xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
複製 0
程式碼 問題管理 合併請求 Actions Packages Projects 版本發佈 Wiki Activity

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

瀏覽代碼 
Pull perf fixes from Ingo Molnar:
 "A bit larger than what I'd wish for - half of it is due to hw driver
  updates to Intel Ivy-Bridge which info got recently released,
  cycles:pp should work there now too, amongst other things.  (but we
  are generally making exceptions for hardware enablement of this type.)

  There are also callchain fixes in it - responding to mostly
  theoretical (but valid) concerns.  The tooling side sports perf.data
  endianness/portability fixes which did not make it for the merge
  window - and various other fixes as well."

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  perf/x86: Check user address explicitly in copy_from_user_nmi()
  perf/x86: Check if user fp is valid
  perf: Limit callchains to 127
  perf/x86: Allow multiple stacks
  perf/x86: Update SNB PEBS constraints
  perf/x86: Enable/Add IvyBridge hardware support
  perf/x86: Implement cycles:p for SNB/IVB
  perf/x86: Fix Intel shared extra MSR allocation
  x86/decoder: Fix bsr/bsf/jmpe decoding with operand-size prefix
  perf: Remove duplicate invocation on perf_event_for_each
  perf uprobes: Remove unnecessary check before strlist__delete
  perf symbols: Check for valid dso before creating map
  perf evsel: Fix 32 bit values endianity swap for sample_id_all header
  perf session: Handle endianity swap on sample_id_all header data
  perf symbols: Handle different endians properly during symbol load
  perf evlist: Pass third argument to ioctl explicitly
  perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP
  perf tools: Make --version show kernel version instead of pull req tag
  perf tools: Check if callchain is corrupted
  perf callchain: Make callchain cursors TLS
  ...
This commit is contained in:
Linus Torvalds
2012-06-08 09:14:46 -07:00
父節點 03d8f54082 db0dc75d64
當前提交 106544d81d
共有 29 個文件被更改，包括 357 次插入 和 120 次删除
Download Patch File Download Diff File Expand all files Collapse all files

11
arch/x86/kernel/cpu/perf_event.c
查看文件

@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
if (!cpuc->shared_regs)
goto error;
}
cpuc->is_fake = 1;
return cpuc;
error:
free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
}
static inline int
valid_user_frame(const void __user *fp, unsigned long size)
{
return (__range_not_ok(fp, size, TASK_SIZE) == 0);
}
#ifdef CONFIG_COMPAT
#include <asm/compat.h>
@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
if (bytes != sizeof(frame))
break;
if (fp < compat_ptr(regs->sp))
if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
if (bytes != sizeof(frame))
break;
if ((unsigned long)fp < regs->sp)
if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);

2
arch/x86/kernel/cpu/perf_event.h
查看文件

@@ -117,6 +117,7 @@ struct cpu_hw_events {
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
unsigned int group_flag;
int is_fake;
/*
* Intel DebugStore bits
@@ -364,6 +365,7 @@ struct x86_pmu {
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
/*
* Intel LBR

