summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-05-29 10:31:36 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-05-29 10:31:36 -0700
commit76bfd3de34783ceda1fc1d73d0db87361de07ecb (patch)
tree468edc58eae863167afa5ff96248a2c7bcc91c9a
parent09f73a1ab8207481d1d6bd91ab7d0125c6722005 (diff)
parentb39181f7c6907dc66ff937b74758671fa6ba430c (diff)
Merge tag 'trace-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing updates from Steven Rostedt: "The majority of the changes are for fixes and clean ups. Notable changes: - Rework trace event triggers code to be easier to interact with. - Support for embedding bootconfig with the kernel (as suppose to having it embedded in initram). This is useful for embedded boards without initram disks. - Speed up boot by parallelizing the creation of tracefs files. - Allow absolute ring buffer timestamps handle timestamps that use more than 59 bits. - Added new tracing clock "TAI" (International Atomic Time) - Have weak functions show up in available_filter_function list as: __ftrace_invalid_address___<invalid-offset> instead of using the name of the function before it" * tag 'trace-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (52 commits) ftrace: Add FTRACE_MCOUNT_MAX_OFFSET to avoid adding weak function tracing: Fix comments for event_trigger_separate_filter() x86/traceponit: Fix comment about irq vector tracepoints x86,tracing: Remove unused headers ftrace: Clean up hash direct_functions on register failures tracing: Fix comments of create_filter() tracing: Disable kcov on trace_preemptirq.c tracing: Initialize integer variable to prevent garbage return value ftrace: Fix typo in comment ftrace: Remove return value of ftrace_arch_modify_*() tracing: Cleanup code by removing init "char *name" tracing: Change "char *" string form to "char []" tracing/timerlat: Do not wakeup the thread if the trace stops at the IRQ tracing/timerlat: Print stacktrace in the IRQ handler if needed tracing/timerlat: Notify IRQ new max latency only if stop tracing is set kprobes: Fix build errors with CONFIG_KRETPROBES=n tracing: Fix return value of trace_pid_write() tracing: Fix potential double free in create_var_ref() tracing: Use strim() to remove whitespace instead of doing it manually ftrace: Deal with error return code of the ftrace_process_locs() function ...
-rw-r--r--Documentation/admin-guide/bootconfig.rst31
-rw-r--r--Documentation/trace/ftrace.rst12
-rw-r--r--Documentation/trace/timerlat-tracer.rst5
-rw-r--r--MAINTAINERS5
-rw-r--r--arch/arm/kernel/ftrace.c6
-rw-r--r--arch/riscv/kernel/ftrace.c6
-rw-r--r--arch/s390/kernel/ftrace.c3
-rw-r--r--arch/x86/include/asm/ftrace.h7
-rw-r--r--arch/x86/kernel/ftrace.c6
-rw-r--r--arch/x86/kernel/tracepoint.c6
-rw-r--r--include/linux/bootconfig.h10
-rw-r--r--include/linux/ftrace.h4
-rw-r--r--include/linux/kprobes.h2
-rw-r--r--init/Kconfig21
-rw-r--r--init/main.c38
-rw-r--r--kernel/kprobes.c144
-rw-r--r--kernel/trace/Makefile4
-rw-r--r--kernel/trace/ftrace.c210
-rw-r--r--kernel/trace/pid_list.c4
-rw-r--r--kernel/trace/ring_buffer.c81
-rw-r--r--kernel/trace/trace.c72
-rw-r--r--kernel/trace/trace.h26
-rw-r--r--kernel/trace/trace_boot.c2
-rw-r--r--kernel/trace/trace_dynevent.c9
-rw-r--r--kernel/trace/trace_eprobe.c24
-rw-r--r--kernel/trace/trace_events.c69
-rw-r--r--kernel/trace/trace_events_filter.c2
-rw-r--r--kernel/trace/trace_events_hist.c191
-rw-r--r--kernel/trace/trace_events_trigger.c324
-rw-r--r--kernel/trace/trace_kprobe.c15
-rw-r--r--kernel/trace/trace_osnoise.c22
-rw-r--r--kernel/trace/trace_output.c25
-rw-r--r--kernel/trace/trace_recursion_record.c7
-rw-r--r--kernel/trace/trace_selftest.c3
-rw-r--r--kernel/trace/trace_syscalls.c35
-rw-r--r--kernel/trace/tracing_map.c3
-rw-r--r--lib/.gitignore1
-rw-r--r--lib/Makefile10
-rw-r--r--lib/bootconfig-data.S10
-rw-r--r--lib/bootconfig.c13
40 files changed, 822 insertions, 646 deletions
diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
index a1860fc0ca88..d99994345d41 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -158,9 +158,15 @@ Each key-value pair is shown in each line with following style::
Boot Kernel With a Boot Config
==============================
-Since the boot configuration file is loaded with initrd, it will be added
-to the end of the initrd (initramfs) image file with padding, size,
-checksum and 12-byte magic word as below.
+There are two options to boot the kernel with bootconfig: attaching the
+bootconfig to the initrd image or embedding it in the kernel itself.
+
+Attaching a Boot Config to Initrd
+---------------------------------
+
+Since the boot configuration file is loaded with initrd by default,
+it will be added to the end of the initrd (initramfs) image file with
+padding, size, checksum and 12-byte magic word as below.
[initrd][bootconfig][padding][size(le32)][checksum(le32)][#BOOTCONFIG\n]
@@ -196,6 +202,25 @@ To remove the config from the image, you can use -d option as below::
Then add "bootconfig" on the normal kernel command line to tell the
kernel to look for the bootconfig at the end of the initrd file.
+Embedding a Boot Config into Kernel
+-----------------------------------
+
+If you can not use initrd, you can also embed the bootconfig file in the
+kernel by Kconfig options. In this case, you need to recompile the kernel
+with the following configs::
+
+ CONFIG_BOOT_CONFIG_EMBED=y
+ CONFIG_BOOT_CONFIG_EMBED_FILE="/PATH/TO/BOOTCONFIG/FILE"
+
+``CONFIG_BOOT_CONFIG_EMBED_FILE`` requires an absolute path or a relative
+path to the bootconfig file from source tree or object tree.
+The kernel will embed it as the default bootconfig.
+
+Just as when attaching the bootconfig to the initrd, you need ``bootconfig``
+option on the kernel command line to enable the embedded bootconfig.
+
+Note that even if you set this option, you can override the embedded
+bootconfig by another bootconfig which attached to the initrd.
Kernel parameters via Boot Config
=================================
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 45b8c56af67a..b37dc19e4d40 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -517,6 +517,18 @@ of ftrace. Here is a list of some of the key files:
processing should be able to handle them. See comments in the
ktime_get_boot_fast_ns() function for more information.
+ tai:
+ This is the tai clock (CLOCK_TAI) and is derived from the wall-
+ clock time. However, this clock does not experience
+ discontinuities and backwards jumps caused by NTP inserting leap
+ seconds. Since the clock access is designed for use in tracing,
+ side effects are possible. The clock access may yield wrong
+ readouts in case the internal TAI offset is updated e.g., caused
+ by setting the system time or using adjtimex() with an offset.
+ These effects are rare and post processing should be able to
+ handle them. See comments in the ktime_get_tai_fast_ns()
+ function for more information.
+
To set a clock, simply echo the clock name into this file::
# echo global > trace_clock
diff --git a/Documentation/trace/timerlat-tracer.rst b/Documentation/trace/timerlat-tracer.rst
index 64d1fe6e9b93..d643c95c01eb 100644
--- a/Documentation/trace/timerlat-tracer.rst
+++ b/Documentation/trace/timerlat-tracer.rst
@@ -74,8 +74,9 @@ directory. The timerlat configs are:
- stop_tracing_total_us: stop the system tracing if a
timer latency at the *thread* context is higher than the configured
value happens. Writing 0 disables this option.
- - print_stack: save the stack of the IRQ occurrence, and print
- it after the *thread context* event".
+ - print_stack: save the stack of the IRQ occurrence. The stack is printed
+ after the *thread context* event, or at the IRQ handler if *stop_tracing_us*
+ is hit.
timerlat and osnoise
----------------------------
diff --git a/MAINTAINERS b/MAINTAINERS
index e02f4601f821..a0f251772b79 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7517,6 +7517,7 @@ S: Maintained
F: Documentation/admin-guide/bootconfig.rst
F: fs/proc/bootconfig.c
F: include/linux/bootconfig.h
+F: lib/bootconfig-data.S
F: lib/bootconfig.c
F: tools/bootconfig/*
F: tools/bootconfig/scripts/*
@@ -20119,8 +20120,8 @@ M: Ingo Molnar <mingo@redhat.com>
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
F: Documentation/trace/ftrace.rst
-F: arch/*/*/*/ftrace.h
-F: arch/*/kernel/ftrace.c
+F: arch/*/*/*/*ftrace*
+F: arch/*/*/*ftrace*
F: fs/tracefs/
F: include/*/ftrace.h
F: include/linux/trace*.h
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 83cc068586bc..a0b6d1e3812f 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -79,16 +79,14 @@ static unsigned long __ref adjust_address(struct dyn_ftrace *rec,
return (unsigned long)&ftrace_regs_caller_from_init;
}
-int ftrace_arch_code_modify_prepare(void)
+void ftrace_arch_code_modify_prepare(void)
{
- return 0;
}
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
{
/* Make sure any TLB misses during machine stop are cleared. */
flush_tlb_all();
- return 0;
}
static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr,
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 4716f4cdc038..2086f6585773 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -12,16 +12,14 @@
#include <asm/patch.h>
#ifdef CONFIG_DYNAMIC_FTRACE
-int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
+void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex)
{
mutex_lock(&text_mutex);
- return 0;
}
-int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
+void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
{
mutex_unlock(&text_mutex);
- return 0;
}
static int ftrace_check_current_call(unsigned long hook_pos,
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 1852d46babb1..416b5a94353d 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -225,14 +225,13 @@ void arch_ftrace_update_code(int command)
ftrace_modify_all_code(command);
}
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
{
/*
* Flush any pre-fetched instructions on all
* CPUs to make the new code visible.
*/
text_poke_sync_lock();
- return 0;
}
#ifdef CONFIG_MODULES
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 024d9797646e..b5ef474be858 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -9,6 +9,13 @@
# define MCOUNT_ADDR ((unsigned long)(__fentry__))
#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */
+/* Ignore unused weak functions which will have non zero offsets */
+#ifdef CONFIG_HAVE_FENTRY
+# include <asm/ibt.h>
+/* Add offset for endbr64 if IBT enabled */
+# define FTRACE_MCOUNT_MAX_OFFSET ENDBR_INSN_SIZE
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE
#define ARCH_SUPPORTS_FTRACE_OPS 1
#endif
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index b09d73c2ba89..5b4efc927d80 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -37,7 +37,7 @@
static int ftrace_poke_late = 0;
-int ftrace_arch_code_modify_prepare(void)
+void ftrace_arch_code_modify_prepare(void)
__acquires(&text_mutex)
{
/*
@@ -47,10 +47,9 @@ int ftrace_arch_code_modify_prepare(void)
*/
mutex_lock(&text_mutex);
ftrace_poke_late = 1;
- return 0;
}
-int ftrace_arch_code_modify_post_process(void)
+void ftrace_arch_code_modify_post_process(void)
__releases(&text_mutex)
{
/*
@@ -61,7 +60,6 @@ int ftrace_arch_code_modify_post_process(void)
text_poke_finish();
ftrace_poke_late = 0;
mutex_unlock(&text_mutex);
- return 0;
}
static const char *ftrace_nop_replace(void)
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
index fcfc077afe2d..03ae1caaa878 100644
--- a/arch/x86/kernel/tracepoint.c
+++ b/arch/x86/kernel/tracepoint.c
@@ -1,17 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Code for supporting irq vector tracepoints.
- *
* Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com>
- *
*/
#include <linux/jump_label.h>
#include <linux/atomic.h>
-#include <asm/hw_irq.h>
-#include <asm/desc.h>
#include <asm/trace/exceptions.h>
-#include <asm/trace/irq_vectors.h>
DEFINE_STATIC_KEY_FALSE(trace_pagefault_key);
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index a4665c7ab07c..1611f9db878e 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -289,4 +289,14 @@ int __init xbc_get_info(int *node_size, size_t *data_size);
/* XBC cleanup data structures */
void __init xbc_exit(void);
+/* XBC embedded bootconfig data in kernel */
+#ifdef CONFIG_BOOT_CONFIG_EMBED
+const char * __init xbc_get_embedded_bootconfig(size_t *size);
+#else
+static inline const char *xbc_get_embedded_bootconfig(size_t *size)
+{
+ return NULL;
+}
+#endif
+
#endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 3eb03d88320d..979f6bfa2c25 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -452,8 +452,8 @@ static inline void stack_tracer_enable(void) { }
#ifdef CONFIG_DYNAMIC_FTRACE
-int ftrace_arch_code_modify_prepare(void);
-int ftrace_arch_code_modify_post_process(void);
+void ftrace_arch_code_modify_prepare(void);
+void ftrace_arch_code_modify_post_process(void);
enum ftrace_bug_type {
FTRACE_BUG_UNKNOWN,
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 157168769fc2..55041d2f884d 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -424,7 +424,7 @@ void unregister_kretprobe(struct kretprobe *rp);
int register_kretprobes(struct kretprobe **rps, int num);
void unregister_kretprobes(struct kretprobe **rps, int num);
-#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+#if defined(CONFIG_KRETPROBE_ON_RETHOOK) || !defined(CONFIG_KRETPROBES)
#define kprobe_flush_task(tk) do {} while (0)
#else
void kprobe_flush_task(struct task_struct *tk);
diff --git a/init/Kconfig b/init/Kconfig
index 583675727b85..251aac1c0ccd 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1338,7 +1338,7 @@ endif
config BOOT_CONFIG
bool "Boot config support"
- select BLK_DEV_INITRD
+ select BLK_DEV_INITRD if !BOOT_CONFIG_EMBED
help
Extra boot config allows system admin to pass a config file as
complemental extension of kernel cmdline when booting.
