aboutsummaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig24
-rw-r--r--kernel/trace/ftrace.c585
-rw-r--r--kernel/trace/kmemtrace.c319
-rw-r--r--kernel/trace/ring_buffer.c1
-rw-r--r--kernel/trace/trace.c15
-rw-r--r--kernel/trace/trace.h10
-rw-r--r--kernel/trace/trace_branch.c4
-rw-r--r--kernel/trace/trace_functions_graph.c25
-rw-r--r--kernel/trace/trace_output.c10
-rw-r--r--kernel/trace/trace_output.h2
-rw-r--r--kernel/trace/trace_stat.c2
-rw-r--r--kernel/trace/trace_stat.h2
-rw-r--r--kernel/trace/trace_workqueue.c2
13 files changed, 869 insertions, 132 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8a4d7293104..23b96ebbf89 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -99,11 +99,11 @@ config FUNCTION_GRAPH_TRACER
help
Enable the kernel to trace a function at both its return
and its entry.
- It's first purpose is to trace the duration of functions and
- draw a call graph for each thread with some informations like
- the return value.
- This is done by setting the current return address on the current
- task structure into a stack of calls.
+ Its first purpose is to trace the duration of functions and
+ draw a call graph for each thread with some information like
+ the return value. This is done by setting the current return
+ address on the current task structure into a stack of calls.
+
config IRQSOFF_TRACER
bool "Interrupts-off Latency Tracer"
@@ -376,6 +376,20 @@ config DYNAMIC_FTRACE
were made. If so, it runs stop_machine (stops all CPUS)
and modifies the code to jump over the call to ftrace.
+config FUNCTION_PROFILER
+ bool "Kernel function profiler"
+ depends on FUNCTION_TRACER
+ default n
+ help
+ This option enables the kernel function profiler. A file is created
+ in debugfs called function_profile_enabled which defaults to zero.
+ When a 1 is echoed into this file profiling begins, and when a
+ zero is entered, profiling stops. A file in the trace_stats
+ directory called functions, that show the list of functions that
+ have been hit and their counters.
+
+ If in doubt, say N
+
config FTRACE_MCOUNT_RECORD
def_bool y
depends on DYNAMIC_FTRACE
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1752a63f37c..678e3d6caf8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -33,7 +33,8 @@
#include <asm/ftrace.h>
-#include "trace.h"
+#include "trace_output.h"
+#include "trace_stat.h"
#define FTRACE_WARN_ON(cond) \
do { \
@@ -68,7 +69,7 @@ static DEFINE_MUTEX(ftrace_lock);
static struct ftrace_ops ftrace_list_end __read_mostly =
{
- .func = ftrace_stub,
+ .func = ftrace_stub,
};
static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
@@ -240,6 +241,576 @@ static void ftrace_update_pid_func(void)
#endif
}
+#ifdef CONFIG_FUNCTION_PROFILER
+struct ftrace_profile {
+ struct hlist_node node;
+ unsigned long ip;
+ unsigned long counter;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ unsigned long long time;
+#endif
+};
+
+struct ftrace_profile_page {
+ struct ftrace_profile_page *next;
+ unsigned long index;
+ struct ftrace_profile records[];
+};
+
+struct ftrace_profile_stat {
+ atomic_t disabled;
+ struct hlist_head *hash;
+ struct ftrace_profile_page *pages;
+ struct ftrace_profile_page *start;
+ struct tracer_stat stat;
+};
+
+#define PROFILE_RECORDS_SIZE \
+ (PAGE_SIZE - offsetof(struct ftrace_profile_page, records))
+
+#define PROFILES_PER_PAGE \
+ (PROFILE_RECORDS_SIZE / sizeof(struct ftrace_profile))
+
+static int ftrace_profile_bits __read_mostly;
+static int ftrace_profile_enabled __read_mostly;
+
+/* ftrace_profile_lock - synchronize the enable and disable of the profiler */
+static DEFINE_MUTEX(ftrace_profile_lock);
+
+static DEFINE_PER_CPU(struct ftrace_profile_stat, ftrace_profile_stats);
+
+#define FTRACE_PROFILE_HASH_SIZE 1024 /* must be power of 2 */
+
+static void *
+function_stat_next(void *v, int idx)
+{
+ struct ftrace_profile *rec = v;
+ struct ftrace_profile_page *pg;
+
+ pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
