You've already forked linux-apfs
mirror of
https://github.com/linux-apfs/linux-apfs.git
synced 2026-05-01 15:00:59 -07:00
Merge branch 'perf/core-v3' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into perf/hw_breakpoints
Pull AMD range breakpoints support from Frederic Weisbecker:
" - Extend breakpoint tools and core to support address range through perf
event with initial backend support for AMD extended breakpoints.
Syntax is:
perf record -e mem:addr/len:type
For example set write breakpoint from 0x1000 to 0x1200 (0x1000 + 512)
perf record -e mem:0x1000/512:w
- Clean up a bit breakpoint code validation
It has been acked by Jiri and Oleg. "
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar
@@ -174,6 +174,7 @@
|
||||
#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */
|
||||
#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
|
||||
#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */
|
||||
#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */
|
||||
#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */
|
||||
|
||||
/*
|
||||
@@ -383,6 +384,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
|
||||
#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16)
|
||||
#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU)
|
||||
#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT)
|
||||
#define cpu_has_bpext boot_cpu_has(X86_FEATURE_BPEXT)
|
||||
|
||||
#if __GNUC__ >= 4
|
||||
extern void warn_pre_alternatives(void);
|
||||
|
||||
@@ -114,5 +114,10 @@ static inline void debug_stack_usage_inc(void) { }
|
||||
static inline void debug_stack_usage_dec(void) { }
|
||||
#endif /* X86_64 */
|
||||
|
||||
#ifdef CONFIG_CPU_SUP_AMD
|
||||
extern void set_dr_addr_mask(unsigned long mask, int dr);
|
||||
#else
|
||||
static inline void set_dr_addr_mask(unsigned long mask, int dr) { }
|
||||
#endif
|
||||
|
||||
#endif /* _ASM_X86_DEBUGREG_H */
|
||||
|
||||
@@ -12,6 +12,7 @@
|
||||
*/
|
||||
struct arch_hw_breakpoint {
|
||||
unsigned long address;
|
||||
unsigned long mask;
|
||||
u8 len;
|
||||
u8 type;
|
||||
};
|
||||
|
||||
@@ -177,6 +177,9 @@ struct x86_pmu_capability {
|
||||
#define IBS_CAPS_BRNTRGT (1U<<5)
|
||||
#define IBS_CAPS_OPCNTEXT (1U<<6)
|
||||
#define IBS_CAPS_RIPINVALIDCHK (1U<<7)
|
||||
#define IBS_CAPS_OPBRNFUSE (1U<<8)
|
||||
#define IBS_CAPS_FETCHCTLEXTD (1U<<9)
|
||||
#define IBS_CAPS_OPDATA4 (1U<<10)
|
||||
|
||||
#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
|
||||
| IBS_CAPS_FETCHSAM \
|
||||
|
||||
@@ -206,11 +206,16 @@
|
||||
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
|
||||
#define MSR_AMD64_IBSCTL 0xc001103a
|
||||
#define MSR_AMD64_IBSBRTARGET 0xc001103b
|
||||
#define MSR_AMD64_IBSOPDATA4 0xc001103d
|
||||
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
|
||||
|
||||
/* Fam 16h MSRs */
|
||||
#define MSR_F16H_L2I_PERF_CTL 0xc0010230
|
||||
#define MSR_F16H_L2I_PERF_CTR 0xc0010231
|
||||
#define MSR_F16H_DR1_ADDR_MASK 0xc0011019
|
||||
#define MSR_F16H_DR2_ADDR_MASK 0xc001101a
|
||||
#define MSR_F16H_DR3_ADDR_MASK 0xc001101b
|
||||
#define MSR_F16H_DR0_ADDR_MASK 0xc0011027
|
||||
|
||||
/* Fam 15h MSRs */
|
||||
#define MSR_F15H_PERF_CTL 0xc0010200
|
||||
|
||||
@@ -870,3 +870,22 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
void set_dr_addr_mask(unsigned long mask, int dr)
|
||||
{
|
||||
if (!cpu_has_bpext)
|
||||
return;
|
||||
|
||||
switch (dr) {
|
||||
case 0:
|
||||
wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
|
||||
break;
|
||||
case 1:
|
||||
case 2:
|
||||
case 3:
|
||||
wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -253,6 +253,10 @@ struct cpu_hw_events {
|
||||
#define INTEL_UEVENT_CONSTRAINT(c, n) \
|
||||
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
|
||||
|
||||
/* Like UEVENT_CONSTRAINT, but match flags too */
|
||||
#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \
|
||||
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
|
||||
|
||||
#define INTEL_PLD_CONSTRAINT(c, n) \
|
||||
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
|
||||
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
|
||||
|
||||
@@ -565,6 +565,21 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
|
||||
perf_ibs->offset_max,
|
||||
offset + 1);
|
||||
} while (offset < offset_max);
|
||||
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
|
||||
/*
|
||||
* Read IbsBrTarget and IbsOpData4 separately
|
||||
* depending on their availability.