@@ -1348,6 +1348,25 @@ config BOOT_CONFIG
If unsure, say Y.
+config BOOT_CONFIG_EMBED
+ bool "Embed bootconfig file in the kernel"
+ depends on BOOT_CONFIG
+ help
+ Embed a bootconfig file given by BOOT_CONFIG_EMBED_FILE in the
+ kernel. Usually, the bootconfig file is loaded with the initrd
+ image. But if the system doesn't support initrd, this option will
+ help you by embedding a bootconfig file while building the kernel.
+
+ If unsure, say N.
+
+config BOOT_CONFIG_EMBED_FILE
+ string "Embedded bootconfig file path"
+ depends on BOOT_CONFIG_EMBED
+ help
+ Specify a bootconfig file which will be embedded to the kernel.
+ This bootconfig will be used if there is no initrd or no other
+ bootconfig in the initrd.
+
config INITRAMFS_PRESERVE_MTIME
bool "Preserve cpio archive mtimes in initramfs"
default y
diff --git a/init/main.c b/init/main.c
index f057c49f1d9d..02eb533018f6 100644
--- a/init/main.c
+++ b/init/main.c
@@ -266,7 +266,7 @@ static int __init loglevel(char *str)
early_param("loglevel", loglevel);
#ifdef CONFIG_BLK_DEV_INITRD
-static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum)
+static void * __init get_boot_config_from_initrd(size_t *_size)
{
u32 size, csum;
char *data;
@@ -300,17 +300,20 @@ found:
return NULL;
}
+ if (xbc_calc_checksum(data, size) != csum) {
+ pr_err("bootconfig checksum failed\n");
+ return NULL;
+ }
+
/* Remove bootconfig from initramfs/initrd */
initrd_end = (unsigned long)data;
if (_size)
*_size = size;
- if (_csum)
- *_csum = csum;
return data;
}
#else
-static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum)
+static void * __init get_boot_config_from_initrd(size_t *_size)
{
return NULL;
}
@@ -407,14 +410,16 @@ static int __init warn_bootconfig(char *str)
static void __init setup_boot_config(void)
{
static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
- const char *msg;
- int pos;
- u32 size, csum;
- char *data, *err;
- int ret;
+ const char *msg, *data;
+ int pos, ret;
+ size_t size;
+ char *err;
/* Cut out the bootconfig data even if we have no bootconfig option */
- data = get_boot_config_from_initrd(&size, &csum);
+ data = get_boot_config_from_initrd(&size);
+ /* If there is no bootconfig in initrd, try embedded one. */
+ if (!data)
+ data = xbc_get_embedded_bootconfig(&size);
strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
err = parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
@@ -433,13 +438,8 @@ static void __init setup_boot_config(void)
}
if (size >= XBC_DATA_MAX) {
- pr_err("bootconfig size %d greater than max size %d\n",
- size, XBC_DATA_MAX);
- return;
- }
-
- if (xbc_calc_checksum(data, size) != csum) {
- pr_err("bootconfig checksum failed\n");
+ pr_err("bootconfig size %ld greater than max size %d\n",
+ (long)size, XBC_DATA_MAX);
return;
}
@@ -452,7 +452,7 @@ static void __init setup_boot_config(void)
msg, pos);
} else {
xbc_get_info(&ret, NULL);
- pr_info("Load bootconfig: %d bytes %d nodes\n", size, ret);
+ pr_info("Load bootconfig: %ld bytes %d nodes\n", (long)size, ret);
/* keys starting with "kernel." are passed via cmdline */
extra_command_line = xbc_make_cmdline("kernel");
/* Also, "init." keys are init arguments */
@@ -471,7 +471,7 @@ static void __init exit_boot_config(void)
static void __init setup_boot_config(void)
{
/* Remove bootconfig data from initrd */
- get_boot_config_from_initrd(NULL, NULL);
+ get_boot_config_from_initrd(NULL);
}
static int __init warn_bootconfig(char *str)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index dd58c0be9ce2..f214f8c088ed 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1257,79 +1257,6 @@ void kprobe_busy_end(void)
preempt_enable();
}
-#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
-static void free_rp_inst_rcu(struct rcu_head *head)
-{
- struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
-
- if (refcount_dec_and_test(&ri->rph->ref))
- kfree(ri->rph);
- kfree(ri);
-}
-NOKPROBE_SYMBOL(free_rp_inst_rcu);
-
-static void recycle_rp_inst(struct kretprobe_instance *ri)
-{
- struct kretprobe *rp = get_kretprobe(ri);
-
- if (likely(rp))
- freelist_add(&ri->freelist, &rp->freelist);
- else
- call_rcu(&ri->rcu, free_rp_inst_rcu);
-}
-NOKPROBE_SYMBOL(recycle_rp_inst);
-
-/*
- * This function is called from delayed_put_task_struct() when a task is
- * dead and cleaned up to recycle any kretprobe instances associated with
- * this task. These left over instances represent probed functions that
- * have been called but will never return.
- */
-void kprobe_flush_task(struct task_struct *tk)
-{
- struct kretprobe_instance *ri;
- struct llist_node *node;
-
- /* Early boot, not yet initialized. */
- if (unlikely(!kprobes_initialized))
- return;
-
- kprobe_busy_begin();
-
- node = __llist_del_all(&tk->kretprobe_instances);
- while (node) {
- ri = container_of(node, struct kretprobe_instance, llist);
- node = node->next;
-
- recycle_rp_inst(ri);
- }
-
- kprobe_busy_end();
-}
-NOKPROBE_SYMBOL(kprobe_flush_task);
-
-static inline void free_rp_inst(struct kretprobe *rp)
-{
- struct kretprobe_instance *ri;
- struct freelist_node *node;
- int count = 0;
-
- node = rp->freelist.head;
- while (node) {
- ri = container_of(node, struct kretprobe_instance, freelist);
- node = node->next;
-
- kfree(ri);
- count++;
- }
-
- if (refcount_sub_and_test(count, &rp->rph->ref)) {
- kfree(rp->rph);
- rp->rph = NULL;
- }
-}
-#endif /* !CONFIG_KRETPROBE_ON_RETHOOK */
-
/* Add the new probe to 'ap->list'. */
static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
{
@@ -1928,6 +1855,77 @@ static struct notifier_block kprobe_exceptions_nb = {
#ifdef CONFIG_KRETPROBES
#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
+static void free_rp_inst_rcu(struct rcu_head *head)
+{
+ struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
+
+ if (refcount_dec_and_test(&ri->rph->ref))
+ kfree(ri->rph);
+ kfree(ri);
+}
+NOKPROBE_SYMBOL(free_rp_inst_rcu);
+
+static void recycle_rp_inst(struct kretprobe_instance *ri)
+{
+ struct kretprobe *rp = get_kretprobe(ri);
+
+ if (likely(rp))
+ freelist_add(&ri->freelist, &rp->freelist);
+ else
+ call_rcu(&ri->rcu, free_rp_inst_rcu);
+}
+NOKPROBE_SYMBOL(recycle_rp_inst);
+
+/*
+ * This function is called from delayed_put_task_struct() when a task is
+ * dead and cleaned up to recycle any kretprobe instances associated with
+ * this task. These left over instances represent probed functions that
+ * have been called but will never return.
+ */
+void kprobe_flush_task(struct task_struct *tk)
+{
+ struct kretprobe_instance *ri;
+ struct llist_node *node;
+
+ /* Early boot, not yet initialized. */
+ if (unlikely(!kprobes_initialized))
+ return;
+
+ kprobe_busy_begin();
+
+ node = __llist_del_all(&tk->kretprobe_instances);
+ while (node) {
+ ri = container_of(node, struct kretprobe_instance, llist);
+ node = node->next;
+
+ recycle_rp_inst(ri);
+ }
+
+ kprobe_busy_end();
+}
+NOKPROBE_SYMBOL(kprobe_flush_task);
+
+static inline void free_rp_inst(struct kretprobe *rp)
+{
+ struct kretprobe_instance *ri;
+ struct freelist_node *node;
+ int count = 0;
+
+ node = rp->freelist.head;
+ while (node) {
+ ri = container_of(node, struct kretprobe_instance, freelist);
+ node = node->next;
+
+ kfree(ri);
+ count++;
+ }
+
+ if (refcount_sub_and_test(count, &rp->rph->ref)) {
+ kfree(rp->rph);
+ rp->rph = NULL;
+ }
+}
+
/* This assumes the 'tsk' is the current task or the is not running. */
static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk,
struct llist_node **cur)
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d77cd8032213..0d261774d6f3 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -31,6 +31,10 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE
GCOV_PROFILE := y
endif
+# Functions in this file could be invoked from early interrupt
+# code and produce random code coverage.
+KCOV_INSTRUMENT_trace_preemptirq.o := n
+
CFLAGS_bpf_trace.o := -I$(src)
CFLAGS_trace_benchmark.o := -I$(src)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f8db59c3a601..e750fe141a60 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -45,6 +45,8 @@
#include "trace_output.h"
#include "trace_stat.h"
+#define FTRACE_INVALID_FUNCTION "__ftrace_invalid_address__"
+
#define FTRACE_WARN_ON(cond) \
({ \
int ___r = cond; \
@@ -119,7 +121,7 @@ struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
struct ftrace_ops global_ops;
-/* Defined by vmlinux.lds.h see the commment above arch_ftrace_ops_list_func for details */
+/* Defined by vmlinux.lds.h see the comment above arch_ftrace_ops_list_func for details */
void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs);
@@ -952,7 +954,6 @@ static struct tracer_stat function_stats __initdata = {
static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
{
struct ftrace_profile_stat *stat;
- struct dentry *entry;
char *name;
int ret;
int cpu;
@@ -983,11 +984,9 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
}
}
- entry = tracefs_create_file("function_profile_enabled",
- TRACE_MODE_WRITE, d_tracer, NULL,
- &ftrace_profile_fops);
- if (!entry)
- pr_warn("Could not create tracefs 'function_profile_enabled' entry\n");
+ trace_create_file("function_profile_enabled",
+ TRACE_MODE_WRITE, d_tracer, NULL,
+ &ftrace_profile_fops);
}
#else /* CONFIG_FUNCTION_PROFILER */
@@ -2707,18 +2706,16 @@ ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec)
* archs can override this function if they must do something
* before the modifying code is performed.
*/
-int __weak ftrace_arch_code_modify_prepare(void)
+void __weak ftrace_arch_code_modify_prepare(void)
{
- return 0;
}
/*
* archs can override this function if they must do something
* after the modifying code is performed.
*/
-int __weak ftrace_arch_code_modify_post_process(void)
+void __weak ftrace_arch_code_modify_post_process(void)
{
- return 0;
}
void ftrace_modify_all_code(int command)
@@ -2804,12 +2801,7 @@ void __weak arch_ftrace_update_code(int command)
static void ftrace_run_update_code(int command)
{
- int ret;
-
- ret = ftrace_arch_code_modify_prepare();
- FTRACE_WARN_ON(ret);
- if (ret)
- return;
+ ftrace_arch_code_modify_prepare();
/*
* By default we use stop_machine() to modify the code.
@@ -2819,8 +2811,7 @@ static void ftrace_run_update_code(int command)
*/
arch_ftrace_update_code(command);
- ret = ftrace_arch_code_modify_post_process();
- FTRACE_WARN_ON(ret);
+ ftrace_arch_code_modify_post_process();
}
static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
@@ -3631,6 +3622,105 @@ static void add_trampoline_func(struct seq_file *m, struct ftrace_ops *ops,
seq_printf(m, " ->%pS", ptr);
}
+#ifdef FTRACE_MCOUNT_MAX_OFFSET
+/*
+ * Weak functions can still have an mcount/fentry that is saved in
+ * the __mcount_loc section. These can be detected by having a
+ * symbol offset of greater than FTRACE_MCOUNT_MAX_OFFSET, as the
+ * symbol found by kallsyms is not the function that the mcount/fentry
+ * is part of. The offset is much greater in these cases.
