kybaaz/linux-xiaomi-chiron
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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

Browse source 
Pull perf updates from Ingo Molnar:
 "Features:

   - Add "uretprobes" - an optimization to uprobes, like kretprobes are
     an optimization to kprobes.  "perf probe -x file sym%return" now
     works like kretprobes.  By Oleg Nesterov.

   - Introduce per core aggregation in 'perf stat', from Stephane
     Eranian.

   - Add memory profiling via PEBS, from Stephane Eranian.

   - Event group view for 'annotate' in --stdio, --tui and --gtk, from
     Namhyung Kim.

   - Add support for AMD NB and L2I "uncore" counters, by Jacob Shin.

   - Add Ivy Bridge-EP uncore support, by Zheng Yan

   - IBM zEnterprise EC12 oprofile support patchlet from Robert Richter.

   - Add perf test entries for checking breakpoint overflow signal
     handler issues, from Jiri Olsa.

   - Add perf test entry for for checking number of EXIT events, from
     Namhyung Kim.

   - Add perf test entries for checking --cpu in record and stat, from
     Jiri Olsa.

   - Introduce perf stat --repeat forever, from Frederik Deweerdt.

   - Add --no-demangle to report/top, from Namhyung Kim.

   - PowerPC fixes plus a couple of cleanups/optimizations in uprobes
     and trace_uprobes, by Oleg Nesterov.

  Various fixes and refactorings:

   - Fix dependency of the python binding wrt libtraceevent, from
     Naohiro Aota.

   - Simplify some perf_evlist methods and to allow 'stat' to share code
     with 'record' and 'trace', by Arnaldo Carvalho de Melo.

   - Remove dead code in related to libtraceevent integration, from
     Namhyung Kim.

   - Revert "perf sched: Handle PERF_RECORD_EXIT events" to get 'perf
     sched lat' back working, by Arnaldo Carvalho de Melo

   - We don't use Newt anymore, just plain libslang, by Arnaldo Carvalho
     de Melo.

   - Kill a bunch of die() calls, from Namhyung Kim.

   - Fix build on non-glibc systems due to libio.h absence, from Cody P
     Schafer.

   - Remove some perf_session and tracing dead code, from David Ahern.

   - Honor parallel jobs, fix from Borislav Petkov

   - Introduce tools/lib/lk library, initially just removing duplication
     among tools/perf and tools/vm.  from Borislav Petkov

  ... and many more I missed to list, see the shortlog and git log for
  more details."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (136 commits)
  perf/x86/intel/P4: Robistify P4 PMU types
  perf/x86/amd: Fix AMD NB and L2I "uncore" support
  perf/x86/amd: Remove old-style NB counter support from perf_event_amd.c
  perf/x86: Check all MSRs before passing hw check
  perf/x86/amd: Add support for AMD NB and L2I "uncore" counters
  perf/x86/intel: Add Ivy Bridge-EP uncore support
  perf/x86/intel: Fix SNB-EP CBO and PCU uncore PMU filter management
  perf/x86: Avoid kfree() in CPU_{STARTING,DYING}
  uprobes/perf: Avoid perf_trace_buf_prepare/submit if ->perf_events is empty
  uprobes/tracing: Don't pass addr=ip to perf_trace_buf_submit()
  uprobes/tracing: Change create_trace_uprobe() to support uretprobes
  uprobes/tracing: Make seq_printf() code uretprobe-friendly
  uprobes/tracing: Make register_uprobe_event() paths uretprobe-friendly
  uprobes/tracing: Make uprobe_{trace,perf}_print() uretprobe-friendly
  uprobes/tracing: Introduce is_ret_probe() and uretprobe_dispatcher()
  uprobes/tracing: Introduce uprobe_{trace,perf}_print() helpers
  uprobes/tracing: Generalize struct uprobe_trace_entry_head
  uprobes/tracing: Kill the pointless local_save_flags/preempt_count calls
  uprobes/tracing: Kill the pointless seq_print_ip_sym() call
  uprobes/tracing: Kill the pointless task_pt_regs() calls
  ...
This commit is contained in:
Linus Torvalds 2013-04-30 07:41:01 -07:00
commit e0972916e8
130 changed files with 5678 additions and 1716 deletions
Download patch file Download diff file Expand all files Collapse all files