145
arch/x86/kernel/cpu/perf_event_intel.c
查看文件

@@ -1119,27 +1119,33 @@ intel_bts_constraints(struct perf_event *event)
return NULL;
}
static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
static int intel_alt_er(int idx)
{
if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
return false;
return idx;
if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= 0x01bb;
event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
} else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
if (idx == EXTRA_REG_RSP_0)
return EXTRA_REG_RSP_1;
if (idx == EXTRA_REG_RSP_1)
return EXTRA_REG_RSP_0;
return idx;
}
static void intel_fixup_er(struct perf_event *event, int idx)
{
event->hw.extra_reg.idx = idx;
if (idx == EXTRA_REG_RSP_0) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= 0x01b7;
event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
} else if (idx == EXTRA_REG_RSP_1) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= 0x01bb;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
}
if (event->hw.extra_reg.idx == orig_idx)
return false;
return true;
}
/*
@@ -1157,14 +1163,18 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
struct event_constraint *c = &emptyconstraint;
struct er_account *era;
unsigned long flags;
int orig_idx = reg->idx;
int idx = reg->idx;
/* already allocated shared msr */
if (reg->alloc)
/*
* reg->alloc can be set due to existing state, so for fake cpuc we
* need to ignore this, otherwise we might fail to allocate proper fake
* state for this extra reg constraint. Also see the comment below.
*/
if (reg->alloc && !cpuc->is_fake)
return NULL; /* call x86_get_event_constraint() */
again:
era = &cpuc->shared_regs->regs[reg->idx];
era = &cpuc->shared_regs->regs[idx];
/*
* we use spin_lock_irqsave() to avoid lockdep issues when
* passing a fake cpuc
@@ -1173,6 +1183,29 @@ again:
if (!atomic_read(&era->ref) || era->config == reg->config) {
/*
* If its a fake cpuc -- as per validate_{group,event}() we
* shouldn't touch event state and we can avoid doing so
* since both will only call get_event_constraints() once
* on each event, this avoids the need for reg->alloc.
*
* Not doing the ER fixup will only result in era->reg being
* wrong, but since we won't actually try and program hardware
* this isn't a problem either.
*/
if (!cpuc->is_fake) {
if (idx != reg->idx)
intel_fixup_er(event, idx);
/*
* x86_schedule_events() can call get_event_constraints()
* multiple times on events in the case of incremental
* scheduling(). reg->alloc ensures we only do the ER
* allocation once.
*/
reg->alloc = 1;
}
/* lock in msr value */
era->config = reg->config;
era->reg = reg->reg;
@@ -1180,17 +1213,17 @@ again:
/* one more user */
atomic_inc(&era->ref);
/* no need to reallocate during incremental event scheduling */
reg->alloc = 1;
/*
* need to call x86_get_event_constraint()
* to check if associated event has constraints
*/
c = NULL;
} else if (intel_try_alt_er(event, orig_idx)) {
raw_spin_unlock_irqrestore(&era->lock, flags);
goto again;
} else {
idx = intel_alt_er(idx);
if (idx != reg->idx) {
raw_spin_unlock_irqrestore(&era->lock, flags);
goto again;
}
}
raw_spin_unlock_irqrestore(&era->lock, flags);
@@ -1204,11 +1237,14 @@ __intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc,
struct er_account *era;
/*
* only put constraint if extra reg was actually
* allocated. Also takes care of event which do
* not use an extra shared reg
* Only put constraint if extra reg was actually allocated. Also takes
* care of event which do not use an extra shared reg.
*
* Also, if this is a fake cpuc we shouldn't touch any event state
* (reg->alloc) and we don't care about leaving inconsistent cpuc state
* either since it'll be thrown out.
*/
if (!reg->alloc)
if (!reg->alloc || cpuc->is_fake)
return;
era = &cpuc->shared_regs->regs[reg->idx];
@@ -1300,15 +1336,9 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
intel_put_shared_regs_event_constraints(cpuc, event);
}
static int intel_pmu_hw_config(struct perf_event *event)
static void intel_pebs_aliases_core2(struct perf_event *event)
{
int ret = x86_pmu_hw_config(event);
if (ret)
return ret;
if (event->attr.precise_ip &&
(event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
* Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
* (0x003c) so that we can use it with PEBS.
@@ -1329,10 +1359,48 @@ static int intel_pmu_hw_config(struct perf_event *event)
*/
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;
}
}
static void intel_pebs_aliases_snb(struct perf_event *event)
{
if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
* Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
* (0x003c) so that we can use it with PEBS.
*
* The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
* PEBS capable. However we can use UOPS_RETIRED.ALL
* (0x01c2), which is a PEBS capable event, to get the same
* count.
*
* UOPS_RETIRED.ALL counts the number of cycles that retires
* CNTMASK micro-ops. By setting CNTMASK to a value (16)
* larger than the maximum number of micro-ops that can be
* retired per cycle (4) and then inverting the condition, we
* count all cycles that retire 16 or less micro-ops, which
* is every cycle.
*
* Thereby we gain a PEBS capable cycle counter.
*/
u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
}
}
static int intel_pmu_hw_config(struct perf_event *event)
{
int ret = x86_pmu_hw_config(event);
if (ret)
return ret;
if (event->attr.precise_ip && x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event);
if (intel_pmu_needs_lbr_smpl(event)) {
ret = intel_pmu_setup_lbr_filter(event);
@@ -1607,6 +1675,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
.pebs_aliases = intel_pebs_aliases_core2,
.format_attrs = intel_arch3_formats_attr,
@@ -1840,8 +1909,9 @@ __init int intel_pmu_init(void)
break;
case 42: /* SandyBridge */
x86_add_quirk(intel_sandybridge_quirk);
case 45: /* SandyBridge, "Romely-EP" */
x86_add_quirk(intel_sandybridge_quirk);
case 58: /* IvyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -1849,6 +1919,7 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
x86_pmu.extra_regs = intel_snb_extra_regs;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;

9
arch/x86/kernel/cpu/perf_event_intel_ds.c
查看文件

@@ -400,14 +400,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */