summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:39:57 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:39:57 +0000
commitdc50eab76b709d68175a358d6e23a5a3890764d3 (patch)
treec754d0390db060af0213ff994f0ac310e4cfd6e9 /kernel/trace
parentAdding debian version 6.6.15-2. (diff)
downloadlinux-dc50eab76b709d68175a358d6e23a5a3890764d3.tar.xz
linux-dc50eab76b709d68175a358d6e23a5a3890764d3.zip
Merging upstream version 6.7.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
-rw-r--r--kernel/trace/bpf_trace.c16
-rw-r--r--kernel/trace/fprobe.c28
-rw-r--r--kernel/trace/ftrace.c10
-rw-r--r--kernel/trace/rethook.c90
-rw-r--r--kernel/trace/ring_buffer.c10
-rw-r--r--kernel/trace/trace.c153
-rw-r--r--kernel/trace/trace.h13
-rw-r--r--kernel/trace/trace_btf.c4
-rw-r--r--kernel/trace/trace_eprobe.c5
-rw-r--r--kernel/trace/trace_events.c333
-rw-r--r--kernel/trace/trace_events_hist.c11
-rw-r--r--kernel/trace/trace_events_synth.c7
-rw-r--r--kernel/trace/trace_events_trigger.c6
-rw-r--r--kernel/trace/trace_events_user.c36
-rw-r--r--kernel/trace/trace_kprobe.c14
-rw-r--r--kernel/trace/trace_osnoise.c6
-rw-r--r--kernel/trace/trace_output.c2
-rw-r--r--kernel/trace/trace_probe.c32
-rw-r--r--kernel/trace/trace_probe.h3
-rw-r--r--kernel/trace/trace_seq.c6
-rw-r--r--kernel/trace/trace_syscalls.c4
21 files changed, 462 insertions, 327 deletions
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1d76f3b014..652c40a14d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -120,6 +120,9 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
* and don't send kprobe event into ring-buffer,
* so return zero here
*/
+ rcu_read_lock();
+ bpf_prog_inc_misses_counters(rcu_dereference(call->prog_array));
+ rcu_read_unlock();
ret = 0;
goto out;
}
@@ -1252,9 +1255,7 @@ static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
};
#ifdef CONFIG_KEYS
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "kfuncs which will be used in BPF programs");
+__bpf_kfunc_start_defs();
/**
* bpf_lookup_user_key - lookup a key by its serial
@@ -1404,7 +1405,7 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
}
#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(key_sig_kfunc_set)
BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
@@ -2387,7 +2388,8 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
u32 *fd_type, const char **buf,
- u64 *probe_offset, u64 *probe_addr)
+ u64 *probe_offset, u64 *probe_addr,
+ unsigned long *missed)
{
bool is_tracepoint, is_syscall_tp;
struct bpf_prog *prog;
@@ -2422,7 +2424,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
#ifdef CONFIG_KPROBE_EVENTS
if (flags & TRACE_EVENT_FL_KPROBE)
err = bpf_get_kprobe_info(event, fd_type, buf,
- probe_offset, probe_addr,
+ probe_offset, probe_addr, missed,
event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
#ifdef CONFIG_UPROBE_EVENTS
@@ -2617,6 +2619,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
info->kprobe_multi.count = kmulti_link->cnt;
info->kprobe_multi.flags = kmulti_link->flags;
+ info->kprobe_multi.missed = kmulti_link->fp.nmissed;
if (!uaddrs)
return 0;
@@ -2713,6 +2716,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
int err;
if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+ bpf_prog_inc_misses_counter(link->link.prog);
err = 0;
goto out;
}
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 881f90f0cb..6cd2a4e3af 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -187,7 +187,7 @@ static void fprobe_init(struct fprobe *fp)
static int fprobe_init_rethook(struct fprobe *fp, int num)
{
- int i, size;
+ int size;
if (num <= 0)
return -EINVAL;
@@ -205,26 +205,18 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
if (size <= 0)
return -EINVAL;
- fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
- if (!fp->rethook)
- return -ENOMEM;
- for (i = 0; i < size; i++) {
- struct fprobe_rethook_node *node;
-
- node = kzalloc(sizeof(*node) + fp->entry_data_size, GFP_KERNEL);
- if (!node) {
- rethook_free(fp->rethook);
- fp->rethook = NULL;
- return -ENOMEM;
- }
- rethook_add_node(fp->rethook, &node->node);
- }
+ /* Initialize rethook */
+ fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler,
+ sizeof(struct fprobe_rethook_node), size);
+ if (IS_ERR(fp->rethook))
+ return PTR_ERR(fp->rethook);
+
return 0;
}
static void fprobe_fail_cleanup(struct fprobe *fp)
{
- if (fp->rethook) {
+ if (!IS_ERR_OR_NULL(fp->rethook)) {
/* Don't need to cleanup rethook->handler because this is not used. */
rethook_free(fp->rethook);
fp->rethook = NULL;
@@ -379,14 +371,14 @@ int unregister_fprobe(struct fprobe *fp)
if (!fprobe_is_registered(fp))
return -EINVAL;
- if (fp->rethook)
+ if (!IS_ERR_OR_NULL(fp->rethook))
rethook_stop(fp->rethook);
ret = unregister_ftrace_function(&fp->ops);
if (ret < 0)
return ret;
- if (fp->rethook)
+ if (!IS_ERR_OR_NULL(fp->rethook))
rethook_free(fp->rethook);
ftrace_free_filter(&fp->ops);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b01ae7d360..83ba342aef 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5325,7 +5325,17 @@ static LIST_HEAD(ftrace_direct_funcs);
static int register_ftrace_function_nolock(struct ftrace_ops *ops);
+/*
+ * If there are multiple ftrace_ops, use SAVE_REGS by default, so that direct
+ * call will be jumped from ftrace_regs_caller. Only if the architecture does
+ * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it
+ * jumps from ftrace_caller for multiple ftrace_ops.
+ */
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS
#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS)
+#else
+#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
+#endif
static int check_direct_multi(struct ftrace_ops *ops)
{
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 3cebcbaf35..fa03094e9e 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -8,7 +8,6 @@
#include <linux/preempt.h>
#include <linux/rethook.h>
#include <linux/slab.h>
-#include <linux/sort.h>
/* Return hook list (shadow stack by list) */
@@ -36,21 +35,7 @@ void rethook_flush_task(struct task_struct *tk)
static void rethook_free_rcu(struct rcu_head *head)
{
struct rethook *rh = container_of(head, struct rethook, rcu);
- struct rethook_node *rhn;
- struct freelist_node *node;
- int count = 1;
-
- node = rh->pool.head;
- while (node) {
- rhn = container_of(node, struct rethook_node, freelist);
- node = node->next;
- kfree(rhn);
- count++;
- }
-
- /* The rh->ref is the number of pooled node + 1 */
- if (refcount_sub_and_test(count, &rh->ref))
- kfree(rh);
+ objpool_fini(&rh->pool);
}
/**
@@ -83,6 +68,20 @@ void rethook_free(struct rethook *rh)
call_rcu(&rh->rcu, rethook_free_rcu);
}
+static int rethook_init_node(void *nod, void *context)
+{
+ struct rethook_node *node = nod;
+
+ node->rethook = context;
+ return 0;
+}
+
+static int rethook_fini_pool(struct objpool_head *head, void *context)
+{
+ kfree(context);
+ return 0;
+}
+
static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
{
return (rethook_handler_t)rcu_dereference_check(rh->handler,
@@ -92,51 +91,45 @@ static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
/**
* rethook_alloc() - Allocate struct rethook.
* @data: a data to pass the @handler when hooking the return.
- * @handler: the return hook callback function.
+ * @handler: the return hook callback function, must NOT be NULL
+ * @size: node size: rethook node and additional data
+ * @num: number of rethook nodes to be preallocated
*
* Allocate and initialize a new rethook with @data and @handler.
- * Return NULL if memory allocation fails or @handler is NULL.
+ * Return pointer of new rethook, or error codes for failures.
+ *
* Note that @handler == NULL means this rethook is going to be freed.
*/
-struct rethook *rethook_alloc(void *data, rethook_handler_t handler)
+struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
+ int size, int num)
{
- struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
+ struct rethook *rh;
- if (!rh || !handler) {
- kfree(rh);
- return NULL;
- }
+ if (!handler || num <= 0 || size < sizeof(struct rethook_node))
+ return ERR_PTR(-EINVAL);
+
+ rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
+ if (!rh)
+ return ERR_PTR(-ENOMEM);
rh->data = data;
rcu_assign_pointer(rh->handler, handler);
- rh->pool.head = NULL;
- refcount_set(&rh->ref, 1);
+ /* initialize the objpool for rethook nodes */
+ if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
+ rethook_init_node, rethook_fini_pool)) {
+ kfree(rh);
+ return ERR_PTR(-ENOMEM);
+ }
return rh;
}
-/**
- * rethook_add_node() - Add a new node to the rethook.
- * @rh: the struct rethook.
- * @node: the struct rethook_node to be added.
- *
- * Add @node to @rh. User must allocate @node (as a part of user's
- * data structure.) The @node fields are initialized in this function.
- */
-void rethook_add_node(struct rethook *rh, struct rethook_node *node)
-{
- node->rethook = rh;
- freelist_add(&node->freelist, &rh->pool);
- refcount_inc(&rh->ref);
-}
-
static void free_rethook_node_rcu(struct rcu_head *head)
{
struct rethook_node *node = container_of(head, struct rethook_node, rcu);
+ struct rethook *rh = node->rethook;
- if (refcount_dec_and_test(&node->rethook->ref))
- kfree(node->rethook);
- kfree(node);
+ objpool_drop(node, &rh->pool);
}
/**
@@ -152,7 +145,7 @@ void rethook_recycle(struct rethook_node *node)
handler = rethook_get_handler(node->rethook);
if (likely(handler))
- freelist_add(&node->freelist, &node->rethook->pool);
+ objpool_push(node, &node->rethook->pool);
else
call_rcu(&node->rcu, free_rethook_node_rcu);
}
@@ -168,7 +161,6 @@ NOKPROBE_SYMBOL(rethook_recycle);
struct rethook_node *rethook_try_get(struct rethook *rh)
{
rethook_handler_t handler = rethook_get_handler(rh);
- struct freelist_node *fn;
/* Check whether @rh is going to be freed. */
if (unlikely(!handler))
@@ -183,11 +175,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
if (unlikely(!rcu_is_watching()))
return NULL;
- fn = freelist_try_get(&rh->pool);
- if (!fn)
- return NULL;
-
- return container_of(fn, struct rethook_node, freelist);
+ return (struct rethook_node *)objpool_pop(&rh->pool);
}
NOKPROBE_SYMBOL(rethook_try_get);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f232cf56fa..6fa67c297e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1091,7 +1091,7 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
full = 0;
} else {
if (!cpumask_test_cpu(cpu, buffer->cpumask))
- return -EINVAL;
+ return EPOLLERR;
cpu_buffer = buffer->buffers[cpu];
work = &cpu_buffer->irq_work;
@@ -2021,7 +2021,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
retries = 10;
success = false;
while (retries--) {
- struct list_head *head_page, *prev_page, *r;
+ struct list_head *head_page, *prev_page;
struct list_head *last_page, *first_page;
struct list_head *head_page_with_bit;
struct buffer_page *hpage = rb_set_head_page(cpu_buffer);
@@ -2040,9 +2040,9 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
last_page->next = head_page_with_bit;
first_page->prev = prev_page;
- r = cmpxchg(&prev_page->next, head_page_with_bit, first_page);
-
- if (r == head_page_with_bit) {
+ /* caution: head_page_with_bit gets updated on cmpxchg failure */
+ if (try_cmpxchg(&prev_page->next,
+ &head_page_with_bit, first_page)) {
/*
* yay, we replaced the page pointer to our new list,
* now, we just have to update to head page's prev
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index fc00356a5a..3fdc57450e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -39,6 +39,7 @@
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/panic_notifier.h>
+#include <linux/kmemleak.h>
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/fs.h>
@@ -54,12 +55,6 @@
#include "trace.h"
#include "trace_output.h"
-/*
- * On boot up, the ring buffer is set to the minimum size, so that
- * we do not waste memory on systems that are not using tracing.
- */
-bool ring_buffer_expanded;
-
#ifdef CONFIG_FTRACE_STARTUP_TEST
/*
* We need to change this state when a selftest is running.
@@ -202,7 +197,7 @@ static int __init set_cmdline_ftrace(char *str)
strscpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
/* We are using ftrace early, expand it */
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
return 1;
}
__setup("ftrace=", set_cmdline_ftrace);
@@ -247,7 +242,7 @@ static int __init boot_alloc_snapshot(char *str)
} else {
allocate_snapshot = true;
/* We also need the main ring buffer expanded */
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
}
return 1;
}
@@ -490,6 +485,13 @@ static struct trace_array global_trace = {
.trace_flags = TRACE_DEFAULT_FLAGS,
};
+void trace_set_ring_buffer_expanded(struct trace_array *tr)
+{
+ if (!tr)
+ tr = &global_trace;
+ tr->ring_buffer_expanded = true;
+}
+
LIST_HEAD(ftrace_trace_arrays);
int trace_array_get(struct trace_array *this_tr)
@@ -1730,15 +1732,15 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
{
int len;
- if (trace_seq_used(s) <= s->seq.readpos)
+ if (trace_seq_used(s) <= s->readpos)
return -EBUSY;
- len = trace_seq_used(s) - s->seq.readpos;
+ len = trace_seq_used(s) - s->readpos;
if (cnt > len)
cnt = len;
- memcpy(buf, s->buffer + s->seq.readpos, cnt);
+ memcpy(buf, s->buffer + s->readpos, cnt);
- s->seq.readpos += cnt;
+ s->readpos += cnt;
return cnt;
}
@@ -2026,7 +2028,7 @@ static int run_tracer_selftest(struct tracer *type)
#ifdef CONFIG_TRACER_MAX_TRACE
if (type->use_max_tr) {
/* If we expanded the buffers, make sure the max is expanded too */
- if (ring_buffer_expanded)
+ if (tr->ring_buffer_expanded)
ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size,
RING_BUFFER_ALL_CPUS);
tr->allocated_snapshot = true;
@@ -2052,7 +2054,7 @@ static int run_tracer_selftest(struct tracer *type)
tr->allocated_snapshot = false;
/* Shrink the max buffer again */
- if (ring_buffer_expanded)
+ if (tr->ring_buffer_expanded)
ring_buffer_resize(tr->max_buffer.buffer, 1,
RING_BUFFER_ALL_CPUS);
}
@@ -2311,7 +2313,7 @@ struct saved_cmdlines_buffer {
unsigned *map_cmdline_to_pid;
unsigned cmdline_num;
int cmdline_idx;
- char *saved_cmdlines;
+ char saved_cmdlines[];
};
static struct saved_cmdlines_buffer *savedcmd;
@@ -2325,47 +2327,60 @@ static inline void set_cmdline(int idx, const char *cmdline)
strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
}
-static int allocate_cmdlines_buffer(unsigned int val,
- struct saved_cmdlines_buffer *s)
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+ int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
+
+ kfree(s->map_cmdline_to_pid);
+ kmemleak_free(s);
+ free_pages((unsigned long)s, order);
+}
+
+static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
{
+ struct saved_cmdlines_buffer *s;
+ struct page *page;
+ int orig_size, size;
+ int order;
+
+ /* Figure out how much is needed to hold the given number of cmdlines */
+ orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+ order = get_order(orig_size);
+ size = 1 << (order + PAGE_SHIFT);
+ page = alloc_pages(GFP_KERNEL, order);
+ if (!page)
+ return NULL;
+
+ s = page_address(page);
+ kmemleak_alloc(s, size, 1, GFP_KERNEL);
+ memset(s, 0, sizeof(*s));
+
+ /* Round up to actual allocation */
+ val = (size - sizeof(*s)) / TASK_COMM_LEN;
+ s->cmdline_num = val;
+
s->map_cmdline_to_pid = kmalloc_array(val,
sizeof(*s->map_cmdline_to_pid),
GFP_KERNEL);
- if (!s->map_cmdline_to_pid)
- return -ENOMEM;
-
- s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
- if (!s->saved_cmdlines) {
- kfree(s->map_cmdline_to_pid);
- return -ENOMEM;
+ if (!s->map_cmdline_to_pid) {
+ free_saved_cmdlines_buffer(s);
+ return NULL;
}
s->cmdline_idx = 0;
- s->cmdline_num = val;
memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
sizeof(s->map_pid_to_cmdline));
memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
val * sizeof(*s->map_cmdline_to_pid));
- return 0;
+ return s;
}
static int trace_create_savedcmd(void)
{
- int ret;
-
- savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
- if (!savedcmd)
- return -ENOMEM;
-
- ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
- if (ret < 0) {
- kfree(savedcmd);
- savedcmd = NULL;
- return -ENOMEM;
- }
+ savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
- return 0;
+ return savedcmd ? 0 : -ENOMEM;
}
int is_tracing_stopped(void)
@@ -3374,7 +3389,7 @@ void trace_printk_init_buffers(void)
pr_warn("**********************************************************\n");
/* Expand the buffers to set size */
- tracing_update_buffers();
+ tracing_update_buffers(&global_trace);
buffers_allocated = 1;
@@ -3798,15 +3813,6 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
return false;
}
-static const char *show_buffer(struct trace_seq *s)
-{
- struct seq_buf *seq = &s->seq;
-
- seq_buf_terminate(seq);
-
- return seq->buffer;
-}
-
static DEFINE_STATIC_KEY_FALSE(trace_no_verify);
static int test_can_verify_check(const char *fmt, ...)
@@ -3946,7 +3952,7 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
*/
if (WARN_ONCE(!trace_safe_str(iter, str, star, len),
"fmt: '%s' current_buffer: '%s'",
- fmt, show_buffer(&iter->seq))) {
+ fmt, seq_buf_str(&iter->seq.seq))) {
int ret;
/* Try to safely read the string */
@@ -6056,26 +6062,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
-static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
-{
- kfree(s->saved_cmdlines);
- kfree(s->map_cmdline_to_pid);
- kfree(s);
-}
-
static int tracing_resize_saved_cmdlines(unsigned int val)
{
struct saved_cmdlines_buffer *s, *savedcmd_temp;
- s = kmalloc(sizeof(*s), GFP_KERNEL);
+ s = allocate_cmdlines_buffer(val);
if (!s)
return -ENOMEM;
- if (allocate_cmdlines_buffer(val, s) < 0) {
- kfree(s);
- return -ENOMEM;
- }
-
preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
savedcmd_temp = savedcmd;
@@ -6370,7 +6364,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
* we use the size that was given, and we can forget about
* expanding it later.
*/
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(tr);
/* May be called before buffers are initialized */
if (!tr->array_buffer.buffer)
@@ -6451,6 +6445,7 @@ out:
/**
* tracing_update_buffers - used by tracing facility to expand ring buffers
+ * @tr: The tracing instance
*
* To save on memory when the tracing is never used on a system with it
* configured in. The ring buffers are set to a minimum size. But once
@@ -6459,13 +6454,13 @@ out:
*
* This function is to be called when a tracer is about to be used.
*/
-int tracing_update_buffers(void)
+int tracing_update_buffers(struct trace_array *tr)
{
int ret = 0;
mutex_lock(&trace_types_lock);
- if (!ring_buffer_expanded)
- ret = __tracing_resize_ring_buffer(&global_trace, trace_buf_size,
+ if (!tr->ring_buffer_expanded)
+ ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
RING_BUFFER_ALL_CPUS);
mutex_unlock(&trace_types_lock);
@@ -6519,7 +6514,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
mutex_lock(&trace_types_lock);
- if (!ring_buffer_expanded) {
+ if (!tr->ring_buffer_expanded) {
ret = __tracing_resize_ring_buffer(tr, trace_buf_size,
RING_BUFFER_ALL_CPUS);
if (ret < 0)
@@ -7005,7 +7000,7 @@ waitagain:
/* Now copy what we have to the user */
sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
- if (iter->seq.seq.readpos >= trace_seq_used(&iter->seq))
+ if (iter->seq.readpos >= trace_seq_used(&iter->seq))
trace_seq_init(&iter->seq);
/*
@@ -7191,7 +7186,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
}
if (buf_size_same) {
- if (!ring_buffer_expanded)
+ if (!tr->ring_buffer_expanded)
r = sprintf(buf, "%lu (expanded: %lu)\n",
size >> 10,
trace_buf_size >> 10);
@@ -7248,10 +7243,10 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf,
mutex_lock(&trace_types_lock);
for_each_tracing_cpu(cpu) {
size += per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10;
- if (!ring_buffer_expanded)
+ if (!tr->ring_buffer_expanded)
expanded_size += trace_buf_size >> 10;
}
- if (ring_buffer_expanded)
+ if (tr->ring_buffer_expanded)
r = sprintf(buf, "%lu\n", size);
else
r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size);
@@ -7645,7 +7640,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
unsigned long val;
int ret;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(tr);
if (ret < 0)
return ret;
@@ -9549,6 +9544,9 @@ static struct trace_array *trace_array_create(const char *name)
if (allocate_trace_buffers(tr, trace_buf_size) < 0)
goto out_free_tr;
+ /* The ring buffer is defaultly expanded */
+ trace_set_ring_buffer_expanded(tr);
+
if (ftrace_allocate_ftrace_ops(tr) < 0)
goto out_free_tr;
@@ -9758,7 +9756,6 @@ static __init void create_trace_instances(struct dentry *d_tracer)
static void
init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
{
- struct trace_event_file *file;
int cpu;
trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer,
@@ -9791,11 +9788,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
trace_create_file("trace_marker", 0220, d_tracer,
tr, &tracing_mark_fops);
- file = __find_event_file(tr, "ftrace", "print");
- if (file && file->ef)
- eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef,
- file, &event_trigger_fops);
- tr->trace_marker_file = file;
+ tr->trace_marker_file = __find_event_file(tr, "ftrace", "print");
trace_create_file("trace_marker_raw", 0220, d_tracer,
tr, &tracing_mark_raw_fops);
@@ -10443,7 +10436,7 @@ __init static int tracer_alloc_buffers(void)
trace_printk_init_buffers();
/* To save memory, keep the ring buffer size to its minimum */
- if (ring_buffer_expanded)
+ if (global_trace.ring_buffer_expanded)
ring_buf_size = trace_buf_size;
else
ring_buf_size = 1;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 51c0a97033..0489e72c81 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -381,7 +381,7 @@ struct trace_array {
struct dentry *dir;
struct dentry *options;
struct dentry *percpu_dir;
- struct dentry *event_dir;
+ struct eventfs_inode *event_dir;
struct trace_options *topts;
struct list_head systems;
struct list_head events;
@@ -410,6 +410,11 @@ struct trace_array {
struct cond_snapshot *cond_snapshot;
#endif
struct trace_func_repeats __percpu *last_func_repeats;
+ /*
+ * On boot up, the ring buffer is set to the minimum size, so that
+ * we do not waste memory on systems that are not using tracing.
+ */
+ bool ring_buffer_expanded;
};
enum {
@@ -762,7 +767,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
extern int DYN_FTRACE_TEST_NAME2(void);
-extern bool ring_buffer_expanded;
+extern void trace_set_ring_buffer_expanded(struct trace_array *tr);
extern bool tracing_selftest_disabled;
#ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1306,7 +1311,7 @@ static inline void trace_branch_disable(void)
#endif /* CONFIG_BRANCH_TRACER */
/* set ring buffers to default size if not already done so */
-int tracing_update_buffers(void);
+int tracing_update_buffers(struct trace_array *tr);
union trace_synth_field {
u8 as_u8;
@@ -1345,7 +1350,7 @@ struct trace_subsystem_dir {
struct list_head list;
struct event_subsystem *subsystem;
struct trace_array *tr;
- struct eventfs_file *ef;
+ struct eventfs_inode *ei;
int ref_count;
int nr_events;
};
diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c
index ca224d53bf..5bbdbcbbde 100644
--- a/kernel/trace/trace_btf.c
+++ b/kernel/trace/trace_btf.c
@@ -91,8 +91,8 @@ retry:
for_each_member(i, type, member) {
if (!member->name_off) {
/* Anonymous union/struct: push it for later use */
- type = btf_type_skip_modifiers(btf, member->type, &tid);
- if (type && top < BTF_ANON_STACK_MAX) {
+ if (btf_type_skip_modifiers(btf, member->type, &tid) &&
+ top < BTF_ANON_STACK_MAX) {
anon_stack[top].tid = tid;
anon_stack[top++].offset =
cur_offset + member->offset;
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 72714cbf47..03c851f579 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -788,12 +788,9 @@ find_and_get_event(const char *system, const char *event_name)
name = trace_event_name(tp_event);
if (!name || strcmp(event_name, name))
continue;
- if (!trace_event_try_get_ref(tp_event)) {
+ if (!trace_event_try_get_ref(tp_event))
return NULL;
- break;
- }
return tp_event;
- break;
}
return NULL;
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 82cb22ad6d..f29e815ca5 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -984,7 +984,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
return;
if (!--dir->nr_events) {
- eventfs_remove(dir->ef);
+ eventfs_remove_dir(dir->ei);
list_del(&dir->list);
__put_system_dir(dir);
}
@@ -1013,7 +1013,7 @@ void event_file_put(struct trace_event_file *file)
static void remove_event_file_dir(struct trace_event_file *file)
{
- eventfs_remove(file->ef);
+ eventfs_remove_dir(file->ei);
list_del(&file->list);
remove_subsystem(file->system);
free_event_filter(file->filter);
@@ -1188,7 +1188,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
if (!cnt)
return 0;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(tr);
if (ret < 0)
return ret;
@@ -1419,18 +1419,20 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (ret)
return ret;
- ret = tracing_update_buffers();
- if (ret < 0)
- return ret;
-
switch (val) {
case 0:
case 1:
ret = -ENODEV;
mutex_lock(&event_mutex);
file = event_file_data(filp);
- if (likely(file && !(file->flags & EVENT_FILE_FL_FREED)))
+ if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) {
+ ret = tracing_update_buffers(file->tr);
+ if (ret < 0) {
+ mutex_unlock(&event_mutex);
+ return ret;
+ }
ret = ftrace_event_enable_disable(file, val);
+ }
mutex_unlock(&event_mutex);
break;
@@ -1504,7 +1506,7 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (ret)
return ret;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(dir->tr);
if (ret < 0)
return ret;
@@ -1978,7 +1980,7 @@ event_pid_write(struct file *filp, const char __user *ubuf,
if (!cnt)
return 0;
- ret = tracing_update_buffers();
+ ret = tracing_update_buffers(tr);
if (ret < 0)
return ret;
@@ -2302,14 +2304,40 @@ create_new_subsystem(const char *name)
return NULL;
}
-static struct eventfs_file *
+static int system_callback(const char *name, umode_t *mode, void **data,
+ const struct file_operations **fops)
+{
+ if (strcmp(name, "filter") == 0)
+ *fops = &ftrace_subsystem_filter_fops;
+
+ else if (strcmp(name, "enable") == 0)
+ *fops = &ftrace_system_enable_fops;
+
+ else
+ return 0;
+
+ *mode = TRACE_MODE_WRITE;
+ return 1;
+}
+
+static struct eventfs_inode *
event_subsystem_dir(struct trace_array *tr, const char *name,
- struct trace_event_file *file, struct dentry *parent)
+ struct trace_event_file *file, struct eventfs_inode *parent)
{
struct event_subsystem *system, *iter;
struct trace_subsystem_dir *dir;
- struct eventfs_file *ef;
- int res;
+ struct eventfs_inode *ei;
+ int nr_entries;
+ static struct eventfs_entry system_entries[] = {
+ {
+ .name = "filter",
+ .callback = system_callback,
+ },
+ {
+ .name = "enable",
+ .callback = system_callback,
+ }
+ };
/* First see if we did not already create this dir */
list_for_each_entry(dir, &tr->systems, list) {
@@ -2317,7 +2345,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
if (strcmp(system->name, name) == 0) {
dir->nr_events++;
file->system = dir;
- return dir->ef;
+ return dir->ei;
}
}
@@ -2341,39 +2369,29 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
} else
__get_system(system);
- ef = eventfs_add_subsystem_dir(name, parent);
- if (IS_ERR(ef)) {
+ /* ftrace only has directories no files */
+ if (strcmp(name, "ftrace") == 0)
+ nr_entries = 0;
+ else
+ nr_entries = ARRAY_SIZE(system_entries);
+
+ ei = eventfs_create_dir(name, parent, system_entries, nr_entries, dir);
+ if (IS_ERR(ei)) {
pr_warn("Failed to create system directory %s\n", name);
__put_system(system);
goto out_free;
}
- dir->ef = ef;
+ dir->ei = ei;
dir->tr = tr;
dir->ref_count = 1;
dir->nr_events = 1;
dir->subsystem = system;
file->system = dir;
- /* the ftrace system is special, do not create enable or filter files */
- if (strcmp(name, "ftrace") != 0) {
-
- res = eventfs_add_file("filter", TRACE_MODE_WRITE,
- dir->ef, dir,
- &ftrace_subsystem_filter_fops);
- if (res) {
- kfree(system->filter);
- system->filter = NULL;
- pr_warn("Could not create tracefs '%s/filter' entry\n", name);
- }
-
- eventfs_add_file("enable", TRACE_MODE_WRITE, dir->ef, dir,
- &ftrace_system_enable_fops);
- }
-
list_add(&dir->list, &tr->systems);
- return dir->ef;
+ return dir->ei;
out_free:
kfree(dir);
@@ -2422,15 +2440,134 @@ event_define_fields(struct trace_event_call *call)
return ret;
}
+static int event_callback(const char *name, umode_t *mode, void **data,
+ const struct file_operations **fops)
+{
+ struct trace_event_file *file = *data;
+ struct trace_event_call *call = file->event_call;
+
+ if (strcmp(name, "format") == 0) {
+ *mode = TRACE_MODE_READ;
+ *fops = &ftrace_event_format_fops;
+ *data = call;
+ return 1;
+ }
+
+ /*
+ * Only event directories that can be enabled should have
+ * triggers or filters, with the exception of the "print"
+ * event that can have a "trigger" file.
+ */
+ if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
+ if (call->class->reg && strcmp(name, "enable") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &ftrace_enable_fops;
+ return 1;
+ }
+
+ if (strcmp(name, "filter") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &ftrace_event_filter_fops;
+ return 1;
+ }
+ }
+
+ if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) ||
+ strcmp(trace_event_name(call), "print") == 0) {
+ if (strcmp(name, "trigger") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &event_trigger_fops;
+ return 1;
+ }
+ }
+
+#ifdef CONFIG_PERF_EVENTS
+ if (call->event.type && call->class->reg &&
+ strcmp(name, "id") == 0) {
+ *mode = TRACE_MODE_READ;
+ *data = (void *)(long)call->event.type;
+ *fops = &ftrace_event_id_fops;
+ return 1;
+ }
+#endif
+
+#ifdef CONFIG_HIST_TRIGGERS
+ if (strcmp(name, "hist") == 0) {
+ *mode = TRACE_MODE_READ;
+ *fops = &event_hist_fops;
+ return 1;
+ }
+#endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+ if (strcmp(name, "hist_debug") == 0) {
+ *mode = TRACE_MODE_READ;
+ *fops = &event_hist_debug_fops;
+ return 1;
+ }
+#endif
+#ifdef CONFIG_TRACE_EVENT_INJECT
+ if (call->event.type && call->class->reg &&
+ strcmp(name, "inject") == 0) {
+ *mode = 0200;
+ *fops = &event_inject_fops;
+ return 1;
+ }
+#endif
+ return 0;
+}
+
static int
-event_create_dir(struct dentry *parent, struct trace_event_file *file)
+event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file)
{
struct trace_event_call *call = file->event_call;
- struct eventfs_file *ef_subsystem = NULL;
struct trace_array *tr = file->tr;
- struct eventfs_file *ef;
+ struct eventfs_inode *e_events;
+ struct eventfs_inode *ei;
const char *name;
+ int nr_entries;
int ret;
+ static struct eventfs_entry event_entries[] = {
+ {
+ .name = "enable",
+ .callback = event_callback,
+ },
+ {
+ .name = "filter",
+ .callback = event_callback,
+ },
+ {
+ .name = "trigger",
+ .callback = event_callback,
+ },
+ {
+ .name = "format",
+ .callback = event_callback,
+ },
+#ifdef CONFIG_PERF_EVENTS
+ {
+ .name = "id",
+ .callback = event_callback,
+ },
+#endif
+#ifdef CONFIG_HIST_TRIGGERS
+ {
+ .name = "hist",
+ .callback = event_callback,
+ },
+#endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+ {
+ .name = "hist_debug",
+ .callback = event_callback,
+ },
+#endif
+#ifdef CONFIG_TRACE_EVENT_INJECT
+ {
+ .name = "inject",
+ .callback = event_callback,
+ },
+#endif
+ };
/*
* If the trace point header did not define TRACE_SYSTEM
@@ -2440,29 +2577,20 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
if (WARN_ON_ONCE(strcmp(call->class->system, TRACE_SYSTEM) == 0))
return -ENODEV;
- ef_subsystem = event_subsystem_dir(tr, call->class->system, file, parent);
- if (!ef_subsystem)
+ e_events = event_subsystem_dir(tr, call->class->system, file, parent);
+ if (!e_events)
return -ENOMEM;
+ nr_entries = ARRAY_SIZE(event_entries);
+
name = trace_event_name(call);
- ef = eventfs_add_dir(name, ef_subsystem);
- if (IS_ERR(ef)) {
+ ei = eventfs_create_dir(name, e_events, event_entries, nr_entries, file);
+ if (IS_ERR(ei)) {
pr_warn("Could not create tracefs '%s' directory\n", name);
return -1;
}
- file->ef = ef;
-
- if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
- eventfs_add_file("enable", TRACE_MODE_WRITE, file->ef, file,
- &ftrace_enable_fops);
-
-#ifdef CONFIG_PERF_EVENTS
- if (call->event.type && call->class->reg)
- eventfs_add_file("id", TRACE_MODE_READ, file->ef,
- (void *)(long)call->event.type,
- &ftrace_event_id_fops);
-#endif
+ file->ei = ei;
ret = event_define_fields(call);
if (ret < 0) {
@@ -2470,35 +2598,6 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
return ret;
}
- /*
- * Only event directories that can be enabled should have
- * triggers or filters.
- */
- if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) {
- eventfs_add_file("filter", TRACE_MODE_WRITE, file->ef,
- file, &ftrace_event_filter_fops);
-
- eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef,
- file, &event_trigger_fops);
- }
-
-#ifdef CONFIG_HIST_TRIGGERS
- eventfs_add_file("hist", TRACE_MODE_READ, file->ef, file,
- &event_hist_fops);
-#endif
-#ifdef CONFIG_HIST_TRIGGERS_DEBUG
- eventfs_add_file("hist_debug", TRACE_MODE_READ, file->ef, file,
- &event_hist_debug_fops);
-#endif
- eventfs_add_file("format", TRACE_MODE_READ, file->ef, call,
- &ftrace_event_format_fops);
-
-#ifdef CONFIG_TRACE_EVENT_INJECT
- if (call->event.type && call->class->reg)
- eventfs_add_file("inject", 0200, file->ef, file,
- &event_inject_fops);
-#endif
-
return 0;
}
@@ -2847,7 +2946,7 @@ static __init int setup_trace_triggers(char *str)
int i;
strscpy(bootup_trigger_buf, str, COMMAND_LINE_SIZE);
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
disable_tracing_selftest("running event triggers");
buf = bootup_trigger_buf;
@@ -3637,37 +3736,72 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
static __init int setup_trace_event(char *str)
{
strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
- ring_buffer_expanded = true;
+ trace_set_ring_buffer_expanded(NULL);
disable_tracing_selftest("running event tracing");
return 1;
}
__setup("trace_event=", setup_trace_event);
+static int events_callback(const char *name, umode_t *mode, void **data,
+ const struct file_operations **fops)
+{
+ if (strcmp(name, "enable") == 0) {
+ *mode = TRACE_MODE_WRITE;
+ *fops = &ftrace_tr_enable_fops;
+ return 1;
+ }
+
+ if (strcmp(name, "header_page") == 0)
+ *data = ring_buffer_print_page_header;
+
+ else if (strcmp(name, "header_event") == 0)
+ *data = ring_buffer_print_entry_header;
+
+ else
+ return 0;
+
+ *mode = TRACE_MODE_READ;
+ *fops = &ftrace_show_header_fops;
+ return 1;
+}
+
/* Expects to have event_mutex held when called */
static int
create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
{
- struct dentry *d_events;
+ struct eventfs_inode *e_events;
struct dentry *entry;
- int error = 0;
+ int nr_entries;
+ static struct eventfs_entry events_entries[] = {
+ {
+ .name = "enable",
+ .callback = events_callback,
+ },
+ {
+ .name = "header_page",
+ .callback = events_callback,
+ },
+ {
+ .name = "header_event",
+ .callback = events_callback,
+ },
+ };
entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
tr, &ftrace_set_event_fops);
if (!entry)
return -ENOMEM;
- d_events = eventfs_create_events_dir("events", parent);
- if (IS_ERR(d_events)) {
+ nr_entries = ARRAY_SIZE(events_entries);
+
+ e_events = eventfs_create_events_dir("events", parent, events_entries,
+ nr_entries, tr);
+ if (IS_ERR(e_events)) {
pr_warn("Could not create tracefs 'events' directory\n");
return -ENOMEM;
}
- error = eventfs_add_events_file("enable", TRACE_MODE_WRITE, d_events,
- tr, &ftrace_tr_enable_fops);
- if (error)
- return -ENOMEM;
-
/* There are not as crucial, just warn if they are not created */
trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
@@ -3677,16 +3811,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
TRACE_MODE_WRITE, parent, tr,
&ftrace_set_event_notrace_pid_fops);
- /* ring buffer internal formats */
- eventfs_add_events_file("header_page", TRACE_MODE_READ, d_events,
- ring_buffer_print_page_header,
- &ftrace_show_header_fops);
-
- eventfs_add_events_file("header_event", TRACE_MODE_READ, d_events,
- ring_buffer_print_entry_header,
- &ftrace_show_header_fops);
-
- tr->event_dir = d_events;
+ tr->event_dir = e_events;
return 0;
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 68aaf0bd7a..5ecf3c8bde 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -774,23 +774,16 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
{
const char *system = NULL, *name = NULL;
struct trace_event_call *call;
- int len;
if (!str)
return;
- /* sizeof() contains the nul byte */
- len = sizeof(HIST_PREFIX) + strlen(str);
kfree(last_cmd);
- last_cmd = kzalloc(len, GFP_KERNEL);
+
+ last_cmd = kasprintf(GFP_KERNEL, HIST_PREFIX "%s", str);
if (!last_cmd)
return;
- strcpy(last_cmd, HIST_PREFIX);
- /* Again, sizeof() contains the nul byte */
- len -= sizeof(HIST_PREFIX);
- strncat(last_cmd, str, len);
-
if (file) {
call = file->event_call;
system = call->class->system;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 846e02c0fb..c82b401a29 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -441,8 +441,9 @@ static unsigned int trace_string(struct synth_trace_event *entry,
if (is_dynamic) {
union trace_synth_field *data = &entry->fields[*n_u64];
+ len = fetch_store_strlen((unsigned long)str_val);
data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size;
- data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val);
+ data->as_dynamic.len = len;
ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
@@ -1137,7 +1138,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_fields);
* @cmd: A pointer to the dynevent_cmd struct representing the new event
* @name: The name of the synthetic event
* @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
*
* NOTE: Users normally won't want to call this function directly, but
* rather use the synth_event_gen_cmd_start() wrapper, which
@@ -1695,7 +1696,7 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state)
* synth_event_trace - Trace a synthetic event
* @file: The trace_event_file representing the synthetic event
* @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
+ * @...: Variable number of args containing the event values
*
* Trace a synthetic event using the values passed in the variable
* argument list.
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 46439e3bce..b33c3861fb 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1470,8 +1470,10 @@ register_snapshot_trigger(char *glob,
struct event_trigger_data *data,
struct trace_event_file *file)
{
- if (tracing_alloc_snapshot_instance(file->tr) != 0)
- return 0;
+ int ret = tracing_alloc_snapshot_instance(file->tr);
+
+ if (ret < 0)
+ return ret;
return register_trigger(glob, data, file);
}
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index b87f41187c..9365ce4074 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -50,18 +50,6 @@
#define EVENT_STATUS_OTHER BIT(7)
/*
- * User register flags are not allowed yet, keep them here until we are
- * ready to expose them out to the user ABI.
- */
-enum user_reg_flag {
- /* Event will not delete upon last reference closing */
- USER_EVENT_REG_PERSIST = 1U << 0,
-
- /* This value or above is currently non-ABI */
- USER_EVENT_REG_MAX = 1U << 1,
-};
-
-/*
* Stores the system name, tables, and locks for a group of events. This
* allows isolation for events by various means.
*/
@@ -220,6 +208,17 @@ static u32 user_event_key(char *name)
return jhash(name, strlen(name), 0);
}
+static bool user_event_capable(u16 reg_flags)
+{
+ /* Persistent events require CAP_PERFMON / CAP_SYS_ADMIN */
+ if (reg_flags & USER_EVENT_REG_PERSIST) {
+ if (!perfmon_capable())
+ return false;
+ }
+
+ return true;
+}
+
static struct user_event *user_event_get(struct user_event *user)
{
refcount_inc(&user->refcnt);
@@ -1811,6 +1810,9 @@ static int user_event_free(struct dyn_event *ev)
if (!user_event_last_ref(user))
return -EBUSY;
+ if (!user_event_capable(user->reg_flags))
+ return -EPERM;
+
return destroy_user_event(user);
}
@@ -1926,10 +1928,13 @@ static int user_event_parse(struct user_event_group *group, char *name,
int argc = 0;
char **argv;
- /* User register flags are not ready yet */
- if (reg_flags != 0 || flags != NULL)
+ /* Currently don't support any text based flags */
+ if (flags != NULL)
return -EINVAL;
+ if (!user_event_capable(reg_flags))
+ return -EPERM;
+
/* Prevent dyn_event from racing */
mutex_lock(&event_mutex);
user = find_user_event(group, name, &key);
@@ -2062,6 +2067,9 @@ static int delete_user_event(struct user_event_group *group, char *name)
if (!user_event_last_ref(user))
return -EBUSY;
+ if (!user_event_capable(user->reg_flags))
+ return -EPERM;
+
return destroy_user_event(user);
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 47812aa16b..52f8b537dd 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1249,6 +1249,12 @@ static const struct file_operations kprobe_events_ops = {
.write = probes_write,
};
+static unsigned long trace_kprobe_missed(struct trace_kprobe *tk)
+{
+ return trace_kprobe_is_return(tk) ?
+ tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed;
+}
+
/* Probes profiling interfaces */
static int probes_profile_seq_show(struct seq_file *m, void *v)
{
@@ -1260,8 +1266,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
return 0;
tk = to_trace_kprobe(ev);
- nmissed = trace_kprobe_is_return(tk) ?
- tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed;
+ nmissed = trace_kprobe_missed(tk);
seq_printf(m, " %-44s %15lu %15lu\n",
trace_probe_name(&tk->tp),
trace_kprobe_nhit(tk),
@@ -1607,7 +1612,8 @@ NOKPROBE_SYMBOL(kretprobe_perf_func);
int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
const char **symbol, u64 *probe_offset,
- u64 *probe_addr, bool perf_type_tracepoint)
+ u64 *probe_addr, unsigned long *missed,
+ bool perf_type_tracepoint)
{
const char *pevent = trace_event_name(event->tp_event);
const char *group = event->tp_event->class->system;
@@ -1626,6 +1632,8 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
*probe_addr = kallsyms_show_value(current_cred()) ?
(unsigned long)tk->rp.kp.addr : 0;
*symbol = tk->symbol;
+ if (missed)
+ *missed = trace_kprobe_missed(tk);
return 0;
}
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index bd0d01d00f..a8e28f9b92 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2444,6 +2444,9 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
tlat = this_cpu_tmr_var();
tlat->count = 0;
+ hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
+ tlat->timer.function = timerlat_irq;
+
migrate_enable();
return 0;
};
@@ -2526,9 +2529,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
tlat->tracing_thread = false;
tlat->kthread = current;
- hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
- tlat->timer.function = timerlat_irq;
-
/* Annotate now to drift new period */
tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 3b7d3e9eb6..3e7fa44dc2 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -404,7 +404,7 @@ static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
vmstart = vma->vm_start;
}
if (file) {
- ret = trace_seq_path(s, &file->f_path);
+ ret = trace_seq_path(s, file_user_path(file));
if (ret)
trace_seq_printf(s, "[+0x%lx]",
ip - vmstart);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 4dc74d73fc..34289f9c67 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1159,9 +1159,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
if (!(ctx->flags & TPARG_FL_TEVENT) &&
(strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
strncmp(arg, "\\\"", 2) == 0)) {
- /* The type of $comm must be "string", and not an array. */
- if (parg->count || (t && strcmp(t, "string")))
+ /* The type of $comm must be "string", and not an array type. */
+ if (parg->count || (t && strcmp(t, "string"))) {
+ trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
+ NEED_STRING_TYPE);
goto out;
+ }
parg->type = find_fetch_type("string", ctx->flags);
} else
parg->type = find_fetch_type(t, ctx->flags);
@@ -1169,18 +1172,6 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE);
goto out;
}
- parg->offset = *size;
- *size += parg->type->size * (parg->count ?: 1);
-
- ret = -ENOMEM;
- if (parg->count) {
- len = strlen(parg->type->fmttype) + 6;
- parg->fmt = kmalloc(len, GFP_KERNEL);
- if (!parg->fmt)
- goto out;
- snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
- parg->count);
- }
code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL);
if (!code)
@@ -1204,6 +1195,19 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
goto fail;
}
}
+ parg->offset = *size;
+ *size += parg->type->size * (parg->count ?: 1);
+
+ if (parg->count) {
+ len = strlen(parg->type->fmttype) + 6;
+ parg->fmt = kmalloc(len, GFP_KERNEL);
+ if (!parg->fmt) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
+ parg->count);
+ }
ret = -EINVAL;
/* Store operation */
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 850d9ecb67..c1877d0182 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -515,7 +515,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(BAD_HYPHEN, "Failed to parse single hyphen. Forgot '>'?"), \
C(NO_BTF_FIELD, "This field is not found."), \
C(BAD_BTF_TID, "Failed to get BTF type info."),\
- C(BAD_TYPE4STR, "This type does not fit for string."),
+ C(BAD_TYPE4STR, "This type does not fit for string."),\
+ C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"),
#undef C
#define C(a, b) TP_ERR_##a
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index bac06ee3b9..7be97229dd 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -370,8 +370,12 @@ EXPORT_SYMBOL_GPL(trace_seq_path);
*/
int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt)
{
+ int ret;
__trace_seq_init(s);
- return seq_buf_to_user(&s->seq, ubuf, cnt);
+ ret = seq_buf_to_user(&s->seq, ubuf, s->readpos, cnt);
+ if (ret > 0)
+ s->readpos += ret;
+ return ret;
}
EXPORT_SYMBOL_GPL(trace_seq_to_user);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index de753403cd..9c581d6da8 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -556,7 +556,7 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
{
struct syscall_tp_t {
struct trace_entry ent;
- unsigned long syscall_nr;
+ int syscall_nr;
unsigned long args[SYSCALL_DEFINE_MAXARGS];
} __aligned(8) param;
int i;
@@ -661,7 +661,7 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
{
struct syscall_tp_t {
struct trace_entry ent;
- unsigned long syscall_nr;
+ int syscall_nr;
unsigned long ret;
} __aligned(8) param;