summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/trace/Kconfig6
-rw-r--r--kernel/trace/bpf_trace.c17
-rw-r--r--kernel/trace/fprobe.c32
-rw-r--r--kernel/trace/ftrace.c51
-rw-r--r--kernel/trace/ring_buffer.c102
-rw-r--r--kernel/trace/trace.c7
-rw-r--r--kernel/trace/trace.h2
-rw-r--r--kernel/trace/trace_events_user.c1034
-rw-r--r--kernel/trace/trace_output.c175
-rw-r--r--kernel/trace/trace_output.h2
12 files changed, 1172 insertions, 260 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index 86902cb5ab78..34b90e2e7cf7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -68,6 +68,7 @@
#include <linux/kprobes.h>
#include <linux/rethook.h>
#include <linux/sysfs.h>
+#include <linux/user_events.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
@@ -818,6 +819,7 @@ void __noreturn do_exit(long code)
coredump_task_exit(tsk);
ptrace_event(PTRACE_EVENT_EXIT, code);
+ user_events_exit(tsk);
validate_creds_for_do_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index eccb35a85216..735d9f4f5acf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -97,6 +97,7 @@
#include <linux/io_uring.h>
#include <linux/bpf.h>
#include <linux/stackprotector.h>
+#include <linux/user_events.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
@@ -2735,6 +2736,7 @@ __latent_entropy struct task_struct *copy_process(
trace_task_newtask(p, clone_flags);
uprobe_copy_process(p, clone_flags);
+ user_events_fork(p, clone_flags);
copy_oom_score_adj(clone_flags, p);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 5b1e7fa41ca8..8cf97fa4a4b3 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -792,15 +792,15 @@ config USER_EVENTS
bool "User trace events"
select TRACING
select DYNAMIC_EVENTS
- depends on BROKEN || COMPILE_TEST # API needs to be straighten out
help
User trace events are user-defined trace events that
can be used like an existing kernel trace event. User trace
events are generated by writing to a tracefs file. User
processes can determine if their tracing events should be
- generated by memory mapping a tracefs file and checking for
- an associated byte being non-zero.
+ generated by registering a value and bit with the kernel
+ that reflects when it is enabled or not.
+ See Documentation/trace/user_events.rst.
If in doubt, say N.
config HIST_TRIGGERS
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index bcf91bc7bf71..9a050e36dc6c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2640,9 +2640,20 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
return err;
}
-static void
+static int
kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
- struct pt_regs *regs)
+ struct pt_regs *regs, void *data)
+{
+ struct bpf_kprobe_multi_link *link;
+
+ link = container_of(fp, struct bpf_kprobe_multi_link, fp);
+ kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs);
+ return 0;
+}
+
+static void
+kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip,
+ struct pt_regs *regs, void *data)
{
struct bpf_kprobe_multi_link *link;
@@ -2844,7 +2855,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
goto error;
if (flags & BPF_F_KPROBE_MULTI_RETURN)
- link->fp.exit_handler = kprobe_multi_link_handler;
+ link->fp.exit_handler = kprobe_multi_link_exit_handler;
else
link->fp.entry_handler = kprobe_multi_link_handler;
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index e8143e368074..9abb3905bc8e 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -17,15 +17,17 @@
struct fprobe_rethook_node {
struct rethook_node node;
unsigned long entry_ip;
+ char data[];
};
static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
struct fprobe_rethook_node *fpr;
- struct rethook_node *rh;
+ struct rethook_node *rh = NULL;
struct fprobe *fp;
- int bit;
+ void *entry_data = NULL;
+ int bit, ret;
fp = container_of(ops, struct fprobe, ops);
if (fprobe_disabled(fp))
@@ -37,9 +39,6 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
return;
}
- if (fp->entry_handler)
- fp->entry_handler(fp, ip, ftrace_get_regs(fregs));
-
if (fp->exit_handler) {
rh = rethook_try_get(fp->rethook);
if (!rh) {
@@ -48,9 +47,20 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
}
fpr = container_of(rh, struct fprobe_rethook_node, node);
fpr->entry_ip = ip;
- rethook_hook(rh, ftrace_get_regs(fregs), true);
+ if (fp->entry_data_size)
+ entry_data = fpr->data;
}
+ if (fp->entry_handler)
+ ret = fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data);
+
+ /* If entry_handler returns !0, nmissed is not counted. */
+ if (rh) {
+ if (ret)
+ rethook_recycle(rh);
+ else
+ rethook_hook(rh, ftrace_get_regs(fregs), true);
+ }
out:
ftrace_test_recursion_unlock(bit);
}
@@ -81,7 +91,8 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data,
fpr = container_of(rh, struct fprobe_rethook_node, node);
- fp->exit_handler(fp, fpr->entry_ip, regs);
+ fp->exit_handler(fp, fpr->entry_ip, regs,
+ fp->entry_data_size ? (void *)fpr->data : NULL);
}
NOKPROBE_SYMBOL(fprobe_exit_handler);
@@ -136,7 +147,10 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
}
/* Initialize rethook if needed */
- size = num * num_possible_cpus() * 2;
+ if (fp->nr_maxactive)
+ size = fp->nr_maxactive;
+ else
+ size = num * num_possible_cpus() * 2;
if (size < 0)
return -E2BIG;
@@ -146,7 +160,7 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
for (i = 0; i < size; i++) {
struct fprobe_rethook_node *node;
- node = kzalloc(sizeof(*node), GFP_KERNEL);
+ node = kzalloc(sizeof(*node) + fp->entry_data_size, GFP_KERNEL);
if (!node) {
rethook_free(fp->rethook);
fp->rethook = NULL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 08155f652554..76973a70ab9d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -45,6 +45,9 @@
#include "trace_output.h"
#include "trace_stat.h"
+/* Flags that do not get reset */
+#define FTRACE_NOCLEAR_FLAGS (FTRACE_FL_DISABLED | FTRACE_FL_TOUCHED)
+
#define FTRACE_INVALID_FUNCTION "__ftrace_invalid_address__"
#define FTRACE_WARN_ON(cond) \
@@ -2256,7 +2259,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
flag ^= rec->flags & FTRACE_FL_ENABLED;
if (update) {
- rec->flags |= FTRACE_FL_ENABLED;
+ rec->flags |= FTRACE_FL_ENABLED | FTRACE_FL_TOUCHED;
if (flag & FTRACE_FL_REGS) {
if (rec->flags & FTRACE_FL_REGS)
rec->flags |= FTRACE_FL_REGS_EN;
@@ -2326,7 +2329,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
if (update) {
/* If there's no more users, clear all flags */
if (!ftrace_rec_count(rec))
- rec->flags &= FTRACE_FL_DISABLED;
+ rec->flags &= FTRACE_NOCLEAR_FLAGS;
else
/*
* Just disable the record, but keep the ops TRAMP
@@ -3147,7 +3150,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
struct dyn_ftrace *rec;
do_for_each_ftrace_rec(pg, rec) {
- if (FTRACE_WARN_ON_ONCE(rec->flags & ~FTRACE_FL_DISABLED))
+ if (FTRACE_WARN_ON_ONCE(rec->flags & ~FTRACE_NOCLEAR_FLAGS))
pr_warn(" %pS flags:%lx\n",
(void *)rec->ip, rec->flags);
} while_for_each_ftrace_rec();
@@ -3598,7 +3601,10 @@ t_func_next(struct seq_file *m, loff_t *pos)
!ftrace_lookup_ip(iter->hash, rec->ip)) ||
((iter->flags & FTRACE_ITER_ENABLED) &&
- !(rec->flags & FTRACE_FL_ENABLED))) {
+ !(rec->flags & FTRACE_FL_ENABLED)) ||
+
+ ((iter->flags & FTRACE_ITER_TOUCHED) &&
+ !(rec->flags & FTRACE_FL_TOUCHED))) {
rec = NULL;
goto retry;
@@ -3857,7 +3863,7 @@ static int t_show(struct seq_file *m, void *v)
return 0;
}
- if (iter->flags & FTRACE_ITER_ENABLED) {
+ if (iter->flags & (FTRACE_ITER_ENABLED | FTRACE_ITER_TOUCHED)) {
struct ftrace_ops *ops;
seq_printf(m, " (%ld)%s%s%s%s",
@@ -3959,6 +3965,31 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
return 0;
}
+static int
+ftrace_touched_open(struct inode *inode, struct file *file)
+{
+ struct ftrace_iterator *iter;
+
+ /*
+ * This shows us what functions have ever been enabled
+ * (traced, direct, patched, etc). Not sure if we want lockdown
+ * to hide such critical information for an admin.
