| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20120722132607.GA6385@gmail.com>
Date: Sun, 22 Jul 2012 15:26:08 +0200
From: Ingo Molnar <mingo@...nel.org>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: linux-kernel@...r.kernel.org,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Arnaldo Carvalho de Melo <acme@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: [GIT PULL] perf events changes for v3.6
Linus,
Please pull the latest perf-core-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-core-for-linus
HEAD: 6e0f17be0361444862637e8986c8c1a3b3f8dcf8 Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/core
Major changes are:
- kernel side:
- Intel uncore PMU support for Nehalem and Sandy Bridge CPUs,
we support both the events available via the MSR and via
the PCI access space.
- various uprobes cleanups and restructurings
- PMU driver quirks by microcode version and required x86
microcode loader cleanups/robustization
- various tracing robustness updates
- static keys: remove obsolete static_branch()
- tooling side:
- GTK browser improvements
- perf report browser: support screenshots to file
- more automated tests
- perf kvm improvements
- perf bench refinements
- build environment improvements
- pipe mode improvements
- libtraceevent updates, we have now hopefully merged most
bits with the out of tree forked code base
... and many other goodies.
Thanks,
Ingo
------------------>
Ananth N Mavinakayanahalli (1):
uprobes: Pass probed vaddr to arch_uprobe_analyze_insn()
Andi Kleen (2):
x86: Add rdpmcl()
perf/x86: Don't assume there can be only 4 PEBS events
Andre Przywara (2):
x86, pvops: Remove hooks for {rd,wr}msr_safe_regs
x86, cpu, amd: Fix crash as Xen Dom0 on AMD Trinity systems
Arnaldo Carvalho de Melo (14):
perf tools: Add sort by src line/number
perf lib: Introduce rtrim
perf hists browser: Implement printing snapshots to files
perf evsel: Carve out event modifier formatting
perf tools: Reconstruct hw cache event with modifiers from perf_event_attr
perf tools: Reconstruct sw event with modifiers from perf_event_attr
perf evsel: Handle all event types in perf_evsel__name
perf tools: Move all users of event_name to perf_evsel__name
perf script: Replace __event_name uses with perf_evsel__name
perf tools: Don't access evsel->name directly
perf tools: Remove __event_name
perf evsel: Reconstruct raw event with modifiers from perf_event_attr
perf evsel: Make some methods private
perf tools: Stop using a global trace events description list
Borislav Petkov (5):
x86, cpu: Fix show_msr MSR accessing function
x86, cpu, amd: Deprecate AMD-specific MSR variants
ftrace: Remove a superfluous check
x86, microcode: Sanitize per-cpu microcode reloading interface
x86, microcode: Make reload interface per system
Dan Carpenter (1):
tracing: Check for allocation failure in __tracing_open()
David Ahern (2):
perf report: Delay sample_type checks in pipe mode
perf tools: Trivial build fix
H. Peter Anvin (1):
x86, cpu: Rename checking_wrmsrl() to wrmsrl_safe()
Hitoshi Mitake (1):
perf bench: Fix confused variable namings and descriptions in mem subsystem
Jason Baron (2):
tracepoint: Use static_key_false(), since static_branch() is deprecated
jump label: Remove static_branch()
Jiri Olsa (13):
perf/tool: Use data struct for arg passing in event parse function
perf/tool: Add support to reuse event grammar to parse out terms
perf/tool: Add automated test for pure terms parsing
perf tools: Remove unused evsel parameter from machine__resolve_callchain
perf test: Fix parse events test to follow proper raw event name
perf tools: Fix hw breakpoint's type modifier parsing
perf evsel: Handle hw breakpoints event names in perf_evsel__name()
perf symbols: Add '.note' check into search for NOTE section
perf tools: Adding round_up/round_down macros
perf test: Use ARRAY_SIZE in parse events tests
perf tools: Add empty rule for new line in event syntax parsing
perf tools: Split out PE_VALUE_SYM parsing token to SW and HW tokens
perf tools: Split event symbols arrays to hw and sw parts
Konstantin Stepanyuk (1):
tools lib traceevent: Fix clean target in Makefile
Namhyung Kim (24):
perf ui: Introduce struct perf_error_ops
perf ui/gtk: Introduce struct perf_gtk_context
perf ui/gtk: Add GTK statusbar widget to browser window
perf ui/gtk: Add GTK info_bar widget to browser window
perf ui/gtk: Use struct perf_error_ops
perf evsel: Fix a build failure on cross compilation
perf bench: Documentation update
tracing/kvm: Use __print_hex() for kvm_emulate_insn tracepoint
tools lib traceevent: Teach [ce]tags about libtraceeevent error codes
tools lib traceevent: Make dependency files regeneratable
tools lib traceevent: Check string is really printable
tools lib traceevent: Use local variable 'field'
tools lib traceevent: Add support for __print_hex()
tools lib traceevent: Replace malloc_or_die to plain malloc in alloc_event()
tools lib traceevent: Fix printk_cmp()
tools lib traceevent: Introduce extend_token()
tools lib traceevent: Handle strdup failure cases
tools lib traceevent: Handle realloc() failure path
tools lib traceevent: Pass string type argument to args
tools lib traceevent: Do not call add_event() again if allocation failed
tools lib traceevent: Fix some comments
tools lib traceevent: Check result of malloc() during reading token
tools lib traceevent: Check return value of arg_to_str()
tools lib traceevent: Cleanup realloc use
Oleg Nesterov (21):
uprobes: Optimize is_swbp_at_addr() for current->mm
uprobes: Change read_opcode() to use FOLL_FORCE
uprobes: Introduce find_active_uprobe() helper
uprobes: Teach find_active_uprobe() to provide the "is_swbp" info
uprobes: Change register_for_each_vma() to take mm->mmap_sem for writing
uprobes: Teach handle_swbp() to rely on "is_swbp" rather than uprobes_srcu
uprobes: Kill uprobes_srcu/uprobe_srcu_id
uprobes: Valid_vma() should reject VM_HUGETLB
uprobes: __copy_insn() should ensure a_ops->readpage != NULL
uprobes: Write_opcode()->__replace_page() can race with try_to_unmap()
uprobes: Install_breakpoint() should fail if is_swbp_insn() == T
uprobes: Rework register_for_each_vma() to make it O(n)
uprobes: Change build_map_info() to try kmalloc(GFP_NOWAIT) first
uprobes: Copy_insn() shouldn't depend on mm/vma/vaddr
uprobes: Copy_insn() should not return -ENOMEM if __copy_insn() fails
uprobes: No need to re-check vma_address() in write_opcode()
uprobes: Move BUG_ON(UPROBE_SWBP_INSN_SIZE) from write_opcode() to install_breakpoint()
uprobes: Simplify the usage of uprobe->pending_list
uprobes: Don't use loff_t for the valid virtual address
uprobes: __copy_insn() needs "loff_t offset"
uprobes: Remove the unnecessary initialization in add_utask()
Pekka Enberg (1):
perf/x86: Fix intel_perfmon_event_mapformatting
Peter Huewe (1):
tools lib traceevent: Add missing break in make_bprint_args
Peter Zijlstra (10):
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
perf/x86: Fix wrmsrl() debug wrapper
uprobes: Document uprobe_register() vs uprobe_mmap() race
perf/x86: Lowercase uncore PMU event names
perf/x86: Fix USER/KERNEL tagging of samples
perf/x86: Add a microcode revision check for SNB-PEBS
perf/x86: Save a few bytes in 'struct x86_pmu'
Pierre-Loup A. Griffais (1):
perf symbols: Follow .gnu_debuglink section to find separate symbols
Robert Richter (8):
perf/x86/amd: Fix RDPMC index calculation for AMD family 15h
oprofile, perf: Use per-cpu framework
perf/x86: Fix section mismatch in uncore_pci_init()
perf tools: Fix generation of pmu list
perf/x86: Rename Intel specific macros
perf/x86: Move Intel specific code to intel_pmu_init()
perf/x86/amd: Unify AMD's generic and family 15h pmus
perf/x86: Improve debug output in check_hw_exists()
Samuel Liao (1):
perf annotate: Check null of sym pointer before using it
Shuah Khan (1):
perf/x86: Convert obsolete simple_strtoul() usage to kstrtoul()
Steven Rostedt (9):
tracing: Add comments for the other bits of ftrace_event_call.flags
tracing: Register the ftrace internal events during early boot
tracing/selftest: Add a WARN_ON() if a tracer test fails
tracing: Remove NR_CPUS array from trace_iterator
ring-buffer: Fix uninitialized read_stamp
tools lib traceevent: Let filtering numbers by string use function names
tools lib traceevent: Add support for "%.*s" in bprintk events
tools lib traceevent: Add support to show migrate disable counter
tools lib traceevent: Fix %pM print format arg handling
Vince Weaver (1):
perf/x86: Use rdpmc() rather than rdmsr() when possible in the kernel
Wolfgang Mauerer (1):
tools lib traceevent: Fix trace_printk for long integers
Yan, Zheng (12):
perf: Export perf_assign_events()
perf: Avoid race between cpu hotplug and installing event
perf: Allow the PMU driver to choose the CPU on which to install events
perf: Introduce perf_pmu_migrate_context()
perf/x86: Add generic Intel uncore PMU support
perf/x86: Add Intel Nehalem and Sandy Bridge uncore PMU support
perf: Add generic PCI uncore PMU device support
perf/x86: Add Intel Nehalem and Sandy Bridge-EP uncore support
perf/x86: Use 0xff as pseudo code for fixed uncore event
perf/x86: Fix event constraint for SandyBridge-EP C-Box
perf/x86: Detect number of instances of uncore CBox
perf/x86: Uncore filter support for SandyBridge-EP
Zheng Yan (2):
perf/tool: Make the event parser re-entrant
perf/tool: Add PMU event alias support
arch/x86/include/asm/kvm_host.h | 4 +-
arch/x86/include/asm/msr.h | 46 +-
arch/x86/include/asm/paravirt.h | 41 +-
arch/x86/include/asm/paravirt_types.h | 2 -
arch/x86/include/asm/perf_event.h | 22 +-
arch/x86/include/asm/uprobes.h | 2 +-
arch/x86/kernel/cpu/Makefile | 4 +-
arch/x86/kernel/cpu/amd.c | 39 +-
arch/x86/kernel/cpu/common.c | 2 +-
arch/x86/kernel/cpu/perf_event.c | 111 +-
arch/x86/kernel/cpu/perf_event.h | 26 +-
arch/x86/kernel/cpu/perf_event_amd.c | 103 +-
arch/x86/kernel/cpu/perf_event_intel.c | 122 +-
arch/x86/kernel/cpu/perf_event_intel_ds.c | 12 +-
arch/x86/kernel/cpu/perf_event_intel_uncore.c | 1850 ++++++++++++++++++++
arch/x86/kernel/cpu/perf_event_intel_uncore.h | 424 +++++
arch/x86/kernel/cpu/perf_event_p4.c | 16 +-
arch/x86/kernel/cpu/perf_event_p6.c | 4 +-
arch/x86/kernel/microcode_core.c | 64 +-
arch/x86/kernel/paravirt.c | 2 -
arch/x86/kernel/process_64.c | 4 +-
arch/x86/kernel/uprobes.c | 3 +-
arch/x86/kvm/pmu.c | 22 +-
arch/x86/kvm/trace.h | 12 +-
arch/x86/lib/msr-reg-export.c | 4 +-
arch/x86/lib/msr-reg.S | 10 +-
arch/x86/oprofile/op_model_amd.c | 4 +-
arch/x86/vdso/vdso32-setup.c | 6 +-
arch/x86/xen/enlighten.c | 2 -
drivers/oprofile/oprofile_perf.c | 23 +-
include/linux/ftrace_event.h | 5 +-
include/linux/jump_label.h | 17 +-
include/linux/pci_ids.h | 11 +
include/linux/perf_event.h | 3 +
include/linux/sched.h | 1 -
include/linux/tracepoint.h | 2 +-
include/trace/ftrace.h | 1 +
kernel/events/core.c | 49 +-
kernel/events/uprobes.c | 461 +++--
kernel/trace/ftrace.c | 8 +-
kernel/trace/ring_buffer.c | 4 +
kernel/trace/trace.c | 33 +-
kernel/trace/trace.h | 8 +
kernel/trace/trace_functions_graph.c | 2 +-
kernel/trace/trace_output.c | 2 +-
tools/lib/traceevent/Makefile | 14 +-
tools/lib/traceevent/event-parse.c | 399 +++--
tools/lib/traceevent/event-parse.h | 7 +
tools/lib/traceevent/parse-filter.c | 86 +-
tools/perf/Documentation/perf-bench.txt | 78 +-
tools/perf/Documentation/perf-report.txt | 2 +-
tools/perf/Documentation/perf-top.txt | 2 +-
tools/perf/Makefile | 8 +-
tools/perf/bench/mem-memcpy.c | 84 +-
tools/perf/bench/mem-memset.c | 88 +-
tools/perf/builtin-bench.c | 4 +-
tools/perf/builtin-evlist.c | 2 +-
tools/perf/builtin-kmem.c | 37 +-
tools/perf/builtin-lock.c | 4 +-
tools/perf/builtin-record.c | 4 +-
tools/perf/builtin-report.c | 16 +-
tools/perf/builtin-sched.c | 38 +-
tools/perf/builtin-script.c | 106 +-
tools/perf/builtin-stat.c | 12 +-
tools/perf/builtin-test.c | 2 +-
tools/perf/builtin-top.c | 12 +-
tools/perf/config/feature-tests.mak | 13 +
tools/perf/ui/browsers/annotate.c | 4 +-
tools/perf/ui/browsers/hists.c | 210 ++-
tools/perf/ui/gtk/browser.c | 69 +-
tools/perf/ui/gtk/gtk.h | 31 +
tools/perf/ui/gtk/setup.c | 5 +
tools/perf/ui/gtk/util.c | 129 ++
tools/perf/ui/tui/setup.c | 6 +
tools/perf/ui/tui/util.c | 243 +++
tools/perf/ui/util.c | 277 +--
tools/perf/ui/util.h | 9 +-
tools/perf/util/debug.c | 2 +-
tools/perf/util/debug.h | 23 +-
tools/perf/util/evlist.c | 4 +-
tools/perf/util/evlist.h | 3 +
tools/perf/util/evsel.c | 227 ++-
tools/perf/util/evsel.h | 15 +-
tools/perf/util/header.c | 33 +-
tools/perf/util/hist.h | 1 +
tools/perf/util/include/linux/kernel.h | 10 +
tools/perf/util/map.h | 2 +-
tools/perf/util/parse-events-test.c | 179 +-
tools/perf/util/parse-events.c | 470 +++--
tools/perf/util/parse-events.h | 17 +-
tools/perf/util/parse-events.l | 134 +-
tools/perf/util/parse-events.y | 86 +-
tools/perf/util/pmu.c | 169 +-
tools/perf/util/pmu.h | 11 +-
.../perf/util/scripting-engines/trace-event-perl.c | 32 +-
.../util/scripting-engines/trace-event-python.c | 25 +-
tools/perf/util/session.c | 65 +-
tools/perf/util/session.h | 14 +-
tools/perf/util/sort.c | 49 +
tools/perf/util/sort.h | 2 +
tools/perf/util/string.c | 22 +
tools/perf/util/symbol.c | 94 +-
tools/perf/util/symbol.h | 1 +
tools/perf/util/top.c | 2 +-
tools/perf/util/trace-event-parse.c | 58 +-
tools/perf/util/trace-event-read.c | 97 +-
tools/perf/util/trace-event-scripting.c | 7 +-
tools/perf/util/trace-event.h | 38 +-
tools/perf/util/util.h | 2 +
109 files changed, 5782 insertions(+), 1706 deletions(-)
create mode 100644 arch/x86/kernel/cpu/perf_event_intel_uncore.c
create mode 100644 arch/x86/kernel/cpu/perf_event_intel_uncore.h
create mode 100644 tools/perf/ui/gtk/util.c
create mode 100644 tools/perf/ui/tui/util.c
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index db7c1f2..2da88c0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -313,8 +313,8 @@ struct kvm_pmu {
u64 counter_bitmask[2];
u64 global_ctrl_mask;
u8 version;
- struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC];
- struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED];
+ struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
+ struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
struct irq_work irq_work;
u64 reprogram_pmi;
};
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 084ef95..813ed10 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -115,8 +115,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
extern unsigned long long native_read_tsc(void);
-extern int native_rdmsr_safe_regs(u32 regs[8]);
-extern int native_wrmsr_safe_regs(u32 regs[8]);
+extern int rdmsr_safe_regs(u32 regs[8]);
+extern int wrmsr_safe_regs(u32 regs[8]);
static __always_inline unsigned long long __native_read_tsc(void)
{
@@ -187,43 +187,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
return err;
}
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
- u32 gprs[8] = { 0 };
- int err;
-
- gprs[1] = msr;
- gprs[7] = 0x9c5a203a;
-
- err = native_rdmsr_safe_regs(gprs);
-
- *p = gprs[0] | ((u64)gprs[2] << 32);
-
- return err;
-}
-
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
-{
- u32 gprs[8] = { 0 };
-
- gprs[0] = (u32)val;
- gprs[1] = msr;
- gprs[2] = val >> 32;
- gprs[7] = 0x9c5a203a;
-
- return native_wrmsr_safe_regs(gprs);
-}
-
-static inline int rdmsr_safe_regs(u32 regs[8])
-{
- return native_rdmsr_safe_regs(regs);
-}
-
-static inline int wrmsr_safe_regs(u32 regs[8])
-{
- return native_wrmsr_safe_regs(regs);
-}
-
#define rdtscl(low) \
((low) = (u32)__native_read_tsc())
@@ -237,6 +200,8 @@ do { \
(high) = (u32)(_l >> 32); \
} while (0)
+#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
+
#define rdtscp(low, high, aux) \
do { \
unsigned long long _val = native_read_tscp(&(aux)); \
@@ -248,8 +213,7 @@ do { \
#endif /* !CONFIG_PARAVIRT */
-
-#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val), \
+#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \
(u32)((val) >> 32))
#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6cbbabf..0b47ddb 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -128,21 +128,11 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err)
return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
}
-static inline int paravirt_rdmsr_regs(u32 *regs)
-{
- return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs);
-}
-
static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
{
return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
}
-static inline int paravirt_wrmsr_regs(u32 *regs)
-{
- return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs);
-}
-
/* These should all do BUG_ON(_err), but our headers are too tangled. */
#define rdmsr(msr, val1, val2) \
do { \
@@ -176,9 +166,6 @@ do { \
_err; \
})
-#define rdmsr_safe_regs(regs) paravirt_rdmsr_regs(regs)
-#define wrmsr_safe_regs(regs) paravirt_wrmsr_regs(regs)
-
static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
{
int err;
@@ -186,32 +173,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
*p = paravirt_read_msr(msr, &err);
return err;
}
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
- u32 gprs[8] = { 0 };
- int err;
-
- gprs[1] = msr;
- gprs[7] = 0x9c5a203a;
-
- err = paravirt_rdmsr_regs(gprs);
-
- *p = gprs[0] | ((u64)gprs[2] << 32);
-
- return err;
-}
-
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
-{
- u32 gprs[8] = { 0 };
-
- gprs[0] = (u32)val;
- gprs[1] = msr;
- gprs[2] = val >> 32;
- gprs[7] = 0x9c5a203a;
-
- return paravirt_wrmsr_regs(gprs);
-}
static inline u64 paravirt_read_tsc(void)
{
@@ -252,6 +213,8 @@ do { \
high = _l >> 32; \
} while (0)
+#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
+
static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
{
return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8e8b9a4..8613cbb 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -153,9 +153,7 @@ struct pv_cpu_ops {
/* MSR, PMC and TSR operations.
err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */
u64 (*read_msr)(unsigned int msr, int *err);
- int (*rdmsr_regs)(u32 *regs);
int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
- int (*wrmsr_regs)(u32 *regs);
u64 (*read_tsc)(void);
u64 (*read_pmc)(int counter);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 588f52e..c78f14a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -5,11 +5,10 @@
* Performance event hw details:
*/
-#define X86_PMC_MAX_GENERIC 32
-#define X86_PMC_MAX_FIXED 3
+#define INTEL_PMC_MAX_GENERIC 32
+#define INTEL_PMC_MAX_FIXED 3
+#define INTEL_PMC_IDX_FIXED 32
-#define X86_PMC_IDX_GENERIC 0
-#define X86_PMC_IDX_FIXED 32
#define X86_PMC_IDX_MAX 64
#define MSR_ARCH_PERFMON_PERFCTR0 0xc1
@@ -48,8 +47,7 @@
(X86_RAW_EVENT_MASK | \
AMD64_EVENTSEL_EVENT)
#define AMD64_NUM_COUNTERS 4
-#define AMD64_NUM_COUNTERS_F15H 6
-#define AMD64_NUM_COUNTERS_MAX AMD64_NUM_COUNTERS_F15H
+#define AMD64_NUM_COUNTERS_CORE 6
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
@@ -121,16 +119,16 @@ struct x86_pmu_capability {
/* Instr_Retired.Any: */
#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309
-#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0)
+#define INTEL_PMC_IDX_FIXED_INSTRUCTIONS (INTEL_PMC_IDX_FIXED + 0)
/* CPU_CLK_Unhalted.Core: */
#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a
-#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1)
+#define INTEL_PMC_IDX_FIXED_CPU_CYCLES (INTEL_PMC_IDX_FIXED + 1)
/* CPU_CLK_Unhalted.Ref: */
#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b
-#define X86_PMC_IDX_FIXED_REF_CYCLES (X86_PMC_IDX_FIXED + 2)
-#define X86_PMC_MSK_FIXED_REF_CYCLES (1ULL << X86_PMC_IDX_FIXED_REF_CYCLES)
+#define INTEL_PMC_IDX_FIXED_REF_CYCLES (INTEL_PMC_IDX_FIXED + 2)
+#define INTEL_PMC_MSK_FIXED_REF_CYCLES (1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES)
/*
* We model BTS tracing as another fixed-mode PMC.
@@ -139,7 +137,7 @@ struct x86_pmu_capability {
* values are used by actual fixed events and higher values are used
* to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
*/
-#define X86_PMC_IDX_FIXED_BTS (X86_PMC_IDX_FIXED + 16)
+#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16)
/*
* IBS cpuid feature detection
@@ -234,6 +232,7 @@ struct perf_guest_switch_msr {
extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
+extern void perf_check_microcode(void);
#else
static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
{
@@ -247,6 +246,7 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
}
static inline void perf_events_lapic_init(void) { }
+static inline void perf_check_microcode(void) { }
#endif
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 1e9bed1..f3971bb 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -48,7 +48,7 @@ struct arch_uprobe_task {
#endif
};
-extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm);
+extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 6ab6aa2..bac4c38 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -32,7 +32,9 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o
ifdef CONFIG_PERF_EVENTS
obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o
-obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o
endif
obj-$(CONFIG_X86_MCE) += mcheck/
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 146bb62..9d92e19 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -19,6 +19,39 @@
#include "cpu.h"
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+ struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+ u32 gprs[8] = { 0 };
+ int err;
+
+ WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__);
+
+ gprs[1] = msr;
+ gprs[7] = 0x9c5a203a;
+
+ err = rdmsr_safe_regs(gprs);
+
+ *p = gprs[0] | ((u64)gprs[2] << 32);
+
+ return err;
+}
+
+static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+{
+ struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+ u32 gprs[8] = { 0 };
+
+ WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__);
+
+ gprs[0] = (u32)val;
+ gprs[1] = msr;
+ gprs[2] = val >> 32;
+ gprs[7] = 0x9c5a203a;
+
+ return wrmsr_safe_regs(gprs);
+}
+
#ifdef CONFIG_X86_32
/*
* B step AMD K6 before B 9730xxxx have hardware bugs that can cause
@@ -586,9 +619,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
!cpu_has(c, X86_FEATURE_TOPOEXT)) {
u64 val;
- if (!rdmsrl_amd_safe(0xc0011005, &val)) {
+ if (!rdmsrl_safe(0xc0011005, &val)) {
val |= 1ULL << 54;
- wrmsrl_amd_safe(0xc0011005, val);
+ wrmsrl_safe(0xc0011005, val);
rdmsrl(0xc0011005, val);
if (val & (1ULL << 54)) {
set_cpu_cap(c, X86_FEATURE_TOPOEXT);
@@ -679,7 +712,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
if (err == 0) {
mask |= (1 << 10);
- checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask);
}
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6b9333b..5bbc082 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -947,7 +947,7 @@ static void __cpuinit __print_cpu_msr(void)
index_max = msr_range_array[i].max;
for (index = index_min; index < index_max; index++) {
- if (rdmsrl_amd_safe(index, &val))
+ if (rdmsrl_safe(index, &val))
continue;
printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c4706cf..29557aa 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -35,17 +35,6 @@
#include "perf_event.h"
-#if 0
-#undef wrmsrl
-#define wrmsrl(msr, val) \
-do { \
- trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\
- (unsigned long)(val)); \
- native_write_msr((msr), (u32)((u64)(val)), \
- (u32)((u64)(val) >> 32)); \
-} while (0)
-#endif
-
struct x86_pmu x86_pmu __read_mostly;
DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
@@ -74,7 +63,7 @@ u64 x86_perf_event_update(struct perf_event *event)
int idx = hwc->idx;
s64 delta;
- if (idx == X86_PMC_IDX_FIXED_BTS)
+ if (idx == INTEL_PMC_IDX_FIXED_BTS)
return 0;
/*
@@ -86,7 +75,7 @@ u64 x86_perf_event_update(struct perf_event *event)
*/
again:
prev_raw_count = local64_read(&hwc->prev_count);
- rdmsrl(hwc->event_base, new_raw_count);
+ rdpmcl(hwc->event_base_rdpmc, new_raw_count);
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count)
@@ -189,7 +178,7 @@ static void release_pmc_hardware(void) {}
static bool check_hw_exists(void)
{
- u64 val, val_new = 0;
+ u64 val, val_new = ~0;
int i, reg, ret = 0;
/*
@@ -222,8 +211,9 @@ static bool check_hw_exists(void)
* that don't trap on the MSR access and always return 0s.
*/
val = 0xabcdUL;
- ret = checking_wrmsrl(x86_pmu_event_addr(0), val);
- ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new);
+ reg = x86_pmu_event_addr(0);
+ ret = wrmsrl_safe(reg, val);
+ ret |= rdmsrl_safe(reg, &val_new);
if (ret || val != val_new)
goto msr_fail;
@@ -240,6 +230,7 @@ bios_fail:
msr_fail:
printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+ printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new);
return false;
}
@@ -388,7 +379,7 @@ int x86_pmu_hw_config(struct perf_event *event)
int precise = 0;
/* Support for constant skid */
- if (x86_pmu.pebs_active) {
+ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
precise++;
/* Support for IP fixup */
@@ -637,8 +628,8 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
c = sched->constraints[sched->state.event];
/* Prefer fixed purpose counters */
- if (x86_pmu.num_counters_fixed) {
- idx = X86_PMC_IDX_FIXED;
+ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
+ idx = INTEL_PMC_IDX_FIXED;
for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) {
if (!__test_and_set_bit(idx, sched->state.used))
goto done;
@@ -646,7 +637,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
}
/* Grab the first unused counter starting with idx */
idx = sched->state.counter;
- for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) {
+ for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
if (!__test_and_set_bit(idx, sched->state.used))
goto done;
}
@@ -704,8 +695,8 @@ static bool perf_sched_next_event(struct perf_sched *sched)
/*
* Assign a counter for each event.
*/
-static int perf_assign_events(struct event_constraint **constraints, int n,
- int wmin, int wmax, int *assign)
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int *assign)
{
struct perf_sched sched;
@@ -824,15 +815,17 @@ static inline void x86_assign_hw_event(struct perf_event *event,
hwc->last_cpu = smp_processor_id();
hwc->last_tag = ++cpuc->tags[i];
- if (hwc->idx == X86_PMC_IDX_FIXED_BTS) {
+ if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
hwc->config_base = 0;
hwc->event_base = 0;
- } else if (hwc->idx >= X86_PMC_IDX_FIXED) {
+ } else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED);
+ hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
+ hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
} else {
hwc->config_base = x86_pmu_config_addr(hwc->idx);
hwc->event_base = x86_pmu_event_addr(hwc->idx);
+ hwc->event_base_rdpmc = hwc->idx;
}
}
@@ -930,7 +923,7 @@ int x86_perf_event_set_period(struct perf_event *event)
s64 period = hwc->sample_period;
int ret = 0, idx = hwc->idx;
- if (idx == X86_PMC_IDX_FIXED_BTS)
+ if (idx == INTEL_PMC_IDX_FIXED_BTS)
return 0;
/*
@@ -1316,7 +1309,6 @@ static struct attribute_group x86_pmu_format_group = {
static int __init init_hw_perf_events(void)
{
struct x86_pmu_quirk *quirk;
- struct event_constraint *c;
int err;
pr_info("Performance Events: ");
@@ -1347,21 +1339,8 @@ static int __init init_hw_perf_events(void)
for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
quirk->func();
- if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
- WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
- x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
- x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
- }
- x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
-
- if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
- WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
- x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
- x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
- }
-
- x86_pmu.intel_ctrl |=
- ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+ if (!x86_pmu.intel_ctrl)
+ x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
perf_events_lapic_init();
register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
@@ -1370,22 +1349,6 @@ static int __init init_hw_perf_events(void)
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
0, x86_pmu.num_counters, 0);
- if (x86_pmu.event_constraints) {
- /*
- * event on fixed counter2 (REF_CYCLES) only works on this
- * counter, so do not extend mask to generic counters
- */
- for_each_event_constraint(c, x86_pmu.event_constraints) {
- if (c->cmask != X86_RAW_EVENT_MASK
- || c->idxmsk64 == X86_PMC_MSK_FIXED_REF_CYCLES) {
- continue;
- }
-
- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
- c->weight += x86_pmu.num_counters;
- }
- }
-
x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
@@ -1620,8 +1583,8 @@ static int x86_pmu_event_idx(struct perf_event *event)
if (!x86_pmu.attr_rdpmc)
return 0;
- if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
- idx -= X86_PMC_IDX_FIXED;
+ if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) {
+ idx -= INTEL_PMC_IDX_FIXED;
idx |= 1 << 30;
}
@@ -1649,7 +1612,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
struct device_attribute *attr,
const char *buf, size_t count)
{
- unsigned long val = simple_strtoul(buf, NULL, 0);
+ unsigned long val;
+ ssize_t ret;
+
+ ret = kstrtoul(buf, 0, &val);
+ if (ret)
+ return ret;
if (!!val != !!x86_pmu.attr_rdpmc) {
x86_pmu.attr_rdpmc = !!val;
@@ -1682,13 +1650,20 @@ static void x86_pmu_flush_branch_stack(void)
x86_pmu.flush_branch_stack();
}
+void perf_check_microcode(void)
+{
+ if (x86_pmu.check_microcode)
+ x86_pmu.check_microcode();
+}
+EXPORT_SYMBOL_GPL(perf_check_microcode);
+
static struct pmu pmu = {
.pmu_enable = x86_pmu_enable,
.pmu_disable = x86_pmu_disable,
- .attr_groups = x86_pmu_attr_groups,
+ .attr_groups = x86_pmu_attr_groups,
- .event_init = x86_pmu_event_init,
+ .event_init = x86_pmu_event_init,
.add = x86_pmu_add,
.del = x86_pmu_del,
@@ -1696,11 +1671,11 @@ static struct pmu pmu = {
.stop = x86_pmu_stop,
.read = x86_pmu_read,
- .start_txn = x86_pmu_start_txn,
- .cancel_txn = x86_pmu_cancel_txn,
- .commit_txn = x86_pmu_commit_txn,
+ .start_txn = x86_pmu_start_txn,
+ .cancel_txn = x86_pmu_cancel_txn,
+ .commit_txn = x86_pmu_commit_txn,
- .event_idx = x86_pmu_event_idx,
+ .event_idx = x86_pmu_event_idx,
.flush_branch_stack = x86_pmu_flush_branch_stack,
};
@@ -1863,7 +1838,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
else
misc |= PERF_RECORD_MISC_GUEST_KERNEL;
} else {
- if (user_mode(regs))
+ if (!kernel_ip(regs->ip))
misc |= PERF_RECORD_MISC_USER;
else
misc |= PERF_RECORD_MISC_KERNEL;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 7241e2f..a15df4b 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -14,6 +14,18 @@
#include <linux/perf_event.h>
+#if 0
+#undef wrmsrl
+#define wrmsrl(msr, val) \
+do { \
+ unsigned int _msr = (msr); \
+ u64 _val = (val); \
+ trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \
+ (unsigned long long)(_val)); \
+ native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \
+} while (0)
+#endif
+
/*
* | NHM/WSM | SNB |
* register -------------------------------
@@ -57,7 +69,7 @@ struct amd_nb {
};
/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS 4
+#define MAX_PEBS_EVENTS 8
/*
* A debug store configuration.
@@ -349,6 +361,8 @@ struct x86_pmu {
void (*cpu_starting)(int cpu);
void (*cpu_dying)(int cpu);
void (*cpu_dead)(int cpu);
+
+ void (*check_microcode)(void);
void (*flush_branch_stack)(void);
/*
@@ -360,12 +374,16 @@ struct x86_pmu {
/*
* Intel DebugStore bits
*/
- int bts, pebs;
- int bts_active, pebs_active;
+ int bts :1,
+ bts_active :1,
+ pebs :1,
+ pebs_active :1,
+ pebs_broken :1;
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
+ int max_pebs_events;
/*
* Intel LBR
@@ -468,6 +486,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
void x86_pmu_enable_all(int added);
+int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int *assign);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
void x86_pmu_stop(struct perf_event *event, int flags);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 11a4eb9..4528ae7 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -366,7 +366,7 @@ static void amd_pmu_cpu_starting(int cpu)
cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
- if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15)
+ if (boot_cpu_data.x86_max_cores < 2)
return;
nb_id = amd_get_nb_id(cpu);
@@ -422,35 +422,6 @@ static struct attribute *amd_format_attr[] = {
NULL,
};
-static __initconst const struct x86_pmu amd_pmu = {
- .name = "AMD",
- .handle_irq = x86_pmu_handle_irq,
- .disable_all = x86_pmu_disable_all,
- .enable_all = x86_pmu_enable_all,
- .enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
- .hw_config = amd_pmu_hw_config,
- .schedule_events = x86_schedule_events,
- .eventsel = MSR_K7_EVNTSEL0,
- .perfctr = MSR_K7_PERFCTR0,
- .event_map = amd_pmu_event_map,
- .max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = AMD64_NUM_COUNTERS,
- .cntval_bits = 48,
- .cntval_mask = (1ULL << 48) - 1,
- .apic = 1,
- /* use highest bit to detect overflow */
- .max_period = (1ULL << 47) - 1,
- .get_event_constraints = amd_get_event_constraints,
- .put_event_constraints = amd_put_event_constraints,
-
- .format_attrs = amd_format_attr,
-
- .cpu_prepare = amd_pmu_cpu_prepare,
- .cpu_starting = amd_pmu_cpu_starting,
- .cpu_dead = amd_pmu_cpu_dead,
-};
-
/* AMD Family 15h */
#define AMD_EVENT_TYPE_MASK 0x000000F0ULL
@@ -597,8 +568,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
}
}
-static __initconst const struct x86_pmu amd_pmu_f15h = {
- .name = "AMD Family 15h",
+static __initconst const struct x86_pmu amd_pmu = {
+ .name = "AMD",
.handle_irq = x86_pmu_handle_irq,
.disable_all = x86_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
@@ -606,50 +577,68 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
.disable = x86_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
- .eventsel = MSR_F15H_PERF_CTL,
- .perfctr = MSR_F15H_PERF_CTR,
+ .eventsel = MSR_K7_EVNTSEL0,
+ .perfctr = MSR_K7_PERFCTR0,
.event_map = amd_pmu_event_map,
.max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = AMD64_NUM_COUNTERS_F15H,
+ .num_counters = AMD64_NUM_COUNTERS,
.cntval_bits = 48,
.cntval_mask = (1ULL << 48) - 1,
.apic = 1,
/* use highest bit to detect overflow */
.max_period = (1ULL << 47) - 1,
- .get_event_constraints = amd_get_event_constraints_f15h,
- /* nortbridge counters not yet implemented: */
-#if 0
+ .get_event_constraints = amd_get_event_constraints,
.put_event_constraints = amd_put_event_constraints,
+ .format_attrs = amd_format_attr,
+
.cpu_prepare = amd_pmu_cpu_prepare,
- .cpu_dead = amd_pmu_cpu_dead,
-#endif
.cpu_starting = amd_pmu_cpu_starting,
- .format_attrs = amd_format_attr,
+ .cpu_dead = amd_pmu_cpu_dead,
};
+static int setup_event_constraints(void)
+{
+ if (boot_cpu_data.x86 >= 0x15)
+ x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
+ return 0;
+}
+
+static int setup_perfctr_core(void)
+{
+ if (!cpu_has_perfctr_core) {
+ WARN(x86_pmu.get_event_constraints == amd_get_event_constraints_f15h,
+ KERN_ERR "Odd, counter constraints enabled but no core perfctrs detected!");
+ return -ENODEV;
+ }
+
+ WARN(x86_pmu.get_event_constraints == amd_get_event_constraints,
+ KERN_ERR "hw perf events core counters need constraints handler!");
+
+ /*
+ * If core performance counter extensions exists, we must use
+ * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also
+ * x86_pmu_addr_offset().
+ */
+ x86_pmu.eventsel = MSR_F15H_PERF_CTL;
+ x86_pmu.perfctr = MSR_F15H_PERF_CTR;
+ x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE;
+
+ printk(KERN_INFO "perf: AMD core performance counters detected\n");
+
+ return 0;
+}
+
__init int amd_pmu_init(void)
{
/* Performance-monitoring supported from K7 and later: */
if (boot_cpu_data.x86 < 6)
return -ENODEV;
- /*
- * If core performance counter extensions exists, it must be
- * family 15h, otherwise fail. See x86_pmu_addr_offset().
- */
- switch (boot_cpu_data.x86) {
- case 0x15:
- if (!cpu_has_perfctr_core)
- return -ENODEV;
- x86_pmu = amd_pmu_f15h;
- break;
- default:
- if (cpu_has_perfctr_core)
- return -ENODEV;
- x86_pmu = amd_pmu;
- break;
- }
+ x86_pmu = amd_pmu;
+
+ setup_event_constraints();
+ setup_perfctr_core();
/* Events are common for all AMDs */
memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 187c294..1f4c8ad 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -21,14 +21,14 @@
*/
static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x003c,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x412e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
- [PERF_COUNT_HW_BUS_CYCLES] = 0x013c,
- [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x003c,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x412e,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
+ [PERF_COUNT_HW_BUS_CYCLES] = 0x013c,
+ [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */
};
static struct event_constraint intel_core_event_constraints[] __read_mostly =
@@ -747,7 +747,7 @@ static void intel_pmu_disable_all(void)
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
- if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+ if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
intel_pmu_pebs_disable_all();
@@ -763,9 +763,9 @@ static void intel_pmu_enable_all(int added)
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
- if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+ if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
struct perf_event *event =
- cpuc->events[X86_PMC_IDX_FIXED_BTS];
+ cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
if (WARN_ON_ONCE(!event))
return;
@@ -871,7 +871,7 @@ static inline void intel_pmu_ack_status(u64 ack)
static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
{
- int idx = hwc->idx - X86_PMC_IDX_FIXED;
+ int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, mask;
mask = 0xfULL << (idx * 4);
@@ -886,7 +886,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
+ if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
intel_pmu_disable_bts();
intel_pmu_drain_bts_buffer();
return;
@@ -915,7 +915,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
{
- int idx = hwc->idx - X86_PMC_IDX_FIXED;
+ int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, bits, mask;
/*
@@ -949,7 +949,7 @@ static void intel_pmu_enable_event(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
+ if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
if (!__this_cpu_read(cpu_hw_events.enabled))
return;
@@ -1003,11 +1003,11 @@ static void intel_pmu_reset(void)
printk("clearing PMU state on CPU#%d\n", smp_processor_id());
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- checking_wrmsrl(x86_pmu_config_addr(idx), 0ull);
- checking_wrmsrl(x86_pmu_event_addr(idx), 0ull);
+ wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
+ wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
}
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
- checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+ wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
if (ds)
ds->bts_index = ds->bts_buffer_base;
@@ -1712,11 +1712,56 @@ static __init void intel_clovertown_quirk(void)
x86_pmu.pebs_constraints = NULL;
}
+static int intel_snb_pebs_broken(int cpu)
+{
+ u32 rev = UINT_MAX; /* default to broken for unknown models */
+
+ switch (cpu_data(cpu).x86_model) {
+ case 42: /* SNB */
+ rev = 0x28;
+ break;
+
+ case 45: /* SNB-EP */
+ switch (cpu_data(cpu).x86_mask) {
+ case 6: rev = 0x618; break;
+ case 7: rev = 0x70c; break;
+ }
+ }
+
+ return (cpu_data(cpu).microcode < rev);
+}
+
+static void intel_snb_check_microcode(void)
+{
+ int pebs_broken = 0;
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ if ((pebs_broken = intel_snb_pebs_broken(cpu)))
+ break;
+ }
+ put_online_cpus();
+
+ if (pebs_broken == x86_pmu.pebs_broken)
+ return;
+
+ /*
+ * Serialized by the microcode lock..
