linux_dsm_epyc7002/include/uapi/linux/perf_event.h

/*
 * Performance events:
 *
 *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
 *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
 *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
 *
 * Data type definitions, declarations, prototypes.
 *
 *    Started by: Thomas Gleixner and Ingo Molnar
 *
 * For licencing details see kernel-base/COPYING
 */
#ifndef _UAPI_LINUX_PERF_EVENT_H
#define _UAPI_LINUX_PERF_EVENT_H

#include <linux/types.h>
#include <linux/ioctl.h>
#include <asm/byteorder.h>

/*
 * User-space ABI bits:
 */

/*
 * attr.type
 */
enum perf_type_id {
	PERF_TYPE_HARDWARE			= 0,
	PERF_TYPE_SOFTWARE			= 1,
	PERF_TYPE_TRACEPOINT			= 2,
	PERF_TYPE_HW_CACHE			= 3,
	PERF_TYPE_RAW				= 4,
	PERF_TYPE_BREAKPOINT			= 5,

	PERF_TYPE_MAX,				/* non-ABI */
};

/*
 * Generalized performance event event_id types, used by the
 * attr.event_id parameter of the sys_perf_event_open()
 * syscall:
 */
enum perf_hw_id {
	/*
	 * Common hardware events, generalized by the kernel:
	 */
	PERF_COUNT_HW_CPU_CYCLES		= 0,
	PERF_COUNT_HW_INSTRUCTIONS		= 1,
	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
	PERF_COUNT_HW_CACHE_MISSES		= 3,
	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
	PERF_COUNT_HW_BRANCH_MISSES		= 5,
	PERF_COUNT_HW_BUS_CYCLES		= 6,
	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,

	PERF_COUNT_HW_MAX,			/* non-ABI */
};

/*
 * Generalized hardware cache events:
 *
 *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
 *       { read, write, prefetch } x
 *       { accesses, misses }
 */
enum perf_hw_cache_id {
	PERF_COUNT_HW_CACHE_L1D			= 0,
	PERF_COUNT_HW_CACHE_L1I			= 1,
	PERF_COUNT_HW_CACHE_LL			= 2,
	PERF_COUNT_HW_CACHE_DTLB		= 3,
	PERF_COUNT_HW_CACHE_ITLB		= 4,
	PERF_COUNT_HW_CACHE_BPU			= 5,
	PERF_COUNT_HW_CACHE_NODE		= 6,

	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
};

enum perf_hw_cache_op_id {
	PERF_COUNT_HW_CACHE_OP_READ		= 0,
	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,

	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
};

enum perf_hw_cache_op_result_id {
	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,

	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
};

/*
 * Special "software" events provided by the kernel, even if the hardware
 * does not support performance events. These events measure various
 * physical and sw events of the kernel (and allow the profiling of them as
 * well):
 */
enum perf_sw_ids {
	PERF_COUNT_SW_CPU_CLOCK			= 0,
	PERF_COUNT_SW_TASK_CLOCK		= 1,
	PERF_COUNT_SW_PAGE_FAULTS		= 2,
	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
	PERF_COUNT_SW_EMULATION_FAULTS		= 8,

	PERF_COUNT_SW_MAX,			/* non-ABI */
};

/*
 * Bits that can be set in attr.sample_type to request information
 * in the overflow packets.
 */
enum perf_event_sample_format {
	PERF_SAMPLE_IP				= 1U << 0,
	PERF_SAMPLE_TID				= 1U << 1,
	PERF_SAMPLE_TIME			= 1U << 2,
	PERF_SAMPLE_ADDR			= 1U << 3,
	PERF_SAMPLE_READ			= 1U << 4,
	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
	PERF_SAMPLE_ID				= 1U << 6,
	PERF_SAMPLE_CPU				= 1U << 7,
	PERF_SAMPLE_PERIOD			= 1U << 8,
	PERF_SAMPLE_STREAM_ID			= 1U << 9,
	PERF_SAMPLE_RAW				= 1U << 10,
	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
	PERF_SAMPLE_REGS_USER			= 1U << 12,
	PERF_SAMPLE_STACK_USER			= 1U << 13,

	PERF_SAMPLE_MAX = 1U << 14,		/* non-ABI */
};

/*
 * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
 *
 * If the user does not pass priv level information via branch_sample_type,
 * the kernel uses the event's priv level. Branch and event priv levels do
 * not have to match. Branch priv level is checked for permissions.
 *
 * The branch types can be combined, however BRANCH_ANY covers all types
 * of branches and therefore it supersedes all the other types.
 */
enum perf_branch_sample_type {
	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */

	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */

	PERF_SAMPLE_BRANCH_MAX		= 1U << 7, /* non-ABI */
};

#define PERF_SAMPLE_BRANCH_PLM_ALL \
	(PERF_SAMPLE_BRANCH_USER|\
	 PERF_SAMPLE_BRANCH_KERNEL|\
	 PERF_SAMPLE_BRANCH_HV)

/*
 * Values to determine ABI of the registers dump.
 */
enum perf_sample_regs_abi {
	PERF_SAMPLE_REGS_ABI_NONE	= 0,
	PERF_SAMPLE_REGS_ABI_32		= 1,
	PERF_SAMPLE_REGS_ABI_64		= 2,
};

/*
 * The format of the data returned by read() on a perf event fd,
 * as specified by attr.read_format:
 *
 * struct read_format {
 *	{ u64		value;
 *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
 *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
 *	  { u64		id;           } && PERF_FORMAT_ID
 *	} && !PERF_FORMAT_GROUP
 *
 *	{ u64		nr;
 *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
 *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
 *	  { u64		value;
 *	    { u64	id;           } && PERF_FORMAT_ID
 *	  }		cntr[nr];
 *	} && PERF_FORMAT_GROUP
 * };
 */
enum perf_event_read_format {
	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
	PERF_FORMAT_ID				= 1U << 2,
	PERF_FORMAT_GROUP			= 1U << 3,

	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
};

#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
#define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
					/* add: sample_stack_user */

/*
 * Hardware event_id to monitor via a performance monitoring event:
 */
struct perf_event_attr {

	/*
	 * Major type: hardware/software/tracepoint/etc.
	 */
	__u32			type;

	/*
	 * Size of the attr structure, for fwd/bwd compat.
	 */
	__u32			size;

	/*
	 * Type specific configuration information.
	 */
	__u64			config;

	union {
		__u64		sample_period;
		__u64		sample_freq;
	};

	__u64			sample_type;
	__u64			read_format;

	__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, /* ditto kernel          */
				exclude_hv     :  1, /* ditto 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:
				 *
				 *  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 PERF_RECORD_MISC_EXACT_IP
				 */
				precise_ip     :  2, /* skid constraint       */
				mmap_data      :  1, /* non-exec mmap data    */
				sample_id_all  :  1, /* sample_type all events */

				exclude_host   :  1, /* don't count in host   */
				exclude_guest  :  1, /* don't count in guest  */

				exclude_callchain_kernel : 1, /* exclude kernel callchains */
				exclude_callchain_user   : 1, /* exclude user callchains */

				__reserved_1   : 41;

	union {
		__u32		wakeup_events;	  /* wakeup every n events */
		__u32		wakeup_watermark; /* bytes before wakeup   */
	};

	__u32			bp_type;
	union {
		__u64		bp_addr;
		__u64		config1; /* extension of config */
	};
	union {
		__u64		bp_len;
		__u64		config2; /* extension of config1 */
	};
	__u64	branch_sample_type; /* enum perf_branch_sample_type */

	/*
	 * Defines set of user regs to dump on samples.
	 * See asm/perf_regs.h for details.
	 */
	__u64	sample_regs_user;

	/*
	 * Defines size of the user stack to dump on samples.
	 */
	__u32	sample_stack_user;

	/* Align to u64. */
	__u32	__reserved_2;
};

#define perf_flags(attr)	(*(&(attr)->read_format + 1))

/*
 * Ioctls that can be done on a perf event fd:
 */
#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)

enum perf_event_ioc_flags {
	PERF_IOC_FLAG_GROUP		= 1U << 0,
};

/*
 * Structure of the page that can be mapped via mmap
 */
struct perf_event_mmap_page {
	__u32	version;		/* version number of this structure */
	__u32	compat_version;		/* lowest version this is compat with */

	/*
	 * Bits needed to read the hw events in user-space.
	 *
	 *   u32 seq, time_mult, time_shift, idx, width;
	 *   u64 count, enabled, running;
	 *   u64 cyc, time_offset;
	 *   s64 pmc = 0;
	 *
	 *   do {
	 *     seq = pc->lock;
	 *     barrier()
	 *
	 *     enabled = pc->time_enabled;
	 *     running = pc->time_running;
	 *
	 *     if (pc->cap_usr_time && enabled != running) {
	 *       cyc = rdtsc();
	 *       time_offset = pc->time_offset;
	 *       time_mult   = pc->time_mult;
	 *       time_shift  = pc->time_shift;
	 *     }
	 *
	 *     idx = pc->index;
	 *     count = pc->offset;
	 *     if (pc->cap_usr_rdpmc && idx) {
	 *       width = pc->pmc_width;
	 *       pmc = rdpmc(idx - 1);
	 *     }
	 *
	 *     barrier();
	 *   } while (pc->lock != seq);
	 *
	 * NOTE: for obvious reason this only works on self-monitoring
	 *       processes.
	 */
	__u32	lock;			/* seqlock for synchronization */
	__u32	index;			/* hardware event identifier */
	__s64	offset;			/* add to hardware event value */
	__u64	time_enabled;		/* time event active */
	__u64	time_running;		/* time event on cpu */
	union {
		__u64	capabilities;
		__u64	cap_usr_time  : 1,
			cap_usr_rdpmc : 1,
			cap_____res   : 62;
	};

	/*
	 * 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 - width;
	 *   pmc >>= 64 - width; // signed shift right
	 *   count += pmc;
	 */
	__u16	pmc_width;

	/*
	 * If cap_usr_time the below fields can be used to compute the time
	 * delta since time_enabled (in ns) using rdtsc or similar.
	 *
	 *   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;
	 */
	__u16	time_shift;
	__u32	time_mult;
	__u64	time_offset;

		/*
		 * Hole for extension of the self monitor capabilities
		 */

	__u64	__reserved[120];	/* align to 1k */

	/*
	 * Control data for the mmap() data buffer.
	 *
	 * User-space reading the @data_head value should issue an rmb(), on
	 * SMP capable platforms, after reading this value -- see
	 * perf_event_wakeup().
	 *
	 * When the mapping is PROT_WRITE the @data_tail value should be
	 * written by userspace to reflect the last read data. In this case
	 * the kernel will not over-write unread data.
	 */
	__u64   data_head;		/* head in the data section */
	__u64	data_tail;		/* user-space written tail */
};

#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
#define PERF_RECORD_MISC_KERNEL			(1 << 0)
#define PERF_RECORD_MISC_USER			(2 << 0)
#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)

/*
 * Indicates that the content of PERF_SAMPLE_IP points to
 * the actual instruction that triggered the event. See also
 * perf_event_attr::precise_ip.
 */
#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
/*
 * Reserve the last bit to indicate some extended misc field
 */
#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)

struct perf_event_header {
	__u32	type;
	__u16	misc;
	__u16	size;
};

enum perf_event_type {

	/*
	 * 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 event took place (TID, TIME, ID, CPU, STREAM_ID)
	 * described in PERF_RECORD_SAMPLE below, it will be stashed just after
	 * the perf_event_header and the fields already present for the existing
	 * fields, i.e. at the end of the payload. That way a newer perf.data
	 * file will be supported by older perf tools, with these new optional
	 * fields being ignored.
	 *
	 * The MMAP events record the PROT_EXEC mappings so that we can
	 * correlate userspace IPs to code. They have the following structure:
	 *
	 * struct {
	 *	struct perf_event_header	header;
	 *
	 *	u32				pid, tid;
	 *	u64				addr;
	 *	u64				len;
	 *	u64				pgoff;
	 *	char				filename[];
	 * };
	 */
	PERF_RECORD_MMAP			= 1,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u64				id;
	 *	u64				lost;
	 * };
	 */
	PERF_RECORD_LOST			= 2,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *
	 *	u32				pid, tid;
	 *	char				comm[];
	 * };
	 */
	PERF_RECORD_COMM			= 3,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u32				pid, ppid;
	 *	u32				tid, ptid;
	 *	u64				time;
	 * };
	 */
	PERF_RECORD_EXIT			= 4,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u64				time;
	 *	u64				id;
	 *	u64				stream_id;
	 * };
	 */
	PERF_RECORD_THROTTLE			= 5,
	PERF_RECORD_UNTHROTTLE			= 6,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u32				pid, ppid;
	 *	u32				tid, ptid;
	 *	u64				time;
	 * };
	 */
	PERF_RECORD_FORK			= 7,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u32				pid, tid;
	 *
	 *	struct read_format		values;
	 * };
	 */
	PERF_RECORD_READ			= 8,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *
	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
	 *	{ u64			time;     } && PERF_SAMPLE_TIME
	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
	 *	{ u64			id;	  } && PERF_SAMPLE_ID
	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
	 *
	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
	 *
	 *	{ u64			nr,
	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
	 *
	 *	#
	 *	# The RAW record below is opaque data wrt the ABI
	 *	#
	 *	# That is, the ABI doesn't make any promises wrt to
	 *	# the stability of its content, it may vary depending
	 *	# on event, hardware, kernel version and phase of
	 *	# the moon.
	 *	#
	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
	 *	#
	 *
	 *	{ u32			size;
	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
	 *
	 *	{ u64                   nr;
	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
	 *
	 * 	{ u64			abi; # enum perf_sample_regs_abi
	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
	 *
	 * 	{ u64			size;
	 * 	  char			data[size];
	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
	 * };
	 */
	PERF_RECORD_SAMPLE			= 9,

	PERF_RECORD_MAX,			/* non-ABI */
};

#define PERF_MAX_STACK_DEPTH		127

enum perf_callchain_context {
	PERF_CONTEXT_HV			= (__u64)-32,
	PERF_CONTEXT_KERNEL		= (__u64)-128,
	PERF_CONTEXT_USER		= (__u64)-512,

	PERF_CONTEXT_GUEST		= (__u64)-2048,
	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,

	PERF_CONTEXT_MAX		= (__u64)-4095,
};

#define PERF_FLAG_FD_NO_GROUP		(1U << 0)
#define PERF_FLAG_FD_OUTPUT		(1U << 1)
#define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */

#endif /* _UAPI_LINUX_PERF_EVENT_H */