stopped(void) { - return trace_stop_count; + return global_trace.stop_count; } /** @@ -1029,12 +1023,12 @@ void tracing_start(void) if (tracing_disabled) return; - raw_spin_lock_irqsave(&tracing_start_lock, flags); - if (--trace_stop_count) { - if (trace_stop_count < 0) { + raw_spin_lock_irqsave(&global_trace.start_lock, flags); + if (--global_trace.stop_count) { + if (global_trace.stop_count < 0) { /* Someone screwed up their debugging */ WARN_ON_ONCE(1); - trace_stop_count = 0; + global_trace.stop_count = 0; } goto out; } @@ -1054,7 +1048,38 @@ void tracing_start(void) ftrace_start(); out: - raw_spin_unlock_irqrestore(&tracing_start_lock, flags); + raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); +} + +static void tracing_start_tr(struct trace_array *tr) +{ + struct ring_buffer *buffer; + unsigned long flags; + + if (tracing_disabled) + return; + + /* If global, we need to also start the max tracer */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return tracing_start(); + + raw_spin_lock_irqsave(&tr->start_lock, flags); + + if (--tr->stop_count) { + if (tr->stop_count < 0) { + /* Someone screwed up their debugging */ + WARN_ON_ONCE(1); + tr->stop_count = 0; + } + goto out; + } + + buffer = tr->buffer; + if (buffer) + ring_buffer_record_enable(buffer); + + out: + raw_spin_unlock_irqrestore(&tr->start_lock, flags); } /** @@ -1069,8 +1094,8 @@ void tracing_stop(void) unsigned long flags; ftrace_stop(); - raw_spin_lock_irqsave(&tracing_start_lock, flags); - if (trace_stop_count++) + raw_spin_lock_irqsave(&global_trace.start_lock, flags); + if (global_trace.stop_count++) goto out; /* Prevent the buffers from switching */ @@ -1087,7 +1112,28 @@ void tracing_stop(void) arch_spin_unlock(&ftrace_max_lock); out: - raw_spin_unlock_irqrestore(&tracing_start_lock, flags); + raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); +} + +static void tracing_stop_tr(struct trace_array *tr) +{ + struct ring_buffer *buffer; + unsigned long flags; + + /* If global, we need to also stop the max tracer */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return tracing_stop(); + + raw_spin_lock_irqsave(&tr->start_lock, flags); + if (tr->stop_count++) + goto out; + + buffer = tr->buffer; + if (buffer) + ring_buffer_record_disable(buffer); + + out: + raw_spin_unlock_irqrestore(&tr->start_lock, flags); } void trace_stop_cmdline_recording(void); @@ -1956,6 +2002,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; @@ -1968,8 +2015,8 @@ static void *s_start(struct seq_file *m, loff_t *pos) * will point to the same string as current_trace->name. */ mutex_lock(&trace_types_lock); - if (unlikely(current_trace && iter->trace->name != current_trace->name)) - *iter->trace = *current_trace; + if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) + *iter->trace = *tr->current_trace; mutex_unlock(&trace_types_lock); if (iter->snapshot && iter->trace->use_max_tr) @@ -2099,7 +2146,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); struct trace_array *tr = iter->tr; struct trace_array_cpu *data = tr->data[tr->cpu]; - struct tracer *type = current_trace; + struct tracer *type = iter->trace; unsigned long entries; unsigned long total; const char *name = "preemption"; @@ -2478,7 +2525,8 @@ static const struct seq_operations tracer_seq_ops = { static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, bool snapshot) { - long cpu_file = (long) inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; struct trace_iterator *iter; int cpu; @@ -2503,19 +2551,20 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (!iter->trace) goto fail; - *iter->trace = *current_trace; + *iter->trace = *tr->current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; - if (current_trace->print_max || snapshot) + /* Currently only the top directory has a snapshot */ + if (tr->current_trace->print_max || snapshot) iter->tr = &max_tr; else - iter->tr = &global_trace; + iter->tr = tr; iter->snapshot = snapshot; iter->pos = -1; mutex_init(&iter->mutex); - iter->cpu_file = cpu_file; + iter->cpu_file = tc->cpu; /* Notify the tracer early; before we stop tracing. */ if (iter->trace && iter->trace->open) @@ -2531,7 +2580,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) /* stop the trace while dumping if we are not opening "snapshot" */ if (!iter->snapshot) - tracing_stop(); + tracing_stop_tr(tr); if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { @@ -2578,6 +2627,7 @@ static int tracing_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct trace_iterator *iter; + struct trace_array *tr; int cpu; if (!(file->f_mode & FMODE_READ)) @@ -2585,6 +2635,12 @@ static int tracing_release(struct inode *inode, struct file *file) iter = m->private; + /* Only the global tracer has a matching max_tr */ + if (iter->tr == &max_tr) + tr = &global_trace; + else + tr = iter->tr; + mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) @@ -2596,7 +2652,7 @@ static int tracing_release(struct inode *inode, struct file *file) if (!iter->snapshot) /* reenable tracing if it was previously enabled */ - tracing_start(); + tracing_start_tr(tr); mutex_unlock(&trace_types_lock); mutex_destroy(&iter->mutex); @@ -2615,12 +2671,13 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { - long cpu = (long) inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; - if (cpu == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(&global_trace); + if (tc->cpu == RING_BUFFER_ALL_CPUS) + tracing_reset_online_cpus(tr); else - tracing_reset(&global_trace, cpu); + tracing_reset(tr, tc->cpu); } if (file->f_mode & FMODE_READ) { @@ -2767,8 +2824,9 @@ static ssize_t tracing_cpumask_write(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { - int err, cpu; + struct trace_array *tr = filp->private_data; cpumask_var_t tracing_cpumask_new; + int err, cpu; if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; @@ -2788,13 +2846,13 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, */ if (cpumask_test_cpu(cpu, tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_inc(&global_trace.data[cpu]->disabled); - ring_buffer_record_disable_cpu(global_trace.buffer, cpu); + atomic_inc(&tr->data[cpu]->disabled); + ring_buffer_record_disable_cpu(tr->buffer, cpu); } if (!cpumask_test_cpu(cpu, tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_dec(&global_trace.data[cpu]->disabled); - ring_buffer_record_enable_cpu(global_trace.buffer, cpu); + atomic_dec(&tr->data[cpu]->disabled); + ring_buffer_record_enable_cpu(tr->buffer, cpu); } } arch_spin_unlock(&ftrace_max_lock); @@ -2823,12 +2881,13 @@ static const struct file_operations tracing_cpumask_fops = { static int tracing_trace_options_show(struct seq_file *m, void *v) { struct tracer_opt *trace_opts; + struct trace_array *tr = m->private; u32 tracer_flags; int i; mutex_lock(&trace_types_lock); - tracer_flags = current_trace->flags->val; - trace_opts = current_trace->flags->opts; + tracer_flags = tr->current_trace->flags->val; + trace_opts = tr->current_trace->flags->opts; for (i = 0; trace_options[i]; i++) { if (trace_flags & (1 << i)) @@ -2892,15 +2951,15 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) return 0; } -int set_tracer_flag(unsigned int mask, int enabled) +int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { /* do nothing if flag is already set */ if (!!(trace_flags & mask) == !!enabled) return 0; /* Give the tracer a chance to approve the change */ - if (current_trace->flag_changed) - if (current_trace->flag_changed(current_trace, mask, !!enabled)) + if (tr->current_trace->flag_changed) + if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled)) return -EINVAL; if (enabled) @@ -2924,7 +2983,7 @@ int set_tracer_flag(unsigned int mask, int enabled) return 0; } -static int trace_set_options(char *option) +static int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; @@ -2942,14 +3001,14 @@ static int trace_set_options(char *option) for (i = 0; trace_options[i]; i++) { if (strcmp(cmp, trace_options[i]) == 0) { - ret = set_tracer_flag(1 << i, !neg); + ret = set_tracer_flag(tr, 1 << i, !neg); break; } } /* If no option could be set, test the specific tracer options */ if (!trace_options[i]) - ret = set_tracer_option(current_trace, cmp, neg); + ret = set_tracer_option(tr->current_trace, cmp, neg); mutex_unlock(&trace_types_lock); @@ -2960,6 +3019,8 @@ static ssize_t tracing_trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; char buf[64]; int ret; @@ -2971,7 +3032,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, buf[cnt] = 0; - ret = trace_set_options(buf); + ret = trace_set_options(tr, buf); if (ret < 0) return ret; @@ -2984,7 +3045,8 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file) { if (tracing_disabled) return -ENODEV; - return single_open(file, tracing_trace_options_show, NULL); + + return single_open(file, tracing_trace_options_show, inode->i_private); } static const struct file_operations tracing_iter_fops = { @@ -3082,11 +3144,12 @@ static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { + struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+2]; int r; mutex_lock(&trace_types_lock); - r = sprintf(buf, "%s\n", current_trace->name); + r = sprintf(buf, "%s\n", tr->current_trace->name); mutex_unlock(&trace_types_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); @@ -3130,7 +3193,8 @@ static int resize_buffer_duplicate_size(struct trace_array *tr, return ret; } -static int __tracing_resize_ring_buffer(unsigned long size, int cpu) +static int __tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu) { int ret; @@ -3142,20 +3206,20 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) ring_buffer_expanded = 1; /* May be called before buffers are initialized */ - if (!global_trace.buffer) + if (!tr->buffer) return 0; - ret = ring_buffer_resize(global_trace.buffer, size, cpu); + ret = ring_buffer_resize(tr->buffer, size, cpu); if (ret < 0) return ret; - if (!current_trace->use_max_tr) + if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || + !tr->current_trace->use_max_tr) goto out; ret = ring_buffer_resize(max_tr.buffer, size, cpu); if (ret < 0) { - int r = resize_buffer_duplicate_size(&global_trace, - &global_trace, cpu); + int r = resize_buffer_duplicate_size(tr, tr, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -3184,14 +3248,15 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) out: if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(&global_trace, size); + set_buffer_entries(tr, size); else - global_trace.data[cpu]->entries = size; + tr->data[cpu]->entries = size; return ret; } -static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) +static ssize_t tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu_id) { int ret = size; @@ -3205,7 +3270,7 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) } } - ret = __tracing_resize_ring_buffer(size, cpu_id); + ret = __tracing_resize_ring_buffer(tr, size, cpu_id); if (ret < 0) ret = -ENOMEM; @@ -3232,7 +3297,7 @@ int tracing_update_buffers(void) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) - ret = __tracing_resize_ring_buffer(trace_buf_size, + ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size, RING_BUFFER_ALL_CPUS); mutex_unlock(&trace_types_lock); @@ -3242,7 +3307,7 @@ int tracing_update_buffers(void) struct trace_option_dentry; static struct trace_option_dentry * -create_trace_option_files(struct tracer *tracer); +create_trace_option_files(struct trace_array *tr, struct tracer *tracer); static void destroy_trace_option_files(struct trace_option_dentry *topts); @@ -3258,7 +3323,7 @@ static int tracing_set_tracer(const char *buf) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) { - ret = __tracing_resize_ring_buffer(trace_buf_size, + ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); if (ret < 0) goto out; @@ -3273,18 +3338,18 @@ static int tracing_set_tracer(const char *buf) ret = -EINVAL; goto out; } - if (t == current_trace) + if (t == tr->current_trace) goto out; trace_branch_disable(); - current_trace->enabled = false; + tr->current_trace->enabled = false; - if (current_trace->reset) - current_trace->reset(tr); + if (tr->current_trace->reset) + tr->current_trace->reset(tr); - had_max_tr = current_trace->allocated_snapshot; - current_trace = &nop_trace; + had_max_tr = tr->current_trace->allocated_snapshot; + tr->current_trace = &nop_trace; if (had_max_tr && !t->use_max_tr) { /* @@ -3303,11 +3368,11 @@ static int tracing_set_tracer(const char *buf) ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&max_tr, 1); tracing_reset_online_cpus(&max_tr); - current_trace->allocated_snapshot = false; + tr->current_trace->allocated_snapshot = false; } destroy_trace_option_files(topts); - topts = create_trace_option_files(t); + topts = create_trace_option_files(tr, t); if (t->use_max_tr && !had_max_tr) { /* we need to make per cpu buffer sizes equivalent */ ret = resize_buffer_duplicate_size(&max_tr, &global_trace, @@ -3323,8 +3388,8 @@ static int tracing_set_tracer(const char *buf) goto out; } - current_trace = t; - current_trace->enabled = true; + tr->current_trace = t; + tr->current_trace->enabled = true; trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); @@ -3398,7 +3463,8 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, static int tracing_open_pipe(struct inode *inode, struct file *filp) { - long cpu_file = (long) inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; struct trace_iterator *iter; int ret = 0; @@ -3423,7 +3489,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) ret = -ENOMEM; goto fail; } - *iter->trace = *current_trace; + *iter->trace = *tr->current_trace; if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { ret = -ENOMEM; @@ -3440,8 +3506,8 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (trace_clocks[trace_clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; - iter->cpu_file = cpu_file; - iter->tr = &global_trace; + iter->cpu_file = tc->cpu; + iter->tr = tc->tr; mutex_init(&iter->mutex); filp->private_data = iter; @@ -3563,6 +3629,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; + struct trace_array *tr = iter->tr; ssize_t sret; /* return any leftover data */ @@ -3574,8 +3641,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(iter->trace->name != current_trace->name)) - *iter->trace = *current_trace; + if (unlikely(iter->trace->name != tr->current_trace->name)) + *iter->trace = *tr->current_trace; mutex_unlock(&trace_types_lock); /* @@ -3731,6 +3798,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; + struct trace_array *tr = iter->tr; ssize_t ret; size_t rem; unsigned int i; @@ -3740,8 +3808,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(iter->trace->name != current_trace->name)) - *iter->trace = *current_trace; + if (unlikely(iter->trace->name != tr->current_trace->name)) + *iter->trace = *tr->current_trace; mutex_unlock(&trace_types_lock); mutex_lock(&iter->mutex); @@ -3803,43 +3871,19 @@ out_err: goto out; } -struct ftrace_entries_info { - struct trace_array *tr; - int cpu; -}; - -static int tracing_entries_open(struct inode *inode, struct file *filp) -{ - struct ftrace_entries_info *info; - - if (tracing_disabled) - return -ENODEV; - - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - return -ENOMEM; - - info->tr = &global_trace; - info->cpu = (unsigned long)inode->i_private; - - filp->private_data = info; - - return 0; -} - static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_entries_info *info = filp->private_data; - struct trace_array *tr = info->tr; + struct trace_cpu *tc = filp->private_data; + struct trace_array *tr = tc->tr; char buf[64]; int r = 0; ssize_t ret; mutex_lock(&trace_types_lock); - if (info->cpu == RING_BUFFER_ALL_CPUS) { + if (tc->cpu == RING_BUFFER_ALL_CPUS) { int cpu, buf_size_same; unsigned long size; @@ -3866,7 +3910,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10); + r = sprintf(buf, "%lu\n", tr->data[tc->cpu]->entries >> 10); mutex_unlock(&trace_types_lock); @@ -3878,7 +3922,7 @@ static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_entries_info *info = filp->private_data; + struct trace_cpu *tc = filp->private_data; unsigned long val; int ret; @@ -3893,7 +3937,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, /* value is in KB */ val <<= 10; - ret = tracing_resize_ring_buffer(val, info->cpu); + ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu); if (ret < 0) return ret; @@ -3902,16 +3946,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, return cnt; } -static int -tracing_entries_release(struct inode *inode, struct file *filp) -{ - struct ftrace_entries_info *info = filp->private_data; - - kfree(info); - - return 0; -} - static ssize_t tracing_total_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -3953,11 +3987,13 @@ tracing_free_buffer_write(struct file *filp, const char __user *ubuf, static int tracing_free_buffer_release(struct inode *inode, struct file *filp) { + struct trace_array *tr = inode->i_private; + /* disable tracing ? */ if (trace_flags & TRACE_ITER_STOP_ON_FREE) tracing_off(); /* resize the ring buffer to 0 */ - tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS); + tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); return 0; } @@ -4068,13 +4104,14 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, static int tracing_clock_show(struct seq_file *m, void *v) { + struct trace_array *tr = m->private; int i; for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) seq_printf(m, "%s%s%s%s", i ? " " : "", - i == trace_clock_id ? "[" : "", trace_clocks[i].name, - i == trace_clock_id ? "]" : ""); + i == tr->clock_id ? "[" : "", trace_clocks[i].name, + i == tr->clock_id ? "]" : ""); seq_putc(m, '\n'); return 0; @@ -4083,6 +4120,8 @@ static int tracing_clock_show(struct seq_file *m, void *v) static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { + struct seq_file *m = filp->private_data; + struct trace_array *tr = m->private; char buf[64]; const char *clockstr; int i; @@ -4104,12 +4143,12 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, if (i == ARRAY_SIZE(trace_clocks)) return -EINVAL; - trace_clock_id = i; - mutex_lock(&trace_types_lock); - ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func); - if (max_tr.buffer) + tr->clock_id = i; + + ring_buffer_set_clock(tr->buffer, trace_clocks[i].func); + if (tr->flags & TRACE_ARRAY_FL_GLOBAL && max_tr.buffer) ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func); /* @@ -4130,20 +4169,37 @@ static int tracing_clock_open(struct inode *inode, struct file *file) { if (tracing_disabled) return -ENODEV; - return single_open(file, tracing_clock_show, NULL); + + return single_open(file, tracing_clock_show, inode->i_private); } #ifdef CONFIG_TRACER_SNAPSHOT static int tracing_snapshot_open(struct inode *inode, struct file *file) { + struct trace_cpu *tc = inode->i_private; struct trace_iterator *iter; + struct seq_file *m; int ret = 0; if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); if (IS_ERR(iter)) ret = PTR_ERR(iter); + } else { + /* Writes still need the seq_file to hold the private data */ + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) + return -ENOMEM; + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) { + kfree(m); + return -ENOMEM; + } + iter->tr = tc->tr; + m->private = iter; + file->private_data = m; } + return ret; } @@ -4151,6 +4207,9 @@ static ssize_t tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct seq_file *m = filp->private_data; + struct trace_iterator *iter = m->private; + struct trace_array *tr = iter->tr; unsigned long val; int ret; @@ -4164,30 +4223,30 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, mutex_lock(&trace_types_lock); - if (current_trace->use_max_tr) { + if (tr->current_trace->use_max_tr) { ret = -EBUSY; goto out; } switch (val) { case 0: - if (current_trace->allocated_snapshot) { + if (tr->current_trace->allocated_snapshot) { /* free spare buffer */ ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&max_tr, 1); tracing_reset_online_cpus(&max_tr); - current_trace->allocated_snapshot = false; + tr->current_trace->allocated_snapshot = false; } break; case 1: - if (!current_trace->allocated_snapshot) { + if (!tr->current_trace->allocated_snapshot) { /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&max_tr, &global_trace, RING_BUFFER_ALL_CPUS); if (ret < 0) break; - current_trace->allocated_snapshot = true; + tr->current_trace->allocated_snapshot = true; } local_irq_disable(); @@ -4196,7 +4255,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, local_irq_enable(); break; default: - if (current_trace->allocated_snapshot) + if (tr->current_trace->allocated_snapshot) tracing_reset_online_cpus(&max_tr); break; } @@ -4209,6 +4268,22 @@ out: mutex_unlock(&trace_types_lock); return ret; } + +static int tracing_snapshot_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + + if (file->f_mode & FMODE_READ) + return tracing_release(inode, file); + + /* If write only, the seq_file is just a stub */ + if (m) + kfree(m->private); + kfree(m); + + return 0; +} + #endif /* CONFIG_TRACER_SNAPSHOT */ @@ -4236,10 +4311,9 @@ static const struct file_operations tracing_pipe_fops = { }; static const struct file_operations tracing_entries_fops = { - .open = tracing_entries_open, + .open = tracing_open_generic, .read = tracing_entries_read, .write = tracing_entries_write, - .release = tracing_entries_release, .llseek = generic_file_llseek, }; @@ -4274,7 +4348,7 @@ static const struct file_operations snapshot_fops = { .read = seq_read, .write = tracing_snapshot_write, .llseek = tracing_seek, - .release = tracing_release, + .release = tracing_snapshot_release, }; #endif /* CONFIG_TRACER_SNAPSHOT */ @@ -4287,7 +4361,8 @@ struct ftrace_buffer_info { static int tracing_buffers_open(struct inode *inode, struct file *filp) { - int cpu = (int)(long)inode->i_private; + struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = tc->tr; struct ftrace_buffer_info *info; if (tracing_disabled) @@ -4297,8 +4372,8 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) if (!info) return -ENOMEM; - info->tr = &global_trace; - info->cpu = cpu; + info->tr = tr; + info->cpu = tc->cpu; info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; @@ -4535,12 +4610,13 @@ static ssize_t tracing_stats_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - unsigned long cpu = (unsigned long)filp->private_data; - struct trace_array *tr = &global_trace; + struct trace_cpu *tc = filp->private_data; + struct trace_array *tr = tc->tr; struct trace_seq *s; unsigned long cnt; unsigned long long t; unsigned long usec_rem; + int cpu = tc->cpu; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) @@ -4636,58 +4712,57 @@ static const struct file_operations tracing_dyn_info_fops = { }; #endif -static struct dentry *d_tracer; - -struct dentry *tracing_init_dentry(void) +struct dentry *tracing_init_dentry_tr(struct trace_array *tr) { static int once; - if (d_tracer) - return d_tracer; + if (tr->dir) + return tr->dir; if (!debugfs_initialized()) return NULL; - d_tracer = debugfs_create_dir("tracing", NULL); + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + tr->dir = debugfs_create_dir("tracing", NULL); - if (!d_tracer && !once) { + if (!tr->dir && !once) { once = 1; pr_warning("Could not create debugfs directory 'tracing'\n"); return NULL; } - return d_tracer; + return tr->dir; } -static struct dentry *d_percpu; +struct dentry *tracing_init_dentry(void) +{ + return tracing_init_dentry_tr(&global_trace); +} -static struct dentry *tracing_dentry_percpu(void) +static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) { - static int once; struct dentry *d_tracer; - if (d_percpu) - return d_percpu; - - d_tracer = tracing_init_dentry(); + if (tr->percpu_dir) + return tr->percpu_dir; + d_tracer = tracing_init_dentry_tr(tr); if (!d_tracer) return NULL; - d_percpu = debugfs_create_dir("per_cpu", d_tracer); + tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer); - if (!d_percpu && !once) { - once = 1; - pr_warning("Could not create debugfs directory 'per_cpu'\n"); - return NULL; - } + WARN_ONCE(!tr->percpu_dir, + "Could not create debugfs directory 'per_cpu/%d'\n", cpu); - return d_percpu; + return tr->percpu_dir; } -static void tracing_init_debugfs_percpu(long cpu) +static void +tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) { - struct dentry *d_percpu = tracing_dentry_percpu(); + struct trace_array_cpu *data = tr->data[cpu]; + struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ @@ -4703,20 +4778,20 @@ static void tracing_init_debugfs_percpu(long cpu) /* per cpu trace_pipe */ trace_create_file("trace_pipe", 0444, d_cpu, - (void *) cpu, &tracing_pipe_fops); + (void *)&data->trace_cpu, &tracing_pipe_fops); /* per cpu trace */ trace_create_file("trace", 0644, d_cpu, - (void *) cpu, &tracing_fops); + (void *)&data->trace_cpu, &tracing_fops); trace_create_file("trace_pipe_raw", 0444, d_cpu, - (void *) cpu, &tracing_buffers_fops); + (void *)&data->trace_cpu, &tracing_buffers_fops); trace_create_file("stats", 0444, d_cpu, - (void *) cpu, &tracing_stats_fops); + (void *)&data->trace_cpu, &tracing_stats_fops); trace_create_file("buffer_size_kb", 0444, d_cpu, - (void *) cpu, &tracing_entries_fops); + (void *)&data->trace_cpu, &tracing_entries_fops); } #ifdef CONFIG_FTRACE_SELFTEST @@ -4727,6 +4802,7 @@ static void tracing_init_debugfs_percpu(long cpu) struct trace_option_dentry { struct tracer_opt *opt; struct tracer_flags *flags; + struct trace_array *tr; struct dentry *entry; }; @@ -4762,7 +4838,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, if (!!