summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-16 00:51:28 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-16 00:51:28 +0200
commitfefa636d815975b34afc45f50852a2810fb23ba9 (patch)
tree5a48fc557bfc2237fbf6dae3a2c929b991315f87
parentMerge tag 'hyperv-next-signed' of git://git.kernel.org/pub/scm/linux/kernel/g... (diff)
parenttracing: support "bool" type in synthetic trace events (diff)
downloadlinux-fefa636d815975b34afc45f50852a2810fb23ba9.tar.xz
linux-fefa636d815975b34afc45f50852a2810fb23ba9.zip
Merge tag 'trace-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing updates from Steven Rostedt: "Updates for tracing and bootconfig: - Add support for "bool" type in synthetic events - Add per instance tracing for bootconfig - Support perf-style return probe ("SYMBOL%return") in kprobes and uprobes - Allow for kprobes to be enabled earlier in boot up - Added tracepoint helper function to allow testing if tracepoints are enabled in headers - Synthetic events can now have dynamic strings (variable length) - Various fixes and cleanups" * tag 'trace-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (58 commits) tracing: support "bool" type in synthetic trace events selftests/ftrace: Add test case for synthetic event syntax errors tracing: Handle synthetic event array field type checking correctly selftests/ftrace: Change synthetic event name for inter-event-combined test tracing: Add synthetic event error logging tracing: Check that the synthetic event and field names are legal tracing: Move is_good_name() from trace_probe.h to trace.h tracing: Don't show dynamic string internals in synthetic event description tracing: Fix some typos in comments tracing/boot: Add ftrace.instance.*.alloc_snapshot option tracing: Fix race in trace_open and buffer resize call tracing: Check return value of __create_val_fields() before using its result tracing: Fix synthetic print fmt check for use of __get_str() tracing: Remove a pointless assignment ftrace: ftrace_global_list is renamed to ftrace_ops_list ftrace: Format variable declarations of ftrace_allocate_records ftrace: Simplify the calculation of page number for ftrace_page->records ftrace: Simplify the dyn_ftrace->flags macro ftrace: Simplify the hash calculation ftrace: Use fls() to get the bits for dup_hash() ...
-rw-r--r--Documentation/trace/boottime-trace.rst38
-rw-r--r--Documentation/trace/events.rst15
-rw-r--r--Documentation/trace/histogram.rst18
-rw-r--r--Documentation/trace/kprobetrace.rst2
-rw-r--r--Documentation/trace/tracepoints.rst27
-rw-r--r--Documentation/trace/uprobetracer.rst2
-rw-r--r--MAINTAINERS1
-rw-r--r--arch/x86/include/asm/msr.h20
-rw-r--r--include/linux/ftrace.h11
-rw-r--r--include/linux/page_ref.h42
-rw-r--r--include/linux/tracepoint-defs.h34
-rw-r--r--kernel/kprobes.c2
-rw-r--r--kernel/trace/fgraph.c8
-rw-r--r--kernel/trace/ftrace.c24
-rw-r--r--kernel/trace/ring_buffer.c10
-rw-r--r--kernel/trace/synth_event_gen_test.c18
-rw-r--r--kernel/trace/trace.c111
-rw-r--r--kernel/trace/trace.h31
-rw-r--r--kernel/trace/trace_boot.c23
-rw-r--r--kernel/trace/trace_dynevent.c10
-rw-r--r--kernel/trace/trace_events.c140
-rw-r--r--kernel/trace/trace_events_hist.c45
-rw-r--r--kernel/trace/trace_events_synth.c413
-rw-r--r--kernel/trace/trace_functions.c22
-rw-r--r--kernel/trace/trace_functions_graph.c8
-rw-r--r--kernel/trace/trace_hwlat.c8
-rw-r--r--kernel/trace/trace_kprobe.c34
-rw-r--r--kernel/trace/trace_printk.c8
-rw-r--r--kernel/trace/trace_probe.h14
-rw-r--r--kernel/trace/trace_stack.c12
-rw-r--r--kernel/trace/trace_stat.c8
-rw-r--r--kernel/trace/trace_synth.h6
-rw-r--r--kernel/trace/trace_uprobe.c24
-rw-r--r--kernel/trace/tracing_map.c2
-rw-r--r--tools/bootconfig/main.c147
-rwxr-xr-xtools/bootconfig/scripts/bconf2ftrace.sh199
-rw-r--r--tools/bootconfig/scripts/ftrace.sh109
-rwxr-xr-xtools/bootconfig/scripts/ftrace2bconf.sh244
-rw-r--r--tools/bootconfig/scripts/xbc.sh56
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc6
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc21
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc6
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc8
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc31
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc19
45 files changed, 1705 insertions, 332 deletions
diff --git a/Documentation/trace/boottime-trace.rst b/Documentation/trace/boottime-trace.rst
index dcb390075ca1..89b64334929b 100644
--- a/Documentation/trace/boottime-trace.rst
+++ b/Documentation/trace/boottime-trace.rst
@@ -61,6 +61,10 @@ These options can be used for each instance including global ftrace node.
ftrace.[instance.INSTANCE.]options = OPT1[, OPT2[...]]
Enable given ftrace options.
+ftrace.[instance.INSTANCE.]tracing_on = 0|1
+ Enable/Disable tracing on this instance when starting boot-time tracing.
+ (you can enable it by the "traceon" event trigger action)
+
ftrace.[instance.INSTANCE.]trace_clock = CLOCK
Set given CLOCK to ftrace's trace_clock.
@@ -116,6 +120,20 @@ instance node, but those are also visible from other instances. So please
take care for event name conflict.
+When to Start
+=============
+
+All boot-time tracing options starting with ``ftrace`` will be enabled at the
+end of core_initcall. This means you can trace the events from postcore_initcall.
+Most of the subsystems and architecture dependent drivers will be initialized
+after that (arch_initcall or subsys_initcall). Thus, you can trace those with
+boot-time tracing.
+If you want to trace events before core_initcall, you can use the options
+starting with ``kernel``. Some of them will be enabled eariler than the initcall
+processing (for example,. ``kernel.ftrace=function`` and ``kernel.trace_event``
+will start before the initcall.)
+
+
Examples
========
@@ -164,6 +182,26 @@ is for tracing functions starting with "user\_", and others tracing
The instance node also accepts event nodes so that each instance
can customize its event tracing.
+With the trigger action and kprobes, you can trace function-graph while
+a function is called. For example, this will trace all function calls in
+the pci_proc_init()::
+
+ ftrace {
+ tracing_on = 0
+ tracer = function_graph
+ event.kprobes {
+ start_event {
+ probes = "pci_proc_init"
+ actions = "traceon"
+ }
+ end_event {
+ probes = "pci_proc_init%return"
+ actions = "traceoff"
+ }
+ }
+ }
+
+
This boot-time tracing also supports ftrace kernel parameters via boot
config.
For example, following kernel parameters::
diff --git a/Documentation/trace/events.rst b/Documentation/trace/events.rst
index f792b1959a33..2a5aa48eff6c 100644
--- a/Documentation/trace/events.rst
+++ b/Documentation/trace/events.rst
@@ -589,8 +589,19 @@ name::
{ .type = "int", .name = "my_int_field" },
};
-See synth_field_size() for available types. If field_name contains [n]
-the field is considered to be an array.
+See synth_field_size() for available types.
+
+If field_name contains [n], the field is considered to be a static array.
+
+If field_names contains[] (no subscript), the field is considered to
+be a dynamic array, which will only take as much space in the event as
+is required to hold the array.
+
+Because space for an event is reserved before assigning field values
+to the event, using dynamic arrays implies that the piecewise
+in-kernel API described below can't be used with dynamic arrays. The
+other non-piecewise in-kernel APIs can, however, be used with dynamic
+arrays.
If the event is created from within a module, a pointer to the module
must be passed to synth_event_create(). This will ensure that the
diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst
index f93333524a44..b71e09f745c3 100644
--- a/Documentation/trace/histogram.rst
+++ b/Documentation/trace/histogram.rst
@@ -1776,6 +1776,24 @@ consisting of the name of the new event along with one or more
variables and their types, which can be any valid field type,
separated by semicolons, to the tracing/synthetic_events file.
+See synth_field_size() for available types.
+
+If field_name contains [n], the field is considered to be a static array.
+
+If field_names contains[] (no subscript), the field is considered to
+be a dynamic array, which will only take as much space in the event as
+is required to hold the array.
+
+A string field can be specified using either the static notation:
+
+ char name[32];
+
+Or the dynamic:
+
+ char name[];
+
+The size limit for either is 256.
+
For instance, the following creates a new event named 'wakeup_latency'
with 3 fields: lat, pid, and prio. Each of those fields is simply a
variable reference to a variable on another event::
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index 10850a9e9af3..b175d88f31eb 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -30,6 +30,7 @@ Synopsis of kprobe_events
p[:[GRP/]EVENT] [MOD:]SYM[+offs]|MEMADDR [FETCHARGS] : Set a probe
r[MAXACTIVE][:[GRP/]EVENT] [MOD:]SYM[+0] [FETCHARGS] : Set a return probe
+ p:[GRP/]EVENT] [MOD:]SYM[+0]%return [FETCHARGS] : Set a return probe
-:[GRP/]EVENT : Clear a probe
GRP : Group name. If omitted, use "kprobes" for it.
@@ -37,6 +38,7 @@ Synopsis of kprobe_events
based on SYM+offs or MEMADDR.
MOD : Module name which has given SYM.
SYM[+offs] : Symbol+offset where the probe is inserted.
+ SYM%return : Return address of the symbol
MEMADDR : Address where the probe is inserted.
MAXACTIVE : Maximum number of instances of the specified function that
can be probed simultaneously, or 0 for the default value
diff --git a/Documentation/trace/tracepoints.rst b/Documentation/trace/tracepoints.rst
index 6e3ce3bf3593..0cb8d9ca3d60 100644
--- a/Documentation/trace/tracepoints.rst
+++ b/Documentation/trace/tracepoints.rst
@@ -146,3 +146,30 @@ with jump labels and avoid conditional branches.
define tracepoints. Check http://lwn.net/Articles/379903,
http://lwn.net/Articles/381064 and http://lwn.net/Articles/383362
for a series of articles with more details.
+
+If you require calling a tracepoint from a header file, it is not
+recommended to call one directly or to use the trace_<tracepoint>_enabled()
+function call, as tracepoints in header files can have side effects if a
+header is included from a file that has CREATE_TRACE_POINTS set, as
+well as the trace_<tracepoint>() is not that small of an inline
+and can bloat the kernel if used by other inlined functions. Instead,
+include tracepoint-defs.h and use tracepoint_enabled().
+
+In a C file::
+
+ void do_trace_foo_bar_wrapper(args)
+ {
+ trace_foo_bar(args);
+ }
+
+In the header file::
+
+ DECLARE_TRACEPOINT(foo_bar);
+
+ static inline void some_inline_function()
+ {
+ [..]
+ if (tracepoint_enabled(foo_bar))
+ do_trace_foo_bar_wrapper(args);
+ [..]
+ }
diff --git a/Documentation/trace/uprobetracer.rst b/Documentation/trace/uprobetracer.rst
index 98cde99939d7..a8e5938f609e 100644
--- a/Documentation/trace/uprobetracer.rst
+++ b/Documentation/trace/uprobetracer.rst
@@ -28,6 +28,7 @@ Synopsis of uprobe_tracer
p[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] : Set a uprobe
r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] : Set a return uprobe (uretprobe)
+ p[:[GRP/]EVENT] PATH:OFFSET%return [FETCHARGS] : Set a return uprobe (uretprobe)
-:[GRP/]EVENT : Clear uprobe or uretprobe event
GRP : Group name. If omitted, "uprobes" is the default value.
@@ -35,6 +36,7 @@ Synopsis of uprobe_tracer
on PATH+OFFSET.
PATH : Path to an executable or a library.
OFFSET : Offset where the probe is inserted.
+ OFFSET%return : Offset where the return probe is inserted.
FETCHARGS : Arguments. Each probe can have up to 128 args.
%REG : Fetch register REG
diff --git a/MAINTAINERS b/MAINTAINERS
index 48b0333d19e2..f310f0a09904 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6626,6 +6626,7 @@ F: fs/proc/bootconfig.c
F: include/linux/bootconfig.h
F: lib/bootconfig.c
F: tools/bootconfig/*
+F: tools/bootconfig/scripts/*
EXYNOS DP DRIVER
M: Jingoo Han <jingoohan1@gmail.com>
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 86f20d520a07..0b4920a7238e 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -60,22 +60,20 @@ struct saved_msrs {
#define EAX_EDX_RET(val, low, high) "=A" (val)
#endif
-#ifdef CONFIG_TRACEPOINTS
/*
* Be very careful with includes. This header is prone to include loops.
*/
#include <asm/atomic.h>
#include <linux/tracepoint-defs.h>
-extern struct tracepoint __tracepoint_read_msr;
-extern struct tracepoint __tracepoint_write_msr;
-extern struct tracepoint __tracepoint_rdpmc;
-#define msr_tracepoint_active(t) static_key_false(&(t).key)
+#ifdef CONFIG_TRACEPOINTS
+DECLARE_TRACEPOINT(read_msr);
+DECLARE_TRACEPOINT(write_msr);
+DECLARE_TRACEPOINT(rdpmc);
extern void do_trace_write_msr(unsigned int msr, u64 val, int failed);
extern void do_trace_read_msr(unsigned int msr, u64 val, int failed);
extern void do_trace_rdpmc(unsigned int msr, u64 val, int failed);
#else
-#define msr_tracepoint_active(t) false
static inline void do_trace_write_msr(unsigned int msr, u64 val, int failed) {}
static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
@@ -128,7 +126,7 @@ static inline unsigned long long native_read_msr(unsigned int msr)
val = __rdmsr(msr);
- if (msr_tracepoint_active(__tracepoint_read_msr))
+ if (tracepoint_enabled(read_msr))
do_trace_read_msr(msr, val, 0);
return val;
@@ -150,7 +148,7 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
_ASM_EXTABLE(2b, 3b)
: [err] "=r" (*err), EAX_EDX_RET(val, low, high)
: "c" (msr), [fault] "i" (-EIO));
- if (msr_tracepoint_active(__tracepoint_read_msr))
+ if (tracepoint_enabled(read_msr))
do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
return EAX_EDX_VAL(val, low, high);
}
@@ -161,7 +159,7 @@ native_write_msr(unsigned int msr, u32 low, u32 high)
{
__wrmsr(msr, low, high);
- if (msr_tracepoint_active(__tracepoint_write_msr))
+ if (tracepoint_enabled(write_msr))
do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
}
@@ -181,7 +179,7 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
: "c" (msr), "0" (low), "d" (high),
[fault] "i" (-EIO)
: "memory");
- if (msr_tracepoint_active(__tracepoint_write_msr))
+ if (tracepoint_enabled(write_msr))
do_trace_write_msr(msr, ((u64)high << 32 | low), err);
return err;
}
@@ -248,7 +246,7 @@ static inline unsigned long long native_read_pmc(int counter)
DECLARE_ARGS(val, low, high);
asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
- if (msr_tracepoint_active(__tracepoint_rdpmc))
+ if (tracepoint_enabled(rdpmc))
do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0);
return EAX_EDX_VAL(val, low, high);
}
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e5c2d5cc6e6a..1bd3a0356ae4 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -217,11 +217,11 @@ extern struct ftrace_ops __rcu *ftrace_ops_list;
extern struct ftrace_ops ftrace_list_end;
/*
- * Traverse the ftrace_global_list, invoking all entries. The reason that we
+ * Traverse the ftrace_ops_list, invoking all entries. The reason that we
* can use rcu_dereference_raw_check() is that elements removed from this list
* are simply leaked, so there is no need to interact with a grace-period
* mechanism. The rcu_dereference_raw_check() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
+ * concurrent insertions into the ftrace_ops_list.
*
* Silly Alpha and silly pointer-speculation compiler optimizations!
*/
@@ -432,7 +432,7 @@ bool is_ftrace_trampoline(unsigned long addr);
* DIRECT - there is a direct function to call
*
* When a new ftrace_ops is registered and wants a function to save
- * pt_regs, the rec->flag REGS is set. When the function has been
+ * pt_regs, the rec->flags REGS is set. When the function has been
* set up to save regs, the REG_EN flag is set. Once a function
* starts saving regs it will do so until all ftrace_ops are removed
* from tracing that function.
@@ -450,12 +450,9 @@ enum {
};
#define FTRACE_REF_MAX_SHIFT 23
-#define FTRACE_FL_BITS 9
-#define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1)
-#define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT)
#define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1)
-#define ftrace_rec_count(rec) ((rec)->flags & ~FTRACE_FL_MASK)
+#define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX)
struct dyn_ftrace {
unsigned long ip; /* address of mcount call-site */
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index d27701199a4d..f3318f34fc54 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -7,13 +7,13 @@
#include <linux/page-flags.h>
#include <linux/tracepoint-defs.h>
-extern struct tracepoint __tracepoint_page_ref_set;
-extern struct tracepoint __tracepoint_page_ref_mod;
-extern struct tracepoint __tracepoint_page_ref_mod_and_test;
-extern struct tracepoint __tracepoint_page_ref_mod_and_return;
-extern struct tracepoint __tracepoint_page_ref_mod_unless;
-extern struct tracepoint __tracepoint_page_ref_freeze;
-extern struct tracepoint __tracepoint_page_ref_unfreeze;
+DECLARE_TRACEPOINT(page_ref_set);
+DECLARE_TRACEPOINT(page_ref_mod);
+DECLARE_TRACEPOINT(page_ref_mod_and_test);
+DECLARE_TRACEPOINT(page_ref_mod_and_return);
+DECLARE_TRACEPOINT(page_ref_mod_unless);
+DECLARE_TRACEPOINT(page_ref_freeze);
+DECLARE_TRACEPOINT(page_ref_unfreeze);
#ifdef CONFIG_DEBUG_PAGE_REF
@@ -24,7 +24,7 @@ extern struct tracepoint __tracepoint_page_ref_unfreeze;
*
* See trace_##name##_enabled(void) in include/linux/tracepoint.h
*/
-#define page_ref_tracepoint_active(t) static_key_false(&(t).key)
+#define page_ref_tracepoint_active(t) tracepoint_enabled(t)
extern void __page_ref_set(struct page *page, int v);
extern void __page_ref_mod(struct page *page, int v);
@@ -75,7 +75,7 @@ static inline int page_count(struct page *page)
static inline void set_page_count(struct page *page, int v)
{
atomic_set(&page->_refcount, v);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_set))
+ if (page_ref_tracepoint_active(page_ref_set))
__page_ref_set(page, v);
}
@@ -91,14 +91,14 @@ static inline void init_page_count(struct page *page)
static inline void page_ref_add(struct page *page, int nr)
{
atomic_add(nr, &page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+ if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, nr);
}
static inline void page_ref_sub(struct page *page, int nr)
{
atomic_sub(nr, &page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+ if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, -nr);
}
@@ -106,7 +106,7 @@ static inline int page_ref_sub_return(struct page *page, int nr)
{
int ret = atomic_sub_return(nr, &page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+ if (page_ref_tracepoint_active(page_ref_mod_and_return))
__page_ref_mod_and_return(page, -nr, ret);
return ret;
}
@@ -114,14 +114,14 @@ static inline int page_ref_sub_return(struct page *page, int nr)
static inline void page_ref_inc(struct page *page)
{
atomic_inc(&page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+ if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, 1);
}
static inline void page_ref_dec(struct page *page)
{
atomic_dec(&page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+ if (page_ref_tracepoint_active(page_ref_mod))
__page_ref_mod(page, -1);
}
@@ -129,7 +129,7 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
{
int ret = atomic_sub_and_test(nr, &page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+ if (page_ref_tracepoint_active(page_ref_mod_and_test))
__page_ref_mod_and_test(page, -nr, ret);
return ret;
}
@@ -138,7 +138,7 @@ static inline int page_ref_inc_return(struct page *page)
{
int ret = atomic_inc_return(&page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+ if (page_ref_tracepoint_active(page_ref_mod_and_return))
__page_ref_mod_and_return(page, 1, ret);
return ret;
}
@@ -147,7 +147,7 @@ static inline int page_ref_dec_and_test(struct page *page)
{
int ret = atomic_dec_and_test(&page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+ if (page_ref_tracepoint_active(page_ref_mod_and_test))
__page_ref_mod_and_test(page, -1, ret);
return ret;
}
@@ -156,7 +156,7 @@ static inline int page_ref_dec_return(struct page *page)
{
int ret = atomic_dec_return(&page->_refcount);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+ if (page_ref_tracepoint_active(page_ref_mod_and_return))
__page_ref_mod_and_return(page, -1, ret);
return ret;
}
@@ -165,7 +165,7 @@ static inline int page_ref_add_unless(struct page *page, int nr, int u)
{
int ret = atomic_add_unless(&page->_refcount, nr, u);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless))
+ if (page_ref_tracepoint_active(page_ref_mod_unless))
__page_ref_mod_unless(page, nr, ret);
return ret;
}
@@ -174,7 +174,7 @@ static inline int page_ref_freeze(struct page *page, int count)
{
int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze))
+ if (page_ref_tracepoint_active(page_ref_freeze))
__page_ref_freeze(page, count, ret);
return ret;
}
@@ -185,7 +185,7 @@ static inline void page_ref_unfreeze(struct page *page, int count)
VM_BUG_ON(count == 0);
atomic_set_release(&page->_refcount, count);
- if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
+ if (page_ref_tracepoint_active(page_ref_unfreeze))
__page_ref_unfreeze(page, count);
}
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index de97450cf190..e7c2276be33e 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -53,4 +53,38 @@ struct bpf_raw_event_map {
u32 writable_size;
} __aligned(32);
+/*
+ * If a tracepoint needs to be called from a header file, it is not
+ * recommended to call it directly, as tracepoints in header files
+ * may cause side-effects and bloat the kernel. Instead, use
+ * tracepoint_enabled() to test if the tracepoint is enabled, then if
+ * it is, call a wrapper function defined in a C file that will then
+ * call the tracepoint.
+ *
+ * For "trace_foo_bar()", you would need to create a wrapper function
+ * in a C file to call trace_foo_bar():
+ * void do_trace_foo_bar(args) { trace_foo_bar(args); }
+ * Then in the header file, declare the tracepoint:
+ * DECLARE_TRACEPOINT(foo_bar);
+ * And call your wrapper:
+ * static inline void some_inlined_function() {
+ * [..]
+ * if (tracepoint_enabled(foo_bar))
+ * do_trace_foo_bar(args);
+ * [..]
+ * }
+ *
+ * Note: tracepoint_enabled(foo_bar) is equivalent to trace_foo_bar_enabled()
+ * but is safe to have in headers, where trace_foo_bar_enabled() is not.
+ */
+#define DECLARE_TRACEPOINT(tp) \
+ extern struct tracepoint __tracepoint_##tp
+
+#ifdef CONFIG_TRACEPOINTS
+# define tracepoint_enabled(tp) \
+ static_key_false(&(__tracepoint_##tp).key)
+#else
+# define tracepoint_enabled(tracepoint) false
+#endif
+
#endif
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 789002da7766..8a12a25fa40d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2614,7 +2614,7 @@ static int __init init_kprobes(void)
init_test_probes();
return err;
}
-subsys_initcall(init_kprobes);
+early_initcall(init_kprobes);
#ifdef CONFIG_DEBUG_FS
static void report_probe(struct seq_file *pi, struct kprobe *p,
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 1af321dec0f1..5658f13037b3 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -387,8 +387,8 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
}
}
- read_lock(&tasklist_lock);
- do_each_thread(g, t) {
+ rcu_read_lock();
+ for_each_process_thread(g, t) {
if (start == end) {
ret = -EAGAIN;
goto unlock;
@@ -403,10 +403,10 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
smp_wmb();
t->ret_stack = ret_stack_list[start++];
}
- } while_each_thread(g, t);
+ }
unlock:
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
free:
for (i = start; i < end; i++)
kfree(ret_stack_list[i]);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 541453927c82..8185f7240095 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -230,7 +230,7 @@ static void update_ftrace_function(void)
/*
* For static tracing, we need to be a bit more careful.
* The function change takes affect immediately. Thus,
- * we need to coorditate the setting of the function_trace_ops
+ * we need to coordinate the setting of the function_trace_ops
* with the setting of the ftrace_trace_function.
*
* Set the function to the list ops, which will call the
@@ -1368,10 +1368,10 @@ static struct ftrace_hash *dup_hash(struct ftrace_hash *src, int size)
int i;
/*
- * Make the hash size about 1/2 the # found
+ * Use around half the size (max bit of it), but
+ * a minimum of 2 is fine (as size of 0 or 1 both give 1 for bits).
*/
- for (size /= 2; size; size >>= 1)
- bits++;
+ bits = fls(size / 2);
/* Don't allocate too much */
if (bits > FTRACE_HASH_MAX_BITS)
@@ -1451,7 +1451,7 @@ static bool hash_contains_ip(unsigned long ip,
{
/*
* The function record is a match if it exists in the filter
- * hash and not in the notrace hash. Note, an emty hash is
+ * hash and not in the notrace hash. Note, an empty hash is
* considered a match for the filter hash, but an empty
* notrace hash is considered not in the notrace hash.
*/
@@ -2402,7 +2402,7 @@ struct ftrace_ops direct_ops = {
*
* If the record has the FTRACE_FL_REGS set, that means that it
* wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
- * is not not set, then it wants to convert to the normal callback.
+ * is not set, then it wants to convert to the normal callback.
*
* Returns the address of the trampoline to set to
*/
@@ -2976,7 +2976,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
synchronize_rcu_tasks_rude();
/*
- * When the kernel is preeptive, tasks can be preempted
+ * When the kernel is preemptive, tasks can be preempted
* while on a ftrace trampoline. Just scheduling a task on
* a CPU is not good enough to flush them. Calling
* synchornize_rcu_tasks() will wait for those tasks to
@@ -3129,18 +3129,20 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
static int ftrace_allocate_records(struct ftrace_page *pg, int count)
{
int order;
+ int pages;
int cnt;
if (WARN_ON(!count))
return -EINVAL;
- order = get_count_order(DIV_ROUND_UP(count, ENTRIES_PER_PAGE));
+ pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE);
+ order = get_count_order(pages);
/*
* We want to fill as much as possible. No more than a page
* may be empty.
*/
- while ((PAGE_SIZE << order) / ENTRY_SIZE >= count + ENTRIES_PER_PAGE)
+ if (!is_power_of_2(pages))
order--;
again:
@@ -4368,7 +4370,7 @@ void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper,
* @ip: The instruction pointer address to map @data to
* @data: The data to map to @ip
*
- * Returns 0 on succes otherwise an error.
+ * Returns 0 on success otherwise an error.
*/
int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
unsigned long ip, void *data)
@@ -4536,7 +4538,7 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
/*
* Note, there's a small window here that the func_hash->filter_hash
- * may be NULL or empty. Need to be carefule when reading the loop.
+ * may be NULL or empty. Need to be careful when reading the loop.
*/
mutex_lock(&probe->ops.func_hash->regex_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 93ef0ab6ea20..15bf28b13e50 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -4866,6 +4866,9 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return;
+ /* prevent another thread from changing buffer sizes */
+ mutex_lock(&buffer->mutex);
+
atomic_inc(&cpu_buffer->resize_disabled);
atomic_inc(&cpu_buffer->record_disabled);
@@ -4876,6 +4879,8 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
atomic_dec(&cpu_buffer->record_disabled);
atomic_dec(&cpu_buffer->resize_disabled);
+
+ mutex_unlock(&buffer->mutex);
}
EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
@@ -4889,6 +4894,9 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
struct ring_buffer_per_cpu *cpu_buffer;
int cpu;
+ /* prevent another thread from changing buffer sizes */
+ mutex_lock(&buffer->mutex);
+
for_each_online_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
@@ -4907,6 +4915,8 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
atomic_dec(&cpu_buffer->record_disabled);
atomic_dec(&cpu_buffer->resize_disabled);
}
+
+ mutex_unlock(&buffer->mutex);
}
/**
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 7d56d621ffea..edd912cd14aa 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -242,9 +242,11 @@ static struct synth_field_desc create_synth_test_fields[] = {
{ .type = "pid_t", .name = "next_pid_field" },
{ .type = "char[16]", .name = "next_comm_field" },
{ .type = "u64", .name = "ts_ns" },
+ { .type = "char[]", .name = "dynstring_field_1" },
{ .type = "u64", .name = "ts_ms" },
{ .type = "unsigned int", .name = "cpu" },
{ .type = "char[64]", .name = "my_string_field" },
+ { .type = "char[]", .name = "dynstring_field_2" },
{ .type = "int", .name = "my_int_field" },
};
@@ -254,7 +256,7 @@ static struct synth_field_desc create_synth_test_fields[] = {
*/
static int __init test_create_synth_event(void)
{
- u64 vals[7];
+ u64 vals[9];
int ret;
/* Create the create_synth_test event with the fields above */
@@ -292,10 +294,12 @@ static int __init test_create_synth_event(void)
vals[0] = 777; /* next_pid_field */
vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */
vals[2] = 1000000; /* ts_ns */
- vals[3] = 1000; /* ts_ms */
- vals[4] = raw_smp_processor_id(); /* cpu */
- vals[5] = (u64)(long)"thneed"; /* my_string_field */
- vals[6] = 398; /* my_int_field */
+ vals[3] = (u64)(long)"xrayspecs"; /* dynstring_field_1 */
+ vals[4] = 1000; /* ts_ms */
+ vals[5] = raw_smp_processor_id(); /* cpu */
+ vals[6] = (u64)(long)"thneed"; /* my_string_field */
+ vals[7] = (u64)(long)"kerplunk"; /* dynstring_field_2 */
+ vals[8] = 398; /* my_int_field */
/* Now generate a create_synth_test event */
ret = synth_event_trace_array(create_synth_test, vals, ARRAY_SIZE(vals));
@@ -422,13 +426,15 @@ static int __init test_trace_synth_event(void)
int ret;
/* Trace some bogus values just for testing */
- ret = synth_event_trace(create_synth_test, 7, /* number of values */
+ ret = synth_event_trace(create_synth_test, 9, /* number of values */
(u64)444, /* next_pid_field */
(u64)(long)"clackers", /* next_comm_field */
(u64)1000000, /* ts_ns */
+ (u64)(long)"viewmaster",/* dynstring_field_1 */
(u64)1000, /* ts_ms */
(u64)raw_smp_processor_id(), /* cpu */
(u64)(long)"Thneed", /* my_string_field */
+ (u64)(long)"yoyos", /* dynstring_field_2 */
(u64)999); /* my_int_field */
return ret;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4c187740c0df..528971714fc6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2650,7 +2650,7 @@ void trace_buffered_event_enable(void)
preempt_disable();
if (cpu == smp_processor_id() &&
- this_cpu_read(trace_buffered_event) !=
+ __this_cpu_read(trace_buffered_event) !=
per_cpu(trace_buffered_event, cpu))
WARN_ON_ONCE(1);
preempt_enable();
@@ -5142,10 +5142,10 @@ static const char readme_msg[] =
"\t -:[<group>/]<event>\n"
#ifdef CONFIG_KPROBE_EVENTS
"\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
- "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n"
+ "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n"
#endif
#ifdef CONFIG_UPROBE_EVENTS
- " place (uprobe): <path>:<offset>[(ref_ctr_offset)]\n"
+ " place (uprobe): <path>:<offset>[%return][(ref_ctr_offset)]\n"
#endif
"\t args: <name>=fetcharg[:type]\n"
"\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n"
@@ -5269,7 +5269,12 @@ static const char readme_msg[] =
"\t trace(<synthetic_event>,param list) - generate synthetic event\n"
"\t save(field,...) - save current event fields\n"
#ifdef CONFIG_TRACER_SNAPSHOT
- "\t snapshot() - snapshot the trace buffer\n"
+ "\t snapshot() - snapshot the trace buffer\n\n"
+#endif
+#ifdef CONFIG_SYNTH_EVENTS
+ " events/synthetic_events\t- Create/append/remove/show synthetic events\n"
+ "\t Write into this file to define/undefine new synthetic events.\n"
+ "\t example: echo 'myevent u64 lat; char name[]' >> synthetic_events\n"
#endif
#endif
;
@@ -6682,7 +6687,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
written = -EFAULT;
} else
written = cnt;
- len = cnt;
if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) {
/* do not add \n before testing triggers, but add \0 */
@@ -8658,6 +8662,24 @@ struct trace_array *trace_array_find_get(const char *instance)
return tr;
}
+static int trace_array_create_dir(struct trace_array *tr)
+{
+ int ret;
+
+ tr->dir = tracefs_create_dir(tr->name, trace_instance_dir);
+ if (!tr->dir)
+ return -EINVAL;
+
+ ret = event_trace_add_tracer(tr->dir, tr);
+ if (ret)
+ tracefs_remove(tr->dir);
+
+ init_tracer_tracefs(tr, tr->dir);
+ __update_tracer_options(tr);
+
+ return ret;
+}
+
static struct trace_array *trace_array_create(const char *name)
{
struct trace_array *tr;
@@ -8693,30 +8715,28 @@ static struct trace_array *trace_array_create(const char *name)
if (allocate_trace_buffers(tr, trace_buf_size) < 0)
goto out_free_tr;
- tr->dir = tracefs_create_dir(name, trace_instance_dir);
- if (!tr->dir)
+ if (ftrace_allocate_ftrace_ops(tr) < 0)
goto out_free_tr;
- ret = event_trace_add_tracer(tr->dir, tr);
- if (ret) {
- tracefs_remove(tr->dir);
- goto out_free_tr;
- }
-
ftrace_init_trace_array(tr);
- init_tracer_tracefs(tr, tr->dir);
init_trace_flags_index(tr);
- __update_tracer_options(tr);
+
+ if (trace_instance_dir) {
+ ret = trace_array_create_dir(tr);
+ if (ret)
+ goto out_free_tr;
+ } else
+ __trace_early_add_events(tr);
list_add(&tr->list, &ftrace_trace_arrays);
tr->ref++;
-
return tr;
out_free_tr:
+ ftrace_free_ftrace_ops(tr);
free_trace_buffers(tr);
free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
@@ -8821,7 +8841,6 @@ static int __remove_instance(struct trace_array *tr)
free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
- tr = NULL;
return 0;
}
@@ -8875,11 +8894,27 @@ static int instance_rmdir(const char *name)
static __init void create_trace_instances(struct dentry *d_tracer)
{
+ struct trace_array *tr;
+
trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer,
instance_mkdir,
instance_rmdir);
if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n"))
return;
+
+ mutex_lock(&event_mutex);
+ mutex_lock(&trace_types_lock);
+
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (!tr->name)
+ continue;
+ if (MEM_FAIL(trace_array_create_dir(tr) < 0,
+ "Failed to create instance directory\n"))
+ break;
+ }
+
+ mutex_unlock(&trace_types_lock);
+ mutex_unlock(&event_mutex);
}
static void
@@ -8993,21 +9028,21 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
* directory. It is called via fs_initcall() by any of the boot up code
* and expects to return the dentry of the top level tracing directory.
*/
-struct dentry *tracing_init_dentry(void)
+int tracing_init_dentry(void)
{
struct trace_array *tr = &global_trace;
if (security_locked_down(LOCKDOWN_TRACEFS)) {
pr_warn("Tracing disabled due to lockdown\n");
- return ERR_PTR(-EPERM);
+ return -EPERM;
}
/* The top level trace array uses NULL as parent */
if (tr->dir)
- return NULL;
+ return 0;
if (WARN_ON(!tracefs_initialized()))
- return ERR_PTR(-ENODEV);
+ return -ENODEV;
/*
* As there may still be users that expect the tracing
@@ -9018,7 +9053,7 @@ struct dentry *tracing_init_dentry(void)
tr->dir = debugfs_create_automount("tracing", NULL,
trace_automount, NULL);
- return NULL;
+ return 0;
}
extern struct trace_eval_map *__start_ftrace_eval_maps[];
@@ -9105,48 +9140,48 @@ static struct notifier_block trace_module_nb = {
static __init int tracer_init_tracefs(void)
{
- struct dentry *d_tracer;
+ int ret;
trace_access_lock_init();
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
event_trace_init();
- init_tracer_tracefs(&global_trace, d_tracer);
- ftrace_init_tracefs_toplevel(&global_trace, d_tracer);
+ init_tracer_tracefs(&global_trace, NULL);
+ ftrace_init_tracefs_toplevel(&global_trace, NULL);
- trace_create_file("tracing_thresh", 0644, d_tracer,
+ trace_create_file("tracing_thresh", 0644, NULL,
&global_trace, &tracing_thresh_fops);
- trace_create_file("README", 0444, d_tracer,
+ trace_create_file("README", 0444, NULL,
NULL, &tracing_readme_fops);
- trace_create_file("saved_cmdlines", 0444, d_tracer,
+ trace_create_file("saved_cmdlines", 0444, NULL,
NULL, &tracing_saved_cmdlines_fops);
- trace_create_file("saved_cmdlines_size", 0644, d_tracer,
+ trace_create_file("saved_cmdlines_size", 0644, NULL,
NULL, &tracing_saved_cmdlines_size_fops);
- trace_create_file("saved_tgids", 0444, d_tracer,
+ trace_create_file("saved_tgids", 0444, NULL,
NULL, &tracing_saved_tgids_fops);
trace_eval_init();
- trace_create_eval_file(d_tracer);
+ trace_create_eval_file(NULL);
#ifdef CONFIG_MODULES
register_module_notifier(&trace_module_nb);
#endif
#ifdef CONFIG_DYNAMIC_FTRACE
- trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
+ trace_create_file("dyn_ftrace_total_info", 0444, NULL,
NULL, &tracing_dyn_info_fops);
#endif
- create_trace_instances(d_tracer);
+ create_trace_instances(NULL);
update_tracer_options(&global_trace);
@@ -9309,7 +9344,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
}
/*
- * We need to stop all tracing on all CPUS to read the
+ * We need to stop all tracing on all CPUS to read
* the next buffer. This is a bit expensive, but is
* not done often. We fill all what we can read,
* and then release the locks again.
@@ -9452,7 +9487,7 @@ __init static int tracer_alloc_buffers(void)
}
/*
- * Make sure we don't accidently add more trace options
+ * Make sure we don't accidentally add more trace options
* than we have bits for.
*/
BUILD_BUG_ON(TRACE_ITER_LAST_BIT > TRACE_FLAGS_MAX_SIZE);
@@ -9481,7 +9516,7 @@ __init static int tracer_alloc_buffers(void)
/*
* The prepare callbacks allocates some memory for the ring buffer. We
- * don't free the buffer if the if the CPU goes down. If we were to free
+ * don't free the buffer if the CPU goes down. If we were to free
* the buffer, then the user would lose any trace that was in the
* buffer. The memory will be removed once the "instance" is removed.
*/
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 610d21355526..34e0c4d5a6e7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -19,6 +19,7 @@
#include <linux/glob.h>
#include <linux/irq_work.h>
#include <linux/workqueue.h>
+#include <linux/ctype.h>
#ifdef CONFIG_FTRACE_SYSCALLS
#include <asm/unistd.h> /* For NR_SYSCALLS */
@@ -246,7 +247,7 @@ typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data);
* tracing_snapshot_cond(tr, cond_data), the cond_data passed in is
* passed in turn to the cond_snapshot.update() function. That data
* can be compared by the update() implementation with the cond_data
- * contained wihin the struct cond_snapshot instance associated with
+ * contained within the struct cond_snapshot instance associated with
* the trace_array. Because the tr->max_lock is held throughout the
* update() call, the update() function can directly retrieve the
* cond_snapshot and cond_data associated with the per-instance
@@ -271,7 +272,7 @@ typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data);
* take the snapshot, by returning 'true' if so, 'false' if no
* snapshot should be taken. Because the max_lock is held for
* the duration of update(), the implementation is safe to
- * directly retrieven and save any implementation data it needs
+ * directly retrieved and save any implementation data it needs
* to in association with the snapshot.
*/
struct cond_snapshot {
@@ -573,7 +574,7 @@ struct tracer {
* The function callback, which can use the FTRACE bits to
* check for recursion.
*
- * Now if the arch does not suppport a feature, and it calls
+ * Now if the arch does not support a feature, and it calls
* the global list function which calls the ftrace callback
* all three of these steps will do a recursion protection.
* There's no reason to do one if the previous caller already
@@ -737,7 +738,7 @@ struct dentry *trace_create_file(const char *name,
void *data,
const struct file_operations *fops);
-struct dentry *tracing_init_dentry(void);
+int tracing_init_dentry(void);
struct ring_buffer_event;
@@ -1125,6 +1126,8 @@ extern int ftrace_is_dead(void);
int ftrace_create_function_files(struct trace_array *tr,
struct dentry *parent);
void ftrace_destroy_function_files(struct trace_array *tr);
+int ftrace_allocate_ftrace_ops(struct trace_array *tr);
+void ftrace_free_ftrace_ops(struct trace_array *tr);
void ftrace_init_global_array_ops(struct trace_array *tr);
void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
void ftrace_reset_array_ops(struct trace_array *tr);
@@ -1146,6 +1149,11 @@ ftrace_create_function_files(struct trace_array *tr,
{
return 0;
}
+static inline int ftrace_allocate_ftrace_ops(struct trace_array *tr)
+{
+ return 0;
+}
+static inline void ftrace_free_ftrace_ops(struct trace_array *tr) { }
static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
static inline __init void
ftrace_init_global_array_ops(struct trace_array *tr) { }
@@ -1472,7 +1480,7 @@ __trace_event_discard_commit(struct trace_buffer *buffer,
/*
* Helper function for event_trigger_unlock_commit{_regs}().
* If there are event triggers attached to this event that requires
- * filtering against its fields, then they wil be called as the
+ * filtering against its fields, then they will be called as the
* entry already holds the field information of the current event.
*
* It also checks if the event should be discarded or not.
@@ -1651,6 +1659,7 @@ extern void trace_event_enable_tgid_record(bool enable);
extern int event_trace_init(void);
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
+extern void __trace_early_add_events(struct trace_array *tr);
extern struct trace_event_file *__find_event_file(struct trace_array *tr,
const char *system,
@@ -2082,4 +2091,16 @@ static __always_inline void trace_iterator_reset(struct trace_iterator *iter)
iter->pos = -1;
}
+/* Check the name is good for event/group/fields */
+static inline bool is_good_name(const char *name)
+{
+ if (!isalpha(*name) && *name != '_')
+ return false;
+ while (*++name != '\0') {
+ if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+ return false;
+ }
+ return true;
+}
+
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index fa0fc08c6ef8..c22a152ef0b4 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -40,6 +40,16 @@ trace_boot_set_instance_options(struct trace_array *tr, struct xbc_node *node)
pr_err("Failed to set option: %s\n", buf);
}
+ p = xbc_node_find_value(node, "tracing_on", NULL);
+ if (p && *p != '\0') {
+ if (kstrtoul(p, 10, &v))
+ pr_err("Failed to set tracing on: %s\n", p);
+ if (v)
+ tracer_tracing_on(tr);
+ else
+ tracer_tracing_off(tr);
+ }
+
p = xbc_node_find_value(node, "trace_clock", NULL);
if (p && *p != '\0') {
if (tracing_set_clock(tr, p) < 0)
@@ -274,6 +284,12 @@ trace_boot_enable_tracer(struct trace_array *tr, struct xbc_node *node)
if (tracing_set_tracer(tr, p) < 0)
pr_err("Failed to set given tracer: %s\n", p);
}
+
+ /* Since tracer can free snapshot buffer, allocate snapshot here.*/
+ if (xbc_node_find_value(node, "alloc_snapshot", NULL)) {
+ if (tracing_alloc_snapshot_instance(tr) < 0)
+ pr_err("Failed to allocate snapshot buffer\n");
+ }
}
static void __init
@@ -330,5 +346,8 @@ static int __init trace_boot_init(void)
return 0;
}
-
-fs_initcall(trace_boot_init);
+/*
+ * Start tracing at the end of core-initcall, so that it starts tracing
+ * from the beginning of postcore_initcall.
+ */
+core_initcall_sync(trace_boot_init);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 9f2e8520b748..5fa49cfd2bb6 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -206,14 +206,14 @@ 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 *d_tracer;
struct dentry *entry;
+ int ret;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
- entry = tracefs_create_file("dynamic_events", 0644, d_tracer,
+ entry = tracefs_create_file("dynamic_events", 0644, NULL,
NULL, &dynamic_events_ops);
/* Event list interface */
@@ -402,7 +402,7 @@ void dynevent_arg_init(struct dynevent_arg *arg,
* whitespace, all followed by a separator, if applicable. After the
* first arg string is successfully appended to the command string,
* the optional @operator is appended, followed by the second arg and
- * and optional @separator. If no separator was specified when
+ * optional @separator. If no separator was specified when
* initializing the arg, a space will be appended.
*/
void dynevent_arg_pair_init(struct dynevent_arg_pair *arg_pair,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index beebf2cd364b..29ca60f058ef 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -38,6 +38,7 @@ DEFINE_MUTEX(event_mutex);
LIST_HEAD(ftrace_events);
static LIST_HEAD(ftrace_generic_fields);
static LIST_HEAD(ftrace_common_fields);
+static bool eventdir_initialized;
#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
@@ -2124,11 +2125,47 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
}
static int
+event_define_fields(struct trace_event_call *call)
+{
+ struct list_head *head;
+ int ret = 0;
+
+ /*
+ * Other events may have the same class. Only update
+ * the fields if they are not already defined.