+ * Although, perhaps it can show information we don't
+ * want people to see, but if something had traced
+ * something, we probably want to know about it.
+ */
+
+ iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
+ if (!iter)
+ return -ENOMEM;
+
+ iter->pg = ftrace_pages_start;
+ iter->flags = FTRACE_ITER_TOUCHED;
+ iter->ops = &global_ops;
+
+ return 0;
+}
+
/**
* ftrace_regex_open - initialize function tracer filter files
* @ops: The ftrace_ops that hold the hash filters
@@ -5872,6 +5903,13 @@ static const struct file_operations ftrace_enabled_fops = {
.release = seq_release_private,
};
+static const struct file_operations ftrace_touched_fops = {
+ .open = ftrace_touched_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
static const struct file_operations ftrace_filter_fops = {
.open = ftrace_filter_open,
.read = seq_read,
@@ -6336,6 +6374,9 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
trace_create_file("enabled_functions", TRACE_MODE_READ,
d_tracer, NULL, &ftrace_enabled_fops);
+ trace_create_file("touched_functions", TRACE_MODE_READ,
+ d_tracer, NULL, &ftrace_touched_fops);
+
ftrace_create_filter_files(&global_ops, d_tracer);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 76a2d91eecad..834b361a4a66 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -163,7 +163,7 @@ enum {
#define extended_time(event) \
(event->type_len >= RINGBUF_TYPE_TIME_EXTEND)
-static inline int rb_null_event(struct ring_buffer_event *event)
+static inline bool rb_null_event(struct ring_buffer_event *event)
{
return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
}
@@ -363,11 +363,9 @@ static void free_buffer_page(struct buffer_page *bpage)
/*
* We need to fit the time_stamp delta into 27 bits.
*/
-static inline int test_time_stamp(u64 delta)
+static inline bool test_time_stamp(u64 delta)
{
- if (delta & TS_DELTA_TEST)
- return 1;
- return 0;
+ return !!(delta & TS_DELTA_TEST);
}
#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
@@ -696,7 +694,7 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
return ret == expect;
}
-static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
+static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
{
unsigned long cnt, top, bottom, msb;
unsigned long cnt2, top2, bottom2, msb2;
@@ -1486,7 +1484,7 @@ rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
return NULL;
}
-static int rb_head_page_replace(struct buffer_page *old,
+static bool rb_head_page_replace(struct buffer_page *old,
struct buffer_page *new)
{
unsigned long *ptr = (unsigned long *)&old->list.prev->next;
@@ -1565,15 +1563,12 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
}
}
-static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
+static void rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
struct buffer_page *bpage)
{
unsigned long val = (unsigned long)bpage;
- if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
- return 1;
-
- return 0;
+ RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK);
}
/**
@@ -1583,30 +1578,28 @@ static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
* As a safety measure we check to make sure the data pages have not
* been corrupted.
*/
-static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
+static void rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
struct list_head *head = rb_list_head(cpu_buffer->pages);
struct list_head *tmp;
if (RB_WARN_ON(cpu_buffer,
rb_list_head(rb_list_head(head->next)->prev) != head))
- return -1;
+ return;
if (RB_WARN_ON(cpu_buffer,
rb_list_head(rb_list_head(head->prev)->next) != head))
- return -1;
+ return;
for (tmp = rb_list_head(head->next); tmp != head; tmp = rb_list_head(tmp->next)) {
if (RB_WARN_ON(cpu_buffer,
rb_list_head(rb_list_head(tmp->next)->prev) != tmp))
- return -1;
+ return;
if (RB_WARN_ON(cpu_buffer,
rb_list_head(rb_list_head(tmp->prev)->next) != tmp))
- return -1;
+ return;
}
-
- return 0;
}
static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
@@ -1774,6 +1767,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
struct list_head *head = cpu_buffer->pages;
struct buffer_page *bpage, *tmp;
+ irq_work_sync(&cpu_buffer->irq_work.work);
+
free_buffer_page(cpu_buffer->reader_page);
if (head) {
@@ -1880,6 +1875,8 @@ ring_buffer_free(struct trace_buffer *buffer)
cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
+ irq_work_sync(&buffer->irq_work.work);
+
for_each_buffer_cpu(buffer, cpu)
rb_free_cpu_buffer(buffer->buffers[cpu]);
@@ -1918,7 +1915,7 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage)
return local_read(&bpage->write) & RB_WRITE_MASK;
}
-static int
+static bool
rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
{
struct list_head *tail_page, *to_remove, *next_page;
@@ -2031,12 +2028,13 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
return nr_removed == 0;
}
-static int
+static bool
rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
struct list_head *pages = &cpu_buffer->new_pages;
- int retries, success;
unsigned long flags;
+ bool success;
+ int retries;
/* Can be called at early boot up, where interrupts must not been enabled */
raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -2055,15 +2053,16 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
* spinning.
*/
retries = 10;
- success = 0;
+ success = false;
while (retries--) {
struct list_head *head_page, *prev_page, *r;
struct list_head *last_page, *first_page;
struct list_head *head_page_with_bit;
+ struct buffer_page *hpage = rb_set_head_page(cpu_buffer);
- head_page = &rb_set_head_page(cpu_buffer)->list;
- if (!head_page)
+ if (!hpage)
break;
+ head_page = &hpage->list;
prev_page = head_page->prev;
first_page = pages->next;
@@ -2084,7 +2083,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
* pointer to point to end of list
*/
head_page->prev = last_page;
- success = 1;
+ success = true;
break;
}
}
@@ -2112,7 +2111,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
- int success;
+ bool success;
if (cpu_buffer->nr_pages_to_update > 0)
success = rb_insert_pages(cpu_buffer);
@@ -2995,7 +2994,7 @@ static u64 rb_time_delta(struct ring_buffer_event *event)
}
}
-static inline int
+static inline bool
rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
@@ -3016,7 +3015,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
delta = rb_time_delta(event);
if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
- return 0;
+ return false;
/* Make sure the write stamp is read before testing the location */
barrier();
@@ -3029,7 +3028,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
/* Something came in, can't discard */
if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
write_stamp, write_stamp - delta))
- return 0;
+ return false;
/*
* It's possible that the event time delta is zero
@@ -3062,12 +3061,12 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
if (index == old_index) {
/* update counters */
local_sub(event_length, &cpu_buffer->entries_bytes);
- return 1;
+ return true;
}
}
/* could not discard */
- return 0;
+ return false;
}
static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
@@ -3288,7 +3287,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
* Note: The TRANSITION bit only handles a single transition between context.
*/
-static __always_inline int
+static __always_inline bool
trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
{
unsigned int val = cpu_buffer->current_context;
@@ -3305,14 +3304,14 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
bit = RB_CTX_TRANSITION;
if (val & (1 << (bit + cpu_buffer->nest))) {
do_ring_buffer_record_recursion();
- return 1;
+ return true;
}
}
val |= (1 << (bit + cpu_buffer->nest));
cpu_buffer->current_context = val;
- return 0;
+ return false;
}
static __always_inline void
@@ -4069,10 +4068,10 @@ void ring_buffer_record_off(struct trace_buffer *buffer)
unsigned int rd;
unsigned int new_rd;
+ rd = atomic_read(&buffer->record_disabled);
do {
- rd = atomic_read(&buffer->record_disabled);
new_rd = rd | RB_BUFFER_OFF;
- } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+ } while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd));
}
EXPORT_SYMBOL_GPL(ring_buffer_record_off);
@@ -4092,10 +4091,10 @@ void ring_buffer_record_on(struct trace_buffer *buffer)
unsigned int rd;
unsigned int new_rd;
+ rd = atomic_read(&buffer->record_disabled);
do {
- rd = atomic_read(&buffer->record_disabled);
new_rd = rd & ~RB_BUFFER_OFF;
- } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+ } while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd));
}
EXPORT_SYMBOL_GPL(ring_buffer_record_on);
@@ -4502,7 +4501,6 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
default:
RB_WARN_ON(cpu_buffer, 1);
}
- return;
}
static void
@@ -4533,7 +4531,6 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
default:
RB_WARN_ON(iter->cpu_buffer, 1);
}
- return;
}
static struct buffer_page *
@@ -4543,7 +4540,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
unsigned long overwrite;
unsigned long flags;
int nr_loops = 0;
- int ret;
+ bool ret;
local_irq_save(flags);
arch_spin_lock(&cpu_buffer->lock);
@@ -4953,7 +4950,6 @@ rb_reader_unlock(struct ring_buffer_per_cpu *cpu_buffer, bool locked)
{
if (likely(locked))
raw_spin_unlock(&cpu_buffer->reader_lock);
- return;
}
/**
@@ -5345,6 +5341,9 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
}
EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
+/* Flag to ensure proper resetting of atomic variables */
+#define RESET_BIT (1 << 30)
+
/**
* ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer
* @buffer: The ring buffer to reset a per cpu buffer of
@@ -5361,20 +5360,27 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
for_each_online_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
- atomic_inc(&cpu_buffer->resize_disabled);
+ atomic_add(RESET_BIT, &cpu_buffer->resize_disabled);
atomic_inc(&cpu_buffer->record_disabled);
}
/* Make sure all commits have finished */
synchronize_rcu();
- for_each_online_buffer_cpu(buffer, cpu) {
+ for_each_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
+ /*
+ * If a CPU came online during the synchronize_rcu(), then
+ * ignore it.
