summaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig3
-rw-r--r--kernel/trace/blktrace.c75
-rw-r--r--kernel/trace/bpf_trace.c60
-rw-r--r--kernel/trace/ftrace.c13
-rw-r--r--kernel/trace/rethook.c9
-rw-r--r--kernel/trace/trace.c13
-rw-r--r--kernel/trace/trace_events_hist.c2
-rw-r--r--kernel/trace/trace_kprobe.c11
-rw-r--r--kernel/trace/trace_uprobe.c1
9 files changed, 115 insertions, 72 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index debbbb083286..ccd6a5ade3e9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -194,7 +194,8 @@ config FUNCTION_TRACER
sequence is then dynamically patched into a tracer call when
tracing is enabled by the administrator. If it's runtime disabled
(the bootup default), then the overhead of the instructions is very
- small and not measurable even in micro-benchmarks.
+ small and not measurable even in micro-benchmarks (at least on
+ x86, but may have impact on other architectures).
config FUNCTION_GRAPH_TRACER
bool "Kernel Function Graph Tracer"
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 10a32b0f2deb..7f5eb295fe19 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -205,7 +205,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
#define BLK_TC_PREFLUSH BLK_TC_FLUSH
/* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
+#define MASK_TC_BIT(rw, __name) ((__force u32)(rw & REQ_ ## __name) << \
(ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name))
/*
@@ -213,8 +213,8 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
* blk_io_trace structure and places it in a per-cpu subbuffer.
*/
static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
- int op, int op_flags, u32 what, int error, int pdu_len,
- void *pdu_data, u64 cgid)
+ const blk_opf_t opf, u32 what, int error,
+ int pdu_len, void *pdu_data, u64 cgid)
{
struct task_struct *tsk = current;
struct ring_buffer_event *event = NULL;
@@ -227,16 +227,17 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
int cpu;
bool blk_tracer = blk_tracer_enabled;
ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
+ const enum req_op op = opf & REQ_OP_MASK;
if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
return;
what |= ddir_act[op_is_write(op) ? WRITE : READ];
- what |= MASK_TC_BIT(op_flags, SYNC);
- what |= MASK_TC_BIT(op_flags, RAHEAD);
- what |= MASK_TC_BIT(op_flags, META);
- what |= MASK_TC_BIT(op_flags, PREFLUSH);
- what |= MASK_TC_BIT(op_flags, FUA);
+ what |= MASK_TC_BIT(opf, SYNC);
+ what |= MASK_TC_BIT(opf, RAHEAD);
+ what |= MASK_TC_BIT(opf, META);
+ what |= MASK_TC_BIT(opf, PREFLUSH);
+ what |= MASK_TC_BIT(opf, FUA);
if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
what |= BLK_TC_ACT(BLK_TC_DISCARD);
if (op == REQ_OP_FLUSH)
@@ -736,12 +737,12 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
switch (cmd) {
case BLKTRACESETUP:
- bdevname(bdev, b);
+ snprintf(b, sizeof(b), "%pg", bdev);
ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
break;
#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
case BLKTRACESETUP32:
- bdevname(bdev, b);
+ snprintf(b, sizeof(b), "%pg", bdev);
ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
break;
#endif
@@ -770,14 +771,11 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
**/
void blk_trace_shutdown(struct request_queue *q)
{
- mutex_lock(&q->debugfs_mutex);
if (rcu_dereference_protected(q->blk_trace,
lockdep_is_held(&q->debugfs_mutex))) {
__blk_trace_startstop(q, 0);
__blk_trace_remove(q);
}
-
- mutex_unlock(&q->debugfs_mutex);
}
#ifdef CONFIG_BLK_CGROUP
@@ -845,9 +843,8 @@ static void blk_add_trace_rq(struct request *rq, blk_status_t error,
else
what |= BLK_TC_ACT(BLK_TC_FS);
- __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
- rq->cmd_flags, what, blk_status_to_errno(error), 0,
- NULL, cgid);
+ __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, rq->cmd_flags,
+ what, blk_status_to_errno(error), 0, NULL, cgid);
rcu_read_unlock();
}
@@ -906,7 +903,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
}
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
- bio_op(bio), bio->bi_opf, what, error, 0, NULL,
+ bio->bi_opf, what, error, 0, NULL,
blk_trace_bio_get_cgid(q, bio));
rcu_read_unlock();
}
@@ -952,7 +949,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
rcu_read_lock();
bt = rcu_dereference(q->blk_trace);
if (bt)
- __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
+ __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
rcu_read_unlock();
}
@@ -972,7 +969,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
else
what = BLK_TA_UNPLUG_TIMER;
- __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
+ __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
}
rcu_read_unlock();
}
@@ -988,8 +985,7 @@ static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu)
