1/*
2 * Performance events x86 architecture header
3 *
4 *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
5 *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
6 *  Copyright (C) 2009 Jaswinder Singh Rajput
7 *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
8 *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
9 *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
10 *  Copyright (C) 2009 Google, Inc., Stephane Eranian
11 *
12 *  For licencing details see kernel-base/COPYING
13 */
14
15#include <linux/perf_event.h>
16
17#include <asm/intel_ds.h>
18
19/* To enable MSR tracing please use the generic trace points. */
20
21/*
22 *          |   NHM/WSM    |      SNB     |
23 * register -------------------------------
24 *          |  HT  | no HT |  HT  | no HT |
25 *-----------------------------------------
26 * offcore  | core | core  | cpu  | core  |
27 * lbr_sel  | core | core  | cpu  | core  |
28 * ld_lat   | cpu  | core  | cpu  | core  |
29 *-----------------------------------------
30 *
31 * Given that there is a small number of shared regs,
32 * we can pre-allocate their slot in the per-cpu
33 * per-core reg tables.
34 */
35enum extra_reg_type {
36	EXTRA_REG_NONE  = -1,	/* not used */
37
38	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
39	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
40	EXTRA_REG_LBR   = 2,	/* lbr_select */
41	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
42	EXTRA_REG_FE    = 4,    /* fe_* */
43
44	EXTRA_REG_MAX		/* number of entries needed */
45};
46
47struct event_constraint {
48	union {
49		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
50		u64		idxmsk64;
51	};
52	u64		code;
53	u64		cmask;
54	int		weight;
55	int		overlap;
56	int		flags;
57	unsigned int	size;
58};
59
60static inline bool constraint_match(struct event_constraint *c, u64 ecode)
61{
62	return ((ecode & c->cmask) - c->code) <= (u64)c->size;
63}
64
65/*
66 * struct hw_perf_event.flags flags
67 */
68#define PERF_X86_EVENT_PEBS_LDLAT	0x0001 /* ld+ldlat data address sampling */
69#define PERF_X86_EVENT_PEBS_ST		0x0002 /* st data address sampling */
70#define PERF_X86_EVENT_PEBS_ST_HSW	0x0004 /* haswell style datala, store */
71#define PERF_X86_EVENT_PEBS_LD_HSW	0x0008 /* haswell style datala, load */
72#define PERF_X86_EVENT_PEBS_NA_HSW	0x0010 /* haswell style datala, unknown */
73#define PERF_X86_EVENT_EXCL		0x0020 /* HT exclusivity on counter */
74#define PERF_X86_EVENT_DYNAMIC		0x0040 /* dynamic alloc'd constraint */
75#define PERF_X86_EVENT_RDPMC_ALLOWED	0x0080 /* grant rdpmc permission */
76#define PERF_X86_EVENT_EXCL_ACCT	0x0100 /* accounted EXCL event */
77#define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
78#define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
79#define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
80#define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
81#define PERF_X86_EVENT_LBR_SELECT	0x2000 /* Save/Restore MSR_LBR_SELECT */
82#define PERF_X86_EVENT_TOPDOWN		0x4000 /* Count Topdown slots/metrics events */
83
84static inline bool is_topdown_count(struct perf_event *event)
85{
86	return event->hw.flags & PERF_X86_EVENT_TOPDOWN;
87}
88
89static inline bool is_metric_event(struct perf_event *event)
90{
91	u64 config = event->attr.config;
92
93	return ((config & ARCH_PERFMON_EVENTSEL_EVENT) == 0) &&
94		((config & INTEL_ARCH_EVENT_MASK) >= INTEL_TD_METRIC_RETIRING)  &&
95		((config & INTEL_ARCH_EVENT_MASK) <= INTEL_TD_METRIC_MAX);
96}
97
98static inline bool is_slots_event(struct perf_event *event)
99{
100	return (event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_TD_SLOTS;
101}
102
103static inline bool is_topdown_event(struct perf_event *event)
104{
105	return is_metric_event(event) || is_slots_event(event);
106}
107
108struct amd_nb {
109	int nb_id;  /* NorthBridge id */
110	int refcnt; /* reference count */
111	struct perf_event *owners[X86_PMC_IDX_MAX];
112	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
113};
114
115#define PEBS_COUNTER_MASK	((1ULL << MAX_PEBS_EVENTS) - 1)
116#define PEBS_PMI_AFTER_EACH_RECORD BIT_ULL(60)
117#define PEBS_OUTPUT_OFFSET	61
118#define PEBS_OUTPUT_MASK	(3ull << PEBS_OUTPUT_OFFSET)
119#define PEBS_OUTPUT_PT		(1ull << PEBS_OUTPUT_OFFSET)
120#define PEBS_VIA_PT_MASK	(PEBS_OUTPUT_PT | PEBS_PMI_AFTER_EACH_RECORD)
121
122/*
123 * Flags PEBS can handle without an PMI.
124 *
125 * TID can only be handled by flushing at context switch.
126 * REGS_USER can be handled for events limited to ring 3.