+
+ again:
+ rec++;
+ if ((void *)rec >= (void *)&pg->records[pg->index]) {
+ pg = pg->next;
+ if (!pg)
+ return NULL;
+ rec = &pg->records[0];
+ if (!rec->counter)
+ goto again;
+ }
+
+ return rec;
+}
+
+static void *function_stat_start(struct tracer_stat *trace)
+{
+ struct ftrace_profile_stat *stat =
+ container_of(trace, struct ftrace_profile_stat, stat);
+
+ if (!stat || !stat->start)
+ return NULL;
+
+ return function_stat_next(&stat->start->records[0], 0);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* function graph compares on total time */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->time < b->time)
+ return -1;
+ if (a->time > b->time)
+ return 1;
+ else
+ return 0;
+}
+#else
+/* not function graph compares against hits */
+static int function_stat_cmp(void *p1, void *p2)
+{
+ struct ftrace_profile *a = p1;
+ struct ftrace_profile *b = p2;
+
+ if (a->counter < b->counter)
+ return -1;
+ if (a->counter > b->counter)
+ return 1;
+ else
+ return 0;
+}
+#endif
+
+static int function_stat_headers(struct seq_file *m)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " Function "
+ "Hit Time Avg\n"
+ " -------- "
+ "--- ---- ---\n");
+#else
+ seq_printf(m, " Function Hit\n"
+ " -------- ---\n");
+#endif
+ return 0;
+}
+
+static int function_stat_show(struct seq_file *m, void *v)
+{
+ struct ftrace_profile *rec = v;
+ char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ static DEFINE_MUTEX(mutex);
+ static struct trace_seq s;
+ unsigned long long avg;
+#endif
+
+ kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+ seq_printf(m, " %-30.30s %10lu", str, rec->counter);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ seq_printf(m, " ");
+ avg = rec->time;
+ do_div(avg, rec->counter);
+
+ mutex_lock(&mutex);
+ trace_seq_init(&s);
+ trace_print_graph_duration(rec->time, &s);
+ trace_seq_puts(&s, " ");
+ trace_print_graph_duration(avg, &s);
+ trace_print_seq(m, &s);
+ mutex_unlock(&mutex);
+#endif
+ seq_putc(m, '\n');
+
+ return 0;
+}
+
+static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+
+ pg = stat->pages = stat->start;
+
+ while (pg) {
+ memset(pg->records, 0, PROFILE_RECORDS_SIZE);
+ pg->index = 0;
+ pg = pg->next;
+ }
+
+ memset(stat->hash, 0,
+ FTRACE_PROFILE_HASH_SIZE * sizeof(struct hlist_head));
+}
+
+int ftrace_profile_pages_init(struct ftrace_profile_stat *stat)
+{
+ struct ftrace_profile_page *pg;
+ int functions;
+ int pages;
+ int i;
+
+ /* If we already allocated, do nothing */
+ if (stat->pages)
+ return 0;
+
+ stat->pages = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!stat->pages)
+ return -ENOMEM;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ functions = ftrace_update_tot_cnt;
+#else
+ /*
+ * We do not know the number of functions that exist because
+ * dynamic tracing is what counts them. With past experience
+ * we have around 20K functions. That should be more than enough.
+ * It is highly unlikely we will execute every function in
+ * the kernel.
+ */
+ functions = 20000;
+#endif
+
+ pg = stat->start = stat->pages;
+
+ pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE);
+
+ for (i = 0; i < pages; i++) {
+ pg->next = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!pg->next)
+ goto out_free;
+ pg = pg->next;
+ }
+
+ return 0;
+
+ out_free:
+ pg = stat->start;
+ while (pg) {
+ unsigned long tmp = (unsigned long)pg;
+
+ pg = pg->next;
+ free_page(tmp);
+ }
+
+ free_page((unsigned long)stat->pages);
+ stat->pages = NULL;
+ stat->start = NULL;
+
+ return -ENOMEM;
+}
+
+static int ftrace_profile_init_cpu(int cpu)
+{
+ struct ftrace_profile_stat *stat;
+ int size;
+
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ if (stat->hash) {
+ /* If the profile is already created, simply reset it */
+ ftrace_profile_reset(stat);
+ return 0;
+ }
+
+ /*
+ * We are profiling all functions, but usually only a few thousand
+ * functions are hit. We'll make a hash of 1024 items.