6
include/linux/compiler.h
View file

@ -351,4 +351,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
*/
#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
#ifdef CONFIG_KPROBES
# define __kprobes __attribute__((__section__(".kprobes.text")))
#else
# define __kprobes
#endif
#endif /* __LINUX_COMPILER_H */

6
include/linux/kprobes.h
View file

@ -29,6 +29,7 @@
* <jkenisto@us.ibm.com> and Prasanna S Panchamukhi
* <prasanna@in.ibm.com> added function-return probes.
*/
#include <linux/compiler.h> /* for __kprobes */
#include <linux/linkage.h>
#include <linux/list.h>
#include <linux/notifier.h>
@ -49,16 +50,11 @@
#define KPROBE_REENTER 0x00000004
#define KPROBE_HIT_SSDONE 0x00000008
/* Attach to insert probes on any functions which should be ignored*/
#define __kprobes __attribute__((__section__(".kprobes.text")))
#else /* CONFIG_KPROBES */
typedef int kprobe_opcode_t;
struct arch_specific_insn {
int dummy;
};
#define __kprobes
#endif /* CONFIG_KPROBES */
struct kprobe;

24
include/linux/perf_event.h
View file

@ -21,7 +21,6 @@
*/
#ifdef CONFIG_PERF_EVENTS
# include <linux/cgroup.h>
# include <asm/perf_event.h>
# include <asm/local64.h>
#endif
@ -128,6 +127,7 @@ struct hw_perf_event {
int event_base_rdpmc;
int idx;
int last_cpu;
int flags;
struct hw_perf_event_extra extra_reg;
struct hw_perf_event_extra branch_reg;
@ -299,22 +299,7 @@ struct swevent_hlist {
#define PERF_ATTACH_GROUP 0x02
#define PERF_ATTACH_TASK 0x04
#ifdef CONFIG_CGROUP_PERF
/*
* perf_cgroup_info keeps track of time_enabled for a cgroup.
* This is a per-cpu dynamically allocated data structure.
*/
struct perf_cgroup_info {
u64 time;
u64 timestamp;
};
struct perf_cgroup {
struct cgroup_subsys_state css;
struct perf_cgroup_info *info; /* timing info, one per cpu */
};
#endif
struct perf_cgroup;
struct ring_buffer;
/**
@ -583,11 +568,13 @@ struct perf_sample_data {
u32 reserved;
} cpu_entry;
u64 period;
union perf_mem_data_src data_src;
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
struct perf_regs_user regs_user;
u64 stack_user_size;
u64 weight;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
@ -601,6 +588,8 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
data->regs_user.regs = NULL;
data->stack_user_size = 0;
data->weight = 0;
data->data_src.val = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
@ -831,6 +820,7 @@ do { \
struct perf_pmu_events_attr {
struct device_attribute attr;
u64 id;
const char *event_str;
};
#define PMU_EVENT_ATTR(_name, _var, _id, _show) \

8
include/linux/uprobes.h
View file

@ -38,6 +38,8 @@ struct inode;
#define UPROBE_HANDLER_REMOVE 1
#define UPROBE_HANDLER_MASK 1
#define MAX_URETPROBE_DEPTH 64
enum uprobe_filter_ctx {
UPROBE_FILTER_REGISTER,
UPROBE_FILTER_UNREGISTER,
@ -46,6 +48,9 @@ enum uprobe_filter_ctx {
struct uprobe_consumer {
int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs);
int (*ret_handler)(struct uprobe_consumer *self,
unsigned long func,
struct pt_regs *regs);
bool (*filter)(struct uprobe_consumer *self,
enum uprobe_filter_ctx ctx,
struct mm_struct *mm);
@ -68,6 +73,8 @@ struct uprobe_task {
enum uprobe_task_state state;
struct arch_uprobe_task autask;
struct return_instance *return_instances;
unsigned int depth;
struct uprobe *active_uprobe;
unsigned long xol_vaddr;
@ -100,6 +107,7 @@ struct uprobes_state {
extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);