__be64 rpdu = cpu_to_be64(pdu);
__blk_add_trace(bt, bio->bi_iter.bi_sector,
- bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
- BLK_TA_SPLIT,
+ bio->bi_iter.bi_size, bio->bi_opf, BLK_TA_SPLIT,
blk_status_to_errno(bio->bi_status),
sizeof(rpdu), &rpdu,
blk_trace_bio_get_cgid(q, bio));
@@ -1025,7 +1021,7 @@ static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev,
r.sector_from = cpu_to_be64(from);
__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
- bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+ bio->bi_opf, BLK_TA_REMAP,
blk_status_to_errno(bio->bi_status),
sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
rcu_read_unlock();
@@ -1061,7 +1057,7 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
r.sector_from = cpu_to_be64(from);
__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
- rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
+ rq->cmd_flags, BLK_TA_REMAP, 0,
sizeof(r), &r, blk_trace_request_get_cgid(rq));
rcu_read_unlock();
}
@@ -1087,7 +1083,7 @@ void blk_add_driver_data(struct request *rq, void *data, size_t len)
return;
}
- __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
+ __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0,
BLK_TA_DRV_DATA, 0, len, data,
blk_trace_request_get_cgid(rq));
rcu_read_unlock();
@@ -1870,17 +1866,6 @@ out_unlock_bdev:
out:
return ret ? ret : count;
}
-
-int blk_trace_init_sysfs(struct device *dev)
-{
- return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
-}
-
-void blk_trace_remove_sysfs(struct device *dev)
-{
- sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
-}
-
#endif /* CONFIG_BLK_DEV_IO_TRACE */
#ifdef CONFIG_EVENT_TRACING
@@ -1888,21 +1873,21 @@ void blk_trace_remove_sysfs(struct device *dev)
/**
* blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string.
* @rwbs: buffer to be filled
- * @op: REQ_OP_XXX for the tracepoint
+ * @opf: request operation type (REQ_OP_XXX) and flags for the tracepoint
*
* Description:
- * Maps the REQ_OP_XXX to character and fills the buffer provided by the
- * caller with resulting string.
+ * Maps each request operation and flag to a single character and fills the
+ * buffer provided by the caller with resulting string.
*
**/
-void blk_fill_rwbs(char *rwbs, unsigned int op)
+void blk_fill_rwbs(char *rwbs, blk_opf_t opf)
{
int i = 0;
- if (op & REQ_PREFLUSH)
+ if (opf & REQ_PREFLUSH)
rwbs[i++] = 'F';
- switch (op & REQ_OP_MASK) {
+ switch (opf & REQ_OP_MASK) {
case REQ_OP_WRITE:
rwbs[i++] = 'W';
break;
@@ -1923,13 +1908,13 @@ void blk_fill_rwbs(char *rwbs, unsigned int op)
rwbs[i++] = 'N';
}
- if (op & REQ_FUA)
+ if (opf & REQ_FUA)
rwbs[i++] = 'F';
- if (op & REQ_RAHEAD)
+ if (opf & REQ_RAHEAD)
rwbs[i++] = 'A';
- if (op & REQ_SYNC)
+ if (opf & REQ_SYNC)
rwbs[i++] = 'S';
- if (op & REQ_META)
+ if (opf & REQ_META)
rwbs[i++] = 'M';
rwbs[i] = '\0';
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7a13e6ac6327..88589d74a892 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2423,7 +2423,7 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
kprobe_multi_link_prog_run(link, entry_ip, regs);
}
-static int symbols_cmp(const void *a, const void *b)
+static int symbols_cmp_r(const void *a, const void *b, const void *priv)
{
const char **str_a = (const char **) a;
const char **str_b = (const char **) b;
@@ -2431,6 +2431,28 @@ static int symbols_cmp(const void *a, const void *b)
return strcmp(*str_a, *str_b);
}
+struct multi_symbols_sort {
+ const char **funcs;
+ u64 *cookies;
+};
+
+static void symbols_swap_r(void *a, void *b, int size, const void *priv)
+{
+ const struct multi_symbols_sort *data = priv;
+ const char **name_a = a, **name_b = b;
+
+ swap(*name_a, *name_b);
+
+ /* If defined, swap also related cookies. */
+ if (data->cookies) {
+ u64 *cookie_a, *cookie_b;
+
+ cookie_a = data->cookies + (name_a - data->funcs);
+ cookie_b = data->cookies + (name_b - data->funcs);
+ swap(*cookie_a, *cookie_b);
+ }
+}
+
int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_kprobe_multi_link *link = NULL;
@@ -2468,38 +2490,46 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
if (!addrs)
return -ENOMEM;
+ ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
+ if (ucookies) {
+ cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
+ if (!cookies) {
+ err = -ENOMEM;
+ goto error;
+ }
+ if (copy_from_user(cookies, ucookies, size)) {
+ err = -EFAULT;
+ goto error;
+ }
+ }
+
if (uaddrs) {
if (copy_from_user(addrs, uaddrs, size)) {
err = -EFAULT;
goto error;
}
} else {
+ struct multi_symbols_sort data = {
+ .cookies = cookies,
+ };
struct user_syms us;
err = copy_user_syms(&us, usyms, cnt);
if (err)
goto error;
- sort(us.syms, cnt, sizeof(*us.syms), symbols_cmp, NULL);