(topt->flags->val & topt->opt->bit) != val) { mutex_lock(&trace_types_lock); - ret = __set_tracer_option(current_trace, topt->flags, + ret = __set_tracer_option(topt->tr->current_trace, topt->flags, topt->opt, !val); mutex_unlock(&trace_types_lock); if (ret) @@ -4801,6 +4877,7 @@ static ssize_t trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct trace_array *tr = &global_trace; long index = (long)filp->private_data; unsigned long val; int ret; @@ -4813,7 +4890,7 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, return -EINVAL; mutex_lock(&trace_types_lock); - ret = set_tracer_flag(1 << index, val); + ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); if (ret < 0) @@ -4847,40 +4924,41 @@ struct dentry *trace_create_file(const char *name, } -static struct dentry *trace_options_init_dentry(void) +static struct dentry *trace_options_init_dentry(struct trace_array *tr) { struct dentry *d_tracer; - static struct dentry *t_options; - if (t_options) - return t_options; + if (tr->options) + return tr->options; - d_tracer = tracing_init_dentry(); + d_tracer = tracing_init_dentry_tr(tr); if (!d_tracer) return NULL; - t_options = debugfs_create_dir("options", d_tracer); - if (!t_options) { + tr->options = debugfs_create_dir("options", d_tracer); + if (!tr->options) { pr_warning("Could not create debugfs directory 'options'\n"); return NULL; } - return t_options; + return tr->options; } static void -create_trace_option_file(struct trace_option_dentry *topt, +create_trace_option_file(struct trace_array *tr, + struct trace_option_dentry *topt, struct tracer_flags *flags, struct tracer_opt *opt) { struct dentry *t_options; - t_options = trace_options_init_dentry(); + t_options = trace_options_init_dentry(tr); if (!t_options) return; topt->flags = flags; topt->opt = opt; + topt->tr = tr; topt->entry = trace_create_file(opt->name, 0644, t_options, topt, &trace_options_fops); @@ -4888,7 +4966,7 @@ create_trace_option_file(struct trace_option_dentry *topt, } static struct trace_option_dentry * -create_trace_option_files(struct tracer *tracer) +create_trace_option_files(struct trace_array *tr, struct tracer *tracer) { struct trace_option_dentry *topts; struct tracer_flags *flags; @@ -4913,7 +4991,7 @@ create_trace_option_files(struct tracer *tracer) return NULL; for (cnt = 0; opts[cnt].name; cnt++) - create_trace_option_file(&topts[cnt], flags, + create_trace_option_file(tr, &topts[cnt], flags, &opts[cnt]); return topts; @@ -4936,11 +5014,12 @@ destroy_trace_option_files(struct trace_option_dentry *topts) } static struct dentry * -create_trace_option_core_file(const char *option, long index) +create_trace_option_core_file(struct trace_array *tr, + const char *option, long index) { struct dentry *t_options; - t_options = trace_options_init_dentry(); + t_options = trace_options_init_dentry(tr); if (!t_options) return NULL; @@ -4948,17 +5027,17 @@ create_trace_option_core_file(const char *option, long index) &trace_options_core_fops); } -static __init void create_trace_options_dir(void) +static __init void create_trace_options_dir(struct trace_array *tr) { struct dentry *t_options; int i; - t_options = trace_options_init_dentry(); + t_options = trace_options_init_dentry(tr); if (!t_options) return; for (i = 0; trace_options[i]; i++) - create_trace_option_core_file(trace_options[i], i); + create_trace_option_core_file(tr, trace_options[i], i); } static ssize_t @@ -4997,12 +5076,12 @@ rb_simple_write(struct file *filp, const char __user *ubuf, mutex_lock(&trace_types_lock); if (val) { ring_buffer_record_on(buffer); - if (current_trace->start) - current_trace->start(tr); + if (tr->current_trace->start) + tr->current_trace->start(tr); } else { ring_buffer_record_off(buffer); - if (current_trace->stop) - current_trace->stop(tr); + if (tr->current_trace->stop) + tr->current_trace->stop(tr); } mutex_unlock(&trace_types_lock); } @@ -5019,6 +5098,38 @@ static const struct file_operations rb_simple_fops = { .llseek = default_llseek, }; +static void +init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) +{ + + trace_create_file("trace_options", 0644, d_tracer, + tr, &tracing_iter_fops); + + trace_create_file("trace", 0644, d_tracer, + (void *)&tr->trace_cpu, &tracing_fops); + + trace_create_file("trace_pipe", 0444, d_tracer, + (void *)&tr->trace_cpu, &tracing_pipe_fops); + + trace_create_file("buffer_size_kb", 0644, d_tracer, + (void *)&tr->trace_cpu, &tracing_entries_fops); + + trace_create_file("buffer_total_size_kb", 0444, d_tracer, + tr, &tracing_total_entries_fops); + + trace_create_file("free_buffer", 0644, d_tracer, + tr, &tracing_free_buffer_fops); + + trace_create_file("trace_marker", 0220, d_tracer, + tr, &tracing_mark_fops); + + trace_create_file("trace_clock", 0644, d_tracer, tr, + &trace_clock_fops); + + trace_create_file("tracing_on", 0644, d_tracer, + tr, &rb_simple_fops); +} + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; @@ -5028,14 +5139,10 @@ static __init int tracer_init_debugfs(void) d_tracer = tracing_init_dentry(); - trace_create_file("trace_options", 0644, d_tracer, - NULL, &tracing_iter_fops); + init_tracer_debugfs(&global_trace, d_tracer); trace_create_file("tracing_cpumask", 0644, d_tracer, - NULL, &tracing_cpumask_fops); - - trace_create_file("trace", 0644, d_tracer, - (void *) RING_BUFFER_ALL_CPUS, &tracing_fops); + &global_trace, &tracing_cpumask_fops); trace_create_file("available_tracers", 0444, d_tracer, &global_trace, &show_traces_fops); @@ -5054,30 +5161,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("README", 0444, d_tracer, NULL, &tracing_readme_fops); - trace_create_file("trace_pipe", 0444, d_tracer, - (void *) RING_BUFFER_ALL_CPUS, &tracing_pipe_fops); - - trace_create_file("buffer_size_kb", 0644, d_tracer, - (void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops); - - trace_create_file("buffer_total_size_kb", 0444, d_tracer, - &global_trace, &tracing_total_entries_fops); - - trace_create_file("free_buffer", 0644, d_tracer, - &global_trace, &tracing_free_buffer_fops); - - trace_create_file("trace_marker", 0220, d_tracer, - NULL, &tracing_mark_fops); - trace_create_file("saved_cmdlines", 0444, d_tracer, NULL, &tracing_saved_cmdlines_fops); - trace_create_file("trace_clock", 0644, d_tracer, NULL, - &trace_clock_fops); - - trace_create_file("tracing_on", 0644, d_tracer, - &global_trace, &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); @@ -5085,13 +5171,13 @@ static __init int tracer_init_debugfs(void) #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_tracer, - (void *) RING_BUFFER_ALL_CPUS, &snapshot_fops); + (void *)&global_trace.trace_cpu, &snapshot_fops); #endif - create_trace_options_dir(); + create_trace_options_dir(&global_trace); for_each_tracing_cpu(cpu) - tracing_init_debugfs_percpu(cpu); + tracing_init_debugfs_percpu(&global_trace, cpu); return 0; } @@ -5161,7 +5247,7 @@ trace_printk_seq(struct trace_seq *s) void trace_init_global_iter(struct trace_iterator *iter) { iter->tr = &global_trace; - iter->trace = current_trace; + iter->trace = iter->tr->current_trace; iter->cpu_file = RING_BUFFER_ALL_CPUS; } @@ -5315,6 +5401,8 @@ __init static int tracer_alloc_buffers(void) cpumask_copy(tracing_buffer_mask, cpu_possible_mask); cpumask_copy(tracing_cpumask, cpu_all_mask); + raw_spin_lock_init(&global_trace.start_lock); + /* TODO: make the number of buffers hot pluggable with CPUS */ global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags); if (!global_trace.buffer) { @@ -5328,6 +5416,7 @@ __init static int tracer_alloc_buffers(void) #ifdef CONFIG_TRACER_MAX_TRACE max_tr.buffer = ring_buffer_alloc(1, rb_flags); + raw_spin_lock_init(&max_tr.start_lock); if (!max_tr.buffer) { printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); WARN_ON(1); @@ -5339,7 +5428,11 @@ __init static int tracer_alloc_buffers(void) /* Allocate the first page for all buffers */ for_each_tracing_cpu(i) { global_trace.data[i] = &per_cpu(global_trace_cpu, i); + global_trace.data[i]->trace_cpu.cpu = i; + global_trace.data[i]->trace_cpu.tr = &global_trace; max_tr.data[i] = &per_cpu(max_tr_data, i); + max_tr.data[i]->trace_cpu.cpu = i; + max_tr.data[i]->trace_cpu.tr = &max_tr; } set_buffer_entries(&global_trace, @@ -5353,6 +5446,8 @@ __init static int tracer_alloc_buffers(void) register_tracer(&nop_trace); + global_trace.current_trace = &nop_trace; + /* All seems OK, enable tracing */ tracing_disabled = 0; @@ -5363,6 +5458,10 @@ __init static int tracer_alloc_buffers(void) global_trace.flags = TRACE_ARRAY_FL_GLOBAL; + /* Holder for file callbacks */ + global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS; + global_trace.trace_cpu.tr = &global_trace; + INIT_LIST_HEAD(&global_trace.systems); INIT_LIST_HEAD(&global_trace.events); list_add(&global_trace.list, &ftrace_trace_arrays); @@ -5371,7 +5470,7 @@ __init static int tracer_alloc_buffers(void) char *option; option = strsep(&trace_boot_options, ","); - trace_set_options(option); + trace_set_options(&global_trace, option); } return 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index da09a037abcd..b80fbcf70af4 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -127,12 +127,21 @@ enum trace_flag_type { #define TRACE_BUF_SIZE 1024 +struct trace_array; + +struct trace_cpu { + struct trace_array *tr; + struct dentry *dir; + int cpu; +}; + /* * The CPU trace array - it consists of thousands of trace entries * plus some other descriptor data: (for example which task started * the trace, etc.) */ struct trace_array_cpu { + struct trace_cpu trace_cpu; atomic_t disabled; void *buffer_page; /* ring buffer spare */ @@ -151,6 +160,8 @@ struct trace_array_cpu { char comm[TASK_COMM_LEN]; }; +struct tracer; + /* * The trace array - an array of per-CPU trace arrays. This is the * highest level data structure that individual tracers deal with. @@ -161,9 +172,16 @@ struct trace_array { struct list_head list; int cpu; int buffer_disabled; + struct trace_cpu trace_cpu; /* place holder */ + int stop_count; + int clock_id; + struct tracer *current_trace; unsigned int flags; cycle_t time_start; + raw_spinlock_t start_lock; struct dentry *dir; + struct dentry *options; + struct dentry *percpu_dir; struct dentry *event_dir; struct list_head systems; struct list_head events; @@ -474,6 +492,7 @@ struct dentry *trace_create_file(const char *name, void *data, const struct file_operations *fops); +struct dentry *tracing_init_dentry_tr(struct trace_array *tr); struct dentry *tracing_init_dentry(void); struct ring_buffer_event; @@ -979,7 +998,7 @@ extern const char *__stop___trace_bprintk_fmt[]; void trace_printk_init_buffers(void); void trace_printk_start_comm(void); int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); -int set_tracer_flag(unsigned int mask, int enabled); +int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 443b25b43b4f..b3cf6bf308ef 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -561,8 +561,8 @@ static void __irqsoff_tracer_init(struct trace_array *tr) save_flags = trace_flags; /* non overwrite screws up the latency tracers */ - set_tracer_flag(TRACE_ITER_OVERWRITE, 1); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; irqsoff_trace = tr; @@ -581,8 +581,8 @@ static void irqsoff_tracer_reset(struct trace_array *tr) stop_irqsoff_tracer(tr, is_graph()); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); - set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); } static void irqsoff_tracer_start(struct trace_array *tr) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index fde652c9a511..5255a8477247 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -543,8 +543,8 @@ static int __wakeup_tracer_init(struct trace_array *tr) save_flags = trace_flags; /* non overwrite screws up the latency tracers */ - set_tracer_flag(TRACE_ITER_OVERWRITE, 1); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; wakeup_trace = tr; @@ -573,8 +573,8 @@ static void wakeup_tracer_reset(struct trace_array *tr) /* make sure we put back any tasks we are tracing */ wakeup_reset(tr); - set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); - set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); + set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); } static void wakeup_tracer_start(struct trace_array *tr) -- cgit v1.2.3 From ccb469a198cffac94a7eea0b69f715f06e2ddf15 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 2 Aug 2012 10:32:10 -0400 Subject: tracing: Pass the ftrace_file to the buffer lock reserve code Pass the struct ftrace_event_file *ftrace_file to the trace_event_buffer_lock_reserve() (new function that replaces the trace_current_buffer_lock_reserver()). The ftrace_file holds a pointer to the trace_array that is in use. In the case of multiple buffers with different trace_arrays, this allows different events to be recorded into different buffers. Also fixed some of the stale comments in include/trace/ftrace.h Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 7 +++++++ include/trace/ftrace.h | 9 +++++---- kernel/trace/trace.c | 12 ++++++++++++ 3 files changed, 24 insertions(+), 4 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index c7191d482f98..fd28c170c597 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -128,6 +128,13 @@ enum print_line_t { void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc); +struct ftrace_event_file; + +struct ring_buffer_event * +trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, + struct ftrace_event_file *ftrace_file, + int type, unsigned long len, + unsigned long flags, int pc); struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer, int type, unsigned long len, diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 191d9661e277..e5d140a91fd7 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -414,7 +414,8 @@ static inline notrace int ftrace_get_offsets_##call( \ * * static void ftrace_raw_event_(void *__data, proto) * { - * struct ftrace_event_call *event_call = __data; + * struct ftrace_event_file *ftrace_file = __data; + * struct ftrace_event_call *event_call = ftrace_file->event_call; * struct ftrace_data_offsets_ __maybe_unused __data_offsets; * struct ring_buffer_event *event; * struct ftrace_raw_ *entry; <-- defined in stage 1 @@ -428,7 +429,7 @@ static inline notrace int ftrace_get_offsets_##call( \ * * __data_size = ftrace_get_offsets_(&__data_offsets, args); * - * event = trace_current_buffer_lock_reserve(&buffer, + * event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, * event_->event.type, * sizeof(*entry) + __data_size, * irq_flags, pc); @@ -440,7 +441,7 @@ static inline notrace int ftrace_get_offsets_##call( \ * __array macros. * * if (!filter_current_check_discard(buffer, event_call, entry, event)) - * trace_current_buffer_unlock_commit(buffer, + * trace_nowake_buffer_unlock_commit(buffer, * event, irq_flags, pc); * } * @@ -533,7 +534,7 @@ ftrace_raw_event_##call(void *__data, proto) \ \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ \ - event = trace_current_buffer_lock_reserve(&buffer, \ + event = trace_event_buffer_lock_reserve(&buffer, ftrace_file, \ event_call->event.type, \ sizeof(*entry) + __data_size, \ irq_flags, pc); \ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 91fe40905828..29bff72f97ef 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1293,6 +1293,18 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit); +struct ring_buffer_event * +trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, + struct ftrace_event_file *ftrace_file, + int type, unsigned long len, + unsigned long flags, int pc) +{ + *current_rb = ftrace_file->tr->buffer; + return trace_buffer_lock_reserve(*current_rb, + type, len, flags, pc); +} +EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); + struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, int type, unsigned long len, -- cgit v1.2.3 From a7603ff4b5f7e26e67af82a4c3d05eeeb8d7b160 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 6 Aug 2012 16:24:11 -0400 Subject: tracing: Replace the static global per_cpu arrays with allocated per_cpu The global and max-tr currently use static per_cpu arrays for the CPU data descriptors. But in order to get new allocated trace_arrays, they need to be allocated per_cpu arrays. Instead of using the static arrays, switch the global and max-tr to use allocated data. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 92 +++++++++++++++++++++--------------- kernel/trace/trace.h | 2 +- kernel/trace/trace_branch.c | 6 ++- kernel/trace/trace_functions.c | 4 +- kernel/trace/trace_functions_graph.c | 4 +- kernel/trace/trace_irqsoff.c | 6 +-- kernel/trace/trace_kdb.c | 4 +- kernel/trace/trace_mmiotrace.c | 4 +- kernel/trace/trace_sched_switch.c | 4 +- kernel/trace/trace_sched_wakeup.c | 14 +++--- 10 files changed, 79 insertions(+), 61 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 29bff72f97ef..406adbc277a0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -191,8 +191,6 @@ static struct trace_array global_trace; LIST_HEAD(ftrace_trace_arrays); -static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); - int filter_current_check_discard(struct ring_buffer *buffer, struct ftrace_event_call *call, void *rec, struct ring_buffer_event *event) @@ -227,8 +225,6 @@ cycle_t ftrace_now(int cpu) */ static struct trace_array max_tr; -static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data); - int tracing_is_enabled(void) { return tracing_is_on(); @@ -666,13 +662,13 @@ unsigned long __read_mostly tracing_max_latency; static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct trace_array_cpu *data = tr->data[cpu]; + struct trace_array_cpu *data = per_cpu_ptr(tr->data, cpu); struct trace_array_cpu *max_data; max_tr.cpu = cpu; max_tr.time_start = data->preempt_timestamp; - max_data = max_tr.data[cpu]; + max_data = per_cpu_ptr(max_tr.data, cpu); max_data->saved_latency = tracing_max_latency; max_data->critical_start = data->critical_start; max_data->critical_end = data->critical_end; @@ -1984,7 +1980,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) unsigned long entries = 0; u64 ts; - tr->data[cpu]->skipped_entries = 0; + per_cpu_ptr(tr->data, cpu)->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) @@ -2004,7 +2000,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) ring_buffer_read(buf_iter, NULL); } - tr->data[cpu]->skipped_entries = entries; + per_cpu_ptr(tr->data, cpu)->skipped_entries = entries; } /* @@ -2099,8 +2095,8 @@ get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *e * entries for the trace and we need to ignore the * ones before the time stamp. */ - if (tr->data[cpu]->skipped_entries) { - count -= tr->data[cpu]->skipped_entries; + if (per_cpu_ptr(tr->data, cpu)->skipped_entries) { + count -= per_cpu_ptr(tr->data, cpu)->skipped_entries; /* total is the same as the entries */ *total += count; } else @@ -2157,7 +2153,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); struct trace_array *tr = iter->tr; - struct trace_array_cpu *data = tr->data[tr->cpu]; + struct trace_array_cpu *data = per_cpu_ptr(tr->data, tr->cpu); struct tracer *type = iter->trace; unsigned long entries; unsigned long total; @@ -2227,7 +2223,7 @@ static void test_cpu_buff_start(struct trace_iterator *iter) if (cpumask_test_cpu(iter->cpu, iter->started)) return; - if (iter->tr->data[iter->cpu]->skipped_entries) + if (per_cpu_ptr(iter->tr->data, iter->cpu)->skipped_entries) return; cpumask_set_cpu(iter->cpu, iter->started); @@ -2858,12 +2854,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, */ if (cpumask_test_cpu(cpu, tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_inc(&tr->data[cpu]->disabled); + atomic_inc(&per_cpu_ptr(tr->data, cpu)->disabled); ring_buffer_record_disable_cpu(tr->buffer, cpu); } if (!cpumask_test_cpu(cpu, tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_dec(&tr->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(tr->data, cpu)->disabled); ring_buffer_record_enable_cpu(tr->buffer, cpu); } } @@ -3177,7 +3173,7 @@ static void set_buffer_entries(struct trace_array *tr, unsigned long val) { int cpu; for_each_tracing_cpu(cpu) - tr->data[cpu]->entries = val; + per_cpu_ptr(tr->data, cpu)->entries = val; } /* resize @tr's buffer to the size of @size_tr's entries */ @@ -3189,17 +3185,18 @@ static int resize_buffer_duplicate_size(struct trace_array *tr, if (cpu_id == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { ret = ring_buffer_resize(tr->buffer, - size_tr->data[cpu]->entries, cpu); + per_cpu_ptr(size_tr->data, cpu)->entries, cpu); if (ret < 0) break; - tr->data[cpu]->entries = size_tr->data[cpu]->entries; + per_cpu_ptr(tr->data, cpu)->entries = + per_cpu_ptr(size_tr->data, cpu)->entries; } } else { ret = ring_buffer_resize(tr->buffer, - size_tr->data[cpu_id]->entries, cpu_id); + per_cpu_ptr(size_tr->data, cpu_id)->entries, cpu_id); if (ret == 0) - tr->data[cpu_id]->entries = - size_tr->data[cpu_id]->entries; + per_cpu_ptr(tr->data, cpu_id)->entries = + per_cpu_ptr(size_tr->data, cpu_id)->entries; } return ret; @@ -3256,13 +3253,13 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, if (cpu == RING_BUFFER_ALL_CPUS) set_buffer_entries(&max_tr, size); else - max_tr.data[cpu]->entries = size; + per_cpu_ptr(max_tr.data, cpu)->entries = size; out: if (cpu == RING_BUFFER_ALL_CPUS) set_buffer_entries(tr, size); else - tr->data[cpu]->entries = size; + per_cpu_ptr(tr->data, cpu)->entries = size; return ret; } @@ -3905,8 +3902,8 @@ tracing_entries_read(struct file *filp, char __user *ubuf, for_each_tracing_cpu(cpu) { /* fill in the size from first enabled cpu */ if (size == 0) - size = tr->data[cpu]->entries; - if (size != tr->data[cpu]->entries) { + size = per_cpu_ptr(tr->data, cpu)->entries; + if (size != per_cpu_ptr(tr->data, cpu)->entries) { buf_size_same = 0; break; } @@ -3922,7 +3919,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", tr->data[tc->cpu]->entries >> 10); + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->data, tc->cpu)->entries >> 10); mutex_unlock(&trace_types_lock); @@ -3969,7 +3966,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { - size += tr->data[cpu]->entries >> 10; + size += per_cpu_ptr(tr->data, cpu)->entries >> 10; if (!ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } @@ -4773,7 +4770,7 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) static void tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) { - struct trace_array_cpu *data = tr->data[cpu]; + struct trace_array_cpu *data = per_cpu_ptr(tr->data, cpu); struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ @@ -5298,7 +5295,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { - atomic_inc(&iter.tr->data[cpu]->disabled); + atomic_inc(&per_cpu_ptr(iter.tr->data, cpu)->disabled); } old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ; @@ -5366,7 +5363,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) trace_flags |= old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&iter.tr->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(iter.tr->data, cpu)->disabled); } tracing_on(); } @@ -5422,11 +5419,31 @@ __init static int tracer_alloc_buffers(void) WARN_ON(1); goto out_free_cpumask; } + + global_trace.data = alloc_percpu(struct trace_array_cpu); + + if (!global_trace.data) { + printk(KERN_ERR "tracer: failed to allocate percpu memory!\n"); + WARN_ON(1); + goto out_free_cpumask; + } + + for_each_tracing_cpu(i) { + memset(per_cpu_ptr(global_trace.data, i), 0, sizeof(struct trace_array_cpu)); + per_cpu_ptr(global_trace.data, i)->trace_cpu.cpu = i; + per_cpu_ptr(global_trace.data, i)->trace_cpu.tr = &global_trace; + } + if (global_trace.buffer_disabled) tracing_off(); - #ifdef CONFIG_TRACER_MAX_TRACE + max_tr.data = alloc_percpu(struct trace_array_cpu); + if (!max_tr.data) { + printk(KERN_ERR "tracer: failed to allocate percpu memory!\n"); + WARN_ON(1); + goto out_free_cpumask; + } max_tr.buffer = ring_buffer_alloc(1, rb_flags); raw_spin_lock_init(&max_tr.start_lock); if (!max_tr.buffer) { @@ -5435,18 +5452,15 @@ __init static int tracer_alloc_buffers(void) ring_buffer_free(global_trace.buffer); goto out_free_cpumask; } -#endif - /* Allocate the first page for all buffers */ for_each_tracing_cpu(i) { - global_trace.data[i] = &per_cpu(global_trace_cpu, i); - global_trace.data[i]->trace_cpu.cpu = i; - global_trace.data[i]->trace_cpu.tr = &global_trace; - max_tr.data[i] = &per_cpu(max_tr_data, i); - max_tr.data[i]->trace_cpu.cpu = i; - max_tr.data[i]->trace_cpu.tr = &max_tr; + memset(per_cpu_ptr(max_tr.data, i), 0, sizeof(struct trace_array_cpu)); + per_cpu_ptr(max_tr.data, i)->trace_cpu.cpu = i; + per_cpu_ptr(max_tr.data, i)->trace_cpu.tr = &max_tr; } +#endif + /* Allocate the first page for all buffers */ set_buffer_entries(&global_trace, ring_buffer_size(global_trace.buffer, 0)); #ifdef CONFIG_TRACER_MAX_TRACE @@ -5488,6 +5502,8 @@ __init static int tracer_alloc_buffers(void) return 0; out_free_cpumask: + free_percpu(global_trace.data); + free_percpu(max_tr.data); free_cpumask_var(tracing_cpumask); out_free_buffer_mask: free_cpumask_var(tracing_buffer_mask); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b80fbcf70af4..15ccd7cd1560 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -186,7 +186,7 @@ struct trace_array { struct list_head systems; struct list_head events; struct task_struct *waiter; - struct trace_array_cpu *data[NR_CPUS]; + struct trace_array_cpu *data; }; enum { diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 95e96842ed29..6dadbefbb1d6 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -32,6 +32,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) { struct ftrace_event_call *call = &event_branch; struct trace_array *tr = branch_tracer; + struct trace_array_cpu *data; struct ring_buffer_event *event; struct trace_branch *entry; struct ring_buffer *buffer; @@ -51,7 +52,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) local_irq_save(flags); cpu = raw_smp_processor_id(); - if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) + data = per_cpu_ptr(tr->data, cpu); + if (atomic_inc_return(&data->disabled) != 1) goto out; pc = preempt_count(); @@ -80,7 +82,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) __buffer_unlock_commit(buffer, event); out: - atomic_dec(&tr->data[cpu]->disabled); + atomic_dec(&data->disabled); local_irq_restore(flags); } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 601152523326..9d73861efc6a 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -76,7 +76,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, goto out; cpu = smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->data, cpu); if (!atomic_read(&data->disabled)) { local_save_flags(flags); trace_function(tr, ip, parent_ip, flags, pc); @@ -107,7 +107,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, */ local_irq_save(flags); cpu = raw_smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 39ada66389cc..ca986d61a282 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -265,7 +265,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); @@ -350,7 +350,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = tr->data[cpu]; + data = per_cpu_ptr(tr->data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index b3cf6bf308ef..9b52f9cf7a0d 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -121,7 +121,7 @@ static int func_prolog_dec(struct trace_array *tr, if (!irqs_disabled_flags(*flags)) return 0; - *data = tr->data[cpu]; + *data = per_cpu_ptr(tr->data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (likely(disabled == 1)) @@ -380,7 +380,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip) if (per_cpu(tracing_cpu, cpu)) return; - data = tr->data[cpu]; + data = per_cpu_ptr(tr->data, cpu); if (unlikely(!data) || atomic_read(&data->disabled)) return; @@ -418,7 +418,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip) if (!tracer_enabled) return; - data = tr->data[cpu]; + data = per_cpu_ptr(tr->data, cpu); if (unlikely(!data) || !data->critical_start || atomic_read(&data->disabled)) diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index cc1dbdc5ee5d..349f6941e8f2 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -26,7 +26,7 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { - atomic_inc(&iter.tr->data[cpu]->disabled); + atomic_inc(&per_cpu_ptr(iter.tr->data, cpu)->disabled); } old_userobj = trace_flags; @@ -83,7 +83,7 @@ out: trace_flags = old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&iter.tr->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(iter.tr->data, cpu)->disabled); } for_each_tracing_cpu(cpu) diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index fd3c8aae55e5..2472f6f76b50 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -330,7 +330,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, void mmio_trace_rw(struct mmiotrace_rw *rw) { struct trace_array *tr = mmio_trace_array; - struct trace_array_cpu *data = tr->data[smp_processor_id()]; + struct trace_array_cpu *data = per_cpu_ptr(tr->data, smp_processor_id()); __trace_mmiotrace_rw(tr, data, rw); } @@ -363,7 +363,7 @@ void mmio_trace_mapping(struct mmiotrace_map *map) struct trace_array_cpu *data; preempt_disable(); - data = tr->data[smp_processor_id()]; + data = per_cpu_ptr(tr->data, smp_processor_id()); __trace_mmiotrace_map(tr, data, map); preempt_enable(); } diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 3374c792ccd8..1ffe39abd6fc 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -69,7 +69,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n pc = preempt_count(); local_irq_save(flags); cpu = raw_smp_processor_id(); - data = ctx_trace->data[cpu]; + data = per_cpu_ptr(ctx_trace->data, cpu); if (likely(!atomic_read(&data->disabled))) tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc); @@ -123,7 +123,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) pc = preempt_count(); local_irq_save(flags); cpu = raw_smp_processor_id(); - data = ctx_trace->data[cpu]; + data = per_cpu_ptr(ctx_trace->data, cpu); if (likely(!atomic_read(&data->disabled))) tracing_sched_wakeup_trace(ctx_trace, wakee, current, diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 5255a8477247..f9ceb75a95b7 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -89,7 +89,7 @@ func_prolog_preempt_disable(struct trace_array *tr, if (cpu != wakeup_current_cpu) goto out_enable; - *data = tr->data[cpu]; + *data = per_cpu_ptr(tr->data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (unlikely(disabled != 1)) goto out; @@ -353,7 +353,7 @@ probe_wakeup_sched_switch(void *ignore, /* disable local data, not wakeup_cpu data */ cpu = raw_smp_processor_id(); - disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); if (likely(disabled != 1)) goto out; @@ -365,7 +365,7 @@ probe_wakeup_sched_switch(void *ignore, goto out_unlock; /* The task we are waiting for is waking up */ - data = wakeup_trace->data[wakeup_cpu]; + data = per_cpu_ptr(wakeup_trace->data, wakeup_cpu); __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc); tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); @@ -387,7 +387,7 @@ out_unlock: arch_spin_unlock(&wakeup_lock); local_irq_restore(flags); out: - atomic_dec(&wakeup_trace->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); } static void __wakeup_reset(struct trace_array *tr) @@ -435,7 +435,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) return; pc = preempt_count(); - disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); if (unlikely(disabled != 1)) goto out; @@ -458,7 +458,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) local_save_flags(flags); - data = wakeup_trace->data[wakeup_cpu]; + data = per_cpu_ptr(wakeup_trace->data, wakeup_cpu); data->preempt_timestamp = ftrace_now(cpu); tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc); @@ -472,7 +472,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) out_locked: arch_spin_unlock(&wakeup_lock); out: - atomic_dec(&wakeup_trace->data[cpu]->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); } static void start_wakeup_tracer(struct trace_array *tr) -- cgit v1.2.3 From 277ba04461c2746cf935353474c0961161951b68 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 3 Aug 2012 16:10:49 -0400 Subject: tracing: Add interface to allow multiple trace buffers Add the interface ("instances" directory) to add multiple buffers to ftrace. To create a new instance, simply do a mkdir in the instances directory: This will create a directory with the following: # cd instances # mkdir foo # ls foo buffer_size_kb free_buffer trace_clock trace_pipe buffer_total_size_kb set_event trace_marker tracing_enabled events/ trace trace_options tracing_on Currently only events are able to be set, and there isn't a way to delete a buffer when one is created (yet). Note, the i_mutex lock is dropped from the parent "instances" directory during the mkdir operation. As the "instances" directory can not be renamed or deleted (created on boot), I do not see any harm in dropping the lock. The creation of the sub directories is protected by trace_types_lock mutex, which only lets one instance get into the code path at a time. If two tasks try to create or delete directories of the same name, only one will occur and the other will fail with -EEXIST. Cc: Al Viro Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 129 ++++++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace.h | 2 + kernel/trace/trace_events.c | 12 ++++- 3 files changed, 142 insertions(+), 1 deletion(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 406adbc277a0..07a63114d938 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5107,6 +5107,133 @@ static const struct file_operations rb_simple_fops = { .llseek = default_llseek, }; +struct dentry *trace_instance_dir; + +static void +init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer); + +static int new_instance_create(const char *name) +{ + enum ring_buffer_flags rb_flags; + struct trace_array *tr; + int ret; + int i; + + mutex_lock(&trace_types_lock); + + ret = -EEXIST; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) + goto out_unlock; + } + + ret = -ENOMEM; + tr = kzalloc(sizeof(*tr), GFP_KERNEL); + if (!tr) + goto out_unlock; + + tr->name = kstrdup(name, GFP_KERNEL); + if (!tr->name) + goto out_free_tr; + + raw_spin_lock_init(&tr->start_lock); + + tr->current_trace = &nop_trace; + + INIT_LIST_HEAD(&tr->systems); + INIT_LIST_HEAD(&tr->events); + + rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; + + tr->buffer = ring_buffer_alloc(trace_buf_size, rb_flags); + if (!tr->buffer) + goto out_free_tr; + + tr->data = alloc_percpu(struct trace_array_cpu); + if (!tr->data) + goto out_free_tr; + + for_each_tracing_cpu(i) { + memset(per_cpu_ptr(tr->data, i), 0, sizeof(struct trace_array_cpu)); + per_cpu_ptr(tr->data, i)->trace_cpu.cpu = i; + per_cpu_ptr(tr->data, i)->trace_cpu.tr = tr; + } + + /* Holder for file callbacks */ + tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS; + tr->trace_cpu.tr = tr; + + tr->dir = debugfs_create_dir(name, trace_instance_dir); + if (!tr->dir) + goto out_free_tr; + + ret = event_trace_add_tracer(tr->dir, tr); + if (ret) + goto out_free_tr; + + init_tracer_debugfs(tr, tr->dir); + + list_add(&tr->list, &ftrace_trace_arrays); + + mutex_unlock(&trace_types_lock); + + return 0; + + out_free_tr: + if (tr->buffer) + ring_buffer_free(tr->buffer); + kfree(tr->name); + kfree(tr); + + out_unlock: + mutex_unlock(&trace_types_lock); + + return ret; + +} + +static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode) +{ + struct dentry *parent; + int ret; + + /* Paranoid: Make sure the parent is the "instances" directory */ + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + if (WARN_ON_ONCE(parent != trace_instance_dir)) + return -ENOENT; + + /* + * The inode mutex is locked, but debugfs_create_dir() will also + * take the mutex. As the instances directory can not be destroyed + * or changed in any other way, it is safe to unlock it, and + * let the dentry try. If two users try to make the same dir at + * the same time, then the new_instance_create() will determine the + * winner. + */ + mutex_unlock(&inode->i_mutex); + + ret = new_instance_create(dentry->d_iname); + + mutex_lock(&inode->i_mutex); + + return ret; +} + +static const struct inode_operations instance_dir_inode_operations = { + .lookup = simple_lookup, + .mkdir = instance_mkdir, +}; + +static __init void create_trace_instances(struct dentry *d_tracer) +{ + trace_instance_dir = debugfs_create_dir("instances", d_tracer); + if (WARN_ON(!trace_instance_dir)) + return; + + /* Hijack the dir inode operations, to allow mkdir */ + trace_instance_dir->d_inode->i_op = &instance_dir_inode_operations; +} + static void init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) { @@ -5183,6 +5310,8 @@ static __init int tracer_init_debugfs(void) (void *)&global_trace.trace_cpu, &snapshot_fops); #endif + create_trace_instances(d_tracer); + create_trace_options_dir(&global_trace); for_each_tracing_cpu(cpu) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 68cad7a9e089..883fe0b62f0a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -175,6 +175,7 @@ struct tracer; struct trace_array { struct ring_buffer *buffer; struct list_head list; + char *name; int cpu; int buffer_disabled; struct trace_cpu trace_cpu; /* place holder */ @@ -999,6 +1000,7 @@ filter_check_discard(struct ftrace_event_call *call, void *rec, } extern void trace_event_enable_cmd_record(bool enable); +extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern struct mutex event_mutex; extern struct list_head ftrace_events; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 439955239bae..58a61302a733 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1754,16 +1754,22 @@ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) struct dentry *d_events; struct dentry *entry; + mutex_lock(&event_mutex); + entry = debugfs_create_file("set_event", 0644, parent, tr, &ftrace_set_event_fops); if (!entry) { pr_warning("Could not create debugfs 'set_event' entry\n"); + mutex_unlock(&event_mutex); return -ENOMEM; } d_events = debugfs_create_dir("events", parent); - if (!d_events) + if (!d_events) { pr_warning("Could not create debugfs 'events' directory\n"); + mutex_unlock(&event_mutex); + return -ENOMEM; + } /* ring buffer internal formats */ trace_create_file("header_page", 0444, d_events, @@ -1778,7 +1784,11 @@ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) tr, &ftrace_tr_enable_fops); tr->event_dir = d_events; + down_write(&trace_event_mutex); __trace_add_event_dirs(tr); + up_write(&trace_event_mutex); + + mutex_unlock(&event_mutex); return 0; } -- cgit v1.2.3 From 0c8916c34203734d3b05953ebace52d7c2969f16 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 7 Aug 2012 16:14:16 -0400 Subject: tracing: Add rmdir to remove multibuffer instances Add a method to the hijacked dentry descriptor of the "instances" directory to allow for rmdir to remove an instance of a multibuffer. Example: cd /debug/tracing/instances mkdir hello ls hello/ rmdir hello ls Like the mkdir method, the i_mutex is dropped for the instances directory. The instances directory is created at boot up and can not be renamed or removed. The trace_types_lock mutex is used to synchronize adding and removing of instances. I've run several stress tests with different threads trying to create and delete directories of the same name, and it has stood up fine. Cc: Al Viro Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 68 +++++++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace.h | 1 + kernel/trace/trace_events.c | 33 ++++++++++++++++++++++ 3 files changed, 102 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 07a63114d938..ab3df804fa96 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5192,6 +5192,42 @@ static int new_instance_create(const char *name) } +static int instance_delete(const char *name) +{ + struct trace_array *tr; + int found = 0; + int ret; + + mutex_lock(&trace_types_lock); + + ret = -ENODEV; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) { + found = 1; + break; + } + } + if (!found) + goto out_unlock; + + list_del(&tr->list); + + event_trace_del_tracer(tr); + debugfs_remove_recursive(tr->dir); + free_percpu(tr->data); + ring_buffer_free(tr->buffer); + + kfree(tr->name); + kfree(tr); + + ret = 0; + + out_unlock: + mutex_unlock(&trace_types_lock); + + return ret; +} + static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode) { struct dentry *parent; @@ -5219,9 +5255,41 @@ static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t m return ret; } +static int instance_rmdir(struct inode *inode, struct dentry *dentry) +{ + struct dentry *parent; + int ret; + + /* Paranoid: Make sure the parent is the "instances" directory */ + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + if (WARN_ON_ONCE(parent != trace_instance_dir)) + return -ENOENT; + + /* The caller did a dget() on dentry */ + mutex_unlock(&dentry->d_inode->i_mutex); + + /* + * The inode mutex is locked, but debugfs_create_dir() will also + * take the mutex. As the instances directory can not be destroyed + * or changed in any other way, it is safe to unlock it, and + * let the dentry try. If two users try to make the same dir at + * the same time, then the instance_delete() will determine the + * winner. + */ + mutex_unlock(&inode->i_mutex); + + ret = instance_delete(dentry->d_iname); + + mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); + mutex_lock(&dentry->d_inode->i_mutex); + + return ret; +} + static const struct inode_operations instance_dir_inode_operations = { .lookup = simple_lookup, .mkdir = instance_mkdir, + .rmdir = instance_rmdir, }; static __init void create_trace_instances(struct dentry *d_tracer) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 883fe0b62f0a..b825ea2d8c64 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1001,6 +1001,7 @@ filter_check_discard(struct ftrace_event_call *call, void *rec, extern void trace_event_enable_cmd_record(bool enable); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); +extern int event_trace_del_tracer(struct trace_array *tr); extern struct mutex event_mutex; extern struct list_head ftrace_events; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 58a61302a733..06d6bc275221 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1709,6 +1709,20 @@ __trace_add_event_dirs(struct trace_array *tr) } } +/* Remove the event directory structure for a trace directory. */ +static void +__trace_remove_event_dirs(struct trace_array *tr) +{ + struct ftrace_event_file *file, *next; + + list_for_each_entry_safe(file, next, &tr->events, list) { + list_del(&file->list); + debugfs_remove_recursive(file->dir); + remove_subsystem(file->system); + kfree(file); + } +} + static void __add_event_to_tracers(struct ftrace_event_call *call, struct ftrace_module_file_ops *file_ops) @@ -1793,6 +1807,25 @@ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) return 0; } +int event_trace_del_tracer(struct trace_array *tr) +{ + /* Disable any running events */ + __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); + + mutex_lock(&event_mutex); + + down_write(&trace_event_mutex); + __trace_remove_event_dirs(tr); + debugfs_remove_recursive(tr->event_dir); + up_write(&trace_event_mutex); + + tr->event_dir = NULL; + + mutex_unlock(&event_mutex); + + return 0; +} + static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); -- cgit v1.2.3 From 189e5784f6c5e001a84127b83f03bc76a8bfb1ec Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 28 Feb 2013 20:03:06 -0500 Subject: tracing: Do not block on splice if either file or splice NONBLOCK flag is set Currently only the splice NONBLOCK flag is checked to determine if the splice read should block or not. But the file descriptor NONBLOCK flag also needs to be checked. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ab3df804fa96..598a7aa7d0ae 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4593,7 +4593,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { - if (flags & SPLICE_F_NONBLOCK) + if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) ret = -EAGAIN; else ret = 0; -- cgit v1.2.3 From cc60cdc952be09bca5b0bff9fefc7aa6185c3049 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 28 Feb 2013 09:17:16 -0500 Subject: tracing: Fix polling on trace_pipe_raw The trace_pipe_raw never implemented polling and this was casing issues for several utilities. This is now implemented. Blocked reads still are on the TODO list. Reported-by: Mauro Carvalho Chehab Tested-by: Mauro Carvalho Chehab Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 78 ++++++++++++++++++++++++++++++++++------------------ 1 file changed, 51 insertions(+), 27 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 598a7aa7d0ae..4a6e461273a9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3555,10 +3555,8 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) } static unsigned int -tracing_poll_pipe(struct file *filp, poll_table *poll_table) +trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table) { - struct trace_iterator *iter = filp->private_data; - if (trace_flags & TRACE_ITER_BLOCK) { /* * Always select as readable when in blocking mode @@ -3567,6 +3565,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) } else { if (!trace_empty(iter)) return POLLIN | POLLRDNORM; + trace_wakeup_needed = true; poll_wait(filp, &trace_wait, poll_table); if (!trace_empty(iter)) return POLLIN | POLLRDNORM; @@ -3575,6 +3574,14 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) } } +static unsigned int +tracing_poll_pipe(struct file *filp, poll_table *poll_table) +{ + struct trace_iterator *iter = filp->private_data; + + return trace_poll(iter, filp, poll_table); +} + /* * This is a make-shift waitqueue. * A tracer might use this callback on some rare cases: @@ -4362,9 +4369,8 @@ static const struct file_operations snapshot_fops = { #endif /* CONFIG_TRACER_SNAPSHOT */ struct ftrace_buffer_info { - struct trace_array *tr; + struct trace_iterator iter; void *spare; - int cpu; unsigned int read; }; @@ -4381,22 +4387,32 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) if (!info) return -ENOMEM; - info->tr = tr; - info->cpu = tc->cpu; - info->spare = NULL; + info->iter.tr = tr; + info->iter.cpu_file = tc->cpu; + info->spare = NULL; /* Force reading ring buffer for first read */ - info->read = (unsigned int)-1; + info->read = (unsigned int)-1; filp->private_data = info; return nonseekable_open(inode, filp); } +static unsigned int +tracing_buffers_poll(struct file *filp, poll_table *poll_table) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + + return trace_poll(iter, filp, poll_table); +} + static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; ssize_t ret; size_t size; @@ -4404,7 +4420,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return 0; if (!info->spare) - info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu); + info->spare = ring_buffer_alloc_read_page(iter->tr->buffer, iter->cpu_file); if (!info->spare) return -ENOMEM; @@ -4412,12 +4428,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (info->read < PAGE_SIZE) goto read; - trace_access_lock(info->cpu); - ret = ring_buffer_read_page(info->tr->buffer, + trace_access_lock(iter->cpu_file); + ret = ring_buffer_read_page(iter->tr->buffer, &info->spare, count, - info->cpu, 0); - trace_access_unlock(info->cpu); + iter->cpu_file, 0); + trace_access_unlock(iter->cpu_file); if (ret < 0) return 0; @@ -4442,9 +4458,10 @@ read: static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; if (info->spare) - ring_buffer_free_read_page(info->tr->buffer, info->spare); + ring_buffer_free_read_page(iter->tr->buffer, info->spare); kfree(info); return 0; @@ -4511,6 +4528,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, unsigned int flags) { struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; struct partial_page partial_def[PIPE_DEF_BUFFERS]; struct page *pages_def[PIPE_DEF_BUFFERS]; struct splice_pipe_desc spd = { @@ -4541,8 +4559,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, len &= PAGE_MASK; } - trace_access_lock(info->cpu); - entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu); + again: + trace_access_lock(iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->tr->buffer, iter->cpu_file); for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) { struct page *page; @@ -4553,15 +4572,15 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; ref->ref = 1; - ref->buffer = info->tr->buffer; - ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu); + ref->buffer = iter->tr->buffer; + ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (!ref->page) { kfree(ref); break; } r = ring_buffer_read_page(ref->buffer, &ref->page, - len, info->cpu, 1); + len, iter->cpu_file, 1); if (r < 0) { ring_buffer_free_read_page(ref->buffer, ref->page); kfree(ref); @@ -4585,20 +4604,24 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, spd.nr_pages++; *ppos += PAGE_SIZE; - entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu); + entries = ring_buffer_entries_cpu(iter->tr->buffer, iter->cpu_file); } - trace_access_unlock(info->cpu); + trace_access_unlock(iter->cpu_file); spd.nr_pages = i; /* did we read anything? */ if (!spd.nr_pages) { - if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) + if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) { ret = -EAGAIN; - else - ret = 0; - /* TODO: block */ - goto out; + goto out; + } + default_wait_pipe(iter); + if (signal_pending(current)) { + ret = -EINTR; + goto out; + } + goto again; } ret = splice_to_pipe(pipe, &spd); @@ -4610,6 +4633,7 @@ out: static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, + .poll = tracing_buffers_poll, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, .llseek = no_llseek, -- cgit v1.2.3 From b627344fef0c38fa4e3050348e168e46db87c905 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 28 Feb 2013 13:44:11 -0500 Subject: tracing: Fix read blocking on trace_pipe_raw If the ring buffer is empty, a read to trace_pipe_raw wont block. The tracing code has the infrastructure to wake up waiting readers, but the trace_pipe_raw doesn't take advantage of that. When a read is done to trace_pipe_raw without the O_NONBLOCK flag set, have the read block until there's data in the requested buffer. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4a6e461273a9..3ec146c96df4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4389,6 +4389,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) info->iter.tr = tr; info->iter.cpu_file = tc->cpu; + info->iter.trace = tr->current_trace; info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; @@ -4428,18 +4429,29 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (info->read < PAGE_SIZE) goto read; + again: trace_access_lock(iter->cpu_file); ret = ring_buffer_read_page(iter->tr->buffer, &info->spare, count, iter->cpu_file, 0); trace_access_unlock(iter->cpu_file); - if (ret < 0) + + if (ret < 0) { + if (trace_empty(iter)) { + if ((filp->f_flags & O_NONBLOCK)) + return -EAGAIN; + iter->trace->wait_pipe(iter); + if (signal_pending(current)) + return -EINTR; + goto again; + } return 0; + } info->read = 0; -read: + read: size = PAGE_SIZE - info->read; if (size > count) size = count; @@ -4616,7 +4628,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, ret = -EAGAIN; goto out; } - default_wait_pipe(iter); + iter->trace->wait_pipe(iter); if (signal_pending(current)) { ret = -EINTR; goto out; -- cgit v1.2.3 From 15693458c4bc0693fd63a50d60f35b628fcf4e29 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 28 Feb 2013 19:59:17 -0500 Subject: tracing/ring-buffer: Move poll wake ups into ring buffer code Move the logic to wake up on ring buffer data into the ring buffer code itself. This simplifies the tracing code a lot and also has the added benefit that waiters on one of the instance buffers can be woken only when data is added to that instance instead of data added to any instance. Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 6 ++ kernel/trace/ring_buffer.c | 146 ++++++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace.c | 83 ++++--------------------- 3 files changed, 164 insertions(+), 71 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 1342e69542f3..d69cf637a15a 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -4,6 +4,7 @@ #include #include #include +#include struct ring_buffer; struct ring_buffer_iter; @@ -96,6 +97,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +void ring_buffer_wait(struct ring_buffer *buffer, int cpu); +int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, + struct file *filp, poll_table *poll_table); + + #define RING_BUFFER_ALL_CPUS -1 void ring_buffer_free(struct ring_buffer *buffer); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7244acde77b0..56b6ea32d2e7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -442,6 +443,12 @@ int ring_buffer_print_page_header(struct trace_seq *s) return ret; } +struct rb_irq_work { + struct irq_work work; + wait_queue_head_t waiters; + bool waiters_pending; +}; + /* * head_page == tail_page && head == tail then buffer is empty. */ @@ -476,6 +483,8 @@ struct ring_buffer_per_cpu { struct list_head new_pages; /* new pages to add */ struct work_struct update_pages_work; struct completion update_done; + + struct rb_irq_work irq_work; }; struct ring_buffer { @@ -495,6 +504,8 @@ struct ring_buffer { struct notifier_block cpu_notify; #endif u64 (*clock)(void); + + struct rb_irq_work irq_work; }; struct ring_buffer_iter { @@ -506,6 +517,118 @@ struct ring_buffer_iter { u64 read_stamp; }; +/* + * rb_wake_up_waiters - wake up tasks waiting for ring buffer input + * + * Schedules a delayed work to wake up any task that is blocked on the + * ring buffer waiters queue. + */ +static void rb_wake_up_waiters(struct irq_work *work) +{ + struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); + + wake_up_all(&rbwork->waiters); +} + +/** + * ring_buffer_wait - wait for input to the ring buffer + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + */ +void ring_buffer_wait(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + DEFINE_WAIT(wait); + struct rb_irq_work *work; + + /* + * Depending on what the caller is waiting for, either any + * data in any cpu buffer, or a specific buffer, put the + * caller on the appropriate wait queue. + */ + if (cpu == RING_BUFFER_ALL_CPUS) + work = &buffer->irq_work; + else { + cpu_buffer = buffer->buffers[cpu]; + work = &cpu_buffer->irq_work; + } + + + prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + work->waiters_pending = true; + + if ((cpu == RING_BUFFER_ALL_CPUS && ring_buffer_empty(buffer)) || + (cpu != RING_BUFFER_ALL_CPUS && ring_buffer_empty_cpu(buffer, cpu))) + schedule(); + + finish_wait(&work->waiters, &wait); +} + +/** + * ring_buffer_poll_wait - poll on buffer input + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * @filp: the file descriptor + * @poll_table: The poll descriptor + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + * + * Returns POLLIN | POLLRDNORM if data exists in the buffers, + * zero otherwise. + */ +int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, + struct file *filp, poll_table *poll_table) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct rb_irq_work *work; + + if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || + (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) + return POLLIN | POLLRDNORM; + + if (cpu == RING_BUFFER_ALL_CPUS) + work = &buffer->irq_work; + else { + cpu_buffer = buffer->buffers[cpu]; + work = &cpu_buffer->irq_work; + } + + work->waiters_pending = true; + poll_wait(filp, &work->waiters, poll_table); + + if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || + (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) + return POLLIN | POLLRDNORM; + return 0; +} + /* buffer may be either ring_buffer or ring_buffer_per_cpu */ #define RB_WARN_ON(b, cond) \ ({ \ @@ -1061,6 +1184,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler); init_completion(&cpu_buffer->update_done); + init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -1156,6 +1280,8 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, buffer->clock = trace_clock_local; buffer->reader_lock_key = key; + init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters); + /* need at least two pages */ if (nr_pages < 2) nr_pages = 2; @@ -2610,6 +2736,22 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, rb_end_commit(cpu_buffer); } +static __always_inline void +rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) +{ + if (buffer->irq_work.waiters_pending) { + buffer->irq_work.waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&buffer->irq_work.work); + } + + if (cpu_buffer->irq_work.waiters_pending) { + cpu_buffer->irq_work.waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&cpu_buffer->irq_work.work); + } +} + /** * ring_buffer_unlock_commit - commit a reserved * @buffer: The buffer to commit to @@ -2629,6 +2771,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer, rb_commit(cpu_buffer, event); + rb_wakeups(buffer, cpu_buffer); + trace_recursive_unlock(); preempt_enable_notrace(); @@ -2801,6 +2945,8 @@ int ring_buffer_write(struct ring_buffer *buffer, rb_commit(cpu_buffer, event); + rb_wakeups(buffer, cpu_buffer); + ret = 0; out: preempt_enable_notrace(); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3ec146c96df4..b5b25b6575a9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -86,14 +85,6 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set) */ static DEFINE_PER_CPU(bool, trace_cmdline_save); -/* - * When a reader is waiting for data, then this variable is - * set to true. - */ -static bool trace_wakeup_needed; - -static struct irq_work trace_work_wakeup; - /* * Kill all tracing for good (never come back). * It is initialized to 1 but will turn to zero if the initialization @@ -334,28 +325,12 @@ static inline void trace_access_lock_init(void) #endif -/* trace_wait is a waitqueue for tasks blocked on trace_poll */ -static DECLARE_WAIT_QUEUE_HEAD(trace_wait); - /* trace_flags holds trace_options default values */ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; -/** - * trace_wake_up - wake up tasks waiting for trace input - * - * Schedules a delayed work to wake up any task that is blocked on the - * trace_wait queue. These is used with trace_poll for tasks polling the - * trace. - */ -static void trace_wake_up(struct irq_work *work) -{ - wake_up_all(&trace_wait); - -} - /** * tracing_on - enable tracing buffers * @@ -763,36 +738,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) static void default_wait_pipe(struct trace_iterator *iter) { - DEFINE_WAIT(wait); - - prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE); - - /* - * The events can happen in critical sections where - * checking a work queue can cause deadlocks. - * After adding a task to the queue, this flag is set - * only to notify events to try to wake up the queue - * using irq_work. - * - * We don't clear it even if the buffer is no longer - * empty. The flag only causes the next event to run - * irq_work to do the work queue wake up. The worse - * that can happen if we race with !trace_empty() is that - * an event will cause an irq_work to try to wake up - * an empty queue. - * - * There's no reason to protect this flag either, as - * the work queue and irq_work logic will do the necessary - * synchronization for the wake ups. The only thing - * that is necessary is that the wake up happens after - * a task has been queued. It's OK for spurious wake ups. - */ - trace_wakeup_needed = true; - - if (trace_empty(iter)) - schedule(); + /* Iterators are static, they should be filled or empty */ + if (trace_buffer_iter(iter, iter->cpu_file)) + return; - finish_wait(&trace_wait, &wait); + ring_buffer_wait(iter->tr->buffer, iter->cpu_file); } /** @@ -1262,11 +1212,6 @@ void __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) { __this_cpu_write(trace_cmdline_save, true); - if (trace_wakeup_needed) { - trace_wakeup_needed = false; - /* irq_work_queue() supplies it's own memory barriers */ - irq_work_queue(&trace_work_wakeup); - } ring_buffer_unlock_commit(buffer, event); } @@ -3557,21 +3502,18 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) static unsigned int trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table) { - if (trace_flags & TRACE_ITER_BLOCK) { + /* Iterators are static, they should be filled or empty */ + if (trace_buffer_iter(iter, iter->cpu_file)) + return POLLIN | POLLRDNORM; + + if (trace_flags & TRACE_ITER_BLOCK) /* * Always select as readable when in blocking mode */ return POLLIN | POLLRDNORM; - } else { - if (!trace_empty(iter)) - return POLLIN | POLLRDNORM; - trace_wakeup_needed = true; - poll_wait(filp, &trace_wait, poll_table); - if (!trace_empty(iter)) - return POLLIN | POLLRDNORM; - - return 0; - } + else + return ring_buffer_poll_wait(iter->tr->buffer, iter->cpu_file, + filp, poll_table); } static unsigned int @@ -5701,7 +5643,6 @@ __init static int tracer_alloc_buffers(void) #endif trace_init_cmdlines(); - init_irq_work(&trace_work_wakeup, trace_wake_up); register_tracer(&nop_trace); -- cgit v1.2.3 From 873c642f5964b260480850040dec21e42d0ae4e4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 4 Mar 2013 23:26:06 -0500 Subject: tracing: Clear all trace buffers when unloaded module event was used Currently we do not know what buffer a module event was enabled in. On unload, it is safest to clear all buffer instances, not just the top level buffer. Todo: Clear only the buffer that the event was used in. The infrastructure is there to do this, but it makes the code a bit more complex. Lets get the current code vetted before we add that. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 10 ++++++++-- kernel/trace/trace.h | 2 +- kernel/trace/trace_events.c | 10 +++++++--- 3 files changed, 16 insertions(+), 6 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b5b25b6575a9..c8a852a55db4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -912,9 +912,15 @@ void tracing_reset_current(int cpu) tracing_reset(&global_trace, cpu); } -void tracing_reset_current_online_cpus(void) +void tracing_reset_all_online_cpus(void) { - tracing_reset_online_cpus(&global_trace); + struct trace_array *tr; + + mutex_lock(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + tracing_reset_online_cpus(tr); + } + mutex_unlock(&trace_types_lock); } #define SAVED_CMDLINES 128 diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6728a249e817..fa60b2977524 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -496,7 +496,7 @@ int tracing_is_enabled(void); void tracing_reset(struct trace_array *tr, int cpu); void tracing_reset_online_cpus(struct trace_array *tr); void tracing_reset_current(int cpu); -void tracing_reset_current_online_cpus(void); +void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); struct dentry *trace_create_file(const char *name, umode_t mode, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9a7dc4bf1171..a376ab5eec5c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1649,14 +1649,18 @@ static void trace_module_remove_events(struct module *mod) list_del(&file_ops->list); kfree(file_ops); } + up_write(&trace_event_mutex); /* * It is safest to reset the ring buffer if the module being unloaded - * registered any events that were used. + * registered any events that were used. The only worry is if + * a new module gets loaded, and takes on the same id as the events + * of this module. When printing out the buffer, traced events left + * over from this module may be passed to the new module events and + * unexpected results may occur. */ if (clear_trace) - tracing_reset_current_online_cpus(); - up_write(&trace_event_mutex); + tracing_reset_all_online_cpus(); } static int trace_module_notify(struct notifier_block *self, -- cgit v1.2.3 From 12883efb670c28dff57dcd7f4f995a1ffe153b2d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 09:24:35 -0500 Subject: tracing: Consolidate max_tr into main trace_array structure Currently, the way the latency tracers and snapshot feature works is to have a separate trace_array called "max_tr" that holds the snapshot buffer. For latency tracers, this snapshot buffer is used to swap the running buffer with this buffer to save the current max latency. The only items needed for the max_tr is really just a copy of the buffer itself, the per_cpu data pointers, the time_start timestamp that states when the max latency was triggered, and the cpu that the max latency was triggered on. All other fields in trace_array are unused by the max_tr, making the max_tr mostly bloat. This change removes the max_tr completely, and adds a new structure called trace_buffer, that holds the buffer pointer, the per_cpu data pointers, the time_start timestamp, and the cpu where the latency occurred. The trace_array, now has two trace_buffers, one for the normal trace and one for the max trace or snapshot. By doing this, not only do we remove the bloat from the max_trace but the instances of traces can now use their own snapshot feature and not have just the top level global_trace have the snapshot feature and latency tracers for itself. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 + kernel/trace/blktrace.c | 4 +- kernel/trace/trace.c | 486 +++++++++++++++++++---------------- kernel/trace/trace.h | 37 ++- kernel/trace/trace_functions.c | 8 +- kernel/trace/trace_functions_graph.c | 12 +- kernel/trace/trace_irqsoff.c | 10 +- kernel/trace/trace_kdb.c | 8 +- kernel/trace/trace_mmiotrace.c | 12 +- kernel/trace/trace_output.c | 2 +- kernel/trace/trace_sched_switch.c | 8 +- kernel/trace/trace_sched_wakeup.c | 16 +- kernel/trace/trace_selftest.c | 42 +-- kernel/trace/trace_syscalls.c | 4 +- 14 files changed, 365 insertions(+), 286 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index d6964244e567..d84c4a575514 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -8,6 +8,7 @@ #include struct trace_array; +struct trace_buffer; struct tracer; struct dentry; @@ -67,6 +68,7 @@ struct trace_entry { struct trace_iterator { struct trace_array *tr; struct tracer *trace; + struct trace_buffer *trace_buffer; void *private; int cpu_file; struct mutex mutex; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 71259e2b6b61..90a55054744c 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -72,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, bool blk_tracer = blk_tracer_enabled; if (blk_tracer) { - buffer = blk_tr->buffer; + buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len, @@ -218,7 +218,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, if (blk_tracer) { tracing_record_cmdline(current); - buffer = blk_tr->buffer; + buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c8a852a55db4..a08c127db865 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -195,27 +195,15 @@ cycle_t ftrace_now(int cpu) u64 ts; /* Early boot up does not have a buffer yet */ - if (!global_trace.buffer) + if (!global_trace.trace_buffer.buffer) return trace_clock_local(); - ts = ring_buffer_time_stamp(global_trace.buffer, cpu); - ring_buffer_normalize_time_stamp(global_trace.buffer, cpu, &ts); + ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu); + ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts); return ts; } -/* - * The max_tr is used to snapshot the global_trace when a maximum - * latency is reached. Some tracers will use this to store a maximum - * trace while it continues examining live traces. - * - * The buffers for the max_tr are set up the same as the global_trace. - * When a snapshot is taken, the link list of the max_tr is swapped - * with the link list of the global_trace and the buffers are reset for - * the global_trace so the tracing can continue. - */ -static struct trace_array max_tr; - int tracing_is_enabled(void) { return tracing_is_on(); @@ -339,8 +327,8 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | */ void tracing_on(void) { - if (global_trace.buffer) - ring_buffer_record_on(global_trace.buffer); + if (global_trace.trace_buffer.buffer) + ring_buffer_record_on(global_trace.trace_buffer.buffer); /* * This flag is only looked at when buffers haven't been * allocated yet. We don't really care about the race @@ -361,8 +349,8 @@ EXPORT_SYMBOL_GPL(tracing_on); */ void tracing_off(void) { - if (global_trace.buffer) - ring_buffer_record_off(global_trace.buffer); + if (global_trace.trace_buffer.buffer) + ring_buffer_record_off(global_trace.trace_buffer.buffer); /* * This flag is only looked at when buffers haven't been * allocated yet. We don't really care about the race @@ -378,8 +366,8 @@ EXPORT_SYMBOL_GPL(tracing_off); */ int tracing_is_on(void) { - if (global_trace.buffer) - return ring_buffer_record_is_on(global_trace.buffer); + if (global_trace.trace_buffer.buffer) + return ring_buffer_record_is_on(global_trace.trace_buffer.buffer); return !global_trace.buffer_disabled; } EXPORT_SYMBOL_GPL(tracing_is_on); @@ -637,13 +625,14 @@ unsigned long __read_mostly tracing_max_latency; static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct trace_array_cpu *data = per_cpu_ptr(tr->data, cpu); - struct trace_array_cpu *max_data; + struct trace_buffer *trace_buf = &tr->trace_buffer; + struct trace_buffer *max_buf = &tr->max_buffer; + struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); + struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); - max_tr.cpu = cpu; - max_tr.time_start = data->preempt_timestamp; + max_buf->cpu = cpu; + max_buf->time_start = data->preempt_timestamp; - max_data = per_cpu_ptr(max_tr.data, cpu); max_data->saved_latency = tracing_max_latency; max_data->critical_start = data->critical_start; max_data->critical_end = data->critical_end; @@ -686,9 +675,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&ftrace_max_lock); - buf = tr->buffer; - tr->buffer = max_tr.buffer; - max_tr.buffer = buf; + buf = tr->trace_buffer.buffer; + tr->trace_buffer.buffer = tr->max_buffer.buffer; + tr->max_buffer.buffer = buf; __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&ftrace_max_lock); @@ -716,7 +705,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&ftrace_max_lock); - ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu); + ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu); if (ret == -EBUSY) { /* @@ -725,7 +714,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) * the max trace buffer (no one writes directly to it) * and flag that it failed. */ - trace_array_printk(&max_tr, _THIS_IP_, + trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, "Failed to swap buffers due to commit in progress\n"); } @@ -742,7 +731,7 @@ static void default_wait_pipe(struct trace_iterator *iter) if (trace_buffer_iter(iter, iter->cpu_file)) return; - ring_buffer_wait(iter->tr->buffer, iter->cpu_file); + ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file); } /** @@ -803,17 +792,19 @@ int register_tracer(struct tracer *type) * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); tr->current_trace = type; +#ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { /* If we expanded the buffers, make sure the max is expanded too */ if (ring_buffer_expanded) - ring_buffer_resize(max_tr.buffer, trace_buf_size, + ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, RING_BUFFER_ALL_CPUS); type->allocated_snapshot = true; } +#endif /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); @@ -827,16 +818,18 @@ int register_tracer(struct tracer *type) goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); +#ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { type->allocated_snapshot = false; /* Shrink the max buffer again */ if (ring_buffer_expanded) - ring_buffer_resize(max_tr.buffer, 1, + ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); } +#endif printk(KERN_CONT "PASSED\n"); } @@ -870,9 +863,9 @@ int register_tracer(struct tracer *type) return ret; } -void tracing_reset(struct trace_array *tr, int cpu) +void tracing_reset(struct trace_buffer *buf, int cpu) { - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = buf->buffer; if (!buffer) return; @@ -886,9 +879,9 @@ void tracing_reset(struct trace_array *tr, int cpu) ring_buffer_record_enable(buffer); } -void tracing_reset_online_cpus(struct trace_array *tr) +void tracing_reset_online_cpus(struct trace_buffer *buf) { - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = buf->buffer; int cpu; if (!buffer) @@ -899,7 +892,7 @@ void tracing_reset_online_cpus(struct trace_array *tr) /* Make sure all commits have finished */ synchronize_sched(); - tr->time_start = ftrace_now(tr->cpu); + buf->time_start = ftrace_now(buf->cpu); for_each_online_cpu(cpu) ring_buffer_reset_cpu(buffer, cpu); @@ -909,7 +902,7 @@ void tracing_reset_online_cpus(struct trace_array *tr) void tracing_reset_current(int cpu) { - tracing_reset(&global_trace, cpu); + tracing_reset(&global_trace.trace_buffer, cpu); } void tracing_reset_all_online_cpus(void) @@ -918,7 +911,10 @@ void tracing_reset_all_online_cpus(void) mutex_lock(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); +#ifdef CONFIG_TRACER_MAX_TRACE + tracing_reset_online_cpus(&tr->max_buffer); +#endif } mutex_unlock(&trace_types_lock); } @@ -988,13 +984,15 @@ void tracing_start(void) /* Prevent the buffers from switching */ arch_spin_lock(&ftrace_max_lock); - buffer = global_trace.buffer; + buffer = global_trace.trace_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); - buffer = max_tr.buffer; +#ifdef CONFIG_TRACER_MAX_TRACE + buffer = global_trace.max_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); +#endif arch_spin_unlock(&ftrace_max_lock); @@ -1026,7 +1024,7 @@ static void tracing_start_tr(struct trace_array *tr) goto out; } - buffer = tr->buffer; + buffer = tr->trace_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); @@ -1053,13 +1051,15 @@ void tracing_stop(void) /* Prevent the buffers from switching */ arch_spin_lock(&ftrace_max_lock); - buffer = global_trace.buffer; + buffer = global_trace.trace_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); - buffer = max_tr.buffer; +#ifdef CONFIG_TRACER_MAX_TRACE + buffer = global_trace.max_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); +#endif arch_spin_unlock(&ftrace_max_lock); @@ -1080,7 +1080,7 @@ static void tracing_stop_tr(struct trace_array *tr) if (tr->stop_count++) goto out; - buffer = tr->buffer; + buffer = tr->trace_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); @@ -1246,7 +1246,7 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, int type, unsigned long len, unsigned long flags, int pc) { - *current_rb = ftrace_file->tr->buffer; + *current_rb = ftrace_file->tr->trace_buffer.buffer; return trace_buffer_lock_reserve(*current_rb, type, len, flags, pc); } @@ -1257,7 +1257,7 @@ trace_current_buffer_lock_reserve(struct ring_buffer **current_rb, int type, unsigned long len, unsigned long flags, int pc) { - *current_rb = global_trace.buffer; + *current_rb = global_trace.trace_buffer.buffer; return trace_buffer_lock_reserve(*current_rb, type, len, flags, pc); } @@ -1296,7 +1296,7 @@ trace_function(struct trace_array *tr, int pc) { struct ftrace_event_call *call = &event_function; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; @@ -1437,7 +1437,7 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { - __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL); + __ftrace_trace_stack(tr->trace_buffer.buffer, flags, skip, pc, NULL); } /** @@ -1453,7 +1453,8 @@ void trace_dump_stack(void) local_save_flags(flags); /* skipping 3 traces, seems to get us at the caller of this function */ - __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL); + __ftrace_trace_stack(global_trace.trace_buffer.buffer, flags, 3, + preempt_count(), NULL); } static DEFINE_PER_CPU(int, user_stack_count); @@ -1623,7 +1624,7 @@ void trace_printk_init_buffers(void) * directly here. If the global_trace.buffer is already * allocated here, then this was called by module code. */ - if (global_trace.buffer) + if (global_trace.trace_buffer.buffer) tracing_start_cmdline_record(); } @@ -1683,7 +1684,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) local_save_flags(flags); size = sizeof(*entry) + sizeof(u32) * len; - buffer = tr->buffer; + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, flags, pc); if (!event) @@ -1706,27 +1707,12 @@ out: } EXPORT_SYMBOL_GPL(trace_vbprintk); -int trace_array_printk(struct trace_array *tr, - unsigned long ip, const char *fmt, ...) -{ - int ret; - va_list ap; - - if (!(trace_flags & TRACE_ITER_PRINTK)) - return 0; - - va_start(ap, fmt); - ret = trace_array_vprintk(tr, ip, fmt, ap); - va_end(ap); - return ret; -} - -int trace_array_vprintk(struct trace_array *tr, - unsigned long ip, const char *fmt, va_list args) +static int +__trace_array_vprintk(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, va_list args) { struct ftrace_event_call *call = &event_print; struct ring_buffer_event *event; - struct ring_buffer *buffer; int len = 0, size, pc; struct print_entry *entry; unsigned long flags; @@ -1754,7 +1740,6 @@ int trace_array_vprintk(struct trace_array *tr, local_save_flags(flags); size = sizeof(*entry) + len + 1; - buffer = tr->buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, flags, pc); if (!event) @@ -1775,6 +1760,42 @@ int trace_array_vprintk(struct trace_array *tr, return len; } +int trace_array_vprintk(struct trace_array *tr, + unsigned long ip, const char *fmt, va_list args) +{ + return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args); +} + +int trace_array_printk(struct trace_array *tr, + unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = trace_array_vprintk(tr, ip, fmt, ap); + va_end(ap); + return ret; +} + +int trace_array_printk_buf(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, ...) +{ + int ret; + va_list ap; + + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; + + va_start(ap, fmt); + ret = __trace_array_vprintk(buffer, ip, fmt, ap); + va_end(ap); + return ret; +} + int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { return trace_array_vprintk(&global_trace, ip, fmt, args); @@ -1800,7 +1821,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); else - event = ring_buffer_peek(iter->tr->buffer, cpu, ts, + event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts, lost_events); if (event) { @@ -1815,7 +1836,7 @@ static struct trace_entry * __find_next_entry(struct trace_iterator *iter, int *ent_cpu, unsigned long *missing_events, u64 *ent_ts) { - struct ring_buffer *buffer = iter->tr->buffer; + struct ring_buffer *buffer = iter->trace_buffer->buffer; struct trace_entry *ent, *next = NULL; unsigned long lost_events = 0, next_lost = 0; int cpu_file = iter->cpu_file; @@ -1892,7 +1913,7 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter) static void trace_consume(struct trace_iterator *iter) { - ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts, + ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts, &iter->lost_events); } @@ -1925,13 +1946,12 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) void tracing_iter_reset(struct trace_iterator *iter, int cpu) { - struct trace_array *tr = iter->tr; struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter; unsigned long entries = 0; u64 ts; - per_cpu_ptr(tr->data, cpu)->skipped_entries = 0; + per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) @@ -1945,13 +1965,13 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) * by the timestamp being before the start of the buffer. */ while ((event = ring_buffer_iter_peek(buf_iter, &ts))) { - if (ts >= iter->tr->time_start) + if (ts >= iter->trace_buffer->time_start) break; entries++; ring_buffer_read(buf_iter, NULL); } - per_cpu_ptr(tr->data, cpu)->skipped_entries = entries; + per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries; } /* @@ -1978,8 +1998,10 @@ static void *s_start(struct seq_file *m, loff_t *pos) *iter->trace = *tr->current_trace; mutex_unlock(&trace_types_lock); +#ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return ERR_PTR(-EBUSY); +#endif if (!iter->snapshot) atomic_inc(&trace_record_cmdline_disabled); @@ -2021,17 +2043,21 @@ static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; +#ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return; +#endif if (!iter->snapshot) atomic_dec(&trace_record_cmdline_disabled); + trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } static void -get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *entries) +get_total_entries(struct trace_buffer *buf, + unsigned long *total, unsigned long *entries) { unsigned long count; int cpu; @@ -2040,19 +2066,19 @@ get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *e *entries = 0; for_each_tracing_cpu(cpu) { - count = ring_buffer_entries_cpu(tr->buffer, cpu); + count = ring_buffer_entries_cpu(buf->buffer, cpu); /* * If this buffer has skipped entries, then we hold all * entries for the trace and we need to ignore the * ones before the time stamp. */ - if (per_cpu_ptr(tr->data, cpu)->skipped_entries) { - count -= per_cpu_ptr(tr->data, cpu)->skipped_entries; + if (per_cpu_ptr(buf->data, cpu)->skipped_entries) { + count -= per_cpu_ptr(buf->data, cpu)->skipped_entries; /* total is the same as the entries */ *total += count; } else *total += count + - ring_buffer_overrun_cpu(tr->buffer, cpu); + ring_buffer_overrun_cpu(buf->buffer, cpu); *entries += count; } } @@ -2069,27 +2095,27 @@ static void print_lat_help_header(struct seq_file *m) seq_puts(m, "# \\ / ||||| \\ | / \n"); } -static void print_event_info(struct trace_array *tr, struct seq_file *m) +static void print_event_info(struct trace_buffer *buf, struct seq_file *m) { unsigned long total; unsigned long entries; - get_total_entries(tr, &total, &entries); + get_total_entries(buf, &total, &entries); seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n", entries, total, num_online_cpus()); seq_puts(m, "#\n"); } -static void print_func_help_header(struct trace_array *tr, struct seq_file *m) +static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m) { - print_event_info(tr, m); + print_event_info(buf, m); seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"); seq_puts(m, "# | | | | |\n"); } -static void print_func_help_header_irq(struct trace_array *tr, struct seq_file *m) +static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) { - print_event_info(tr, m); + print_event_info(buf, m); seq_puts(m, "# _-----=> irqs-off\n"); seq_puts(m, "# / _----=> need-resched\n"); seq_puts(m, "# | / _---=> hardirq/softirq\n"); @@ -2103,8 +2129,8 @@ void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); - struct trace_array *tr = iter->tr; - struct trace_array_cpu *data = per_cpu_ptr(tr->data, tr->cpu); + struct trace_buffer *buf = iter->trace_buffer; + struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu); struct tracer *type = iter->trace; unsigned long entries; unsigned long total; @@ -2112,7 +2138,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) name = type->name; - get_total_entries(tr, &total, &entries); + get_total_entries(buf, &total, &entries); seq_printf(m, "# %s latency trace v1.1.5 on %s\n", name, UTS_RELEASE); @@ -2123,7 +2149,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) nsecs_to_usecs(data->saved_latency), entries, total, - tr->cpu, + buf->cpu, #if defined(CONFIG_PREEMPT_NONE) "server", #elif defined(CONFIG_PREEMPT_VOLUNTARY) @@ -2174,7 +2200,7 @@ static void test_cpu_buff_start(struct trace_iterator *iter) if (cpumask_test_cpu(iter->cpu, iter->started)) return; - if (per_cpu_ptr(iter->tr->data, iter->cpu)->skipped_entries) + if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries) return; cpumask_set_cpu(iter->cpu, iter->started); @@ -2304,7 +2330,7 @@ int trace_empty(struct trace_iterator *iter) if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) return 0; } return 1; @@ -2316,7 +2342,7 @@ int trace_empty(struct trace_iterator *iter) if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) return 0; } } @@ -2394,9 +2420,9 @@ void trace_default_header(struct seq_file *m) } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) - print_func_help_header_irq(iter->tr, m); + print_func_help_header_irq(iter->trace_buffer, m); else - print_func_help_header(iter->tr, m); + print_func_help_header(iter->trace_buffer, m); } } } @@ -2515,11 +2541,15 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; + iter->tr = tr; + +#ifdef CONFIG_TRACER_MAX_TRACE /* Currently only the top directory has a snapshot */ if (tr->current_trace->print_max || snapshot) - iter->tr = &max_tr; + iter->trace_buffer = &tr->max_buffer; else - iter->tr = tr; +#endif + iter->trace_buffer = &tr->trace_buffer; iter->snapshot = snapshot; iter->pos = -1; mutex_init(&iter->mutex); @@ -2530,7 +2560,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ - if (ring_buffer_overruns(iter->tr->buffer)) + if (ring_buffer_overruns(iter->trace_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ @@ -2544,7 +2574,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->tr->buffer, cpu); + ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); } ring_buffer_read_prepare_sync(); for_each_tracing_cpu(cpu) { @@ -2554,7 +2584,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->tr->buffer, cpu); + ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu); ring_buffer_read_prepare_sync(); ring_buffer_read_start(iter->buffer_iter[cpu]); tracing_iter_reset(iter, cpu); @@ -2593,12 +2623,7 @@ static int tracing_release(struct inode *inode, struct file *file) return 0; iter = m->private; - - /* Only the global tracer has a matching max_tr */ - if (iter->tr == &max_tr) - tr = &global_trace; - else - tr = iter->tr; + tr = iter->tr; mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { @@ -2634,9 +2659,9 @@ static int tracing_open(struct inode *inode, struct file *file) struct trace_array *tr = tc->tr; if (tc->cpu == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); else - tracing_reset(tr, tc->cpu); + tracing_reset(&tr->trace_buffer, tc->cpu); } if (file->f_mode & FMODE_READ) { @@ -2805,13 +2830,13 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, */ if (cpumask_test_cpu(cpu, tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_inc(&per_cpu_ptr(tr->data, cpu)->disabled); - ring_buffer_record_disable_cpu(tr->buffer, cpu); + atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); + ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu); } if (!cpumask_test_cpu(cpu, tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_dec(&per_cpu_ptr(tr->data, cpu)->disabled); - ring_buffer_record_enable_cpu(tr->buffer, cpu); + atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); + ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu); } } arch_spin_unlock(&ftrace_max_lock); @@ -2930,9 +2955,9 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) trace_event_enable_cmd_record(enabled); if (mask == TRACE_ITER_OVERWRITE) { - ring_buffer_change_overwrite(global_trace.buffer, enabled); + ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE - ring_buffer_change_overwrite(max_tr.buffer, enabled); + ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); #endif } @@ -3116,42 +3141,44 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, int tracer_init(struct tracer *t, struct trace_array *tr) { - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); return t->init(tr); } -static void set_buffer_entries(struct trace_array *tr, unsigned long val) +static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) { int cpu; for_each_tracing_cpu(cpu) - per_cpu_ptr(tr->data, cpu)->entries = val; + per_cpu_ptr(buf->data, cpu)->entries = val; } +#ifdef CONFIG_TRACER_MAX_TRACE /* resize @tr's buffer to the size of @size_tr's entries */ -static int resize_buffer_duplicate_size(struct trace_array *tr, - struct trace_array *size_tr, int cpu_id) +static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, + struct trace_buffer *size_buf, int cpu_id) { int cpu, ret = 0; if (cpu_id == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { - ret = ring_buffer_resize(tr->buffer, - per_cpu_ptr(size_tr->data, cpu)->entries, cpu); + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu)->entries, cpu); if (ret < 0) break; - per_cpu_ptr(tr->data, cpu)->entries = - per_cpu_ptr(size_tr->data, cpu)->entries; + per_cpu_ptr(trace_buf->data, cpu)->entries = + per_cpu_ptr(size_buf->data, cpu)->entries; } } else { - ret = ring_buffer_resize(tr->buffer, - per_cpu_ptr(size_tr->data, cpu_id)->entries, cpu_id); + ret = ring_buffer_resize(trace_buf->buffer, + per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id); if (ret == 0) - per_cpu_ptr(tr->data, cpu_id)->entries = - per_cpu_ptr(size_tr->data, cpu_id)->entries; + per_cpu_ptr(trace_buf->data, cpu_id)->entries = + per_cpu_ptr(size_buf->data, cpu_id)->entries; } return ret; } +#endif /* CONFIG_TRACER_MAX_TRACE */ static int __tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu) @@ -3166,20 +3193,22 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, ring_buffer_expanded = 1; /* May be called before buffers are initialized */ - if (!tr->buffer) + if (!tr->trace_buffer.buffer) return 0; - ret = ring_buffer_resize(tr->buffer, size, cpu); + ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu); if (ret < 0) return ret; +#ifdef CONFIG_TRACER_MAX_TRACE if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || !tr->current_trace->use_max_tr) goto out; - ret = ring_buffer_resize(max_tr.buffer, size, cpu); + ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); if (ret < 0) { - int r = resize_buffer_duplicate_size(tr, tr, cpu); + int r = resize_buffer_duplicate_size(&tr->trace_buffer, + &tr->trace_buffer, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -3202,15 +3231,17 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, } if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(&max_tr, size); + set_buffer_entries(&tr->max_buffer, size); else - per_cpu_ptr(max_tr.data, cpu)->entries = size; + per_cpu_ptr(tr->max_buffer.data, cpu)->entries = size; out: +#endif /* CONFIG_TRACER_MAX_TRACE */ + if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(tr, size); + set_buffer_entries(&tr->trace_buffer, size); else - per_cpu_ptr(tr->data, cpu)->entries = size; + per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size; return ret; } @@ -3277,7 +3308,9 @@ static int tracing_set_tracer(const char *buf) static struct trace_option_dentry *topts; struct trace_array *tr = &global_trace; struct tracer *t; +#ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; +#endif int ret = 0; mutex_lock(&trace_types_lock); @@ -3308,7 +3341,10 @@ static int tracing_set_tracer(const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); +#ifdef CONFIG_TRACER_MAX_TRACE had_max_tr = tr->current_trace->allocated_snapshot; + + /* Current trace needs to be nop_trace before synchronize_sched */ tr->current_trace = &nop_trace; if (had_max_tr && !t->use_max_tr) { @@ -3325,22 +3361,28 @@ static int tracing_set_tracer(const char *buf) * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ - ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); - set_buffer_entries(&max_tr, 1); - tracing_reset_online_cpus(&max_tr); + ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); + set_buffer_entries(&tr->max_buffer, 1); + tracing_reset_online_cpus(&tr->max_buffer); tr->current_trace->allocated_snapshot = false; } +#else + tr->current_trace = &nop_trace; +#endif destroy_trace_option_files(topts); topts = create_trace_option_files(tr, t); + +#ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { /* we need to make per cpu buffer sizes equivalent */ - ret = resize_buffer_duplicate_size(&max_tr, &global_trace, + ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->trace_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) goto out; t->allocated_snapshot = true; } +#endif if (t->init) { ret = tracer_init(t, tr); @@ -3468,6 +3510,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->cpu_file = tc->cpu; iter->tr = tc->tr; + iter->trace_buffer = &tc->tr->trace_buffer; mutex_init(&iter->mutex); filp->private_data = iter; @@ -3518,7 +3561,7 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl */ return POLLIN | POLLRDNORM; else - return ring_buffer_poll_wait(iter->tr->buffer, iter->cpu_file, + return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file, filp, poll_table); } @@ -3857,8 +3900,8 @@ tracing_entries_read(struct file *filp, char __user *ubuf, for_each_tracing_cpu(cpu) { /* fill in the size from first enabled cpu */ if (size == 0) - size = per_cpu_ptr(tr->data, cpu)->entries; - if (size != per_cpu_ptr(tr->data, cpu)->entries) { + size = per_cpu_ptr(tr->trace_buffer.data, cpu)->entries; + if (size != per_cpu_ptr(tr->trace_buffer.data, cpu)->entries) { buf_size_same = 0; break; } @@ -3874,7 +3917,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->data, tc->cpu)->entries >> 10); + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10); mutex_unlock(&trace_types_lock); @@ -3921,7 +3964,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { - size += per_cpu_ptr(tr->data, cpu)->entries >> 10; + size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10; if (!ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } @@ -4026,7 +4069,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, local_save_flags(irq_flags); size = sizeof(*entry) + cnt + 2; /* possible \n added */ - buffer = global_trace.buffer; + buffer = global_trace.trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, irq_flags, preempt_count()); if (!event) { @@ -4111,16 +4154,19 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, tr->clock_id = i; - ring_buffer_set_clock(tr->buffer, trace_clocks[i].func); - if (tr->flags & TRACE_ARRAY_FL_GLOBAL && max_tr.buffer) - ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func); + ring_buffer_set_clock(tr->trace_buffer.buffer, trace_clocks[i].func); /* * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ - tracing_reset_online_cpus(&global_trace); - tracing_reset_online_cpus(&max_tr); + tracing_reset_online_cpus(&global_trace.trace_buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) + ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); + tracing_reset_online_cpus(&global_trace.max_buffer); +#endif mutex_unlock(&trace_types_lock); @@ -4160,6 +4206,7 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) return -ENOMEM; } iter->tr = tc->tr; + iter->trace_buffer = &tc->tr->max_buffer; m->private = iter; file->private_data = m; } @@ -4196,18 +4243,18 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, case 0: if (tr->current_trace->allocated_snapshot) { /* free spare buffer */ - ring_buffer_resize(max_tr.buffer, 1, + ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); - set_buffer_entries(&max_tr, 1); - tracing_reset_online_cpus(&max_tr); + set_buffer_entries(&tr->max_buffer, 1); + tracing_reset_online_cpus(&tr->max_buffer); tr->current_trace->allocated_snapshot = false; } break; case 1: if (!tr->current_trace->allocated_snapshot) { /* allocate spare buffer */ - ret = resize_buffer_duplicate_size(&max_tr, - &global_trace, RING_BUFFER_ALL_CPUS); + ret = resize_buffer_duplicate_size(&tr->max_buffer, + &tr->trace_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) break; tr->current_trace->allocated_snapshot = true; @@ -4220,7 +4267,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, break; default: if (tr->current_trace->allocated_snapshot) - tracing_reset_online_cpus(&max_tr); + tracing_reset_online_cpus(&tr->max_buffer); break; } @@ -4338,6 +4385,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) info->iter.tr = tr; info->iter.cpu_file = tc->cpu; info->iter.trace = tr->current_trace; + info->iter.trace_buffer = &tr->trace_buffer; info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; @@ -4369,7 +4417,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return 0; if (!info->spare) - info->spare = ring_buffer_alloc_read_page(iter->tr->buffer, iter->cpu_file); + info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, + iter->cpu_file); if (!info->spare) return -ENOMEM; @@ -4379,7 +4428,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, again: trace_access_lock(iter->cpu_file); - ret = ring_buffer_read_page(iter->tr->buffer, + ret = ring_buffer_read_page(iter->trace_buffer->buffer, &info->spare, count, iter->cpu_file, 0); @@ -4421,7 +4470,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) struct trace_iterator *iter = &info->iter; if (info->spare) - ring_buffer_free_read_page(iter->tr->buffer, info->spare); + ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare); kfree(info); return 0; @@ -4521,7 +4570,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, again: trace_access_lock(iter->cpu_file); - entries = ring_buffer_entries_cpu(iter->tr->buffer, iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) { struct page *page; @@ -4532,7 +4581,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; ref->ref = 1; - ref->buffer = iter->tr->buffer; + ref->buffer = iter->trace_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (!ref->page) { kfree(ref); @@ -4564,7 +4613,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, spd.nr_pages++; *ppos += PAGE_SIZE; - entries = ring_buffer_entries_cpu(iter->tr->buffer, iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); } trace_access_unlock(iter->cpu_file); @@ -4605,6 +4654,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, { struct trace_cpu *tc = filp->private_data; struct trace_array *tr = tc->tr; + struct trace_buffer *trace_buf = &tr->trace_buffer; struct trace_seq *s; unsigned long cnt; unsigned long long t; @@ -4617,41 +4667,41 @@ tracing_stats_read(struct file *filp, char __user *ubuf, trace_seq_init(s); - cnt = ring_buffer_entries_cpu(tr->buffer, cpu); + cnt = ring_buffer_entries_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "entries: %ld\n", cnt); - cnt = ring_buffer_overrun_cpu(tr->buffer, cpu); + cnt = ring_buffer_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "overrun: %ld\n", cnt); - cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu); + cnt = ring_buffer_commit_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "commit overrun: %ld\n", cnt); - cnt = ring_buffer_bytes_cpu(tr->buffer, cpu); + cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); if (trace_clocks[trace_clock_id].in_ns) { /* local or global for trace_clock */ - t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu)); + t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); - t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu)); + t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); } else { /* counter or tsc mode for trace_clock */ trace_seq_printf(s, "oldest event ts: %llu\n", - ring_buffer_oldest_event_ts(tr->buffer, cpu)); + ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); trace_seq_printf(s, "now ts: %llu\n", - ring_buffer_time_stamp(tr->buffer, cpu)); + ring_buffer_time_stamp(trace_buf->buffer, cpu)); } - cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu); + cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "dropped events: %ld\n", cnt); - cnt = ring_buffer_read_events_cpu(tr->buffer, cpu); + cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "read events: %ld\n", cnt); count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); @@ -4754,7 +4804,7 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) static void tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) { - struct trace_array_cpu *data = per_cpu_ptr(tr->data, cpu); + struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu); struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ @@ -5038,7 +5088,7 @@ rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; char buf[64]; int r; @@ -5057,7 +5107,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; unsigned long val; int ret; @@ -5129,18 +5179,18 @@ static int new_instance_create(const char *name) rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; - tr->buffer = ring_buffer_alloc(trace_buf_size, rb_flags); - if (!tr->buffer) + tr->trace_buffer.buffer = ring_buffer_alloc(trace_buf_size, rb_flags); + if (!tr->trace_buffer.buffer) goto out_free_tr; - tr->data = alloc_percpu(struct trace_array_cpu); - if (!tr->data) + tr->trace_buffer.data = alloc_percpu(struct trace_array_cpu); + if (!tr->trace_buffer.data) goto out_free_tr; for_each_tracing_cpu(i) { - memset(per_cpu_ptr(tr->data, i), 0, sizeof(struct trace_array_cpu)); - per_cpu_ptr(tr->data, i)->trace_cpu.cpu = i; - per_cpu_ptr(tr->data, i)->trace_cpu.tr = tr; + memset(per_cpu_ptr(tr->trace_buffer.data, i), 0, sizeof(struct trace_array_cpu)); + per_cpu_ptr(tr->trace_buffer.data, i)->trace_cpu.cpu = i; + per_cpu_ptr(tr->trace_buffer.data, i)->trace_cpu.tr = tr; } /* Holder for file callbacks */ @@ -5164,8 +5214,8 @@ static int new_instance_create(const char *name) return 0; out_free_tr: - if (tr->buffer) - ring_buffer_free(tr->buffer); + if (tr->trace_buffer.buffer) + ring_buffer_free(tr->trace_buffer.buffer); kfree(tr->name); kfree(tr); @@ -5198,8 +5248,8 @@ static int instance_delete(const char *name) event_trace_del_tracer(tr); debugfs_remove_recursive(tr->dir); - free_percpu(tr->data); - ring_buffer_free(tr->buffer); + free_percpu(tr->trace_buffer.data); + ring_buffer_free(tr->trace_buffer.buffer); kfree(tr->name); kfree(tr); @@ -5439,6 +5489,7 @@ void trace_init_global_iter(struct trace_iterator *iter) iter->tr = &global_trace; iter->trace = iter->tr->current_trace; iter->cpu_file = RING_BUFFER_ALL_CPUS; + iter->trace_buffer = &global_trace.trace_buffer; } static void @@ -5476,7 +5527,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { - atomic_inc(&per_cpu_ptr(iter.tr->data, cpu)->disabled); + atomic_inc(&per_cpu_ptr(iter.tr->trace_buffer.data, cpu)->disabled); } old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ; @@ -5544,7 +5595,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) trace_flags |= old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&per_cpu_ptr(iter.tr->data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } tracing_on(); } @@ -5594,58 +5645,59 @@ __init static int tracer_alloc_buffers(void) raw_spin_lock_init(&global_trace.start_lock); /* TODO: make the number of buffers hot pluggable with CPUS */ - global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags); - if (!global_trace.buffer) { + global_trace.trace_buffer.buffer = ring_buffer_alloc(ring_buf_size, rb_flags); + if (!global_trace.trace_buffer.buffer) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); WARN_ON(1); goto out_free_cpumask; } - global_trace.data = alloc_percpu(struct trace_array_cpu); + global_trace.trace_buffer.data = alloc_percpu(struct trace_array_cpu); - if (!global_trace.data) { + if (!global_trace.trace_buffer.data) { printk(KERN_ERR "tracer: failed to allocate percpu memory!\n"); WARN_ON(1); goto out_free_cpumask; } for_each_tracing_cpu(i) { - memset(per_cpu_ptr(global_trace.data, i), 0, sizeof(struct trace_array_cpu)); - per_cpu_ptr(global_trace.data, i)->trace_cpu.cpu = i; - per_cpu_ptr(global_trace.data, i)->trace_cpu.tr = &global_trace; + memset(per_cpu_ptr(global_trace.trace_buffer.data, i), 0, + sizeof(struct trace_array_cpu)); + per_cpu_ptr(global_trace.trace_buffer.data, i)->trace_cpu.cpu = i; + per_cpu_ptr(global_trace.trace_buffer.data, i)->trace_cpu.tr = &global_trace; } if (global_trace.buffer_disabled) tracing_off(); #ifdef CONFIG_TRACER_MAX_TRACE - max_tr.data = alloc_percpu(struct trace_array_cpu); - if (!max_tr.data) { + global_trace.max_buffer.data = alloc_percpu(struct trace_array_cpu); + if (!global_trace.max_buffer.data) { printk(KERN_ERR "tracer: failed to allocate percpu memory!\n"); WARN_ON(1); goto out_free_cpumask; } - max_tr.buffer = ring_buffer_alloc(1, rb_flags); - raw_spin_lock_init(&max_tr.start_lock); - if (!max_tr.buffer) { + global_trace.max_buffer.buffer = ring_buffer_alloc(1, rb_flags); + if (!global_trace.max_buffer.buffer) { printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); WARN_ON(1); - ring_buffer_free(global_trace.buffer); + ring_buffer_free(global_trace.trace_buffer.buffer); goto out_free_cpumask; } for_each_tracing_cpu(i) { - memset(per_cpu_ptr(max_tr.data, i), 0, sizeof(struct trace_array_cpu)); - per_cpu_ptr(max_tr.data, i)->trace_cpu.cpu = i; - per_cpu_ptr(max_tr.data, i)->trace_cpu.tr = &max_tr; + memset(per_cpu_ptr(global_trace.max_buffer.data, i), 0, + sizeof(struct trace_array_cpu)); + per_cpu_ptr(global_trace.max_buffer.data, i)->trace_cpu.cpu = i; + per_cpu_ptr(global_trace.max_buffer.data, i)->trace_cpu.tr = &global_trace; } #endif /* Allocate the first page for all buffers */ - set_buffer_entries(&global_trace, - ring_buffer_size(global_trace.buffer, 0)); + set_buffer_entries(&global_trace.trace_buffer, + ring_buffer_size(global_trace.trace_buffer.buffer, 0)); #ifdef CONFIG_TRACER_MAX_TRACE - set_buffer_entries(&max_tr, 1); + set_buffer_entries(&global_trace.max_buffer, 1); #endif trace_init_cmdlines(); @@ -5682,8 +5734,10 @@ __init static int tracer_alloc_buffers(void) return 0; out_free_cpumask: - free_percpu(global_trace.data); - free_percpu(max_tr.data); + free_percpu(global_trace.trace_buffer.data); +#ifdef CONFIG_TRACER_MAX_TRACE + free_percpu(global_trace.max_buffer.data); +#endif free_cpumask_var(tracing_cpumask); out_free_buffer_mask: free_cpumask_var(tracing_buffer_mask); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index fa60b2977524..986834f1f4dd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -167,16 +167,37 @@ struct trace_array_cpu { struct tracer; +struct trace_buffer { + struct trace_array *tr; + struct ring_buffer *buffer; + struct trace_array_cpu __percpu *data; + cycle_t time_start; + int cpu; +}; + /* * The trace array - an array of per-CPU trace arrays. This is the * highest level data structure that individual tracers deal with. * They have on/off state as well: */ struct trace_array { - struct ring_buffer *buffer; struct list_head list; char *name; - int cpu; + struct trace_buffer trace_buffer; +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * The max_buffer is used to snapshot the trace when a maximum + * latency is reached, or when the user initiates a snapshot. + * Some tracers will use this to store a maximum trace while + * it continues examining live traces. + * + * The buffers for the max_buffer are set up the same as the trace_buffer + * When a snapshot is taken, the buffer of the max_buffer is swapped + * with the buffer of the trace_buffer and the buffers are reset for + * the trace_buffer so the tracing can continue. + */ + struct trace_buffer max_buffer; +#endif int buffer_disabled; struct trace_cpu trace_cpu; /* place holder */ #ifdef CONFIG_FTRACE_SYSCALLS @@ -189,7 +210,6 @@ struct trace_array { int clock_id; struct tracer *current_trace; unsigned int flags; - cycle_t time_start; raw_spinlock_t start_lock; struct dentry *dir; struct dentry *options; @@ -198,7 +218,6 @@ struct trace_array { struct list_head systems; struct list_head events; struct task_struct *waiter; - struct trace_array_cpu __percpu *data; }; enum { @@ -345,9 +364,11 @@ struct tracer { struct tracer *next; struct tracer_flags *flags; bool print_max; + bool enabled; +#ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; bool allocated_snapshot; - bool enabled; +#endif }; @@ -493,8 +514,8 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu) int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); -void tracing_reset(struct trace_array *tr, int cpu); -void tracing_reset_online_cpus(struct trace_array *tr); +void tracing_reset(struct trace_buffer *buf, int cpu); +void tracing_reset_online_cpus(struct trace_buffer *buf); void tracing_reset_current(int cpu); void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); @@ -674,6 +695,8 @@ trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args); int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...); +int trace_array_printk_buf(struct ring_buffer *buffer, + unsigned long ip, const char *fmt, ...); void trace_printk_seq(struct trace_seq *s); enum print_line_t print_trace_line(struct trace_iterator *iter); diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 9d73861efc6a..e467c0c7bdd5 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -28,7 +28,7 @@ static void tracing_stop_function_trace(void); static int function_trace_init(struct trace_array *tr) { func_trace = tr; - tr->cpu = get_cpu(); + tr->trace_buffer.cpu = get_cpu(); put_cpu(); tracing_start_cmdline_record(); @@ -44,7 +44,7 @@ static void function_trace_reset(struct trace_array *tr) static void function_trace_start(struct trace_array *tr) { - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); } /* Our option */ @@ -76,7 +76,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, goto out; cpu = smp_processor_id(); - data = per_cpu_ptr(tr->data, cpu); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); if (!atomic_read(&data->disabled)) { local_save_flags(flags); trace_function(tr, ip, parent_ip, flags, pc); @@ -107,7 +107,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, */ local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->data, cpu); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index ca986d61a282..8388bc99f2ee 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -218,7 +218,7 @@ int __trace_graph_entry(struct trace_array *tr, { struct ftrace_event_call *call = &event_funcgraph_entry; struct ring_buffer_event *event; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ent_entry *entry; if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) @@ -265,7 +265,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->data, cpu); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); @@ -323,7 +323,7 @@ void __trace_graph_return(struct trace_array *tr, { struct ftrace_event_call *call = &event_funcgraph_exit; struct ring_buffer_event *event; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ret_entry *entry; if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) @@ -350,7 +350,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->data, cpu); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); @@ -560,9 +560,9 @@ get_return_for_leaf(struct trace_iterator *iter, * We need to consume the current entry to see * the next one. */ - ring_buffer_consume(iter->tr->buffer, iter->cpu, + ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, NULL, NULL); - event = ring_buffer_peek(iter->tr->buffer, iter->cpu, + event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu, NULL, NULL); } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 9b52f9cf7a0d..5aa40ab72b57 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -121,7 +121,7 @@ static int func_prolog_dec(struct trace_array *tr, if (!irqs_disabled_flags(*flags)) return 0; - *data = per_cpu_ptr(tr->data, cpu); + *data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (likely(disabled == 1)) @@ -175,7 +175,7 @@ static int irqsoff_set_flag(u32 old_flags, u32 bit, int set) per_cpu(tracing_cpu, cpu) = 0; tracing_max_latency = 0; - tracing_reset_online_cpus(irqsoff_trace); + tracing_reset_online_cpus(&irqsoff_trace->trace_buffer); return start_irqsoff_tracer(irqsoff_trace, set); } @@ -380,7 +380,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip) if (per_cpu(tracing_cpu, cpu)) return; - data = per_cpu_ptr(tr->data, cpu); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); if (unlikely(!data) || atomic_read(&data->disabled)) return; @@ -418,7 +418,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip) if (!tracer_enabled) return; - data = per_cpu_ptr(tr->data, cpu); + data = per_cpu_ptr(tr->trace_buffer.data, cpu); if (unlikely(!data) || !data->critical_start || atomic_read(&data->disabled)) @@ -568,7 +568,7 @@ static void __irqsoff_tracer_init(struct trace_array *tr) irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); if (start_irqsoff_tracer(tr, is_graph())) printk(KERN_ERR "failed to start irqsoff tracer\n"); diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 349f6941e8f2..bd90e1b06088 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -26,7 +26,7 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { - atomic_inc(&per_cpu_ptr(iter.tr->data, cpu)->disabled); + atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } old_userobj = trace_flags; @@ -46,14 +46,14 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file) if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter.buffer_iter[cpu] = - ring_buffer_read_prepare(iter.tr->buffer, cpu); + ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu); ring_buffer_read_start(iter.buffer_iter[cpu]); tracing_iter_reset(&iter, cpu); } } else { iter.cpu_file = cpu_file; iter.buffer_iter[cpu_file] = - ring_buffer_read_prepare(iter.tr->buffer, cpu_file); + ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file); ring_buffer_read_start(iter.buffer_iter[cpu_file]); tracing_iter_reset(&iter, cpu_file); } @@ -83,7 +83,7 @@ out: trace_flags = old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&per_cpu_ptr(iter.tr->data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } for_each_tracing_cpu(cpu) diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 2472f6f76b50..a5e8f4878bfa 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -31,7 +31,7 @@ static void mmio_reset_data(struct trace_array *tr) overrun_detected = false; prev_overruns = 0; - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); } static int mmio_trace_init(struct trace_array *tr) @@ -128,7 +128,7 @@ static void mmio_close(struct trace_iterator *iter) static unsigned long count_overruns(struct trace_iterator *iter) { unsigned long cnt = atomic_xchg(&dropped_count, 0); - unsigned long over = ring_buffer_overruns(iter->tr->buffer); + unsigned long over = ring_buffer_overruns(iter->trace_buffer->buffer); if (over > prev_overruns) cnt += over - prev_overruns; @@ -309,7 +309,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, struct mmiotrace_rw *rw) { struct ftrace_event_call *call = &event_mmiotrace_rw; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_rw *entry; int pc = preempt_count(); @@ -330,7 +330,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, void mmio_trace_rw(struct mmiotrace_rw *rw) { struct trace_array *tr = mmio_trace_array; - struct trace_array_cpu *data = per_cpu_ptr(tr->data, smp_processor_id()); + struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); __trace_mmiotrace_rw(tr, data, rw); } @@ -339,7 +339,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr, struct mmiotrace_map *map) { struct ftrace_event_call *call = &event_mmiotrace_map; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_map *entry; int pc = preempt_count(); @@ -363,7 +363,7 @@ void mmio_trace_mapping(struct mmiotrace_map *map) struct trace_array_cpu *data; preempt_disable(); - data = per_cpu_ptr(tr->data, smp_processor_id()); + data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); __trace_mmiotrace_map(tr, data, map); preempt_enable(); } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index aa92ac322ba2..2edc7220d017 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -643,7 +643,7 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts) { unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE; unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS; - unsigned long long abs_ts = iter->ts - iter->tr->time_start; + unsigned long long abs_ts = iter->ts - iter->trace_buffer->time_start; unsigned long long rel_ts = next_ts - iter->ts; struct trace_seq *s = &iter->seq; diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 1ffe39abd6fc..4e98e3b257a3 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -28,7 +28,7 @@ tracing_sched_switch_trace(struct trace_array *tr, unsigned long flags, int pc) { struct ftrace_event_call *call = &event_context_switch; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ring_buffer_event *event; struct ctx_switch_entry *entry; @@ -69,7 +69,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n pc = preempt_count(); local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(ctx_trace->data, cpu); + data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu); if (likely(!atomic_read(&data->disabled))) tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc); @@ -86,7 +86,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, struct ftrace_event_call *call = &event_wakeup; struct ring_buffer_event *event; struct ctx_switch_entry *entry; - struct ring_buffer *buffer = tr->buffer; + struct ring_buffer *buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_WAKE, sizeof(*entry), flags, pc); @@ -123,7 +123,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success) pc = preempt_count(); local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(ctx_trace->data, cpu); + data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu); if (likely(!atomic_read(&data->disabled))) tracing_sched_wakeup_trace(ctx_trace, wakee, current, diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index f9ceb75a95b7..c16f8cd63c3c 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -89,7 +89,7 @@ func_prolog_preempt_disable(struct trace_array *tr, if (cpu != wakeup_current_cpu) goto out_enable; - *data = per_cpu_ptr(tr->data, cpu); + *data = per_cpu_ptr(tr->trace_buffer.data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (unlikely(disabled != 1)) goto out; @@ -353,7 +353,7 @@ probe_wakeup_sched_switch(void *ignore, /* disable local data, not wakeup_cpu data */ cpu = raw_smp_processor_id(); - disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); if (likely(disabled != 1)) goto out; @@ -365,7 +365,7 @@ probe_wakeup_sched_switch(void *ignore, goto out_unlock; /* The task we are waiting for is waking up */ - data = per_cpu_ptr(wakeup_trace->data, wakeup_cpu); + data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc); tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); @@ -387,7 +387,7 @@ out_unlock: arch_spin_unlock(&wakeup_lock); local_irq_restore(flags); out: - atomic_dec(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); } static void __wakeup_reset(struct trace_array *tr) @@ -405,7 +405,7 @@ static void wakeup_reset(struct trace_array *tr) { unsigned long flags; - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); local_irq_save(flags); arch_spin_lock(&wakeup_lock); @@ -435,7 +435,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) return; pc = preempt_count(); - disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); if (unlikely(disabled != 1)) goto out; @@ -458,7 +458,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) local_save_flags(flags); - data = per_cpu_ptr(wakeup_trace->data, wakeup_cpu); + data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); data->preempt_timestamp = ftrace_now(cpu); tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc); @@ -472,7 +472,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success) out_locked: arch_spin_unlock(&wakeup_lock); out: - atomic_dec(&per_cpu_ptr(wakeup_trace->data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); } static void start_wakeup_tracer(struct trace_array *tr) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 51c819c12c29..8672c40cb153 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -21,13 +21,13 @@ static inline int trace_valid_entry(struct trace_entry *entry) return 0; } -static int trace_test_buffer_cpu(struct trace_array *tr, int cpu) +static int trace_test_buffer_cpu(struct trace_buffer *buf, int cpu) { struct ring_buffer_event *event; struct trace_entry *entry; unsigned int loops = 0; - while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) { + while ((event = ring_buffer_consume(buf->buffer, cpu, NULL, NULL))) { entry = ring_buffer_event_data(event); /* @@ -58,7 +58,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu) * Test the trace buffer to see if all the elements * are still sane. */ -static int trace_test_buffer(struct trace_array *tr, unsigned long *count) +static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count) { unsigned long flags, cnt = 0; int cpu, ret = 0; @@ -67,7 +67,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) local_irq_save(flags); arch_spin_lock(&ftrace_max_lock); - cnt = ring_buffer_entries(tr->buffer); + cnt = ring_buffer_entries(buf->buffer); /* * The trace_test_buffer_cpu runs a while loop to consume all data. @@ -78,7 +78,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) */ tracing_off(); for_each_possible_cpu(cpu) { - ret = trace_test_buffer_cpu(tr, cpu); + ret = trace_test_buffer_cpu(buf, cpu); if (ret) break; } @@ -355,7 +355,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, msleep(100); /* we should have nothing in the buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); if (ret) goto out; @@ -376,7 +376,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, ftrace_enabled = 0; /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); tracing_start(); /* we should only have one item */ @@ -666,7 +666,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ftrace_enabled = 0; /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); @@ -737,7 +737,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, * Simulate the init() callback but we attach a watchdog callback * to detect and recover from possible hangs */ - tracing_reset_online_cpus(tr); + tracing_reset_online_cpus(&tr->trace_buffer); set_graph_array(tr); ret = register_ftrace_graph(&trace_graph_return, &trace_graph_entry_watchdog); @@ -760,7 +760,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); @@ -815,9 +815,9 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (!ret) - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); tracing_start(); @@ -877,9 +877,9 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (!ret) - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); tracing_start(); @@ -943,11 +943,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (ret) goto out; - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); if (ret) goto out; @@ -973,11 +973,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); if (ret) goto out; - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); @@ -1084,10 +1084,10 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(tr, NULL); + ret = trace_test_buffer(&tr->trace_buffer, NULL); printk("ret = %d\n", ret); if (!ret) - ret = trace_test_buffer(&max_tr, &count); + ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); @@ -1126,7 +1126,7 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr /* stop the tracing. */ tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 1cd37ffb4093..68f3f344be65 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -321,7 +321,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; - buffer = tr->buffer; + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, sys_data->enter_event->event.type, size, 0, 0); if (!event) @@ -355,7 +355,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) if (!sys_data) return; - buffer = tr->buffer; + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, sys_data->exit_event->event.type, sizeof(*entry), 0, 0); if (!event) -- cgit v1.2.3 From f1affcaaa861f27752a769f889bf1486ebd301fe Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 14:35:11 -0500 Subject: tracing: Add snapshot in the per_cpu trace directories Add the snapshot file into the per_cpu tracing directories to allow them to be read for an individual cpu. This also allows to clear an individual cpu from the snapshot buffer. If the kernel allows it (CONFIG_RING_BUFFER_ALLOW_SWAP is set), then echoing in '1' into one of the per_cpu snapshot files will do an individual cpu buffer swap instead of the entire file. Cc: Hiraku Toyooka Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 66 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 56 insertions(+), 10 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a08c127db865..303932688964 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2436,6 +2436,31 @@ static void test_ftrace_alive(struct seq_file *m) } #ifdef CONFIG_TRACER_MAX_TRACE +static void show_snapshot_main_help(struct seq_file *m) +{ + seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n"); + seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n"); + seq_printf(m, "# Takes a snapshot of the main buffer.