perf_counter: update documentation
Impact: documentation fix
This updates the perfcounter documentation to reflect recent changes.
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/Documentation/perf_counter/design.txt b/Documentation/perf_counter/design.txt
index fddd321..aaf105c 100644
--- a/Documentation/perf_counter/design.txt
+++ b/Documentation/perf_counter/design.txt
@@ -11,7 +11,9 @@
The Linux Performance Counter subsystem provides an abstraction of these
hardware capabilities. It provides per task and per CPU counters, counter
-groups, and it provides event capabilities on top of those.
+groups, and it provides event capabilities on top of those. It
+provides "virtual" 64-bit counters, regardless of the width of the
+underlying hardware counters.
Performance counters are accessed via special file descriptors.
There's one file descriptor per virtual counter used.
@@ -20,7 +22,8 @@
system call:
int sys_perf_counter_open(struct perf_counter_hw_event *hw_event_uptr,
- pid_t pid, int cpu, int group_fd);
+ pid_t pid, int cpu, int group_fd,
+ unsigned long flags);
The syscall returns the new fd. The fd can be used via the normal
VFS system calls: read() can be used to read the counter, fcntl()
@@ -32,90 +35,180 @@
When creating a new counter fd, 'perf_counter_hw_event' is:
/*
- * Hardware event to monitor via a performance monitoring counter:
+ * Event to monitor via a performance monitoring counter:
*/
struct perf_counter_hw_event {
- s64 type;
+ __u64 event_config;
- u64 irq_period;
- u32 record_type;
+ __u64 irq_period;
+ __u64 record_type;
+ __u64 read_format;
- u32 disabled : 1, /* off by default */
- nmi : 1, /* NMI sampling */
- raw : 1, /* raw event type */
- __reserved_1 : 29;
+ __u64 disabled : 1, /* off by default */
+ nmi : 1, /* NMI sampling */
+ 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, /* ditto kernel */
+ exclude_hv : 1, /* ditto hypervisor */
+ exclude_idle : 1, /* don't count when idle */
- u64 __reserved_2;
+ __reserved_1 : 55;
+
+ __u32 extra_config_len;
+
+ __u32 __reserved_4;
+ __u64 __reserved_2;
+ __u64 __reserved_3;
};
+The 'event_config' field specifies what the counter should count. It
+is divided into 3 bit-fields:
+
+raw_type: 1 bit (most significant bit) 0x8000_0000_0000_0000
+type: 7 bits (next most significant) 0x7f00_0000_0000_0000
+event_id: 56 bits (least significant) 0x00ff_0000_0000_0000
+
+If 'raw_type' is 1, then the counter will count a hardware event
+specified by the remaining 63 bits of event_config. The encoding is
+machine-specific.
+
+If 'raw_type' is 0, then the 'type' field says what kind of counter
+this is, with the following encoding:
+
+enum perf_event_types {
+ PERF_TYPE_HARDWARE = 0,
+ PERF_TYPE_SOFTWARE = 1,
+ PERF_TYPE_TRACEPOINT = 2,
+};
+
+A counter of PERF_TYPE_HARDWARE will count the hardware event
+specified by 'event_id':
+
/*
- * Generalized performance counter event types, used by the hw_event.type
+ * Generalized performance counter event types, used by the hw_event.event_id
* parameter of the sys_perf_counter_open() syscall:
*/
-enum hw_event_types {
+enum hw_event_ids {
/*
* Common hardware events, generalized by the kernel:
*/
- PERF_COUNT_CYCLES = 0,
- PERF_COUNT_INSTRUCTIONS = 1,
- PERF_COUNT_CACHE_REFERENCES = 2,
- PERF_COUNT_CACHE_MISSES = 3,
- PERF_COUNT_BRANCH_INSTRUCTIONS = 4,
- PERF_COUNT_BRANCH_MISSES = 5,
-
- /*
- * Special "software" counters provided by the kernel, even if
- * the hardware does not support performance counters. These
- * counters measure various physical and sw events of the
- * kernel (and allow the profiling of them as well):
- */
- PERF_COUNT_CPU_CLOCK = -1,
- PERF_COUNT_TASK_CLOCK = -2,
- /*
- * Future software events:
- */
- /* PERF_COUNT_PAGE_FAULTS = -3,
- PERF_COUNT_CONTEXT_SWITCHES = -4, */
+ PERF_COUNT_CPU_CYCLES = 0,
+ PERF_COUNT_INSTRUCTIONS = 1,
+ PERF_COUNT_CACHE_REFERENCES = 2,
+ PERF_COUNT_CACHE_MISSES = 3,
+ PERF_COUNT_BRANCH_INSTRUCTIONS = 4,
+ PERF_COUNT_BRANCH_MISSES = 5,
+ PERF_COUNT_BUS_CYCLES = 6,
};
-These are standardized types of events that work uniformly on all CPUs
-that implements Performance Counters support under Linux. If a CPU is
-not able to count branch-misses, then the system call will return
--EINVAL.
+These are standardized types of events that work relatively uniformly
+on all CPUs that implement Performance Counters support under Linux,
+although there may be variations (e.g., different CPUs might count
+cache references and misses at different levels of the cache hierarchy).
+If a CPU is not able to count the selected event, then the system call
+will return -EINVAL.
-More hw_event_types are supported as well, but they are CPU
-specific and are enumerated via /sys on a per CPU basis. Raw hw event
-types can be passed in under hw_event.type if hw_event.raw is 1.
-For example, to count "External bus cycles while bus lock signal asserted"
-events on Intel Core CPUs, pass in a 0x4064 event type value and set
-hw_event.raw to 1.
+More hw_event_types are supported as well, but they are CPU-specific
+and accessed as raw events. For example, to count "External bus
+cycles while bus lock signal asserted" events on Intel Core CPUs, pass
+in a 0x4064 event_id value and set hw_event.raw_type to 1.
-'record_type' is the type of data that a read() will provide for the
-counter, and it can be one of:
+A counter of type PERF_TYPE_SOFTWARE will count one of the available
+software events, selected by 'event_id':
+
+/*
+ * Special "software" counters provided by the kernel, even if the hardware
+ * does not support performance counters. These counters measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum sw_event_ids {
+ PERF_COUNT_CPU_CLOCK = 0,
+ PERF_COUNT_TASK_CLOCK = 1,
+ PERF_COUNT_PAGE_FAULTS = 2,
+ PERF_COUNT_CONTEXT_SWITCHES = 3,
+ PERF_COUNT_CPU_MIGRATIONS = 4,
+ PERF_COUNT_PAGE_FAULTS_MIN = 5,
+ PERF_COUNT_PAGE_FAULTS_MAJ = 6,
+};
+
+Counters come in two flavours: counting counters and sampling
+counters. A "counting" counter is one that is used for counting the
+number of events that occur, and is characterised by having
+irq_period = 0 and record_type = PERF_RECORD_SIMPLE. A read() on a
+counting counter simply returns the current value of the counter as
+an 8-byte number.
+
+A "sampling" counter is one that is set up to generate an interrupt
+every N events, where N is given by 'irq_period'. A sampling counter
+has irq_period > 0 and record_type != PERF_RECORD_SIMPLE. The
+record_type controls what data is recorded on each interrupt, and the
+available values are currently:
/*
* IRQ-notification data record type:
*/
enum perf_counter_record_type {
- PERF_RECORD_SIMPLE = 0,
- PERF_RECORD_IRQ = 1,
- PERF_RECORD_GROUP = 2,
+ PERF_RECORD_SIMPLE = 0,
+ PERF_RECORD_IRQ = 1,
+ PERF_RECORD_GROUP = 2,
};
-a "simple" counter is one that counts hardware events and allows
-them to be read out into a u64 count value. (read() returns 8 on
-a successful read of a simple counter.)
+A record_type value of PERF_RECORD_IRQ will record the instruction
+pointer (IP) at which the interrupt occurred. A record_type value of
+PERF_RECORD_GROUP will record the event_config and counter value of
+all of the other counters in the group, and should only be used on a
+group leader (see below). Currently these two values are mutually
+exclusive, but record_type will become a bit-mask in future and
+support other values.
-An "irq" counter is one that will also provide an IRQ context information:
-the IP of the interrupted context. In this case read() will return
-the 8-byte counter value, plus the Instruction Pointer address of the
-interrupted context.
+A sampling counter has an event queue, into which an event is placed
+on each interrupt. A read() on a sampling counter will read the next
+event from the event queue. If the queue is empty, the read() will
+either block or return an EAGAIN error, depending on whether the fd
+has been set to non-blocking mode or not.
-The parameter 'hw_event_period' is the number of events before waking up
-a read() that is blocked on a counter fd. Zero value means a non-blocking
-counter.
+The 'disabled' bit specifies whether the counter starts out disabled
+or enabled. If it is initially disabled, it can be enabled by ioctl
+or prctl (see below).
-The 'pid' parameter allows the counter to be specific to a task:
+The 'nmi' bit specifies, for hardware events, whether the counter
+should be set up to request non-maskable interrupts (NMIs) or normal
+interrupts. This bit is ignored if the user doesn't have
+CAP_SYS_ADMIN privilege (i.e. is not root) or if the CPU doesn't
+generate NMIs from hardware counters.
+
+The 'inherit' bit, if set, specifies that this counter should count
+events on descendant tasks as well as the task specified. This only
+applies to new descendents, not to any existing descendents at the
+time the counter is created (nor to any new descendents of existing
+descendents).
+
+The 'pinned' bit, if set, specifies that the counter should always be
+on the CPU if at all possible. It only applies to hardware counters
+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() returns 0)
+until the counter is subsequently enabled or disabled.
+
+The 'exclusive' bit, if set, specifies that when this counter's group
+is on the CPU, it should be the only group using the CPU's counters.
+In future, this will allow sophisticated monitoring programs to supply
+extra configuration information via 'extra_config_len' to exploit
+advanced features of the CPU's Performance Monitor Unit (PMU) that are
+not otherwise accessible and that might disrupt other hardware
+counters.
+
+The 'exclude_user', 'exclude_kernel' and 'exclude_hv' bits provide a
+way to request that counting of events be restricted to times when the
+CPU is in user, kernel and/or hypervisor mode.
+
+
+The 'pid' parameter to the perf_counter_open() system call allows the
+counter to be specific to a task:
pid == 0: if the pid parameter is zero, the counter is attached to the
current task.
@@ -125,8 +218,7 @@
pid < 0: all tasks are counted (per cpu counters)
-The 'cpu' parameter allows a counter to be made specific to a full
-CPU:
+The 'cpu' parameter allows a counter to be made specific to a CPU:
cpu >= 0: the counter is restricted to a specific CPU
cpu == -1: the counter counts on all CPUs
@@ -141,7 +233,51 @@
A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts
all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege.
-Group counters are created by passing in a group_fd of another counter.
-Groups are scheduled at once and can be used with PERF_RECORD_GROUP
-to record multi-dimensional timestamps.
+The 'flags' parameter is currently unused and must be zero.
+
+The 'group_fd' parameter allows counter "groups" to be set up. A
+counter group has one counter which is the group "leader". The leader
+is created first, with group_fd = -1 in the perf_counter_open call
+that creates it. The rest of the group members are created
+subsequently, with group_fd giving the fd of the group leader.
+(A single counter on its own is created with group_fd = -1 and is
+considered to be a group with only 1 member.)
+
+A counter group is scheduled onto the CPU as a unit, that is, it will
+only be put onto the CPU if all of the counters in the group can be
+put onto the CPU. This means that the values of the member counters
+can be meaningfully compared, added, divided (to get ratios), etc.,
+with each other, since they have counted events for the same set of
+executed instructions.
+
+Counters can be enabled and disabled in two ways: via ioctl and via
+prctl. When a counter is disabled, it doesn't count or generate
+events but does continue to exist and maintain its count value.
+
+An individual counter or counter group can be enabled with
+
+ ioctl(fd, PERF_COUNTER_IOC_ENABLE);
+
+or disabled with
+
+ ioctl(fd, PERF_COUNTER_IOC_DISABLE);
+
+Enabling or disabling the leader of a group enables or disables the
+whole group; that is, while the group leader is disabled, none of the
+counters in the group will count. Enabling or disabling a member of a
+group other than the leader only affects that counter - disabling an
+non-leader stops that counter from counting but doesn't affect any
+other counter.
+
+A process can enable or disable all the counter groups that are
+attached to it, using prctl:
+
+ prctl(PR_TASK_PERF_COUNTERS_ENABLE);
+
+ prctl(PR_TASK_PERF_COUNTERS_DISABLE);
+
+This applies to all counters on the current process, whether created
+by this process or by another, and doesn't affect any counters that
+this process has created on other processes. It only enables or
+disables the group leaders, not any other members in the groups.
