dect
/
linux-2.6
Archived
13
0
Fork 0
Code Releases Activity

Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull perf events changes for v3.4 from Ingo Molnar:

 - New "hardware based branch profiling" feature both on the kernel and
   the tooling side, on CPUs that support it.  (modern x86 Intel CPUs
   with the 'LBR' hardware feature currently.)

   This new feature is basically a sophisticated 'magnifying glass' for
   branch execution - something that is pretty difficult to extract from
   regular, function histogram centric profiles.

   The simplest mode is activated via 'perf record -b', and the result
   looks like this in perf report:

	$ perf record -b any_call,u -e cycles:u branchy

	$ perf report -b --sort=symbol
	    52.34%  [.] main                   [.] f1
	    24.04%  [.] f1                     [.] f3
	    23.60%  [.] f1                     [.] f2
	     0.01%  [k] _IO_new_file_xsputn    [k] _IO_file_overflow
	     0.01%  [k] _IO_vfprintf_internal  [k] _IO_new_file_xsputn
	     0.01%  [k] _IO_vfprintf_internal  [k] strchrnul
	     0.01%  [k] __printf               [k] _IO_vfprintf_internal
	     0.01%  [k] main                   [k] __printf

   This output shows from/to branch columns and shows the highest
   percentage (from,to) jump combinations - i.e.  the most likely taken
   branches in the system.  "branches" can also include function calls
   and any other synchronous and asynchronous transitions of the
   instruction pointer that are not 'next instruction' - such as system
   calls, traps, interrupts, etc.

   This feature comes with (hopefully intuitive) flat ascii and TUI
   support in perf report.

 - Various 'perf annotate' visual improvements for us assembly junkies.
   It will now recognize function calls in the TUI and by hitting enter
   you can follow the call (recursively) and back, amongst other
   improvements.

 - Multiple threads/processes recording support in perf record, perf
   stat, perf top - which is activated via a comma-list of PIDs:

	perf top -p 21483,21485
	perf stat -p 21483,21485 -ddd
	perf record -p 21483,21485

 - Support for per UID views, via the --uid paramter to perf top, perf
   report, etc.  For example 'perf top --uid mingo' will only show the
   tasks that I am running, excluding other users, root, etc.

 - Jump label restructurings and improvements - this includes the
   factoring out of the (hopefully much clearer) include/linux/static_key.h
   generic facility:

	struct static_key key = STATIC_KEY_INIT_FALSE;

	...

	if (static_key_false(&key))
	        do unlikely code
	else
	        do likely code

	...
	static_key_slow_inc();
	...
	static_key_slow_inc();
	...

   The static_key_false() branch will be generated into the code with as
   little impact to the likely code path as possible.  the
   static_key_slow_*() APIs flip the branch via live kernel code patching.

   This facility can now be used more widely within the kernel to
   micro-optimize hot branches whose likelihood matches the static-key
   usage and fast/slow cost patterns.

 - SW function tracer improvements: perf support and filtering support.

 - Various hardenings of the perf.data ABI, to make older perf.data's
   smoother on newer tool versions, to make new features integrate more
   smoothly, to support cross-endian recording/analyzing workflows
   better, etc.

 - Restructuring of the kprobes code, the splitting out of 'optprobes',
   and a corner case bugfix.

 - Allow the tracing of kernel console output (printk).

 - Improvements/fixes to user-space RDPMC support, allowing user-space
   self-profiling code to extract PMU counts without performing any
   system calls, while playing nice with the kernel side.

 - 'perf bench' improvements

 - ... and lots of internal restructurings, cleanups and fixes that made
   these features possible.  And, as usual this list is incomplete as
   there were also lots of other improvements

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits)
  perf report: Fix annotate double quit issue in branch view mode
  perf report: Remove duplicate annotate choice in branch view mode
  perf/x86: Prettify pmu config literals
  perf report: Enable TUI in branch view mode
  perf report: Auto-detect branch stack sampling mode
  perf record: Add HEADER_BRANCH_STACK tag
  perf record: Provide default branch stack sampling mode option
  perf tools: Make perf able to read files from older ABIs
  perf tools: Fix ABI compatibility bug in print_event_desc()
  perf tools: Enable reading of perf.data files from different ABI rev
  perf: Add ABI reference sizes
  perf report: Add support for taken branch sampling
  perf record: Add support for sampling taken branch
  perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK
  x86/kprobes: Split out optprobe related code to kprobes-opt.c
  x86/kprobes: Fix a bug which can modify kernel code permanently
  x86/kprobes: Fix instruction recovery on optimized path
  perf: Add callback to flush branch_stack on context switch
  perf: Disable PERF_SAMPLE_BRANCH_* when not supported
  perf/x86: Add LBR software filter support for Intel CPUs
  ...
This commit is contained in:
Linus Torvalds 2012-03-20 10:29:15 -07:00
parent 0bbfcaff9b bea95c152d
commit 9c2b957db1
165 changed files with 6110 additions and 1987 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
Documentation/lockup-watchdogs.txt Normal file
View File

@ -0,0 +1,63 @@
===============================================================
Softlockup detector and hardlockup detector (aka nmi_watchdog)
===============================================================
The Linux kernel can act as a watchdog to detect both soft and hard
lockups.
A 'softlockup' is defined as a bug that causes the kernel to loop in
kernel mode for more than 20 seconds (see "Implementation" below for
details), without giving other tasks a chance to run. The current
stack trace is displayed upon detection and, by default, the system
will stay locked up. Alternatively, the kernel can be configured to
panic; a sysctl, "kernel.softlockup_panic", a kernel parameter,
"softlockup_panic" (see "Documentation/kernel-parameters.txt" for
details), and a compile option, "BOOTPARAM_HARDLOCKUP_PANIC", are
provided for this.
A 'hardlockup' is defined as a bug that causes the CPU to loop in
kernel mode for more than 10 seconds (see "Implementation" below for
details), without letting other interrupts have a chance to run.
Similarly to the softlockup case, the current stack trace is displayed
upon detection and the system will stay locked up unless the default
behavior is changed, which can be done through a compile time knob,
"BOOTPARAM_HARDLOCKUP_PANIC", and a kernel parameter, "nmi_watchdog"
(see "Documentation/kernel-parameters.txt" for details).
The panic option can be used in combination with panic_timeout (this
timeout is set through the confusingly named "kernel.panic" sysctl),
to cause the system to reboot automatically after a specified amount
of time.
=== Implementation ===
The soft and hard lockup detectors are built on top of the hrtimer and
perf subsystems, respectively. A direct consequence of this is that,
in principle, they should work in any architecture where these
subsystems are present.
A periodic hrtimer runs to generate interrupts and kick the watchdog
task. An NMI perf event is generated every "watchdog_thresh"
(compile-time initialized to 10 and configurable through sysctl of the
same name) seconds to check for hardlockups. If any CPU in the system
does not receive any hrtimer interrupt during that time the
'hardlockup detector' (the handler for the NMI perf event) will
generate a kernel warning or call panic, depending on the
configuration.
The watchdog task is a high priority kernel thread that updates a
timestamp every time it is scheduled. If that timestamp is not updated
for 2*watchdog_thresh seconds (the softlockup threshold) the
'softlockup detector' (coded inside the hrtimer callback function)
will dump useful debug information to the system log, after which it
will call panic if it was instructed to do so or resume execution of
other kernel code.
The period of the hrtimer is 2*watchdog_thresh/5, which means it has
two or three chances to generate an interrupt before the hardlockup
detector kicks in.
As explained above, a kernel knob is provided that allows
administrators to configure the period of the hrtimer and the perf
event. The right value for a particular environment is a trade-off
between fast response to lockups and detection overhead.

83
Documentation/nmi_watchdog.txt
View File

@ -1,83 +0,0 @@
[NMI watchdog is available for x86 and x86-64 architectures]
Is your system locking up unpredictably? No keyboard activity, just
a frustrating complete hard lockup? Do you want to help us debugging
such lockups? If all yes then this document is definitely for you.
On many x86/x86-64 type hardware there is a feature that enables
us to generate 'watchdog NMI interrupts'. (NMI: Non Maskable Interrupt
which get executed even if the system is otherwise locked up hard).
This can be used to debug hard kernel lockups. By executing periodic
NMI interrupts, the kernel can monitor whether any CPU has locked up,
and print out debugging messages if so.
In order to use the NMI watchdog, you need to have APIC support in your
kernel. For SMP kernels, APIC support gets compiled in automatically. For
UP, enable either CONFIG_X86_UP_APIC (Processor type and features -> Local
APIC support on uniprocessors) or CONFIG_X86_UP_IOAPIC (Processor type and
features -> IO-APIC support on uniprocessors) in your kernel config.
CONFIG_X86_UP_APIC is for uniprocessor machines without an IO-APIC.
CONFIG_X86_UP_IOAPIC is for uniprocessor with an IO-APIC. [Note: certain
kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
may implicitly disable the NMI watchdog.]
For x86-64, the needed APIC is always compiled in.
Using local APIC (nmi_watchdog=2) needs the first performance register, so
you can't use it for other purposes (such as high precision performance
profiling.) However, at least oprofile and the perfctr driver disable the
local APIC NMI watchdog automatically.
To actually enable the NMI watchdog, use the 'nmi_watchdog=N' boot
parameter. Eg. the relevant lilo.conf entry:
append="nmi_watchdog=1"
For SMP machines and UP machines with an IO-APIC use nmi_watchdog=1.
For UP machines without an IO-APIC use nmi_watchdog=2, this only works
for some processor types. If in doubt, boot with nmi_watchdog=1 and
check the NMI count in /proc/interrupts; if the count is zero then
reboot with nmi_watchdog=2 and check the NMI count. If it is still
zero then log a problem, you probably have a processor that needs to be
added to the nmi code.
A 'lockup' is the following scenario: if any CPU in the system does not
execute the period local timer interrupt for more than 5 seconds, then
the NMI handler generates an oops and kills the process. This
'controlled crash' (and the resulting kernel messages) can be used to
debug the lockup. Thus whenever the lockup happens, wait 5 seconds and
the oops will show up automatically. If the kernel produces no messages
then the system has crashed so hard (eg. hardware-wise) that either it
cannot even accept NMI interrupts, or the crash has made the kernel
unable to print messages.
Be aware that when using local APIC, the frequency of NMI interrupts
it generates, depends on the system load. The local APIC NMI watchdog,
lacking a better source, uses the "cycles unhalted" event. As you may
guess it doesn't tick when the CPU is in the halted state (which happens
when the system is idle), but if your system locks up on anything but the
"hlt" processor instruction, the watchdog will trigger very soon as the
"cycles unhalted" event will happen every clock tick. If it locks up on
"hlt", then you are out of luck -- the event will not happen at all and the
watchdog won't trigger. This is a shortcoming of the local APIC watchdog
-- unfortunately there is no "clock ticks" event that would work all the
time. The I/O APIC watchdog is driven externally and has no such shortcoming.
But its NMI frequency is much higher, resulting in a more significant hit
to the overall system performance.
On x86 nmi_watchdog is disabled by default so you have to enable it with
a boot time parameter.
It's possible to disable the NMI watchdog in run-time by writing "0" to
/proc/sys/kernel/nmi_watchdog. Writing "1" to the same file will re-enable
the NMI watchdog. Notice that you still need to use "nmi_watchdog=" parameter
at boot time.
NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
on x86 SMP boxes.
[ feel free to send bug reports, suggestions and patches to
Ingo Molnar <mingo@redhat.com> or the Linux SMP mailing
list at <linux-smp@vger.kernel.org> ]

286
Documentation/static-keys.txt Normal file
View File

@ -0,0 +1,286 @@
Static Keys
-----------
By: Jason Baron <jbaron@redhat.com>
0) Abstract
Static keys allows the inclusion of seldom used features in
performance-sensitive fast-path kernel code, via a GCC feature and a code
patching technique. A quick example:
struct static_key key = STATIC_KEY_INIT_FALSE;
...
if (static_key_false(&key))
do unlikely code
else
do likely code
...
static_key_slow_inc();
...
static_key_slow_inc();
...
The static_key_false() branch will be generated into the code with as little
impact to the likely code path as possible.
1) Motivation
Currently, tracepoints are implemented using a conditional branch. The
conditional check requires checking a global variable for each tracepoint.
Although the overhead of this check is small, it increases when the memory
cache comes under pressure (memory cache lines for these global variables may
be shared with other memory accesses). As we increase the number of tracepoints
in the kernel this overhead may become more of an issue. In addition,
tracepoints are often dormant (disabled) and provide no direct kernel
functionality. Thus, it is highly desirable to reduce their impact as much as
possible. Although tracepoints are the original motivation for this work, other
kernel code paths should be able to make use of the static keys facility.
2) Solution
gcc (v4.5) adds a new 'asm goto' statement that allows branching to a label:
http://gcc.gnu.org/ml/gcc-patches/2009-07/msg01556.html
Using the 'asm goto', we can create branches that are either taken or not taken
by default, without the need to check memory. Then, at run-time, we can patch
the branch site to change the branch direction.
For example, if we have a simple branch that is disabled by default:
if (static_key_false(&key))
printk("I am the true branch\n");
Thus, by default the 'printk' will not be emitted. And the code generated will
consist of a single atomic 'no-op' instruction (5 bytes on x86), in the
straight-line code path. When the branch is 'flipped', we will patch the
'no-op' in the straight-line codepath with a 'jump' instruction to the
out-of-line true branch. Thus, changing branch direction is expensive but
branch selection is basically 'free'. That is the basic tradeoff of this
optimization.
This lowlevel patching mechanism is called 'jump label patching', and it gives
the basis for the static keys facility.
3) Static key label API, usage and examples:
In order to make use of this optimization you must first define a key:
struct static_key key;
Which is initialized as:
struct static_key key = STATIC_KEY_INIT_TRUE;
or:
struct static_key key = STATIC_KEY_INIT_FALSE;
If the key is not initialized, it is default false. The 'struct static_key',
must be a 'global'. That is, it can't be allocated on the stack or dynamically
allocated at run-time.
The key is then used in code as:
if (static_key_false(&key))
do unlikely code
else
do likely code
Or:
if (static_key_true(&key))
do likely code
else
do unlikely code
A key that is initialized via 'STATIC_KEY_INIT_FALSE', must be used in a
'static_key_false()' construct. Likewise, a key initialized via
'STATIC_KEY_INIT_TRUE' must be used in a 'static_key_true()' construct. A
single key can be used in many branches, but all the branches must match the
way that the key has been initialized.
The branch(es) can then be switched via:
static_key_slow_inc(&key);
...
static_key_slow_dec(&key);
Thus, 'static_key_slow_inc()' means 'make the branch true', and
'static_key_slow_dec()' means 'make the the branch false' with appropriate
reference counting. For example, if the key is initialized true, a
static_key_slow_dec(), will switch the branch to false. And a subsequent
static_key_slow_inc(), will change the branch back to true. Likewise, if the
key is initialized false, a 'static_key_slow_inc()', will change the branch to
true. And then a 'static_key_slow_dec()', will again make the branch false.
An example usage in the kernel is the implementation of tracepoints:
static inline void trace_##name(proto) \
{ \
if (static_key_false(&__tracepoint_##name.key)) \
__DO_TRACE(&__tracepoint_##name, \
TP_PROTO(data_proto), \
TP_ARGS(data_args), \
TP_CONDITION(cond)); \
}
Tracepoints are disabled by default, and can be placed in performance critical
pieces of the kernel. Thus, by using a static key, the tracepoints can have
absolutely minimal impact when not in use.
4) Architecture level code patching interface, 'jump labels'
There are a few functions and macros that architectures must implement in order
to take advantage of this optimization. If there is no architecture support, we
simply fall back to a traditional, load, test, and jump sequence.
* select HAVE_ARCH_JUMP_LABEL, see: arch/x86/Kconfig
* #define JUMP_LABEL_NOP_SIZE, see: arch/x86/include/asm/jump_label.h
* __always_inline bool arch_static_branch(struct static_key *key), see:
arch/x86/include/asm/jump_label.h
* void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type),
see: arch/x86/kernel/jump_label.c
* __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type),
see: arch/x86/kernel/jump_label.c
* struct jump_entry, see: arch/x86/include/asm/jump_label.h
5) Static keys / jump label analysis, results (x86_64):
As an example, let's add the following branch to 'getppid()', such that the
system call now looks like:
SYSCALL_DEFINE0(getppid)
{
int pid;
+ if (static_key_false(&key))
+ printk("I am the true branch\n");
rcu_read_lock();
pid = task_tgid_vnr(rcu_dereference(current->real_parent));
rcu_read_unlock();
return pid;
}
The resulting instructions with jump labels generated by GCC is:
ffffffff81044290 <sys_getppid>:
ffffffff81044290: 55 push %rbp
ffffffff81044291: 48 89 e5 mov %rsp,%rbp
ffffffff81044294: e9 00 00 00 00 jmpq ffffffff81044299 <sys_getppid+0x9>
ffffffff81044299: 65 48 8b 04 25 c0 b6 mov %gs:0xb6c0,%rax
ffffffff810442a0: 00 00
ffffffff810442a2: 48 8b 80 80 02 00 00 mov 0x280(%rax),%rax
ffffffff810442a9: 48 8b 80 b0 02 00 00 mov 0x2b0(%rax),%rax
ffffffff810442b0: 48 8b b8 e8 02 00 00 mov 0x2e8(%rax),%rdi
ffffffff810442b7: e8 f4 d9 00 00 callq ffffffff81051cb0 <pid_vnr>
ffffffff810442bc: 5d pop %rbp
ffffffff810442bd: 48 98 cltq
ffffffff810442bf: c3 retq
ffffffff810442c0: 48 c7 c7 e3 54 98 81 mov $0xffffffff819854e3,%rdi
ffffffff810442c7: 31 c0 xor %eax,%eax
ffffffff810442c9: e8 71 13 6d 00 callq ffffffff8171563f <printk>
ffffffff810442ce: eb c9 jmp ffffffff81044299 <sys_getppid+0x9>
Without the jump label optimization it looks like:
ffffffff810441f0 <sys_getppid>:
ffffffff810441f0: 8b 05 8a 52 d8 00 mov 0xd8528a(%rip),%eax # ffffffff81dc9480 <key>
ffffffff810441f6: 55 push %rbp
ffffffff810441f7: 48 89 e5 mov %rsp,%rbp
ffffffff810441fa: 85 c0 test %eax,%eax
ffffffff810441fc: 75 27 jne ffffffff81044225 <sys_getppid+0x35>
ffffffff810441fe: 65 48 8b 04 25 c0 b6 mov %gs:0xb6c0,%rax
ffffffff81044205: 00 00
ffffffff81044207: 48 8b 80 80 02 00 00 mov 0x280(%rax),%rax
ffffffff8104420e: 48 8b 80 b0 02 00 00 mov 0x2b0(%rax),%rax
ffffffff81044215: 48 8b b8 e8 02 00 00 mov 0x2e8(%rax),%rdi
ffffffff8104421c: e8 2f da 00 00 callq ffffffff81051c50 <pid_vnr>
ffffffff81044221: 5d pop %rbp
ffffffff81044222: 48 98 cltq
ffffffff81044224: c3 retq
ffffffff81044225: 48 c7 c7 13 53 98 81 mov $0xffffffff81985313,%rdi
ffffffff8104422c: 31 c0 xor %eax,%eax
ffffffff8104422e: e8 60 0f 6d 00 callq ffffffff81715193 <printk>
ffffffff81044233: eb c9 jmp ffffffff810441fe <sys_getppid+0xe>
ffffffff81044235: 66 66 2e 0f 1f 84 00 data32 nopw %cs:0x0(%rax,%rax,1)
ffffffff8104423c: 00 00 00 00
Thus, the disable jump label case adds a 'mov', 'test' and 'jne' instruction
vs. the jump label case just has a 'no-op' or 'jmp 0'. (The jmp 0, is patched
to a 5 byte atomic no-op instruction at boot-time.) Thus, the disabled jump
label case adds:
6 (mov) + 2 (test) + 2 (jne) = 10 - 5 (5 byte jump 0) = 5 addition bytes.
If we then include the padding bytes, the jump label code saves, 16 total bytes
of instruction memory for this small fucntion. In this case the non-jump label
function is 80 bytes long. Thus, we have have saved 20% of the instruction
footprint. We can in fact improve this even further, since the 5-byte no-op
really can be a 2-byte no-op since we can reach the branch with a 2-byte jmp.
However, we have not yet implemented optimal no-op sizes (they are currently
hard-coded).
Since there are a number of static key API uses in the scheduler paths,
'pipe-test' (also known as 'perf bench sched pipe') can be used to show the
performance improvement. Testing done on 3.3.0-rc2:
jump label disabled:
Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
855.700314 task-clock # 0.534 CPUs utilized ( +- 0.11% )
200,003 context-switches # 0.234 M/sec ( +- 0.00% )
0 CPU-migrations # 0.000 M/sec ( +- 39.58% )
487 page-faults # 0.001 M/sec ( +- 0.02% )
1,474,374,262 cycles # 1.723 GHz ( +- 0.17% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
1,178,049,567 instructions # 0.80 insns per cycle ( +- 0.06% )
208,368,926 branches # 243.507 M/sec ( +- 0.06% )
5,569,188 branch-misses # 2.67% of all branches ( +- 0.54% )
1.601607384 seconds time elapsed ( +- 0.07% )
jump label enabled:
Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
841.043185 task-clock # 0.533 CPUs utilized ( +- 0.12% )
200,004 context-switches # 0.238 M/sec ( +- 0.00% )
0 CPU-migrations # 0.000 M/sec ( +- 40.87% )
487 page-faults # 0.001 M/sec ( +- 0.05% )
1,432,559,428 cycles # 1.703 GHz ( +- 0.18% )
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
1,175,363,994 instructions # 0.82 insns per cycle ( +- 0.04% )
206,859,359 branches # 245.956 M/sec ( +- 0.04% )
4,884,119 branch-misses # 2.36% of all branches ( +- 0.85% )
1.579384366 seconds time elapsed
The percentage of saved branches is .7%, and we've saved 12% on
'branch-misses'. This is where we would expect to get the most savings, since
this optimization is about reducing the number of branches. In addition, we've
saved .2% on instructions, and 2.8% on cycles and 1.4% on elapsed time.

7
Documentation/trace/ftrace.txt
View File

@ -226,6 +226,13 @@ Here is the list of current tracers that may be configured.
Traces and records the max latency that it takes for
the highest priority task to get scheduled after
it has been woken up.
Traces all tasks as an average developer would expect.
"wakeup_rt"
Traces and records the max latency that it takes for just
RT tasks (as the current "wakeup" does). This is useful
for those interested in wake up timings of RT tasks.
"hw-branch-tracer"

29
arch/Kconfig
View File

@ -47,18 +47,29 @@ config KPROBES
If in doubt, say "N".
config JUMP_LABEL
bool "Optimize trace point call sites"
bool "Optimize very unlikely/likely branches"
depends on HAVE_ARCH_JUMP_LABEL
help
If it is detected that the compiler has support for "asm goto",
the kernel will compile trace point locations with just a
nop instruction. When trace points are enabled, the nop will
be converted to a jump to the trace function. This technique
lowers overhead and stress on the branch prediction of the
processor.
This option enables a transparent branch optimization that
makes certain almost-always-true or almost-always-false branch
conditions even cheaper to execute within the kernel.
On i386, options added to the compiler flags may increase
the size of the kernel slightly.
Certain performance-sensitive kernel code, such as trace points,
scheduler functionality, networking code and KVM have such
branches and include support for this optimization technique.
If it is detected that the compiler has support for "asm goto",
the kernel will compile such branches with just a nop
instruction. When the condition flag is toggled to true, the
nop will be converted to a jump instruction to execute the
conditional block of instructions.
This technique lowers overhead and stress on the branch prediction
of the processor and generally makes the kernel faster. The update
of the condition is slower, but those are always very rare.
( On 32-bit x86, the necessary options added to the compiler
flags may increase the size of the kernel slightly. )
config OPTPROBES
def_bool y

4
arch/alpha/kernel/perf_event.c
View File

@ -685,6 +685,10 @@ static int alpha_pmu_event_init(struct perf_event *event)
{
int err;
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
switch (event->attr.type) {
case PERF_TYPE_RAW:
case PERF_TYPE_HARDWARE:

4
arch/arm/include/asm/perf_event.h
View File

@ -12,10 +12,6 @@
#ifndef __ARM_PERF_EVENT_H__
#define __ARM_PERF_EVENT_H__
/* ARM performance counters start from 1 (in the cp15 accesses) so use the
* same indexes here for consistency. */
#define PERF_EVENT_INDEX_OFFSET 1
/* ARM perf PMU IDs for use by internal perf clients. */
enum arm_perf_pmu_ids {
ARM_PERF_PMU_ID_XSCALE1 = 0,

4
arch/arm/kernel/perf_event.c
View File

@ -539,6 +539,10 @@ static int armpmu_event_init(struct perf_event *event)
int err = 0;
atomic_t *active_events = &armpmu->active_events;
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
if (armpmu->map_event(event) == -ENOENT)
return -ENOENT;

2
arch/frv/include/asm/perf_event.h
View File

@ -12,6 +12,4 @@
#ifndef _ASM_PERF_EVENT_H
#define _ASM_PERF_EVENT_H
#define PERF_EVENT_INDEX_OFFSET 0
#endif /* _ASM_PERF_EVENT_H */

2
arch/hexagon/include/asm/perf_event.h
View File

@ -19,6 +19,4 @@
#ifndef _ASM_PERF_EVENT_H
#define _ASM_PERF_EVENT_H
#define PERF_EVENT_INDEX_OFFSET 0
#endif /* _ASM_PERF_EVENT_H */

6
arch/ia64/include/asm/paravirt.h
View File

@ -281,9 +281,9 @@ paravirt_init_missing_ticks_accounting(int cpu)
pv_time_ops.init_missing_ticks_accounting(cpu);
}
struct jump_label_key;
extern struct jump_label_key paravirt_steal_enabled;
extern struct jump_label_key paravirt_steal_rq_enabled;
struct static_key;
extern struct static_key paravirt_steal_enabled;
extern struct static_key paravirt_steal_rq_enabled;
static inline int
paravirt_do_steal_accounting(unsigned long *new_itm)

4
arch/ia64/kernel/paravirt.c
View File

@ -634,8 +634,8 @@ struct pv_irq_ops pv_irq_ops = {
* pv_time_ops
* time operations
*/
struct jump_label_key paravirt_steal_enabled;
struct jump_label_key paravirt_steal_rq_enabled;
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
static int
ia64_native_do_steal_accounting(unsigned long *new_itm)

2
arch/mips/include/asm/jump_label.h
View File

@ -20,7 +20,7 @@
#define WORD_INSN ".word"
#endif
static __always_inline bool arch_static_branch(struct jump_label_key *key)
static __always_inline bool arch_static_branch(struct static_key *key)
{
asm goto("1:\tnop\n\t"
"nop\n\t"

4
arch/mips/kernel/perf_event_mipsxx.c
View File

@ -606,6 +606,10 @@ static int mipspmu_event_init(struct perf_event *event)
{
int err = 0;
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
switch (event->attr.type) {
case PERF_TYPE_RAW:
case PERF_TYPE_HARDWARE:

2
arch/powerpc/include/asm/jump_label.h
View File

@ -17,7 +17,7 @@
#define JUMP_ENTRY_TYPE stringify_in_c(FTR_ENTRY_LONG)
#define JUMP_LABEL_NOP_SIZE 4
static __always_inline bool arch_static_branch(struct jump_label_key *key)
static __always_inline bool arch_static_branch(struct static_key *key)
{
asm goto("1:\n\t"
"nop\n\t"

2
arch/powerpc/include/asm/perf_event_server.h
View File

@ -61,8 +61,6 @@ struct pt_regs;
extern unsigned long perf_misc_flags(struct pt_regs *regs);
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
#define PERF_EVENT_INDEX_OFFSET 1
/*
* Only override the default definitions in include/linux/perf_event.h
* if we have hardware PMU support.