+ */
+ if (x86_pmu.pebs_broken) {
+ pr_info("PEBS enabled due to microcode update\n");
+ x86_pmu.pebs_broken = 0;
+ } else {
+ pr_info("PEBS disabled due to CPU errata, please upgrade microcode\n");
+ x86_pmu.pebs_broken = 1;
+ }
+}
+
static __init void intel_sandybridge_quirk(void)
{
- printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
- x86_pmu.pebs = 0;
- x86_pmu.pebs_constraints = NULL;
+ x86_pmu.check_microcode = intel_snb_check_microcode;
+ intel_snb_check_microcode();
}
static const struct { int id; char *name; } intel_arch_events_map[] __initconst = {
@@ -1765,6 +1810,7 @@ __init int intel_pmu_init(void)
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
+ struct event_constraint *c;
unsigned int unused;
int version;
@@ -1800,6 +1846,8 @@ __init int intel_pmu_init(void)
x86_pmu.events_maskl = ebx.full;
x86_pmu.events_mask_len = eax.split.mask_length;
+ x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
+
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
* assume at least 3 events:
@@ -1951,5 +1999,37 @@ __init int intel_pmu_init(void)
}
}
+ if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
+ WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
+ x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
+ x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
+ }
+ x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+
+ if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
+ WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
+ x86_pmu.num_counters_fixed, INTEL_PMC_MAX_FIXED);
+ x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
+ }
+
+ x86_pmu.intel_ctrl |=
+ ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+
+ if (x86_pmu.event_constraints) {
+ /*
+ * event on fixed counter2 (REF_CYCLES) only works on this
+ * counter, so do not extend mask to generic counters
+ */
+ for_each_event_constraint(c, x86_pmu.event_constraints) {
+ if (c->cmask != X86_RAW_EVENT_MASK
+ || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+ continue;
+ }
+
+ c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+ c->weight += x86_pmu.num_counters;
+ }
+ }
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 35e2192..629ae0b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -248,7 +248,7 @@ void reserve_ds_buffers(void)
*/
struct event_constraint bts_constraint =
- EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
+ EVENT_CONSTRAINT(0, 1ULL << INTEL_PMC_IDX_FIXED_BTS, 0);
void intel_pmu_enable_bts(u64 config)
{
@@ -295,7 +295,7 @@ int intel_pmu_drain_bts_buffer(void)
u64 to;
u64 flags;
};
- struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
+ struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
struct bts_record *at, *top;
struct perf_output_handle handle;
struct perf_event_header header;
@@ -620,7 +620,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
* Should not happen, we program the threshold at 1 and do not
* set a reset value.
*/
- WARN_ON_ONCE(n > 1);
+ WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
at += n - 1;
__intel_pmu_pebs_event(event, iregs, at);
@@ -651,10 +651,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
* Should not happen, we program the threshold at 1 and do not
* set a reset value.
*/
- WARN_ON_ONCE(n > MAX_PEBS_EVENTS);
+ WARN_ONCE(n > x86_pmu.max_pebs_events, "Unexpected number of pebs records %d\n", n);
for ( ; at < top; at++) {
- for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) {
+ for_each_set_bit(bit, (unsigned long *)&at->status, x86_pmu.max_pebs_events) {
event = cpuc->events[bit];
if (!test_bit(bit, cpuc->active_mask))
continue;
@@ -670,7 +670,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
break;
}
- if (!event || bit >= MAX_PEBS_EVENTS)
+ if (!event || bit >= x86_pmu.max_pebs_events)
continue;
__intel_pmu_pebs_event(event, iregs, at);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
new file mode 100644
index 0000000..19faffc
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -0,0 +1,1850 @@
+#include "perf_event_intel_uncore.h"
+
+static struct intel_uncore_type *empty_uncore[] = { NULL, };
+static struct intel_uncore_type **msr_uncores = empty_uncore;
+static struct intel_uncore_type **pci_uncores = empty_uncore;
+/* pci bus to socket mapping */
+static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
+
+static DEFINE_RAW_SPINLOCK(uncore_box_lock);
+
+/* mask of cpus that collect uncore events */
+static cpumask_t uncore_cpu_mask;
+
+/* constraint for the fixed counter */
+static struct event_constraint constraint_fixed =
+ EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL);
+static struct event_constraint constraint_empty =
+ EVENT_CONSTRAINT(0, 0, 0);
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
+DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
+DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_brand0, filter_brand0, "config1:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(filter_brand1, filter_brand1, "config1:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(filter_brand2, filter_brand2, "config1:16-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_brand3, filter_brand3, "config1:24-31");
+
+/* Sandy Bridge-EP uncore support */
+static struct intel_uncore_type snbep_uncore_cbox;
+static struct intel_uncore_type snbep_uncore_pcu;
+
+static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+ u32 config;
+
+ pci_read_config_dword(pdev, box_ctl, &config);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+}
+
+static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+ u32 config;
+
+ pci_read_config_dword(pdev, box_ctl, &config);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+}
+
+static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config |
+ SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config);
+}
+
+static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 count;
+
+ pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
+ pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
+ return count;
+}
+
+static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL,
+ SNBEP_PMON_BOX_CTL_INT);
+}
+
+static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ u64 config;
+ unsigned msr;
+
+ msr = uncore_msr_box_ctl(box);
+ if (msr) {
+ rdmsrl(msr, config);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ wrmsrl(msr, config);
+ return;
+ }
+}
+
+static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ u64 config;
+ unsigned msr;
+
+ msr = uncore_msr_box_ctl(box);
+ if (msr) {
+ rdmsrl(msr, config);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ wrmsrl(msr, config);
+ return;
+ }
+}
+
+static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE)
+ wrmsrl(reg1->reg, reg1->config);
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ wrmsrl(hwc->config_base, hwc->config);
+}
+
+static u64 snbep_uncore_msr_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 count;
+
+ rdmsrl(hwc->event_base, count);
+ return count;
+}
+
+static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+ if (msr)
+ wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static struct event_constraint *
+snbep_uncore_get_constraint(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct intel_uncore_extra_reg *er;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ unsigned long flags;
+ bool ok = false;
+
+ if (reg1->idx == EXTRA_REG_NONE || (box->phys_id >= 0 && reg1->alloc))
+ return NULL;
+
+ er = &box->shared_regs[reg1->idx];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ if (!atomic_read(&er->ref) || er->config1 == reg1->config) {
+ atomic_inc(&er->ref);
+ er->config1 = reg1->config;
+ ok = true;
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ if (ok) {
+ if (box->phys_id >= 0)
+ reg1->alloc = 1;
+ return NULL;
+ }
+ return &constraint_empty;
+}
+
+static void snbep_uncore_put_constraint(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct intel_uncore_extra_reg *er;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+
+ if (box->phys_id < 0 || !reg1->alloc)
+ return;
+
+ er = &box->shared_regs[reg1->idx];
+ atomic_dec(&er->ref);
+ reg1->alloc = 0;
+}
+
+static int snbep_uncore_hw_config(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (box->pmu->type == &snbep_uncore_cbox) {
+ reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+ SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 &
+ SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK;
+ } else if (box->pmu->type == &snbep_uncore_pcu) {
+ reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+ reg1->config = event->attr.config1 &
+ SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK;
+ } else {
+ return 0;
+ }
+ reg1->idx = 0;
+ return 0;
+}
+
+static struct attribute *snbep_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_ubox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_cbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid.attr,
+ &format_attr_filter_nid.attr,
+ &format_attr_filter_state.attr,
+ &format_attr_filter_opc.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_pcu_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_occ_sel.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ &format_attr_occ_invert.attr,
+ &format_attr_occ_edge.attr,
+ &format_attr_filter_brand0.attr,
+ &format_attr_filter_brand1.attr,
+ &format_attr_filter_brand2.attr,
+ &format_attr_filter_brand3.attr,
+ NULL,
+};
+
+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_write, "event=0x04,umask=0x0c"),
+ { /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc snbep_uncore_qpi_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
+ INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
+ INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute_group snbep_uncore_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_ubox_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_cbox_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_pcu_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_pcu_formats_attr,
+};
+
+static struct intel_uncore_ops snbep_uncore_msr_ops = {
+ .init_box = snbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = snbep_uncore_msr_enable_event,
+ .read_counter = snbep_uncore_msr_read_counter,
+ .get_constraint = snbep_uncore_get_constraint,
+ .put_constraint = snbep_uncore_put_constraint,
+ .hw_config = snbep_uncore_hw_config,
+};
+
+static struct intel_uncore_ops snbep_uncore_pci_ops = {
+ .init_box = snbep_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_uncore_pci_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+};
+
+static struct event_constraint snbep_uncore_cbox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
+ EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
+ UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snbep_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNBEP_U_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &snbep_uncore_msr_ops,
+ .format_group = &snbep_uncore_ubox_format_group,
+};
+
+static struct intel_uncore_type snbep_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .num_boxes = 8,
+ .perf_ctr_bits = 44,
+ .event_ctl = SNBEP_C0_MSR_PMON_CTL0,
+ .perf_ctr = SNBEP_C0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL,
+ .msr_offset = SNBEP_CBO_MSR_OFFSET,
+ .num_shared_regs = 1,
+ .constraints = snbep_uncore_cbox_constraints,
+ .ops = &snbep_uncore_msr_ops,
+ .format_group = &snbep_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_type snbep_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snbep_uncore_msr_ops,
+ .format_group = &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *snbep_msr_uncores[] = {
+ &snbep_uncore_ubox,
+ &snbep_uncore_cbox,
+ &snbep_uncore_pcu,
+ NULL,
+};
+
+#define SNBEP_UNCORE_PCI_COMMON_INIT() \
+ .perf_ctr = SNBEP_PCI_PMON_CTR0, \
+ .event_ctl = SNBEP_PCI_PMON_CTL0, \
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \
+ .ops = &snbep_uncore_pci_ops, \
+ .format_group = &snbep_uncore_format_group
+
+static struct intel_uncore_type snbep_uncore_ha = {
+ .name = "ha",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 4,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+ .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+ .event_descs = snbep_uncore_imc_events,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_qpi = {
+ .name = "qpi",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_descs = snbep_uncore_qpi_events,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+
+static struct intel_uncore_type snbep_uncore_r2pcie = {
+ .name = "r2pcie",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r2pcie_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_r3qpi = {
+ .name = "r3qpi",
+ .num_counters = 3,
+ .num_boxes = 2,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r3qpi_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type *snbep_pci_uncores[] = {
+ &snbep_uncore_ha,
+ &snbep_uncore_imc,
+ &snbep_uncore_qpi,
+ &snbep_uncore_r2pcie,
+ &snbep_uncore_r3qpi,
+ NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
+ { /* Home Agent */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
+ .driver_data = (unsigned long)&snbep_uncore_ha,
+ },
+ { /* MC Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* MC Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* MC Channel 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* MC Channel 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
+ .driver_data = (unsigned long)&snbep_uncore_imc,
+ },
+ { /* QPI Port 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
+ .driver_data = (unsigned long)&snbep_uncore_qpi,
+ },
+ { /* QPI Port 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
+ .driver_data = (unsigned long)&snbep_uncore_qpi,
+ },
+ { /* P2PCIe */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
+ .driver_data = (unsigned long)&snbep_uncore_r2pcie,
+ },
+ { /* R3QPI Link 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
+ .driver_data = (unsigned long)&snbep_uncore_r3qpi,
+ },
+ { /* R3QPI Link 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
+ .driver_data = (unsigned long)&snbep_uncore_r3qpi,
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver snbep_uncore_pci_driver = {
+ .name = "snbep_uncore",
+ .id_table = snbep_uncore_pci_ids,
+};
+
+/*
+ * build pci bus to socket mapping
+ */
+static void snbep_pci2phy_map_init(void)
+{
+ struct pci_dev *ubox_dev = NULL;
+ int i, bus, nodeid;
+ u32 config;
+
+ while (1) {
+ /* find the UBOX device */
+ ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX,
+ ubox_dev);
+ if (!ubox_dev)
+ break;
+ bus = ubox_dev->bus->number;
+ /* get the Node ID of the local register */
+ pci_read_config_dword(ubox_dev, 0x40, &config);
+ nodeid = config;
+ /* get the Node ID mapping */
+ pci_read_config_dword(ubox_dev, 0x54, &config);
+ /*
+ * every three bits in the Node ID mapping register maps
+ * to a particular node.
+ */
+ for (i = 0; i < 8; i++) {
+ if (nodeid == ((config >> (3 * i)) & 0x7)) {
+ pcibus_to_physid[bus] = i;
+ break;
+ }
+ }
+ };
+ return;
+}
+/* end of Sandy Bridge-EP uncore support */
+
+
+/* Sandy Bridge uncore support */
+static void snb_uncore_msr_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ else
+ wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+}
+
+static void snb_uncore_msr_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ wrmsrl(event->hw.config_base, 0);
+}
+
+static u64 snb_uncore_msr_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ u64 count;
+ rdmsrl(event->hw.event_base, count);
+ return count;
+}
+
+static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ if (box->pmu->pmu_idx == 0) {
+ wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+ SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+ }
+}
+
+static struct attribute *snb_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask5.attr,
+ NULL,
+};
+
+static struct attribute_group snb_uncore_format_group = {
+ .name = "format",
+ .attrs = snb_uncore_formats_attr,
+};
+
+static struct intel_uncore_ops snb_uncore_msr_ops = {
+ .init_box = snb_uncore_msr_init_box,
+ .disable_event = snb_uncore_msr_disable_event,
+ .enable_event = snb_uncore_msr_enable_event,
+ .read_counter = snb_uncore_msr_read_counter,
+};
+
+static struct event_constraint snb_uncore_cbox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snb_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 2,
+ .num_boxes = 4,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNB_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = SNB_UNC_CBO_MSR_OFFSET,
+ .constraints = snb_uncore_cbox_constraints,
+ .ops = &snb_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+};
+
+static struct intel_uncore_type *snb_msr_uncores[] = {
+ &snb_uncore_cbox,
+ NULL,
+};
+/* end of Sandy Bridge uncore support */
+
+/* Nehalem uncore support */
+static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHM_UNC_PERF_GLOBAL_CTL,
+ NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+}
+
+static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ else
+ wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+}
+
+static struct attribute *nhm_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask8.attr,
+ NULL,
+};
+
+static struct attribute_group nhm_uncore_format_group = {
+ .name = "format",
+ .attrs = nhm_uncore_formats_attr,
+};
+
+static struct uncore_event_desc nhm_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhm_uncore_msr_ops = {
+ .disable_box = nhm_uncore_msr_disable_box,
+ .enable_box = nhm_uncore_msr_enable_box,
+ .disable_event = snb_uncore_msr_disable_event,
+ .enable_event = nhm_uncore_msr_enable_event,
+ .read_counter = snb_uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type nhm_uncore = {
+ .name = "",
+ .num_counters = 8,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .event_ctl = NHM_UNC_PERFEVTSEL0,
+ .perf_ctr = NHM_UNC_UNCORE_PMC0,
+ .fixed_ctr = NHM_UNC_FIXED_CTR,
+ .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL,
+ .event_mask = NHM_UNC_RAW_EVENT_MASK,
+ .event_descs = nhm_uncore_events,
+ .ops = &nhm_uncore_msr_ops,
+ .format_group = &nhm_uncore_format_group,
+};
+
+static struct intel_uncore_type *nhm_msr_uncores[] = {
+ &nhm_uncore,
+ NULL,
+};
+/* end of Nehalem uncore support */
+
+static void uncore_assign_hw_event(struct intel_uncore_box *box,
+ struct perf_event *event, int idx)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ hwc->idx = idx;
+ hwc->last_tag = ++box->tags[idx];
+
+ if (hwc->idx == UNCORE_PMC_IDX_FIXED) {
+ hwc->event_base = uncore_fixed_ctr(box);
+ hwc->config_base = uncore_fixed_ctl(box);
+ return;
+ }
+
+ hwc->config_base = uncore_event_ctl(box, hwc->idx);
+ hwc->event_base = uncore_perf_ctr(box, hwc->idx);
+}
+
+static void uncore_perf_event_update(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ u64 prev_count, new_count, delta;
+ int shift;
+
+ if (event->hw.idx >= UNCORE_PMC_IDX_FIXED)
+ shift = 64 - uncore_fixed_ctr_bits(box);
+ else
+ shift = 64 - uncore_perf_ctr_bits(box);
+
+ /* the hrtimer might modify the previous event value */
+again:
+ prev_count = local64_read(&event->hw.prev_count);
+ new_count = uncore_read_counter(box, event);
+ if (local64_xchg(&event->hw.prev_count, new_count) != prev_count)
+ goto again;
+
+ delta = (new_count << shift) - (prev_count << shift);
+ delta >>= shift;
+
+ local64_add(delta, &event->count);
+}
+
+/*
+ * The overflow interrupt is unavailable for SandyBridge-EP, is broken
+ * for SandyBridge. So we use hrtimer to periodically poll the counter
+ * to avoid overflow.
+ */
+static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
+{
+ struct intel_uncore_box *box;
+ unsigned long flags;
+ int bit;
+
+ box = container_of(hrtimer, struct intel_uncore_box, hrtimer);
+ if (!box->n_active || box->cpu != smp_processor_id())
+ return HRTIMER_NORESTART;
+ /*
+ * disable local interrupt to prevent uncore_pmu_event_start/stop
+ * to interrupt the update process
+ */
+ local_irq_save(flags);
+
+ for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
+ uncore_perf_event_update(box, box->events[bit]);
+
+ local_irq_restore(flags);
+
+ hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL));
+ return HRTIMER_RESTART;
+}
+
+static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
+{
+ __hrtimer_start_range_ns(&box->hrtimer,
+ ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0,
+ HRTIMER_MODE_REL_PINNED, 0);
+}
+
+static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
+{
+ hrtimer_cancel(&box->hrtimer);
+}
+
+static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
+{
+ hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ box->hrtimer.function = uncore_pmu_hrtimer;
+}
+
+struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
+ int cpu)
+{
+ struct intel_uncore_box *box;
+ int i, size;
+
+ size = sizeof(*box) + type->num_shared_regs *
+ sizeof(struct intel_uncore_extra_reg);
+
+ box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu));
+ if (!box)
+ return NULL;
+
+ for (i = 0; i < type->num_shared_regs; i++)
+ raw_spin_lock_init(&box->shared_regs[i].lock);
+
+ uncore_pmu_init_hrtimer(box);
+ atomic_set(&box->refcnt, 1);
+ box->cpu = -1;
+ box->phys_id = -1;
+
+ return box;
+}
+
+static struct intel_uncore_box *
+uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+{
+ static struct intel_uncore_box *box;
+
+ box = *per_cpu_ptr(pmu->box, cpu);
+ if (box)
+ return box;
+
+ raw_spin_lock(&uncore_box_lock);
+ list_for_each_entry(box, &pmu->box_list, list) {
+ if (box->phys_id == topology_physical_package_id(cpu)) {
+ atomic_inc(&box->refcnt);
+ *per_cpu_ptr(pmu->box, cpu) = box;
+ break;
+ }
+ }
+ raw_spin_unlock(&uncore_box_lock);
+
+ return *per_cpu_ptr(pmu->box, cpu);
+}
+
+static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+ return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+ /*
+ * perf core schedules event on the basis of cpu, uncore events are
+ * collected by one of the cpus inside a physical package.
+ */
+ return uncore_pmu_to_box(uncore_event_to_pmu(event),
+ smp_processor_id());
+}
+
+static int uncore_collect_events(struct intel_uncore_box *box,
+ struct perf_event *leader, bool dogrp)
+{
+ struct perf_event *event;
+ int n, max_count;
+
+ max_count = box->pmu->type->num_counters;
+ if (box->pmu->type->fixed_ctl)
+ max_count++;
+
+ if (box->n_events >= max_count)
+ return -EINVAL;
+
+ n = box->n_events;
+ box->event_list[n] = leader;
+ n++;
+ if (!dogrp)
+ return n;
+
+ list_for_each_entry(event, &leader->sibling_list, group_entry) {
+ if (event->state <= PERF_EVENT_STATE_OFF)
+ continue;
+
+ if (n >= max_count)
+ return -EINVAL;
+
+ box->event_list[n] = event;
+ n++;
+ }
+ return n;
+}
+
+static struct event_constraint *
+uncore_get_event_constraint(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct intel_uncore_type *type = box->pmu->type;
+ struct event_constraint *c;
+
+ if (type->ops->get_constraint) {
+ c = type->ops->get_constraint(box, event);
+ if (c)
+ return c;
+ }
+
+ if (event->hw.config == ~0ULL)
+ return &constraint_fixed;
+
+ if (type->constraints) {
+ for_each_event_constraint(c, type->constraints) {
+ if ((event->hw.config & c->cmask) == c->code)
+ return c;
+ }
+ }
+
+ return &type->unconstrainted;
+}
+
+static void uncore_put_event_constraint(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ if (box->pmu->type->ops->put_constraint)
+ box->pmu->type->ops->put_constraint(box, event);
+}
+
+static int uncore_assign_events(struct intel_uncore_box *box,
+ int assign[], int n)
+{
+ unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
+ struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX];
+ int i, wmin, wmax, ret = 0;
+ struct hw_perf_event *hwc;
+
+ bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
+
+ for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
+ c = uncore_get_event_constraint(box, box->event_list[i]);
+ constraints[i] = c;
+ wmin = min(wmin, c->weight);
+ wmax = max(wmax, c->weight);
+ }
+
+ /* fastpath, try to reuse previous register */
+ for (i = 0; i < n; i++) {
+ hwc = &box->event_list[i]->hw;
+ c = constraints[i];
+
+ /* never assigned */
+ if (hwc->idx == -1)
+ break;
+
+ /* constraint still honored */
+ if (!test_bit(hwc->idx, c->idxmsk))
+ break;
+
+ /* not already used */
+ if (test_bit(hwc->idx, used_mask))
+ break;
+
+ __set_bit(hwc->idx, used_mask);
+ if (assign)
+ assign[i] = hwc->idx;
+ }
+ /* slow path */
+ if (i != n)
+ ret = perf_assign_events(constraints, n, wmin, wmax, assign);
+
+ if (!assign || ret) {
+ for (i = 0; i < n; i++)
+ uncore_put_event_constraint(box, box->event_list[i]);
+ }
+ return ret ? -EINVAL : 0;
+}
+
+static void uncore_pmu_event_start(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ int idx = event->hw.idx;
+
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
+ return;
+
+ event->hw.state = 0;
+ box->events[idx] = event;
+ box->n_active++;
+ __set_bit(idx, box->active_mask);
+
+ local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
+ uncore_enable_event(box, event);
+
+ if (box->n_active == 1) {
+ uncore_enable_box(box);
+ uncore_pmu_start_hrtimer(box);
+ }
+}
+
+static void uncore_pmu_event_stop(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (__test_and_clear_bit(hwc->idx, box->active_mask)) {
+ uncore_disable_event(box, event);
+ box->n_active--;
+ box->events[hwc->idx] = NULL;
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+
+ if (box->n_active == 0) {
+ uncore_disable_box(box);
+ uncore_pmu_cancel_hrtimer(box);
+ }
+ }
+
+ if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+ /*
+ * Drain the remaining delta count out of a event
+ * that we are disabling:
+ */
+ uncore_perf_event_update(box, event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+}
+
+static int uncore_pmu_event_add(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+ int assign[UNCORE_PMC_IDX_MAX];
+ int i, n, ret;
+
+ if (!box)
+ return -ENODEV;
+
+ ret = n = uncore_collect_events(box, event, false);
+ if (ret < 0)
+ return ret;
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+ if (!(flags & PERF_EF_START))
+ hwc->state |= PERF_HES_ARCH;
+
+ ret = uncore_assign_events(box, assign, n);
+ if (ret)
+ return ret;
+
+ /* save events moving to new counters */
+ for (i = 0; i < box->n_events; i++) {
+ event = box->event_list[i];
+ hwc = &event->hw;
+
+ if (hwc->idx == assign[i] &&
+ hwc->last_tag == box->tags[assign[i]])
+ continue;
+ /*
+ * Ensure we don't accidentally enable a stopped
+ * counter simply because we rescheduled.
+ */
+ if (hwc->state & PERF_HES_STOPPED)
+ hwc->state |= PERF_HES_ARCH;
+
+ uncore_pmu_event_stop(event, PERF_EF_UPDATE);
+ }
+
+ /* reprogram moved events into new counters */
+ for (i = 0; i < n; i++) {
+ event = box->event_list[i];
+ hwc = &event->hw;
+
+ if (hwc->idx != assign[i] ||
+ hwc->last_tag != box->tags[assign[i]])
+ uncore_assign_hw_event(box, event, assign[i]);
+ else if (i < box->n_events)
+ continue;
+
+ if (hwc->state & PERF_HES_ARCH)
+ continue;
+
+ uncore_pmu_event_start(event, 0);
+ }
+ box->n_events = n;
+
+ return 0;
+}
+
+static void uncore_pmu_event_del(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ int i;
+
+ uncore_pmu_event_stop(event, PERF_EF_UPDATE);
+
+ for (i = 0; i < box->n_events; i++) {
+ if (event == box->event_list[i]) {
+ uncore_put_event_constraint(box, event);
+
+ while (++i < box->n_events)
+ box->event_list[i - 1] = box->event_list[i];
+
+ --box->n_events;
+ break;
+ }
+ }
+
+ event->hw.idx = -1;
+ event->hw.last_tag = ~0ULL;
+}
+
+static void uncore_pmu_event_read(struct perf_event *event)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ uncore_perf_event_update(box, event);
+}
+
+/*
+ * validation ensures the group can be loaded onto the
+ * PMU if it was the only group available.
+ */
+static int uncore_validate_group(struct intel_uncore_pmu *pmu,
+ struct perf_event *event)
+{
+ struct perf_event *leader = event->group_leader;
+ struct intel_uncore_box *fake_box;
+ int ret = -EINVAL, n;
+
+ fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+ if (!fake_box)
+ return -ENOMEM;
+
+ fake_box->pmu = pmu;
+ /*
+ * the event is not yet connected with its
+ * siblings therefore we must first collect
+ * existing siblings, then add the new event
+ * before we can simulate the scheduling
+ */
+ n = uncore_collect_events(fake_box, leader, true);
+ if (n < 0)
+ goto out;
+
+ fake_box->n_events = n;
+ n = uncore_collect_events(fake_box, event, false);
+ if (n < 0)
+ goto out;
+
+ fake_box->n_events = n;
+
+ ret = uncore_assign_events(fake_box, NULL, n);
+out:
+ kfree(fake_box);
+ return ret;
+}
+
+int uncore_pmu_event_init(struct perf_event *event)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ struct hw_perf_event *hwc = &event->hw;
+ int ret;
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ pmu = uncore_event_to_pmu(event);
+ /* no device found for this pmu */
+ if (pmu->func_id < 0)
+ return -ENOENT;
+
+ /*
+ * Uncore PMU does measure at all privilege level all the time.
+ * So it doesn't make sense to specify any exclude bits.
+ */
+ if (event->attr.exclude_user || event->attr.exclude_kernel ||
+ event->attr.exclude_hv || event->attr.exclude_idle)
+ return -EINVAL;
+
+ /* Sampling not supported yet */
+ if (hwc->sample_period)
+ return -EINVAL;
+
+ /*
+ * Place all uncore events for a particular physical package
+ * onto a single cpu
+ */
+ if (event->cpu < 0)
+ return -EINVAL;
+ box = uncore_pmu_to_box(pmu, event->cpu);
+ if (!box || box->cpu < 0)
+ return -EINVAL;
+ event->cpu = box->cpu;
+
+ event->hw.idx = -1;
+ event->hw.last_tag = ~0ULL;
+ event->hw.extra_reg.idx = EXTRA_REG_NONE;
+
+ if (event->attr.config == UNCORE_FIXED_EVENT) {
+ /* no fixed counter */
+ if (!pmu->type->fixed_ctl)
+ return -EINVAL;
+ /*
+ * if there is only one fixed counter, only the first pmu
+ * can access the fixed counter
+ */
+ if (pmu->type->single_fixed && pmu->pmu_idx > 0)
+ return -EINVAL;
+ hwc->config = ~0ULL;
+ } else {
+ hwc->config = event->attr.config & pmu->type->event_mask;
+ if (pmu->type->ops->hw_config) {
+ ret = pmu->type->ops->hw_config(box, event);
+ if (ret)
+ return ret;
+ }
+ }
+
+ if (event->group_leader != event)
+ ret = uncore_validate_group(pmu, event);
+ else
+ ret = 0;
+
+ return ret;
+}
+
+static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
+{
+ int ret;
+
+ pmu->pmu = (struct pmu) {
+ .attr_groups = pmu->type->attr_groups,
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = uncore_pmu_event_init,
+ .add = uncore_pmu_event_add,
+ .del = uncore_pmu_event_del,
+ .start = uncore_pmu_event_start,
+ .stop = uncore_pmu_event_stop,
+ .read = uncore_pmu_event_read,
+ };
+
+ if (pmu->type->num_boxes == 1) {
+ if (strlen(pmu->type->name) > 0)
+ sprintf(pmu->name, "uncore_%s", pmu->type->name);
+ else
+ sprintf(pmu->name, "uncore");
+ } else {
+ sprintf(pmu->name, "uncore_%s_%d", pmu->type->name,
+ pmu->pmu_idx);
+ }
+
+ ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
+ return ret;
+}
+
+static void __init uncore_type_exit(struct intel_uncore_type *type)
+{
+ int i;
+
+ for (i = 0; i < type->num_boxes; i++)
+ free_percpu(type->pmus[i].box);
+ kfree(type->pmus);
+ type->pmus = NULL;
+ kfree(type->attr_groups[1]);
+ type->attr_groups[1] = NULL;
+}
+
+static void uncore_types_exit(struct intel_uncore_type **types)
+{
+ int i;
+ for (i = 0; types[i]; i++)
+ uncore_type_exit(types[i]);
+}
+
+static int __init uncore_type_init(struct intel_uncore_type *type)
+{
+ struct intel_uncore_pmu *pmus;
+ struct attribute_group *events_group;
+ struct attribute **attrs;
+ int i, j;
+
+ pmus = kzalloc(sizeof(*pmus) * type->num_boxes, GFP_KERNEL);
+ if (!pmus)
+ return -ENOMEM;
+
+ type->unconstrainted = (struct event_constraint)
+ __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
+ 0, type->num_counters, 0);
+
+ for (i = 0; i < type->num_boxes; i++) {
+ pmus[i].func_id = -1;
+ pmus[i].pmu_idx = i;
+ pmus[i].type = type;
+ INIT_LIST_HEAD(&pmus[i].box_list);
+ pmus[i].box = alloc_percpu(struct intel_uncore_box *);
+ if (!pmus[i].box)
+ goto fail;
+ }
+
+ if (type->event_descs) {
+ i = 0;
+ while (type->event_descs[i].attr.attr.name)
+ i++;
+
+ events_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
+ sizeof(*events_group), GFP_KERNEL);
+ if (!events_group)
+ goto fail;
+
+ attrs = (struct attribute **)(events_group + 1);
+ events_group->name = "events";
+ events_group->attrs = attrs;
+
+ for (j = 0; j < i; j++)
+ attrs[j] = &type->event_descs[j].attr.attr;
+
+ type->attr_groups[1] = events_group;
+ }
+
+ type->pmus = pmus;
+ return 0;
+fail:
+ uncore_type_exit(type);
+ return -ENOMEM;
+}
+
+static int __init uncore_types_init(struct intel_uncore_type **types)
+{
+ int i, ret;
+
+ for (i = 0; types[i]; i++) {
+ ret = uncore_type_init(types[i]);
+ if (ret)
+ goto fail;
+ }
+ return 0;
+fail:
+ while (--i >= 0)
+ uncore_type_exit(types[i]);
+ return ret;
+}
+
+static struct pci_driver *uncore_pci_driver;
+static bool pcidrv_registered;
+
+/*
+ * add a pci uncore device
+ */
+static int __devinit uncore_pci_add(struct intel_uncore_type *type,
+ struct pci_dev *pdev)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, phys_id;
+
+ phys_id = pcibus_to_physid[pdev->bus->number];
+ if (phys_id < 0)
+ return -ENODEV;
+
+ box = uncore_alloc_box(type, 0);
+ if (!box)
+ return -ENOMEM;
+
+ /*
+ * for performance monitoring unit with multiple boxes,
+ * each box has a different function id.
+ */
+ for (i = 0; i < type->num_boxes; i++) {
+ pmu = &type->pmus[i];
+ if (pmu->func_id == pdev->devfn)
+ break;
+ if (pmu->func_id < 0) {
+ pmu->func_id = pdev->devfn;
+ break;
+ }
+ pmu = NULL;
+ }
+
+ if (!pmu) {
+ kfree(box);
+ return -EINVAL;
+ }
+
+ box->phys_id = phys_id;
+ box->pci_dev = pdev;
+ box->pmu = pmu;
+ uncore_box_init(box);
+ pci_set_drvdata(pdev, box);
+
+ raw_spin_lock(&uncore_box_lock);
+ list_add_tail(&box->list, &pmu->box_list);
+ raw_spin_unlock(&uncore_box_lock);
+
+ return 0;
+}
+
+static void uncore_pci_remove(struct pci_dev *pdev)
+{
+ struct intel_uncore_box *box = pci_get_drvdata(pdev);
+ struct intel_uncore_pmu *pmu = box->pmu;
+ int cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+
+ if (WARN_ON_ONCE(phys_id != box->phys_id))
+ return;
+
+ raw_spin_lock(&uncore_box_lock);
+ list_del(&box->list);
+ raw_spin_unlock(&uncore_box_lock);
+
+ for_each_possible_cpu(cpu) {
+ if (*per_cpu_ptr(pmu->box, cpu) == box) {
+ *per_cpu_ptr(pmu->box, cpu) = NULL;
+ atomic_dec(&box->refcnt);
+ }
+ }
+
+ WARN_ON_ONCE(atomic_read(&box->refcnt) != 1);
+ kfree(box);
+}
+
+static int __devinit uncore_pci_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ struct intel_uncore_type *type;
+
+ type = (struct intel_uncore_type *)id->driver_data;
+ return uncore_pci_add(type, pdev);
+}
+
+static int __init uncore_pci_init(void)
+{
+ int ret;
+
+ switch (boot_cpu_data.x86_model) {
+ case 45: /* Sandy Bridge-EP */
+ pci_uncores = snbep_pci_uncores;
+ uncore_pci_driver = &snbep_uncore_pci_driver;
+ snbep_pci2phy_map_init();
+ break;
+ default:
+ return 0;
+ }
+
+ ret = uncore_types_init(pci_uncores);
+ if (ret)
+ return ret;
+
+ uncore_pci_driver->probe = uncore_pci_probe;
+ uncore_pci_driver->remove = uncore_pci_remove;
+
+ ret = pci_register_driver(uncore_pci_driver);
+ if (ret == 0)
+ pcidrv_registered = true;
+ else
+ uncore_types_exit(pci_uncores);
+
+ return ret;
+}
+
+static void __init uncore_pci_exit(void)
+{
+ if (pcidrv_registered) {
+ pcidrv_registered = false;
+ pci_unregister_driver(uncore_pci_driver);
+ uncore_types_exit(pci_uncores);
+ }
+}
+
+static void __cpuinit uncore_cpu_dying(int cpu)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, j;
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ box = *per_cpu_ptr(pmu->box, cpu);
+ *per_cpu_ptr(pmu->box, cpu) = NULL;
+ if (box && atomic_dec_and_test(&box->refcnt))
+ kfree(box);
+ }
+ }
+}
+
+static int __cpuinit uncore_cpu_starting(int cpu)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box, *exist;
+ int i, j, k, phys_id;
+
+ phys_id = topology_physical_package_id(cpu);
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ box = *per_cpu_ptr(pmu->box, cpu);
+ /* called by uncore_cpu_init? */
+ if (box && box->phys_id >= 0) {
+ uncore_box_init(box);
+ continue;
+ }
+
+ for_each_online_cpu(k) {
+ exist = *per_cpu_ptr(pmu->box, k);
+ if (exist && exist->phys_id == phys_id) {
+ atomic_inc(&exist->refcnt);
+ *per_cpu_ptr(pmu->box, cpu) = exist;
+ kfree(box);
+ box = NULL;
+ break;
+ }
+ }
+
+ if (box) {
+ box->phys_id = phys_id;
+ uncore_box_init(box);
+ }
+ }
+ }
+ return 0;
+}
+
+static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, j;
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ if (pmu->func_id < 0)
+ pmu->func_id = j;
+
+ box = uncore_alloc_box(type, cpu);
+ if (!box)
+ return -ENOMEM;
+
+ box->pmu = pmu;
+ box->phys_id = phys_id;
+ *per_cpu_ptr(pmu->box, cpu) = box;
+ }
+ }
+ return 0;
+}
+
+static void __cpuinit uncore_change_context(struct intel_uncore_type **uncores,
+ int old_cpu, int new_cpu)
+{
+ struct intel_uncore_type *type;
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ int i, j;
+
+ for (i = 0; uncores[i]; i++) {
+ type = uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ if (old_cpu < 0)
+ box = uncore_pmu_to_box(pmu, new_cpu);
+ else
+ box = uncore_pmu_to_box(pmu, old_cpu);
+ if (!box)
+ continue;
+
+ if (old_cpu < 0) {
+ WARN_ON_ONCE(box->cpu != -1);
+ box->cpu = new_cpu;
+ continue;
+ }
+
+ WARN_ON_ONCE(box->cpu != old_cpu);
+ if (new_cpu >= 0) {
+ uncore_pmu_cancel_hrtimer(box);
+ perf_pmu_migrate_context(&pmu->pmu,
+ old_cpu, new_cpu);
+ box->cpu = new_cpu;
+ } else {
+ box->cpu = -1;
+ }
+ }
+ }
+}
+
+static void __cpuinit uncore_event_exit_cpu(int cpu)
+{
+ int i, phys_id, target;
+
+ /* if exiting cpu is used for collecting uncore events */
+ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
+ return;
+
+ /* find a new cpu to collect uncore events */
+ phys_id = topology_physical_package_id(cpu);
+ target = -1;
+ for_each_online_cpu(i) {
+ if (i == cpu)
+ continue;
+ if (phys_id == topology_physical_package_id(i)) {
+ target = i;
+ break;
+ }
+ }
+
+ /* migrate uncore events to the new cpu */
+ if (target >= 0)
+ cpumask_set_cpu(target, &uncore_cpu_mask);
+
+ uncore_change_context(msr_uncores, cpu, target);
+ uncore_change_context(pci_uncores, cpu, target);
+}
+
+static void __cpuinit uncore_event_init_cpu(int cpu)
+{
+ int i, phys_id;
+
+ phys_id = topology_physical_package_id(cpu);
+ for_each_cpu(i, &uncore_cpu_mask) {
+ if (phys_id == topology_physical_package_id(i))
+ return;
+ }
+
+ cpumask_set_cpu(cpu, &uncore_cpu_mask);
+
+ uncore_change_context(msr_uncores, -1, cpu);
+ uncore_change_context(pci_uncores, -1, cpu);
+}
+
+static int __cpuinit uncore_cpu_notifier(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (long)hcpu;
+
+ /* allocate/free data structure for uncore box */
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+ uncore_cpu_prepare(cpu, -1);
+ break;
+ case CPU_STARTING:
+ uncore_cpu_starting(cpu);
+ break;
+ case CPU_UP_CANCELED:
+ case CPU_DYING:
+ uncore_cpu_dying(cpu);
+ break;
+ default:
+ break;
+ }
+
+ /* select the cpu that collects uncore events */
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_FAILED:
+ case CPU_STARTING:
+ uncore_event_init_cpu(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ uncore_event_exit_cpu(cpu);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block uncore_cpu_nb __cpuinitdata = {
+ .notifier_call = uncore_cpu_notifier,
+ /*
+ * to migrate uncore events, our notifier should be executed
+ * before perf core's notifier.
+ */
+ .priority = CPU_PRI_PERF + 1,
+};
+
+static void __init uncore_cpu_setup(void *dummy)
+{
+ uncore_cpu_starting(smp_processor_id());
+}
+
+static int __init uncore_cpu_init(void)
+{
+ int ret, cpu, max_cores;
+
+ max_cores = boot_cpu_data.x86_max_cores;
+ switch (boot_cpu_data.x86_model) {
+ case 26: /* Nehalem */
+ case 30:
+ case 37: /* Westmere */
+ case 44:
+ msr_uncores = nhm_msr_uncores;
+ break;
+ case 42: /* Sandy Bridge */
+ if (snb_uncore_cbox.num_boxes > max_cores)
+ snb_uncore_cbox.num_boxes = max_cores;
+ msr_uncores = snb_msr_uncores;
+ break;
+ case 45: /* Sandy Birdge-EP */
+ if (snbep_uncore_cbox.num_boxes > max_cores)
+ snbep_uncore_cbox.num_boxes = max_cores;
+ msr_uncores = snbep_msr_uncores;
+ break;
+ default:
+ return 0;
+ }
+
+ ret = uncore_types_init(msr_uncores);
+ if (ret)
+ return ret;
+
+ get_online_cpus();
+
+ for_each_online_cpu(cpu) {
+ int i, phys_id = topology_physical_package_id(cpu);
+
+ for_each_cpu(i, &uncore_cpu_mask) {
+ if (phys_id == topology_physical_package_id(i)) {
+ phys_id = -1;
+ break;
+ }
+ }
+ if (phys_id < 0)
+ continue;
+
+ uncore_cpu_prepare(cpu, phys_id);
+ uncore_event_init_cpu(cpu);
+ }
+ on_each_cpu(uncore_cpu_setup, NULL, 1);
+
+ register_cpu_notifier(&uncore_cpu_nb);
+
+ put_online_cpus();
+
+ return 0;
+}
+
+static int __init uncore_pmus_register(void)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_type *type;
+ int i, j;
+
+ for (i = 0; msr_uncores[i]; i++) {
+ type = msr_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ uncore_pmu_register(pmu);
+ }
+ }
+
+ for (i = 0; pci_uncores[i]; i++) {
+ type = pci_uncores[i];
+ for (j = 0; j < type->num_boxes; j++) {
+ pmu = &type->pmus[j];
+ uncore_pmu_register(pmu);
+ }
+ }
+
+ return 0;
+}
+
+static int __init intel_uncore_init(void)
+{
+ int ret;
+
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return -ENODEV;
+
+ ret = uncore_pci_init();
+ if (ret)
+ goto fail;
+ ret = uncore_cpu_init();
+ if (ret) {
+ uncore_pci_exit();
+ goto fail;
+ }
+
+ uncore_pmus_register();
+ return 0;
+fail:
+ return ret;
+}
+device_initcall(intel_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
new file mode 100644
index 0000000..b13e9ea
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -0,0 +1,424 @@
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/perf_event.h>
+#include "perf_event.h"
+
+#define UNCORE_PMU_NAME_LEN 32
+#define UNCORE_BOX_HASH_SIZE 8
+
+#define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC)
+
+#define UNCORE_FIXED_EVENT 0xff
+#define UNCORE_PMC_IDX_MAX_GENERIC 8
+#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC
+#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1)
+
+#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
+
+/* SNB event control */
+#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
+#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00
+#define SNB_UNC_CTL_EDGE_DET (1 << 18)
+#define SNB_UNC_CTL_EN (1 << 22)
+#define SNB_UNC_CTL_INVERT (1 << 23)
+#define SNB_UNC_CTL_CMASK_MASK 0x1f000000
+#define NHM_UNC_CTL_CMASK_MASK 0xff000000
+#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0)
+
+#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
+ SNB_UNC_CTL_UMASK_MASK | \
+ SNB_UNC_CTL_EDGE_DET | \
+ SNB_UNC_CTL_INVERT | \
+ SNB_UNC_CTL_CMASK_MASK)
+
+#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
+ SNB_UNC_CTL_UMASK_MASK | \
+ SNB_UNC_CTL_EDGE_DET | \
+ SNB_UNC_CTL_INVERT | \
+ NHM_UNC_CTL_CMASK_MASK)
+
+/* SNB global control register */
+#define SNB_UNC_PERF_GLOBAL_CTL 0x391
+#define SNB_UNC_FIXED_CTR_CTRL 0x394
+#define SNB_UNC_FIXED_CTR 0x395
+
+/* SNB uncore global control */
+#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1)
+#define SNB_UNC_GLOBAL_CTL_EN (1 << 29)
+
+/* SNB Cbo register */
+#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700
+#define SNB_UNC_CBO_0_PER_CTR0 0x706
+#define SNB_UNC_CBO_MSR_OFFSET 0x10
+
+/* NHM global control register */
+#define NHM_UNC_PERF_GLOBAL_CTL 0x391
+#define NHM_UNC_FIXED_CTR 0x394
+#define NHM_UNC_FIXED_CTR_CTRL 0x395
+
+/* NHM uncore global control */
+#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1)
+#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32)
+
+/* NHM uncore register */
+#define NHM_UNC_PERFEVTSEL0 0x3c0
+#define NHM_UNC_UNCORE_PMC0 0x3b0
+
+/* SNB-EP Box level control */
+#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0)
+#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1)
+#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8)
+#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16)
+#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \
+ SNBEP_PMON_BOX_CTL_RST_CTRS | \
+ SNBEP_PMON_BOX_CTL_FRZ_EN)
+/* SNB-EP event control */
+#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff
+#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00
+#define SNBEP_PMON_CTL_RST (1 << 17)
+#define SNBEP_PMON_CTL_EDGE_DET (1 << 18)
+#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) /* only for QPI */
+#define SNBEP_PMON_CTL_EN (1 << 22)
+#define SNBEP_PMON_CTL_INVERT (1 << 23)
+#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000
+#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_PMON_CTL_TRESH_MASK)
+
+/* SNB-EP Ubox event control */
+#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000
+#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+
+#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19)
+#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_CBO_PMON_CTL_TID_EN)
+
+/* SNB-EP PCU event control */
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000
+#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30)
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31)
+#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+
+/* SNB-EP pci control register */
+#define SNBEP_PCI_PMON_BOX_CTL 0xf4
+#define SNBEP_PCI_PMON_CTL0 0xd8
+/* SNB-EP pci counter register */
+#define SNBEP_PCI_PMON_CTR0 0xa0
+
+/* SNB-EP home agent register */
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44
+#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48
+/* SNB-EP memory controller register */
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0
+/* SNB-EP QPI register */
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c
+
+/* SNB-EP Ubox register */
+#define SNBEP_U_MSR_PMON_CTR0 0xc16
+#define SNBEP_U_MSR_PMON_CTL0 0xc10
+
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09
+
+/* SNB-EP Cbo register */
+#define SNBEP_C0_MSR_PMON_CTR0 0xd16
+#define SNBEP_C0_MSR_PMON_CTL0 0xd10
+#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04
+#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK 0xfffffc1f
+#define SNBEP_CBO_MSR_OFFSET 0x20
+
+/* SNB-EP PCU register */
+#define SNBEP_PCU_MSR_PMON_CTR0 0xc36
+#define SNBEP_PCU_MSR_PMON_CTL0 0xc30
+#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff
+#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc
+#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd
+
+struct intel_uncore_ops;
+struct intel_uncore_pmu;
+struct intel_uncore_box;
+struct uncore_event_desc;
+
+struct intel_uncore_type {
+ const char *name;
+ int num_counters;
+ int num_boxes;
+ int perf_ctr_bits;
+ int fixed_ctr_bits;
+ unsigned perf_ctr;
+ unsigned event_ctl;
+ unsigned event_mask;
+ unsigned fixed_ctr;
+ unsigned fixed_ctl;
+ unsigned box_ctl;
+ unsigned msr_offset;
+ unsigned num_shared_regs:8;
+ unsigned single_fixed:1;
+ struct event_constraint unconstrainted;
+ struct event_constraint *constraints;
+ struct intel_uncore_pmu *pmus;
+ struct intel_uncore_ops *ops;
+ struct uncore_event_desc *event_descs;
+ const struct attribute_group *attr_groups[3];
+};
+
+#define format_group attr_groups[0]
+
+struct intel_uncore_ops {
+ void (*init_box)(struct intel_uncore_box *);
+ void (*disable_box)(struct intel_uncore_box *);
+ void (*enable_box)(struct intel_uncore_box *);
+ void (*disable_event)(struct intel_uncore_box *, struct perf_event *);
+ void (*enable_event)(struct intel_uncore_box *, struct perf_event *);
+ u64 (*read_counter)(struct intel_uncore_box *, struct perf_event *);
+ int (*hw_config)(struct intel_uncore_box *, struct perf_event *);
+ struct event_constraint *(*get_constraint)(struct intel_uncore_box *,
+ struct perf_event *);
+ void (*put_constraint)(struct intel_uncore_box *, struct perf_event *);
+};
+
+struct intel_uncore_pmu {
+ struct pmu pmu;
+ char name[UNCORE_PMU_NAME_LEN];
+ int pmu_idx;
+ int func_id;
+ struct intel_uncore_type *type;
+ struct intel_uncore_box ** __percpu box;
+ struct list_head box_list;
+};
+
+struct intel_uncore_extra_reg {
+ raw_spinlock_t lock;
+ u64 config1;
+ atomic_t ref;
+};
+
+struct intel_uncore_box {
+ int phys_id;
+ int n_active; /* number of active events */
+ int n_events;
+ int cpu; /* cpu to collect events */
+ unsigned long flags;
+ atomic_t refcnt;
+ struct perf_event *events[UNCORE_PMC_IDX_MAX];
+ struct perf_event *event_list[UNCORE_PMC_IDX_MAX];
+ unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
+ u64 tags[UNCORE_PMC_IDX_MAX];
+ struct pci_dev *pci_dev;
+ struct intel_uncore_pmu *pmu;
+ struct hrtimer hrtimer;
+ struct list_head list;
+ struct intel_uncore_extra_reg shared_regs[0];
+};
+
+#define UNCORE_BOX_FLAG_INITIATED 0
+
+struct uncore_event_desc {
+ struct kobj_attribute attr;
+ const char *config;
+};
+
+#define INTEL_UNCORE_EVENT_DESC(_name, _config) \
+{ \
+ .attr = __ATTR(_name, 0444, uncore_event_show, NULL), \
+ .config = _config, \
+}
+
+#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \
+static ssize_t __uncore_##_var##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct kobj_attribute format_attr_##_var = \
+ __ATTR(_name, 0444, __uncore_##_var##_show, NULL)
+
+
+static ssize_t uncore_event_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct uncore_event_desc *event =
+ container_of(attr, struct uncore_event_desc, attr);
+ return sprintf(buf, "%s", event->config);
+}
+
+static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
+{
+ return box->pmu->type->box_ctl;
+}
+
+static inline unsigned uncore_pci_fixed_ctl(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctl;
+}
+
+static inline unsigned uncore_pci_fixed_ctr(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctr;
+}
+
+static inline
+unsigned uncore_pci_event_ctl(struct intel_uncore_box *box, int idx)
+{
+ return idx * 4 + box->pmu->type->event_ctl;
+}
+
+static inline
+unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx)
+{
+ return idx * 8 + box->pmu->type->perf_ctr;
+}
+
+static inline
+unsigned uncore_msr_box_ctl(struct intel_uncore_box *box)
+{
+ if (!box->pmu->type->box_ctl)
+ return 0;
+ return box->pmu->type->box_ctl +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+}
+
+static inline
+unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box)
+{
+ if (!box->pmu->type->fixed_ctl)
+ return 0;
+ return box->pmu->type->fixed_ctl +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+}
+
+static inline
+unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctr +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+}
+
+static inline
+unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
+{
+ return idx + box->pmu->type->event_ctl +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+}
+
+static inline
+unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
+{
+ return idx + box->pmu->type->perf_ctr +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+}
+
+static inline
+unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
+{
+ if (box->pci_dev)
+ return uncore_pci_fixed_ctl(box);
+ else
+ return uncore_msr_fixed_ctl(box);
+}
+
+static inline
+unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
+{
+ if (box->pci_dev)
+ return uncore_pci_fixed_ctr(box);
+ else
+ return uncore_msr_fixed_ctr(box);
+}
+
+static inline
+unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
+{
+ if (box->pci_dev)
+ return uncore_pci_event_ctl(box, idx);
+ else
+ return uncore_msr_event_ctl(box, idx);
+}
+
+static inline
+unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx)
+{
+ if (box->pci_dev)
+ return uncore_pci_perf_ctr(box, idx);
+ else
+ return uncore_msr_perf_ctr(box, idx);
+}
+
+static inline int uncore_perf_ctr_bits(struct intel_uncore_box *box)
+{
+ return box->pmu->type->perf_ctr_bits;
+}
+
+static inline int uncore_fixed_ctr_bits(struct intel_uncore_box *box)
+{
+ return box->pmu->type->fixed_ctr_bits;
+}
+
+static inline int uncore_num_counters(struct intel_uncore_box *box)
+{
+ return box->pmu->type->num_counters;
+}
+
+static inline void uncore_disable_box(struct intel_uncore_box *box)
+{
+ if (box->pmu->type->ops->disable_box)
+ box->pmu->type->ops->disable_box(box);
+}
+
+static inline void uncore_enable_box(struct intel_uncore_box *box)
+{
+ if (box->pmu->type->ops->enable_box)
+ box->pmu->type->ops->enable_box(box);
+}
+
+static inline void uncore_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ box->pmu->type->ops->disable_event(box, event);
+}
+
+static inline void uncore_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ box->pmu->type->ops->enable_event(box, event);
+}
+
+static inline u64 uncore_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ return box->pmu->type->ops->read_counter(box, event);
+}
+
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+ if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+ if (box->pmu->type->ops->init_box)
+ box->pmu->type->ops->init_box(box);
+ }
+}
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 47124a7..92c7e39 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void)
* So at moment let leave metrics turned on forever -- it's
* ok for now but need to be revisited!
*
- * (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)0);
- * (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)0);
+ * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0);
+ * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0);
*/
}
@@ -909,7 +909,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
* state we need to clear P4_CCCR_OVF, otherwise interrupt get
* asserted again and again
*/
- (void)checking_wrmsrl(hwc->config_base,
+ (void)wrmsrl_safe(hwc->config_base,
(u64)(p4_config_unpack_cccr(hwc->config)) &
~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
}
@@ -943,8 +943,8 @@ static void p4_pmu_enable_pebs(u64 config)
bind = &p4_pebs_bind_map[idx];
- (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs);
- (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert);
+ (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs);
+ (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert);
}
static void p4_pmu_enable_event(struct perf_event *event)
@@ -978,8 +978,8 @@ static void p4_pmu_enable_event(struct perf_event *event)
*/
p4_pmu_enable_pebs(hwc->config);
- (void)checking_wrmsrl(escr_addr, escr_conf);
- (void)checking_wrmsrl(hwc->config_base,
+ (void)wrmsrl_safe(escr_addr, escr_conf);
+ (void)wrmsrl_safe(hwc->config_base,
(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
}
@@ -1325,7 +1325,7 @@ __init int p4_pmu_init(void)
unsigned int low, high;
/* If we get stripped -- indexing fails */
- BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC);
+ BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC);
rdmsr(MSR_IA32_MISC_ENABLE, low, high);
if (!(low & (1 << 7))) {
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 32bcfc7..e4dd0f7 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -71,7 +71,7 @@ p6_pmu_disable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base, val);
+ (void)wrmsrl_safe(hwc->config_base, val);
}
static void p6_pmu_enable_event(struct perf_event *event)
@@ -84,7 +84,7 @@ static void p6_pmu_enable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)checking_wrmsrl(hwc->config_base, val);
+ (void)wrmsrl_safe(hwc->config_base, val);
}
PMU_FORMAT_ATTR(event, "config:0-7" );
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index fbdfc69..1649cf8 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -87,6 +87,7 @@
#include <asm/microcode.h>
#include <asm/processor.h>
#include <asm/cpu_device_id.h>
+#include <asm/perf_event.h>
MODULE_DESCRIPTION("Microcode Update Driver");
MODULE_AUTHOR("Tigran Aivazian <tigran@...azian.fsnet.co.uk>");
@@ -277,7 +278,6 @@ static int reload_for_cpu(int cpu)
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
int err = 0;
- mutex_lock(µcode_mutex);
if (uci->valid) {
enum ucode_state ustate;
@@ -288,7 +288,6 @@ static int reload_for_cpu(int cpu)
if (ustate == UCODE_ERROR)
err = -EINVAL;
}
- mutex_unlock(µcode_mutex);
return err;
}
@@ -298,19 +297,31 @@ static ssize_t reload_store(struct device *dev,
const char *buf, size_t size)
{
unsigned long val;
- int cpu = dev->id;
- ssize_t ret = 0;
+ int cpu;
+ ssize_t ret = 0, tmp_ret;
ret = kstrtoul(buf, 0, &val);
if (ret)
return ret;
- if (val == 1) {
- get_online_cpus();
- if (cpu_online(cpu))
- ret = reload_for_cpu(cpu);
- put_online_cpus();
+ if (val != 1)
+ return size;
+
+ get_online_cpus();
+ mutex_lock(µcode_mutex);
+ for_each_online_cpu(cpu) {
+ tmp_ret = reload_for_cpu(cpu);
+ if (tmp_ret != 0)
+ pr_warn("Error reloading microcode on CPU %d\n", cpu);
+
+ /* save retval of the first encountered reload error */
+ if (!ret)
+ ret = tmp_ret;
}
+ if (!ret)
+ perf_check_microcode();
+ mutex_unlock(µcode_mutex);
+ put_online_cpus();
if (!ret)
ret = size;
@@ -339,7 +350,6 @@ static DEVICE_ATTR(version, 0400, version_show, NULL);
static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL);
static struct attribute *mc_default_attrs[] = {
- &dev_attr_reload.attr,
&dev_attr_version.attr,
&dev_attr_processor_flags.attr,
NULL
@@ -516,6 +526,16 @@ static const struct x86_cpu_id microcode_id[] = {
MODULE_DEVICE_TABLE(x86cpu, microcode_id);
#endif
+static struct attribute *cpu_root_microcode_attrs[] = {
+ &dev_attr_reload.attr,
+ NULL
+};
+
+static struct attribute_group cpu_root_microcode_group = {
+ .name = "microcode",
+ .attrs = cpu_root_microcode_attrs,
+};
+
static int __init microcode_init(void)
{
struct cpuinfo_x86 *c = &cpu_data(0);
@@ -540,16 +560,25 @@ static int __init microcode_init(void)
mutex_lock(µcode_mutex);
error = subsys_interface_register(&mc_cpu_interface);
-
+ if (!error)
+ perf_check_microcode();
mutex_unlock(µcode_mutex);
put_online_cpus();
if (error)
goto out_pdev;
+ error = sysfs_create_group(&cpu_subsys.dev_root->kobj,
+ &cpu_root_microcode_group);
+
+ if (error) {
+ pr_err("Error creating microcode group!\n");
+ goto out_driver;
+ }
+
error = microcode_dev_init();
if (error)
- goto out_driver;
+ goto out_ucode_group;
register_syscore_ops(&mc_syscore_ops);
register_hotcpu_notifier(&mc_cpu_notifier);
@@ -559,7 +588,11 @@ static int __init microcode_init(void)
return 0;
-out_driver:
+ out_ucode_group:
+ sysfs_remove_group(&cpu_subsys.dev_root->kobj,
+ &cpu_root_microcode_group);
+
+ out_driver:
get_online_cpus();
mutex_lock(µcode_mutex);
@@ -568,7 +601,7 @@ out_driver:
mutex_unlock(µcode_mutex);
put_online_cpus();
-out_pdev:
+ out_pdev:
platform_device_unregister(microcode_pdev);
return error;
@@ -584,6 +617,9 @@ static void __exit microcode_exit(void)
unregister_hotcpu_notifier(&mc_cpu_notifier);
unregister_syscore_ops(&mc_syscore_ops);
+ sysfs_remove_group(&cpu_subsys.dev_root->kobj,
+ &cpu_root_microcode_group);
+
get_online_cpus();
mutex_lock(µcode_mutex);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9ce8859..17fff18 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -352,9 +352,7 @@ struct pv_cpu_ops pv_cpu_ops = {
#endif
.wbinvd = native_wbinvd,
.read_msr = native_read_msr_safe,
- .rdmsr_regs = native_rdmsr_safe_regs,
.write_msr = native_write_msr_safe,
- .wrmsr_regs = native_wrmsr_safe_regs,
.read_tsc = native_read_tsc,
.read_pmc = native_read_pmc,
.read_tscp = native_read_tscp,
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 61cdf7f..3e215ba 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -466,7 +466,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
task->thread.gs = addr;
if (doit) {
load_gs_index(0);
- ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr);
+ ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
}
}
put_cpu();
@@ -494,7 +494,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
/* set the selector to 0 to not confuse
__switch_to */
loadsegment(fs, 0);
- ret = checking_wrmsrl(MSR_FS_BASE, addr);
+ ret = wrmsrl_safe(MSR_FS_BASE, addr);
}
}
put_cpu();
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index dc4e910..36fd420 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -409,9 +409,10 @@ static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm,
* arch_uprobe_analyze_insn - instruction analysis including validity and fixups.
* @mm: the probed address space.
* @arch_uprobe: the probepoint information.
+ * @addr: virtual address at which to install the probepoint
* Return 0 on success or a -ve number on error.
*/
-int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm)
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr)
{
int ret;
struct insn insn;
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 2e88438..9b7ec11 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -80,10 +80,10 @@ static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx)
static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx)
{
- if (idx < X86_PMC_IDX_FIXED)
+ if (idx < INTEL_PMC_IDX_FIXED)
return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0);
else
- return get_fixed_pmc_idx(pmu, idx - X86_PMC_IDX_FIXED);
+ return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED);
}
void kvm_deliver_pmi(struct kvm_vcpu *vcpu)
@@ -291,7 +291,7 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx)
if (pmc_is_gp(pmc))
reprogram_gp_counter(pmc, pmc->eventsel);
else {
- int fidx = idx - X86_PMC_IDX_FIXED;
+ int fidx = idx - INTEL_PMC_IDX_FIXED;
reprogram_fixed_counter(pmc,
fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx);
}
@@ -452,7 +452,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
return;
pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff,
- X86_PMC_MAX_GENERIC);
+ INTEL_PMC_MAX_GENERIC);
pmu->counter_bitmask[KVM_PMC_GP] =
((u64)1 << ((entry->eax >> 16) & 0xff)) - 1;
bitmap_len = (entry->eax >> 24) & 0xff;
@@ -462,13 +462,13 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
pmu->nr_arch_fixed_counters = 0;
} else {
pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
- X86_PMC_MAX_FIXED);
+ INTEL_PMC_MAX_FIXED);
pmu->counter_bitmask[KVM_PMC_FIXED] =
((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
}
pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
- (((1ull << pmu->nr_arch_fixed_counters) - 1) << X86_PMC_IDX_FIXED);
+ (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
pmu->global_ctrl_mask = ~pmu->global_ctrl;
}
@@ -478,15 +478,15 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = &vcpu->arch.pmu;
memset(pmu, 0, sizeof(*pmu));
- for (i = 0; i < X86_PMC_MAX_GENERIC; i++) {
+ for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
pmu->gp_counters[i].type = KVM_PMC_GP;
pmu->gp_counters[i].vcpu = vcpu;
pmu->gp_counters[i].idx = i;
}
- for (i = 0; i < X86_PMC_MAX_FIXED; i++) {
+ for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
pmu->fixed_counters[i].type = KVM_PMC_FIXED;
pmu->fixed_counters[i].vcpu = vcpu;
- pmu->fixed_counters[i].idx = i + X86_PMC_IDX_FIXED;
+ pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
}
init_irq_work(&pmu->irq_work, trigger_pmi);
kvm_pmu_cpuid_update(vcpu);
@@ -498,13 +498,13 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu)
int i;
irq_work_sync(&pmu->irq_work);
- for (i = 0; i < X86_PMC_MAX_GENERIC; i++) {
+ for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
struct kvm_pmc *pmc = &pmu->gp_counters[i];
stop_counter(pmc);
pmc->counter = pmc->eventsel = 0;
}
- for (i = 0; i < X86_PMC_MAX_FIXED; i++)
+ for (i = 0; i < INTEL_PMC_MAX_FIXED; i++)
stop_counter(&pmu->fixed_counters[i]);
pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 911d264..62d02e3 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -710,16 +710,6 @@ TRACE_EVENT(kvm_skinit,
__entry->rip, __entry->slb)
);
-#define __print_insn(insn, ilen) ({ \
- int i; \
- const char *ret = p->buffer + p->len; \
- \
- for (i = 0; i < ilen; ++i) \
- trace_seq_printf(p, " %02x", insn[i]); \
- trace_seq_printf(p, "%c", 0); \
- ret; \
- })
-
#define KVM_EMUL_INSN_F_CR0_PE (1 << 0)
#define KVM_EMUL_INSN_F_EFL_VM (1 << 1)
#define KVM_EMUL_INSN_F_CS_D (1 << 2)
@@ -786,7 +776,7 @@ TRACE_EVENT(kvm_emulate_insn,
TP_printk("%x:%llx:%s (%s)%s",
__entry->csbase, __entry->rip,
- __print_insn(__entry->insn, __entry->len),
+ __print_hex(__entry->insn, __entry->len),
__print_symbolic(__entry->flags,
kvm_trace_symbol_emul_flags),
__entry->failed ? " failed" : ""
diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c
index a311cc5..8d6ef78 100644
--- a/arch/x86/lib/msr-reg-export.c
+++ b/arch/x86/lib/msr-reg-export.c
@@ -1,5 +1,5 @@
#include <linux/module.h>
#include <asm/msr.h>
-EXPORT_SYMBOL(native_rdmsr_safe_regs);
-EXPORT_SYMBOL(native_wrmsr_safe_regs);
+EXPORT_SYMBOL(rdmsr_safe_regs);
+EXPORT_SYMBOL(wrmsr_safe_regs);
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index 69fa106..f6d13ee 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -6,13 +6,13 @@
#ifdef CONFIG_X86_64
/*
- * int native_{rdmsr,wrmsr}_safe_regs(u32 gprs[8]);
+ * int {rdmsr,wrmsr}_safe_regs(u32 gprs[8]);
*
* reg layout: u32 gprs[eax, ecx, edx, ebx, esp, ebp, esi, edi]
*
*/
.macro op_safe_regs op
-ENTRY(native_\op\()_safe_regs)
+ENTRY(\op\()_safe_regs)
CFI_STARTPROC
pushq_cfi %rbx
pushq_cfi %rbp
@@ -45,13 +45,13 @@ ENTRY(native_\op\()_safe_regs)
_ASM_EXTABLE(1b, 3b)
CFI_ENDPROC
-ENDPROC(native_\op\()_safe_regs)
+ENDPROC(\op\()_safe_regs)
.endm
#else /* X86_32 */
.macro op_safe_regs op
-ENTRY(native_\op\()_safe_regs)
+ENTRY(\op\()_safe_regs)
CFI_STARTPROC
pushl_cfi %ebx
pushl_cfi %ebp
@@ -92,7 +92,7 @@ ENTRY(native_\op\()_safe_regs)
_ASM_EXTABLE(1b, 3b)
CFI_ENDPROC
-ENDPROC(native_\op\()_safe_regs)
+ENDPROC(\op\()_safe_regs)
.endm
#endif
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 303f086..b2b9443 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -312,7 +312,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
goto fail;
}
/* both registers must be reserved */
- if (num_counters == AMD64_NUM_COUNTERS_F15H) {
+ if (num_counters == AMD64_NUM_COUNTERS_CORE) {
msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1);
msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1);
} else {
@@ -514,7 +514,7 @@ static int op_amd_init(struct oprofile_operations *ops)
ops->create_files = setup_ibs_files;
if (boot_cpu_data.x86 == 0x15) {
- num_counters = AMD64_NUM_COUNTERS_F15H;
+ num_counters = AMD64_NUM_COUNTERS_CORE;
} else {
num_counters = AMD64_NUM_COUNTERS;
}
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 66e6d93..0faad64 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -205,9 +205,9 @@ void syscall32_cpu_init(void)
{
/* Load these always in case some future AMD CPU supports
SYSENTER from compat mode too. */
- checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL);
- checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
wrmsrl(MSR_CSTAR, ia32_cstar_target);
}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ff962d4..ed7d549 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1124,9 +1124,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.wbinvd = native_wbinvd,
.read_msr = native_read_msr_safe,
- .rdmsr_regs = native_rdmsr_safe_regs,
.write_msr = xen_write_msr_safe,
- .wrmsr_regs = native_wrmsr_safe_regs,
.read_tsc = native_read_tsc,
.read_pmc = native_read_pmc,
diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c
index efc4b7f..f3cfa0b 100644
--- a/drivers/oprofile/oprofile_perf.c
+++ b/drivers/oprofile/oprofile_perf.c
@@ -1,5 +1,6 @@
/*
* Copyright 2010 ARM Ltd.
+ * Copyright 2012 Advanced Micro Devices, Inc., Robert Richter
*
* Perf-events backend for OProfile.
*/
@@ -25,7 +26,7 @@ static int oprofile_perf_enabled;
static DEFINE_MUTEX(oprofile_perf_mutex);
static struct op_counter_config *counter_config;
-static struct perf_event **perf_events[NR_CPUS];
+static DEFINE_PER_CPU(struct perf_event **, perf_events);
static int num_counters;
/*
@@ -38,7 +39,7 @@ static void op_overflow_handler(struct perf_event *event,
u32 cpu = smp_processor_id();
for (id = 0; id < num_counters; ++id)
- if (perf_events[cpu][id] == event)
+ if (per_cpu(perf_events, cpu)[id] == event)
break;
if (id != num_counters)
@@ -74,7 +75,7 @@ static int op_create_counter(int cpu, int event)
{
struct perf_event *pevent;
- if (!counter_config[event].enabled || perf_events[cpu][event])
+ if (!counter_config[event].enabled || per_cpu(perf_events, cpu)[event])
return 0;
pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
@@ -91,18 +92,18 @@ static int op_create_counter(int cpu, int event)
return -EBUSY;
}
- perf_events[cpu][event] = pevent;
+ per_cpu(perf_events, cpu)[event] = pevent;
return 0;
}
static void op_destroy_counter(int cpu, int event)
{
- struct perf_event *pevent = perf_events[cpu][event];
+ struct perf_event *pevent = per_cpu(perf_events, cpu)[event];
if (pevent) {
perf_event_release_kernel(pevent);
- perf_events[cpu][event] = NULL;
+ per_cpu(perf_events, cpu)[event] = NULL;
}
}
@@ -257,12 +258,12 @@ void oprofile_perf_exit(void)
for_each_possible_cpu(cpu) {
for (id = 0; id < num_counters; ++id) {
- event = perf_events[cpu][id];
+ event = per_cpu(perf_events, cpu)[id];
if (event)
perf_event_release_kernel(event);
}
- kfree(perf_events[cpu]);
+ kfree(per_cpu(perf_events, cpu));
}
kfree(counter_config);
@@ -277,8 +278,6 @@ int __init oprofile_perf_init(struct oprofile_operations *ops)
if (ret)
return ret;
- memset(&perf_events, 0, sizeof(perf_events));
-
num_counters = perf_num_counters();
if (num_counters <= 0) {
pr_info("oprofile: no performance counters\n");
@@ -298,9 +297,9 @@ int __init oprofile_perf_init(struct oprofile_operations *ops)
}
for_each_possible_cpu(cpu) {
- perf_events[cpu] = kcalloc(num_counters,
+ per_cpu(perf_events, cpu) = kcalloc(num_counters,
sizeof(struct perf_event *), GFP_KERNEL);
- if (!perf_events[cpu]) {
+ if (!per_cpu(perf_events, cpu)) {
pr_info("oprofile: failed to allocate %d perf events "
"for cpu %d\n", num_counters, cpu);
ret = -ENOMEM;
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 176a939..af961d6 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -65,7 +65,7 @@ struct trace_iterator {
void *private;
int cpu_file;
struct mutex mutex;
- struct ring_buffer_iter *buffer_iter[NR_CPUS];
+ struct ring_buffer_iter **buffer_iter;
unsigned long iter_flags;
/* trace_seq for __print_flags() and __print_symbolic() etc. */
@@ -207,6 +207,9 @@ struct ftrace_event_call {
* bit 1: enabled
* bit 2: filter_active
* bit 3: enabled cmd record
+ * bit 4: allow trace by non root (cap any)
+ * bit 5: failed to apply filter
+ * bit 6: ftrace internal event (do not enable)
*
* Changes to flags must hold the event_mutex.
*
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index c513a40..0976fc4 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -42,8 +42,7 @@
* allowed.
*
* Not initializing the key (static data is initialized to 0s anyway) is the
- * same as using STATIC_KEY_INIT_FALSE and static_key_false() is
- * equivalent with static_branch().
+ * same as using STATIC_KEY_INIT_FALSE.
*
*/
@@ -107,12 +106,6 @@ static __always_inline bool static_key_true(struct static_key *key)
return !static_key_false(key);
}
-/* Deprecated. Please use 'static_key_false() instead. */
-static __always_inline bool static_branch(struct static_key *key)
-{
- return arch_static_branch(key);
-}
-
extern struct jump_entry __start___jump_table[];
extern struct jump_entry __stop___jump_table[];
@@ -166,14 +159,6 @@ static __always_inline bool static_key_true(struct static_key *key)
return false;
}
-/* Deprecated. Please use 'static_key_false() instead. */
-static __always_inline bool static_branch(struct static_key *key)
-{
- if (unlikely(atomic_read(&key->enabled)) > 0)
- return true;
- return false;
-}
-
static inline void static_key_slow_inc(struct static_key *key)
{
atomic_inc(&key->enabled);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index ab741b0..5f18702 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2755,6 +2755,17 @@
#define PCI_DEVICE_ID_INTEL_IOAT_SNB7 0x3c27
#define PCI_DEVICE_ID_INTEL_IOAT_SNB8 0x3c2e
#define PCI_DEVICE_ID_INTEL_IOAT_SNB9 0x3c2f
+#define PCI_DEVICE_ID_INTEL_UNC_HA 0x3c46
+#define PCI_DEVICE_ID_INTEL_UNC_IMC0 0x3cb0
+#define PCI_DEVICE_ID_INTEL_UNC_IMC1 0x3cb1
+#define PCI_DEVICE_ID_INTEL_UNC_IMC2 0x3cb4
+#define PCI_DEVICE_ID_INTEL_UNC_IMC3 0x3cb5
+#define PCI_DEVICE_ID_INTEL_UNC_QPI0 0x3c41
+#define PCI_DEVICE_ID_INTEL_UNC_QPI1 0x3c42
+#define PCI_DEVICE_ID_INTEL_UNC_R2PCIE 0x3c43
+#define PCI_DEVICE_ID_INTEL_UNC_R3QPI0 0x3c44
+#define PCI_DEVICE_ID_INTEL_UNC_R3QPI1 0x3c45
+#define PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX 0x3ce0
#define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f
#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0
#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 45db49f..76c5c8b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -677,6 +677,7 @@ struct hw_perf_event {
u64 last_tag;
unsigned long config_base;
unsigned long event_base;
+ int event_base_rdpmc;
int idx;
int last_cpu;
@@ -1106,6 +1107,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
struct task_struct *task,
perf_overflow_handler_t callback,
void *context);
+extern void perf_pmu_migrate_context(struct pmu *pmu,
+ int src_cpu, int dst_cpu);
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4a1f493..64d9df5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1581,7 +1581,6 @@ struct task_struct {
#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
- int uprobe_srcu_id;
#endif
};
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index bd96ecd..802de56 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -153,7 +153,7 @@ static inline void tracepoint_synchronize_unregister(void)
} \
static inline void trace_##name##_rcuidle(proto) \
{ \
- if (static_branch(&__tracepoint_##name.key)) \
+ if (static_key_false(&__tracepoint_##name.key)) \
__DO_TRACE(&__tracepoint_##name, \
TP_PROTO(data_proto), \
TP_ARGS(data_args), \
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 7697249..c6bc2fa 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -571,6 +571,7 @@ static inline void ftrace_test_probe_##call(void) \
#undef __print_flags
#undef __print_symbolic
+#undef __print_hex
#undef __get_dynamic_array
#undef __get_str
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d7d71d6..f1cf0ed 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1645,6 +1645,8 @@ perf_install_in_context(struct perf_event_context *ctx,
lockdep_assert_held(&ctx->mutex);
event->ctx = ctx;
+ if (event->cpu != -1)
+ event->cpu = cpu;
if (!task) {
/*
@@ -6252,6 +6254,8 @@ SYSCALL_DEFINE5(perf_event_open,
}
}
+ get_online_cpus();
+
event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
NULL, NULL);
if (IS_ERR(event)) {
@@ -6304,7 +6308,7 @@ SYSCALL_DEFINE5(perf_event_open,
/*
* Get the target context (task or percpu):
*/
- ctx = find_get_context(pmu, task, cpu);
+ ctx = find_get_context(pmu, task, event->cpu);
if (IS_ERR(ctx)) {
err = PTR_ERR(ctx);
goto err_alloc;
@@ -6377,20 +6381,23 @@ SYSCALL_DEFINE5(perf_event_open,
mutex_lock(&ctx->mutex);
if (move_group) {
- perf_install_in_context(ctx, group_leader, cpu);
+ synchronize_rcu();
+ perf_install_in_context(ctx, group_leader, event->cpu);
get_ctx(ctx);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
- perf_install_in_context(ctx, sibling, cpu);
+ perf_install_in_context(ctx, sibling, event->cpu);
get_ctx(ctx);
}
}
- perf_install_in_context(ctx, event, cpu);
+ perf_install_in_context(ctx, event, event->cpu);
++ctx->generation;
perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
+ put_online_cpus();
+
event->owner = current;
mutex_lock(¤t->perf_event_mutex);
@@ -6419,6 +6426,7 @@ err_context:
err_alloc:
free_event(event);
err_task:
+ put_online_cpus();
if (task)
put_task_struct(task);
err_group_fd:
@@ -6479,6 +6487,39 @@ err:
}
EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
+void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
+{
+ struct perf_event_context *src_ctx;
+ struct perf_event_context *dst_ctx;
+ struct perf_event *event, *tmp;
+ LIST_HEAD(events);
+
+ src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx;
+ dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx;
+
+ mutex_lock(&src_ctx->mutex);
+ list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
+ event_entry) {
+ perf_remove_from_context(event);
+ put_ctx(src_ctx);
+ list_add(&event->event_entry, &events);
+ }
+ mutex_unlock(&src_ctx->mutex);
+
+ synchronize_rcu();
+
+ mutex_lock(&dst_ctx->mutex);
+ list_for_each_entry_safe(event, tmp, &events, event_entry) {
+ list_del(&event->event_entry);
+ if (event->state >= PERF_EVENT_STATE_OFF)
+ event->state = PERF_EVENT_STATE_INACTIVE;
+ perf_install_in_context(dst_ctx, event, dst_cpu);
+ get_ctx(dst_ctx);
+ }
+ mutex_unlock(&dst_ctx->mutex);
+}
+EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
+
static void sync_child_event(struct perf_event *child_event,
struct task_struct *child)
{
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 985be4d..f935327 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -38,13 +38,29 @@
#define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES)
#define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE
-static struct srcu_struct uprobes_srcu;
static struct rb_root uprobes_tree = RB_ROOT;
static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */
#define UPROBES_HASH_SZ 13
+/*
+ * We need separate register/unregister and mmap/munmap lock hashes because
+ * of mmap_sem nesting.
+ *
+ * uprobe_register() needs to install probes on (potentially) all processes
+ * and thus needs to acquire multiple mmap_sems (consequtively, not
+ * concurrently), whereas uprobe_mmap() is called while holding mmap_sem
+ * for the particular process doing the mmap.
+ *
+ * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem
+ * because of lock order against i_mmap_mutex. This means there's a hole in
+ * the register vma iteration where a mmap() can happen.
+ *
+ * Thus uprobe_register() can race with uprobe_mmap() and we can try and
+ * install a probe where one is already installed.
+ */
+
/* serialize (un)register */
static struct mutex uprobes_mutex[UPROBES_HASH_SZ];
@@ -61,17 +77,6 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
*/
static atomic_t uprobe_events = ATOMIC_INIT(0);
-/*
- * Maintain a temporary per vma info that can be used to search if a vma
- * has already been handled. This structure is introduced since extending
- * vm_area_struct wasnt recommended.
- */
-struct vma_info {
- struct list_head probe_list;
- struct mm_struct *mm;
- loff_t vaddr;
-};
-
struct uprobe {
struct rb_node rb_node; /* node in the rb tree */
atomic_t ref;
@@ -100,7 +105,8 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register)
if (!is_register)
return true;
- if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC))
+ if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED))
+ == (VM_READ|VM_EXEC))
return true;
return false;
@@ -129,33 +135,17 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset)
static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage)
{
struct mm_struct *mm = vma->vm_mm;
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *ptep;
- spinlock_t *ptl;
unsigned long addr;
- int err = -EFAULT;
+ spinlock_t *ptl;
+ pte_t *ptep;
addr = page_address_in_vma(page, vma);
if (addr == -EFAULT)
- goto out;
-
- pgd = pgd_offset(mm, addr);
- if (!pgd_present(*pgd))
- goto out;
-
- pud = pud_offset(pgd, addr);
- if (!pud_present(*pud))
- goto out;
-
- pmd = pmd_offset(pud, addr);
- if (!pmd_present(*pmd))
- goto out;
+ return -EFAULT;
- ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ ptep = page_check_address(page, mm, addr, &ptl, 0);
if (!ptep)
- goto out;
+ return -EAGAIN;
get_page(kpage);
page_add_new_anon_rmap(kpage, vma, addr);
@@ -174,10 +164,8 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct
try_to_free_swap(page);
put_page(page);
pte_unmap_unlock(ptep, ptl);
- err = 0;
-out:
- return err;
+ return 0;
}
/**
@@ -222,9 +210,8 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
void *vaddr_old, *vaddr_new;
struct vm_area_struct *vma;
struct uprobe *uprobe;
- loff_t addr;
int ret;
-
+retry:
/* Read the page with vaddr into memory */
ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
if (ret <= 0)
@@ -246,10 +233,6 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
if (mapping != vma->vm_file->f_mapping)
goto put_out;
- addr = vma_address(vma, uprobe->offset);
- if (vaddr != (unsigned long)addr)
- goto put_out;
-
ret = -ENOMEM;
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
if (!new_page)
@@ -267,11 +250,7 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
vaddr_new = kmap_atomic(new_page);
memcpy(vaddr_new, vaddr_old, PAGE_SIZE);
-
- /* poke the new insn in, ASSUMES we don't cross page boundary */
- vaddr &= ~PAGE_MASK;
- BUG_ON(vaddr + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
- memcpy(vaddr_new + vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+ memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE);
kunmap_atomic(vaddr_new);
kunmap_atomic(vaddr_old);
@@ -291,6 +270,8 @@ unlock_out:
put_out:
put_page(old_page);
+ if (unlikely(ret == -EAGAIN))
+ goto retry;
return ret;
}
@@ -312,7 +293,7 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_
void *vaddr_new;
int ret;
- ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL);
+ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
if (ret <= 0)
return ret;
@@ -333,10 +314,20 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
uprobe_opcode_t opcode;
int result;
+ if (current->mm == mm) {
+ pagefault_disable();
+ result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
+ sizeof(opcode));
+ pagefault_enable();
+
+ if (likely(result == 0))
+ goto out;
+ }
+
result = read_opcode(mm, vaddr, &opcode);
if (result)
return result;
-
+out:
if (is_swbp_insn(&opcode))
return 1;
@@ -355,7 +346,9 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
int result;
-
+ /*
+ * See the comment near uprobes_hash().
+ */
result = is_swbp_at_addr(mm, vaddr);
if (result == 1)
return -EEXIST;
@@ -520,7 +513,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
uprobe->inode = igrab(inode);
uprobe->offset = offset;
init_rwsem(&uprobe->consumer_rwsem);
- INIT_LIST_HEAD(&uprobe->pending_list);
/* add to uprobes_tree, sorted on inode:offset */
cur_uprobe = insert_uprobe(uprobe);
@@ -588,20 +580,22 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
}
static int
-__copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *insn,
- unsigned long nbytes, unsigned long offset)
+__copy_insn(struct address_space *mapping, struct file *filp, char *insn,
+ unsigned long nbytes, loff_t offset)
{
- struct file *filp = vma->vm_file;
struct page *page;
void *vaddr;
- unsigned long off1;
- unsigned long idx;
+ unsigned long off;
+ pgoff_t idx;
if (!filp)
return -EINVAL;
- idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT);
- off1 = offset &= ~PAGE_MASK;
+ if (!mapping->a_ops->readpage)
+ return -EIO;
+
+ idx = offset >> PAGE_CACHE_SHIFT;
+ off = offset & ~PAGE_MASK;
/*
* Ensure that the page that has the original instruction is
@@ -612,22 +606,20 @@ __copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *ins
return PTR_ERR(page);
vaddr = kmap_atomic(page);
- memcpy(insn, vaddr + off1, nbytes);
+ memcpy(insn, vaddr + off, nbytes);
kunmap_atomic(vaddr);
page_cache_release(page);
return 0;
}
-static int
-copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr)
+static int copy_insn(struct uprobe *uprobe, struct file *filp)
{
struct address_space *mapping;
unsigned long nbytes;
int bytes;
- addr &= ~PAGE_MASK;
- nbytes = PAGE_SIZE - addr;
+ nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK);
mapping = uprobe->inode->i_mapping;
/* Instruction at end of binary; copy only available bytes */
@@ -638,13 +630,13 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr)
/* Instruction at the page-boundary; copy bytes in second page */
if (nbytes < bytes) {
- if (__copy_insn(mapping, vma, uprobe->arch.insn + nbytes,
- bytes - nbytes, uprobe->offset + nbytes))
- return -ENOMEM;
-
+ int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes,
+ bytes - nbytes, uprobe->offset + nbytes);
+ if (err)
+ return err;
bytes = nbytes;
}
- return __copy_insn(mapping, vma, uprobe->arch.insn, bytes, uprobe->offset);
+ return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset);
}
/*
@@ -672,9 +664,8 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr)
*/
static int
install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
- struct vm_area_struct *vma, loff_t vaddr)
+ struct vm_area_struct *vma, unsigned long vaddr)
{
- unsigned long addr;
int ret;
/*
@@ -687,20 +678,22 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
if (!uprobe->consumers)
return -EEXIST;
- addr = (unsigned long)vaddr;
-
if (!(uprobe->flags & UPROBE_COPY_INSN)) {
- ret = copy_insn(uprobe, vma, addr);
+ ret = copy_insn(uprobe, vma->vm_file);
if (ret)
return ret;
if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
- return -EEXIST;
+ return -ENOTSUPP;
- ret = arch_uprobe_analyze_insn(&uprobe->arch, mm);
+ ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
if (ret)
return ret;
+ /* write_opcode() assumes we don't cross page boundary */
+ BUG_ON((uprobe->offset & ~PAGE_MASK) +
+ UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
+
uprobe->flags |= UPROBE_COPY_INSN;
}
@@ -713,7 +706,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
* Hence increment before and decrement on failure.
*/
atomic_inc(&mm->uprobes_state.count);
- ret = set_swbp(&uprobe->arch, mm, addr);
+ ret = set_swbp(&uprobe->arch, mm, vaddr);
if (ret)
atomic_dec(&mm->uprobes_state.count);
@@ -721,27 +714,21 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
}
static void
-remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr)
+remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
{
- if (!set_orig_insn(&uprobe->arch, mm, (unsigned long)vaddr, true))
+ if (!set_orig_insn(&uprobe->arch, mm, vaddr, true))
atomic_dec(&mm->uprobes_state.count);
}
/*
- * There could be threads that have hit the breakpoint and are entering the
- * notifier code and trying to acquire the uprobes_treelock. The thread
- * calling delete_uprobe() that is removing the uprobe from the rb_tree can
- * race with these threads and might acquire the uprobes_treelock compared
- * to some of the breakpoint hit threads. In such a case, the breakpoint
- * hit threads will not find the uprobe. The current unregistering thread
- * waits till all other threads have hit a breakpoint, to acquire the
- * uprobes_treelock before the uprobe is removed from the rbtree.
+ * There could be threads that have already hit the breakpoint. They
+ * will recheck the current insn and restart if find_uprobe() fails.
+ * See find_active_uprobe().
*/
static void delete_uprobe(struct uprobe *uprobe)
{
unsigned long flags;
- synchronize_srcu(&uprobes_srcu);
spin_lock_irqsave(&uprobes_treelock, flags);
rb_erase(&uprobe->rb_node, &uprobes_tree);
spin_unlock_irqrestore(&uprobes_treelock, flags);
@@ -750,139 +737,135 @@ static void delete_uprobe(struct uprobe *uprobe)
atomic_dec(&uprobe_events);
}
-static struct vma_info *
-__find_next_vma_info(struct address_space *mapping, struct list_head *head,
- struct vma_info *vi, loff_t offset, bool is_register)
+struct map_info {
+ struct map_info *next;
+ struct mm_struct *mm;
+ unsigned long vaddr;
+};
+
+static inline struct map_info *free_map_info(struct map_info *info)
+{
+ struct map_info *next = info->next;
+ kfree(info);
+ return next;
+}
+
+static struct map_info *
+build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
{
+ unsigned long pgoff = offset >> PAGE_SHIFT;
struct prio_tree_iter iter;
struct vm_area_struct *vma;
- struct vma_info *tmpvi;
- unsigned long pgoff;
- int existing_vma;
- loff_t vaddr;
-
- pgoff = offset >> PAGE_SHIFT;
+ struct map_info *curr = NULL;
+ struct map_info *prev = NULL;
+ struct map_info *info;
+ int more = 0;
+ again:
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
if (!valid_vma(vma, is_register))
continue;
- existing_vma = 0;
- vaddr = vma_address(vma, offset);
-
- list_for_each_entry(tmpvi, head, probe_list) {
- if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) {
- existing_vma = 1;
- break;
- }
+ if (!prev && !more) {
+ /*
+ * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through
+ * reclaim. This is optimistic, no harm done if it fails.
+ */
+ prev = kmalloc(sizeof(struct map_info),
+ GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN);
+ if (prev)
+ prev->next = NULL;
}
-
- /*
- * Another vma needs a probe to be installed. However skip
- * installing the probe if the vma is about to be unlinked.
- */
- if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) {
- vi->mm = vma->vm_mm;
- vi->vaddr = vaddr;
- list_add(&vi->probe_list, head);
-
- return vi;
+ if (!prev) {
+ more++;
+ continue;
}
- }
- return NULL;
-}
-
-/*
- * Iterate in the rmap prio tree and find a vma where a probe has not
- * yet been inserted.
- */
-static struct vma_info *
-find_next_vma_info(struct address_space *mapping, struct list_head *head,
- loff_t offset, bool is_register)
-{
- struct vma_info *vi, *retvi;
+ if (!atomic_inc_not_zero(&vma->vm_mm->mm_users))
+ continue;
- vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL);
- if (!vi)
- return ERR_PTR(-ENOMEM);
+ info = prev;
+ prev = prev->next;
+ info->next = curr;
+ curr = info;
- mutex_lock(&mapping->i_mmap_mutex);
- retvi = __find_next_vma_info(mapping, head, vi, offset, is_register);
+ info->mm = vma->vm_mm;
+ info->vaddr = vma_address(vma, offset);
+ }
mutex_unlock(&mapping->i_mmap_mutex);
- if (!retvi)
- kfree(vi);
+ if (!more)
+ goto out;
+
+ prev = curr;
+ while (curr) {
+ mmput(curr->mm);
+ curr = curr->next;
+ }
- return retvi;
+ do {
+ info = kmalloc(sizeof(struct map_info), GFP_KERNEL);
+ if (!info) {
+ curr = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ info->next = prev;
+ prev = info;
+ } while (--more);
+
+ goto again;
+ out:
+ while (prev)
+ prev = free_map_info(prev);
+ return curr;
}
static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
{
- struct list_head try_list;
- struct vm_area_struct *vma;
- struct address_space *mapping;
- struct vma_info *vi, *tmpvi;
- struct mm_struct *mm;
- loff_t vaddr;
- int ret;
+ struct map_info *info;
+ int err = 0;
- mapping = uprobe->inode->i_mapping;
- INIT_LIST_HEAD(&try_list);
+ info = build_map_info(uprobe->inode->i_mapping,
+ uprobe->offset, is_register);
+ if (IS_ERR(info))
+ return PTR_ERR(info);
- ret = 0;
+ while (info) {
+ struct mm_struct *mm = info->mm;
+ struct vm_area_struct *vma;
- for (;;) {
- vi = find_next_vma_info(mapping, &try_list, uprobe->offset, is_register);
- if (!vi)
- break;
+ if (err)
+ goto free;
- if (IS_ERR(vi)) {
- ret = PTR_ERR(vi);
- break;
- }
+ down_write(&mm->mmap_sem);
+ vma = find_vma(mm, (unsigned long)info->vaddr);
+ if (!vma || !valid_vma(vma, is_register))
+ goto unlock;
- mm = vi->mm;
- down_read(&mm->mmap_sem);
- vma = find_vma(mm, (unsigned long)vi->vaddr);
- if (!vma || !valid_vma(vma, is_register)) {
- list_del(&vi->probe_list);
- kfree(vi);
- up_read(&mm->mmap_sem);
- mmput(mm);
- continue;
- }
- vaddr = vma_address(vma, uprobe->offset);
if (vma->vm_file->f_mapping->host != uprobe->inode ||
- vaddr != vi->vaddr) {
- list_del(&vi->probe_list);
- kfree(vi);
- up_read(&mm->mmap_sem);
- mmput(mm);
- continue;
- }
-
- if (is_register)
- ret = install_breakpoint(uprobe, mm, vma, vi->vaddr);
- else
- remove_breakpoint(uprobe, mm, vi->vaddr);
+ vma_address(vma, uprobe->offset) != info->vaddr)
+ goto unlock;
- up_read(&mm->mmap_sem);
- mmput(mm);
if (is_register) {
- if (ret && ret == -EEXIST)
- ret = 0;
- if (ret)
- break;
+ err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+ /*
+ * We can race against uprobe_mmap(), see the
+ * comment near uprobe_hash().
+ */
+ if (err == -EEXIST)
+ err = 0;
+ } else {
+ remove_breakpoint(uprobe, mm, info->vaddr);
}
+ unlock:
+ up_write(&mm->mmap_sem);
+ free:
+ mmput(mm);
+ info = free_map_info(info);
}
- list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) {
- list_del(&vi->probe_list);
- kfree(vi);
- }
-
- return ret;
+ return err;
}
static int __uprobe_register(struct uprobe *uprobe)
@@ -1048,7 +1031,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head)
int uprobe_mmap(struct vm_area_struct *vma)
{
struct list_head tmp_list;
- struct uprobe *uprobe, *u;
+ struct uprobe *uprobe;
struct inode *inode;
int ret, count;
@@ -1066,12 +1049,9 @@ int uprobe_mmap(struct vm_area_struct *vma)
ret = 0;
count = 0;
- list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
- loff_t vaddr;
-
- list_del(&uprobe->pending_list);
+ list_for_each_entry(uprobe, &tmp_list, pending_list) {
if (!ret) {
- vaddr = vma_address(vma, uprobe->offset);
+ loff_t vaddr = vma_address(vma, uprobe->offset);
if (vaddr < vma->vm_start || vaddr >= vma->vm_end) {
put_uprobe(uprobe);
@@ -1079,8 +1059,10 @@ int uprobe_mmap(struct vm_area_struct *vma)
}
ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
-
- /* Ignore double add: */
+ /*
+ * We can race against uprobe_register(), see the
+ * comment near uprobe_hash().
+ */
if (ret == -EEXIST) {
ret = 0;
@@ -1115,7 +1097,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
struct list_head tmp_list;
- struct uprobe *uprobe, *u;
+ struct uprobe *uprobe;
struct inode *inode;
if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
@@ -1132,11 +1114,8 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
mutex_lock(uprobes_mmap_hash(inode));
build_probe_list(inode, &tmp_list);
- list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
- loff_t vaddr;
-
- list_del(&uprobe->pending_list);
- vaddr = vma_address(vma, uprobe->offset);
+ list_for_each_entry(uprobe, &tmp_list, pending_list) {
+ loff_t vaddr = vma_address(vma, uprobe->offset);
if (vaddr >= start && vaddr < end) {
/*
@@ -1378,9 +1357,6 @@ void uprobe_free_utask(struct task_struct *t)
{
struct uprobe_task *utask = t->utask;
- if (t->uprobe_srcu_id != -1)
- srcu_read_unlock_raw(&uprobes_srcu, t->uprobe_srcu_id);
-
if (!utask)
return;
@@ -1398,7 +1374,6 @@ void uprobe_free_utask(struct task_struct *t)
void uprobe_copy_process(struct task_struct *t)
{
t->utask = NULL;
- t->uprobe_srcu_id = -1;
}
/*
@@ -1417,7 +1392,6 @@ static struct uprobe_task *add_utask(void)
if (unlikely(!utask))
return NULL;
- utask->active_uprobe = NULL;
current->utask = utask;
return utask;
}
@@ -1479,41 +1453,64 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
return false;
}
+static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
+{
+ struct mm_struct *mm = current->mm;
+ struct uprobe *uprobe = NULL;
+ struct vm_area_struct *vma;
+
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, bp_vaddr);
+ if (vma && vma->vm_start <= bp_vaddr) {
+ if (valid_vma(vma, false)) {
+ struct inode *inode;
+ loff_t offset;
+
+ inode = vma->vm_file->f_mapping->host;
+ offset = bp_vaddr - vma->vm_start;
+ offset += (vma->vm_pgoff << PAGE_SHIFT);
+ uprobe = find_uprobe(inode, offset);
+ }
+
+ if (!uprobe)
+ *is_swbp = is_swbp_at_addr(mm, bp_vaddr);
+ } else {
+ *is_swbp = -EFAULT;
+ }
+ up_read(&mm->mmap_sem);
+
+ return uprobe;
+}
+
/*
* Run handler and ask thread to singlestep.
* Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
*/
static void handle_swbp(struct pt_regs *regs)
{
- struct vm_area_struct *vma;
struct uprobe_task *utask;
struct uprobe *uprobe;
- struct mm_struct *mm;
unsigned long bp_vaddr;
+ int uninitialized_var(is_swbp);
- uprobe = NULL;
bp_vaddr = uprobe_get_swbp_addr(regs);
- mm = current->mm;
- down_read(&mm->mmap_sem);
- vma = find_vma(mm, bp_vaddr);
-
- if (vma && vma->vm_start <= bp_vaddr && valid_vma(vma, false)) {
- struct inode *inode;
- loff_t offset;
-
- inode = vma->vm_file->f_mapping->host;
- offset = bp_vaddr - vma->vm_start;
- offset += (vma->vm_pgoff << PAGE_SHIFT);
- uprobe = find_uprobe(inode, offset);
- }
-
- srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id);
- current->uprobe_srcu_id = -1;
- up_read(&mm->mmap_sem);
+ uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
if (!uprobe) {
- /* No matching uprobe; signal SIGTRAP. */
- send_sig(SIGTRAP, current, 0);
+ if (is_swbp > 0) {
+ /* No matching uprobe; signal SIGTRAP. */
+ send_sig(SIGTRAP, current, 0);
+ } else {
+ /*
+ * Either we raced with uprobe_unregister() or we can't
+ * access this memory. The latter is only possible if
+ * another thread plays with our ->mm. In both cases
+ * we can simply restart. If this vma was unmapped we
+ * can pretend this insn was not executed yet and get
+ * the (correct) SIGSEGV after restart.
+ */
+ instruction_pointer_set(regs, bp_vaddr);
+ }
return;
}
@@ -1620,7 +1617,6 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs)
utask->state = UTASK_BP_HIT;
set_thread_flag(TIF_UPROBE);
- current->uprobe_srcu_id = srcu_read_lock_raw(&uprobes_srcu);
return 1;
}
@@ -1655,7 +1651,6 @@ static int __init init_uprobes(void)
mutex_init(&uprobes_mutex[i]);
mutex_init(&uprobes_mmap_mutex[i]);
}
- init_srcu_struct(&uprobes_srcu);
return register_die_notifier(&uprobe_exception_nb);
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a008663..b4f20fb 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -312,7 +312,7 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
static int __register_ftrace_function(struct ftrace_ops *ops)
{
- if (ftrace_disabled)
+ if (unlikely(ftrace_disabled))
return -ENODEV;
if (FTRACE_WARN_ON(ops == &global_ops))
@@ -4299,16 +4299,12 @@ int register_ftrace_function(struct ftrace_ops *ops)
mutex_lock(&ftrace_lock);
- if (unlikely(ftrace_disabled))
- goto out_unlock;
-
ret = __register_ftrace_function(ops);
if (!ret)
ret = ftrace_startup(ops, 0);
-
- out_unlock:
mutex_unlock(&ftrace_lock);
+
return ret;
}
EXPORT_SYMBOL_GPL(register_ftrace_function);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f765465..49491fa 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3239,6 +3239,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
if (cpu_buffer->commit_page == cpu_buffer->reader_page)
goto out;
+ /* Don't bother swapping if the ring buffer is empty */
+ if (rb_num_of_entries(cpu_buffer) == 0)
+ goto out;
+
/*
* Reset the reader page to size zero.
*/
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a7fa070..a120f98 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -830,6 +830,8 @@ int register_tracer(struct tracer *type)
current_trace = saved_tracer;
if (ret) {
printk(KERN_CONT "FAILED!\n");
+ /* Add the warning after printing 'FAILED' */
+ WARN_ON(1);
goto out;
}
/* Only reset on passing, to avoid touching corrupted buffers */
@@ -1708,9 +1710,11 @@ EXPORT_SYMBOL_GPL(trace_vprintk);
static void trace_iterator_increment(struct trace_iterator *iter)
{
+ struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu);
+
iter->idx++;
- if (iter->buffer_iter[iter->cpu])
- ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+ if (buf_iter)
+ ring_buffer_read(buf_iter, NULL);
}
static struct trace_entry *
@@ -1718,7 +1722,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
unsigned long *lost_events)
{
struct ring_buffer_event *event;
- struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
+ struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu);
if (buf_iter)
event = ring_buffer_iter_peek(buf_iter, ts);
@@ -1856,10 +1860,10 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
tr->data[cpu]->skipped_entries = 0;
- if (!iter->buffer_iter[cpu])
+ buf_iter = trace_buffer_iter(iter, cpu);
+ if (!buf_iter)
return;
- buf_iter = iter->buffer_iter[cpu];
ring_buffer_iter_reset(buf_iter);
/*
@@ -2205,13 +2209,15 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
int trace_empty(struct trace_iterator *iter)
{
+ struct ring_buffer_iter *buf_iter;
int cpu;
/* If we are looking at one CPU buffer, only check that one */
if (iter->cpu_file != TRACE_PIPE_ALL_CPU) {
cpu = iter->cpu_file;
- if (iter->buffer_iter[cpu]) {
- if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+ buf_iter = trace_buffer_iter(iter, cpu);
+ if (buf_iter) {
+ if (!ring_buffer_iter_empty(buf_iter))
return 0;
} else {
if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
@@ -2221,8 +2227,9 @@ int trace_empty(struct trace_iterator *iter)
}
for_each_tracing_cpu(cpu) {
- if (iter->buffer_iter[cpu]) {
- if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+ buf_iter = trace_buffer_iter(iter, cpu);
+ if (buf_iter) {
+ if (!ring_buffer_iter_empty(buf_iter))
return 0;
} else {
if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
@@ -2381,6 +2388,11 @@ __tracing_open(struct inode *inode, struct file *file)
if (!iter)
return ERR_PTR(-ENOMEM);
+ iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(),
+ GFP_KERNEL);
+ if (!iter->buffer_iter)
+ goto release;
+
/*
* We make a copy of the current tracer to avoid concurrent
* changes on it while we are reading.
@@ -2441,6 +2453,8 @@ __tracing_open(struct inode *inode, struct file *file)
fail:
mutex_unlock(&trace_types_lock);
kfree(iter->trace);
+ kfree(iter->buffer_iter);
+release:
seq_release_private(inode, file);
return ERR_PTR(-ENOMEM);
}
@@ -2481,6 +2495,7 @@ static int tracing_release(struct inode *inode, struct file *file)
mutex_destroy(&iter->mutex);
free_cpumask_var(iter->started);
kfree(iter->trace);
+ kfree(iter->buffer_iter);
seq_release_private(inode, file);
return 0;
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 5aec220..55e1f7f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -317,6 +317,14 @@ struct tracer {
#define TRACE_PIPE_ALL_CPU -1
+static inline struct ring_buffer_iter *
+trace_buffer_iter(struct trace_iterator *iter, int cpu)
+{
+ if (iter->buffer_iter && iter->buffer_iter[cpu])
+ return iter->buffer_iter[cpu];
+ return NULL;
+}
+
int tracer_init(struct tracer *t, struct trace_array *tr);
int tracing_is_enabled(void);
void trace_wake_up(void);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a7d2a4c..ce27c8b 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -538,7 +538,7 @@ get_return_for_leaf(struct trace_iterator *iter,
next = &data->ret;
} else {
- ring_iter = iter->buffer_iter[iter->cpu];
+ ring_iter = trace_buffer_iter(iter, iter->cpu);
/* First peek to compare current entry and the next one */
if (ring_iter)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index df611a0..123b189 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1325,4 +1325,4 @@ __init static int init_events(void)
return 0;
}
-device_initcall(init_events);
+early_initcall(init_events);
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 3d69aa9..46c2f6b 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -250,8 +250,12 @@ endef
all_objs := $(sort $(ALL_OBJS))
all_deps := $(all_objs:%.o=.%.d)
+# let .d file also depends on the source and header files
define check_deps
- $(CC) -M $(CFLAGS) $< > $@;
+ @set -e; $(RM) $@; \
+ $(CC) -M $(CFLAGS) $< > $@...$$; \
+ sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@...$$ > $@; \
+ $(RM) $@...$$
endef
$(gui_deps): ks_version.h
@@ -270,11 +274,13 @@ endif
tags: force
$(RM) tags
- find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px
+ find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+ --regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
TAGS: force
$(RM) TAGS
- find . -name '*.[ch]' | xargs etags
+ find . -name '*.[ch]' | xargs etags \
+ --regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
define do_install
$(print_install) \
@@ -290,7 +296,7 @@ install_lib: all_cmd install_plugins install_python
install: install_lib
clean:
- $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES).*.d
+ $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
$(RM) tags TAGS
endif # skip-makefile
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 5548282..5f34aa3 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -467,8 +467,10 @@ int pevent_register_function(struct pevent *pevent, char *func,
item->mod = NULL;
item->addr = addr;
- pevent->funclist = item;
+ if (!item->func || (mod && !item->mod))
+ die("malloc func");
+ pevent->funclist = item;
pevent->func_count++;
return 0;
@@ -511,12 +513,12 @@ struct printk_list {
static int printk_cmp(const void *a, const void *b)
{
- const struct func_map *fa = a;
- const struct func_map *fb = b;
+ const struct printk_map *pa = a;
+ const struct printk_map *pb = b;
- if (fa->addr < fb->addr)
+ if (pa->addr < pb->addr)
return -1;
- if (fa->addr > fb->addr)
+ if (pa->addr > pb->addr)
return 1;
return 0;
@@ -583,10 +585,13 @@ int pevent_register_print_string(struct pevent *pevent, char *fmt,
item = malloc_or_die(sizeof(*item));
item->next = pevent->printklist;
- pevent->printklist = item;
item->printk = strdup(fmt);
item->addr = addr;
+ if (!item->printk)
+ die("malloc fmt");
+
+ pevent->printklist = item;
pevent->printk_count++;
return 0;
@@ -616,7 +621,9 @@ static struct event_format *alloc_event(void)
{
struct event_format *event;
- event = malloc_or_die(sizeof(*event));
+ event = malloc(sizeof(*event));
+ if (!event)
+ return NULL;
memset(event, 0, sizeof(*event));
return event;
@@ -626,12 +633,8 @@ static void add_event(struct pevent *pevent, struct event_format *event)
{
int i;
- if (!pevent->events)
- pevent->events = malloc_or_die(sizeof(event));
- else
- pevent->events =
- realloc(pevent->events, sizeof(event) *
- (pevent->nr_events + 1));
+ pevent->events = realloc(pevent->events, sizeof(event) *
+ (pevent->nr_events + 1));
if (!pevent->events)
die("Can not allocate events");
@@ -697,6 +700,10 @@ static void free_arg(struct print_arg *arg)
free_arg(arg->symbol.field);
free_flag_sym(arg->symbol.symbols);
break;
+ case PRINT_HEX:
+ free_arg(arg->hex.field);
+ free_arg(arg->hex.size);
+ break;
case PRINT_TYPE:
free(arg->typecast.type);
free_arg(arg->typecast.item);
@@ -775,6 +782,25 @@ int pevent_peek_char(void)
return __peek_char();
}
+static int extend_token(char **tok, char *buf, int size)
+{
+ char *newtok = realloc(*tok, size);
+
+ if (!newtok) {
+ free(*tok);
+ *tok = NULL;
+ return -1;
+ }
+
+ if (!*tok)
+ strcpy(newtok, buf);
+ else
+ strcat(newtok, buf);
+ *tok = newtok;
+
+ return 0;
+}
+
static enum event_type force_token(const char *str, char **tok);
static enum event_type __read_token(char **tok)
@@ -859,17 +885,10 @@ static enum event_type __read_token(char **tok)
do {
if (i == (BUFSIZ - 1)) {
buf[i] = 0;
- if (*tok) {
- *tok = realloc(*tok, tok_size + BUFSIZ);
- if (!*tok)
- return EVENT_NONE;
- strcat(*tok, buf);
- } else
- *tok = strdup(buf);
+ tok_size += BUFSIZ;
- if (!*tok)
+ if (extend_token(tok, buf, tok_size) < 0)
return EVENT_NONE;
- tok_size += BUFSIZ;
i = 0;
}
last_ch = ch;
@@ -908,17 +927,10 @@ static enum event_type __read_token(char **tok)
while (get_type(__peek_char()) == type) {
if (i == (BUFSIZ - 1)) {
buf[i] = 0;
- if (*tok) {
- *tok = realloc(*tok, tok_size + BUFSIZ);
- if (!*tok)
- return EVENT_NONE;
- strcat(*tok, buf);
- } else
- *tok = strdup(buf);
+ tok_size += BUFSIZ;
- if (!*tok)
+ if (extend_token(tok, buf, tok_size) < 0)
return EVENT_NONE;
- tok_size += BUFSIZ;
i = 0;
}
ch = __read_char();
@@ -927,14 +939,7 @@ static enum event_type __read_token(char **tok)
out:
buf[i] = 0;
- if (*tok) {
- *tok = realloc(*tok, tok_size + i);
- if (!*tok)
- return EVENT_NONE;
- strcat(*tok, buf);
- } else
- *tok = strdup(buf);
- if (!*tok)
+ if (extend_token(tok, buf, tok_size + i + 1) < 0)
return EVENT_NONE;
if (type == EVENT_ITEM) {
@@ -1255,9 +1260,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f
field->flags |= FIELD_IS_POINTER;
if (field->type) {
- field->type = realloc(field->type,
- strlen(field->type) +
- strlen(last_token) + 2);
+ char *new_type;
+ new_type = realloc(field->type,
+ strlen(field->type) +
+ strlen(last_token) + 2);
+ if (!new_type) {
+ free(last_token);
+ goto fail;
+ }
+ field->type = new_type;
strcat(field->type, " ");
strcat(field->type, last_token);
free(last_token);
@@ -1282,6 +1293,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
if (strcmp(token, "[") == 0) {
enum event_type last_type = type;
char *brackets = token;
+ char *new_brackets;
int len;
field->flags |= FIELD_IS_ARRAY;
@@ -1301,9 +1313,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f
len = 1;
last_type = type;
- brackets = realloc(brackets,
- strlen(brackets) +
- strlen(token) + len);
+ new_brackets = realloc(brackets,
+ strlen(brackets) +
+ strlen(token) + len);
+ if (!new_brackets) {
+ free(brackets);
+ goto fail;
+ }
+ brackets = new_brackets;
if (len == 2)
strcat(brackets, " ");
strcat(brackets, token);
@@ -1319,7 +1336,12 @@ static int event_read_fields(struct event_format *event, struct format_field **f
free_token(token);
- brackets = realloc(brackets, strlen(brackets) + 2);
+ new_brackets = realloc(brackets, strlen(brackets) + 2);
+ if (!new_brackets) {
+ free(brackets);
+ goto fail;
+ }
+ brackets = new_brackets;
strcat(brackets, "]");
/* add brackets to type */
@@ -1330,10 +1352,16 @@ static int event_read_fields(struct event_format *event, struct format_field **f
* the format: type [] item;
*/
if (type == EVENT_ITEM) {
- field->type = realloc(field->type,
- strlen(field->type) +
- strlen(field->name) +
- strlen(brackets) + 2);
+ char *new_type;
+ new_type = realloc(field->type,
+ strlen(field->type) +
+ strlen(field->name) +
+ strlen(brackets) + 2);
+ if (!new_type) {
+ free(brackets);
+ goto fail;
+ }
+ field->type = new_type;
strcat(field->type, " ");
strcat(field->type, field->name);
free_token(field->name);
@@ -1341,9 +1369,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f
field->name = token;
type = read_token(&token);
} else {
- field->type = realloc(field->type,
- strlen(field->type) +
- strlen(brackets) + 1);
+ char *new_type;
+ new_type = realloc(field->type,
+ strlen(field->type) +
+ strlen(brackets) + 1);
+ if (!new_type) {
+ free(brackets);
+ goto fail;
+ }
+ field->type = new_type;
strcat(field->type, brackets);
}
free(brackets);
@@ -1726,10 +1760,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
/* could just be a type pointer */
if ((strcmp(arg->op.op, "*") == 0) &&
type == EVENT_DELIM && (strcmp(token, ")") == 0)) {
+ char *new_atom;
+
if (left->type != PRINT_ATOM)
die("bad pointer type");
- left->atom.atom = realloc(left->atom.atom,
+ new_atom = realloc(left->atom.atom,
strlen(left->atom.atom) + 3);
+ if (!new_atom)
+ goto out_free;
+
+ left->atom.atom = new_atom;
strcat(left->atom.atom, " *");
free(arg->op.op);
*arg = *left;
@@ -2146,6 +2186,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
if (value == NULL)
goto out_free;
field->value = strdup(value);
+ if (field->value == NULL)
+ goto out_free;
free_arg(arg);
arg = alloc_arg();
@@ -2159,6 +2201,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char **
if (value == NULL)
goto out_free;
field->str = strdup(value);
+ if (field->str == NULL)
+ goto out_free;
free_arg(arg);
arg = NULL;
@@ -2260,6 +2304,45 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
}
static enum event_type
+process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+{
+ struct print_arg *field;
+ enum event_type type;
+ char *token;
+
+ memset(arg, 0, sizeof(*arg));
+ arg->type = PRINT_HEX;
+
+ field = alloc_arg();
+ type = process_arg(event, field, &token);
+
+ if (test_type_token(type, token, EVENT_DELIM, ","))
+ goto out_free;
+
+ arg->hex.field = field;
+
+ free_token(token);
+
+ field = alloc_arg();
+ type = process_arg(event, field, &token);
+
+ if (test_type_token(type, token, EVENT_DELIM, ")"))
+ goto out_free;
+
+ arg->hex.size = field;
+
+ free_token(token);
+ type = read_token_item(tok);
+ return type;
+
+ out_free:
+ free_arg(field);
+ free_token(token);
+ *tok = NULL;
+ return EVENT_ERROR;
+}
+
+static enum event_type
process_dynamic_array(struct event_format *event, struct print_arg *arg, char **tok)
{
struct format_field *field;
@@ -2488,6 +2571,10 @@ process_function(struct event_format *event, struct print_arg *arg,
is_symbolic_field = 1;
return process_symbols(event, arg, tok);
}
+ if (strcmp(token, "__print_hex") == 0) {
+ free_token(token);
+ return process_hex(event, arg, tok);
+ }
if (strcmp(token, "__get_str") == 0) {
free_token(token);
return process_str(event, arg, tok);
@@ -2541,7 +2628,16 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
}
/* atoms can be more than one token long */
while (type == EVENT_ITEM) {
- atom = realloc(atom, strlen(atom) + strlen(token) + 2);
+ char *new_atom;
+ new_atom = realloc(atom,
+ strlen(atom) + strlen(token) + 2);
+ if (!new_atom) {
+ free(atom);
+ *tok = NULL;
+ free_token(token);
+ return EVENT_ERROR;
+ }
+ atom = new_atom;
strcat(atom, " ");
strcat(atom, token);
free_token(token);
@@ -2835,7 +2931,7 @@ static int get_common_info(struct pevent *pevent,
event = pevent->events[0];
field = pevent_find_common_field(event, type);
if (!field)
- die("field '%s' not found", type);
+ return -1;
*offset = field->offset;
*size = field->size;
@@ -2886,15 +2982,16 @@ static int parse_common_flags(struct pevent *pevent, void *data)
static int parse_common_lock_depth(struct pevent *pevent, void *data)
{
- int ret;
-
- ret = __parse_common(pevent, data,
- &pevent->ld_size, &pevent->ld_offset,
- "common_lock_depth");
- if (ret < 0)
- return -1;
+ return __parse_common(pevent, data,
+ &pevent->ld_size, &pevent->ld_offset,
+ "common_lock_depth");
+}
- return ret;
+static int parse_common_migrate_disable(struct pevent *pevent, void *data)
+{
+ return __parse_common(pevent, data,
+ &pevent->ld_size, &pevent->ld_offset,
+ "common_migrate_disable");
}
static int events_id_cmp(const void *a, const void *b);
@@ -2995,6 +3092,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
break;
case PRINT_FLAGS:
case PRINT_SYMBOL:
+ case PRINT_HEX:
break;
case PRINT_TYPE:
val = eval_num_arg(data, size, event, arg->typecast.item);
@@ -3214,11 +3312,13 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
{
struct pevent *pevent = event->pevent;
struct print_flag_sym *flag;
+ struct format_field *field;
unsigned long long val, fval;
unsigned long addr;
char *str;
+ unsigned char *hex;
int print;
- int len;
+ int i, len;
switch (arg->type) {
case PRINT_NULL:
@@ -3228,27 +3328,29 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
print_str_to_seq(s, format, len_arg, arg->atom.atom);
return;
case PRINT_FIELD:
- if (!arg->field.field) {
- arg->field.field = pevent_find_any_field(event, arg->field.name);
- if (!arg->field.field)
+ field = arg->field.field;
+ if (!field) {
+ field = pevent_find_any_field(event, arg->field.name);
+ if (!field)
die("field %s not found", arg->field.name);
+ arg->field.field = field;
}
/* Zero sized fields, mean the rest of the data */
- len = arg->field.field->size ? : size - arg->field.field->offset;
+ len = field->size ? : size - field->offset;
/*
* Some events pass in pointers. If this is not an array
* and the size is the same as long_size, assume that it
* is a pointer.
*/
- if (!(arg->field.field->flags & FIELD_IS_ARRAY) &&
- arg->field.field->size == pevent->long_size) {
- addr = *(unsigned long *)(data + arg->field.field->offset);
+ if (!(field->flags & FIELD_IS_ARRAY) &&
+ field->size == pevent->long_size) {
+ addr = *(unsigned long *)(data + field->offset);
trace_seq_printf(s, "%lx", addr);
break;
}
str = malloc_or_die(len + 1);
- memcpy(str, data + arg->field.field->offset, len);
+ memcpy(str, data + field->offset, len);
str[len] = 0;
print_str_to_seq(s, format, len_arg, str);
free(str);
@@ -3281,6 +3383,23 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
}
}
break;
+ case PRINT_HEX:
+ field = arg->hex.field->field.field;
+ if (!field) {
+ str = arg->hex.field->field.name;
+ field = pevent_find_any_field(event, str);
+ if (!field)
+ die("field %s not found", str);
+ arg->hex.field->field.field = field;
+ }
+ hex = data + field->offset;
+ len = eval_num_arg(data, size, event, arg->hex.size);
+ for (i = 0; i < len; i++) {
+ if (i)
+ trace_seq_putc(s, ' ');
+ trace_seq_printf(s, "%02x", hex[i]);
+ }
+ break;
case PRINT_TYPE:
break;
@@ -3299,7 +3418,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
break;
}
case PRINT_BSTRING:
- trace_seq_printf(s, format, arg->string.string);
+ print_str_to_seq(s, format, len_arg, arg->string.string);
break;
case PRINT_OP:
/*
@@ -3363,6 +3482,10 @@ process_defined_func(struct trace_seq *s, void *data, int size,
string = malloc_or_die(sizeof(*string));
string->next = strings;
string->str = strdup(str.buffer);
+ if (!string->str)
+ die("malloc str");
+
+ args[i] = (unsigned long long)string->str;
strings = string;
trace_seq_destroy(&str);
break;
@@ -3400,6 +3523,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
unsigned long long ip, val;
char *ptr;
void *bptr;
+ int vsize;
field = pevent->bprint_buf_field;
ip_field = pevent->bprint_ip_field;
@@ -3448,6 +3572,8 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
goto process_again;
case '0' ... '9':
goto process_again;
+ case '.':
+ goto process_again;
case 'p':
ls = 1;
/* fall through */
@@ -3455,23 +3581,30 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
case 'u':
case 'x':
case 'i':
- /* the pointers are always 4 bytes aligned */
- bptr = (void *)(((unsigned long)bptr + 3) &
- ~3);
switch (ls) {
case 0:
- ls = 4;
+ vsize = 4;
break;
case 1:
- ls = pevent->long_size;
+ vsize = pevent->long_size;
break;
case 2:
- ls = 8;
+ vsize = 8;
+ break;
default:
+ vsize = ls; /* ? */
break;
}
- val = pevent_read_number(pevent, bptr, ls);
- bptr += ls;
+ /* fall through */
+ case '*':
+ if (*ptr == '*')
+ vsize = 4;
+
+ /* the pointers are always 4 bytes aligned */
+ bptr = (void *)(((unsigned long)bptr + 3) &
+ ~3);
+ val = pevent_read_number(pevent, bptr, vsize);
+ bptr += vsize;
arg = alloc_arg();
arg->next = NULL;
arg->type = PRINT_ATOM;
@@ -3479,12 +3612,21 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
sprintf(arg->atom.atom, "%lld", val);
*next = arg;
next = &arg->next;
+ /*
+ * The '*' case means that an arg is used as the length.
+ * We need to continue to figure out for what.
+ */
+ if (*ptr == '*')
+ goto process_again;
+
break;
case 's':
arg = alloc_arg();
arg->next = NULL;
arg->type = PRINT_BSTRING;
arg->string.string = strdup(bptr);
+ if (!arg->string.string)
+ break;
bptr += strlen(bptr) + 1;
*next = arg;
next = &arg->next;
@@ -3589,6 +3731,16 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]);
}
+static int is_printable_array(char *p, unsigned int len)
+{
+ unsigned int i;
+
+ for (i = 0; i < len && p[i]; i++)
+ if (!isprint(p[i]))
+ return 0;
+ return 1;
+}
+
static void print_event_fields(struct trace_seq *s, void *data, int size,
struct event_format *event)
{
@@ -3608,7 +3760,8 @@ static void print_event_fields(struct trace_seq *s, void *data, int size,
len = offset >> 16;
offset &= 0xffff;
}
- if (field->flags & FIELD_IS_STRING) {
+ if (field->flags & FIELD_IS_STRING &&
+ is_printable_array(data + offset, len)) {
trace_seq_printf(s, "%s", (char *)data + offset);
} else {
trace_seq_puts(s, "ARRAY[");
@@ -3619,6 +3772,7 @@ static void print_event_fields(struct trace_seq *s, void *data, int size,
*((unsigned char *)data + offset + i));
}
trace_seq_putc(s, ']');
+ field->flags &= ~FIELD_IS_STRING;
}
} else {
val = pevent_read_number(event->pevent, data + field->offset,
@@ -3758,6 +3912,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
} else if (*(ptr+1) == 'M' || *(ptr+1) == 'm') {
print_mac_arg(s, *(ptr+1), data, size, event, arg);
ptr++;
+ arg = arg->next;
break;
}
@@ -3794,14 +3949,15 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
break;
}
}
- if (pevent->long_size == 8 && ls) {
+ if (pevent->long_size == 8 && ls &&
+ sizeof(long) != 8) {
char *p;
ls = 2;
/* make %l into %ll */
p = strchr(format, 'l');
if (p)
- memmove(p, p+1, strlen(p)+1);
+ memmove(p+1, p, strlen(p)+1);
else if (strcmp(format, "%p") == 0)
strcpy(format, "0x%llx");
}
@@ -3878,8 +4034,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
* pevent_data_lat_fmt - parse the data for the latency format
* @pevent: a handle to the pevent
* @s: the trace_seq to write to
- * @data: the raw data to read from
- * @size: currently unused.
+ * @record: the record to read from
*
* This parses out the Latency format (interrupts disabled,
* need rescheduling, in hard/soft interrupt, preempt count
@@ -3889,10 +4044,13 @@ void pevent_data_lat_fmt(struct pevent *pevent,
struct trace_seq *s, struct pevent_record *record)
{
static int check_lock_depth = 1;
+ static int check_migrate_disable = 1;
static int lock_depth_exists;
+ static int migrate_disable_exists;
unsigned int lat_flags;
unsigned int pc;
int lock_depth;
+ int migrate_disable;
int hardirq;
int softirq;
void *data = record->data;
@@ -3900,18 +4058,26 @@ void pevent_data_lat_fmt(struct pevent *pevent,
lat_flags = parse_common_flags(pevent, data);
pc = parse_common_pc(pevent, data);
/* lock_depth may not always exist */
- if (check_lock_depth) {
- struct format_field *field;
- struct event_format *event;
-
- check_lock_depth = 0;
- event = pevent->events[0];
- field = pevent_find_common_field(event, "common_lock_depth");
- if (field)
- lock_depth_exists = 1;
- }
if (lock_depth_exists)
lock_depth = parse_common_lock_depth(pevent, data);
+ else if (check_lock_depth) {
+ lock_depth = parse_common_lock_depth(pevent, data);
+ if (lock_depth < 0)
+ check_lock_depth = 0;
+ else
+ lock_depth_exists = 1;
+ }
+
+ /* migrate_disable may not always exist */
+ if (migrate_disable_exists)
+ migrate_disable = parse_common_migrate_disable(pevent, data);
+ else if (check_migrate_disable) {
+ migrate_disable = parse_common_migrate_disable(pevent, data);
+ if (migrate_disable < 0)
+ check_migrate_disable = 0;
+ else
+ migrate_disable_exists = 1;
+ }
hardirq = lat_flags & TRACE_FLAG_HARDIRQ;
softirq = lat_flags & TRACE_FLAG_SOFTIRQ;
@@ -3930,6 +4096,13 @@ void pevent_data_lat_fmt(struct pevent *pevent,
else
trace_seq_putc(s, '.');
+ if (migrate_disable_exists) {
+ if (migrate_disable < 0)
+ trace_seq_putc(s, '.');
+ else
+ trace_seq_printf(s, "%d", migrate_disable);
+ }
+
if (lock_depth_exists) {
if (lock_depth < 0)
trace_seq_putc(s, '.');
@@ -3996,10 +4169,7 @@ const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid)
* pevent_data_comm_from_pid - parse the data into the print format
* @s: the trace_seq to write to
* @event: the handle to the event
- * @cpu: the cpu the event was recorded on
- * @data: the raw data
- * @size: the size of the raw data
- * @nsecs: the timestamp of the event
+ * @record: the record to read from
*
* This parses the raw @data using the given @event information and
* writes the print format into the trace_seq.
@@ -4279,6 +4449,13 @@ static void print_args(struct print_arg *args)
trace_seq_destroy(&s);
printf(")");
break;
+ case PRINT_HEX:
+ printf("__print_hex(");
+ print_args(args->hex.field);
+ printf(", ");
+ print_args(args->hex.size);
+ printf(")");
+ break;
case PRINT_STRING:
case PRINT_BSTRING:
printf("__get_str(%s)", args->string.string);
@@ -4541,6 +4718,8 @@ int pevent_parse_event(struct pevent *pevent,
die("failed to read event id");
event->system = strdup(sys);
+ if (!event->system)
+ die("failed to allocate system");
/* Add pevent to event so that it can be referenced */
event->pevent = pevent;
@@ -4582,6 +4761,11 @@ int pevent_parse_event(struct pevent *pevent,
list = &arg->next;
arg->type = PRINT_FIELD;
arg->field.name = strdup(field->name);
+ if (!arg->field.name) {
+ do_warning("failed to allocate field name");
+ event->flags |= EVENT_FL_FAILED;
+ return -1;
+ }
arg->field.field = field;
}
return 0;
@@ -4753,7 +4937,7 @@ int pevent_get_any_field_val(struct trace_seq *s, struct event_format *event,
* @record: The record with the field name.
* @err: print default error if failed.
*
- * Returns: 0 on success, -1 field not fould, or 1 if buffer is full.
+ * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
*/
int pevent_print_num_field(struct trace_seq *s, const char *fmt,
struct event_format *event, const char *name,
@@ -4795,11 +4979,12 @@ static void free_func_handle(struct pevent_function_handler *func)
* pevent_register_print_function - register a helper function
* @pevent: the handle to the pevent
* @func: the function to process the helper function
+ * @ret_type: the return type of the helper function
* @name: the name of the helper function
* @parameters: A list of enum pevent_func_arg_type
*
* Some events may have helper functions in the print format arguments.
- * This allows a plugin to dynmically create a way to process one
+ * This allows a plugin to dynamically create a way to process one
* of these functions.
*
* The @parameters is a variable list of pevent_func_arg_type enums that
@@ -4870,12 +5055,13 @@ int pevent_register_print_function(struct pevent *pevent,
}
/**
- * pevent_register_event_handle - register a way to parse an event
+ * pevent_register_event_handler - register a way to parse an event
* @pevent: the handle to the pevent
* @id: the id of the event to register
* @sys_name: the system name the event belongs to
* @event_name: the name of the event
* @func: the function to call to parse the event information
+ * @context: the data to be passed to @func
*
* This function allows a developer to override the parsing of
* a given event. If for some reason the default print format
@@ -4925,6 +5111,11 @@ int pevent_register_event_handler(struct pevent *pevent,
if (sys_name)
handle->sys_name = strdup(sys_name);
+ if ((event_name && !handle->event_name) ||
+ (sys_name && !handle->sys_name)) {
+ die("Failed to allocate event/sys name");
+ }
+
handle->func = func;
handle->next = pevent->handlers;
pevent->handlers = handle;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index ac997bc..5772ad8 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -226,6 +226,11 @@ struct print_arg_symbol {
struct print_flag_sym *symbols;
};
+struct print_arg_hex {
+ struct print_arg *field;
+ struct print_arg *size;
+};
+
struct print_arg_dynarray {
struct format_field *field;
struct print_arg *index;
@@ -253,6 +258,7 @@ enum print_arg_type {
PRINT_FIELD,
PRINT_FLAGS,
PRINT_SYMBOL,
+ PRINT_HEX,
PRINT_TYPE,
PRINT_STRING,
PRINT_BSTRING,
@@ -270,6 +276,7 @@ struct print_arg {
struct print_arg_typecast typecast;
struct print_arg_flags flags;
struct print_arg_symbol symbol;
+ struct print_arg_hex hex;
struct print_arg_func func;
struct print_arg_string string;
struct print_arg_op op;
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index dfcfe2c..ad17855 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -96,7 +96,7 @@ static enum event_type read_token(char **tok)
(strcmp(token, "=") == 0 || strcmp(token, "!") == 0) &&
pevent_peek_char() == '~') {
/* append it */
- *tok = malloc(3);
+ *tok = malloc_or_die(3);
sprintf(*tok, "%c%c", *token, '~');
free_token(token);
/* Now remove the '~' from the buffer */
@@ -148,17 +148,11 @@ add_filter_type(struct event_filter *filter, int id)
if (filter_type)
return filter_type;
- if (!filter->filters)
- filter->event_filters =
- malloc_or_die(sizeof(*filter->event_filters));
- else {
- filter->event_filters =
- realloc(filter->event_filters,
- sizeof(*filter->event_filters) *
- (filter->filters + 1));
- if (!filter->event_filters)
- die("Could not allocate filter");
- }
+ filter->event_filters = realloc(filter->event_filters,
+ sizeof(*filter->event_filters) *
+ (filter->filters + 1));
+ if (!filter->event_filters)
+ die("Could not allocate filter");
for (i = 0; i < filter->filters; i++) {
if (filter->event_filters[i].event_id > id)
@@ -1480,7 +1474,7 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
{
struct filter_type *filter_type;
int count = 0;
- int *ids;
+ int *ids = NULL;
int i;
if (!filter->filters)
@@ -1504,10 +1498,8 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
default:
break;
}
- if (count)
- ids = realloc(ids, sizeof(*ids) * (count + 1));
- else
- ids = malloc(sizeof(*ids));
+
+ ids = realloc(ids, sizeof(*ids) * (count + 1));
if (!ids)
die("Can't allocate ids");
ids[count++] = filter_type->event_id;
@@ -1710,18 +1702,43 @@ static int test_num(struct event_format *event,
static const char *get_field_str(struct filter_arg *arg, struct pevent_record *record)
{
- const char *val = record->data + arg->str.field->offset;
+ struct event_format *event;
+ struct pevent *pevent;
+ unsigned long long addr;
+ const char *val = NULL;
+ char hex[64];
- /*
- * We need to copy the data since we can't be sure the field
- * is null terminated.
- */
- if (*(val + arg->str.field->size - 1)) {
- /* copy it */
- memcpy(arg->str.buffer, val, arg->str.field->size);
- /* the buffer is already NULL terminated */
- val = arg->str.buffer;
+ /* If the field is not a string convert it */
+ if (arg->str.field->flags & FIELD_IS_STRING) {
+ val = record->data + arg->str.field->offset;
+
+ /*
+ * We need to copy the data since we can't be sure the field
+ * is null terminated.
+ */
+ if (*(val + arg->str.field->size - 1)) {
+ /* copy it */
+ memcpy(arg->str.buffer, val, arg->str.field->size);
+ /* the buffer is already NULL terminated */
+ val = arg->str.buffer;
+ }
+
+ } else {
+ event = arg->str.field->event;
+ pevent = event->pevent;
+ addr = get_value(event, arg->str.field, record);
+
+ if (arg->str.field->flags & (FIELD_IS_POINTER | FIELD_IS_LONG))
+ /* convert to a kernel symbol */
+ val = pevent_find_function(pevent, addr);
+
+ if (val == NULL) {
+ /* just use the hex of the string name */
+ snprintf(hex, 64, "0x%llx", addr);
+ val = hex;
+ }
}
+
return val;
}
@@ -2001,11 +2018,13 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
char *lstr;
char *rstr;
char *op;
- char *str;
+ char *str = NULL;
int len;
lstr = arg_to_str(filter, arg->exp.left);
rstr = arg_to_str(filter, arg->exp.right);
+ if (!lstr || !rstr)
+ goto out;
switch (arg->exp.type) {
case FILTER_EXP_ADD:
@@ -2045,6 +2064,7 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
len = strlen(op) + strlen(lstr) + strlen(rstr) + 4;
str = malloc_or_die(len);
snprintf(str, len, "%s %s %s", lstr, op, rstr);
+out:
free(lstr);
free(rstr);
@@ -2061,6 +2081,8 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
lstr = arg_to_str(filter, arg->num.left);
rstr = arg_to_str(filter, arg->num.right);
+ if (!lstr || !rstr)
+ goto out;
switch (arg->num.type) {
case FILTER_CMP_EQ:
@@ -2097,6 +2119,7 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
break;
}
+out:
free(lstr);
free(rstr);
return str;
@@ -2247,7 +2270,12 @@ int pevent_filter_compare(struct event_filter *filter1, struct event_filter *fil
/* The best way to compare complex filters is with strings */
str1 = arg_to_str(filter1, filter_type1->filter);
str2 = arg_to_str(filter2, filter_type2->filter);
- result = strcmp(str1, str2) != 0;
+ if (str1 && str2)
+ result = strcmp(str1, str2) != 0;
+ else
+ /* bail out if allocation fails */
+ result = 1;
+
free(str1);
free(str2);
if (result)
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index a3dbadb..7065cd6 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -12,7 +12,7 @@ SYNOPSIS
DESCRIPTION
-----------
-This 'perf bench' command is general framework for benchmark suites.
+This 'perf bench' command is a general framework for benchmark suites.
COMMON OPTIONS
--------------
@@ -45,14 +45,20 @@ SUBSYSTEM
'sched'::
Scheduler and IPC mechanisms.
+'mem'::
+ Memory access performance.
+
+'all'::
+ All benchmark subsystems.
+
SUITES FOR 'sched'
~~~~~~~~~~~~~~~~~~
*messaging*::
Suite for evaluating performance of scheduler and IPC mechanisms.
Based on hackbench by Rusty Russell.
-Options of *pipe*
-^^^^^^^^^^^^^^^^^
+Options of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
-p::
--pipe::
Use pipe() instead of socketpair()
@@ -115,6 +121,72 @@ Example of *pipe*
59004 ops/sec
---------------------
+SUITES FOR 'mem'
+~~~~~~~~~~~~~~~~
+*memcpy*::
+Suite for evaluating performance of simple memory copy in various ways.
+
+Options of *memcpy*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to copy (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to copy (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
+
+-i::
+--iterations::
+Repeat memcpy invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memcpy.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memcpy.
+
+*memset*::
+Suite for evaluating performance of simple memory set in various ways.
+
+Options of *memset*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to set (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to set (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
+
+-i::
+--iterations::
+Repeat memset invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memset.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memset.
+
SEE ALSO
--------
linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2d89f02..495210a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -57,7 +57,7 @@ OPTIONS
-s::
--sort=::
- Sort by key(s): pid, comm, dso, symbol, parent.
+ Sort by key(s): pid, comm, dso, symbol, parent, srcline.
-p::
--parent=<regex>::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 4a5680c..5b80d84 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -112,7 +112,7 @@ Default is to monitor all CPUS.
-s::
--sort::
- Sort by key(s): pid, comm, dso, symbol, parent
+ Sort by key(s): pid, comm, dso, symbol, parent, srcline.
-n::
--show-nr-samples::
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 0eee64c..75d74e5 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -155,7 +155,7 @@ endif
### --- END CONFIGURATION SECTION ---
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
BASIC_LDFLAGS =
# Guard against environment variables
@@ -503,6 +503,7 @@ else
LIB_OBJS += $(OUTPUT)ui/progress.o
LIB_OBJS += $(OUTPUT)ui/util.o
LIB_OBJS += $(OUTPUT)ui/tui/setup.o
+ LIB_OBJS += $(OUTPUT)ui/tui/util.o
LIB_H += ui/browser.h
LIB_H += ui/browsers/map.h
LIB_H += ui/helpline.h
@@ -522,13 +523,18 @@ else
msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
BASIC_CFLAGS += -DNO_GTK2_SUPPORT
else
+ ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y)
+ BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR
+ endif
BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0)
EXTLIBS += $(shell pkg-config --libs gtk+-2.0)
LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
+ LIB_OBJS += $(OUTPUT)ui/gtk/util.o
# Make sure that it'd be included only once.
ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),)
LIB_OBJS += $(OUTPUT)ui/setup.o
+ LIB_OBJS += $(OUTPUT)ui/util.o
endif
endif
endif
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 7155722..02dad5d 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -24,21 +24,21 @@
static const char *length_str = "1MB";
static const char *routine = "default";
static int iterations = 1;
-static bool use_clock;
-static int clock_fd;
+static bool use_cycle;
+static int cycle_fd;
static bool only_prefault;
static bool no_prefault;
static const struct option options[] = {
OPT_STRING('l', "length", &length_str, "1MB",
"Specify length of memory to copy. "
- "available unit: B, MB, GB (upper and lower)"),
+ "Available units: B, KB, MB, GB and TB (upper and lower)"),
OPT_STRING('r', "routine", &routine, "default",
"Specify routine to copy"),
OPT_INTEGER('i', "iterations", &iterations,
"repeat memcpy() invocation this number of times"),
- OPT_BOOLEAN('c', "clock", &use_clock,
- "Use CPU clock for measuring"),
+ OPT_BOOLEAN('c', "cycle", &use_cycle,
+ "Use cycles event instead of gettimeofday() for measuring"),
OPT_BOOLEAN('o', "only-prefault", &only_prefault,
"Show only the result with page faults before memcpy()"),
OPT_BOOLEAN('n', "no-prefault", &no_prefault,
@@ -76,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = {
NULL
};
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES
};
-static void init_clock(void)
+static void init_cycle(void)
{
- clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+ cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
- if (clock_fd < 0 && errno == ENOSYS)
+ if (cycle_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
else
- BUG_ON(clock_fd < 0);
+ BUG_ON(cycle_fd < 0);
}
-static u64 get_clock(void)
+static u64 get_cycle(void)
{
int ret;
u64 clk;
- ret = read(clock_fd, &clk, sizeof(u64));
+ ret = read(cycle_fd, &clk, sizeof(u64));
BUG_ON(ret != sizeof(u64));
return clk;
@@ -119,9 +119,9 @@ static void alloc_mem(void **dst, void **src, size_t length)
die("memory allocation failed - maybe length is too large?\n");
}
-static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
+static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
{
- u64 clock_start = 0ULL, clock_end = 0ULL;
+ u64 cycle_start = 0ULL, cycle_end = 0ULL;
void *src = NULL, *dst = NULL;
int i;
@@ -130,14 +130,14 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
if (prefault)
fn(dst, src, len);
- clock_start = get_clock();
+ cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, src, len);
- clock_end = get_clock();
+ cycle_end = get_cycle();
free(src);
free(dst);
- return clock_end - clock_start;
+ return cycle_end - cycle_start;
}
static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
@@ -182,17 +182,17 @@ int bench_mem_memcpy(int argc, const char **argv,
int i;
size_t len;
double result_bps[2];
- u64 result_clock[2];
+ u64 result_cycle[2];
argc = parse_options(argc, argv, options,
bench_mem_memcpy_usage, 0);
- if (use_clock)
- init_clock();
+ if (use_cycle)
+ init_cycle();
len = (size_t)perf_atoll((char *)length_str);
- result_clock[0] = result_clock[1] = 0ULL;
+ result_cycle[0] = result_cycle[1] = 0ULL;
result_bps[0] = result_bps[1] = 0.0;
if ((s64)len <= 0) {
@@ -223,11 +223,11 @@ int bench_mem_memcpy(int argc, const char **argv,
if (!only_prefault && !no_prefault) {
/* show both of results */
- if (use_clock) {
- result_clock[0] =
- do_memcpy_clock(routines[i].fn, len, false);
- result_clock[1] =
- do_memcpy_clock(routines[i].fn, len, true);
+ if (use_cycle) {
+ result_cycle[0] =
+ do_memcpy_cycle(routines[i].fn, len, false);
+ result_cycle[1] =
+ do_memcpy_cycle(routines[i].fn, len, true);
} else {
result_bps[0] =
do_memcpy_gettimeofday(routines[i].fn,
@@ -237,9 +237,9 @@ int bench_mem_memcpy(int argc, const char **argv,
len, true);
}
} else {
- if (use_clock) {
- result_clock[pf] =
- do_memcpy_clock(routines[i].fn,
+ if (use_cycle) {
+ result_cycle[pf] =
+ do_memcpy_cycle(routines[i].fn,
len, only_prefault);
} else {
result_bps[pf] =
@@ -251,12 +251,12 @@ int bench_mem_memcpy(int argc, const char **argv,
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
if (!only_prefault && !no_prefault) {
- if (use_clock) {
- printf(" %14lf Clock/Byte\n",
- (double)result_clock[0]
+ if (use_cycle) {
+ printf(" %14lf Cycle/Byte\n",
+ (double)result_cycle[0]
/ (double)len);
- printf(" %14lf Clock/Byte (with prefault)\n",
- (double)result_clock[1]
+ printf(" %14lf Cycle/Byte (with prefault)\n",
+ (double)result_cycle[1]
/ (double)len);
} else {
print_bps(result_bps[0]);
@@ -265,9 +265,9 @@ int bench_mem_memcpy(int argc, const char **argv,
printf(" (with prefault)\n");
}
} else {
- if (use_clock) {
- printf(" %14lf Clock/Byte",
- (double)result_clock[pf]
+ if (use_cycle) {
+ printf(" %14lf Cycle/Byte",
+ (double)result_cycle[pf]
/ (double)len);
} else
print_bps(result_bps[pf]);
@@ -277,17 +277,17 @@ int bench_mem_memcpy(int argc, const char **argv,
break;
case BENCH_FORMAT_SIMPLE:
if (!only_prefault && !no_prefault) {
- if (use_clock) {
+ if (use_cycle) {
printf("%lf %lf\n",
- (double)result_clock[0] / (double)len,
- (double)result_clock[1] / (double)len);
+ (double)result_cycle[0] / (double)len,
+ (double)result_cycle[1] / (double)len);
} else {
printf("%lf %lf\n",
result_bps[0], result_bps[1]);
}
} else {
- if (use_clock) {
- printf("%lf\n", (double)result_clock[pf]
+ if (use_cycle) {
+ printf("%lf\n", (double)result_cycle[pf]
/ (double)len);
} else
printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index e907918..350cc95 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -24,21 +24,21 @@
static const char *length_str = "1MB";
static const char *routine = "default";
static int iterations = 1;
-static bool use_clock;
-static int clock_fd;
+static bool use_cycle;
+static int cycle_fd;
static bool only_prefault;
static bool no_prefault;
static const struct option options[] = {
OPT_STRING('l', "length", &length_str, "1MB",
- "Specify length of memory to copy. "
- "available unit: B, MB, GB (upper and lower)"),
+ "Specify length of memory to set. "
+ "Available units: B, KB, MB, GB and TB (upper and lower)"),
OPT_STRING('r', "routine", &routine, "default",
- "Specify routine to copy"),
+ "Specify routine to set"),
OPT_INTEGER('i', "iterations", &iterations,
"repeat memset() invocation this number of times"),
- OPT_BOOLEAN('c', "clock", &use_clock,
- "Use CPU clock for measuring"),
+ OPT_BOOLEAN('c', "cycle", &use_cycle,
+ "Use cycles event instead of gettimeofday() for measuring"),
OPT_BOOLEAN('o', "only-prefault", &only_prefault,
"Show only the result with page faults before memset()"),
OPT_BOOLEAN('n', "no-prefault", &no_prefault,
@@ -76,27 +76,27 @@ static const char * const bench_mem_memset_usage[] = {
NULL
};
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES
};
-static void init_clock(void)
+static void init_cycle(void)
{
- clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+ cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
- if (clock_fd < 0 && errno == ENOSYS)
+ if (cycle_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
else
- BUG_ON(clock_fd < 0);
+ BUG_ON(cycle_fd < 0);
}
-static u64 get_clock(void)
+static u64 get_cycle(void)
{
int ret;
u64 clk;
- ret = read(clock_fd, &clk, sizeof(u64));
+ ret = read(cycle_fd, &clk, sizeof(u64));
BUG_ON(ret != sizeof(u64));
return clk;
@@ -115,9 +115,9 @@ static void alloc_mem(void **dst, size_t length)
die("memory allocation failed - maybe length is too large?\n");
}
-static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
+static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
{
- u64 clock_start = 0ULL, clock_end = 0ULL;
+ u64 cycle_start = 0ULL, cycle_end = 0ULL;
void *dst = NULL;
int i;
@@ -126,13 +126,13 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
if (prefault)
fn(dst, -1, len);
- clock_start = get_clock();
+ cycle_start = get_cycle();
for (i = 0; i < iterations; ++i)
fn(dst, i, len);
- clock_end = get_clock();
+ cycle_end = get_cycle();
free(dst);
- return clock_end - clock_start;
+ return cycle_end - cycle_start;
}
static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
@@ -176,17 +176,17 @@ int bench_mem_memset(int argc, const char **argv,
int i;
size_t len;
double result_bps[2];
- u64 result_clock[2];
+ u64 result_cycle[2];
argc = parse_options(argc, argv, options,
bench_mem_memset_usage, 0);
- if (use_clock)
- init_clock();
+ if (use_cycle)
+ init_cycle();
len = (size_t)perf_atoll((char *)length_str);
- result_clock[0] = result_clock[1] = 0ULL;
+ result_cycle[0] = result_cycle[1] = 0ULL;
result_bps[0] = result_bps[1] = 0.0;
if ((s64)len <= 0) {
@@ -217,11 +217,11 @@ int bench_mem_memset(int argc, const char **argv,
if (!only_prefault && !no_prefault) {
/* show both of results */
- if (use_clock) {
- result_clock[0] =
- do_memset_clock(routines[i].fn, len, false);
- result_clock[1] =
- do_memset_clock(routines[i].fn, len, true);
+ if (use_cycle) {
+ result_cycle[0] =
+ do_memset_cycle(routines[i].fn, len, false);
+ result_cycle[1] =
+ do_memset_cycle(routines[i].fn, len, true);
} else {
result_bps[0] =
do_memset_gettimeofday(routines[i].fn,
@@ -231,9 +231,9 @@ int bench_mem_memset(int argc, const char **argv,
len, true);
}
} else {
- if (use_clock) {
- result_clock[pf] =
- do_memset_clock(routines[i].fn,
+ if (use_cycle) {
+ result_cycle[pf] =
+ do_memset_cycle(routines[i].fn,
len, only_prefault);
} else {
result_bps[pf] =
@@ -245,12 +245,12 @@ int bench_mem_memset(int argc, const char **argv,
switch (bench_format) {
case BENCH_FORMAT_DEFAULT:
if (!only_prefault && !no_prefault) {
- if (use_clock) {
- printf(" %14lf Clock/Byte\n",
- (double)result_clock[0]
+ if (use_cycle) {
+ printf(" %14lf Cycle/Byte\n",
+ (double)result_cycle[0]
/ (double)len);
- printf(" %14lf Clock/Byte (with prefault)\n ",
- (double)result_clock[1]
+ printf(" %14lf Cycle/Byte (with prefault)\n ",
+ (double)result_cycle[1]
/ (double)len);
} else {
print_bps(result_bps[0]);
@@ -259,9 +259,9 @@ int bench_mem_memset(int argc, const char **argv,
printf(" (with prefault)\n");
}
} else {
- if (use_clock) {
- printf(" %14lf Clock/Byte",
- (double)result_clock[pf]
+ if (use_cycle) {
+ printf(" %14lf Cycle/Byte",
+ (double)result_cycle[pf]
/ (double)len);
} else
print_bps(result_bps[pf]);
@@ -271,17 +271,17 @@ int bench_mem_memset(int argc, const char **argv,
break;
case BENCH_FORMAT_SIMPLE:
if (!only_prefault && !no_prefault) {
- if (use_clock) {
+ if (use_cycle) {
printf("%lf %lf\n",
- (double)result_clock[0] / (double)len,
- (double)result_clock[1] / (double)len);
+ (double)result_cycle[0] / (double)len,
+ (double)result_cycle[1] / (double)len);
} else {
printf("%lf %lf\n",
result_bps[0], result_bps[1]);
}
} else {
- if (use_clock) {
- printf("%lf\n", (double)result_clock[pf]
+ if (use_cycle) {
+ printf("%lf\n", (double)result_cycle[pf]
/ (double)len);
} else
printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b0e74ab..1f31002 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -33,7 +33,7 @@ struct bench_suite {
};
\
/* sentinel: easy for help */
-#define suite_all { "all", "test all suite (pseudo suite)", NULL }
+#define suite_all { "all", "Test all benchmark suites", NULL }
static struct bench_suite sched_suites[] = {
{ "messaging",
@@ -75,7 +75,7 @@ static struct bench_subsys subsystems[] = {
"memory access performance",
mem_suites },
{ "all", /* sentinel: easy for help */
- "test all subsystem (pseudo subsystem)",
+ "all benchmark subsystem",
NULL },
{ NULL,
NULL,
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index acd78dc..0dd5a05 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -60,7 +60,7 @@ static int __cmd_evlist(const char *input_name, struct perf_attr_details *detail
list_for_each_entry(pos, &session->evlist->entries, node) {
bool first = true;
- printf("%s", event_name(pos));
+ printf("%s", perf_evsel__name(pos));
if (details->verbose || details->freq) {
comma_printf(&first, " sample_freq=%" PRIu64,
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 547af48..ce35015 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -57,6 +57,11 @@ static unsigned long nr_allocs, nr_cross_allocs;
#define PATH_SYS_NODE "/sys/devices/system/node"
+struct perf_kmem {
+ struct perf_tool tool;
+ struct perf_session *session;
+};
+
static void init_cpunode_map(void)
{
FILE *fp;
@@ -278,14 +283,16 @@ static void process_free_event(void *data,
s_alloc->alloc_cpu = -1;
}
-static void process_raw_event(union perf_event *raw_event __used, void *data,
+static void process_raw_event(struct perf_tool *tool,
+ union perf_event *raw_event __used, void *data,
int cpu, u64 timestamp, struct thread *thread)
{
+ struct perf_kmem *kmem = container_of(tool, struct perf_kmem, tool);
struct event_format *event;
int type;
- type = trace_parse_common_type(data);
- event = trace_find_event(type);
+ type = trace_parse_common_type(kmem->session->pevent, data);
+ event = pevent_find_event(kmem->session->pevent, type);
if (!strcmp(event->name, "kmalloc") ||
!strcmp(event->name, "kmem_cache_alloc")) {
@@ -306,7 +313,7 @@ static void process_raw_event(union perf_event *raw_event __used, void *data,
}
}
-static int process_sample_event(struct perf_tool *tool __used,
+static int process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel __used,
@@ -322,16 +329,18 @@ static int process_sample_event(struct perf_tool *tool __used,
dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
- process_raw_event(event, sample->raw_data, sample->cpu,
+ process_raw_event(tool, event, sample->raw_data, sample->cpu,
sample->time, thread);
return 0;
}
-static struct perf_tool perf_kmem = {
- .sample = process_sample_event,
- .comm = perf_event__process_comm,
- .ordered_samples = true,
+static struct perf_kmem perf_kmem = {
+ .tool = {
+ .sample = process_sample_event,
+ .comm = perf_event__process_comm,
+ .ordered_samples = true,
+ },
};
static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -486,11 +495,15 @@ static void sort_result(void)
static int __cmd_kmem(void)
{
int err = -EINVAL;
- struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &perf_kmem);
+ struct perf_session *session;
+
+ session = perf_session__new(input_name, O_RDONLY, 0, false,
+ &perf_kmem.tool);
if (session == NULL)
return -ENOMEM;
+ perf_kmem.session = session;
+
if (perf_session__create_kernel_maps(session) < 0)
goto out_delete;
@@ -498,7 +511,7 @@ static int __cmd_kmem(void)
goto out_delete;
setup_pager();
- err = perf_session__process_events(session, &perf_kmem);
+ err = perf_session__process_events(session, &perf_kmem.tool);
if (err != 0)
goto out_delete;
sort_result();
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index fd53319..b3c4285 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -724,8 +724,8 @@ process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread)
struct event_format *event;
int type;
- type = trace_parse_common_type(data);
- event = trace_find_event(type);
+ type = trace_parse_common_type(session->pevent, data);
+ event = pevent_find_event(session->pevent, type);
if (!strcmp(event->name, "lock_acquire"))
process_lock_acquire_event(data, event, cpu, timestamp, thread);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f95840d..f5a6452 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -265,7 +265,7 @@ try_again:
if (err == ENOENT) {
ui__error("The %s event is not supported.\n",
- event_name(pos));
+ perf_evsel__name(pos));
exit(EXIT_FAILURE);
}
@@ -916,7 +916,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
usage_with_options(record_usage, record_options);
list_for_each_entry(pos, &evsel_list->entries, node) {
- if (perf_header__push_event(pos->attr.config, event_name(pos)))
+ if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos)))
goto out_free_fd;
}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 25249f7..69b1c11 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -69,7 +69,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
- err = machine__resolve_callchain(machine, evsel, al->thread,
+ err = machine__resolve_callchain(machine, al->thread,
sample->callchain, &parent);
if (err)
return err;
@@ -140,7 +140,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
- err = machine__resolve_callchain(machine, evsel, al->thread,
+ err = machine__resolve_callchain(machine, al->thread,
sample->callchain, &parent);
if (err)
return err;
@@ -230,7 +230,7 @@ static int process_read_event(struct perf_tool *tool,
struct perf_report *rep = container_of(tool, struct perf_report, tool);
if (rep->show_threads) {
- const char *name = evsel ? event_name(evsel) : "unknown";
+ const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
perf_read_values_add_value(&rep->show_threads_values,
event->read.pid, event->read.tid,
event->read.id,
@@ -239,17 +239,18 @@ static int process_read_event(struct perf_tool *tool,
}
dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
- evsel ? event_name(evsel) : "FAIL",
+ evsel ? perf_evsel__name(evsel) : "FAIL",
event->read.value);
return 0;
}
+/* For pipe mode, sample_type is not currently set */
static int perf_report__setup_sample_type(struct perf_report *rep)
{
struct perf_session *self = rep->session;
- if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+ if (!self->fd_pipe && !(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
if (sort__has_parent) {
ui__error("Selected --sort parent, but no "
"callchain data. Did you call "
@@ -272,7 +273,8 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
}
if (sort__branch_mode == 1) {
- if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
+ if (!self->fd_pipe &&
+ !(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) {
ui__error("Selected -b but no branch data. "
"Did you call perf record without -b?\n");
return -1;
@@ -314,7 +316,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
list_for_each_entry(pos, &evlist->entries, node) {
struct hists *hists = &pos->hists;
- const char *evname = event_name(pos);
+ const char *evname = perf_evsel__name(pos);
hists__fprintf_nr_sample_events(hists, evname, stdout);
hists__fprintf(hists, NULL, false, true, 0, 0, stdout);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b125e07..7a9ad2b 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -43,6 +43,11 @@ static u64 sleep_measurement_overhead;
static unsigned long nr_tasks;
+struct perf_sched {
+ struct perf_tool tool;
+ struct perf_session *session;
+};
+
struct sched_atom;
struct task_desc {
@@ -1597,11 +1602,13 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
struct perf_evsel *evsel,
struct machine *machine)
{
+ struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+ struct pevent *pevent = sched->session->pevent;
struct thread *thread = machine__findnew_thread(machine, sample->pid);
if (thread == NULL) {
pr_debug("problem processing %s event, skipping it.\n",
- evsel->name);
+ perf_evsel__name(evsel));
return -1;
}
@@ -1612,7 +1619,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
tracepoint_handler f = evsel->handler.func;
if (evsel->handler.data == NULL)
- evsel->handler.data = trace_find_event(evsel->attr.config);
+ evsel->handler.data = pevent_find_event(pevent,
+ evsel->attr.config);
f(tool, evsel->handler.data, sample, machine, thread);
}
@@ -1620,12 +1628,14 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
return 0;
}
-static struct perf_tool perf_sched = {
- .sample = perf_sched__process_tracepoint_sample,
- .comm = perf_event__process_comm,
- .lost = perf_event__process_lost,
- .fork = perf_event__process_task,
- .ordered_samples = true,
+static struct perf_sched perf_sched = {
+ .tool = {
+ .sample = perf_sched__process_tracepoint_sample,
+ .comm = perf_event__process_comm,
+ .lost = perf_event__process_lost,
+ .fork = perf_event__process_task,
+ .ordered_samples = true,
+ },
};
static void read_events(bool destroy, struct perf_session **psession)
@@ -1640,16 +1650,20 @@ static void read_events(bool destroy, struct perf_session **psession)
{ "sched:sched_process_exit", process_sched_exit_event, },
{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
};
- struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &perf_sched);
+ struct perf_session *session;
+
+ session = perf_session__new(input_name, O_RDONLY, 0, false,
+ &perf_sched.tool);
if (session == NULL)
die("No Memory");
- err = perf_evlist__set_tracepoints_handlers_array(session->evlist, handlers);
+ perf_sched.session = session;
+
+ err = perf_session__set_tracepoints_handlers(session, handlers);
assert(err == 0);
if (perf_session__has_traces(session, "record -R")) {
- err = perf_session__process_events(session, &perf_sched);
+ err = perf_session__process_events(session, &perf_sched.tool);
if (err)
die("Failed to process events, error %d", err);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8e395a5..1e60ab7 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -28,6 +28,11 @@ static bool system_wide;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+struct perf_script {
+ struct perf_tool tool;
+ struct perf_session *session;
+};
+
enum perf_output_field {
PERF_OUTPUT_COMM = 1U << 0,
PERF_OUTPUT_TID = 1U << 1,
@@ -137,10 +142,11 @@ static const char *output_field2str(enum perf_output_field field)
#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x)
-static int perf_event_attr__check_stype(struct perf_event_attr *attr,
- u64 sample_type, const char *sample_msg,
- enum perf_output_field field)
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+ u64 sample_type, const char *sample_msg,
+ enum perf_output_field field)
{
+ struct perf_event_attr *attr = &evsel->attr;
int type = attr->type;
const char *evname;
@@ -148,7 +154,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr,
return 0;
if (output[type].user_set) {
- evname = __event_name(attr->type, attr->config);
+ evname = perf_evsel__name(evsel);
pr_err("Samples for '%s' event do not have %s attribute set. "
"Cannot print '%s' field.\n",
evname, sample_msg, output_field2str(field));
@@ -157,7 +163,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr,
/* user did not ask for it explicitly so remove from the default list */
output[type].fields &= ~field;
- evname = __event_name(attr->type, attr->config);
+ evname = perf_evsel__name(evsel);
pr_debug("Samples for '%s' event do not have %s attribute set. "
"Skipping '%s' field.\n",
evname, sample_msg, output_field2str(field));
@@ -175,8 +181,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
return -EINVAL;
if (PRINT_FIELD(IP)) {
- if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP",
- PERF_OUTPUT_IP))
+ if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
+ PERF_OUTPUT_IP))
return -EINVAL;
if (!no_callchain &&
@@ -185,8 +191,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
}
if (PRINT_FIELD(ADDR) &&
- perf_event_attr__check_stype(attr, PERF_SAMPLE_ADDR, "ADDR",
- PERF_OUTPUT_ADDR))
+ perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+ PERF_OUTPUT_ADDR))
return -EINVAL;
if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
@@ -208,18 +214,18 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
}
if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
- perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID",
- PERF_OUTPUT_TID|PERF_OUTPUT_PID))
+ perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
+ PERF_OUTPUT_TID|PERF_OUTPUT_PID))
return -EINVAL;
if (PRINT_FIELD(TIME) &&
- perf_event_attr__check_stype(attr, PERF_SAMPLE_TIME, "TIME",
- PERF_OUTPUT_TIME))
+ perf_evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME",
+ PERF_OUTPUT_TIME))
return -EINVAL;
if (PRINT_FIELD(CPU) &&
- perf_event_attr__check_stype(attr, PERF_SAMPLE_CPU, "CPU",
- PERF_OUTPUT_CPU))
+ perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+ PERF_OUTPUT_CPU))
return -EINVAL;
return 0;
@@ -256,11 +262,13 @@ static int perf_session__check_output_opt(struct perf_session *session)
return 0;
}
-static void print_sample_start(struct perf_sample *sample,
+static void print_sample_start(struct pevent *pevent,
+ struct perf_sample *sample,
struct thread *thread,
- struct perf_event_attr *attr)
+ struct perf_evsel *evsel)
{
int type;
+ struct perf_event_attr *attr = &evsel->attr;
struct event_format *event;
const char *evname = NULL;
unsigned long secs;
@@ -300,12 +308,18 @@ static void print_sample_start(struct perf_sample *sample,
if (PRINT_FIELD(EVNAME)) {
if (attr->type == PERF_TYPE_TRACEPOINT) {
- type = trace_parse_common_type(sample->raw_data);
- event = trace_find_event(type);
+ /*
+ * XXX Do we really need this here?