+ */
+ head = trace_get_fields(call);
+ if (list_empty(head)) {
+ struct trace_event_fields *field = call->class->fields_array;
+ unsigned int offset = sizeof(struct trace_entry);
+
+ for (; field->type; field++) {
+ if (field->type == TRACE_FUNCTION_TYPE) {
+ field->define_fields(call);
+ break;
+ }
+
+ offset = ALIGN(offset, field->align);
+ ret = trace_define_field(call, field->type, field->name,
+ offset, field->size,
+ field->is_signed, field->filter_type);
+ if (WARN_ON_ONCE(ret)) {
+ pr_err("error code is %d\n", ret);
+ break;
+ }
+
+ offset += field->size;
+ }
+ }
+
+ return ret;
+}
+
+static int
event_create_dir(struct dentry *parent, struct trace_event_file *file)
{
struct trace_event_call *call = file->event_call;
struct trace_array *tr = file->tr;
- struct list_head *head;
struct dentry *d_events;
const char *name;
int ret;
@@ -2162,35 +2199,10 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
&ftrace_event_id_fops);
#endif
- /*
- * Other events may have the same class. Only update
- * the fields if they are not already defined.
- */
- head = trace_get_fields(call);
- if (list_empty(head)) {
- struct trace_event_fields *field = call->class->fields_array;
- unsigned int offset = sizeof(struct trace_entry);
-
- for (; field->type; field++) {
- if (field->type == TRACE_FUNCTION_TYPE) {
- ret = field->define_fields(call);
- break;
- }
-
- offset = ALIGN(offset, field->align);
- ret = trace_define_field(call, field->type, field->name,
- offset, field->size,
- field->is_signed, field->filter_type);
- if (ret)
- break;
-
- offset += field->size;
- }
- if (ret < 0) {
- pr_warn("Could not initialize trace point events/%s\n",
- name);
- return -1;
- }
+ ret = event_define_fields(call);
+ if (ret < 0) {
+ pr_warn("Could not initialize trace point events/%s\n", name);
+ return ret;
}
/*
@@ -2475,7 +2487,10 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
if (!file)
return -ENOMEM;
- return event_create_dir(tr->event_dir, file);
+ if (eventdir_initialized)
+ return event_create_dir(tr->event_dir, file);
+ else
+ return event_define_fields(call);
}
/*
@@ -2493,7 +2508,7 @@ __trace_early_add_new_event(struct trace_event_call *call,
if (!file)
return -ENOMEM;
- return 0;
+ return event_define_fields(call);
}
struct ftrace_module_file_ops;
@@ -3116,14 +3131,13 @@ static inline int register_event_cmds(void) { return 0; }
#endif /* CONFIG_DYNAMIC_FTRACE */
/*
- * The top level array has already had its trace_event_file
- * descriptors created in order to allow for early events to
- * be recorded. This function is called after the tracefs has been
- * initialized, and we now have to create the files associated
- * to the events.
+ * The top level array and trace arrays created by boot-time tracing
+ * have already had its trace_event_file descriptors created in order
+ * to allow for early events to be recorded.
+ * This function is called after the tracefs has been initialized,
+ * and we now have to create the files associated to the events.
*/
-static __init void
-__trace_early_add_event_dirs(struct trace_array *tr)
+static void __trace_early_add_event_dirs(struct trace_array *tr)
{
struct trace_event_file *file;
int ret;
@@ -3138,13 +3152,12 @@ __trace_early_add_event_dirs(struct trace_array *tr)
}
/*
- * For early boot up, the top trace array requires to have
- * a list of events that can be enabled. This must be done before
- * the filesystem is set up in order to allow events to be traced
- * early.
+ * For early boot up, the top trace array and the trace arrays created
+ * by boot-time tracing require to have a list of events that can be
+ * enabled. This must be done before the filesystem is set up in order
+ * to allow events to be traced early.
*/
-static __init void
-__trace_early_add_events(struct trace_array *tr)
+void __trace_early_add_events(struct trace_array *tr)
{
struct trace_event_call *call;
int ret;
@@ -3275,7 +3288,11 @@ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
goto out;
down_write(&trace_event_sem);
- __trace_add_event_dirs(tr);
+ /* If tr already has the event list, it is initialized in early boot. */
+ if (unlikely(!list_empty(&tr->events)))
+ __trace_early_add_event_dirs(tr);
+ else
+ __trace_add_event_dirs(tr);
up_write(&trace_event_sem);
out:
@@ -3431,10 +3448,21 @@ static __init int event_trace_enable_again(void)
early_initcall(event_trace_enable_again);
+/* Init fields which doesn't related to the tracefs */
+static __init int event_trace_init_fields(void)
+{
+ if (trace_define_generic_fields())
+ pr_warn("tracing: Failed to allocated generic fields");
+
+ if (trace_define_common_fields())
+ pr_warn("tracing: Failed to allocate common fields");
+
+ return 0;
+}
+
__init int event_trace_init(void)
{
struct trace_array *tr;
- struct dentry *d_tracer;
struct dentry *entry;
int ret;
@@ -3442,22 +3470,12 @@ __init int event_trace_init(void)
if (!tr)
return -ENODEV;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
- return 0;
-
- entry = tracefs_create_file("available_events", 0444, d_tracer,
+ entry = tracefs_create_file("available_events", 0444, NULL,
tr, &ftrace_avail_fops);
if (!entry)
pr_warn("Could not create tracefs 'available_events' entry\n");
- if (trace_define_generic_fields())
- pr_warn("tracing: Failed to allocated generic fields");
-
- if (trace_define_common_fields())
- pr_warn("tracing: Failed to allocate common fields");
-
- ret = early_event_add_tracer(d_tracer, tr);
+ ret = early_event_add_tracer(NULL, tr);
if (ret)
return ret;
@@ -3466,6 +3484,9 @@ __init int event_trace_init(void)
if (ret)
pr_warn("Failed to register trace events module notifier\n");
#endif
+
+ eventdir_initialized = true;
+
return 0;
}
@@ -3474,6 +3495,7 @@ void __init trace_event_init(void)
event_trace_memsetup();
init_ftrace_syscalls();
event_trace_enable();
+ event_trace_init_fields();
}
#ifdef CONFIG_EVENT_TRACE_STARTUP_TEST
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1b2ef6490229..96c3f86b81c5 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -147,6 +147,8 @@ struct hist_field {
*/
unsigned int var_ref_idx;
bool read_once;
+
+ unsigned int var_str_idx;
};
static u64 hist_field_none(struct hist_field *field,
@@ -349,6 +351,7 @@ struct hist_trigger_data {
unsigned int n_keys;
unsigned int n_fields;
unsigned int n_vars;
+ unsigned int n_var_str;
unsigned int key_size;
struct tracing_map_sort_key sort_keys[TRACING_MAP_SORT_KEYS_MAX];
unsigned int n_sort_keys;
@@ -1396,7 +1399,14 @@ static int hist_trigger_elt_data_alloc(struct tracing_map_elt *elt)
}
}
- n_str = hist_data->n_field_var_str + hist_data->n_save_var_str;
+ n_str = hist_data->n_field_var_str + hist_data->n_save_var_str +
+ hist_data->n_var_str;
+ if (n_str > SYNTH_FIELDS_MAX) {
+ hist_elt_data_free(elt_data);
+ return -EINVAL;
+ }
+
+ BUILD_BUG_ON(STR_VAR_LEN_MAX & (sizeof(u64) - 1));
size = STR_VAR_LEN_MAX;
@@ -3279,6 +3289,15 @@ static int check_synth_field(struct synth_event *event,
field = event->fields[field_pos];
+ /*
+ * A dynamic string synth field can accept static or
+ * dynamic. A static string synth field can only accept a
+ * same-sized static string, which is checked for later.
+ */
+ if (strstr(hist_field->type, "char[") && field->is_string
+ && field->is_dynamic)
+ return 0;
+
if (strcmp(field->type, hist_field->type) != 0) {
if (field->size != hist_field->size ||
field->is_signed != hist_field->is_signed)
@@ -3651,6 +3670,7 @@ static int create_var_field(struct hist_trigger_data *hist_data,
{
struct trace_array *tr = hist_data->event_file->tr;
unsigned long flags = 0;
+ int ret;
if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX + TRACING_MAP_VARS_MAX))
return -EINVAL;
@@ -3665,7 +3685,12 @@ static int create_var_field(struct hist_trigger_data *hist_data,
if (WARN_ON(hist_data->n_vars > TRACING_MAP_VARS_MAX))
return -EINVAL;
- return __create_val_field(hist_data, val_idx, file, var_name, expr_str, flags);
+ ret = __create_val_field(hist_data, val_idx, file, var_name, expr_str, flags);
+
+ if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_STRING)
+ hist_data->fields[val_idx]->var_str_idx = hist_data->n_var_str++;
+
+ return ret;
}
static int create_val_fields(struct hist_trigger_data *hist_data,
@@ -4392,6 +4417,22 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
hist_val = hist_field->fn(hist_field, elt, rbe, rec);
if (hist_field->flags & HIST_FIELD_FL_VAR) {
var_idx = hist_field->var.idx;
+
+ if (hist_field->flags & HIST_FIELD_FL_STRING) {
+ unsigned int str_start, var_str_idx, idx;
+ char *str, *val_str;
+
+ str_start = hist_data->n_field_var_str +
+ hist_data->n_save_var_str;
+ var_str_idx = hist_field->var_str_idx;
+ idx = str_start + var_str_idx;
+
+ str = elt_data->field_var_str[idx];
+ val_str = (char *)(uintptr_t)hist_val;
+ strscpy(str, val_str, STR_VAR_LEN_MAX);
+
+ hist_val = (u64)(uintptr_t)str;
+ }
tracing_map_set_var(elt, var_idx, hist_val);
continue;
}
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index c6cca0d1d584..3212e2c653b3 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -20,6 +20,48 @@
#include "trace_synth.h"
+#undef ERRORS
+#define ERRORS \
+ C(BAD_NAME, "Illegal name"), \
+ C(CMD_INCOMPLETE, "Incomplete command"), \
+ C(EVENT_EXISTS, "Event already exists"), \
+ C(TOO_MANY_FIELDS, "Too many fields"), \
+ C(INCOMPLETE_TYPE, "Incomplete type"), \
+ C(INVALID_TYPE, "Invalid type"), \
+ C(INVALID_FIELD, "Invalid field"), \
+ C(CMD_TOO_LONG, "Command too long"),
+
+#undef C
+#define C(a, b) SYNTH_ERR_##a
+
+enum { ERRORS };
+
+#undef C
+#define C(a, b) b
+
+static const char *err_text[] = { ERRORS };
+
+static char last_cmd[MAX_FILTER_STR_VAL];
+
+static int errpos(const char *str)
+{
+ return err_pos(last_cmd, str);
+}
+
+static void last_cmd_set(char *str)
+{
+ if (!str)
+ return;
+
+ strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1);
+}
+
+static void synth_err(u8 err_type, u8 err_pos)
+{
+ tracing_log_err(NULL, "synthetic_events", last_cmd, err_text,
+ err_type, err_pos);
+}
+
static int create_synth_event(int argc, const char **argv);
static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
static int synth_event_release(struct dyn_event *ev);
@@ -88,7 +130,7 @@ static int synth_event_define_fields(struct trace_event_call *call)
event->fields[i]->offset = n_u64;
- if (event->fields[i]->is_string) {
+ if (event->fields[i]->is_string && !event->fields[i]->is_dynamic) {
offset += STR_VAR_LEN_MAX;
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
} else {
@@ -132,13 +174,16 @@ static int synth_field_string_size(char *type)
start += sizeof("char[") - 1;
end = strchr(type, ']');
- if (!end || end < start)
+ if (!end || end < start || type + strlen(type) > end + 1)
return -EINVAL;
len = end - start;
if (len > 3)
return -EINVAL;
+ if (len == 0)
+ return 0; /* variable-length string */
+
strncpy(buf, start, len);
buf[len] = '\0';
@@ -184,6 +229,8 @@ static int synth_field_size(char *type)
size = sizeof(long);
else if (strcmp(type, "unsigned long") == 0)
size = sizeof(unsigned long);
+ else if (strcmp(type, "bool") == 0)
+ size = sizeof(bool);
else if (strcmp(type, "pid_t") == 0)
size = sizeof(pid_t);
else if (strcmp(type, "gfp_t") == 0)
@@ -226,12 +273,14 @@ static const char *synth_field_fmt(char *type)
fmt = "%ld";
else if (strcmp(type, "unsigned long") == 0)
fmt = "%lu";
+ else if (strcmp(type, "bool") == 0)
+ fmt = "%d";
else if (strcmp(type, "pid_t") == 0)
fmt = "%d";
else if (strcmp(type, "gfp_t") == 0)
fmt = "%x";
else if (synth_field_is_string(type))
- fmt = "%s";
+ fmt = "%.*s";
return fmt;
}
@@ -290,10 +339,27 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
/* parameter values */
if (se->fields[i]->is_string) {
- trace_seq_printf(s, print_fmt, se->fields[i]->name,
- (char *)&entry->fields[n_u64],
- i == se->n_fields - 1 ? "" : " ");
- n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+ if (se->fields[i]->is_dynamic) {
+ u32 offset, data_offset;
+ char *str_field;
+
+ offset = (u32)entry->fields[n_u64];
+ data_offset = offset & 0xffff;
+
+ str_field = (char *)entry + data_offset;
+
+ trace_seq_printf(s, print_fmt, se->fields[i]->name,
+ STR_VAR_LEN_MAX,
+ str_field,
+ i == se->n_fields - 1 ? "" : " ");
+ n_u64++;
+ } else {
+ trace_seq_printf(s, print_fmt, se->fields[i]->name,
+ STR_VAR_LEN_MAX,
+ (char *)&entry->fields[n_u64],
+ i == se->n_fields - 1 ? "" : " ");
+ n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+ }
} else {
struct trace_print_flags __flags[] = {
__def_gfpflag_names, {-1, NULL} };
@@ -325,16 +391,52 @@ static struct trace_event_functions synth_event_funcs = {
.trace = print_synth_event
};
+static unsigned int trace_string(struct synth_trace_event *entry,
+ struct synth_event *event,
+ char *str_val,
+ bool is_dynamic,
+ unsigned int data_size,
+ unsigned int *n_u64)
+{
+ unsigned int len = 0;
+ char *str_field;
+
+ if (is_dynamic) {
+ u32 data_offset;
+
+ data_offset = offsetof(typeof(*entry), fields);
+ data_offset += event->n_u64 * sizeof(u64);
+ data_offset += data_size;
+
+ str_field = (char *)entry + data_offset;
+
+ len = strlen(str_val) + 1;
+ strscpy(str_field, str_val, len);
+
+ data_offset |= len << 16;
+ *(u32 *)&entry->fields[*n_u64] = data_offset;
+
+ (*n_u64)++;
+ } else {
+ str_field = (char *)&entry->fields[*n_u64];
+
+ strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+ (*n_u64) += STR_VAR_LEN_MAX / sizeof(u64);
+ }
+
+ return len;
+}
+
static notrace void trace_event_raw_event_synth(void *__data,
u64 *var_ref_vals,
unsigned int *var_ref_idx)
{
+ unsigned int i, n_u64, val_idx, len, data_size = 0;
struct trace_event_file *trace_file = __data;
struct synth_trace_event *entry;
struct trace_event_buffer fbuffer;
struct trace_buffer *buffer;
struct synth_event *event;
- unsigned int i, n_u64, val_idx;
int fields_size = 0;
event = trace_file->event_call->data;
@@ -344,6 +446,18 @@ static notrace void trace_event_raw_event_synth(void *__data,
fields_size = event->n_u64 * sizeof(u64);
+ for (i = 0; i < event->n_dynamic_fields; i++) {
+ unsigned int field_pos = event->dynamic_fields[i]->field_pos;
+ char *str_val;
+
+ val_idx = var_ref_idx[field_pos];
+ str_val = (char *)(long)var_ref_vals[val_idx];
+
+ len = strlen(str_val) + 1;
+
+ fields_size += len;
+ }
+
/*
* Avoid ring buffer recursion detection, as this event
* is being performed within another event.
@@ -360,10 +474,11 @@ static notrace void trace_event_raw_event_synth(void *__data,
val_idx = var_ref_idx[i];
if (event->fields[i]->is_string) {
char *str_val = (char *)(long)var_ref_vals[val_idx];
- char *str_field = (char *)&entry->fields[n_u64];
- strscpy(str_field, str_val, STR_VAR_LEN_MAX);
- n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+ len = trace_string(entry, event, str_val,
+ event->fields[i]->is_dynamic,
+ data_size, &n_u64);
+ data_size += len; /* only dynamic string increments */
} else {
struct synth_field *field = event->fields[i];
u64 val = var_ref_vals[val_idx];
@@ -422,8 +537,13 @@ static int __set_synth_event_print_fmt(struct synth_event *event,
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
for (i = 0; i < event->n_fields; i++) {
- pos += snprintf(buf + pos, LEN_OR_ZERO,
- ", REC->%s", event->fields[i]->name);
+ if (event->fields[i]->is_string &&
+ event->fields[i]->is_dynamic)
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ ", __get_str(%s)", event->fields[i]->name);
+ else
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ ", REC->%s", event->fields[i]->name);
}
#undef LEN_OR_ZERO
@@ -465,13 +585,16 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
struct synth_field *field;
const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
int len, ret = 0;
+ ssize_t size;
if (field_type[0] == ';')
field_type++;
if (!strcmp(field_type, "unsigned")) {
- if (argc < 3)
+ if (argc < 3) {
+ synth_err(SYNTH_ERR_INCOMPLETE_TYPE, errpos(field_type));
return ERR_PTR(-EINVAL);
+ }
prefix = "unsigned ";
field_type = argv[1];
field_name = argv[2];
@@ -497,12 +620,23 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
ret = -ENOMEM;
goto free;
}
+ if (!is_good_name(field->name)) {
+ synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name));
+ ret = -EINVAL;
+ goto free;
+ }
if (field_type[0] == ';')
field_type++;
len = strlen(field_type) + 1;
- if (array)
- len += strlen(array);
+
+ if (array) {
+ int l = strlen(array);
+
+ if (l && array[l - 1] == ';')
+ l--;
+ len += l;
+ }
if (prefix)
len += strlen(prefix);
@@ -520,17 +654,40 @@ static struct synth_field *parse_synth_field(int argc, const char **argv,
field->type[len - 1] = '\0';
}
- field->size = synth_field_size(field->type);
- if (!field->size) {
+ size = synth_field_size(field->type);
+ if (size < 0) {
+ synth_err(SYNTH_ERR_INVALID_TYPE, errpos(field_type));
ret = -EINVAL;
goto free;
+ } else if (size == 0) {
+ if (synth_field_is_string(field->type)) {
+ char *type;
+
+ type = kzalloc(sizeof("__data_loc ") + strlen(field->type) + 1, GFP_KERNEL);
+ if (!type) {
+ ret = -ENOMEM;
+ goto free;
+ }
+
+ strcat(type, "__data_loc ");
+ strcat(type, field->type);
+ kfree(field->type);
+ field->type = type;
+
+ field->is_dynamic = true;
+ size = sizeof(u64);
+ } else {
+ synth_err(SYNTH_ERR_INVALID_TYPE, errpos(field_type));
+ ret = -EINVAL;
+ goto free;
+ }
}
+ field->size = size;
if (synth_field_is_string(field->type))
field->is_string = true;
field->is_signed = synth_field_signed(field->type);
-
out:
return field;
free:
@@ -661,6 +818,7 @@ static void free_synth_event(struct synth_event *event)
free_synth_field(event->fields[i]);
kfree(event->fields);
+ kfree(event->dynamic_fields);
kfree(event->name);
kfree(event->class.system);
free_synth_tracepoint(event->tp);
@@ -671,8 +829,8 @@ static void free_synth_event(struct synth_event *event)
static struct synth_event *alloc_synth_event(const char *name, int n_fields,
struct synth_field **fields)
{
+ unsigned int i, j, n_dynamic_fields = 0;
struct synth_event *event;
- unsigned int i;
event = kzalloc(sizeof(*event), GFP_KERNEL);
if (!event) {
@@ -694,11 +852,33 @@ static struct synth_event *alloc_synth_event(const char *name, int n_fields,
goto out;
}
+ for (i = 0; i < n_fields; i++)
+ if (fields[i]->is_dynamic)
+ n_dynamic_fields++;
+
+ if (n_dynamic_fields) {
+ event->dynamic_fields = kcalloc(n_dynamic_fields,
+ sizeof(*event->dynamic_fields),
+ GFP_KERNEL);
+ if (!event->dynamic_fields) {
+ free_synth_event(event);
+ event = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ }
+
dyn_event_init(&event->devent, &synth_event_ops);
- for (i = 0; i < n_fields; i++)
+ for (i = 0, j = 0; i < n_fields; i++) {
event->fields[i] = fields[i];
+ if (fields[i]->is_dynamic) {
+ event->dynamic_fields[j] = fields[i];
+ event->dynamic_fields[j]->field_pos = i;
+ event->dynamic_fields[j++] = fields[i];
+ event->n_dynamic_fields++;
+ }
+ }
event->n_fields = n_fields;
out:
return event;
@@ -710,6 +890,10 @@ static int synth_event_check_arg_fn(void *data)
int size;
size = synth_field_size((char *)arg_pair->lhs);
+ if (size == 0) {
+ if (strstr((char *)arg_pair->lhs, "["))
+ return 0;
+ }
return size ? 0 : -EINVAL;
}
@@ -971,12 +1155,47 @@ int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name,
}
EXPORT_SYMBOL_GPL(synth_event_gen_cmd_array_start);
+static int save_cmdstr(int argc, const char *name, const char **argv)
+{
+ struct seq_buf s;
+ char *buf;
+ int i;
+
+ buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ seq_buf_init(&s, buf, MAX_DYNEVENT_CMD_LEN);
+
+ seq_buf_puts(&s, name);
+
+ for (i = 0; i < argc; i++) {
+ seq_buf_putc(&s, ' ');
+ seq_buf_puts(&s, argv[i]);
+ }
+
+ if (!seq_buf_buffer_left(&s)) {
+ synth_err(SYNTH_ERR_CMD_TOO_LONG, 0);
+ kfree(buf);
+ return -EINVAL;
+ }
+ buf[s.len] = 0;
+ last_cmd_set(buf);
+
+ kfree(buf);
+ return 0;
+}
+
static int __create_synth_event(int argc, const char *name, const char **argv)
{
struct synth_field *field, *fields[SYNTH_FIELDS_MAX];
struct synth_event *event = NULL;
int i, consumed = 0, n_fields = 0, ret = 0;
+ ret = save_cmdstr(argc, name, argv);
+ if (ret)
+ return ret;
+
/*
* Argument syntax:
* - Add synthetic event: <event_name> field[;field] ...
@@ -984,13 +1203,22 @@ static int __create_synth_event(int argc, const char *name, const char **argv)
* where 'field' = type field_name
*/
- if (name[0] == '\0' || argc < 1)
+ if (name[0] == '\0' || argc < 1) {
+ synth_err(SYNTH_ERR_CMD_INCOMPLETE, 0);
return -EINVAL;
+ }
mutex_lock(&event_mutex);
+ if (!is_good_name(name)) {
+ synth_err(SYNTH_ERR_BAD_NAME, errpos(name));
+ ret = -EINVAL;
+ goto out;
+ }
+
event = find_synth_event(name);
if (event) {
+ synth_err(SYNTH_ERR_EVENT_EXISTS, errpos(name));
ret = -EEXIST;
goto out;
}
@@ -999,6 +1227,7 @@ static int __create_synth_event(int argc, const char *name, const char **argv)
if (strcmp(argv[i], ";") == 0)
continue;
if (n_fields == SYNTH_FIELDS_MAX) {
+ synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0);
ret = -EINVAL;
goto err;
}
@@ -1013,6 +1242,7 @@ static int __create_synth_event(int argc, const char *name, const char **argv)
}
if (i < argc && strcmp(argv[i], ";") != 0) {
+ synth_err(SYNTH_ERR_INVALID_FIELD, errpos(argv[i]));
ret = -EINVAL;
goto err;
}
@@ -1198,10 +1428,9 @@ void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen)
EXPORT_SYMBOL_GPL(synth_event_cmd_init);
static inline int
-__synth_event_trace_start(struct trace_event_file *file,
- struct synth_event_trace_state *trace_state)
+__synth_event_trace_init(struct trace_event_file *file,
+ struct synth_event_trace_state *trace_state)
{
- int entry_size, fields_size = 0;
int ret = 0;
memset(trace_state, '\0', sizeof(*trace_state));
@@ -1211,7 +1440,7 @@ __synth_event_trace_start(struct trace_event_file *file,
* ENABLED bit is set (which attaches the probe thus allowing
* this code to be called, etc). Because this is called
* directly by the user, we don't have that but we still need
- * to honor not logging when disabled. For the the iterated
+ * to honor not logging when disabled. For the iterated
* trace case, we save the enabed state upon start and just
* ignore the following data calls.
*/
@@ -1223,8 +1452,20 @@ __synth_event_trace_start(struct trace_event_file *file,
}
trace_state->event = file->event_call->data;
+out:
+ return ret;
+}
+
+static inline int
+__synth_event_trace_start(struct trace_event_file *file,
+ struct synth_event_trace_state *trace_state,
+ int dynamic_fields_size)
+{
+ int entry_size, fields_size = 0;
+ int ret = 0;
fields_size = trace_state->event->n_u64 * sizeof(u64);
+ fields_size += dynamic_fields_size;
/*
* Avoid ring buffer recursion detection, as this event
@@ -1241,7 +1482,7 @@ __synth_event_trace_start(struct trace_event_file *file,
ring_buffer_nest_end(trace_state->buffer);
ret = -EINVAL;
}
-out:
+
return ret;
}
@@ -1274,23 +1515,46 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state)
*/
int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
{
+ unsigned int i, n_u64, len, data_size = 0;
struct synth_event_trace_state state;
- unsigned int i, n_u64;
va_list args;
int ret;
- ret = __synth_event_trace_start(file, &state);
+ ret = __synth_event_trace_init(file, &state);
if (ret) {
if (ret == -ENOENT)
ret = 0; /* just disabled, not really an error */
return ret;
}
+ if (state.event->n_dynamic_fields) {
+ va_start(args, n_vals);
+
+ for (i = 0; i < state.event->n_fields; i++) {
+ u64 val = va_arg(args, u64);
+
+ if (state.event->fields[i]->is_string &&
+ state.event->fields[i]->is_dynamic) {
+ char *str_val = (char *)(long)val;
+
+ data_size += strlen(str_val) + 1;
+ }
+ }
+
+ va_end(args);
+ }
+
+ ret = __synth_event_trace_start(file, &state, data_size);
+ if (ret)
+ return ret;
+
if (n_vals != state.event->n_fields) {
ret = -EINVAL;
goto out;
}
+ data_size = 0;
+
va_start(args, n_vals);
for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
u64 val;
@@ -1299,10 +1563,11 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
if (state.event->fields[i]->is_string) {
char *str_val = (char *)(long)val;
- char *str_field = (char *)&state.entry->fields[n_u64];
- strscpy(str_field, str_val, STR_VAR_LEN_MAX);
- n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+ len = trace_string(state.entry, state.event, str_val,
+ state.event->fields[i]->is_dynamic,
+ data_size, &n_u64);
+ data_size += len; /* only dynamic string increments */
} else {
struct synth_field *field = state.event->fields[i];
@@ -1355,29 +1620,46 @@ EXPORT_SYMBOL_GPL(synth_event_trace);
int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
unsigned int n_vals)
{
+ unsigned int i, n_u64, field_pos, len, data_size = 0;
struct synth_event_trace_state state;
- unsigned int i, n_u64;
+ char *str_val;
int ret;
- ret = __synth_event_trace_start(file, &state);
+ ret = __synth_event_trace_init(file, &state);
if (ret) {
if (ret == -ENOENT)
ret = 0; /* just disabled, not really an error */
return ret;
}
+ if (state.event->n_dynamic_fields) {
+ for (i = 0; i < state.event->n_dynamic_fields; i++) {
+ field_pos = state.event->dynamic_fields[i]->field_pos;
+ str_val = (char *)(long)vals[field_pos];
+ len = strlen(str_val) + 1;
+ data_size += len;
+ }
+ }
+
+ ret = __synth_event_trace_start(file, &state, data_size);
+ if (ret)
+ return ret;
+
if (n_vals != state.event->n_fields) {
ret = -EINVAL;
goto out;
}
+ data_size = 0;
+
for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
if (state.event->fields[i]->is_string) {
char *str_val = (char *)(long)vals[i];
- char *str_field = (char *)&state.entry->fields[n_u64];
- strscpy(str_field, str_val, STR_VAR_LEN_MAX);
- n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+ len = trace_string(state.entry, state.event, str_val,
+ state.event->fields[i]->is_dynamic,
+ data_size, &n_u64);
+ data_size += len; /* only dynamic string increments */
} else {
struct synth_field *field = state.event->fields[i];
u64 val = vals[i];
@@ -1445,9 +1727,17 @@ int synth_event_trace_start(struct trace_event_file *file,
if (!trace_state)
return -EINVAL;
- ret = __synth_event_trace_start(file, trace_state);
- if (ret == -ENOENT)
- ret = 0; /* just disabled, not really an error */
+ ret = __synth_event_trace_init(file, trace_state);
+ if (ret) {
+ if (ret == -ENOENT)
+ ret = 0; /* just disabled, not really an error */
+ return ret;
+ }
+
+ if (trace_state->event->n_dynamic_fields)
+ return -ENOTSUPP;
+
+ ret = __synth_event_trace_start(file, trace_state, 0);
return ret;
}
@@ -1508,6 +1798,11 @@ static int __synth_event_add_val(const char *field_name, u64 val,
char *str_val = (char *)(long)val;
char *str_field;
+ if (field->is_dynamic) { /* add_val can't do dynamic strings */
+ ret = -EINVAL;
+ goto out;
+ }
+
if (!str_val) {
ret = -EINVAL;
goto out;
@@ -1679,14 +1974,22 @@ static int __synth_event_show(struct seq_file *m, struct synth_event *event)
{
struct synth_field *field;
unsigned int i;
+ char *type, *t;
seq_printf(m, "%s\t", event->name);
for (i = 0; i < event->n_fields; i++) {
field = event->fields[i];
+ type = field->type;
+ t = strstr(type, "__data_loc");
+ if (t) { /* __data_loc belongs in format but not event desc */
+ t += sizeof("__data_loc");
+ type = t;
+ }
+
/* parameter values */
- seq_printf(m, "%s %s%s", field->type, field->name,
+ seq_printf(m, "%s %s%s", type, field->name,
i == event->n_fields - 1 ? "" : "; ");
}
@@ -1754,25 +2057,31 @@ static const struct file_operations synth_events_fops = {
.release = seq_release,
};
-static __init int trace_events_synth_init(void)
+/*
+ * Register dynevent at core_initcall. This allows kernel to setup kprobe
+ * events in postcore_initcall without tracefs.