+ *
+ * Test the record to make sure that the ip points to a valid kallsyms
+ * and if not, mark it disabled.
+ */
+static int test_for_valid_rec(struct dyn_ftrace *rec)
+{
+ char str[KSYM_SYMBOL_LEN];
+ unsigned long offset;
+ const char *ret;
+
+ ret = kallsyms_lookup(rec->ip, NULL, &offset, NULL, str);
+
+ /* Weak functions can cause invalid addresses */
+ if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) {
+ rec->flags |= FTRACE_FL_DISABLED;
+ return 0;
+ }
+ return 1;
+}
+
+static struct workqueue_struct *ftrace_check_wq __initdata;
+static struct work_struct ftrace_check_work __initdata;
+
+/*
+ * Scan all the mcount/fentry entries to make sure they are valid.
+ */
+static __init void ftrace_check_work_func(struct work_struct *work)
+{
+ struct ftrace_page *pg;
+ struct dyn_ftrace *rec;
+
+ mutex_lock(&ftrace_lock);
+ do_for_each_ftrace_rec(pg, rec) {
+ test_for_valid_rec(rec);
+ } while_for_each_ftrace_rec();
+ mutex_unlock(&ftrace_lock);
+}
+
+static int __init ftrace_check_for_weak_functions(void)
+{
+ INIT_WORK(&ftrace_check_work, ftrace_check_work_func);
+
+ ftrace_check_wq = alloc_workqueue("ftrace_check_wq", WQ_UNBOUND, 0);
+
+ queue_work(ftrace_check_wq, &ftrace_check_work);
+ return 0;
+}
+
+static int __init ftrace_check_sync(void)
+{
+ /* Make sure the ftrace_check updates are finished */
+ if (ftrace_check_wq)
+ destroy_workqueue(ftrace_check_wq);
+ return 0;
+}
+
+late_initcall_sync(ftrace_check_sync);
+subsys_initcall(ftrace_check_for_weak_functions);
+
+static int print_rec(struct seq_file *m, unsigned long ip)
+{
+ unsigned long offset;
+ char str[KSYM_SYMBOL_LEN];
+ char *modname;
+ const char *ret;
+
+ ret = kallsyms_lookup(ip, NULL, &offset, &modname, str);
+ /* Weak functions can cause invalid addresses */
+ if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) {
+ snprintf(str, KSYM_SYMBOL_LEN, "%s_%ld",
+ FTRACE_INVALID_FUNCTION, offset);
+ ret = NULL;
+ }
+
+ seq_puts(m, str);
+ if (modname)
+ seq_printf(m, " [%s]", modname);
+ return ret == NULL ? -1 : 0;
+}
+#else
+static inline int test_for_valid_rec(struct dyn_ftrace *rec)
+{
+ return 1;
+}
+
+static inline int print_rec(struct seq_file *m, unsigned long ip)
+{
+ seq_printf(m, "%ps", (void *)ip);
+ return 0;
+}
+#endif
+
static int t_show(struct seq_file *m, void *v)
{
struct ftrace_iterator *iter = m->private;
@@ -3655,7 +3745,13 @@ static int t_show(struct seq_file *m, void *v)
if (!rec)
return 0;
- seq_printf(m, "%ps", (void *)rec->ip);
+ if (print_rec(m, rec->ip)) {
+ /* This should only happen when a rec is disabled */
+ WARN_ON_ONCE(!(rec->flags & FTRACE_FL_DISABLED));
+ seq_putc(m, '\n');
+ return 0;
+ }
+
if (iter->flags & FTRACE_ITER_ENABLED) {
struct ftrace_ops *ops;
@@ -3973,6 +4069,24 @@ add_rec_by_index(struct ftrace_hash *hash, struct ftrace_glob *func_g,
return 0;
}
+#ifdef FTRACE_MCOUNT_MAX_OFFSET
+static int lookup_ip(unsigned long ip, char **modname, char *str)
+{
+ unsigned long offset;
+
+ kallsyms_lookup(ip, NULL, &offset, modname, str);
+ if (offset > FTRACE_MCOUNT_MAX_OFFSET)
+ return -1;
+ return 0;
+}
+#else
+static int lookup_ip(unsigned long ip, char **modname, char *str)
+{
+ kallsyms_lookup(ip, NULL, NULL, modname, str);
+ return 0;
+}
+#endif
+
static int
ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
struct ftrace_glob *mod_g, int exclude_mod)
@@ -3980,7 +4094,12 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g,
char str[KSYM_SYMBOL_LEN];
char *modname;
- kallsyms_lookup(rec->ip, NULL, NULL, &modname, str);
+ if (lookup_ip(rec->ip, &modname, str)) {
+ /* This should only happen when a rec is disabled */
+ WARN_ON_ONCE(system_state == SYSTEM_RUNNING &&
+ !(rec->flags & FTRACE_FL_DISABLED));
+ return 0;
+ }
if (mod_g) {
int mod_matches = (modname) ? ftrace_match(modname, mod_g) : 0;
@@ -4431,7 +4550,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
* @ip: The instruction pointer address to remove the data from
*
* Returns the data if it is found, otherwise NULL.
- * Note, if the data pointer is used as the data itself, (see
+ * Note, if the data pointer is used as the data itself, (see
* ftrace_func_mapper_find_ip(), then the return value may be meaningless,
* if the data pointer was set to zero.
*/
@@ -4526,8 +4645,8 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
struct ftrace_probe_ops *probe_ops,
void *data)
{
+ struct ftrace_func_probe *probe = NULL, *iter;
struct ftrace_func_entry *entry;
- struct ftrace_func_probe *probe;
struct ftrace_hash **orig_hash;
struct ftrace_hash *old_hash;
struct ftrace_hash *hash;
@@ -4546,11 +4665,13 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
mutex_lock(&ftrace_lock);
/* Check if the probe_ops is already registered */
- list_for_each_entry(probe, &tr->func_probes, list) {
- if (probe->probe_ops == probe_ops)
+ list_for_each_entry(iter, &tr->func_probes, list) {
+ if (iter->probe_ops == probe_ops) {
+ probe = iter;
break;
+ }
}
- if (&probe->list == &tr->func_probes) {
+ if (!probe) {
probe = kzalloc(sizeof(*probe), GFP_KERNEL);
if (!probe) {
mutex_unlock(&ftrace_lock);
@@ -4668,9 +4789,9 @@ int
unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
struct ftrace_probe_ops *probe_ops)
{
+ struct ftrace_func_probe *probe = NULL, *iter;
struct ftrace_ops_hash old_hash_ops;
struct ftrace_func_entry *entry;
- struct ftrace_func_probe *probe;
struct ftrace_glob func_g;
struct ftrace_hash **orig_hash;
struct ftrace_hash *old_hash;
@@ -4698,11 +4819,13 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
mutex_lock(&ftrace_lock);
/* Check if the probe_ops is already registered */
- list_for_each_entry(probe, &tr->func_probes, list) {
- if (probe->probe_ops == probe_ops)
+ list_for_each_entry(iter, &tr->func_probes, list) {
+ if (iter->probe_ops == probe_ops) {
+ probe = iter;
break;
+ }
}
- if (&probe->list == &tr->func_probes)
+ if (!probe)
goto err_unlock_ftrace;
ret = -EINVAL;
@@ -5161,8 +5284,6 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
goto out_unlock;
ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0);
- if (ret)
- remove_hash_entry(direct_functions, entry);
if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) {
ret = register_ftrace_function(&direct_ops);
@@ -5171,6 +5292,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
}
if (ret) {
+ remove_hash_entry(direct_functions, entry);
kfree(entry);
if (!direct->count) {
list_del_rcu(&direct->next);
@@ -6793,6 +6915,13 @@ void ftrace_module_enable(struct module *mod)
!within_module_init(rec->ip, mod))
break;
+ /* Weak functions should still be ignored */
+ if (!test_for_valid_rec(rec)) {
+ /* Clear all other flags. Should not be enabled anyway */
+ rec->flags = FTRACE_FL_DISABLED;
+ continue;
+ }
+
cnt = 0;
/*
@@ -6829,11 +6958,16 @@ void ftrace_module_enable(struct module *mod)
void ftrace_module_init(struct module *mod)
{
+ int ret;
+
if (ftrace_disabled || !mod->num_ftrace_callsites)
return;
- ftrace_process_locs(mod, mod->ftrace_callsites,
- mod->ftrace_callsites + mod->num_ftrace_callsites);
+ ret = ftrace_process_locs(mod, mod->ftrace_callsites,
+ mod->ftrace_callsites + mod->num_ftrace_callsites);
+ if (ret)
+ pr_warn("ftrace: failed to allocate entries for module '%s' functions\n",
+ mod->name);
}
static void save_ftrace_mod_rec(struct ftrace_mod_map *mod_map,
@@ -7166,15 +7300,19 @@ void __init ftrace_init(void)
pr_info("ftrace: allocating %ld entries in %ld pages\n",
count, count / ENTRIES_PER_PAGE + 1);
- last_ftrace_enabled = ftrace_enabled = 1;
-
ret = ftrace_process_locs(NULL,
__start_mcount_loc,
__stop_mcount_loc);
+ if (ret) {
+ pr_warn("ftrace: failed to allocate entries for functions\n");
+ goto failed;
+ }
pr_info("ftrace: allocated %ld pages with %ld groups\n",
ftrace_number_of_pages, ftrace_number_of_groups);
+ last_ftrace_enabled = ftrace_enabled = 1;
+
set_ftrace_early_filters();
return;
diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
index a2ef1d18126a..95106d02b32d 100644
--- a/kernel/trace/pid_list.c
+++ b/kernel/trace/pid_list.c
@@ -118,9 +118,9 @@ static inline unsigned int pid_join(unsigned int upper1,
/**
* trace_pid_list_is_set - test if the pid is set in the list
* @pid_list: The pid list to test
- * @pid: The pid to to see if set in the list.
+ * @pid: The pid to see if set in the list.
*
- * Tests if @pid is is set in the @pid_list. This is usually called
+ * Tests if @pid is set in the @pid_list. This is usually called
* from the scheduler when a task is scheduled. Its pid is checked
* if it should be traced or not.
*
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 05dfc7a12d3d..d59b6a328b7f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -29,6 +29,14 @@
#include <asm/local.h>
+/*
+ * The "absolute" timestamp in the buffer is only 59 bits.
+ * If a clock has the 5 MSBs set, it needs to be saved and
+ * reinserted.
+ */
+#define TS_MSB (0xf8ULL << 56)
+#define ABS_TS_MASK (~TS_MSB)
+
static void update_pages_handler(struct work_struct *work);
/*
@@ -468,6 +476,7 @@ struct rb_time_struct {
local_t cnt;
local_t top;
local_t bottom;
+ local_t msb;
};
#else
#include <asm/local64.h>
@@ -569,7 +578,6 @@ struct ring_buffer_iter {
* For the ring buffer, 64 bit required operations for the time is
* the following:
*
- * - Only need 59 bits (uses 60 to make it even).
* - Reads may fail if it interrupted a modification of the time stamp.
* It will succeed if it did not interrupt another write even if
* the read itself is interrupted by a write.
@@ -594,6 +602,7 @@ struct ring_buffer_iter {
*/
#define RB_TIME_SHIFT 30
#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
+#define RB_TIME_MSB_SHIFT 60
static inline int rb_time_cnt(unsigned long val)
{
@@ -613,7 +622,7 @@ static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
{
- unsigned long top, bottom;
+ unsigned long top, bottom, msb;
unsigned long c;
/*
@@ -625,6 +634,7 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
c = local_read(&t->cnt);
top = local_read(&t->top);
bottom = local_read(&t->bottom);
+ msb = local_read(&t->msb);
} while (c != local_read(&t->cnt));
*cnt = rb_time_cnt(top);
@@ -633,7 +643,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
if (*cnt != rb_time_cnt(bottom))
return false;
- *ret = rb_time_val(top, bottom);
+ /* The shift to msb will lose its cnt bits */
+ *ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT);
return true;
}
@@ -649,10 +660,12 @@ static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt
return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
}
-static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom)
+static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom,
+ unsigned long *msb)
{
*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
+ *msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT);
}
static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
@@ -663,15 +676,16 @@ static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long
static void rb_time_set(rb_time_t *t, u64 val)
{
- unsigned long cnt, top, bottom;
+ unsigned long cnt, top, bottom, msb;
- rb_time_split(val, &top, &bottom);
+ rb_time_split(val, &top, &bottom, &msb);
/* Writes always succeed with a valid number even if it gets interrupted. */
do {
cnt = local_inc_return(&t->cnt);
rb_time_val_set(&t->top, top, cnt);
rb_time_val_set(&t->bottom, bottom, cnt);
+ rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt);
} while (cnt != local_read(&t->cnt));
}
@@ -686,8 +700,8 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
{
- unsigned long cnt, top, bottom;
- unsigned long cnt2, top2, bottom2;
+ unsigned long cnt, top, bottom, msb;
+ unsigned long cnt2, top2, bottom2, msb2;
u64 val;
/* The cmpxchg always fails if it interrupted an update */
@@ -703,16 +717,18 @@ static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
cnt2 = cnt + 1;
- rb_time_split(val, &top, &bottom);
+ rb_time_split(val, &top, &bottom, &msb);
top = rb_time_val_cnt(top, cnt);
bottom = rb_time_val_cnt(bottom, cnt);
- rb_time_split(set, &top2, &bottom2);
+ rb_time_split(set, &top2, &bottom2, &msb2);
top2 = rb_time_val_cnt(top2, cnt2);
bottom2 = rb_time_val_cnt(bottom2, cnt2);
if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
return false;
+ if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
+ return false;
if (!rb_time_read_cmpxchg(&t->top, top, top2))
return false;
if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
@@ -783,6 +799,24 @@ static inline void verify_event(struct ring_buffer_per_cpu *cpu_buffer,
}
#endif
+/*
+ * The absolute time stamp drops the 5 MSBs and some clocks may
+ * require them. The rb_fix_abs_ts() will take a previous full
+ * time stamp, and add the 5 MSB of that time stamp on to the
+ * saved absolute time stamp. Then they are compared in case of
+ * the unlikely event that the latest time stamp incremented
+ * the 5 MSB.
