aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-02-23 10:20:49 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2023-02-23 10:20:49 -0800
commitb72b5fecc1b8a2e595bd03d7d257c88ea3f9fd45 (patch)
treefa30b384382d496f9c38718f3fb35611e4b9700b /kernel
parentMerge tag 'trace-v6.2-rc7-3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace (diff)
parenttracing: Remove unnecessary NULL assignment (diff)
downloadwireguard-linux-b72b5fecc1b8a2e595bd03d7d257c88ea3f9fd45.tar.xz
wireguard-linux-b72b5fecc1b8a2e595bd03d7d257c88ea3f9fd45.zip
Merge tag 'trace-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace
Pull tracing updates from Steven Rostedt: - Add function names as a way to filter function addresses - Add sample module to test ftrace ops and dynamic trampolines - Allow stack traces to be passed from beginning event to end event for synthetic events. This will allow seeing the stack trace of when a task is scheduled out and recorded when it gets scheduled back in. - Add trace event helper __get_buf() to use as a temporary buffer when printing out trace event output. - Add kernel command line to create trace instances on boot up. - Add enabling of events to instances created at boot up. - Add trace_array_puts() to write into instances. - Allow boot instances to take a snapshot at the end of boot up. - Allow live patch modules to include trace events - Minor fixes and clean ups * tag 'trace-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (31 commits) tracing: Remove unnecessary NULL assignment tracepoint: Allow livepatch module add trace event tracing: Always use canonical ftrace path tracing/histogram: Fix stacktrace histogram Documententation tracing/histogram: Fix stacktrace key tracing/histogram: Fix a few problems with stacktrace variable printing tracing: Add BUILD_BUG() to make sure stacktrace fits in strings tracing/histogram: Don't use strlen to find length of stacktrace variables tracing: Allow boot instances to have snapshot buffers tracing: Add trace_array_puts() to write into instance tracing: Add enabling of events to boot instances tracing: Add creation of instances at boot command line tracing: Fix trace_event_raw_event_synth() if else statement samples: ftrace: Make some global variables static ftrace: sample: avoid open-coded 64-bit division samples: ftrace: Include the nospec-branch.h only for x86 tracing: Acquire buffer from temparary trace sequence tracing/histogram: Wrap remaining shell snippets in code blocks tracing/osnoise: No need for schedule_hrtimeout range bpf/tracing: Use stage6 of tracing to not duplicate macros ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/trace/Kconfig20
-rw-r--r--kernel/trace/kprobe_event_gen_test.c2
-rw-r--r--kernel/trace/ring_buffer.c9
-rw-r--r--kernel/trace/synth_event_gen_test.c2
-rw-r--r--kernel/trace/trace.c164
-rw-r--r--kernel/trace/trace.h6
-rw-r--r--kernel/trace/trace_events.c13
-rw-r--r--kernel/trace/trace_events_filter.c93
-rw-r--r--kernel/trace/trace_events_hist.c126
-rw-r--r--kernel/trace/trace_events_synth.c90
-rw-r--r--kernel/trace/trace_osnoise.c2
-rw-r--r--kernel/trace/trace_seq.c23
-rw-r--r--kernel/trace/trace_synth.h1
-rw-r--r--kernel/tracepoint.c4
14 files changed, 483 insertions, 72 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index caf32389faf3..a856d4a34c67 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -242,7 +242,7 @@ config DYNAMIC_FTRACE
enabled, and the functions not enabled will not affect
performance of the system.
- See the files in /sys/kernel/debug/tracing:
+ See the files in /sys/kernel/tracing:
available_filter_functions
set_ftrace_filter
set_ftrace_notrace
@@ -306,7 +306,7 @@ config STACK_TRACER
select KALLSYMS
help
This special tracer records the maximum stack footprint of the
- kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
+ kernel and displays it in /sys/kernel/tracing/stack_trace.
This tracer works by hooking into every function call that the
kernel executes, and keeping a maximum stack depth value and
@@ -346,7 +346,7 @@ config IRQSOFF_TRACER
disabled by default and can be runtime (re-)started
via:
- echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
+ echo 0 > /sys/kernel/tracing/tracing_max_latency
(Note that kernel size and overhead increase with this option
enabled. This option and the preempt-off timing option can be
@@ -370,7 +370,7 @@ config PREEMPT_TRACER
disabled by default and can be runtime (re-)started
via:
- echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
+ echo 0 > /sys/kernel/tracing/tracing_max_latency
(Note that kernel size and overhead increase with this option
enabled. This option and the irqs-off timing option can be
@@ -522,7 +522,7 @@ config TRACER_SNAPSHOT
Allow tracing users to take snapshot of the current buffer using the
ftrace interface, e.g.:
- echo 1 > /sys/kernel/debug/tracing/snapshot
+ echo 1 > /sys/kernel/tracing/snapshot
cat snapshot
config TRACER_SNAPSHOT_PER_CPU_SWAP
@@ -534,7 +534,7 @@ config TRACER_SNAPSHOT_PER_CPU_SWAP
full swap (all buffers). If this is set, then the following is
allowed:
- echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
+ echo 1 > /sys/kernel/tracing/per_cpu/cpu2/snapshot
After which, only the tracing buffer for CPU 2 was swapped with
the main tracing buffer, and the other CPU buffers remain the same.
@@ -581,7 +581,7 @@ config PROFILE_ANNOTATED_BRANCHES
This tracer profiles all likely and unlikely macros
in the kernel. It will display the results in:
- /sys/kernel/debug/tracing/trace_stat/branch_annotated
+ /sys/kernel/tracing/trace_stat/branch_annotated
Note: this will add a significant overhead; only turn this
on if you need to profile the system's use of these macros.
@@ -594,7 +594,7 @@ config PROFILE_ALL_BRANCHES
taken in the kernel is recorded whether it hit or miss.
The results will be displayed in:
- /sys/kernel/debug/tracing/trace_stat/branch_all
+ /sys/kernel/tracing/trace_stat/branch_all
This option also enables the likely/unlikely profiler.
@@ -645,8 +645,8 @@ config BLK_DEV_IO_TRACE
Tracing also is possible using the ftrace interface, e.g.:
echo 1 > /sys/block/sda/sda1/trace/enable
- echo blk > /sys/kernel/debug/tracing/current_tracer
- cat /sys/kernel/debug/tracing/trace_pipe
+ echo blk > /sys/kernel/tracing/current_tracer
+ cat /sys/kernel/tracing/trace_pipe
If unsure, say N.
diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c
index c736487fc0e4..4850fdfe27f1 100644
--- a/kernel/trace/kprobe_event_gen_test.c
+++ b/kernel/trace/kprobe_event_gen_test.c
@@ -21,7 +21,7 @@
* Then:
*
* # insmod kernel/trace/kprobe_event_gen_test.ko
- * # cat /sys/kernel/debug/tracing/trace
+ * # cat /sys/kernel/tracing/trace
*
* You should see many instances of the "gen_kprobe_test" and
* "gen_kretprobe_test" events in the trace buffer.
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b641cab2745e..af50d931b020 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2864,7 +2864,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
sched_clock_stable() ? "" :
"If you just came from a suspend/resume,\n"
"please switch to the trace global clock:\n"
- " echo global > /sys/kernel/debug/tracing/trace_clock\n"
+ " echo global > /sys/kernel/tracing/trace_clock\n"
"or add trace_clock=global to the kernel command line\n");
}
@@ -5604,11 +5604,16 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
*/
void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data)
{
- struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_per_cpu *cpu_buffer;
struct buffer_data_page *bpage = data;
struct page *page = virt_to_page(bpage);
unsigned long flags;
+ if (!buffer || !buffer->buffers || !buffer->buffers[cpu])
+ return;
+
+ cpu_buffer = buffer->buffers[cpu];
+
/* If the page is still in use someplace else, we can't reuse it */
if (page_ref_count(page) > 1)
goto out;
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 8d77526892f4..8dfe85499d4a 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -22,7 +22,7 @@
* Then:
*
* # insmod kernel/trace/synth_event_gen_test.ko
- * # cat /sys/kernel/debug/tracing/trace
+ * # cat /sys/kernel/tracing/trace
*
* You should see several events in the trace buffer -
* "create_synth_test", "empty_synth_test", and several instances of
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 54a163ae4815..0fa59acfea17 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -49,6 +49,8 @@
#include <linux/irq_work.h>
#include <linux/workqueue.h>
+#include <asm/setup.h> /* COMMAND_LINE_SIZE */
+
#include "trace.h"
#include "trace_output.h"
@@ -186,6 +188,12 @@ static char *default_bootup_tracer;
static bool allocate_snapshot;
static bool snapshot_at_boot;
+static char boot_instance_info[COMMAND_LINE_SIZE] __initdata;
+static int boot_instance_index;
+
+static char boot_snapshot_info[COMMAND_LINE_SIZE] __initdata;
+static int boot_snapshot_index;
+
static int __init set_cmdline_ftrace(char *str)
{
strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
@@ -222,9 +230,22 @@ __setup("traceoff_on_warning", stop_trace_on_warning);
static int __init boot_alloc_snapshot(char *str)
{
- allocate_snapshot = true;
- /* We also need the main ring buffer expanded */
- ring_buffer_expanded = true;
+ char *slot = boot_snapshot_info + boot_snapshot_index;
+ int left = sizeof(boot_snapshot_info) - boot_snapshot_index;
+ int ret;
+
+ if (str[0] == '=') {
+ str++;
+ if (strlen(str) >= left)
+ return -1;
+
+ ret = snprintf(slot, left, "%s\t", str);
+ boot_snapshot_index += ret;
+ } else {
+ allocate_snapshot = true;
+ /* We also need the main ring buffer expanded */
+ ring_buffer_expanded = true;
+ }
return 1;
}
__setup("alloc_snapshot", boot_alloc_snapshot);
@@ -239,6 +260,23 @@ static int __init boot_snapshot(char *str)
__setup("ftrace_boot_snapshot", boot_snapshot);
+static int __init boot_instance(char *str)
+{
+ char *slot = boot_instance_info + boot_instance_index;
+ int left = sizeof(boot_instance_info) - boot_instance_index;
+ int ret;
+
+ if (strlen(str) >= left)
+ return -1;
+
+ ret = snprintf(slot, left, "%s\t", str);
+ boot_instance_index += ret;
+
+ return 1;
+}
+__setup("trace_instance=", boot_instance);
+
+
static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
static int __init set_trace_boot_options(char *str)
@@ -1001,13 +1039,8 @@ __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *ev
ring_buffer_unlock_commit(buffer);
}
-/**
- * __trace_puts - write a constant string into the trace buffer.
- * @ip: The address of the caller
- * @str: The constant string to write
- * @size: The size of the string.
- */
-int __trace_puts(unsigned long ip, const char *str, int size)
+int __trace_array_puts(struct trace_array *tr, unsigned long ip,
+ const char *str, int size)
{
struct ring_buffer_event *event;
struct trace_buffer *buffer;
@@ -1015,7 +1048,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
unsigned int trace_ctx;
int alloc;
- if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
+ if (!(tr->trace_flags & TRACE_ITER_PRINTK))
return 0;
if (unlikely(tracing_selftest_running || tracing_disabled))
@@ -1024,7 +1057,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
alloc = sizeof(*entry) + size + 2; /* possible \n added */
trace_ctx = tracing_gen_ctx();
- buffer = global_trace.array_buffer.buffer;
+ buffer = tr->array_buffer.buffer;
ring_buffer_nest_start(buffer);
event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
trace_ctx);
@@ -1046,11 +1079,23 @@ int __trace_puts(unsigned long ip, const char *str, int size)
entry->buf[size] = '\0';
__buffer_unlock_commit(buffer, event);
- ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL);
+ ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL);
out:
ring_buffer_nest_end(buffer);
return size;
}
+EXPORT_SYMBOL_GPL(__trace_array_puts);
+
+/**
+ * __trace_puts - write a constant string into the trace buffer.
+ * @ip: The address of the caller
+ * @str: The constant string to write
+ * @size: The size of the string.
+ */
+int __trace_puts(unsigned long ip, const char *str, int size)
+{
+ return __trace_array_puts(&global_trace, ip, str, size);
+}
EXPORT_SYMBOL_GPL(__trace_puts);
/**
@@ -1142,7 +1187,7 @@ void tracing_snapshot_instance(struct trace_array *tr)
*
* Note, make sure to allocate the snapshot with either
* a tracing_snapshot_alloc(), or by doing it manually
- * with: echo 1 > /sys/kernel/debug/tracing/snapshot
+ * with: echo 1 > /sys/kernel/tracing/snapshot
*
* If the snapshot buffer is not allocated, it will stop tracing.
* Basically making a permanent snapshot.
@@ -5760,7 +5805,7 @@ static const char readme_msg[] =
#ifdef CONFIG_SYNTH_EVENTS
" events/synthetic_events\t- Create/append/remove/show synthetic events\n"
"\t Write into this file to define/undefine new synthetic events.\n"
- "\t example: echo 'myevent u64 lat; char name[]' >> synthetic_events\n"
+ "\t example: echo 'myevent u64 lat; char name[]; long[] stack' >> synthetic_events\n"
#endif
#endif
;
@@ -9225,10 +9270,6 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
}
tr->allocated_snapshot = allocate_snapshot;
- /*
- * Only the top level trace array gets its snapshot allocated
- * from the kernel command line.
- */
allocate_snapshot = false;
#endif
@@ -10144,6 +10185,79 @@ out:
return ret;
}
+#ifdef CONFIG_TRACER_MAX_TRACE
+__init static bool tr_needs_alloc_snapshot(const char *name)
+{
+ char *test;
+ int len = strlen(name);
+ bool ret;
+
+ if (!boot_snapshot_index)
+ return false;
+
+ if (strncmp(name, boot_snapshot_info, len) == 0 &&
+ boot_snapshot_info[len] == '\t')
+ return true;
+
+ test = kmalloc(strlen(name) + 3, GFP_KERNEL);
+ if (!test)
+ return false;
+
+ sprintf(test, "\t%s\t", name);
+ ret = strstr(boot_snapshot_info, test) == NULL;
+ kfree(test);
+ return ret;
+}
+
+__init static void do_allocate_snapshot(const char *name)
+{
+ if (!tr_needs_alloc_snapshot(name))
+ return;
+
+ /*
+ * When allocate_snapshot is set, the next call to
+ * allocate_trace_buffers() (called by trace_array_get_by_name())
+ * will allocate the snapshot buffer. That will alse clear
+ * this flag.
+ */
+ allocate_snapshot = true;
+}
+#else
+static inline void do_allocate_snapshot(const char *name) { }
+#endif
+
+__init static void enable_instances(void)
+{
+ struct trace_array *tr;
+ char *curr_str;
+ char *str;
+ char *tok;
+
+ /* A tab is always appended */
+ boot_instance_info[boot_instance_index - 1] = '\0';
+ str = boot_instance_info;
+
+ while ((curr_str = strsep(&str, "\t"))) {
+
+ tok = strsep(&curr_str, ",");
+
+ if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE))
+ do_allocate_snapshot(tok);
+
+ tr = trace_array_get_by_name(tok);
+ if (!tr) {
+ pr_warn("Failed to create instance buffer %s\n", curr_str);
+ continue;
+ }
+ /* Allow user space to delete it */
+ trace_array_put(tr);
+
+ while ((tok = strsep(&curr_str, ","))) {
+ early_enable_events(tr, tok, true);
+ }
+ }
+}
+
__init static int tracer_alloc_buffers(void)
{
int ring_buf_size;
@@ -10277,10 +10391,19 @@ out:
void __init ftrace_boot_snapshot(void)
{
+ struct trace_array *tr;
+
if (snapshot_at_boot) {
tracing_snapshot();
internal_trace_puts("** Boot snapshot taken **\n");
}
+
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (tr == &global_trace)
+ continue;
+ trace_array_puts(tr, "** Boot snapshot taken **\n");
+ tracing_snapshot_instance(tr);
+ }
}
void __init early_trace_init(void)
@@ -10302,6 +10425,9 @@ void __init early_trace_init(void)
void __init trace_init(void)
{
trace_event_init();
+
+ if (boot_instance_index)
+ enable_instances();
}
__init static void clear_boot_tracer(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 085a31b978a5..f3aae2be1d53 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -113,6 +113,10 @@ enum trace_type {
#define MEM_FAIL(condition, fmt, ...) \
DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__)
+#define HIST_STACKTRACE_DEPTH 16
+#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
+#define HIST_STACKTRACE_SKIP 5
+
/*
* syscalls are special, and need special handling, this is why
* they are not included in trace_entries.h
@@ -1331,6 +1335,8 @@ DECLARE_PER_CPU(int, trace_buffered_event_cnt);
void trace_buffered_event_disable(void);
void trace_buffered_event_enable(void);
+void early_enable_events(struct trace_array *tr, char *buf, bool disable_first);
+
static inline void
__trace_event_discard_commit(struct trace_buffer *buffer,
struct ring_buffer_event *event)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6a942fa275c7..654ffa40457a 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2281,8 +2281,6 @@ create_new_subsystem(const char *name)
if (!system->name)
goto out_free;
- system->filter = NULL;
-
system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
if (!system->filter)
goto out_free;
@@ -2843,7 +2841,7 @@ static __init int setup_trace_triggers(char *str)
if (!trigger)
break;
bootup_triggers[i].event = strsep(&trigger, ".");
- bootup_triggers[i].trigger = strsep(&trigger, ".");
+ bootup_triggers[i].trigger = trigger;
if (!bootup_triggers[i].trigger)
break;
}
@@ -3771,10 +3769,9 @@ static __init int event_trace_memsetup(void)
return 0;
}
-static __init void
-early_enable_events(struct trace_array *tr, bool disable_first)
+__init void
+early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
{
- char *buf = bootup_event_buf;
char *token;
int ret;
@@ -3827,7 +3824,7 @@ static __init int event_trace_enable(void)
*/
__trace_early_add_events(tr);
- early_enable_events(tr, false);
+ early_enable_events(tr, bootup_event_buf, false);
trace_printk_start_comm();
@@ -3855,7 +3852,7 @@ static __init int event_trace_enable_again(void)
if (!tr)
return -ENODEV;
- early_enable_events(tr, true);
+ early_enable_events(tr, bootup_event_buf, true);
return 0;
}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e095c3b3a50d..1dad64267878 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -64,6 +64,7 @@ enum filter_pred_fn {
FILTER_PRED_FN_PCHAR_USER,
FILTER_PRED_FN_PCHAR,
FILTER_PRED_FN_CPU,
+ FILTER_PRED_FN_FUNCTION,
FILTER_PRED_FN_,
FILTER_PRED_TEST_VISITED,
};
@@ -71,6 +72,7 @@ enum filter_pred_fn {
struct filter_pred {
enum filter_pred_fn fn_num;
u64 val;
+ u64 val2;
struct regex regex;
unsigned short *ops;
struct ftrace_event_field *field;
@@ -103,6 +105,7 @@ struct filter_pred {
C(INVALID_FILTER, "Meaningless filter expression"), \
C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \
C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \
+ C(NO_FUNCTION, "Function not found"), \
C(ERRNO, "Error"), \
C(NO_FILTER, "No filter found")
@@ -876,6 +879,17 @@ static int filter_pred_comm(struct filter_pred *pred, void *event)
return cmp ^ pred->not;
}
+/* Filter predicate for functions. */
+static int filter_pred_function(struct filter_pred *pred, void *event)
+{
+ unsigned long *addr = (unsigned long *)(event + pred->offset);
+ unsigned long start = (unsigned long)pred->val;
