From: Ingo Molnar <mingo@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Arnaldo Carvalho de Melo <acme@infradead.org>,
Thomas Gleixner <tglx@linutronix.de>,
Andrew Morton <akpm@linux-foundation.org>
Subject: [GIT PULL] perf fixes
Date: Fri, 8 Jun 2012 11:20:02 +0200 [thread overview]
Message-ID: <20120608092002.GA12129@gmail.com> (raw)
Linus,
Please pull the latest perf-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
HEAD: db0dc75d6403b6663c0eab4c6ccb672eb9b2ed72 perf/x86: Check user address explicitly in copy_from_user_nmi()
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.
Thanks,
Ingo
------------------>
Arnaldo Carvalho de Melo (5):
perf report: Use the right symbol for annotation
perf annotate browser: Fix help window entry for navigating to hottest line
perf stat: Initialize default events wrt exclude_{guest,host}
perf tools: Fix make tarballs
perf tools: Make --version show kernel version instead of pull req tag
Arun Sharma (4):
perf/x86: Allow multiple stacks
perf: Limit callchains to 127
perf/x86: Check if user fp is valid
perf/x86: Check user address explicitly in copy_from_user_nmi()
Avik Sil (1):
perf tools: Fix pager on minimal-install embedded systems
David Ahern (1):
perf script: Fix regression in callchain dso name
Jiri Olsa (3):
perf symbols: Handle different endians properly during symbol load
perf session: Handle endianity swap on sample_id_all header data
perf evsel: Fix 32 bit values endianity swap for sample_id_all header
Masami Hiramatsu (1):
x86/decoder: Fix bsr/bsf/jmpe decoding with operand-size prefix
Namhyung Kim (5):
perf callchain: Make callchain cursors TLS
perf tools: Check if callchain is corrupted
perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP
perf evlist: Pass third argument to ioctl explicitly
perf: Remove duplicate invocation on perf_event_for_each
Peter Zijlstra (4):
perf/x86: Fix Intel shared extra MSR allocation
perf/x86: Implement cycles:p for SNB/IVB
perf/x86: Enable/Add IvyBridge hardware support
perf/x86: Update SNB PEBS constraints
Srikar Dronamraju (2):
perf symbols: Check for valid dso before creating map
perf uprobes: Remove unnecessary check before strlist__delete
arch/x86/include/asm/uaccess.h | 12 +--
arch/x86/kernel/cpu/perf_event.c | 11 ++-
arch/x86/kernel/cpu/perf_event.h | 2 +
arch/x86/kernel/cpu/perf_event_intel.c | 145 ++++++++++++++++++++++--------
arch/x86/kernel/cpu/perf_event_intel_ds.c | 9 +-
arch/x86/lib/usercopy.c | 4 +
arch/x86/lib/x86-opcode-map.txt | 8 +-
arch/x86/tools/gen-insn-attr-x86.awk | 14 +--
include/linux/perf_event.h | 4 +-
kernel/events/core.c | 1 -
tools/perf/MANIFEST | 2 +
tools/perf/builtin-report.c | 4 +-
tools/perf/builtin-stat.c | 8 +-
tools/perf/builtin-top.c | 2 +-
tools/perf/design.txt | 7 +-
tools/perf/ui/browsers/annotate.c | 2 +-
tools/perf/util/PERF-VERSION-GEN | 2 +-
tools/perf/util/callchain.c | 2 +
tools/perf/util/callchain.h | 2 +
tools/perf/util/evlist.c | 17 +++-
tools/perf/util/evlist.h | 4 +
tools/perf/util/evsel.c | 29 ++++--
tools/perf/util/hist.c | 7 +-
tools/perf/util/hist.h | 2 -
| 4 +
tools/perf/util/probe-event.c | 8 +-
tools/perf/util/session.c | 97 +++++++++++++++-----
tools/perf/util/symbol.c | 38 +++++++-
tools/perf/util/symbol.h | 30 +++++++
29 files changed, 357 insertions(+), 120 deletions(-)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 04cd688..e1f3a17 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,9 +33,8 @@
#define segment_eq(a, b) ((a).seg == (b).seg)
#define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr) \
- ((unsigned long __force)(addr) < \
- (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) \
+ ((unsigned long __force)(addr) < user_addr_max())
/*
* Test whether a block of memory is a valid user space address.
@@ -47,14 +46,14 @@
* This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
*/
-#define __range_not_ok(addr, size) \
+#define __range_not_ok(addr, size, limit) \
({ \
unsigned long flag, roksum; \
__chk_user_ptr(addr); \
asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \
: "=&r" (flag), "=r" (roksum) \
: "1" (addr), "g" ((long)(size)), \
- "rm" (current_thread_info()->addr_limit.seg)); \
+ "rm" (limit)); \
flag; \
})
@@ -77,7 +76,8 @@
* checks that the pointer is in the user space range - after calling
* this function, memory access functions may still return -EFAULT.
