perf_counter: update documentation

Impact: documentation fix

This updates the perfcounter documentation to reflect recent changes.

Signed-off-by: Paul Mackerras <paulus@samba.org>

1 files changed, 202 insertions, 66 deletions

diff --git a/Documentation/perf_counter/design.txt b/Documentation/perf_counter/design.txt
index fddd32189a5..aaf105c02fb 100644
--- a/Documentation/perf_counter/design.txt
+++ b/Documentation/perf_counter/design.txt
@@ -11,7 +11,9 @@ thus be used to profile the code that runs on that CPU.
 
 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 @@ The special file descriptor is opened via the perf_counter_open()
 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 @@ can be poll()ed.
 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':
 
 /*
- * IRQ-notification data record type:
+ * 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 perf_counter_record_type {
-	PERF_RECORD_SIMPLE		=  0,
-	PERF_RECORD_IRQ			=  1,
-	PERF_RECORD_GROUP		=  2,
+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,
 };
 
-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.)
+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.
 
-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 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:
 
-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.
+/*
+ * IRQ-notification data record type:
+ */
+enum perf_counter_record_type {
+	PERF_RECORD_SIMPLE		= 0,
+	PERF_RECORD_IRQ			= 1,
+	PERF_RECORD_GROUP		= 2,
+};
 
-The 'pid' parameter allows the counter to be specific to a task:
+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.
+
+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 '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 '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 @@ The 'pid' parameter allows the counter to be specific to a task:
 
  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 @@ their own tasks.
 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.