+ */
+static __init int trace_events_synth_init_early(void)
{
- struct dentry *entry = NULL;
- struct dentry *d_tracer;
int err = 0;
err = dyn_event_register(&synth_event_ops);
- if (err) {
+ if (err)
pr_warn("Could not register synth_event_ops\n");
- return err;
- }
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer)) {
- err = PTR_ERR(d_tracer);
+ return err;
+}
+core_initcall(trace_events_synth_init_early);
+
+static __init int trace_events_synth_init(void)
+{
+ struct dentry *entry = NULL;
+ int err = 0;
+ err = tracing_init_dentry();
+ if (err)
goto err;
- }
- entry = tracefs_create_file("synthetic_events", 0644, d_tracer,
+ entry = tracefs_create_file("synthetic_events", 0644, NULL,
NULL, &synth_events_fops);
if (!entry) {
err = -ENODEV;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index dd4dff71d89a..2c2126e1871d 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -34,10 +34,14 @@ enum {
TRACE_FUNC_OPT_STACK = 0x1,
};
-static int allocate_ftrace_ops(struct trace_array *tr)
+int ftrace_allocate_ftrace_ops(struct trace_array *tr)
{
struct ftrace_ops *ops;
+ /* The top level array uses the "global_ops" */
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+ return 0;
+
ops = kzalloc(sizeof(*ops), GFP_KERNEL);
if (!ops)
return -ENOMEM;
@@ -48,15 +52,19 @@ static int allocate_ftrace_ops(struct trace_array *tr)
tr->ops = ops;
ops->private = tr;
+
return 0;
}
+void ftrace_free_ftrace_ops(struct trace_array *tr)
+{
+ kfree(tr->ops);
+ tr->ops = NULL;
+}
int ftrace_create_function_files(struct trace_array *tr,
struct dentry *parent)
{
- int ret;
-
/*
* The top level array uses the "global_ops", and the files are
* created on boot up.
@@ -64,9 +72,8 @@ int ftrace_create_function_files(struct trace_array *tr,
if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
return 0;
- ret = allocate_ftrace_ops(tr);
- if (ret)
- return ret;
+ if (!tr->ops)
+ return -EINVAL;
ftrace_create_filter_files(tr->ops, parent);
@@ -76,8 +83,7 @@ int ftrace_create_function_files(struct trace_array *tr,
void ftrace_destroy_function_files(struct trace_array *tr)
{
ftrace_destroy_filter_files(tr->ops);
- kfree(tr->ops);
- tr->ops = NULL;
+ ftrace_free_ftrace_ops(tr);
}
static int function_trace_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 4a9c49c08ec9..60d66278aa0d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1336,13 +1336,13 @@ static const struct file_operations graph_depth_fops = {
static __init int init_graph_tracefs(void)
{
- struct dentry *d_tracer;
+ int ret;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
- trace_create_file("max_graph_depth", 0644, d_tracer,
+ trace_create_file("max_graph_depth", 0644, NULL,
NULL, &graph_depth_fops);
return 0;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 17873e5d0353..c9ad5c6fbaad 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -538,14 +538,14 @@ static const struct file_operations window_fops = {
*/
static int init_tracefs(void)
{
- struct dentry *d_tracer;
+ int ret;
struct dentry *top_dir;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return -ENOMEM;
- top_dir = tracefs_create_dir("hwlat_detector", d_tracer);
+ top_dir = tracefs_create_dir("hwlat_detector", NULL);
if (!top_dir)
return -ENOMEM;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 19c00ee90945..b911e9f6d9f5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -718,6 +718,9 @@ static int trace_kprobe_create(int argc, const char *argv[])
* p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
* - Add kretprobe:
* r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
+ * Or
+ * p:[GRP/]EVENT] [MOD:]KSYM[+0]%return [FETCHARGS]
+ *
* Fetch args:
* $retval : fetch return value
* $stack : fetch stack address
@@ -747,7 +750,6 @@ static int trace_kprobe_create(int argc, const char *argv[])
switch (argv[0][0]) {
case 'r':
is_return = true;
- flags |= TPARG_FL_RETURN;
break;
case 'p':
break;
@@ -805,12 +807,26 @@ static int trace_kprobe_create(int argc, const char *argv[])
symbol = kstrdup(argv[1], GFP_KERNEL);
if (!symbol)
return -ENOMEM;
+
+ tmp = strchr(symbol, '%');
+ if (tmp) {
+ if (!strcmp(tmp, "%return")) {
+ *tmp = '\0';
+ is_return = true;
+ } else {
+ trace_probe_log_err(tmp - symbol, BAD_ADDR_SUFFIX);
+ goto parse_error;
+ }
+ }
+
/* TODO: support .init module functions */
ret = traceprobe_split_symbol_offset(symbol, &offset);
if (ret || offset < 0 || offset > UINT_MAX) {
trace_probe_log_err(0, BAD_PROBE_ADDR);
goto parse_error;
}
+ if (is_return)
+ flags |= TPARG_FL_RETURN;
if (kprobe_on_func_entry(NULL, symbol, offset))
flags |= TPARG_FL_FENTRY;
if (offset && is_return && !(flags & TPARG_FL_FENTRY)) {
@@ -1881,8 +1897,8 @@ static __init void setup_boot_kprobe_events(void)
}
/*
- * Register dynevent at subsys_initcall. This allows kernel to setup kprobe
- * events in fs_initcall without tracefs.
+ * Register dynevent at core_initcall. This allows kernel to setup kprobe
+ * events in postcore_initcall without tracefs.
*/
static __init int init_kprobe_trace_early(void)
{
@@ -1897,19 +1913,19 @@ static __init int init_kprobe_trace_early(void)
return 0;
}
-subsys_initcall(init_kprobe_trace_early);
+core_initcall(init_kprobe_trace_early);
/* Make a tracefs interface for controlling probe points */
static __init int init_kprobe_trace(void)
{
- struct dentry *d_tracer;
+ int ret;
struct dentry *entry;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
- entry = tracefs_create_file("kprobe_events", 0644, d_tracer,
+ entry = tracefs_create_file("kprobe_events", 0644, NULL,
NULL, &kprobe_events_ops);
/* Event list interface */
@@ -1917,7 +1933,7 @@ static __init int init_kprobe_trace(void)
pr_warn("Could not create tracefs 'kprobe_events' entry\n");
/* Profile interface */
- entry = tracefs_create_file("kprobe_profile", 0444, d_tracer,
+ entry = tracefs_create_file("kprobe_profile", 0444, NULL,
NULL, &kprobe_profile_ops);
if (!entry)
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index bb7783b90361..ff32476df072 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -367,13 +367,13 @@ static const struct file_operations ftrace_formats_fops = {
static __init int init_trace_printk_function_export(void)
{
- struct dentry *d_tracer;
+ int ret;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
- trace_create_file("printk_formats", 0444, d_tracer,
+ trace_create_file("printk_formats", 0444, NULL,
NULL, &ftrace_formats_fops);
return 0;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index a22b62813f8c..2f703a20c724 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -16,7 +16,6 @@
#include <linux/tracefs.h>
#include <linux/types.h>
#include <linux/string.h>
-#include <linux/ctype.h>
#include <linux/ptrace.h>
#include <linux/perf_event.h>
#include <linux/kprobes.h>
@@ -348,18 +347,6 @@ bool trace_probe_match_command_args(struct trace_probe *tp,
#define trace_probe_for_each_link_rcu(pos, tp) \
list_for_each_entry_rcu(pos, &(tp)->event->files, list)
-/* Check the name is good for event/group/fields */
-static inline bool is_good_name(const char *name)
-{
- if (!isalpha(*name) && *name != '_')
- return false;
- while (*++name != '\0') {
- if (!isalpha(*name) && !isdigit(*name) && *name != '_')
- return false;
- }
- return true;
-}
-
#define TPARG_FL_RETURN BIT(0)
#define TPARG_FL_KERNEL BIT(1)
#define TPARG_FL_FENTRY BIT(2)
@@ -404,6 +391,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(MAXACT_TOO_BIG, "Maxactive is too big"), \
C(BAD_PROBE_ADDR, "Invalid probed address or symbol"), \
C(BAD_RETPROBE, "Retprobe address must be an function entry"), \
+ C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \
C(NO_GROUP_NAME, "Group name is not specified"), \
C(GROUP_TOO_LONG, "Group name is too long"), \
C(BAD_GROUP_NAME, "Group name must follow the same rules as C identifiers"), \
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 98bba4764c52..c408423e5d65 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -554,20 +554,20 @@ __setup("stacktrace", enable_stacktrace);
static __init int stack_trace_init(void)
{
- struct dentry *d_tracer;
+ int ret;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
- trace_create_file("stack_max_size", 0644, d_tracer,
+ trace_create_file("stack_max_size", 0644, NULL,
&stack_trace_max_size, &stack_max_size_fops);
- trace_create_file("stack_trace", 0444, d_tracer,
+ trace_create_file("stack_trace", 0444, NULL,
NULL, &stack_trace_fops);
#ifdef CONFIG_DYNAMIC_FTRACE
- trace_create_file("stack_trace_filter", 0644, d_tracer,
+ trace_create_file("stack_trace_filter", 0644, NULL,
&trace_ops, &stack_trace_filter_fops);
#endif
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index d1fa19773cc8..8d141c3825a9 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -276,13 +276,13 @@ static const struct file_operations tracing_stat_fops = {
static int tracing_stat_init(void)
{
- struct dentry *d_tracing;
+ int ret;
- d_tracing = tracing_init_dentry();
- if (IS_ERR(d_tracing))
+ ret = tracing_init_dentry();
+ if (ret)
return -ENODEV;
- stat_dir = tracefs_create_dir("trace_stat", d_tracing);
+ stat_dir = tracefs_create_dir("trace_stat", NULL);
if (!stat_dir) {
pr_warn("Could not create tracefs 'trace_stat' entry\n");
return -ENOMEM;
diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h
index ac35c45207c4..6e146b959dcd 100644
--- a/kernel/trace/trace_synth.h
+++ b/kernel/trace/trace_synth.h
@@ -7,7 +7,7 @@
#define SYNTH_SYSTEM "synthetic"
#define SYNTH_FIELDS_MAX 32
-#define STR_VAR_LEN_MAX 32 /* must be multiple of sizeof(u64) */
+#define STR_VAR_LEN_MAX MAX_FILTER_STR_VAL /* must be multiple of sizeof(u64) */
struct synth_field {
char *type;
@@ -16,6 +16,8 @@ struct synth_field {
unsigned int offset;
bool is_signed;
bool is_string;
+ bool is_dynamic;
+ bool field_pos;
};
struct synth_event {
@@ -24,6 +26,8 @@ struct synth_event {
char *name;
struct synth_field **fields;
unsigned int n_fields;
+ struct synth_field **dynamic_fields;
+ unsigned int n_dynamic_fields;
unsigned int n_u64;
struct trace_event_class class;
struct trace_event_call call;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index f4286c9bdeb4..3cf7128e1ad3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -528,7 +528,7 @@ end:
/*
* Argument syntax:
- * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS]
+ * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET[%return][(REF)] [FETCHARGS]
*/
static int trace_uprobe_create(int argc, const char **argv)
{
@@ -617,6 +617,19 @@ static int trace_uprobe_create(int argc, const char **argv)
}
}
+ /* Check if there is %return suffix */
+ tmp = strchr(arg, '%');
+ if (tmp) {
+ if (!strcmp(tmp, "%return")) {
+ *tmp = '\0';
+ is_return = true;
+ } else {
+ trace_probe_log_err(tmp - filename, BAD_ADDR_SUFFIX);
+ ret = -EINVAL;
+ goto fail_address_parse;
+ }
+ }
+
/* Parse uprobe offset. */
ret = kstrtoul(arg, 0, &offset);
if (ret) {
@@ -1625,21 +1638,20 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call)
/* Make a trace interface for controling probe points */
static __init int init_uprobe_trace(void)
{
- struct dentry *d_tracer;
int ret;
ret = dyn_event_register(&trace_uprobe_ops);
if (ret)
return ret;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
- trace_create_file("uprobe_events", 0644, d_tracer,
+ trace_create_file("uprobe_events", 0644, NULL,
NULL, &uprobe_events_ops);
/* Profile interface */
- trace_create_file("uprobe_profile", 0444, d_tracer,
+ trace_create_file("uprobe_profile", 0444, NULL,
NULL, &uprobe_profile_ops);
return 0;
}
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 74738c9856f1..4b50fc0cb12c 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -260,7 +260,7 @@ int tracing_map_add_var(struct tracing_map *map)
* to use cmp_fn.
*
* A key can be a subset of a compound key; for that purpose, the
- * offset param is used to describe where within the the compound key
+ * offset param is used to describe where within the compound key
* the key referenced by this key field resides.