10
arch/powerpc/kernel/perf_event.c
View File

@ -1084,6 +1084,10 @@ static int power_pmu_event_init(struct perf_event *event)
if (!ppmu)
return -ENOENT;
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
switch (event->attr.type) {
case PERF_TYPE_HARDWARE:
ev = event->attr.config;
@ -1193,6 +1197,11 @@ static int power_pmu_event_init(struct perf_event *event)
return err;
}
static int power_pmu_event_idx(struct perf_event *event)
{
return event->hw.idx;
}
struct pmu power_pmu = {
.pmu_enable = power_pmu_enable,
.pmu_disable = power_pmu_disable,
@ -1205,6 +1214,7 @@ struct pmu power_pmu = {
.start_txn = power_pmu_start_txn,
.cancel_txn = power_pmu_cancel_txn,
.commit_txn = power_pmu_commit_txn,
.event_idx = power_pmu_event_idx,
};
/*

2
arch/s390/include/asm/jump_label.h
View File

@ -13,7 +13,7 @@
#define ASM_ALIGN ".balign 4"
#endif
static __always_inline bool arch_static_branch(struct jump_label_key *key)
static __always_inline bool arch_static_branch(struct static_key *key)
{
asm goto("0: brcl 0,0\n"
".pushsection __jump_table, \"aw\"\n"

1
arch/s390/include/asm/perf_event.h
View File

@ -6,4 +6,3 @@
/* Empty, just to avoid compiling error */
#define PERF_EVENT_INDEX_OFFSET 0

4
arch/sh/kernel/perf_event.c
View File

@ -310,6 +310,10 @@ static int sh_pmu_event_init(struct perf_event *event)
{
int err;
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
switch (event->attr.type) {
case PERF_TYPE_RAW:
case PERF_TYPE_HW_CACHE:

2
arch/sparc/include/asm/jump_label.h
View File

@ -7,7 +7,7 @@
#define JUMP_LABEL_NOP_SIZE 4
static __always_inline bool arch_static_branch(struct jump_label_key *key)
static __always_inline bool arch_static_branch(struct static_key *key)
{
asm goto("1:\n\t"
"nop\n\t"

4
arch/sparc/kernel/perf_event.c
View File

@ -1105,6 +1105,10 @@ static int sparc_pmu_event_init(struct perf_event *event)
if (atomic_read(&nmi_active) < 0)
return -ENODEV;
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
switch (attr->type) {
case PERF_TYPE_HARDWARE:
if (attr->config >= sparc_pmu->max_events)

5
arch/x86/include/asm/inat.h
View File

@ -97,11 +97,12 @@
/* Attribute search APIs */
extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
insn_byte_t last_pfx,
int lpfx_id,
insn_attr_t esc_attr);
extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
insn_byte_t last_pfx,
int lpfx_id,
insn_attr_t esc_attr);
extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
insn_byte_t vex_m,

18
arch/x86/include/asm/insn.h
View File

@ -96,12 +96,6 @@ struct insn {
#define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */
#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */
/* The last prefix is needed for two-byte and three-byte opcodes */
static inline insn_byte_t insn_last_prefix(struct insn *insn)
{
return insn->prefixes.bytes[3];
}
extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
extern void insn_get_prefixes(struct insn *insn);
extern void insn_get_opcode(struct insn *insn);
@ -160,6 +154,18 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
return X86_VEX_P(insn->vex_prefix.bytes[2]);
}
/* Get the last prefix id from last prefix or VEX prefix */
static inline int insn_last_prefix_id(struct insn *insn)
{
if (insn_is_avx(insn))
return insn_vex_p_bits(insn); /* VEX_p is a SIMD prefix id */
if (insn->prefixes.bytes[3])
return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
return 0;
}
/* Offset of each field from kaddr */
static inline int insn_offset_rex_prefix(struct insn *insn)
{

6
arch/x86/include/asm/jump_label.h
View File

@ -9,12 +9,12 @@
#define JUMP_LABEL_NOP_SIZE 5
#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
static __always_inline bool arch_static_branch(struct jump_label_key *key)
static __always_inline bool arch_static_branch(struct static_key *key)
{
asm goto("1:"
JUMP_LABEL_INITIAL_NOP
STATIC_KEY_INITIAL_NOP
".pushsection __jump_table, \"aw\" \n\t"
_ASM_ALIGN "\n\t"
_ASM_PTR "1b, %l[l_yes], %c0 \n\t"

7
arch/x86/include/asm/msr-index.h
View File

@ -56,6 +56,13 @@
#define MSR_OFFCORE_RSP_0 0x000001a6
#define MSR_OFFCORE_RSP_1 0x000001a7
#define MSR_LBR_SELECT 0x000001c8
#define MSR_LBR_TOS 0x000001c9
#define MSR_LBR_NHM_FROM 0x00000680
#define MSR_LBR_NHM_TO 0x000006c0
#define MSR_LBR_CORE_FROM 0x00000040
#define MSR_LBR_CORE_TO 0x00000060
#define MSR_IA32_PEBS_ENABLE 0x000003f1
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345

6
arch/x86/include/asm/paravirt.h
View File

@ -230,9 +230,9 @@ static inline unsigned long long paravirt_sched_clock(void)
return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
}
struct jump_label_key;
extern struct jump_label_key paravirt_steal_enabled;
extern struct jump_label_key paravirt_steal_rq_enabled;
struct static_key;
extern struct static_key paravirt_steal_enabled;
extern struct static_key paravirt_steal_rq_enabled;
static inline u64 paravirt_steal_clock(int cpu)
{

2
arch/x86/include/asm/perf_event.h
View File

@ -188,8 +188,6 @@ extern u32 get_ibs_caps(void);
#ifdef CONFIG_PERF_EVENTS
extern void perf_events_lapic_init(void);
#define PERF_EVENT_INDEX_OFFSET 0
/*
* Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
* This flag is otherwise unused and ABI specified to be 0, so nobody should

1
arch/x86/kernel/Makefile
View File

@ -69,6 +69,7 @@ obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_OPTPROBES) += kprobes-opt.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o
obj-$(CONFIG_KGDB) += kgdb.o

3
arch/x86/kernel/cpu/amd.c
View File

@ -5,6 +5,7 @@
#include <linux/mm.h>
#include <linux/io.h>
#include <linux/sched.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cpu.h>
@ -456,6 +457,8 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
if (!check_tsc_unstable())
sched_clock_stable = 1;
}
#ifdef CONFIG_X86_64

167
arch/x86/kernel/cpu/perf_event.c
View File

@ -24,6 +24,7 @@
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <linux/device.h>
#include <asm/apic.h>
#include <asm/stacktrace.h>
@ -31,6 +32,7 @@
#include <asm/compat.h>
#include <asm/smp.h>
#include <asm/alternative.h>
#include <asm/timer.h>
#include "perf_event.h"
@ -351,6 +353,36 @@ int x86_setup_perfctr(struct perf_event *event)
return 0;
}
/*
* check that branch_sample_type is compatible with
* settings needed for precise_ip > 1 which implies
* using the LBR to capture ALL taken branches at the
* priv levels of the measurement
*/
static inline int precise_br_compat(struct perf_event *event)
{
u64 m = event->attr.branch_sample_type;
u64 b = 0;
/* must capture all branches */
if (!(m & PERF_SAMPLE_BRANCH_ANY))
return 0;
m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
if (!event->attr.exclude_user)
b |= PERF_SAMPLE_BRANCH_USER;
if (!event->attr.exclude_kernel)
b |= PERF_SAMPLE_BRANCH_KERNEL;
/*
* ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
*/
return m == b;
}
int x86_pmu_hw_config(struct perf_event *event)
{
if (event->attr.precise_ip) {
@ -367,6 +399,36 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.precise_ip > precise)
return -EOPNOTSUPP;
/*
* check that PEBS LBR correction does not conflict with
* whatever the user is asking with attr->branch_sample_type
*/
if (event->attr.precise_ip > 1) {
u64 *br_type = &event->attr.branch_sample_type;
if (has_branch_stack(event)) {
if (!precise_br_compat(event))
return -EOPNOTSUPP;
/* branch_sample_type is compatible */
} else {
/*
* user did not specify branch_sample_type
*
* For PEBS fixups, we capture all
* the branches at the priv level of the
* event.
*/
*br_type = PERF_SAMPLE_BRANCH_ANY;
if (!event->attr.exclude_user)
*br_type |= PERF_SAMPLE_BRANCH_USER;
if (!event->attr.exclude_kernel)
*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
}
}
}
/*
@ -424,6 +486,10 @@ static int __x86_pmu_event_init(struct perf_event *event)
/* mark unused */
event->hw.extra_reg.idx = EXTRA_REG_NONE;
/* mark not used */
event->hw.extra_reg.idx = EXTRA_REG_NONE;
event->hw.branch_reg.idx = EXTRA_REG_NONE;
return x86_pmu.hw_config(event);
}
@ -1210,6 +1276,8 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
break;
case CPU_STARTING:
if (x86_pmu.attr_rdpmc)
set_in_cr4(X86_CR4_PCE);
if (x86_pmu.cpu_starting)
x86_pmu.cpu_starting(cpu);
break;
@ -1319,6 +1387,8 @@ static int __init init_hw_perf_events(void)
}
}
x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
pr_info("... generic registers: %d\n", x86_pmu.num_counters);
@ -1542,23 +1612,106 @@ static int x86_pmu_event_init(struct perf_event *event)
return err;
}
static int x86_pmu_event_idx(struct perf_event *event)
{
int idx = event->hw.idx;
if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
idx -= X86_PMC_IDX_FIXED;
idx |= 1 << 30;
}
return idx + 1;
}
static ssize_t get_attr_rdpmc(struct device *cdev,
struct device_attribute *attr,
char *buf)
{
return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc);
}
static void change_rdpmc(void *info)
{
bool enable = !!(unsigned long)info;
if (enable)
set_in_cr4(X86_CR4_PCE);
else
clear_in_cr4(X86_CR4_PCE);
}
static ssize_t set_attr_rdpmc(struct device *cdev,
struct device_attribute *attr,
const char *buf, size_t count)
{
unsigned long val = simple_strtoul(buf, NULL, 0);
if (!!val != !!x86_pmu.attr_rdpmc) {
x86_pmu.attr_rdpmc = !!val;
smp_call_function(change_rdpmc, (void *)val, 1);
}
return count;
}
static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
static struct attribute *x86_pmu_attrs[] = {
&dev_attr_rdpmc.attr,
NULL,
};
static struct attribute_group x86_pmu_attr_group = {
.attrs = x86_pmu_attrs,
};
static const struct attribute_group *x86_pmu_attr_groups[] = {
&x86_pmu_attr_group,
NULL,
};
static void x86_pmu_flush_branch_stack(void)
{
if (x86_pmu.flush_branch_stack)
x86_pmu.flush_branch_stack();
}
static struct pmu pmu = {
.pmu_enable = x86_pmu_enable,
.pmu_disable = x86_pmu_disable,
.pmu_enable = x86_pmu_enable,
.pmu_disable = x86_pmu_disable,
.attr_groups = x86_pmu_attr_groups,
.event_init = x86_pmu_event_init,
.add = x86_pmu_add,
.del = x86_pmu_del,
.start = x86_pmu_start,
.stop = x86_pmu_stop,
.read = x86_pmu_read,
.add = x86_pmu_add,
.del = x86_pmu_del,
.start = x86_pmu_start,
.stop = x86_pmu_stop,
.read = x86_pmu_read,
.start_txn = x86_pmu_start_txn,
.cancel_txn = x86_pmu_cancel_txn,
.commit_txn = x86_pmu_commit_txn,
.event_idx = x86_pmu_event_idx,
.flush_branch_stack = x86_pmu_flush_branch_stack,
};
void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
{
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
return;
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
return;
userpg->time_mult = this_cpu_read(cyc2ns);
userpg->time_shift = CYC2NS_SCALE_FACTOR;
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
}
/*
* callchain support
*/

50
arch/x86/kernel/cpu/perf_event.h
View File

@ -33,6 +33,7 @@ enum extra_reg_type {
EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */
EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */
EXTRA_REG_LBR = 2, /* lbr_select */
EXTRA_REG_MAX /* number of entries needed */
};
@ -130,6 +131,8 @@ struct cpu_hw_events {
void *lbr_context;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
u64 br_sel;
/*
* Intel host/guest exclude bits
@ -268,6 +271,29 @@ struct x86_pmu_quirk {
void (*func)(void);
};
union x86_pmu_config {
struct {
u64 event:8,
umask:8,
usr:1,
os:1,
edge:1,
pc:1,
interrupt:1,
__reserved1:1,
en:1,
inv:1,
cmask:8,
event2:4,
__reserved2:4,
go:1,
ho:1;
} bits;
u64 value;
};
#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value
/*
* struct x86_pmu - generic x86 pmu
*/
@ -309,10 +335,19 @@ struct x86_pmu {
struct x86_pmu_quirk *quirks;
int perfctr_second_write;
/*
* sysfs attrs
*/
int attr_rdpmc;
/*
* CPU Hotplug hooks
*/
int (*cpu_prepare)(int cpu);
void (*cpu_starting)(int cpu);
void (*cpu_dying)(int cpu);
void (*cpu_dead)(int cpu);
void (*flush_branch_stack)(void);
/*
* Intel Arch Perfmon v2+
@ -334,6 +369,8 @@ struct x86_pmu {
*/
unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */
int lbr_nr; /* hardware stack size */
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
const int *lbr_sel_map; /* lbr_select mappings */
/*
* Extra registers for events
@ -447,6 +484,15 @@ extern struct event_constraint emptyconstraint;
extern struct event_constraint unconstrained;
static inline bool kernel_ip(unsigned long ip)
{
#ifdef CONFIG_X86_32
return ip > PAGE_OFFSET;
#else
return (long)ip < 0;
#endif
}
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
@ -527,6 +573,10 @@ void intel_pmu_lbr_init_nhm(void);
void intel_pmu_lbr_init_atom(void);
void intel_pmu_lbr_init_snb(void);
int intel_pmu_setup_lbr_filter(struct perf_event *event);
int p4_pmu_init(void);
int p6_pmu_init(void);

3
arch/x86/kernel/cpu/perf_event_amd.c
View File

@ -139,6 +139,9 @@ static int amd_pmu_hw_config(struct perf_event *event)
if (ret)
return ret;
if (has_branch_stack(event))
return -EOPNOTSUPP;
if (event->attr.exclude_host && event->attr.exclude_guest)
/*
* When HO == GO == 1 the hardware treats that as GO == HO == 0

139
arch/x86/kernel/cpu/perf_event_intel.c
View File

@ -728,6 +728,19 @@ static __initconst const u64 atom_hw_cache_event_ids
},
};
static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
{
/* user explicitly requested branch sampling */
if (has_branch_stack(event))
return true;
/* implicit branch sampling to correct PEBS skid */
if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
return true;
return false;
}
static void intel_pmu_disable_all(void)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@ -882,6 +895,13 @@ static void intel_pmu_disable_event(struct perf_event *event)
cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
/*
* must disable before any actual event
* because any event may be combined with LBR
*/
if (intel_pmu_needs_lbr_smpl(event))
intel_pmu_lbr_disable(event);
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
@ -936,6 +956,12 @@ static void intel_pmu_enable_event(struct perf_event *event)
intel_pmu_enable_bts(hwc->config);
return;
}
/*
* must enabled before any actual event
* because any event may be combined with LBR
*/
if (intel_pmu_needs_lbr_smpl(event))
intel_pmu_lbr_enable(event);
if (event->attr.exclude_host)
cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
@ -1058,6 +1084,9 @@ again:
data.period = event->hw.last_period;
if (has_branch_stack(event))
data.br_stack = &cpuc->lbr_stack;
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
}
@ -1124,17 +1153,17 @@ static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
*/
static struct event_constraint *
__intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event)
struct perf_event *event,
struct hw_perf_event_extra *reg)
{
struct event_constraint *c = &emptyconstraint;
struct hw_perf_event_extra *reg = &event->hw.extra_reg;
struct er_account *era;
unsigned long flags;
int orig_idx = reg->idx;
/* already allocated shared msr */
if (reg->alloc)
return &unconstrained;
return NULL; /* call x86_get_event_constraint() */
again:
era = &cpuc->shared_regs->regs[reg->idx];
@ -1157,14 +1186,10 @@ again:
reg->alloc = 1;
/*
* All events using extra_reg are unconstrained.
* Avoids calling x86_get_event_constraints()
*
* Must revisit if extra_reg controlling events
* ever have constraints. Worst case we go through
* the regular event constraint table.
* need to call x86_get_event_constraint()
* to check if associated event has constraints
*/
c = &unconstrained;
c = NULL;
} else if (intel_try_alt_er(event, orig_idx)) {
raw_spin_unlock_irqrestore(&era->lock, flags);
goto again;
@ -1201,11 +1226,23 @@ static struct event_constraint *
intel_shared_regs_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event)
{
struct event_constraint *c = NULL;
if (event->hw.extra_reg.idx != EXTRA_REG_NONE)
c = __intel_shared_reg_get_constraints(cpuc, event);
struct event_constraint *c = NULL, *d;
struct hw_perf_event_extra *xreg, *breg;
xreg = &event->hw.extra_reg;
if (xreg->idx != EXTRA_REG_NONE) {
c = __intel_shared_reg_get_constraints(cpuc, event, xreg);
if (c == &emptyconstraint)
return c;
}
breg = &event->hw.branch_reg;
if (breg->idx != EXTRA_REG_NONE) {
d = __intel_shared_reg_get_constraints(cpuc, event, breg);
if (d == &emptyconstraint) {
__intel_shared_reg_put_constraints(cpuc, xreg);
c = d;
}
}
return c;
}
@ -1253,6 +1290,10 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
reg = &event->hw.extra_reg;
if (reg->idx != EXTRA_REG_NONE)
__intel_shared_reg_put_constraints(cpuc, reg);
reg = &event->hw.branch_reg;
if (reg->idx != EXTRA_REG_NONE)
__intel_shared_reg_put_constraints(cpuc, reg);
}
static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
@ -1288,12 +1329,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
*
* Thereby we gain a PEBS capable cycle counter.
*/
u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */
u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
}
if (intel_pmu_needs_lbr_smpl(event)) {
ret = intel_pmu_setup_lbr_filter(event);
if (ret)
return ret;
}
if (event->attr.type != PERF_TYPE_RAW)
return 0;
@ -1432,7 +1480,7 @@ static int intel_pmu_cpu_prepare(int cpu)
{
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
if (!x86_pmu.extra_regs)
if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map))
return NOTIFY_OK;
cpuc->shared_regs = allocate_shared_regs(cpu);
@ -1454,22 +1502,28 @@ static void intel_pmu_cpu_starting(int cpu)
*/
intel_pmu_lbr_reset();
if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING))
cpuc->lbr_sel = NULL;
if (!cpuc->shared_regs)
return;
for_each_cpu(i, topology_thread_cpumask(cpu)) {
struct intel_shared_regs *pc;
if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) {
for_each_cpu(i, topology_thread_cpumask(cpu)) {
struct intel_shared_regs *pc;
pc = per_cpu(cpu_hw_events, i).shared_regs;
if (pc && pc->core_id == core_id) {
cpuc->kfree_on_online = cpuc->shared_regs;
cpuc->shared_regs = pc;
break;
pc = per_cpu(cpu_hw_events, i).shared_regs;
if (pc && pc->core_id == core_id) {
cpuc->kfree_on_online = cpuc->shared_regs;
cpuc->shared_regs = pc;
break;
}
}
cpuc->shared_regs->core_id = core_id;
cpuc->shared_regs->refcnt++;
}
cpuc->shared_regs->core_id = core_id;
cpuc->shared_regs->refcnt++;
if (x86_pmu.lbr_sel_map)
cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
}
static void intel_pmu_cpu_dying(int cpu)
@ -1487,6 +1541,18 @@ static void intel_pmu_cpu_dying(int cpu)
fini_debug_store_on_cpu(cpu);
}
static void intel_pmu_flush_branch_stack(void)
{
/*
* Intel LBR does not tag entries with the
* PID of the current task, then we need to
* flush it on ctxsw
* For now, we simply reset it
*/
if (x86_pmu.lbr_nr)
intel_pmu_lbr_reset();
}
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
@ -1514,6 +1580,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
.guest_get_msrs = intel_guest_get_msrs,
.flush_branch_stack = intel_pmu_flush_branch_stack,
};
static __init void intel_clovertown_quirk(void)
@ -1690,9 +1757,11 @@ __init int intel_pmu_init(void)
x86_pmu.extra_regs = intel_nehalem_extra_regs;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
x86_add_quirk(intel_nehalem_quirk);
@ -1727,9 +1796,11 @@ __init int intel_pmu_init(void)
x86_pmu.er_flags |= ERF_HAS_RSP_1;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
pr_cont("Westmere events, ");
break;
@ -1740,7 +1811,7 @@ __init int intel_pmu_init(void)
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
intel_pmu_lbr_init_nhm();
intel_pmu_lbr_init_snb();
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
@ -1750,9 +1821,11 @@ __init int intel_pmu_init(void)
x86_pmu.er_flags |= ERF_NO_HT_SHARING;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
/* UOPS_DISPATCHED.THREAD,c=1,i=1 to count stall cycles*/
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x18001b1;
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1);
pr_cont("SandyBridge events, ");
break;

22
arch/x86/kernel/cpu/perf_event_intel_ds.c
View File

@ -3,6 +3,7 @@
#include <linux/slab.h>
#include <asm/perf_event.h>
#include <asm/insn.h>
#include "perf_event.h"
@ -439,9 +440,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
cpuc->pebs_enabled |= 1ULL << hwc->idx;
if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
intel_pmu_lbr_enable(event);
}
void intel_pmu_pebs_disable(struct perf_event *event)
@ -454,9 +452,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
intel_pmu_lbr_disable(event);
}
void intel_pmu_pebs_enable_all(void)
@ -475,17 +470,6 @@ void intel_pmu_pebs_disable_all(void)
wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
#include <asm/insn.h>
static inline bool kernel_ip(unsigned long ip)
{
#ifdef CONFIG_X86_32
return ip > PAGE_OFFSET;
#else
return (long)ip < 0;
#endif
}
static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@ -572,6 +556,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
* both formats and we don't use the other fields in this
* routine.
*/
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct pebs_record_core *pebs = __pebs;
struct perf_sample_data data;
struct pt_regs regs;
@ -602,6 +587,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
else
regs.flags &= ~PERF_EFLAGS_EXACT;
if (has_branch_stack(event))
data.br_stack = &cpuc->lbr_stack;
if (perf_event_overflow(event, &data, &regs))
x86_pmu_stop(event, 0);
}

526
arch/x86/kernel/cpu/perf_event_intel_lbr.c
View File

@ -3,6 +3,7 @@
#include <asm/perf_event.h>
#include <asm/msr.h>
#include <asm/insn.h>
#include "perf_event.h"
@ -13,6 +14,100 @@ enum {
LBR_FORMAT_EIP_FLAGS = 0x03,
};
/*
* Intel LBR_SELECT bits
* Intel Vol3a, April 2011, Section 16.7 Table 16-10
*
* Hardware branch filter (not available on all CPUs)
*/
#define LBR_KERNEL_BIT 0 /* do not capture at ring0 */
#define LBR_USER_BIT 1 /* do not capture at ring > 0 */
#define LBR_JCC_BIT 2 /* do not capture conditional branches */
#define LBR_REL_CALL_BIT 3 /* do not capture relative calls */
#define LBR_IND_CALL_BIT 4 /* do not capture indirect calls */
#define LBR_RETURN_BIT 5 /* do not capture near returns */
#define LBR_IND_JMP_BIT 6 /* do not capture indirect jumps */
#define LBR_REL_JMP_BIT 7 /* do not capture relative jumps */
#define LBR_FAR_BIT 8 /* do not capture far branches */
#define LBR_KERNEL (1 << LBR_KERNEL_BIT)
#define LBR_USER (1 << LBR_USER_BIT)
#define LBR_JCC (1 << LBR_JCC_BIT)
#define LBR_REL_CALL (1 << LBR_REL_CALL_BIT)
#define LBR_IND_CALL (1 << LBR_IND_CALL_BIT)
#define LBR_RETURN (1 << LBR_RETURN_BIT)
#define LBR_REL_JMP (1 << LBR_REL_JMP_BIT)
#define LBR_IND_JMP (1 << LBR_IND_JMP_BIT)
#define LBR_FAR (1 << LBR_FAR_BIT)
#define LBR_PLM (LBR_KERNEL | LBR_USER)
#define LBR_SEL_MASK 0x1ff /* valid bits in LBR_SELECT */
#define LBR_NOT_SUPP -1 /* LBR filter not supported */
#define LBR_IGN 0 /* ignored */
#define LBR_ANY \
(LBR_JCC |\
LBR_REL_CALL |\
LBR_IND_CALL |\
LBR_RETURN |\
LBR_REL_JMP |\
LBR_IND_JMP |\
LBR_FAR)
#define LBR_FROM_FLAG_MISPRED (1ULL << 63)
#define for_each_branch_sample_type(x) \
for ((x) = PERF_SAMPLE_BRANCH_USER; \
(x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
/*
* x86control flow change classification
* x86control flow changes include branches, interrupts, traps, faults
*/
enum {
X86_BR_NONE = 0, /* unknown */
X86_BR_USER = 1 << 0, /* branch target is user */
X86_BR_KERNEL = 1 << 1, /* branch target is kernel */
X86_BR_CALL = 1 << 2, /* call */
X86_BR_RET = 1 << 3, /* return */
X86_BR_SYSCALL = 1 << 4, /* syscall */
X86_BR_SYSRET = 1 << 5, /* syscall return */
X86_BR_INT = 1 << 6, /* sw interrupt */
X86_BR_IRET = 1 << 7, /* return from interrupt */
X86_BR_JCC = 1 << 8, /* conditional */
X86_BR_JMP = 1 << 9, /* jump */
X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */
X86_BR_IND_CALL = 1 << 11,/* indirect calls */
};
#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
#define X86_BR_ANY \
(X86_BR_CALL |\
X86_BR_RET |\
X86_BR_SYSCALL |\
X86_BR_SYSRET |\
X86_BR_INT |\
X86_BR_IRET |\
X86_BR_JCC |\
X86_BR_JMP |\
X86_BR_IRQ |\
X86_BR_IND_CALL)
#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
#define X86_BR_ANY_CALL \
(X86_BR_CALL |\
X86_BR_IND_CALL |\
X86_BR_SYSCALL |\
X86_BR_IRQ |\
X86_BR_INT)
static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
/*
* We only support LBR implementations that have FREEZE_LBRS_ON_PMI
* otherwise it becomes near impossible to get a reliable stack.
@ -21,6 +116,10 @@ enum {
static void __intel_pmu_lbr_enable(void)
{
u64 debugctl;
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
if (cpuc->lbr_sel)
wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
@ -76,11 +175,11 @@ void intel_pmu_lbr_enable(struct perf_event *event)
* Reset the LBR stack if we changed task context to
* avoid data leaks.
*/
if (event->ctx->task && cpuc->lbr_context != event->ctx) {
intel_pmu_lbr_reset();
cpuc->lbr_context = event->ctx;
}
cpuc->br_sel = event->hw.branch_reg.reg;
cpuc->lbr_users++;
}
@ -95,8 +194,11 @@ void intel_pmu_lbr_disable(struct perf_event *event)
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
if (cpuc->enabled && !cpuc->lbr_users)
if (cpuc->enabled && !cpuc->lbr_users) {
__intel_pmu_lbr_disable();
/* avoid stale pointer */
cpuc->lbr_context = NULL;
}
}
void intel_pmu_lbr_enable_all(void)
@ -115,6 +217,9 @@ void intel_pmu_lbr_disable_all(void)
__intel_pmu_lbr_disable();
}
/*
* TOS = most recently recorded branch
*/
static inline u64 intel_pmu_lbr_tos(void)
{
u64 tos;
@ -142,15 +247,15 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
cpuc->lbr_entries[i].from = msr_lastbranch.from;
cpuc->lbr_entries[i].to = msr_lastbranch.to;
cpuc->lbr_entries[i].flags = 0;
cpuc->lbr_entries[i].from = msr_lastbranch.from;
cpuc->lbr_entries[i].to = msr_lastbranch.to;
cpuc->lbr_entries[i].mispred = 0;
cpuc->lbr_entries[i].predicted = 0;
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
}
#define LBR_FROM_FLAG_MISPRED (1ULL << 63)
/*
* Due to lack of segmentation in Linux the effective address (offset)
* is the same as the linear address, allowing us to merge the LIP and EIP
@ -165,19 +270,22 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
for (i = 0; i < x86_pmu.lbr_nr; i++) {
unsigned long lbr_idx = (tos - i) & mask;
u64 from, to, flags = 0;
u64 from, to, mis = 0, pred = 0;
rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
rdmsrl(x86_pmu.lbr_to + lbr_idx, to);
if (lbr_format == LBR_FORMAT_EIP_FLAGS) {
flags = !!(from & LBR_FROM_FLAG_MISPRED);
mis = !!(from & LBR_FROM_FLAG_MISPRED);
pred = !mis;
from = (u64)((((s64)from) << 1) >> 1);
}
cpuc->lbr_entries[i].from = from;
cpuc->lbr_entries[i].to = to;
cpuc->lbr_entries[i].flags = flags;
cpuc->lbr_entries[i].from = from;
cpuc->lbr_entries[i].to = to;
cpuc->lbr_entries[i].mispred = mis;
cpuc->lbr_entries[i].predicted = pred;
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
}
@ -193,28 +301,404 @@ void intel_pmu_lbr_read(void)
intel_pmu_lbr_read_32(cpuc);
else
intel_pmu_lbr_read_64(cpuc);
intel_pmu_lbr_filter(cpuc);
}
/*
* SW filter is used:
* - in case there is no HW filter
* - in case the HW filter has errata or limitations
*/
static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
{
u64 br_type = event->attr.branch_sample_type;
int mask = 0;
if (br_type & PERF_SAMPLE_BRANCH_USER)
mask |= X86_BR_USER;
if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
mask |= X86_BR_KERNEL;
/* we ignore BRANCH_HV here */
if (br_type & PERF_SAMPLE_BRANCH_ANY)
mask |= X86_BR_ANY;
if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL)
mask |= X86_BR_ANY_CALL;
if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET;
if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
mask |= X86_BR_IND_CALL;
/*
* stash actual user request into reg, it may
* be used by fixup code for some CPU
*/
event->hw.branch_reg.reg = mask;
}
/*
* setup the HW LBR filter
* Used only when available, may not be enough to disambiguate
* all branches, may need the help of the SW filter
*/
static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
{
struct hw_perf_event_extra *reg;
u64 br_type = event->attr.branch_sample_type;
u64 mask = 0, m;
u64 v;
for_each_branch_sample_type(m) {
if (!(br_type & m))
continue;
v = x86_pmu.lbr_sel_map[m];
if (v == LBR_NOT_SUPP)
return -EOPNOTSUPP;
if (v != LBR_IGN)
mask |= v;
}
reg = &event->hw.branch_reg;
reg->idx = EXTRA_REG_LBR;
/* LBR_SELECT operates in suppress mode so invert mask */
reg->config = ~mask & x86_pmu.lbr_sel_mask;
return 0;
}
int intel_pmu_setup_lbr_filter(struct perf_event *event)
{
int ret = 0;
/*
* no LBR on this PMU
*/
if (!x86_pmu.lbr_nr)
return -EOPNOTSUPP;
/*
* setup SW LBR filter
*/
intel_pmu_setup_sw_lbr_filter(event);
/*
* setup HW LBR filter, if any
*/
if (x86_pmu.lbr_sel_map)
ret = intel_pmu_setup_hw_lbr_filter(event);
return ret;
}
/*
* return the type of control flow change at address "from"
* intruction is not necessarily a branch (in case of interrupt).
*
* The branch type returned also includes the priv level of the
* target of the control flow change (X86_BR_USER, X86_BR_KERNEL).
*
* If a branch type is unknown OR the instruction cannot be
* decoded (e.g., text page not present), then X86_BR_NONE is
* returned.
*/
static int branch_type(unsigned long from, unsigned long to)
{
struct insn insn;
void *addr;
int bytes, size = MAX_INSN_SIZE;
int ret = X86_BR_NONE;
int ext, to_plm, from_plm;
u8 buf[MAX_INSN_SIZE];
int is64 = 0;
to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER;
/*
* maybe zero if lbr did not fill up after a reset by the time
* we get a PMU interrupt
*/
if (from == 0 || to == 0)
return X86_BR_NONE;
if (from_plm == X86_BR_USER) {
/*
* can happen if measuring at the user level only
* and we interrupt in a kernel thread, e.g., idle.
*/
if (!current->mm)
return X86_BR_NONE;
/* may fail if text not present */
bytes = copy_from_user_nmi(buf, (void __user *)from, size);
if (bytes != size)
return X86_BR_NONE;
addr = buf;
} else
addr = (void *)from;
/*
* decoder needs to know the ABI especially
* on 64-bit systems running 32-bit apps
*/
#ifdef CONFIG_X86_64
is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
#endif
insn_init(&insn, addr, is64);
insn_get_opcode(&insn);
switch (insn.opcode.bytes[0]) {
case 0xf:
switch (insn.opcode.bytes[1]) {
case 0x05: /* syscall */
case 0x34: /* sysenter */
ret = X86_BR_SYSCALL;
break;
case 0x07: /* sysret */
case 0x35: /* sysexit */
ret = X86_BR_SYSRET;
break;
case 0x80 ... 0x8f: /* conditional */
ret = X86_BR_JCC;
break;
default:
ret = X86_BR_NONE;
}
break;
case 0x70 ... 0x7f: /* conditional */
ret = X86_BR_JCC;
break;
case 0xc2: /* near ret */
case 0xc3: /* near ret */
case 0xca: /* far ret */
case 0xcb: /* far ret */
ret = X86_BR_RET;
break;
case 0xcf: /* iret */
ret = X86_BR_IRET;
break;
case 0xcc ... 0xce: /* int */
ret = X86_BR_INT;
break;
case 0xe8: /* call near rel */
case 0x9a: /* call far absolute */
ret = X86_BR_CALL;
break;
case 0xe0 ... 0xe3: /* loop jmp */
ret = X86_BR_JCC;
break;
case 0xe9 ... 0xeb: /* jmp */
ret = X86_BR_JMP;
break;
case 0xff: /* call near absolute, call far absolute ind */
insn_get_modrm(&insn);
ext = (insn.modrm.bytes[0] >> 3) & 0x7;
switch (ext) {
case 2: /* near ind call */
case 3: /* far ind call */
ret = X86_BR_IND_CALL;
break;
case 4:
case 5:
ret = X86_BR_JMP;
break;
}
break;
default:
ret = X86_BR_NONE;
}
/*
* interrupts, traps, faults (and thus ring transition) may
* occur on any instructions. Thus, to classify them correctly,
* we need to first look at the from and to priv levels. If they
* are different and to is in the kernel, then it indicates
* a ring transition. If the from instruction is not a ring
* transition instr (syscall, systenter, int), then it means
* it was a irq, trap or fault.
*
* we have no way of detecting kernel to kernel faults.
*/
if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL
&& ret != X86_BR_SYSCALL && ret != X86_BR_INT)
ret = X86_BR_IRQ;
/*
* branch priv level determined by target as
* is done by HW when LBR_SELECT is implemented
*/
if (ret != X86_BR_NONE)
ret |= to_plm;
return ret;
}
/*
* implement actual branch filter based on user demand.
* Hardware may not exactly satisfy that request, thus
* we need to inspect opcodes. Mismatched branches are
* discarded. Therefore, the number of branches returned
* in PERF_SAMPLE_BRANCH_STACK sample may vary.
*/
static void
intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
{
u64 from, to;
int br_sel = cpuc->br_sel;
int i, j, type;
bool compress = false;
/* if sampling all branches, then nothing to filter */
if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
return;
for (i = 0; i < cpuc->lbr_stack.nr; i++) {
from = cpuc->lbr_entries[i].from;
to = cpuc->lbr_entries[i].to;
type = branch_type(from, to);
/* if type does not correspond, then discard */
if (type == X86_BR_NONE || (br_sel & type) != type) {
cpuc->lbr_entries[i].from = 0;
compress = true;
}
}
if (!compress)
return;
/* remove all entries with from=0 */
for (i = 0; i < cpuc->lbr_stack.nr; ) {
if (!cpuc->lbr_entries[i].from) {
j = i;
while (++j < cpuc->lbr_stack.nr)
cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
cpuc->lbr_stack.nr--;
if (!cpuc->lbr_entries[i].from)
continue;
}
i++;
}
}
/*
* Map interface branch filters onto LBR filters
*/
static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
[PERF_SAMPLE_BRANCH_ANY] = LBR_ANY,
[PERF_SAMPLE_BRANCH_USER] = LBR_USER,
[PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL,
[PERF_SAMPLE_BRANCH_HV] = LBR_IGN,
[PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_REL_JMP
| LBR_IND_JMP | LBR_FAR,
/*
* NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
*/
[PERF_SAMPLE_BRANCH_ANY_CALL] =
LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
/*
* NHM/WSM erratum: must include IND_JMP to capture IND_CALL
*/
[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
};
static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
[PERF_SAMPLE_BRANCH_ANY] = LBR_ANY,
[PERF_SAMPLE_BRANCH_USER] = LBR_USER,
[PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL,
[PERF_SAMPLE_BRANCH_HV] = LBR_IGN,
[PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_FAR,
[PERF_SAMPLE_BRANCH_ANY_CALL] = LBR_REL_CALL | LBR_IND_CALL
| LBR_FAR,
[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL,
};
/* core */
void intel_pmu_lbr_init_core(void)
{
x86_pmu.lbr_nr = 4;
x86_pmu.lbr_tos = 0x01c9;
x86_pmu.lbr_from = 0x40;
x86_pmu.lbr_to = 0x60;
x86_pmu.lbr_tos = MSR_LBR_TOS;
x86_pmu.lbr_from = MSR_LBR_CORE_FROM;
x86_pmu.lbr_to = MSR_LBR_CORE_TO;
/*
* SW branch filter usage:
* - compensate for lack of HW filter
*/
pr_cont("4-deep LBR, ");
}
/* nehalem/westmere */
void intel_pmu_lbr_init_nhm(void)
{
x86_pmu.lbr_nr = 16;
x86_pmu.lbr_tos = 0x01c9;
x86_pmu.lbr_from = 0x680;
x86_pmu.lbr_to = 0x6c0;
x86_pmu.lbr_tos = MSR_LBR_TOS;
x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
x86_pmu.lbr_to = MSR_LBR_NHM_TO;
x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
x86_pmu.lbr_sel_map = nhm_lbr_sel_map;
/*
* SW branch filter usage:
* - workaround LBR_SEL errata (see above)
* - support syscall, sysret capture.
* That requires LBR_FAR but that means far
* jmp need to be filtered out
*/
pr_cont("16-deep LBR, ");
}
/* sandy bridge */
void intel_pmu_lbr_init_snb(void)
{
x86_pmu.lbr_nr = 16;
x86_pmu.lbr_tos = MSR_LBR_TOS;
x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
x86_pmu.lbr_to = MSR_LBR_NHM_TO;
x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
x86_pmu.lbr_sel_map = snb_lbr_sel_map;
/*
* SW branch filter usage:
* - support syscall, sysret capture.
* That requires LBR_FAR but that means far
* jmp need to be filtered out
*/
pr_cont("16-deep LBR, ");
}
/* atom */
void intel_pmu_lbr_init_atom(void)
{
/*
* only models starting at stepping 10 seems
* to have an operational LBR which can freeze
* on PMU interrupt
*/
if (boot_cpu_data.x86_mask < 10) {
pr_cont("LBR disabled due to erratum");
return;
}
x86_pmu.lbr_nr = 8;
x86_pmu.lbr_tos = 0x01c9;
x86_pmu.lbr_from = 0x40;
x86_pmu.lbr_to = 0x60;
x86_pmu.lbr_tos = MSR_LBR_TOS;
x86_pmu.lbr_from = MSR_LBR_CORE_FROM;
x86_pmu.lbr_to = MSR_LBR_CORE_TO;
/*
* SW branch filter usage:
* - compensate for lack of HW filter
*/
pr_cont("8-deep LBR, ");
}

102
arch/x86/kernel/kprobes-common.h Normal file
View File

@ -0,0 +1,102 @@
#ifndef __X86_KERNEL_KPROBES_COMMON_H
#define __X86_KERNEL_KPROBES_COMMON_H
/* Kprobes and Optprobes common header */
#ifdef CONFIG_X86_64
#define SAVE_REGS_STRING \
/* Skip cs, ip, orig_ax. */ \
" subq $24, %rsp\n" \
" pushq %rdi\n" \
" pushq %rsi\n" \
" pushq %rdx\n" \
" pushq %rcx\n" \
" pushq %rax\n" \
" pushq %r8\n" \
" pushq %r9\n" \
" pushq %r10\n" \
" pushq %r11\n" \
" pushq %rbx\n" \
" pushq %rbp\n" \
" pushq %r12\n" \
" pushq %r13\n" \
" pushq %r14\n" \
" pushq %r15\n"
#define RESTORE_REGS_STRING \
" popq %r15\n" \
" popq %r14\n" \
" popq %r13\n" \
" popq %r12\n" \
" popq %rbp\n" \
" popq %rbx\n" \
" popq %r11\n" \
" popq %r10\n" \
" popq %r9\n" \
" popq %r8\n" \
" popq %rax\n" \
" popq %rcx\n" \
" popq %rdx\n" \
" popq %rsi\n" \
" popq %rdi\n" \
/* Skip orig_ax, ip, cs */ \
" addq $24, %rsp\n"
#else
#define SAVE_REGS_STRING \
/* Skip cs, ip, orig_ax and gs. */ \
" subl $16, %esp\n" \
" pushl %fs\n" \
" pushl %es\n" \
" pushl %ds\n" \
" pushl %eax\n" \
" pushl %ebp\n" \
" pushl %edi\n" \
" pushl %esi\n" \
" pushl %edx\n" \
" pushl %ecx\n" \
" pushl %ebx\n"
#define RESTORE_REGS_STRING \
" popl %ebx\n" \
" popl %ecx\n" \
" popl %edx\n" \
" popl %esi\n" \
" popl %edi\n" \
" popl %ebp\n" \
" popl %eax\n" \
/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
" addl $24, %esp\n"
#endif
/* Ensure if the instruction can be boostable */
extern int can_boost(kprobe_opcode_t *instruction);
/* Recover instruction if given address is probed */
extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
unsigned long addr);
/*
* Copy an instruction and adjust the displacement if the instruction
* uses the %rip-relative addressing mode.
*/
extern int __copy_instruction(u8 *dest, u8 *src);
/* Generate a relative-jump/call instruction */
extern void synthesize_reljump(void *from, void *to);
extern void synthesize_relcall(void *from, void *to);
#ifdef CONFIG_OPTPROBES
extern int arch_init_optprobes(void);
extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
#else /* !CONFIG_OPTPROBES */
static inline int arch_init_optprobes(void)
{
return 0;
}
static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
{
return 0;
}
static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
return addr;
}
#endif
#endif

512
arch/x86/kernel/kprobes-opt.c Normal file
View File

@ -0,0 +1,512 @@
/*
* Kernel Probes Jump Optimization (Optprobes)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright (C) IBM Corporation, 2002, 2004
* Copyright (C) Hitachi Ltd., 2012
*/
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/hardirq.h>
#include <linux/preempt.h>
#include <linux/module.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
#include <linux/ftrace.h>
#include <asm/cacheflush.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/uaccess.h>
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/debugreg.h>
#include "kprobes-common.h"
unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
struct optimized_kprobe *op;
struct kprobe *kp;
long offs;
int i;
for (i = 0; i < RELATIVEJUMP_SIZE; i++) {
kp = get_kprobe((void *)addr - i);
/* This function only handles jump-optimized kprobe */
if (kp && kprobe_optimized(kp)) {
op = container_of(kp, struct optimized_kprobe, kp);
/* If op->list is not empty, op is under optimizing */
if (list_empty(&op->list))
goto found;
}
}
return addr;
found:
/*
* If the kprobe can be optimized, original bytes which can be
* overwritten by jump destination address. In this case, original
* bytes must be recovered from op->optinsn.copied_insn buffer.
*/
memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
if (addr == (unsigned long)kp->addr) {
buf[0] = kp->opcode;
memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
} else {
offs = addr - (unsigned long)kp->addr - 1;
memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs);
}
return (unsigned long)buf;
}
/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
{
#ifdef CONFIG_X86_64
*addr++ = 0x48;
*addr++ = 0xbf;
#else
*addr++ = 0xb8;
#endif
*(unsigned long *)addr = val;
}
static void __used __kprobes kprobes_optinsn_template_holder(void)
{
asm volatile (
".global optprobe_template_entry\n"
"optprobe_template_entry:\n"
#ifdef CONFIG_X86_64
/* We don't bother saving the ss register */
" pushq %rsp\n"
" pushfq\n"
SAVE_REGS_STRING
" movq %rsp, %rsi\n"
".global optprobe_template_val\n"
"optprobe_template_val:\n"
ASM_NOP5
ASM_NOP5
".global optprobe_template_call\n"
"optprobe_template_call:\n"
ASM_NOP5
/* Move flags to rsp */
" movq 144(%rsp), %rdx\n"
" movq %rdx, 152(%rsp)\n"
RESTORE_REGS_STRING
/* Skip flags entry */
" addq $8, %rsp\n"
" popfq\n"
#else /* CONFIG_X86_32 */
" pushf\n"
SAVE_REGS_STRING
" movl %esp, %edx\n"
".global optprobe_template_val\n"
"optprobe_template_val:\n"
ASM_NOP5
".global optprobe_template_call\n"
"optprobe_template_call:\n"
ASM_NOP5
RESTORE_REGS_STRING
" addl $4, %esp\n" /* skip cs */
" popf\n"
#endif
".global optprobe_template_end\n"
"optprobe_template_end:\n");
}
#define TMPL_MOVE_IDX \
((long)&optprobe_template_val - (long)&optprobe_template_entry)
#define TMPL_CALL_IDX \
((long)&optprobe_template_call - (long)&optprobe_template_entry)
#define TMPL_END_IDX \
((long)&optprobe_template_end - (long)&optprobe_template_entry)
#define INT3_SIZE sizeof(kprobe_opcode_t)
/* Optimized kprobe call back function: called from optinsn */
static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long flags;
/* This is possible if op is under delayed unoptimizing */
if (kprobe_disabled(&op->kp))
return;
local_irq_save(flags);
if (kprobe_running()) {
kprobes_inc_nmissed_count(&op->kp);
} else {
/* Save skipped registers */
#ifdef CONFIG_X86_64
regs->cs = __KERNEL_CS;
#else
regs->cs = __KERNEL_CS | get_kernel_rpl();
regs->gs = 0;
#endif
regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
regs->orig_ax = ~0UL;
__this_cpu_write(current_kprobe, &op->kp);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
opt_pre_handler(&op->kp, regs);
__this_cpu_write(current_kprobe, NULL);
}
local_irq_restore(flags);
}
static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
{
int len = 0, ret;
while (len < RELATIVEJUMP_SIZE) {
ret = __copy_instruction(dest + len, src + len);
if (!ret || !can_boost(dest + len))
return -EINVAL;
len += ret;
}
/* Check whether the address range is reserved */
if (ftrace_text_reserved(src, src + len - 1) ||
alternatives_text_reserved(src, src + len - 1) ||
jump_label_text_reserved(src, src + len - 1))
return -EBUSY;
return len;
}
/* Check whether insn is indirect jump */
static int __kprobes insn_is_indirect_jump(struct insn *insn)
{
return ((insn->opcode.bytes[0] == 0xff &&
(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
insn->opcode.bytes[0] == 0xea); /* Segment based jump */
}
/* Check whether insn jumps into specified address range */
static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
{
unsigned long target = 0;
switch (insn->opcode.bytes[0]) {
case 0xe0: /* loopne */
case 0xe1: /* loope */
case 0xe2: /* loop */
case 0xe3: /* jcxz */
case 0xe9: /* near relative jump */
case 0xeb: /* short relative jump */
break;
case 0x0f:
if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
break;
return 0;
default:
if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
break;
return 0;
}
target = (unsigned long)insn->next_byte + insn->immediate.value;
return (start <= target && target <= start + len);
}
/* Decode whole function to ensure any instructions don't jump into target */
static int __kprobes can_optimize(unsigned long paddr)
{
unsigned long addr, size = 0, offset = 0;
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
/* Lookup symbol including addr */
if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
return 0;
/*
* Do not optimize in the entry code due to the unstable
* stack handling.
*/
if ((paddr >= (unsigned long)__entry_text_start) &&
(paddr < (unsigned long)__entry_text_end))
return 0;
/* Check there is enough space for a relative jump. */
if (size - offset < RELATIVEJUMP_SIZE)
return 0;
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr - offset + size) { /* Decode until function end */
if (search_exception_tables(addr))
/*
* Since some fixup code will jumps into this function,
* we can't optimize kprobe in this function.
*/
return 0;
kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr));
insn_get_length(&insn);
/* Another subsystem puts a breakpoint */
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;
/* Recover address */
insn.kaddr = (void *)addr;
insn.next_byte = (void *)(addr + insn.length);
/* Check any instructions don't jump into target */
if (insn_is_indirect_jump(&insn) ||
insn_jump_into_range(&insn, paddr + INT3_SIZE,
RELATIVE_ADDR_SIZE))
return 0;
addr += insn.length;
}
return 1;
}
/* Check optimized_kprobe can actually be optimized. */
int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
{
int i;
struct kprobe *p;
for (i = 1; i < op->optinsn.size; i++) {
p = get_kprobe(op->kp.addr + i);
if (p && !kprobe_disabled(p))
return -EEXIST;
}
return 0;
}
/* Check the addr is within the optimized instructions. */
int __kprobes
arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr)
{
return ((unsigned long)op->kp.addr <= addr &&
(unsigned long)op->kp.addr + op->optinsn.size > addr);
}
/* Free optimized instruction slot */
static __kprobes
void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
{
if (op->optinsn.insn) {
free_optinsn_slot(op->optinsn.insn, dirty);
op->optinsn.insn = NULL;
op->optinsn.size = 0;
}
}
void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
{
__arch_remove_optimized_kprobe(op, 1);
}
/*
* Copy replacing target instructions
* Target instructions MUST be relocatable (checked inside)
* This is called when new aggr(opt)probe is allocated or reused.
*/
int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
{
u8 *buf;
int ret;
long rel;
if (!can_optimize((unsigned long)op->kp.addr))
return -EILSEQ;
op->optinsn.insn = get_optinsn_slot();
if (!op->optinsn.insn)
return -ENOMEM;
/*
* Verify if the address gap is in 2GB range, because this uses
* a relative jump.
*/
rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
if (abs(rel) > 0x7fffffff)
return -ERANGE;
buf = (u8 *)op->optinsn.insn;
/* Copy instructions into the out-of-line buffer */
ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
if (ret < 0) {
__arch_remove_optimized_kprobe(op, 0);
return ret;
}
op->optinsn.size = ret;
/* Copy arch-dep-instance from template */
memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
/* Set probe information */
synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
/* Set probe function call */
synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
/* Set returning jmp instruction at the tail of out-of-line buffer */
synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
(u8 *)op->kp.addr + op->optinsn.size);
flush_icache_range((unsigned long) buf,
(unsigned long) buf + TMPL_END_IDX +
op->optinsn.size + RELATIVEJUMP_SIZE);
return 0;
}
#define MAX_OPTIMIZE_PROBES 256
static struct text_poke_param *jump_poke_params;
static struct jump_poke_buffer {
u8 buf[RELATIVEJUMP_SIZE];
} *jump_poke_bufs;
static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
u8 *insn_buf,
struct optimized_kprobe *op)
{
s32 rel = (s32)((long)op->optinsn.insn -
((long)op->kp.addr + RELATIVEJUMP_SIZE));
/* Backup instructions which will be replaced by jump address */
memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
RELATIVE_ADDR_SIZE);
insn_buf[0] = RELATIVEJUMP_OPCODE;
*(s32 *)(&insn_buf[1]) = rel;
tprm->addr = op->kp.addr;
tprm->opcode = insn_buf;
tprm->len = RELATIVEJUMP_SIZE;
}
/*
* Replace breakpoints (int3) with relative jumps.
* Caller must call with locking kprobe_mutex and text_mutex.
*/
void __kprobes arch_optimize_kprobes(struct list_head *oplist)
{
struct optimized_kprobe *op, *tmp;
int c = 0;
list_for_each_entry_safe(op, tmp, oplist, list) {
WARN_ON(kprobe_disabled(&op->kp));
/* Setup param */
setup_optimize_kprobe(&jump_poke_params[c],
jump_poke_bufs[c].buf, op);
list_del_init(&op->list);
if (++c >= MAX_OPTIMIZE_PROBES)
break;
}
/*
* text_poke_smp doesn't support NMI/MCE code modifying.
* However, since kprobes itself also doesn't support NMI/MCE
* code probing, it's not a problem.
*/
text_poke_smp_batch(jump_poke_params, c);
}
static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
u8 *insn_buf,
struct optimized_kprobe *op)
{
/* Set int3 to first byte for kprobes */
insn_buf[0] = BREAKPOINT_INSTRUCTION;
memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
tprm->addr = op->kp.addr;
tprm->opcode = insn_buf;
tprm->len = RELATIVEJUMP_SIZE;
}
/*
* Recover original instructions and breakpoints from relative jumps.
* Caller must call with locking kprobe_mutex.
*/
extern void arch_unoptimize_kprobes(struct list_head *oplist,
struct list_head *done_list)
{
struct optimized_kprobe *op, *tmp;
int c = 0;
list_for_each_entry_safe(op, tmp, oplist, list) {
/* Setup param */
setup_unoptimize_kprobe(&jump_poke_params[c],
jump_poke_bufs[c].buf, op);
list_move(&op->list, done_list);
if (++c >= MAX_OPTIMIZE_PROBES)
break;
}
/*
* text_poke_smp doesn't support NMI/MCE code modifying.
* However, since kprobes itself also doesn't support NMI/MCE
* code probing, it's not a problem.
*/
text_poke_smp_batch(jump_poke_params, c);
}
/* Replace a relative jump with a breakpoint (int3). */
void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
{
u8 buf[RELATIVEJUMP_SIZE];
/* Set int3 to first byte for kprobes */
buf[0] = BREAKPOINT_INSTRUCTION;
memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
}
int __kprobes
setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
{
struct optimized_kprobe *op;
if (p->flags & KPROBE_FLAG_OPTIMIZED) {
/* This kprobe is really able to run optimized path. */
op = container_of(p, struct optimized_kprobe, kp);
/* Detour through copied instructions */
regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
if (!reenter)
reset_current_kprobe();
preempt_enable_no_resched();
return 1;
}
return 0;
}
int __kprobes arch_init_optprobes(void)
{
/* Allocate code buffer and parameter array */
jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
MAX_OPTIMIZE_PROBES, GFP_KERNEL);
if (!jump_poke_bufs)
return -ENOMEM;
jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
MAX_OPTIMIZE_PROBES, GFP_KERNEL);
if (!jump_poke_params) {
kfree(jump_poke_bufs);
jump_poke_bufs = NULL;
return -ENOMEM;
}
return 0;
}