127 *
128 */
129#define LARGE_PEBS_FLAGS \
130	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
131	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
132	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
133	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
134	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
135	PERF_SAMPLE_PERIOD)
136
137#define PEBS_GP_REGS			\
138	((1ULL << PERF_REG_X86_AX)    | \
139	 (1ULL << PERF_REG_X86_BX)    | \
140	 (1ULL << PERF_REG_X86_CX)    | \
141	 (1ULL << PERF_REG_X86_DX)    | \
142	 (1ULL << PERF_REG_X86_DI)    | \
143	 (1ULL << PERF_REG_X86_SI)    | \
144	 (1ULL << PERF_REG_X86_SP)    | \
145	 (1ULL << PERF_REG_X86_BP)    | \
146	 (1ULL << PERF_REG_X86_IP)    | \
147	 (1ULL << PERF_REG_X86_FLAGS) | \
148	 (1ULL << PERF_REG_X86_R8)    | \
149	 (1ULL << PERF_REG_X86_R9)    | \
150	 (1ULL << PERF_REG_X86_R10)   | \
151	 (1ULL << PERF_REG_X86_R11)   | \
152	 (1ULL << PERF_REG_X86_R12)   | \
153	 (1ULL << PERF_REG_X86_R13)   | \
154	 (1ULL << PERF_REG_X86_R14)   | \
155	 (1ULL << PERF_REG_X86_R15))
156
157/*
158 * Per register state.
159 */
160struct er_account {
161	raw_spinlock_t      lock;	/* per-core: protect structure */
162	u64                 config;	/* extra MSR config */
163	u64                 reg;	/* extra MSR number */
164	atomic_t            ref;	/* reference count */
165};
166
167/*
168 * Per core/cpu state
169 *
170 * Used to coordinate shared registers between HT threads or
171 * among events on a single PMU.
172 */
173struct intel_shared_regs {
174	struct er_account       regs[EXTRA_REG_MAX];
175	int                     refcnt;		/* per-core: #HT threads */
176	unsigned                core_id;	/* per-core: core id */
177};
178
179enum intel_excl_state_type {
180	INTEL_EXCL_UNUSED    = 0, /* counter is unused */
181	INTEL_EXCL_SHARED    = 1, /* counter can be used by both threads */
182	INTEL_EXCL_EXCLUSIVE = 2, /* counter can be used by one thread only */
183};
184
185struct intel_excl_states {
186	enum intel_excl_state_type state[X86_PMC_IDX_MAX];
187	bool sched_started; /* true if scheduling has started */
188};
189
190struct intel_excl_cntrs {
191	raw_spinlock_t	lock;
192
193	struct intel_excl_states states[2];
194
195	union {
196		u16	has_exclusive[2];
197		u32	exclusive_present;
198	};
199
200	int		refcnt;		/* per-core: #HT threads */
201	unsigned	core_id;	/* per-core: core id */
202};
203
204struct x86_perf_task_context;
205#define MAX_LBR_ENTRIES		32
206
207enum {
208	LBR_FORMAT_32		= 0x00,
209	LBR_FORMAT_LIP		= 0x01,
210	LBR_FORMAT_EIP		= 0x02,
211	LBR_FORMAT_EIP_FLAGS	= 0x03,
212	LBR_FORMAT_EIP_FLAGS2	= 0x04,
213	LBR_FORMAT_INFO		= 0x05,
214	LBR_FORMAT_TIME		= 0x06,
215	LBR_FORMAT_MAX_KNOWN    = LBR_FORMAT_TIME,
216};
217
218enum {
219	X86_PERF_KFREE_SHARED = 0,
220	X86_PERF_KFREE_EXCL   = 1,
221	X86_PERF_KFREE_MAX
222};
223
224struct cpu_hw_events {
225	/*
226	 * Generic x86 PMC bits
227	 */
228	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
229	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
230	unsigned long		running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
231	int			enabled;
232
233	int			n_events; /* the # of events in the below arrays */
234	int			n_added;  /* the # last events in the below arrays;
235					     they've never been enabled yet */
236	int			n_txn;    /* the # last events in the below arrays;
237					     added in the current transaction */
238	int			n_txn_pair;
239	int			n_txn_metric;
240	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
241	u64			tags[X86_PMC_IDX_MAX];
242
243	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
244	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
245
246	int			n_excl; /* the number of exclusive events */
247
248	unsigned int		txn_flags;
249	int			is_fake;
250
251	/*
252	 * Intel DebugStore bits
253	 */
254	struct debug_store	*ds;
255	void			*ds_pebs_vaddr;
256	void			*ds_bts_vaddr;
257	u64			pebs_enabled;
258	int			n_pebs;
259	int			n_large_pebs;
260	int			n_pebs_via_pt;
261	int			pebs_output;
262
263	/* Current super set of events hardware configuration */
264	u64			pebs_data_cfg;
265	u64			active_pebs_data_cfg;
266	int			pebs_record_size;
267
268	/*
269	 * Intel LBR bits
270	 */
271	int				lbr_users;
272	int				lbr_pebs_users;
273	struct perf_branch_stack	lbr_stack;
274	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
275	union {
276		struct er_account		*lbr_sel;
277		struct er_account		*lbr_ctl;
278	};
279	u64				br_sel;
280	void				*last_task_ctx;
281	int				last_log_id;