+ */
+static inline u64 rb_fix_abs_ts(u64 abs, u64 save_ts)
+{
+ if (save_ts & TS_MSB) {
+ abs |= save_ts & TS_MSB;
+ /* Check for overflow */
+ if (unlikely(abs < save_ts))
+ abs += 1ULL << 59;
+ }
+ return abs;
+}
static inline u64 rb_time_stamp(struct trace_buffer *buffer);
@@ -811,8 +845,10 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
u64 ts;
/* If the event includes an absolute time, then just use that */
- if (event->type_len == RINGBUF_TYPE_TIME_STAMP)
- return rb_event_time_stamp(event);
+ if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
+ ts = rb_event_time_stamp(event);
+ return rb_fix_abs_ts(ts, cpu_buffer->tail_page->page->time_stamp);
+ }
nest = local_read(&cpu_buffer->committing);
verify_event(cpu_buffer, event);
@@ -2754,8 +2790,15 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE);
if (unlikely(info->delta > (1ULL << 59))) {
+ /*
+ * Some timers can use more than 59 bits, and when a timestamp
+ * is added to the buffer, it will lose those bits.
+ */
+ if (abs && (info->ts & TS_MSB)) {
+ info->delta &= ABS_TS_MASK;
+
/* did the clock go backwards */
- if (info->before == info->after && info->before > info->ts) {
+ } else if (info->before == info->after && info->before > info->ts) {
/* not interrupted */
static int once;
@@ -3304,7 +3347,7 @@ static void dump_buffer_page(struct buffer_data_page *bpage,
case RINGBUF_TYPE_TIME_STAMP:
delta = rb_event_time_stamp(event);
- ts = delta;
+ ts = rb_fix_abs_ts(delta, ts);
pr_warn(" [%lld] absolute:%lld TIME STAMP\n", ts, delta);
break;
@@ -3380,7 +3423,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
case RINGBUF_TYPE_TIME_STAMP:
delta = rb_event_time_stamp(event);
- ts = delta;
+ ts = rb_fix_abs_ts(delta, ts);
break;
case RINGBUF_TYPE_PADDING:
@@ -4367,6 +4410,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
case RINGBUF_TYPE_TIME_STAMP:
delta = rb_event_time_stamp(event);
+ delta = rb_fix_abs_ts(delta, cpu_buffer->read_stamp);
cpu_buffer->read_stamp = delta;
return;
@@ -4397,6 +4441,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
case RINGBUF_TYPE_TIME_STAMP:
delta = rb_event_time_stamp(event);
+ delta = rb_fix_abs_ts(delta, iter->read_stamp);
iter->read_stamp = delta;
return;
@@ -4650,6 +4695,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
case RINGBUF_TYPE_TIME_STAMP:
if (ts) {
*ts = rb_event_time_stamp(event);
+ *ts = rb_fix_abs_ts(*ts, reader->page->time_stamp);
ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
cpu_buffer->cpu, ts);
}
@@ -4741,6 +4787,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
case RINGBUF_TYPE_TIME_STAMP:
if (ts) {
*ts = rb_event_time_stamp(event);
+ *ts = rb_fix_abs_ts(*ts, iter->head_page->page->time_stamp);
ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
cpu_buffer->cpu, ts);
}
@@ -6011,10 +6058,10 @@ static __init int test_ringbuffer(void)
pr_info(" total events: %ld\n", total_lost + total_read);
pr_info(" recorded len bytes: %ld\n", total_len);
pr_info(" recorded size bytes: %ld\n", total_size);
- if (total_lost)
+ if (total_lost) {
pr_info(" With dropped events, record len and size may not match\n"
" alloced and written from above\n");
- if (!total_lost) {
+ } else {
if (RB_WARN_ON(buffer, total_len != total_alloc ||
total_size != total_written))
break;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 124f1897fd56..2c95992e2c71 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -721,13 +721,16 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
pos = 0;
ret = trace_get_user(&parser, ubuf, cnt, &pos);
- if (ret < 0 || !trace_parser_loaded(&parser))
+ if (ret < 0)
break;
read += ret;
ubuf += ret;
cnt -= ret;
+ if (!trace_parser_loaded(&parser))
+ break;
+
ret = -EINVAL;
if (kstrtoul(parser.buffer, 0, &val))
break;
@@ -753,7 +756,6 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
if (!nr_pids) {
/* Cleared the list of pids */
trace_pid_list_free(pid_list);
- read = ret;
pid_list = NULL;
}
@@ -1174,7 +1176,7 @@ void tracing_snapshot_cond(struct trace_array *tr, void *cond_data)
EXPORT_SYMBOL_GPL(tracing_snapshot_cond);
/**
- * tracing_snapshot_cond_data - get the user data associated with a snapshot
+ * tracing_cond_snapshot_data - get the user data associated with a snapshot
* @tr: The tracing instance
*
* When the user enables a conditional snapshot using
@@ -1542,6 +1544,7 @@ static struct {
{ ktime_get_mono_fast_ns, "mono", 1 },
{ ktime_get_raw_fast_ns, "mono_raw", 1 },
{ ktime_get_boot_fast_ns, "boot", 1 },
+ { ktime_get_tai_fast_ns, "tai", 1 },
ARCH_TRACE_CLOCKS
};
@@ -2835,7 +2838,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
}
EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
-static DEFINE_SPINLOCK(tracepoint_iter_lock);
+static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock);
static DEFINE_MUTEX(tracepoint_printk_mutex);
static void output_printk(struct trace_event_buffer *fbuffer)
@@ -2863,14 +2866,14 @@ static void output_printk(struct trace_event_buffer *fbuffer)
event = &fbuffer->trace_file->event_call->event;
- spin_lock_irqsave(&tracepoint_iter_lock, flags);
+ raw_spin_lock_irqsave(&tracepoint_iter_lock, flags);
trace_seq_init(&iter->seq);
iter->ent = fbuffer->entry;
event_call->event.funcs->trace(iter, 0, event);
trace_seq_putc(&iter->seq, 0);
printk("%s", iter->seq.buffer);
- spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
+ raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
}
int tracepoint_printk_sysctl(struct ctl_table *table, int write,
@@ -4249,7 +4252,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file
unsigned int flags)
{
bool tgid = flags & TRACE_ITER_RECORD_TGID;
- const char *space = " ";
+ static const char space[] = " ";
int prec = tgid ? 12 : 2;
print_event_info(buf, m);
@@ -4273,9 +4276,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
struct tracer *type = iter->trace;
unsigned long entries;
unsigned long total;
- const char *name = "preemption";
-
- name = type->name;
+ const char *name = type->name;
get_total_entries(buf, &total, &entries);
@@ -5469,7 +5470,7 @@ static const char readme_msg[] =
" error_log\t- error log for failed commands (that support it)\n"
" buffer_size_kb\t- view and modify size of per cpu buffer\n"
" buffer_total_size_kb - view total size of all cpu buffers\n\n"
- " trace_clock\t\t-change the clock used to order events\n"
+ " trace_clock\t\t- change the clock used to order events\n"
" local: Per cpu clock but may not be synced across CPUs\n"
" global: Synced across CPUs but slows tracing down.\n"
" counter: Not a clock, but just an increment\n"
@@ -5478,7 +5479,7 @@ static const char readme_msg[] =
#ifdef CONFIG_X86_64
" x86-tsc: TSC cycle counter\n"
#endif
- "\n timestamp_mode\t-view the mode used to timestamp events\n"
+ "\n timestamp_mode\t- view the mode used to timestamp events\n"
" delta: Delta difference against a buffer-wide timestamp\n"
" absolute: Absolute (standalone) timestamp\n"
"\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n"
@@ -6326,12 +6327,18 @@ static void tracing_set_nop(struct trace_array *tr)
tr->current_trace = &nop_trace;
}
+static bool tracer_options_updated;
+
static void add_tracer_options(struct trace_array *tr, struct tracer *t)
{
/* Only enable if the directory has been created already. */
if (!tr->dir)
return;
+ /* Only create trace option files after update_tracer_options finish */
+ if (!tracer_options_updated)
+ return;
+
create_trace_option_files(tr, t);
}
@@ -6448,7 +6455,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
{
struct trace_array *tr = filp->private_data;
char buf[MAX_TRACER_SIZE+1];
- int i;
+ char *name;
size_t ret;
int err;
@@ -6462,11 +6469,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
buf[cnt] = 0;
- /* strip ending whitespace. */
- for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
- buf[i] = 0;
+ name = strim(buf);
- err = tracing_set_tracer(tr, buf);
+ err = tracing_set_tracer(tr, name);
if (err)
return err;
@@ -9170,6 +9175,7 @@ static void __update_tracer_options(struct trace_array *tr)
static void update_tracer_options(struct trace_array *tr)
{
mutex_lock(&trace_types_lock);
+ tracer_options_updated = true;
__update_tracer_options(tr);
mutex_unlock(&trace_types_lock);
}
@@ -9602,6 +9608,7 @@ extern struct trace_eval_map *__stop_ftrace_eval_maps[];
static struct workqueue_struct *eval_map_wq __initdata;
static struct work_struct eval_map_work __initdata;
+static struct work_struct tracerfs_init_work __initdata;
static void __init eval_map_work_func(struct work_struct *work)
{
@@ -9627,6 +9634,8 @@ static int __init trace_eval_init(void)
return 0;
}
+subsys_initcall(trace_eval_init);
+
static int __init trace_eval_sync(void)
{
/* Make sure the eval map updates are finished */
@@ -9709,15 +9718,8 @@ static struct notifier_block trace_module_nb = {
};
#endif /* CONFIG_MODULES */
-static __init int tracer_init_tracefs(void)
+static __init void tracer_init_tracefs_work_func(struct work_struct *work)
{
- int ret;
-
- trace_access_lock_init();
-
- ret = tracing_init_dentry();
- if (ret)
- return 0;
event_trace_init();
@@ -9739,8 +9741,6 @@ static __init int tracer_init_tracefs(void)
trace_create_file("saved_tgids", TRACE_MODE_READ, NULL,
NULL, &tracing_saved_tgids_fops);
- trace_eval_init();
-
trace_create_eval_file(NULL);
#ifdef CONFIG_MODULES
@@ -9755,6 +9755,24 @@ static __init int tracer_init_tracefs(void)
create_trace_instances(NULL);
update_tracer_options(&global_trace);
+}
+
+static __init int tracer_init_tracefs(void)
+{
+ int ret;
+
+ trace_access_lock_init();
+
+ ret = tracing_init_dentry();
+ if (ret)
+ return 0;
+
+ if (eval_map_wq) {
+ INIT_WORK(&tracerfs_init_work, tracer_init_tracefs_work_func);
+ queue_work(eval_map_wq, &tracerfs_init_work);
+ } else {
+ tracer_init_tracefs_work_func(NULL);
+ }
return 0;
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 07d990270e2a..ff816fb41e48 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1573,13 +1573,12 @@ struct enable_trigger_data {
};
extern int event_enable_trigger_print(struct seq_file *m,
- struct event_trigger_ops *ops,
- struct event_trigger_data *data);
-extern void event_enable_trigger_free(struct event_trigger_ops *ops,
struct event_trigger_data *data);
+extern void event_enable_trigger_free(struct event_trigger_data *data);
extern int event_enable_trigger_parse(struct event_command *cmd_ops,
struct trace_event_file *file,
- char *glob, char *cmd, char *param);
+ char *glob, char *cmd,
+ char *param_and_filter);
extern int event_enable_register_trigger(char *glob,
struct event_trigger_data *data,
struct trace_event_file *file);
@@ -1587,8 +1586,7 @@ extern void event_enable_unregister_trigger(char *glob,
struct event_trigger_data *test,
struct trace_event_file *file);
extern void trigger_data_free(struct event_trigger_data *data);
-extern int event_trigger_init(struct event_trigger_ops *ops,
- struct event_trigger_data *data);
+extern int event_trigger_init(struct event_trigger_data *data);
extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
int trigger_enable);
extern void update_cond_flag(struct trace_event_file *file);
@@ -1629,10 +1627,11 @@ extern void event_trigger_reset_filter(struct event_command *cmd_ops,
extern int event_trigger_register(struct event_command *cmd_ops,
struct trace_event_file *file,
char *glob,
- char *cmd,
- char *trigger,
- struct event_trigger_data *trigger_data,
- int *n_registered);
+ struct event_trigger_data *trigger_data);
+extern void event_trigger_unregister(struct event_command *cmd_ops,
+ struct trace_event_file *file,
+ char *glob,
+ struct event_trigger_data *trigger_data);
/**
* struct event_trigger_ops - callbacks for trace event triggers
@@ -1686,12 +1685,9 @@ struct event_trigger_ops {
struct trace_buffer *buffer,
void *rec,
struct ring_buffer_event *rbe);
- int (*init)(struct event_trigger_ops *ops,
- struct event_trigger_data *data);
- void (*free)(struct event_trigger_ops *ops,
- struct event_trigger_data *data);
+ int (*init)(struct event_trigger_data *data);
+ void (*free)(struct event_trigger_data *data);
int (*print)(struct seq_file *m,
- struct event_trigger_ops *ops,
struct event_trigger_data *data);
};
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 0580287d7a0d..778200dd8ede 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -300,7 +300,7 @@ trace_boot_hist_add_handlers(struct xbc_node *hnode, char **bufp,
{
struct xbc_node *node;
const char *p, *handler;
- int ret;
+ int ret = 0;
handler = xbc_node_get_data(hnode);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index e34e8182ee4b..076b447a1b88 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -255,19 +255,14 @@ static const struct file_operations dynamic_events_ops = {
/* Make a tracefs interface for controlling dynamic events */
static __init int init_dynamic_event(void)
{
- struct dentry *entry;
int ret;
ret = tracing_init_dentry();
if (ret)
return 0;
- entry = tracefs_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
- NULL, &dynamic_events_ops);
-
- /* Event list interface */
- if (!entry)
- pr_warn("Could not create tracefs 'dynamic_events' entry\n");
+ trace_create_file("dynamic_events", TRACE_MODE_WRITE, NULL,
+ NULL, &dynamic_events_ops);
return 0;
}
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 541aa13581b9..7d4478525c66 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -511,20 +511,17 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
* functions are just stubs to fulfill what is needed to use the trigger
* infrastructure.