*
* Return: The index identifying the field in the map and associated
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index e0878f5f74b1..eb92027817a7 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -14,18 +14,19 @@
#include <linux/kernel.h>
#include <linux/bootconfig.h>
-static int xbc_show_value(struct xbc_node *node)
+static int xbc_show_value(struct xbc_node *node, bool semicolon)
{
- const char *val;
+ const char *val, *eol;
char q;
int i = 0;
+ eol = semicolon ? ";\n" : "\n";
xbc_array_for_each_value(node, val) {
if (strchr(val, '"'))
q = '\'';
else
q = '"';
- printf("%c%s%c%s", q, val, q, node->next ? ", " : ";\n");
+ printf("%c%s%c%s", q, val, q, node->next ? ", " : eol);
i++;
}
return i;
@@ -53,7 +54,7 @@ static void xbc_show_compact_tree(void)
continue;
} else if (cnode && xbc_node_is_value(cnode)) {
printf("%s = ", xbc_node_get_data(node));
- xbc_show_value(cnode);
+ xbc_show_value(cnode, true);
} else {
printf("%s;\n", xbc_node_get_data(node));
}
@@ -77,8 +78,28 @@ static void xbc_show_compact_tree(void)
}
}
+static void xbc_show_list(void)
+{
+ char key[XBC_KEYLEN_MAX];
+ struct xbc_node *leaf;
+ const char *val;
+ int ret = 0;
+
+ xbc_for_each_key_value(leaf, val) {
+ ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX);
+ if (ret < 0)
+ break;
+ printf("%s = ", key);
+ if (!val || val[0] == '\0') {
+ printf("\"\"\n");
+ continue;
+ }
+ xbc_show_value(xbc_node_get_child(leaf), false);
+ }
+}
+
/* Simple real checksum */
-int checksum(unsigned char *buf, int len)
+static int checksum(unsigned char *buf, int len)
{
int i, sum = 0;
@@ -90,7 +111,7 @@ int checksum(unsigned char *buf, int len)
#define PAGE_SIZE 4096
-int load_xbc_fd(int fd, char **buf, int size)
+static int load_xbc_fd(int fd, char **buf, int size)
{
int ret;
@@ -107,7 +128,7 @@ int load_xbc_fd(int fd, char **buf, int size)
}
/* Return the read size or -errno */
-int load_xbc_file(const char *path, char **buf)
+static int load_xbc_file(const char *path, char **buf)
{
struct stat stat;
int fd, ret;
@@ -126,7 +147,7 @@ int load_xbc_file(const char *path, char **buf)
return ret;
}
-int load_xbc_from_initrd(int fd, char **buf)
+static int load_xbc_from_initrd(int fd, char **buf)
{
struct stat stat;
int ret;
@@ -195,10 +216,55 @@ int load_xbc_from_initrd(int fd, char **buf)
return size;
}
-int show_xbc(const char *path)
+static void show_xbc_error(const char *data, const char *msg, int pos)
+{
+ int lin = 1, col, i;
+
+ if (pos < 0) {
+ pr_err("Error: %s.\n", msg);
+ return;
+ }
+
+ /* Note that pos starts from 0 but lin and col should start from 1. */
+ col = pos + 1;
+ for (i = 0; i < pos; i++) {
+ if (data[i] == '\n') {
+ lin++;
+ col = pos - i;
+ }
+ }
+ pr_err("Parse Error: %s at %d:%d\n", msg, lin, col);
+
+}
+
+static int init_xbc_with_error(char *buf, int len)
+{
+ char *copy = strdup(buf);
+ const char *msg;
+ int ret, pos;
+
+ if (!copy)
+ return -ENOMEM;
+
+ ret = xbc_init(buf, &msg, &pos);
+ if (ret < 0)
+ show_xbc_error(copy, msg, pos);
+ free(copy);
+
+ return ret;
+}
+
+static int show_xbc(const char *path, bool list)
{
int ret, fd;
char *buf = NULL;
+ struct stat st;
+
+ ret = stat(path, &st);
+ if (ret < 0) {
+ pr_err("Failed to stat %s: %d\n", path, -errno);
+ return -errno;
+ }
fd = open(path, O_RDONLY);
if (fd < 0) {
@@ -207,20 +273,33 @@ int show_xbc(const char *path)
}
ret = load_xbc_from_initrd(fd, &buf);
+ close(fd);
if (ret < 0) {
pr_err("Failed to load a boot config from initrd: %d\n", ret);
goto out;
}
- xbc_show_compact_tree();
+ /* Assume a bootconfig file if it is enough small */
+ if (ret == 0 && st.st_size <= XBC_DATA_MAX) {
+ ret = load_xbc_file(path, &buf);
+ if (ret < 0) {
+ pr_err("Failed to load a boot config: %d\n", ret);
+ goto out;
+ }
+ if (init_xbc_with_error(buf, ret) < 0)
+ goto out;
+ }
+ if (list)
+ xbc_show_list();
+ else
+ xbc_show_compact_tree();
ret = 0;
out:
- close(fd);
free(buf);
return ret;
}
-int delete_xbc(const char *path)
+static int delete_xbc(const char *path)
{
struct stat stat;
int ret = 0, fd, size;
@@ -251,28 +330,7 @@ int delete_xbc(const char *path)
return ret;
}
-static void show_xbc_error(const char *data, const char *msg, int pos)
-{
- int lin = 1, col, i;
-
- if (pos < 0) {
- pr_err("Error: %s.\n", msg);
- return;
- }
-
- /* Note that pos starts from 0 but lin and col should start from 1. */
- col = pos + 1;
- for (i = 0; i < pos; i++) {
- if (data[i] == '\n') {
- lin++;
- col = pos - i;
- }
- }
- pr_err("Parse Error: %s at %d:%d\n", msg, lin, col);
-
-}
-
-int apply_xbc(const char *path, const char *xbc_path)
+static int apply_xbc(const char *path, const char *xbc_path)
{
u32 size, csum;
char *buf, *data;
@@ -349,14 +407,16 @@ out:
return ret;
}
-int usage(void)
+static int usage(void)
{
printf("Usage: bootconfig [OPTIONS] <INITRD>\n"
+ "Or bootconfig <CONFIG>\n"
" Apply, delete or show boot config to initrd.\n"
" Options:\n"
" -a <config>: Apply boot config to initrd\n"
- " -d : Delete boot config file from initrd\n\n"
- " If no option is given, show current applied boot config.\n");
+ " -d : Delete boot config file from initrd\n"
+ " -l : list boot config in initrd or file\n\n"
+ " If no option is given, show the bootconfig in the given file.\n");
return -1;
}
@@ -364,10 +424,10 @@ int main(int argc, char **argv)
{
char *path = NULL;
char *apply = NULL;
- bool delete = false;
+ bool delete = false, list = false;
int opt;
- while ((opt = getopt(argc, argv, "hda:")) != -1) {
+ while ((opt = getopt(argc, argv, "hda:l")) != -1) {
switch (opt) {
case 'd':
delete = true;
@@ -375,14 +435,17 @@ int main(int argc, char **argv)
case 'a':
apply = optarg;
break;
+ case 'l':
+ list = true;
+ break;
case 'h':
default:
return usage();
}
}
- if (apply && delete) {
- pr_err("Error: You can not specify both -a and -d at once.\n");
+ if ((apply && delete) || (delete && list) || (apply && list)) {
+ pr_err("Error: You can give one of -a, -d or -l at once.\n");
return usage();
}
@@ -398,5 +461,5 @@ int main(int argc, char **argv)
else if (delete)
return delete_xbc(path);
- return show_xbc(path);
+ return show_xbc(path, list);
}
diff --git a/tools/bootconfig/scripts/bconf2ftrace.sh b/tools/bootconfig/scripts/bconf2ftrace.sh
new file mode 100755
index 000000000000..595e164dc352
--- /dev/null
+++ b/tools/bootconfig/scripts/bconf2ftrace.sh
@@ -0,0 +1,199 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+usage() {
+ echo "Ftrace boottime trace test tool"
+ echo "Usage: $0 [--apply|--init] [--debug] BOOTCONFIG-FILE"
+ echo " --apply: Test actual apply to tracefs (need sudo)"
+ echo " --init: Initialize ftrace before applying (imply --apply)"
+ exit 1
+}
+
+[ $# -eq 0 ] && usage
+
+BCONF=
+DEBUG=
+APPLY=
+INIT=
+while [ x"$1" != x ]; do
+ case "$1" in
+ "--debug")
+ DEBUG=$1;;
+ "--apply")
+ APPLY=$1;;
+ "--init")
+ APPLY=$1
+ INIT=$1;;
+ *)
+ [ ! -f $1 ] && usage
+ BCONF=$1;;
+ esac
+ shift 1
+done
+
+if [ x"$APPLY" != x ]; then
+ if [ `id -u` -ne 0 ]; then
+ echo "This must be run by root user. Try sudo." 1>&2
+ exec sudo $0 $DEBUG $APPLY $BCONF
+ fi
+fi
+
+run_cmd() { # command
+ echo "$*"
+ if [ x"$APPLY" != x ]; then # apply command
+ eval $*
+ fi
+}
+
+if [ x"$DEBUG" != x ]; then
+ set -x
+fi
+
+TRACEFS=`grep -m 1 -w tracefs /proc/mounts | cut -f 2 -d " "`
+if [ -z "$TRACEFS" ]; then
+ if ! grep -wq debugfs /proc/mounts; then
+ echo "Error: No tracefs/debugfs was mounted." 1>&2
+ exit 1
+ fi
+ TRACEFS=`grep -m 1 -w debugfs /proc/mounts | cut -f 2 -d " "`/tracing
+ if [ ! -d $TRACEFS ]; then
+ echo "Error: ftrace is not enabled on this kernel." 1>&2
+ exit 1
+ fi
+fi
+
+if [ x"$INIT" != x ]; then
+ . `dirname $0`/ftrace.sh
+ (cd $TRACEFS; initialize_ftrace)
+fi
+
+. `dirname $0`/xbc.sh
+
+######## main #########
+set -e
+
+xbc_init $BCONF
+
+set_value_of() { # key file
+ if xbc_has_key $1; then
+ val=`xbc_get_val $1 1`
+ run_cmd "echo '$val' >> $2"
+ fi
+}
+
+set_array_of() { # key file
+ if xbc_has_key $1; then
+ xbc_get_val $1 | while read line; do
+ run_cmd "echo '$line' >> $2"
+ done
+ fi
+}
+
+compose_synth() { # event_name branch
+ echo -n "$1 "
+ xbc_get_val $2 | while read field; do echo -n "$field; "; done
+}
+
+setup_event() { # prefix group event [instance]
+ branch=$1.$2.$3
+ if [ "$4" ]; then
+ eventdir="$TRACEFS/instances/$4/events/$2/$3"
+ else
+ eventdir="$TRACEFS/events/$2/$3"
+ fi
+ case $2 in
+ kprobes)
+ xbc_get_val ${branch}.probes | while read line; do
+ run_cmd "echo 'p:kprobes/$3 $line' >> $TRACEFS/kprobe_events"
+ done
+ ;;
+ synthetic)
+ run_cmd "echo '`compose_synth $3 ${branch}.fields`' >> $TRACEFS/synthetic_events"
+ ;;
+ esac
+
+ set_value_of ${branch}.filter ${eventdir}/filter
+ set_array_of ${branch}.actions ${eventdir}/trigger
+
+ if xbc_has_key ${branch}.enable; then
+ run_cmd "echo 1 > ${eventdir}/enable"
+ fi
+}
+
+setup_events() { # prefix("ftrace" or "ftrace.instance.INSTANCE") [instance]
+ prefix="${1}.event"
+ if xbc_has_branch ${1}.event; then
+ for grpev in `xbc_subkeys ${1}.event 2`; do
+ setup_event $prefix ${grpev%.*} ${grpev#*.} $2
+ done
+ fi
+}
+
+size2kb() { # size[KB|MB]
+ case $1 in
+ *KB)
+ echo ${1%KB};;
+ *MB)
+ expr ${1%MB} \* 1024;;
+ *)
+ expr $1 / 1024 ;;
+ esac
+}
+
+setup_instance() { # [instance]
+ if [ "$1" ]; then
+ instance="ftrace.instance.${1}"
+ instancedir=$TRACEFS/instances/$1
+ else
+ instance="ftrace"
+ instancedir=$TRACEFS
+ fi
+
+ set_array_of ${instance}.options ${instancedir}/trace_options
+ set_value_of ${instance}.trace_clock ${instancedir}/trace_clock
+ set_value_of ${instance}.cpumask ${instancedir}/tracing_cpumask
+ set_value_of ${instance}.tracer ${instancedir}/current_tracer
+ set_array_of ${instance}.ftrace.filters \
+ ${instancedir}/set_ftrace_filter
+ set_array_of ${instance}.ftrace.notrace \
+ ${instancedir}/set_ftrace_notrace
+
+ if xbc_has_key ${instance}.alloc_snapshot; then
+ run_cmd "echo 1 > ${instancedir}/snapshot"
+ fi
+
+ if xbc_has_key ${instance}.buffer_size; then
+ size=`xbc_get_val ${instance}.buffer_size 1`
+ size=`eval size2kb $size`
+ run_cmd "echo $size >> ${instancedir}/buffer_size_kb"
+ fi
+
+ setup_events ${instance} $1
+ set_array_of ${instance}.events ${instancedir}/set_event
+}
+
+# ftrace global configs (kernel.*)
+if xbc_has_key "kernel.dump_on_oops"; then
+ dump_mode=`xbc_get_val "kernel.dump_on_oops" 1`
+ [ "$dump_mode" ] && dump_mode=`eval echo $dump_mode` || dump_mode=1
+ run_cmd "echo \"$dump_mode\" > /proc/sys/kernel/ftrace_dump_on_oops"
+fi
+
+set_value_of kernel.fgraph_max_depth $TRACEFS/max_graph_depth
+set_array_of kernel.fgraph_filters $TRACEFS/set_graph_function
+set_array_of kernel.fgraph_notraces $TRACEFS/set_graph_notrace
+
+# Per-instance/per-event configs
+if ! xbc_has_branch "ftrace" ; then
+ exit 0
+fi
+
+setup_instance # root instance
+
+if xbc_has_branch "ftrace.instance"; then
+ for i in `xbc_subkeys "ftrace.instance" 1`; do
+ run_cmd "mkdir -p $TRACEFS/instances/$i"
+ setup_instance $i
+ done
+fi
+
diff --git a/tools/bootconfig/scripts/ftrace.sh b/tools/bootconfig/scripts/ftrace.sh
new file mode 100644
index 000000000000..186eed923041
--- /dev/null
+++ b/tools/bootconfig/scripts/ftrace.sh
@@ -0,0 +1,109 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+clear_trace() { # reset trace output
+ echo > trace
+}
+
+disable_tracing() { # stop trace recording
+ echo 0 > tracing_on
+}
+
+enable_tracing() { # start trace recording
+ echo 1 > tracing_on
+}
+
+reset_tracer() { # reset the current tracer
+ echo nop > current_tracer
+}
+
+reset_trigger_file() {
+ # remove action triggers first
+ grep -H ':on[^:]*(' $@ |
+ while read line; do
+ cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["`
+ file=`echo $line | cut -f1 -d:`
+ echo "!$cmd" >> $file
+ done
+ grep -Hv ^# $@ |
+ while read line; do
+ cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["`
+ file=`echo $line | cut -f1 -d:`
+ echo "!$cmd" > $file
+ done
+}
+
+reset_trigger() { # reset all current setting triggers
+ if [ -d events/synthetic ]; then
+ reset_trigger_file events/synthetic/*/trigger
+ fi
+ reset_trigger_file events/*/*/trigger
+}
+
+reset_events_filter() { # reset all current setting filters
+ grep -v ^none events/*/*/filter |
+ while read line; do
+ echo 0 > `echo $line | cut -f1 -d:`
+ done
+}
+
+reset_ftrace_filter() { # reset all triggers in set_ftrace_filter
+ if [ ! -f set_ftrace_filter ]; then
+ return 0
+ fi
+ echo > set_ftrace_filter
+ grep -v '^#' set_ftrace_filter | while read t; do
+ tr=`echo $t | cut -d: -f2`
+ if [ "$tr" = "" ]; then
+ continue
+ fi
+ if ! grep -q "$t" set_ftrace_filter; then
+ continue;
+ fi
+ name=`echo $t | cut -d: -f1 | cut -d' ' -f1`
+ if [ $tr = "enable_event" -o $tr = "disable_event" ]; then
+ tr=`echo $t | cut -d: -f2-4`
+ limit=`echo $t | cut -d: -f5`
+ else
+ tr=`echo $t | cut -d: -f2`
+ limit=`echo $t | cut -d: -f3`
+ fi
+ if [ "$limit" != "unlimited" ]; then
+ tr="$tr:$limit"
+ fi
+ echo "!$name:$tr" > set_ftrace_filter
+ done
+}
+
+disable_events() {
+ echo 0 > events/enable
+}
+
+clear_synthetic_events() { # reset all current synthetic events
+ grep -v ^# synthetic_events |
+ while read line; do
+ echo "!$line" >> synthetic_events
+ done
+}
+
+initialize_ftrace() { # Reset ftrace to initial-state
+# As the initial state, ftrace will be set to nop tracer,
+# no events, no triggers, no filters, no function filters,
+# no probes, and tracing on.