+ */
+ if (!(atomic_read(&cpu_buffer->resize_disabled) & RESET_BIT))
+ continue;
+
reset_disabled_cpu_buffer(cpu_buffer);
atomic_dec(&cpu_buffer->record_disabled);
- atomic_dec(&cpu_buffer->resize_disabled);
+ atomic_sub(RESET_BIT, &cpu_buffer->resize_disabled);
}
mutex_unlock(&buffer->mutex);
@@ -5424,8 +5430,8 @@ bool ring_buffer_empty(struct trace_buffer *buffer)
struct ring_buffer_per_cpu *cpu_buffer;
unsigned long flags;
bool dolock;
+ bool ret;
int cpu;
- int ret;
/* yes this is racy, but if you don't like the race, lock the buffer */
for_each_buffer_cpu(buffer, cpu) {
@@ -5454,7 +5460,7 @@ bool ring_buffer_empty_cpu(struct trace_buffer *buffer, int cpu)
struct ring_buffer_per_cpu *cpu_buffer;
unsigned long flags;
bool dolock;
- int ret;
+ bool ret;
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return true;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 36a6037823cd..427da2341bf0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3726,7 +3726,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
#define STATIC_FMT_BUF_SIZE 128
static char static_fmt_buf[STATIC_FMT_BUF_SIZE];
-static char *trace_iter_expand_format(struct trace_iterator *iter)
+char *trace_iter_expand_format(struct trace_iterator *iter)
{
char *tmp;
@@ -4446,8 +4446,11 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
if (trace_seq_has_overflowed(s))
return TRACE_TYPE_PARTIAL_LINE;
- if (event)
+ if (event) {
+ if (tr->trace_flags & TRACE_ITER_FIELDS)
+ return print_event_fields(iter, event);
return event->funcs->trace(iter, sym_flags, event);
+ }
trace_seq_printf(s, "Unknown type %d\n", entry->type);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 616e1aa1c4da..79bdefe9261b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -619,6 +619,7 @@ bool trace_is_tracepoint_string(const char *str);
const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
va_list ap) __printf(2, 0);
+char *trace_iter_expand_format(struct trace_iterator *iter);
int trace_empty(struct trace_iterator *iter);
@@ -1199,6 +1200,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
C(HEX, "hex"), \
C(BIN, "bin"), \
C(BLOCK, "block"), \
+ C(FIELDS, "fields"), \
C(PRINTK, "trace_printk"), \
C(ANNOTATE, "annotate"), \
C(USERSTACKTRACE, "userstacktrace"), \
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 908e8a13c675..b1ecd7677642 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -19,14 +19,12 @@
#include <linux/tracefs.h>
#include <linux/types.h>
#include <linux/uaccess.h>
-/* Reminder to move to uapi when everything works */
-#ifdef CONFIG_COMPILE_TEST
+#include <linux/highmem.h>
+#include <linux/init.h>
#include <linux/user_events.h>
-#else
-#include <uapi/linux/user_events.h>
-#endif
-#include "trace.h"
#include "trace_dynevent.h"
+#include "trace_output.h"
+#include "trace.h"
#define USER_EVENTS_PREFIX_LEN (sizeof(USER_EVENTS_PREFIX)-1)
@@ -34,35 +32,12 @@
#define FIELD_DEPTH_NAME 1
#define FIELD_DEPTH_SIZE 2
-/*
- * Limits how many trace_event calls user processes can create:
- * Must be a power of two of PAGE_SIZE.
- */
-#define MAX_PAGE_ORDER 0
-#define MAX_PAGES (1 << MAX_PAGE_ORDER)
-#define MAX_BYTES (MAX_PAGES * PAGE_SIZE)
-#define MAX_EVENTS (MAX_BYTES * 8)
-
/* Limit how long of an event name plus args within the subsystem. */
#define MAX_EVENT_DESC 512
#define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
#define MAX_FIELD_ARRAY_SIZE 1024
/*
- * The MAP_STATUS_* macros are used for taking a index and determining the
- * appropriate byte and the bit in the byte to set/reset for an event.
- *
- * The lower 3 bits of the index decide which bit to set.
- * The remaining upper bits of the index decide which byte to use for the bit.
- *
- * This is used when an event has a probe attached/removed to reflect live
- * status of the event wanting tracing or not to user-programs via shared
- * memory maps.
- */
-#define MAP_STATUS_BYTE(index) ((index) >> 3)
-#define MAP_STATUS_MASK(index) BIT((index) & 7)
-
-/*
* Internal bits (kernel side only) to keep track of connected probes:
* These are used when status is requested in text form about an event. These
* bits are compared against an internal byte on the event to determine which
@@ -75,25 +50,25 @@
#define EVENT_STATUS_OTHER BIT(7)
/*
- * Stores the pages, tables, and locks for a group of events.
- * Each logical grouping of events has its own group, with a
- * matching page for status checks within user programs. This
- * allows for isolation of events to user programs by various
- * means.
+ * Stores the system name, tables, and locks for a group of events. This
+ * allows isolation for events by various means.
*/
struct user_event_group {
- struct page *pages;
- char *register_page_data;
- char *system_name;
- struct hlist_node node;
- struct mutex reg_mutex;
+ char *system_name;
+ struct hlist_node node;
+ struct mutex reg_mutex;
DECLARE_HASHTABLE(register_table, 8);
- DECLARE_BITMAP(page_bitmap, MAX_EVENTS);
};
/* Group for init_user_ns mapping, top-most group */
static struct user_event_group *init_group;
+/* Max allowed events for the whole system */
+static unsigned int max_user_events = 32768;
+
+/* Current number of events on the whole system */
+static unsigned int current_user_events;
+
/*
* Stores per-event properties, as users register events
* within a file a user_event might be created if it does not
@@ -102,21 +77,61 @@ static struct user_event_group *init_group;
* refcnt reaches one.
*/
struct user_event {
- struct user_event_group *group;
- struct tracepoint tracepoint;
- struct trace_event_call call;
- struct trace_event_class class;
- struct dyn_event devent;
- struct hlist_node node;
- struct list_head fields;
- struct list_head validators;
- refcount_t refcnt;
- int index;
- int flags;
- int min_size;
- char status;
+ struct user_event_group *group;
+ struct tracepoint tracepoint;
+ struct trace_event_call call;
+ struct trace_event_class class;
+ struct dyn_event devent;
+ struct hlist_node node;
+ struct list_head fields;
+ struct list_head validators;
+ refcount_t refcnt;
+ int min_size;
+ char status;
+};
+
+/*
+ * Stores per-mm/event properties that enable an address to be
+ * updated properly for each task. As tasks are forked, we use
+ * these to track enablement sites that are tied to an event.
+ */
+struct user_event_enabler {
+ struct list_head link;
+ struct user_event *event;
+ unsigned long addr;
+
+ /* Track enable bit, flags, etc. Aligned for bitops. */
+ unsigned int values;
+};
+
+/* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */
+#define ENABLE_VAL_BIT_MASK 0x3F
+
+/* Bit 6 is for faulting status of enablement */
+#define ENABLE_VAL_FAULTING_BIT 6
+
+/* Bit 7 is for freeing status of enablement */
+#define ENABLE_VAL_FREEING_BIT 7
+
+/* Only duplicate the bit value */
+#define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK
+
+#define ENABLE_BITOPS(e) ((unsigned long *)&(e)->values)
+
+/* Used for asynchronous faulting in of pages */
+struct user_event_enabler_fault {
+ struct work_struct work;
+ struct user_event_mm *mm;
+ struct user_event_enabler *enabler;
+ int attempt;
};
+static struct kmem_cache *fault_cache;
+
+/* Global list of memory descriptors using user_events */
+static LIST_HEAD(user_event_mms);
+static DEFINE_SPINLOCK(user_event_mms_lock);
+
/*
* Stores per-file events references, as users register events
* within a file this structure is modified and freed via RCU.
