#include <linux/perf_event.h>
       #include <linux/hw_breakpoint.h>

       int perf_event_open(struct perf_event_attr *attr,
                           pid_t pid, int cpu, int group_fd,
                           unsigned long flags);

       Note: There is no glibc wrapper for this system call; see NOTES.

       Given  a  list of parameters, perf_event_open() returns a file descrip-
       tor, for use in subsequent system calls  (read(2),  mmap(2),  prctl(2),
       fcntl(2), etc.).

       A  call to perf_event_open() creates a file descriptor that allows mea-
       suring performance information.  Each file  descriptor  corresponds  to
       one  event  that  is measured; these can be grouped together to measure
       multiple events simultaneously.

       Events can be enabled and disabled in two ways: via  ioctl(2)  and  via
       prctl(2).   When  an  event  is  disabled it does not count or generate
       overflows but does continue to exist and maintain its count value.

       Events come in two flavors: counting and sampled.  A counting event  is
       one  that  is  used  for  counting  the aggregate number of events that
       occur.  In general, counting event results are gathered with a  read(2)
       call.   A  sampling  event periodically writes measurements to a buffer
       that can then be accessed via mmap(2).

       The argument pid allows events to be attached to processes  in  various
       ways.   If  pid is 0, measurements happen on the current thread, if pid
       is greater than 0, the process indicated by pid is measured, and if pid
       is -1, all processes are counted.

       The  cpu  argument allows measurements to be specific to a CPU.  If cpu
       is greater than or equal to 0, measurements are restricted to the spec-
       ified CPU; if cpu is -1, the events are measured on all CPUs.

       Note that the combination of pid == -1 and cpu == -1 is not valid.

       A  pid  > 0 and cpu == -1 setting measures per-process and follows that
       process to whatever CPU the process  gets  scheduled  to.   Per-process
       events can be created by any user.

       A  pid == -1 and cpu >= 0 setting is per-CPU and measures all processes
       on the specified CPU.  Per-CPU events need the CAP_SYS_ADMIN capability
       or a /proc/sys/kernel/perf_event_paranoid value of less than 1.

       The  group_fd  argument  allows  event  groups to be created.  An event
       group has one event which is the group leader.  The leader  is  created
       first,  with  group_fd = -1.  The rest of the group members are created
              This flag allows creating an event as part of an event group but
              having no group leader.  It is unclear why this is useful.

              This  flag  re-routes  the  output  from  an  event to the group

       PERF_FLAG_PID_CGROUP (Since Linux 2.6.39).
              This flag activates  per-container  system-wide  monitoring.   A
              container is an abstraction that isolates a set of resources for
              finer grain control (CPUs, memory, etc.).   In  this  mode,  the
              event  is  measured  only if the thread running on the monitored
              CPU belongs to the designated container (cgroup).  The cgroup is
              identified  by passing a file descriptor opened on its directory
              in the cgroupfs filesystem.  For instance, if the cgroup to mon-
              itor   is   called  test,  then  a  file  descriptor  opened  on
              /dev/cgroup/test (assuming cgroupfs is mounted  on  /dev/cgroup)
              must  be  passed  as  the  pid  parameter.  cgroup monitoring is
              available only for system-wide events and may therefore  require
              extra permissions.

       The  perf_event_attr structure provides detailed configuration informa-
       tion for the event being created.

           struct perf_event_attr {
               __u32     type;         /* Type of event */
               __u32     size;         /* Size of attribute structure */
               __u64     config;       /* Type-specific configuration */

               union {
                   __u64 sample_period;    /* Period of sampling */
                   __u64 sample_freq;      /* Frequency of sampling */

               __u64     sample_type;  /* Specifies values included in sample */
               __u64     read_format;  /* Specifies values returned in read */

               __u64     disabled       : 1,   /* off by default */
                         inherit        : 1,   /* children inherit it */
                         pinned         : 1,   /* must always be on PMU */
                         exclusive      : 1,   /* only group on PMU */
                         exclude_user   : 1,   /* don't count user */
                         exclude_kernel : 1,   /* don't count kernel */
                         exclude_hv     : 1,   /* don't count hypervisor */
                         exclude_idle   : 1,   /* don't count when idle */
                         mmap           : 1,   /* include mmap data */
                         comm           : 1,   /* include comm data */
                         freq           : 1,   /* use freq, not period */
                         inherit_stat   : 1,   /* per task counts */
                         enable_on_exec : 1,   /* next exec enables */
                         task           : 1,   /* trace fork/exit */
                         watermark      : 1,   /* wakeup_watermark */
                         precise_ip     : 2,   /* skid constraint */

                   __u32 wakeup_watermark; /* bytes before wakeup */

               __u32     bp_type;          /* breakpoint type */

               union {
                   __u64 bp_addr;          /* breakpoint address */
                   __u64 config1;          /* extension of config */

               union {
                   __u64 bp_len;           /* breakpoint length */
                   __u64 config2;          /* extension of config1 */
               __u64   branch_sample_type; /* enum perf_branch_sample_type */
               __u64   sample_regs_user;   /* user regs to dump on samples */
               __u32   sample_stack_user;  /* size of stack to dump on
                                              samples */
               __u32   __reserved_2;       /* Align to u64 */


       The fields of the  perf_event_attr  structure  are  described  in  more
       detail below:

       type   This  field specifies the overall event type.  It has one of the
              following values:

                     This indicates one of the "generalized"  hardware  events
                     provided  by the kernel.  See the config field definition
                     for more details.