71
include/uapi/linux/perf_event.h
View file

@ -132,8 +132,10 @@ enum perf_event_sample_format {
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
PERF_SAMPLE_REGS_USER = 1U << 12,
PERF_SAMPLE_STACK_USER = 1U << 13,
PERF_SAMPLE_WEIGHT = 1U << 14,
PERF_SAMPLE_DATA_SRC = 1U << 15,
PERF_SAMPLE_MAX = 1U << 14, /* non-ABI */
PERF_SAMPLE_MAX = 1U << 16, /* non-ABI */
};
/*
@ -443,6 +445,7 @@ struct perf_event_mmap_page {
#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0)
#define PERF_RECORD_MISC_GUEST_USER (5 << 0)
#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
/*
* Indicates that the content of PERF_SAMPLE_IP points to
* the actual instruction that triggered the event. See also
@ -588,6 +591,9 @@ enum perf_event_type {
* { u64 size;
* char data[size];
* u64 dyn_size; } && PERF_SAMPLE_STACK_USER
*
* { u64 weight; } && PERF_SAMPLE_WEIGHT
* { u64 data_src; } && PERF_SAMPLE_DATA_SRC
* };
*/
PERF_RECORD_SAMPLE = 9,
@ -613,4 +619,67 @@ enum perf_callchain_context {
#define PERF_FLAG_FD_OUTPUT (1U << 1)
#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */
union perf_mem_data_src {
__u64 val;
struct {
__u64 mem_op:5, /* type of opcode */
mem_lvl:14, /* memory hierarchy level */
mem_snoop:5, /* snoop mode */
mem_lock:2, /* lock instr */
mem_dtlb:7, /* tlb access */
mem_rsvd:31;
};
};
/* type of opcode (load/store/prefetch,code) */
#define PERF_MEM_OP_NA 0x01 /* not available */
#define PERF_MEM_OP_LOAD 0x02 /* load instruction */
#define PERF_MEM_OP_STORE 0x04 /* store instruction */
#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */
#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */
#define PERF_MEM_OP_SHIFT 0
/* memory hierarchy (memory level, hit or miss) */
#define PERF_MEM_LVL_NA 0x01 /* not available */
#define PERF_MEM_LVL_HIT 0x02 /* hit level */
#define PERF_MEM_LVL_MISS 0x04 /* miss level */
#define PERF_MEM_LVL_L1 0x08 /* L1 */
#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */
#define PERF_MEM_LVL_L2 0x20 /* L2 */
#define PERF_MEM_LVL_L3 0x40 /* L3 */
#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */
#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */
#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */
#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */
#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */
#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */
#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */
#define PERF_MEM_LVL_SHIFT 5
/* snoop mode */
#define PERF_MEM_SNOOP_NA 0x01 /* not available */
#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */
#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */
#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */
#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */
#define PERF_MEM_SNOOP_SHIFT 19
/* locked instruction */
#define PERF_MEM_LOCK_NA 0x01 /* not available */
#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */
#define PERF_MEM_LOCK_SHIFT 24
/* TLB access */
#define PERF_MEM_TLB_NA 0x01 /* not available */
#define PERF_MEM_TLB_HIT 0x02 /* hit level */
#define PERF_MEM_TLB_MISS 0x04 /* miss level */
#define PERF_MEM_TLB_L1 0x08 /* L1 */
#define PERF_MEM_TLB_L2 0x10 /* L2 */
#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/
#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */
#define PERF_MEM_TLB_SHIFT 26
#define PERF_MEM_S(a, s) \
(((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
#endif /* _UAPI_LINUX_PERF_EVENT_H */