|
||||
* Can't add to offset_max as they are staggered
|
||||
*/
|
||||
if (ibs_caps & IBS_CAPS_BRNTRGT) {
|
||||
rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++);
|
||||
size++;
|
||||
}
|
||||
if (ibs_caps & IBS_CAPS_OPDATA4) {
|
||||
rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++);
|
||||
size++;
|
||||
}
|
||||
}
|
||||
ibs_data.size = sizeof(u64) * size;
|
||||
|
||||
regs = *iregs;
|
||||
|
||||
@@ -552,18 +552,18 @@ int intel_pmu_drain_bts_buffer(void)
|
||||
* PEBS
|
||||
*/
|
||||
struct event_constraint intel_core2_pebs_event_constraints[] = {
|
||||
INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
|
||||
INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
|
||||
INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
|
||||
INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
|
||||
INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
|
||||
EVENT_CONSTRAINT_END
|
||||
};
|
||||
|
||||
struct event_constraint intel_atom_pebs_event_constraints[] = {
|
||||
INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
|
||||
INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
|
||||
INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
|
||||
EVENT_CONSTRAINT_END
|
||||
};
|
||||
|
||||
@@ -577,36 +577,36 @@ struct event_constraint intel_slm_pebs_event_constraints[] = {
|
||||
|
||||
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
|
||||
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
|
||||
INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
|
||||
INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
|
||||
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
|
||||
INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
|
||||
INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
|
||||
INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
|
||||
INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
|
||||
EVENT_CONSTRAINT_END
|
||||
};
|
||||
|
||||
struct event_constraint intel_westmere_pebs_event_constraints[] = {
|
||||
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
|
||||
INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
|
||||
INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
|
||||
INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
|
||||
INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
|
||||
INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
|
||||
EVENT_CONSTRAINT_END
|
||||
};
|
||||
|
||||
struct event_constraint intel_snb_pebs_event_constraints[] = {
|
||||
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
|
||||
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
|
||||
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
|
||||
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
|
||||
@@ -617,7 +617,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
|
||||
};
|
||||
|
||||
struct event_constraint intel_ivb_pebs_event_constraints[] = {
|
||||
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
|
||||
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
|
||||
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
|
||||
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
|
||||
@@ -628,7 +628,7 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
|
||||
};
|
||||
|
||||
struct event_constraint intel_hsw_pebs_event_constraints[] = {
|
||||
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
|
||||
INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
|
||||
INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */
|
||||
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
|
||||
INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
|
||||
@@ -886,6 +886,29 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
|
||||
regs.bp = pebs->bp;
|
||||
regs.sp = pebs->sp;
|
||||
|
||||
if (sample_type & PERF_SAMPLE_REGS_INTR) {
|
||||
regs.ax = pebs->ax;
|
||||
regs.bx = pebs->bx;
|
||||
regs.cx = pebs->cx;
|
||||
regs.dx = pebs->dx;
|
||||
regs.si = pebs->si;
|
||||
regs.di = pebs->di;
|
||||
regs.bp = pebs->bp;
|
||||
regs.sp = pebs->sp;
|
||||
|
||||
regs.flags = pebs->flags;
|
||||