                     This indicates one of the  software-defined  events  pro-
                     vided  by  the  kernel  (even  if  no hardware support is

                     This indicates a tracepoint provided by the kernel trace-
                     point infrastructure.

                     This  indicates  a hardware cache event.  This has a spe-
                     cial encoding, described in the config field definition.

                     This indicates a "raw" implementation-specific  event  in
                     the config field.

              PERF_TYPE_BREAKPOINT (Since Linux 2.6.33)
                     This  indicates  a hardware breakpoint as provided by the
                     CPU.   Breakpoints  can  be  read/write  accesses  to  an
                     address as well as execution of an instruction address.

       size   The size of the perf_event_attr structure  for  forward/backward
              compatibility.  Set this using sizeof(struct perf_event_attr) to
              allow the kernel to see the struct size at the time of  compila-

              The  related  define  PERF_ATTR_SIZE_VER0 is set to 64; this was
              the size of the first published struct.  PERF_ATTR_SIZE_VER1  is
              72,  corresponding  to  the  addition  of  breakpoints  in Linux
              2.6.33.  PERF_ATTR_SIZE_VER2 is 80 corresponding to the addition
              of  branch sampling in Linux 3.4.  PERF_ATR_SIZE_VER3 is 96 cor-
              responding  to  the  addition  of  sample_regs_user   and   sam-
              ple_stack_user in Linux 3.7.

       config This  specifies  which  event  you want, in conjunction with the
              type field.  The config1 and config2 fields are also taken  into
              account  in  cases  where 64 bits is not enough to fully specify
              the event.  The encoding of these fields are event dependent.

              The most significant bit (bit 63) of config  signifies  CPU-spe-
              cific  (raw) counter configuration data; if the most significant
              bit is unset, the next 7 bits are an event type and the rest  of
              the bits are the event identifier.

              There  are  various ways to set the config field that are depen-
              dent on the value of the previously described type field.   What
              follows  are  various possible settings for config separated out
              by type.

              If type is PERF_TYPE_HARDWARE, we are measuring one of the  gen-
              eralized hardware CPU events.  Not all of these are available on
              all platforms.  Set config to one of the following:

                          Total cycles.  Be wary of what  happens  during  CPU
                          frequency scaling.

                          Retired  instructions.   Be  careful,  these  can be
                          affected by various issues,  most  notably  hardware
                          interrupt counts.

                          Cache  accesses.   Usually this indicates Last Level
                          Cache accesses but this may vary depending  on  your
                          CPU.  This may include prefetches and coherency mes-
                          sages; again this depends on the design of your CPU.

                          Cache misses.  Usually  this  indicates  Last  Level
                          Cache  misses;  this  is intended to be used in con-
                          junction  with  the   PERF_COUNT_HW_CACHE_REFERENCES
                          event to calculate cache miss rates.

                          Stalled cycles during issue.

                   PERF_COUNT_HW_STALLED_CYCLES_BACKEND (Since Linux 3.0)
                          Stalled cycles during retirement.

                   PERF_COUNT_HW_REF_CPU_CYCLES (Since Linux 3.3)
                          Total cycles; not affected by CPU frequency scaling.

              If  type is PERF_TYPE_SOFTWARE, we are measuring software events
              provided by the kernel.  Set config to one of the following:

                          This reports the CPU clock, a  high-resolution  per-
                          CPU timer.

                          This reports a clock count specific to the task that
                          is running.

                          This reports the number of page faults.

                          This counts context switches.  Until  Linux  2.6.34,
                          these  were all reported as user-space events, after
                          that they are reported as happening in the kernel.

                          This reports the number of  times  the  process  has
                          migrated to a new CPU.

                          This  counts the number of minor page faults.  These
                          did not require disk I/O to handle.

                          This counts the number of major page faults.   These
                          required disk I/O to handle.

                   PERF_COUNT_SW_ALIGNMENT_FAULTS (Since Linux 2.6.33)
                          This  counts  the number of alignment faults.  These
                          happen when unaligned memory  accesses  happen;  the
                          kernel  can handle these but it reduces performance.
                          This happens only on some  architectures  (never  on

                   PERF_COUNT_SW_EMULATION_FAULTS (Since Linux 2.6.33)
                          This  counts  the  number  of emulation faults.  The
                          kernel sometimes traps on unimplemented instructions
                          and  emulates  them  for user space.  This can nega-
                          tively impact performance.

              If type is PERF_TYPE_TRACEPOINT, then we  are  measuring  kernel
              tracepoints.   The  value  to use in config can be obtained from
                             for measuring Level 1 Data Cache

                             for measuring Level 1 Instruction Cache

                             for measuring Last-Level Cache

                             for measuring the Data TLB

                             for measuring the Instruction TLB

                             for measuring the branch prediction unit

                      PERF_COUNT_HW_CACHE_NODE (Since Linux 3.0)
                             for measuring local memory accesses

                  and perf_hw_cache_op_id is one of

                             for read accesses

                             for write accesses

                             for prefetch accesses

                  and perf_hw_cache_op_result_id is one of

                             to measure accesses

                             to measure misses

              If  type  is  PERF_TYPE_RAW, then a custom "raw" config value is
              needed.  Most CPUs support events that are not  covered  by  the
              "generalized"  events.   These  are  implementation defined; see
              your CPU manual (for example the Intel Volume  3B  documentation
              or  the  AMD  BIOS  and  Kernel  Developer  Guide).  The libpfm4
              library can be used to translate from the name in the  architec-
              tural  manuals to the raw hex value perf_event_open() expects in
              this field.