666
arch/x86/kernel/kprobes.c
View File

@ -30,16 +30,15 @@
* <jkenisto@us.ibm.com> and Prasanna S Panchamukhi
* <prasanna@in.ibm.com> added function-return probes.
* 2005-May Rusty Lynch <rusty.lynch@intel.com>
* Added function return probes functionality
* Added function return probes functionality
* 2006-Feb Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
* kprobe-booster and kretprobe-booster for i386.
* kprobe-booster and kretprobe-booster for i386.
* 2007-Dec Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
* and kretprobe-booster for x86-64
* and kretprobe-booster for x86-64
* 2007-Dec Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven
* <arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
* unified x86 kprobes code.
* <arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
* unified x86 kprobes code.
*/
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/string.h>
@ -59,6 +58,8 @@
#include <asm/insn.h>
#include <asm/debugreg.h>
#include "kprobes-common.h"
void jprobe_return_end(void);
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
@ -108,6 +109,7 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {
doesn't switch kernel stack.*/
{NULL, NULL} /* Terminator */
};
const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
@ -123,11 +125,17 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
}
/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
static void __kprobes synthesize_reljump(void *from, void *to)
void __kprobes synthesize_reljump(void *from, void *to)
{
__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
}
/* Insert a call instruction at address 'from', which calls address 'to'.*/
void __kprobes synthesize_relcall(void *from, void *to)
{
__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
}
/*
* Skip the prefixes of the instruction.
*/
@ -151,7 +159,7 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
* Returns non-zero if opcode is boostable.
* RIP relative instructions are adjusted at copying time in 64 bits mode
*/
static int __kprobes can_boost(kprobe_opcode_t *opcodes)
int __kprobes can_boost(kprobe_opcode_t *opcodes)
{
kprobe_opcode_t opcode;
kprobe_opcode_t *orig_opcodes = opcodes;
@ -207,13 +215,15 @@ retry:
}
}
/* Recover the probed instruction at addr for further analysis. */
static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
static unsigned long
__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
struct kprobe *kp;
kp = get_kprobe((void *)addr);
/* There is no probe, return original address */
if (!kp)
return -EINVAL;
return addr;
/*
* Basically, kp->ainsn.insn has an original instruction.
@ -230,14 +240,29 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
*/
memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
buf[0] = kp->opcode;
return 0;
return (unsigned long)buf;
}
/*
* Recover the probed instruction at addr for further analysis.
* Caller must lock kprobes by kprobe_mutex, or disable preemption
* for preventing to release referencing kprobes.
*/
unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
{
unsigned long __addr;
__addr = __recover_optprobed_insn(buf, addr);
if (__addr != addr)
return __addr;
return __recover_probed_insn(buf, addr);
}
/* Check if paddr is at an instruction boundary */
static int __kprobes can_probe(unsigned long paddr)
{
int ret;
unsigned long addr, offset = 0;
unsigned long addr, __addr, offset = 0;
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
@ -247,26 +272,24 @@ static int __kprobes can_probe(unsigned long paddr)
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr) {
kernel_insn_init(&insn, (void *)addr);
insn_get_opcode(&insn);
/*
* Check if the instruction has been modified by another
* kprobe, in which case we replace the breakpoint by the
* original instruction in our buffer.
* Also, jump optimization will change the breakpoint to
* relative-jump. Since the relative-jump itself is
* normally used, we just go through if there is no kprobe.
*/
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
ret = recover_probed_instruction(buf, addr);
if (ret)
/*
* Another debugging subsystem might insert
* this breakpoint. In that case, we can't
* recover it.
*/
return 0;
kernel_insn_init(&insn, buf);
}
__addr = recover_probed_instruction(buf, addr);
kernel_insn_init(&insn, (void *)__addr);
insn_get_length(&insn);
/*
* Another debugging subsystem might insert this breakpoint.
* In that case, we can't recover it.
*/
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;
addr += insn.length;
}
@ -299,24 +322,16 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
* If not, return null.
* Only applicable to 64-bit x86.
*/
static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
int __kprobes __copy_instruction(u8 *dest, u8 *src)
{
struct insn insn;
int ret;
kprobe_opcode_t buf[MAX_INSN_SIZE];
kernel_insn_init(&insn, src);
if (recover) {
insn_get_opcode(&insn);
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
ret = recover_probed_instruction(buf,
(unsigned long)src);
if (ret)
return 0;
kernel_insn_init(&insn, buf);
}
}
kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
insn_get_length(&insn);
/* Another subsystem puts a breakpoint, failed to recover */
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;
memcpy(dest, insn.kaddr, insn.length);
#ifdef CONFIG_X86_64
@ -337,8 +352,7 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
* extension of the original signed 32-bit displacement would
* have given.
*/
newdisp = (u8 *) src + (s64) insn.displacement.value -
(u8 *) dest;
newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */
disp = (u8 *) dest + insn_offset_displacement(&insn);
*(s32 *) disp = (s32) newdisp;
@ -349,18 +363,20 @@ static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
static void __kprobes arch_copy_kprobe(struct kprobe *p)
{
/*
* Copy an instruction without recovering int3, because it will be
* put by another subsystem.
*/
__copy_instruction(p->ainsn.insn, p->addr, 0);
/* Copy an instruction with recovering if other optprobe modifies it.*/
__copy_instruction(p->ainsn.insn, p->addr);
if (can_boost(p->addr))
/*
* __copy_instruction can modify the displacement of the instruction,
* but it doesn't affect boostable check.
*/
if (can_boost(p->ainsn.insn))
p->ainsn.boostable = 0;
else
p->ainsn.boostable = -1;
p->opcode = *p->addr;
/* Also, displacement change doesn't affect the first byte */
p->opcode = p->ainsn.insn[0];
}
int __kprobes arch_prepare_kprobe(struct kprobe *p)
@ -442,8 +458,8 @@ static void __kprobes restore_btf(void)
}
}
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
void __kprobes
arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
{
unsigned long *sara = stack_addr(regs);
@ -453,16 +469,8 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
*sara = (unsigned long) &kretprobe_trampoline;
}
#ifdef CONFIG_OPTPROBES
static int __kprobes setup_detour_execution(struct kprobe *p,
struct pt_regs *regs,
int reenter);
#else
#define setup_detour_execution(p, regs, reenter) (0)
#endif
static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb, int reenter)
static void __kprobes
setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter)
{
if (setup_detour_execution(p, regs, reenter))
return;
@ -504,8 +512,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
* within the handler. We save the original kprobes variables and just single
* step on the instruction of the new probe without calling any user handlers.
*/
static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
static int __kprobes
reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
switch (kcb->kprobe_status) {
case KPROBE_HIT_SSDONE:
@ -600,69 +608,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
return 0;
}
#ifdef CONFIG_X86_64
#define SAVE_REGS_STRING \
/* Skip cs, ip, orig_ax. */ \
" subq $24, %rsp\n" \
" pushq %rdi\n" \
" pushq %rsi\n" \
" pushq %rdx\n" \
" pushq %rcx\n" \
" pushq %rax\n" \
" pushq %r8\n" \
" pushq %r9\n" \
" pushq %r10\n" \
" pushq %r11\n" \
" pushq %rbx\n" \
" pushq %rbp\n" \
" pushq %r12\n" \
" pushq %r13\n" \
" pushq %r14\n" \
" pushq %r15\n"
#define RESTORE_REGS_STRING \
" popq %r15\n" \
" popq %r14\n" \
" popq %r13\n" \
" popq %r12\n" \
" popq %rbp\n" \
" popq %rbx\n" \
" popq %r11\n" \
" popq %r10\n" \
" popq %r9\n" \
" popq %r8\n" \
" popq %rax\n" \
" popq %rcx\n" \
" popq %rdx\n" \
" popq %rsi\n" \
" popq %rdi\n" \
/* Skip orig_ax, ip, cs */ \
" addq $24, %rsp\n"
#else
#define SAVE_REGS_STRING \
/* Skip cs, ip, orig_ax and gs. */ \
" subl $16, %esp\n" \
" pushl %fs\n" \
" pushl %es\n" \
" pushl %ds\n" \
" pushl %eax\n" \
" pushl %ebp\n" \
" pushl %edi\n" \
" pushl %esi\n" \
" pushl %edx\n" \
" pushl %ecx\n" \
" pushl %ebx\n"
#define RESTORE_REGS_STRING \
" popl %ebx\n" \
" popl %ecx\n" \
" popl %edx\n" \
" popl %esi\n" \
" popl %edi\n" \
" popl %ebp\n" \
" popl %eax\n" \
/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
" addl $24, %esp\n"
#endif
/*
* When a retprobed function returns, this code saves registers and
* calls trampoline_handler() runs, which calls the kretprobe's handler.
@ -816,8 +761,8 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
* jump instruction after the copied instruction, that jumps to the next
* instruction after the probepoint.
*/
static void __kprobes resume_execution(struct kprobe *p,
struct pt_regs *regs, struct kprobe_ctlblk *kcb)
static void __kprobes
resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
unsigned long *tos = stack_addr(regs);
unsigned long copy_ip = (unsigned long)p->ainsn.insn;
@ -996,8 +941,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
/*
* Wrapper routine for handling exceptions.
*/
int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
int __kprobes
kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
{
struct die_args *args = data;
int ret = NOTIFY_DONE;
@ -1107,466 +1052,9 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
return 0;
}
#ifdef CONFIG_OPTPROBES
/* Insert a call instruction at address 'from', which calls address 'to'.*/
static void __kprobes synthesize_relcall(void *from, void *to)
{
__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
}
/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr,
unsigned long val)
{
#ifdef CONFIG_X86_64
*addr++ = 0x48;
*addr++ = 0xbf;
#else
*addr++ = 0xb8;
#endif
*(unsigned long *)addr = val;
}
static void __used __kprobes kprobes_optinsn_template_holder(void)
{
asm volatile (
".global optprobe_template_entry\n"
"optprobe_template_entry: \n"
#ifdef CONFIG_X86_64
/* We don't bother saving the ss register */
" pushq %rsp\n"
" pushfq\n"
SAVE_REGS_STRING
" movq %rsp, %rsi\n"
".global optprobe_template_val\n"
"optprobe_template_val: \n"
ASM_NOP5
ASM_NOP5
".global optprobe_template_call\n"
"optprobe_template_call: \n"
ASM_NOP5
/* Move flags to rsp */
" movq 144(%rsp), %rdx\n"
" movq %rdx, 152(%rsp)\n"
RESTORE_REGS_STRING
/* Skip flags entry */
" addq $8, %rsp\n"
" popfq\n"
#else /* CONFIG_X86_32 */
" pushf\n"
SAVE_REGS_STRING
" movl %esp, %edx\n"
".global optprobe_template_val\n"
"optprobe_template_val: \n"
ASM_NOP5
".global optprobe_template_call\n"
"optprobe_template_call: \n"
ASM_NOP5
RESTORE_REGS_STRING
" addl $4, %esp\n" /* skip cs */
" popf\n"
#endif
".global optprobe_template_end\n"
"optprobe_template_end: \n");
}
#define TMPL_MOVE_IDX \
((long)&optprobe_template_val - (long)&optprobe_template_entry)
#define TMPL_CALL_IDX \
((long)&optprobe_template_call - (long)&optprobe_template_entry)
#define TMPL_END_IDX \
((long)&optprobe_template_end - (long)&optprobe_template_entry)
#define INT3_SIZE sizeof(kprobe_opcode_t)
/* Optimized kprobe call back function: called from optinsn */
static void __kprobes optimized_callback(struct optimized_kprobe *op,
struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long flags;
/* This is possible if op is under delayed unoptimizing */
if (kprobe_disabled(&op->kp))
return;
local_irq_save(flags);
if (kprobe_running()) {
kprobes_inc_nmissed_count(&op->kp);
} else {
/* Save skipped registers */
#ifdef CONFIG_X86_64
regs->cs = __KERNEL_CS;
#else
regs->cs = __KERNEL_CS | get_kernel_rpl();
regs->gs = 0;
#endif
regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
regs->orig_ax = ~0UL;
__this_cpu_write(current_kprobe, &op->kp);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
opt_pre_handler(&op->kp, regs);
__this_cpu_write(current_kprobe, NULL);
}
local_irq_restore(flags);
}
static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
{
int len = 0, ret;
while (len < RELATIVEJUMP_SIZE) {
ret = __copy_instruction(dest + len, src + len, 1);
if (!ret || !can_boost(dest + len))
return -EINVAL;
len += ret;
}
/* Check whether the address range is reserved */
if (ftrace_text_reserved(src, src + len - 1) ||
alternatives_text_reserved(src, src + len - 1) ||
jump_label_text_reserved(src, src + len - 1))
return -EBUSY;
return len;
}
/* Check whether insn is indirect jump */
static int __kprobes insn_is_indirect_jump(struct insn *insn)
{
return ((insn->opcode.bytes[0] == 0xff &&
(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
insn->opcode.bytes[0] == 0xea); /* Segment based jump */
}
/* Check whether insn jumps into specified address range */
static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
{
unsigned long target = 0;
switch (insn->opcode.bytes[0]) {
case 0xe0: /* loopne */
case 0xe1: /* loope */
case 0xe2: /* loop */
case 0xe3: /* jcxz */
case 0xe9: /* near relative jump */
case 0xeb: /* short relative jump */
break;
case 0x0f:
if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
break;
return 0;
default:
if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
break;
return 0;
}
target = (unsigned long)insn->next_byte + insn->immediate.value;
return (start <= target && target <= start + len);
}
/* Decode whole function to ensure any instructions don't jump into target */
static int __kprobes can_optimize(unsigned long paddr)
{
int ret;
unsigned long addr, size = 0, offset = 0;
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
/* Lookup symbol including addr */
if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
return 0;
/*
* Do not optimize in the entry code due to the unstable
* stack handling.
*/
if ((paddr >= (unsigned long )__entry_text_start) &&
(paddr < (unsigned long )__entry_text_end))
return 0;
/* Check there is enough space for a relative jump. */
if (size - offset < RELATIVEJUMP_SIZE)
return 0;
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr - offset + size) { /* Decode until function end */
if (search_exception_tables(addr))
/*
* Since some fixup code will jumps into this function,
* we can't optimize kprobe in this function.
*/
return 0;
kernel_insn_init(&insn, (void *)addr);
insn_get_opcode(&insn);
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
ret = recover_probed_instruction(buf, addr);
if (ret)
return 0;
kernel_insn_init(&insn, buf);
}
insn_get_length(&insn);
/* Recover address */
insn.kaddr = (void *)addr;
insn.next_byte = (void *)(addr + insn.length);
/* Check any instructions don't jump into target */
if (insn_is_indirect_jump(&insn) ||
insn_jump_into_range(&insn, paddr + INT3_SIZE,
RELATIVE_ADDR_SIZE))
return 0;
addr += insn.length;
}
return 1;
}
/* Check optimized_kprobe can actually be optimized. */
int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
{
int i;
struct kprobe *p;
for (i = 1; i < op->optinsn.size; i++) {
p = get_kprobe(op->kp.addr + i);
if (p && !kprobe_disabled(p))
return -EEXIST;
}
return 0;
}
/* Check the addr is within the optimized instructions. */
int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op,
unsigned long addr)
{
return ((unsigned long)op->kp.addr <= addr &&
(unsigned long)op->kp.addr + op->optinsn.size > addr);
}
/* Free optimized instruction slot */
static __kprobes
void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
{
if (op->optinsn.insn) {
free_optinsn_slot(op->optinsn.insn, dirty);
op->optinsn.insn = NULL;
op->optinsn.size = 0;
}
}
void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
{
__arch_remove_optimized_kprobe(op, 1);
}
/*
* Copy replacing target instructions
* Target instructions MUST be relocatable (checked inside)
*/
int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
{
u8 *buf;
int ret;
long rel;
if (!can_optimize((unsigned long)op->kp.addr))
return -EILSEQ;
op->optinsn.insn = get_optinsn_slot();
if (!op->optinsn.insn)
return -ENOMEM;
/*
* Verify if the address gap is in 2GB range, because this uses
* a relative jump.
*/
rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
if (abs(rel) > 0x7fffffff)
return -ERANGE;
buf = (u8 *)op->optinsn.insn;
/* Copy instructions into the out-of-line buffer */
ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
if (ret < 0) {
__arch_remove_optimized_kprobe(op, 0);
return ret;
}
op->optinsn.size = ret;
/* Copy arch-dep-instance from template */
memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
/* Set probe information */
synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
/* Set probe function call */
synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
/* Set returning jmp instruction at the tail of out-of-line buffer */
synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
(u8 *)op->kp.addr + op->optinsn.size);
flush_icache_range((unsigned long) buf,
(unsigned long) buf + TMPL_END_IDX +
op->optinsn.size + RELATIVEJUMP_SIZE);
return 0;
}
#define MAX_OPTIMIZE_PROBES 256
static struct text_poke_param *jump_poke_params;
static struct jump_poke_buffer {
u8 buf[RELATIVEJUMP_SIZE];
} *jump_poke_bufs;
static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
u8 *insn_buf,
struct optimized_kprobe *op)
{
s32 rel = (s32)((long)op->optinsn.insn -
((long)op->kp.addr + RELATIVEJUMP_SIZE));
/* Backup instructions which will be replaced by jump address */
memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
RELATIVE_ADDR_SIZE);
insn_buf[0] = RELATIVEJUMP_OPCODE;
*(s32 *)(&insn_buf[1]) = rel;
tprm->addr = op->kp.addr;
tprm->opcode = insn_buf;
tprm->len = RELATIVEJUMP_SIZE;
}
/*
* Replace breakpoints (int3) with relative jumps.
* Caller must call with locking kprobe_mutex and text_mutex.
*/
void __kprobes arch_optimize_kprobes(struct list_head *oplist)
{
struct optimized_kprobe *op, *tmp;
int c = 0;
list_for_each_entry_safe(op, tmp, oplist, list) {
WARN_ON(kprobe_disabled(&op->kp));
/* Setup param */
setup_optimize_kprobe(&jump_poke_params[c],
jump_poke_bufs[c].buf, op);
list_del_init(&op->list);
if (++c >= MAX_OPTIMIZE_PROBES)
break;
}
/*
* text_poke_smp doesn't support NMI/MCE code modifying.
* However, since kprobes itself also doesn't support NMI/MCE
* code probing, it's not a problem.
*/
text_poke_smp_batch(jump_poke_params, c);
}
static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
u8 *insn_buf,
struct optimized_kprobe *op)
{
/* Set int3 to first byte for kprobes */
insn_buf[0] = BREAKPOINT_INSTRUCTION;
memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
tprm->addr = op->kp.addr;
tprm->opcode = insn_buf;
tprm->len = RELATIVEJUMP_SIZE;
}
/*
* Recover original instructions and breakpoints from relative jumps.
* Caller must call with locking kprobe_mutex.
*/
extern void arch_unoptimize_kprobes(struct list_head *oplist,
struct list_head *done_list)
{
struct optimized_kprobe *op, *tmp;
int c = 0;
list_for_each_entry_safe(op, tmp, oplist, list) {
/* Setup param */
setup_unoptimize_kprobe(&jump_poke_params[c],
jump_poke_bufs[c].buf, op);
list_move(&op->list, done_list);
if (++c >= MAX_OPTIMIZE_PROBES)
break;
}
/*
* text_poke_smp doesn't support NMI/MCE code modifying.
* However, since kprobes itself also doesn't support NMI/MCE
* code probing, it's not a problem.
*/
text_poke_smp_batch(jump_poke_params, c);
}
/* Replace a relative jump with a breakpoint (int3). */
void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
{
u8 buf[RELATIVEJUMP_SIZE];
/* Set int3 to first byte for kprobes */
buf[0] = BREAKPOINT_INSTRUCTION;
memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
}
static int __kprobes setup_detour_execution(struct kprobe *p,
struct pt_regs *regs,
int reenter)
{
struct optimized_kprobe *op;
if (p->flags & KPROBE_FLAG_OPTIMIZED) {
/* This kprobe is really able to run optimized path. */
op = container_of(p, struct optimized_kprobe, kp);
/* Detour through copied instructions */
regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
if (!reenter)
reset_current_kprobe();
preempt_enable_no_resched();
return 1;
}
return 0;
}
static int __kprobes init_poke_params(void)
{
/* Allocate code buffer and parameter array */
jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
MAX_OPTIMIZE_PROBES, GFP_KERNEL);
if (!jump_poke_bufs)
return -ENOMEM;
jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
MAX_OPTIMIZE_PROBES, GFP_KERNEL);
if (!jump_poke_params) {
kfree(jump_poke_bufs);
jump_poke_bufs = NULL;
return -ENOMEM;
}
return 0;
}
#else /* !CONFIG_OPTPROBES */
static int __kprobes init_poke_params(void)
{
return 0;
}
#endif
int __init arch_init_kprobes(void)
{
return init_poke_params();
return arch_init_optprobes();
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)

4
arch/x86/kernel/kvm.c
View File

@ -438,9 +438,9 @@ void __init kvm_guest_init(void)
static __init int activate_jump_labels(void)
{
if (has_steal_clock) {
jump_label_inc(&paravirt_steal_enabled);
static_key_slow_inc(&paravirt_steal_enabled);
if (steal_acc)
jump_label_inc(&paravirt_steal_rq_enabled);
static_key_slow_inc(&paravirt_steal_rq_enabled);
}
return 0;

4
arch/x86/kernel/paravirt.c
View File

@ -202,8 +202,8 @@ static void native_flush_tlb_single(unsigned long addr)
__native_flush_tlb_single(addr);
}
struct jump_label_key paravirt_steal_enabled;
struct jump_label_key paravirt_steal_rq_enabled;
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
static u64 native_steal_clock(int cpu)
{

24
arch/x86/kernel/process.c
View File

@ -377,8 +377,8 @@ static inline int hlt_use_halt(void)
void default_idle(void)
{
if (hlt_use_halt()) {
trace_power_start(POWER_CSTATE, 1, smp_processor_id());
trace_cpu_idle(1, smp_processor_id());
trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
trace_cpu_idle_rcuidle(1, smp_processor_id());
current_thread_info()->status &= ~TS_POLLING;
/*
* TS_POLLING-cleared state must be visible before we
@ -391,8 +391,8 @@ void default_idle(void)
else
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
trace_power_end(smp_processor_id());
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
trace_power_end_rcuidle(smp_processor_id());
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
} else {
local_irq_enable();
/* loop is done by the caller */
@ -450,8 +450,8 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
static void mwait_idle(void)
{
if (!need_resched()) {
trace_power_start(POWER_CSTATE, 1, smp_processor_id());
trace_cpu_idle(1, smp_processor_id());
trace_power_start_rcuidle(POWER_CSTATE, 1, smp_processor_id());
trace_cpu_idle_rcuidle(1, smp_processor_id());
if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)&current_thread_info()->flags);
@ -461,8 +461,8 @@ static void mwait_idle(void)
__sti_mwait(0, 0);
else
local_irq_enable();
trace_power_end(smp_processor_id());
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
trace_power_end_rcuidle(smp_processor_id());
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
} else
local_irq_enable();
}
@ -474,13 +474,13 @@ static void mwait_idle(void)
*/
static void poll_idle(void)
{
trace_power_start(POWER_CSTATE, 0, smp_processor_id());
trace_cpu_idle(0, smp_processor_id());
trace_power_start_rcuidle(POWER_CSTATE, 0, smp_processor_id());
trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
while (!need_resched())
cpu_relax();
trace_power_end(smp_processor_id());
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
trace_power_end_rcuidle(smp_processor_id());
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
/*

8
arch/x86/kvm/mmu_audit.c
View File

@ -234,7 +234,7 @@ static void audit_vcpu_spte(struct kvm_vcpu *vcpu)
}
static bool mmu_audit;
static struct jump_label_key mmu_audit_key;
static struct static_key mmu_audit_key;
static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
{
@ -250,7 +250,7 @@ static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
static inline void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
{
if (static_branch((&mmu_audit_key)))
if (static_key_false((&mmu_audit_key)))
__kvm_mmu_audit(vcpu, point);
}
@ -259,7 +259,7 @@ static void mmu_audit_enable(void)
if (mmu_audit)
return;
jump_label_inc(&mmu_audit_key);
static_key_slow_inc(&mmu_audit_key);
mmu_audit = true;
}
@ -268,7 +268,7 @@ static void mmu_audit_disable(void)
if (!mmu_audit)
return;
jump_label_dec(&mmu_audit_key);
static_key_slow_dec(&mmu_audit_key);
mmu_audit = false;
}

36
arch/x86/lib/inat.c
View File

@ -29,46 +29,46 @@ insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
return inat_primary_table[opcode];
}
insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, insn_byte_t last_pfx,
int inat_get_last_prefix_id(insn_byte_t last_pfx)
{
insn_attr_t lpfx_attr;
lpfx_attr = inat_get_opcode_attribute(last_pfx);
return inat_last_prefix_id(lpfx_attr);
}
insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
insn_attr_t esc_attr)
{
const insn_attr_t *table;
insn_attr_t lpfx_attr;
int n, m = 0;
int n;
n = inat_escape_id(esc_attr);
if (last_pfx) {
lpfx_attr = inat_get_opcode_attribute(last_pfx);
m = inat_last_prefix_id(lpfx_attr);
}
table = inat_escape_tables[n][0];
if (!table)
return 0;
if (inat_has_variant(table[opcode]) && m) {
table = inat_escape_tables[n][m];
if (inat_has_variant(table[opcode]) && lpfx_id) {
table = inat_escape_tables[n][lpfx_id];
if (!table)
return 0;
}
return table[opcode];
}
insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx,
insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
insn_attr_t grp_attr)
{
const insn_attr_t *table;
insn_attr_t lpfx_attr;
int n, m = 0;
int n;
n = inat_group_id(grp_attr);
if (last_pfx) {
lpfx_attr = inat_get_opcode_attribute(last_pfx);
m = inat_last_prefix_id(lpfx_attr);
}
table = inat_group_tables[n][0];
if (!table)
return inat_group_common_attribute(grp_attr);
if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && m) {
table = inat_group_tables[n][m];
if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
table = inat_group_tables[n][lpfx_id];
if (!table)
return inat_group_common_attribute(grp_attr);
}

13
arch/x86/lib/insn.c
View File

@ -185,7 +185,8 @@ err_out:
void insn_get_opcode(struct insn *insn)
{
struct insn_field *opcode = &insn->opcode;
insn_byte_t op, pfx;
insn_byte_t op;
int pfx_id;
if (opcode->got)
return;
if (!insn->prefixes.got)
@ -212,8 +213,8 @@ void insn_get_opcode(struct insn *insn)
/* Get escaped opcode */
op = get_next(insn_byte_t, insn);
opcode->bytes[opcode->nbytes++] = op;
pfx = insn_last_prefix(insn);
insn->attr = inat_get_escape_attribute(op, pfx, insn->attr);
pfx_id = insn_last_prefix_id(insn);
insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
}
if (inat_must_vex(insn->attr))
insn->attr = 0; /* This instruction is bad */
@ -235,7 +236,7 @@ err_out:
void insn_get_modrm(struct insn *insn)
{
struct insn_field *modrm = &insn->modrm;
insn_byte_t pfx, mod;
insn_byte_t pfx_id, mod;
if (modrm->got)
return;
if (!insn->opcode.got)
@ -246,8 +247,8 @@ void insn_get_modrm(struct insn *insn)
modrm->value = mod;
modrm->nbytes = 1;
if (inat_is_group(insn->attr)) {
pfx = insn_last_prefix(insn);
insn->attr = inat_get_group_attribute(mod, pfx,
pfx_id = insn_last_prefix_id(insn);
insn->attr = inat_get_group_attribute(mod, pfx_id,
insn->attr);
if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
insn->attr = 0; /* This is bad */

8
drivers/cpuidle/cpuidle.c
View File

@ -94,13 +94,13 @@ int cpuidle_idle_call(void)
target_state = &drv->states[next_state];
trace_power_start(POWER_CSTATE, next_state, dev->cpu);
trace_cpu_idle(next_state, dev->cpu);
trace_power_start_rcuidle(POWER_CSTATE, next_state, dev->cpu);
trace_cpu_idle_rcuidle(next_state, dev->cpu);
entered_state = target_state->enter(dev, drv, next_state);
trace_power_end(dev->cpu);
trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
trace_power_end_rcuidle(dev->cpu);
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
if (entered_state >= 0) {
/* Update cpuidle counters */

9
fs/exec.c
View File

@ -63,6 +63,8 @@
#include <trace/events/task.h>
#include "internal.h"
#include <trace/events/sched.h>
int core_uses_pid;
char core_pattern[CORENAME_MAX_SIZE] = "core";
unsigned int core_pipe_limit;
@ -1402,9 +1404,10 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
*/
bprm->recursion_depth = depth;
if (retval >= 0) {
if (depth == 0)
ptrace_event(PTRACE_EVENT_EXEC,
old_pid);
if (depth == 0) {
trace_sched_process_exec(current, old_pid, bprm);
ptrace_event(PTRACE_EVENT_EXEC, old_pid);
}
put_binfmt(fmt);
allow_write_access(bprm->file);
if (bprm->file)

77
include/linux/ftrace.h
View File

@ -31,16 +31,33 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
/*
* FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
* set in the flags member.
*
* ENABLED - set/unset when ftrace_ops is registered/unregistered
* GLOBAL - set manualy by ftrace_ops user to denote the ftrace_ops
* is part of the global tracers sharing the same filter
* via set_ftrace_* debugfs files.
* DYNAMIC - set when ftrace_ops is registered to denote dynamically
* allocated ftrace_ops which need special care
* CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops
* could be controled by following calls:
* ftrace_function_local_enable
* ftrace_function_local_disable
*/
enum {
FTRACE_OPS_FL_ENABLED = 1 << 0,
FTRACE_OPS_FL_GLOBAL = 1 << 1,
FTRACE_OPS_FL_DYNAMIC = 1 << 2,
FTRACE_OPS_FL_CONTROL = 1 << 3,
};
struct ftrace_ops {
ftrace_func_t func;
struct ftrace_ops *next;
unsigned long flags;
int __percpu *disabled;
#ifdef CONFIG_DYNAMIC_FTRACE
struct ftrace_hash *notrace_hash;
struct ftrace_hash *filter_hash;
@ -97,6 +114,55 @@ int register_ftrace_function(struct ftrace_ops *ops);
int unregister_ftrace_function(struct ftrace_ops *ops);
void clear_ftrace_function(void);
/**
* ftrace_function_local_enable - enable controlled ftrace_ops on current cpu
*
* This function enables tracing on current cpu by decreasing
* the per cpu control variable.
* It must be called with preemption disabled and only on ftrace_ops
* registered with FTRACE_OPS_FL_CONTROL. If called without preemption
* disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
*/
static inline void ftrace_function_local_enable(struct ftrace_ops *ops)
{
if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
return;
(*this_cpu_ptr(ops->disabled))--;
}
/**
* ftrace_function_local_disable - enable controlled ftrace_ops on current cpu
*
* This function enables tracing on current cpu by decreasing
* the per cpu control variable.
* It must be called with preemption disabled and only on ftrace_ops
* registered with FTRACE_OPS_FL_CONTROL. If called without preemption
* disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
*/
static inline void ftrace_function_local_disable(struct ftrace_ops *ops)
{
if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
return;
(*this_cpu_ptr(ops->disabled))++;
}
/**
* ftrace_function_local_disabled - returns ftrace_ops disabled value
* on current cpu
*
* This function returns value of ftrace_ops::disabled on current cpu.
* It must be called with preemption disabled and only on ftrace_ops
* registered with FTRACE_OPS_FL_CONTROL. If called without preemption
* disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
*/
static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
{
WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL));
return *this_cpu_ptr(ops->disabled);
}
extern void ftrace_stub(unsigned long a0, unsigned long a1);
#else /* !CONFIG_FUNCTION_TRACER */
@ -178,12 +244,13 @@ struct dyn_ftrace {
};
int ftrace_force_update(void);
void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset);
void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset);
void ftrace_set_global_filter(unsigned char *buf, int len, int reset);
void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
void ftrace_free_filter(struct ftrace_ops *ops);
int register_ftrace_command(struct ftrace_func_command *cmd);
int unregister_ftrace_command(struct ftrace_func_command *cmd);
@ -314,9 +381,6 @@ extern void ftrace_enable_daemon(void);
#else
static inline int skip_trace(unsigned long ip) { return 0; }
static inline int ftrace_force_update(void) { return 0; }
static inline void ftrace_set_filter(unsigned char *buf, int len, int reset)
{
}
static inline void ftrace_disable_daemon(void) { }
static inline void ftrace_enable_daemon(void) { }
static inline void ftrace_release_mod(struct module *mod) {}
@ -340,6 +404,9 @@ static inline int ftrace_text_reserved(void *start, void *end)
*/
#define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; })
#define ftrace_set_early_filter(ops, buf, enable) do { } while (0)
#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_free_filter(ops) do { } while (0)
static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos) { return -ENODEV; }

9
include/linux/ftrace_event.h
View File

@ -146,6 +146,10 @@ enum trace_reg {
TRACE_REG_UNREGISTER,
TRACE_REG_PERF_REGISTER,
TRACE_REG_PERF_UNREGISTER,
TRACE_REG_PERF_OPEN,
TRACE_REG_PERF_CLOSE,
TRACE_REG_PERF_ADD,
TRACE_REG_PERF_DEL,
};
struct ftrace_event_call;
@ -157,7 +161,7 @@ struct ftrace_event_class {
void *perf_probe;
#endif
int (*reg)(struct ftrace_event_call *event,
enum trace_reg type);
enum trace_reg type, void *data);
int (*define_fields)(struct ftrace_event_call *);
struct list_head *(*get_fields)(struct ftrace_event_call *);
struct list_head fields;
@ -165,7 +169,7 @@ struct ftrace_event_class {
};
extern int ftrace_event_reg(struct ftrace_event_call *event,
enum trace_reg type);
enum trace_reg type, void *data);
enum {
TRACE_EVENT_FL_ENABLED_BIT,
@ -241,6 +245,7 @@ enum {
FILTER_STATIC_STRING,
FILTER_DYN_STRING,
FILTER_PTR_STRING,
FILTER_TRACE_FN,
};
#define EVENT_STORAGE_SIZE 128

7
include/linux/interrupt.h
View File

@ -20,7 +20,6 @@
#include <linux/atomic.h>
#include <asm/ptrace.h>
#include <asm/system.h>
#include <trace/events/irq.h>
/*
* These correspond to the IORESOURCE_IRQ_* defines in
@ -456,11 +455,7 @@ asmlinkage void do_softirq(void);
asmlinkage void __do_softirq(void);
extern void open_softirq(int nr, void (*action)(struct softirq_action *));
extern void softirq_init(void);
static inline void __raise_softirq_irqoff(unsigned int nr)
{
trace_softirq_raise(nr);
or_softirq_pending(1UL << nr);
}
extern void __raise_softirq_irqoff(unsigned int nr);
extern void raise_softirq_irqoff(unsigned int nr);
extern void raise_softirq(unsigned int nr);

162
include/linux/jump_label.h
View File

@ -1,22 +1,69 @@
#ifndef _LINUX_JUMP_LABEL_H
#define _LINUX_JUMP_LABEL_H
/*
* Jump label support
*
* Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com>
* Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
*
* Jump labels provide an interface to generate dynamic branches using
* self-modifying code. Assuming toolchain and architecture support the result
* of a "if (static_key_false(&key))" statement is a unconditional branch (which
* defaults to false - and the true block is placed out of line).
*
* However at runtime we can change the branch target using
* static_key_slow_{inc,dec}(). These function as a 'reference' count on the key
* object and for as long as there are references all branches referring to
* that particular key will point to the (out of line) true block.
*
* Since this relies on modifying code the static_key_slow_{inc,dec}() functions
* must be considered absolute slow paths (machine wide synchronization etc.).
* OTOH, since the affected branches are unconditional their runtime overhead
* will be absolutely minimal, esp. in the default (off) case where the total
* effect is a single NOP of appropriate size. The on case will patch in a jump
* to the out-of-line block.
*
* When the control is directly exposed to userspace it is prudent to delay the
* decrement to avoid high frequency code modifications which can (and do)
* cause significant performance degradation. Struct static_key_deferred and
* static_key_slow_dec_deferred() provide for this.
*
* Lacking toolchain and or architecture support, it falls back to a simple
* conditional branch.
*
* struct static_key my_key = STATIC_KEY_INIT_TRUE;
*
* if (static_key_true(&my_key)) {
* }
*
* will result in the true case being in-line and starts the key with a single
* reference. Mixing static_key_true() and static_key_false() on the same key is not
* allowed.
*
* Not initializing the key (static data is initialized to 0s anyway) is the
* same as using STATIC_KEY_INIT_FALSE and static_key_false() is
* equivalent with static_branch().
*
*/
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/workqueue.h>
#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
struct jump_label_key {
struct static_key {
atomic_t enabled;
/* Set lsb bit to 1 if branch is default true, 0 ot */
struct jump_entry *entries;
#ifdef CONFIG_MODULES
struct jump_label_mod *next;
struct static_key_mod *next;
#endif
};
struct jump_label_key_deferred {
struct jump_label_key key;
struct static_key_deferred {
struct static_key key;
unsigned long timeout;
struct delayed_work work;
};
@ -34,13 +81,34 @@ struct module;
#ifdef HAVE_JUMP_LABEL
#ifdef CONFIG_MODULES
#define JUMP_LABEL_INIT {ATOMIC_INIT(0), NULL, NULL}
#else
#define JUMP_LABEL_INIT {ATOMIC_INIT(0), NULL}
#endif
#define JUMP_LABEL_TRUE_BRANCH 1UL
static __always_inline bool static_branch(struct jump_label_key *key)
static
inline struct jump_entry *jump_label_get_entries(struct static_key *key)
{
return (struct jump_entry *)((unsigned long)key->entries
& ~JUMP_LABEL_TRUE_BRANCH);
}
static inline bool jump_label_get_branch_default(struct static_key *key)
{
if ((unsigned long)key->entries & JUMP_LABEL_TRUE_BRANCH)
return true;
return false;
}
static __always_inline bool static_key_false(struct static_key *key)
{
return arch_static_branch(key);
}
static __always_inline bool static_key_true(struct static_key *key)
{
return !static_key_false(key);
}
/* Deprecated. Please use 'static_key_false() instead. */
static __always_inline bool static_branch(struct static_key *key)
{
return arch_static_branch(key);
}
@ -56,21 +124,23 @@ extern void arch_jump_label_transform(struct jump_entry *entry,
extern void arch_jump_label_transform_static(struct jump_entry *entry,
enum jump_label_type type);
extern int jump_label_text_reserved(void *start, void *end);
extern void jump_label_inc(struct jump_label_key *key);
extern void jump_label_dec(struct jump_label_key *key);
extern void jump_label_dec_deferred(struct jump_label_key_deferred *key);
extern bool jump_label_enabled(struct jump_label_key *key);
extern void static_key_slow_inc(struct static_key *key);
extern void static_key_slow_dec(struct static_key *key);
extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
extern void jump_label_apply_nops(struct module *mod);
extern void jump_label_rate_limit(struct jump_label_key_deferred *key,
unsigned long rl);
extern void
jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
#define STATIC_KEY_INIT_TRUE ((struct static_key) \
{ .enabled = ATOMIC_INIT(1), .entries = (void *)1 })
#define STATIC_KEY_INIT_FALSE ((struct static_key) \
{ .enabled = ATOMIC_INIT(0), .entries = (void *)0 })
#else /* !HAVE_JUMP_LABEL */
#include <linux/atomic.h>
#define JUMP_LABEL_INIT {ATOMIC_INIT(0)}
struct jump_label_key {
struct static_key {
atomic_t enabled;
};
@ -78,30 +148,45 @@ static __always_inline void jump_label_init(void)
{
}
struct jump_label_key_deferred {
struct jump_label_key key;
struct static_key_deferred {
struct static_key key;
};
static __always_inline bool static_branch(struct jump_label_key *key)
static __always_inline bool static_key_false(struct static_key *key)
{
if (unlikely(atomic_read(&key->enabled)))
if (unlikely(atomic_read(&key->enabled)) > 0)
return true;
return false;
}
static inline void jump_label_inc(struct jump_label_key *key)
static __always_inline bool static_key_true(struct static_key *key)
{
if (likely(atomic_read(&key->enabled)) > 0)
return true;
return false;
}
/* Deprecated. Please use 'static_key_false() instead. */
static __always_inline bool static_branch(struct static_key *key)
{
if (unlikely(atomic_read(&key->enabled)) > 0)
return true;
return false;
}
static inline void static_key_slow_inc(struct static_key *key)
{
atomic_inc(&key->enabled);
}
static inline void jump_label_dec(struct jump_label_key *key)
static inline void static_key_slow_dec(struct static_key *key)
{
atomic_dec(&key->enabled);
}
static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key)
static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
{
jump_label_dec(&key->key);
static_key_slow_dec(&key->key);
}
static inline int jump_label_text_reserved(void *start, void *end)
@ -112,23 +197,30 @@ static inline int jump_label_text_reserved(void *start, void *end)
static inline void jump_label_lock(void) {}
static inline void jump_label_unlock(void) {}
static inline bool jump_label_enabled(struct jump_label_key *key)
{
return !!atomic_read(&key->enabled);
}
static inline int jump_label_apply_nops(struct module *mod)
{
return 0;
}
static inline void jump_label_rate_limit(struct jump_label_key_deferred *key,
static inline void
jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
}
#define STATIC_KEY_INIT_TRUE ((struct static_key) \
{ .enabled = ATOMIC_INIT(1) })
#define STATIC_KEY_INIT_FALSE ((struct static_key) \
{ .enabled = ATOMIC_INIT(0) })
#endif /* HAVE_JUMP_LABEL */
#define jump_label_key_enabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(1), })
#define jump_label_key_disabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(0), })
#define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
#define jump_label_enabled static_key_enabled
static inline bool static_key_enabled(struct static_key *key)
{
return (atomic_read(&key->enabled) > 0);
}
#endif /* _LINUX_JUMP_LABEL_H */

4
include/linux/netdevice.h
View File

@ -214,8 +214,8 @@ enum {
#include <linux/skbuff.h>
#ifdef CONFIG_RPS
#include <linux/jump_label.h>
extern struct jump_label_key rps_needed;
#include <linux/static_key.h>
extern struct static_key rps_needed;
#endif
struct neighbour;

6
include/linux/netfilter.h
View File

@ -163,13 +163,13 @@ extern struct ctl_path nf_net_ipv4_netfilter_sysctl_path[];
extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
#if defined(CONFIG_JUMP_LABEL)
#include <linux/jump_label.h>
extern struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
#include <linux/static_key.h>
extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
{
if (__builtin_constant_p(pf) &&
__builtin_constant_p(hook))
return static_branch(&nf_hooks_needed[pf][hook]);
return static_key_false(&nf_hooks_needed[pf][hook]);
return !list_empty(&nf_hooks[pf][hook]);
}

108
include/linux/perf_event.h
View File

@ -129,10 +129,39 @@ enum perf_event_sample_format {
PERF_SAMPLE_PERIOD = 1U << 8,
PERF_SAMPLE_STREAM_ID = 1U << 9,
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */
PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */
};
/*
* values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
*
* If the user does not pass priv level information via branch_sample_type,
* the kernel uses the event's priv level. Branch and event priv levels do
* not have to match. Branch priv level is checked for permissions.
*
* The branch types can be combined, however BRANCH_ANY covers all types
* of branches and therefore it supersedes all the other types.
*/
enum perf_branch_sample_type {
PERF_SAMPLE_BRANCH_USER = 1U << 0, /* user branches */
PERF_SAMPLE_BRANCH_KERNEL = 1U << 1, /* kernel branches */
PERF_SAMPLE_BRANCH_HV = 1U << 2, /* hypervisor branches */
PERF_SAMPLE_BRANCH_ANY = 1U << 3, /* any branch types */
PERF_SAMPLE_BRANCH_ANY_CALL = 1U << 4, /* any call branch */
PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << 5, /* any return branch */
PERF_SAMPLE_BRANCH_IND_CALL = 1U << 6, /* indirect calls */
PERF_SAMPLE_BRANCH_MAX = 1U << 7, /* non-ABI */
};
#define PERF_SAMPLE_BRANCH_PLM_ALL \
(PERF_SAMPLE_BRANCH_USER|\
PERF_SAMPLE_BRANCH_KERNEL|\
PERF_SAMPLE_BRANCH_HV)
/*
* The format of the data returned by read() on a perf event fd,
* as specified by attr.read_format:
@ -163,6 +192,8 @@ enum perf_event_read_format {
};
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
/*
* Hardware event_id to monitor via a performance monitoring event:
@ -240,6 +271,7 @@ struct perf_event_attr {
__u64 bp_len;
__u64 config2; /* extension of config1 */
};
__u64 branch_sample_type; /* enum branch_sample_type */
};
/*
@ -291,12 +323,14 @@ struct perf_event_mmap_page {
__s64 offset; /* add to hardware event value */
__u64 time_enabled; /* time event active */
__u64 time_running; /* time event on cpu */
__u32 time_mult, time_shift;
__u64 time_offset;
/*
* Hole for extension of the self monitor capabilities
*/
__u64 __reserved[123]; /* align to 1k */
__u64 __reserved[121]; /* align to 1k */
/*
* Control data for the mmap() data buffer.
@ -456,6 +490,8 @@ enum perf_event_type {
*
* { u32 size;
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
* };
*/
PERF_RECORD_SAMPLE = 9,
@ -512,7 +548,7 @@ struct perf_guest_info_callbacks {
#include <linux/ftrace.h>
#include <linux/cpu.h>
#include <linux/irq_work.h>
#include <linux/jump_label.h>
#include <linux/static_key.h>
#include <linux/atomic.h>
#include <asm/local.h>
@ -528,12 +564,34 @@ struct perf_raw_record {
void *data;
};
/*
* single taken branch record layout:
*
* from: source instruction (may not always be a branch insn)
* to: branch target
* mispred: branch target was mispredicted
* predicted: branch target was predicted
*
* support for mispred, predicted is optional. In case it
* is not supported mispred = predicted = 0.
*/
struct perf_branch_entry {
__u64 from;
__u64 to;
__u64 flags;
__u64 from;
__u64 to;
__u64 mispred:1, /* target mispredicted */
predicted:1,/* target predicted */
reserved:62;
};
/*
* branch stack layout:
* nr: number of taken branches stored in entries[]
*
* Note that nr can vary from sample to sample
* branches (to, from) are stored from most recent
* to least recent, i.e., entries[0] contains the most
* recent branch.
*/
struct perf_branch_stack {
__u64 nr;
struct perf_branch_entry entries[0];
@ -564,7 +622,9 @@ struct hw_perf_event {
unsigned long event_base;
int idx;
int last_cpu;
struct hw_perf_event_extra extra_reg;
struct hw_perf_event_extra branch_reg;
};
struct { /* software */
struct hrtimer hrtimer;
@ -616,6 +676,7 @@ struct pmu {
struct list_head entry;
struct device *dev;
const struct attribute_group **attr_groups;
char *name;
int type;
@ -681,6 +742,17 @@ struct pmu {
* for each successful ->add() during the transaction.
*/
void (*cancel_txn) (struct pmu *pmu); /* optional */
/*
* Will return the value for perf_event_mmap_page::index for this event,
* if no implementation is provided it will default to: event->hw.idx + 1.
*/
int (*event_idx) (struct perf_event *event); /*optional */
/*
* flush branch stack on context-switches (needed in cpu-wide mode)
*/
void (*flush_branch_stack) (void);
};
/**
@ -850,6 +922,9 @@ struct perf_event {
#ifdef CONFIG_EVENT_TRACING
struct ftrace_event_call *tp_event;
struct event_filter *filter;
#ifdef CONFIG_FUNCTION_TRACER
struct ftrace_ops ftrace_ops;
#endif
#endif
#ifdef CONFIG_CGROUP_PERF
@ -911,7 +986,8 @@ struct perf_event_context {
u64 parent_gen;
u64 generation;
int pin_count;
int nr_cgroups; /* cgroup events present */
int nr_cgroups; /* cgroup evts */
int nr_branch_stack; /* branch_stack evt */
struct rcu_head rcu_head;
};
@ -976,6 +1052,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
struct perf_sample_data {
u64 type;
@ -995,12 +1072,14 @@ struct perf_sample_data {
u64 period;
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
};
static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
{
data->addr = addr;
data->raw = NULL;
data->br_stack = NULL;
}
extern void perf_output_sample(struct perf_output_handle *handle,
@ -1029,7 +1108,7 @@ static inline int is_software_event(struct perf_event *event)
return event->pmu->task_ctx_nr == perf_sw_context;
}
extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
@ -1057,7 +1136,7 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
{
struct pt_regs hot_regs;
if (static_branch(&perf_swevent_enabled[event_id])) {
if (static_key_false(&perf_swevent_enabled[event_id])) {
if (!regs) {
perf_fetch_caller_regs(&hot_regs);
regs = &hot_regs;
@ -1066,12 +1145,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
}
}
extern struct jump_label_key_deferred perf_sched_events;
extern struct static_key_deferred perf_sched_events;
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
if (static_branch(&perf_sched_events.key))
if (static_key_false(&perf_sched_events.key))
__perf_event_task_sched_in(prev, task);
}
@ -1080,7 +1159,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
{
perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
if (static_branch(&perf_sched_events.key))
if (static_key_false(&perf_sched_events.key))
__perf_event_task_sched_out(prev, next);
}
@ -1139,6 +1218,11 @@ extern void perf_bp_event(struct perf_event *event, void *data);
# define perf_instruction_pointer(regs) instruction_pointer(regs)
#endif
static inline bool has_branch_stack(struct perf_event *event)
{
return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
}
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);

1
include/linux/static_key.h Normal file
View File

@ -0,0 +1 @@
#include <linux/jump_label.h>

28
include/linux/tracepoint.h
View File

@ -17,7 +17,7 @@
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/jump_label.h>
#include <linux/static_key.h>
struct module;
struct tracepoint;
@ -29,7 +29,7 @@ struct tracepoint_func {
struct tracepoint {
const char *name; /* Tracepoint name */
struct jump_label_key key;
struct static_key key;
void (*regfunc)(void);
void (*unregfunc)(void);
struct tracepoint_func __rcu *funcs;
@ -114,7 +114,7 @@ static inline void tracepoint_synchronize_unregister(void)
* as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
* "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
*/
#define __DO_TRACE(tp, proto, args, cond) \
#define __DO_TRACE(tp, proto, args, cond, prercu, postrcu) \
do { \
struct tracepoint_func *it_func_ptr; \
void *it_func; \
@ -122,6 +122,7 @@ static inline void tracepoint_synchronize_unregister(void)
\
if (!(cond)) \
return; \
prercu; \
rcu_read_lock_sched_notrace(); \
it_func_ptr = rcu_dereference_sched((tp)->funcs); \
if (it_func_ptr) { \
@ -132,6 +133,7 @@ static inline void tracepoint_synchronize_unregister(void)
} while ((++it_func_ptr)->func); \
} \
rcu_read_unlock_sched_notrace(); \
postrcu; \
} while (0)
/*
@ -139,15 +141,25 @@ static inline void tracepoint_synchronize_unregister(void)
* not add unwanted padding between the beginning of the section and the
* structure. Force alignment to the same alignment as the section start.
*/
#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
extern struct tracepoint __tracepoint_##name; \
static inline void trace_##name(proto) \
{ \
if (static_key_false(&__tracepoint_##name.key)) \
__DO_TRACE(&__tracepoint_##name, \
TP_PROTO(data_proto), \
TP_ARGS(data_args), \
TP_CONDITION(cond),,); \
} \
static inline void trace_##name##_rcuidle(proto) \
{ \
if (static_branch(&__tracepoint_##name.key)) \
__DO_TRACE(&__tracepoint_##name, \
TP_PROTO(data_proto), \
TP_ARGS(data_args), \
TP_CONDITION(cond)); \
TP_CONDITION(cond), \
rcu_idle_exit(), \
rcu_idle_enter()); \
} \
static inline int \
register_trace_##name(void (*probe)(data_proto), void *data) \
@ -176,7 +188,7 @@ static inline void tracepoint_synchronize_unregister(void)
__attribute__((section("__tracepoints_strings"))) = #name; \
struct tracepoint __tracepoint_##name \
__attribute__((section("__tracepoints"))) = \
{ __tpstrtab_##name, JUMP_LABEL_INIT, reg, unreg, NULL };\
{ __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
static struct tracepoint * const __tracepoint_ptr_##name __used \
__attribute__((section("__tracepoints_ptrs"))) = \
&__tracepoint_##name;
@ -190,9 +202,11 @@ static inline void tracepoint_synchronize_unregister(void)
EXPORT_SYMBOL(__tracepoint_##name)
#else /* !CONFIG_TRACEPOINTS */
#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
static inline void trace_##name(proto) \
{ } \
static inline void trace_##name##_rcuidle(proto) \
{ } \
static inline int \
register_trace_##name(void (*probe)(data_proto), \
void *data) \

6
include/net/sock.h
View File

@ -55,7 +55,7 @@
#include <linux/uaccess.h>
#include <linux/memcontrol.h>
#include <linux/res_counter.h>
#include <linux/jump_label.h>
#include <linux/static_key.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
@ -924,13 +924,13 @@ inline void sk_refcnt_debug_release(const struct sock *sk)
#endif /* SOCK_REFCNT_DEBUG */
#if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET)
extern struct jump_label_key memcg_socket_limit_enabled;
extern struct static_key memcg_socket_limit_enabled;
static inline struct cg_proto *parent_cg_proto(struct proto *proto,
struct cg_proto *cg_proto)
{
return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
}
#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled)
#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled)
#else
#define mem_cgroup_sockets_enabled 0
static inline struct cg_proto *parent_cg_proto(struct proto *proto,

2
include/trace/events/power.h
View File

@ -151,6 +151,8 @@ enum {
events get removed */
static inline void trace_power_start(u64 type, u64 state, u64 cpuid) {};
static inline void trace_power_end(u64 cpuid) {};
static inline void trace_power_start_rcuidle(u64 type, u64 state, u64 cpuid) {};
static inline void trace_power_end_rcuidle(u64 cpuid) {};
static inline void trace_power_frequency(u64 type, u64 state, u64 cpuid) {};
#endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */

41
include/trace/events/printk.h Normal file
View File

@ -0,0 +1,41 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM printk
#if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_PRINTK_H
#include <linux/tracepoint.h>
TRACE_EVENT_CONDITION(console,
TP_PROTO(const char *log_buf, unsigned start, unsigned end,
unsigned log_buf_len),
TP_ARGS(log_buf, start, end, log_buf_len),
TP_CONDITION(start != end),
TP_STRUCT__entry(
__dynamic_array(char, msg, end - start + 1)
),
TP_fast_assign(
if ((start & (log_buf_len - 1)) > (end & (log_buf_len - 1))) {
memcpy(__get_dynamic_array(msg),
log_buf + (start & (log_buf_len - 1)),
log_buf_len - (start & (log_buf_len - 1)));
memcpy((char *)__get_dynamic_array(msg) +
log_buf_len - (start & (log_buf_len - 1)),
log_buf, end & (log_buf_len - 1));
} else
memcpy(__get_dynamic_array(msg),
log_buf + (start & (log_buf_len - 1)),
end - start);
((char *)__get_dynamic_array(msg))[end - start] = 0;
),
TP_printk("%s", __get_str(msg))
);
#endif /* _TRACE_PRINTK_H */
/* This part must be outside protection */
#include <trace/define_trace.h>

27
include/trace/events/sched.h
View File

@ -6,6 +6,7 @@
#include <linux/sched.h>
#include <linux/tracepoint.h>
#include <linux/binfmts.h>
/*
* Tracepoint for calling kthread_stop, performed to end a kthread:
@ -275,6 +276,32 @@ TRACE_EVENT(sched_process_fork,
__entry->child_comm, __entry->child_pid)
);
/*
* Tracepoint for exec:
*/
TRACE_EVENT(sched_process_exec,
TP_PROTO(struct task_struct *p, pid_t old_pid,
struct linux_binprm *bprm),
TP_ARGS(p, old_pid, bprm),
TP_STRUCT__entry(
__string( filename, bprm->filename )
__field( pid_t, pid )
__field( pid_t, old_pid )
),
TP_fast_assign(
__assign_str(filename, bprm->filename);
__entry->pid = p->pid;
__entry->old_pid = p->pid;
),
TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename),
__entry->pid, __entry->old_pid)
);
/*
* XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
* adding sched_stat support to SCHED_FIFO/RR would be welcome.

85
include/trace/events/signal.h
View File

@ -23,11 +23,23 @@
} \
} while (0)
#ifndef TRACE_HEADER_MULTI_READ
enum {
TRACE_SIGNAL_DELIVERED,
TRACE_SIGNAL_IGNORED,
TRACE_SIGNAL_ALREADY_PENDING,
TRACE_SIGNAL_OVERFLOW_FAIL,
TRACE_SIGNAL_LOSE_INFO,
};
#endif
/**
* signal_generate - called when a signal is generated
* @sig: signal number
* @info: pointer to struct siginfo
* @task: pointer to struct task_struct
* @group: shared or private
* @result: TRACE_SIGNAL_*
*
* Current process sends a 'sig' signal to 'task' process with
* 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV,
@ -37,9 +49,10 @@
*/
TRACE_EVENT(signal_generate,
TP_PROTO(int sig, struct siginfo *info, struct task_struct *task),
TP_PROTO(int sig, struct siginfo *info, struct task_struct *task,
int group, int result),
TP_ARGS(sig, info, task),
TP_ARGS(sig, info, task, group, result),
TP_STRUCT__entry(
__field( int, sig )
@ -47,6 +60,8 @@ TRACE_EVENT(signal_generate,
__field( int, code )
__array( char, comm, TASK_COMM_LEN )
__field( pid_t, pid )
__field( int, group )
__field( int, result )
),
TP_fast_assign(
@ -54,11 +69,14 @@ TRACE_EVENT(signal_generate,
TP_STORE_SIGINFO(__entry, info);
memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
__entry->pid = task->pid;
__entry->group = group;
__entry->result = result;
),
TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d",
TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d grp=%d res=%d",
__entry->sig, __entry->errno, __entry->code,
__entry->comm, __entry->pid)
__entry->comm, __entry->pid, __entry->group,
__entry->result)
);
/**
@ -101,65 +119,6 @@ TRACE_EVENT(signal_deliver,
__entry->sa_handler, __entry->sa_flags)
);
DECLARE_EVENT_CLASS(signal_queue_overflow,
TP_PROTO(int sig, int group, struct siginfo *info),
TP_ARGS(sig, group, info),
TP_STRUCT__entry(
__field( int, sig )
__field( int, group )
__field( int, errno )
__field( int, code )
),
TP_fast_assign(
__entry->sig = sig;
__entry->group = group;
TP_STORE_SIGINFO(__entry, info);
),
TP_printk("sig=%d group=%d errno=%d code=%d",
__entry->sig, __entry->group, __entry->errno, __entry->code)
);
/**
* signal_overflow_fail - called when signal queue is overflow
* @sig: signal number
* @group: signal to process group or not (bool)
* @info: pointer to struct siginfo
*
* Kernel fails to generate 'sig' signal with 'info' siginfo, because
* siginfo queue is overflow, and the signal is dropped.
* 'group' is not 0 if the signal will be sent to a process group.
* 'sig' is always one of RT signals.
*/
DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail,
TP_PROTO(int sig, int group, struct siginfo *info),
TP_ARGS(sig, group, info)
);
/**
* signal_lose_info - called when siginfo is lost
* @sig: signal number
* @group: signal to process group or not (bool)
* @info: pointer to struct siginfo
*
* Kernel generates 'sig' signal but loses 'info' siginfo, because siginfo
* queue is overflow.
* 'group' is not 0 if the signal will be sent to a process group.
* 'sig' is always one of non-RT signals.
*/
DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
TP_PROTO(int sig, int group, struct siginfo *info),
TP_ARGS(sig, group, info)
);
#endif /* _TRACE_SIGNAL_H */
/* This part must be outside protection */

246
kernel/events/core.c
View File

@ -118,6 +118,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
PERF_FLAG_FD_OUTPUT |\
PERF_FLAG_PID_CGROUP)
/*
* branch priv levels that need permission checks
*/
#define PERF_SAMPLE_BRANCH_PERM_PLM \
(PERF_SAMPLE_BRANCH_KERNEL |\
PERF_SAMPLE_BRANCH_HV)
enum event_type_t {
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
@ -128,8 +135,9 @@ enum event_type_t {
* perf_sched_events : >0 events exist
* perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
*/
struct jump_label_key_deferred perf_sched_events __read_mostly;
struct static_key_deferred perf_sched_events __read_mostly;
static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
@ -881,6 +889,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
if (is_cgroup_event(event))
ctx->nr_cgroups++;
if (has_branch_stack(event))
ctx->nr_branch_stack++;
list_add_rcu(&event->event_entry, &ctx->event_list);
if (!ctx->nr_events)
perf_pmu_rotate_start(ctx->pmu);
@ -1020,6 +1031,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
cpuctx->cgrp = NULL;
}
if (has_branch_stack(event))
ctx->nr_branch_stack--;
ctx->nr_events--;
if (event->attr.inherit_stat)
ctx->nr_stat--;
@ -2194,6 +2208,66 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
perf_pmu_rotate_start(ctx->pmu);
}
/*
* When sampling the branck stack in system-wide, it may be necessary
* to flush the stack on context switch. This happens when the branch
* stack does not tag its entries with the pid of the current task.
* Otherwise it becomes impossible to associate a branch entry with a
* task. This ambiguity is more likely to appear when the branch stack
* supports priv level filtering and the user sets it to monitor only
* at the user level (which could be a useful measurement in system-wide
* mode). In that case, the risk is high of having a branch stack with
* branch from multiple tasks. Flushing may mean dropping the existing
* entries or stashing them somewhere in the PMU specific code layer.
*
* This function provides the context switch callback to the lower code
* layer. It is invoked ONLY when there is at least one system-wide context
* with at least one active event using taken branch sampling.
*/
static void perf_branch_stack_sched_in(struct task_struct *prev,
struct task_struct *task)
{
struct perf_cpu_context *cpuctx;
struct pmu *pmu;
unsigned long flags;
/* no need to flush branch stack if not changing task */
if (prev == task)
return;
local_irq_save(flags);
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
/*
* check if the context has at least one
* event using PERF_SAMPLE_BRANCH_STACK
*/
if (cpuctx->ctx.nr_branch_stack > 0
&& pmu->flush_branch_stack) {
pmu = cpuctx->ctx.pmu;
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(pmu);
pmu->flush_branch_stack();
perf_pmu_enable(pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
}
rcu_read_unlock();
local_irq_restore(flags);
}
/*
* Called from scheduler to add the events of the current task
* with interrupts disabled.
@ -2225,6 +2299,10 @@ void __perf_event_task_sched_in(struct task_struct *prev,
*/
if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
perf_cgroup_sched_in(prev, task);
/* check for system-wide branch_stack events */
if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
perf_branch_stack_sched_in(prev, task);
}
static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@ -2778,7 +2856,7 @@ static void free_event(struct perf_event *event)
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
jump_label_dec_deferred(&perf_sched_events);
static_key_slow_dec_deferred(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
@ -2789,7 +2867,15 @@ static void free_event(struct perf_event *event)
put_callchain_buffers();
if (is_cgroup_event(event)) {
atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
jump_label_dec_deferred(&perf_sched_events);
static_key_slow_dec_deferred(&perf_sched_events);
}
if (has_branch_stack(event)) {
static_key_slow_dec_deferred(&perf_sched_events);
/* is system-wide event */
if (!(event->attach_state & PERF_ATTACH_TASK))
atomic_dec(&per_cpu(perf_branch_stack_events,
event->cpu));
}
}
@ -3238,10 +3324,6 @@ int perf_event_task_disable(void)
return 0;
}
#ifndef PERF_EVENT_INDEX_OFFSET
# define PERF_EVENT_INDEX_OFFSET 0
#endif
static int perf_event_index(struct perf_event *event)
{
if (event->hw.state & PERF_HES_STOPPED)
@ -3250,21 +3332,26 @@ static int perf_event_index(struct perf_event *event)
if (event->state != PERF_EVENT_STATE_ACTIVE)
return 0;
return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET;
return event->pmu->event_idx(event);
}
static void calc_timer_values(struct perf_event *event,
u64 *now,
u64 *enabled,
u64 *running)
{
u64 now, ctx_time;
u64 ctx_time;
now = perf_clock();
ctx_time = event->shadow_ctx_time + now;
*now = perf_clock();
ctx_time = event->shadow_ctx_time + *now;
*enabled = ctx_time - event->tstamp_enabled;
*running = ctx_time - event->tstamp_running;
}
void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
{
}
/*
* Callers need to ensure there can be no nesting of this function, otherwise
* the seqlock logic goes bad. We can not serialize this because the arch
@ -3274,7 +3361,7 @@ void perf_event_update_userpage(struct perf_event *event)
{
struct perf_event_mmap_page *userpg;
struct ring_buffer *rb;
u64 enabled, running;
u64 enabled, running, now;
rcu_read_lock();
/*
@ -3286,7 +3373,7 @@ void perf_event_update_userpage(struct perf_event *event)
* because of locking issue as we can be called in
* NMI context
*/
calc_timer_values(event, &enabled, &running);
calc_timer_values(event, &now, &enabled, &running);
rb = rcu_dereference(event->rb);
if (!rb)
goto unlock;
@ -3302,7 +3389,7 @@ void perf_event_update_userpage(struct perf_event *event)
barrier();
userpg->index = perf_event_index(event);
userpg->offset = perf_event_count(event);
if (event->state == PERF_EVENT_STATE_ACTIVE)
if (userpg->index)
userpg->offset -= local64_read(&event->hw.prev_count);
userpg->time_enabled = enabled +
@ -3311,6 +3398,8 @@ void perf_event_update_userpage(struct perf_event *event)
userpg->time_running = running +
atomic64_read(&event->child_total_time_running);
perf_update_user_clock(userpg, now);
barrier();
++userpg->lock;
preempt_enable();
@ -3568,6 +3657,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
event->mmap_user = get_current_user();
vma->vm_mm->pinned_vm += event->mmap_locked;
perf_event_update_userpage(event);
unlock:
if (!ret)
atomic_inc(&event->mmap_count);
@ -3799,7 +3890,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
static void perf_output_read(struct perf_output_handle *handle,
struct perf_event *event)
{
u64 enabled = 0, running = 0;
u64 enabled = 0, running = 0, now;
u64 read_format = event->attr.read_format;
/*
@ -3812,7 +3903,7 @@ static void perf_output_read(struct perf_output_handle *handle,
* NMI context
*/
if (read_format & PERF_FORMAT_TOTAL_TIMES)
calc_timer_values(event, &enabled, &running);
calc_timer_values(event, &now, &enabled, &running);
if (event->attr.read_format & PERF_FORMAT_GROUP)
perf_output_read_group(handle, event, enabled, running);
@ -3902,6 +3993,24 @@ void perf_output_sample(struct perf_output_handle *handle,
}
}
}
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
if (data->br_stack) {
size_t size;
size = data->br_stack->nr
* sizeof(struct perf_branch_entry);
perf_output_put(handle, data->br_stack->nr);
perf_output_copy(handle, data->br_stack->entries, size);
} else {
/*
* we always store at least the value of nr
*/
u64 nr = 0;
perf_output_put(handle, nr);
}
}
}
void perf_prepare_sample(struct perf_event_header *header,
@ -3944,6 +4053,15 @@ void perf_prepare_sample(struct perf_event_header *header,
WARN_ON_ONCE(size & (sizeof(u64)-1));
header->size += size;
}
if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
int size = sizeof(u64); /* nr */
if (data->br_stack) {
size += data->br_stack->nr
* sizeof(struct perf_branch_entry);
}
header->size += size;
}
}
static void perf_event_output(struct perf_event *event,
@ -4986,7 +5104,7 @@ fail:
return err;
}
struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
static void sw_perf_event_destroy(struct perf_event *event)
{
@ -4994,7 +5112,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
WARN_ON(event->parent);
jump_label_dec(&perf_swevent_enabled[event_id]);
static_key_slow_dec(&perf_swevent_enabled[event_id]);
swevent_hlist_put(event);
}
@ -5005,6 +5123,12 @@ static int perf_swevent_init(struct perf_event *event)
if (event->attr.type != PERF_TYPE_SOFTWARE)
return -ENOENT;
/*
* no branch sampling for software events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
switch (event_id) {
case PERF_COUNT_SW_CPU_CLOCK:
case PERF_COUNT_SW_TASK_CLOCK:
@ -5024,13 +5148,18 @@ static int perf_swevent_init(struct perf_event *event)
if (err)
return err;
jump_label_inc(&perf_swevent_enabled[event_id]);
static_key_slow_inc(&perf_swevent_enabled[event_id]);
event->destroy = sw_perf_event_destroy;
}
return 0;
}
static int perf_swevent_event_idx(struct perf_event *event)
{
return 0;
}
static struct pmu perf_swevent = {
.task_ctx_nr = perf_sw_context,
@ -5040,6 +5169,8 @@ static struct pmu perf_swevent = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
.event_idx = perf_swevent_event_idx,
};
#ifdef CONFIG_EVENT_TRACING
@ -5108,6 +5239,12 @@ static int perf_tp_event_init(struct perf_event *event)
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -ENOENT;
/*
* no branch sampling for tracepoint events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
err = perf_trace_init(event);
if (err)
return err;
@ -5126,6 +5263,8 @@ static struct pmu perf_tracepoint = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
.event_idx = perf_swevent_event_idx,
};
static inline void perf_tp_register(void)
@ -5331,6 +5470,12 @@ static int cpu_clock_event_init(struct perf_event *event)
if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
return -ENOENT;
/*
* no branch sampling for software events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
perf_swevent_init_hrtimer(event);
return 0;
@ -5345,6 +5490,8 @@ static struct pmu perf_cpu_clock = {
.start = cpu_clock_event_start,
.stop = cpu_clock_event_stop,
.read = cpu_clock_event_read,
.event_idx = perf_swevent_event_idx,
};
/*
@ -5403,6 +5550,12 @@ static int task_clock_event_init(struct perf_event *event)
if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
return -ENOENT;
/*
* no branch sampling for software events
*/
if (has_branch_stack(event))
return -EOPNOTSUPP;
perf_swevent_init_hrtimer(event);
return 0;
@ -5417,6 +5570,8 @@ static struct pmu perf_task_clock = {
.start = task_clock_event_start,
.stop = task_clock_event_stop,
.read = task_clock_event_read,
.event_idx = perf_swevent_event_idx,
};
static void perf_pmu_nop_void(struct pmu *pmu)
@ -5444,6 +5599,11 @@ static void perf_pmu_cancel_txn(struct pmu *pmu)
perf_pmu_enable(pmu);
}
static int perf_event_idx_default(struct perf_event *event)
{
return event->hw.idx + 1;
}
/*
* Ensures all contexts with the same task_ctx_nr have the same
* pmu_cpu_context too.
@ -5530,6 +5690,7 @@ static int pmu_dev_alloc(struct pmu *pmu)
if (!pmu->dev)
goto out;
pmu->dev->groups = pmu->attr_groups;
device_initialize(pmu->dev);
ret = dev_set_name(pmu->dev, "%s", pmu->name);
if (ret)
@ -5633,6 +5794,9 @@ got_cpu_context:
pmu->pmu_disable = perf_pmu_nop_void;
}
if (!pmu->event_idx)
pmu->event_idx = perf_event_idx_default;
list_add_rcu(&pmu->entry, &pmus);
ret = 0;
unlock:
@ -5825,7 +5989,7 @@ done:
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
jump_label_inc(&perf_sched_events.key);
static_key_slow_inc(&perf_sched_events.key);
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
@ -5839,6 +6003,12 @@ done:
return ERR_PTR(err);
}
}
if (has_branch_stack(event)) {
static_key_slow_inc(&perf_sched_events.key);
if (!(event->attach_state & PERF_ATTACH_TASK))
atomic_inc(&per_cpu(perf_branch_stack_events,
event->cpu));
}
}
return event;
@ -5908,6 +6078,40 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
if (attr->read_format & ~(PERF_FORMAT_MAX-1))
return -EINVAL;
if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
u64 mask = attr->branch_sample_type;
/* only using defined bits */
if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
return -EINVAL;
/* at least one branch bit must be set */
if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
return -EINVAL;
/* kernel level capture: check permissions */
if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
&& perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
return -EACCES;
/* propagate priv level, when not set for branch */
if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {
/* exclude_kernel checked on syscall entry */
if (!attr->exclude_kernel)
mask |= PERF_SAMPLE_BRANCH_KERNEL;
if (!attr->exclude_user)
mask |= PERF_SAMPLE_BRANCH_USER;
if (!attr->exclude_hv)
mask |= PERF_SAMPLE_BRANCH_HV;
/*
* adjust user setting (for HW filter setup)
*/
attr->branch_sample_type = mask;
}
}
out:
return ret;
@ -6063,7 +6267,7 @@ SYSCALL_DEFINE5(perf_event_open,
* - that may need work on context switch
*/
atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
jump_label_inc(&perf_sched_events.key);
static_key_slow_inc(&perf_sched_events.key);
}
/*

13
kernel/events/hw_breakpoint.c
View File

@ -581,6 +581,12 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
if (bp->attr.type != PERF_TYPE_BREAKPOINT)
return -ENOENT;
/*
* no branch sampling for breakpoint events
*/
if (has_branch_stack(bp))
return -EOPNOTSUPP;
err = register_perf_hw_breakpoint(bp);
if (err)
return err;
@ -613,6 +619,11 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags)
bp->hw.state = PERF_HES_STOPPED;
}
static int hw_breakpoint_event_idx(struct perf_event *bp)
{
return 0;
}
static struct pmu perf_breakpoint = {
.task_ctx_nr = perf_sw_context, /* could eventually get its own */
@ -622,6 +633,8 @@ static struct pmu perf_breakpoint = {
.start = hw_breakpoint_start,
.stop = hw_breakpoint_stop,
.read = hw_breakpoint_pmu_read,
.event_idx = hw_breakpoint_event_idx,
};
int __init init_hw_breakpoint(void)

2
kernel/irq/chip.c
View File

@ -16,6 +16,8 @@
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <trace/events/irq.h>
#include "internals.h"
/**

135
kernel/jump_label.c
View File

@ -12,7 +12,7 @@
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/err.h>
#include <linux/jump_label.h>
#include <linux/static_key.h>
#ifdef HAVE_JUMP_LABEL
@ -29,11 +29,6 @@ void jump_label_unlock(void)
mutex_unlock(&jump_label_mutex);
}
bool jump_label_enabled(struct jump_label_key *key)
{
return !!atomic_read(&key->enabled);
}
static int jump_label_cmp(const void *a, const void *b)
{
const struct jump_entry *jea = a;
@ -58,56 +53,66 @@ jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
}
static void jump_label_update(struct jump_label_key *key, int enable);
static void jump_label_update(struct static_key *key, int enable);
void jump_label_inc(struct jump_label_key *key)
void static_key_slow_inc(struct static_key *key)
{
if (atomic_inc_not_zero(&key->enabled))
return;
jump_label_lock();
if (atomic_read(&key->enabled) == 0)
jump_label_update(key, JUMP_LABEL_ENABLE);
if (atomic_read(&key->enabled) == 0) {
if (!jump_label_get_branch_default(key))
jump_label_update(key, JUMP_LABEL_ENABLE);
else
jump_label_update(key, JUMP_LABEL_DISABLE);
}
atomic_inc(&key->enabled);
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(jump_label_inc);
EXPORT_SYMBOL_GPL(static_key_slow_inc);
static void __jump_label_dec(struct jump_label_key *key,
static void __static_key_slow_dec(struct static_key *key,
unsigned long rate_limit, struct delayed_work *work)
{
if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex))
if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
WARN(atomic_read(&key->enabled) < 0,
"jump label: negative count!\n");
return;
}
if (rate_limit) {
atomic_inc(&key->enabled);
schedule_delayed_work(work, rate_limit);
} else
jump_label_update(key, JUMP_LABEL_DISABLE);
} else {
if (!jump_label_get_branch_default(key))
jump_label_update(key, JUMP_LABEL_DISABLE);
else
jump_label_update(key, JUMP_LABEL_ENABLE);
}
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(jump_label_dec);
static void jump_label_update_timeout(struct work_struct *work)
{
struct jump_label_key_deferred *key =
container_of(work, struct jump_label_key_deferred, work.work);
__jump_label_dec(&key->key, 0, NULL);
struct static_key_deferred *key =
container_of(work, struct static_key_deferred, work.work);
__static_key_slow_dec(&key->key, 0, NULL);
}
void jump_label_dec(struct jump_label_key *key)
void static_key_slow_dec(struct static_key *key)
{
__jump_label_dec(key, 0, NULL);
__static_key_slow_dec(key, 0, NULL);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec);
void jump_label_dec_deferred(struct jump_label_key_deferred *key)
void static_key_slow_dec_deferred(struct static_key_deferred *key)
{
__jump_label_dec(&key->key, key->timeout, &key->work);
__static_key_slow_dec(&key->key, key->timeout, &key->work);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
void jump_label_rate_limit(struct jump_label_key_deferred *key,
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
key->timeout = rl;
@ -150,7 +155,7 @@ void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry
arch_jump_label_transform(entry, type);
}
static void __jump_label_update(struct jump_label_key *key,
static void __jump_label_update(struct static_key *key,
struct jump_entry *entry,
struct jump_entry *stop, int enable)
{
@ -167,27 +172,40 @@ static void __jump_label_update(struct jump_label_key *key,
}
}
static enum jump_label_type jump_label_type(struct static_key *key)
{
bool true_branch = jump_label_get_branch_default(key);
bool state = static_key_enabled(key);
if ((!true_branch && state) || (true_branch && !state))
return JUMP_LABEL_ENABLE;
return JUMP_LABEL_DISABLE;
}
void __init jump_label_init(void)
{
struct jump_entry *iter_start = __start___jump_table;
struct jump_entry *iter_stop = __stop___jump_table;
struct jump_label_key *key = NULL;
struct static_key *key = NULL;
struct jump_entry *iter;
jump_label_lock();
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
struct jump_label_key *iterk;
struct static_key *iterk;
iterk = (struct jump_label_key *)(unsigned long)iter->key;
arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
iterk = (struct static_key *)(unsigned long)iter->key;
arch_jump_label_transform_static(iter, jump_label_type(iterk));
if (iterk == key)
continue;
key = iterk;
key->entries = iter;
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
*((unsigned long *)&key->entries) += (unsigned long)iter;
#ifdef CONFIG_MODULES
key->next = NULL;
#endif
@ -197,8 +215,8 @@ void __init jump_label_init(void)
#ifdef CONFIG_MODULES
struct jump_label_mod {
struct jump_label_mod *next;
struct static_key_mod {
struct static_key_mod *next;
struct jump_entry *entries;
struct module *mod;
};
@ -218,9 +236,9 @@ static int __jump_label_mod_text_reserved(void *start, void *end)
start, end);
}
static void __jump_label_mod_update(struct jump_label_key *key, int enable)
static void __jump_label_mod_update(struct static_key *key, int enable)
{
struct jump_label_mod *mod = key->next;
struct static_key_mod *mod = key->next;
while (mod) {
struct module *m = mod->mod;
@ -251,11 +269,7 @@ void jump_label_apply_nops(struct module *mod)
return;
for (iter = iter_start; iter < iter_stop; iter++) {
struct jump_label_key *iterk;
iterk = (struct jump_label_key *)(unsigned long)iter->key;
arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE);
}
}
@ -264,8 +278,8 @@ static int jump_label_add_module(struct module *mod)
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
struct jump_label_key *key = NULL;
struct jump_label_mod *jlm;
struct static_key *key = NULL;
struct static_key_mod *jlm;
/* if the module doesn't have jump label entries, just return */
if (iter_start == iter_stop)
@ -274,28 +288,30 @@ static int jump_label_add_module(struct module *mod)
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
if (iter->key == (jump_label_t)(unsigned long)key)
struct static_key *iterk;
iterk = (struct static_key *)(unsigned long)iter->key;
if (iterk == key)
continue;
key = (struct jump_label_key *)(unsigned long)iter->key;
key = iterk;
if (__module_address(iter->key) == mod) {
atomic_set(&key->enabled, 0);
key->entries = iter;
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
*((unsigned long *)&key->entries) += (unsigned long)iter;
key->next = NULL;
continue;
}
jlm = kzalloc(sizeof(struct jump_label_mod), GFP_KERNEL);
jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
if (!jlm)
return -ENOMEM;
jlm->mod = mod;
jlm->entries = iter;
jlm->next = key->next;
key->next = jlm;
if (jump_label_enabled(key))
if (jump_label_type(key) == JUMP_LABEL_ENABLE)
__jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE);
}
@ -307,14 +323,14 @@ static void jump_label_del_module(struct module *mod)
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
struct jump_label_key *key = NULL;
struct jump_label_mod *jlm, **prev;
struct static_key *key = NULL;
struct static_key_mod *jlm, **prev;
for (iter = iter_start; iter < iter_stop; iter++) {
if (iter->key == (jump_label_t)(unsigned long)key)
continue;
key = (struct jump_label_key *)(unsigned long)iter->key;
key = (struct static_key *)(unsigned long)iter->key;
if (__module_address(iter->key) == mod)
continue;
@ -416,12 +432,13 @@ int jump_label_text_reserved(void *start, void *end)
return ret;
}
static void jump_label_update(struct jump_label_key *key, int enable)
static void jump_label_update(struct static_key *key, int enable)
{
struct jump_entry *entry = key->entries, *stop = __stop___jump_table;
struct jump_entry *stop = __stop___jump_table;
struct jump_entry *entry = jump_label_get_entries(key);
#ifdef CONFIG_MODULES
struct module *mod = __module_address((jump_label_t)key);
struct module *mod = __module_address((unsigned long)key);
__jump_label_mod_update(key, enable);

5
kernel/printk.c
View File

@ -44,6 +44,9 @@
#include <asm/uaccess.h>
#define CREATE_TRACE_POINTS
#include <trace/events/printk.h>
/*
* Architectures can override it:
*/
@ -542,6 +545,8 @@ MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to"
static void _call_console_drivers(unsigned start,
unsigned end, int msg_log_level)
{
trace_console(&LOG_BUF(0), start, end, log_buf_len);
if ((msg_log_level < console_loglevel || ignore_loglevel) &&
console_drivers && start != end) {
if ((start & LOG_BUF_MASK) > (end & LOG_BUF_MASK)) {

18
kernel/sched/core.c
View File

@ -162,13 +162,13 @@ static int sched_feat_show(struct seq_file *m, void *v)
#ifdef HAVE_JUMP_LABEL
#define jump_label_key__true jump_label_key_enabled
#define jump_label_key__false jump_label_key_disabled
#define jump_label_key__true STATIC_KEY_INIT_TRUE
#define jump_label_key__false STATIC_KEY_INIT_FALSE
#define SCHED_FEAT(name, enabled) \
jump_label_key__##enabled ,
struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = {
struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
#include "features.h"
};
@ -176,14 +176,14 @@ struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = {
static void sched_feat_disable(int i)
{
if (jump_label_enabled(&sched_feat_keys[i]))
jump_label_dec(&sched_feat_keys[i]);
if (static_key_enabled(&sched_feat_keys[i]))
static_key_slow_dec(&sched_feat_keys[i]);
}
static void sched_feat_enable(int i)
{
if (!jump_label_enabled(&sched_feat_keys[i]))
jump_label_inc(&sched_feat_keys[i]);
if (!static_key_enabled(&sched_feat_keys[i]))
static_key_slow_inc(&sched_feat_keys[i]);
}
#else
static void sched_feat_disable(int i) { };
@ -894,7 +894,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
delta -= irq_delta;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
if (static_branch((&paravirt_steal_rq_enabled))) {
if (static_key_false((&paravirt_steal_rq_enabled))) {
u64 st;
steal = paravirt_steal_clock(cpu_of(rq));
@ -2755,7 +2755,7 @@ void account_idle_time(cputime_t cputime)
static __always_inline bool steal_account_process_tick(void)
{
#ifdef CONFIG_PARAVIRT
if (static_branch(&paravirt_steal_enabled)) {
if (static_key_false(&paravirt_steal_enabled)) {
u64 steal, st = 0;
steal = paravirt_steal_clock(smp_processor_id());

8
kernel/sched/fair.c
View File

@ -1401,20 +1401,20 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
#ifdef CONFIG_CFS_BANDWIDTH
#ifdef HAVE_JUMP_LABEL
static struct jump_label_key __cfs_bandwidth_used;
static struct static_key __cfs_bandwidth_used;
static inline bool cfs_bandwidth_used(void)
{
return static_branch(&__cfs_bandwidth_used);
return static_key_false(&__cfs_bandwidth_used);
}
void account_cfs_bandwidth_used(int enabled, int was_enabled)
{
/* only need to count groups transitioning between enabled/!enabled */
if (enabled && !was_enabled)
jump_label_inc(&__cfs_bandwidth_used);
static_key_slow_inc(&__cfs_bandwidth_used);
else if (!enabled && was_enabled)
jump_label_dec(&__cfs_bandwidth_used);
static_key_slow_dec(&__cfs_bandwidth_used);
}
#else /* HAVE_JUMP_LABEL */
static bool cfs_bandwidth_used(void)

14
kernel/sched/sched.h
View File

@ -611,7 +611,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
*/
#ifdef CONFIG_SCHED_DEBUG
# include <linux/jump_label.h>
# include <linux/static_key.h>
# define const_debug __read_mostly
#else
# define const_debug const
@ -630,18 +630,18 @@ enum {
#undef SCHED_FEAT
#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
static __always_inline bool static_branch__true(struct jump_label_key *key)
static __always_inline bool static_branch__true(struct static_key *key)
{
return likely(static_branch(key)); /* Not out of line branch. */
return static_key_true(key); /* Not out of line branch. */
}
static __always_inline bool static_branch__false(struct jump_label_key *key)
static __always_inline bool static_branch__false(struct static_key *key)
{
return unlikely(static_branch(key)); /* Out of line branch. */
return static_key_false(key); /* Out of line branch. */
}
#define SCHED_FEAT(name, enabled) \
static __always_inline bool static_branch_##name(struct jump_label_key *key) \
static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
return static_branch__##enabled(key); \
}
@ -650,7 +650,7 @@ static __always_inline bool static_branch_##name(struct jump_label_key *key) \
#undef SCHED_FEAT
extern struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR];
extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))

28
kernel/signal.c
View File

@ -1054,13 +1054,13 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
struct sigpending *pending;
struct sigqueue *q;
int override_rlimit;
trace_signal_generate(sig, info, t);
int ret = 0, result;
assert_spin_locked(&t->sighand->siglock);
result = TRACE_SIGNAL_IGNORED;
if (!prepare_signal(sig, t, from_ancestor_ns))
return 0;
goto ret;
pending = group ? &t->signal->shared_pending : &t->pending;
/*
@ -1068,8 +1068,11 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
* exactly one non-rt signal, so that we can get more
* detailed information about the cause of the signal.
*/
result = TRACE_SIGNAL_ALREADY_PENDING;
if (legacy_queue(pending, sig))
return 0;
goto ret;
result = TRACE_SIGNAL_DELIVERED;
/*
* fast-pathed signals for kernel-internal things like SIGSTOP
* or SIGKILL.
@ -1127,14 +1130,15 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
* signal was rt and sent by user using something
* other than kill().
*/
trace_signal_overflow_fail(sig, group, info);
return -EAGAIN;
result = TRACE_SIGNAL_OVERFLOW_FAIL;
ret = -EAGAIN;
goto ret;
} else {
/*
* This is a silent loss of information. We still
* send the signal, but the *info bits are lost.
*/
trace_signal_lose_info(sig, group, info);
result = TRACE_SIGNAL_LOSE_INFO;
}
}
@ -1142,7 +1146,9 @@ out_set:
signalfd_notify(t, sig);
sigaddset(&pending->signal, sig);
complete_signal(sig, t, group);
return 0;
ret:
trace_signal_generate(sig, info, t, group, result);
return ret;
}
static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
@ -1585,7 +1591,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
int sig = q->info.si_signo;
struct sigpending *pending;
unsigned long flags;
int ret;
int ret, result;
BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
@ -1594,6 +1600,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
goto ret;
ret = 1; /* the signal is ignored */
result = TRACE_SIGNAL_IGNORED;
if (!prepare_signal(sig, t, 0))
goto out;
@ -1605,6 +1612,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
*/
BUG_ON(q->info.si_code != SI_TIMER);
q->info.si_overrun++;
result = TRACE_SIGNAL_ALREADY_PENDING;
goto out;
}
q->info.si_overrun = 0;
@ -1614,7 +1622,9 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
list_add_tail(&q->list, &pending->list);
sigaddset(&pending->signal, sig);
complete_signal(sig, t, group);
result = TRACE_SIGNAL_DELIVERED;
out:
trace_signal_generate(sig, &q->info, t, group, result);
unlock_task_sighand(t, &flags);
ret:
return ret;

6
kernel/softirq.c
View File

@ -375,6 +375,12 @@ void raise_softirq(unsigned int nr)
local_irq_restore(flags);
}
void __raise_softirq_irqoff(unsigned int nr)
{
trace_softirq_raise(nr);
or_softirq_pending(1UL << nr);
}
void open_softirq(int nr, void (*action)(struct softirq_action *))
{
softirq_vec[nr].action = action;

134
kernel/trace/ftrace.c
View File

@ -62,6 +62,8 @@
#define FTRACE_HASH_DEFAULT_BITS 10
#define FTRACE_HASH_MAX_BITS 12
#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
/* ftrace_enabled is a method to turn ftrace on or off */
int ftrace_enabled __read_mostly;
static int last_ftrace_enabled;
@ -89,12 +91,14 @@ static struct ftrace_ops ftrace_list_end __read_mostly = {
};
static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
static struct ftrace_ops global_ops;
static struct ftrace_ops control_ops;
static void
ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
@ -168,6 +172,32 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
}
#endif
static void control_ops_disable_all(struct ftrace_ops *ops)
{
int cpu;
for_each_possible_cpu(cpu)
*per_cpu_ptr(ops->disabled, cpu) = 1;
}
static int control_ops_alloc(struct ftrace_ops *ops)
{
int __percpu *disabled;
disabled = alloc_percpu(int);
if (!disabled)
return -ENOMEM;
ops->disabled = disabled;
control_ops_disable_all(ops);
return 0;
}
static void control_ops_free(struct ftrace_ops *ops)
{
free_percpu(ops->disabled);
}
static void update_global_ops(void)
{
ftrace_func_t func;
@ -259,6 +289,26 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
return 0;
}
static void add_ftrace_list_ops(struct ftrace_ops **list,
struct ftrace_ops *main_ops,
struct ftrace_ops *ops)
{
int first = *list == &ftrace_list_end;
add_ftrace_ops(list, ops);
if (first)
add_ftrace_ops(&ftrace_ops_list, main_ops);
}
static int remove_ftrace_list_ops(struct ftrace_ops **list,
struct ftrace_ops *main_ops,
struct ftrace_ops *ops)
{
int ret = remove_ftrace_ops(list, ops);
if (!ret && *list == &ftrace_list_end)
ret = remove_ftrace_ops(&ftrace_ops_list, main_ops);
return ret;
}
static int __register_ftrace_function(struct ftrace_ops *ops)
{
if (ftrace_disabled)
@ -270,15 +320,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
return -EBUSY;
/* We don't support both control and global flags set. */
if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
return -EINVAL;
if (!core_kernel_data((unsigned long)ops))
ops->flags |= FTRACE_OPS_FL_DYNAMIC;
if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
int first = ftrace_global_list == &ftrace_list_end;
add_ftrace_ops(&ftrace_global_list, ops);
add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops);
ops->flags |= FTRACE_OPS_FL_ENABLED;
if (first)
add_ftrace_ops(&ftrace_ops_list, &global_ops);
} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
if (control_ops_alloc(ops))
return -ENOMEM;
add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops);
} else
add_ftrace_ops(&ftrace_ops_list, ops);
@ -302,11 +357,23 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
return -EINVAL;
if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
ret = remove_ftrace_ops(&ftrace_global_list, ops);
if (!ret && ftrace_global_list == &ftrace_list_end)
ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops);
ret = remove_ftrace_list_ops(&ftrace_global_list,
&global_ops, ops);
if (!ret)
ops->flags &= ~FTRACE_OPS_FL_ENABLED;
} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
ret = remove_ftrace_list_ops(&ftrace_control_list,
&control_ops, ops);
if (!ret) {
/*
* The ftrace_ops is now removed from the list,
* so there'll be no new users. We must ensure
* all current users are done before we free
* the control data.
*/
synchronize_sched();
control_ops_free(ops);
}
} else
ret = remove_ftrace_ops(&ftrace_ops_list, ops);
@ -1119,6 +1186,12 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
}
void ftrace_free_filter(struct ftrace_ops *ops)
{
free_ftrace_hash(ops->filter_hash);
free_ftrace_hash(ops->notrace_hash);
}
static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
{
struct ftrace_hash *hash;
@ -1129,7 +1202,7 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
return NULL;
size = 1 << size_bits;
hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL);
hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL);
if (!hash->buckets) {
kfree(hash);
@ -3146,8 +3219,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
mutex_lock(&ftrace_regex_lock);
if (reset)
ftrace_filter_reset(hash);
if (buf)
ftrace_match_records(hash, buf, len);
if (buf && !ftrace_match_records(hash, buf, len)) {
ret = -EINVAL;
goto out_regex_unlock;
}
mutex_lock(&ftrace_lock);
ret = ftrace_hash_move(ops, enable, orig_hash, hash);
@ -3157,6 +3232,7 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
mutex_unlock(&ftrace_lock);
out_regex_unlock:
mutex_unlock(&ftrace_regex_lock);
free_ftrace_hash(hash);
@ -3173,10 +3249,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
* Filters denote which functions should be enabled when tracing is enabled.
* If @buf is NULL and reset is set, all functions will be enabled for tracing.
*/
void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
{
ftrace_set_regex(ops, buf, len, reset, 1);
return ftrace_set_regex(ops, buf, len, reset, 1);
}
EXPORT_SYMBOL_GPL(ftrace_set_filter);
@ -3191,10 +3267,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter);
* is enabled. If @buf is NULL and reset is set, all functions will be enabled
* for tracing.
*/
void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
{
ftrace_set_regex(ops, buf, len, reset, 0);
return ftrace_set_regex(ops, buf, len, reset, 0);
}
EXPORT_SYMBOL_GPL(ftrace_set_notrace);
/**
@ -3870,6 +3946,36 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
#endif /* CONFIG_DYNAMIC_FTRACE */
static void
ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
{
struct ftrace_ops *op;
if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
return;
/*
* Some of the ops may be dynamically allocated,
* they must be freed after a synchronize_sched().
*/
preempt_disable_notrace();
trace_recursion_set(TRACE_CONTROL_BIT);
op = rcu_dereference_raw(ftrace_control_list);
while (op != &ftrace_list_end) {
if (!ftrace_function_local_disabled(op) &&
ftrace_ops_test(op, ip))
op->func(ip, parent_ip);
op = rcu_dereference_raw(op->next);
};
trace_recursion_clear(TRACE_CONTROL_BIT);
preempt_enable_notrace();
}
static struct ftrace_ops control_ops = {
.func = ftrace_ops_control_func,
};
static void
ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
{

6
kernel/trace/trace.c
View File

@ -2764,12 +2764,12 @@ static const char readme_msg[] =
"tracing mini-HOWTO:\n\n"
"# mount -t debugfs nodev /sys/kernel/debug\n\n"
"# cat /sys/kernel/debug/tracing/available_tracers\n"
"wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
"wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n"
"# cat /sys/kernel/debug/tracing/current_tracer\n"
"nop\n"
"# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n"
"# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n"
"# cat /sys/kernel/debug/tracing/current_tracer\n"
"sched_switch\n"
"wakeup\n"
"# cat /sys/kernel/debug/tracing/trace_options\n"
"noprint-parent nosym-offset nosym-addr noverbose\n"
"# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"

38
kernel/trace/trace.h
View File

@ -56,17 +56,23 @@ enum trace_type {
#define F_STRUCT(args...) args
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
struct struct_name { \
struct trace_entry ent; \
tstruct \
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
struct struct_name { \
struct trace_entry ent; \
tstruct \
}
#undef TP_ARGS
#define TP_ARGS(args...) args
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
#undef FTRACE_ENTRY_REG
#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
filter, regfn) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter)
#include "trace_entries.h"
@ -288,6 +294,8 @@ struct tracer {
/* for function tracing recursion */
#define TRACE_INTERNAL_BIT (1<<11)
#define TRACE_GLOBAL_BIT (1<<12)
#define TRACE_CONTROL_BIT (1<<13)
/*
* Abuse of the trace_recursion.
* As we need a way to maintain state if we are tracing the function
@ -589,6 +597,8 @@ static inline int ftrace_trace_task(struct task_struct *task)
static inline int ftrace_is_dead(void) { return 0; }
#endif
int ftrace_event_is_function(struct ftrace_event_call *call);
/*
* struct trace_parser - servers for reading the user input separated by spaces
* @cont: set if the input is not complete - no final space char was found
@ -766,9 +776,7 @@ struct filter_pred {
u64 val;
struct regex regex;
unsigned short *ops;
#ifdef CONFIG_FTRACE_STARTUP_TEST
struct ftrace_event_field *field;
#endif
int offset;
int not;
int op;
@ -818,12 +826,22 @@ extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \
extern struct ftrace_event_call \
__attribute__((__aligned__(4))) event_##call;
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter)
#include "trace_entries.h"
#ifdef CONFIG_PERF_EVENTS
#ifdef CONFIG_FUNCTION_TRACER
int perf_ftrace_event_register(struct ftrace_event_call *call,
enum trace_reg type, void *data);
#else
#define perf_ftrace_event_register NULL
#endif /* CONFIG_FUNCTION_TRACER */
#endif /* CONFIG_PERF_EVENTS */
#endif /* _LINUX_KERNEL_TRACE_H */

54
kernel/trace/trace_entries.h
View File

@ -55,7 +55,7 @@
/*
* Function trace entry - function address and parent function address:
*/
FTRACE_ENTRY(function, ftrace_entry,
FTRACE_ENTRY_REG(function, ftrace_entry,
TRACE_FN,
@ -64,7 +64,11 @@ FTRACE_ENTRY(function, ftrace_entry,
__field( unsigned long, parent_ip )
),
F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip),
FILTER_TRACE_FN,
perf_ftrace_event_register
);
/* Function call entry */
@ -78,7 +82,9 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
__field_desc( int, graph_ent, depth )
),
F_printk("--> %lx (%d)", __entry->func, __entry->depth)
F_printk("--> %lx (%d)", __entry->func, __entry->depth),
FILTER_OTHER
);
/* Function return entry */
@ -98,7 +104,9 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d",
__entry->func, __entry->depth,
__entry->calltime, __entry->rettime,
__entry->depth)
__entry->depth),
FILTER_OTHER
);
/*
@ -127,8 +135,9 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry,
F_printk("%u:%u:%u ==> %u:%u:%u [%03u]",
__entry->prev_pid, __entry->prev_prio, __entry->prev_state,
__entry->next_pid, __entry->next_prio, __entry->next_state,
__entry->next_cpu
)
__entry->next_cpu),
FILTER_OTHER
);
/*
@ -146,8 +155,9 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]",
__entry->prev_pid, __entry->prev_prio, __entry->prev_state,
__entry->next_pid, __entry->next_prio, __entry->next_state,
__entry->next_cpu
)
__entry->next_cpu),
FILTER_OTHER
);
/*
@ -169,7 +179,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
"\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
__entry->caller[0], __entry->caller[1], __entry->caller[2],
__entry->caller[3], __entry->caller[4], __entry->caller[5],
__entry->caller[6], __entry->caller[7])
__entry->caller[6], __entry->caller[7]),
FILTER_OTHER
);
FTRACE_ENTRY(user_stack, userstack_entry,
@ -185,7 +197,9 @@ FTRACE_ENTRY(user_stack, userstack_entry,
"\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
__entry->caller[0], __entry->caller[1], __entry->caller[2],
__entry->caller[3], __entry->caller[4], __entry->caller[5],
__entry->caller[6], __entry->caller[7])
__entry->caller[6], __entry->caller[7]),
FILTER_OTHER
);
/*
@ -202,7 +216,9 @@ FTRACE_ENTRY(bprint, bprint_entry,
),
F_printk("%08lx fmt:%p",
__entry->ip, __entry->fmt)
__entry->ip, __entry->fmt),
FILTER_OTHER
);
FTRACE_ENTRY(print, print_entry,
@ -215,7 +231,9 @@ FTRACE_ENTRY(print, print_entry,
),
F_printk("%08lx %s",
__entry->ip, __entry->buf)
__entry->ip, __entry->buf),
FILTER_OTHER
);
FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
@ -234,7 +252,9 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
F_printk("%lx %lx %lx %d %x %x",
(unsigned long)__entry->phys, __entry->value, __entry->pc,
__entry->map_id, __entry->opcode, __entry->width)
__entry->map_id, __entry->opcode, __entry->width),
FILTER_OTHER
);
FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
@ -252,7 +272,9 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
F_printk("%lx %lx %lx %d %x",
(unsigned long)__entry->phys, __entry->virt, __entry->len,
__entry->map_id, __entry->opcode)
__entry->map_id, __entry->opcode),
FILTER_OTHER
);
@ -272,6 +294,8 @@ FTRACE_ENTRY(branch, trace_branch,
F_printk("%u:%s:%s (%u)",
__entry->line,
__entry->func, __entry->file, __entry->correct)
__entry->func, __entry->file, __entry->correct),
FILTER_OTHER
);

208
kernel/trace/trace_event_perf.c
View File

@ -24,6 +24,11 @@ static int total_ref_count;
static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
/* The ftrace function trace is allowed only for root. */
if (ftrace_event_is_function(tp_event) &&
perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
return -EPERM;
/* No tracing, just counting, so no obvious leak */
if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
return 0;
@ -44,23 +49,17 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
return 0;
}
static int perf_trace_event_init(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
static int perf_trace_event_reg(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
struct hlist_head __percpu *list;
int ret;
int ret = -ENOMEM;
int cpu;
ret = perf_trace_event_perm(tp_event, p_event);
if (ret)
return ret;
p_event->tp_event = tp_event;
if (tp_event->perf_refcount++ > 0)
return 0;
ret = -ENOMEM;
list = alloc_percpu(struct hlist_head);
if (!list)
goto fail;
@ -83,7 +82,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
}
}
ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL);
if (ret)
goto fail;
@ -108,6 +107,69 @@ fail:
return ret;
}
static void perf_trace_event_unreg(struct perf_event *p_event)
{
struct ftrace_event_call *tp_event = p_event->tp_event;
int i;
if (--tp_event->perf_refcount > 0)
goto out;
tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
/*
* Ensure our callback won't be called anymore. The buffers
* will be freed after that.
*/
tracepoint_synchronize_unregister();
free_percpu(tp_event->perf_events);
tp_event->perf_events = NULL;
if (!--total_ref_count) {
for (i = 0; i < PERF_NR_CONTEXTS; i++) {
free_percpu(perf_trace_buf[i]);
perf_trace_buf[i] = NULL;
}
}
out:
module_put(tp_event->mod);
}
static int perf_trace_event_open(struct perf_event *p_event)
{
struct ftrace_event_call *tp_event = p_event->tp_event;
return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event);
}
static void perf_trace_event_close(struct perf_event *p_event)
{
struct ftrace_event_call *tp_event = p_event->tp_event;
tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event);
}
static int perf_trace_event_init(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
int ret;
ret = perf_trace_event_perm(tp_event, p_event);
if (ret)
return ret;
ret = perf_trace_event_reg(tp_event, p_event);
if (ret)
return ret;
ret = perf_trace_event_open(p_event);
if (ret) {
perf_trace_event_unreg(p_event);
return ret;
}
return 0;
}
int perf_trace_init(struct perf_event *p_event)
{
struct ftrace_event_call *tp_event;
@ -130,6 +192,14 @@ int perf_trace_init(struct perf_event *p_event)
return ret;
}
void perf_trace_destroy(struct perf_event *p_event)
{
mutex_lock(&event_mutex);
perf_trace_event_close(p_event);
perf_trace_event_unreg(p_event);
mutex_unlock(&event_mutex);
}
int perf_trace_add(struct perf_event *p_event, int flags)
{
struct ftrace_event_call *tp_event = p_event->tp_event;
@ -146,43 +216,14 @@ int perf_trace_add(struct perf_event *p_event, int flags)
list = this_cpu_ptr(pcpu_list);
hlist_add_head_rcu(&p_event->hlist_entry, list);
return 0;
return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event);
}
void perf_trace_del(struct perf_event *p_event, int flags)
{
hlist_del_rcu(&p_event->hlist_entry);
}
void perf_trace_destroy(struct perf_event *p_event)
{
struct ftrace_event_call *tp_event = p_event->tp_event;
int i;
mutex_lock(&event_mutex);
if (--tp_event->perf_refcount > 0)
goto out;
tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
/*
* Ensure our callback won't be called anymore. The buffers
* will be freed after that.
*/
tracepoint_synchronize_unregister();
free_percpu(tp_event->perf_events);
tp_event->perf_events = NULL;
if (!--total_ref_count) {
for (i = 0; i < PERF_NR_CONTEXTS; i++) {
free_percpu(perf_trace_buf[i]);
perf_trace_buf[i] = NULL;
}
}
out:
module_put(tp_event->mod);
mutex_unlock(&event_mutex);
hlist_del_rcu(&p_event->hlist_entry);
tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
}
__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
@ -214,3 +255,86 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
return raw_data;
}
EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
#ifdef CONFIG_FUNCTION_TRACER
static void
perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
{
struct ftrace_entry *entry;
struct hlist_head *head;
struct pt_regs regs;
int rctx;
#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
sizeof(u64)) - sizeof(u32))
BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
perf_fetch_caller_regs(&regs);
entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
if (!entry)
return;
entry->ip = ip;
entry->parent_ip = parent_ip;
head = this_cpu_ptr(event_function.perf_events);
perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
1, &regs, head);
#undef ENTRY_SIZE
}
static int perf_ftrace_function_register(struct perf_event *event)
{
struct ftrace_ops *ops = &event->ftrace_ops;
ops->flags |= FTRACE_OPS_FL_CONTROL;
ops->func = perf_ftrace_function_call;
return register_ftrace_function(ops);
}
static int perf_ftrace_function_unregister(struct perf_event *event)
{
struct ftrace_ops *ops = &event->ftrace_ops;
int ret = unregister_ftrace_function(ops);
ftrace_free_filter(ops);
return ret;
}
static void perf_ftrace_function_enable(struct perf_event *event)
{
ftrace_function_local_enable(&event->ftrace_ops);
}
static void perf_ftrace_function_disable(struct perf_event *event)
{
ftrace_function_local_disable(&event->ftrace_ops);
}
int perf_ftrace_event_register(struct ftrace_event_call *call,
enum trace_reg type, void *data)
{
switch (type) {
case TRACE_REG_REGISTER:
case TRACE_REG_UNREGISTER:
break;
case TRACE_REG_PERF_REGISTER:
case TRACE_REG_PERF_UNREGISTER:
return 0;
case TRACE_REG_PERF_OPEN:
return perf_ftrace_function_register(data);
case TRACE_REG_PERF_CLOSE:
return perf_ftrace_function_unregister(data);
case TRACE_REG_PERF_ADD:
perf_ftrace_function_enable(data);
return 0;
case TRACE_REG_PERF_DEL:
perf_ftrace_function_disable(data);
return 0;
}
return -EINVAL;
}
#endif /* CONFIG_FUNCTION_TRACER */

12
kernel/trace/trace_events.c
View File

@ -147,7 +147,8 @@ int trace_event_raw_init(struct ftrace_event_call *call)
}
EXPORT_SYMBOL_GPL(trace_event_raw_init);
int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
int ftrace_event_reg(struct ftrace_event_call *call,
enum trace_reg type, void *data)
{
switch (type) {
case TRACE_REG_REGISTER:
@ -170,6 +171,11 @@ int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
call->class->perf_probe,
call);
return 0;
case TRACE_REG_PERF_OPEN:
case TRACE_REG_PERF_CLOSE:
case TRACE_REG_PERF_ADD:
case TRACE_REG_PERF_DEL:
return 0;
#endif
}
return 0;
@ -209,7 +215,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
tracing_stop_cmdline_record();
call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
}
call->class->reg(call, TRACE_REG_UNREGISTER);
call->class->reg(call, TRACE_REG_UNREGISTER, NULL);
}
break;
case 1:
@ -218,7 +224,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
tracing_start_cmdline_record();
call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
}
ret = call->class->reg(call, TRACE_REG_REGISTER);
ret = call->class->reg(call, TRACE_REG_REGISTER, NULL);
if (ret) {
tracing_stop_cmdline_record();
pr_info("event trace: Could not enable event "

175
kernel/trace/trace_events_filter.c
View File

@ -81,6 +81,7 @@ enum {
FILT_ERR_TOO_MANY_PREDS,
FILT_ERR_MISSING_FIELD,
FILT_ERR_INVALID_FILTER,
FILT_ERR_IP_FIELD_ONLY,
};
static char *err_text[] = {
@ -96,6 +97,7 @@ static char *err_text[] = {
"Too many terms in predicate expression",
"Missing field name and/or value",
"Meaningless filter expression",
"Only 'ip' field is supported for function trace",
};
struct opstack_op {
@ -685,7 +687,7 @@ find_event_field(struct ftrace_event_call *call, char *name)
static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
{
stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL);
if (!stack->preds)
return -ENOMEM;
stack->index = n_preds;
@ -826,8 +828,7 @@ static int __alloc_preds(struct event_filter *filter, int n_preds)
if (filter->preds)
__free_preds(filter);
filter->preds =
kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
filter->preds = kcalloc(n_preds, sizeof(*filter->preds), GFP_KERNEL);
if (!filter->preds)
return -ENOMEM;
@ -900,6 +901,11 @@ int filter_assign_type(const char *type)
return FILTER_OTHER;
}
static bool is_function_field(struct ftrace_event_field *field)
{
return field->filter_type == FILTER_TRACE_FN;
}
static bool is_string_field(struct ftrace_event_field *field)
{
return field->filter_type == FILTER_DYN_STRING ||
@ -987,6 +993,11 @@ static int init_pred(struct filter_parse_state *ps,
fn = filter_pred_strloc;
else
fn = filter_pred_pchar;
} else if (is_function_field(field)) {
if (strcmp(field->name, "ip")) {
parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0);
return -EINVAL;
}
} else {
if (field->is_signed)
ret = strict_strtoll(pred->regex.pattern, 0, &val);
@ -1334,10 +1345,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps,
strcpy(pred.regex.pattern, operand2);
pred.regex.len = strlen(pred.regex.pattern);
#ifdef CONFIG_FTRACE_STARTUP_TEST
pred.field = field;
#endif
return init_pred(ps, field, &pred) ? NULL : &pred;
}
@ -1486,7 +1494,7 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
children = count_leafs(preds, &preds[root->left]);
children += count_leafs(preds, &preds[root->right]);
root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
root->ops = kcalloc(children, sizeof(*root->ops), GFP_KERNEL);
if (!root->ops)
return -ENOMEM;
@ -1950,6 +1958,148 @@ void ftrace_profile_free_filter(struct perf_event *event)
__free_filter(filter);
}
struct function_filter_data {
struct ftrace_ops *ops;
int first_filter;
int first_notrace;
};
#ifdef CONFIG_FUNCTION_TRACER
static char **
ftrace_function_filter_re(char *buf, int len, int *count)
{
char *str, *sep, **re;
str = kstrndup(buf, len, GFP_KERNEL);
if (!str)
return NULL;
/*
* The argv_split function takes white space
* as a separator, so convert ',' into spaces.
*/
while ((sep = strchr(str, ',')))
*sep = ' ';
re = argv_split(GFP_KERNEL, str, count);
kfree(str);
return re;
}
static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter,
int reset, char *re, int len)
{
int ret;
if (filter)
ret = ftrace_set_filter(ops, re, len, reset);
else
ret = ftrace_set_notrace(ops, re, len, reset);
return ret;
}
static int __ftrace_function_set_filter(int filter, char *buf, int len,
struct function_filter_data *data)
{
int i, re_cnt, ret;
int *reset;
char **re;
reset = filter ? &data->first_filter : &data->first_notrace;
/*
* The 'ip' field could have multiple filters set, separated
* either by space or comma. We first cut the filter and apply
* all pieces separatelly.
*/
re = ftrace_function_filter_re(buf, len, &re_cnt);
if (!re)
return -EINVAL;
for (i = 0; i < re_cnt; i++) {
ret = ftrace_function_set_regexp(data->ops, filter, *reset,
re[i], strlen(re[i]));
if (ret)
break;
if (*reset)
*reset = 0;
}
argv_free(re);
return ret;
}
static int ftrace_function_check_pred(struct filter_pred *pred, int leaf)
{
struct ftrace_event_field *field = pred->field;
if (leaf) {
/*
* Check the leaf predicate for function trace, verify:
* - only '==' and '!=' is used
* - the 'ip' field is used
*/
if ((pred->op != OP_EQ) && (pred->op != OP_NE))
return -EINVAL;
if (strcmp(field->name, "ip"))
return -EINVAL;
} else {
/*
* Check the non leaf predicate for function trace, verify:
* - only '||' is used
*/
if (pred->op != OP_OR)
return -EINVAL;
}
return 0;
}
static int ftrace_function_set_filter_cb(enum move_type move,
struct filter_pred *pred,
int *err, void *data)
{
/* Checking the node is valid for function trace. */
if ((move != MOVE_DOWN) ||
(pred->left != FILTER_PRED_INVALID)) {
*err = ftrace_function_check_pred(pred, 0);
} else {
*err = ftrace_function_check_pred(pred, 1);
if (*err)
return WALK_PRED_ABORT;
*err = __ftrace_function_set_filter(pred->op == OP_EQ,
pred->regex.pattern,
pred->regex.len,
data);
}
return (*err) ? WALK_PRED_ABORT : WALK_PRED_DEFAULT;
}
static int ftrace_function_set_filter(struct perf_event *event,
struct event_filter *filter)
{
struct function_filter_data data = {
.first_filter = 1,
.first_notrace = 1,
.ops = &event->ftrace_ops,
};
return walk_pred_tree(filter->preds, filter->root,
ftrace_function_set_filter_cb, &data);
}
#else
static int ftrace_function_set_filter(struct perf_event *event,
struct event_filter *filter)
{
return -ENODEV;
}
#endif /* CONFIG_FUNCTION_TRACER */
int ftrace_profile_set_filter(struct perf_event *event, int event_id,
char *filter_str)
{
@ -1970,9 +2120,16 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
goto out_unlock;
err = create_filter(call, filter_str, false, &filter);
if (!err)
event->filter = filter;
if (err)
goto free_filter;
if (ftrace_event_is_function(call))
err = ftrace_function_set_filter(event, filter);
else
event->filter = filter;
free_filter:
if (err || ftrace_event_is_function(call))
__free_filter(filter);
out_unlock:

64
kernel/trace/trace_export.c
View File

@ -18,6 +18,16 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM ftrace
/*
* The FTRACE_ENTRY_REG macro allows ftrace entry to define register
* function and thus become accesible via perf.
*/
#undef FTRACE_ENTRY_REG
#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
filter, regfn) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter)
/* not needed for this file */
#undef __field_struct
#define __field_struct(type, item)
@ -44,21 +54,22 @@
#define F_printk(fmt, args...) fmt, args
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
struct ____ftrace_##name { \
tstruct \
}; \
static void __always_unused ____ftrace_check_##name(void) \
{ \
struct ____ftrace_##name *__entry = NULL; \
\
/* force compile-time check on F_printk() */ \
printk(print); \
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
struct ____ftrace_##name { \
tstruct \
}; \
static void __always_unused ____ftrace_check_##name(void) \
{ \
struct ____ftrace_##name *__entry = NULL; \
\
/* force compile-time check on F_printk() */ \
printk(print); \
}
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
filter)
#include "trace_entries.h"
@ -67,7 +78,7 @@ static void __always_unused ____ftrace_check_##name(void) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
is_signed_type(type), filter_type); \
if (ret) \
return ret;
@ -77,7 +88,7 @@ static void __always_unused ____ftrace_check_##name(void) \
offsetof(typeof(field), \
container.item), \
sizeof(field.container.item), \
is_signed_type(type), FILTER_OTHER); \
is_signed_type(type), filter_type); \
if (ret) \
return ret;
@ -91,7 +102,7 @@ static void __always_unused ____ftrace_check_##name(void) \
ret = trace_define_field(event_call, event_storage, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
is_signed_type(type), filter_type); \
mutex_unlock(&event_storage_mutex); \
if (ret) \
return ret; \
@ -104,7 +115,7 @@ static void __always_unused ____ftrace_check_##name(void) \
offsetof(typeof(field), \
container.item), \
sizeof(field.container.item), \
is_signed_type(type), FILTER_OTHER); \
is_signed_type(type), filter_type); \
if (ret) \
return ret;
@ -112,17 +123,18 @@ static void __always_unused ____ftrace_check_##name(void) \
#define __dynamic_array(type, item) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
0, is_signed_type(type), FILTER_OTHER);\
0, is_signed_type(type), filter_type);\
if (ret) \
return ret;
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
int \
ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
{ \
struct struct_name field; \
int ret; \
int filter_type = filter; \
\
tstruct; \
\
@ -152,13 +164,15 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
#undef F_printk
#define F_printk(fmt, args...) #fmt ", " __stringify(args)
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \
#undef FTRACE_ENTRY_REG
#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
regfn) \
\
struct ftrace_event_class event_class_ftrace_##call = { \
.system = __stringify(TRACE_SYSTEM), \
.define_fields = ftrace_define_fields_##call, \
.fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
.reg = regfn, \
}; \
\
struct ftrace_event_call __used event_##call = { \
@ -170,4 +184,14 @@ struct ftrace_event_call __used event_##call = { \
struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \
FTRACE_ENTRY_REG(call, struct_name, etype, \
PARAMS(tstruct), PARAMS(print), filter, NULL)
int ftrace_event_is_function(struct ftrace_event_call *call)
{
return call == &event_function;
}
#include "trace_entries.h"

8
kernel/trace/trace_kprobe.c
View File

@ -1892,7 +1892,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
#endif /* CONFIG_PERF_EVENTS */
static __kprobes
int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
int kprobe_register(struct ftrace_event_call *event,
enum trace_reg type, void *data)
{
struct trace_probe *tp = (struct trace_probe *)event->data;
@ -1909,6 +1910,11 @@ int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
case TRACE_REG_PERF_UNREGISTER:
disable_trace_probe(tp, TP_FLAG_PROFILE);
return 0;
case TRACE_REG_PERF_OPEN:
case TRACE_REG_PERF_CLOSE:
case TRACE_REG_PERF_ADD:
case TRACE_REG_PERF_DEL:
return 0;
#endif
}
return 0;

12
kernel/trace/trace_output.c
View File

@ -300,7 +300,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
unsigned long mask;
const char *str;
const char *ret = p->buffer + p->len;
int i;
int i, first = 1;
for (i = 0; flag_array[i].name && flags; i++) {
@ -310,14 +310,16 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
str = flag_array[i].name;
flags &= ~mask;
if (p->len && delim)
if (!first && delim)
trace_seq_puts(p, delim);
else
first = 0;
trace_seq_puts(p, str);
}
/* check for left over flags */
if (flags) {
if (p->len && delim)
if (!first && delim)
trace_seq_puts(p, delim);
trace_seq_printf(p, "0x%lx", flags);
}
@ -344,7 +346,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
break;
}
if (!p->len)
if (ret == (const char *)(p->buffer + p->len))
trace_seq_printf(p, "0x%lx", val);
trace_seq_putc(p, 0);
@ -370,7 +372,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
break;
}
if (!p->len)
if (ret == (const char *)(p->buffer + p->len))
trace_seq_printf(p, "0x%llx", val);
trace_seq_putc(p, 0);

22
kernel/trace/trace_syscalls.c
View File

@ -17,9 +17,9 @@ static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
static int syscall_enter_register(struct ftrace_event_call *event,
enum trace_reg type);
enum trace_reg type, void *data);
static int syscall_exit_register(struct ftrace_event_call *event,
enum trace_reg type);
enum trace_reg type, void *data);
static int syscall_enter_define_fields(struct ftrace_event_call *call);
static int syscall_exit_define_fields(struct ftrace_event_call *call);
@ -468,8 +468,8 @@ int __init init_ftrace_syscalls(void)
unsigned long addr;
int i;
syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
NR_syscalls, GFP_KERNEL);
syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
GFP_KERNEL);
if (!syscalls_metadata) {
WARN_ON(1);
return -ENOMEM;
@ -649,7 +649,7 @@ void perf_sysexit_disable(struct ftrace_event_call *call)
#endif /* CONFIG_PERF_EVENTS */
static int syscall_enter_register(struct ftrace_event_call *event,
enum trace_reg type)
enum trace_reg type, void *data)
{
switch (type) {
case TRACE_REG_REGISTER:
@ -664,13 +664,18 @@ static int syscall_enter_register(struct ftrace_event_call *event,
case TRACE_REG_PERF_UNREGISTER:
perf_sysenter_disable(event);
return 0;
case TRACE_REG_PERF_OPEN:
case TRACE_REG_PERF_CLOSE:
case TRACE_REG_PERF_ADD:
case TRACE_REG_PERF_DEL:
return 0;
#endif
}
return 0;
}
static int syscall_exit_register(struct ftrace_event_call *event,
enum trace_reg type)
enum trace_reg type, void *data)
{
switch (type) {
case TRACE_REG_REGISTER:
@ -685,6 +690,11 @@ static int syscall_exit_register(struct ftrace_event_call *event,
case TRACE_REG_PERF_UNREGISTER:
perf_sysexit_disable(event);
return 0;
case TRACE_REG_PERF_OPEN:
case TRACE_REG_PERF_CLOSE:
case TRACE_REG_PERF_ADD:
case TRACE_REG_PERF_DEL:
return 0;
#endif
}
return 0;

20
kernel/tracepoint.c
View File

@ -25,7 +25,7 @@
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/jump_label.h>
#include <linux/static_key.h>
extern struct tracepoint * const __start___tracepoints_ptrs[];
extern struct tracepoint * const __stop___tracepoints_ptrs[];
@ -256,9 +256,9 @@ static void set_tracepoint(struct tracepoint_entry **entry,
{
WARN_ON(strcmp((*entry)->name, elem->name) != 0);
if (elem->regfunc && !jump_label_enabled(&elem->key) && active)
if (elem->regfunc && !static_key_enabled(&elem->key) && active)
elem->regfunc();
else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active)
else if (elem->unregfunc && static_key_enabled(&elem->key) && !active)
elem->unregfunc();
/*
@ -269,10 +269,10 @@ static void set_tracepoint(struct tracepoint_entry **entry,
* is used.
*/
rcu_assign_pointer(elem->funcs, (*entry)->funcs);
if (active && !jump_label_enabled(&elem->key))
jump_label_inc(&elem->key);
else if (!active && jump_label_enabled(&elem->key))
jump_label_dec(&elem->key);
if (active && !static_key_enabled(&elem->key))
static_key_slow_inc(&elem->key);
else if (!active && static_key_enabled(&elem->key))
static_key_slow_dec(&elem->key);
}
/*
@ -283,11 +283,11 @@ static void set_tracepoint(struct tracepoint_entry **entry,
*/
static void disable_tracepoint(struct tracepoint *elem)
{
if (elem->unregfunc && jump_label_enabled(&elem->key))
if (elem->unregfunc && static_key_enabled(&elem->key))
elem->unregfunc();
if (jump_label_enabled(&elem->key))
jump_label_dec(&elem->key);
if (static_key_enabled(&elem->key))
static_key_slow_dec(&elem->key);
rcu_assign_pointer(elem->funcs, NULL);
}

24
kernel/watchdog.c
View File

@ -3,12 +3,9 @@
*
* started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
*
* this code detects hard lockups: incidents in where on a CPU
* the kernel does not respond to anything except NMI.
*
* Note: Most of this code is borrowed heavily from softlockup.c,
* so thanks to Ingo for the initial implementation.
* Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks
* Note: Most of this code is borrowed heavily from the original softlockup
* detector, so thanks to Ingo for the initial implementation.
* Some chunks also taken from the old x86-specific nmi watchdog code, thanks
* to those contributors as well.
*/
@ -117,9 +114,10 @@ static unsigned long get_sample_period(void)
{
/*
* convert watchdog_thresh from seconds to ns
* the divide by 5 is to give hrtimer 5 chances to
* increment before the hardlockup detector generates
* a warning
* the divide by 5 is to give hrtimer several chances (two
* or three with the current relation between the soft
* and hard thresholds) to increment before the
* hardlockup detector generates a warning
*/
return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
}
@ -336,9 +334,11 @@ static int watchdog(void *unused)
set_current_state(TASK_INTERRUPTIBLE);
/*
* Run briefly once per second to reset the softlockup timestamp.
* If this gets delayed for more than 60 seconds then the
* debug-printout triggers in watchdog_timer_fn().
* Run briefly (kicked by the hrtimer callback function) once every
* get_sample_period() seconds (4 seconds by default) to reset the
* softlockup timestamp. If this gets delayed for more than
* 2*watchdog_thresh seconds then the debug-printout triggers in
* watchdog_timer_fn().
*/
while (!kthread_should_stop()) {
__touch_watchdog();

18
lib/Kconfig.debug
View File

@ -166,18 +166,21 @@ config LOCKUP_DETECTOR
hard and soft lockups.
Softlockups are bugs that cause the kernel to loop in kernel
mode for more than 60 seconds, without giving other tasks a
mode for more than 20 seconds, without giving other tasks a
chance to run. The current stack trace is displayed upon
detection and the system will stay locked up.
Hardlockups are bugs that cause the CPU to loop in kernel mode
for more than 60 seconds, without letting other interrupts have a
for more than 10 seconds, without letting other interrupts have a
chance to run. The current stack trace is displayed upon detection
and the system will stay locked up.
The overhead should be minimal. A periodic hrtimer runs to
generate interrupts and kick the watchdog task every 10-12 seconds.
An NMI is generated every 60 seconds or so to check for hardlockups.
generate interrupts and kick the watchdog task every 4 seconds.
An NMI is generated every 10 seconds or so to check for hardlockups.
The frequency of hrtimer and NMI events and the soft and hard lockup
thresholds can be controlled through the sysctl watchdog_thresh.
config HARDLOCKUP_DETECTOR
def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \
@ -189,7 +192,8 @@ config BOOTPARAM_HARDLOCKUP_PANIC
help
Say Y here to enable the kernel to panic on "hard lockups",
which are bugs that cause the kernel to loop in kernel
mode with interrupts disabled for more than 60 seconds.
mode with interrupts disabled for more than 10 seconds (configurable
using the watchdog_thresh sysctl).
Say N if unsure.
@ -206,8 +210,8 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
help
Say Y here to enable the kernel to panic on "soft lockups",
which are bugs that cause the kernel to loop in kernel
mode for more than 60 seconds, without giving other tasks a
chance to run.
mode for more than 20 seconds (configurable using the watchdog_thresh
sysctl), without giving other tasks a chance to run.
The panic can be used in combination with panic_timeout,
to cause the system to reboot automatically after a

24
net/core/dev.c
View File

@ -134,7 +134,7 @@
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/net_tstamp.h>
#include <linux/jump_label.h>
#include <linux/static_key.h>
#include <net/flow_keys.h>
#include "net-sysfs.h"
@ -1441,11 +1441,11 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
}
EXPORT_SYMBOL(call_netdevice_notifiers);
static struct jump_label_key netstamp_needed __read_mostly;
static struct static_key netstamp_needed __read_mostly;
#ifdef HAVE_JUMP_LABEL
/* We are not allowed to call jump_label_dec() from irq context
/* We are not allowed to call static_key_slow_dec() from irq context
* If net_disable_timestamp() is called from irq context, defer the
* jump_label_dec() calls.
* static_key_slow_dec() calls.
*/
static atomic_t netstamp_needed_deferred;
#endif
@ -1457,12 +1457,12 @@ void net_enable_timestamp(void)
if (deferred) {
while (--deferred)
jump_label_dec(&netstamp_needed);
static_key_slow_dec(&netstamp_needed);
return;
}
#endif
WARN_ON(in_interrupt());
jump_label_inc(&netstamp_needed);
static_key_slow_inc(&netstamp_needed);
}
EXPORT_SYMBOL(net_enable_timestamp);
@ -1474,19 +1474,19 @@ void net_disable_timestamp(void)
return;
}
#endif
jump_label_dec(&netstamp_needed);
static_key_slow_dec(&netstamp_needed);
}
EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp_set(struct sk_buff *skb)
{
skb->tstamp.tv64 = 0;
if (static_branch(&netstamp_needed))
if (static_key_false(&netstamp_needed))
__net_timestamp(skb);
}
#define net_timestamp_check(COND, SKB) \
if (static_branch(&netstamp_needed)) { \
if (static_key_false(&netstamp_needed)) { \
if ((COND) && !(SKB)->tstamp.tv64) \
__net_timestamp(SKB); \
} \
@ -2660,7 +2660,7 @@ EXPORT_SYMBOL(__skb_get_rxhash);
struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
EXPORT_SYMBOL(rps_sock_flow_table);
struct jump_label_key rps_needed __read_mostly;
struct static_key rps_needed __read_mostly;
static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
@ -2945,7 +2945,7 @@ int netif_rx(struct sk_buff *skb)
trace_netif_rx(skb);
#ifdef CONFIG_RPS
if (static_branch(&rps_needed)) {
if (static_key_false(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu;
@ -3309,7 +3309,7 @@ int netif_receive_skb(struct sk_buff *skb)
return NET_RX_SUCCESS;
#ifdef CONFIG_RPS
if (static_branch(&rps_needed)) {
if (static_key_false(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu, ret;

4
net/core/net-sysfs.c
View File

@ -608,10 +608,10 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
spin_unlock(&rps_map_lock);
if (map)
jump_label_inc(&rps_needed);
static_key_slow_inc(&rps_needed);
if (old_map) {
kfree_rcu(old_map, rcu);
jump_label_dec(&rps_needed);
static_key_slow_dec(&rps_needed);
}
free_cpumask_var(mask);
return len;

4
net/core/sock.c
View File

@ -111,7 +111,7 @@
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
#include <linux/jump_label.h>
#include <linux/static_key.h>
#include <linux/memcontrol.h>
#include <asm/uaccess.h>
@ -184,7 +184,7 @@ void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
struct jump_label_key memcg_socket_limit_enabled;
struct static_key memcg_socket_limit_enabled;
EXPORT_SYMBOL(memcg_socket_limit_enabled);
/*

4
net/core/sysctl_net_core.c
View File

@ -69,9 +69,9 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write,
if (sock_table != orig_sock_table) {
rcu_assign_pointer(rps_sock_flow_table, sock_table);
if (sock_table)
jump_label_inc(&rps_needed);
static_key_slow_inc(&rps_needed);
if (orig_sock_table) {
jump_label_dec(&rps_needed);
static_key_slow_dec(&rps_needed);
synchronize_rcu();
vfree(orig_sock_table);
}

6
net/ipv4/tcp_memcontrol.c
View File

@ -111,7 +111,7 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
if (val != RESOURCE_MAX)
jump_label_dec(&memcg_socket_limit_enabled);
static_key_slow_dec(&memcg_socket_limit_enabled);
}
EXPORT_SYMBOL(tcp_destroy_cgroup);
@ -143,9 +143,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
net->ipv4.sysctl_tcp_mem[i]);
if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX)
jump_label_dec(&memcg_socket_limit_enabled);
static_key_slow_dec(&memcg_socket_limit_enabled);
else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
jump_label_inc(&memcg_socket_limit_enabled);
static_key_slow_inc(&memcg_socket_limit_enabled);
return 0;
}

6
net/netfilter/core.c
View File

@ -56,7 +56,7 @@ struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly;
EXPORT_SYMBOL(nf_hooks);
#if defined(CONFIG_JUMP_LABEL)
struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
EXPORT_SYMBOL(nf_hooks_needed);
#endif
@ -77,7 +77,7 @@ int nf_register_hook(struct nf_hook_ops *reg)
list_add_rcu(&reg->list, elem->list.prev);
mutex_unlock(&nf_hook_mutex);
#if defined(CONFIG_JUMP_LABEL)
jump_label_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
#endif
return 0;
}
@ -89,7 +89,7 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
list_del_rcu(&reg->list);
mutex_unlock(&nf_hook_mutex);
#if defined(CONFIG_JUMP_LABEL)
jump_label_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
#endif
synchronize_net();
}

84
tools/perf/Documentation/Makefile
View File

@ -1,3 +1,10 @@
OUTPUT := ./
ifeq ("$(origin O)", "command line")
ifneq ($(O),)
OUTPUT := $(O)/
endif
endif
MAN1_TXT= \
$(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \
$(wildcard perf-*.txt)) \
@ -6,10 +13,11 @@ MAN5_TXT=
MAN7_TXT=
MAN_TXT = $(MAN1_TXT) $(MAN5_TXT) $(MAN7_TXT)
MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT))
_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT))
DOC_HTML=$(MAN_HTML)
MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML))
MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML))
ARTICLES =
# with their own formatting rules.
@ -18,11 +26,17 @@ API_DOCS = $(patsubst %.txt,%,$(filter-out technical/api-index-skel.txt technica
SP_ARTICLES += $(API_DOCS)
SP_ARTICLES += technical/api-index
DOC_HTML += $(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
_DOC_HTML = $(_MAN_HTML)
_DOC_HTML+=$(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES))
DOC_HTML=$(addprefix $(OUTPUT),$(_DOC_HTML))
DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
_DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT))
_DOC_MAN5=$(patsubst %.txt,%.5,$(MAN5_TXT))
_DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT))
DOC_MAN1=$(addprefix $(OUTPUT),$(_DOC_MAN1))
DOC_MAN5=$(addprefix $(OUTPUT),$(_DOC_MAN5))
DOC_MAN7=$(addprefix $(OUTPUT),$(_DOC_MAN7))
# Make the path relative to DESTDIR, not prefix
ifndef DESTDIR
@ -150,9 +164,9 @@ man1: $(DOC_MAN1)
man5: $(DOC_MAN5)
man7: $(DOC_MAN7)
info: perf.info perfman.info
info: $(OUTPUT)perf.info $(OUTPUT)perfman.info
pdf: user-manual.pdf
pdf: $(OUTPUT)user-manual.pdf
install: install-man
@ -166,7 +180,7 @@ install-man: man
install-info: info
$(INSTALL) -d -m 755 $(DESTDIR)$(infodir)
$(INSTALL) -m 644 perf.info perfman.info $(DESTDIR)$(infodir)
$(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir)
if test -r $(DESTDIR)$(infodir)/dir; then \
$(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\
$(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\
@ -176,7 +190,7 @@ install-info: info
install-pdf: pdf
$(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
$(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
$(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir)
#install-html: html
# '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
@ -189,14 +203,14 @@ install-pdf: pdf
#
# Determine "include::" file references in asciidoc files.
#
doc.dep : $(wildcard *.txt) build-docdep.perl
$(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl
$(QUIET_GEN)$(RM) $@+ $@ && \
$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
mv $@+ $@
-include doc.dep
-include $(OUPTUT)doc.dep
cmds_txt = cmds-ancillaryinterrogators.txt \
_cmds_txt = cmds-ancillaryinterrogators.txt \
cmds-ancillarymanipulators.txt \
cmds-mainporcelain.txt \
cmds-plumbinginterrogators.txt \
@ -205,32 +219,36 @@ cmds_txt = cmds-ancillaryinterrogators.txt \
cmds-synchelpers.txt \
cmds-purehelpers.txt \
cmds-foreignscminterface.txt
cmds_txt=$(addprefix $(OUTPUT),$(_cmds_txt))
$(cmds_txt): cmd-list.made
$(cmds_txt): $(OUTPUT)cmd-list.made
cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
$(OUTPUT)cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT)
$(QUIET_GEN)$(RM) $@ && \
$(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \
date >$@
clean:
$(RM) *.xml *.xml+ *.html *.html+ *.1 *.5 *.7
$(RM) *.texi *.texi+ *.texi++ perf.info perfman.info
$(RM) howto-index.txt howto/*.html doc.dep
$(RM) technical/api-*.html technical/api-index.txt
$(RM) $(cmds_txt) *.made
$(RM) $(MAN_XML) $(addsuffix +,$(MAN_XML))
$(RM) $(MAN_HTML) $(addsuffix +,$(MAN_HTML))
$(RM) $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7)
$(RM) $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++
$(RM) $(OUTPUT)perf.info $(OUTPUT)perfman.info
$(RM) $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep
$(RM) $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt
$(RM) $(cmds_txt) $(OUTPUT)*.made
$(MAN_HTML): %.html : %.txt
$(MAN_HTML): $(OUTPUT)%.html : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
$(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
mv $@+ $@
%.1 %.5 %.7 : %.xml
$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
$(QUIET_XMLTO)$(RM) $@ && \
xmlto -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
xmlto -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
%.xml : %.txt
$(OUTPUT)%.xml : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
$(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
@ -239,25 +257,25 @@ $(MAN_HTML): %.html : %.txt
XSLT = docbook.xsl
XSLTOPTS = --xinclude --stringparam html.stylesheet docbook-xsl.css
user-manual.html: user-manual.xml
$(OUTPUT)user-manual.html: $(OUTPUT)user-manual.xml
$(QUIET_XSLTPROC)xsltproc $(XSLTOPTS) -o $@ $(XSLT) $<
perf.info: user-manual.texi
$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ user-manual.texi
$(OUTPUT)perf.info: $(OUTPUT)user-manual.texi
$(QUIET_MAKEINFO)$(MAKEINFO) --no-split -o $@ $(OUTPUT)user-manual.texi
user-manual.texi: user-manual.xml
$(OUTPUT)user-manual.texi: $(OUTPUT)user-manual.xml
$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
$(DOCBOOK2X_TEXI) user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
$(DOCBOOK2X_TEXI) $(OUTPUT)user-manual.xml --encoding=UTF-8 --to-stdout >$@++ && \
$(PERL_PATH) fix-texi.perl <$@++ >$@+ && \
rm $@++ && \
mv $@+ $@
user-manual.pdf: user-manual.xml
$(OUTPUT)user-manual.pdf: $(OUTPUT)user-manual.xml
$(QUIET_DBLATEX)$(RM) $@+ $@ && \
$(DBLATEX) -o $@+ -p /etc/asciidoc/dblatex/asciidoc-dblatex.xsl -s /etc/asciidoc/dblatex/asciidoc-dblatex.sty $< && \
mv $@+ $@
perfman.texi: $(MAN_XML) cat-texi.perl
$(OUTPUT)perfman.texi: $(MAN_XML) cat-texi.perl
$(QUIET_DB2TEXI)$(RM) $@+ $@ && \
($(foreach xml,$(MAN_XML),$(DOCBOOK2X_TEXI) --encoding=UTF-8 \
--to-stdout $(xml) &&) true) > $@++ && \
@ -265,7 +283,7 @@ perfman.texi: $(MAN_XML) cat-texi.perl
rm $@++ && \
mv $@+ $@
perfman.info: perfman.texi
$(OUTPUT)perfman.info: $(OUTPUT)perfman.texi
$(QUIET_MAKEINFO)$(MAKEINFO) --no-split --no-validate $*.texi
$(patsubst %.txt,%.texi,$(MAN_TXT)): %.texi : %.xml

20
tools/perf/Documentation/perf-lock.txt
View File

@ -8,7 +8,7 @@ perf-lock - Analyze lock events
SYNOPSIS
--------
[verse]
'perf lock' {record|report|trace}
'perf lock' {record|report|script|info}
DESCRIPTION
-----------
@ -20,10 +20,13 @@ and statistics with this 'perf lock' command.
produces the file "perf.data" which contains tracing
results of lock events.
'perf lock trace' shows raw lock events.
'perf lock report' reports statistical data.
'perf lock script' shows raw lock events.
'perf lock info' shows metadata like threads or addresses
of lock instances.
COMMON OPTIONS
--------------
@ -47,6 +50,17 @@ REPORT OPTIONS
Sorting key. Possible values: acquired (default), contended,
wait_total, wait_max, wait_min.
INFO OPTIONS
------------
-t::
--threads::
dump thread list in perf.data
-m::
--map::
dump map of lock instances (address:name table)
SEE ALSO
--------
linkperf:perf[1]

38
tools/perf/Documentation/perf-record.txt
View File

@ -52,11 +52,15 @@ OPTIONS
-p::
--pid=::
Record events on existing process ID.
Record events on existing process ID (comma separated list).
-t::
--tid=::
Record events on existing thread ID.
Record events on existing thread ID (comma separated list).
-u::
--uid=::
Record events in threads owned by uid. Name or number.
-r::
--realtime=::
@ -148,6 +152,36 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha
corresponding events, i.e., they always refer to events defined earlier on the command
line.
-b::
--branch-any::
Enable taken branch stack sampling. Any type of taken branch may be sampled.
This is a shortcut for --branch-filter any. See --branch-filter for more infos.
-j::
--branch-filter::
Enable taken branch stack sampling. Each sample captures a series of consecutive
taken branches. The number of branches captured with each sample depends on the
underlying hardware, the type of branches of interest, and the executed code.
It is possible to select the types of branches captured by enabling filters. The
following filters are defined:
- any: any type of branches
- any_call: any function call or system call
- any_ret: any function return or system call return
- any_ind: any indirect branch
- u: only when the branch target is at the user level
- k: only when the branch target is in the kernel
- hv: only when the target is at the hypervisor level
+
The option requires at least one branch type among any, any_call, any_ret, ind_call.
The privilege levels may be ommitted, in which case, the privilege levels of the associated
event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
levels are subject to permissions. When sampling on multiple events, branch stack sampling
is enabled for all the sampling events. The sampled branch type is the same for all events.
The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
Note that this feature may not be available on all processors.
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]

10
tools/perf/Documentation/perf-report.txt
View File

@ -153,6 +153,16 @@ OPTIONS
information which may be very large and thus may clutter the display.
It currently includes: cpu and numa topology of the host system.
-b::
--branch-stack::
Use the addresses of sampled taken branches instead of the instruction
address to build the histograms. To generate meaningful output, the
perf.data file must have been obtained using perf record -b or
perf record --branch-filter xxx where xxx is a branch filter option.
perf report is able to auto-detect whether a perf.data file contains
branch stacks and it will automatically switch to the branch view mode,
unless --no-branch-stack is used.
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-annotate[1]

5
tools/perf/Documentation/perf-script.txt
View File

@ -115,7 +115,7 @@ OPTIONS
-f::
--fields::
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr.
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace
@ -200,6 +200,9 @@ OPTIONS
It currently includes: cpu and numa topology of the host system.
It can only be used with the perf script report mode.
--show-kernel-path::
Try to resolve the path of [kernel.kallsyms]
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],

4
tools/perf/Documentation/perf-stat.txt
View File

@ -35,11 +35,11 @@ OPTIONS
child tasks do not inherit counters
-p::
--pid=<pid>::
stat events on existing process id
stat events on existing process id (comma separated list)
-t::
--tid=<tid>::
stat events on existing thread id
stat events on existing thread id (comma separated list)
-a::

8
tools/perf/Documentation/perf-top.txt
View File

@ -72,11 +72,15 @@ Default is to monitor all CPUS.
-p <pid>::
--pid=<pid>::
Profile events on existing Process ID.
Profile events on existing Process ID (comma separated list).
-t <tid>::
--tid=<tid>::
Profile events on existing thread ID.
Profile events on existing thread ID (comma separated list).
-u::
--uid=::
Record events in threads owned by uid. Name or number.
-r <priority>::
--realtime=<priority>::

1
tools/perf/MANIFEST
View File

@ -9,6 +9,7 @@ lib/rbtree.c
include/linux/swab.h
arch/*/include/asm/unistd*.h
arch/*/lib/memcpy*.S
arch/*/lib/memset*.S
include/linux/poison.h
include/linux/magic.h
include/linux/hw_breakpoint.h

26
tools/perf/Makefile
View File

@ -15,6 +15,16 @@ endif
# Define V to have a more verbose compile.
#
# Define O to save output files in a separate directory.
#
# Define ARCH as name of target architecture if you want cross-builds.
#
# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds.
#
# Define NO_LIBPERL to disable perl script extension.
#
# Define NO_LIBPYTHON to disable python script extension.
#
# Define PYTHON to point to the python binary if the default
# `python' is not correct; for example: PYTHON=python2
#
@ -32,6 +42,10 @@ endif
# Define NO_DWARF if you do not want debug-info analysis feature at all.
#
# Define WERROR=0 to disable treating any warnings as errors.
#
# Define NO_NEWT if you do not want TUI support.
#
# Define NO_DEMANGLE if you do not want C++ symbol demangling.
$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@ -61,7 +75,7 @@ ifeq ($(ARCH),x86_64)
ifeq (${IS_X86_64}, 1)
RAW_ARCH := x86_64
ARCH_CFLAGS := -DARCH_X86_64
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
endif
@ -183,7 +197,10 @@ SCRIPT_SH += perf-archive.sh
grep-libs = $(filter -l%,$(1))
strip-libs = $(filter-out -l%,$(1))
$(OUTPUT)python/perf.so: $(PYRF_OBJS)
PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
$(OUTPUT)python/perf.so: $(PYRF_OBJS) $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
--quiet build_ext; \
mkdir -p $(OUTPUT)python && \
@ -258,6 +275,7 @@ LIB_H += util/callchain.h
LIB_H += util/build-id.h
LIB_H += util/debug.h
LIB_H += util/debugfs.h
LIB_H += util/sysfs.h
LIB_H += util/event.h
LIB_H += util/evsel.h
LIB_H += util/evlist.h
@ -304,6 +322,7 @@ LIB_OBJS += $(OUTPUT)util/build-id.o
LIB_OBJS += $(OUTPUT)util/config.o
LIB_OBJS += $(OUTPUT)util/ctype.o
LIB_OBJS += $(OUTPUT)util/debugfs.o
LIB_OBJS += $(OUTPUT)util/sysfs.o
LIB_OBJS += $(OUTPUT)util/environment.o
LIB_OBJS += $(OUTPUT)util/event.o
LIB_OBJS += $(OUTPUT)util/evlist.o
@ -361,8 +380,10 @@ BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
ifeq ($(RAW_ARCH),x86_64)
BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
endif
BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
@ -794,7 +815,6 @@ help:
@echo ' quick-install-html - install the html documentation quickly'
@echo ''
@echo 'Perf maintainer targets:'
@echo ' distclean - alias to clean'
@echo ' clean - clean all binary objects and build output'
doc:

Some files were not shown because too many files have changed in this diff Show More