@@ -124,23 +139,23 @@ struct user_event {
* These are not shared and only accessible by the file that created it.
*/
struct user_event_refs {
- struct rcu_head rcu;
- int count;
- struct user_event *events[];
+ struct rcu_head rcu;
+ int count;
+ struct user_event *events[];
};
struct user_event_file_info {
- struct user_event_group *group;
- struct user_event_refs *refs;
+ struct user_event_group *group;
+ struct user_event_refs *refs;
};
#define VALIDATOR_ENSURE_NULL (1 << 0)
#define VALIDATOR_REL (1 << 1)
struct user_event_validator {
- struct list_head link;
- int offset;
- int flags;
+ struct list_head link;
+ int offset;
+ int flags;
};
typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i,
@@ -150,33 +165,17 @@ static int user_event_parse(struct user_event_group *group, char *name,
char *args, char *flags,
struct user_event **newuser);
+static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm);
+static struct user_event_mm *user_event_mm_get_all(struct user_event *user);
+static void user_event_mm_put(struct user_event_mm *mm);
+
static u32 user_event_key(char *name)
{
return jhash(name, strlen(name), 0);
}
-static void set_page_reservations(char *pages, bool set)
-{
- int page;
-
- for (page = 0; page < MAX_PAGES; ++page) {
- void *addr = pages + (PAGE_SIZE * page);
-
- if (set)
- SetPageReserved(virt_to_page(addr));
- else
- ClearPageReserved(virt_to_page(addr));
- }
-}
-
static void user_event_group_destroy(struct user_event_group *group)
{
- if (group->register_page_data)
- set_page_reservations(group->register_page_data, false);
-
- if (group->pages)
- __free_pages(group->pages, MAX_PAGE_ORDER);
-
kfree(group->system_name);
kfree(group);
}
@@ -247,19 +246,6 @@ static struct user_event_group
if (!group->system_name)
goto error;
- group->pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER);
-
- if (!group->pages)
- goto error;
-
- group->register_page_data = page_address(group->pages);
-
- set_page_reservations(group->register_page_data, true);
-
- /* Zero all bits beside 0 (which is reserved for failures) */
- bitmap_zero(group->page_bitmap, MAX_EVENTS);
- set_bit(0, group->page_bitmap);
-
mutex_init(&group->reg_mutex);
hash_init(group->register_table);
@@ -271,20 +257,514 @@ error:
return NULL;
};
-static __always_inline
-void user_event_register_set(struct user_event *user)
+static void user_event_enabler_destroy(struct user_event_enabler *enabler)
+{
+ list_del_rcu(&enabler->link);
+
+ /* No longer tracking the event via the enabler */
+ refcount_dec(&enabler->event->refcnt);
+
+ kfree(enabler);
+}
+
+static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr,
+ int attempt)
+{
+ bool unlocked;
+ int ret;
+
+ /*
+ * Normally this is low, ensure that it cannot be taken advantage of by
+ * bad user processes to cause excessive looping.
+ */
+ if (attempt > 10)
+ return -EFAULT;
+
+ mmap_read_lock(mm->mm);
+
+ /* Ensure MM has tasks, cannot use after exit_mm() */
+ if (refcount_read(&mm->tasks) == 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ ret = fixup_user_fault(mm->mm, uaddr, FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE,
+ &unlocked);
+out:
+ mmap_read_unlock(mm->mm);
+
+ return ret;
+}
+
+static int user_event_enabler_write(struct user_event_mm *mm,
+ struct user_event_enabler *enabler,
+ bool fixup_fault, int *attempt);
+
+static void user_event_enabler_fault_fixup(struct work_struct *work)
+{
+ struct user_event_enabler_fault *fault = container_of(
+ work, struct user_event_enabler_fault, work);
+ struct user_event_enabler *enabler = fault->enabler;
+ struct user_event_mm *mm = fault->mm;
+ unsigned long uaddr = enabler->addr;
+ int attempt = fault->attempt;
+ int ret;
+
+ ret = user_event_mm_fault_in(mm, uaddr, attempt);
+
+ if (ret && ret != -ENOENT) {
+ struct user_event *user = enabler->event;
+
+ pr_warn("user_events: Fault for mm: 0x%pK @ 0x%llx event: %s\n",
+ mm->mm, (unsigned long long)uaddr, EVENT_NAME(user));
+ }
+
+ /* Prevent state changes from racing */
+ mutex_lock(&event_mutex);
+
+ /* User asked for enabler to be removed during fault */
+ if (test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))) {
+ user_event_enabler_destroy(enabler);
+ goto out;
+ }
+
+ /*
+ * If we managed to get the page, re-issue the write. We do not
+ * want to get into a possible infinite loop, which is why we only
+ * attempt again directly if the page came in. If we couldn't get
+ * the page here, then we will try again the next time the event is
+ * enabled/disabled.
+ */
+ clear_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler));
+
+ if (!ret) {
+ mmap_read_lock(mm->mm);
+ user_event_enabler_write(mm, enabler, true, &attempt);
+ mmap_read_unlock(mm->mm);
+ }
+out:
+ mutex_unlock(&event_mutex);
+
+ /* In all cases we no longer need the mm or fault */
+ user_event_mm_put(mm);
+ kmem_cache_free(fault_cache, fault);
+}
+
+static bool user_event_enabler_queue_fault(struct user_event_mm *mm,
+ struct user_event_enabler *enabler,
+ int attempt)
+{
+ struct user_event_enabler_fault *fault;
+
+ fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT | __GFP_NOWARN);
+
+ if (!fault)
+ return false;
+
+ INIT_WORK(&fault->work, user_event_enabler_fault_fixup);
+ fault->mm = user_event_mm_get(mm);
+ fault->enabler = enabler;
+ fault->attempt = attempt;
+
+ /* Don't try to queue in again while we have a pending fault */
+ set_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler));
+
+ if (!schedule_work(&fault->work)) {
+ /* Allow another attempt later */
+ clear_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler));
+
+ user_event_mm_put(mm);
+ kmem_cache_free(fault_cache, fault);
+
+ return false;
+ }
+
+ return true;
+}
+
+static int user_event_enabler_write(struct user_event_mm *mm,
+ struct user_event_enabler *enabler,
+ bool fixup_fault, int *attempt)
+{
+ unsigned long uaddr = enabler->addr;
+ unsigned long *ptr;
+ struct page *page;
+ void *kaddr;
+ int ret;
+
+ lockdep_assert_held(&event_mutex);
+ mmap_assert_locked(mm->mm);
+
+ *attempt += 1;
+
+ /* Ensure MM has tasks, cannot use after exit_mm() */
+ if (refcount_read(&mm->tasks) == 0)
+ return -ENOENT;
+
+ if (unlikely(test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)) ||
+ test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))))
+ return -EBUSY;
+
+ ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT,
+ &page, NULL, NULL);
+
+ if (unlikely(ret <= 0)) {
+ if (!fixup_fault)
+ return -EFAULT;
+
+ if (!user_event_enabler_queue_fault(mm, enabler, *attempt))
+ pr_warn("user_events: Unable to queue fault handler\n");
+
+ return -EFAULT;
+ }
+
+ kaddr = kmap_local_page(page);
+ ptr = kaddr + (uaddr & ~PAGE_MASK);
+
+ /* Update bit atomically, user tracers must be atomic as well */
+ if (enabler->event && enabler->event->status)
+ set_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr);
+ else
+ clear_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr);
+
+ kunmap_local(kaddr);
+ unpin_user_pages_dirty_lock(&page, 1, true);
+
+ return 0;
+}
+
+static bool user_event_enabler_exists(struct user_event_mm *mm,
+ unsigned long uaddr, unsigned char bit)
{
- int i = user->index;
+ struct user_event_enabler *enabler;
+ struct user_event_enabler *next;
- user->group->register_page_data[MAP_STATUS_BYTE(i)] |= MAP_STATUS_MASK(i);
+ list_for_each_entry_safe(enabler, next, &mm->enablers, link) {
+ if (enabler->addr == uaddr &&
+ (enabler->values & ENABLE_VAL_BIT_MASK) == bit)
+ return true;
+ }
+
+ return false;
}
-static __always_inline
-void user_event_register_clear(struct user_event *user)
+static void user_event_enabler_update(struct user_event *user)
{
- int i = user->index;
+ struct user_event_enabler *enabler;
+ struct user_event_mm *mm = user_event_mm_get_all(user);
+ struct user_event_mm *next;
+ int attempt;
+
+ while (mm) {
+ next = mm->next;
+ mmap_read_lock(mm->mm);
+ rcu_read_lock();
- user->group->register_page_data[MAP_STATUS_BYTE(i)] &= ~MAP_STATUS_MASK(i);
+ list_for_each_entry_rcu(enabler, &mm->enablers, link) {
+ if (enabler->event == user) {
+ attempt = 0;
+ user_event_enabler_write(mm, enabler, true, &attempt);
+ }
+ }
+
+ rcu_read_unlock();
+ mmap_read_unlock(mm->mm);
+ user_event_mm_put(mm);
+ mm = next;
+ }
+}
+
+static bool user_event_enabler_dup(struct user_event_enabler *orig,
+ struct user_event_mm *mm)
+{
+ struct user_event_enabler *enabler;
+
+ /* Skip pending frees */
+ if (unlikely(test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(orig))))
+ return true;
+
+ enabler = kzalloc(sizeof(*enabler), GFP_NOWAIT | __GFP_ACCOUNT);
+
+ if (!enabler)
+ return false;
+
+ enabler->event = orig->event;
+ enabler->addr = orig->addr;
+
+ /* Only dup part of value (ignore future flags, etc) */
+ enabler->values = orig->values & ENABLE_VAL_DUP_MASK;
+
+ refcount_inc(&enabler->event->refcnt);
+ list_add_rcu(&enabler->link, &mm->enablers);
+
+ return true;
+}
+
+static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm)
+{
+ refcount_inc(&mm->refcnt);
+
+ return mm;
+}
+
+static struct user_event_mm *user_event_mm_get_all(struct user_event *user)
+{
+ struct user_event_mm *found = NULL;
+ struct user_event_enabler *enabler;
+ struct user_event_mm *mm;
+
+ /*
+ * We do not want to block fork/exec while enablements are being
+ * updated, so we use RCU to walk the current tasks that have used
+ * user_events ABI for 1 or more events. Each enabler found in each
+ * task that matches the event being updated has a write to reflect
+ * the kernel state back into the process. Waits/faults must not occur
+ * during this. So we scan the list under RCU for all the mm that have
+ * the event within it. This is needed because mm_read_lock() can wait.
+ * Each user mm returned has a ref inc to handle remove RCU races.
+ */
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(mm, &user_event_mms, link)
+ list_for_each_entry_rcu(enabler, &mm->enablers, link)
+ if (enabler->event == user) {
+ mm->next = found;
+ found = user_event_mm_get(mm);
+ break;
+ }
+
+ rcu_read_unlock();
+
+ return found;
+}
+
+static struct user_event_mm *user_event_mm_create(struct task_struct *t)
+{
+ struct user_event_mm *user_mm;
+ unsigned long flags;
+
+ user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL_ACCOUNT);
+
+ if (!user_mm)
+ return NULL;
+
+ user_mm->mm = t->mm;
+ INIT_LIST_HEAD(&user_mm->enablers);
+ refcount_set(&user_mm->refcnt, 1);
+ refcount_set(&user_mm->tasks, 1);
+
+ spin_lock_irqsave(&user_event_mms_lock, flags);
+ list_add_rcu(&user_mm->link, &user_event_mms);
+ spin_unlock_irqrestore(&user_event_mms_lock, flags);
+
+ t->user_event_mm = user_mm;
+
+ /*
+ * The lifetime of the memory descriptor can slightly outlast
+ * the task lifetime if a ref to the user_event_mm is taken
+ * between list_del_rcu() and call_rcu(). Therefore we need
+ * to take a reference to it to ensure it can live this long
+ * under this corner case. This can also occur in clones that
+ * outlast the parent.
+ */
+ mmgrab(user_mm->mm);
+
+ return user_mm;
+}
+
+static struct user_event_mm *current_user_event_mm(void)
+{
+ struct user_event_mm *user_mm = current->user_event_mm;
+
+ if (user_mm)
+ goto inc;
+
+ user_mm = user_event_mm_create(current);
+
+ if (!user_mm)
+ goto error;
+inc:
+ refcount_inc(&user_mm->refcnt);
+error:
+ return user_mm;
+}
+
+static void user_event_mm_destroy(struct user_event_mm *mm)
+{
+ struct user_event_enabler *enabler, *next;
+
+ list_for_each_entry_safe(enabler, next, &mm->enablers, link)
+ user_event_enabler_destroy(enabler);
+
+ mmdrop(mm->mm);
+ kfree(mm);
+}
+
+static void user_event_mm_put(struct user_event_mm *mm)
+{
+ if (mm && refcount_dec_and_test(&mm->refcnt))
+ user_event_mm_destroy(mm);
+}
+
+static void delayed_user_event_mm_put(struct work_struct *work)
+{
+ struct user_event_mm *mm;
+
+ mm = container_of(to_rcu_work(work), struct user_event_mm, put_rwork);
+ user_event_mm_put(mm);
+}
+
+void user_event_mm_remove(struct task_struct *t)
+{
+ struct user_event_mm *mm;
+ unsigned long flags;
+
+ might_sleep();
+
+ mm = t->user_event_mm;
+ t->user_event_mm = NULL;
+
+ /* Clone will increment the tasks, only remove if last clone */
+ if (!refcount_dec_and_test(&mm->tasks))
+ return;
+
+ /* Remove the mm from the list, so it can no longer be enabled */
+ spin_lock_irqsave(&user_event_mms_lock, flags);
+ list_del_rcu(&mm->link);
+ spin_unlock_irqrestore(&user_event_mms_lock, flags);
+
+ /*
+ * We need to wait for currently occurring writes to stop within
+ * the mm. This is required since exit_mm() snaps the current rss
+ * stats and clears them. On the final mmdrop(), check_mm() will
+ * report a bug if these increment.
+ *
+ * All writes/pins are done under mmap_read lock, take the write
+ * lock to ensure in-progress faults have completed. Faults that
+ * are pending but yet to run will check the task count and skip
+ * the fault since the mm is going away.
+ */
+ mmap_write_lock(mm->mm);
+ mmap_write_unlock(mm->mm);
+
+ /*
+ * Put for mm must be done after RCU delay to handle new refs in
+ * between the list_del_rcu() and now. This ensures any get refs
+ * during rcu_read_lock() are accounted for during list removal.
+ *
+ * CPU A | CPU B
+ * ---------------------------------------------------------------
+ * user_event_mm_remove() | rcu_read_lock();
+ * list_del_rcu() | list_for_each_entry_rcu();
+ * call_rcu() | refcount_inc();
+ * . | rcu_read_unlock();
+ * schedule_work() | .
+ * user_event_mm_put() | .
+ *
+ * mmdrop() cannot be called in the softirq context of call_rcu()
+ * so we use a work queue after call_rcu() to run within.
+ */
+ INIT_RCU_WORK(&mm->put_rwork, delayed_user_event_mm_put);
+ queue_rcu_work(system_wq, &mm->put_rwork);
+}
+
+void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm)
+{
+ struct user_event_mm *mm = user_event_mm_create(t);
+ struct user_event_enabler *enabler;
+
+ if (!mm)
+ return;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(enabler, &old_mm->enablers, link)
+ if (!user_event_enabler_dup(enabler, mm))
+ goto error;
+
+ rcu_read_unlock();
+
+ return;
+error:
+ rcu_read_unlock();
+ user_event_mm_remove(t);
+}
+
+static bool current_user_event_enabler_exists(unsigned long uaddr,
+ unsigned char bit)
+{
+ struct user_event_mm *user_mm = current_user_event_mm();
+ bool exists;
+
+ if (!user_mm)
+ return false;
+
+ exists = user_event_enabler_exists(user_mm, uaddr, bit);
+
+ user_event_mm_put(user_mm);
+
+ return exists;
+}
+
+static struct user_event_enabler
+*user_event_enabler_create(struct user_reg *reg, struct user_event *user,
+ int *write_result)
+{
+ struct user_event_enabler *enabler;
+ struct user_event_mm *user_mm;
+ unsigned long uaddr = (unsigned long)reg->enable_addr;
+ int attempt = 0;
+
+ user_mm = current_user_event_mm();
+
+ if (!user_mm)
+ return NULL;
+
+ enabler = kzalloc(sizeof(*enabler), GFP_KERNEL_ACCOUNT);
+
+ if (!enabler)
+ goto out;
+
+ enabler->event = user;
+ enabler->addr = uaddr;
+ enabler->values = reg->enable_bit;
+retry:
+ /* Prevents state changes from racing with new enablers */
+ mutex_lock(&event_mutex);
+
+ /* Attempt to reflect the current state within the process */
+ mmap_read_lock(user_mm->mm);
+ *write_result = user_event_enabler_write(user_mm, enabler, false,
+ &attempt);
+ mmap_read_unlock(user_mm->mm);
+
+ /*
+ * If the write works, then we will track the enabler. A ref to the
+ * underlying user_event is held by the enabler to prevent it going
+ * away while the enabler is still in use by a process. The ref is
+ * removed when the enabler is destroyed. This means a event cannot
+ * be forcefully deleted from the system until all tasks using it
+ * exit or run exec(), which includes forks and clones.
