Commit 56edab31 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branches 'perf-urgent-for-linus' and 'perf-core-for-linus' of... 

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

Pull perf fixes from Ingo Molnar:

 - Leftover AMD PMU driver fix fix from the end of the v3.4
   stabilization cycle.

 - Late tools/perf/ changes that missed the first round:
    * endianness fixes
    * event parsing improvements
    * libtraceevent fixes factored out from trace-cmd
    * perl scripting engine fixes related to libtraceevent,
    * testcase improvements
    * perf inject / pipe mode fixes
    * plus a kernel side fix

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86: Update event scheduling constraints for AMD family 15h models

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Revert "sched, perf: Use a single callback into the scheduler"
  perf evlist: Show event attribute details
  perf tools: Bump default sample freq to 4 kHz
  perf buildid-list: Work better with pipe mode
  perf tools: Fix piped mode read code
  perf inject: Fix broken perf inject -b
  perf tools: rename HEADER_TRACE_INFO to HEADER_TRACING_DATA
  perf tools: Add union u64_swap type for swapping u64 data
  perf tools: Carry perf_event_attr bitfield throught different endians
  perf record: Fix documentation for branch stack sampling
  perf target: Add cpu flag to sample_type if target has cpu
  perf tools: Always try to build libtraceevent
  perf tools: Rename libparsevent to libtraceevent in Makefile
  perf script: Rename struct event to struct event_format in perl engine
  perf script: Explicitly handle known default print arg type
  perf tools: Add hardcoded name term for pmu events
  perf tools: Separate 'mem:' event scanner bits
  perf tools: Use allocated list for each parsed event
  perf tools: Add support for displaying event parser debug info
  perf test: Move parse event automated tests to separated object
parents 3813d402 5bcdf5e4 ab0cce56

arch/x86/kernel/cpu/perf_event_amd.c

+10 −1
Original line number Diff line number Diff line
@@ -496,6 +496,7 @@ static __initconst const struct x86_pmu amd_pmu = { 
 * 0x023	DE	PERF_CTL[2:0]

 * 0x02D	LS	PERF_CTL[3]

 * 0x02E	LS	PERF_CTL[3,0]

 * 0x031	LS	PERF_CTL[2:0] (**)

 * 0x043	CU	PERF_CTL[2:0]

 * 0x045	CU	PERF_CTL[2:0]

 * 0x046	CU	PERF_CTL[2:0]
@@ -509,10 +510,12 @@ static __initconst const struct x86_pmu amd_pmu = { 
 * 0x0DD	LS	PERF_CTL[5:0]

 * 0x0DE	LS	PERF_CTL[5:0]

 * 0x0DF	LS	PERF_CTL[5:0]

 * 0x1C0	EX	PERF_CTL[5:3]

 * 0x1D6	EX	PERF_CTL[5:0]

 * 0x1D8	EX	PERF_CTL[5:0]

 *

 * (*)  depending on the umask all FPU counters may be used

 * (**) only one unitmask enabled at a time

 */



static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -562,6 +565,12 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev 
			return &amd_f15_PMC3;

		case 0x02E:

			return &amd_f15_PMC30;

		case 0x031:

			if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)

				return &amd_f15_PMC20;

			return &emptyconstraint;

		case 0x1C0:

			return &amd_f15_PMC53;

		default:

			return &amd_f15_PMC50;

		}

include/linux/perf_event.h

+18 −6
Original line number Diff line number Diff line
@@ -1084,7 +1084,9 @@ extern void perf_pmu_unregister(struct pmu *pmu); 


extern int perf_num_counters(void);

extern const char *perf_pmu_name(void);

extern void __perf_event_task_sched(struct task_struct *prev,

extern void __perf_event_task_sched_in(struct task_struct *prev,

				       struct task_struct *task);

extern void __perf_event_task_sched_out(struct task_struct *prev,

					struct task_struct *next);

extern int perf_event_init_task(struct task_struct *child);

extern void perf_event_exit_task(struct task_struct *child);
@@ -1205,13 +1207,20 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) 


extern struct static_key_deferred perf_sched_events;



static inline void perf_event_task_sched(struct task_struct *prev,

static inline void perf_event_task_sched_in(struct task_struct *prev,

					    struct task_struct *task)

{

	if (static_key_false(&perf_sched_events.key))

		__perf_event_task_sched_in(prev, task);

}



static inline void perf_event_task_sched_out(struct task_struct *prev,

					     struct task_struct *next)

{

	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);



	if (static_key_false(&perf_sched_events.key))

		__perf_event_task_sched(prev, task);

		__perf_event_task_sched_out(prev, next);

}



extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -1286,8 +1295,11 @@ extern void perf_event_disable(struct perf_event *event); 
extern void perf_event_task_tick(void);

#else

static inline void

perf_event_task_sched(struct task_struct *prev,

perf_event_task_sched_in(struct task_struct *prev,

			 struct task_struct *task)			{ }

static inline void

perf_event_task_sched_out(struct task_struct *prev,

			  struct task_struct *next)			{ }

static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }

static inline void perf_event_exit_task(struct task_struct *child)	{ }

static inline void perf_event_free_task(struct task_struct *task)	{ }

kernel/events/core.c

+4 −10
Original line number Diff line number Diff line
@@ -2039,7 +2039,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, 
 * accessing the event control register. If a NMI hits, then it will

 * not restart the event.

 */

static void __perf_event_task_sched_out(struct task_struct *task,

void __perf_event_task_sched_out(struct task_struct *task,

				 struct task_struct *next)

{

	int ctxn;
@@ -2279,7 +2279,7 @@ static void perf_branch_stack_sched_in(struct task_struct *prev, 
 * accessing the event control register. If a NMI hits, then it will

 * keep the event running.

 */

static void __perf_event_task_sched_in(struct task_struct *prev,

void __perf_event_task_sched_in(struct task_struct *prev,

				struct task_struct *task)

{

	struct perf_event_context *ctx;
@@ -2305,12 +2305,6 @@ static void __perf_event_task_sched_in(struct task_struct *prev, 
		perf_branch_stack_sched_in(prev, task);

}



void __perf_event_task_sched(struct task_struct *prev, struct task_struct *next)

{

	__perf_event_task_sched_out(prev, next);

	__perf_event_task_sched_in(prev, next);

}



static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)

{

	u64 frequency = event->attr.sample_freq;

kernel/sched/core.c

+8 −1
Original line number Diff line number Diff line
@@ -1912,7 +1912,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, 
		    struct task_struct *next)

{

	sched_info_switch(prev, next);

	perf_event_task_sched(prev, next);

	perf_event_task_sched_out(prev, next);

	fire_sched_out_preempt_notifiers(prev, next);

	prepare_lock_switch(rq, next);

	prepare_arch_switch(next);
@@ -1955,6 +1955,13 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) 
	 */

	prev_state = prev->state;

	finish_arch_switch(prev);

#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW

	local_irq_disable();

#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */

	perf_event_task_sched_in(prev, current);

#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW

	local_irq_enable();

#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */

	finish_lock_switch(rq, prev);

	finish_arch_post_lock_switch();

tools/perf/Documentation/perf-evlist.txt

+8 −0
Original line number Diff line number Diff line
@@ -20,6 +20,14 @@ OPTIONS 
--input=::

        Input file name. (default: perf.data unless stdin is a fifo)



-F::

--freq=::

	Show just the sample frequency used for each event.



-v::

--verbose=::

	Show all fields.



SEE ALSO

--------

linkperf:perf-record[1], linkperf:perf-list[1],

CRA Git | Maintained and supported by SUSTech CRA and CCSE