282	int				lbr_select;
283	void				*lbr_xsave;
284
285	/*
286	 * Intel host/guest exclude bits
287	 */
288	u64				intel_ctrl_guest_mask;
289	u64				intel_ctrl_host_mask;
290	struct perf_guest_switch_msr	guest_switch_msrs[X86_PMC_IDX_MAX];
291
292	/*
293	 * Intel checkpoint mask
294	 */
295	u64				intel_cp_status;
296
297	/*
298	 * manage shared (per-core, per-cpu) registers
299	 * used on Intel NHM/WSM/SNB
300	 */
301	struct intel_shared_regs	*shared_regs;
302	/*
303	 * manage exclusive counter access between hyperthread
304	 */
305	struct event_constraint *constraint_list; /* in enable order */
306	struct intel_excl_cntrs		*excl_cntrs;
307	int excl_thread_id; /* 0 or 1 */
308
309	/*
310	 * SKL TSX_FORCE_ABORT shadow
311	 */
312	u64				tfa_shadow;
313
314	/*
315	 * Perf Metrics
316	 */
317	/* number of accepted metrics events */
318	int				n_metric;
319
320	/*
321	 * AMD specific bits
322	 */
323	struct amd_nb			*amd_nb;
324	/* Inverted mask of bits to clear in the perf_ctr ctrl registers */
325	u64				perf_ctr_virt_mask;
326	int				n_pair; /* Large increment events */
327
328	void				*kfree_on_online[X86_PERF_KFREE_MAX];
329
330	struct pmu			*pmu;
331};
332
333#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) {	\
334	{ .idxmsk64 = (n) },		\
335	.code = (c),			\
336	.size = (e) - (c),		\
337	.cmask = (m),			\
338	.weight = (w),			\
339	.overlap = (o),			\
340	.flags = f,			\
341}
342
343#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
344	__EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
345
346#define EVENT_CONSTRAINT(c, n, m)	\
347	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
348
349/*
350 * The constraint_match() function only works for 'simple' event codes
351 * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
352 */
353#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
354	__EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
355
356#define INTEL_EXCLEVT_CONSTRAINT(c, n)	\
357	__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
358			   0, PERF_X86_EVENT_EXCL)
359
360/*
361 * The overlap flag marks event constraints with overlapping counter
362 * masks. This is the case if the counter mask of such an event is not
363 * a subset of any other counter mask of a constraint with an equal or
364 * higher weight, e.g.:
365 *
366 *  c_overlaps = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
367 *  c_another1 = EVENT_CONSTRAINT(0, 0x07, 0);
368 *  c_another2 = EVENT_CONSTRAINT(0, 0x38, 0);
369 *
370 * The event scheduler may not select the correct counter in the first
371 * cycle because it needs to know which subsequent events will be
372 * scheduled. It may fail to schedule the events then. So we set the
373 * overlap flag for such constraints to give the scheduler a hint which
374 * events to select for counter rescheduling.
375 *
376 * Care must be taken as the rescheduling algorithm is O(n!) which
377 * will increase scheduling cycles for an over-committed system
378 * dramatically.  The number of such EVENT_CONSTRAINT_OVERLAP() macros
379 * and its counter masks must be kept at a minimum.
380 */
381#define EVENT_CONSTRAINT_OVERLAP(c, n, m)	\
382	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0)
383
384/*
385 * Constraint on the Event code.
386 */
387#define INTEL_EVENT_CONSTRAINT(c, n)	\
388	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
389
390/*
391 * Constraint on a range of Event codes
392 */
393#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n)			\
394	EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
395
396/*
397 * Constraint on the Event code + UMask + fixed-mask
398 *
399 * filter mask to validate fixed counter events.
400 * the following filters disqualify for fixed counters:
401 *  - inv
402 *  - edge
403 *  - cnt-mask
404 *  - in_tx
405 *  - in_tx_checkpointed
406 *  The other filters are supported by fixed counters.
407 *  The any-thread option is supported starting with v3.
408 */
409#define FIXED_EVENT_FLAGS (X86_RAW_EVENT_MASK|HSW_IN_TX|HSW_IN_TX_CHECKPOINTED)
410#define FIXED_EVENT_CONSTRAINT(c, n)	\
411	EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS)
412
413/*
414 * The special metric counters do not actually exist. They are calculated from
415 * the combination of the FxCtr3 + MSR_PERF_METRICS.
416 *
417 * The special metric counters are mapped to a dummy offset for the scheduler.
418 * The sharing between multiple users of the same metric without multiplexing
419 * is not allowed, even though the hardware supports that in principle.
420 */
421
422#define METRIC_EVENT_CONSTRAINT(c, n)					\
423	EVENT_CONSTRAINT(c, (1ULL << (INTEL_PMC_IDX_METRIC_BASE + n)),	\
424			 INTEL_ARCH_EVENT_MASK)
425
426/*
427 * Constraint on the Event code + UMask
428 */
429#define INTEL_UEVENT_CONSTRAINT(c, n)	\
430	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
431
432/* Constraint on specific umask bit only + event */
433#define INTEL_UBIT_EVENT_CONSTRAINT(c, n)	\
434	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c))
435
436/* Like UEVENT_CONSTRAINT, but match flags too */
437#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n)	\
438	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
439
440#define INTEL_EXCLUEVT_CONSTRAINT(c, n)	\
441	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
442			   HWEIGHT(n), 0, PERF_X86_EVENT_EXCL)
443
444#define INTEL_PLD_CONSTRAINT(c, n)	\
445	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
446			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
447
448#define INTEL_PST_CONSTRAINT(c, n)	\
449	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
450			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
451
452/* Event constraint, but match on all event flags too. */
453#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
454	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
455
456#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n)			\
457	EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
458
459/* Check only flags, but allow all event/umask */
460#define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\
461	EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
462
463/* Check flags and event code, and set the HSW store flag */
464#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \
465	__EVENT_CONSTRAINT(code, n, 			\
466			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
467			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
468
469/* Check flags and event code, and set the HSW load flag */
470#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \
471	__EVENT_CONSTRAINT(code, n,			\
472			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
473			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
474
475#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
476	__EVENT_CONSTRAINT_RANGE(code, end, n,				\
477			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
478			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
479
480#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
481	__EVENT_CONSTRAINT(code, n,			\
482			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
483			  HWEIGHT(n), 0, \
484			  PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL)
485
486/* Check flags and event code/umask, and set the HSW store flag */
487#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \
488	__EVENT_CONSTRAINT(code, n, 			\
489			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
490			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
491
492#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(code, n) \
493	__EVENT_CONSTRAINT(code, n,			\
494			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
495			  HWEIGHT(n), 0, \
496			  PERF_X86_EVENT_PEBS_ST_HSW|PERF_X86_EVENT_EXCL)
497
498/* Check flags and event code/umask, and set the HSW load flag */
499#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \
500	__EVENT_CONSTRAINT(code, n, 			\
501			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
502			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
503
504#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(code, n) \
505	__EVENT_CONSTRAINT(code, n,			\
506			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
507			  HWEIGHT(n), 0, \
508			  PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL)
509
510/* Check flags and event code/umask, and set the HSW N/A flag */
511#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
512	__EVENT_CONSTRAINT(code, n, 			\
513			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
514			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
515
516
517/*
518 * We define the end marker as having a weight of -1
519 * to enable blacklisting of events using a counter bitmask
520 * of zero and thus a weight of zero.
521 * The end marker has a weight that cannot possibly be
522 * obtained from counting the bits in the bitmask.
523 */
524#define EVENT_CONSTRAINT_END { .weight = -1 }
525
526/*
527 * Check for end marker with weight == -1
528 */
529#define for_each_event_constraint(e, c)	\
530	for ((e) = (c); (e)->weight != -1; (e)++)
531
532/*
533 * Extra registers for specific events.
534 *
535 * Some events need large masks and require external MSRs.
536 * Those extra MSRs end up being shared for all events on
537 * a PMU and sometimes between PMU of sibling HT threads.
538 * In either case, the kernel needs to handle conflicting
539 * accesses to those extra, shared, regs. The data structure
540 * to manage those registers is stored in cpu_hw_event.
541 */
542struct extra_reg {
543	unsigned int		event;
544	unsigned int		msr;
545	u64			config_mask;
546	u64			valid_mask;
547	int			idx;  /* per_xxx->regs[] reg index */
548	bool			extra_msr_access;
549};
550
551#define EVENT_EXTRA_REG(e, ms, m, vm, i) {	\
552	.event = (e),			\
553	.msr = (ms),			\
554	.config_mask = (m),		\
555	.valid_mask = (vm),		\
556	.idx = EXTRA_REG_##i,		\
557	.extra_msr_access = true,	\
558	}
559
560#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\
561	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx)
562
563#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \
564	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \
565			ARCH_PERFMON_EVENTSEL_UMASK, vm, idx)
566
567#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \
568	INTEL_UEVENT_EXTRA_REG(c, \
569			       MSR_PEBS_LD_LAT_THRESHOLD, \
570			       0xffff, \
571			       LDLAT)
572
573#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0)
574
575union perf_capabilities {
576	struct {
577		u64	lbr_format:6;
578		u64	pebs_trap:1;
579		u64	pebs_arch_reg:1;
580		u64	pebs_format:4;
581		u64	smm_freeze:1;
582		/*
583		 * PMU supports separate counter range for writing
584		 * values > 32bit.
585		 */
586		u64	full_width_write:1;
587		u64     pebs_baseline:1;
588		u64	perf_metrics:1;
589		u64	pebs_output_pt_available:1;
590		u64	anythread_deprecated:1;
591	};
592	u64	capabilities;
593};
594
595struct x86_pmu_quirk {
596	struct x86_pmu_quirk *next;
597	void (*func)(void);
598};
599
600union x86_pmu_config {
601	struct {
602		u64 event:8,
603		    umask:8,
604		    usr:1,
605		    os:1,
606		    edge:1,
607		    pc:1,
608		    interrupt:1,
609		    __reserved1:1,
610		    en:1,
611		    inv:1,
612		    cmask:8,
613		    event2:4,
614		    __reserved2:4,
615		    go:1,
616		    ho:1;
617	} bits;
618	u64 value;
619};
620
621#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value
622
623enum {
624	x86_lbr_exclusive_lbr,
625	x86_lbr_exclusive_bts,
626	x86_lbr_exclusive_pt,
627	x86_lbr_exclusive_max,
628};
629
630/*
631 * struct x86_pmu - generic x86 pmu
632 */
633struct x86_pmu {
634	/*
635	 * Generic x86 PMC bits
636	 */
637	const char	*name;
638	int		version;
639	int		(*handle_irq)(struct pt_regs *);
640	void		(*disable_all)(void);
641	void		(*enable_all)(int added);
642	void		(*enable)(struct perf_event *);
643	void		(*disable)(struct perf_event *);
644	void		(*add)(struct perf_event *);
645	void		(*del)(struct perf_event *);
646	void		(*read)(struct perf_event *event);
647	int		(*hw_config)(struct perf_event *event);
648	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
649	unsigned	eventsel;
650	unsigned	perfctr;
651	int		(*addr_offset)(int index, bool eventsel);
652	int		(*rdpmc_index)(int index);
653	u64		(*event_map)(int);
654	int		max_events;
655	int		num_counters;
656	int		num_counters_fixed;
657	int		cntval_bits;
658	u64		cntval_mask;
659	union {
660			unsigned long events_maskl;
661			unsigned long events_mask[BITS_TO_LONGS(ARCH_PERFMON_EVENTS_COUNT)];
662	};
663	int		events_mask_len;
664	int		apic;
665	u64		max_period;
666	struct event_constraint *
667			(*get_event_constraints)(struct cpu_hw_events *cpuc,
668						 int idx,
669						 struct perf_event *event);
670
671	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
672						 struct perf_event *event);
673
674	void		(*start_scheduling)(struct cpu_hw_events *cpuc);
675
676	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
677
678	void		(*stop_scheduling)(struct cpu_hw_events *cpuc);
679
680	struct event_constraint *event_constraints;
681	struct x86_pmu_quirk *quirks;
682	int		perfctr_second_write;
683	u64		(*limit_period)(struct perf_event *event, u64 l);
684
685	/* PMI handler bits */
686	unsigned int	late_ack		:1,
687			enabled_ack		:1,
688			counter_freezing	:1;
689	/*
690	 * sysfs attrs
691	 */
692	int		attr_rdpmc_broken;
693	int		attr_rdpmc;
694	struct attribute **format_attrs;
695
696	ssize_t		(*events_sysfs_show)(char *page, u64 config);
697	const struct attribute_group **attr_update;
698
699	unsigned long	attr_freeze_on_smi;
700
701	/*
702	 * CPU Hotplug hooks
703	 */
704	int		(*cpu_prepare)(int cpu);
705	void		(*cpu_starting)(int cpu);
706	void		(*cpu_dying)(int cpu);
707	void		(*cpu_dead)(int cpu);
708
709	void		(*check_microcode)(void);
710	void		(*sched_task)(struct perf_event_context *ctx,
711				      bool sched_in);
712
713	/*
714	 * Intel Arch Perfmon v2+
715	 */
716	u64			intel_ctrl;
717	union perf_capabilities intel_cap;
718
719	/*
720	 * Intel DebugStore bits
721	 */
722	unsigned int	bts			:1,
723			bts_active		:1,
724			pebs			:1,
725			pebs_active		:1,
726			pebs_broken		:1,
727			pebs_prec_dist		:1,
728			pebs_no_tlb		:1,
729			pebs_no_isolation	:1;
730	int		pebs_record_size;
731	int		pebs_buffer_size;
732	int		max_pebs_events;
733	void		(*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
734	struct event_constraint *pebs_constraints;
735	void		(*pebs_aliases)(struct perf_event *event);
736	unsigned long	large_pebs_flags;
737	u64		rtm_abort_event;
738
739	/*
740	 * Intel LBR
741	 */
742	unsigned int	lbr_tos, lbr_from, lbr_to,
743			lbr_info, lbr_nr;	   /* LBR base regs and size */
744	union {
745		u64	lbr_sel_mask;		   /* LBR_SELECT valid bits */
746		u64	lbr_ctl_mask;		   /* LBR_CTL valid bits */
747	};
748	union {
749		const int	*lbr_sel_map;	   /* lbr_select mappings */
750		int		*lbr_ctl_map;	   /* LBR_CTL mappings */
751	};
752	bool		lbr_double_abort;	   /* duplicated lbr aborts */
753	bool		lbr_pt_coexist;		   /* (LBR|BTS) may coexist with PT */
754
755	/*
756	 * Intel Architectural LBR CPUID Enumeration
757	 */
758	unsigned int	lbr_depth_mask:8;
759	unsigned int	lbr_deep_c_reset:1;
760	unsigned int	lbr_lip:1;
761	unsigned int	lbr_cpl:1;
762	unsigned int	lbr_filter:1;
763	unsigned int	lbr_call_stack:1;
764	unsigned int	lbr_mispred:1;
765	unsigned int	lbr_timed_lbr:1;
766	unsigned int	lbr_br_type:1;
767
768	void		(*lbr_reset)(void);
769	void		(*lbr_read)(struct cpu_hw_events *cpuc);
770	void		(*lbr_save)(void *ctx);
771	void		(*lbr_restore)(void *ctx);
772
773	/*
774	 * Intel PT/LBR/BTS are exclusive
775	 */
776	atomic_t	lbr_exclusive[x86_lbr_exclusive_max];
777
778	/*
779	 * Intel perf metrics
780	 */
781	u64		(*update_topdown_event)(struct perf_event *event);
782	int		(*set_topdown_event_period)(struct perf_event *event);
783
784	/*
785	 * perf task context (i.e. struct perf_event_context::task_ctx_data)
786	 * switch helper to bridge calls from perf/core to perf/x86.
787	 * See struct pmu::swap_task_ctx() usage for examples;
788	 */
789	void		(*swap_task_ctx)(struct perf_event_context *prev,
790					 struct perf_event_context *next);
791
792	/*
793	 * AMD bits
794	 */
795	unsigned int	amd_nb_constraints : 1;
796	u64		perf_ctr_pair_en;
797
798	/*
799	 * Extra registers for events
800	 */
801	struct extra_reg *extra_regs;
802	unsigned int flags;
803
804	/*
805	 * Intel host/guest support (KVM)
806	 */
807	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
808
809	/*
810	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
811	 */
812	int (*check_period) (struct perf_event *event, u64 period);
813
814	int (*aux_output_match) (struct perf_event *event);
815};
816
817struct x86_perf_task_context_opt {
818	int lbr_callstack_users;
819	int lbr_stack_state;
820	int log_id;
821};
822
823struct x86_perf_task_context {
824	u64 lbr_sel;
825	int tos;
826	int valid_lbrs;
827	struct x86_perf_task_context_opt opt;
828	struct lbr_entry lbr[MAX_LBR_ENTRIES];
829};
830
831struct x86_perf_task_context_arch_lbr {
832	struct x86_perf_task_context_opt opt;
833	struct lbr_entry entries[];
834};
835
836/*
837 * Add padding to guarantee the 64-byte alignment of the state buffer.
838 *
839 * The structure is dynamically allocated. The size of the LBR state may vary
840 * based on the number of LBR registers.
841 *
842 * Do not put anything after the LBR state.
843 */
844struct x86_perf_task_context_arch_lbr_xsave {
845	struct x86_perf_task_context_opt		opt;
846
847	union {
848		struct xregs_state			xsave;
849		struct {
850			struct fxregs_state		i387;
851			struct xstate_header		header;
852			struct arch_lbr_state		lbr;
853		} __attribute__ ((packed, aligned (XSAVE_ALIGNMENT)));
854	};
855};
856
857#define x86_add_quirk(func_)						\
858do {									\
859	static struct x86_pmu_quirk __quirk __initdata = {		\
860		.func = func_,						\
861	};								\
862	__quirk.next = x86_pmu.quirks;					\
863	x86_pmu.quirks = &__quirk;					\
864} while (0)
865
866/*
867 * x86_pmu flags
868 */
869#define PMU_FL_NO_HT_SHARING	0x1 /* no hyper-threading resource sharing */
870#define PMU_FL_HAS_RSP_1	0x2 /* has 2 equivalent offcore_rsp regs   */
871#define PMU_FL_EXCL_CNTRS	0x4 /* has exclusive counter requirements  */
872#define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
873#define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
874#define PMU_FL_TFA		0x20 /* deal with TSX force abort */
875#define PMU_FL_PAIR		0x40 /* merge counters for large incr. events */
876
877#define EVENT_VAR(_id)  event_attr_##_id
878#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
879
880#define EVENT_ATTR(_name, _id)						\
881static struct perf_pmu_events_attr EVENT_VAR(_id) = {			\
882	.attr		= __ATTR(_name, 0444, events_sysfs_show, NULL),	\
883	.id		= PERF_COUNT_HW_##_id,				\
884	.event_str	= NULL,						\
885};
886
887#define EVENT_ATTR_STR(_name, v, str)					\
888static struct perf_pmu_events_attr event_attr_##v = {			\
889	.attr		= __ATTR(_name, 0444, events_sysfs_show, NULL),	\
890	.id		= 0,						\
891	.event_str	= str,						\
892};
893
894#define EVENT_ATTR_STR_HT(_name, v, noht, ht)				\
895static struct perf_pmu_events_ht_attr event_attr_##v = {		\
896	.attr		= __ATTR(_name, 0444, events_ht_sysfs_show, NULL),\
897	.id		= 0,						\
898	.event_str_noht	= noht,						\
899	.event_str_ht	= ht,						\
900}
901
902struct pmu *x86_get_pmu(unsigned int cpu);
903extern struct x86_pmu x86_pmu __read_mostly;
904
905static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
906{
907	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
908		return &((struct x86_perf_task_context_arch_lbr *)ctx)->opt;
909
910	return &((struct x86_perf_task_context *)ctx)->opt;
911}
912
913static inline bool x86_pmu_has_lbr_callstack(void)
914{
915	return  x86_pmu.lbr_sel_map &&
916		x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0;
917}
918
919DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
920
921int x86_perf_event_set_period(struct perf_event *event);
922
923/*
924 * Generalized hw caching related hw_event table, filled
925 * in on a per model basis. A value of 0 means
926 * 'not supported', -1 means 'hw_event makes no sense on
927 * this CPU', any other value means the raw hw_event
928 * ID.
929 */
930
931#define C(x) PERF_COUNT_HW_CACHE_##x
932
933extern u64 __read_mostly hw_cache_event_ids
934				[PERF_COUNT_HW_CACHE_MAX]
935				[PERF_COUNT_HW_CACHE_OP_MAX]
936				[PERF_COUNT_HW_CACHE_RESULT_MAX];
937extern u64 __read_mostly hw_cache_extra_regs
938				[PERF_COUNT_HW_CACHE_MAX]
939				[PERF_COUNT_HW_CACHE_OP_MAX]
940				[PERF_COUNT_HW_CACHE_RESULT_MAX];
941
942u64 x86_perf_event_update(struct perf_event *event);
943
944static inline unsigned int x86_pmu_config_addr(int index)
945{
946	return x86_pmu.eventsel + (x86_pmu.addr_offset ?