+ */
+ size = FTRACE_PROFILE_HASH_SIZE;
+
+ stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL);
+
+ if (!stat->hash)
+ return -ENOMEM;
+
+ if (!ftrace_profile_bits) {
+ size--;
+
+ for (; size; size >>= 1)
+ ftrace_profile_bits++;
+ }
+
+ /* Preallocate the function profiling pages */
+ if (ftrace_profile_pages_init(stat) < 0) {
+ kfree(stat->hash);
+ stat->hash = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int ftrace_profile_init(void)
+{
+ int cpu;
+ int ret = 0;
+
+ for_each_online_cpu(cpu) {
+ ret = ftrace_profile_init_cpu(cpu);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/* interrupts must be disabled */
+static struct ftrace_profile *
+ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec;
+ struct hlist_head *hhd;
+ struct hlist_node *n;
+ unsigned long key;
+
+ key = hash_long(ip, ftrace_profile_bits);
+ hhd = &stat->hash[key];
+
+ if (hlist_empty(hhd))
+ return NULL;
+
+ hlist_for_each_entry_rcu(rec, n, hhd, node) {
+ if (rec->ip == ip)
+ return rec;
+ }
+
+ return NULL;
+}
+
+static void ftrace_add_profile(struct ftrace_profile_stat *stat,
+ struct ftrace_profile *rec)
+{
+ unsigned long key;
+
+ key = hash_long(rec->ip, ftrace_profile_bits);
+ hlist_add_head_rcu(&rec->node, &stat->hash[key]);
+}
+
+/*
+ * The memory is already allocated, this simply finds a new record to use.
+ */
+static struct ftrace_profile *
+ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
+{
+ struct ftrace_profile *rec = NULL;
+
+ /* prevent recursion (from NMIs) */
+ if (atomic_inc_return(&stat->disabled) != 1)
+ goto out;
+
+ /*
+ * Try to find the function again since an NMI
+ * could have added it
+ */
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (rec)
+ goto out;
+
+ if (stat->pages->index == PROFILES_PER_PAGE) {
+ if (!stat->pages->next)
+ goto out;
+ stat->pages = stat->pages->next;
+ }
+
+ rec = &stat->pages->records[stat->pages->index++];
+ rec->ip = ip;
+ ftrace_add_profile(stat, rec);
+
+ out:
+ atomic_dec(&stat->disabled);
+
+ return rec;
+}
+
+static void
+function_profile_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_profile_stat *stat;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ if (!ftrace_profile_enabled)
+ return;
+
+ local_irq_save(flags);
+
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash)
+ goto out;
+
+ rec = ftrace_find_profiled_func(stat, ip);
+ if (!rec) {
+ rec = ftrace_profile_alloc(stat, ip);
+ if (!rec)
+ goto out;
+ }
+
+ rec->counter++;
+ out:
+ local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int profile_graph_entry(struct ftrace_graph_ent *trace)
+{
+ function_profile_call(trace->func, 0);
+ return 1;
+}
+
+static void profile_graph_return(struct ftrace_graph_ret *trace)
+{
+ struct ftrace_profile_stat *stat;
+ unsigned long long calltime;
+ struct ftrace_profile *rec;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ stat = &__get_cpu_var(ftrace_profile_stats);
+ if (!stat->hash)
+ goto out;
+
+ calltime = trace->rettime - trace->calltime;
+
+ if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
+ int index;
+
+ index = trace->depth;
+
+ /* Append this call time to the parent time to subtract */
+ if (index)
+ current->ret_stack[index - 1].subtime += calltime;
+
+ if (current->ret_stack[index].subtime < calltime)
+ calltime -= current->ret_stack[index].subtime;
+ else
+ calltime = 0;
+ }
+
+ rec = ftrace_find_profiled_func(stat, trace->func);
+ if (rec)
+ rec->time += calltime;
+
+ out:
+ local_irq_restore(flags);
+}
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_graph(&profile_graph_return,
+ &profile_graph_entry);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_graph();
+}
+#else
+static struct ftrace_ops ftrace_profile_ops __read_mostly =
+{
+ .func = function_profile_call,
+};
+
+static int register_ftrace_profiler(void)
+{
+ return register_ftrace_function(&ftrace_profile_ops);
+}
+
+static void unregister_ftrace_profiler(void)
+{
+ unregister_ftrace_function(&ftrace_profile_ops);
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static ssize_t