              If type is PERF_TYPE_BREAKPOINT, then leave config set to  zero.
              Its parameters are set in other places.

       sample_period, sample_freq
              A  "sampling" counter is one that generates an interrupt every N
              in the sample.  They will be recorded in a ring-buffer, which is
              available to user space using mmap(2).  The order in  which  the
              values are saved in the sample are documented in the MMAP Layout
              subsection below; it is not  the  enum  perf_event_sample_format

                     Records instruction pointer.

                     Records the process and thread IDs.

                     Records a timestamp.

                     Records an address, if applicable.

                     Record counter values for all events in a group, not just
                     the group leader.

                     Records the callchain (stack backtrace).

                     Records a unique ID for the opened event's group leader.

                     Records CPU number.

                     Records the current sampling period.

                     Records  a  unique  ID  for  the  opened  event.   Unlike
                     PERF_SAMPLE_ID  the  actual ID is returned, not the group
                     leader.  This ID is the  same  as  the  one  returned  by

                     Records additional data, if applicable.  Usually returned
                     by tracepoint events.

              PERF_SAMPLE_BRANCH_STACK (Since Linux 3.4)
                     This provides a record of recent branches, as provided by
                     CPU  branch  sampling hardware (such as Intel Last Branch
                     Record).  Not all hardware supports this feature.

                     See the branch_sample_type field for how to filter  which
                     branches are reported.

              PERF_SAMPLE_REGS_USER (Since Linux 3.7)
                     Records  the  current  user-level CPU register state (the
                     the  data  associated  with  the sampled instruction came
                     from.  This is only available if the underlying  hardware
                     supports this feature.

              This  field specifies the format of the data returned by read(2)
              on a perf_event_open() file descriptor.

                     Adds the 64-bit time_enabled field.  This can be used  to
                     calculate  estimated  totals  if the PMU is overcommitted
                     and multiplexing is happening.

                     Adds the 64-bit time_running field.  This can be used  to
                     calculate  estimated  totals  if the PMU is overcommitted
                     and  multiplexing is happening.

                     Adds a 64-bit unique value that corresponds to the  event

                     Allows  all  counter  values in an event group to be read
                     with one read.

              The disabled bit specifies whether the counter starts  out  dis-
              abled  or  enabled.  If disabled, the event can later be enabled
              by ioctl(2), prctl(2), or enable_on_exec.

              The inherit bit specifies that this counter should count  events
              of child tasks as well as the task specified.  This applies only
              to new children, not to any existing children at  the  time  the
              counter  is  created  (nor to any new children of existing chil-

              Inherit does not work for  some  combinations  of  read_formats,
              such as PERF_FORMAT_GROUP.

       pinned The  pinned  bit  specifies that the counter should always be on
              the CPU if at all possible.  It applies only to  hardware  coun-
              ters  and  only to group leaders.  If a pinned counter cannot be
              put onto the CPU (e.g., because there are  not  enough  hardware
              counters  or  because of a conflict with some other event), then
              the counter goes into an 'error' state, where reads return  end-
              of-file  (i.e.,  read(2)  returns 0) until the counter is subse-
              quently enabled or disabled.

              The exclusive bit specifies that when this counter's group is on
              the  CPU,  it should be the only group using the CPU's counters.
              In the future this may allow monitoring programs to support  PMU
              If this bit is set, the count excludes events that happen in the
              hypervisor.   This is mainly for PMUs that have built-in support
              for handling this (such as POWER).  Extra support is needed  for
              handling hypervisor measurements on most machines.

              If set, don't count when the CPU is idle.

       mmap   The mmap bit enables recording of exec mmap events.

       comm   The  comm  bit enables tracking of process command name as modi-
              fied by the exec(2) and prctl(PR_SET_NAME) system calls.  Unfor-
              tunately  for  tools,  there is no way to distinguish one system
              call versus the other.

       freq   If this bit is set, then sample_frequency not  sample_period  is
              used when setting up the sampling interval.

              This  bit  enables  saving of event counts on context switch for
              inherited tasks.  This is meaningful only if the  inherit  field
              is set.

              If  this  bit is set, a counter is automatically enabled after a
              call to exec(2).

       task   If this bit is set, then fork/exit notifications are included in
              the ring buffer.

              If  set,  have  a  sampling  interrupt  happen when we cross the
              wakeup_watermark boundary.  Otherwise  interrupts  happen  after
              wakeup_events samples.

       precise_ip (Since Linux 2.6.35)
              This controls the amount of skid.  Skid is how many instructions
              execute between an event of interest happening  and  the  kernel
              being able to stop and record the event.  Smaller skid is better
              and allows more accurate reporting of which events correspond to
              which instructions, but hardware is often limited with how small
              this can be.

              The values of this are the following:

              0 -    SAMPLE_IP can have arbitrary skid.

              1 -    SAMPLE_IP must have constant skid.

              2 -    SAMPLE_IP requested to have 0 skid.