+ if (cookies)
+ data.funcs = us.syms;
+
+ sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r,
+ symbols_swap_r, &data);
+
err = ftrace_lookup_symbols(us.syms, cnt, addrs);
free_user_syms(&us);
if (err)
goto error;
}
- ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies);
- if (ucookies) {
- cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
- if (!cookies) {
- err = -ENOMEM;
- goto error;
- }
- if (copy_from_user(cookies, ucookies, size)) {
- err = -EFAULT;
- goto error;
- }
- }
-
link = kzalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
err = -ENOMEM;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e750fe141a60..601ccf1b2f09 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8029,15 +8029,23 @@ static int kallsyms_callback(void *data, const char *name,
struct module *mod, unsigned long addr)
{
struct kallsyms_data *args = data;
+ const char **sym;
+ int idx;
- if (!bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp))
+ sym = bsearch(&name, args->syms, args->cnt, sizeof(*args->syms), symbols_cmp);
+ if (!sym)
+ return 0;
+
+ idx = sym - args->syms;
+ if (args->addrs[idx])
return 0;
addr = ftrace_location(addr);
if (!addr)
return 0;
- args->addrs[args->found++] = addr;
+ args->addrs[idx] = addr;
+ args->found++;
return args->found == args->cnt ? 1 : 0;
}
@@ -8062,6 +8070,7 @@ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *a
struct kallsyms_data args;
int err;
+ memset(addrs, 0, sizeof(*addrs) * cnt);
args.addrs = addrs;
args.syms = sorted_syms;
args.cnt = cnt;
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index b56833700d23..c69d82273ce7 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -154,6 +154,15 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
if (unlikely(!handler))
return NULL;
+ /*
+ * This expects the caller will set up a rethook on a function entry.
+ * When the function returns, the rethook will eventually be reclaimed
+ * or released in the rethook_recycle() with call_rcu().
+ * This means the caller must be run in the RCU-availabe context.
+ */
+ if (unlikely(!rcu_is_watching()))
+ return NULL;
+
fn = freelist_try_get(&rh->pool);
if (!fn)
return NULL;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5fc7f17f5ec7..0c517c8c8999 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6424,9 +6424,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
synchronize_rcu();
free_snapshot(tr);
}
-#endif
-#ifdef CONFIG_TRACER_MAX_TRACE
if (t->use_max_tr && !had_max_tr) {
ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
@@ -9866,6 +9864,12 @@ void trace_init_global_iter(struct trace_iterator *iter)
/* Output in nanoseconds only if we are using a clock in nanoseconds. */
if (trace_clocks[iter->tr->clock_id].in_ns)
iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
+ /* Can not use kmalloc for iter.temp and iter.fmt */
+ iter->temp = static_temp_buf;
+ iter->temp_size = STATIC_TEMP_BUF_SIZE;
+ iter->fmt = static_fmt_buf;
+ iter->fmt_size = STATIC_FMT_BUF_SIZE;
}
void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
@@ -9898,11 +9902,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
/* Simulate the iterator */
trace_init_global_iter(&iter);
- /* Can not use kmalloc for iter.temp and iter.fmt */
- iter.temp = static_temp_buf;
- iter.temp_size = STATIC_TEMP_BUF_SIZE;
- iter.fmt = static_fmt_buf;
- iter.fmt_size = STATIC_FMT_BUF_SIZE;
for_each_tracing_cpu(cpu) {
atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 48e82e141d54..e87a46794079 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4430,6 +4430,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
s = kstrdup(field_str, GFP_KERNEL);
if (!s) {
+ kfree(hist_data->attrs->var_defs.name[n_vars]);
+ hist_data->attrs->var_defs.name[n_vars] = NULL;
ret = -ENOMEM;
goto free;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 93507330462c..a245ea673715 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1718,8 +1718,17 @@ static int
kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
{
struct kretprobe *rp = get_kretprobe(ri);
- struct trace_kprobe *tk = container_of(rp, struct trace_kprobe, rp);
+ struct trace_kprobe *tk;
+
+ /*
+ * There is a small chance that get_kretprobe(ri) returns NULL when
+ * the kretprobe is unregister on another CPU between kretprobe's
+ * trampoline_handler and this function.
+ */
+ if (unlikely(!rp))
+ return 0;
+ tk = container_of(rp, struct trace_kprobe, rp);
raw_cpu_inc(*tk->nhit);
if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 9711589273cd..c3dc4f859a6b 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -546,7 +546,6 @@ static int __trace_uprobe_create(int argc, const char **argv)
bool is_return = false;
int i, ret;
- ret = 0;
ref_ctr_offset = 0;
switch (argv[0][0]) {