+ * perf_evlist__set_tracepoint_names should have done
+ * this already
+ */
+ type = trace_parse_common_type(pevent,
+ sample->raw_data);
+ event = pevent_find_event(pevent, type);
if (event)
evname = event->name;
} else
- evname = __event_name(attr->type, attr->config);
+ evname = perf_evsel__name(evsel);
printf("%s: ", evname ? evname : "[unknown]");
}
@@ -387,7 +401,7 @@ static void print_sample_bts(union perf_event *event,
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine, evsel,
+ perf_event__print_ip(event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
@@ -402,6 +416,7 @@ static void print_sample_bts(union perf_event *event,
}
static void process_event(union perf_event *event __unused,
+ struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine,
@@ -412,7 +427,7 @@ static void process_event(union perf_event *event __unused,
if (output[attr->type].fields == 0)
return;
- print_sample_start(sample, thread, attr);
+ print_sample_start(pevent, sample, thread, evsel);
if (is_bts_event(attr)) {
print_sample_bts(event, sample, evsel, machine, thread);
@@ -420,7 +435,7 @@ static void process_event(union perf_event *event __unused,
}
if (PRINT_FIELD(TRACE))
- print_trace_event(sample->cpu, sample->raw_data,
+ print_trace_event(pevent, sample->cpu, sample->raw_data,
sample->raw_size);
if (PRINT_FIELD(ADDR))
@@ -431,7 +446,7 @@ static void process_event(union perf_event *event __unused,
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine, evsel,
+ perf_event__print_ip(event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
@@ -451,7 +466,8 @@ static int default_stop_script(void)
return 0;
}
-static int default_generate_script(const char *outfile __unused)
+static int default_generate_script(struct pevent *pevent __unused,
+ const char *outfile __unused)
{
return 0;
}
@@ -489,6 +505,7 @@ static int process_sample_event(struct perf_tool *tool __used,
struct machine *machine)
{
struct addr_location al;
+ struct perf_script *scr = container_of(tool, struct perf_script, tool);
struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
if (thread == NULL) {
@@ -520,24 +537,27 @@ static int process_sample_event(struct perf_tool *tool __used,
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
return 0;
- scripting_ops->process_event(event, sample, evsel, machine, thread);
+ scripting_ops->process_event(event, scr->session->pevent,
+ sample, evsel, machine, thread);
evsel->hists.stats.total_period += sample->period;
return 0;
}
-static struct perf_tool perf_script = {
- .sample = process_sample_event,
- .mmap = perf_event__process_mmap,
- .comm = perf_event__process_comm,
- .exit = perf_event__process_task,
- .fork = perf_event__process_task,
- .attr = perf_event__process_attr,
- .event_type = perf_event__process_event_type,
- .tracing_data = perf_event__process_tracing_data,
- .build_id = perf_event__process_build_id,
- .ordered_samples = true,
- .ordering_requires_timestamps = true,
+static struct perf_script perf_script = {
+ .tool = {
+ .sample = process_sample_event,
+ .mmap = perf_event__process_mmap,
+ .comm = perf_event__process_comm,
+ .exit = perf_event__process_task,
+ .fork = perf_event__process_task,
+ .attr = perf_event__process_attr,
+ .event_type = perf_event__process_event_type,
+ .tracing_data = perf_event__process_tracing_data,
+ .build_id = perf_event__process_build_id,
+ .ordered_samples = true,
+ .ordering_requires_timestamps = true,
+ },
};
extern volatile int session_done;
@@ -553,7 +573,7 @@ static int __cmd_script(struct perf_session *session)
signal(SIGINT, sig_handler);
- ret = perf_session__process_events(session, &perf_script);
+ ret = perf_session__process_events(session, &perf_script.tool);
if (debug_mode)
pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
@@ -1335,10 +1355,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
if (!script_name)
setup_pager();
- session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_script);
+ session = perf_session__new(input_name, O_RDONLY, 0, false,
+ &perf_script.tool);
if (session == NULL)
return -ENOMEM;
+ perf_script.session = session;
+
if (cpu_list) {
if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
return -1;
@@ -1384,7 +1407,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
return -1;
}
- err = scripting_ops->generate_script("perf-script");
+ err = scripting_ops->generate_script(session->pevent,
+ "perf-script");
goto out;
}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 07b5c77..861f0ae 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -391,7 +391,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
if (verbose) {
fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
- event_name(counter), count[0], count[1], count[2]);
+ perf_evsel__name(counter), count[0], count[1], count[2]);
}
/*
@@ -496,7 +496,7 @@ static int run_perf_stat(int argc __used, const char **argv)
errno == ENXIO) {
if (verbose)
ui__warning("%s event is not supported by the kernel.\n",
- event_name(counter));
+ perf_evsel__name(counter));
counter->supported = false;
continue;
}
@@ -594,7 +594,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
csv_output ? 0 : -4,
evsel_list->cpus->map[cpu], csv_sep);
- fprintf(output, fmt, cpustr, msecs, csv_sep, event_name(evsel));
+ fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel));
if (evsel->cgrp)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -792,7 +792,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
else
cpu = 0;
- fprintf(output, fmt, cpustr, avg, csv_sep, event_name(evsel));
+ fprintf(output, fmt, cpustr, avg, csv_sep, perf_evsel__name(evsel));
if (evsel->cgrp)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -908,7 +908,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
csv_sep,
csv_output ? 0 : -24,
- event_name(counter));
+ perf_evsel__name(counter));
if (counter->cgrp)
fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
@@ -961,7 +961,7 @@ static void print_counter(struct perf_evsel *counter)
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
csv_sep,
csv_output ? 0 : -24,
- event_name(counter));
+ perf_evsel__name(counter));
if (counter->cgrp)
fprintf(output, "%s%s",
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 5a8727c..5ce3030 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -583,7 +583,7 @@ static int test__basic_mmap(void)
if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
pr_debug("expected %d %s events, got %d\n",
expected_nr_events[evsel->idx],
- event_name(evsel), nr_events[evsel->idx]);
+ perf_evsel__name(evsel), nr_events[evsel->idx]);
goto out_munmap;
}
}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6bb0277..e3cab5f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -245,7 +245,7 @@ static void perf_top__show_details(struct perf_top *top)
if (notes->src == NULL)
goto out_unlock;
- printf("Showing %s for %s\n", event_name(top->sym_evsel), symbol->name);
+ printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name);
printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter);
more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel->idx,
@@ -408,7 +408,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top)
fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top->print_entries);
if (top->evlist->nr_entries > 1)
- fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top->sym_evsel));
+ fprintf(stdout, "\t[E] active event counter. \t(%s)\n", perf_evsel__name(top->sym_evsel));
fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter);
@@ -503,13 +503,13 @@ static void perf_top__handle_keypress(struct perf_top *top, int c)
fprintf(stderr, "\nAvailable events:");
list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
- fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, event_name(top->sym_evsel));
+ fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
prompt_integer(&counter, "Enter details event counter");
if (counter >= top->evlist->nr_entries) {
top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node);
- fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top->sym_evsel));
+ fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel));
sleep(1);
break;
}
@@ -774,7 +774,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
- err = machine__resolve_callchain(machine, evsel, al.thread,
+ err = machine__resolve_callchain(machine, al.thread,
sample->callchain, &parent);
if (err)
return;
@@ -960,7 +960,7 @@ try_again:
if (err == ENOENT) {
ui__error("The %s event is not supported.\n",
- event_name(counter));
+ perf_evsel__name(counter));
goto out_err;
} else if (err == EMFILE) {
ui__error("Too many events are opened.\n"
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index d9084e0..6c18785 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -78,6 +78,19 @@ int main(int argc, char *argv[])
return 0;
}
endef
+
+define SOURCE_GTK2_INFOBAR
+#pragma GCC diagnostic ignored \"-Wstrict-prototypes\"
+#include <gtk/gtk.h>
+#pragma GCC diagnostic error \"-Wstrict-prototypes\"
+
+int main(void)
+{
+ gtk_info_bar_new();
+
+ return 0;
+}
+endef
endif
ifndef NO_LIBPERL
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 34b1c46..67a2703 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -814,7 +814,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
{
struct disasm_line *pos, *n;
struct annotation *notes;
- const size_t size = symbol__size(sym);
+ size_t size;
struct map_symbol ms = {
.map = map,
.sym = sym,
@@ -834,6 +834,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
if (sym == NULL)
return -1;
+ size = symbol__size(sym);
+
if (map->dso->annotate_warned)
return -1;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 53f6697..482f051 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -23,6 +23,7 @@ struct hist_browser {
struct hists *hists;
struct hist_entry *he_selection;
struct map_symbol *selection;
+ int print_seq;
bool has_symbols;
};
@@ -800,6 +801,196 @@ do_offset:
}
}
+static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser,
+ struct callchain_node *chain_node,
+ u64 total, int level,
+ FILE *fp)
+{
+ struct rb_node *node;
+ int offset = level * LEVEL_OFFSET_STEP;
+ u64 new_total, remaining;
+ int printed = 0;
+
+ if (callchain_param.mode == CHAIN_GRAPH_REL)
+ new_total = chain_node->children_hit;
+ else
+ new_total = total;
+
+ remaining = new_total;
+ node = rb_first(&chain_node->rb_root);
+ while (node) {
+ struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+ struct rb_node *next = rb_next(node);
+ u64 cumul = callchain_cumul_hits(child);
+ struct callchain_list *chain;
+ char folded_sign = ' ';
+ int first = true;
+ int extra_offset = 0;
+
+ remaining -= cumul;
+
+ list_for_each_entry(chain, &child->val, list) {
+ char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str;
+ const char *str;
+ bool was_first = first;
+
+ if (first)
+ first = false;
+ else
+ extra_offset = LEVEL_OFFSET_STEP;
+
+ folded_sign = callchain_list__folded(chain);
+
+ alloc_str = NULL;
+ str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+ if (was_first) {
+ double percent = cumul * 100.0 / new_total;
+
+ if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
+ str = "Not enough memory!";
+ else
+ str = alloc_str;
+ }
+
+ printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str);
+ free(alloc_str);
+ if (folded_sign == '+')
+ break;
+ }
+
+ if (folded_sign == '-') {
+ const int new_level = level + (extra_offset ? 2 : 1);
+ printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total,
+ new_level, fp);
+ }
+
+ node = next;
+ }
+
+ return printed;
+}
+
+static int hist_browser__fprintf_callchain_node(struct hist_browser *browser,
+ struct callchain_node *node,
+ int level, FILE *fp)
+{
+ struct callchain_list *chain;
+ int offset = level * LEVEL_OFFSET_STEP;
+ char folded_sign = ' ';
+ int printed = 0;
+
+ list_for_each_entry(chain, &node->val, list) {
+ char ipstr[BITS_PER_LONG / 4 + 1], *s;
+
+ folded_sign = callchain_list__folded(chain);
+ s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+ printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
+ }
+
+ if (folded_sign == '-')
+ printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node,
+ browser->hists->stats.total_period,
+ level + 1, fp);
+ return printed;
+}
+
+static int hist_browser__fprintf_callchain(struct hist_browser *browser,
+ struct rb_root *chain, int level, FILE *fp)
+{
+ struct rb_node *nd;
+ int printed = 0;
+
+ for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+ struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+
+ printed += hist_browser__fprintf_callchain_node(browser, node, level, fp);
+ }
+
+ return printed;
+}
+
+static int hist_browser__fprintf_entry(struct hist_browser *browser,
+ struct hist_entry *he, FILE *fp)
+{
+ char s[8192];
+ double percent;
+ int printed = 0;
+ char folded_sign = ' ';
+
+ if (symbol_conf.use_callchain)
+ folded_sign = hist_entry__folded(he);
+
+ hist_entry__snprintf(he, s, sizeof(s), browser->hists);
+ percent = (he->period * 100.0) / browser->hists->stats.total_period;
+
+ if (symbol_conf.use_callchain)
+ printed += fprintf(fp, "%c ", folded_sign);
+
+ printed += fprintf(fp, " %5.2f%%", percent);
+
+ if (symbol_conf.show_nr_samples)
+ printed += fprintf(fp, " %11u", he->nr_events);
+
+ if (symbol_conf.show_total_period)
+ printed += fprintf(fp, " %12" PRIu64, he->period);
+
+ printed += fprintf(fp, "%s\n", rtrim(s));
+
+ if (folded_sign == '-')
+ printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp);
+
+ return printed;
+}
+
+static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
+{
+ struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries));
+ int printed = 0;
+
+ while (nd) {
+ struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+ printed += hist_browser__fprintf_entry(browser, h, fp);
+ nd = hists__filter_entries(rb_next(nd));
+ }
+
+ return printed;
+}
+
+static int hist_browser__dump(struct hist_browser *browser)
+{
+ char filename[64];
+ FILE *fp;
+
+ while (1) {
+ scnprintf(filename, sizeof(filename), "perf.hist.%d", browser->print_seq);
+ if (access(filename, F_OK))
+ break;
+ /*
+ * XXX: Just an arbitrary lazy upper limit
+ */
+ if (++browser->print_seq == 8192) {
+ ui_helpline__fpush("Too many perf.hist.N files, nothing written!");
+ return -1;
+ }
+ }
+
+ fp = fopen(filename, "w");
+ if (fp == NULL) {
+ char bf[64];
+ strerror_r(errno, bf, sizeof(bf));
+ ui_helpline__fpush("Couldn't write to %s: %s", filename, bf);
+ return -1;
+ }
+
+ ++browser->print_seq;
+ hist_browser__fprintf(browser, fp);
+ fclose(fp);
+ ui_helpline__fpush("%s written!", filename);
+
+ return 0;
+}
+
static struct hist_browser *hist_browser__new(struct hists *hists)
{
struct hist_browser *browser = zalloc(sizeof(*browser));
@@ -937,6 +1128,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
browser->selection->map->dso->annotate_warned)
continue;
goto do_annotate;
+ case 'P':
+ hist_browser__dump(browser);
+ continue;
case 'd':
goto zoom_dso;
case 't':
@@ -969,6 +1163,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
"E Expand all callchains\n"
"d Zoom into current DSO\n"
"t Zoom into current Thread\n"
+ "P Print histograms to perf.hist.N\n"
"/ Filter symbol by name");
continue;
case K_ENTER:
@@ -1172,7 +1367,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
bool current_entry = ui_browser__is_current_entry(browser, row);
unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
- const char *ev_name = event_name(evsel);
+ const char *ev_name = perf_evsel__name(evsel);
char bf[256], unit;
const char *warn = " ";
size_t printed;
@@ -1240,7 +1435,7 @@ browse_hists:
*/
if (timer)
timer(arg);
- ev_name = event_name(pos);
+ ev_name = perf_evsel__name(pos);
key = perf_evsel__hists_browse(pos, nr_events, help,
ev_name, true, timer,
arg, delay_secs);
@@ -1309,17 +1504,11 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
ui_helpline__push("Press ESC to exit");
list_for_each_entry(pos, &evlist->entries, node) {
- const char *ev_name = event_name(pos);
+ const char *ev_name = perf_evsel__name(pos);
size_t line_len = strlen(ev_name) + 7;
if (menu.b.width < line_len)
menu.b.width = line_len;
- /*
- * Cache the evsel name, tracepoints have a _high_ cost per
- * event_name() call.
- */
- if (pos->name == NULL)
- pos->name = strdup(ev_name);
}
return perf_evsel_menu__run(&menu, evlist->nr_entries, help, timer,
@@ -1330,11 +1519,10 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
void(*timer)(void *arg), void *arg,
int delay_secs)
{
-
if (evlist->nr_entries == 1) {
struct perf_evsel *first = list_entry(evlist->entries.next,
struct perf_evsel, node);
- const char *ev_name = event_name(first);
+ const char *ev_name = perf_evsel__name(first);
return perf_evsel__hists_browse(first, evlist->nr_entries, help,
ev_name, false, timer, arg,
delay_secs);
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 0656c38..ec12e0b 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -11,8 +11,8 @@
static void perf_gtk__signal(int sig)
{
+ perf_gtk__exit(false);
psignal(sig, "perf");
- gtk_main_quit();
}
static void perf_gtk__resize_window(GtkWidget *window)
@@ -122,13 +122,59 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
gtk_container_add(GTK_CONTAINER(window), view);
}
+#ifdef HAVE_GTK_INFO_BAR
+static GtkWidget *perf_gtk__setup_info_bar(void)
+{
+ GtkWidget *info_bar;
+ GtkWidget *label;
+ GtkWidget *content_area;
+
+ info_bar = gtk_info_bar_new();
+ gtk_widget_set_no_show_all(info_bar, TRUE);
+
+ label = gtk_label_new("");
+ gtk_widget_show(label);
+
+ content_area = gtk_info_bar_get_content_area(GTK_INFO_BAR(info_bar));
+ gtk_container_add(GTK_CONTAINER(content_area), label);
+
+ gtk_info_bar_add_button(GTK_INFO_BAR(info_bar), GTK_STOCK_OK,
+ GTK_RESPONSE_OK);
+ g_signal_connect(info_bar, "response",
+ G_CALLBACK(gtk_widget_hide), NULL);
+
+ pgctx->info_bar = info_bar;
+ pgctx->message_label = label;
+
+ return info_bar;
+}
+#endif
+
+static GtkWidget *perf_gtk__setup_statusbar(void)
+{
+ GtkWidget *stbar;
+ unsigned ctxid;
+
+ stbar = gtk_statusbar_new();
+
+ ctxid = gtk_statusbar_get_context_id(GTK_STATUSBAR(stbar),
+ "perf report");
+ pgctx->statbar = stbar;
+ pgctx->statbar_ctx_id = ctxid;
+
+ return stbar;
+}
+
int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
const char *help __used,
void (*timer) (void *arg)__used,
void *arg __used, int delay_secs __used)
{
struct perf_evsel *pos;
+ GtkWidget *vbox;
GtkWidget *notebook;
+ GtkWidget *info_bar;
+ GtkWidget *statbar;
GtkWidget *window;
signal(SIGSEGV, perf_gtk__signal);
@@ -143,11 +189,17 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+ pgctx = perf_gtk__activate_context(window);
+ if (!pgctx)
+ return -1;
+
+ vbox = gtk_vbox_new(FALSE, 0);
+
notebook = gtk_notebook_new();
list_for_each_entry(pos, &evlist->entries, node) {
struct hists *hists = &pos->hists;
- const char *evname = event_name(pos);
+ const char *evname = perf_evsel__name(pos);
GtkWidget *scrolled_window;
GtkWidget *tab_label;
@@ -164,7 +216,16 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
}
- gtk_container_add(GTK_CONTAINER(window), notebook);
+ gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0);
+
+ info_bar = perf_gtk__setup_info_bar();
+ if (info_bar)
+ gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0);
+
+ statbar = perf_gtk__setup_statusbar();
+ gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0);
+
+ gtk_container_add(GTK_CONTAINER(window), vbox);
gtk_widget_show_all(window);
@@ -174,5 +235,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
gtk_main();
+ perf_gtk__deactivate_context(&pgctx);
+
return 0;
}
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 75177ee..a4d0f2b 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -1,8 +1,39 @@
#ifndef _PERF_GTK_H_
#define _PERF_GTK_H_ 1
+#include <stdbool.h>
+
#pragma GCC diagnostic ignored "-Wstrict-prototypes"
#include <gtk/gtk.h>
#pragma GCC diagnostic error "-Wstrict-prototypes"
+
+struct perf_gtk_context {
+ GtkWidget *main_window;
+
+#ifdef HAVE_GTK_INFO_BAR
+ GtkWidget *info_bar;
+ GtkWidget *message_label;
+#endif
+ GtkWidget *statbar;
+ guint statbar_ctx_id;
+};
+
+extern struct perf_gtk_context *pgctx;
+
+static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx)
+{
+ return ctx && ctx->main_window;
+}
+
+struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window);
+int perf_gtk__deactivate_context(struct perf_gtk_context **ctx);
+
+#ifndef HAVE_GTK_INFO_BAR
+static inline GtkWidget *perf_gtk__setup_info_bar(void)
+{
+ return NULL;
+}
+#endif
+
#endif /* _PERF_GTK_H_ */
diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c
index 8295299..92879ce 100644
--- a/tools/perf/ui/gtk/setup.c
+++ b/tools/perf/ui/gtk/setup.c
@@ -1,12 +1,17 @@
#include "gtk.h"
#include "../../util/cache.h"
+#include "../../util/debug.h"
+
+extern struct perf_error_ops perf_gtk_eops;
int perf_gtk__init(void)
{
+ perf_error__register(&perf_gtk_eops);
return gtk_init_check(NULL, NULL) ? 0 : -1;
}
void perf_gtk__exit(bool wait_for_ok __used)
{
+ perf_error__unregister(&perf_gtk_eops);
gtk_main_quit();
}
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
new file mode 100644
index 0000000..0ead373
--- /dev/null
+++ b/tools/perf/ui/gtk/util.c
@@ -0,0 +1,129 @@
+#include "../util.h"
+#include "../../util/debug.h"
+#include "gtk.h"
+
+#include <string.h>
+
+
+struct perf_gtk_context *pgctx;
+
+struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window)
+{
+ struct perf_gtk_context *ctx;
+
+ ctx = malloc(sizeof(*pgctx));
+ if (ctx)
+ ctx->main_window = window;
+
+ return ctx;
+}
+
+int perf_gtk__deactivate_context(struct perf_gtk_context **ctx)
+{
+ if (!perf_gtk__is_active_context(*ctx))
+ return -1;
+
+ free(*ctx);
+ *ctx = NULL;
+ return 0;
+}
+
+static int perf_gtk__error(const char *format, va_list args)
+{
+ char *msg;
+ GtkWidget *dialog;
+
+ if (!perf_gtk__is_active_context(pgctx) ||
+ vasprintf(&msg, format, args) < 0) {
+ fprintf(stderr, "Error:\n");
+ vfprintf(stderr, format, args);
+ fprintf(stderr, "\n");
+ return -1;
+ }
+
+ dialog = gtk_message_dialog_new_with_markup(GTK_WINDOW(pgctx->main_window),
+ GTK_DIALOG_DESTROY_WITH_PARENT,
+ GTK_MESSAGE_ERROR,
+ GTK_BUTTONS_CLOSE,
+ "<b>Error</b>\n\n%s", msg);
+ gtk_dialog_run(GTK_DIALOG(dialog));
+
+ gtk_widget_destroy(dialog);
+ free(msg);
+ return 0;
+}
+
+#ifdef HAVE_GTK_INFO_BAR
+static int perf_gtk__warning_info_bar(const char *format, va_list args)
+{
+ char *msg;
+
+ if (!perf_gtk__is_active_context(pgctx) ||
+ vasprintf(&msg, format, args) < 0) {
+ fprintf(stderr, "Warning:\n");
+ vfprintf(stderr, format, args);
+ fprintf(stderr, "\n");
+ return -1;
+ }
+
+ gtk_label_set_text(GTK_LABEL(pgctx->message_label), msg);
+ gtk_info_bar_set_message_type(GTK_INFO_BAR(pgctx->info_bar),
+ GTK_MESSAGE_WARNING);
+ gtk_widget_show(pgctx->info_bar);
+
+ free(msg);
+ return 0;
+}
+#else
+static int perf_gtk__warning_statusbar(const char *format, va_list args)
+{
+ char *msg, *p;
+
+ if (!perf_gtk__is_active_context(pgctx) ||
+ vasprintf(&msg, format, args) < 0) {
+ fprintf(stderr, "Warning:\n");
+ vfprintf(stderr, format, args);
+ fprintf(stderr, "\n");
+ return -1;
+ }
+
+ gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar),
+ pgctx->statbar_ctx_id);
+
+ /* Only first line can be displayed */
+ p = strchr(msg, '\n');
+ if (p)
+ *p = '\0';
+
+ gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar),
+ pgctx->statbar_ctx_id, msg);
+
+ free(msg);
+ return 0;
+}
+#endif
+
+struct perf_error_ops perf_gtk_eops = {
+ .error = perf_gtk__error,
+#ifdef HAVE_GTK_INFO_BAR
+ .warning = perf_gtk__warning_info_bar,
+#else
+ .warning = perf_gtk__warning_statusbar,
+#endif
+};
+
+/*
+ * FIXME: Functions below should be implemented properly.
+ * For now, just add stubs for NO_NEWT=1 build.
+ */
+#ifdef NO_NEWT_SUPPORT
+int ui_helpline__show_help(const char *format __used, va_list ap __used)
+{
+ return 0;
+}
+
+void ui_progress__update(u64 curr __used, u64 total __used,
+ const char *title __used)
+{
+}
+#endif
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index d33e943..e813c1d 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -15,6 +15,8 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
static volatile int ui__need_resize;
+extern struct perf_error_ops perf_tui_eops;
+
void ui__refresh_dimensions(bool force)
{
if (force || ui__need_resize) {
@@ -122,6 +124,8 @@ int ui__init(void)
signal(SIGINT, ui__signal);
signal(SIGQUIT, ui__signal);
signal(SIGTERM, ui__signal);
+
+ perf_error__register(&perf_tui_eops);
out:
return err;
}
@@ -137,4 +141,6 @@ void ui__exit(bool wait_for_ok)
SLsmg_refresh();
SLsmg_reset_smg();
SLang_reset_tty();
+
+ perf_error__unregister(&perf_tui_eops);
}
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
new file mode 100644
index 0000000..092902e
--- /dev/null
+++ b/tools/perf/ui/tui/util.c
@@ -0,0 +1,243 @@
+#include "../../util/util.h"
+#include <signal.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/ttydefaults.h>
+
+#include "../../util/cache.h"
+#include "../../util/debug.h"
+#include "../browser.h"
+#include "../keysyms.h"
+#include "../helpline.h"
+#include "../ui.h"
+#include "../util.h"
+#include "../libslang.h"
+
+static void ui_browser__argv_write(struct ui_browser *browser,
+ void *entry, int row)
+{
+ char **arg = entry;
+ bool current_entry = ui_browser__is_current_entry(browser, row);
+
+ ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+ HE_COLORSET_NORMAL);
+ slsmg_write_nstring(*arg, browser->width);
+}
+
+static int popup_menu__run(struct ui_browser *menu)
+{
+ int key;
+
+ if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0)
+ return -1;
+
+ while (1) {
+ key = ui_browser__run(menu, 0);
+
+ switch (key) {
+ case K_RIGHT:
+ case K_ENTER:
+ key = menu->index;
+ break;
+ case K_LEFT:
+ case K_ESC:
+ case 'q':
+ case CTRL('c'):
+ key = -1;
+ break;
+ default:
+ continue;
+ }
+
+ break;
+ }
+
+ ui_browser__hide(menu);
+ return key;
+}
+
+int ui__popup_menu(int argc, char * const argv[])
+{
+ struct ui_browser menu = {
+ .entries = (void *)argv,
+ .refresh = ui_browser__argv_refresh,
+ .seek = ui_browser__argv_seek,
+ .write = ui_browser__argv_write,
+ .nr_entries = argc,
+ };
+
+ return popup_menu__run(&menu);
+}
+
+int ui_browser__input_window(const char *title, const char *text, char *input,
+ const char *exit_msg, int delay_secs)
+{
+ int x, y, len, key;
+ int max_len = 60, nr_lines = 0;
+ static char buf[50];
+ const char *t;
+
+ t = text;
+ while (1) {
+ const char *sep = strchr(t, '\n');
+
+ if (sep == NULL)
+ sep = strchr(t, '\0');
+ len = sep - t;
+ if (max_len < len)
+ max_len = len;
+ ++nr_lines;
+ if (*sep == '\0')
+ break;
+ t = sep + 1;
+ }
+
+ max_len += 2;
+ nr_lines += 8;
+ y = SLtt_Screen_Rows / 2 - nr_lines / 2;
+ x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+ SLsmg_set_color(0);
+ SLsmg_draw_box(y, x++, nr_lines, max_len);
+ if (title) {
+ SLsmg_gotorc(y, x + 1);
+ SLsmg_write_string((char *)title);
+ }
+ SLsmg_gotorc(++y, x);
+ nr_lines -= 7;
+ max_len -= 2;
+ SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+ nr_lines, max_len, 1);
+ y += nr_lines;
+ len = 5;
+ while (len--) {
+ SLsmg_gotorc(y + len - 1, x);
+ SLsmg_write_nstring((char *)" ", max_len);
+ }
+ SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
+
+ SLsmg_gotorc(y + 3, x);
+ SLsmg_write_nstring((char *)exit_msg, max_len);
+ SLsmg_refresh();
+
+ x += 2;
+ len = 0;
+ key = ui__getch(delay_secs);
+ while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+ if (key == K_BKSPC) {
+ if (len == 0)
+ goto next_key;
+ SLsmg_gotorc(y, x + --len);
+ SLsmg_write_char(' ');
+ } else {
+ buf[len] = key;
+ SLsmg_gotorc(y, x + len++);
+ SLsmg_write_char(key);
+ }
+ SLsmg_refresh();
+
+ /* XXX more graceful overflow handling needed */
+ if (len == sizeof(buf) - 1) {
+ ui_helpline__push("maximum size of symbol name reached!");
+ key = K_ENTER;
+ break;
+ }
+next_key:
+ key = ui__getch(delay_secs);
+ }
+
+ buf[len] = '\0';
+ strncpy(input, buf, len+1);
+ return key;
+}
+
+int ui__question_window(const char *title, const char *text,
+ const char *exit_msg, int delay_secs)
+{
+ int x, y;
+ int max_len = 0, nr_lines = 0;
+ const char *t;
+
+ t = text;
+ while (1) {
+ const char *sep = strchr(t, '\n');
+ int len;
+
+ if (sep == NULL)
+ sep = strchr(t, '\0');
+ len = sep - t;
+ if (max_len < len)
+ max_len = len;
+ ++nr_lines;
+ if (*sep == '\0')
+ break;
+ t = sep + 1;
+ }
+
+ max_len += 2;
+ nr_lines += 4;
+ y = SLtt_Screen_Rows / 2 - nr_lines / 2,
+ x = SLtt_Screen_Cols / 2 - max_len / 2;
+
+ SLsmg_set_color(0);
+ SLsmg_draw_box(y, x++, nr_lines, max_len);
+ if (title) {
+ SLsmg_gotorc(y, x + 1);
+ SLsmg_write_string((char *)title);
+ }
+ SLsmg_gotorc(++y, x);
+ nr_lines -= 2;
+ max_len -= 2;
+ SLsmg_write_wrapped_string((unsigned char *)text, y, x,
+ nr_lines, max_len, 1);
+ SLsmg_gotorc(y + nr_lines - 2, x);
+ SLsmg_write_nstring((char *)" ", max_len);
+ SLsmg_gotorc(y + nr_lines - 1, x);
+ SLsmg_write_nstring((char *)exit_msg, max_len);
+ SLsmg_refresh();
+ return ui__getch(delay_secs);
+}
+
+int ui__help_window(const char *text)
+{
+ return ui__question_window("Help", text, "Press any key...", 0);
+}
+
+int ui__dialog_yesno(const char *msg)
+{
+ return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0);
+}
+
+static int __ui__warning(const char *title, const char *format, va_list args)
+{
+ char *s;
+
+ if (vasprintf(&s, format, args) > 0) {
+ int key;
+
+ pthread_mutex_lock(&ui__lock);
+ key = ui__question_window(title, s, "Press any key...", 0);
+ pthread_mutex_unlock(&ui__lock);
+ free(s);
+ return key;
+ }
+
+ fprintf(stderr, "%s\n", title);
+ vfprintf(stderr, format, args);
+ return K_ESC;
+}
+
+static int perf_tui__error(const char *format, va_list args)
+{
+ return __ui__warning("Error:", format, args);
+}
+
+static int perf_tui__warning(const char *format, va_list args)
+{
+ return __ui__warning("Warning:", format, args);
+}
+
+struct perf_error_ops perf_tui_eops = {
+ .error = perf_tui__error,
+ .warning = perf_tui__warning,
+};
diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c
index ad4374a..4f98977 100644
--- a/tools/perf/ui/util.c
+++ b/tools/perf/ui/util.c
@@ -1,250 +1,85 @@
-#include "../util.h"
-#include <signal.h>
-#include <stdbool.h>
-#include <string.h>
-#include <sys/ttydefaults.h>
-
-#include "../cache.h"
-#include "../debug.h"
-#include "browser.h"
-#include "keysyms.h"
-#include "helpline.h"
-#include "ui.h"
#include "util.h"
-#include "libslang.h"
-
-static void ui_browser__argv_write(struct ui_browser *browser,
- void *entry, int row)
-{
- char **arg = entry;
- bool current_entry = ui_browser__is_current_entry(browser, row);
-
- ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
- HE_COLORSET_NORMAL);
- slsmg_write_nstring(*arg, browser->width);
-}
-
-static int popup_menu__run(struct ui_browser *menu)
-{
- int key;
-
- if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0)
- return -1;
+#include "../debug.h"
- while (1) {
- key = ui_browser__run(menu, 0);
-
- switch (key) {
- case K_RIGHT:
- case K_ENTER:
- key = menu->index;
- break;
- case K_LEFT:
- case K_ESC:
- case 'q':
- case CTRL('c'):
- key = -1;
- break;
- default:
- continue;
- }
-
- break;
- }
-
- ui_browser__hide(menu);
- return key;
-}
-int ui__popup_menu(int argc, char * const argv[])
+/*
+ * Default error logging functions
+ */
+static int perf_stdio__error(const char *format, va_list args)
{
- struct ui_browser menu = {
- .entries = (void *)argv,
- .refresh = ui_browser__argv_refresh,
- .seek = ui_browser__argv_seek,
- .write = ui_browser__argv_write,
- .nr_entries = argc,
- };
-
- return popup_menu__run(&menu);
+ fprintf(stderr, "Error:\n");
+ vfprintf(stderr, format, args);
+ return 0;
}
-int ui_browser__input_window(const char *title, const char *text, char *input,
- const char *exit_msg, int delay_secs)
+static int perf_stdio__warning(const char *format, va_list args)
{
- int x, y, len, key;
- int max_len = 60, nr_lines = 0;
- static char buf[50];
- const char *t;
-
- t = text;
- while (1) {
- const char *sep = strchr(t, '\n');
-
- if (sep == NULL)
- sep = strchr(t, '\0');
- len = sep - t;
- if (max_len < len)
- max_len = len;
- ++nr_lines;
- if (*sep == '\0')
- break;
- t = sep + 1;
- }
-
- max_len += 2;
- nr_lines += 8;
- y = SLtt_Screen_Rows / 2 - nr_lines / 2;
- x = SLtt_Screen_Cols / 2 - max_len / 2;
-
- SLsmg_set_color(0);
- SLsmg_draw_box(y, x++, nr_lines, max_len);
- if (title) {
- SLsmg_gotorc(y, x + 1);
- SLsmg_write_string((char *)title);
- }
- SLsmg_gotorc(++y, x);
- nr_lines -= 7;
- max_len -= 2;
- SLsmg_write_wrapped_string((unsigned char *)text, y, x,
- nr_lines, max_len, 1);
- y += nr_lines;
- len = 5;
- while (len--) {
- SLsmg_gotorc(y + len - 1, x);
- SLsmg_write_nstring((char *)" ", max_len);
- }
- SLsmg_draw_box(y++, x + 1, 3, max_len - 2);
-
- SLsmg_gotorc(y + 3, x);
- SLsmg_write_nstring((char *)exit_msg, max_len);
- SLsmg_refresh();
-
- x += 2;
- len = 0;
- key = ui__getch(delay_secs);
- while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
- if (key == K_BKSPC) {
- if (len == 0)
- goto next_key;
- SLsmg_gotorc(y, x + --len);
- SLsmg_write_char(' ');
- } else {
- buf[len] = key;
- SLsmg_gotorc(y, x + len++);
- SLsmg_write_char(key);
- }
- SLsmg_refresh();
-
- /* XXX more graceful overflow handling needed */
- if (len == sizeof(buf) - 1) {
- ui_helpline__push("maximum size of symbol name reached!");
- key = K_ENTER;
- break;
- }
-next_key:
- key = ui__getch(delay_secs);
- }
-
- buf[len] = '\0';
- strncpy(input, buf, len+1);
- return key;
+ fprintf(stderr, "Warning:\n");
+ vfprintf(stderr, format, args);
+ return 0;
}
-int ui__question_window(const char *title, const char *text,
- const char *exit_msg, int delay_secs)
+static struct perf_error_ops default_eops =
{
- int x, y;
- int max_len = 0, nr_lines = 0;
- const char *t;
-
- t = text;
- while (1) {
- const char *sep = strchr(t, '\n');
- int len;
-
- if (sep == NULL)
- sep = strchr(t, '\0');
- len = sep - t;
- if (max_len < len)
- max_len = len;
- ++nr_lines;
- if (*sep == '\0')
- break;
- t = sep + 1;
- }
-
- max_len += 2;
- nr_lines += 4;
- y = SLtt_Screen_Rows / 2 - nr_lines / 2,
- x = SLtt_Screen_Cols / 2 - max_len / 2;
-
- SLsmg_set_color(0);
- SLsmg_draw_box(y, x++, nr_lines, max_len);
- if (title) {
- SLsmg_gotorc(y, x + 1);
- SLsmg_write_string((char *)title);
- }
- SLsmg_gotorc(++y, x);
- nr_lines -= 2;
- max_len -= 2;
- SLsmg_write_wrapped_string((unsigned char *)text, y, x,
- nr_lines, max_len, 1);
- SLsmg_gotorc(y + nr_lines - 2, x);
- SLsmg_write_nstring((char *)" ", max_len);
- SLsmg_gotorc(y + nr_lines - 1, x);
- SLsmg_write_nstring((char *)exit_msg, max_len);
- SLsmg_refresh();
- return ui__getch(delay_secs);
-}
+ .error = perf_stdio__error,
+ .warning = perf_stdio__warning,
+};
-int ui__help_window(const char *text)
-{
- return ui__question_window("Help", text, "Press any key...", 0);
-}
+static struct perf_error_ops *perf_eops = &default_eops;
-int ui__dialog_yesno(const char *msg)
-{
- return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0);
-}
-int __ui__warning(const char *title, const char *format, va_list args)
+int ui__error(const char *format, ...)
{
- char *s;
-
- if (use_browser > 0 && vasprintf(&s, format, args) > 0) {
- int key;
+ int ret;
+ va_list args;
- pthread_mutex_lock(&ui__lock);
- key = ui__question_window(title, s, "Press any key...", 0);
- pthread_mutex_unlock(&ui__lock);
- free(s);
- return key;
- }
+ va_start(args, format);
+ ret = perf_eops->error(format, args);
+ va_end(args);
- fprintf(stderr, "%s:\n", title);
- vfprintf(stderr, format, args);
- return K_ESC;
+ return ret;
}
int ui__warning(const char *format, ...)
{
- int key;
+ int ret;
va_list args;
va_start(args, format);
- key = __ui__warning("Warning", format, args);
+ ret = perf_eops->warning(format, args);
va_end(args);
- return key;
+
+ return ret;
}
-int ui__error(const char *format, ...)
+
+/**
+ * perf_error__register - Register error logging functions
+ * @eops: The pointer to error logging function struct
+ *
+ * Register UI-specific error logging functions. Before calling this,
+ * other logging functions should be unregistered, if any.
+ */
+int perf_error__register(struct perf_error_ops *eops)
{
- int key;
- va_list args;
+ if (perf_eops != &default_eops)
+ return -1;
- va_start(args, format);
- key = __ui__warning("Error", format, args);
- va_end(args);
- return key;
+ perf_eops = eops;
+ return 0;
+}
+
+/**
+ * perf_error__unregister - Unregister error logging functions
+ * @eops: The pointer to error logging function struct
+ *
+ * Unregister already registered error logging functions.
+ */
+int perf_error__unregister(struct perf_error_ops *eops)
+{
+ if (perf_eops != eops)
+ return -1;
+
+ perf_eops = &default_eops;
+ return 0;
}
diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h
index 2d1738b..361f08c 100644
--- a/tools/perf/ui/util.h
+++ b/tools/perf/ui/util.h
@@ -9,6 +9,13 @@ int ui__help_window(const char *text);
int ui__dialog_yesno(const char *msg);
int ui__question_window(const char *title, const char *text,
const char *exit_msg, int delay_secs);
-int __ui__warning(const char *title, const char *format, va_list args);
+
+struct perf_error_ops {
+ int (*error)(const char *format, va_list args);
+ int (*warning)(const char *format, va_list args);
+};
+
+int perf_error__register(struct perf_error_ops *eops);
+int perf_error__unregister(struct perf_error_ops *eops);
#endif /* _PERF_UI_UTIL_H_ */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index efb1fce..4dfe0bb 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -47,7 +47,7 @@ int dump_printf(const char *fmt, ...)
return ret;
}
-#ifdef NO_NEWT_SUPPORT
+#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT)
int ui__warning(const char *format, ...)
{
va_list args;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 6bebe7f..015c91d 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -12,8 +12,9 @@ int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
void trace_event(union perf_event *event);
struct ui_progress;
+struct perf_error_ops;
-#ifdef NO_NEWT_SUPPORT
+#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT)
static inline int ui_helpline__show_help(const char *format __used, va_list ap __used)
{
return 0;
@@ -23,12 +24,28 @@ static inline void ui_progress__update(u64 curr __used, u64 total __used,
const char *title __used) {}
#define ui__error(format, arg...) ui__warning(format, ##arg)
-#else
+
+static inline int
+perf_error__register(struct perf_error_ops *eops __used)
+{
+ return 0;
+}
+
+static inline int
+perf_error__unregister(struct perf_error_ops *eops __used)
+{
+ return 0;
+}
+
+#else /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */
+
extern char ui_helpline__last_msg[];
int ui_helpline__show_help(const char *format, va_list ap);
#include "../ui/progress.h"
int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
-#endif
+#include "../ui/util.h"
+
+#endif /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */
int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
int ui__error_paranoid(void);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7400fb3..f74e956 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -224,8 +224,8 @@ out_free_attrs:
return err;
}
-static struct perf_evsel *
- perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
{
struct perf_evsel *evsel;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 989bee9..40d4d3c 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -73,6 +73,9 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \
perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
+
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
int cpu, int thread, u64 id);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9f6cebd..e817713 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,7 +15,7 @@
#include "cpumap.h"
#include "thread_map.h"
#include "target.h"
-#include "../../include/linux/perf_event.h"
+#include "../../../include/linux/hw_breakpoint.h"
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
#define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
@@ -78,7 +78,7 @@ static const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
"ref-cycles",
};
-const char *__perf_evsel__hw_name(u64 config)
+static const char *__perf_evsel__hw_name(u64 config)
{
if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
return perf_evsel__hw_names[config];
@@ -86,16 +86,15 @@ const char *__perf_evsel__hw_name(u64 config)
return "unknown-hardware";
}
-static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size)
{
- int colon = 0;
+ int colon = 0, r = 0;
struct perf_event_attr *attr = &evsel->attr;
- int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(attr->config));
bool exclude_guest_default = false;
#define MOD_PRINT(context, mod) do { \
if (!attr->exclude_##context) { \
- if (!colon) colon = r++; \
+ if (!colon) colon = ++r; \
r += scnprintf(bf + r, size - r, "%c", mod); \
} } while(0)
@@ -108,7 +107,7 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
if (attr->precise_ip) {
if (!colon)
- colon = r++;
+ colon = ++r;
r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
exclude_guest_default = true;
}
@@ -119,39 +118,211 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
}
#undef MOD_PRINT
if (colon)
- bf[colon] = ':';
+ bf[colon - 1] = ':';
return r;
}
-int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+ int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config));
+ return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+static const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
+ "cpu-clock",
+ "task-clock",
+ "page-faults",
+ "context-switches",
+ "CPU-migrations",
+ "minor-faults",
+ "major-faults",
+ "alignment-faults",
+ "emulation-faults",
+};
+
+static const char *__perf_evsel__sw_name(u64 config)
{
- int ret;
+ if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
+ return perf_evsel__sw_names[config];
+ return "unknown-software";
+}
+
+static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+ int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config));
+ return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
+{
+ int r;
+
+ r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr);
+
+ if (type & HW_BREAKPOINT_R)
+ r += scnprintf(bf + r, size - r, "r");
+
+ if (type & HW_BREAKPOINT_W)
+ r += scnprintf(bf + r, size - r, "w");
+
+ if (type & HW_BREAKPOINT_X)
+ r += scnprintf(bf + r, size - r, "x");
+
+ return r;
+}
+
+static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+ struct perf_event_attr *attr = &evsel->attr;
+ int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
+ return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+}
+
+const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_EVSEL__MAX_ALIASES] = {
+ { "L1-dcache", "l1-d", "l1d", "L1-data", },
+ { "L1-icache", "l1-i", "l1i", "L1-instruction", },
+ { "LLC", "L2", },
+ { "dTLB", "d-tlb", "Data-TLB", },
+ { "iTLB", "i-tlb", "Instruction-TLB", },
+ { "branch", "branches", "bpu", "btb", "bpc", },
+ { "node", },
+};
+
+const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_EVSEL__MAX_ALIASES] = {
+ { "load", "loads", "read", },
+ { "store", "stores", "write", },
+ { "prefetch", "prefetches", "speculative-read", "speculative-load", },
+};
+
+const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
+ [PERF_EVSEL__MAX_ALIASES] = {
+ { "refs", "Reference", "ops", "access", },
+ { "misses", "miss", },
+};
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+#define CACHE_READ (1 << C(OP_READ))
+#define CACHE_WRITE (1 << C(OP_WRITE))
+#define CACHE_PREFETCH (1 << C(OP_PREFETCH))
+#define COP(x) (1 << x)
+
+/*
+ * cache operartion stat
+ * L1I : Read and prefetch only
+ * ITLB and BPU : Read-only
+ */
+static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
+ [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(L1I)] = (CACHE_READ | CACHE_PREFETCH),
+ [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+ [C(ITLB)] = (CACHE_READ),
+ [C(BPU)] = (CACHE_READ),
+ [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
+};
+
+bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
+{
+ if (perf_evsel__hw_cache_stat[type] & COP(op))
+ return true; /* valid */
+ else
+ return false; /* invalid */
+}
+
+int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
+ char *bf, size_t size)
+{
+ if (result) {
+ return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
+ perf_evsel__hw_cache_op[op][0],
+ perf_evsel__hw_cache_result[result][0]);
+ }
+
+ return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0],
+ perf_evsel__hw_cache_op[op][1]);
+}
+
+static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
+{
+ u8 op, result, type = (config >> 0) & 0xff;
+ const char *err = "unknown-ext-hardware-cache-type";
+
+ if (type > PERF_COUNT_HW_CACHE_MAX)
+ goto out_err;
+
+ op = (config >> 8) & 0xff;
+ err = "unknown-ext-hardware-cache-op";
+ if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+ goto out_err;
+
+ result = (config >> 16) & 0xff;
+ err = "unknown-ext-hardware-cache-result";
+ if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+ goto out_err;
+
+ err = "invalid-cache";
+ if (!perf_evsel__is_cache_op_valid(type, op))
+ goto out_err;
+
+ return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
+out_err:
+ return scnprintf(bf, size, "%s", err);
+}
+
+static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+ int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size);
+ return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+}
+
+static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
+{
+ int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
+ return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+}
+
+const char *perf_evsel__name(struct perf_evsel *evsel)
+{
+ char bf[128];
+
+ if (evsel->name)
+ return evsel->name;
switch (evsel->attr.type) {
case PERF_TYPE_RAW:
- ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
+ perf_evsel__raw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_HARDWARE:
- ret = perf_evsel__hw_name(evsel, bf, size);
+ perf_evsel__hw_name(evsel, bf, sizeof(bf));
+ break;
+
+ case PERF_TYPE_HW_CACHE:
+ perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
+ break;
+
+ case PERF_TYPE_SOFTWARE:
+ perf_evsel__sw_name(evsel, bf, sizeof(bf));
break;
+
+ case PERF_TYPE_TRACEPOINT:
+ scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
+ break;
+
+ case PERF_TYPE_BREAKPOINT:
+ perf_evsel__bp_name(evsel, bf, sizeof(bf));
+ break;
+
default:
- /*
- * FIXME
- *
- * This is the minimal perf_evsel__name so that we can
- * reconstruct event names taking into account event modifiers.
- *
- * The old event_name uses it now for raw anr hw events, so that
- * we don't drag all the parsing stuff into the python binding.
- *
- * On the next devel cycle the rest of the event naming will be
- * brought here.
- */
- return 0;
- }
-
- return ret;
+ scnprintf(bf, sizeof(bf), "%s", "unknown attr type");
+ break;
+ }
+
+ evsel->name = strdup(bf);
+
+ return evsel->name ?: "unknown";
}
void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4ba8b56..67cc503 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -83,8 +83,19 @@ void perf_evsel__config(struct perf_evsel *evsel,
struct perf_record_opts *opts,
struct perf_evsel *first);
-const char* __perf_evsel__hw_name(u64 config);
-int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size);
+bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
+
+#define PERF_EVSEL__MAX_ALIASES 8
+
+extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_EVSEL__MAX_ALIASES];
+extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_EVSEL__MAX_ALIASES];
+const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
+ [PERF_EVSEL__MAX_ALIASES];
+int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
+ char *bf, size_t size);
+const char *perf_evsel__name(struct perf_evsel *evsel);
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e909d43..5a47aba 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -641,7 +641,7 @@ static int write_event_desc(int fd, struct perf_header *h __used,
/*
* write event string as passed on cmdline
*/
- ret = do_write_string(fd, event_name(attr));
+ ret = do_write_string(fd, perf_evsel__name(attr));
if (ret < 0)
return ret;
/*
@@ -1474,15 +1474,15 @@ out:
static int process_tracing_data(struct perf_file_section *section __unused,
struct perf_header *ph __unused,
- int feat __unused, int fd)
+ int feat __unused, int fd, void *data)
{
- trace_report(fd, false);
+ trace_report(fd, data, false);
return 0;
}
static int process_build_id(struct perf_file_section *section,
struct perf_header *ph,
- int feat __unused, int fd)
+ int feat __unused, int fd, void *data __used)
{
if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
pr_debug("Failed to read buildids, continuing...\n");
@@ -1493,7 +1493,7 @@ struct feature_ops {
int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
void (*print)(struct perf_header *h, int fd, FILE *fp);
int (*process)(struct perf_file_section *section,
- struct perf_header *h, int feat, int fd);
+ struct perf_header *h, int feat, int fd, void *data);
const char *name;
bool full_only;
};
@@ -1988,7 +1988,7 @@ int perf_file_header__read(struct perf_file_header *header,
static int perf_file_section__process(struct perf_file_section *section,
struct perf_header *ph,
- int feat, int fd, void *data __used)
+ int feat, int fd, void *data)
{
if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
@@ -2004,7 +2004,7 @@ static int perf_file_section__process(struct perf_file_section *section,
if (!feat_ops[feat].process)
return 0;
- return feat_ops[feat].process(section, ph, feat, fd);
+ return feat_ops[feat].process(section, ph, feat, fd, data);
}
static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
@@ -2093,9 +2093,11 @@ static int read_attr(int fd, struct perf_header *ph,
return ret <= 0 ? -1 : 0;
}
-static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
+static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel,
+ struct pevent *pevent)
{
- struct event_format *event = trace_find_event(evsel->attr.config);
+ struct event_format *event = pevent_find_event(pevent,
+ evsel->attr.config);
char bf[128];
if (event == NULL)
@@ -2109,13 +2111,14 @@ static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
return 0;
}
-static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist)
+static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist,
+ struct pevent *pevent)
{
struct perf_evsel *pos;
list_for_each_entry(pos, &evlist->entries, node) {
if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
- perf_evsel__set_tracepoint_name(pos))
+ perf_evsel__set_tracepoint_name(pos, pevent))
return -1;
}
@@ -2198,12 +2201,12 @@ int perf_session__read_header(struct perf_session *session, int fd)
event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type);
}
- perf_header__process_sections(header, fd, NULL,
+ perf_header__process_sections(header, fd, &session->pevent,
perf_file_section__process);
lseek(fd, header->data_offset, SEEK_SET);
- if (perf_evlist__set_tracepoint_names(session->evlist))
+ if (perf_evlist__set_tracepoint_names(session->evlist, session->pevent))
goto out_delete_evlist;
header->frozen = 1;
@@ -2419,8 +2422,8 @@ int perf_event__process_tracing_data(union perf_event *event,
lseek(session->fd, offset + sizeof(struct tracing_data_event),
SEEK_SET);
- size_read = trace_report(session->fd, session->repipe);
-
+ size_read = trace_report(session->fd, &session->pevent,
+ session->repipe);
padding = ALIGN(size_read, sizeof(u64)) - size_read;
if (read(session->fd, buf, padding) < 0)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 34bb556..0b096c2 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -47,6 +47,7 @@ enum hist_column {
HISTC_SYMBOL_TO,
HISTC_DSO_FROM,
HISTC_DSO_TO,
+ HISTC_SRCLINE,
HISTC_NR_COLS, /* Last entry */
};
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 1eb804f..b6842c1 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -108,4 +108,14 @@ int eprintf(int level,
#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
#endif
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 81371ba..c14c665 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -157,7 +157,7 @@ void machine__exit(struct machine *self);
void machine__delete(struct machine *self);
int machine__resolve_callchain(struct machine *machine,
- struct perf_evsel *evsel, struct thread *thread,
+ struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent);
int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index 76b98e2..1b997d2 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -181,6 +181,22 @@ static int test__checkevent_breakpoint_w(struct perf_evlist *evlist)
return 0;
}
+static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+ TEST_ASSERT_VAL("wrong type",
+ PERF_TYPE_BREAKPOINT == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong bp_type",
+ (HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type);
+ TEST_ASSERT_VAL("wrong bp_len",
+ HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len);
+ return 0;
+}
+
static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = list_entry(evlist->entries.next,
@@ -309,6 +325,8 @@ static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong name",
+ !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:u"));
return test__checkevent_breakpoint(evlist);
}
@@ -322,6 +340,8 @@ static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong name",
+ !strcmp(perf_evsel__name(evsel), "mem:0x0:x:k"));
return test__checkevent_breakpoint_x(evlist);
}
@@ -335,6 +355,8 @@ static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong name",
+ !strcmp(perf_evsel__name(evsel), "mem:0x0:r:hp"));
return test__checkevent_breakpoint_r(evlist);
}
@@ -348,10 +370,27 @@ static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong name",
+ !strcmp(perf_evsel__name(evsel), "mem:0x0:w:up"));
return test__checkevent_breakpoint_w(evlist);
}
+static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong name",
+ !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:kp"));
+
+ return test__checkevent_breakpoint_rw(evlist);
+}
+
static int test__checkevent_pmu(struct perf_evlist *evlist)
{
@@ -413,19 +452,63 @@ static int test__checkevent_pmu_name(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
- /* cpu/config=1,name=krava1/u */
+ /* cpu/config=1,name=krava/u */
evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
- TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "krava"));
+ TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava"));
- /* cpu/config=2/" */
+ /* cpu/config=2/u" */
evsel = list_entry(evsel->node.next, struct perf_evsel, node);
TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
TEST_ASSERT_VAL("wrong config", 2 == evsel->attr.config);
- TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "raw 0x2"));
+ TEST_ASSERT_VAL("wrong name",
+ !strcmp(perf_evsel__name(evsel), "raw 0x2:u"));
+
+ return 0;
+}
+
+static int test__checkterms_simple(struct list_head *terms)
+{
+ struct parse_events__term *term;
+
+ /* config=10 */
+ term = list_entry(terms->next, struct parse_events__term, list);
+ TEST_ASSERT_VAL("wrong type term",
+ term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG);
+ TEST_ASSERT_VAL("wrong type val",
+ term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+ TEST_ASSERT_VAL("wrong val", term->val.num == 10);
+ TEST_ASSERT_VAL("wrong config", !term->config);
+
+ /* config1 */
+ term = list_entry(term->list.next, struct parse_events__term, list);
+ TEST_ASSERT_VAL("wrong type term",
+ term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1);
+ TEST_ASSERT_VAL("wrong type val",
+ term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+ TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+ TEST_ASSERT_VAL("wrong config", !term->config);
+
+ /* config2=3 */
+ term = list_entry(term->list.next, struct parse_events__term, list);
+ TEST_ASSERT_VAL("wrong type term",
+ term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2);
+ TEST_ASSERT_VAL("wrong type val",
+ term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+ TEST_ASSERT_VAL("wrong val", term->val.num == 3);
+ TEST_ASSERT_VAL("wrong config", !term->config);
+
+ /* umask=1*/
+ term = list_entry(term->list.next, struct parse_events__term, list);
+ TEST_ASSERT_VAL("wrong type term",
+ term->type_term == PARSE_EVENTS__TERM_TYPE_USER);
+ TEST_ASSERT_VAL("wrong type val",
+ term->type_val == PARSE_EVENTS__TERM_TYPE_NUM);
+ TEST_ASSERT_VAL("wrong val", term->val.num == 1);
+ TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "umask"));
return 0;
}
@@ -541,10 +624,16 @@ static struct test__event_st test__events[] = {
.name = "instructions:H",
.check = test__checkevent_exclude_guest_modifier,
},
+ [26] = {
+ .name = "mem:0:rw",
+ .check = test__checkevent_breakpoint_rw,
+ },
+ [27] = {
+ .name = "mem:0:rw:kp",
+ .check = test__checkevent_breakpoint_rw_modifier,
+ },
};
-#define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
-
static struct test__event_st test__events_pmu[] = {
[0] = {
.name = "cpu/config=10,config1,config2=3,period=1000/u",
@@ -556,10 +645,23 @@ static struct test__event_st test__events_pmu[] = {
},
};
-#define TEST__EVENTS_PMU_CNT (sizeof(test__events_pmu) / \
- sizeof(struct test__event_st))
+struct test__term {
+ const char *str;
+ __u32 type;
+ int (*check)(struct list_head *terms);
+};
+
+static struct test__term test__terms[] = {
+ [0] = {
+ .str = "config=10,config1,config2=3,umask=1",
+ .check = test__checkterms_simple,
+ },
+};
+
+#define TEST__TERMS_CNT (sizeof(test__terms) / \
+ sizeof(struct test__term))
-static int test(struct test__event_st *e)
+static int test_event(struct test__event_st *e)
{
struct perf_evlist *evlist;
int ret;
@@ -590,7 +692,48 @@ static int test_events(struct test__event_st *events, unsigned cnt)
struct test__event_st *e = &events[i];
pr_debug("running test %d '%s'\n", i, e->name);
- ret = test(e);
+ ret = test_event(e);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+static int test_term(struct test__term *t)
+{
+ struct list_head *terms;
+ int ret;
+
+ terms = malloc(sizeof(*terms));
+ if (!terms)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(terms);
+
+ ret = parse_events_terms(terms, t->str);
+ if (ret) {
+ pr_debug("failed to parse terms '%s', err %d\n",
+ t->str , ret);
+ return ret;
+ }
+
+ ret = t->check(terms);
+ parse_events__free_terms(terms);
+
+ return ret;
+}
+
+static int test_terms(struct test__term *terms, unsigned cnt)
+{
+ int ret = 0;
+ unsigned i;
+
+ for (i = 0; i < cnt; i++) {
+ struct test__term *t = &terms[i];
+
+ pr_debug("running test %d '%s'\n", i, t->str);
+ ret = test_term(t);
if (ret)
break;
}
@@ -617,9 +760,17 @@ int parse_events__test(void)
{
int ret;
- ret = test_events(test__events, TEST__EVENTS_CNT);
- if (!ret && test_pmu())
- ret = test_events(test__events_pmu, TEST__EVENTS_PMU_CNT);
+#define TEST_EVENTS(tests) \
+do { \
+ ret = test_events(tests, ARRAY_SIZE(tests)); \
+ if (ret) \
+ return ret; \
+} while (0)
- return ret;
+ TEST_EVENTS(test__events);
+
+ if (test_pmu())
+ TEST_EVENTS(test__events_pmu);
+
+ return test_terms(test__terms, ARRAY_SIZE(test__terms));
}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 05dbc8b..1aa721d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -11,14 +11,14 @@
#include "cache.h"
#include "header.h"
#include "debugfs.h"
+#include "parse-events-bison.h"
+#define YY_EXTRA_TYPE int
#include "parse-events-flex.h"
#include "pmu.h"
#define MAX_NAME_LEN 100
struct event_symbol {
- u8 type;
- u64 config;
const char *symbol;
const char *alias;
};
@@ -26,32 +26,88 @@ struct event_symbol {
#ifdef PARSER_DEBUG
extern int parse_events_debug;
#endif
-int parse_events_parse(struct list_head *list, int *idx);
-
-#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
-#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
-
-static struct event_symbol event_symbols[] = {
- { CHW(CPU_CYCLES), "cpu-cycles", "cycles" },
- { CHW(STALLED_CYCLES_FRONTEND), "stalled-cycles-frontend", "idle-cycles-frontend" },
- { CHW(STALLED_CYCLES_BACKEND), "stalled-cycles-backend", "idle-cycles-backend" },
- { CHW(INSTRUCTIONS), "instructions", "" },
- { CHW(CACHE_REFERENCES), "cache-references", "" },
- { CHW(CACHE_MISSES), "cache-misses", "" },
- { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" },
- { CHW(BRANCH_MISSES), "branch-misses", "" },
- { CHW(BUS_CYCLES), "bus-cycles", "" },
- { CHW(REF_CPU_CYCLES), "ref-cycles", "" },
-
- { CSW(CPU_CLOCK), "cpu-clock", "" },
- { CSW(TASK_CLOCK), "task-clock", "" },
- { CSW(PAGE_FAULTS), "page-faults", "faults" },
- { CSW(PAGE_FAULTS_MIN), "minor-faults", "" },
- { CSW(PAGE_FAULTS_MAJ), "major-faults", "" },
- { CSW(CONTEXT_SWITCHES), "context-switches", "cs" },
- { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" },
- { CSW(ALIGNMENT_FAULTS), "alignment-faults", "" },
- { CSW(EMULATION_FAULTS), "emulation-faults", "" },
+int parse_events_parse(void *data, void *scanner);
+
+static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = {
+ .symbol = "cpu-cycles",
+ .alias = "cycles",
+ },
+ [PERF_COUNT_HW_INSTRUCTIONS] = {
+ .symbol = "instructions",
+ .alias = "",
+ },
+ [PERF_COUNT_HW_CACHE_REFERENCES] = {
+ .symbol = "cache-references",
+ .alias = "",
+ },
+ [PERF_COUNT_HW_CACHE_MISSES] = {
+ .symbol = "cache-misses",
+ .alias = "",
+ },
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = {
+ .symbol = "branch-instructions",
+ .alias = "branches",
+ },
+ [PERF_COUNT_HW_BRANCH_MISSES] = {
+ .symbol = "branch-misses",
+ .alias = "",
+ },
+ [PERF_COUNT_HW_BUS_CYCLES] = {
+ .symbol = "bus-cycles",
+ .alias = "",
+ },
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = {
+ .symbol = "stalled-cycles-frontend",
+ .alias = "idle-cycles-frontend",
+ },
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = {
+ .symbol = "stalled-cycles-backend",
+ .alias = "idle-cycles-backend",
+ },
+ [PERF_COUNT_HW_REF_CPU_CYCLES] = {
+ .symbol = "ref-cycles",
+ .alias = "",
+ },
+};
+
+static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
+ [PERF_COUNT_SW_CPU_CLOCK] = {
+ .symbol = "cpu-clock",
+ .alias = "",
+ },
+ [PERF_COUNT_SW_TASK_CLOCK] = {
+ .symbol = "task-clock",
+ .alias = "",
+ },
+ [PERF_COUNT_SW_PAGE_FAULTS] = {
+ .symbol = "page-faults",
+ .alias = "faults",
+ },
+ [PERF_COUNT_SW_CONTEXT_SWITCHES] = {
+ .symbol = "context-switches",
+ .alias = "cs",
+ },
+ [PERF_COUNT_SW_CPU_MIGRATIONS] = {
+ .symbol = "cpu-migrations",
+ .alias = "migrations",
+ },
+ [PERF_COUNT_SW_PAGE_FAULTS_MIN] = {
+ .symbol = "minor-faults",
+ .alias = "",
+ },
+ [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = {
+ .symbol = "major-faults",
+ .alias = "",
+ },
+ [PERF_COUNT_SW_ALIGNMENT_FAULTS] = {
+ .symbol = "alignment-faults",
+ .alias = "",
+ },
+ [PERF_COUNT_SW_EMULATION_FAULTS] = {
+ .symbol = "emulation-faults",
+ .alias = "",
+ },
};
#define __PERF_EVENT_FIELD(config, name) \
@@ -62,63 +118,6 @@ static struct event_symbol event_symbols[] = {
#define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE)
#define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT)
-static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
- "cpu-clock",
- "task-clock",
- "page-faults",
- "context-switches",
- "CPU-migrations",
- "minor-faults",
- "major-faults",
- "alignment-faults",
- "emulation-faults",
-};
-
-#define MAX_ALIASES 8
-
-static const char *hw_cache[PERF_COUNT_HW_CACHE_MAX][MAX_ALIASES] = {
- { "L1-dcache", "l1-d", "l1d", "L1-data", },
- { "L1-icache", "l1-i", "l1i", "L1-instruction", },
- { "LLC", "L2", },
- { "dTLB", "d-tlb", "Data-TLB", },
- { "iTLB", "i-tlb", "Instruction-TLB", },
- { "branch", "branches", "bpu", "btb", "bpc", },
- { "node", },
-};
-
-static const char *hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][MAX_ALIASES] = {
- { "load", "loads", "read", },
- { "store", "stores", "write", },
- { "prefetch", "prefetches", "speculative-read", "speculative-load", },
-};
-
-static const char *hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
- [MAX_ALIASES] = {
- { "refs", "Reference", "ops", "access", },
- { "misses", "miss", },
-};
-
-#define C(x) PERF_COUNT_HW_CACHE_##x
-#define CACHE_READ (1 << C(OP_READ))
-#define CACHE_WRITE (1 << C(OP_WRITE))
-#define CACHE_PREFETCH (1 << C(OP_PREFETCH))
-#define COP(x) (1 << x)
-
-/*
- * cache operartion stat
- * L1I : Read and prefetch only
- * ITLB and BPU : Read-only
- */
-static unsigned long hw_cache_stat[C(MAX)] = {
- [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(L1I)] = (CACHE_READ | CACHE_PREFETCH),
- [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
- [C(ITLB)] = (CACHE_READ),
- [C(BPU)] = (CACHE_READ),
- [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
-};
-
#define for_each_subsystem(sys_dir, sys_dirent, sys_next) \
while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next) \
if (sys_dirent.d_type == DT_DIR && \
@@ -218,48 +217,6 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
return NULL;
}
-#define TP_PATH_LEN (MAX_EVENT_LENGTH * 2 + 1)
-static const char *tracepoint_id_to_name(u64 config)
-{
- static char buf[TP_PATH_LEN];
- struct tracepoint_path *path;
-
- path = tracepoint_id_to_path(config);
- if (path) {
- snprintf(buf, TP_PATH_LEN, "%s:%s", path->system, path->name);
- free(path->name);
- free(path->system);
- free(path);
- } else
- snprintf(buf, TP_PATH_LEN, "%s:%s", "unknown", "unknown");
-
- return buf;
-}
-
-static int is_cache_op_valid(u8 cache_type, u8 cache_op)
-{
- if (hw_cache_stat[cache_type] & COP(cache_op))
- return 1; /* valid */
- else
- return 0; /* invalid */
-}
-
-static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
-{
- static char name[50];
-
- if (cache_result) {
- sprintf(name, "%s-%s-%s", hw_cache[cache_type][0],
- hw_cache_op[cache_op][0],
- hw_cache_result[cache_result][0]);
- } else {
- sprintf(name, "%s-%s", hw_cache[cache_type][0],
- hw_cache_op[cache_op][1]);
- }
-
- return name;
-}
-
const char *event_type(int type)
{
switch (type) {
@@ -282,76 +239,6 @@ const char *event_type(int type)
return "unknown";
}
-const char *event_name(struct perf_evsel *evsel)
-{
- u64 config = evsel->attr.config;
- int type = evsel->attr.type;
-
- if (type == PERF_TYPE_RAW || type == PERF_TYPE_HARDWARE) {
- /*
- * XXX minimal fix, see comment on perf_evsen__name, this static buffer
- * will go away together with event_name in the next devel cycle.
- */
- static char bf[128];
- perf_evsel__name(evsel, bf, sizeof(bf));
- return bf;
- }
-
- if (evsel->name)
- return evsel->name;
-
- return __event_name(type, config);
-}
-
-const char *__event_name(int type, u64 config)
-{
- static char buf[32];
-
- if (type == PERF_TYPE_RAW) {
- sprintf(buf, "raw 0x%" PRIx64, config);
- return buf;
- }
-
- switch (type) {
- case PERF_TYPE_HARDWARE:
- return __perf_evsel__hw_name(config);
-
- case PERF_TYPE_HW_CACHE: {
- u8 cache_type, cache_op, cache_result;
-
- cache_type = (config >> 0) & 0xff;
- if (cache_type > PERF_COUNT_HW_CACHE_MAX)
- return "unknown-ext-hardware-cache-type";
-
- cache_op = (config >> 8) & 0xff;
- if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX)
- return "unknown-ext-hardware-cache-op";
-
- cache_result = (config >> 16) & 0xff;
- if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX)
- return "unknown-ext-hardware-cache-result";
-
- if (!is_cache_op_valid(cache_type, cache_op))
- return "invalid-cache";
-
- return event_cache_name(cache_type, cache_op, cache_result);
- }
-
- case PERF_TYPE_SOFTWARE:
- if (config < PERF_COUNT_SW_MAX && sw_event_names[config])
- return sw_event_names[config];
- return "unknown-software";
-
- case PERF_TYPE_TRACEPOINT:
- return tracepoint_id_to_name(config);
-
- default:
- break;
- }
-
- return "unknown";
-}
-
static int add_event(struct list_head **_list, int *idx,
struct perf_event_attr *attr, char *name)
{
@@ -373,19 +260,20 @@ static int add_event(struct list_head **_list, int *idx,
return -ENOMEM;
}
- evsel->name = strdup(name);
+ if (name)
+ evsel->name = strdup(name);
list_add_tail(&evsel->node, list);
*_list = list;
return 0;
}
-static int parse_aliases(char *str, const char *names[][MAX_ALIASES], int size)
+static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
{
int i, j;
int n, longest = -1;
for (i = 0; i < size; i++) {
- for (j = 0; j < MAX_ALIASES && names[i][j]; j++) {
+ for (j = 0; j < PERF_EVSEL__MAX_ALIASES && names[i][j]; j++) {
n = strlen(names[i][j]);
if (n > longest && !strncasecmp(str, names[i][j], n))
longest = n;
@@ -410,7 +298,7 @@ int parse_events_add_cache(struct list_head **list, int *idx,
* No fallback - if we cannot get a clear cache type
* then bail out:
*/
- cache_type = parse_aliases(type, hw_cache,
+ cache_type = parse_aliases(type, perf_evsel__hw_cache,
PERF_COUNT_HW_CACHE_MAX);
if (cache_type == -1)
return -EINVAL;
@@ -423,18 +311,18 @@ int parse_events_add_cache(struct list_head **list, int *idx,
snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str);
if (cache_op == -1) {
- cache_op = parse_aliases(str, hw_cache_op,
+ cache_op = parse_aliases(str, perf_evsel__hw_cache_op,
PERF_COUNT_HW_CACHE_OP_MAX);
if (cache_op >= 0) {
- if (!is_cache_op_valid(cache_type, cache_op))
+ if (!perf_evsel__is_cache_op_valid(cache_type, cache_op))
return -EINVAL;
continue;
}
}
if (cache_result == -1) {
- cache_result = parse_aliases(str, hw_cache_result,
- PERF_COUNT_HW_CACHE_RESULT_MAX);
+ cache_result = parse_aliases(str, perf_evsel__hw_cache_result,
+ PERF_COUNT_HW_CACHE_RESULT_MAX);
if (cache_result >= 0)
continue;
}
@@ -549,21 +437,31 @@ parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
if (!type || !type[i])
break;
+#define CHECK_SET_TYPE(bit) \
+do { \
+ if (attr->bp_type & bit) \
+ return -EINVAL; \
+ else \
+ attr->bp_type |= bit; \
+} while (0)
+
switch (type[i]) {
case 'r':
- attr->bp_type |= HW_BREAKPOINT_R;
+ CHECK_SET_TYPE(HW_BREAKPOINT_R);
break;
case 'w':
- attr->bp_type |= HW_BREAKPOINT_W;
+ CHECK_SET_TYPE(HW_BREAKPOINT_W);
break;
case 'x':
- attr->bp_type |= HW_BREAKPOINT_X;
+ CHECK_SET_TYPE(HW_BREAKPOINT_X);
break;
default:
return -EINVAL;
}
}
+#undef CHECK_SET_TYPE
+
if (!attr->bp_type) /* Default */
attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W;
@@ -574,7 +472,6 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
void *ptr, char *type)
{
struct perf_event_attr attr;
- char name[MAX_NAME_LEN];
memset(&attr, 0, sizeof(attr));
attr.bp_addr = (unsigned long) ptr;
@@ -593,8 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
attr.type = PERF_TYPE_BREAKPOINT;
- snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw");
- return add_event(list, idx, &attr, name);
+ return add_event(list, idx, &attr, NULL);
}
static int config_term(struct perf_event_attr *attr,
@@ -666,8 +562,7 @@ int parse_events_add_numeric(struct list_head **list, int *idx,
config_attr(&attr, head_config, 1))
return -EINVAL;
- return add_event(list, idx, &attr,
- (char *) __event_name(type, config));
+ return add_event(list, idx, &attr, NULL);
}
static int parse_events__is_name_term(struct parse_events__term *term)
@@ -675,8 +570,7 @@ static int parse_events__is_name_term(struct parse_events__term *term)
return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
}
-static char *pmu_event_name(struct perf_event_attr *attr,
- struct list_head *head_terms)
+static char *pmu_event_name(struct list_head *head_terms)
{
struct parse_events__term *term;
@@ -684,7 +578,7 @@ static char *pmu_event_name(struct perf_event_attr *attr,
if (parse_events__is_name_term(term))
return term->val.str;
- return (char *) __event_name(PERF_TYPE_RAW, attr->config);
+ return NULL;
}
int parse_events_add_pmu(struct list_head **list, int *idx,
@@ -699,6 +593,9 @@ int parse_events_add_pmu(struct list_head **list, int *idx,
memset(&attr, 0, sizeof(attr));
+ if (perf_pmu__check_alias(pmu, head_config))
+ return -EINVAL;
+
/*
* Configure hardcoded terms first, no need to check
* return value when called with fail == 0 ;)
@@ -709,7 +606,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx,
return -EINVAL;
return add_event(list, idx, &attr,
- pmu_event_name(&attr, head_config));
+ pmu_event_name(head_config));
}
void parse_events_update_lists(struct list_head *list_event,
@@ -787,27 +684,62 @@ int parse_events_modifier(struct list_head *list, char *str)
return 0;
}
-int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
+static int parse_events__scanner(const char *str, void *data, int start_token)
{
- LIST_HEAD(list);
- LIST_HEAD(list_tmp);
YY_BUFFER_STATE buffer;
- int ret, idx = evlist->nr_entries;
+ void *scanner;
+ int ret;
+
+ ret = parse_events_lex_init_extra(start_token, &scanner);
+ if (ret)
+ return ret;
- buffer = parse_events__scan_string(str);
+ buffer = parse_events__scan_string(str, scanner);
#ifdef PARSER_DEBUG
parse_events_debug = 1;
#endif
- ret = parse_events_parse(&list, &idx);
+ ret = parse_events_parse(data, scanner);
- parse_events__flush_buffer(buffer);
- parse_events__delete_buffer(buffer);
- parse_events_lex_destroy();
+ parse_events__flush_buffer(buffer, scanner);
+ parse_events__delete_buffer(buffer, scanner);
+ parse_events_lex_destroy(scanner);
+ return ret;
+}
+
+/*
+ * parse event config string, return a list of event terms.
+ */
+int parse_events_terms(struct list_head *terms, const char *str)
+{
+ struct parse_events_data__terms data = {
+ .terms = NULL,
+ };
+ int ret;
+ ret = parse_events__scanner(str, &data, PE_START_TERMS);
if (!ret) {
- int entries = idx - evlist->nr_entries;
- perf_evlist__splice_list_tail(evlist, &list, entries);
+ list_splice(data.terms, terms);
+ free(data.terms);
+ return 0;
+ }
+
+ parse_events__free_terms(data.terms);
+ return ret;
+}
+
+int parse_events(struct perf_evlist *evlist, const char *str, int unset __used)
+{
+ struct parse_events_data__events data = {
+ .list = LIST_HEAD_INIT(data.list),
+ .idx = evlist->nr_entries,
+ };
+ int ret;
+
+ ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+ if (!ret) {
+ int entries = data.idx - evlist->nr_entries;
+ perf_evlist__splice_list_tail(evlist, &data.list, entries);
return 0;
}
@@ -946,16 +878,13 @@ int is_valid_tracepoint(const char *event_string)
return 0;
}
-void print_events_type(u8 type)
+static void __print_events_type(u8 type, struct event_symbol *syms,
+ unsigned max)
{
- struct event_symbol *syms = event_symbols;
- unsigned int i;
char name[64];
+ unsigned i;
- for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
- if (type != syms->type)
- continue;
-
+ for (i = 0; i < max ; i++, syms++) {
if (strlen(syms->alias))
snprintf(name, sizeof(name), "%s OR %s",
syms->symbol, syms->alias);
@@ -967,19 +896,28 @@ void print_events_type(u8 type)
}
}
+void print_events_type(u8 type)
+{
+ if (type == PERF_TYPE_SOFTWARE)
+ __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX);
+ else
+ __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX);
+}
+
int print_hwcache_events(const char *event_glob)
{
unsigned int type, op, i, printed = 0;
+ char name[64];
for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
/* skip invalid cache type */
- if (!is_cache_op_valid(type, op))
+ if (!perf_evsel__is_cache_op_valid(type, op))
continue;
for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
- char *name = event_cache_name(type, op, i);
-
+ __perf_evsel__hw_cache_type_op_res_name(type, op, i,
+ name, sizeof(name));
if (event_glob != NULL && !strglobmatch(name, event_glob))
continue;
@@ -993,26 +931,13 @@ int print_hwcache_events(const char *event_glob)
return printed;
}
-/*
- * Print the help text for the event symbols:
- */
-void print_events(const char *event_glob)
+static void print_symbol_events(const char *event_glob, unsigned type,
+ struct event_symbol *syms, unsigned max)
{
- unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
- struct event_symbol *syms = event_symbols;
+ unsigned i, printed = 0;
char name[MAX_NAME_LEN];
- printf("\n");
- printf("List of pre-defined events (to be used in -e):\n");
-
- for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
- type = syms->type;
-
- if (type != prev_type && printed) {
- printf("\n");
- printed = 0;
- ntypes_printed++;
- }
+ for (i = 0; i < max; i++, syms++) {
if (event_glob != NULL &&
!(strglobmatch(syms->symbol, event_glob) ||
@@ -1023,17 +948,31 @@ void print_events(const char *event_glob)
snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
else
strncpy(name, syms->symbol, MAX_NAME_LEN);
- printf(" %-50s [%s]\n", name,
- event_type_descriptors[type]);
- prev_type = type;
- ++printed;
+ printf(" %-50s [%s]\n", name, event_type_descriptors[type]);
+
+ printed++;
}
- if (ntypes_printed) {
- printed = 0;
+ if (printed)
printf("\n");
- }
+}
+
+/*
+ * Print the help text for the event symbols:
+ */
+void print_events(const char *event_glob)
+{
+
+ printf("\n");
+ printf("List of pre-defined events (to be used in -e):\n");
+
+ print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
+ event_symbols_hw, PERF_COUNT_HW_MAX);
+
+ print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
+ event_symbols_sw, PERF_COUNT_SW_MAX);
+
print_hwcache_events(event_glob);
if (event_glob != NULL)
@@ -1106,6 +1045,13 @@ int parse_events__term_str(struct parse_events__term **term,
config, str, 0);
}
+int parse_events__term_clone(struct parse_events__term **new,
+ struct parse_events__term *term)
+{
+ return new_term(new, term->type_val, term->type_term, term->config,
+ term->val.str, term->val.num);
+}
+
void parse_events__free_terms(struct list_head *terms)
{
struct parse_events__term *term, *h;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 8cac57a..ee9c218 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -26,13 +26,12 @@ extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
extern bool have_tracepoints(struct list_head *evlist);
const char *event_type(int type);
-const char *event_name(struct perf_evsel *event);
-extern const char *__event_name(int type, u64 config);
extern int parse_events_option(const struct option *opt, const char *str,
int unset);
extern int parse_events(struct perf_evlist *evlist, const char *str,
int unset);
+extern int parse_events_terms(struct list_head *terms, const char *str);
extern int parse_filter(const struct option *opt, const char *str, int unset);
#define EVENTS_HELP_MAX (128*1024)
@@ -63,11 +62,22 @@ struct parse_events__term {
struct list_head list;
};
+struct parse_events_data__events {
+ struct list_head list;
+ int idx;
+};
+
+struct parse_events_data__terms {
+ struct list_head *terms;
+};
+
int parse_events__is_hardcoded_term(struct parse_events__term *term);
int parse_events__term_num(struct parse_events__term **_term,
int type_term, char *config, long num);
int parse_events__term_str(struct parse_events__term **_term,
int type_term, char *config, char *str);
+int parse_events__term_clone(struct parse_events__term **new,
+ struct parse_events__term *term);
void parse_events__free_terms(struct list_head *terms);
int parse_events_modifier(struct list_head *list, char *str);
int parse_events_add_tracepoint(struct list_head **list, int *idx,
@@ -83,8 +93,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx,
char *pmu , struct list_head *head_config);
void parse_events_update_lists(struct list_head *list_event,
struct list_head *list_all);
-void parse_events_error(struct list_head *list_all,
- int *idx, char const *msg);
+void parse_events_error(void *data, void *scanner, char const *msg);
int parse_events__test(void);
void print_events(const char *event_glob);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 618a8e7..384ca74 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -1,4 +1,6 @@
+%option reentrant
+%option bison-bridge
%option prefix="parse_events_"
%option stack
@@ -8,7 +10,10 @@
#include "parse-events-bison.h"
#include "parse-events.h"
-static int __value(char *str, int base, int token)
+char *parse_events_get_text(yyscan_t yyscanner);
+YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
+
+static int __value(YYSTYPE *yylval, char *str, int base, int token)
{
long num;
@@ -17,35 +22,48 @@ static int __value(char *str, int base, int token)
if (errno)
return PE_ERROR;
- parse_events_lval.num = num;
+ yylval->num = num;
return token;
}
-static int value(int base)
+static int value(yyscan_t scanner, int base)
{
- return __value(parse_events_text, base, PE_VALUE);
+ YYSTYPE *yylval = parse_events_get_lval(scanner);
+ char *text = parse_events_get_text(scanner);
+
+ return __value(yylval, text, base, PE_VALUE);
}
-static int raw(void)
+static int raw(yyscan_t scanner)
{
- return __value(parse_events_text + 1, 16, PE_RAW);
+ YYSTYPE *yylval = parse_events_get_lval(scanner);
+ char *text = parse_events_get_text(scanner);
+
+ return __value(yylval, text + 1, 16, PE_RAW);
}
-static int str(int token)
+static int str(yyscan_t scanner, int token)
{
- parse_events_lval.str = strdup(parse_events_text);
+ YYSTYPE *yylval = parse_events_get_lval(scanner);
+ char *text = parse_events_get_text(scanner);
+
+ yylval->str = strdup(text);
return token;
}
-static int sym(int type, int config)
+static int sym(yyscan_t scanner, int type, int config)
{
- parse_events_lval.num = (type << 16) + config;
- return PE_VALUE_SYM;
+ YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+ yylval->num = (type << 16) + config;
+ return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
}
-static int term(int type)
+static int term(yyscan_t scanner, int type)
{
- parse_events_lval.num = type;
+ YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+ yylval->num = type;
return PE_TERM;
}
@@ -58,28 +76,41 @@ num_hex 0x[a-fA-F0-9]+
num_raw_hex [a-fA-F0-9]+
name [a-zA-Z_*?][a-zA-Z0-9_*?]*
modifier_event [ukhpGH]{1,8}
-modifier_bp [rwx]
+modifier_bp [rwx]{1,3}
%%
-cpu-cycles|cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
-cpu-clock { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
-task-clock { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
-page-faults|faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
-minor-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
-major-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
-context-switches|cs { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
-cpu-migrations|migrations { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
-alignment-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
-emulation-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+
+%{
+ {
+ int start_token;
+
+ start_token = (int) parse_events_get_extra(yyscanner);
+ if (start_token) {
+ parse_events_set_extra(NULL, yyscanner);
+ return start_token;
+ }
+ }
+%}
+
+cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
L1-dcache|l1-d|l1d|L1-data |
L1-icache|l1-i|l1i|L1-instruction |
@@ -87,14 +118,14 @@ LLC|L2 |
dTLB|d-tlb|Data-TLB |
iTLB|i-tlb|Instruction-TLB |
branch|branches|bpu|btb|bpc |
-node { return str(PE_NAME_CACHE_TYPE); }
+node { return str(yyscanner, PE_NAME_CACHE_TYPE); }
load|loads|read |
store|stores|write |
prefetch|prefetches |
speculative-read|speculative-load |
refs|Reference|ops|access |
-misses|miss { return str(PE_NAME_CACHE_OP_RESULT); }
+misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
/*
* These are event config hardcoded term names to be specified
@@ -102,38 +133,39 @@ misses|miss { return str(PE_NAME_CACHE_OP_RESULT); }
* so we can put them here directly. In case the we have a conflict
* in future, this needs to go into '//' condition block.
*/
-config { return term(PARSE_EVENTS__TERM_TYPE_CONFIG); }
-config1 { return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); }
-config2 { return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); }
-name { return term(PARSE_EVENTS__TERM_TYPE_NAME); }
-period { return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
-branch_type { return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
+config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
+config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
+name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
+period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
+branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
mem: { BEGIN(mem); return PE_PREFIX_MEM; }
-r{num_raw_hex} { return raw(); }
-{num_dec} { return value(10); }
-{num_hex} { return value(16); }
+r{num_raw_hex} { return raw(yyscanner); }
+{num_dec} { return value(yyscanner, 10); }
+{num_hex} { return value(yyscanner, 16); }
-{modifier_event} { return str(PE_MODIFIER_EVENT); }
-{name} { return str(PE_NAME); }
+{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); }
+{name} { return str(yyscanner, PE_NAME); }
"/" { return '/'; }
- { return '-'; }
, { return ','; }
: { return ':'; }
= { return '='; }
+\n { }
<mem>{
-{modifier_bp} { return str(PE_MODIFIER_BP); }
+{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); }
: { return ':'; }
-{num_dec} { return value(10); }
-{num_hex} { return value(16); }
+{num_dec} { return value(yyscanner, 10); }
+{num_hex} { return value(yyscanner, 16); }
/*
* We need to separate 'mem:' scanner part, in order to get specific
* modifier bits parsed out. Otherwise we would need to handle PE_NAME
* and we'd need to parse it manually. During the escape from <mem>
* state we need to put the escaping char back, so we dont miss it.
*/
-. { unput(*parse_events_text); BEGIN(INITIAL); }
+. { unput(*yytext); BEGIN(INITIAL); }
/*
* We destroy the scanner after reaching EOF,
* but anyway just to be sure get back to INIT state.