+ftrace_profile_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned long val;
+ char buf[64]; /* big enough to hold a number */
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ val = !!val;
+
+ mutex_lock(&ftrace_profile_lock);
+ if (ftrace_profile_enabled ^ val) {
+ if (val) {
+ ret = ftrace_profile_init();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+
+ ret = register_ftrace_profiler();
+ if (ret < 0) {
+ cnt = ret;
+ goto out;
+ }
+ ftrace_profile_enabled = 1;
+ } else {
+ ftrace_profile_enabled = 0;
+ unregister_ftrace_profiler();
+ }
+ }
+ out:
+ mutex_unlock(&ftrace_profile_lock);
+
+ filp->f_pos += cnt;
+
+ return cnt;
+}
+
+static ssize_t
+ftrace_profile_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64]; /* big enough to hold a number */
+ int r;
+
+ r = sprintf(buf, "%u\n", ftrace_profile_enabled);
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static const struct file_operations ftrace_profile_fops = {
+ .open = tracing_open_generic,
+ .read = ftrace_profile_read,
+ .write = ftrace_profile_write,
+};
+
+/* used to initialize the real stat files */
+static struct tracer_stat function_stats __initdata = {
+ .name = "functions",
+ .stat_start = function_stat_start,
+ .stat_next = function_stat_next,
+ .stat_cmp = function_stat_cmp,
+ .stat_headers = function_stat_headers,
+ .stat_show = function_stat_show
+};
+
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+ struct ftrace_profile_stat *stat;
+ struct dentry *entry;
+ char *name;
+ int ret;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ stat = &per_cpu(ftrace_profile_stats, cpu);
+
+ /* allocate enough for function name + cpu number */
+ name = kmalloc(32, GFP_KERNEL);
+ if (!name) {
+ /*
+ * The files created are permanent, if something happens
+ * we still do not free memory.
+ */
+ kfree(stat);
+ WARN(1,
+ "Could not allocate stat file for cpu %d\n",
+ cpu);
+ return;
+ }
+ stat->stat = function_stats;
+ snprintf(name, 32, "function%d", cpu);
+ stat->stat.name = name;
+ ret = register_stat_tracer(&stat->stat);
+ if (ret) {
+ WARN(1,
+ "Could not register function stat for cpu %d\n",
+ cpu);
+ kfree(name);
+ return;
+ }
+ }
+
+ entry = debugfs_create_file("function_profile_enabled", 0644,
+ d_tracer, NULL, &ftrace_profile_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'function_profile_enabled' entry\n");
+}
+
+#else /* CONFIG_FUNCTION_PROFILER */
+static void ftrace_profile_debugfs(struct dentry *d_tracer)
+{
+}
+#endif /* CONFIG_FUNCTION_PROFILER */
+
/* set when tracing only a pid */
struct pid *ftrace_pid_trace;
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
@@ -261,7 +832,6 @@ struct ftrace_func_probe {
struct rcu_head rcu;
};
-
enum {
FTRACE_ENABLE_CALLS = (1 << 0),
FTRACE_DISABLE_CALLS = (1 << 1),
@@ -1408,7 +1978,7 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
static struct ftrace_ops trace_probe_ops __read_mostly =
{
- .func = function_trace_probe_call,
+ .func = function_trace_probe_call,
};
static int ftrace_probe_registered;
@@ -2430,6 +3000,9 @@ static __init int ftrace_init_debugfs(void)
if (!entry)
pr_warning("Could not create debugfs "
"'set_ftrace_pid' entry\n");
+
+ ftrace_profile_debugfs(d_tracer);
+
return 0;
}
fs_initcall(ftrace_init_debugfs);
@@ -2719,6 +3292,9 @@ void unregister_ftrace_graph(void)
{
mutex_lock(&ftrace_lock);
+ if (!unlikely(atomic_read(&ftrace_graph_active)))
+ goto out;
+
atomic_dec(&ftrace_graph_active);
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
@@ -2726,6 +3302,7 @@ void unregister_ftrace_graph(void)
ftrace_shutdown(FTRACE_STOP_FUNC_RET);
unregister_pm_notifier(&ftrace_suspend_notifier);
+ out:
mutex_unlock(&ftrace_lock);
}
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index ae201b3eda8..5011f4d91e3 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -6,14 +6,16 @@
* Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
*/
-#include <linux/dcache.h>
+#include <linux/tracepoint.h>
+#include <linux/seq_file.h>
#include <linux/debugfs.h>