+ */
+ if (!*write_result) {
+ refcount_inc(&enabler->event->refcnt);
+ list_add_rcu(&enabler->link, &user_mm->enablers);
+ }
+
+ mutex_unlock(&event_mutex);
+
+ if (*write_result) {
+ /* Attempt to fault-in and retry if it worked */
+ if (!user_event_mm_fault_in(user_mm, uaddr, attempt))
+ goto retry;
+
+ kfree(enabler);
+ enabler = NULL;
+ }
+out:
+ user_event_mm_put(user_mm);
+
+ return enabler;
}
static __always_inline __must_check
@@ -449,7 +929,7 @@ static int user_event_add_field(struct user_event *user, const char *type,
struct ftrace_event_field *field;
int validator_flags = 0;
- field = kmalloc(sizeof(*field), GFP_KERNEL);
+ field = kmalloc(sizeof(*field), GFP_KERNEL_ACCOUNT);
if (!field)
return -ENOMEM;
@@ -468,7 +948,7 @@ add_validator:
if (strstr(type, "char") != NULL)
validator_flags |= VALIDATOR_ENSURE_NULL;
- validator = kmalloc(sizeof(*validator), GFP_KERNEL);
+ validator = kmalloc(sizeof(*validator), GFP_KERNEL_ACCOUNT);
if (!validator) {
kfree(field);
@@ -489,6 +969,9 @@ add_field:
field->is_signed = is_signed;
field->filter_type = filter_type;
+ if (filter_type == FILTER_OTHER)
+ field->filter_type = filter_assign_type(type);
+
list_add(&field->link, &user->fields);
/*
@@ -754,7 +1237,7 @@ static int user_event_create_print_fmt(struct user_event *user)
len = user_event_set_print_fmt(user, NULL, 0);
- print_fmt = kmalloc(len, GFP_KERNEL);
+ print_fmt = kmalloc(len, GFP_KERNEL_ACCOUNT);
if (!print_fmt)
return -ENOMEM;
@@ -770,11 +1253,7 @@ static enum print_line_t user_event_print_trace(struct trace_iterator *iter,
int flags,
struct trace_event *event)
{
- /* Unsafe to try to decode user provided print_fmt, use hex */
- trace_print_hex_dump_seq(&iter->seq, "", DUMP_PREFIX_OFFSET, 16,
- 1, iter->ent, iter->ent_size, true);
-
- return trace_handle_return(&iter->seq);
+ return print_event_fields(iter, event);
}
static struct trace_event_functions user_event_funcs = {
@@ -820,6 +1299,8 @@ static int destroy_user_event(struct user_event *user)
{
int ret = 0;
+ lockdep_assert_held(&event_mutex);
+
/* Must destroy fields before call removal */
user_event_destroy_fields(user);
@@ -829,9 +1310,6 @@ static int destroy_user_event(struct user_event *user)
return ret;
dyn_event_remove(&user->devent);
-
- user_event_register_clear(user);
- clear_bit(user->index, user->group->page_bitmap);
hash_del(&user->node);
user_event_destroy_validators(user);
@@ -839,6 +1317,11 @@ static int destroy_user_event(struct user_event *user)
kfree(EVENT_NAME(user));
kfree(user);
+ if (current_user_events > 0)
+ current_user_events--;
+ else
+ pr_alert("BUG: Bad current_user_events\n");
+
return ret;
}
@@ -977,9 +1460,9 @@ discard:
#endif
/*
- * Update the register page that is shared between user processes.
+ * Update the enabled bit among all user processes.
*/
-static void update_reg_page_for(struct user_event *user)
+static void update_enable_bit_for(struct user_event *user)
{
struct tracepoint *tp = &user->tracepoint;
char status = 0;
@@ -1010,12 +1493,9 @@ static void update_reg_page_for(struct user_event *user)
rcu_read_unlock_sched();
}
- if (status)
- user_event_register_set(user);
- else
- user_event_register_clear(user);
-
user->status = status;
+
+ user_event_enabler_update(user);
}
/*
@@ -1072,10 +1552,10 @@ static int user_event_reg(struct trace_event_call *call,
return ret;
inc:
refcount_inc(&user->refcnt);
- update_reg_page_for(user);
+ update_enable_bit_for(user);
return 0;
dec:
- update_reg_page_for(user);
+ update_enable_bit_for(user);
refcount_dec(&user->refcnt);
return 0;
}
@@ -1093,7 +1573,7 @@ static int user_event_create(const char *raw_command)
raw_command += USER_EVENTS_PREFIX_LEN;
raw_command = skip_spaces(raw_command);
- name = kstrdup(raw_command, GFP_KERNEL);
+ name = kstrdup(raw_command, GFP_KERNEL_ACCOUNT);
if (!name)
return -ENOMEM;
@@ -1271,7 +1751,6 @@ static int user_event_parse(struct user_event_group *group, char *name,
struct user_event **newuser)
{
int ret;
- int index;
u32 key;
struct user_event *user;
@@ -1290,12 +1769,7 @@ static int user_event_parse(struct user_event_group *group, char *name,
return 0;
}
- index = find_first_zero_bit(group->page_bitmap, MAX_EVENTS);
-
- if (index == MAX_EVENTS)
- return -EMFILE;
-
- user = kzalloc(sizeof(*user), GFP_KERNEL);
+ user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT);
if (!user)
return -ENOMEM;
@@ -1335,20 +1809,23 @@ static int user_event_parse(struct user_event_group *group, char *name,
mutex_lock(&event_mutex);
+ if (current_user_events >= max_user_events) {
+ ret = -EMFILE;
+ goto put_user_lock;
+ }
+
ret = user_event_trace_register(user);
if (ret)
goto put_user_lock;
- user->index = index;
-
/* Ensure we track self ref and caller ref (2) */
refcount_set(&user->refcnt, 2);
dyn_event_init(&user->devent, &user_event_dops);
dyn_event_add(&user->devent, &user->call);
- set_bit(user->index, group->page_bitmap);
hash_add(group->register_table, &user->node, key);
+ current_user_events++;
mutex_unlock(&event_mutex);
@@ -1398,6 +1875,9 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i)
if (unlikely(copy_from_iter(&idx, sizeof(idx), i) != sizeof(idx)))
return -EFAULT;
+ if (idx < 0)
+ return -EINVAL;
+
rcu_read_lock_sched();
refs = rcu_dereference_sched(info->refs);
@@ -1468,7 +1948,7 @@ static int user_events_open(struct inode *node, struct file *file)
if (!group)
return -ENOENT;
- info = kzalloc(sizeof(*info), GFP_KERNEL);
+ info = kzalloc(sizeof(*info), GFP_KERNEL_ACCOUNT);
if (!info)
return -ENOMEM;
@@ -1521,7 +2001,7 @@ static int user_events_ref_add(struct user_event_file_info *info,
size = struct_size(refs, events, count + 1);
- new_refs = kzalloc(size, GFP_KERNEL);
+ new_refs = kzalloc(size, GFP_KERNEL_ACCOUNT);
if (!new_refs)
return -ENOMEM;
@@ -1564,6 +2044,37 @@ static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg)
if (ret)
return ret;
+ /* Ensure no flags, since we don't support any yet */
+ if (kreg->flags != 0)
+ return -EINVAL;
+
+ /* Ensure supported size */
+ switch (kreg->enable_size) {
+ case 4:
+ /* 32-bit */
+ break;
+#if BITS_PER_LONG >= 64
+ case 8:
+ /* 64-bit */
+ break;
+#endif
+ default:
+ return -EINVAL;
+ }
+
+ /* Ensure natural alignment */
+ if (kreg->enable_addr % kreg->enable_size)
+ return -EINVAL;
+
+ /* Ensure bit range for size */
+ if (kreg->enable_bit > (kreg->enable_size * BITS_PER_BYTE) - 1)
+ return -EINVAL;
+
+ /* Ensure accessible */
+ if (!access_ok((const void __user *)(uintptr_t)kreg->enable_addr,
+ kreg->enable_size))
+ return -EFAULT;
+
kreg->size = size;
return 0;
@@ -1578,14 +2089,26 @@ static long user_events_ioctl_reg(struct user_event_file_info *info,
struct user_reg __user *ureg = (struct user_reg __user *)uarg;
struct user_reg reg;
struct user_event *user;
+ struct user_event_enabler *enabler;
char *name;
long ret;
+ int write_result;
ret = user_reg_get(ureg, &reg);
if (ret)
return ret;
+ /*
+ * Prevent users from using the same address and bit multiple times
+ * within the same mm address space. This can cause unexpected behavior
+ * for user processes that is far easier to debug if this is explictly
+ * an error upon registering.
