summaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/blktrace.c6
-rw-r--r--kernel/trace/bpf_trace.c133
-rw-r--r--kernel/trace/ftrace.c62
-rw-r--r--kernel/trace/power-traces.c2
-rw-r--r--kernel/trace/ring_buffer.c35
-rw-r--r--kernel/trace/trace.c76
-rw-r--r--kernel/trace/trace.h113
-rw-r--r--kernel/trace/trace_event_perf.c43
-rw-r--r--kernel/trace/trace_events.c27
-rw-r--r--kernel/trace/trace_events_filter.c12
-rw-r--r--kernel/trace/trace_events_trigger.c88
-rw-r--r--kernel/trace/trace_functions.c6
-rw-r--r--kernel/trace/trace_functions_graph.c7
-rw-r--r--kernel/trace/trace_irqsoff.c9
-rw-r--r--kernel/trace/trace_kprobe.c56
-rw-r--r--kernel/trace/trace_mmiotrace.c2
-rw-r--r--kernel/trace/trace_nop.c4
-rw-r--r--kernel/trace/trace_output.c10
-rw-r--r--kernel/trace/trace_printk.c3
-rw-r--r--kernel/trace/trace_probe.c4
-rw-r--r--kernel/trace/trace_stat.c3
-rw-r--r--kernel/trace/trace_syscalls.c40
-rw-r--r--kernel/trace/trace_uprobe.c7
23 files changed, 516 insertions, 232 deletions
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 2aeb6ff..9aef865 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1349,6 +1349,7 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
if (t->action == BLK_TN_MESSAGE) {
log_action(iter, long_act ? "message" : "m");
blk_log_msg(s, iter->ent);
+ return trace_handle_return(s);
}
if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
@@ -1437,12 +1438,12 @@ static struct trace_event trace_blk_event = {
static int __init init_blk_tracer(void)
{
if (!register_trace_event(&trace_blk_event)) {
- pr_warning("Warning: could not register block events\n");
+ pr_warn("Warning: could not register block events\n");
return 1;
}
if (register_tracer(&blk_tracer) != 0) {
- pr_warning("Warning: could not register the block tracer\n");
+ pr_warn("Warning: could not register the block tracer\n");
unregister_trace_event(&trace_blk_event);
return 1;
}
@@ -1551,6 +1552,7 @@ static const struct {
{ BLK_TC_COMPLETE, "complete" },
{ BLK_TC_FS, "fs" },
{ BLK_TC_PC, "pc" },
+ { BLK_TC_NOTIFY, "notify" },
{ BLK_TC_AHEAD, "ahead" },
{ BLK_TC_META, "meta" },
{ BLK_TC_DISCARD, "discard" },
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 326a75e..780bcbe 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -13,8 +13,6 @@
#include <linux/ctype.h>
#include "trace.h"
-static DEFINE_PER_CPU(int, bpf_prog_active);
-
/**
* trace_call_bpf - invoke BPF program
* @prog: BPF program
@@ -64,17 +62,21 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
void *dst = (void *) (long) r1;
- int size = (int) r2;
+ int ret, size = (int) r2;
void *unsafe_ptr = (void *) (long) r3;
- return probe_kernel_read(dst, unsafe_ptr, size);
+ ret = probe_kernel_read(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+
+ return ret;
}
static const struct bpf_func_proto bpf_probe_read_proto = {
.func = bpf_probe_read,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_STACK,
+ .arg1_type = ARG_PTR_TO_RAW_STACK,
.arg2_type = ARG_CONST_STACK_SIZE,
.arg3_type = ARG_ANYTHING,
};
@@ -223,11 +225,12 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
.arg2_type = ARG_ANYTHING,
};
-static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
{
struct pt_regs *regs = (struct pt_regs *) (long) r1;
struct bpf_map *map = (struct bpf_map *) (long) r2;
struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u64 index = flags & BPF_F_INDEX_MASK;
void *data = (void *) (long) r4;
struct perf_sample_data sample_data;
struct perf_event *event;
@@ -237,6 +240,10 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
.data = data,
};
+ if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+ return -EINVAL;
+ if (index == BPF_F_CURRENT_CPU)
+ index = raw_smp_processor_id();
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
@@ -270,7 +277,34 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
.arg5_type = ARG_CONST_STACK_SIZE,
};
-static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
+
+static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
+{
+ struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
+
+ perf_fetch_caller_regs(regs);
+
+ return bpf_perf_event_output((long)regs, r2, flags, r4, size);
+}
+
+static const struct bpf_func_proto bpf_event_output_proto = {
+ .func = bpf_event_output,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_STACK,
+ .arg5_type = ARG_CONST_STACK_SIZE,
+};
+
+const struct bpf_func_proto *bpf_get_event_output_proto(void)
+{
+ return &bpf_event_output_proto;
+}
+
+static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
case BPF_FUNC_map_lookup_elem:
@@ -297,10 +331,20 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
return &bpf_get_smp_processor_id_proto;
case BPF_FUNC_perf_event_read:
return &bpf_perf_event_read_proto;
+ default:
+ return NULL;
+ }
+}
+
+static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
case BPF_FUNC_perf_event_output:
return &bpf_perf_event_output_proto;
+ case BPF_FUNC_get_stackid:
+ return &bpf_get_stackid_proto;
default:
- return NULL;
+ return tracing_func_proto(func_id);
}
}
@@ -332,9 +376,82 @@ static struct bpf_prog_type_list kprobe_tl = {
.type = BPF_PROG_TYPE_KPROBE,
};
+static u64 bpf_perf_event_output_tp(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+{
+ /*
+ * r1 points to perf tracepoint buffer where first 8 bytes are hidden
+ * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it
+ * from there and call the same bpf_perf_event_output() helper
+ */
+ u64 ctx = *(long *)(uintptr_t)r1;
+
+ return bpf_perf_event_output(ctx, r2, index, r4, size);
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
+ .func = bpf_perf_event_output_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_STACK,
+ .arg5_type = ARG_CONST_STACK_SIZE,
+};
+
+static u64 bpf_get_stackid_tp(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ u64 ctx = *(long *)(uintptr_t)r1;
+
+ return bpf_get_stackid(ctx, r2, r3, r4, r5);
+}
+
+static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
+ .func = bpf_get_stackid_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_perf_event_output:
+ return &bpf_perf_event_output_proto_tp;
+ case BPF_FUNC_get_stackid:
+ return &bpf_get_stackid_proto_tp;
+ default:
+ return tracing_func_proto(func_id);
+ }
+}
+
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+ if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
+ return false;
+ if (type != BPF_READ)
+ return false;
+ if (off % size != 0)
+ return false;
+ return true;
+}
+
+static const struct bpf_verifier_ops tracepoint_prog_ops = {
+ .get_func_proto = tp_prog_func_proto,
+ .is_valid_access = tp_prog_is_valid_access,
+};
+
+static struct bpf_prog_type_list tracepoint_tl = {
+ .ops = &tracepoint_prog_ops,
+ .type = BPF_PROG_TYPE_TRACEPOINT,
+};
+
static int __init register_kprobe_prog_ops(void)
{
bpf_register_prog_type(&kprobe_tl);
+ bpf_register_prog_type(&tracepoint_tl);
return 0;
}
late_initcall(register_kprobe_prog_ops);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 57a6eea..7e8d792 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1030,8 +1030,7 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
for_each_possible_cpu(cpu) {
stat = &per_cpu(ftrace_profile_stats, cpu);
- /* allocate enough for function name + cpu number */
- name = kmalloc(32, GFP_KERNEL);
+ name = kasprintf(GFP_KERNEL, "function%d", cpu);
if (!name) {
/*
* The files created are permanent, if something happens
@@ -1043,7 +1042,6 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
return;
}
stat->stat = function_stats;
- snprintf(name, 32, "function%d", cpu);
stat->stat.name = name;
ret = register_stat_tracer(&stat->stat);
if (ret) {
@@ -1058,8 +1056,7 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
entry = tracefs_create_file("function_profile_enabled", 0644,
d_tracer, NULL, &ftrace_profile_fops);
if (!entry)
- pr_warning("Could not create tracefs "
- "'function_profile_enabled' entry\n");
+ pr_warn("Could not create tracefs 'function_profile_enabled' entry\n");
}
#else /* CONFIG_FUNCTION_PROFILER */
@@ -1533,7 +1530,19 @@ static int ftrace_cmp_recs(const void *a, const void *b)
return 0;
}
-static unsigned long ftrace_location_range(unsigned long start, unsigned long end)
+/**
+ * ftrace_location_range - return the first address of a traced location
+ * if it touches the given ip range
+ * @start: start of range to search.