+ unsigned long end = (unsigned long)pred->val2;
+ int ret = *addr >= start && *addr < end;
+
+ return pred->op == OP_EQ ? ret : !ret;
+}
+
/*
* regex_match_foo - Basic regex callbacks
*
@@ -1335,6 +1349,8 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event)
return filter_pred_pchar(pred, event);
case FILTER_PRED_FN_CPU:
return filter_pred_cpu(pred, event);
+ case FILTER_PRED_FN_FUNCTION:
+ return filter_pred_function(pred, event);
case FILTER_PRED_TEST_VISITED:
return test_pred_visited_fn(pred, event);
default:
@@ -1350,8 +1366,13 @@ static int parse_pred(const char *str, void *data,
struct trace_event_call *call = data;
struct ftrace_event_field *field;
struct filter_pred *pred = NULL;
+ unsigned long offset;
+ unsigned long size;
+ unsigned long ip;
char num_buf[24]; /* Big enough to hold an address */
char *field_name;
+ char *name;
+ bool function = false;
bool ustring = false;
char q;
u64 val;
@@ -1393,6 +1414,12 @@ static int parse_pred(const char *str, void *data,
i += len;
}
+ /* See if the field is a kernel function name */
+ if ((len = str_has_prefix(str + i, ".function"))) {
+ function = true;
+ i += len;
+ }
+
while (isspace(str[i]))
i++;
@@ -1423,7 +1450,71 @@ static int parse_pred(const char *str, void *data,
pred->offset = field->offset;
pred->op = op;
- if (ftrace_event_is_function(call)) {
+ if (function) {
+ /* The field must be the same size as long */
+ if (field->size != sizeof(long)) {
+ parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i);
+ goto err_free;
+ }
+
+ /* Function only works with '==' or '!=' and an unquoted string */
+ switch (op) {
+ case OP_NE:
+ case OP_EQ:
+ break;
+ default:
+ parse_error(pe, FILT_ERR_INVALID_OP, pos + i);
+ goto err_free;
+ }
+
+ if (isdigit(str[i])) {
+ /* We allow 0xDEADBEEF */
+ while (isalnum(str[i]))
+ i++;
+
+ len = i - s;
+ /* 0xfeedfacedeadbeef is 18 chars max */
+ if (len >= sizeof(num_buf)) {
+ parse_error(pe, FILT_ERR_OPERAND_TOO_LONG, pos + i);
+ goto err_free;
+ }
+
+ strncpy(num_buf, str + s, len);
+ num_buf[len] = 0;
+
+ ret = kstrtoul(num_buf, 0, &ip);
+ if (ret) {
+ parse_error(pe, FILT_ERR_INVALID_VALUE, pos + i);
+ goto err_free;
+ }
+ } else {
+ s = i;
+ for (; str[i] && !isspace(str[i]); i++)
+ ;
+
+ len = i - s;
+ name = kmemdup_nul(str + s, len, GFP_KERNEL);
+ if (!name)
+ goto err_mem;
+ ip = kallsyms_lookup_name(name);
+ kfree(name);
+ if (!ip) {
+ parse_error(pe, FILT_ERR_NO_FUNCTION, pos + i);
+ goto err_free;
+ }
+ }
+
+ /* Now find the function start and end address */
+ if (!kallsyms_lookup_size_offset(ip, &size, &offset)) {
+ parse_error(pe, FILT_ERR_NO_FUNCTION, pos + i);
+ goto err_free;
+ }
+
+ pred->fn_num = FILTER_PRED_FN_FUNCTION;
+ pred->val = ip - offset;
+ pred->val2 = pred->val + size;
+
+ } else if (ftrace_event_is_function(call)) {
/*
* Perf does things different with function events.
* It only allows an "ip" field, and expects a string.
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5edbf6b1da3f..89877a18f933 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -135,6 +135,7 @@ enum hist_field_fn {
HIST_FIELD_FN_DIV_NOT_POWER2,
HIST_FIELD_FN_DIV_MULT_SHIFT,
HIST_FIELD_FN_EXECNAME,
+ HIST_FIELD_FN_STACK,
};
/*
@@ -480,10 +481,6 @@ DEFINE_HIST_FIELD_FN(u8);
#define for_each_hist_key_field(i, hist_data) \
for ((i) = (hist_data)->n_vals; (i) < (hist_data)->n_fields; (i)++)
-#define HIST_STACKTRACE_DEPTH 16
-#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
-#define HIST_STACKTRACE_SKIP 5
-
#define HITCOUNT_IDX 0
#define HIST_KEY_SIZE_MAX (MAX_FILTER_STR_VAL + HIST_STACKTRACE_SIZE)
@@ -1360,7 +1357,12 @@ static const char *hist_field_name(struct hist_field *field,
field_name = field->name;
} else if (field->flags & HIST_FIELD_FL_TIMESTAMP)
field_name = "common_timestamp";
- else if (field->flags & HIST_FIELD_FL_HITCOUNT)
+ else if (field->flags & HIST_FIELD_FL_STACKTRACE) {
+ if (field->field)
+ field_name = field->field->name;
+ else
+ field_name = "stacktrace";
+ } else if (field->flags & HIST_FIELD_FL_HITCOUNT)
field_name = "hitcount";
if (field_name == NULL)
@@ -1718,6 +1720,8 @@ static const char *get_hist_field_flags(struct hist_field *hist_field)
flags_str = "percent";
else if (hist_field->flags & HIST_FIELD_FL_GRAPH)
flags_str = "graph";
+ else if (hist_field->flags & HIST_FIELD_FL_STACKTRACE)
+ flags_str = "stacktrace";
return flags_str;
}
@@ -1979,7 +1983,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
}
if (flags & HIST_FIELD_FL_STACKTRACE) {
- hist_field->fn_num = HIST_FIELD_FN_NOP;
+ if (field)
+ hist_field->fn_num = HIST_FIELD_FN_STACK;
+ else
+ hist_field->fn_num = HIST_FIELD_FN_NOP;
+ hist_field->size = HIST_STACKTRACE_SIZE;
+ hist_field->type = kstrdup_const("unsigned long[]", GFP_KERNEL);
+ if (!hist_field->type)
+ goto free;
goto out;
}
@@ -2312,6 +2323,8 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
*flags |= HIST_FIELD_FL_EXECNAME;
else if (strcmp(modifier, "syscall") == 0)
*flags |= HIST_FIELD_FL_SYSCALL;
+ else if (strcmp(modifier, "stacktrace") == 0)
+ *flags |= HIST_FIELD_FL_STACKTRACE;
else if (strcmp(modifier, "log2") == 0)
*flags |= HIST_FIELD_FL_LOG2;
else if (strcmp(modifier, "usecs") == 0)
@@ -2351,6 +2364,8 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
hist_data->enable_timestamps = true;
if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
hist_data->attrs->ts_in_usecs = true;
+ } else if (strcmp(field_name, "stacktrace") == 0) {
+ *flags |= HIST_FIELD_FL_STACKTRACE;
} else if (strcmp(field_name, "common_cpu") == 0)
*flags |= HIST_FIELD_FL_CPU;
else if (strcmp(field_name, "hitcount") == 0)
@@ -3111,6 +3126,9 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
unsigned int i, j, var_idx;
u64 var_val;
+ /* Make sure stacktrace can fit in the string variable length */
+ BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) >= STR_VAR_LEN_MAX);
+
for (i = 0, j = field_var_str_start; i < n_field_vars; i++) {
struct field_var *field_var = field_vars[i];
struct hist_field *var = field_var->var;
@@ -3119,13 +3137,26 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
var_val = hist_fn_call(val, elt, buffer, rbe, rec);
var_idx = var->var.idx;
- if (val->flags & HIST_FIELD_FL_STRING) {
+ if (val->flags & (HIST_FIELD_FL_STRING |
+ HIST_FIELD_FL_STACKTRACE)) {
char *str = elt_data->field_var_str[j++];
char *val_str = (char *)(uintptr_t)var_val;
unsigned int size;
- size = min(val->size, STR_VAR_LEN_MAX);
- strscpy(str, val_str, size);
+ if (val->flags & HIST_FIELD_FL_STRING) {
+ size = min(val->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
+ } else {
+ char *stack_start = str + sizeof(unsigned long);
+ int e;
+
+ e = stack_trace_save((void *)stack_start,
+ HIST_STACKTRACE_DEPTH,
+ HIST_STACKTRACE_SKIP);
+ if (e < HIST_STACKTRACE_DEPTH - 1)
+ ((unsigned long *)stack_start)[e] = 0;
+ *((unsigned long *)str) = e;
+ }
var_val = (u64)(uintptr_t)str;
}
tracing_map_set_var(elt, var_idx, var_val);
@@ -3824,7 +3855,8 @@ static void save_field_var(struct hist_trigger_data *hist_data,
{
hist_data->field_vars[hist_data->n_field_vars++] = field_var;
- if (field_var->val->flags & HIST_FIELD_FL_STRING)
+ /* Stack traces are saved in the string storage too */
+ if (field_var->val->flags & (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE))
hist_data->n_field_var_str++;
}
@@ -3849,6 +3881,9 @@ static int check_synth_field(struct synth_event *event,
&& field->is_dynamic)
return 0;
+ if (strstr(hist_field->type, "long[") && field->is_stack)
+ return 0;
+
if (strcmp(field->type, hist_field->type) != 0) {
if (field->size != hist_field->size ||
(!field->is_string && field->is_signed != hist_field->is_signed))
@@ -4103,7 +4138,8 @@ static int action_create(struct hist_trigger_data *hist_data,
}
hist_data->save_vars[hist_data->n_save_vars++] = field_var;
- if (field_var->val->flags & HIST_FIELD_FL_STRING)
+ if (field_var->val->flags &
+ (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE))
hist_data->n_save_var_str++;
kfree(param);
}
@@ -4242,6 +4278,19 @@ static u64 hist_field_execname(struct hist_field *hist_field,
return (u64)(unsigned long)(elt_data->comm);
}
+static u64 hist_field_stack(struct hist_field *hist_field,
+ struct tracing_map_elt *elt,
+ struct trace_buffer *buffer,
+ struct ring_buffer_event *rbe,
+ void *event)
+{
+ u32 str_item = *(u32 *)(event + hist_field->field->offset);
+ int str_loc = str_item & 0xffff;
+ char *addr = (char *)(event + str_loc);
+
+ return (u64)(unsigned long)addr;
+}
+
static u64 hist_fn_call(struct hist_field *hist_field,
struct tracing_map_elt *elt,
struct trace_buffer *buffer,
@@ -4305,6 +4354,8 @@ static u64 hist_fn_call(struct hist_field *hist_field,
return div_by_mult_and_shift(hist_field, elt, buffer, rbe, event);
case HIST_FIELD_FN_EXECNAME:
return hist_field_execname(hist_field, elt, buffer, rbe, event);
+ case HIST_FIELD_FN_STACK:
+ return hist_field_stack(hist_field, elt, buffer, rbe, event);
default:
return 0;
}
@@ -4351,7 +4402,8 @@ static int create_var_field(struct hist_trigger_data *hist_data,
if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_EXECNAME)
update_var_execname(hist_data->fields[val_idx]);
- if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_STRING)
+ if (!ret && hist_data->fields[val_idx]->flags &
+ (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE))
hist_data->fields[val_idx]->var_str_idx = hist_data->n_var_str++;
return ret;
@@ -5092,7 +5144,8 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
if (hist_field->flags & HIST_FIELD_FL_VAR) {
var_idx = hist_field->var.idx;
- if (hist_field->flags & HIST_FIELD_FL_STRING) {
+ if (hist_field->flags &
+ (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE)) {
unsigned int str_start, var_str_idx, idx;
char *str, *val_str;
unsigned int size;
@@ -5105,9 +5158,20 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
str = elt_data->field_var_str[idx];
val_str = (char *)(uintptr_t)hist_val;
- size = min(hist_field->size, STR_VAR_LEN_MAX);
- strscpy(str, val_str, size);
-
+ if (hist_field->flags & HIST_FIELD_FL_STRING) {
+ size = min(hist_field->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
+ } else {
+ char *stack_start = str + sizeof(unsigned long);
+ int e;
+
+ e = stack_trace_save((void *)stack_start,
+ HIST_STACKTRACE_DEPTH,
+ HIST_STACKTRACE_SKIP);
+ if (e < HIST_STACKTRACE_DEPTH - 1)
+ ((unsigned long *)stack_start)[e] = 0;
+ *((unsigned long *)str) = e;
+ }
hist_val = (u64)(uintptr_t)str;
}
tracing_map_set_var(elt, var_idx, hist_val);
@@ -5193,8 +5257,17 @@ static void event_hist_trigger(struct event_trigger_data *data,
if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
memset(entries, 0, HIST_STACKTRACE_SIZE);
- stack_trace_save(entries, HIST_STACKTRACE_DEPTH,
- HIST_STACKTRACE_SKIP);
+ if (key_field->field) {
+ unsigned long *stack, n_entries;
+
+ field_contents = hist_fn_call(key_field, elt, buffer, rbe, rec);
+ stack = (unsigned long *)(long)field_contents;
+ n_entries = *stack;
+ memcpy(entries, ++stack, n_entries * sizeof(unsigned long));
+ } else {
+ stack_trace_save(entries, HIST_STACKTRACE_DEPTH,
+ HIST_STACKTRACE_SKIP);
+ }
key = entries;
} else {
field_contents = hist_fn_call(key_field, elt, buffer, rbe, rec);
@@ -5297,7 +5370,10 @@ static void hist_trigger_print_key(struct seq_file *m,
seq_printf(m, "%s: %-30s[%3llu]", field_name,
syscall_name, uval);
} else if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
- seq_puts(m, "stacktrace:\n");
+ if (key_field->field)
+ seq_printf(m, "%s.stacktrace", key_field->field->name);
+ else
+ seq_puts(m, "stacktrace:\n");
hist_trigger_stacktrace_print(m,
key + key_field->offset,
HIST_STACKTRACE_DEPTH);
@@ -5842,7 +5918,8 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
if (hist_field->flags) {
if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) &&
- !(hist_field->flags & HIST_FIELD_FL_EXPR)) {
+ !(hist_field->flags & HIST_FIELD_FL_EXPR) &&
+ !(hist_field->flags & HIST_FIELD_FL_STACKTRACE)) {
const char *flags = get_hist_field_flags(hist_field);
if (flags)
@@ -5875,9 +5952,12 @@ static int event_hist_trigger_print(struct seq_file *m,
if (i > hist_data->n_vals)
seq_puts(m, ",");
- if (field->flags & HIST_FIELD_FL_STACKTRACE)
- seq_puts(m, "stacktrace");
- else
+ if (field->flags & HIST_FIELD_FL_STACKTRACE) {
+ if (field->field)
+ seq_printf(m, "%s.stacktrace", field->field->name);
+ else
+ seq_puts(m, "stacktrace");
+ } else
hist_field_print(m, field);
}
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 67592eed0be8..70bddb25d9c0 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -173,6 +173,14 @@ static int synth_field_is_string(char *type)
return false;
}
+static int synth_field_is_stack(char *type)
+{
+ if (strstr(type, "long[") != NULL)
+ return true;
+
+ return false;
+}
+
static int synth_field_string_size(char *type)
{
char buf[4], *end, *start;
@@ -248,6 +256,8 @@ static int synth_field_size(char *type)
size = sizeof(gfp_t);
else if (synth_field_is_string(type))
size = synth_field_string_size(type);
+ else if (synth_field_is_stack(type))
+ size = 0;
return size;
}
@@ -292,6 +302,8 @@ static const char *synth_field_fmt(char *type)
fmt = "%x";
else if (synth_field_is_string(type))
fmt = "%.*s";
+ else if (synth_field_is_stack(type))
+ fmt = "%s";
return fmt;
}
@@ -371,6 +383,23 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
i == se->n_fields - 1 ? "" : " ");
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
}
+ } else if (se->fields[i]->is_stack) {
+ u32 offset, data_offset, len;
+ unsigned long *p, *end;
+
+ offset = (u32)entry->fields[n_u64];
+ data_offset = offset & 0xffff;
+ len = offset >> 16;
+
+ p = (void *)entry + data_offset;
+ end = (void *)p + len - (sizeof(long) - 1);
+
+ trace_seq_printf(s, "%s=STACK:\n", se->fields[i]->name);
+
+ for (; *p && p < end; p++)
+ trace_seq_printf(s, "=> %pS\n", (void *)*p);
+ n_u64++;
+
} else {
struct trace_print_flags __flags[] = {
__def_gfpflag_names, {-1, NULL} };
@@ -416,8 +445,7 @@ static unsigned int trace_string(struct synth_trace_event *entry,
if (is_dynamic) {
u32 data_offset;
- data_offset = offsetof(typeof(*entry), fields);
- data_offset += event->n_u64 * sizeof(u64);
+ data_offset = struct_size(entry, fields, event->n_u64);
data_offset += data_size;
len = kern_fetch_store_strlen((unsigned long)str_val);
@@ -447,6 +475,43 @@ static unsigned int trace_string(struct synth_trace_event *entry,
return len;
}
+static unsigned int trace_stack(struct synth_trace_event *entry,
+ struct synth_event *event,
+ long *stack,
+ unsigned int data_size,
+ unsigned int *n_u64)