+ disable_tracing
+ reset_tracer
+ reset_trigger
+ reset_events_filter
+ reset_ftrace_filter
+ disable_events
+ [ -f set_event_pid ] && echo > set_event_pid
+ [ -f set_ftrace_pid ] && echo > set_ftrace_pid
+ [ -f set_ftrace_notrace ] && echo > set_ftrace_notrace
+ [ -f set_graph_function ] && echo | tee set_graph_*
+ [ -f stack_trace_filter ] && echo > stack_trace_filter
+ [ -f kprobe_events ] && echo > kprobe_events
+ [ -f uprobe_events ] && echo > uprobe_events
+ [ -f synthetic_events ] && echo > synthetic_events
+ [ -f snapshot ] && echo 0 > snapshot
+ clear_trace
+ enable_tracing
+}
diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh
new file mode 100755
index 000000000000..6c0d4b61e0c2
--- /dev/null
+++ b/tools/bootconfig/scripts/ftrace2bconf.sh
@@ -0,0 +1,244 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+usage() {
+ echo "Dump boot-time tracing bootconfig from ftrace"
+ echo "Usage: $0 [--debug] [ > BOOTCONFIG-FILE]"
+ exit 1
+}
+
+DEBUG=
+while [ x"$1" != x ]; do
+ case "$1" in
+ "--debug")
+ DEBUG=$1;;
+ -*)
+ usage
+ ;;
+ esac
+ shift 1
+done
+
+if [ x"$DEBUG" != x ]; then
+ set -x
+fi
+
+TRACEFS=`grep -m 1 -w tracefs /proc/mounts | cut -f 2 -d " "`
+if [ -z "$TRACEFS" ]; then
+ if ! grep -wq debugfs /proc/mounts; then
+ echo "Error: No tracefs/debugfs was mounted."
+ exit 1
+ fi
+ TRACEFS=`grep -m 1 -w debugfs /proc/mounts | cut -f 2 -d " "`/tracing
+ if [ ! -d $TRACEFS ]; then
+ echo "Error: ftrace is not enabled on this kernel." 1>&2
+ exit 1
+ fi
+fi
+
+######## main #########
+
+set -e
+
+emit_kv() { # key =|+= value
+ echo "$@"
+}
+
+global_options() {
+ val=`cat $TRACEFS/max_graph_depth`
+ [ $val != 0 ] && emit_kv kernel.fgraph_max_depth = $val
+ if grep -qv "^#" $TRACEFS/set_graph_function $TRACEFS/set_graph_notrace ; then
+ cat 1>&2 << EOF
+# WARN: kernel.fgraph_filters and kernel.fgraph_notrace are not supported, since the wild card expression was expanded and lost from memory.
+EOF
+ fi
+}
+
+kprobe_event_options() {
+ cat $TRACEFS/kprobe_events | while read p args; do
+ case $p in
+ r*)
+ cat 1>&2 << EOF
+# WARN: A return probe found but it is not supported by bootconfig. Skip it.
+EOF
+ continue;;
+ esac
+ p=${p#*:}
+ event=${p#*/}
+ group=${p%/*}
+ if [ $group != "kprobes" ]; then
+ cat 1>&2 << EOF
+# WARN: kprobes group name $group is changed to "kprobes" for bootconfig.
+EOF
+ fi
+ emit_kv $PREFIX.event.kprobes.$event.probes += $args
+ done
+}
+
+synth_event_options() {
+ cat $TRACEFS/synthetic_events | while read event fields; do
+ emit_kv $PREFIX.event.synthetic.$event.fields = `echo $fields | sed "s/;/,/g"`
+ done
+}
+
+# Variables resolver
+DEFINED_VARS=
+UNRESOLVED_EVENTS=
+
+defined_vars() { # event-dir
+ grep "^hist" $1/trigger | grep -o ':[a-zA-Z0-9]*='
+}
+referred_vars() {
+ grep "^hist" $1/trigger | grep -o '$[a-zA-Z0-9]*'
+}
+
+per_event_options() { # event-dir
+ evdir=$1
+ # Check the special event which has no filter and no trigger
+ [ ! -f $evdir/filter ] && return
+
+ if grep -q "^hist:" $evdir/trigger; then
+ # hist action can refer the undefined variables
+ __vars=`defined_vars $evdir`
+ for v in `referred_vars $evdir`; do
+ if echo $DEFINED_VARS $__vars | grep -vqw ${v#$}; then
+ # $v is not defined yet, defer it
+ UNRESOLVED_EVENTS="$UNRESOLVED_EVENTS $evdir"
+ return;
+ fi
+ done
+ DEFINED_VARS="$DEFINED_VARS "`defined_vars $evdir`
+ fi
+ grep -v "^#" $evdir/trigger | while read action active; do
+ emit_kv $PREFIX.event.$group.$event.actions += \'$action\'
+ done
+
+ # enable is not checked; this is done by set_event in the instance.
+ val=`cat $evdir/filter`
+ if [ "$val" != "none" ]; then
+ emit_kv $PREFIX.event.$group.$event.filter = "$val"
+ fi
+}
+
+retry_unresolved() {
+ unresolved=$UNRESOLVED_EVENTS
+ UNRESOLVED_EVENTS=
+ for evdir in $unresolved; do
+ event=${evdir##*/}
+ group=${evdir%/*}; group=${group##*/}
+ per_event_options $evdir
+ done
+}
+
+event_options() {
+ # PREFIX and INSTANCE must be set
+ if [ $PREFIX = "ftrace" ]; then
+ # define the dynamic events
+ kprobe_event_options
+ synth_event_options
+ fi
+ for group in `ls $INSTANCE/events/` ; do
+ [ ! -d $INSTANCE/events/$group ] && continue
+ for event in `ls $INSTANCE/events/$group/` ;do
+ [ ! -d $INSTANCE/events/$group/$event ] && continue
+ per_event_options $INSTANCE/events/$group/$event
+ done
+ done
+ retry=0
+ while [ $retry -lt 3 ]; do
+ retry_unresolved
+ retry=$((retry + 1))
+ done
+ if [ "$UNRESOLVED_EVENTS" ]; then
+ cat 1>&2 << EOF
+! ERROR: hist triggers in $UNRESOLVED_EVENTS use some undefined variables.
+EOF
+ fi
+}
+
+is_default_trace_option() { # option
+grep -qw $1 << EOF
+print-parent
+nosym-offset
+nosym-addr
+noverbose
+noraw
+nohex
+nobin
+noblock
+trace_printk
+annotate
+nouserstacktrace
+nosym-userobj
+noprintk-msg-only
+context-info
+nolatency-format
+record-cmd
+norecord-tgid
+overwrite
+nodisable_on_free
+irq-info
+markers
+noevent-fork
+nopause-on-trace
+function-trace
+nofunction-fork
+nodisplay-graph
+nostacktrace
+notest_nop_accept
+notest_nop_refuse
+EOF
+}
+
+instance_options() { # [instance-name]
+ if [ $# -eq 0 ]; then
+ PREFIX="ftrace"
+ INSTANCE=$TRACEFS
+ else
+ PREFIX="ftrace.instance.$1"
+ INSTANCE=$TRACEFS/instances/$1
+ fi
+ val=
+ for i in `cat $INSTANCE/trace_options`; do
+ is_default_trace_option $i && continue
+ val="$val, $i"
+ done
+ [ "$val" ] && emit_kv $PREFIX.options = "${val#,}"
+ val="local"
+ for i in `cat $INSTANCE/trace_clock` ; do
+ [ "${i#*]}" ] && continue
+ i=${i%]}; val=${i#[}
+ done
+ [ $val != "local" ] && emit_kv $PREFIX.trace_clock = $val
+ val=`cat $INSTANCE/buffer_size_kb`
+ if echo $val | grep -vq "expanded" ; then
+ emit_kv $PREFIX.buffer_size = $val"KB"
+ fi
+ if grep -q "is allocated" $INSTANCE/snapshot ; then
+ emit_kv $PREFIX.alloc_snapshot
+ fi
+ val=`cat $INSTANCE/tracing_cpumask`
+ if [ `echo $val | sed -e s/f//g`x != x ]; then
+ emit_kv $PREFIX.cpumask = $val
+ fi
+
+ val=
+ for i in `cat $INSTANCE/set_event`; do
+ val="$val, $i"
+ done
+ [ "$val" ] && emit_kv $PREFIX.events = "${val#,}"
+ val=`cat $INSTANCE/current_tracer`
+ [ $val != nop ] && emit_kv $PREFIX.tracer = $val
+ if grep -qv "^#" $INSTANCE/set_ftrace_filter $INSTANCE/set_ftrace_notrace; then
+ cat 1>&2 << EOF
+# WARN: kernel.ftrace.filters and kernel.ftrace.notrace are not supported, since the wild card expression was expanded and lost from memory.
+EOF
+ fi
+ event_options
+}
+
+global_options
+instance_options
+for i in `ls $TRACEFS/instances` ; do
+ instance_options $i
+done
diff --git a/tools/bootconfig/scripts/xbc.sh b/tools/bootconfig/scripts/xbc.sh
new file mode 100644
index 000000000000..b8c84e654556
--- /dev/null
+++ b/tools/bootconfig/scripts/xbc.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+# bootconfig utility functions
+
+XBC_TMPFILE=
+XBC_BASEDIR=`dirname $0`
+BOOTCONFIG=${BOOTCONFIG:=$XBC_BASEDIR/../bootconfig}
+if [ ! -x "$BOOTCONFIG" ]; then
+ BOOTCONFIG=`which bootconfig`
+ if [ -z "$BOOTCONFIG" ]; then
+ echo "Erorr: bootconfig command is not found" 1>&2
+ exit 1
+ fi
+fi
+
+xbc_cleanup() {
+ if [ "$XBC_TMPFILE" ]; then
+ rm -f "$XBC_TMPFILE"
+ fi
+}
+
+xbc_init() { # bootconfig-file
+ xbc_cleanup
+ XBC_TMPFILE=`mktemp bconf-XXXX`
+ trap xbc_cleanup EXIT TERM
+
+ $BOOTCONFIG -l $1 > $XBC_TMPFILE || exit 1
+}
+
+nr_args() { # args
+ echo $#
+}
+
+xbc_get_val() { # key [maxnum]
+ if [ "$2" ]; then
+ MAXOPT="-L $2"
+ fi
+ grep "^$1 =" $XBC_TMPFILE | cut -d= -f2- | \
+ sed -e 's/", /" /g' -e "s/',/' /g" | \
+ xargs $MAXOPT -n 1 echo
+}
+
+xbc_has_key() { # key
+ grep -q "^$1 =" $XBC_TMPFILE
+}
+
+xbc_has_branch() { # prefix-key
+ grep -q "^$1" $XBC_TMPFILE
+}
+
+xbc_subkeys() { # prefix-key depth
+ __keys=`echo $1 | sed "s/\./ /g"`
+ __s=`nr_args $__keys`
+ grep "^$1" $XBC_TMPFILE | cut -d= -f1| cut -d. -f$((__s + 1))-$((__s + $2)) | uniq
+}
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index c02ea50d63ea..1b5550ef8a9b 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -97,4 +97,10 @@ check_error 'p:kprobes/testevent kernel_clone ^abcd=\"foo"' # DIFF_ARG_TYPE
check_error '^p:kprobes/testevent kernel_clone abcd=\1' # SAME_PROBE
fi
+# %return suffix errors
+if grep -q "place (kretprobe): .*%return.*" README; then
+check_error 'p vfs_read^%hoge' # BAD_ADDR_SUFFIX
+check_error 'p ^vfs_read+10%return' # BAD_RETPROBE
+fi
+
exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc
new file mode 100644
index 000000000000..f07bd15cc033
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_return_suffix.tc
@@ -0,0 +1,21 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kretprobe %%return suffix test
+# requires: kprobe_events '<symbol>[+<offset>]%return':README
+
+# Test for kretprobe by "r"
+echo 'r:myprobeaccept vfs_read' > kprobe_events
+RESULT1=`cat kprobe_events`
+
+# Test for kretprobe by "%return"
+echo 'p:myprobeaccept vfs_read%return' > kprobe_events
+RESULT2=`cat kprobe_events`
+
+if [ "$RESULT1" != "$RESULT2" ]; then
+ echo "Error: %return suffix didn't make a return probe."
+ echo "r-command: $RESULT1"
+ echo "%return: $RESULT2"
+ exit_fail
+fi
+
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
index 7b5b60c3c5a2..f5e3f9e4a01f 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
@@ -17,4 +17,10 @@ check_error 'p /bin/sh:10(10)^a' # BAD_REFCNT_SUFFIX
check_error 'p /bin/sh:10 ^@+ab' # BAD_FILE_OFFS
check_error 'p /bin/sh:10 ^@symbol' # SYM_ON_UPROBE
+# %return suffix error
+if grep -q "place (uprobe): .*%return.*" README; then
+check_error 'p /bin/sh:10^%hoge' # BAD_ADDR_SUFFIX
+check_error 'p /bin/sh:10(10)^%return' # BAD_REFCNT_SUFFIX
+fi
+
exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
index 7449a4b8f1f9..9098f1e7433f 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -25,12 +25,12 @@ echo 'wakeup_latency u64 lat pid_t pid' >> synthetic_events
echo 'hist:keys=pid:ts1=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger
echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts1:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid) if next_comm=="ping"' > events/sched/sched_switch/trigger
-echo 'waking+wakeup_latency u64 lat; pid_t pid' >> synthetic_events
-echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking+wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger
-echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking+wakeup_latency/trigger
+echo 'waking_plus_wakeup_latency u64 lat; pid_t pid' >> synthetic_events
+echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking_plus_wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger
+echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking_plus_wakeup_latency/trigger
ping $LOCALHOST -c 3
-if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then
+if ! grep -q "pid:" events/synthetic/waking_plus_wakeup_latency/hist; then
fail "Failed to create combined histogram"
fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc
new file mode 100644
index 000000000000..3d65c856eca3
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc
@@ -0,0 +1,31 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: event trigger - test inter-event histogram trigger trace action with dynamic string param
+# requires: set_event synthetic_events events/sched/sched_process_exec/hist "char name[]' >> synthetic_events":README
+
+fail() { #msg
+ echo $1
+ exit_fail
+}
+
+echo "Test create synthetic event"
+
+echo 'ping_test_latency u64 lat; char filename[]' > synthetic_events
+if [ ! -d events/synthetic/ping_test_latency ]; then
+ fail "Failed to create ping_test_latency synthetic event"
+fi
+
+echo "Test create histogram for synthetic event using trace action and dynamic strings"
+echo "Test histogram dynamic string variables,simple expression support and trace action"
+
+echo 'hist:key=pid:filenamevar=filename:ts0=common_timestamp.usecs' > events/sched/sched_process_exec/trigger
+echo 'hist:key=pid:lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_process_exec).ping_test_latency($lat,$filenamevar) if comm == "ping"' > events/sched/sched_process_exit/trigger
+echo 'hist:keys=filename,lat:sort=filename,lat' > events/synthetic/ping_test_latency/trigger
+
+ping $LOCALHOST -c 5
+
+if ! grep -q "ping" events/synthetic/ping_test_latency/hist; then
+ fail "Failed to create dynamic string trace action inter-event histogram"
+fi
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc
new file mode 100644
index 000000000000..ada594fe16cb
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc
@@ -0,0 +1,19 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: event trigger - test synthetic_events syntax parser errors
+# requires: synthetic_events error_log
+
+check_error() { # command-with-error-pos-by-^
+ ftrace_errlog_check 'synthetic_events' "$1" 'synthetic_events'
+}
+
+check_error 'myevent ^chr arg' # INVALID_TYPE
+check_error 'myevent ^char str[];; int v' # INVALID_TYPE
+check_error 'myevent char ^str]; int v' # INVALID_NAME
+check_error 'myevent char ^str;[]' # INVALID_NAME
+check_error 'myevent ^char str[; int v' # INVALID_TYPE
+check_error '^mye;vent char str[]' # BAD_NAME
+check_error 'myevent char str[]; ^int' # INVALID_FIELD
+check_error '^myevent' # INCOMPLETE_CMD
+
+exit 0