+ * @end: end of range to search (inclusive). @end points to the last byte
+ * to check.
+ *
+ * Returns rec->ip if the related ftrace location is a least partly within
+ * the given address range. That is, the first address of the instruction
+ * that is either a NOP or call to the function tracer. It checks the ftrace
+ * internal tables to determine if the address belongs or not.
+ */
+unsigned long ftrace_location_range(unsigned long start, unsigned long end)
{
struct ftrace_page *pg;
struct dyn_ftrace *rec;
@@ -1610,7 +1619,7 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
return keep_regs;
}
-static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
+static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
int filter_hash,
bool inc)
{
@@ -1618,12 +1627,13 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
struct ftrace_hash *other_hash;
struct ftrace_page *pg;
struct dyn_ftrace *rec;
+ bool update = false;
int count = 0;
int all = 0;
/* Only update if the ops has been registered */
if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
- return;
+ return false;
/*
* In the filter_hash case:
@@ -1650,7 +1660,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
* then there's nothing to do.
*/
if (ftrace_hash_empty(hash))
- return;
+ return false;
}
do_for_each_ftrace_rec(pg, rec) {
@@ -1694,7 +1704,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
if (inc) {
rec->flags++;
if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
- return;
+ return false;
/*
* If there's only a single callback registered to a
@@ -1720,7 +1730,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
rec->flags |= FTRACE_FL_REGS;
} else {
if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
- return;
+ return false;
rec->flags--;
/*
@@ -1753,22 +1763,28 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
*/
}
count++;
+
+ /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */
+ update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;
+
/* Shortcut, if we handled all records, we are done. */
if (!all && count == hash->count)
- return;
+ return update;
} while_for_each_ftrace_rec();
+
+ return update;
}
-static void ftrace_hash_rec_disable(struct ftrace_ops *ops,
+static bool ftrace_hash_rec_disable(struct ftrace_ops *ops,
int filter_hash)
{
- __ftrace_hash_rec_update(ops, filter_hash, 0);
+ return __ftrace_hash_rec_update(ops, filter_hash, 0);
}
-static void ftrace_hash_rec_enable(struct ftrace_ops *ops,
+static bool ftrace_hash_rec_enable(struct ftrace_ops *ops,
int filter_hash)
{
- __ftrace_hash_rec_update(ops, filter_hash, 1);
+ return __ftrace_hash_rec_update(ops, filter_hash, 1);
}
static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops,
@@ -2314,8 +2330,8 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec)
if (rec->flags & FTRACE_FL_TRAMP_EN) {
ops = ftrace_find_tramp_ops_curr(rec);
if (FTRACE_WARN_ON(!ops)) {
- pr_warning("Bad trampoline accounting at: %p (%pS)\n",
- (void *)rec->ip, (void *)rec->ip);
+ pr_warn("Bad trampoline accounting at: %p (%pS)\n",
+ (void *)rec->ip, (void *)rec->ip);
/* Ftrace is shutting down, return anything */
return (unsigned long)FTRACE_ADDR;
}
@@ -2644,7 +2660,6 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
return ret;
ftrace_start_up++;
- command |= FTRACE_UPDATE_CALLS;
/*
* Note that ftrace probes uses this to start up
@@ -2665,7 +2680,8 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
return ret;
}
- ftrace_hash_rec_enable(ops, 1);
+ if (ftrace_hash_rec_enable(ops, 1))
+ command |= FTRACE_UPDATE_CALLS;
ftrace_startup_enable(command);
@@ -2695,11 +2711,11 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
/* Disabling ipmodify never fails */
ftrace_hash_ipmodify_disable(ops);
- ftrace_hash_rec_disable(ops, 1);
- ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+ if (ftrace_hash_rec_disable(ops, 1))
+ command |= FTRACE_UPDATE_CALLS;
- command |= FTRACE_UPDATE_CALLS;
+ ops->flags &= ~FTRACE_OPS_FL_ENABLED;
if (saved_ftrace_func != ftrace_trace_function) {
saved_ftrace_func = ftrace_trace_function;
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index eb4220a..0c7dee2 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -15,4 +15,6 @@
EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
+EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 95181e3..9c14373 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -437,7 +437,7 @@ struct ring_buffer_per_cpu {
raw_spinlock_t reader_lock; /* serialize readers */
arch_spinlock_t lock;
struct lock_class_key lock_key;
- unsigned int nr_pages;
+ unsigned long nr_pages;
unsigned int current_context;
struct list_head *pages;
struct buffer_page *head_page; /* read from head */
@@ -458,7 +458,7 @@ struct ring_buffer_per_cpu {
u64 write_stamp;
u64 read_stamp;
/* ring buffer pages to update, > 0 to add, < 0 to remove */
- int nr_pages_to_update;
+ long nr_pages_to_update;
struct list_head new_pages; /* new pages to add */
struct work_struct update_pages_work;
struct completion update_done;
@@ -1128,10 +1128,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
return 0;
}
-static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu)
+static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
{
- int i;
struct buffer_page *bpage, *tmp;
+ long i;
for (i = 0; i < nr_pages; i++) {
struct page *page;
@@ -1168,7 +1168,7 @@ free_pages:
}
static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned nr_pages)
+ unsigned long nr_pages)
{
LIST_HEAD(pages);
@@ -1193,7 +1193,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
}
static struct ring_buffer_per_cpu *
-rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, long nr_pages, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct buffer_page *bpage;
@@ -1293,8 +1293,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
struct lock_class_key *key)
{
struct ring_buffer *buffer;
+ long nr_pages;
int bsize;
- int cpu, nr_pages;
+ int cpu;
/* keep it in its own cache line */
buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
@@ -1420,12 +1421,12 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage)
}
static int
-rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
{
struct list_head *tail_page, *to_remove, *next_page;
struct buffer_page *to_remove_page, *tmp_iter_page;
struct buffer_page *last_page, *first_page;
- unsigned int nr_removed;
+ unsigned long nr_removed;
unsigned long head_bit;
int page_entries;
@@ -1642,7 +1643,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
int cpu_id)
{
struct ring_buffer_per_cpu *cpu_buffer;
- unsigned nr_pages;
+ unsigned long nr_pages;
int cpu, err = 0;
/*
@@ -1656,14 +1657,13 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
!cpumask_test_cpu(cpu_id, buffer->cpumask))
return size;
- size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
- size *= BUF_PAGE_SIZE;
+ nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
/* we need a minimum of two pages */
- if (size < BUF_PAGE_SIZE * 2)
- size = BUF_PAGE_SIZE * 2;
+ if (nr_pages < 2)
+ nr_pages = 2;
- nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+ size = nr_pages * BUF_PAGE_SIZE;
/*
* Don't succeed if resizing is disabled, as a reader might be
@@ -4640,8 +4640,9 @@ static int rb_cpu_notify(struct notifier_block *self,
struct ring_buffer *buffer =
container_of(self, struct ring_buffer, cpu_notify);
long cpu = (long)hcpu;
- int cpu_i, nr_pages_same;
- unsigned int nr_pages;
+ long nr_pages_same;
+ int cpu_i;
+ unsigned long nr_pages;
switch (action) {
case CPU_UP_PREPARE:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d929340..a2f0b9f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -74,11 +74,6 @@ static struct tracer_opt dummy_tracer_opt[] = {
{ }
};
-static struct tracer_flags dummy_tracer_flags = {
- .val = 0,
- .opts = dummy_tracer_opt
-};
-
static int
dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
@@ -1258,12 +1253,22 @@ int __init register_tracer(struct tracer *type)
if (!type->set_flag)
type->set_flag = &dummy_set_flag;
- if (!type->flags)
- type->flags = &dummy_tracer_flags;
- else
+ if (!type->flags) {
+ /*allocate a dummy tracer_flags*/
+ type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL);
+ if (!type->flags) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ type->flags->val = 0;
+ type->flags->opts = dummy_tracer_opt;
+ } else
if (!type->flags->opts)
type->flags->opts = dummy_tracer_opt;
+ /* store the tracer for __set_tracer_option */
+ type->flags->trace = type;
+
ret = run_tracer_selftest(type);
if (ret < 0)
goto out;
@@ -1659,6 +1664,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
#else
TRACE_FLAG_IRQS_NOSUPPORT |
#endif
+ ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) |
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
@@ -2071,20 +2077,20 @@ void trace_printk_init_buffers(void)
/* trace_printk() is for debug use only. Don't use it in production. */
- pr_warning("\n");
- pr_warning("**********************************************************\n");
- pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n");
- pr_warning("** **\n");
- pr_warning("** trace_printk() being used. Allocating extra memory. **\n");
- pr_warning("** **\n");
- pr_warning("** This means that this is a DEBUG kernel and it is **\n");
- pr_warning("** unsafe for production use. **\n");
- pr_warning("** **\n");
- pr_warning("** If you see this message and you are not debugging **\n");
- pr_warning("** the kernel, report this immediately to your vendor! **\n");
- pr_warning("** **\n");
- pr_warning("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n");
- pr_warning("**********************************************************\n");
+ pr_warn("\n");
+ pr_warn("**********************************************************\n");
+ pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n");
+ pr_warn("** **\n");
+ pr_warn("** trace_printk() being used. Allocating extra memory. **\n");
+ pr_warn("** **\n");
+ pr_warn("** This means that this is a DEBUG kernel and it is **\n");
+ pr_warn("** unsafe for production use. **\n");
+ pr_warn("** **\n");
+ pr_warn("** If you see this message and you are not debugging **\n");
+ pr_warn("** the kernel, report this immediately to your vendor! **\n");
+ pr_warn("** **\n");
+ pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n");
+ pr_warn("**********************************************************\n");
/* Expand the buffers to set size */
tracing_update_buffers();
@@ -3505,7 +3511,7 @@ static int __set_tracer_option(struct trace_array *tr,
struct tracer_flags *tracer_flags,
struct tracer_opt *opts, int neg)
{
- struct tracer *trace = tr->current_trace;
+ struct tracer *trace = tracer_flags->trace;
int ret;
ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg);
@@ -4101,7 +4107,7 @@ trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start,
*/
map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL);
if (!map_array) {
- pr_warning("Unable to allocate trace enum mapping\n");
+ pr_warn("Unable to allocate trace enum mapping\n");
return;
}
@@ -4949,7 +4955,10 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
spd.nr_pages = i;
- ret = splice_to_pipe(pipe, &spd);
+ if (i)
+ ret = splice_to_pipe(pipe, &spd);
+ else
+ ret = 0;
out:
splice_shrink_spd(&spd);
return ret;
@@ -6131,7 +6140,7 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
snprintf(cpu_dir, 30, "cpu%ld", cpu);
d_cpu = tracefs_create_dir(cpu_dir, d_percpu);
if (!d_cpu) {
- pr_warning("Could not create tracefs '%s' entry\n", cpu_dir);
+ pr_warn("Could not create tracefs '%s' entry\n", cpu_dir);
return;
}
@@ -6318,7 +6327,7 @@ struct dentry *trace_create_file(const char *name,
ret = tracefs_create_file(name, mode, parent, data, fops);
if (!ret)
- pr_warning("Could not create tracefs '%s' entry\n", name);
+ pr_warn("Could not create tracefs '%s' entry\n", name);
return ret;
}
@@ -6337,7 +6346,7 @@ static struct dentry *trace_options_init_dentry(struct trace_array *tr)
tr->options = tracefs_create_dir("options", d_tracer);
if (!tr->options) {
- pr_warning("Could not create tracefs directory 'options'\n");
+ pr_warn("Could not create tracefs directory 'options'\n");
return NULL;
}
@@ -6391,11 +6400,8 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer)
return;
for (i = 0; i < tr->nr_topts; i++) {
- /*
- * Check if these flags have already been added.
- * Some tracers share flags.
- */
- if (tr->topts[i].tracer->flags == tracer->flags)
+ /* Make sure there's no duplicate flags. */
+ if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags))
return;
}
@@ -7248,8 +7254,8 @@ __init static int tracer_alloc_buffers(void)
if (trace_boot_clock) {
ret = tracing_set_clock(&global_trace, trace_boot_clock);
if (ret < 0)
- pr_warning("Trace clock %s not defined, going back to default\n",
- trace_boot_clock);
+ pr_warn("Trace clock %s not defined, going back to default\n",
+ trace_boot_clock);
}
/*
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8414fa4..3fff4ad 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -125,6 +125,7 @@ enum trace_flag_type {
TRACE_FLAG_HARDIRQ = 0x08,
TRACE_FLAG_SOFTIRQ = 0x10,
TRACE_FLAG_PREEMPT_RESCHED = 0x20,
+ TRACE_FLAG_NMI = 0x40,
};
#define TRACE_BUF_SIZE 1024
@@ -345,6 +346,7 @@ struct tracer_opt {
struct tracer_flags {
u32 val;
struct tracer_opt *opts;
+ struct tracer *trace;
};
/* Makes more easy to define a tracer opt */
@@ -1111,6 +1113,18 @@ struct filter_pred {
unsigned short right;
};
+static inline bool is_string_field(struct ftrace_event_field *field)
+{
+ return field->filter_type == FILTER_DYN_STRING ||
+ field->filter_type == FILTER_STATIC_STRING ||
+ field->filter_type == FILTER_PTR_STRING;
+}
+
+static inline bool is_function_field(struct ftrace_event_field *field)
+{
+ return field->filter_type == FILTER_TRACE_FN;
+}
+
extern enum regex_type
filter_parse_regex(char *buff, int len, char **search, int *not);
extern void print_event_filter(struct trace_event_file *file,
@@ -1159,9 +1173,24 @@ struct event_trigger_data {
struct event_filter __rcu *filter;
char *filter_str;
void *private_data;
+ bool paused;
struct list_head list;
};
+extern void trigger_data_free(struct event_trigger_data *data);
+extern int event_trigger_init(struct event_trigger_ops *ops,
+ struct event_trigger_data *data);
+extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
+ int trigger_enable);
+extern void update_cond_flag(struct trace_event_file *file);
+extern void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct trace_event_file *file);
+extern int set_trigger_filter(char *filter_str,
+ struct event_trigger_data *trigger_data,
+ struct trace_event_file *file);
+extern int register_event_command(struct event_command *cmd);
+
/**
* struct event_trigger_ops - callbacks for trace event triggers
*
@@ -1174,7 +1203,8 @@ struct event_trigger_data {
* @func: The trigger 'probe' function called when the triggering
* event occurs. The data passed into this callback is the data
* that was supplied to the event_command @reg() function that
- * registered the trigger (see struct event_command).
+ * registered the trigger (see struct event_command) along with
+ * the trace record, rec.
*
* @init: An optional initialization function called for the trigger
* when the trigger is registered (via the event_command reg()
@@ -1199,7 +1229,8 @@ struct event_trigger_data {
* (see trace_event_triggers.c).
*/
struct event_trigger_ops {
- void (*func)(struct event_trigger_data *data);
+ void (*func)(struct event_trigger_data *data,
+ void *rec);
int (*init)(struct event_trigger_ops *ops,
struct event_trigger_data *data);
void (*free)(struct event_trigger_ops *ops,
@@ -1243,27 +1274,10 @@ struct event_trigger_ops {
* values are defined by adding new values to the trigger_type
* enum in include/linux/trace_events.h.
*
- * @post_trigger: A flag that says whether or not this command needs
- * to have its action delayed until after the current event has
- * been closed. Some triggers need to avoid being invoked while
- * an event is currently in the process of being logged, since
- * the trigger may itself log data into the trace buffer. Thus
- * we make sure the current event is committed before invoking
- * those triggers. To do that, the trigger invocation is split
- * in two - the first part checks the filter using the current
- * trace record; if a command has the @post_trigger flag set, it
- * sets a bit for itself in the return value, otherwise it
- * directly invokes the trigger. Once all commands have been
- * either invoked or set their return flag, the current record is
- * either committed or discarded. At that point, if any commands
- * have deferred their triggers, those commands are finally
- * invoked following the close of the current event. In other
- * words, if the event_trigger_ops @func() probe implementation
- * itself logs to the trace buffer, this flag should be set,
- * otherwise it can be left unspecified.
+ * @flags: See the enum event_command_flags below.
*
- * All the methods below, except for @set_filter(), must be
- * implemented.
+ * All the methods below, except for @set_filter() and @unreg_all(),
+ * must be implemented.
*
* @func: The callback function responsible for parsing and
* registering the trigger written to the 'trigger' file by the
@@ -1288,6 +1302,10 @@ struct event_trigger_ops {
* This is usually implemented by the generic utility function
* @unregister_trigger() (see trace_event_triggers.c).
*
+ * @unreg_all: An optional function called to remove all the triggers
+ * from the list of triggers associated with the event. Called
+ * when a trigger file is opened in truncate mode.
+ *
* @set_filter: An optional function called to parse and set a filter
* for the trigger. If no @set_filter() method is set for the
* event command, filters set by the user for the command will be
@@ -1301,7 +1319,7 @@ struct event_command {
struct list_head list;
char *name;
enum event_trigger_type trigger_type;
- bool post_trigger;
+ int flags;
int (*func)(struct event_command *cmd_ops,
struct trace_event_file *file,
char *glob, char *cmd, char *params);
@@ -1313,12 +1331,56 @@ struct event_command {
struct event_trigger_ops *ops,
struct event_trigger_data *data,
struct trace_event_file *file);
+ void (*unreg_all)(struct trace_event_file *file);
int (*set_filter)(char *filter_str,
struct event_trigger_data *data,
struct trace_event_file *file);
struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
};
+/**
+ * enum event_command_flags - flags for struct event_command
+ *
+ * @POST_TRIGGER: A flag that says whether or not this command needs
+ * to have its action delayed until after the current event has
+ * been closed. Some triggers need to avoid being invoked while
+ * an event is currently in the process of being logged, since
+ * the trigger may itself log data into the trace buffer. Thus
+ * we make sure the current event is committed before invoking
+ * those triggers. To do that, the trigger invocation is split
+ * in two - the first part checks the filter using the current
+ * trace record; if a command has the @post_trigger flag set, it
+ * sets a bit for itself in the return value, otherwise it
+ * directly invokes the trigger. Once all commands have been
+ * either invoked or set their return flag, the current record is
+ * either committed or discarded. At that point, if any commands
+ * have deferred their triggers, those commands are finally
+ * invoked following the close of the current event. In other
+ * words, if the event_trigger_ops @func() probe implementation
+ * itself logs to the trace buffer, this flag should be set,
+ * otherwise it can be left unspecified.
+ *
+ * @NEEDS_REC: A flag that says whether or not this command needs
+ * access to the trace record in order to perform its function,
+ * regardless of whether or not it has a filter associated with
+ * it (filters make a trigger require access to the trace record
+ * but are not always present).
+ */
+enum event_command_flags {
+ EVENT_CMD_FL_POST_TRIGGER = 1,
+ EVENT_CMD_FL_NEEDS_REC = 2,
+};
+
+static inline bool event_command_post_trigger(struct event_command *cmd_ops)
+{
+ return cmd_ops->flags & EVENT_CMD_FL_POST_TRIGGER;
+}
+
+static inline bool event_command_needs_rec(struct event_command *cmd_ops)
+{
+ return cmd_ops->flags & EVENT_CMD_FL_NEEDS_REC;
+}
+
extern int trace_event_enable_disable(struct trace_event_file *file,
int enable, int soft_disable);
extern int tracing_alloc_snapshot(void);
@@ -1365,8 +1427,13 @@ int perf_ftrace_event_register(struct trace_event_call *call,
#ifdef CONFIG_FTRACE_SYSCALLS
void init_ftrace_syscalls(void);
+const char *get_syscall_name(int syscall);
#else
static inline void init_ftrace_syscalls(void) { }
+static inline const char *get_syscall_name(int syscall)
+{
+ return NULL;
+}
#endif
#ifdef CONFIG_EVENT_TRACING
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 00df25f..562fa69 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -47,6 +47,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event,
if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!is_sampling_event(p_event))
+ return 0;
+
/*
* We don't allow user space callchains for function trace
* event, due to issues with page faults while tracing page
@@ -260,42 +263,43 @@ void perf_trace_del(struct perf_event *p_event, int flags)
tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
}
-void *perf_trace_buf_prepare(int size, unsigned short type,
- struct pt_regs **regs, int *rctxp)
+void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp)
{
- struct trace_entry *entry;
- unsigned long flags;
char *raw_data;
- int pc;
+ int rctx;
BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
- "perf buffer not large enough"))
+ "perf buffer not large enough"))
return NULL;
- pc = preempt_count();
-
- *rctxp = perf_swevent_get_recursion_context();
- if (*rctxp < 0)
+ *rctxp = rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
return NULL;
if (regs)
- *regs = this_cpu_ptr(&__perf_regs[*rctxp]);
- raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
+ *regs = this_cpu_ptr(&__perf_regs[rctx]);
+ raw_data = this_cpu_ptr(perf_trace_buf[rctx]);
/* zero the dead bytes from align to not leak stack to user */
memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
+ return raw_data;
+}
+EXPORT_SYMBOL_GPL(perf_trace_buf_alloc);
+NOKPROBE_SYMBOL(perf_trace_buf_alloc);
+
+void perf_trace_buf_update(void *record, u16 type)
+{
+ struct trace_entry *entry = record;
+ int pc = preempt_count();
+ unsigned long flags;
- entry = (struct trace_entry *)raw_data;
local_save_flags(flags);
tracing_generic_entry_update(entry, flags, pc);
entry->type = type;
-
- return raw_data;
}
-EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
-NOKPROBE_SYMBOL(perf_trace_buf_prepare);
+NOKPROBE_SYMBOL(perf_trace_buf_update);
#ifdef CONFIG_FUNCTION_TRACER
static void
@@ -316,15 +320,16 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
+ memset(&regs, 0, sizeof(regs));
perf_fetch_caller_regs(&regs);
- entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
+ entry = perf_trace_buf_alloc(ENTRY_SIZE, NULL, &rctx);
if (!entry)
return;
entry->ip = ip;
entry->parent_ip = parent_ip;
- perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
+ perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN,
1, &regs, head, NULL);
#undef ENTRY_SIZE
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 05ddc08..b7b0760 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -204,6 +204,24 @@ static void trace_destroy_fields(struct trace_event_call *call)
}
}
+/*
+ * run-time version of trace_event_get_offsets_<call>() that returns the last
+ * accessible offset of trace fields excluding __dynamic_array bytes
+ */
+int trace_event_get_offsets(struct trace_event_call *call)
+{
+ struct ftrace_event_field *tail;
+ struct list_head *head;
+
+ head = trace_get_fields(call);
+ /*
+ * head->next points to the last field with the largest offset,
+ * since it was added last by trace_define_field()
+ */
+ tail = list_first_entry(head, struct ftrace_event_field, link);
+ return tail->offset + tail->size;
+}
+
int trace_event_raw_init(struct trace_event_call *call)
{
int id;
@@ -2095,8 +2113,13 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
trace_create_file("filter", 0644, file->dir, file,
&ftrace_event_filter_fops);
- trace_create_file("trigger", 0644, file->dir, file,
- &event_trigger_fops);
+ /*
+ * Only event directories that can be enabled should have
+ * triggers.
+ */
+ if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
+ trace_create_file("trigger", 0644, file->dir, file,
+ &event_trigger_fops);
trace_create_file("format", 0444, file->dir, call,
&ftrace_event_format_fops);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 6816302..b3f5051 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -961,18 +961,6 @@ int filter_assign_type(const char *type)
return FILTER_OTHER;
}
-static bool is_function_field(struct ftrace_event_field *field)
-{
- return field->filter_type == FILTER_TRACE_FN;
-}
-
-static bool is_string_field(struct ftrace_event_field *field)
-{
- return field->filter_type == FILTER_DYN_STRING ||
- field->filter_type == FILTER_STATIC_STRING ||
- field->filter_type == FILTER_PTR_STRING;
-}
-
static bool is_legal_op(struct ftrace_event_field *field, int op)
{
if (is_string_field(field) &&
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index b38f617..d67992f 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -28,8 +28,7 @@
static LIST_HEAD(trigger_commands);
static DEFINE_MUTEX(trigger_cmd_mutex);
-static void
-trigger_data_free(struct event_trigger_data *data)
+void trigger_data_free(struct event_trigger_data *data)
{
if (data->cmd_ops->set_filter)
data->cmd_ops->set_filter(NULL, data, NULL);
@@ -73,18 +72,20 @@ event_triggers_call(struct trace_event_file *file, void *rec)
return tt;
list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->paused)
+ continue;
if (!rec) {
- data->ops->func(data);
+ data->ops->func(data, rec);
continue;
}
filter = rcu_dereference_sched(data->filter);
if (filter && !filter_match_preds(filter, rec))
continue;
- if (data->cmd_ops->post_trigger) {
+ if (event_command_post_trigger(data->cmd_ops)) {
tt |= data->cmd_ops->trigger_type;
continue;
}
- data->ops->func(data);
+ data->ops->func(data, rec);
}
return tt;
}
@@ -94,6 +95,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call);
* event_triggers_post_call - Call 'post_triggers' for a trace event
* @file: The trace_event_file associated with the event
* @tt: enum event_trigger_type containing a set bit for each trigger to invoke
+ * @rec: The trace entry for the event
*
* For each trigger associated with an event, invoke the trigger
* function registered with the associated trigger command, if the
@@ -104,13 +106,16 @@ EXPORT_SYMBOL_GPL(event_triggers_call);
*/
void
event_triggers_post_call(struct trace_event_file *file,
- enum event_trigger_type tt)
+ enum event_trigger_type tt,
+ void *rec)
{
struct event_trigger_data *data;
list_for_each_entry_rcu(data, &file->triggers, list) {
+ if (data->paused)
+ continue;
if (data->cmd_ops->trigger_type & tt)
- data->ops->func(data);
+ data->ops->func(data, rec);
}
}
EXPORT_SYMBOL_GPL(event_triggers_post_call);
@@ -188,6 +193,19 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
return -ENODEV;
}
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC)) {
+ struct trace_event_file *event_file;
+ struct event_command *p;
+
+ event_file = event_file_data(file);
+
+ list_for_each_entry(p, &trigger_commands, list) {
+ if (p->unreg_all)
+ p->unreg_all(event_file);
+ }
+ }
+
if (file->f_mode & FMODE_READ) {
ret = seq_open(file, &event_triggers_seq_ops);
if (!ret) {
@@ -306,7 +324,7 @@ const struct file_operations event_trigger_fops = {
* Currently we only register event commands from __init, so mark this
* __init too.
*/
-static __init int register_event_command(struct event_command *cmd)
+__init int register_event_command(struct event_command *cmd)
{
struct event_command *p;
int ret = 0;
@@ -395,9 +413,8 @@ event_trigger_print(const char *name, struct seq_file *m,
*
* Return: 0 on success, errno otherwise
*/
-static int
-event_trigger_init(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+int event_trigger_init(struct event_trigger_ops *ops,
+ struct event_trigger_data *data)
{
data->ref++;
return 0;
@@ -425,8 +442,8 @@ event_trigger_free(struct event_trigger_ops *ops,
trigger_data_free(data);
}
-static int trace_event_trigger_enable_disable(struct trace_event_file *file,
- int trigger_enable)
+int trace_event_trigger_enable_disable(struct trace_event_file *file,
+ int trigger_enable)
{
int ret = 0;
@@ -483,13 +500,14 @@ clear_event_triggers(struct trace_array *tr)
* its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be
* cleared.
*/
-static void update_cond_flag(struct trace_event_file *file)
+void update_cond_flag(struct trace_event_file *file)
{
struct event_trigger_data *data;
bool set_cond = false;
list_for_each_entry_rcu(data, &file->triggers, list) {
- if (data->filter || data->cmd_ops->post_trigger) {
+ if (data->filter || event_command_post_trigger(data->cmd_ops) ||
+ event_command_needs_rec(data->cmd_ops)) {
set_cond = true;
break;
}
@@ -560,9 +578,9 @@ out:
* Usually used directly as the @unreg method in event command
* implementations.
*/
-static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
- struct event_trigger_data *test,
- struct trace_event_file *file)
+void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+ struct event_trigger_data *test,
+ struct trace_event_file *file)
{
struct event_trigger_data *data;
bool unregistered = false;
@@ -696,9 +714,9 @@ event_trigger_callback(struct event_command *cmd_ops,
*
* Return: 0 on success, errno otherwise
*/
-static int set_trigger_filter(char *filter_str,
- struct event_trigger_data *trigger_data,
- struct trace_event_file *file)
+int set_trigger_filter(char *filter_str,
+ struct event_trigger_data *trigger_data,
+ struct trace_event_file *file)
{
struct event_trigger_data *data = trigger_data;
struct event_filter *filter = NULL, *tmp;
@@ -747,7 +765,7 @@ static int set_trigger_filter(char *filter_str,
}
static void
-traceon_trigger(struct event_trigger_data *data)
+traceon_trigger(struct event_trigger_data *data, void *rec)
{
if (tracing_is_on())
return;
@@ -756,7 +774,7 @@ traceon_trigger(struct event_trigger_data *data)
}
static void
-traceon_count_trigger(struct event_trigger_data *data)
+traceon_count_trigger(struct event_trigger_data *data, void *rec)
{
if (tracing_is_on())
return;
@@ -771,7 +789,7 @@ traceon_count_trigger(struct event_trigger_data *data)
}
static void
-traceoff_trigger(struct event_trigger_data *data)
+traceoff_trigger(struct event_trigger_data *data, void *rec)
{
if (!tracing_is_on())
return;
@@ -780,7 +798,7 @@ traceoff_trigger(struct event_trigger_data *data)
}
static void
-traceoff_count_trigger(struct event_trigger_data *data)
+traceoff_count_trigger(struct event_trigger_data *data, void *rec)
{
if (!tracing_is_on())
return;
@@ -876,13 +894,13 @@ static struct event_command trigger_traceoff_cmd = {
#ifdef CONFIG_TRACER_SNAPSHOT
static void
-snapshot_trigger(struct event_trigger_data *data)
+snapshot_trigger(struct event_trigger_data *data, void *rec)
{
tracing_snapshot();
}
static void
-snapshot_count_trigger(struct event_trigger_data *data)
+snapshot_count_trigger(struct event_trigger_data *data, void *rec)
{
if (!data->count)
return;
@@ -890,7 +908,7 @@ snapshot_count_trigger(struct event_trigger_data *data)
if (data->count != -1)
(data->count)--;
- snapshot_trigger(data);
+ snapshot_trigger(data, rec);
}
static int
@@ -969,13 +987,13 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; }
#define STACK_SKIP 3
static void
-stacktrace_trigger(struct event_trigger_data *data)
+stacktrace_trigger(struct event_trigger_data *data, void *rec)
{
trace_dump_stack(STACK_SKIP);
}
static void
-stacktrace_count_trigger(struct event_trigger_data *data)
+stacktrace_count_trigger(struct event_trigger_data *data, void *rec)
{
if (!data->count)
return;
@@ -983,7 +1001,7 @@ stacktrace_count_trigger(struct event_trigger_data *data)
if (data->count != -1)
(data->count)--;
- stacktrace_trigger(data);
+ stacktrace_trigger(data, rec);
}
static int
@@ -1017,7 +1035,7 @@ stacktrace_get_trigger_ops(char *cmd, char *param)
static struct event_command trigger_stacktrace_cmd = {
.name = "stacktrace",
.trigger_type = ETT_STACKTRACE,
- .post_trigger = true,
+ .flags = EVENT_CMD_FL_POST_TRIGGER,
.func = event_trigger_callback,
.reg = register_trigger,
.unreg = unregister_trigger,
@@ -1054,7 +1072,7 @@ struct enable_trigger_data {
};
static void
-event_enable_trigger(struct event_trigger_data *data)
+event_enable_trigger(struct event_trigger_data *data, void *rec)
{
struct enable_trigger_data *enable_data = data->private_data;
@@ -1065,7 +1083,7 @@ event_enable_trigger(struct event_trigger_data *data)
}
static void
-event_enable_count_trigger(struct event_trigger_data *data)
+event_enable_count_trigger(struct event_trigger_data *data, void *rec)
{
struct enable_trigger_data *enable_data = data->private_data;
@@ -1079,7 +1097,7 @@ event_enable_count_trigger(struct event_trigger_data *data)
if (data->count != -1)
(data->count)--;
- event_enable_trigger(data);
+ event_enable_trigger(data, rec);
}
static int
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index fcd41a1..5a095c2 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -219,6 +219,8 @@ static void tracing_stop_function_trace(struct trace_array *tr)
unregister_ftrace_function(tr->ops);
}
+static struct tracer function_trace;
+
static int
func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
@@ -228,6 +230,10 @@ func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
break;
+ /* We can change this flag when not running. */
+ if (tr->current_trace != &function_trace)
+ break;
+
unregister_ftrace_function(tr->ops);
if (set) {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a663cbb..3a0244f 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -8,6 +8,7 @@
*/
#include <linux/uaccess.h>
#include <linux/ftrace.h>
+#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/fs.h>
@@ -1350,7 +1351,7 @@ void graph_trace_open(struct trace_iterator *iter)
out_err_free:
kfree(data);
out_err:
- pr_warning("function graph tracer: not enough memory\n");
+ pr_warn("function graph tracer: not enough memory\n");
}
void graph_trace_close(struct trace_iterator *iter)
@@ -1468,12 +1469,12 @@ static __init int init_graph_trace(void)
max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
if (!register_trace_event(&graph_trace_entry_event)) {
- pr_warning("Warning: could not register graph trace events\n");
+ pr_warn("Warning: could not register graph trace events\n");
return 1;
}
if (!register_trace_event(&graph_trace_ret_event)) {
- pr_warning("Warning: could not register graph trace events\n");
+ pr_warn("Warning: could not register graph trace events\n");
return 1;
}
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index e4e5658..03cdff8 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -109,8 +109,12 @@ static int func_prolog_dec(struct trace_array *tr,
return 0;
local_save_flags(*flags);
- /* slight chance to get a false positive on tracing_cpu */
- if (!irqs_disabled_flags(*flags))
+ /*
+ * Slight chance to get a false positive on tracing_cpu,
+ * although I'm starting to think there isn't a chance.
+ * Leave this for now just to be paranoid.
+ */
+ if (!irqs_disabled_flags(*flags) && !preempt_count())
return 0;
*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
@@ -622,7 +626,6 @@ static int __irqsoff_tracer_init(struct trace_array *tr)
irqsoff_trace = tr;
/* make sure that the tracer is visible */
smp_wmb();
- tracing_reset_online_cpus(&tr->trace_buffer);
ftrace_init_array_ops(tr, irqsoff_tracer_call);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c995644..5546eec 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -30,7 +30,7 @@
struct trace_kprobe {
struct list_head list;
struct kretprobe rp; /* Use rp.kp for kprobe use */
- unsigned long nhit;
+ unsigned long __percpu *nhit;
const char *symbol; /* symbol name */
struct trace_probe tp;
};
@@ -274,6 +274,10 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
if (!tk)
return ERR_PTR(ret);
+ tk->nhit = alloc_percpu(unsigned long);
+ if (!tk->nhit)
+ goto error;
+
if (symbol) {
tk->symbol = kstrdup(symbol, GFP_KERNEL);
if (!tk->symbol)
@@ -313,6 +317,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
error:
kfree(tk->tp.call.name);
kfree(tk->symbol);
+ free_percpu(tk->nhit);
kfree(tk);
return ERR_PTR(ret);
}
@@ -327,6 +332,7 @@ static void free_trace_kprobe(struct trace_kprobe *tk)
kfree(tk->tp.call.class->system);
kfree(tk->tp.call.name);
kfree(tk->symbol);
+ free_percpu(tk->nhit);
kfree(tk);
}
@@ -453,16 +459,14 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
if (ret == 0)
tk->tp.flags |= TP_FLAG_REGISTERED;
else {
- pr_warning("Could not insert probe at %s+%lu: %d\n",
- trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
+ pr_warn("Could not insert probe at %s+%lu: %d\n",
+ trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
- pr_warning("This probe might be able to register after"
- "target module is loaded. Continue.\n");
+ pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;
} else if (ret == -EILSEQ) {
- pr_warning("Probing address(0x%p) is not an "
- "instruction boundary.\n",
- tk->rp.kp.addr);
+ pr_warn("Probing address(0x%p) is not an instruction boundary.\n",
+ tk->rp.kp.addr);
ret = -EINVAL;
}
}
@@ -523,7 +527,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
/* Register new event */
ret = register_kprobe_event(tk);
if (ret) {
- pr_warning("Failed to register probe event(%d)\n", ret);
+ pr_warn("Failed to register probe event(%d)\n", ret);
goto end;
}
@@ -558,10 +562,9 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
__unregister_trace_kprobe(tk);
ret = __register_trace_kprobe(tk);
if (ret)
- pr_warning("Failed to re-register probe %s on"
- "%s: %d\n",
- trace_event_name(&tk->tp.call),
- mod->name, ret);
+ pr_warn("Failed to re-register probe %s on %s: %d\n",
+ trace_event_name(&tk->tp.call),
+ mod->name, ret);
}
}
mutex_unlock(&probe_lock);
@@ -874,9 +877,14 @@ static const struct file_operations kprobe_events_ops = {
static int probes_profile_seq_show(struct seq_file *m, void *v)
{
struct trace_kprobe *tk = v;
+ unsigned long nhit = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ nhit += *per_cpu_ptr(tk->nhit, cpu);
seq_printf(m, " %-44s %15lu %15lu\n",
- trace_event_name(&tk->tp.call), tk->nhit,
+ trace_event_name(&tk->tp.call), nhit,
tk->rp.kp.nmissed);
return 0;
@@ -1141,14 +1149,15 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
if (!entry)
return;
entry->ip = (unsigned long)tk->rp.kp.addr;
memset(&entry[1], 0, dsize);
store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
}
NOKPROBE_SYMBOL(kprobe_perf_func);
@@ -1176,14 +1185,15 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
if (!entry)
return;
entry->func = (unsigned long)tk->rp.kp.addr;
entry->ret_ip = (unsigned long)ri->ret_addr;
store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
- perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
}
NOKPROBE_SYMBOL(kretprobe_perf_func);
#endif /* CONFIG_PERF_EVENTS */
@@ -1225,7 +1235,7 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
{
struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
- tk->nhit++;
+ raw_cpu_inc(*tk->nhit);
if (tk->tp.flags & TP_FLAG_TRACE)
kprobe_trace_func(tk, regs);
@@ -1242,7 +1252,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
{
struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);
- tk->nhit++;
+ raw_cpu_inc(*tk->nhit);
if (tk->tp.flags & TP_FLAG_TRACE)
kretprobe_trace_func(tk, ri, regs);
@@ -1325,16 +1335,14 @@ static __init int init_kprobe_trace(void)
/* Event list interface */
if (!entry)
- pr_warning("Could not create tracefs "
- "'kprobe_events' entry\n");
+ pr_warn("Could not create tracefs 'kprobe_events' entry\n");
/* Profile interface */
entry = tracefs_create_file("kprobe_profile", 0444, d_tracer,
NULL, &kprobe_profile_ops);
if (!entry)
- pr_warning("Could not create tracefs "
- "'kprobe_profile' entry\n");
+ pr_warn("Could not create tracefs 'kprobe_profile' entry\n");
return 0;
}
fs_initcall(init_kprobe_trace);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 2be8c4f..68f376c 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -146,7 +146,7 @@ static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp,
/* XXX: This is later than where events were lost. */
trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n);
if (!overrun_detected)
- pr_warning("mmiotrace has lost events.\n");
+ pr_warn("mmiotrace has lost events\n");
overrun_detected = true;
goto print_out;
}
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 8bb2071..49f61fe 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -56,7 +56,7 @@ static void nop_trace_reset(struct trace_array *tr)
}
/* It only serves as a signal handler and a callback to
- * accept or refuse tthe setting of a flag.