+#include <linux/dcache.h>
#include <linux/fs.h>
-#include <linux/seq_file.h>
+
#include <trace/kmemtrace.h>
-#include "trace.h"
#include "trace_output.h"
+#include "trace.h"
/* Select an alternative, minimalistic output than the original one */
#define TRACE_KMEM_OPT_MINIMAL 0x1
@@ -25,14 +27,156 @@ static struct tracer_opt kmem_opts[] = {
};
static struct tracer_flags kmem_tracer_flags = {
- .val = 0,
- .opts = kmem_opts
+ .val = 0,
+ .opts = kmem_opts
};
-
-static bool kmem_tracing_enabled __read_mostly;
static struct trace_array *kmemtrace_array;
+/* Trace allocations */
+static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
+ unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node)
+{
+ struct trace_array *tr = kmemtrace_array;
+ struct kmemtrace_alloc_entry *entry;
+ struct ring_buffer_event *event;
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, 0);
+
+ entry->ent.type = TRACE_KMEM_ALLOC;
+ entry->type_id = type_id;
+ entry->call_site = call_site;
+ entry->ptr = ptr;
+ entry->bytes_req = bytes_req;
+ entry->bytes_alloc = bytes_alloc;
+ entry->gfp_flags = gfp_flags;
+ entry->node = node;
+
+ ring_buffer_unlock_commit(tr->buffer, event);
+
+ trace_wake_up();
+}
+
+static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
+ unsigned long call_site,
+ const void *ptr)
+{
+ struct trace_array *tr = kmemtrace_array;
+ struct kmemtrace_free_entry *entry;
+ struct ring_buffer_event *event;
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, 0);
+
+ entry->ent.type = TRACE_KMEM_FREE;
+ entry->type_id = type_id;
+ entry->call_site = call_site;
+ entry->ptr = ptr;
+
+ ring_buffer_unlock_commit(tr->buffer, event);
+
+ trace_wake_up();
+}
+
+static void kmemtrace_kmalloc(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, -1);
+}
+
+static void kmemtrace_kmalloc_node(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+ const void *ptr,
+ size_t bytes_req,
+ size_t bytes_alloc,
+ gfp_t gfp_flags,
+ int node)
+{
+ kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
+ bytes_req, bytes_alloc, gfp_flags, node);
+}
+
+static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+{
+ kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
+}
+
+static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+{
+ kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
+}
+
+static int kmemtrace_start_probes(void)
+{
+ int err;
+
+ err = register_trace_kmalloc(kmemtrace_kmalloc);
+ if (err)
+ return err;
+ err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+ if (err)
+ return err;
+ err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+ if (err)
+ return err;
+ err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+ if (err)
+ return err;
+ err = register_trace_kfree(kmemtrace_kfree);
+ if (err)
+ return err;
+ err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+
+ return err;
+}
+
+static void kmemtrace_stop_probes(void)
+{
+ unregister_trace_kmalloc(kmemtrace_kmalloc);
+ unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+ unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
+ unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+ unregister_trace_kfree(kmemtrace_kfree);
+ unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+}
+
static int kmem_trace_init(struct trace_array *tr)
{
int cpu;
@@ -41,14 +185,14 @@ static int kmem_trace_init(struct trace_array *tr)
for_each_cpu_mask(cpu, cpu_possible_map)
tracing_reset(tr, cpu);
- kmem_tracing_enabled = true;
+ kmemtrace_start_probes();
return 0;
}
static void kmem_trace_reset(struct trace_array *tr)
{
- kmem_tracing_enabled = false;
+ kmemtrace_stop_probes();
}
static void kmemtrace_headers(struct seq_file *s)
@@ -66,47 +210,84 @@ static void kmemtrace_headers(struct seq_file *s)
}
/*
- * The two following functions give the original output from kmemtrace,
- * or something close to....perhaps they need some missing things
+ * The following functions give the original output from kmemtrace,
+ * plus the origin CPU, since reordering occurs in-kernel now.
*/
+
+#define KMEMTRACE_USER_ALLOC 0
+#define KMEMTRACE_USER_FREE 1
+
+struct kmemtrace_user_event {
+ u8 event_id;
+ u8 type_id;
+ u16 event_size;
+ u32 cpu;
+ u64 timestamp;
+ unsigned long call_site;
+ unsigned long ptr;
+};
+
+struct kmemtrace_user_event_alloc {
+ size_t bytes_req;
+ size_t bytes_alloc;
+ unsigned gfp_flags;
+ int node;
+};
+
static enum print_line_t
-kmemtrace_print_alloc_original(struct trace_iterator *iter,
- struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc_user(struct trace_iterator *iter,
+ struct kmemtrace_alloc_entry *entry)
{
+ struct kmemtrace_user_event_alloc *ev_alloc;
struct trace_seq *s = &iter->seq;
- int ret;
+ struct kmemtrace_user_event *ev;
+
+ ev = trace_seq_reserve(s, sizeof(*ev));
+ if (!ev)
+ return TRACE_TYPE_PARTIAL_LINE;
- /* Taken from the old linux/kmemtrace.h */
- ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu "
- "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
- entry->type_id, entry->call_site, (unsigned long) entry->ptr,
- (unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc,
- (unsigned long) entry->gfp_flags, entry->node);
+ ev->event_id = KMEMTRACE_USER_ALLOC;
+ ev->type_id = entry->type_id;
+ ev->event_size = sizeof(*ev) + sizeof(*ev_alloc);
+ ev->cpu = iter->cpu;
+ ev->timestamp = iter->ts;
+ ev->call_site = entry->call_site;
+ ev->ptr = (unsigned long)entry->ptr;
- if (!ret)
+ ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc));
+ if (!ev_alloc)
return TRACE_TYPE_PARTIAL_LINE;
+ ev_alloc->bytes_req = entry->bytes_req;
+ ev_alloc->bytes_alloc = entry->bytes_alloc;
+ ev_alloc->gfp_flags = entry->gfp_flags;
+ ev_alloc->node = entry->node;
+
return TRACE_TYPE_HANDLED;
}
static enum print_line_t
-kmemtrace_print_free_original(struct trace_iterator *iter,
- struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_user(struct trace_iterator *iter,
+ struct kmemtrace_free_entry *entry)
{
struct trace_seq *s = &iter->seq;
- int ret;
+ struct kmemtrace_user_event *ev;
- /* Taken from the old linux/kmemtrace.h */
- ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n",
- entry->type_id, entry->call_site, (unsigned long) entry->ptr);
-
- if (!ret)
+ ev = trace_seq_reserve(s, sizeof(*ev));
+ if (!ev)
return TRACE_TYPE_PARTIAL_LINE;
+ ev->event_id = KMEMTRACE_USER_FREE;
+ ev->type_id = entry->type_id;
+ ev->event_size = sizeof(*ev);
+ ev->cpu = iter->cpu;
+ ev->timestamp = iter->ts;
+ ev->call_site = entry->call_site;
+ ev->ptr = (unsigned long)entry->ptr;
+
return TRACE_TYPE_HANDLED;
}
-
/* The two other following provide a more minimalistic output */
static enum print_line_t
kmemtrace_print_alloc_compress(struct trace_iterator *iter,
@@ -178,7 +359,7 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
static enum print_line_t
kmemtrace_print_free_compress(struct trace_iterator *iter,
- struct kmemtrace_free_entry *entry)
+ struct kmemtrace_free_entry *entry)
{
struct trace_seq *s = &iter->seq;
int ret;
@@ -239,20 +420,22 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
switch (entry->type) {
case TRACE_KMEM_ALLOC: {
struct kmemtrace_alloc_entry *field;
+
trace_assign_type(field, entry);
if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
return kmemtrace_print_alloc_compress(iter, field);
else
- return kmemtrace_print_alloc_original(iter, field);
+ return kmemtrace_print_alloc_user(iter, field);
}
case TRACE_KMEM_FREE: {
struct kmemtrace_free_entry *field;
+
trace_assign_type(field, entry);
if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
return kmemtrace_print_free_compress(iter, field);
else
- return kmemtrace_print_free_original(iter, field);
+ return kmemtrace_print_free_user(iter, field);
}
default:
@@ -260,70 +443,13 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
}
}
-/* Trace allocations */
-void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
- unsigned long call_site,
- const void *ptr,
- size_t bytes_req,
- size_t bytes_alloc,
- gfp_t gfp_flags,
- int node)
-{
- struct ring_buffer_event *event;
- struct kmemtrace_alloc_entry *entry;
- struct trace_array *tr = kmemtrace_array;
-
- if (!kmem_tracing_enabled)
- return;
-
- event = trace_buffer_lock_reserve(tr, TRACE_KMEM_ALLOC,
- sizeof(*entry), 0, 0);
- if (!event)
- return;
- entry = ring_buffer_event_data(event);
-
- entry->call_site = call_site;
- entry->ptr = ptr;
- entry->bytes_req = bytes_req;
- entry->bytes_alloc = bytes_alloc;
- entry->gfp_flags = gfp_flags;
- entry->node = node;
-
- trace_buffer_unlock_commit(tr, event, 0, 0);
-}
-EXPORT_SYMBOL(kmemtrace_mark_alloc_node);
-
-void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
- unsigned long call_site,
- const void *ptr)
-{
- struct ring_buffer_event *event;
- struct kmemtrace_free_entry *entry;
- struct trace_array *tr = kmemtrace_array;
-
- if (!kmem_tracing_enabled)
- return;
-
- event = trace_buffer_lock_reserve(tr, TRACE_KMEM_FREE,
- sizeof(*entry), 0, 0);
- if (!event)
- return;
- entry = ring_buffer_event_data(event);
- entry->type_id = type_id;
- entry->call_site = call_site;
- entry->ptr = ptr;
-
- trace_buffer_unlock_commit(tr, event, 0, 0);
-}
-EXPORT_SYMBOL(kmemtrace_mark_free);
-
static struct tracer kmem_tracer __read_mostly = {
- .name = "kmemtrace",
- .init = kmem_trace_init,
- .reset = kmem_trace_reset,
- .print_line = kmemtrace_print_line,
- .print_header = kmemtrace_headers,
- .flags = &kmem_tracer_flags
+ .name = "kmemtrace",
+ .init = kmem_trace_init,
+ .reset = kmem_trace_reset,
+ .print_line = kmemtrace_print_line,
+ .print_header = kmemtrace_headers,
+ .flags = &kmem_tracer_flags
};
void kmemtrace_init(void)
@@ -335,5 +461,4 @@ static int __init init_kmem_tracer(void)
{
return register_tracer(&kmem_tracer);
}
-
device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index edce2ff3894..960cbf44c84 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -563,7 +563,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
struct list_head *head = &cpu_buffer->pages;
struct buffer_page *bpage, *tmp;
- list_del_init(&cpu_buffer->reader_page->list);
free_buffer_page(cpu_buffer->reader_page);
list_for_each_entry_safe(bpage, tmp, head, list) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9d28476a985..32653c8c6e2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -255,7 +255,8 @@ 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_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
+ TRACE_ITER_GRAPH_TIME;
/**
* trace_wake_up - wake up tasks waiting for trace input
@@ -317,6 +318,7 @@ static const char *trace_options[] = {
"latency-format",
"global-clock",
"sleep-time",
+ "graph-time",
NULL
};
@@ -402,17 +404,6 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
return cnt;
}
-static void
-trace_print_seq(struct seq_file *m, struct trace_seq *s)
-{
- int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
-
- s->buffer[len] = 0;
- seq_puts(m, s->buffer);
-
- trace_seq_init(s);
-}
-
/**
* update_max_tr - snapshot all trace buffers from global_trace to max_tr
* @tr: tracer
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0d81a4a2a4a..47aa6d0c97a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -182,6 +182,12 @@ struct trace_power {
struct power_trace state_data;
};
+enum kmemtrace_type_id {
+ KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */
+ KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */
+ KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */
+};
+
struct kmemtrace_alloc_entry {
struct trace_entry ent;
enum kmemtrace_type_id type_id;
@@ -607,6 +613,8 @@ extern unsigned long trace_flags;
/* Standard output formatting function used for function return traces */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
@@ -638,7 +646,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
return 1;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
-
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
static inline enum print_line_t
print_graph_function(struct trace_iterator *iter)
@@ -686,6 +693,7 @@ enum trace_iterator_flags {
TRACE_ITER_LATENCY_FMT = 0x40000,
TRACE_ITER_GLOBAL_CLK = 0x80000,
TRACE_ITER_SLEEP_TIME = 0x100000,
+ TRACE_ITER_GRAPH_TIME = 0x200000,
};
/*
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index ad8c22efff4..e6e32912ffb 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -263,7 +263,7 @@ static int branch_stat_show(struct seq_file *m, void *v)
return 0;
}
-static void *annotated_branch_stat_start(void)