#ifndef CONFIG_X86_32
|
||||
regs.r8 = pebs->r8;
|
||||
regs.r9 = pebs->r9;
|
||||
regs.r10 = pebs->r10;
|
||||
regs.r11 = pebs->r11;
|
||||
regs.r12 = pebs->r12;
|
||||
regs.r13 = pebs->r13;
|
||||
regs.r14 = pebs->r14;
|
||||
regs.r15 = pebs->r15;
|
||||
#endif
|
||||
}
|
||||
|
||||
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
|
||||
regs.ip = pebs->real_ip;
|
||||
regs.flags |= PERF_EFLAGS_EXACT;
|
||||
|
||||
@@ -449,7 +449,11 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = {
|
||||
static struct uncore_event_desc snbep_uncore_imc_events[] = {
|
||||
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
|
||||
{ /* end: all zeroes */ },
|
||||
};
|
||||
|
||||
@@ -2036,7 +2040,11 @@ static struct intel_uncore_type hswep_uncore_ha = {
|
||||
static struct uncore_event_desc hswep_uncore_imc_events[] = {
|
||||
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
|
||||
INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
|
||||
{ /* end: all zeroes */ },
|
||||
};
|
||||
|
||||
|
||||
@@ -126,6 +126,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
|
||||
*dr7 |= encode_dr7(i, info->len, info->type);
|
||||
|
||||
set_debugreg(*dr7, 7);
|
||||
if (info->mask)
|
||||
set_dr_addr_mask(info->mask, i);
|
||||
|
||||
return 0;
|
||||
}
|
||||
@@ -161,29 +163,8 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
|
||||
*dr7 &= ~__encode_dr7(i, info->len, info->type);
|
||||
|
||||
set_debugreg(*dr7, 7);
|
||||
}
|
||||
|
||||
static int get_hbp_len(u8 hbp_len)
|
||||
{
|
||||
unsigned int len_in_bytes = 0;
|
||||
|
||||
switch (hbp_len) {
|
||||
case X86_BREAKPOINT_LEN_1:
|
||||
len_in_bytes = 1;
|
||||
break;
|
||||
case X86_BREAKPOINT_LEN_2:
|
||||
len_in_bytes = 2;
|
||||
break;
|
||||
case X86_BREAKPOINT_LEN_4:
|
||||
len_in_bytes = 4;
|
||||
break;
|
||||
#ifdef CONFIG_X86_64
|
||||
case X86_BREAKPOINT_LEN_8:
|
||||
len_in_bytes = 8;
|
||||
break;
|
||||
#endif
|
||||
}
|
||||
return len_in_bytes;
|
||||
if (info->mask)
|
||||
set_dr_addr_mask(0, i);
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -196,7 +177,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
|
||||
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
|
||||
|
||||
va = info->address;
|
||||
len = get_hbp_len(info->len);
|
||||
len = bp->attr.bp_len;
|
||||
|
||||
return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
|
||||
}
|
||||
@@ -277,6 +258,8 @@ static int arch_build_bp_info(struct perf_event *bp)
|
||||
}
|
||||
|
||||
/* Len */
|
||||
info->mask = 0;
|
||||
|
||||
switch (bp->attr.bp_len) {
|
||||
case HW_BREAKPOINT_LEN_1:
|
||||
info->len = X86_BREAKPOINT_LEN_1;
|
||||
@@ -293,11 +276,17 @@ static int arch_build_bp_info(struct perf_event *bp)
|
||||
break;
|
||||
#endif
|
||||
default:
|
||||
return -EINVAL;
|
||||
if (!is_power_of_2(bp->attr.bp_len))
|
||||
return -EINVAL;
|
||||
if (!cpu_has_bpext)
|
||||
return -EOPNOTSUPP;
|
||||
info->mask = bp->attr.bp_len - 1;
|
||||
info->len = X86_BREAKPOINT_LEN_1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Validate the arch-specific HW Breakpoint register settings
|
||||
*/
|
||||
@@ -312,11 +301,11 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
ret = -EINVAL;
|
||||
|
||||
switch (info->len) {
|
||||
case X86_BREAKPOINT_LEN_1:
|
||||
align = 0;
|
||||
if (info->mask)
|
||||
align = info->mask;
|
||||
break;
|
||||
case X86_BREAKPOINT_LEN_2:
|
||||
align = 1;
|
||||
@@ -330,7 +319,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
|
||||
break;
|
||||
#endif
|
||||
default:
|
||||
return ret;
|
||||
WARN_ON_ONCE(1);
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
+20
-17
@@ -79,7 +79,7 @@ struct perf_branch_stack {
|
||||
struct perf_branch_entry entries[0];
|
||||
};
|
||||
|
||||
struct perf_regs_user {
|
||||
struct perf_regs {
|
||||
__u64 abi;
|
||||
struct pt_regs *regs;
|
||||
};
|
||||
@@ -580,34 +580,40 @@ extern u64 perf_event_read_value(struct perf_event *event,
|
||||
|
||||
|
||||
struct perf_sample_data {
|
||||
u64 type;
|
||||
/*
|
||||
* Fields set by perf_sample_data_init(), group so as to
|
||||
* minimize the cachelines touched.