              3 -    SAMPLE_IP    must    have    0    skid.      See     also

       exclude_guest (Since Linux 3.2)
              Do not measure time spent in VM guest.

       exclude_callchain_kernel (Since Linux 3.7)
              Do not include kernel callchains.

       exclude_callchain_user (Since Linux 3.7)
              Do not include user callchains.

       wakeup_events, wakeup_watermark
              This union  sets  how  many  samples  (wakeup_events)  or  bytes
              (wakeup_watermark)  happen  before  an  overflow signal happens.
              Which one is used is selected by the watermark bitflag.

              wakeup_events only counts PERF_RECORD_SAMPLE record  types.   To
              receive  a  signal  for  every  incoming  PERF_RECORD  type  set
              wakeup_watermark to 1.

       bp_type (Since Linux 2.6.33)
              This chooses the breakpoint type.  It is one of:

                     No breakpoint.

                     Count when we read the memory location.

                     Count when we write the memory location.

                     Count when we read or write the memory location.

                     Count when we execute code at the memory location.

              The values can be combined via a bitwise or, but the combination
              of  HW_BREAKPOINT_R  or  HW_BREAKPOINT_W with HW_BREAKPOINT_X is
              not allowed.

       bp_addr (Since Linux 2.6.33)
              bp_addr address of the breakpoint.   For  execution  breakpoints
              this  is  the memory address of the instruction of interest; for
              read and write breakpoints it is the memory address of the  mem-
              ory location of interest.

       config1 (Since Linux 2.6.39)
              config1  is  used for setting events that need an extra register
              or otherwise do not fit in the regular config field.   Raw  OFF-
              CORE_EVENTS  on  Nehalem/Westmere/SandyBridge  use this field on
              3.3 and later kernels.

       bp_len (Since Linux 2.6.33)
              bp_len is the length of the breakpoint being measured if type is
              The first part of the value is the privilege level, which  is  a
              combination  of  one  of the following values.  If the user does
              not set privilege level explicitly,  the  kernel  will  use  the
              event's  privilege  level.  Event and branch privilege levels do
              not have to match.

                     Branch target is in user space.

                     Branch target is in kernel space.

                     Branch target is in hypervisor.

                     A convenience value that is the  three  preceding  values
                     ORed together.

              In  addition to the privilege value, at least one or more of the
              following bits must be set.

                     Any branch type.

                     Any call branch.

                     Any return branch.

                     Indirect calls.

              PERF_SAMPLE_BRANCH_ABORT_TX (Since Linux 3.11)
                     Transactional memory aborts.

              PERF_SAMPLE_BRANCH_IN_TX (Since Linux 3.11)
                     Branch in transactional memory transaction.

              PERF_SAMPLE_BRANCH_NO_TX (Since Linux 3.11)
                     Branch not in transactional memory transaction.

       sample_regs_user (Since Linux 3.7)
              This bitmask defines the set of user CPU registers  to  dump  on
              samples.   The  layout of the register mask is architecture spe-
              cific     and     described     in     the     kernel     header

       sample_stack_user (Since Linux 3.7)
              This  defines  the  size  of the user stack to dump if PERF_SAM-

       * If PERF_FORMAT_GROUP was specified to allow reading all events  in  a
         group at once:

             struct read_format {
                 u64 nr;            /* The number of events */
                 u64 time_enabled;  /* if PERF_FORMAT_TOTAL_TIME_ENABLED */
                 u64 time_running;  /* if PERF_FORMAT_TOTAL_TIME_RUNNING */
                     u64 value;     /* The value of the event */
                     u64 id;        /* if PERF_FORMAT_ID */
                 } values[nr];

       * If PERF_FORMAT_GROUP was not specified:

             struct read_format {
                 u64 value;         /* The value of the event */
                 u64 time_enabled;  /* if PERF_FORMAT_TOTAL_TIME_ENABLED */
                 u64 time_running;  /* if PERF_FORMAT_TOTAL_TIME_RUNNING */
                 u64 id;            /* if PERF_FORMAT_ID */

       The values read are as follows:

       nr     The number of events in this file descriptor.  Only available if
              PERF_FORMAT_GROUP was specified.

       time_enabled, time_running
              Total time the event was enabled and  running.   Normally  these
              are the same.  If more events are started than available counter
              slots on the PMU, then multiplexing happens and events run  only
              part  of  the time.  In that case the time_enabled and time run-
              ning values can be used to scale  an  estimated  value  for  the

       value  An unsigned 64-bit value containing the counter result.

       id     A globally unique value for this particular event, only there if
              PERF_FORMAT_ID was specified in read_format.

   MMAP layout
       When using perf_event_open() in sampled mode, asynchronous events (like
       counter  overflow  or  PROT_EXEC mmap tracking) are logged into a ring-
       buffer.  This ring-buffer is created and accessed through mmap(2).

       The mmap size should be 1+2^n pages, where the first page is a metadata
       page (struct perf_event_mmap_page) that contains various bits of infor-
       mation such as where the ring-buffer head is.

       Before kernel 2.6.39, there is a bug that means  you  must  allocate  a
       mmap ring buffer when sampling even if you do not plan to access it.

       The structure of the first metadata mmap page is as follows:
                           cap_usr_rdpmc : 1,
               __u16   pmc_width;
               __u16   time_shift;
               __u32   time_mult;
               __u64   time_offset;
               __u64   __reserved[120];   /* Pad to 1k */
               __u64   data_head;         /* head in the data section */
               __u64   data_tail;         /* user-space written tail */

       The following looks at the fields in the perf_event_mmap_page structure
       in more detail:

              Version number of this structure.

              The lowest version this is compatible with.

       lock   A seqlock for synchronization.

       index  A unique hardware counter identifier.

       offset Add this to hardware counter value??

              Time the event was active.

              Time the event was running.

              User time capability.

              If the hardware supports user-space read of performance counters
              without  syscall  (this is the "rdpmc" instruction on x86), then
              the following code can be used to do a read:

                  u32 seq, time_mult, time_shift, idx, width;
                  u64 count, enabled, running;
                  u64 cyc, time_offset;
                  s64 pmc = 0;

                  do {
                      seq = pc->lock;
                      enabled = pc->time_enabled;
                      running = pc->time_running;

                      if (pc->cap_usr_time && enabled != running) {
                          cyc = rdtsc();
                          time_offset = pc->time_offset;

                  } while (pc->lock != seq);

              If cap_usr_rdpmc, this field provides the bit-width of the value
              read  using  the  rdpmc  or equivalent instruction.  This can be
              used to sign extend the result like:

                  pmc <<= 64 - pmc_width;
                  pmc >>= 64 - pmc_width; // signed shift right
                  count += pmc;

       time_shift, time_mult, time_offset

              If cap_usr_time, these fields can be used to  compute  the  time
              delta  since  time_enabled (in nanoseconds) using rdtsc or simi-

                  u64 quot, rem;
                  u64 delta;
                  quot = (cyc >> time_shift);
                  rem = cyc & ((1 << time_shift) - 1);
                  delta = time_offset + quot * time_mult +
                          ((rem * time_mult) >> time_shift);

              Where time_offset, time_mult, time_shift, and cyc  are  read  in
              the seqcount loop described above.  This delta can then be added
              to enabled and possible running (if idx), improving the scaling:

                  enabled += delta;
                  if (idx)
                      running += delta;
                  quot = count / running;
                  rem  = count % running;
                  count = quot * enabled + (rem * enabled) / running;

              This points to the head of the data section.  The value continu-
              ously  increases, it does not wrap.  The value needs to be manu-
              ally wrapped by the size of the mmap buffer before accessing the

              On  SMP-capable  platforms,  after  reading the data_head value,
              user space should issue an rmb().

              When the mapping is PROT_WRITE, the data_tail  value  should  be
              written  by  user  space to reflect the last read data.  In this
              case the kernel will not over-write unread data.

       The following 2^n ring-buffer pages have the layout described below.

       If perf_event_attr.sample_id_all is set, then all event types will have
       the  sample_type  selected  fields  related to where/when (identity) an
               __u16   size;

       Below,  we  describe  the perf_event_header fields in more detail.  For
       ease of reading, the fields with  shorter  descriptions  are  presented

       size   This indicates the size of the record.

       misc   The misc field contains additional information about the sample.

              The  CPU  mode can be determined from this value by masking with
              PERF_RECORD_MISC_CPUMODE_MASK and looking for one of the follow-
              ing  (note  these  are  not  bit masks, only one can be set at a

                     Unknown CPU mode.

                     Sample happened in the kernel.

                     Sample happened in user code.

                     Sample happened in the hypervisor.

                     Sample happened in the guest kernel.

                     Sample happened in guest user code.

              In addition, one of the following bits can be set:

                     This is set when the mapping is not executable; otherwise
                     the mapping is executable.

                     This  indicates that the content of PERF_SAMPLE_IP points
                     to the actual instruction that triggered the event.   See
                     also perf_event_attr.precise_ip.

                     This  indicates  there  is  extended data available (cur-
                     rently not used).

       type   The type value is one of the below.  The values  in  the  corre-
              sponding  record  (that  follows  the header) depend on the type
              selected as shown.


                  This record indicates when events are lost.

                      struct {
                          struct perf_event_header header;
                          u64 id;
                          u64 lost;

                  id     is the unique event ID  for  the  samples  that  were

                  lost   is the number of events that were lost.

                  This record indicates a change in the process name.

                      struct {
                          struct perf_event_header header;
                          u32 pid, tid;
                          char comm[];

                  This record indicates a process exit event.

                      struct {
                          struct perf_event_header header;
                          u32 pid, ppid;
                          u32 tid, ptid;
                          u64 time;

                  This record indicates a throttle/unthrottle event.

                      struct {
                          struct perf_event_header header;
                          u64 time;
                          u64 id;
                          u64 stream_id;

                  This record indicates a fork event.

                      struct {
                          struct perf_event_header header;
                          u32 pid, ppid;
                          u32 tid, ptid;
                          u64 time;

                      struct {
                          struct perf_event_header header;
                          u64   ip;         /* if PERF_SAMPLE_IP */
                          u32   pid, tid;   /* if PERF_SAMPLE_TID */
                          u64   time;       /* if PERF_SAMPLE_TIME */
                          u64   addr;       /* if PERF_SAMPLE_ADDR */
                          u64   id;         /* if PERF_SAMPLE_ID */
                          u64   stream_id;  /* if PERF_SAMPLE_STREAM_ID */
                          u32   cpu, res;   /* if PERF_SAMPLE_CPU */
                          u64   period;     /* if PERF_SAMPLE_PERIOD */
                          struct read_format v; /* if PERF_SAMPLE_READ */
                          u64   nr;         /* if PERF_SAMPLE_CALLCHAIN */
                          u64   ips[nr];    /* if PERF_SAMPLE_CALLCHAIN */
                          u32   size;       /* if PERF_SAMPLE_RAW */
                          char  data[size]; /* if PERF_SAMPLE_RAW */
                          u64   bnr;        /* if PERF_SAMPLE_BRANCH_STACK */
                          struct perf_branch_entry lbr[bnr];
                                            /* if PERF_SAMPLE_BRANCH_STACK */
                          u64   abi;        /* if PERF_SAMPLE_REGS_USER */
                          u64   regs[weight(mask)];
                                            /* if PERF_SAMPLE_REGS_USER */
                          u64   size;       /* if PERF_SAMPLE_STACK_USER */
                          char  data[size]; /* if PERF_SAMPLE_STACK_USER */
                          u64   dyn_size;   /* if PERF_SAMPLE_STACK_USER */
                          u64   weight;     /* if PERF_SAMPLE_WEIGHT */
                          u64   data_src;   /* if PERF_SAMPLE_DATA_SRC */