947				   x86_pmu.addr_offset(index, true) : index);
948}
949
950static inline unsigned int x86_pmu_event_addr(int index)
951{
952	return x86_pmu.perfctr + (x86_pmu.addr_offset ?
953				  x86_pmu.addr_offset(index, false) : index);
954}
955
956static inline int x86_pmu_rdpmc_index(int index)
957{
958	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
959}
960
961int x86_add_exclusive(unsigned int what);
962
963void x86_del_exclusive(unsigned int what);
964
965int x86_reserve_hardware(void);
966
967void x86_release_hardware(void);
968
969int x86_pmu_max_precise(void);
970
971void hw_perf_lbr_event_destroy(struct perf_event *event);
972
973int x86_setup_perfctr(struct perf_event *event);
974
975int x86_pmu_hw_config(struct perf_event *event);
976
977void x86_pmu_disable_all(void);
978
979static inline bool is_counter_pair(struct hw_perf_event *hwc)
980{
981	return hwc->flags & PERF_X86_EVENT_PAIR;
982}
983
984static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
985					  u64 enable_mask)
986{
987	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
988
989	if (hwc->extra_reg.reg)
990		wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
991
992	/*
993	 * Add enabled Merge event on next counter
994	 * if large increment event being enabled on this counter
995	 */
996	if (is_counter_pair(hwc))
997		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
998
999	wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
1000}
1001
1002void x86_pmu_enable_all(int added);
1003
1004int perf_assign_events(struct event_constraint **constraints, int n,
1005			int wmin, int wmax, int gpmax, int *assign);
1006int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
1007
1008void x86_pmu_stop(struct perf_event *event, int flags);
1009
1010static inline void x86_pmu_disable_event(struct perf_event *event)
1011{
1012	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
1013	struct hw_perf_event *hwc = &event->hw;
1014
1015	wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
1016
1017	if (is_counter_pair(hwc))
1018		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
1019}
1020
1021void x86_pmu_enable_event(struct perf_event *event);
1022
1023int x86_pmu_handle_irq(struct pt_regs *regs);
1024
1025extern struct event_constraint emptyconstraint;
1026
1027extern struct event_constraint unconstrained;
1028
1029static inline bool kernel_ip(unsigned long ip)
1030{
1031#ifdef CONFIG_X86_32
1032	return ip > PAGE_OFFSET;
1033#else
1034	return (long)ip < 0;
1035#endif
1036}
1037
1038/*
1039 * Not all PMUs provide the right context information to place the reported IP
1040 * into full context. Specifically segment registers are typically not
1041 * supplied.
1042 *
1043 * Assuming the address is a linear address (it is for IBS), we fake the CS and
1044 * vm86 mode using the known zero-based code segment and 'fix up' the registers
1045 * to reflect this.
1046 *
1047 * Intel PEBS/LBR appear to typically provide the effective address, nothing
1048 * much we can do about that but pray and treat it like a linear address.
1049 */
1050static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
1051{
1052	regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS;
1053	if (regs->flags & X86_VM_MASK)
1054		regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK);
1055	regs->ip = ip;
1056}
1057
1058ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
1059ssize_t intel_event_sysfs_show(char *page, u64 config);
1060
1061ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
1062			  char *page);
1063ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
1064			  char *page);
1065
1066#ifdef CONFIG_CPU_SUP_AMD
1067
1068int amd_pmu_init(void);
1069
1070#else /* CONFIG_CPU_SUP_AMD */
1071
1072static inline int amd_pmu_init(void)
1073{
1074	return 0;
1075}
1076
1077#endif /* CONFIG_CPU_SUP_AMD */
1078
1079static inline int is_pebs_pt(struct perf_event *event)
1080{
1081	return !!(event->hw.flags & PERF_X86_EVENT_PEBS_VIA_PT);
1082}
1083
1084#ifdef CONFIG_CPU_SUP_INTEL
1085
1086static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
1087{
1088	struct hw_perf_event *hwc = &event->hw;
1089	unsigned int hw_event, bts_event;
1090
1091	if (event->attr.freq)
1092		return false;
1093
1094	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
1095	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
1096
1097	return hw_event == bts_event && period == 1;
1098}
1099
1100static inline bool intel_pmu_has_bts(struct perf_event *event)
1101{
1102	struct hw_perf_event *hwc = &event->hw;
1103
1104	return intel_pmu_has_bts_period(event, hwc->sample_period);
1105}
1106
1107int intel_pmu_save_and_restart(struct perf_event *event);
1108
1109struct event_constraint *
1110x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
1111			  struct perf_event *event);
1112
1113extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu);
1114extern void intel_cpuc_finish(struct cpu_hw_events *cpuc);
1115
1116int intel_pmu_init(void);