\n"); + seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n"); + seq_printf(m, "# (Doesn't have to be '2' works with any number that\n"); + seq_printf(m, "# is not a '0' or '1')\n"); +} + +static void show_snapshot_percpu_help(struct seq_file *m) +{ + seq_printf(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n"); +#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP + seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n"); + seq_printf(m, "# Takes a snapshot of the main buffer for this cpu.\n"); +#else + seq_printf(m, "# echo 1 > snapshot : Not supported with this kernel.\n"); + seq_printf(m, "# Must use main snapshot file to allocate.\n"); +#endif + seq_printf(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n"); + seq_printf(m, "# (Doesn't have to be '2' works with any number that\n"); + seq_printf(m, "# is not a '0' or '1')\n"); +} + static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { if (iter->trace->allocated_snapshot) @@ -2444,12 +2469,10 @@ static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) seq_printf(m, "#\n# * Snapshot is freed *\n#\n"); seq_printf(m, "# Snapshot commands:\n"); - seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n"); - seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n"); - seq_printf(m, "# Takes a snapshot of the main buffer.\n"); - seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n"); - seq_printf(m, "# (Doesn't have to be '2' works with any number that\n"); - seq_printf(m, "# is not a '0' or '1')\n"); + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + show_snapshot_main_help(m); + else + show_snapshot_percpu_help(m); } #else /* Should never be called */ @@ -4207,6 +4230,7 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) } iter->tr = tc->tr; iter->trace_buffer = &tc->tr->max_buffer; + iter->cpu_file = tc->cpu; m->private = iter; file->private_data = m; } @@ -4241,6 +4265,10 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, switch (val) { case 0: + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { + ret = -EINVAL; + break; + } if (tr->current_trace->allocated_snapshot) { /* free spare buffer */ ring_buffer_resize(tr->max_buffer.buffer, 1, @@ -4251,6 +4279,13 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, } break; case 1: +/* Only allow per-cpu swap if the ring buffer supports it */ +#ifndef CONFIG_RING_BUFFER_ALLOW_SWAP + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { + ret = -EINVAL; + break; + } +#endif if (!tr->current_trace->allocated_snapshot) { /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, @@ -4259,15 +4294,21 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, break; tr->current_trace->allocated_snapshot = true; } - local_irq_disable(); /* Now, we're going to swap */ - update_max_tr(&global_trace, current, smp_processor_id()); + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + update_max_tr(&global_trace, current, smp_processor_id()); + else + update_max_tr_single(&global_trace, current, iter->cpu_file); local_irq_enable(); break; default: - if (tr->current_trace->allocated_snapshot) - tracing_reset_online_cpus(&tr->max_buffer); + if (tr->current_trace->allocated_snapshot) { + if (iter->cpu_file == RING_BUFFER_ALL_CPUS) + tracing_reset_online_cpus(&tr->max_buffer); + else + tracing_reset(&tr->max_buffer, iter->cpu_file); + } break; } @@ -4835,6 +4876,11 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) trace_create_file("buffer_size_kb", 0444, d_cpu, (void *)&data->trace_cpu, &tracing_entries_fops); + +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_file("snapshot", 0644, d_cpu, + (void *)&data->trace_cpu, &snapshot_fops); +#endif } #ifdef CONFIG_FTRACE_SELFTEST -- cgit v1.2.3 From 6de58e6269cd0568ca5fbae14423914eff0f7811 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 16:18:16 -0500 Subject: tracing: Add snapshot_raw to extract the raw data from snapshot Add a 'snapshot_raw' per_cpu file that allows tools to read the raw binary data of the snapshot buffer. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 113 +++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 95 insertions(+), 18 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 303932688964..9bb0b52cbd32 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4206,6 +4206,12 @@ static int tracing_clock_open(struct inode *inode, struct file *file) return single_open(file, tracing_clock_show, inode->i_private); } +struct ftrace_buffer_info { + struct trace_iterator iter; + void *spare; + unsigned int read; +}; + #ifdef CONFIG_TRACER_SNAPSHOT static int tracing_snapshot_open(struct inode *inode, struct file *file) { @@ -4336,6 +4342,35 @@ static int tracing_snapshot_release(struct inode *inode, struct file *file) return 0; } +static int tracing_buffers_open(struct inode *inode, struct file *filp); +static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos); +static int tracing_buffers_release(struct inode *inode, struct file *file); +static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, unsigned int flags); + +static int snapshot_raw_open(struct inode *inode, struct file *filp) +{ + struct ftrace_buffer_info *info; + int ret; + + ret = tracing_buffers_open(inode, filp); + if (ret < 0) + return ret; + + info = filp->private_data; + + if (info->iter.trace->use_max_tr) { + tracing_buffers_release(inode, filp); + return -EBUSY; + } + + info->iter.snapshot = true; + info->iter.trace_buffer = &info->iter.tr->max_buffer; + + return ret; +} + #endif /* CONFIG_TRACER_SNAPSHOT */ @@ -4402,14 +4437,17 @@ static const struct file_operations snapshot_fops = { .llseek = tracing_seek, .release = tracing_snapshot_release, }; -#endif /* CONFIG_TRACER_SNAPSHOT */ -struct ftrace_buffer_info { - struct trace_iterator iter; - void *spare; - unsigned int read; +static const struct file_operations snapshot_raw_fops = { + .open = snapshot_raw_open, + .read = tracing_buffers_read, + .release = tracing_buffers_release, + .splice_read = tracing_buffers_splice_read, + .llseek = no_llseek, }; +#endif /* CONFIG_TRACER_SNAPSHOT */ + static int tracing_buffers_open(struct inode *inode, struct file *filp) { struct trace_cpu *tc = inode->i_private; @@ -4452,16 +4490,26 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; ssize_t ret; - size_t size; + ssize_t size; if (!count) return 0; + mutex_lock(&trace_types_lock); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->tr->current_trace->use_max_tr) { + size = -EBUSY; + goto out_unlock; + } +#endif + if (!info->spare) info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, iter->cpu_file); + size = -ENOMEM; if (!info->spare) - return -ENOMEM; + goto out_unlock; /* Do we have previous read data to read? */ if (info->read < PAGE_SIZE) @@ -4477,31 +4525,42 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (ret < 0) { if (trace_empty(iter)) { - if ((filp->f_flags & O_NONBLOCK)) - return -EAGAIN; + if ((filp->f_flags & O_NONBLOCK)) { + size = -EAGAIN; + goto out_unlock; + } + mutex_unlock(&trace_types_lock); iter->trace->wait_pipe(iter); - if (signal_pending(current)) - return -EINTR; + mutex_lock(&trace_types_lock); + if (signal_pending(current)) { + size = -EINTR; + goto out_unlock; + } goto again; } - return 0; + size = 0; + goto out_unlock; } info->read = 0; - read: size = PAGE_SIZE - info->read; if (size > count) size = count; ret = copy_to_user(ubuf, info->spare + info->read, size); - if (ret == size) - return -EFAULT; + if (ret == size) { + size = -EFAULT; + goto out_unlock; + } size -= ret; *ppos += size; info->read += size; + out_unlock: + mutex_unlock(&trace_types_lock); + return size; } @@ -4591,10 +4650,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, }; struct buffer_ref *ref; int entries, size, i; - size_t ret; + ssize_t ret; - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; + mutex_lock(&trace_types_lock); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (iter->snapshot && iter->tr->current_trace->use_max_tr) { + ret = -EBUSY; + goto out; + } +#endif + + if (splice_grow_spd(pipe, &spd)) { + ret = -ENOMEM; + goto out; + } if (*ppos & (PAGE_SIZE - 1)) { ret = -EINVAL; @@ -4666,7 +4736,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, ret = -EAGAIN; goto out; } + mutex_unlock(&trace_types_lock); iter->trace->wait_pipe(iter); + mutex_lock(&trace_types_lock); if (signal_pending(current)) { ret = -EINTR; goto out; @@ -4677,6 +4749,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, ret = splice_to_pipe(pipe, &spd); splice_shrink_spd(&spd); out: + mutex_unlock(&trace_types_lock); + return ret; } @@ -4880,6 +4954,9 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_cpu, (void *)&data->trace_cpu, &snapshot_fops); + + trace_create_file("snapshot_raw", 0444, d_cpu, + (void *)&data->trace_cpu, &snapshot_raw_fops); #endif } -- cgit v1.2.3 From 45ad21ca5530efdca6a19e4a5ac5e7bd6e24f996 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 18:25:02 -0500 Subject: tracing: Have trace_array keep track if snapshot buffer is allocated The snapshot buffer belongs to the trace array not the tracer that is running. The trace array should be the data structure that keeps track of whether or not the snapshot buffer is allocated, not the tracer desciptor. Having the trace array keep track of it makes modifications so much easier. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 32 +++++++++++++++----------------- kernel/trace/trace.h | 2 +- 2 files changed, 16 insertions(+), 18 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9bb0b52cbd32..bcc9460c2d65 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -667,7 +667,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) WARN_ON_ONCE(!irqs_disabled()); - if (!tr->current_trace->allocated_snapshot) { + if (!tr->allocated_snapshot) { /* Only the nop tracer should hit this when disabling */ WARN_ON_ONCE(tr->current_trace != &nop_trace); return; @@ -700,7 +700,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) return; WARN_ON_ONCE(!irqs_disabled()); - if (WARN_ON_ONCE(!tr->current_trace->allocated_snapshot)) + if (WARN_ON_ONCE(!tr->allocated_snapshot)) return; arch_spin_lock(&ftrace_max_lock); @@ -802,7 +802,7 @@ int register_tracer(struct tracer *type) if (ring_buffer_expanded) ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, RING_BUFFER_ALL_CPUS); - type->allocated_snapshot = true; + tr->allocated_snapshot = true; } #endif @@ -822,7 +822,7 @@ int register_tracer(struct tracer *type) #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { - type->allocated_snapshot = false; + tr->allocated_snapshot = false; /* Shrink the max buffer again */ if (ring_buffer_expanded) @@ -2463,7 +2463,7 @@ static void show_snapshot_percpu_help(struct seq_file *m) static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { - if (iter->trace->allocated_snapshot) + if (iter->tr->allocated_snapshot) seq_printf(m, "#\n# * Snapshot is allocated *\n#\n"); else seq_printf(m, "#\n# * Snapshot is freed *\n#\n"); @@ -3364,12 +3364,12 @@ static int tracing_set_tracer(const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); -#ifdef CONFIG_TRACER_MAX_TRACE - had_max_tr = tr->current_trace->allocated_snapshot; - /* Current trace needs to be nop_trace before synchronize_sched */ tr->current_trace = &nop_trace; +#ifdef CONFIG_TRACER_MAX_TRACE + had_max_tr = tr->allocated_snapshot; + if (had_max_tr && !t->use_max_tr) { /* * We need to make sure that the update_max_tr sees that @@ -3387,10 +3387,8 @@ static int tracing_set_tracer(const char *buf) ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&tr->max_buffer, 1); tracing_reset_online_cpus(&tr->max_buffer); - tr->current_trace->allocated_snapshot = false; + tr->allocated_snapshot = false; } -#else - tr->current_trace = &nop_trace; #endif destroy_trace_option_files(topts); @@ -3403,7 +3401,7 @@ static int tracing_set_tracer(const char *buf) RING_BUFFER_ALL_CPUS); if (ret < 0) goto out; - t->allocated_snapshot = true; + tr->allocated_snapshot = true; } #endif @@ -4275,13 +4273,13 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = -EINVAL; break; } - if (tr->current_trace->allocated_snapshot) { + if (tr->allocated_snapshot) { /* free spare buffer */ ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&tr->max_buffer, 1); tracing_reset_online_cpus(&tr->max_buffer); - tr->current_trace->allocated_snapshot = false; + tr->allocated_snapshot = false; } break; case 1: @@ -4292,13 +4290,13 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, break; } #endif - if (!tr->current_trace->allocated_snapshot) { + if (!tr->allocated_snapshot) { /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->trace_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) break; - tr->current_trace->allocated_snapshot = true; + tr->allocated_snapshot = true; } local_irq_disable(); /* Now, we're going to swap */ @@ -4309,7 +4307,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, local_irq_enable(); break; default: - if (tr->current_trace->allocated_snapshot) { + if (tr->allocated_snapshot) { if (iter->cpu_file == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(&tr->max_buffer); else diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 986834f1f4dd..1a456c291a07 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -197,6 +197,7 @@ struct trace_array { * the trace_buffer so the tracing can continue. */ struct trace_buffer max_buffer; + bool allocated_snapshot; #endif int buffer_disabled; struct trace_cpu trace_cpu; /* place holder */ @@ -367,7 +368,6 @@ struct tracer { bool enabled; #ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; - bool allocated_snapshot; #endif }; -- cgit v1.2.3 From 737223fbca3b1c91feb947c7f571b35749b743b6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 21:13:47 -0500 Subject: tracing: Consolidate buffer allocation code There's a bit of duplicate code in creating the trace buffers for the normal trace buffer and the max trace buffer among the instances and the main global_trace. This code can be consolidated and cleaned up a bit making the code cleaner and more readable as well as less duplication. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 130 +++++++++++++++++++++++++-------------------------- 1 file changed, 63 insertions(+), 67 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bcc9460c2d65..57895d476509 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3171,6 +3171,7 @@ int tracer_init(struct tracer *t, struct trace_array *tr) static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) { int cpu; + for_each_tracing_cpu(cpu) per_cpu_ptr(buf->data, cpu)->entries = val; } @@ -5267,12 +5268,70 @@ struct dentry *trace_instance_dir; static void init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer); -static int new_instance_create(const char *name) +static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf) +{ + int cpu; + + for_each_tracing_cpu(cpu) { + memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu)); + per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu; + per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr; + } +} + +static int allocate_trace_buffers(struct trace_array *tr, int size) { enum ring_buffer_flags rb_flags; + + rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; + + tr->trace_buffer.buffer = ring_buffer_alloc(size, rb_flags); + if (!tr->trace_buffer.buffer) + goto out_free; + + tr->trace_buffer.data = alloc_percpu(struct trace_array_cpu); + if (!tr->trace_buffer.data) + goto out_free; + + init_trace_buffers(tr, &tr->trace_buffer); + + /* Allocate the first page for all buffers */ + set_buffer_entries(&tr->trace_buffer, + ring_buffer_size(tr->trace_buffer.buffer, 0)); + +#ifdef CONFIG_TRACER_MAX_TRACE + + tr->max_buffer.buffer = ring_buffer_alloc(1, rb_flags); + if (!tr->max_buffer.buffer) + goto out_free; + + tr->max_buffer.data = alloc_percpu(struct trace_array_cpu); + if (!tr->max_buffer.data) + goto out_free; + + init_trace_buffers(tr, &tr->max_buffer); + + set_buffer_entries(&tr->max_buffer, 1); +#endif + return 0; + + out_free: + if (tr->trace_buffer.buffer) + ring_buffer_free(tr->trace_buffer.buffer); + free_percpu(tr->trace_buffer.data); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->max_buffer.buffer) + ring_buffer_free(tr->max_buffer.buffer); + free_percpu(tr->max_buffer.data); +#endif + return -ENOMEM; +} + +static int new_instance_create(const char *name) +{ struct trace_array *tr; int ret; - int i; mutex_lock(&trace_types_lock); @@ -5298,22 +5357,9 @@ static int new_instance_create(const char *name) INIT_LIST_HEAD(&tr->systems); INIT_LIST_HEAD(&tr->events); - rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; - - tr->trace_buffer.buffer = ring_buffer_alloc(trace_buf_size, rb_flags); - if (!tr->trace_buffer.buffer) - goto out_free_tr; - - tr->trace_buffer.data = alloc_percpu(struct trace_array_cpu); - if (!tr->trace_buffer.data) + if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; - for_each_tracing_cpu(i) { - memset(per_cpu_ptr(tr->trace_buffer.data, i), 0, sizeof(struct trace_array_cpu)); - per_cpu_ptr(tr->trace_buffer.data, i)->trace_cpu.cpu = i; - per_cpu_ptr(tr->trace_buffer.data, i)->trace_cpu.tr = tr; - } - /* Holder for file callbacks */ tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS; tr->trace_cpu.tr = tr; @@ -5736,8 +5782,6 @@ EXPORT_SYMBOL_GPL(ftrace_dump); __init static int tracer_alloc_buffers(void) { int ring_buf_size; - enum ring_buffer_flags rb_flags; - int i; int ret = -ENOMEM; @@ -5758,69 +5802,21 @@ __init static int tracer_alloc_buffers(void) else ring_buf_size = 1; - rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; - cpumask_copy(tracing_buffer_mask, cpu_possible_mask); cpumask_copy(tracing_cpumask, cpu_all_mask); raw_spin_lock_init(&global_trace.start_lock); /* TODO: make the number of buffers hot pluggable with CPUS */ - global_trace.trace_buffer.buffer = ring_buffer_alloc(ring_buf_size, rb_flags); - if (!global_trace.trace_buffer.buffer) { + if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); WARN_ON(1); goto out_free_cpumask; } - global_trace.trace_buffer.data = alloc_percpu(struct trace_array_cpu); - - if (!global_trace.trace_buffer.data) { - printk(KERN_ERR "tracer: failed to allocate percpu memory!\n"); - WARN_ON(1); - goto out_free_cpumask; - } - - for_each_tracing_cpu(i) { - memset(per_cpu_ptr(global_trace.trace_buffer.data, i), 0, - sizeof(struct trace_array_cpu)); - per_cpu_ptr(global_trace.trace_buffer.data, i)->trace_cpu.cpu = i; - per_cpu_ptr(global_trace.trace_buffer.data, i)->trace_cpu.tr = &global_trace; - } - if (global_trace.buffer_disabled) tracing_off(); -#ifdef CONFIG_TRACER_MAX_TRACE - global_trace.max_buffer.data = alloc_percpu(struct trace_array_cpu); - if (!global_trace.max_buffer.data) { - printk(KERN_ERR "tracer: failed to allocate percpu memory!\n"); - WARN_ON(1); - goto out_free_cpumask; - } - global_trace.max_buffer.buffer = ring_buffer_alloc(1, rb_flags); - if (!global_trace.max_buffer.buffer) { - printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); - WARN_ON(1); - ring_buffer_free(global_trace.trace_buffer.buffer); - goto out_free_cpumask; - } - - for_each_tracing_cpu(i) { - memset(per_cpu_ptr(global_trace.max_buffer.data, i), 0, - sizeof(struct trace_array_cpu)); - per_cpu_ptr(global_trace.max_buffer.data, i)->trace_cpu.cpu = i; - per_cpu_ptr(global_trace.max_buffer.data, i)->trace_cpu.tr = &global_trace; - } -#endif - - /* Allocate the first page for all buffers */ - set_buffer_entries(&global_trace.trace_buffer, - ring_buffer_size(global_trace.trace_buffer.buffer, 0)); -#ifdef CONFIG_TRACER_MAX_TRACE - set_buffer_entries(&global_trace.max_buffer, 1); -#endif - trace_init_cmdlines(); register_tracer(&nop_trace); -- cgit v1.2.3 From ce9bae55972b228cf7bac34350c4d2caf8ea0d0b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 21:23:55 -0500 Subject: tracing: Add snapshot feature to instances Add the "snapshot" file to the the multi-buffer instances. cd /sys/kernel/debug/tracing/instances mkdir foo ls foo buffer_size_kb buffer_total_size_kb events free_buffer set_event snapshot trace trace_clock trace_marker trace_options trace_pipe tracing_on cat foo/snapshot # tracer: nop # # # * Snapshot is freed * # # Snapshot commands: # echo 0 > snapshot : Clears and frees snapshot buffer # echo 1 > snapshot : Allocates snapshot buffer, if not already allocated. # Takes a snapshot of the main buffer. # echo 2 > snapshot : Clears snapshot buffer (but does not allocate) # (Doesn't have to be '2' works with any number that # is not a '0' or '1') Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 57895d476509..17671bc9a4b1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4302,9 +4302,9 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, local_irq_disable(); /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) - update_max_tr(&global_trace, current, smp_processor_id()); + update_max_tr(tr, current, smp_processor_id()); else - update_max_tr_single(&global_trace, current, iter->cpu_file); + update_max_tr_single(tr, current, iter->cpu_file); local_irq_enable(); break; default: @@ -5533,6 +5533,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("tracing_on", 0644, d_tracer, tr, &rb_simple_fops); + +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_file("snapshot", 0644, d_tracer, + (void *)&tr->trace_cpu, &snapshot_fops); +#endif } static __init int tracer_init_debugfs(void) @@ -5574,11 +5579,6 @@ static __init int tracer_init_debugfs(void) &ftrace_update_tot_cnt, &tracing_dyn_info_fops); #endif -#ifdef CONFIG_TRACER_SNAPSHOT - trace_create_file("snapshot", 0644, d_tracer, - (void *)&global_trace.trace_cpu, &snapshot_fops); -#endif - create_trace_instances(d_tracer); create_trace_options_dir(&global_trace); -- cgit v1.2.3 From 121aaee7b0a82605d33af200c7e9ebab6fd6e444 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 21:52:25 -0500 Subject: tracing: Add per_cpu directory into tracing instances Add the per_cpu directory to the created tracing instances: cd /sys/kernel/debug/tracing/instances mkdir foo ls foo/per_cpu/cpu0 buffer_size_kb snapshot_raw trace trace_pipe_raw snapshot stats trace_pipe Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 17671bc9a4b1..c547ebbe36ff 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5506,6 +5506,7 @@ static __init void create_trace_instances(struct dentry *d_tracer) static void init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) { + int cpu; trace_create_file("trace_options", 0644, d_tracer, tr, &tracing_iter_fops); @@ -5538,12 +5539,15 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("snapshot", 0644, d_tracer, (void *)&tr->trace_cpu, &snapshot_fops); #endif + + for_each_tracing_cpu(cpu) + tracing_init_debugfs_percpu(tr, cpu); + } static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; - int cpu; trace_access_lock_init(); @@ -5583,9 +5587,6 @@ static __init int tracer_init_debugfs(void) create_trace_options_dir(&global_trace); - for_each_tracing_cpu(cpu) - tracing_init_debugfs_percpu(&global_trace, cpu); - return 0; } -- cgit v1.2.3 From a695cb5816228f86576f5f5c6809fdf8ed382ece Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 6 Mar 2013 15:27:24 -0500 Subject: tracing: Prevent deleting instances when they are being read Add a ref count to the trace_array structure and prevent removal of instances that have open descriptors. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 23 +++++++++++++++++++++++ kernel/trace/trace.h | 1 + 2 files changed, 24 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c547ebbe36ff..3a89496dc99b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2613,6 +2613,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) tracing_iter_reset(iter, cpu); } + tr->ref++; + mutex_unlock(&trace_types_lock); return iter; @@ -2649,6 +2651,10 @@ static int tracing_release(struct inode *inode, struct file *file) tr = iter->tr; mutex_lock(&trace_types_lock); + + WARN_ON(!tr->ref); + tr->ref--; + for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) ring_buffer_read_finish(iter->buffer_iter[cpu]); @@ -4460,6 +4466,10 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) if (!info) return -ENOMEM; + mutex_lock(&trace_types_lock); + + tr->ref++; + info->iter.tr = tr; info->iter.cpu_file = tc->cpu; info->iter.trace = tr->current_trace; @@ -4470,6 +4480,8 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) filp->private_data = info; + mutex_unlock(&trace_types_lock); + return nonseekable_open(inode, filp); } @@ -4568,10 +4580,17 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; + mutex_lock(&trace_types_lock); + + WARN_ON(!iter->tr->ref); + iter->tr->ref--; + if (info->spare) ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare); kfree(info); + mutex_unlock(&trace_types_lock); + return 0; } @@ -5411,6 +5430,10 @@ static int instance_delete(const char *name) if (!found) goto out_unlock; + ret = -EBUSY; + if (tr->ref) + goto out_unlock; + list_del(&tr->list); event_trace_del_tracer(tr); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 1a456c291a07..f4931821a966 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -219,6 +219,7 @@ struct trace_array { struct list_head systems; struct list_head events; struct task_struct *waiter; + int ref; }; enum { -- cgit v1.2.3 From ad909e21bbe69f1d39055d346540abd827190eca Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 6 Mar 2013 21:45:37 -0500 Subject: tracing: Add internal tracing_snapshot() functions The new snapshot feature is quite handy. It's a way for the user to take advantage of the spare buffer that, until then, only the latency tracers used to "snapshot" the buffer when it hit a max latency. Now users can trigger a "snapshot" manually when some condition is hit in a program. But a snapshot currently can not be triggered by a condition inside the kernel. With the addition of tracing_snapshot() and tracing_snapshot_alloc(), snapshots can now be taking when a condition is hit, and the developer wants to snapshot the case without stopping the trace. Note, any snapshot will overwrite the old one, so take care in how this is done. These new functions are to be used like tracing_on(), tracing_off() and trace_printk() are. That is, they should never be called in the mainline Linux kernel. They are solely for the purpose of debugging. The tracing_snapshot() will not allocate a buffer, but it is safe to be called from any context (except NMIs). But if a snapshot buffer isn't allocated when it is called, it will write to the live buffer, complaining about the lack of a snapshot buffer, and then stop tracing (giving you the "permanent snapshot"). tracing_snapshot_alloc() will allocate the snapshot buffer if it was not already allocated and then take the snapshot. This routine *may sleep*, and must be called from context that can sleep. The allocation is done with GFP_KERNEL and not atomic. If you need a snapshot in an atomic context, say in early boot, then it is best to call the tracing_snapshot_alloc() before then, where it will allocate the buffer, and then you can use the tracing_snapshot() anywhere you want and still get snapshots. Cc: Hiraku Toyooka Cc: Thomas Gleixner Cc: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 4 +++ kernel/trace/trace.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index c566927efcbd..bc5392a326ab 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -483,6 +483,8 @@ enum ftrace_dump_mode { void tracing_on(void); void tracing_off(void); int tracing_is_on(void); +void tracing_snapshot(void); +void tracing_snapshot_alloc(void); extern void tracing_start(void); extern void tracing_stop(void); @@ -570,6 +572,8 @@ static inline void trace_dump_stack(void) { } static inline void tracing_on(void) { } static inline void tracing_off(void) { } static inline int tracing_is_on(void) { return 0; } +static inline void tracing_snapshot(void) { } +static inline void tracing_snapshot_alloc(void) { } static inline __printf(1, 2) int trace_printk(const char *fmt, ...) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3a89496dc99b..307524d784ec 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -339,6 +339,90 @@ void tracing_on(void) } EXPORT_SYMBOL_GPL(tracing_on); +#ifdef CONFIG_TRACER_SNAPSHOT +/** + * trace_snapshot - take a snapshot of the current buffer. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + * + * Note, make sure to allocate the snapshot with either + * a tracing_snapshot_alloc(), or by doing it manually + * with: echo 1 > /sys/kernel/debug/tracing/snapshot + * + * If the snapshot buffer is not allocated, it will stop tracing. + * Basically making a permanent snapshot. + */ +void tracing_snapshot(void) +{ + struct trace_array *tr = &global_trace; + struct tracer *tracer = tr->current_trace; + unsigned long flags; + + if (!tr->allocated_snapshot) { + trace_printk("*** SNAPSHOT NOT ALLOCATED ***\n"); + trace_printk("*** stopping trace here! ***\n"); + tracing_off(); + return; + } + + /* Note, snapshot can not be used when the tracer uses it */ + if (tracer->use_max_tr) { + trace_printk("*** LATENCY TRACER ACTIVE ***\n"); + trace_printk("*** Can not use snapshot (sorry) ***\n"); + return; + } + + local_irq_save(flags); + update_max_tr(tr, current, smp_processor_id()); + local_irq_restore(flags); +} + +static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, + struct trace_buffer *size_buf, int cpu_id); + +/** + * trace_snapshot_alloc - allocate and take a snapshot of the current buffer. + * + * This is similar to trace_snapshot(), but it will allocate the + * snapshot buffer if it isn't already allocated. Use this only + * where it is safe to sleep, as the allocation may sleep. + * + * This causes a swap between the snapshot buffer and the current live + * tracing buffer. You can use this to take snapshots of the live + * trace when some condition is triggered, but continue to trace. + */ +void tracing_snapshot_alloc(void) +{ + struct trace_array *tr = &global_trace; + int ret; + + if (!tr->allocated_snapshot) { + + /* allocate spare buffer */ + ret = resize_buffer_duplicate_size(&tr->max_buffer, + &tr->trace_buffer, RING_BUFFER_ALL_CPUS); + if (WARN_ON(ret < 0)) + return; + + tr->allocated_snapshot = true; + } + + tracing_snapshot(); +} +#else +void tracing_snapshot(void) +{ + WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used"); +} +void tracing_snapshot_alloc(void) +{ + /* Give warning */ + tracing_snapshot(); +} +#endif /* CONFIG_TRACER_SNAPSHOT */ + /** * tracing_off - turn off tracing buffers * -- cgit v1.2.3 From f4e781c0a89d5810729772290441ac7d61f321ec Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 7 Mar 2013 11:10:56 -0500 Subject: tracing: Move the tracing selftest code into its own function Move the tracing startup selftest code into its own function and when not enabled, always have that function succeed. This makes the register_tracer() function much more readable. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 124 ++++++++++++++++++++++++++++----------------------- 1 file changed, 69 insertions(+), 55 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 307524d784ec..57b4220d96a9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -818,6 +818,72 @@ static void default_wait_pipe(struct trace_iterator *iter) ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file); } +#ifdef CONFIG_FTRACE_STARTUP_TEST +static int run_tracer_selftest(struct tracer *type) +{ + struct trace_array *tr = &global_trace; + struct tracer *saved_tracer = tr->current_trace; + int ret; + + if (!type->selftest || tracing_selftest_disabled) + return 0; + + /* + * Run a selftest on this tracer. + * Here we reset the trace buffer, and set the current + * tracer to be this tracer. The tracer can then run some + * internal tracing to verify that everything is in order. + * If we fail, we do not register this tracer. + */ + tracing_reset_online_cpus(&tr->trace_buffer); + + tr->current_trace = type; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (type->use_max_tr) { + /* If we expanded the buffers, make sure the max is expanded too */ + if (ring_buffer_expanded) + ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, + RING_BUFFER_ALL_CPUS); + tr->allocated_snapshot = true; + } +#endif + + /* the test is responsible for initializing and enabling */ + pr_info("Testing tracer %s: ", type->name); + ret = type->selftest(type, tr); + /* the test is responsible for resetting too */ + tr->current_trace = saved_tracer; + if (ret) { + printk(KERN_CONT "FAILED!\n"); + /* Add the warning after printing 'FAILED' */ + WARN_ON(1); + return -1; + } + /* Only reset on passing, to avoid touching corrupted buffers */ + tracing_reset_online_cpus(&tr->trace_buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + if (type->use_max_tr) { + tr->allocated_snapshot = false; + + /* Shrink the max buffer again */ + if (ring_buffer_expanded) + ring_buffer_resize(tr->max_buffer.buffer, 1, + RING_BUFFER_ALL_CPUS); + } +#endif + + printk(KERN_CONT "PASSED\n"); + return 0; +} +#else +static inline int run_tracer_selftest(struct tracer *type) +{ + return 0; +} +#endif /* CONFIG_FTRACE_STARTUP_TEST */ + /** * register_tracer - register a tracer with the ftrace system. * @type - the plugin for the tracer @@ -863,61 +929,9 @@ int register_tracer(struct tracer *type) if (!type->wait_pipe) type->wait_pipe = default_wait_pipe; - -#ifdef CONFIG_FTRACE_STARTUP_TEST - if (type->selftest && !tracing_selftest_disabled) { - struct trace_array *tr = &global_trace; - struct tracer *saved_tracer = tr->current_trace; - - /* - * Run a selftest on this tracer. - * Here we reset the trace buffer, and set the current - * tracer to be this tracer. The tracer can then run some - * internal tracing to verify that everything is in order. - * If we fail, we do not register this tracer. - */ - tracing_reset_online_cpus(&tr->trace_buffer); - - tr->current_trace = type; - -#ifdef CONFIG_TRACER_MAX_TRACE - if (type->use_max_tr) { - /* If we expanded the buffers, make sure the max is expanded too */ - if (ring_buffer_expanded) - ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, - RING_BUFFER_ALL_CPUS); - tr->allocated_snapshot = true; - } -#endif - - /* the test is responsible for initializing and enabling */ - pr_info("Testing tracer %s: ", type->name); - ret = type->selftest(type, tr); - /* the test is responsible for resetting too */ - tr->current_trace = saved_tracer; - if (ret) { - printk(KERN_CONT "FAILED!\n"); - /* Add the warning after printing 'FAILED' */ - WARN_ON(1); - goto out; - } - /* Only reset on passing, to avoid touching corrupted buffers */ - tracing_reset_online_cpus(&tr->trace_buffer); - -#ifdef CONFIG_TRACER_MAX_TRACE - if (type->use_max_tr) { - tr->allocated_snapshot = false; - - /* Shrink the max buffer again */ - if (ring_buffer_expanded) - ring_buffer_resize(tr->max_buffer.buffer, 1, - RING_BUFFER_ALL_CPUS); - } -#endif - - printk(KERN_CONT "PASSED\n"); - } -#endif + ret = run_tracer_selftest(type); + if (ret < 0) + goto out; type->next = trace_types; trace_types = type; -- cgit v1.2.3 From 55034cd6e648155393b0d665eef76b38d49ad6bf Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 7 Mar 2013 22:48:09 -0500 Subject: tracing: Add alloc_snapshot kernel command line parameter If debugging the kernel, and the developer wants to use tracing_snapshot() in places where tracing_snapshot_alloc() may be difficult (or more likely, the developer is lazy and doesn't want to bother with tracing_snapshot_alloc() at all), then adding alloc_snapshot to the kernel command line parameter will tell ftrace to allocate the snapshot buffer (if configured) when it allocates the main tracing buffer. I also noticed that ring_buffer_expanded and tracing_selftest_disabled had inconsistent use of boolean "true" and "false" with "0" and "1". I cleaned that up too. Signed-off-by: Steven Rostedt --- Documentation/kernel-parameters.txt | 7 ++++ kernel/trace/trace.c | 81 ++++++++++++++++++++++--------------- kernel/trace/trace.h | 2 +- kernel/trace/trace_events.c | 4 +- 4 files changed, 58 insertions(+), 36 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 6c723811c0a0..0edc409f9ede 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -320,6 +320,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. on: enable for both 32- and 64-bit processes off: disable for both 32- and 64-bit processes + alloc_snapshot [FTRACE] + Allocate the ftrace snapshot buffer on boot up when the + main buffer is allocated. This is handy if debugging + and you need to use tracing_snapshot() on boot up, and + do not want to use tracing_snapshot_alloc() as it needs + to be done where GFP_KERNEL allocations are allowed. + amd_iommu= [HW,X86-64] Pass parameters to the AMD IOMMU driver in the system. Possible values are: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 57b4220d96a9..4021a5e66412 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -47,7 +47,7 @@ * On boot up, the ring buffer is set to the minimum size, so that * we do not waste memory on systems that are not using tracing. */ -int ring_buffer_expanded; +bool ring_buffer_expanded; /* * We need to change this state when a selftest is running. @@ -121,12 +121,14 @@ static int tracing_set_tracer(const char *buf); static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; +static bool allocate_snapshot; + static int __init set_cmdline_ftrace(char *str) { 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; + ring_buffer_expanded = true; return 1; } __setup("ftrace=", set_cmdline_ftrace); @@ -147,6 +149,15 @@ static int __init set_ftrace_dump_on_oops(char *str) } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); +static int __init alloc_snapshot(char *str) +{ + allocate_snapshot = true; + /* We also need the main ring buffer expanded */ + ring_buffer_expanded = true; + return 1; +} +__setup("alloc_snapshot", alloc_snapshot); + static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static char *trace_boot_options __initdata; @@ -951,7 +962,7 @@ int register_tracer(struct tracer *type) tracing_set_tracer(type->name); default_bootup_tracer = NULL; /* disable other selftests, since this will break it. */ - tracing_selftest_disabled = 1; + tracing_selftest_disabled = true; #ifdef CONFIG_FTRACE_STARTUP_TEST printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n", type->name); @@ -3318,7 +3329,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, * we use the size that was given, and we can forget about * expanding it later. */ - ring_buffer_expanded = 1; + ring_buffer_expanded = true; /* May be called before buffers are initialized */ if (!tr->trace_buffer.buffer) @@ -5396,53 +5407,57 @@ static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf) } } -static int allocate_trace_buffers(struct trace_array *tr, int size) +static int +allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) { enum ring_buffer_flags rb_flags; rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; - tr->trace_buffer.buffer = ring_buffer_alloc(size, rb_flags); - if (!tr->trace_buffer.buffer) - goto out_free; + buf->buffer = ring_buffer_alloc(size, rb_flags); + if (!buf->buffer) + return -ENOMEM; - tr->trace_buffer.data = alloc_percpu(struct trace_array_cpu); - if (!tr->trace_buffer.data) - goto out_free; + buf->data = alloc_percpu(struct trace_array_cpu); + if (!buf->data) { + ring_buffer_free(buf->buffer); + return -ENOMEM; + } - init_trace_buffers(tr, &tr->trace_buffer); + init_trace_buffers(tr, buf); /* Allocate the first page for all buffers */ set_buffer_entries(&tr->trace_buffer, ring_buffer_size(tr->trace_buffer.buffer, 0)); -#ifdef CONFIG_TRACER_MAX_TRACE - - tr->max_buffer.buffer = ring_buffer_alloc(1, rb_flags); - if (!tr->max_buffer.buffer) - goto out_free; - - tr->max_buffer.data = alloc_percpu(struct trace_array_cpu); - if (!tr->max_buffer.data) - goto out_free; + return 0; +} - init_trace_buffers(tr, &tr->max_buffer); +static int allocate_trace_buffers(struct trace_array *tr, int size) +{ + int ret; - set_buffer_entries(&tr->max_buffer, 1); -#endif - return 0; + ret = allocate_trace_buffer(tr, &tr->trace_buffer, size); + if (ret) + return ret; - out_free: - if (tr->trace_buffer.buffer) +#ifdef CONFIG_TRACER_MAX_TRACE + ret = allocate_trace_buffer(tr, &tr->max_buffer, + allocate_snapshot ? size : 1); + if (WARN_ON(ret)) { ring_buffer_free(tr->trace_buffer.buffer); - free_percpu(tr->trace_buffer.data); + free_percpu(tr->trace_buffer.data); + return -ENOMEM; + } + tr->allocated_snapshot = allocate_snapshot; -#ifdef CONFIG_TRACER_MAX_TRACE - if (tr->max_buffer.buffer) - ring_buffer_free(tr->max_buffer.buffer); - free_percpu(tr->max_buffer.data); + /* + * Only the top level trace array gets its snapshot allocated + * from the kernel command line. + */ + allocate_snapshot = false; #endif - return -ENOMEM; + return 0; } static int new_instance_create(const char *name) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f4931821a966..26bc71834041 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -660,7 +660,7 @@ extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); -extern int ring_buffer_expanded; +extern bool ring_buffer_expanded; extern bool tracing_selftest_disabled; DECLARE_PER_CPU(int, ftrace_cpu_disabled); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a376ab5eec5c..38b54c5edeb9 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1844,8 +1844,8 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; static __init int setup_trace_event(char *str) { strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE); - ring_buffer_expanded = 1; - tracing_selftest_disabled = 1; + ring_buffer_expanded = true; + tracing_selftest_disabled = true; return 1; } -- cgit v1.2.3 From 09ae72348eccb60e304cf8ce94653f4a78fcd407 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 8 Mar 2013 21:02:34 -0500 Subject: tracing: Add trace_puts() for even faster trace_printk() tracing The trace_printk() is extremely fast and is very handy as it can be used in any context (including NMIs!). But it still requires scanning the fmt string for parsing the args. Even the trace_bprintk() requires a scan to know what args will be saved, although it doesn't copy the format string itself. Several times trace_printk() has no args, and wastes cpu cycles scanning the fmt string. Adding trace_puts() allows the developer to use an even faster tracing method that only saves the pointer to the string in the ring buffer without doing any format parsing at all. This will help remove even more of the "Heisenbug" effect, when debugging. Also fixed up the F_printk()s for the ftrace internal bprint and print events. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 41 +++++++++++++++++++++++- kernel/trace/trace.c | 76 ++++++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace.h | 2 ++ kernel/trace/trace_entries.h | 23 +++++++++++--- kernel/trace/trace_output.c | 75 +++++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace_output.h | 2 ++ 6 files changed, 214 insertions(+), 5 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bc5392a326ab..a3a5574a61fc 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -514,7 +514,8 @@ do { \ * * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in - * your code. + * your code. (Extra memory is used for special buffers that are + * allocated when trace_printk() is used) */ #define trace_printk(fmt, args...) \ @@ -537,6 +538,44 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) int __trace_printk(unsigned long ip, const char *fmt, ...); +/** + * trace_puts - write a string into the ftrace buffer + * @str: the string to record + * + * Note: __trace_bputs is an internal function for trace_puts and + * the @ip is passed in via the trace_puts macro. + * + * This is similar to trace_printk() but is made for those really fast + * paths that a developer wants the least amount of "Heisenbug" affects, + * where the processing of the print format is still too much. + * + * This function allows a kernel developer to debug fast path sections + * that printk is not appropriate for. By scattering in various + * printk like tracing in the code, a developer can quickly see + * where problems are occurring. + * + * This is intended as a debugging tool for the developer only. + * Please refrain from leaving trace_puts scattered around in + * your code. (Extra memory is used for special buffers that are + * allocated when trace_puts() is used) + * + * Returns: 0 if nothing was written, positive # if string was. + * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) + */ + +extern int __trace_bputs(unsigned long ip, const char *str); +extern int __trace_puts(unsigned long ip, const char *str, int size); +#define trace_puts(str) ({ \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(str) ? str : NULL; \ + \ + if (__builtin_constant_p(str)) \ + __trace_bputs(_THIS_IP_, trace_printk_fmt); \ + else \ + __trace_puts(_THIS_IP_, str, strlen(str)); \ +}) + extern void trace_dump_stack(void); /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4021a5e66412..5043a0c4dde0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -350,6 +350,77 @@ void tracing_on(void) } EXPORT_SYMBOL_GPL(tracing_on); +/** + * __trace_puts - write a constant string into the trace buffer. + * @ip: The address of the caller + * @str: The constant string to write + * @size: The size of the string. + */ +int __trace_puts(unsigned long ip, const char *str, int size) +{ + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct print_entry *entry; + unsigned long irq_flags; + int alloc; + + alloc = sizeof(*entry) + size + 2; /* possible \n added */ + + local_save_flags(irq_flags); + buffer = global_trace.trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + irq_flags, preempt_count()); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + + memcpy(&entry->buf, str, size); + + /* Add a newline if necessary */ + if (entry->buf[size - 1] != '\n') { + entry->buf[size] = '\n'; + entry->buf[size + 1] = '\0'; + } else + entry->buf[size] = '\0'; + + __buffer_unlock_commit(buffer, event); + + return size; +} +EXPORT_SYMBOL_GPL(__trace_puts); + +/** + * __trace_bputs - write the pointer to a constant string into trace buffer + * @ip: The address of the caller + * @str: The constant string to write to the buffer to + */ +int __trace_bputs(unsigned long ip, const char *str) +{ + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct bputs_entry *entry; + unsigned long irq_flags; + int size = sizeof(struct bputs_entry); + + local_save_flags(irq_flags); + buffer = global_trace.trace_buffer.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, + irq_flags, preempt_count()); + if (!event) + return 0; + + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->str = str; + + __buffer_unlock_commit(buffer, event); + + return 1; +} +EXPORT_SYMBOL_GPL(__trace_bputs); + #ifdef CONFIG_TRACER_SNAPSHOT /** * trace_snapshot - take a snapshot of the current buffer. @@ -2475,6 +2546,11 @@ enum print_line_t print_trace_line(struct trace_iterator *iter) return ret; } + if (iter->ent->type == TRACE_BPUTS && + trace_flags & TRACE_ITER_PRINTK && + trace_flags & TRACE_ITER_PRINTK_MSGONLY) + return trace_print_bputs_msg_only(iter); + if (iter->ent->type == TRACE_BPRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 26bc71834041..d5764a8532e2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -34,6 +34,7 @@ enum trace_type { TRACE_GRAPH_ENT, TRACE_USER_STACK, TRACE_BLK, + TRACE_BPUTS, __TRACE_LAST_TYPE, }; @@ -277,6 +278,7 @@ extern void __ftrace_bad_type(void); IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \ + IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ TRACE_MMIO_RW); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \ diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 4108e1250ca2..e2d027ac66a2 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -223,8 +223,8 @@ FTRACE_ENTRY(bprint, bprint_entry, __dynamic_array( u32, buf ) ), - F_printk("%08lx fmt:%p", - __entry->ip, __entry->fmt), + F_printk("%pf: %s", + (void *)__entry->ip, __entry->fmt), FILTER_OTHER ); @@ -238,8 +238,23 @@ FTRACE_ENTRY(print, print_entry, __dynamic_array( char, buf ) ), - F_printk("%08lx %s", - __entry->ip, __entry->buf), + F_printk("%pf: %s", + (void *)__entry->ip, __entry->buf), + + FILTER_OTHER +); + +FTRACE_ENTRY(bputs, bputs_entry, + + TRACE_BPUTS, + + F_STRUCT( + __field( unsigned long, ip ) + __field( const char *, str ) + ), + + F_printk("%pf: %s", + (void *)__entry->ip, __entry->str), FILTER_OTHER ); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 2edc7220d017..19f48e7edc39 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -37,6 +37,22 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s) return ret; } +enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct bputs_entry *field; + int ret; + + trace_assign_type(field, entry); + + ret = trace_seq_puts(s, field->str); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; @@ -1244,6 +1260,64 @@ static struct trace_event trace_user_stack_event = { .funcs = &trace_user_stack_funcs, }; +/* TRACE_BPUTS */ +static enum print_line_t +trace_bputs_print(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + struct bputs_entry *field; + + trace_assign_type(field, entry); + + if (!seq_print_ip_sym(s, field->ip, flags)) + goto partial; + + if (!trace_seq_puts(s, ": ")) + goto partial; + + if (!trace_seq_puts(s, field->str)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + + +static enum print_line_t +trace_bputs_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct bputs_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(s, ": %lx : ", field->ip)) + goto partial; + + if (!trace_seq_puts(s, field->str)) + goto partial; + + return TRACE_TYPE_HANDLED; + + partial: + return TRACE_TYPE_PARTIAL_LINE; +} + +static struct trace_event_functions trace_bputs_funcs = { + .trace = trace_bputs_print, + .raw = trace_bputs_raw, +}; + +static struct trace_event trace_bputs_event = { + .type = TRACE_BPUTS, + .funcs = &trace_bputs_funcs, +}; + /* TRACE_BPRINT */ static enum print_line_t trace_bprint_print(struct trace_iterator *iter, int flags, @@ -1356,6 +1430,7 @@ static struct trace_event *events[] __initdata = { &trace_wake_event, &trace_stack_event, &trace_user_stack_event, + &trace_bputs_event, &trace_bprint_event, &trace_print_event, NULL diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index c038eba0492b..af77870de278 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -4,6 +4,8 @@ #include #include "trace.h" +extern enum print_line_t +trace_print_bputs_msg_only(struct trace_iterator *iter); extern enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter); extern enum print_line_t -- cgit v1.2.3 From ca268da6e415448a43138e1abc5d5f057af319d7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Sat, 9 Mar 2013 00:40:58 -0500 Subject: tracing: Add internal ftrace trace_puts() for ftrace to use There's a few places that ftrace uses trace_printk() for internal use, but this requires context (normal, softirq, irq, NMI) buffers to keep things lockless. But the trace_puts() does not, as it can write the string directly into the ring buffer. Make a internal helper for trace_puts() and have the internal functions use that. This way the extra context buffers are not used. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 8 ++++---- kernel/trace/trace.h | 11 +++++++++++ 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5043a0c4dde0..d372c6504c99 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -443,16 +443,16 @@ void tracing_snapshot(void) unsigned long flags; if (!tr->allocated_snapshot) { - trace_printk("*** SNAPSHOT NOT ALLOCATED ***\n"); - trace_printk("*** stopping trace here! ***\n"); + internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n"); + internal_trace_puts("*** stopping trace here! ***\n"); tracing_off(); return; } /* Note, snapshot can not be used when the tracer uses it */ if (tracer->use_max_tr) { - trace_printk("*** LATENCY TRACER ACTIVE ***\n"); - trace_printk("*** Can not use snapshot (sorry) ***\n"); + internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n"); + internal_trace_puts("*** Can not use snapshot (sorry) ***\n"); return; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index d5764a8532e2..0e430b401ab6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1040,6 +1040,17 @@ void trace_printk_start_comm(void); int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); +/* + * Normal trace_printk() and friends allocates special buffers + * to do the manipulation, as well as saves the print formats + * into sections to display. But the trace infrastructure wants + * to use these without the added overhead at the price of being + * a bit slower (used mainly for warnings, where we don't care + * about performance). The internal_trace_puts() is for such + * a purpose. + */ +#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) + #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ -- cgit v1.2.3 From 1b22e382ab40b0e3ee5abb3e310dffb16fee22aa Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Sat, 9 Mar 2013 00:56:08 -0500 Subject: tracing: Let tracing_snapshot() be used by modules but not NMI Add EXPORT_SYMBOL_GPL() to let the tracing_snapshot() functions be called from modules. Also add a test to see if the snapshot was called from NMI context and just warn in the tracing buffer if so, and return. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d372c6504c99..5c53e4092269 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -442,6 +442,12 @@ void tracing_snapshot(void) struct tracer *tracer = tr->current_trace; unsigned long flags; + if (in_nmi()) { + internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); + internal_trace_puts("*** snapshot is being ignored ***\n"); + return; + } + if (!tr->allocated_snapshot) { internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n"); internal_trace_puts("*** stopping trace here! ***\n"); @@ -460,6 +466,7 @@ void tracing_snapshot(void) update_max_tr(tr, current, smp_processor_id()); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(tracing_snapshot); static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, struct trace_buffer *size_buf, int cpu_id); @@ -493,16 +500,19 @@ void tracing_snapshot_alloc(void) tracing_snapshot(); } +EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); #else void tracing_snapshot(void) { WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used"); } +EXPORT_SYMBOL_GPL(tracing_snapshot); void tracing_snapshot_alloc(void) { /* Give warning */ tracing_snapshot(); } +EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); #endif /* CONFIG_TRACER_SNAPSHOT */ /** -- cgit v1.2.3 From 3209cff4490bee55fd2bc1d087cb8ecf2a686a88 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 12 Mar 2013 11:17:54 -0400 Subject: tracing: Add alloc/free_snapshot() to replace duplicate code Add alloc_snapshot() and free_snapshot() to allocate and free the snapshot buffer respectively, and use these to remove duplicate code. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 79 ++++++++++++++++++++++++++++------------------------ 1 file changed, 42 insertions(+), 37 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5c53e4092269..906049c0af90 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -149,14 +149,14 @@ static int __init set_ftrace_dump_on_oops(char *str) } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); -static int __init alloc_snapshot(char *str) +static int __init boot_alloc_snapshot(char *str) { allocate_snapshot = true; /* We also need the main ring buffer expanded */ ring_buffer_expanded = true; return 1; } -__setup("alloc_snapshot", alloc_snapshot); +__setup("alloc_snapshot", boot_alloc_snapshot); static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; @@ -470,6 +470,38 @@ EXPORT_SYMBOL_GPL(tracing_snapshot); static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, struct trace_buffer *size_buf, int cpu_id); +static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); + +static int alloc_snapshot(struct trace_array *tr) +{ + int ret; + + if (!tr->allocated_snapshot) { + + /* allocate spare buffer */ + ret = resize_buffer_duplicate_size(&tr->max_buffer, + &tr->trace_buffer, RING_BUFFER_ALL_CPUS); + if (ret < 0) + return ret; + + tr->allocated_snapshot = true; + } + + return 0; +} + +void free_snapshot(struct trace_array *tr) +{ + /* + * We don't free the ring buffer. instead, resize it because + * The max_tr ring buffer has some state (e.g. ring->clock) and + * we want preserve it. + */ + ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); + set_buffer_entries(&tr->max_buffer, 1); + tracing_reset_online_cpus(&tr->max_buffer); + tr->allocated_snapshot = false; +} /** * trace_snapshot_alloc - allocate and take a snapshot of the current buffer. @@ -487,16 +519,9 @@ void tracing_snapshot_alloc(void) struct trace_array *tr = &global_trace; int ret; - if (!tr->allocated_snapshot) { - - /* allocate spare buffer */ - ret = resize_buffer_duplicate_size(&tr->max_buffer, - &tr->trace_buffer, RING_BUFFER_ALL_CPUS); - if (WARN_ON(ret < 0)) - return; - - tr->allocated_snapshot = true; - } + ret = alloc_snapshot(tr); + if (WARN_ON(ret < 0)) + return; tracing_snapshot(); } @@ -3581,15 +3606,7 @@ static int tracing_set_tracer(const char *buf) * so a synchronized_sched() is sufficient. */ synchronize_sched(); - /* - * We don't free the ring buffer. instead, resize it because - * The max_tr ring buffer has some state (e.g. ring->clock) and - * we want preserve it. - */ - ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); - set_buffer_entries(&tr->max_buffer, 1); - tracing_reset_online_cpus(&tr->max_buffer); - tr->allocated_snapshot = false; + free_snapshot(tr); } #endif destroy_trace_option_files(topts); @@ -3598,12 +3615,9 @@ static int tracing_set_tracer(const char *buf) #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { - /* we need to make per cpu buffer sizes equivalent */ - ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->trace_buffer, - RING_BUFFER_ALL_CPUS); + ret = alloc_snapshot(tr); if (ret < 0) goto out; - tr->allocated_snapshot = true; } #endif @@ -4475,14 +4489,8 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = -EINVAL; break; } - if (tr->allocated_snapshot) { - /* free spare buffer */ - ring_buffer_resize(tr->max_buffer.buffer, 1, - RING_BUFFER_ALL_CPUS); - set_buffer_entries(&tr->max_buffer, 1); - tracing_reset_online_cpus(&tr->max_buffer); - tr->allocated_snapshot = false; - } + if (tr->allocated_snapshot) + free_snapshot(tr); break; case 1: /* Only allow per-cpu swap if the ring buffer supports it */ @@ -4493,12 +4501,9 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, } #endif if (!tr->allocated_snapshot) { - /* allocate spare buffer */ - ret = resize_buffer_duplicate_size(&tr->max_buffer, - &tr->trace_buffer, RING_BUFFER_ALL_CPUS); + ret = alloc_snapshot(tr); if (ret < 0) break; - tr->allocated_snapshot = true; } local_irq_disable(); /* Now, we're going to swap */ -- cgit v1.2.3 From 77fd5c15e3216b901be69047ca43b05ae9099951 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 12 Mar 2013 11:49:18 -0400 Subject: tracing: Add snapshot trigger to function probes echo 'schedule:snapshot:1' > /debug/tracing/set_ftrace_filter This will cause the scheduler to trigger a snapshot the next time it's called (you can use any function that's not called by NMI). Even though it triggers only once, you still need to remove it with: echo '!schedule:snapshot:0' > /debug/tracing/set_ftrace_filter The :1 can be left off for the first command: echo 'schedule:snapshot' > /debug/tracing/set_ftrace_filter But this will cause all calls to schedule to trigger a snapshot. This must be removed without the ':0' echo '!schedule:snapshot' > /debug/tracing/set_ftrace_filter As adding a "count" is a different operation (internally). Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 111 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 110 insertions(+), 1 deletion(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 906049c0af90..c5b844621562 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5086,7 +5086,114 @@ static const struct file_operations tracing_dyn_info_fops = { .read = tracing_read_dyn_info, .llseek = generic_file_llseek, }; -#endif +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) +static void +ftrace_snapshot(unsigned long ip, unsigned long parent_ip, void **data) +{ + tracing_snapshot(); +} + +static void +ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, void **data) +{ + unsigned long *count = (long *)data; + + if (!*count) + return; + + if (*count != -1) + (*count)--; + + tracing_snapshot(); +} + +static int +ftrace_snapshot_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + long count = (long)data; + + seq_printf(m, "%ps:", (void *)ip); + + seq_printf(m, "snapshot"); + + if (count == -1) + seq_printf(m, ":unlimited\n"); + else + seq_printf(m, ":count=%ld\n", count); + + return 0; +} + +static struct ftrace_probe_ops snapshot_probe_ops = { + .func = ftrace_snapshot, + .print = ftrace_snapshot_print, +}; + +static struct ftrace_probe_ops snapshot_count_probe_ops = { + .func = ftrace_count_snapshot, + .print = ftrace_snapshot_print, +}; + +static int +ftrace_trace_snapshot_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + void *count = (void *)-1; + char *number; + int ret; + + /* hash funcs only work with set_ftrace_filter */ + if (!enable) + return -EINVAL; + + ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; + + if (glob[0] == '!') { + unregister_ftrace_function_probe_func(glob+1, ops); + return 0; + } + + if (!param) + goto out_reg; + + number = strsep(¶m, ":"); + + if (!strlen(number)) + goto out_reg; + + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, (unsigned long *)&count); + if (ret) + return ret; + + out_reg: + ret = register_ftrace_function_probe(glob, ops, count); + + if (ret >= 0) + alloc_snapshot(&global_trace); + + return ret < 0 ? ret : 0; +} + +static struct ftrace_func_command ftrace_snapshot_cmd = { + .name = "snapshot", + .func = ftrace_trace_snapshot_callback, +}; + +static int register_snapshot_cmd(void) +{ + return register_ftrace_command(&ftrace_snapshot_cmd); +} +#else +static inline int register_snapshot_cmd(void) { return 0; } +#endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ struct dentry *tracing_init_dentry_tr(struct trace_array *tr) { @@ -6076,6 +6183,8 @@ __init static int tracer_alloc_buffers(void) trace_set_options(&global_trace, option); } + register_snapshot_cmd(); + return 0; out_free_cpumask: -- cgit v1.2.3 From c142be8ebe0b7bf73c8a0063925623f3e4b980c0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 13 Mar 2013 09:55:57 -0400 Subject: tracing: Add skip argument to trace_dump_stack() Altough the trace_dump_stack() already skips three functions in the call to stack trace, which gets the stack trace to start at the caller of the function, the caller may want to skip some more too (as it may have helper functions). Add a skip argument to the trace_dump_stack() that lets the caller skip back tracing functions that it doesn't care about. Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 2 +- kernel/trace/trace.c | 13 +++++++++---- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d0a16fe03fef..239dbb9627ca 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -597,7 +597,7 @@ extern int __trace_puts(unsigned long ip, const char *str, int size); __trace_puts(_THIS_IP_, str, strlen(str)); \ }) -extern void trace_dump_stack(void); +extern void trace_dump_stack(int skip); /* * The double __builtin_constant_p is because gcc will give us an error diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c5b844621562..8aa53213201f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1657,8 +1657,9 @@ void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, /** * trace_dump_stack - record a stack back trace in the trace buffer + * @skip: Number of functions to skip (helper handlers) */ -void trace_dump_stack(void) +void trace_dump_stack(int skip) { unsigned long flags; @@ -1667,9 +1668,13 @@ void trace_dump_stack(void) local_save_flags(flags); - /* skipping 3 traces, seems to get us at the caller of this function */ - __ftrace_trace_stack(global_trace.trace_buffer.buffer, flags, 3, - preempt_count(), NULL); + /* + * Skip 3 more, seems to get us at the caller of + * this function. + */ + skip += 3; + __ftrace_trace_stack(global_trace.trace_buffer.buffer, + flags, skip, preempt_count(), NULL); } static DEFINE_PER_CPU(int, user_stack_count); -- cgit v1.2.3 From 328df4759c03e2c3e7429cc6cb0e180c38f32063 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 14 Mar 2013 12:10:40 -0400 Subject: tracing: Add function-trace option to disable function tracing of latency tracers Currently, the only way to stop the latency tracers from doing function tracing is to fully disable the function tracer from the proc file system: echo 0 > /proc/sys/kernel/ftrace_enabled This is a big hammer approach as it disables function tracing for all users. This includes kprobes, perf, stack tracer, etc. Instead, create a function-trace option that the latency tracers can check to determine if it should enable function tracing or not. This option can be set or cleared even while the tracer is active and the tracers will disable or enable function tracing depending on how the option was set. Instead of using the proc file, disable latency function tracing with echo 0 > /debug/tracing/options/function-trace Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Clark Williams Cc: John Kacur Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 3 +- kernel/trace/trace.h | 1 + kernel/trace/trace_irqsoff.c | 67 ++++++++++++++++++++++++++++++++------- kernel/trace/trace_sched_wakeup.c | 63 ++++++++++++++++++++++++++++++------ 4 files changed, 111 insertions(+), 23 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8aa53213201f..f90ca16afcf2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -328,7 +328,7 @@ static inline void trace_access_lock_init(void) unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | - TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; + TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION; /** * tracing_on - enable tracing buffers @@ -635,6 +635,7 @@ static const char *trace_options[] = { "disable_on_free", "irq-info", "markers", + "function-trace", NULL }; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0e430b401ab6..5cc52361bc9f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -867,6 +867,7 @@ enum trace_iterator_flags { TRACE_ITER_STOP_ON_FREE = 0x400000, TRACE_ITER_IRQ_INFO = 0x800000, TRACE_ITER_MARKERS = 0x1000000, + TRACE_ITER_FUNCTION = 0x2000000, }; /* diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 5aa40ab72b57..b19d065a28cb 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -33,6 +33,7 @@ enum { static int trace_type __read_mostly; static int save_flags; +static bool function_enabled; static void stop_irqsoff_tracer(struct trace_array *tr, int graph); static int start_irqsoff_tracer(struct trace_array *tr, int graph); @@ -528,15 +529,60 @@ void trace_preempt_off(unsigned long a0, unsigned long a1) } #endif /* CONFIG_PREEMPT_TRACER */ -static int start_irqsoff_tracer(struct trace_array *tr, int graph) +static int register_irqsoff_function(int graph, int set) { - int ret = 0; + int ret; - if (!graph) - ret = register_ftrace_function(&trace_ops); - else + /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ + if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION))) + return 0; + + if (graph) ret = register_ftrace_graph(&irqsoff_graph_return, &irqsoff_graph_entry); + else + ret = register_ftrace_function(&trace_ops); + + if (!ret) + function_enabled = true; + + return ret; +} + +static void unregister_irqsoff_function(int graph) +{ + if (!function_enabled) + return; + + if (graph) + unregister_ftrace_graph(); + else + unregister_ftrace_function(&trace_ops); + + function_enabled = false; +} + +static void irqsoff_function_set(int set) +{ + if (set) + register_irqsoff_function(is_graph(), 1); + else + unregister_irqsoff_function(is_graph()); +} + +static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set) +{ + if (mask & TRACE_ITER_FUNCTION) + irqsoff_function_set(set); + + return trace_keep_overwrite(tracer, mask, set); +} + +static int start_irqsoff_tracer(struct trace_array *tr, int graph) +{ + int ret; + + ret = register_irqsoff_function(graph, 0); if (!ret && tracing_is_enabled()) tracer_enabled = 1; @@ -550,10 +596,7 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph) { tracer_enabled = 0; - if (!graph) - unregister_ftrace_function(&trace_ops); - else - unregister_ftrace_graph(); + unregister_irqsoff_function(graph); } static void __irqsoff_tracer_init(struct trace_array *tr) @@ -615,7 +658,7 @@ static struct tracer irqsoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = irqsoff_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_irqsoff, #endif @@ -649,7 +692,7 @@ static struct tracer preemptoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = irqsoff_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptoff, #endif @@ -685,7 +728,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = irqsoff_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptirqsoff, #endif diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index c16f8cd63c3c..fee77e15d815 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -37,6 +37,7 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace); static void wakeup_graph_return(struct ftrace_graph_ret *trace); static int save_flags; +static bool function_enabled; #define TRACE_DISPLAY_GRAPH 1 @@ -134,15 +135,60 @@ static struct ftrace_ops trace_ops __read_mostly = }; #endif /* CONFIG_FUNCTION_TRACER */ -static int start_func_tracer(int graph) +static int register_wakeup_function(int graph, int set) { int ret; - if (!graph) - ret = register_ftrace_function(&trace_ops); - else + /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ + if (function_enabled || (!set && !(trace_flags & TRACE_ITER_FUNCTION))) + return 0; + + if (graph) ret = register_ftrace_graph(&wakeup_graph_return, &wakeup_graph_entry); + else + ret = register_ftrace_function(&trace_ops); + + if (!ret) + function_enabled = true; + + return ret; +} + +static void unregister_wakeup_function(int graph) +{ + if (!function_enabled) + return; + + if (graph) + unregister_ftrace_graph(); + else + unregister_ftrace_function(&trace_ops); + + function_enabled = false; +} + +static void wakeup_function_set(int set) +{ + if (set) + register_wakeup_function(is_graph(), 1); + else + unregister_wakeup_function(is_graph()); +} + +static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set) +{ + if (mask & TRACE_ITER_FUNCTION) + wakeup_function_set(set); + + return trace_keep_overwrite(tracer, mask, set); +} + +static int start_func_tracer(int graph) +{ + int ret; + + ret = register_wakeup_function(graph, 0); if (!ret && tracing_is_enabled()) tracer_enabled = 1; @@ -156,10 +202,7 @@ static void stop_func_tracer(int graph) { tracer_enabled = 0; - if (!graph) - unregister_ftrace_function(&trace_ops); - else - unregister_ftrace_graph(); + unregister_wakeup_function(graph); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -600,7 +643,7 @@ static struct tracer wakeup_tracer __read_mostly = .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = wakeup_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif @@ -622,7 +665,7 @@ static struct tracer wakeup_rt_tracer __read_mostly = .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, - .flag_changed = trace_keep_overwrite, + .flag_changed = wakeup_flag_changed, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif -- cgit v1.2.3 From 8aacf017b065a805d27467843490c976835eb4a5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 14 Mar 2013 13:13:45 -0400 Subject: tracing: Add "uptime" trace clock that uses jiffies Add a simple trace clock called "uptime" for those that are interested in the uptime of the trace. It uses jiffies as that's the safest method, as other uptime clocks grab seq locks, which could cause a deadlock if taken from an event or function tracer. Requested-by: Mauro Carvalho Chehab Cc: Thomas Gleixner Cc: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/trace_clock.h | 1 + kernel/trace/trace.c | 1 + kernel/trace/trace_clock.c | 10 ++++++++++ 3 files changed, 12 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h index d563f37e1a1d..1d7ca2739272 100644 --- a/include/linux/trace_clock.h +++ b/include/linux/trace_clock.h @@ -16,6 +16,7 @@ extern u64 notrace trace_clock_local(void); extern u64 notrace trace_clock(void); +extern u64 notrace trace_clock_jiffies(void); extern u64 notrace trace_clock_global(void); extern u64 notrace trace_clock_counter(void); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f90ca16afcf2..8eabfbb8003e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -647,6 +647,7 @@ static struct { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, + { trace_clock_jiffies, "uptime", 1 }, ARCH_TRACE_CLOCKS }; diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index aa8f5f48dae6..26dc348332b7 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -57,6 +57,16 @@ u64 notrace trace_clock(void) return local_clock(); } +/* + * trace_jiffy_clock(): Simply use jiffies as a clock counter. + */ +u64 notrace trace_clock_jiffies(void) +{ + u64 jiffy = jiffies - INITIAL_JIFFIES; + + /* Return nsecs */ + return (u64)jiffies_to_usecs(jiffy) * 1000ULL; +} /* * trace_clock_global(): special globally coherent trace clock -- cgit v1.2.3 From 76f119179b8ce3188a8c61d2486d37810a416655 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 14 Mar 2013 17:53:25 -0400 Subject: tracing: Add "perf" trace_clock The function trace_clock() calls "local_clock()" which is exactly the same clock that perf uses. I'm not sure why perf doesn't call trace_clock(), as trace_clock() doesn't have any users. But now it does. As trace_clock() calls local_clock() like perf does, I added the trace_clock "perf" option that uses trace_clock(). Now the ftrace buffers can use the same clock as perf uses. This will be useful when perf starts reading the ftrace buffers, and will be able to interleave them with the same clock data. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8eabfbb8003e..7f0e7fa6d62c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -648,6 +648,7 @@ static struct { { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, { trace_clock_jiffies, "uptime", 1 }, + { trace_clock, "perf", 1 }, ARCH_TRACE_CLOCKS }; -- cgit v1.2.3 From 687c878afb526a0c3117dbc408ca76ad80d689f7 Mon Sep 17 00:00:00 2001 From: "zhangwei(Jovi)" Date: Mon, 11 Mar 2013 15:13:29 +0800 Subject: tracing: Use pr_warn_once instead of open coded implementation Use pr_warn_once, instead of making an open coded implementation. Link: http://lkml.kernel.org/r/513D8419.20400@huawei.com Signed-off-by: zhangwei(Jovi) Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7f0e7fa6d62c..bba1ba958ee8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5205,8 +5205,6 @@ static inline int register_snapshot_cmd(void) { return 0; } struct dentry *tracing_init_dentry_tr(struct trace_array *tr) { - static int once; - if (tr->dir) return tr->dir; @@ -5216,11 +5214,8 @@ struct dentry *tracing_init_dentry_tr(struct trace_array *tr) if (tr->flags & TRACE_ARRAY_FL_GLOBAL) tr->dir = debugfs_create_dir("tracing", NULL); - if (!tr->dir && !once) { - once = 1; - pr_warning("Could not create debugfs directory 'tracing'\n"); - return NULL; - } + if (!tr->dir) + pr_warn_once("Could not create debugfs directory 'tracing'\n"); return tr->dir; } -- cgit v1.2.3 From bd6df18716fa45bc4aa9587aca033de909e5382b Mon Sep 17 00:00:00 2001 From: "zhangwei(Jovi)" Date: Mon, 11 Mar 2013 15:13:37 +0800 Subject: tracing: Use TRACE_MAX_PRINT instead of constant TRACE_MAX_PRINT macro is defined, but is not used. Link: http://lkml.kernel.org/r/513D8421.4070404@huawei.com Signed-off-by: zhangwei(Jovi) Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bba1ba958ee8..848625674752 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5978,8 +5978,8 @@ void trace_printk_seq(struct trace_seq *s) { /* Probably should print a warning here. */ - if (s->len >= 1000) - s->len = 1000; + if (s->len >= TRACE_MAX_PRINT) + s->len = TRACE_MAX_PRINT; /* should be zero ended, but we are paranoid. */ s->buffer[s->len] = 0; -- cgit v1.2.3 From 7fe70b579c9e3daba71635e31b6189394e7b79d3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 15 Mar 2013 13:10:35 -0400 Subject: tracing: Fix ftrace_dump() ftrace_dump() had a lot of issues. What ftrace_dump() does, is when ftrace_dump_on_oops is set (via a kernel parameter or sysctl), it will dump out the ftrace buffers to the console when either a oops, panic, or a sysrq-z occurs. This was written a long time ago when ftrace was fragile to recursion. But it wasn't written well even for that. There's a possible deadlock that can occur if a ftrace_dump() is happening and an NMI triggers another dump. This is because it grabs a lock before checking if the dump ran. It also totally disables ftrace, and tracing for no good reasons. As the ring_buffer now checks if it is read via a oops or NMI, where there's a chance that the buffer gets corrupted, it will disable itself. No need to have ftrace_dump() do the same. ftrace_dump() is now cleaned up where it uses an atomic counter to make sure only one dump happens at a time. A simple atomic_inc_return() is enough that is needed for both other CPUs and NMIs. No need for a spinlock, as if one CPU is running the dump, no other CPU needs to do it too. The tracing_on variable is turned off and not turned on. The original code did this, but it wasn't pretty. By just disabling this variable we get the result of not seeing traces that happen between crashes. For sysrq-z, it doesn't get turned on, but the user can always write a '1' to the tracing_on file. If they are using sysrq-z, then they should know about tracing_on. The new code is much easier to read and less error prone. No more deadlock possibility when an NMI triggers here. Reported-by: zhangwei(Jovi) Cc: stable@vger.kernel.org Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 62 ++++++++++++++++++------------------------- kernel/trace/trace_selftest.c | 9 ++++--- 2 files changed, 31 insertions(+), 40 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 848625674752..3dc7999594e1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5997,36 +5997,32 @@ void trace_init_global_iter(struct trace_iterator *iter) iter->trace_buffer = &global_trace.trace_buffer; } -static void -__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) +void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { - static arch_spinlock_t ftrace_dump_lock = - (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; + static atomic_t dump_running; unsigned int old_userobj; - static int dump_ran; unsigned long flags; int cnt = 0, cpu; - /* only one dump */ - local_irq_save(flags); - arch_spin_lock(&ftrace_dump_lock); - if (dump_ran) - goto out; - - dump_ran = 1; + /* Only allow one dump user at a time. */ + if (atomic_inc_return(&dump_running) != 1) { + atomic_dec(&dump_running); + return; + } + /* + * Always turn off tracing when we dump. + * We don't need to show trace output of what happens + * between multiple crashes. + * + * If the user does a sysrq-z, then they can re-enable + * tracing with echo 1 > tracing_on. + */ tracing_off(); - /* Did function tracer already get disabled? */ - if (ftrace_is_dead()) { - printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n"); - printk("# MAY BE MISSING FUNCTION EVENTS\n"); - } - - if (disable_tracing) - ftrace_kill(); + local_irq_save(flags); /* Simulate the iterator */ trace_init_global_iter(&iter); @@ -6056,6 +6052,12 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) printk(KERN_TRACE "Dumping ftrace buffer:\n"); + /* Did function tracer already get disabled? */ + if (ftrace_is_dead()) { + printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n"); + printk("# MAY BE MISSING FUNCTION EVENTS\n"); + } + /* * We need to stop all tracing on all CPUS to read the * the next buffer. This is a bit expensive, but is @@ -6095,26 +6097,14 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) printk(KERN_TRACE "---------------------------------\n"); out_enable: - /* Re-enable tracing if requested */ - if (!disable_tracing) { - trace_flags |= old_userobj; + trace_flags |= old_userobj; - for_each_tracing_cpu(cpu) { - atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); - } - tracing_on(); + for_each_tracing_cpu(cpu) { + atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); } - - out: - arch_spin_unlock(&ftrace_dump_lock); + atomic_dec(&dump_running); local_irq_restore(flags); } - -/* By default: disable tracing after the dump */ -void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) -{ - __ftrace_dump(true, oops_dump_mode); -} EXPORT_SYMBOL_GPL(ftrace_dump); __init static int tracer_alloc_buffers(void) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 8672c40cb153..55e2cf66967b 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -703,8 +703,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) /* Maximum number of functions to trace before diagnosing a hang */ #define GRAPH_MAX_FUNC_TEST 100000000 -static void -__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode); static unsigned int graph_hang_thresh; /* Wrap the real function entry probe to avoid possible hanging */ @@ -714,8 +712,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { ftrace_graph_stop(); printk(KERN_WARNING "BUG: Function graph tracer hang!\n"); - if (ftrace_dump_on_oops) - __ftrace_dump(false, DUMP_ALL); + if (ftrace_dump_on_oops) { + ftrace_dump(DUMP_ALL); + /* ftrace_dump() disables tracing */ + tracing_on(); + } return 0; } -- cgit v1.2.3 From 22f45649ce08642ad7df238d5c25fa5c86bfdd31 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 15 Mar 2013 17:23:20 -0400 Subject: tracing: Update debugfs README file Update the README file in debugfs/tracing to something more useful. What's currently in the file is very old and what it shows doesn't have much use. Heck, it tells you how to mount debugfs! But to read this file you would have already needed to mount it. Replace the file with current up-to-date information. It's rather limited, but what do you expect from a pseudo README file. Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 92 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 78 insertions(+), 14 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3dc7999594e1..829b2bee24e8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3300,20 +3300,84 @@ static const struct file_operations tracing_iter_fops = { 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 wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n" - "# cat /sys/kernel/debug/tracing/current_tracer\n" - "nop\n" - "# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n" - "# cat /sys/kernel/debug/tracing/current_tracer\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" - "# echo 1 > /sys/kernel/debug/tracing/tracing_on\n" - "# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n" - "# echo 0 > /sys/kernel/debug/tracing/tracing_on\n" + "# echo 0 > tracing_on : quick way to disable tracing\n" + "# echo 1 > tracing_on : quick way to re-enable tracing\n\n" + " Important files:\n" + " trace\t\t\t- The static contents of the buffer\n" + "\t\t\t To clear the buffer write into this file: echo > trace\n" + " trace_pipe\t\t- A consuming read to see the contents of the buffer\n" + " current_tracer\t- function and latency tracers\n" + " available_tracers\t- list of configured tracers for current_tracer\n" + " buffer_size_kb\t- view and modify size of per cpu buffer\n" + " buffer_total_size_kb - view total size of all cpu buffers\n\n" + " trace_clock\t\t-change the clock used to order events\n" + " local: Per cpu clock but may not be synced across CPUs\n" + " global: Synced across CPUs but slows tracing down.\n" + " counter: Not a clock, but just an increment\n" + " uptime: Jiffy counter from time of boot\n" + " perf: Same clock that perf events use\n" +#ifdef CONFIG_X86_64 + " x86-tsc: TSC cycle counter\n" +#endif + "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n" + " tracing_cpumask\t- Limit which CPUs to trace\n" + " instances\t\t- Make sub-buffers with: mkdir instances/foo\n" + "\t\t\t Remove sub-buffer with rmdir\n" + " trace_options\t\t- Set format or modify how tracing happens\n" + "\t\t\t Disable an option by adding a suffix 'no' to the option name\n" +#ifdef CONFIG_DYNAMIC_FTRACE + "\n available_filter_functions - list of functions that can be filtered on\n" + " set_ftrace_filter\t- echo function name in here to only trace these functions\n" + " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" + " modules: Can select a group via module\n" + " Format: :mod:\n" + " example: echo :mod:ext3 > set_ftrace_filter\n" + " triggers: a command to perform when function is hit\n" + " Format: :[:count]\n" + " trigger: traceon, traceoff\n" + " enable_event::\n" + " disable_event::\n" +#ifdef CONFIG_STACKTRACE + " stacktrace\n" +#endif +#ifdef CONFIG_TRACER_SNAPSHOT + " snapshot\n" +#endif + " example: echo do_fault:traceoff > set_ftrace_filter\n" + " echo do_trap:traceoff:3 > set_ftrace_filter\n" + " The first one will disable tracing every time do_fault is hit\n" + " The second will disable tracing at most 3 times when do_trap is hit\n" + " The first time do trap is hit and it disables tracing, the counter\n" + " will decrement to 2. If tracing is already disabled, the counter\n" + " will not decrement. It only decrements when the trigger did work\n" + " To remove trigger without count:\n" + " echo '!: > set_ftrace_filter\n" + " To remove trigger with a count:\n" + " echo '!::0 > set_ftrace_filter\n" + " set_ftrace_notrace\t- echo function name in here to never trace.\n" + " accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" + " modules: Can select a group via module command :mod:\n" + " Does not accept triggers\n" +#endif /* CONFIG_DYNAMIC_FTRACE */ +#ifdef CONFIG_FUNCTION_TRACER + " set_ftrace_pid\t- Write pid(s) to only function trace those pids (function)\n" +#endif +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" + " max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n" +#endif +#ifdef CONFIG_TRACER_SNAPSHOT + "\n snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n" + "\t\t\t Read the contents for more information\n" +#endif +#ifdef CONFIG_STACKTRACE + " stack_trace\t\t- Shows the max stack trace when active\n" + " stack_max_size\t- Shows current max stack size that was traced\n" + "\t\t\t Write into this file to reset the max size (trigger a new trace)\n" +#ifdef CONFIG_DYNAMIC_FTRACE + " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n" +#endif +#endif /* CONFIG_STACKTRACE */ ; static ssize_t -- cgit v1.2.3 From 9607a869ee59594f3f7b9f3ac43a11d92bf3f960 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Mon, 8 Apr 2013 12:06:44 +0800 Subject: kernel: tracing: Use strlcpy instead of strncpy Use strlcpy() instead of strncpy() as it will always add a '\0' to the end of the string even if the buffer is smaller than what is being copied. Link: http://lkml.kernel.org/r/51624254.30301@asianux.com Signed-off-by: Chen Gang Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 4 ++-- kernel/trace/trace.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 25770824598f..548a1f7ea2c1 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3496,14 +3496,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata; static int __init set_ftrace_notrace(char *str) { - strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_notrace=", set_ftrace_notrace); static int __init set_ftrace_filter(char *str) { - strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_filter=", set_ftrace_filter); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 829b2bee24e8..07860b995752 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -125,7 +125,7 @@ static bool allocate_snapshot; static int __init set_cmdline_ftrace(char *str) { - strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); + strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ ring_buffer_expanded = true; @@ -164,7 +164,7 @@ static char *trace_boot_options __initdata; static int __init set_trace_boot_options(char *str) { - strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); trace_boot_options = trace_boot_options_buf; return 0; } -- cgit v1.2.3 From ed6f1c996bfe4b6e520cf7a74b51cd6988d84420 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 10 Apr 2013 09:18:12 +0900 Subject: tracing: Check return value of tracing_init_dentry() Check return value and bail out if it's NULL. Link: http://lkml.kernel.org/r/1365553093-10180-2-git-send-email-namhyung@kernel.org Cc: Frederic Weisbecker Cc: Namhyung Kim Cc: stable@vger.kernel.org Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 ++ kernel/trace/trace_stack.c | 2 ++ kernel/trace/trace_stat.c | 2 ++ 3 files changed, 6 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 07860b995752..72970793b40a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5953,6 +5953,8 @@ static __init int tracer_init_debugfs(void) trace_access_lock_init(); d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; init_tracer_debugfs(&global_trace, d_tracer); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index aab277b67fa9..8c3f37e2dc43 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -431,6 +431,8 @@ static __init int stack_trace_init(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; trace_create_file("stack_max_size", 0644, d_tracer, &max_stack_size, &stack_max_size_fops); diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 96cffb269e73..847f88a6194b 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -307,6 +307,8 @@ static int tracing_stat_init(void) struct dentry *d_tracing; d_tracing = tracing_init_dentry(); + if (!d_tracing) + return 0; stat_dir = debugfs_create_dir("trace_stat", d_tracing); if (!stat_dir) -- cgit v1.2.3