+ */
+ if (current_user_event_enabler_exists((unsigned long)reg.enable_addr,
+ reg.enable_bit))
+ return -EADDRINUSE;
+
name = strndup_user((const char __user *)(uintptr_t)reg.name_args,
MAX_EVENT_DESC);
@@ -1610,8 +2133,28 @@ static long user_events_ioctl_reg(struct user_event_file_info *info,
if (ret < 0)
return ret;
+ /*
+ * user_events_ref_add succeeded:
+ * At this point we have a user_event, it's lifetime is bound by the
+ * reference count, not this file. If anything fails, the user_event
+ * still has a reference until the file is released. During release
+ * any remaining references (from user_events_ref_add) are decremented.
+ *
+ * Attempt to create an enabler, which too has a lifetime tied in the
+ * same way for the event. Once the task that caused the enabler to be
+ * created exits or issues exec() then the enablers it has created
+ * will be destroyed and the ref to the event will be decremented.
+ */
+ enabler = user_event_enabler_create(&reg, user, &write_result);
+
+ if (!enabler)
+ return -ENOMEM;
+
+ /* Write failed/faulted, give error back to caller */
+ if (write_result)
+ return write_result;
+
put_user((u32)ret, &ureg->write_index);
- put_user(user->index, &ureg->status_bit);
return 0;
}
@@ -1641,6 +2184,114 @@ static long user_events_ioctl_del(struct user_event_file_info *info,
return ret;
}
+static long user_unreg_get(struct user_unreg __user *ureg,
+ struct user_unreg *kreg)
+{
+ u32 size;
+ long ret;
+
+ ret = get_user(size, &ureg->size);
+
+ if (ret)
+ return ret;
+
+ if (size > PAGE_SIZE)
+ return -E2BIG;
+
+ if (size < offsetofend(struct user_unreg, disable_addr))
+ return -EINVAL;
+
+ ret = copy_struct_from_user(kreg, sizeof(*kreg), ureg, size);
+
+ /* Ensure no reserved values, since we don't support any yet */
+ if (kreg->__reserved || kreg->__reserved2)
+ return -EINVAL;
+
+ return ret;
+}
+
+static int user_event_mm_clear_bit(struct user_event_mm *user_mm,
+ unsigned long uaddr, unsigned char bit)
+{
+ struct user_event_enabler enabler;
+ int result;
+ int attempt = 0;
+
+ memset(&enabler, 0, sizeof(enabler));
+ enabler.addr = uaddr;
+ enabler.values = bit;
+retry:
+ /* Prevents state changes from racing with new enablers */
+ mutex_lock(&event_mutex);
+
+ /* Force the bit to be cleared, since no event is attached */
+ mmap_read_lock(user_mm->mm);
+ result = user_event_enabler_write(user_mm, &enabler, false, &attempt);
+ mmap_read_unlock(user_mm->mm);
+
+ mutex_unlock(&event_mutex);
+
+ if (result) {
+ /* Attempt to fault-in and retry if it worked */
+ if (!user_event_mm_fault_in(user_mm, uaddr, attempt))
+ goto retry;
+ }
+
+ return result;
+}
+
+/*
+ * Unregisters an enablement address/bit within a task/user mm.
+ */
+static long user_events_ioctl_unreg(unsigned long uarg)
+{
+ struct user_unreg __user *ureg = (struct user_unreg __user *)uarg;
+ struct user_event_mm *mm = current->user_event_mm;
+ struct user_event_enabler *enabler, *next;
+ struct user_unreg reg;
+ long ret;
+
+ ret = user_unreg_get(ureg, &reg);
+
+ if (ret)
+ return ret;
+
+ if (!mm)
+ return -ENOENT;
+
+ ret = -ENOENT;
+
+ /*
+ * Flags freeing and faulting are used to indicate if the enabler is in
+ * use at all. When faulting is set a page-fault is occurring asyncly.
+ * During async fault if freeing is set, the enabler will be destroyed.
+ * If no async fault is happening, we can destroy it now since we hold
+ * the event_mutex during these checks.
+ */
+ mutex_lock(&event_mutex);
+
+ list_for_each_entry_safe(enabler, next, &mm->enablers, link)
+ if (enabler->addr == reg.disable_addr &&
+ (enabler->values & ENABLE_VAL_BIT_MASK) == reg.disable_bit) {
+ set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler));
+
+ if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)))
+ user_event_enabler_destroy(enabler);
+
+ /* Removed at least one */
+ ret = 0;
+ }
+
+ mutex_unlock(&event_mutex);
+
+ /* Ensure bit is now cleared for user, regardless of event status */
+ if (!ret)
+ ret = user_event_mm_clear_bit(mm, reg.disable_addr,
+ reg.disable_bit);
+
+ return ret;
+}
+
/*
* Handles the ioctl from user mode to register or alter operations.
*/
@@ -1663,6 +2314,12 @@ static long user_events_ioctl(struct file *file, unsigned int cmd,
ret = user_events_ioctl_del(info, uarg);
mutex_unlock(&group->reg_mutex);
break;
+
+ case DIAG_IOCSUNREG:
+ mutex_lock(&group->reg_mutex);
+ ret = user_events_ioctl_unreg(uarg);
+ mutex_unlock(&group->reg_mutex);
+ break;
}
return ret;
@@ -1718,45 +2375,13 @@ out:
}
static const struct file_operations user_data_fops = {
- .open = user_events_open,
- .write = user_events_write,
- .write_iter = user_events_write_iter,
+ .open = user_events_open,
+ .write = user_events_write,
+ .write_iter = user_events_write_iter,
.unlocked_ioctl = user_events_ioctl,
- .release = user_events_release,
+ .release = user_events_release,
};
-static struct user_event_group *user_status_group(struct file *file)
-{
- struct seq_file *m = file->private_data;
-
- if (!m)
- return NULL;
-
- return m->private;
-}
-
-/*
- * Maps the shared page into the user process for checking if event is enabled.