1117
1118void init_debug_store_on_cpu(int cpu);
1119
1120void fini_debug_store_on_cpu(int cpu);
1121
1122void release_ds_buffers(void);
1123
1124void reserve_ds_buffers(void);
1125
1126void release_lbr_buffers(void);
1127
1128void reserve_lbr_buffers(void);
1129
1130extern struct event_constraint bts_constraint;
1131extern struct event_constraint vlbr_constraint;
1132
1133void intel_pmu_enable_bts(u64 config);
1134
1135void intel_pmu_disable_bts(void);
1136
1137int intel_pmu_drain_bts_buffer(void);
1138
1139extern struct event_constraint intel_core2_pebs_event_constraints[];
1140
1141extern struct event_constraint intel_atom_pebs_event_constraints[];
1142
1143extern struct event_constraint intel_slm_pebs_event_constraints[];
1144
1145extern struct event_constraint intel_glm_pebs_event_constraints[];
1146
1147extern struct event_constraint intel_glp_pebs_event_constraints[];
1148
1149extern struct event_constraint intel_nehalem_pebs_event_constraints[];
1150
1151extern struct event_constraint intel_westmere_pebs_event_constraints[];
1152
1153extern struct event_constraint intel_snb_pebs_event_constraints[];
1154
1155extern struct event_constraint intel_ivb_pebs_event_constraints[];
1156
1157extern struct event_constraint intel_hsw_pebs_event_constraints[];
1158
1159extern struct event_constraint intel_bdw_pebs_event_constraints[];
1160
1161extern struct event_constraint intel_skl_pebs_event_constraints[];
1162
1163extern struct event_constraint intel_icl_pebs_event_constraints[];
1164
1165struct event_constraint *intel_pebs_constraints(struct perf_event *event);
1166
1167void intel_pmu_pebs_add(struct perf_event *event);
1168
1169void intel_pmu_pebs_del(struct perf_event *event);
1170
1171void intel_pmu_pebs_enable(struct perf_event *event);
1172
1173void intel_pmu_pebs_disable(struct perf_event *event);
1174
1175void intel_pmu_pebs_enable_all(void);
1176
1177void intel_pmu_pebs_disable_all(void);
1178
1179void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
1180
1181void intel_pmu_auto_reload_read(struct perf_event *event);
1182
1183void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
1184
1185void intel_ds_init(void);
1186
1187void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
1188				 struct perf_event_context *next);
1189
1190void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
1191
1192u64 lbr_from_signext_quirk_wr(u64 val);
1193
1194void intel_pmu_lbr_reset(void);
1195
1196void intel_pmu_lbr_reset_32(void);
1197
1198void intel_pmu_lbr_reset_64(void);
1199
1200void intel_pmu_lbr_add(struct perf_event *event);
1201
1202void intel_pmu_lbr_del(struct perf_event *event);
1203
1204void intel_pmu_lbr_enable_all(bool pmi);
1205
1206void intel_pmu_lbr_disable_all(void);
1207
1208void intel_pmu_lbr_read(void);
1209
1210void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc);
1211
1212void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc);
1213
1214void intel_pmu_lbr_save(void *ctx);
1215
1216void intel_pmu_lbr_restore(void *ctx);
1217
1218void intel_pmu_lbr_init_core(void);
1219
1220void intel_pmu_lbr_init_nhm(void);
1221
1222void intel_pmu_lbr_init_atom(void);
1223
1224void intel_pmu_lbr_init_slm(void);
1225
1226void intel_pmu_lbr_init_snb(void);
1227
1228void intel_pmu_lbr_init_hsw(void);
1229
1230void intel_pmu_lbr_init_skl(void);
1231
1232void intel_pmu_lbr_init_knl(void);
1233
1234void intel_pmu_arch_lbr_init(void);
1235
1236void intel_pmu_pebs_data_source_nhm(void);
1237
1238void intel_pmu_pebs_data_source_skl(bool pmem);
1239
1240int intel_pmu_setup_lbr_filter(struct perf_event *event);
1241
1242void intel_pt_interrupt(void);
1243
1244int intel_bts_interrupt(void);
1245
1246void intel_bts_enable_local(void);
1247
1248void intel_bts_disable_local(void);
1249
1250int p4_pmu_init(void);
1251
1252int p6_pmu_init(void);
1253
1254int knc_pmu_init(void);
1255
1256static inline int is_ht_workaround_enabled(void)
1257{
1258	return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
1259}
1260
1261#else /* CONFIG_CPU_SUP_INTEL */
1262
1263static inline void reserve_ds_buffers(void)
1264{
1265}
1266
1267static inline void release_ds_buffers(void)
1268{
1269}
1270
1271static inline void release_lbr_buffers(void)
1272{
1273}
1274
1275static inline void reserve_lbr_buffers(void)
1276{
1277}
1278
1279static inline int intel_pmu_init(void)
1280{
1281	return 0;
1282}
1283
1284static inline int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
1285{
1286	return 0;
1287}
1288
1289static inline void intel_cpuc_finish(struct cpu_hw_events *cpuc)
1290{
1291}
1292
1293static inline int is_ht_workaround_enabled(void)
1294{
1295	return 0;
1296}
1297#endif /* CONFIG_CPU_SUP_INTEL */
1298
1299#if ((defined CONFIG_CPU_SUP_CENTAUR) || (defined CONFIG_CPU_SUP_ZHAOXIN))
1300int zhaoxin_pmu_init(void);
1301#else
1302static inline int zhaoxin_pmu_init(void)
1303{
1304	return 0;
1305}
1306#endif /*CONFIG_CPU_SUP_CENTAUR or CONFIG_CPU_SUP_ZHAOXIN*/
1307