                  ip  If  PERF_SAMPLE_IP is enabled, then a 64-bit instruction
                      pointer value is included.

                  pid, tid
                      If PERF_SAMPLE_TID is enabled, then a 32-bit process  ID
                      and 32-bit thread ID are included.

                      If  PERF_SAMPLE_TIME is enabled, then a 64-bit timestamp
                      is included.  This is obtained via  local_clock()  which
                      is  a  hardware  timestamp  if available and the jiffies
                      value if not.

                      If PERF_SAMPLE_ADDR is enabled, then a 64-bit address is
                      included.   This is usually the address of a tracepoint,
                      breakpoint, or software event; otherwise the value is 0.

                  id  If PERF_SAMPLE_ID is enabled,  a  64-bit  unique  ID  is
                      included.   If  the event is a member of an event group,
                      the group leader ID is returned.  This ID is the same as
                      the one returned by PERF_FORMAT_ID.

                      If  PERF_SAMPLE_STREAM_ID is enabled, a 64-bit unique ID
                      is included.  Unlike PERF_SAMPLE_ID  the  actual  ID  is

                  v   If  PERF_SAMPLE_READ  is  enabled,  a  structure of type
                      read_format is included which has values for all  events
                      in  the  event group.  The values included depend on the
                      read_format value used at perf_event_open() time.

                  nr, ips[nr]
                      If PERF_SAMPLE_CALLCHAIN is enabled, then a 64-bit  num-
                      ber  is  included  which  indicates  how  many following
                      64-bit instruction pointers will follow.   This  is  the
                      current callchain.

                  size, data[size]
                      If PERF_SAMPLE_RAW is enabled, then a 32-bit value indi-
                      cating size is included followed by an  array  of  8-bit
                      values  of length size.  The values are padded with 0 to
                      have 64-bit alignment.

                      This RAW record data is opaque with respect to the  ABI.
                      The  ABI  doesn't  make any promises with respect to the
                      stability of its  content,  it  may  vary  depending  on
                      event, hardware, and kernel version.

                  bnr, lbr[bnr]
                      If  PERF_SAMPLE_BRANCH_STACK  is  enabled, then a 64-bit
                      value indicating the number of records is included, fol-
                      lowed  by  bnr  perf_branch_entry  structures which each
                      include the fields:

                      from   This indicates the source instruction (may not be
                             a branch).

                      to     The branch target.

                             The branch target was mispredicted.

                             The branch target was predicted.

                      in_tx (Since Linux 3.11)
                             The branch was in a transactional memory transac-

                      abort (Since Linux 3.11)
                             The branch was in an aborted transactional memory

                      The  entries are from most to least recent, so the first
                      entry has the most recent branch.

                      Support for mispred and predicted is  optional;  if  not
                      supported, both values will be 0.

                      were  specified by the sample_regs_user attr field.  The
                      number of values is the number of bits set in  the  sam-
                      ple_regs_user bitmask.

                  size, data[size], dyn_size
                      If  PERF_SAMPLE_STACK_USER  is  enabled, then record the
                      user stack to enable  backtracing.   size  is  the  size
                      requested  by  the  user  in stack_user_size or else the
                      maximum record size.  data is the stack data.   dyn_size
                      is  the amount of data actually dumped (can be less than

                      If PERF_SAMPLE_WEIGHT is enabled, then a  64  bit  value
                      provided  by the hardware is recorded that indicates how
                      costly the event was.  This allows expensive  events  to
                      stand out more clearly in profiles.

                      If  PERF_SAMPLE_DATA_SRC is enabled, then a 64 bit value
                      is recorded that is made up of the following fields:

                          Type of opcode, a bitwise combination of:

                          PERF_MEM_OP_NA          Not available
                          PERF_MEM_OP_LOAD        Load instruction
                          PERF_MEM_OP_STORE       Store instruction
                          PERF_MEM_OP_PFETCH      Prefetch
                          PERF_MEM_OP_EXEC        Executable code

                          Memory hierarchy level hit or miss, a bitwise combi-
                          nation of:

                          PERF_MEM_LVL_NA         Not available
                          PERF_MEM_LVL_HIT        Hit
                          PERF_MEM_LVL_MISS       Miss
                          PERF_MEM_LVL_L1         Level 1 cache
                          PERF_MEM_LVL_LFB        Line fill buffer
                          PERF_MEM_LVL_L2         Level 2 cache
                          PERF_MEM_LVL_L3         Level 3 cache
                          PERF_MEM_LVL_LOC_RAM    Local DRAM
                          PERF_MEM_LVL_REM_RAM1   Remote DRAM 1 hop
                          PERF_MEM_LVL_REM_RAM2   Remote DRAM 2 hops
                          PERF_MEM_LVL_REM_CCE1   Remote cache 1 hop
                          PERF_MEM_LVL_REM_CCE2   Remote cache 2 hops
                          PERF_MEM_LVL_IO         I/O memory
                          PERF_MEM_LVL_UNC        Uncached memory

                          Snoop mode, a bitwise combination of:

                          PERF_MEM_SNOOP_NA       Not available
                          TLB access hit or miss, a bitwise combination of:

                          PERF_MEM_TLB_NA         Not available
                          PERF_MEM_TLB_HIT        Hit
                          PERF_MEM_TLB_MISS       Miss
                          PERF_MEM_TLB_L1         Level 1 TLB
                          PERF_MEM_TLB_L2         Level 2 TLB
                          PERF_MEM_TLB_WK         Hardware walker
                          PERF_MEM_TLB_OS         OS fault handler

   Signal overflow
       Events can be set to deliver a signal when a threshold is crossed.  The
       signal handler is set up using the  poll(2),  select(2),  epoll(2)  and
       fcntl(2), system calls.

       To  generate signals, sampling must be enabled (sample_period must have
       a non-zero value).

       There are two ways to generate signals.

       The first is to set a wakeup_events or wakeup_watermark value that will
       generate  a  signal  if  a certain number of samples or bytes have been
       written to the mmap ring buffer.  In this case a signal of type POLL_IN
       is sent.

       The  other  way  is  by  use of the PERF_EVENT_IOC_REFRESH ioctl.  This
       ioctl adds to a counter that decrements each time the event  overflows.
       When non-zero, a POLL_IN signal is sent on overflow, but once the value
       reaches 0, a signal is sent of type POLL_HUP and the  underlying  event
       is disabled.

       Note:  on  newer kernels (definitely noticed with 3.2) a signal is pro-
       vided for every overflow, even if wakeup_events is not set.

   rdpmc instruction
       Starting with Linux 3.4 on x86, you can use the  rdpmc  instruction  to
       get  low-latency  reads  without having to enter the kernel.  Note that
       using rdpmc is not necessarily faster than other  methods  for  reading
       event values.

       Support  for  this  can be detected with the cap_usr_rdpmc field in the
       mmap page; documentation on how to calculate event values can be  found
       in that section.

   perf_event ioctl calls
       Various ioctls act on perf_event_open() file descriptors

              Enables  the  individual  event  or event group specified by the
              file descriptor argument.

              If the PERF_IOC_FLAG_GROUP bit is set  in  the  ioctl  argument,
              then all events in a group are enabled, even if the event speci-
              fied is not the group leader (but see BUGS).
              If the PERF_IOC_FLAG_GROUP bit is set  in  the  ioctl  argument,
              then all events in a group are disabled, even if the event spec-
              ified is not the group leader (but see BUGS).

              Non-inherited overflow counters can use this to enable a counter
              for a number of overflows specified by the argument, after which
              it is disabled.  Subsequent calls of this ioctl add the argument
              value to the current count.  A signal with POLL_IN set will hap-
              pen on each overflow until the count reaches 0; when  that  hap-
              pens  a  signal  with POLL_HUP set is sent and the event is dis-
              abled.  Using an argument of 0 is considered undefined behavior.

              Reset the event count specified by the file descriptor  argument
              to  zero.  This resets only the counts; there is no way to reset
              the multiplexing time_enabled or time_running values.

              If the PERF_IOC_FLAG_GROUP bit is set  in  the  ioctl  argument,
              then  all  events in a group are reset, even if the event speci-
              fied is not the group leader (but see BUGS).

              IOC_PERIOD is the command to update  the  period;  it  does  not
              update the current period but instead defers until next.

              The  argument  is  a  pointer  to  a 64-bit value containing the
              desired new period.

              This tells the kernel to report event notifications to the spec-
              ified  file  descriptor  rather  than the default one.  The file
              descriptors must all be on the same CPU.

              The argument specifies the desired file  descriptor,  or  -1  if
              output should be ignored.

       PERF_EVENT_IOC_SET_FILTER (Since Linux 2.6.33)
              This adds an ftrace filter to this event.

              The argument is a pointer to the desired ftrace filter.

   Using prctl
       A  process can enable or disable all the event groups that are attached
       to   it   using    the    prctl(2)    PR_TASK_PERF_EVENTS_ENABLE    and
       PR_TASK_PERF_EVENTS_DISABLE  operations.   This applies to all counters
       on the current process, whether created by this process or by  another,
       and does not affect any counters that this process has created on other
       processes.  It enables or disables only  the  group  leaders,  not  any
       other members in the groups.

   perf_event related configuration files
       Files in /proc/sys/kernel/

                  -1  no restrictions.

                  The  existence  of the perf_event_paranoid file is the offi-
                  cial  method  for   determining   if   a   kernel   supports


                  This  sets  the  maximum sample rate.  Setting this too high
                  can allow users to sample at a  rate  that  impacts  overall
                  machine  performance  and  potentially  lock up the machine.
                  The default value is 100000 (samples per second).


                  Maximum number of pages an unprivileged user can mlock (2) .
                  The default is 516 (kB).

       Files in /sys/bus/event_source/devices/
           Since  Linux 2.6.34 the kernel supports having multiple PMUs avail-
           able for monitoring.  Information on how to program these PMUs  can
           be  found  under /sys/bus/event_source/devices/.  Each subdirectory
           corresponds to a different PMU.

           /sys/bus/event_source/devices/*/type (Since Linux 2.6.38)
                  This contains an integer that can be used in the type  field
                  of perf_event_attr to indicate you wish to use this PMU.

           /sys/bus/event_source/devices/*/rdpmc (Since Linux 3.4)
                  If this file is 1, then direct user-space access to the per-
                  formance counter registers is allowed via the rdpmc instruc-
                  tion.  This can be disabled by echoing 0 to the file.

           /sys/bus/event_source/devices/*/format/ (Since Linux 3.4)
                  This sub-directory contains information on the architecture-
                  specific sub-fields available for  programming  the  various
                  config fields in the perf_event_attr struct.

                  The  content  of  each file is the name of the config field,
                  followed by a colon, followed by a  series  of  integer  bit
                  ranges separated by commas.  For example, the file event may
                  contain the value  config1:1,6-10,44  which  indicates  that
                  event  is  an attribute that occupies bits 1,6-10, and 44 of

           /sys/bus/event_source/devices/*/events/ (Since Linux 3.4)
                  This sub-directory contains files with  pre-defined  events.
                  The  contents  are  strings  describing  the  event settings
                  expressed in terms of the fields  found  in  the  previously
                  mentioned  ./format/  directory.   These are not necessarily
                  complete lists of all events supported by a PMU, but usually
                  a subset of events deemed useful or interesting.

                  The  content of each file is a list of attribute names sepa-
                  (package) on the motherboard.  This is needed  when  setting
                  up  uncore  or  northbridge  events,  as  those PMUs present
                  socket-wide events.

       perf_event_open() returns the new file descriptor, or -1  if  an  error
       occurred (in which case, errno is set appropriately).

       EINVAL Returned if the specified event is not available.

       ENOSPC Prior  to Linux 3.3, if there was not enough room for the event,
              ENOSPC was returned.  Linus did not  like  this,  and  this  was
              changed  to EINVAL.  ENOSPC is still returned if you try to read
              results into too small of a buffer.

       perf_event_open()  was  introduced  in  Linux  2.6.31  but  was  called
       perf_counter_open().  It was renamed in Linux 2.6.32.

       This  perf_event_open()  system  call Linux- specific and should not be
       used in programs intended to be portable.

       Glibc does not provide a wrapper for this system call;  call  it  using
       syscall(2).  See the example below.

       The  official way of knowing if perf_event_open() support is enabled is
       checking   for   the   existence    of    the    file    /proc/sys/ker-

       The  F_SETOWN_EX  option to fcntl(2) is needed to properly get overflow
       signals in threads.  This was introduced in Linux 2.6.32.

       Prior to Linux 2.6.33 (at least for x86) the kernel did  not  check  if
       events  could  be scheduled together until read time.  The same happens
       on all known kernels if the NMI watchdog is enabled.  This means to see
       if  a  given  set of events works you have to perf_event_open(), start,
       then read before you know for sure you can get valid measurements.

       Prior to Linux 2.6.34 event constraints were not enforced by  the  ker-
       nel.  In that case, some events would silently return "0" if the kernel
       scheduled them in an improper counter slot.

       Prior to Linux 2.6.34 there was a bug when multiplexing where the wrong
       results could be returned.

       Kernels  from Linux 2.6.35 to Linux 2.6.39 can quickly crash the kernel
       if "inherit" is enabled and many threads are started.

       Prior to Linux 2.6.35, PERF_FORMAT_GROUP did  not  work  with  attached

       Always  double-check your results!  Various generalized events have had
       wrong values.  For example, retired branches measured the  wrong  thing
       on AMD machines until Linux 2.6.35.

       The  following  is  a short example that measures the total instruction
       count of a call to printf(3).

       #include <stdlib.h>
       #include <stdio.h>
       #include <unistd.h>
       #include <string.h>
       #include <sys/ioctl.h>
       #include <linux/perf_event.h>
       #include <asm/unistd.h>

       perf_event_open(struct perf_event_attr *hw_event, pid_t pid,
                       int cpu, int group_fd, unsigned long flags)
           int ret;

           ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,
                          group_fd, flags);
           return ret;

       main(int argc, char **argv)
           struct perf_event_attr pe;
           long long count;
           int fd;

           memset(&pe, 0, sizeof(struct perf_event_attr));
           pe.type = PERF_TYPE_HARDWARE;
           pe.size = sizeof(struct perf_event_attr);
           pe.config = PERF_COUNT_HW_INSTRUCTIONS;
           pe.disabled = 1;
           pe.exclude_kernel = 1;
           pe.exclude_hv = 1;

           fd = perf_event_open(&pe, 0, -1, -1, 0);
           if (fd == -1) {
              fprintf(stderr, "Error opening leader %llx\n", pe.config);

           ioctl(fd, PERF_EVENT_IOC_RESET, 0);
           ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);

           printf("Measuring instruction count for this printf\n");

       This page is part of release 3.54 of the Linux  man-pages  project.   A
       description  of  the project, and information about reporting bugs, can
       be found at

Linux                             2013-09-13                PERF_EVENT_OPEN(2)
Man Pages Copyright Respective Owners. Site Copyright (C) 1994 - 2019 Hurricane Electric. All Rights Reserved.