- */
-static int user_status_mmap(struct file *file, struct vm_area_struct *vma)
-{
- char *pages;
- struct user_event_group *group = user_status_group(file);
- unsigned long size = vma->vm_end - vma->vm_start;
-
- if (size != MAX_BYTES)
- return -EINVAL;
-
- if (!group)
- return -EINVAL;
-
- pages = group->register_page_data;
-
- return remap_pfn_range(vma, vma->vm_start,
- virt_to_phys(pages) >> PAGE_SHIFT,
- size, vm_get_page_prot(VM_READ));
-}
-
static void *user_seq_start(struct seq_file *m, loff_t *pos)
{
if (*pos)
@@ -1780,7 +2405,7 @@ static int user_seq_show(struct seq_file *m, void *p)
struct user_event_group *group = m->private;
struct user_event *user;
char status;
- int i, active = 0, busy = 0, flags;
+ int i, active = 0, busy = 0;
if (!group)
return -EINVAL;
@@ -1789,11 +2414,10 @@ static int user_seq_show(struct seq_file *m, void *p)
hash_for_each(group->register_table, i, user, node) {
status = user->status;
- flags = user->flags;
- seq_printf(m, "%d:%s", user->index, EVENT_NAME(user));
+ seq_printf(m, "%s", EVENT_NAME(user));
- if (flags != 0 || status != 0)
+ if (status != 0)
seq_puts(m, " #");
if (status != 0) {
@@ -1816,16 +2440,15 @@ static int user_seq_show(struct seq_file *m, void *p)
seq_puts(m, "\n");
seq_printf(m, "Active: %d\n", active);
seq_printf(m, "Busy: %d\n", busy);
- seq_printf(m, "Max: %ld\n", MAX_EVENTS);
return 0;
}
static const struct seq_operations user_seq_ops = {
- .start = user_seq_start,
- .next = user_seq_next,
- .stop = user_seq_stop,
- .show = user_seq_show,
+ .start = user_seq_start,
+ .next = user_seq_next,
+ .stop = user_seq_stop,
+ .show = user_seq_show,
};
static int user_status_open(struct inode *node, struct file *file)
@@ -1851,11 +2474,10 @@ static int user_status_open(struct inode *node, struct file *file)
}
static const struct file_operations user_status_fops = {
- .open = user_status_open,
- .mmap = user_status_mmap,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
+ .open = user_status_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
};
/*
@@ -1873,8 +2495,7 @@ static int create_user_tracefs(void)
goto err;
}
- /* mmap with MAP_SHARED requires writable fd */
- emmap = tracefs_create_file("user_events_status", TRACE_MODE_WRITE,
+ emmap = tracefs_create_file("user_events_status", TRACE_MODE_READ,
NULL, NULL, &user_status_fops);
if (!emmap) {
@@ -1888,20 +2509,53 @@ err:
return -ENODEV;
}
+static int set_max_user_events_sysctl(struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret;
+
+ mutex_lock(&event_mutex);
+
+ ret = proc_douintvec(table, write, buffer, lenp, ppos);
+
+ mutex_unlock(&event_mutex);
+
+ return ret;
+}
+
+static struct ctl_table user_event_sysctls[] = {
+ {
+ .procname = "user_events_max",
+ .data = &max_user_events,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = set_max_user_events_sysctl,
+ },
+ {}
+};
+
static int __init trace_events_user_init(void)
{
int ret;
+ fault_cache = KMEM_CACHE(user_event_enabler_fault, 0);
+
+ if (!fault_cache)
+ return -ENOMEM;
+
init_group = user_event_group_create(&init_user_ns);
- if (!init_group)
+ if (!init_group) {
+ kmem_cache_destroy(fault_cache);
return -ENOMEM;
+ }
ret = create_user_tracefs();
if (ret) {
pr_warn("user_events could not register with tracefs\n");
user_event_group_destroy(init_group);
+ kmem_cache_destroy(fault_cache);
init_group = NULL;
return ret;
}
@@ -1909,6 +2563,8 @@ static int __init trace_events_user_init(void)
if (dyn_event_register(&user_event_dops))
pr_warn("user_events could not register with dyn_events\n");
+ register_sysctl_init("kernel", user_event_sysctls);
+
return 0;
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index bd475a00f96d..15f05faaae44 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -221,8 +221,11 @@ trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len,
const char *ret = trace_seq_buffer_ptr(p);
const char *fmt = concatenate ? "%*phN" : "%*ph";
- for (i = 0; i < buf_len; i += 16)
+ for (i = 0; i < buf_len; i += 16) {
+ if (!concatenate && i != 0)
+ trace_seq_putc(p, ' ');
trace_seq_printf(p, fmt, min(buf_len - i, 16), &buf[i]);
+ }
trace_seq_putc(p, 0);
return ret;
@@ -808,6 +811,176 @@ EXPORT_SYMBOL_GPL(unregister_trace_event);
* Standard events
*/
+static void print_array(struct trace_iterator *iter, void *pos,
+ struct ftrace_event_field *field)
+{
+ int offset;
+ int len;
+ int i;
+
+ offset = *(int *)pos & 0xffff;
+ len = *(int *)pos >> 16;
+
+ if (field)
+ offset += field->offset + sizeof(int);
+
+ if (offset + len > iter->ent_size) {
+ trace_seq_puts(&iter->seq, "<OVERFLOW>");
+ return;
+ }
+
+ pos = (void *)iter->ent + offset;
+
+ for (i = 0; i < len; i++, pos++) {
+ if (i)
+ trace_seq_putc(&iter->seq, ',');
+ trace_seq_printf(&iter->seq, "%02x", *(unsigned char *)pos);
+ }
+}
+
+static void print_fields(struct trace_iterator *iter, struct trace_event_call *call,
+ struct list_head *head)
+{
+ struct ftrace_event_field *field;
+ int offset;
+ int len;
+ int ret;
+ void *pos;
+
+ list_for_each_entry(field, head, link) {
+ trace_seq_printf(&iter->seq, " %s=", field->name);
+ if (field->offset + field->size > iter->ent_size) {
+ trace_seq_puts(&iter->seq, "<OVERFLOW>");
+ continue;
+ }
+ pos = (void *)iter->ent + field->offset;
+
+ switch (field->filter_type) {
+ case FILTER_COMM:
+ case FILTER_STATIC_STRING:
+ trace_seq_printf(&iter->seq, "%.*s", field->size, (char *)pos);
+ break;
+ case FILTER_RDYN_STRING:
+ case FILTER_DYN_STRING:
+ offset = *(int *)pos & 0xffff;
+ len = *(int *)pos >> 16;
+
+ if (field->filter_type == FILTER_RDYN_STRING)
+ offset += field->offset + sizeof(int);
+
+ if (offset + len > iter->ent_size) {
+ trace_seq_puts(&iter->seq, "<OVERFLOW>");
+ break;
+ }
+ pos = (void *)iter->ent + offset;
+ trace_seq_printf(&iter->seq, "%.*s", len, (char *)pos);
+ break;
+ case FILTER_PTR_STRING:
+ if (!iter->fmt_size)
+ trace_iter_expand_format(iter);
+ pos = *(void **)pos;
+ ret = strncpy_from_kernel_nofault(iter->fmt, pos,
+ iter->fmt_size);
+ if (ret < 0)
+ trace_seq_printf(&iter->seq, "(0x%px)", pos);
+ else
+ trace_seq_printf(&iter->seq, "(0x%px:%s)",
+ pos, iter->fmt);
+ break;
+ case FILTER_TRACE_FN:
+ pos = *(void **)pos;
+ trace_seq_printf(&iter->seq, "%pS", pos);
+ break;
+ case FILTER_CPU:
+ case FILTER_OTHER:
+ switch (field->size) {
+ case 1:
+ if (isprint(*(char *)pos)) {
+ trace_seq_printf(&iter->seq, "'%c'",
+ *(unsigned char *)pos);
+ }
+ trace_seq_printf(&iter->seq, "(%d)",
+ *(unsigned char *)pos);
+ break;
+ case 2:
+ trace_seq_printf(&iter->seq, "0x%x (%d)",
+ *(unsigned short *)pos,
+ *(unsigned short *)pos);
+ break;
+ case 4:
+ /* dynamic array info is 4 bytes */
+ if (strstr(field->type, "__data_loc")) {
+ print_array(iter, pos, NULL);
+ break;
+ }
+
+ if (strstr(field->type, "__rel_loc")) {
+ print_array(iter, pos, field);
+ break;
+ }
+
+ trace_seq_printf(&iter->seq, "0x%x (%d)",
+ *(unsigned int *)pos,
+ *(unsigned int *)pos);
+ break;
+ case 8:
+ trace_seq_printf(&iter->seq, "0x%llx (%lld)",
+ *(unsigned long long *)pos,
+ *(unsigned long long *)pos);
+ break;
+ default:
+ trace_seq_puts(&iter->seq, "<INVALID-SIZE>");
+ break;
+ }
+ break;
+ default:
+ trace_seq_puts(&iter->seq, "<INVALID-TYPE>");
+ }
+ }
+ trace_seq_putc(&iter->seq, '\n');
+}
+
+enum print_line_t print_event_fields(struct trace_iterator *iter,
+ struct trace_event *event)
+{
+ struct trace_event_call *call;
+ struct list_head *head;
+
+ /* ftrace defined events have separate call structures */
+ if (event->type <= __TRACE_LAST_TYPE) {
+ bool found = false;
+
+ down_read(&trace_event_sem);
+ list_for_each_entry(call, &ftrace_events, list) {
+ if (call->event.type == event->type) {
+ found = true;
+ break;
+ }
+ /* No need to search all events */
+ if (call->event.type > __TRACE_LAST_TYPE)
+ break;
+ }
+ up_read(&trace_event_sem);
+ if (!found) {
+ trace_seq_printf(&iter->seq, "UNKNOWN TYPE %d\n", event->type);
+ goto out;
+ }
+ } else {
+ call = container_of(event, struct trace_event_call, event);
+ }
+ head = trace_get_fields(call);
+
+ trace_seq_printf(&iter->seq, "%s:", trace_event_name(call));
+
+ if (head && !list_empty(head))
+ print_fields(iter, call, head);
+ else
+ trace_seq_puts(&iter->seq, "No fields found\n");
+
+ out:
+ return trace_handle_return(&iter->seq);
+}
+
enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 4c954636caf0..dca40f1f1da4 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -19,6 +19,8 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
extern void trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset);
extern int trace_print_context(struct trace_iterator *iter);
extern int trace_print_lat_context(struct trace_iterator *iter);
+extern enum print_line_t print_event_fields(struct trace_iterator *iter,
+ struct trace_event *event);
extern void trace_event_read_lock(void);
extern void trace_event_read_unlock(void);
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-02-11 02:30:46 +0000