+static void *annotated_branch_stat_start(struct tracer_stat *trace)
{
return __start_annotated_branch_profile;
}
@@ -338,7 +338,7 @@ static int all_branch_stat_headers(struct seq_file *m)
return 0;
}
-static void *all_branch_stat_start(void)
+static void *all_branch_stat_start(struct tracer_stat *trace)
{
return __start_branch_profile;
}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d28687e7b3a..10f6ad7d85f 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -78,13 +78,14 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
current->ret_stack[index].ret = ret;
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = calltime;
+ current->ret_stack[index].subtime = 0;
*depth = index;
return 0;
}
/* Retrieve a function return address to the trace stack on thread info.*/
-void
+static void
ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
{
int index;
@@ -104,9 +105,6 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
trace->calltime = current->ret_stack[index].calltime;
trace->overrun = atomic_read(&current->trace_overrun);
trace->depth = index;
- barrier();
- current->curr_ret_stack--;
-
}
/*
@@ -121,6 +119,8 @@ unsigned long ftrace_return_to_handler(void)
ftrace_pop_return_trace(&trace, &ret);
trace.rettime = trace_clock_local();
ftrace_graph_return(&trace);
+ barrier();
+ current->curr_ret_stack--;
if (unlikely(!ret)) {
ftrace_graph_stop();
@@ -426,8 +426,8 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t
-print_graph_duration(unsigned long long duration, struct trace_seq *s)
+enum print_line_t
+trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
{
unsigned long nsecs_rem = do_div(duration, 1000);
/* log10(ULONG_MAX) + '\0' */
@@ -464,12 +464,23 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_print_graph_duration(duration, s);
+ if (ret != TRACE_TYPE_HANDLED)
+ return ret;
ret = trace_seq_printf(s, "| ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
- return TRACE_TYPE_HANDLED;
+ return TRACE_TYPE_HANDLED;
}
/* Case of a leaf function on its call entry */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 64b54a59c55..0e70fb07ca7 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -19,6 +19,16 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
static int next_event_type = __TRACE_LAST_TYPE + 1;
+void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+ int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+
+ s->buffer[len] = 0;
+ seq_puts(m, s->buffer);
+
+ trace_seq_init(s);
+}
+
enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index e0bde39c2dd..91630217fb4 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -20,6 +20,8 @@ trace_print_bprintk_msg_only(struct trace_iterator *iter);
extern enum print_line_t
trace_print_printk_msg_only(struct trace_iterator *iter);
+extern void trace_print_seq(struct seq_file *m, struct trace_seq *s);
+
extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
__attribute__ ((format (printf, 2, 3)));
extern int
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index acdebd771a9..fdde3a4a94c 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -85,7 +85,7 @@ static int stat_seq_init(struct tracer_stat_session *session)
if (!ts->stat_cmp)
ts->stat_cmp = dummy_cmp;
- stat = ts->stat_start();
+ stat = ts->stat_start(ts);
if (!stat)
goto exit;
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index 202274cf7f3..f3546a2cd82 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -12,7 +12,7 @@ struct tracer_stat {
/* The name of your stat file */
const char *name;
/* Iteration over statistic entries */
- void *(*stat_start)(void);
+ void *(*stat_start)(struct tracer_stat *trace);
void *(*stat_next)(void *prev, int idx);
/* Compare two entries for stats sorting */
int (*stat_cmp)(void *p1, void *p2);
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 797201e4a13..984b9175c13 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -152,7 +152,7 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
return ret;
}
-static void *workqueue_stat_start(void)
+static void *workqueue_stat_start(struct tracer_stat *trace)
{
int cpu;
void *ret = NULL;
generated by cgit v1.2.3 (git 2.25.1) at 2024-08-07 01:21:37 +0000