|
||||
*/
|
||||
u64 addr;
|
||||
struct perf_raw_record *raw;
|
||||
struct perf_branch_stack *br_stack;
|
||||
u64 period;
|
||||
u64 weight;
|
||||
u64 txn;
|
||||
union perf_mem_data_src data_src;
|
||||
|
||||
/*
|
||||
* The other fields, optionally {set,used} by
|
||||
* perf_{prepare,output}_sample().
|
||||
*/
|
||||
u64 type;
|
||||
u64 ip;
|
||||
struct {
|
||||
u32 pid;
|
||||
u32 tid;
|
||||
} tid_entry;
|
||||
u64 time;
|
||||
u64 addr;
|
||||
u64 id;
|
||||
u64 stream_id;
|
||||
struct {
|
||||
u32 cpu;
|
||||
u32 reserved;
|
||||
} cpu_entry;
|
||||
u64 period;
|
||||
union perf_mem_data_src data_src;
|
||||
struct perf_callchain_entry *callchain;
|
||||
struct perf_raw_record *raw;
|
||||
struct perf_branch_stack *br_stack;
|
||||
struct perf_regs_user regs_user;
|
||||
struct perf_regs regs_user;
|
||||
struct perf_regs regs_intr;
|
||||
u64 stack_user_size;
|
||||
u64 weight;
|
||||
/*
|
||||
* Transaction flags for abort events:
|
||||
*/
|
||||
u64 txn;
|
||||
};
|
||||
} ____cacheline_aligned;
|
||||
|
||||
/* default value for data source */
|
||||
#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\
|
||||
@@ -624,9 +630,6 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
|
||||
data->raw = NULL;
|
||||
data->br_stack = NULL;
|
||||
data->period = period;
|
||||
data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
|
||||
data->regs_user.regs = NULL;
|
||||
data->stack_user_size = 0;
|
||||
data->weight = 0;
|
||||
data->data_src.val = PERF_MEM_NA;
|
||||
data->txn = 0;
|
||||
|
||||
@@ -137,8 +137,9 @@ enum perf_event_sample_format {
|
||||
PERF_SAMPLE_DATA_SRC = 1U << 15,
|
||||
PERF_SAMPLE_IDENTIFIER = 1U << 16,
|
||||
PERF_SAMPLE_TRANSACTION = 1U << 17,
|
||||
PERF_SAMPLE_REGS_INTR = 1U << 18,
|
||||
|
||||
PERF_SAMPLE_MAX = 1U << 18, /* non-ABI */
|
||||
PERF_SAMPLE_MAX = 1U << 19, /* non-ABI */
|
||||
};
|
||||
|
||||
/*
|
||||
@@ -238,6 +239,7 @@ enum perf_event_read_format {
|
||||
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
|
||||
#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */
|
||||
/* add: sample_stack_user */
|
||||
#define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */
|
||||
|
||||
/*
|
||||
* Hardware event_id to monitor via a performance monitoring event:
|
||||
@@ -334,6 +336,15 @@ struct perf_event_attr {
|
||||
|
||||
/* Align to u64. */
|
||||
__u32 __reserved_2;
|
||||
/*
|
||||
* Defines set of regs to dump for each sample
|
||||
* state captured on:
|
||||
* - precise = 0: PMU interrupt
|
||||
* - precise > 0: sampled instruction
|
||||
*
|
||||
* See asm/perf_regs.h for details.