*/
-static int eprobe_trigger_init(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+static int eprobe_trigger_init(struct event_trigger_data *data)
{
return 0;
}
-static void eprobe_trigger_free(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+static void eprobe_trigger_free(struct event_trigger_data *data)
{
}
static int eprobe_trigger_print(struct seq_file *m,
- struct event_trigger_ops *ops,
struct event_trigger_data *data)
{
/* Do not print eprobe event triggers */
@@ -549,7 +546,8 @@ static struct event_trigger_ops eprobe_trigger_ops = {
static int eprobe_trigger_cmd_parse(struct event_command *cmd_ops,
struct trace_event_file *file,
- char *glob, char *cmd, char *param)
+ char *glob, char *cmd,
+ char *param_and_filter)
{
return -1;
}
@@ -650,7 +648,7 @@ static struct trace_event_functions eprobe_funcs = {
static int disable_eprobe(struct trace_eprobe *ep,
struct trace_array *tr)
{
- struct event_trigger_data *trigger;
+ struct event_trigger_data *trigger = NULL, *iter;
struct trace_event_file *file;
struct eprobe_data *edata;
@@ -658,14 +656,16 @@ static int disable_eprobe(struct trace_eprobe *ep,
if (!file)
return -ENOENT;
- list_for_each_entry(trigger, &file->triggers, list) {
- if (!(trigger->flags & EVENT_TRIGGER_FL_PROBE))
+ list_for_each_entry(iter, &file->triggers, list) {
+ if (!(iter->flags & EVENT_TRIGGER_FL_PROBE))
continue;
- edata = trigger->private_data;
- if (edata->ep == ep)
+ edata = iter->private_data;
+ if (edata->ep == ep) {
+ trigger = iter;
break;
+ }
}
- if (list_entry_is_head(trigger, &file->triggers, list))
+ if (!trigger)
return -ENODEV;
list_del_rcu(&trigger->list);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f97de82d1342..181f08186d32 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -392,12 +392,6 @@ static void test_event_printk(struct trace_event_call *call)
if (!(dereference_flags & (1ULL << arg)))
goto next_arg;
- /* Check for __get_sockaddr */;
- if (str_has_prefix(fmt + i, "__get_sockaddr(")) {
- dereference_flags &= ~(1ULL << arg);
- goto next_arg;
- }
-
/* Find the REC-> in the argument */
c = strchr(fmt + i, ',');
r = strstr(fmt + i, "REC->");
@@ -413,7 +407,14 @@ static void test_event_printk(struct trace_event_call *call)
a = strchr(fmt + i, '&');
if ((a && (a < r)) || test_field(r, call))
dereference_flags &= ~(1ULL << arg);
+ } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) &&
+ (!c || r < c)) {
+ dereference_flags &= ~(1ULL << arg);
+ } else if ((r = strstr(fmt + i, "__get_sockaddr(")) &&
+ (!c || r < c)) {
+ dereference_flags &= ~(1ULL << arg);
}
+
next_arg:
i--;
arg++;
@@ -1723,9 +1724,9 @@ static LIST_HEAD(event_subsystems);
static int subsystem_open(struct inode *inode, struct file *filp)
{
+ struct trace_subsystem_dir *dir = NULL, *iter_dir;
+ struct trace_array *tr = NULL, *iter_tr;
struct event_subsystem *system = NULL;
- struct trace_subsystem_dir *dir = NULL; /* Initialize for gcc */
- struct trace_array *tr;
int ret;
if (tracing_is_disabled())
@@ -1734,10 +1735,12 @@ static int subsystem_open(struct inode *inode, struct file *filp)
/* Make sure the system still exists */
mutex_lock(&event_mutex);
mutex_lock(&trace_types_lock);
- list_for_each_entry(tr, &ftrace_trace_arrays, list) {
- list_for_each_entry(dir, &tr->systems, list) {
- if (dir == inode->i_private) {
+ list_for_each_entry(iter_tr, &ftrace_trace_arrays, list) {
+ list_for_each_entry(iter_dir, &iter_tr->systems, list) {
+ if (iter_dir == inode->i_private) {
/* Don't open systems with no events */
+ tr = iter_tr;
+ dir = iter_dir;
if (dir->nr_events) {
__get_system_dir(dir);
system = dir->subsystem;
@@ -1753,9 +1756,6 @@ static int subsystem_open(struct inode *inode, struct file *filp)
if (!system)
return -ENODEV;
- /* Some versions of gcc think dir can be uninitialized here */
- WARN_ON(!dir);
-
/* Still need to increment the ref count of the system */
if (trace_array_get(tr) < 0) {
put_system(dir);
@@ -2280,8 +2280,8 @@ static struct dentry *
event_subsystem_dir(struct trace_array *tr, const char *name,
struct trace_event_file *file, struct dentry *parent)
{
+ struct event_subsystem *system, *iter;
struct trace_subsystem_dir *dir;
- struct event_subsystem *system;
struct dentry *entry;
/* First see if we did not already create this dir */
@@ -2295,13 +2295,13 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
}
/* Now see if the system itself exists. */
- list_for_each_entry(system, &event_subsystems, list) {
- if (strcmp(system->name, name) == 0)
+ system = NULL;
+ list_for_each_entry(iter, &event_subsystems, list) {
+ if (strcmp(iter->name, name) == 0) {
+ system = iter;
break;
+ }
}
- /* Reset system variable when not found */
- if (&system->list == &event_subsystems)
- system = NULL;
dir = kmalloc(sizeof(*dir), GFP_KERNEL);
if (!dir)
@@ -3546,12 +3546,10 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
struct dentry *d_events;
struct dentry *entry;
- entry = tracefs_create_file("set_event", TRACE_MODE_WRITE, parent,
- tr, &ftrace_set_event_fops);
- if (!entry) {
- pr_warn("Could not create tracefs 'set_event' entry\n");
+ entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent,
+ tr, &ftrace_set_event_fops);
+ if (!entry)
return -ENOMEM;
- }
d_events = tracefs_create_dir("events", parent);
if (!d_events) {
@@ -3566,16 +3564,12 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
/* There are not as crucial, just warn if they are not created */
- entry = tracefs_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
- tr, &ftrace_set_event_pid_fops);
- if (!entry)
- pr_warn("Could not create tracefs 'set_event_pid' entry\n");
+ trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent,
+ tr, &ftrace_set_event_pid_fops);
- entry = tracefs_create_file("set_event_notrace_pid",
- TRACE_MODE_WRITE, parent, tr,
- &ftrace_set_event_notrace_pid_fops);
- if (!entry)
- pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n");
+ trace_create_file("set_event_notrace_pid",
+ TRACE_MODE_WRITE, parent, tr,
+ &ftrace_set_event_notrace_pid_fops);
/* ring buffer internal formats */
trace_create_file("header_page", TRACE_MODE_READ, d_events,
@@ -3790,17 +3784,14 @@ static __init int event_trace_init_fields(void)
__init int event_trace_init(void)
{
struct trace_array *tr;
- struct dentry *entry;
int ret;
tr = top_trace_array();
if (!tr)
return -ENODEV;
- entry = tracefs_create_file("available_events", TRACE_MODE_READ,
- NULL, tr, &ftrace_avail_fops);
- if (!entry)
- pr_warn("Could not create tracefs 'available_events' entry\n");
+ trace_create_file("available_events", TRACE_MODE_READ,
+ NULL, tr, &ftrace_avail_fops);
ret = early_event_add_tracer(NULL, tr);
if (ret)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index b458a9afa2c0..4b1057ab9d96 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1816,7 +1816,7 @@ static void create_filter_finish(struct filter_parse_error *pe)
* create_filter - create a filter for a trace_event_call
* @tr: the trace array associated with these events
* @call: trace_event_call to create a filter for
- * @filter_str: filter string
+ * @filter_string: filter string
* @set_str: remember @filter_str and enable detailed error in filter
* @filterp: out param for created filter (always updated on return)
* Must be a pointer that references a NULL pointer.