+{
+ unsigned int len;
+ u32 data_offset;
+ void *data_loc;
+
+ data_offset = struct_size(entry, fields, event->n_u64);
+ data_offset += data_size;
+
+ for (len = 0; len < HIST_STACKTRACE_DEPTH; len++) {
+ if (!stack[len])
+ break;
+ }
+
+ /* Include the zero'd element if it fits */
+ if (len < HIST_STACKTRACE_DEPTH)
+ len++;
+
+ len *= sizeof(long);
+
+ /* Find the dynamic section to copy the stack into. */
+ data_loc = (void *)entry + data_offset;
+ memcpy(data_loc, stack, len);
+
+ /* Fill in the field that holds the offset/len combo */
+ data_offset |= len << 16;
+ *(u32 *)&entry->fields[*n_u64] = data_offset;
+
+ (*n_u64)++;
+
+ return len;
+}
+
static notrace void trace_event_raw_event_synth(void *__data,
u64 *var_ref_vals,
unsigned int *var_ref_idx)
@@ -473,7 +538,12 @@ static notrace void trace_event_raw_event_synth(void *__data,
val_idx = var_ref_idx[field_pos];
str_val = (char *)(long)var_ref_vals[val_idx];
- len = kern_fetch_store_strlen((unsigned long)str_val);
+ if (event->dynamic_fields[i]->is_stack) {
+ len = *((unsigned long *)str_val);
+ len *= sizeof(unsigned long);
+ } else {
+ len = kern_fetch_store_strlen((unsigned long)str_val);
+ }
fields_size += len;
}
@@ -499,6 +569,12 @@ static notrace void trace_event_raw_event_synth(void *__data,
event->fields[i]->is_dynamic,
data_size, &n_u64);
data_size += len; /* only dynamic string increments */
+ } else if (event->fields[i]->is_stack) {
+ long *stack = (long *)(long)var_ref_vals[val_idx];
+
+ len = trace_stack(entry, event, stack,
+ data_size, &n_u64);
+ data_size += len;
} else {
struct synth_field *field = event->fields[i];
u64 val = var_ref_vals[val_idx];
@@ -561,6 +637,9 @@ static int __set_synth_event_print_fmt(struct synth_event *event,
event->fields[i]->is_dynamic)
pos += snprintf(buf + pos, LEN_OR_ZERO,
", __get_str(%s)", event->fields[i]->name);
+ else if (event->fields[i]->is_stack)
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ ", __get_stacktrace(%s)", event->fields[i]->name);
else
pos += snprintf(buf + pos, LEN_OR_ZERO,
", REC->%s", event->fields[i]->name);
@@ -697,7 +776,8 @@ static struct synth_field *parse_synth_field(int argc, char **argv,
ret = -EINVAL;
goto free;
} else if (size == 0) {
- if (synth_field_is_string(field->type)) {
+ if (synth_field_is_string(field->type) ||
+ synth_field_is_stack(field->type)) {
char *type;
len = sizeof("__data_loc ") + strlen(field->type) + 1;
@@ -728,6 +808,8 @@ static struct synth_field *parse_synth_field(int argc, char **argv,
if (synth_field_is_string(field->type))
field->is_string = true;
+ else if (synth_field_is_stack(field->type))
+ field->is_stack = true;
field->is_signed = synth_field_signed(field->type);
out:
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 210e1f168392..04f0fdae19a1 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1539,7 +1539,7 @@ static void osnoise_sleep(void)
wake_time = ktime_add_us(ktime_get(), interval);
__set_current_state(TASK_INTERRUPTIBLE);
- while (schedule_hrtimeout_range(&wake_time, 0, HRTIMER_MODE_ABS)) {
+ while (schedule_hrtimeout(&wake_time, HRTIMER_MODE_ABS)) {
if (kthread_should_stop())
break;
}
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 9c90b3a7dce2..e5e299260d0c 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -403,3 +403,26 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str,
return 1;
}
EXPORT_SYMBOL(trace_seq_hex_dump);
+
+/*
+ * trace_seq_acquire - acquire seq buffer with size len
+ * @s: trace sequence descriptor
+ * @len: size of buffer to be acquired
+ *
+ * acquire buffer with size of @len from trace_seq for output usage,
+ * user can fill string into that buffer.
+ *
+ * Returns start address of acquired buffer.
+ *
+ * it allow multiple usage in one trace output function call.
+ */
+char *trace_seq_acquire(struct trace_seq *s, unsigned int len)
+{
+ char *ret = trace_seq_buffer_ptr(s);
+
+ if (!WARN_ON_ONCE(seq_buf_buffer_left(&s->seq) < len))
+ seq_buf_commit(&s->seq, len);
+
+ return ret;
+}
+EXPORT_SYMBOL(trace_seq_acquire);
diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h
index b29595fe3ac5..43f6fb6078db 100644
--- a/kernel/trace/trace_synth.h
+++ b/kernel/trace/trace_synth.h
@@ -18,6 +18,7 @@ struct synth_field {
bool is_signed;
bool is_string;
bool is_dynamic;
+ bool is_stack;
};
struct synth_event {
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index f23144af5743..8d1507dd0724 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -571,8 +571,8 @@ static void for_each_tracepoint_range(
bool trace_module_has_bad_taint(struct module *mod)
{
return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) |
- (1 << TAINT_UNSIGNED_MODULE) |
- (1 << TAINT_TEST));
+ (1 << TAINT_UNSIGNED_MODULE) | (1 << TAINT_TEST) |
+ (1 << TAINT_LIVEPATCH));
}
static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list);