|
||||
*/
|
||||
__u64 sample_regs_intr;
|
||||
};
|
||||
|
||||
#define perf_flags(attr) (*(&(attr)->read_format + 1))
|
||||
@@ -686,6 +697,8 @@ enum perf_event_type {
|
||||
* { u64 weight; } && PERF_SAMPLE_WEIGHT
|
||||
* { u64 data_src; } && PERF_SAMPLE_DATA_SRC
|
||||
* { u64 transaction; } && PERF_SAMPLE_TRANSACTION
|
||||
* { u64 abi; # enum perf_sample_regs_abi
|
||||
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
|
||||
* };
|
||||
*/
|
||||
PERF_RECORD_SAMPLE = 9,
|
||||
|
||||
+51
-9
@@ -4460,7 +4460,7 @@ perf_output_sample_regs(struct perf_output_handle *handle,
|
||||
}
|
||||
}
|
||||
|
||||
static void perf_sample_regs_user(struct perf_regs_user *regs_user,
|
||||
static void perf_sample_regs_user(struct perf_regs *regs_user,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
if (!user_mode(regs)) {
|
||||
@@ -4471,11 +4471,22 @@ static void perf_sample_regs_user(struct perf_regs_user *regs_user,
|
||||
}
|
||||
|
||||
if (regs) {
|
||||
regs_user->regs = regs;
|
||||
regs_user->abi = perf_reg_abi(current);
|
||||
regs_user->regs = regs;
|
||||
} else {
|
||||
regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
|
||||
regs_user->regs = NULL;
|
||||
}
|
||||
}
|
||||
|
||||
static void perf_sample_regs_intr(struct perf_regs *regs_intr,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
regs_intr->regs = regs;
|
||||
regs_intr->abi = perf_reg_abi(current);
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* Get remaining task size from user stack pointer.
|
||||
*
|
||||
@@ -4857,6 +4868,23 @@ void perf_output_sample(struct perf_output_handle *handle,
|
||||
if (sample_type & PERF_SAMPLE_TRANSACTION)
|
||||
perf_output_put(handle, data->txn);
|
||||
|
||||
if (sample_type & PERF_SAMPLE_REGS_INTR) {
|
||||
u64 abi = data->regs_intr.abi;
|
||||
/*
|
||||
* If there are no regs to dump, notice it through
|
||||
* first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
|
||||
*/
|
||||
perf_output_put(handle, abi);
|
||||
|
||||
if (abi) {
|
||||
u64 mask = event->attr.sample_regs_intr;
|
||||
|
||||
perf_output_sample_regs(handle,
|
||||
data->regs_intr.regs,
|
||||
mask);
|
||||
}
|
||||
}
|
||||
|
||||
if (!event->attr.watermark) {
|
||||
int wakeup_events = event->attr.wakeup_events;
|
||||
|
||||
@@ -4922,12 +4950,13 @@ void perf_prepare_sample(struct perf_event_header *header,
|
||||
header->size += size;
|
||||
}
|
||||
|
||||
if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
|
||||
perf_sample_regs_user(&data->regs_user, regs);
|
||||
|
||||
if (sample_type & PERF_SAMPLE_REGS_USER) {
|
||||
/* regs dump ABI info */
|
||||
int size = sizeof(u64);
|
||||
|
||||
perf_sample_regs_user(&data->regs_user, regs);
|
||||
|
||||
if (data->regs_user.regs) {
|
||||
u64 mask = event->attr.sample_regs_user;
|
||||
size += hweight64(mask) * sizeof(u64);
|
||||
@@ -4943,15 +4972,11 @@ void perf_prepare_sample(struct perf_event_header *header,
|
||||
* in case new sample type is added, because we could eat
|
||||
* up the rest of the sample size.