*/
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+ (likely(__range_not_ok(addr, size, user_addr_max()) == 0))
/*
* The exception table consists of pairs of addresses relative to the
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e049d6d..c4706cf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -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);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6638aaf..7241e2f 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -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
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 166546e..187c294 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -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;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5a3edc2..35e2192 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -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 */
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index f61ee67..677b1ed 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -8,6 +8,7 @@
#include <linux/module.h>
#include <asm/word-at-a-time.h>
+#include <linux/sched.h>
/*
* best effort, GUP based copy_from_user() that is NMI-safe
@@ -21,6 +22,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
void *map;
int ret;
+ if (__range_not_ok(from, n, TASK_SIZE) == 0)
+ return len;
+
do {
ret = __get_user_pages_fast(addr, 1, 0, &page);
if (!ret)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 8191379..5d7e51f 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -28,7 +28,7 @@
# - (66): the last prefix is 0x66
# - (F3): the last prefix is 0xF3
# - (F2): the last prefix is 0xF2
-#
+# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
Table: one byte opcode
Referrer:
@@ -515,12 +515,12 @@ b4: LFS Gv,Mp
b5: LGS Gv,Mp
b6: MOVZX Gv,Eb
b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
b9: Grp10 (1A)
ba: Grp8 Ev,Ib (1A)
bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
be: MOVSX Gv,Eb
bf: MOVSX Gv,Ew
# 0x0f 0xc0-0xcf
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5f6a5b6..ddcf39b 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -66,9 +66,10 @@ BEGIN {
rex_expr = "^REX(\\.[XRWB]+)*"
fpu_expr = "^ESC" # TODO
- lprefix1_expr = "\\(66\\)"
+ lprefix1_expr = "\\((66|!F3)\\)"
lprefix2_expr = "\\(F3\\)"
- lprefix3_expr = "\\(F2\\)"
+ lprefix3_expr = "\\((F2|!F3)\\)"
+ lprefix_expr = "\\((66|F2|F3)\\)"
max_lprefix = 4
# All opcodes starting with lower-case 'v' or with (v1) superscript
@@ -333,13 +334,16 @@ function convert_operands(count,opnd, i,j,imm,mod)
if (match(ext, lprefix1_expr)) {
lptable1[idx] = add_flags(lptable1[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix2_expr)) {
+ }
+ if (match(ext, lprefix2_expr)) {
lptable2[idx] = add_flags(lptable2[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix3_expr)) {
+ }
+ if (match(ext, lprefix3_expr)) {
lptable3[idx] = add_flags(lptable3[idx],flags)
variant = "INAT_VARIANT"
- } else {
+ }
+ if (!match(ext, lprefix_expr)){
table[idx] = add_flags(table[idx],flags)
}
}
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f325786..45db49f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -555,6 +555,8 @@ enum perf_event_type {
PERF_RECORD_MAX, /* non-ABI */
};
+#define PERF_MAX_STACK_DEPTH 127
+
enum perf_callchain_context {
PERF_CONTEXT_HV = (__u64)-32,
PERF_CONTEXT_KERNEL = (__u64)-128,
@@ -609,8 +611,6 @@ struct perf_guest_info_callbacks {
#include <linux/sysfs.h>
#include <asm/local.h>
-#define PERF_MAX_STACK_DEPTH 255
-
struct perf_callchain_entry {
__u64 nr;
__u64 ip[PERF_MAX_STACK_DEPTH];
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5b06cbb..f85c015 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3181,7 +3181,6 @@ static void perf_event_for_each(struct perf_event *event,
event = event->group_leader;
perf_event_for_each_child(event, func);
- func(event);
list_for_each_entry(sibling, &event->sibling_list, group_entry)
perf_event_for_each_child(sibling, func);
mutex_unlock(&ctx->mutex);
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 5476bc0..b4b572e 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,4 +1,6 @@
tools/perf
+tools/scripts
+tools/lib/traceevent
include/linux/const.h
include/linux/perf_event.h
include/linux/rbtree.h
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8c767c6..25249f7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -152,7 +152,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
if (symbol_conf.use_callchain) {
err = callchain_append(he->callchain,
- &evsel->hists.callchain_cursor,
+ &callchain_cursor,
sample->period);
if (err)
return err;
@@ -162,7 +162,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
* so we don't allocated the extra space needed because the stdio
* code will not use it.
*/
- if (al->sym != NULL && use_browser > 0) {
+ if (he->ms.sym != NULL && use_browser > 0) {
struct annotation *notes = symbol__annotation(he->ms.sym);
assert(evsel != NULL);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 62ae30d..2625899 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1129,7 +1129,7 @@ static int add_default_attributes(void)
return 0;
if (!evsel_list->nr_entries) {
- if (perf_evlist__add_attrs_array(evsel_list, default_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
return -1;
}
@@ -1139,21 +1139,21 @@ static int add_default_attributes(void)
return 0;
/* Append detailed run extra attributes: */
- if (perf_evlist__add_attrs_array(evsel_list, detailed_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
return -1;
if (detailed_run < 2)
return 0;
/* Append very detailed run extra attributes: */
- if (perf_evlist__add_attrs_array(evsel_list, very_detailed_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
return -1;
if (detailed_run < 3)
return 0;
/* Append very, very detailed run extra attributes: */
- return perf_evlist__add_attrs_array(evsel_list, very_very_detailed_attrs);
+ return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
}
int cmd_stat(int argc, const char **argv, const char *prefix __used)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 871b540..6bb0277 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -787,7 +787,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
}
if (symbol_conf.use_callchain) {
- err = callchain_append(he->callchain, &evsel->hists.callchain_cursor,
+ err = callchain_append(he->callchain, &callchain_cursor,
sample->period);
if (err)
return;
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index bd0bb1b..67e5d0c 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -409,14 +409,15 @@ Counters can be enabled and disabled in two ways: via ioctl and via
prctl. When a counter is disabled, it doesn't count or generate
events but does continue to exist and maintain its count value.
-An individual counter or counter group can be enabled with
+An individual counter can be enabled with
- ioctl(fd, PERF_EVENT_IOC_ENABLE);
+ ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
or disabled with
- ioctl(fd, PERF_EVENT_IOC_DISABLE);
+ ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+For a counter group, pass PERF_IOC_FLAG_GROUP as the third argument.
Enabling or disabling the leader of a group enables or disables the
whole group; that is, while the group leader is disabled, none of the
counters in the group will count. Enabling or disabling a member of a
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4deea6a..34b1c46 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -668,7 +668,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx,
"q/ESC/CTRL+C Exit\n\n"
"-> Go to target\n"
"<- Exit\n"
- "h Cycle thru hottest instructions\n"
+ "H Cycle thru hottest instructions\n"
"j Toggle showing jump to target arrows\n"
"J Toggle showing number of jump sources on targets\n"
"n Search next string\n"
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index ad73300..95264f3 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -12,7 +12,7 @@ LF='
# First check if there is a .git to get the version from git describe
# otherwise try to get the version from the kernel makefile
if test -d ../../.git -o -f ../../.git &&
- VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
+ VN=$(git describe --match 'v[0-9].[0-9]*' --abbrev=4 HEAD 2>/dev/null) &&
case "$VN" in
*$LF*) (exit 1) ;;
v[0-9]*)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 9f7106a..3a6bff4 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -18,6 +18,8 @@
#include "util.h"
#include "callchain.h"
+__thread struct callchain_cursor callchain_cursor;
+
bool ip_callchain__valid(struct ip_callchain *chain,
const union perf_event *event)
{
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 7f9c0f1..3bdb407 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -76,6 +76,8 @@ struct callchain_cursor {
struct callchain_cursor_node *curr;
};
+extern __thread struct callchain_cursor callchain_cursor;
+
static inline void callchain_init(struct callchain_root *root)
{
INIT_LIST_HEAD(&root->node.siblings);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4ac5f5a..7400fb3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -159,6 +159,17 @@ out_delete_partial_list:
return -1;
}
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs)
+{
+ size_t i;
+
+ for (i = 0; i < nr_attrs; i++)
+ event_attr_init(attrs + i);
+
+ return perf_evlist__add_attrs(evlist, attrs, nr_attrs);
+}
+
static int trace_event__id(const char *evname)
{
char *filename, *colon;
@@ -263,7 +274,8 @@ void perf_evlist__disable(struct perf_evlist *evlist)
for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
list_for_each_entry(pos, &evlist->entries, node) {
for (thread = 0; thread < evlist->threads->nr; thread++)
- ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE);
+ ioctl(FD(pos, cpu, thread),
+ PERF_EVENT_IOC_DISABLE, 0);
}
}
}
@@ -276,7 +288,8 @@ void perf_evlist__enable(struct perf_evlist *evlist)
for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
list_for_each_entry(pos, &evlist->entries, node) {
for (thread = 0; thread < evlist->threads->nr; thread++)
- ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+ ioctl(FD(pos, cpu, thread),
+ PERF_EVENT_IOC_ENABLE, 0);
}
}
}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 58abb63..989bee9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -54,6 +54,8 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
int perf_evlist__add_default(struct perf_evlist *evlist);
int perf_evlist__add_attrs(struct perf_evlist *evlist,
struct perf_event_attr *attrs, size_t nr_attrs);
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs);
int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
const char *tracepoints[], size_t nr_tracepoints);
int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
@@ -62,6 +64,8 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
#define perf_evlist__add_attrs_array(evlist, array) \
perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
+#define perf_evlist__add_default_attrs(evlist, array) \
+ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
#define perf_evlist__add_tracepoints_array(evlist, array) \
perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 91d1913..9f6cebd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -494,16 +494,24 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel,
}
static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
- struct perf_sample *sample)
+ struct perf_sample *sample,
+ bool swapped)
{
const u64 *array = event->sample.array;
+ union u64_swap u;
array += ((event->header.size -
sizeof(event->header)) / sizeof(u64)) - 1;
if (type & PERF_SAMPLE_CPU) {
- u32 *p = (u32 *)array;
- sample->cpu = *p;
+ u.val64 = *array;
+ if (swapped) {
+ /* undo swap of u64, then swap on individual u32s */
+ u.val64 = bswap_64(u.val64);
+ u.val32[0] = bswap_32(u.val32[0]);
+ }
+
+ sample->cpu = u.val32[0];
array--;
}
@@ -523,9 +531,16 @@ static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
}
if (type & PERF_SAMPLE_TID) {
- u32 *p = (u32 *)array;
- sample->pid = p[0];
- sample->tid = p[1];
+ u.val64 = *array;
+ if (swapped) {
+ /* undo swap of u64, then swap on individual u32s */
+ u.val64 = bswap_64(u.val64);
+ u.val32[0] = bswap_32(u.val32[0]);
+ u.val32[1] = bswap_32(u.val32[1]);
+ }
+
+ sample->pid = u.val32[0];
+ sample->tid = u.val32[1];
}
return 0;
@@ -562,7 +577,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
if (event->header.type != PERF_RECORD_SAMPLE) {
if (!sample_id_all)
return 0;
- return perf_event__parse_id_sample(event, type, data);
+ return perf_event__parse_id_sample(event, type, data, swapped);
}
array = event->sample.array;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 1293b5e..514e2a4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -378,7 +378,7 @@ void hist_entry__free(struct hist_entry *he)
* collapse the histogram
*/
-static bool hists__collapse_insert_entry(struct hists *hists,
+static bool hists__collapse_insert_entry(struct hists *hists __used,
struct rb_root *root,
struct hist_entry *he)
{
@@ -397,8 +397,9 @@ static bool hists__collapse_insert_entry(struct hists *hists,
iter->period += he->period;
iter->nr_events += he->nr_events;
if (symbol_conf.use_callchain) {
- callchain_cursor_reset(&hists->callchain_cursor);
- callchain_merge(&hists->callchain_cursor, iter->callchain,
+ callchain_cursor_reset(&callchain_cursor);
+ callchain_merge(&callchain_cursor,
+ iter->callchain,
he->callchain);
}
hist_entry__free(he);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index cfc64e2..34bb556 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -67,8 +67,6 @@ struct hists {
struct events_stats stats;
u64 event_stream;
u16 col_len[HISTC_NR_COLS];
- /* Best would be to reuse the session callchain cursor */
- struct callchain_cursor callchain_cursor;
};
struct hist_entry *__hists__add_entry(struct hists *self,
--git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 1915de2..3322b84 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -57,6 +57,10 @@ void setup_pager(void)
}
if (!pager)
pager = getenv("PAGER");
+ if (!pager) {
+ if (!access("/usr/bin/pager", X_OK))
+ pager = "/usr/bin/pager";
+ }
if (!pager)
pager = "less";
else if (!*pager || !strcmp(pager, "cat"))
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 59dccc9..0dda25d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2164,16 +2164,12 @@ int del_perf_probe_events(struct strlist *dellist)
error:
if (kfd >= 0) {
- if (namelist)
- strlist__delete(namelist);
-
+ strlist__delete(namelist);
close(kfd);
}
if (ufd >= 0) {
- if (unamelist)
- strlist__delete(unamelist);
-
+ strlist__delete(unamelist);
close(ufd);
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 93d355d..2600916 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -288,7 +288,8 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
return bi;
}
-int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
+int machine__resolve_callchain(struct machine *self,
+ struct perf_evsel *evsel __used,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent)
@@ -297,7 +298,12 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
unsigned int i;
int err;
- callchain_cursor_reset(&evsel->hists.callchain_cursor);
+ callchain_cursor_reset(&callchain_cursor);
+
+ if (chain->nr > PERF_MAX_STACK_DEPTH) {
+ pr_warning("corrupted callchain. skipping...\n");
+ return 0;
+ }
for (i = 0; i < chain->nr; i++) {
u64 ip;
@@ -317,7 +323,14 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
case PERF_CONTEXT_USER:
cpumode = PERF_RECORD_MISC_USER; break;
default:
- break;
+ pr_debug("invalid callchain context: "
+ "%"PRId64"\n", (s64) ip);
+ /*
+ * It seems the callchain is corrupted.