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 44db5ba9cabb..48e82e141d54 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2093,8 +2093,11 @@ static int init_var_ref(struct hist_field *ref_field,
return err;
free:
kfree(ref_field->system);
+ ref_field->system = NULL;
kfree(ref_field->event_name);
+ ref_field->event_name = NULL;
kfree(ref_field->name);
+ ref_field->name = NULL;
goto out;
}
@@ -2785,7 +2788,8 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data,
static struct event_command trigger_hist_cmd;
static int event_hist_trigger_parse(struct event_command *cmd_ops,
struct trace_event_file *file,
- char *glob, char *cmd, char *param);
+ char *glob, char *cmd,
+ char *param_and_filter);
static bool compatible_keys(struct hist_trigger_data *target_hist_data,
struct hist_trigger_data *hist_data,
@@ -4161,7 +4165,7 @@ static int create_val_field(struct hist_trigger_data *hist_data,
return __create_val_field(hist_data, val_idx, file, NULL, field_str, 0);
}
-static const char *no_comm = "(no comm)";
+static const char no_comm[] = "(no comm)";
static u64 hist_field_execname(struct hist_field *hist_field,
struct tracing_map_elt *elt,
@@ -5252,7 +5256,7 @@ static void hist_trigger_show(struct seq_file *m,
seq_puts(m, "\n\n");
seq_puts(m, "# event histogram\n#\n# trigger info: ");
- data->ops->print(m, data->ops, data);
+ data->ops->print(m, data);
seq_puts(m, "#\n\n");
hist_data = data->private_data;
@@ -5484,7 +5488,7 @@ static void hist_trigger_debug_show(struct seq_file *m,
seq_puts(m, "\n\n");
seq_puts(m, "# event histogram\n#\n# trigger info: ");
- data->ops->print(m, data->ops, data);
+ data->ops->print(m, data);
seq_puts(m, "#\n\n");
hist_data = data->private_data;
@@ -5621,7 +5625,6 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
}
static int event_hist_trigger_print(struct seq_file *m,
- struct event_trigger_ops *ops,
struct event_trigger_data *data)
{
struct hist_trigger_data *hist_data = data->private_data;
@@ -5729,8 +5732,7 @@ static int event_hist_trigger_print(struct seq_file *m,
return 0;
}
-static int event_hist_trigger_init(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+static int event_hist_trigger_init(struct event_trigger_data *data)
{
struct hist_trigger_data *hist_data = data->private_data;
@@ -5758,8 +5760,7 @@ static void unregister_field_var_hists(struct hist_trigger_data *hist_data)
}
}
-static void event_hist_trigger_free(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+static void event_hist_trigger_free(struct event_trigger_data *data)
{
struct hist_trigger_data *hist_data = data->private_data;
@@ -5788,25 +5789,23 @@ static struct event_trigger_ops event_hist_trigger_ops = {
.free = event_hist_trigger_free,
};
-static int event_hist_trigger_named_init(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+static int event_hist_trigger_named_init(struct event_trigger_data *data)
{
data->ref++;
save_named_trigger(data->named_data->name, data);
- event_hist_trigger_init(ops, data->named_data);
+ event_hist_trigger_init(data->named_data);
return 0;
}
-static void event_hist_trigger_named_free(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+static void event_hist_trigger_named_free(struct event_trigger_data *data)
{
if (WARN_ON_ONCE(data->ref <= 0))
return;
- event_hist_trigger_free(ops, data->named_data);
+ event_hist_trigger_free(data->named_data);
data->ref--;
if (!data->ref) {
@@ -5933,6 +5932,48 @@ static bool hist_trigger_match(struct event_trigger_data *data,
return true;
}
+static bool existing_hist_update_only(char *glob,
+ struct event_trigger_data *data,
+ struct trace_event_file *file)
+{
+ struct hist_trigger_data *hist_data = data->private_data;
+ struct event_trigger_data *test, *named_data = NULL;
+ bool updated = false;
+
+ if (!hist_data->attrs->pause && !hist_data->attrs->cont &&
+ !hist_data->attrs->clear)
+ goto out;
+
+ if (hist_data->attrs->name) {
+ named_data = find_named_trigger(hist_data->attrs->name);
+ if (named_data) {
+ if (!hist_trigger_match(data, named_data, named_data,
+ true))
+ goto out;
+ }
+ }
+
+ if (hist_data->attrs->name && !named_data)
+ goto out;
+
+ list_for_each_entry(test, &file->triggers, list) {
+ if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+ if (!hist_trigger_match(data, test, named_data, false))
+ continue;
+ if (hist_data->attrs->pause)
+ test->paused = true;
+ else if (hist_data->attrs->cont)
+ test->paused = false;
+ else if (hist_data->attrs->clear)
+ hist_clear(test);
+ updated = true;
+ goto out;
+ }
+ }
+ out:
+ return updated;
+}
+
static int hist_register_trigger(char *glob,
struct event_trigger_data *data,
struct trace_event_file *file)
@@ -5961,19 +6002,11 @@ static int hist_register_trigger(char *glob,
list_for_each_entry(test, &file->triggers, list) {
if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
- if (!hist_trigger_match(data, test, named_data, false))
- continue;
- if (hist_data->attrs->pause)
- test->paused = true;
- else if (hist_data->attrs->cont)
- test->paused = false;
- else if (hist_data->attrs->clear)
- hist_clear(test);
- else {
+ if (hist_trigger_match(data, test, named_data, false)) {
hist_err(tr, HIST_ERR_TRIGGER_EEXIST, 0);
ret = -EEXIST;
+ goto out;
}
- goto out;
}
}
new:
@@ -5993,7 +6026,7 @@ static int hist_register_trigger(char *glob,
}
if (data->ops->init) {
- ret = data->ops->init(data->ops, data);
+ ret = data->ops->init(data);
if (ret < 0)
goto out;
}
@@ -6012,8 +6045,6 @@ static int hist_register_trigger(char *glob,
if (named_data)
destroy_hist_data(hist_data);
-
- ret++;
out:
return ret;
}
@@ -6089,20 +6120,19 @@ static void hist_unregister_trigger(char *glob,
struct event_trigger_data *data,
struct trace_event_file *file)
{
+ struct event_trigger_data *test = NULL, *iter, *named_data = NULL;
struct hist_trigger_data *hist_data = data->private_data;
- struct event_trigger_data *test, *named_data = NULL;
- bool unregistered = false;
lockdep_assert_held(&event_mutex);
if (hist_data->attrs->name)
named_data = find_named_trigger(hist_data->attrs->name);
- list_for_each_entry(test, &file->triggers, list) {
- if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
- if (!hist_trigger_match(data, test, named_data, false))
+ list_for_each_entry(iter, &file->triggers, list) {
+ if (iter->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+ if (!hist_trigger_match(data, iter, named_data, false))
continue;
- unregistered = true;
+ test = iter;
list_del_rcu(&test->list);
trace_event_trigger_enable_disable(file, 0);
update_cond_flag(file);
@@ -6110,11 +6140,11 @@ static void hist_unregister_trigger(char *glob,
}
}
- if (unregistered && test->ops->free)
- test->ops->free(test->ops, test);
+ if (test && test->ops->free)
+ test->ops->free(test);
if (hist_data->enable_timestamps) {
- if (!hist_data->remove || unregistered)
+ if (!hist_data->remove || test)
tracing_set_filter_buffering(file->tr, false);
}
}
@@ -6164,57 +6194,57 @@ static void hist_unreg_all(struct trace_event_file *file)
if (hist_data->enable_timestamps)
tracing_set_filter_buffering(file->tr, false);
if (test->ops->free)
- test->ops->free(test->ops, test);
+ test->ops->free(test);
}
}
}
static int event_hist_trigger_parse(struct event_command *cmd_ops,
struct trace_event_file *file,
- char *glob, char *cmd, char *param)
+ char *glob, char *cmd,
+ char *param_and_filter)
{
unsigned int hist_trigger_bits = TRACING_MAP_BITS_DEFAULT;
struct event_trigger_data *trigger_data;
struct hist_trigger_attrs *attrs;
- struct event_trigger_ops *trigger_ops;
struct hist_trigger_data *hist_data;
+ char *param, *filter, *p, *start;
struct synth_event *se;
const char *se_name;
- bool remove = false;
- char *trigger, *p, *start;
+ bool remove;
int ret = 0;
lockdep_assert_held(&event_mutex);
- WARN_ON(!glob);
+ if (WARN_ON(!glob))
+ return -EINVAL;
- if (strlen(glob)) {
+ if (glob[0]) {
hist_err_clear();
- last_cmd_set(file, param);
+ last_cmd_set(file, param_and_filter);
}
- if (!param)
- return -EINVAL;
+ remove = event_trigger_check_remove(glob);
- if (glob[0] == '!')
- remove = true;
+ if (event_trigger_empty_param(param_and_filter))
+ return -EINVAL;
/*
* separate the trigger from the filter (k:v [if filter])
* allowing for whitespace in the trigger
*/
- p = trigger = param;
+ p = param = param_and_filter;
do {
p = strstr(p, "if");
if (!p)
break;
- if (p == param)
+ if (p == param_and_filter)
return -EINVAL;
if (*(p - 1) != ' ' && *(p - 1) != '\t') {
p++;
continue;
}
- if (p >= param + strlen(param) - (sizeof("if") - 1) - 1)
+ if (p >= param_and_filter + strlen(param_and_filter) - (sizeof("if") - 1) - 1)
return -EINVAL;
if (*(p + sizeof("if") - 1) != ' ' && *(p + sizeof("if") - 1) != '\t') {
p++;
@@ -6224,24 +6254,24 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
} while (1);
if (!p)
- param = NULL;
+ filter = NULL;
else {
*(p - 1) = '\0';
- param = strstrip(p);
- trigger = strstrip(trigger);
+ filter = strstrip(p);
+ param = strstrip(param);
}
/*
* To simplify arithmetic expression parsing, replace occurrences of
* '.sym-offset' modifier with '.symXoffset'
*/
- start = strstr(trigger, ".sym-offset");
+ start = strstr(param, ".sym-offset");
while (start) {
*(start + 4) = 'X';
start = strstr(start + 11, ".sym-offset");
}
- attrs = parse_hist_trigger_attrs(file->tr, trigger);
+ attrs = parse_hist_trigger_attrs(file->tr, param);
if (IS_ERR(attrs))
return PTR_ERR(attrs);
@@ -6254,29 +6284,15 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
return PTR_ERR(hist_data);
}
- trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
-
- trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ trigger_data = event_trigger_alloc(cmd_ops, cmd, param, hist_data);
if (!trigger_data) {
ret = -ENOMEM;
goto out_free;
}
- trigger_data->count = -1;
- trigger_data->ops = trigger_ops;
- trigger_data->cmd_ops = cmd_ops;
-
- INIT_LIST_HEAD(&trigger_data->list);
- RCU_INIT_POINTER(trigger_data->filter, NULL);
-
- trigger_data->private_data = hist_data;
-
- /* if param is non-empty, it's supposed to be a filter */
- if (param && cmd_ops->set_filter) {
- ret = cmd_ops->set_filter(param, trigger_data, file);
- if (ret < 0)
- goto out_free;
- }
+ ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
+ if (ret < 0)
+ goto out_free;
if (remove) {
if (!have_hist_trigger_match(trigger_data, file))
@@ -6287,7 +6303,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
goto out_free;
}
- cmd_ops->unreg(glob+1, trigger_data, file);
+ event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
se_name = trace_event_name(file->event_call);
se = find_synth_event(se_name);
if (se)
@@ -6296,17 +6312,11 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
goto out_free;
}
- ret = cmd_ops->reg(glob, trigger_data, file);
- /*
- * The above returns on success the # of triggers registered,
- * but if it didn't register any it returns zero. Consider no
- * triggers registered a failure too.
- */
- if (!ret) {
- if (!(attrs->pause || attrs->cont || attrs->clear))
- ret = -ENOENT;
+ if (existing_hist_update_only(glob, trigger_data, file))
goto out_free;
- } else if (ret < 0)
+
+ ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+ if (ret < 0)
goto out_free;
if (get_named_trigger_data(trigger_data))
@@ -6331,18 +6341,15 @@ enable:
se = find_synth_event(se_name);
if (se)
se->ref++;
- /* Just return zero, not the number of registered triggers */
- ret = 0;
out:
if (ret == 0)
hist_err_clear();
return ret;
out_unreg:
- cmd_ops->unreg(glob+1, trigger_data, file);
+ event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
out_free:
- if (cmd_ops->set_filter)
- cmd_ops->set_filter(NULL, trigger_data, NULL);
+ event_trigger_reset_filter(cmd_ops, trigger_data);
remove_hist_vars(hist_data);
@@ -6463,7 +6470,7 @@ static void hist_enable_unreg_all(struct trace_event_file *file)
update_cond_flag(file);
trace_event_trigger_enable_disable(file, 0);
if (test->ops->free)
- test->ops->free(test->ops, test);
+ test->ops->free(test);
}
}
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 7eb9d04f1c2e..cb866c3141af 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -188,7 +188,7 @@ static int trigger_show(struct seq_file *m, void *v)
}
data = list_entry(v, struct event_trigger_data, list);
- data->ops->print(m, data->ops, data);
+ data->ops->print(m, data);
return 0;
}
@@ -432,7 +432,6 @@ event_trigger_print(const char *name, struct seq_file *m,
/**
* event_trigger_init - Generic event_trigger_ops @init implementation
- * @ops: The trigger ops associated with the trigger
* @data: Trigger-specific data
*
* Common implementation of event trigger initialization.
@@ -442,8 +441,7 @@ event_trigger_print(const char *name, struct seq_file *m,
*
* Return: 0 on success, errno otherwise
*/
-int event_trigger_init(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+int event_trigger_init(struct event_trigger_data *data)
{
data->ref++;
return 0;
@@ -451,7 +449,6 @@ int event_trigger_init(struct event_trigger_ops *ops,
/**
* event_trigger_free - Generic event_trigger_ops @free implementation
- * @ops: The trigger ops associated with the trigger
* @data: Trigger-specific data
*
* Common implementation of event trigger de-initialization.
@@ -460,8 +457,7 @@ int event_trigger_init(struct event_trigger_ops *ops,
* implementations.
*/
static void
-event_trigger_free(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+event_trigger_free(struct event_trigger_data *data)
{
if (WARN_ON_ONCE(data->ref <= 0))
return;
@@ -515,7 +511,7 @@ clear_event_triggers(struct trace_array *tr)
trace_event_trigger_enable_disable(file, 0);
list_del_rcu(&data->list);
if (data->ops->free)
- data->ops->free(data->ops, data);
+ data->ops->free(data);
}
}
}
@@ -581,19 +577,18 @@ static int register_trigger(char *glob,
}
if (data->ops->init) {
- ret = data->ops->init(data->ops, data);
+ ret = data->ops->init(data);
if (ret < 0)
goto out;
}
list_add_rcu(&data->list, &file->triggers);
- ret++;
update_cond_flag(file);
- if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ ret = trace_event_trigger_enable_disable(file, 1);
+ if (ret < 0) {
list_del_rcu(&data->list);
update_cond_flag(file);
- ret--;
}
out:
return ret;
@@ -614,14 +609,13 @@ static void unregister_trigger(char *glob,
struct event_trigger_data *test,
struct trace_event_file *file)
{
- struct event_trigger_data *data;
- bool unregistered = false;
+ struct event_trigger_data *data = NULL, *iter;
lockdep_assert_held(&event_mutex);
- list_for_each_entry(data, &file->triggers, list) {
- if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
- unregistered = true;
+ list_for_each_entry(iter, &file->triggers, list) {
+ if (iter->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
+ data = iter;
list_del_rcu(&data->list);
trace_event_trigger_enable_disable(file, 0);
update_cond_flag(file);
@@ -629,8 +623,8 @@ static void unregister_trigger(char *glob,
}
}
- if (unregistered && data->ops->free)
- data->ops->free(data->ops, data);
+ if (data && data->ops->free)
+ data->ops->free(data);
}
/*
@@ -744,15 +738,15 @@ bool event_trigger_empty_param(const char *param)
/**
* event_trigger_separate_filter - separate an event trigger from a filter
- * @param: The param string containing trigger and possibly filter
- * @trigger: outparam, will be filled with a pointer to the trigger
+ * @param_and_filter: String containing trigger and possibly filter
+ * @param: outparam, will be filled with a pointer to the trigger
* @filter: outparam, will be filled with a pointer to the filter
* @param_required: Specifies whether or not the param string is required
*
* Given a param string of the form '[trigger] [if filter]', this
* function separates the filter from the trigger and returns the
- * trigger in *trigger and the filter in *filter. Either the *trigger
- * or the *filter may be set to NULL by this function - if not set to
+ * trigger in @param and the filter in @filter. Either the @param
+ * or the @filter may be set to NULL by this function - if not set to
* NULL, they will contain strings corresponding to the trigger and
* filter.
*
@@ -927,48 +921,37 @@ void event_trigger_reset_filter(struct event_command *cmd_ops,
* @cmd_ops: The event_command operations for the trigger
* @file: The event file for the trigger's event
* @glob: The trigger command string, with optional remove(!) operator
- * @cmd: The cmd string
- * @param: The param string
* @trigger_data: The trigger_data for the trigger
- * @n_registered: optional outparam, the number of triggers registered
*
* Register an event trigger. The @cmd_ops are used to call the
- * cmd_ops->reg() function which actually does the registration. The
- * cmd_ops->reg() function returns the number of triggers registered,
- * which is assigned to n_registered, if n_registered is non-NULL.
+ * cmd_ops->reg() function which actually does the registration.
*
* Return: 0 on success, errno otherwise
*/
int event_trigger_register(struct event_command *cmd_ops,
struct trace_event_file *file,
char *glob,
- char *cmd,
- char *param,
- struct event_trigger_data *trigger_data,
- int *n_registered)
+ struct event_trigger_data *trigger_data)
{
- int ret;
-
- if (n_registered)
- *n_registered = 0;
-
- ret = cmd_ops->reg(glob, trigger_data, file);
- /*
- * The above returns on success the # of functions enabled,
- * but if it didn't find any functions it returns zero.
- * Consider no functions a failure too.
- */
- if (!ret) {
- cmd_ops->unreg(glob, trigger_data, file);
- ret = -ENOENT;
- } else if (ret > 0) {
- if (n_registered)
- *n_registered = ret;
- /* Just return zero, not the number of enabled functions */
- ret = 0;
- }
+ return cmd_ops->reg(glob, trigger_data, file);
+}
- return ret;
+/**
+ * event_trigger_unregister - unregister an event trigger
+ * @cmd_ops: The event_command operations for the trigger
+ * @file: The event file for the trigger's event
+ * @glob: The trigger command string, with optional remove(!) operator
+ * @trigger_data: The trigger_data for the trigger
+ *
+ * Unregister an event trigger. The @cmd_ops are used to call the
+ * cmd_ops->unreg() function which actually does the unregistration.
+ */
+void event_trigger_unregister(struct event_command *cmd_ops,
+ struct trace_event_file *file,
+ char *glob,
+ struct event_trigger_data *trigger_data)
+{
+ cmd_ops->unreg(glob, trigger_data, file);
}
/*
@@ -981,7 +964,7 @@ int event_trigger_register(struct event_command *cmd_ops,
* @file: The trace_event_file associated with the event
* @glob: The raw string used to register the trigger
* @cmd: The cmd portion of the string used to register the trigger
- * @param: The params portion of the string used to register the trigger
+ * @param_and_filter: The param and filter portion of the string used to register the trigger
*
* Common implementation for event command parsing and trigger
* instantiation.
@@ -994,94 +977,53 @@ int event_trigger_register(struct event_command *cmd_ops,
static int
event_trigger_parse(struct event_command *cmd_ops,
struct trace_event_file *file,
- char *glob, char *cmd, char *param)
+ char *glob, char *cmd, char *param_and_filter)
{
struct event_trigger_data *trigger_data;
- struct event_trigger_ops *trigger_ops;
- char *trigger = NULL;
- char *number;
+ char *param, *filter;
+ bool remove;
int ret;
- /* separate the trigger from the filter (t:n [if filter]) */
- if (param && isdigit(param[0])) {
- trigger = strsep(&param, " \t");
- if (param) {
- param = skip_spaces(param);
- if (!*param)
- param = NULL;
- }
- }
+ remove = event_trigger_check_remove(glob);
- trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+ ret = event_trigger_separate_filter(param_and_filter, &param, &filter, false);
+ if (ret)
+ return ret;
ret = -ENOMEM;
- trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+ trigger_data = event_trigger_alloc(cmd_ops, cmd, param, file);
if (!trigger_data)
goto out;
- trigger_data->count = -1;
- trigger_data->ops = trigger_ops;
- trigger_data->cmd_ops = cmd_ops;
- trigger_data->private_data = file;
- INIT_LIST_HEAD(&trigger_data->list);
- INIT_LIST_HEAD(&trigger_data->named_list);
-
- if (glob[0] == '!') {
- cmd_ops->unreg(glob+1, trigger_data, file);
+ if (remove) {
+ event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
kfree(trigger_data);
ret = 0;
goto out;
}
- if (trigger) {
- number = strsep(&trigger, ":");
-
- ret = -EINVAL;
- if (!strlen(number))
- goto out_free;
-
- /*
- * We use the callback data field (which is a pointer)
- * as our counter.
- */
- ret = kstrtoul(number, 0, &trigger_data->count);
- if (ret)
- goto out_free;
- }
-
- if (!param) /* if param is non-empty, it's supposed to be a filter */
- goto out_reg;
-
- if (!cmd_ops->set_filter)
- goto out_reg;
+ ret = event_trigger_parse_num(param, trigger_data);
+ if (ret)
+ goto out_free;
- ret = cmd_ops->set_filter(param, trigger_data, file);
+ ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
if (ret < 0)
goto out_free;
- out_reg:
/* Up the trigger_data count to make sure reg doesn't free it on failure */
- event_trigger_init(trigger_ops, trigger_data);
- ret = cmd_ops->reg(glob, trigger_data, file);
- /*
- * The above returns on success the # of functions enabled,
- * but if it didn't find any functions it returns zero.
- * Consider no functions a failure too.
- */
- if (!ret) {
- cmd_ops->unreg(glob, trigger_data, file);
- ret = -ENOENT;
- } else if (ret > 0)
- ret = 0;
+ event_trigger_init(trigger_data);
+
+ ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+ if (ret)
+ goto out_free;
/* Down the counter of trigger_data or free it if not used anymore */
- event_trigger_free(trigger_ops, trigger_data);
+ event_trigger_free(trigger_data);
out:
return ret;
out_free:
- if (cmd_ops->set_filter)
- cmd_ops->set_filter(NULL, trigger_data, NULL);
+ event_trigger_reset_filter(cmd_ops, trigger_data);
kfree(trigger_data);
goto out;
}
@@ -1401,16 +1343,14 @@ traceoff_count_trigger(struct event_trigger_data *data,
}
static int
-traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+traceon_trigger_print(struct seq_file *m, struct event_trigger_data *data)
{
return event_trigger_print("traceon", m, (void *)data->count,
data->filter_str);
}
static int
-traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+traceoff_trigger_print(struct seq_file *m, struct event_trigger_data *data)
{
return event_trigger_print("traceoff", m, (void *)data->count,
data->filter_str);
@@ -1521,8 +1461,7 @@ register_snapshot_trigger(char *glob,
}
static int
-snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+snapshot_trigger_print(struct seq_file *m, struct event_trigger_data *data)
{
return event_trigger_print("snapshot", m, (void *)data->count,
data->filter_str);
@@ -1617,8 +1556,7 @@ stacktrace_count_trigger(struct event_trigger_data *data,
}
static int
-stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+stacktrace_trigger_print(struct seq_file *m, struct event_trigger_data *data)
{
return event_trigger_print("stacktrace", m, (void *)data->count,
data->filter_str);
@@ -1708,7 +1646,6 @@ event_enable_count_trigger(struct event_trigger_data *data,
}
int event_enable_trigger_print(struct seq_file *m,
- struct event_trigger_ops *ops,
struct event_trigger_data *data)
{
struct enable_trigger_data *enable_data = data->private_data;
@@ -1733,8 +1670,7 @@ int event_enable_trigger_print(struct seq_file *m,
return 0;
}
-void event_enable_trigger_free(struct event_trigger_ops *ops,
- struct event_trigger_data *data)
+void event_enable_trigger_free(struct event_trigger_data *data)
{
struct enable_trigger_data *enable_data = data->private_data;
@@ -1781,39 +1717,33 @@ static struct event_trigger_ops event_disable_count_trigger_ops = {
int event_enable_trigger_parse(struct event_command *cmd_ops,
struct trace_event_file *file,
- char *glob, char *cmd, char *param)
+ char *glob, char *cmd, char *param_and_filter)
{
struct trace_event_file *event_enable_file;
struct enable_trigger_data *enable_data;
struct event_trigger_data *trigger_data;
- struct event_trigger_ops *trigger_ops;
struct trace_array *tr = file->tr;
+ char *param, *filter;
+ bool enable, remove;
const char *system;
const char *event;
bool hist = false;
- char *trigger;
- char *number;
- bool enable;
int ret;
- if (!param)
- return -EINVAL;
+ remove = event_trigger_check_remove(glob);
- /* separate the trigger from the filter (s:e:n [if filter]) */
- trigger = strsep(&param, " \t");
- if (!trigger)
+ if (event_trigger_empty_param(param_and_filter))
return -EINVAL;
- if (param) {
- param = skip_spaces(param);
- if (!*param)
- param = NULL;
- }
- system = strsep(&trigger, ":");
- if (!trigger)
+ ret = event_trigger_separate_filter(param_and_filter, &param, &filter, true);
+ if (ret)
+ return ret;
+
+ system = strsep(&param, ":");
+ if (!param)
return -EINVAL;
- event = strsep(&trigger, ":");
+ event = strsep(&param, ":");
ret = -EINVAL;
event_enable_file = find_event_file(tr, system, event);
@@ -1829,32 +1759,24 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
#else
enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;
#endif
- trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
-
ret = -ENOMEM;
- trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
- if (!trigger_data)
- goto out;
enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
- if (!enable_data) {
- kfree(trigger_data);
+ if (!enable_data)
goto out;
- }
-
- trigger_data->count = -1;
- trigger_data->ops = trigger_ops;
- trigger_data->cmd_ops = cmd_ops;
- INIT_LIST_HEAD(&trigger_data->list);
- RCU_INIT_POINTER(trigger_data->filter, NULL);
enable_data->hist = hist;
enable_data->enable = enable;
enable_data->file = event_enable_file;
- trigger_data->private_data = enable_data;
- if (glob[0] == '!') {
- cmd_ops->unreg(glob+1, trigger_data, file);
+ trigger_data = event_trigger_alloc(cmd_ops, cmd, param, enable_data);
+ if (!trigger_data) {
+ kfree(enable_data);
+ goto out;
+ }
+
+ if (remove) {
+ event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
kfree(trigger_data);
kfree(enable_data);
ret = 0;
@@ -1862,35 +1784,16 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
}
/* Up the trigger_data count to make sure nothing frees it on failure */
- event_trigger_init(trigger_ops, trigger_data);
-
- if (trigger) {
- number = strsep(&trigger, ":");
-
- ret = -EINVAL;
- if (!strlen(number))
- goto out_free;
-
- /*
- * We use the callback data field (which is a pointer)
- * as our counter.
- */
- ret = kstrtoul(number, 0, &trigger_data->count);
- if (ret)
- goto out_free;
- }
+ event_trigger_init(trigger_data);
- if (!param) /* if param is non-empty, it's supposed to be a filter */
- goto out_reg;
-
- if (!cmd_ops->set_filter)
- goto out_reg;
+ ret = event_trigger_parse_num(param, trigger_data);
+ if (ret)
+ goto out_free;
- ret = cmd_ops->set_filter(param, trigger_data, file);
+ ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data);
if (ret < 0)
goto out_free;
- out_reg:
/* Don't let event modules unload while probe registered */
ret = trace_event_try_get_ref(event_enable_file->event_call);
if (!ret) {
@@ -1901,32 +1804,23 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
ret = trace_event_enable_disable(event_enable_file, 1, 1);
if (ret < 0)
goto out_put;
- ret = cmd_ops->reg(glob, trigger_data, file);
- /*
- * The above returns on success the # of functions enabled,
- * but if it didn't find any functions it returns zero.
- * Consider no functions a failure too.
- */
- if (!ret) {
- ret = -ENOENT;
- goto out_disable;
- } else if (ret < 0)
+
+ ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+ if (ret)
goto out_disable;
- /* Just return zero, not the number of enabled functions */
- ret = 0;
- event_trigger_free(trigger_ops, trigger_data);
+
+ event_trigger_free(trigger_data);
out:
return ret;
-
out_disable:
trace_event_enable_disable(event_enable_file, 0, 1);
out_put:
trace_event_put_ref(event_enable_file->event_call);
out_free:
- if (cmd_ops->set_filter)
- cmd_ops->set_filter(NULL, trigger_data, NULL);
- event_trigger_free(trigger_ops, trigger_data);
+ event_trigger_reset_filter(cmd_ops, trigger_data);
+ event_trigger_free(trigger_data);
kfree(enable_data);
+
goto out;
}
@@ -1953,19 +1847,18 @@ int event_enable_register_trigger(char *glob,
}
if (data->ops->init) {
- ret = data->ops->init(data->ops, data);
+ ret = data->ops->init(data);
if (ret < 0)
goto out;
}
list_add_rcu(&data->list, &file->triggers);
- ret++;
update_cond_flag(file);
- if (trace_event_trigger_enable_disable(file, 1) < 0) {
+ ret = trace_event_trigger_enable_disable(file, 1);
+ if (ret < 0) {
list_del_rcu(&data->list);
update_cond_flag(file);
- ret--;
}
out:
return ret;
@@ -1976,19 +1869,18 @@ void event_enable_unregister_trigger(char *glob,
struct trace_event_file *file)
{
struct enable_trigger_data *test_enable_data = test->private_data;
+ struct event_trigger_data *data = NULL, *iter;
struct enable_trigger_data *enable_data;
- struct event_trigger_data *data;
- bool unregistered = false;
lockdep_assert_held(&event_mutex);
- list_for_each_entry(data, &file->triggers, list) {
- enable_data = data->private_data;
+ list_for_each_entry(iter, &file->triggers, list) {
+ enable_data = iter->private_data;
if (enable_data &&
- (data->cmd_ops->trigger_type ==
+ (iter->cmd_ops->trigger_type ==
test->cmd_ops->trigger_type) &&
(enable_data->file == test_enable_data->file)) {
- unregistered = true;
+ data = iter;
list_del_rcu(&data->list);
trace_event_trigger_enable_disable(file, 0);
update_cond_flag(file);
@@ -1996,8 +1888,8 @@ void event_enable_unregister_trigger(char *glob,
}
}
- if (unregistered && data->ops->free)
- data->ops->free(data->ops, data);
+ if (data && data->ops->free)
+ data->ops->free(data);
}
static struct event_trigger_ops *
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 47cebef78532..93507330462c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1907,25 +1907,18 @@ core_initcall(init_kprobe_trace_early);
static __init int init_kprobe_trace(void)
{
int ret;
- struct dentry *entry;
ret = tracing_init_dentry();
if (ret)
return 0;
- entry = tracefs_create_file("kprobe_events", TRACE_MODE_WRITE,
- NULL, NULL, &kprobe_events_ops);
-
/* Event list interface */
- if (!entry)
- pr_warn("Could not create tracefs 'kprobe_events' entry\n");
+ trace_create_file("kprobe_events", TRACE_MODE_WRITE,
+ NULL, NULL, &kprobe_events_ops);
/* Profile interface */
- entry = tracefs_create_file("kprobe_profile", TRACE_MODE_READ,
- NULL, NULL, &kprobe_profile_ops);
-
- if (!entry)
- pr_warn("Could not create tracefs 'kprobe_profile' entry\n");
+ trace_create_file("kprobe_profile", TRACE_MODE_READ,
+ NULL, NULL, &kprobe_profile_ops);
setup_boot_kprobe_events();
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index afb92e2f0aea..313439920a8c 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1578,11 +1578,27 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
trace_timerlat_sample(&s);
- notify_new_max_latency(diff);
+ if (osnoise_data.stop_tracing) {
+ if (time_to_us(diff) >= osnoise_data.stop_tracing) {
+
+ /*
+ * At this point, if stop_tracing is set and <= print_stack,
+ * print_stack is set and would be printed in the thread handler.
+ *
+ * Thus, print the stack trace as it is helpful to define the
+ * root cause of an IRQ latency.
+ */
+ if (osnoise_data.stop_tracing <= osnoise_data.print_stack) {
+ timerlat_save_stack(0);
+ timerlat_dump_stack(time_to_us(diff));
+ }
- if (osnoise_data.stop_tracing)
- if (time_to_us(diff) >= osnoise_data.stop_tracing)
osnoise_stop_tracing();
+ notify_new_max_latency(diff);
+
+ return HRTIMER_NORESTART;
+ }
+ }
wake_up_process(tlat->kthread);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 8aa493d25c73..67f47ea27921 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -692,7 +692,7 @@ static LIST_HEAD(ftrace_event_list);
static int trace_search_list(struct list_head **list)
{
- struct trace_event *e;
+ struct trace_event *e = NULL, *iter;
int next = __TRACE_LAST_TYPE;
if (list_empty(&ftrace_event_list)) {
@@ -704,9 +704,11 @@ static int trace_search_list(struct list_head **list)
* We used up all possible max events,
* lets see if somebody freed one.
*/
- list_for_each_entry(e, &ftrace_event_list, list) {
- if (e->type != next)
+ list_for_each_entry(iter, &ftrace_event_list, list) {
+ if (iter->type != next) {
+ e = iter;
break;
+ }
next++;
}
@@ -714,7 +716,10 @@ static int trace_search_list(struct list_head **list)
if (next > TRACE_EVENT_TYPE_MAX)
return 0;
- *list = &e->list;
+ if (e)
+ *list = &e->list;
+ else
+ *list = &ftrace_event_list;
return next;
}
@@ -778,9 +783,8 @@ int register_trace_event(struct trace_event *event)
list_add_tail(&event->list, list);
- } else if (event->type > __TRACE_LAST_TYPE) {
- printk(KERN_WARNING "Need to add type to trace.h\n");
- WARN_ON(1);
+ } else if (WARN(event->type > __TRACE_LAST_TYPE,
+ "Need to add type to trace.h")) {
goto out;
} else {
/* Is this event already used */
@@ -1571,13 +1575,8 @@ __init static int init_events(void)
for (i = 0; events[i]; i++) {
event = events[i];
-
ret = register_trace_event(event);
- if (!ret) {
- printk(KERN_WARNING "event %d failed to register\n",
- event->type);
- WARN_ON_ONCE(1);
- }
+ WARN_ONCE(!ret, "event %d failed to register", event->type);
}
return 0;
diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c
index 4d4b78c8ca25..a520b11afb0d 100644
--- a/kernel/trace/trace_recursion_record.c
+++ b/kernel/trace/trace_recursion_record.c
@@ -224,12 +224,9 @@ static const struct file_operations recursed_functions_fops = {
__init static int create_recursed_functions(void)
{
- struct dentry *dentry;
- dentry = trace_create_file("recursed_functions", TRACE_MODE_WRITE,
- NULL, NULL, &recursed_functions_fops);
- if (!dentry)
- pr_warn("WARNING: Failed to create recursed_functions\n");
+ trace_create_file("recursed_functions", TRACE_MODE_WRITE,
+ NULL, NULL, &recursed_functions_fops);
return 0;
}
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index abcadbe933bb..a2d301f58ced 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -895,6 +895,9 @@ trace_selftest_startup_function_graph(struct tracer *trace,
ret = -1;
goto out;
}
+
+ /* Enable tracing on all functions again */
+ ftrace_set_global_filter(NULL, 0, 1);
#endif
/* Don't test dynamic tracing, the function tracer already did */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index f755bde42fd0..b69e207012c9 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -154,7 +154,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags,
goto end;
/* parameter types */
- if (tr->trace_flags & TRACE_ITER_VERBOSE)
+ if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
trace_seq_printf(s, "%s ", entry->types[i]);
/* parameter values */
@@ -296,9 +296,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
struct trace_event_file *trace_file;
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
- struct ring_buffer_event *event;
- struct trace_buffer *buffer;
- unsigned int trace_ctx;
+ struct trace_event_buffer fbuffer;
unsigned long args[6];
int syscall_nr;
int size;
@@ -321,20 +319,16 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
- trace_ctx = tracing_gen_ctx();
-
- event = trace_event_buffer_lock_reserve(&buffer, trace_file,
- sys_data->enter_event->event.type, size, trace_ctx);
- if (!event)
+ entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
+ if (!entry)
return;
- entry = ring_buffer_event_data(event);
+ entry = ring_buffer_event_data(fbuffer.event);
entry->nr = syscall_nr;
syscall_get_arguments(current, regs, args);
memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
- event_trigger_unlock_commit(trace_file, buffer, event, entry,
- trace_ctx);
+ trace_event_buffer_commit(&fbuffer);
}
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -343,9 +337,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
struct trace_event_file *trace_file;
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
- struct ring_buffer_event *event;
- struct trace_buffer *buffer;
- unsigned int trace_ctx;
+ struct trace_event_buffer fbuffer;
int syscall_nr;
syscall_nr = trace_get_syscall_nr(current, regs);
@@ -364,20 +356,15 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
if (!sys_data)
return;
- trace_ctx = tracing_gen_ctx();
-
- event = trace_event_buffer_lock_reserve(&buffer, trace_file,
- sys_data->exit_event->event.type, sizeof(*entry),
- trace_ctx);
- if (!event)
+ entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry));
+ if (!entry)
return;
- entry = ring_buffer_event_data(event);
+ entry = ring_buffer_event_data(fbuffer.event);
entry->nr = syscall_nr;
entry->ret = syscall_get_return_value(current, regs);
- event_trigger_unlock_commit(trace_file, buffer, event, entry,
- trace_ctx);
+ trace_event_buffer_commit(&fbuffer);
}
static int reg_event_syscall_enter(struct trace_event_file *file,
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9628b5571846..9901708ce6b8 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -1045,7 +1045,8 @@ static void sort_secondary(struct tracing_map *map,
/**
* tracing_map_sort_entries - Sort the current set of tracing_map_elts in a map
* @map: The tracing_map
- * @sort_key: The sort key to use for sorting
+ * @sort_keys: The sort key to use for sorting
+ * @n_sort_keys: hitcount, always have at least one
* @sort_entries: outval: pointer to allocated and sorted array of entries
*
* tracing_map_sort_entries() sorts the current set of entries in the
diff --git a/lib/.gitignore b/lib/.gitignore
index e5e217b8307b..54596b634ecb 100644
--- a/lib/.gitignore
+++ b/lib/.gitignore
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
/crc32table.h
/crc64table.h
+/default.bconf
/gen_crc32table
/gen_crc64table
/oid_registry_data.c
diff --git a/lib/Makefile b/lib/Makefile
index 89fcae891361..ea54294d73bf 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -281,7 +281,15 @@ $(foreach file, $(libfdt_files), \
$(eval CFLAGS_$(file) = -I $(srctree)/scripts/dtc/libfdt))
lib-$(CONFIG_LIBFDT) += $(libfdt_files)
-lib-$(CONFIG_BOOT_CONFIG) += bootconfig.o
+obj-$(CONFIG_BOOT_CONFIG) += bootconfig.o
+obj-$(CONFIG_BOOT_CONFIG_EMBED) += bootconfig-data.o
+
+$(obj)/bootconfig-data.o: $(obj)/default.bconf
+
+targets += default.bconf
+filechk_defbconf = cat $(or $(real-prereqs), /dev/null)
+$(obj)/default.bconf: $(CONFIG_BOOT_CONFIG_EMBED_FILE) FORCE
+ $(call filechk,defbconf)
obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o
obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o
diff --git a/lib/bootconfig-data.S b/lib/bootconfig-data.S
new file mode 100644
index 000000000000..ef85ba1a82f4
--- /dev/null
+++ b/lib/bootconfig-data.S
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Embed default bootconfig in the kernel.
+ */
+ .section .init.rodata, "aw"
+ .global embedded_bootconfig_data
+embedded_bootconfig_data:
+ .incbin "lib/default.bconf"
+ .global embedded_bootconfig_data_end
+embedded_bootconfig_data_end:
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 74f3201ab8e5..c59d26068a64 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -12,6 +12,19 @@
#include <linux/kernel.h>
#include <linux/memblock.h>
#include <linux/string.h>
+
+#ifdef CONFIG_BOOT_CONFIG_EMBED
+/* embedded_bootconfig_data is defined in bootconfig-data.S */
+extern __visible const char embedded_bootconfig_data[];
+extern __visible const char embedded_bootconfig_data_end[];
+
+const char * __init xbc_get_embedded_bootconfig(size_t *size)
+{
+ *size = embedded_bootconfig_data_end - embedded_bootconfig_data;
+ return (*size) ? embedded_bootconfig_data : NULL;
+}
+#endif
+
#else /* !__KERNEL__ */
/*
* NOTE: This is only for tools/bootconfig, because tools/bootconfig will