+ * accept or refuse the setting of a flag.
* If you don't implement it, then the flag setting will be
* automatically accepted.
*/
@@ -75,7 +75,7 @@ static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
if (bit == TRACE_NOP_OPT_REFUSE) {
printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse."
- "Now cat trace_options to see the result\n",
+ " Now cat trace_options to see the result\n",
set);
return -EINVAL;
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 2829821..0bb9cf2 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -389,7 +389,9 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
char irqs_off;
int hardirq;
int softirq;
+ int nmi;
+ nmi = entry->flags & TRACE_FLAG_NMI;
hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
@@ -415,10 +417,12 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
}
hardsoft_irq =
+ (nmi && hardirq) ? 'Z' :
+ nmi ? 'z' :
(hardirq && softirq) ? 'H' :
- hardirq ? 'h' :
- softirq ? 's' :
- '.';
+ hardirq ? 'h' :
+ softirq ? 's' :
+ '.' ;
trace_seq_printf(s, "%c%c%c",
irqs_off, need_resched, hardsoft_irq);
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 060df67..f96f038 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -296,6 +296,9 @@ static int t_show(struct seq_file *m, void *v)
const char *str = *fmt;
int i;
+ if (!*fmt)
+ return 0;
+
seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
/*
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 1769a81..1d372fa 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -636,8 +636,8 @@ ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer,
*tmp = '\0';
size = tmp - kbuf + 1;
} else if (done + size < count) {
- pr_warning("Line length is too long: "
- "Should be less than %d.", WRITE_BUFSIZE);
+ pr_warn("Line length is too long: Should be less than %d\n",
+ WRITE_BUFSIZE);
ret = -EINVAL;
goto out;
}
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 6cf9353..413ff10 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -281,8 +281,7 @@ static int tracing_stat_init(void)
stat_dir = tracefs_create_dir("trace_stat", d_tracing);
if (!stat_dir)
- pr_warning("Could not create tracefs "
- "'trace_stat' entry\n");
+ pr_warn("Could not create tracefs 'trace_stat' entry\n");
return 0;
}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 0655afb..b2b6efc 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -106,6 +106,17 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr)
return syscalls_metadata[nr];
}
+const char *get_syscall_name(int syscall)
+{
+ struct syscall_metadata *entry;
+
+ entry = syscall_nr_to_meta(syscall);
+ if (!entry)
+ return NULL;
+
+ return entry->name;
+}
+
static enum print_line_t
print_syscall_enter(struct trace_iterator *iter, int flags,
struct trace_event *event)
@@ -186,11 +197,11 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
extern char *__bad_type_size(void);
-#define SYSCALL_FIELD(type, name) \
- sizeof(type) != sizeof(trace.name) ? \
+#define SYSCALL_FIELD(type, field, name) \
+ sizeof(type) != sizeof(trace.field) ? \
__bad_type_size() : \
- #type, #name, offsetof(typeof(trace), name), \
- sizeof(trace.name), is_signed_type(type)
+ #type, #name, offsetof(typeof(trace), field), \
+ sizeof(trace.field), is_signed_type(type)
static int __init
__set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
@@ -261,7 +272,8 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call)
int i;
int offset = offsetof(typeof(trace), args);
- ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+ ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
+ FILTER_OTHER);
if (ret)
return ret;
@@ -281,11 +293,12 @@ static int __init syscall_exit_define_fields(struct trace_event_call *call)
struct syscall_trace_exit trace;
int ret;
- ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+ ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
+ FILTER_OTHER);
if (ret)
return ret;
- ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
+ ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret),
FILTER_OTHER);
return ret;
@@ -574,15 +587,16 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
size = ALIGN(size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
- sys_data->enter_event->event.type, NULL, &rctx);
+ rec = perf_trace_buf_alloc(size, NULL, &rctx);
if (!rec)
return;
rec->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
- perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(rec, size, rctx,
+ sys_data->enter_event->event.type, 1, regs,
+ head, NULL);
}
static int perf_sysenter_enable(struct trace_event_call *call)
@@ -647,14 +661,14 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
- sys_data->exit_event->event.type, NULL, &rctx);
+ rec = perf_trace_buf_alloc(size, NULL, &rctx);
if (!rec)
return;
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
- perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
+ 1, regs, head, NULL);
}
static int perf_sysexit_enable(struct trace_event_call *call)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index d2f6d0b..c534854 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -334,7 +334,7 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
ret = register_uprobe_event(tu);
if (ret) {
- pr_warning("Failed to register probe event(%d)\n", ret);
+ pr_warn("Failed to register probe event(%d)\n", ret);
goto end;
}
@@ -1131,7 +1131,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
if (hlist_empty(head))
goto out;
- entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
+ entry = perf_trace_buf_alloc(size, NULL, &rctx);
if (!entry)
goto out;
@@ -1152,7 +1152,8 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
memset(data + len, 0, size - esize - len);
}
- perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
+ perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
+ head, NULL);
out:
preempt_enable();
}
generated by cgit v0.10.2 at 2024-07-26 18:01:32 (GMT)