+ * Discard all.
+ */
+ callchain_cursor_reset(&callchain_cursor);
+ return 0;
}
continue;
}
@@ -333,7 +346,7 @@ int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
break;
}
- err = callchain_cursor_append(&evsel->hists.callchain_cursor,
+ err = callchain_cursor_append(&callchain_cursor,
ip, al.map, al.sym);
if (err)
return err;
@@ -441,37 +454,65 @@ void mem_bswap_64(void *src, int byte_size)
}
}
-static void perf_event__all64_swap(union perf_event *event)
+static void swap_sample_id_all(union perf_event *event, void *data)
+{
+ void *end = (void *) event + event->header.size;
+ int size = end - data;
+
+ BUG_ON(size % sizeof(u64));
+ mem_bswap_64(data, size);
+}
+
+static void perf_event__all64_swap(union perf_event *event,
+ bool sample_id_all __used)
{
struct perf_event_header *hdr = &event->header;
mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
}
-static void perf_event__comm_swap(union perf_event *event)
+static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
{
event->comm.pid = bswap_32(event->comm.pid);
event->comm.tid = bswap_32(event->comm.tid);
+
+ if (sample_id_all) {
+ void *data = &event->comm.comm;
+
+ data += ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
}
-static void perf_event__mmap_swap(union perf_event *event)
+static void perf_event__mmap_swap(union perf_event *event,
+ bool sample_id_all)
{
event->mmap.pid = bswap_32(event->mmap.pid);
event->mmap.tid = bswap_32(event->mmap.tid);
event->mmap.start = bswap_64(event->mmap.start);
event->mmap.len = bswap_64(event->mmap.len);
event->mmap.pgoff = bswap_64(event->mmap.pgoff);
+
+ if (sample_id_all) {
+ void *data = &event->mmap.filename;
+
+ data += ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
}
-static void perf_event__task_swap(union perf_event *event)
+static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
{
event->fork.pid = bswap_32(event->fork.pid);
event->fork.tid = bswap_32(event->fork.tid);
event->fork.ppid = bswap_32(event->fork.ppid);
event->fork.ptid = bswap_32(event->fork.ptid);
event->fork.time = bswap_64(event->fork.time);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->fork + 1);
}
-static void perf_event__read_swap(union perf_event *event)
+static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
{
event->read.pid = bswap_32(event->read.pid);
event->read.tid = bswap_32(event->read.tid);
@@ -479,6 +520,9 @@ static void perf_event__read_swap(union perf_event *event)
event->read.time_enabled = bswap_64(event->read.time_enabled);
event->read.time_running = bswap_64(event->read.time_running);
event->read.id = bswap_64(event->read.id);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->read + 1);
}
static u8 revbyte(u8 b)
@@ -530,7 +574,8 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
-static void perf_event__hdr_attr_swap(union perf_event *event)
+static void perf_event__hdr_attr_swap(union perf_event *event,
+ bool sample_id_all __used)
{
size_t size;
@@ -541,18 +586,21 @@ static void perf_event__hdr_attr_swap(union perf_event *event)
mem_bswap_64(event->attr.id, size);
}
-static void perf_event__event_type_swap(union perf_event *event)
+static void perf_event__event_type_swap(union perf_event *event,
+ bool sample_id_all __used)
{
event->event_type.event_type.event_id =
bswap_64(event->event_type.event_type.event_id);
}
-static void perf_event__tracing_data_swap(union perf_event *event)
+static void perf_event__tracing_data_swap(union perf_event *event,
+ bool sample_id_all __used)
{
event->tracing_data.size = bswap_32(event->tracing_data.size);
}
-typedef void (*perf_event__swap_op)(union perf_event *event);
+typedef void (*perf_event__swap_op)(union perf_event *event,
+ bool sample_id_all);
static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_MMAP] = perf_event__mmap_swap,
@@ -986,6 +1034,15 @@ static int perf_session__process_user_event(struct perf_session *session, union
}
}
+static void event_swap(union perf_event *event, bool sample_id_all)
+{
+ perf_event__swap_op swap;
+
+ swap = perf_event__swap_ops[event->header.type];
+ if (swap)
+ swap(event, sample_id_all);
+}
+
static int perf_session__process_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool,
@@ -994,9 +1051,8 @@ static int perf_session__process_event(struct perf_session *session,
struct perf_sample sample;
int ret;
- if (session->header.needs_swap &&
- perf_event__swap_ops[event->header.type])
- perf_event__swap_ops[event->header.type](event);
+ if (session->header.needs_swap)
+ event_swap(event, session->sample_id_all);
if (event->header.type >= PERF_RECORD_HEADER_MAX)
return -EINVAL;
@@ -1428,7 +1484,6 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
int print_sym, int print_dso, int print_symoffset)
{
struct addr_location al;
- struct callchain_cursor *cursor = &evsel->hists.callchain_cursor;
struct callchain_cursor_node *node;
if (perf_event__preprocess_sample(event, machine, &al, sample,
@@ -1446,10 +1501,10 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
error("Failed to resolve callchain. Skipping\n");
return;
}
- callchain_cursor_commit(cursor);
+ callchain_cursor_commit(&callchain_cursor);
while (1) {
- node = callchain_cursor_current(cursor);
+ node = callchain_cursor_current(&callchain_cursor);
if (!node)
break;
@@ -1460,12 +1515,12 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
}
if (print_dso) {
printf(" (");
- map__fprintf_dsoname(al.map, stdout);
+ map__fprintf_dsoname(node->map, stdout);
printf(")");
}
printf("\n");
- callchain_cursor_advance(cursor);
+ callchain_cursor_advance(&callchain_cursor);
}
} else {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e2ba885..3e2e5ea 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -323,6 +323,7 @@ struct dso *dso__new(const char *name)
dso->sorted_by_name = 0;
dso->has_build_id = 0;
dso->kernel = DSO_TYPE_USER;
+ dso->needs_swap = DSO_SWAP__UNSET;
INIT_LIST_HEAD(&dso->node);
}
@@ -1156,6 +1157,33 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
return -1;
}
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+ static unsigned int const endian = 1;
+
+ dso->needs_swap = DSO_SWAP__NO;
+
+ switch (eidata) {
+ case ELFDATA2LSB:
+ /* We are big endian, DSO is little endian. */
+ if (*(unsigned char const *)&endian != 1)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ case ELFDATA2MSB:
+ /* We are little endian, DSO is big endian. */
+ if (*(unsigned char const *)&endian != 0)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ default:
+ pr_err("unrecognized DSO data encoding %d\n", eidata);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
int fd, symbol_filter_t filter, int kmodule,
int want_symtab)
@@ -1187,6 +1215,9 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
goto out_elf_end;
}
+ if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+ goto out_elf_end;
+
/* Always reject images with a mismatched build-id: */
if (dso->has_build_id) {
u8 build_id[BUILD_ID_SIZE];
@@ -1272,7 +1303,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
if (opdsec && sym.st_shndx == opdidx) {
u32 offset = sym.st_value - opdshdr.sh_addr;
u64 *opd = opddata->d_buf + offset;
- sym.st_value = *opd;
+ sym.st_value = DSO__SWAP(dso, u64, *opd);
sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
}
@@ -2786,8 +2817,11 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
struct map *dso__new_map(const char *name)
{
+ struct map *map = NULL;
struct dso *dso = dso__new(name);
- struct map *map = map__new2(0, dso, MAP__FUNCTION);
+
+ if (dso)
+ map = map__new2(0, dso, MAP__FUNCTION);
return map;
}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5649d63..af0752b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -9,6 +9,7 @@
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdio.h>
+#include <byteswap.h>
#ifdef HAVE_CPLUS_DEMANGLE
extern char *cplus_demangle(const char *, int);
@@ -160,11 +161,18 @@ enum dso_kernel_type {
DSO_TYPE_GUEST_KERNEL
};
+enum dso_swap_type {
+ DSO_SWAP__UNSET,
+ DSO_SWAP__NO,
+ DSO_SWAP__YES,
+};
+
struct dso {
struct list_head node;
struct rb_root symbols[MAP__NR_TYPES];
struct rb_root symbol_names[MAP__NR_TYPES];
enum dso_kernel_type kernel;
+ enum dso_swap_type needs_swap;
u8 adjust_symbols:1;
u8 has_build_id:1;
u8 hit:1;
@@ -182,6 +190,28 @@ struct dso {
char name[0];
};
+#define DSO__SWAP(dso, type, val) \
+({ \
+ type ____r = val; \
+ BUG_ON(dso->needs_swap == DSO_SWAP__UNSET); \
+ if (dso->needs_swap == DSO_SWAP__YES) { \
+ switch (sizeof(____r)) { \
+ case 2: \
+ ____r = bswap_16(val); \
+ break; \
+ case 4: \
+ ____r = bswap_32(val); \
+ break; \
+ case 8: \
+ ____r = bswap_64(val); \
+ break; \
+ default: \
+ BUG_ON(1); \
+ } \
+ } \
+ ____r; \
+})
+
struct dso *dso__new(const char *name);
void dso__delete(struct dso *dso);
next reply other threads:[~2012-06-08 9:20 UTC|newest]
Thread overview: 376+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-08 9:20 Ingo Molnar [this message]
-- strict thread matches above, loose matches on Subject: below --
2023-01-06 11:57 [GIT PULL] perf fixes Ingo Molnar
2023-01-06 21:19 ` pr-tracker-bot
2022-10-02 10:56 Ingo Molnar
2022-10-02 16:47 ` Linus Torvalds
2022-10-03 10:55 ` Ingo Molnar
2022-10-02 17:20 ` pr-tracker-bot
2022-08-28 14:35 Ingo Molnar
2022-08-28 18:18 ` pr-tracker-bot
2022-08-06 19:10 Ingo Molnar
2022-08-07 0:50 ` pr-tracker-bot
2021-07-11 13:26 Ingo Molnar
2021-07-11 18:22 ` pr-tracker-bot
2021-06-12 12:48 Ingo Molnar
2021-06-12 19:09 ` pr-tracker-bot
2021-03-21 10:56 Ingo Molnar
2021-03-21 18:45 ` pr-tracker-bot
2020-08-15 11:21 Ingo Molnar
2020-08-16 1:55 ` pr-tracker-bot
2020-04-25 9:19 Ingo Molnar
2020-04-25 19:30 ` pr-tracker-bot
2020-03-24 9:19 Ingo Molnar
2020-03-24 17:15 ` pr-tracker-bot
2020-03-02 7:23 Ingo Molnar
2020-03-03 23:35 ` pr-tracker-bot
2020-02-15 8:53 Ingo Molnar
2020-02-15 21:25 ` pr-tracker-bot
2020-01-18 17:58 Ingo Molnar
2020-01-18 21:05 ` pr-tracker-bot
2019-12-21 16:16 Ingo Molnar
2019-12-21 18:55 ` pr-tracker-bot
2019-12-17 11:34 Ingo Molnar
2019-12-17 19:06 ` Linus Torvalds
2019-12-18 6:58 ` Ingo Molnar
2019-12-17 19:20 ` pr-tracker-bot
2019-12-01 22:15 Ingo Molnar
2019-12-02 4:40 ` pr-tracker-bot
2019-11-16 21:33 Ingo Molnar
2019-11-17 0:35 ` pr-tracker-bot
2019-11-01 17:48 Ingo Molnar
2019-11-01 18:48 ` Linus Torvalds
2019-11-01 20:30 ` Ingo Molnar
2019-11-01 21:01 ` Ingo Molnar
2019-11-01 22:15 ` Linus Torvalds
2019-11-01 19:10 ` pr-tracker-bot
2019-10-12 13:31 Ingo Molnar
2019-10-12 22:35 ` pr-tracker-bot
2019-07-14 12:01 Ingo Molnar
2019-07-14 18:45 ` pr-tracker-bot
2019-06-29 8:54 Ingo Molnar
2019-06-29 11:45 ` pr-tracker-bot
2019-06-02 17:39 Ingo Molnar
2019-06-02 18:15 ` pr-tracker-bot
2019-05-16 16:05 Ingo Molnar
2019-05-16 18:20 ` pr-tracker-bot
2019-05-05 12:47 Ingo Molnar
2019-05-05 22:10 ` pr-tracker-bot
2019-04-20 7:43 Ingo Molnar
2019-04-20 19:25 ` pr-tracker-bot
2019-04-12 13:06 Ingo Molnar
2019-04-13 4:05 ` pr-tracker-bot
2019-02-17 10:10 Ingo Molnar
2019-02-17 16:50 ` pr-tracker-bot
2019-02-10 9:01 Ingo Molnar
2019-02-10 18:30 ` pr-tracker-bot
2019-01-11 7:44 Ingo Molnar
2019-01-11 18:00 ` pr-tracker-bot
2018-11-30 6:25 Ingo Molnar
2018-11-30 21:00 ` pr-tracker-bot
2018-11-17 10:55 Ingo Molnar
2018-11-18 20:05 ` pr-tracker-bot
2018-10-20 8:10 Ingo Molnar
2018-10-20 13:28 ` Greg Kroah-Hartman
2018-10-11 9:12 Ingo Molnar
2018-10-11 12:32 ` Greg Kroah-Hartman
2018-10-11 8:59 Ingo Molnar
2018-10-05 9:42 Ingo Molnar
2018-10-05 9:55 ` Ingo Molnar
2018-10-05 23:30 ` Greg Kroah-Hartman
2018-09-15 13:11 Ingo Molnar
2018-07-30 17:53 Ingo Molnar
2018-07-13 19:59 Ingo Molnar
2018-06-30 8:44 Ingo Molnar
2018-06-04 9:04 Ingo Molnar
2018-03-31 10:40 Ingo Molnar
2018-03-25 8:53 Ingo Molnar
2018-02-06 21:29 Ingo Molnar
2017-12-06 22:17 Ingo Molnar
2017-11-26 12:40 Ingo Molnar
2017-11-05 14:40 Ingo Molnar
2017-11-09 8:13 ` Markus Trippelsdorf
2017-10-14 16:04 Ingo Molnar
2017-09-13 18:00 Ingo Molnar
2017-09-12 15:32 Ingo Molnar
2017-07-21 10:15 Ingo Molnar
2017-06-10 8:39 Ingo Molnar
2017-05-12 7:31 Ingo Molnar
2017-03-07 20:30 Ingo Molnar
2017-02-28 8:01 Ingo Molnar
2017-02-11 18:12 Ingo Molnar
2017-02-02 21:01 Ingo Molnar
2017-01-18 9:27 Ingo Molnar
2017-01-15 9:59 Ingo Molnar
2016-12-23 22:50 Ingo Molnar
2016-12-07 18:45 Ingo Molnar
2016-11-23 9:00 Ingo Molnar
2016-11-14 7:56 Ingo Molnar
2016-10-28 19:41 Ingo Molnar
2016-10-18 11:07 Ingo Molnar
2016-09-13 18:14 Ingo Molnar
2016-08-18 20:38 Ingo Molnar
2016-08-12 19:35 Ingo Molnar
2016-07-26 14:13 Ingo Molnar
2016-07-08 13:42 Ingo Molnar
2016-06-10 12:50 Ingo Molnar
2016-05-13 18:51 Ingo Molnar
2016-05-06 11:26 Ingo Molnar
2016-04-28 17:56 Ingo Molnar
2016-04-03 11:00 Ingo Molnar
2016-02-20 11:14 Ingo Molnar
2016-01-14 10:03 Ingo Molnar
2016-01-08 12:46 Ingo Molnar
2015-12-08 4:22 Ingo Molnar
2015-09-17 8:02 Ingo Molnar
2015-09-02 18:11 Ingo Molnar
2015-08-22 12:19 Ingo Molnar
2015-08-14 7:12 Ingo Molnar
2015-07-18 2:53 Ingo Molnar
2015-07-06 15:29 Ingo Molnar
2015-06-13 14:29 Ingo Molnar
2015-06-05 8:37 Ingo Molnar
2015-05-15 7:17 Ingo Molnar
2015-05-06 12:52 Ingo Molnar
2015-04-03 13:11 Ingo Molnar
2015-03-17 16:48 Ingo Molnar
2015-03-01 17:00 Ingo Molnar
2015-02-20 13:40 Ingo Molnar
2015-01-30 18:44 Ingo Molnar
2015-01-17 14:15 Ingo Molnar
2015-01-11 8:42 Ingo Molnar
2014-11-20 7:46 Ingo Molnar
2014-10-31 11:13 Ingo Molnar
2014-11-03 9:02 ` Paul Bolle
2014-11-03 10:04 ` Peter Zijlstra
2014-09-19 10:46 Ingo Molnar
2014-08-24 20:25 Ingo Molnar
2014-07-16 11:11 Ingo Molnar
2014-06-18 16:39 Ingo Molnar
2014-05-22 8:04 Ingo Molnar
2014-05-01 6:34 Ingo Molnar
2014-04-20 8:02 Ingo Molnar
2014-04-19 10:41 Ingo Molnar
2014-04-16 13:04 Ingo Molnar
2014-03-22 9:06 Ingo Molnar
2014-03-16 16:34 Ingo Molnar
2014-03-02 8:51 Ingo Molnar
2014-02-22 19:16 Ingo Molnar
2014-02-09 8:01 Ingo Molnar
2014-01-25 7:30 Ingo Molnar
2014-01-19 12:08 Ingo Molnar
2013-12-19 16:52 Ingo Molnar
2013-12-02 14:39 Ingo Molnar
2013-11-15 19:46 Ingo Molnar
2013-11-01 9:56 Ingo Molnar
2013-10-29 10:04 Ingo Molnar
2013-10-26 12:24 Ingo Molnar
2013-10-28 8:28 ` Markus Trippelsdorf
2013-10-28 9:02 ` ------------------------------ Markus Trippelsdorf
2013-10-28 9:34 ` Markus Trippelsdorf
2013-10-28 12:34 ` Arnaldo Carvalho de Melo
2013-10-28 12:42 ` Arnaldo Carvalho de Melo
2013-10-28 12:59 ` Markus Trippelsdorf
2013-10-29 9:50 ` Stephane Eranian
2013-10-29 10:06 ` Ingo Molnar
2013-10-29 12:47 ` Arnaldo Carvalho de Melo
2013-10-08 12:12 Ingo Molnar
2013-09-28 18:03 Ingo Molnar
2013-09-29 11:47 ` Markus Trippelsdorf
2013-09-29 21:33 ` Andi Kleen
2013-09-29 22:47 ` Markus Trippelsdorf
2013-09-30 6:27 ` Ingo Molnar
2013-09-30 18:54 ` Andi Kleen
2013-10-01 8:42 ` Ingo Molnar
2013-09-25 18:00 Ingo Molnar
2013-09-18 16:06 Ingo Molnar
2013-09-12 13:38 Ingo Molnar
2013-09-12 18:03 ` Linus Torvalds
2013-09-12 18:10 ` Linus Torvalds
2013-09-12 18:43 ` Arnaldo Carvalho de Melo
2013-09-12 19:12 ` Arnaldo Carvalho de Melo
2013-09-12 19:13 ` Linus Torvalds
2013-09-12 19:55 ` Ingo Molnar
2013-09-12 19:58 ` David Ahern
2013-09-12 20:02 ` Arnaldo Carvalho de Melo
2013-09-12 20:31 ` Ingo Molnar
2013-09-12 20:43 ` Ingo Molnar
2013-09-12 20:18 ` Ingo Molnar
2013-09-12 20:38 ` Arnaldo Carvalho de Melo
2013-09-12 20:46 ` Ingo Molnar
2013-09-12 21:09 ` David Ahern
2013-09-12 21:18 ` Ingo Molnar
2013-09-12 22:10 ` David Ahern
2013-09-13 5:09 ` Ingo Molnar
2013-09-13 9:32 ` Jean Pihet
2013-09-13 9:45 ` Ingo Molnar
2013-09-13 17:15 ` Jean Pihet
2013-09-12 18:51 ` Linus Torvalds
2013-09-12 20:33 ` Ingo Molnar
2013-09-12 20:38 ` Linus Torvalds
2013-09-12 20:49 ` Ingo Molnar
2013-09-12 20:52 ` Linus Torvalds
2013-09-12 21:01 ` Ingo Molnar
2013-09-12 20:10 ` Ingo Molnar
2013-08-13 16:51 Ingo Molnar
2013-07-10 8:52 Ingo Molnar
2013-06-26 8:52 Ingo Molnar
2013-06-20 8:58 Ingo Molnar
2013-05-05 10:10 Ingo Molnar
2013-04-21 8:16 Ingo Molnar
2013-04-14 15:20 Ingo Molnar
2013-03-21 9:56 Ingo Molnar
2013-03-11 14:28 Ingo Molnar
2013-02-26 7:02 Ingo Molnar
2013-03-14 20:32 ` Linus Torvalds
2013-03-14 21:06 ` Linus Torvalds
2013-03-14 22:09 ` Stephane Eranian
2013-03-14 22:17 ` Linus Torvalds
2013-03-14 22:19 ` Stephane Eranian
2013-03-14 22:42 ` Stephane Eranian
2013-03-14 22:53 ` Stephane Eranian
2013-03-14 23:11 ` Stephane Eranian
2013-03-15 0:24 ` Stephane Eranian
2013-03-15 1:06 ` Linus Torvalds
2013-03-15 8:01 ` Stephane Eranian
2013-03-15 10:50 ` Stephane Eranian
2013-02-04 18:20 Ingo Molnar
2012-12-01 11:11 Ingo Molnar
2012-10-26 14:44 Ingo Molnar
2012-10-23 11:02 Ingo Molnar
2012-10-20 0:56 Ingo Molnar
2012-09-21 19:08 Ingo Molnar
2012-09-13 14:39 Ingo Molnar
2012-08-23 10:59 Ingo Molnar
2012-08-20 9:08 Ingo Molnar
2012-08-21 7:59 ` Ingo Molnar
2012-08-05 17:43 Ingo Molnar
2012-08-03 16:40 Ingo Molnar
2012-07-14 7:51 Ingo Molnar
2012-06-22 13:36 Ingo Molnar
2012-06-22 18:07 ` Linus Torvalds
2012-06-22 18:38 ` Hagen Paul Pfeifer
2012-06-22 18:52 ` Linus Torvalds
2012-06-22 19:06 ` Hagen Paul Pfeifer
2012-06-22 19:54 ` Steven Rostedt
[not found] ` <86448d73-2e19-416f-8104-ce72aa5d76eb@email.android.com>
2012-06-22 23:18 ` Steven Rostedt
2012-06-23 0:51 ` Arjan van de Ven
2012-06-23 1:57 ` Steven Rostedt
2012-06-23 18:25 ` H. Peter Anvin
2012-06-22 18:50 ` Steven Rostedt
2012-06-15 18:48 Ingo Molnar
2012-05-30 15:39 Ingo Molnar
2012-05-17 8:19 Ingo Molnar
2012-04-27 6:32 Ingo Molnar
2012-04-16 17:48 Ingo Molnar
2012-04-14 10:54 Ingo Molnar
2012-04-03 22:40 Ingo Molnar
2012-03-13 16:56 Ingo Molnar
2012-03-05 9:27 Ingo Molnar
2012-03-02 10:47 Ingo Molnar
2012-02-10 12:45 Ingo Molnar
2012-02-02 10:00 Ingo Molnar
2012-01-26 18:11 Ingo Molnar
2011-12-29 21:02 Ingo Molnar
2011-12-09 6:16 Ingo Molnar
2011-12-05 19:13 Ingo Molnar
2011-11-07 18:49 Ingo Molnar
2011-11-07 19:00 ` Linus Torvalds
2011-11-07 19:50 ` Ingo Molnar
2011-08-22 17:00 Ingo Molnar
2011-08-11 8:17 Ingo Molnar
2011-07-07 18:11 Ingo Molnar
2011-06-19 8:44 Ingo Molnar
2011-06-13 9:53 Ingo Molnar
2011-06-08 13:46 Ingo Molnar
2011-05-28 16:34 Ingo Molnar
2011-05-24 2:41 Ingo Molnar
2011-05-23 13:41 Ingo Molnar
2011-05-23 22:10 ` Eric Dumazet
2011-05-23 22:19 ` Frederic Weisbecker
2011-05-23 22:22 ` Eric Dumazet
2011-05-20 17:18 Ingo Molnar
2011-05-17 22:07 Ingo Molnar
2011-05-07 18:20 Ingo Molnar
2011-04-29 18:17 Ingo Molnar
2011-04-22 13:42 Ingo Molnar
2011-04-19 15:56 Ingo Molnar
2011-04-16 10:03 Ingo Molnar
2011-04-07 17:48 Ingo Molnar
2011-04-02 10:25 Ingo Molnar
2011-03-25 13:11 Ingo Molnar
2011-03-10 7:53 Ingo Molnar
2011-02-28 17:34 Ingo Molnar
2011-02-22 16:03 Ingo Molnar
2011-02-15 16:58 Ingo Molnar
2011-02-06 11:27 Ingo Molnar
2011-02-03 15:47 Ingo Molnar
2011-01-24 13:34 Ingo Molnar
2011-01-24 19:48 ` Linus Torvalds
2011-01-24 20:07 ` Ingo Molnar
2011-01-24 20:11 ` Ingo Molnar
2011-01-24 20:17 ` Ingo Molnar
2011-01-24 20:17 ` Linus Torvalds
2011-01-24 20:27 ` Linus Torvalds
2011-01-24 20:38 ` Arnaldo Carvalho de Melo
2011-01-24 21:13 ` Linus Torvalds
2011-01-24 21:25 ` Ingo Molnar
2011-01-24 22:00 ` Arnaldo Carvalho de Melo
2011-01-25 0:16 ` Ingo Molnar
2011-01-24 20:37 ` Davidlohr Bueso
2011-01-24 20:14 ` Arnaldo Carvalho de Melo
2011-01-18 18:59 Ingo Molnar
2011-01-18 9:42 Ingo Molnar
2011-01-15 15:24 Ingo Molnar
2011-01-11 11:32 Ingo Molnar
2011-01-03 19:04 Ingo Molnar
2010-12-23 12:56 Ingo Molnar
2010-12-19 15:34 Ingo Molnar
2010-12-08 7:55 Ingo Molnar
2010-11-28 17:36 Ingo Molnar
2010-11-26 13:20 Ingo Molnar
2010-11-11 10:38 Ingo Molnar
2010-10-30 18:21 Ingo Molnar
2010-10-13 15:21 Ingo Molnar
2010-10-05 14:49 Ingo Molnar
2010-09-26 8:38 Ingo Molnar
2010-09-21 19:39 Ingo Molnar
2010-09-10 14:26 Ingo Molnar
2010-08-25 17:44 Ingo Molnar
2010-08-24 19:06 Ingo Molnar
2010-08-19 14:55 Ingo Molnar
2010-08-18 8:14 Ingo Molnar
2010-07-23 19:41 Ingo Molnar
2010-07-16 17:30 Ingo Molnar
2010-07-08 4:36 Frederic Weisbecker
2010-07-08 4:40 ` Frederic Weisbecker
2010-07-08 6:36 ` Ingo Molnar
2010-07-04 20:24 Ingo Molnar
2010-06-10 10:25 Ingo Molnar
2010-06-02 12:28 Ingo Molnar
2010-05-31 23:02 Frederic Weisbecker
2010-06-01 6:59 ` Ingo Molnar
2010-05-30 19:27 Ingo Molnar
2010-05-20 9:44 Frederic Weisbecker
2010-05-20 12:40 ` Ingo Molnar
2010-05-11 19:18 Ingo Molnar
2010-05-12 0:39 ` Linus Torvalds
2010-04-06 17:49 Ingo Molnar
2010-04-04 10:15 Ingo Molnar
2010-04-03 10:47 Frederic Weisbecker
2010-03-28 5:11 Frederic Weisbecker
2010-03-29 3:33 ` Ingo Molnar
2010-03-26 15:16 Ingo Molnar
2010-03-16 16:06 Ingo Molnar
2010-03-11 19:12 Ingo Molnar
2010-02-22 16:50 Ingo Molnar
2010-02-22 17:01 ` Linus Torvalds
2010-02-22 17:15 ` Frederic Weisbecker
2010-02-14 9:06 Ingo Molnar
2010-01-31 17:32 Ingo Molnar
2010-01-21 15:38 Ingo Molnar
2009-12-31 12:00 Ingo Molnar
2009-12-18 18:59 Ingo Molnar
2009-09-22 7:51 Ingo Molnar
2009-09-22 14:49 ` Linus Torvalds
2009-09-22 14:59 ` Ingo Molnar
2009-09-22 15:13 ` Linus Torvalds
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20120608092002.GA12129@gmail.com \
--to=mingo@kernel.org \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.