|
||||
*/
|
||||
struct perf_regs_user *uregs = &data->regs_user;
|
||||
u16 stack_size = event->attr.sample_stack_user;
|
||||
u16 size = sizeof(u64);
|
||||
|
||||
if (!uregs->abi)
|
||||
perf_sample_regs_user(uregs, regs);
|
||||
|
||||
stack_size = perf_sample_ustack_size(stack_size, header->size,
|
||||
uregs->regs);
|
||||
data->regs_user.regs);
|
||||
|
||||
/*
|
||||
* If there is something to dump, add space for the dump
|
||||
@@ -4964,6 +4989,21 @@ void perf_prepare_sample(struct perf_event_header *header,
|
||||
data->stack_user_size = stack_size;
|
||||
header->size += size;
|
||||
}
|
||||
|
||||
if (sample_type & PERF_SAMPLE_REGS_INTR) {
|
||||
/* regs dump ABI info */
|
||||
int size = sizeof(u64);
|
||||
|
||||
perf_sample_regs_intr(&data->regs_intr, regs);
|
||||
|
||||
if (data->regs_intr.regs) {
|
||||
u64 mask = event->attr.sample_regs_intr;
|
||||
|
||||
size += hweight64(mask) * sizeof(u64);
|
||||
}
|
||||
|
||||
header->size += size;
|
||||
}
|
||||
}
|
||||
|
||||
static void perf_event_output(struct perf_event *event,
|
||||
@@ -7151,6 +7191,8 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
|
||||
ret = -EINVAL;
|
||||
}
|
||||
|
||||
if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
|
||||
ret = perf_reg_validate(attr->sample_regs_intr);
|
||||
out:
|
||||
return ret;
|
||||
|
||||
|
||||
@@ -2,6 +2,8 @@ PERF-CFLAGS
|
||||
PERF-GUI-VARS
|
||||
PERF-VERSION-FILE
|
||||
perf
|
||||
perf-read-vdso32
|
||||
perf-read-vdsox32
|
||||
perf-help
|
||||
perf-record
|
||||
perf-report
|
||||
|
||||
@@ -33,12 +33,15 @@ OPTIONS
|
||||
- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
|
||||
hexadecimal event descriptor.
|
||||
|
||||
- a hardware breakpoint event in the form of '\mem:addr[:access]'
|
||||
- a hardware breakpoint event in the form of '\mem:addr[/len][:access]'
|
||||
where addr is the address in memory you want to break in.
|
||||
Access is the memory access type (read, write, execute) it can
|
||||
be passed as follows: '\mem:addr[:[r][w][x]]'.
|
||||
be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range,
|
||||
number of bytes from specified addr, which the breakpoint will cover.
|
||||
If you want to profile read-write accesses in 0x1000, just set
|
||||
'mem:0x1000:rw'.
|
||||
If you want to profile write accesses in [0x1000~1008), just set
|
||||
'mem:0x1000/8:w'.
|
||||
|
||||
--filter=<filter>::
|
||||
Event filter.
|
||||
@@ -214,6 +217,12 @@ if combined with -a or -C options.
|
||||
After starting the program, wait msecs before measuring. This is useful to
|
||||
filter out the startup phase of the program, which is often very different.
|
||||
|
||||
-I::
|
||||
--intr-regs::
|
||||
Capture machine state (registers) at interrupt, i.e., on counter overflows for
|
||||
each sample. List of captured registers depends on the architecture. This option
|
||||
is off by default.
|
||||
|
||||
SEE ALSO
|
||||
--------
|
||||
linkperf:perf-stat[1], linkperf:perf-list[1]
|
||||
|
||||
@@ -60,6 +60,15 @@ include config/utilities.mak
|
||||
#
|
||||
# Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
|
||||
# for dwarf backtrace post unwind.
|
||||
#
|
||||
# Define NO_PERF_READ_VDSO32 if you do not want to build perf-read-vdso32
|
||||
# for reading the 32-bit compatibility VDSO in 64-bit mode
|
||||
#
|
||||
# Define NO_PERF_READ_VDSOX32 if you do not want to build perf-read-vdsox32
|
||||
# for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode
|
||||
#
|
||||
# Define NO_ZLIB if you do not want to support compressed kernel modules
|
||||
|
||||
|
||||
ifeq ($(srctree),)
|
||||
srctree := $(patsubst %/,%,$(dir $(shell pwd)))
|
||||
@@ -171,11 +180,16 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
|
||||
|
||||
SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
|
||||
|
||||
#
|
||||
# Single 'perf' binary right now:
|
||||
#
|
||||
PROGRAMS += $(OUTPUT)perf
|
||||
|
||||
ifndef NO_PERF_READ_VDSO32
|
||||
PROGRAMS += $(OUTPUT)perf-read-vdso32
|
||||
endif
|
||||
|
||||
ifndef NO_PERF_READ_VDSOX32
|
||||
PROGRAMS += $(OUTPUT)perf-read-vdsox32
|
||||
endif
|
||||
|
||||
# what 'all' will build and 'install' will install, in perfexecdir
|
||||
ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
|
||||
|
||||
@@ -247,12 +261,14 @@ LIB_H += util/annotate.h
|
||||
LIB_H += util/cache.h
|
||||
LIB_H += util/callchain.h
|
||||
LIB_H += util/build-id.h
|
||||
LIB_H += util/db-export.h
|
||||
LIB_H += util/debug.h
|
||||
LIB_H += util/pmu.h
|
||||
LIB_H += util/event.h
|
||||
LIB_H += util/evsel.h
|
||||
LIB_H += util/evlist.h
|
||||
LIB_H += util/exec_cmd.h
|
||||
LIB_H += util/find-vdso-map.c
|
||||
LIB_H += util/levenshtein.h
|
||||
LIB_H += util/machine.h
|
||||
LIB_H += util/map.h
|
||||
@@ -304,6 +320,7 @@ LIB_H += ui/util.h
|
||||
LIB_H += ui/ui.h
|
||||
LIB_H += util/data.h
|
||||
LIB_H += util/kvm-stat.h
|
||||
LIB_H += util/thread-stack.h
|
||||
|
||||
LIB_OBJS += $(OUTPUT)util/abspath.o
|
||||
LIB_OBJS += $(OUTPUT)util/alias.o
|
||||
@@ -311,6 +328,7 @@ LIB_OBJS += $(OUTPUT)util/annotate.o
|
||||
LIB_OBJS += $(OUTPUT)util/build-id.o
|
||||
LIB_OBJS += $(OUTPUT)util/config.o
|
||||
LIB_OBJS += $(OUTPUT)util/ctype.o
|
||||
LIB_OBJS += $(OUTPUT)util/db-export.o
|
||||
LIB_OBJS += $(OUTPUT)util/pmu.o
|
||||
LIB_OBJS += $(OUTPUT)util/environment.o
|
||||
LIB_OBJS += $(OUTPUT)util/event.o
|
||||
@@ -380,6 +398,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
|
||||
LIB_OBJS += $(OUTPUT)util/data.o
|
||||
LIB_OBJS += $(OUTPUT)util/tsc.o
|
||||
LIB_OBJS += $(OUTPUT)util/cloexec.o
|
||||
LIB_OBJS += $(OUTPUT)util/thread-stack.o
|
||||
|
||||
LIB_OBJS += $(OUTPUT)ui/setup.o
|
||||
LIB_OBJS += $(OUTPUT)ui/helpline.o
|
||||
@@ -478,8 +497,6 @@ ifneq ($(OUTPUT),)
|
||||
endif
|
||||
|
||||
ifdef NO_LIBELF
|
||||
EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
|
||||
|
||||
# Remove ELF/DWARF dependent codes
|
||||
LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS))
|
||||
LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS))
|
||||
@@ -568,6 +585,10 @@ ifndef NO_LIBNUMA
|
||||
BUILTIN_OBJS += $(OUTPUT)bench/numa.o
|
||||
endif
|
||||
|
||||
ifndef NO_ZLIB
|
||||
LIB_OBJS += $(OUTPUT)util/zlib.o
|
||||
endif
|
||||
|
||||
ifdef ASCIIDOC8
|
||||
export ASCIIDOC8
|
||||
endif
|
||||
@@ -732,6 +753,16 @@ $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Uti
|
||||
$(OUTPUT)perf-%: %.o $(PERFLIBS)
|
||||
$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
|
||||
|
||||
ifndef NO_PERF_READ_VDSO32
|
||||
$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c
|
||||
$(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
|
||||
endif
|
||||
|
||||
ifndef NO_PERF_READ_VDSOX32
|
||||
$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
|
||||
$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
|
||||
endif
|
||||
|
||||
$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
|
||||
$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
|
||||
|
||||
@@ -876,6 +907,14 @@ install-bin: all install-gtk
|
||||
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
|
||||
$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
|
||||
$(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'
|
||||
ifndef NO_PERF_READ_VDSO32
|
||||
$(call QUIET_INSTALL, perf-read-vdso32) \
|
||||
$(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)';
|
||||
endif
|
||||
ifndef NO_PERF_READ_VDSOX32
|
||||
$(call QUIET_INSTALL, perf-read-vdsox32) \
|
||||
$(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)';
|
||||
endif
|
||||
$(call QUIET_INSTALL, libexec) \
|
||||
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
|
||||
$(call QUIET_INSTALL, perf-archive) \
|
||||
@@ -928,7 +967,7 @@ config-clean:
|
||||
|
||||
clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
|
||||
$(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
|
||||
$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
|
||||
$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
|
||||
$(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
|
||||
$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
|
||||
$(python-clean)
|
||||
|
||||
@@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
|
||||
* yet used)
|
||||
* -1 in case of errors
|
||||
*/
|
||||
static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
|
||||
static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
|
||||
{
|
||||
int rc = -1;
|
||||
Dwfl *dwfl;
|
||||
@@ -156,15 +156,27 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
|
||||
Dwarf_Addr end = pc;
|
||||
bool signalp;
|
||||
|
||||
dwfl = dwfl_begin(&offline_callbacks);
|
||||
if (!dwfl) {
|
||||
pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
|
||||
return -1;
|
||||
}
|
||||
dwfl = dso->dwfl;
|
||||
|
||||
if (dwfl_report_offline(dwfl, "", exec_file, -1) == NULL) {
|
||||
pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
|
||||
goto out;
|
||||
if (!dwfl) {
|
||||
dwfl = dwfl_begin(&offline_callbacks);
|
||||
if (!dwfl) {
|
||||
pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) {
|
||||
pr_debug("dwfl_report_offline() failed %s\n",
|
||||
dwarf_errmsg(-1));
|
||||
/*
|
||||
* We normally cache the DWARF debug info and never
|
||||
* call dwfl_end(). But to prevent fd leak, free in
|
||||
* case of error.
|
||||
*/
|
||||
dwfl_end(dwfl);
|
||||
goto out;
|
||||
}
|
||||
dso->dwfl = dwfl;
|
||||
}
|
||||
|
||||
mod = dwfl_addrmodule(dwfl, pc);
|
||||
@@ -194,7 +206,6 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
|
||||
rc = check_return_reg(ra_regno, frame);
|
||||
|
||||
out:
|
||||
dwfl_end(dwfl);
|
||||
return rc;
|
||||
}
|
||||
|
||||
@@ -221,8 +232,7 @@ out:
|
||||
* index: of callchain entry that needs to be ignored (if any)
|
||||
* -1 if no entry needs to be ignored or in case of errors
|
||||
*/
|
||||
int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
|
||||
struct ip_callchain *chain)
|
||||
int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
|
||||
{
|
||||
struct addr_location al;
|
||||
struct dso *dso = NULL;
|
||||
@@ -235,7 +245,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
|
||||
|
||||
ip = chain->ips[2];
|
||||
|
||||
thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
|
||||
thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
|
||||
MAP__FUNCTION, ip, &al);
|
||||
|
||||
if (al.map)
|
||||
@@ -246,7 +256,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
|
||||
return skip_slot;
|
||||
}
|
||||
|
||||
rc = check_return_addr(dso->long_name, ip);
|
||||
rc = check_return_addr(dso, ip);
|
||||
|
||||
pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
|
||||
dso->long_name, chain->nr, ip, rc);
|
||||
|
||||
@@ -357,6 +357,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
|
||||
static struct perf_tool tool = {
|
||||
.sample = diff__process_sample_event,
|
||||
.mmap = perf_event__process_mmap,
|
||||
.mmap2 = perf_event__process_mmap2,
|
||||
.comm = perf_event__process_comm,
|
||||
.exit = perf_event__process_exit,
|
||||
.fork = perf_event__process_fork,
|
||||
|
||||
@@ -217,8 +217,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
|
||||
goto repipe;
|
||||
}
|
||||
|
||||
thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
|
||||
sample->ip, &al);
|
||||
thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
|
||||
|
||||
if (al.map != NULL) {
|
||||
if (!al.map->dso->hit) {
|
||||
@@ -410,6 +409,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
|
||||
.tracing_data = perf_event__repipe_op2_synth,
|
||||
.finished_round = perf_event__repipe_op2_synth,
|
||||
.build_id = perf_event__repipe_op2_synth,
|
||||
.id_index = perf_event__repipe_op2_synth,
|
||||
},
|
||||
.input_name = "-",
|
||||
.samples = LIST_HEAD_INIT(inject.samples),
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user