Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 6480c561 authored by Ingo Molnar's avatar Ingo Molnar
Browse files

Merge tag 'perf-core-for-mingo' of...

Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf

 into perf/core

Pull perf/core improvements and fixes from Jiri Olsa:

  * Add libdw DWARF post unwind support for ARM (Jean Pihet)

  * Consolidate types.h for ARM and ARM64 (Jean Pihet)

  * Fix possible null pointer dereference in session.c (Masanari Iida)

  * Cleanup, remove unused variables in map_switch_event() (Dongsheng Yang)

  * Remove nr_state_machine_bugs in perf latency (Dongsheng Yang)

  * Remove usage of trace_sched_wakeup(.success) (Peter Zijlstra)

Signed-off-by: default avatarJiri Olsa <jolsa@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parents 722e76e6 97eac381
Loading
Loading
Loading
Loading
+1 −1
Original line number Diff line number Diff line
@@ -411,7 +411,7 @@ LIB_OBJS += $(OUTPUT)tests/code-reading.o
LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
ifndef NO_DWARF_UNWIND
ifeq ($(ARCH),x86)
ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o
endif
endif
+7 −0
Original line number Diff line number Diff line
@@ -5,3 +5,10 @@ endif
ifndef NO_LIBUNWIND
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
endif
ifndef NO_LIBDW_DWARF_UNWIND
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
endif
ifndef NO_DWARF_UNWIND
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
endif
+6 −1
Original line number Diff line number Diff line
@@ -2,10 +2,15 @@
#define ARCH_PERF_REGS_H

#include <stdlib.h>
#include "../../util/types.h"
#include <linux/types.h>
#include <asm/perf_regs.h>

void perf_regs_load(u64 *regs);

#define PERF_REGS_MASK	((1ULL << PERF_REG_ARM_MAX) - 1)
#define PERF_REGS_MAX	PERF_REG_ARM_MAX
#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32

#define PERF_REG_IP	PERF_REG_ARM_PC
#define PERF_REG_SP	PERF_REG_ARM_SP

+60 −0
Original line number Diff line number Diff line
#include <string.h>
#include "perf_regs.h"
#include "thread.h"
#include "map.h"
#include "event.h"
#include "tests/tests.h"

#define STACK_SIZE 8192

static int sample_ustack(struct perf_sample *sample,
			 struct thread *thread, u64 *regs)
{
	struct stack_dump *stack = &sample->user_stack;
	struct map *map;
	unsigned long sp;
	u64 stack_size, *buf;

	buf = malloc(STACK_SIZE);
	if (!buf) {
		pr_debug("failed to allocate sample uregs data\n");
		return -1;
	}

	sp = (unsigned long) regs[PERF_REG_ARM_SP];

	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
	if (!map) {
		pr_debug("failed to get stack map\n");
		free(buf);
		return -1;
	}

	stack_size = map->end - sp;
	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;

	memcpy(buf, (void *) sp, stack_size);
	stack->data = (char *) buf;
	stack->size = stack_size;
	return 0;
}

int test__arch_unwind_sample(struct perf_sample *sample,
			     struct thread *thread)
{
	struct regs_dump *regs = &sample->user_regs;
	u64 *buf;

	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
	if (!buf) {
		pr_debug("failed to allocate sample uregs data\n");
		return -1;
	}

	perf_regs_load(buf);
	regs->abi  = PERF_SAMPLE_REGS_ABI;
	regs->regs = buf;
	regs->mask = PERF_REGS_MASK;

	return sample_ustack(sample, thread, buf);
}
+58 −0
Original line number Diff line number Diff line
#include <linux/linkage.h>

#define R0 0x00
#define R1 0x08
#define R2 0x10
#define R3 0x18
#define R4 0x20
#define R5 0x28
#define R6 0x30
#define R7 0x38
#define R8 0x40
#define R9 0x48
#define SL 0x50
#define FP 0x58
#define IP 0x60
#define SP 0x68
#define LR 0x70
#define PC 0x78

/*
 * Implementation of void perf_regs_load(u64 *regs);
 *
 * This functions fills in the 'regs' buffer from the actual registers values,
 * in the way the perf built-in unwinding test expects them:
 * - the PC at the time at the call to this function. Since this function
 *   is called using a bl instruction, the PC value is taken from LR.
 * The built-in unwinding test then unwinds the call stack from the dwarf
 * information in unwind__get_entries.
 *
 * Notes:
 * - the 8 bytes stride in the registers offsets comes from the fact
 * that the registers are stored in an u64 array (u64 *regs),
 * - the regs buffer needs to be zeroed before the call to this function,
 * in this case using a calloc in dwarf-unwind.c.
 */

.text
.type perf_regs_load,%function
ENTRY(perf_regs_load)
	str r0, [r0, #R0]
	str r1, [r0, #R1]
	str r2, [r0, #R2]
	str r3, [r0, #R3]
	str r4, [r0, #R4]
	str r5, [r0, #R5]
	str r6, [r0, #R6]
	str r7, [r0, #R7]
	str r8, [r0, #R8]
	str r9, [r0, #R9]
	str sl, [r0, #SL]
	str fp, [r0, #FP]
	str ip, [r0, #IP]
	str sp, [r0, #SP]
	str lr, [r0, #LR]
	str lr, [r0, #PC]	// store pc as lr in order to skip the call
	                        //  to this function
	mov pc, lr
ENDPROC(perf_regs_load)
Loading