@@ -143,7 +175,7 @@ r{num_raw_hex} { return raw(); }
%%
-int parse_events_wrap(void)
+int parse_events_wrap(void *scanner __used)
{
return 1;
}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 362cc59..2bc5fbf 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -1,7 +1,8 @@
-
+%pure-parser
%name-prefix "parse_events_"
-%parse-param {struct list_head *list_all}
-%parse-param {int *idx}
+%parse-param {void *_data}
+%parse-param {void *scanner}
+%lex-param {void* scanner}
%{
@@ -12,8 +13,9 @@
#include "types.h"
#include "util.h"
#include "parse-events.h"
+#include "parse-events-bison.h"
-extern int parse_events_lex (void);
+extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
#define ABORT_ON(val) \
do { \
@@ -23,14 +25,16 @@ do { \
%}
-%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM
+%token PE_START_EVENTS PE_START_TERMS
+%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
%token PE_NAME
%token PE_MODIFIER_EVENT PE_MODIFIER_BP
%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
%token PE_PREFIX_MEM PE_PREFIX_RAW
%token PE_ERROR
%type <num> PE_VALUE
-%type <num> PE_VALUE_SYM
+%type <num> PE_VALUE_SYM_HW
+%type <num> PE_VALUE_SYM_SW
%type <num> PE_RAW
%type <num> PE_TERM
%type <str> PE_NAME
@@ -38,6 +42,7 @@ do { \
%type <str> PE_NAME_CACHE_OP_RESULT
%type <str> PE_MODIFIER_EVENT
%type <str> PE_MODIFIER_BP
+%type <num> value_sym
%type <head> event_config
%type <term> event_term
%type <head> event_pmu
@@ -58,24 +63,33 @@ do { \
}
%%
+start:
+PE_START_EVENTS events
+|
+PE_START_TERMS terms
+
events:
events ',' event | event
event:
event_def PE_MODIFIER_EVENT
{
+ struct parse_events_data__events *data = _data;
+
/*
* Apply modifier on all events added by single event definition
* (there could be more events added for multiple tracepoint
* definitions via '*?'.
*/
ABORT_ON(parse_events_modifier($1, $2));
- parse_events_update_lists($1, list_all);
+ parse_events_update_lists($1, &data->list);
}
|
event_def
{
- parse_events_update_lists($1, list_all);
+ struct parse_events_data__events *data = _data;
+
+ parse_events_update_lists($1, &data->list);
}
event_def: event_pmu |
@@ -89,104 +103,131 @@ event_def: event_pmu |
event_pmu:
PE_NAME '/' event_config '/'
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_pmu(&list, idx, $1, $3));
+ ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3));
parse_events__free_terms($3);
$$ = list;
}
+value_sym:
+PE_VALUE_SYM_HW
+|
+PE_VALUE_SYM_SW
+
event_legacy_symbol:
-PE_VALUE_SYM '/' event_config '/'
+value_sym '/' event_config '/'
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
int type = $1 >> 16;
int config = $1 & 255;
- ABORT_ON(parse_events_add_numeric(&list, idx, type, config, $3));
+ ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+ type, config, $3));
parse_events__free_terms($3);
$$ = list;
}
|
-PE_VALUE_SYM sep_slash_dc
+value_sym sep_slash_dc
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
int type = $1 >> 16;
int config = $1 & 255;
- ABORT_ON(parse_events_add_numeric(&list, idx, type, config, NULL));
+ ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+ type, config, NULL));
$$ = list;
}
event_legacy_cache:
PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, $5));
+ ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5));
$$ = list;
}
|
PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, NULL));
+ ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL));
$$ = list;
}
|
PE_NAME_CACHE_TYPE
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_cache(&list, idx, $1, NULL, NULL));
+ ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL));
$$ = list;
}
event_legacy_mem:
PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, $4));
+ ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+ (void *) $2, $4));
$$ = list;
}
|
PE_PREFIX_MEM PE_VALUE sep_dc
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, NULL));
+ ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+ (void *) $2, NULL));
$$ = list;
}
event_legacy_tracepoint:
PE_NAME ':' PE_NAME
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_tracepoint(&list, idx, $1, $3));
+ ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3));
$$ = list;
}
event_legacy_numeric:
PE_VALUE ':' PE_VALUE
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_numeric(&list, idx, $1, $3, NULL));
+ ABORT_ON(parse_events_add_numeric(&list, &data->idx, $1, $3, NULL));
$$ = list;
}
event_legacy_raw:
PE_RAW
{
+ struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_numeric(&list, idx, PERF_TYPE_RAW, $1, NULL));
+ ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+ PERF_TYPE_RAW, $1, NULL));
$$ = list;
}
+terms: event_config
+{
+ struct parse_events_data__terms *data = _data;
+ data->terms = $1;
+}
+
event_config:
event_config ',' event_term
{
@@ -267,8 +308,7 @@ sep_slash_dc: '/' | ':' |
%%
-void parse_events_error(struct list_head *list_all __used,
- int *idx __used,
+void parse_events_error(void *data __used, void *scanner __used,
char const *msg __used)
{
}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a119a53..67715a4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -72,7 +72,7 @@ static int pmu_format(char *name, struct list_head *format)
"%s/bus/event_source/devices/%s/format", sysfs, name);
if (stat(path, &st) < 0)
- return -1;
+ return 0; /* no error if format does not exist */
if (pmu_format_parse(path, format))
return -1;
@@ -80,6 +80,114 @@ static int pmu_format(char *name, struct list_head *format)
return 0;
}
+static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
+{
+ struct perf_pmu__alias *alias;
+ char buf[256];
+ int ret;
+
+ ret = fread(buf, 1, sizeof(buf), file);
+ if (ret == 0)
+ return -EINVAL;
+ buf[ret] = 0;
+
+ alias = malloc(sizeof(*alias));
+ if (!alias)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&alias->terms);
+ ret = parse_events_terms(&alias->terms, buf);
+ if (ret) {
+ free(alias);
+ return ret;
+ }
+
+ alias->name = strdup(name);
+ list_add_tail(&alias->list, list);
+ return 0;
+}
+
+/*
+ * Process all the sysfs attributes located under the directory
+ * specified in 'dir' parameter.
+ */
+static int pmu_aliases_parse(char *dir, struct list_head *head)
+{
+ struct dirent *evt_ent;
+ DIR *event_dir;
+ int ret = 0;
+
+ event_dir = opendir(dir);
+ if (!event_dir)
+ return -EINVAL;
+
+ while (!ret && (evt_ent = readdir(event_dir))) {
+ char path[PATH_MAX];
+ char *name = evt_ent->d_name;
+ FILE *file;
+
+ if (!strcmp(name, ".") || !strcmp(name, ".."))
+ continue;
+
+ snprintf(path, PATH_MAX, "%s/%s", dir, name);
+
+ ret = -EINVAL;
+ file = fopen(path, "r");
+ if (!file)
+ break;
+ ret = perf_pmu__new_alias(head, name, file);
+ fclose(file);
+ }
+
+ closedir(event_dir);
+ return ret;
+}
+
+/*
+ * Reading the pmu event aliases definition, which should be located at:
+ * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
+ */
+static int pmu_aliases(char *name, struct list_head *head)
+{
+ struct stat st;
+ char path[PATH_MAX];
+ const char *sysfs;
+
+ sysfs = sysfs_find_mountpoint();
+ if (!sysfs)
+ return -1;
+
+ snprintf(path, PATH_MAX,
+ "%s/bus/event_source/devices/%s/events", sysfs, name);
+
+ if (stat(path, &st) < 0)
+ return -1;
+
+ if (pmu_aliases_parse(path, head))
+ return -1;
+
+ return 0;
+}
+
+static int pmu_alias_terms(struct perf_pmu__alias *alias,
+ struct list_head *terms)
+{
+ struct parse_events__term *term, *clone;
+ LIST_HEAD(list);
+ int ret;
+
+ list_for_each_entry(term, &alias->terms, list) {
+ ret = parse_events__term_clone(&clone, term);
+ if (ret) {
+ parse_events__free_terms(&list);
+ return ret;
+ }
+ list_add_tail(&clone->list, &list);
+ }
+ list_splice(&list, terms);
+ return 0;
+}
+
/*
* Reading/parsing the default pmu type value, which should be
* located at:
@@ -118,6 +226,7 @@ static struct perf_pmu *pmu_lookup(char *name)
{
struct perf_pmu *pmu;
LIST_HEAD(format);
+ LIST_HEAD(aliases);
__u32 type;
/*
@@ -135,10 +244,15 @@ static struct perf_pmu *pmu_lookup(char *name)
if (!pmu)
return NULL;
+ pmu_aliases(name, &aliases);
+
INIT_LIST_HEAD(&pmu->format);
+ INIT_LIST_HEAD(&pmu->aliases);
list_splice(&format, &pmu->format);
+ list_splice(&aliases, &pmu->aliases);
pmu->name = strdup(name);
pmu->type = type;
+ list_add_tail(&pmu->list, &pmus);
return pmu;
}
@@ -279,6 +393,59 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
return pmu_config(&pmu->format, attr, head_terms);
}
+static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu,
+ struct parse_events__term *term)
+{
+ struct perf_pmu__alias *alias;
+ char *name;
+
+ if (parse_events__is_hardcoded_term(term))
+ return NULL;
+
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+ if (term->val.num != 1)
+ return NULL;
+ if (pmu_find_format(&pmu->format, term->config))
+ return NULL;
+ name = term->config;
+ } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+ if (strcasecmp(term->config, "event"))
+ return NULL;
+ name = term->val.str;
+ } else {
+ return NULL;
+ }
+
+ list_for_each_entry(alias, &pmu->aliases, list) {
+ if (!strcasecmp(alias->name, name))
+ return alias;
+ }
+ return NULL;
+}
+
+/*
+ * Find alias in the terms list and replace it with the terms
+ * defined for the alias
+ */
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
+{
+ struct parse_events__term *term, *h;
+ struct perf_pmu__alias *alias;
+ int ret;
+
+ list_for_each_entry_safe(term, h, head_terms, list) {
+ alias = pmu_find_alias(pmu, term);
+ if (!alias)
+ continue;
+ ret = pmu_alias_terms(alias, &term->list);
+ if (ret)
+ return ret;
+ list_del(&term->list);
+ free(term);
+ }
+ return 0;
+}
+
int perf_pmu__new_format(struct list_head *list, char *name,
int config, unsigned long *bits)
{
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 68c0db9..535f2c5 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -19,17 +19,26 @@ struct perf_pmu__format {
struct list_head list;
};
+struct perf_pmu__alias {
+ char *name;
+ struct list_head terms;
+ struct list_head list;
+};
+
struct perf_pmu {
char *name;
__u32 type;
struct list_head format;
+ struct list_head aliases;
struct list_head list;
};
struct perf_pmu *perf_pmu__find(char *name);
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
struct list_head *head_terms);
-
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
+struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
+ struct list_head *head_terms);
int perf_pmu_wrap(void);
void perf_pmu_error(struct list_head *list, char *name, char const *msg);
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 4c1b3d7..02dfa19 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -209,6 +209,10 @@ static void define_event_symbols(struct event_format *event,
define_symbolic_values(args->symbol.symbols, ev_name,
cur_field_name);
break;
+ case PRINT_HEX:
+ define_event_symbols(event, ev_name, args->hex.field);
+ define_event_symbols(event, ev_name, args->hex.size);
+ break;
case PRINT_BSTRING:
case PRINT_DYNAMIC_ARRAY:
case PRINT_STRING:
@@ -233,7 +237,8 @@ static void define_event_symbols(struct event_format *event,
define_event_symbols(event, ev_name, args->next);
}
-static inline struct event_format *find_cache_event(int type)
+static inline
+struct event_format *find_cache_event(struct pevent *pevent, int type)
{
static char ev_name[256];
struct event_format *event;
@@ -241,7 +246,7 @@ static inline struct event_format *find_cache_event(int type)
if (events[type])
return events[type];
- events[type] = event = trace_find_event(type);
+ events[type] = event = pevent_find_event(pevent, type);
if (!event)
return NULL;
@@ -252,7 +257,8 @@ static inline struct event_format *find_cache_event(int type)
return event;
}
-static void perl_process_tracepoint(union perf_event *pevent __unused,
+static void perl_process_tracepoint(union perf_event *perf_event __unused,
+ struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine __unused,
@@ -275,13 +281,13 @@ static void perl_process_tracepoint(union perf_event *pevent __unused,
if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
return;
- type = trace_parse_common_type(data);
+ type = trace_parse_common_type(pevent, data);
- event = find_cache_event(type);
+ event = find_cache_event(pevent, type);
if (!event)
die("ug! no event found for type %d", type);
- pid = trace_parse_common_pid(data);
+ pid = trace_parse_common_pid(pevent, data);
sprintf(handler, "%s::%s", event->system, event->name);
@@ -314,7 +320,8 @@ static void perl_process_tracepoint(union perf_event *pevent __unused,
offset = field->offset;
XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0)));
} else { /* FIELD_IS_NUMERIC */
- val = read_size(data + field->offset, field->size);
+ val = read_size(pevent, data + field->offset,
+ field->size);
if (field->flags & FIELD_IS_SIGNED) {
XPUSHs(sv_2mortal(newSViv(val)));
} else {
@@ -368,14 +375,15 @@ static void perl_process_event_generic(union perf_event *pevent __unused,
LEAVE;
}
-static void perl_process_event(union perf_event *pevent,
+static void perl_process_event(union perf_event *event,
+ struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine,
struct thread *thread)
{
- perl_process_tracepoint(pevent, sample, evsel, machine, thread);
- perl_process_event_generic(pevent, sample, evsel, machine, thread);
+ perl_process_tracepoint(event, pevent, sample, evsel, machine, thread);
+ perl_process_event_generic(event, sample, evsel, machine, thread);
}
static void run_start_sub(void)
@@ -448,7 +456,7 @@ static int perl_stop_script(void)
return 0;
}
-static int perl_generate_script(const char *outfile)
+static int perl_generate_script(struct pevent *pevent, const char *outfile)
{
struct event_format *event = NULL;
struct format_field *f;
@@ -495,7 +503,7 @@ static int perl_generate_script(const char *outfile)
fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n");
fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n");
- while ((event = trace_find_next_event(event))) {
+ while ((event = trace_find_next_event(pevent, event))) {
fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
fprintf(ofp, "\tmy (");
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index acb9795..ce4d1b0 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -166,6 +166,10 @@ static void define_event_symbols(struct event_format *event,
define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
cur_field_name);
break;
+ case PRINT_HEX:
+ define_event_symbols(event, ev_name, args->hex.field);
+ define_event_symbols(event, ev_name, args->hex.size);
+ break;
case PRINT_STRING:
break;
case PRINT_TYPE:
@@ -190,7 +194,8 @@ static void define_event_symbols(struct event_format *event,
define_event_symbols(event, ev_name, args->next);
}
-static inline struct event_format *find_cache_event(int type)
+static inline
+struct event_format *find_cache_event(struct pevent *pevent, int type)
{
static char ev_name[256];
struct event_format *event;
@@ -198,7 +203,7 @@ static inline struct event_format *find_cache_event(int type)
if (events[type])
return events[type];
- events[type] = event = trace_find_event(type);
+ events[type] = event = pevent_find_event(pevent, type);
if (!event)
return NULL;
@@ -209,7 +214,8 @@ static inline struct event_format *find_cache_event(int type)
return event;
}
-static void python_process_event(union perf_event *pevent __unused,
+static void python_process_event(union perf_event *perf_event __unused,
+ struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel __unused,
struct machine *machine __unused,
@@ -233,13 +239,13 @@ static void python_process_event(union perf_event *pevent __unused,
if (!t)
Py_FatalError("couldn't create Python tuple");
- type = trace_parse_common_type(data);
+ type = trace_parse_common_type(pevent, data);
- event = find_cache_event(type);
+ event = find_cache_event(pevent, type);
if (!event)
die("ug! no event found for type %d", type);
- pid = trace_parse_common_pid(data);
+ pid = trace_parse_common_pid(pevent, data);
sprintf(handler_name, "%s__%s", event->system, event->name);
@@ -284,7 +290,8 @@ static void python_process_event(union perf_event *pevent __unused,
offset = field->offset;
obj = PyString_FromString((char *)data + offset);
} else { /* FIELD_IS_NUMERIC */
- val = read_size(data + field->offset, field->size);
+ val = read_size(pevent, data + field->offset,
+ field->size);
if (field->flags & FIELD_IS_SIGNED) {
if ((long long)val >= LONG_MIN &&
(long long)val <= LONG_MAX)
@@ -438,7 +445,7 @@ out:
return err;
}
-static int python_generate_script(const char *outfile)
+static int python_generate_script(struct pevent *pevent, const char *outfile)
{
struct event_format *event = NULL;
struct format_field *f;
@@ -487,7 +494,7 @@ static int python_generate_script(const char *outfile)
fprintf(ofp, "def trace_end():\n");
fprintf(ofp, "\tprint \"in trace_end\"\n\n");
- while ((event = trace_find_next_event(event))) {
+ while ((event = trace_find_next_event(pevent, event))) {
fprintf(ofp, "def %s__%s(", event->system, event->name);
fprintf(ofp, "event_name, ");
fprintf(ofp, "context, ");
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 56142d0..8e48559 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,7 @@
#include "sort.h"
#include "util.h"
#include "cpumap.h"
+#include "event-parse.h"
static int perf_session__open(struct perf_session *self, bool force)
{
@@ -289,7 +290,6 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
}
int machine__resolve_callchain(struct machine *self,
- struct perf_evsel *evsel __used,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent)
@@ -1449,7 +1449,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
ret += hists__fprintf_nr_events(&session->hists, fp);
list_for_each_entry(pos, &session->evlist->entries, node) {
- ret += fprintf(fp, "%s stats:\n", event_name(pos));
+ ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
ret += hists__fprintf_nr_events(&pos->hists, fp);
}
@@ -1490,8 +1490,8 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
}
void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, struct perf_evsel *evsel,
- int print_sym, int print_dso, int print_symoffset)
+ struct machine *machine, int print_sym,
+ int print_dso, int print_symoffset)
{
struct addr_location al;
struct callchain_cursor_node *node;
@@ -1505,7 +1505,7 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
if (symbol_conf.use_callchain && sample->callchain) {
- if (machine__resolve_callchain(machine, evsel, al.thread,
+ if (machine__resolve_callchain(machine, al.thread,
sample->callchain, NULL) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
@@ -1611,3 +1611,58 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
perf_header__fprintf_info(session, fp, full);
fprintf(fp, "# ========\n#\n");
}
+
+
+int __perf_session__set_tracepoints_handlers(struct perf_session *session,
+ const struct perf_evsel_str_handler *assocs,
+ size_t nr_assocs)
+{
+ struct perf_evlist *evlist = session->evlist;
+ struct event_format *format;
+ struct perf_evsel *evsel;
+ char *tracepoint, *name;
+ size_t i;
+ int err;
+
+ for (i = 0; i < nr_assocs; i++) {
+ err = -ENOMEM;
+ tracepoint = strdup(assocs[i].name);
+ if (tracepoint == NULL)
+ goto out;
+
+ err = -ENOENT;
+ name = strchr(tracepoint, ':');
+ if (name == NULL)
+ goto out_free;
+
+ *name++ = '\0';
+ format = pevent_find_event_by_name(session->pevent,
+ tracepoint, name);
+ if (format == NULL) {
+ /*
+ * Adding a handler for an event not in the session,
+ * just ignore it.
+ */
+ goto next;
+ }
+
+ evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id);
+ if (evsel == NULL)
+ goto next;
+
+ err = -EEXIST;
+ if (evsel->handler.func != NULL)
+ goto out_free;
+ evsel->handler.func = assocs[i].handler;
+next:
+ free(tracepoint);
+ }
+
+ err = 0;
+out:
+ return err;
+
+out_free:
+ free(tracepoint);
+ goto out;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0c702e3..7c435bd 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -33,6 +33,7 @@ struct perf_session {
struct machine host_machine;
struct rb_root machines;
struct perf_evlist *evlist;
+ struct pevent *pevent;
/*
* FIXME: Need to split this up further, we need global
* stats + per event stats. 'perf diff' also needs
@@ -151,11 +152,20 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type);
void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, struct perf_evsel *evsel,
- int print_sym, int print_dso, int print_symoffset);
+ struct machine *machine, int print_sym,
+ int print_dso, int print_symoffset);
int perf_session__cpu_bitmap(struct perf_session *session,
const char *cpu_list, unsigned long *cpu_bitmap);
void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
+
+struct perf_evsel_str_handler;
+
+int __perf_session__set_tracepoints_handlers(struct perf_session *session,
+ const struct perf_evsel_str_handler *assocs,
+ size_t nr_assocs);
+
+#define perf_session__set_tracepoints_handlers(session, array) \
+ __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
#endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index a272374..0f5a0a4 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -241,6 +241,54 @@ struct sort_entry sort_sym = {
.se_width_idx = HISTC_SYMBOL,
};
+/* --sort srcline */
+
+static int64_t
+sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return (int64_t)(right->ip - left->ip);
+}
+
+static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width __used)
+{
+ FILE *fp;
+ char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
+ size_t line_len;
+
+ if (path != NULL)
+ goto out_path;
+
+ snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64,
+ self->ms.map->dso->long_name, self->ip);
+ fp = popen(cmd, "r");
+ if (!fp)
+ goto out_ip;
+
+ if (getline(&path, &line_len, fp) < 0 || !line_len)
+ goto out_ip;
+ fclose(fp);
+ self->srcline = strdup(path);
+ if (self->srcline == NULL)
+ goto out_ip;
+
+ nl = strchr(self->srcline, '\n');
+ if (nl != NULL)
+ *nl = '\0';
+ path = self->srcline;
+out_path:
+ return repsep_snprintf(bf, size, "%s", path);
+out_ip:
+ return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip);
+}
+
+struct sort_entry sort_srcline = {
+ .se_header = "Source:Line",
+ .se_cmp = sort__srcline_cmp,
+ .se_snprintf = hist_entry__srcline_snprintf,
+ .se_width_idx = HISTC_SRCLINE,
+};
+
/* --sort parent */
static int64_t
@@ -439,6 +487,7 @@ static struct sort_dimension sort_dimensions[] = {
DIM(SORT_PARENT, "parent", sort_parent),
DIM(SORT_CPU, "cpu", sort_cpu),
DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
+ DIM(SORT_SRCLINE, "srcline", sort_srcline),
};
int sort_dimension__add(const char *tok)
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 472aa5a..e724b26 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -71,6 +71,7 @@ struct hist_entry {
char level;
bool used;
u8 filtered;
+ char *srcline;
struct symbol *parent;
union {
unsigned long position;
@@ -93,6 +94,7 @@ enum sort_type {
SORT_SYM_FROM,
SORT_SYM_TO,
SORT_MISPREDICT,
+ SORT_SRCLINE,
};
/*
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d583638..199bc4d 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -313,3 +313,25 @@ int strtailcmp(const char *s1, const char *s2)
return 0;
}
+/**
+ * rtrim - Removes trailing whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Note that the first trailing whitespace is replaced with a %NUL-terminator
+ * in the given string @s. Returns @s.
+ */
+char *rtrim(char *s)
+{
+ size_t size = strlen(s);
+ char *end;
+
+ if (!size)
+ return s;
+
+ end = s + size - 1;
+ while (end >= s && isspace(*end))
+ end--;
+ *(end + 1) = '\0';
+
+ return s;
+}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3e2e5ea..50958bb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1478,14 +1478,31 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
goto out;
}
- sec = elf_section_by_name(elf, &ehdr, &shdr,
- ".note.gnu.build-id", NULL);
- if (sec == NULL) {
+ /*
+ * Check following sections for notes:
+ * '.note.gnu.build-id'
+ * '.notes'
+ * '.note' (VDSO specific)
+ */
+ do {
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".note.gnu.build-id", NULL);
+ if (sec)
+ break;
+
sec = elf_section_by_name(elf, &ehdr, &shdr,
".notes", NULL);
- if (sec == NULL)
- goto out;
- }
+ if (sec)
+ break;
+
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".note", NULL);
+ if (sec)
+ break;
+
+ return err;
+
+ } while (0);
data = elf_getdata(sec, NULL);
if (data == NULL)
@@ -1590,11 +1607,62 @@ out:
return err;
}
+static int filename__read_debuglink(const char *filename,
+ char *debuglink, size_t size)
+{
+ int fd, err = -1;
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ Elf_Data *data;
+ Elf_Scn *sec;
+ Elf_Kind ek;
+
+ fd = open(filename, O_RDONLY);
+ if (fd < 0)
+ goto out;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL) {
+ pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
+ goto out_close;
+ }
+
+ ek = elf_kind(elf);
+ if (ek != ELF_K_ELF)
+ goto out_close;
+
+ if (gelf_getehdr(elf, &ehdr) == NULL) {
+ pr_err("%s: cannot get elf header.\n", __func__);
+ goto out_close;
+ }
+
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".gnu_debuglink", NULL);
+ if (sec == NULL)
+ goto out_close;
+
+ data = elf_getdata(sec, NULL);
+ if (data == NULL)
+ goto out_close;
+
+ /* the start of this section is a zero-terminated string */
+ strncpy(debuglink, data->d_buf, size);
+
+ elf_end(elf);
+
+out_close:
+ close(fd);
+out:
+ return err;
+}
+
char dso__symtab_origin(const struct dso *dso)
{
static const char origin[] = {
[SYMTAB__KALLSYMS] = 'k',
[SYMTAB__JAVA_JIT] = 'j',
+ [SYMTAB__DEBUGLINK] = 'l',
[SYMTAB__BUILD_ID_CACHE] = 'B',
[SYMTAB__FEDORA_DEBUGINFO] = 'f',
[SYMTAB__UBUNTU_DEBUGINFO] = 'u',
@@ -1662,10 +1730,22 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
*/
want_symtab = 1;
restart:
- for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE;
+ for (dso->symtab_type = SYMTAB__DEBUGLINK;
dso->symtab_type != SYMTAB__NOT_FOUND;
dso->symtab_type++) {
switch (dso->symtab_type) {
+ case SYMTAB__DEBUGLINK: {
+ char *debuglink;
+ strncpy(name, dso->long_name, size);
+ debuglink = name + dso->long_name_len;
+ while (debuglink != name && *debuglink != '/')
+ debuglink--;
+ if (*debuglink == '/')
+ debuglink++;
+ filename__read_debuglink(dso->long_name, debuglink,
+ size - (debuglink - name));
+ }
+ break;
case SYMTAB__BUILD_ID_CACHE:
/* skip the locally configured cache if a symfs is given */
if (symbol_conf.symfs[0] ||
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index af0752b..a884b99 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -257,6 +257,7 @@ enum symtab_type {
SYMTAB__KALLSYMS = 0,
SYMTAB__GUEST_KALLSYMS,
SYMTAB__JAVA_JIT,
+ SYMTAB__DEBUGLINK,
SYMTAB__BUILD_ID_CACHE,
SYMTAB__FEDORA_DEBUGINFO,
SYMTAB__UBUNTU_DEBUGINFO,
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index abe0e8e..7eeebce 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -65,7 +65,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
top->freq ? "Hz" : "");
}
- ret += SNPRINTF(bf + ret, size - ret, "%s", event_name(top->sym_evsel));
+ ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel));
ret += SNPRINTF(bf + ret, size - ret, "], ");
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 5dd3b5e..0715c84 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -32,29 +32,25 @@ int header_page_size_size;
int header_page_ts_size;
int header_page_data_offset;
-struct pevent *perf_pevent;
-static struct pevent *pevent;
-
bool latency_format;
-int read_trace_init(int file_bigendian, int host_bigendian)
+struct pevent *read_trace_init(int file_bigendian, int host_bigendian)
{
- if (pevent)
- return 0;
-
- perf_pevent = pevent_alloc();
- pevent = perf_pevent;
+ struct pevent *pevent = pevent_alloc();
- pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
- pevent_set_file_bigendian(pevent, file_bigendian);
- pevent_set_host_bigendian(pevent, host_bigendian);
+ if (pevent != NULL) {
+ pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+ pevent_set_file_bigendian(pevent, file_bigendian);
+ pevent_set_host_bigendian(pevent, host_bigendian);
+ }
- return 0;
+ return pevent;
}
static int get_common_field(struct scripting_context *context,
int *offset, int *size, const char *type)
{
+ struct pevent *pevent = context->pevent;
struct event_format *event;
struct format_field *field;
@@ -150,7 +146,7 @@ void *raw_field_ptr(struct event_format *event, const char *name, void *data)
return data + field->offset;
}
-int trace_parse_common_type(void *data)
+int trace_parse_common_type(struct pevent *pevent, void *data)
{
struct pevent_record record;
@@ -158,7 +154,7 @@ int trace_parse_common_type(void *data)
return pevent_data_type(pevent, &record);
}
-int trace_parse_common_pid(void *data)
+int trace_parse_common_pid(struct pevent *pevent, void *data)
{
struct pevent_record record;
@@ -166,27 +162,21 @@ int trace_parse_common_pid(void *data)
return pevent_data_pid(pevent, &record);
}
-unsigned long long read_size(void *ptr, int size)
+unsigned long long read_size(struct pevent *pevent, void *ptr, int size)
{
return pevent_read_number(pevent, ptr, size);
}
-struct event_format *trace_find_event(int type)
-{
- return pevent_find_event(pevent, type);
-}
-
-
-void print_trace_event(int cpu, void *data, int size)
+void print_trace_event(struct pevent *pevent, int cpu, void *data, int size)
{
struct event_format *event;
struct pevent_record record;
struct trace_seq s;
int type;
- type = trace_parse_common_type(data);
+ type = trace_parse_common_type(pevent, data);
- event = trace_find_event(type);
+ event = pevent_find_event(pevent, type);
if (!event) {
warning("ug! no event found for type %d", type);
return;
@@ -202,8 +192,8 @@ void print_trace_event(int cpu, void *data, int size)
trace_seq_do_printf(&s);
}
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
- char *comm)
+void print_event(struct pevent *pevent, int cpu, void *data, int size,
+ unsigned long long nsecs, char *comm)
{
struct pevent_record record;
struct trace_seq s;
@@ -226,7 +216,8 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs,
printf("\n");
}
-void parse_proc_kallsyms(char *file, unsigned int size __unused)
+void parse_proc_kallsyms(struct pevent *pevent,
+ char *file, unsigned int size __unused)
{
unsigned long long addr;
char *func;
@@ -257,7 +248,8 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused)
}
}
-void parse_ftrace_printk(char *file, unsigned int size __unused)
+void parse_ftrace_printk(struct pevent *pevent,
+ char *file, unsigned int size __unused)
{
unsigned long long addr;
char *printk;
@@ -281,17 +273,19 @@ void parse_ftrace_printk(char *file, unsigned int size __unused)
}
}
-int parse_ftrace_file(char *buf, unsigned long size)
+int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
{
return pevent_parse_event(pevent, buf, size, "ftrace");
}
-int parse_event_file(char *buf, unsigned long size, char *sys)
+int parse_event_file(struct pevent *pevent,
+ char *buf, unsigned long size, char *sys)
{
return pevent_parse_event(pevent, buf, size, sys);
}
-struct event_format *trace_find_next_event(struct event_format *event)
+struct event_format *trace_find_next_event(struct pevent *pevent,
+ struct event_format *event)
{
static int idx;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f097e0d..719ed74 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -114,20 +114,20 @@ static void skip(int size)
};
}
-static unsigned int read4(void)
+static unsigned int read4(struct pevent *pevent)
{
unsigned int data;
read_or_die(&data, 4);
- return __data2host4(perf_pevent, data);
+ return __data2host4(pevent, data);
}
-static unsigned long long read8(void)
+static unsigned long long read8(struct pevent *pevent)
{
unsigned long long data;
read_or_die(&data, 8);
- return __data2host8(perf_pevent, data);
+ return __data2host8(pevent, data);
}
static char *read_string(void)
@@ -168,12 +168,12 @@ static char *read_string(void)
return str;
}
-static void read_proc_kallsyms(void)
+static void read_proc_kallsyms(struct pevent *pevent)
{
unsigned int size;
char *buf;
- size = read4();
+ size = read4(pevent);
if (!size)
return;
@@ -181,29 +181,29 @@ static void read_proc_kallsyms(void)
read_or_die(buf, size);
buf[size] = '\0';
- parse_proc_kallsyms(buf, size);
+ parse_proc_kallsyms(pevent, buf, size);
free(buf);
}
-static void read_ftrace_printk(void)
+static void read_ftrace_printk(struct pevent *pevent)
{
unsigned int size;
char *buf;
- size = read4();
+ size = read4(pevent);
if (!size)
return;
buf = malloc_or_die(size);
read_or_die(buf, size);
- parse_ftrace_printk(buf, size);
+ parse_ftrace_printk(pevent, buf, size);
free(buf);
}
-static void read_header_files(void)
+static void read_header_files(struct pevent *pevent)
{
unsigned long long size;
char *header_event;
@@ -214,7 +214,7 @@ static void read_header_files(void)
if (memcmp(buf, "header_page", 12) != 0)
die("did not read header page");
- size = read8();
+ size = read8(pevent);
skip(size);
/*
@@ -227,47 +227,48 @@ static void read_header_files(void)
if (memcmp(buf, "header_event", 13) != 0)
die("did not read header event");
- size = read8();
+ size = read8(pevent);
header_event = malloc_or_die(size);
read_or_die(header_event, size);
free(header_event);
}
-static void read_ftrace_file(unsigned long long size)
+static void read_ftrace_file(struct pevent *pevent, unsigned long long size)
{
char *buf;
buf = malloc_or_die(size);
read_or_die(buf, size);
- parse_ftrace_file(buf, size);
+ parse_ftrace_file(pevent, buf, size);
free(buf);
}
-static void read_event_file(char *sys, unsigned long long size)
+static void read_event_file(struct pevent *pevent, char *sys,
+ unsigned long long size)
{
char *buf;
buf = malloc_or_die(size);
read_or_die(buf, size);
- parse_event_file(buf, size, sys);
+ parse_event_file(pevent, buf, size, sys);
free(buf);
}
-static void read_ftrace_files(void)
+static void read_ftrace_files(struct pevent *pevent)
{
unsigned long long size;
int count;
int i;
- count = read4();
+ count = read4(pevent);
for (i = 0; i < count; i++) {
- size = read8();
- read_ftrace_file(size);
+ size = read8(pevent);
+ read_ftrace_file(pevent, size);
}
}
-static void read_event_files(void)
+static void read_event_files(struct pevent *pevent)
{
unsigned long long size;
char *sys;
@@ -275,15 +276,15 @@ static void read_event_files(void)
int count;
int i,x;
- systems = read4();
+ systems = read4(pevent);
for (i = 0; i < systems; i++) {
sys = read_string();
- count = read4();
+ count = read4(pevent);
for (x=0; x < count; x++) {
- size = read8();
- read_event_file(sys, size);
+ size = read8(pevent);
+ read_event_file(pevent, sys, size);
}
}
}
@@ -377,7 +378,7 @@ static int calc_index(void *ptr, int cpu)
return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page;
}
-struct pevent_record *trace_peek_data(int cpu)
+struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu)
{
struct pevent_record *data;
void *page = cpu_data[cpu].page;
@@ -399,15 +400,15 @@ struct pevent_record *trace_peek_data(int cpu)
/* FIXME: handle header page */
if (header_page_ts_size != 8)
die("expected a long long type for timestamp");
- cpu_data[cpu].timestamp = data2host8(perf_pevent, ptr);
+ cpu_data[cpu].timestamp = data2host8(pevent, ptr);
ptr += 8;
switch (header_page_size_size) {
case 4:
- cpu_data[cpu].page_size = data2host4(perf_pevent, ptr);
+ cpu_data[cpu].page_size = data2host4(pevent, ptr);
ptr += 4;
break;
case 8:
- cpu_data[cpu].page_size = data2host8(perf_pevent, ptr);
+ cpu_data[cpu].page_size = data2host8(pevent, ptr);
ptr += 8;
break;
default:
@@ -421,10 +422,10 @@ read_again:
if (idx >= cpu_data[cpu].page_size) {
get_next_page(cpu);
- return trace_peek_data(cpu);
+ return trace_peek_data(pevent, cpu);
}
- type_len_ts = data2host4(perf_pevent, ptr);
+ type_len_ts = data2host4(pevent, ptr);
ptr += 4;
type_len = type_len4host(type_len_ts);
@@ -434,14 +435,14 @@ read_again:
case RINGBUF_TYPE_PADDING:
if (!delta)
die("error, hit unexpected end of page");
- length = data2host4(perf_pevent, ptr);
+ length = data2host4(pevent, ptr);
ptr += 4;
length *= 4;
ptr += length;
goto read_again;
case RINGBUF_TYPE_TIME_EXTEND:
- extend = data2host4(perf_pevent, ptr);
+ extend = data2host4(pevent, ptr);
ptr += 4;
extend <<= TS_SHIFT;
extend += delta;
@@ -452,7 +453,7 @@ read_again:
ptr += 12;
break;
case 0:
- length = data2host4(perf_pevent, ptr);
+ length = data2host4(pevent, ptr);
ptr += 4;
die("here! length=%d", length);
break;
@@ -477,17 +478,17 @@ read_again:
return data;
}
-struct pevent_record *trace_read_data(int cpu)
+struct pevent_record *trace_read_data(struct pevent *pevent, int cpu)
{
struct pevent_record *data;
- data = trace_peek_data(cpu);
+ data = trace_peek_data(pevent, cpu);
cpu_data[cpu].next = NULL;
return data;
}
-ssize_t trace_report(int fd, bool __repipe)
+ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
{
char buf[BUFSIZ];
char test[] = { 23, 8, 68 };
@@ -519,30 +520,32 @@ ssize_t trace_report(int fd, bool __repipe)
file_bigendian = buf[0];
host_bigendian = bigendian();
- read_trace_init(file_bigendian, host_bigendian);
+ *ppevent = read_trace_init(file_bigendian, host_bigendian);
+ if (*ppevent == NULL)
+ die("read_trace_init failed");
read_or_die(buf, 1);
long_size = buf[0];
- page_size = read4();
+ page_size = read4(*ppevent);
- read_header_files();
+ read_header_files(*ppevent);
- read_ftrace_files();
- read_event_files();
- read_proc_kallsyms();
- read_ftrace_printk();
+ read_ftrace_files(*ppevent);
+ read_event_files(*ppevent);
+ read_proc_kallsyms(*ppevent);
+ read_ftrace_printk(*ppevent);
size = calc_data_size - 1;
calc_data_size = 0;
repipe = false;
if (show_funcs) {
- pevent_print_funcs(perf_pevent);
+ pevent_print_funcs(*ppevent);
return size;
}
if (show_printk) {
- pevent_print_printk(perf_pevent);
+ pevent_print_printk(*ppevent);
return size;
}
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 18ae6c1..474aa7a 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -36,6 +36,7 @@ static int stop_script_unsupported(void)
}
static void process_event_unsupported(union perf_event *event __unused,
+ struct pevent *pevent __unused,
struct perf_sample *sample __unused,
struct perf_evsel *evsel __unused,
struct machine *machine __unused,
@@ -61,7 +62,8 @@ static int python_start_script_unsupported(const char *script __unused,
return -1;
}
-static int python_generate_script_unsupported(const char *outfile __unused)
+static int python_generate_script_unsupported(struct pevent *pevent __unused,
+ const char *outfile __unused)
{
print_python_unsupported_msg();
@@ -122,7 +124,8 @@ static int perl_start_script_unsupported(const char *script __unused,
return -1;
}
-static int perl_generate_script_unsupported(const char *outfile __unused)
+static int perl_generate_script_unsupported(struct pevent *pevent __unused,
+ const char *outfile __unused)
{
print_perl_unsupported_msg();
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 639852a..8fef1d6 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -8,6 +8,7 @@
struct machine;
struct perf_sample;
union perf_event;
+struct perf_tool;
struct thread;
extern int header_page_size_size;
@@ -29,35 +30,36 @@ enum {
int bigendian(void);
-int read_trace_init(int file_bigendian, int host_bigendian);
-void print_trace_event(int cpu, void *data, int size);
+struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
+void print_trace_event(struct pevent *pevent, int cpu, void *data, int size);
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
- char *comm);
+void print_event(struct pevent *pevent, int cpu, void *data, int size,
+ unsigned long long nsecs, char *comm);
-int parse_ftrace_file(char *buf, unsigned long size);
-int parse_event_file(char *buf, unsigned long size, char *sys);
+int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size);
+int parse_event_file(struct pevent *pevent,
+ char *buf, unsigned long size, char *sys);
-struct pevent_record *trace_peek_data(int cpu);
-struct event_format *trace_find_event(int type);
+struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu);
unsigned long long
raw_field_value(struct event_format *event, const char *name, void *data);
void *raw_field_ptr(struct event_format *event, const char *name, void *data);
-void parse_proc_kallsyms(char *file, unsigned int size __unused);
-void parse_ftrace_printk(char *file, unsigned int size __unused);
+void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
+void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
-ssize_t trace_report(int fd, bool repipe);
+ssize_t trace_report(int fd, struct pevent **pevent, bool repipe);
-int trace_parse_common_type(void *data);
-int trace_parse_common_pid(void *data);
+int trace_parse_common_type(struct pevent *pevent, void *data);
+int trace_parse_common_pid(struct pevent *pevent, void *data);
-struct event_format *trace_find_next_event(struct event_format *event);
-unsigned long long read_size(void *ptr, int size);
+struct event_format *trace_find_next_event(struct pevent *pevent,
+ struct event_format *event);
+unsigned long long read_size(struct pevent *pevent, void *ptr, int size);
unsigned long long eval_flag(const char *flag);
-struct pevent_record *trace_read_data(int cpu);
+struct pevent_record *trace_read_data(struct pevent *pevent, int cpu);
int read_tracing_data(int fd, struct list_head *pattrs);
struct tracing_data {
@@ -77,11 +79,12 @@ struct scripting_ops {
int (*start_script) (const char *script, int argc, const char **argv);
int (*stop_script) (void);
void (*process_event) (union perf_event *event,
+ struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine,
struct thread *thread);
- int (*generate_script) (const char *outfile);
+ int (*generate_script) (struct pevent *pevent, const char *outfile);
};
int script_spec_register(const char *spec, struct scripting_ops *ops);
@@ -90,6 +93,7 @@ void setup_perl_scripting(void);
void setup_python_scripting(void);
struct scripting_context {
+ struct pevent *pevent;
void *event_data;
};
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 2daaedb..b13c733 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -264,4 +264,6 @@ bool is_power_of_2(unsigned long n)
size_t hex_width(u64 v);
+char *rtrim(char *s);
+
#endif
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists