xref: /kernel/linux/linux-5.10/arch/x86/events/intel/lbr.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0
2#include <linux/perf_event.h>
3#include <linux/types.h>
4
5#include <asm/perf_event.h>
6#include <asm/msr.h>
7#include <asm/insn.h>
8
9#include "../perf_event.h"
10
11static const enum {
12	LBR_EIP_FLAGS		= 1,
13	LBR_TSX			= 2,
14} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = {
15	[LBR_FORMAT_EIP_FLAGS]  = LBR_EIP_FLAGS,
16	[LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX,
17};
18
19/*
20 * Intel LBR_SELECT bits
21 * Intel Vol3a, April 2011, Section 16.7 Table 16-10
22 *
23 * Hardware branch filter (not available on all CPUs)
24 */
25#define LBR_KERNEL_BIT		0 /* do not capture at ring0 */
26#define LBR_USER_BIT		1 /* do not capture at ring > 0 */
27#define LBR_JCC_BIT		2 /* do not capture conditional branches */
28#define LBR_REL_CALL_BIT	3 /* do not capture relative calls */
29#define LBR_IND_CALL_BIT	4 /* do not capture indirect calls */
30#define LBR_RETURN_BIT		5 /* do not capture near returns */
31#define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
32#define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
33#define LBR_FAR_BIT		8 /* do not capture far branches */
34#define LBR_CALL_STACK_BIT	9 /* enable call stack */
35
36/*
37 * Following bit only exists in Linux; we mask it out before writing it to
38 * the actual MSR. But it helps the constraint perf code to understand
39 * that this is a separate configuration.
40 */
41#define LBR_NO_INFO_BIT	       63 /* don't read LBR_INFO. */
42
43#define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
44#define LBR_USER	(1 << LBR_USER_BIT)
45#define LBR_JCC		(1 << LBR_JCC_BIT)
46#define LBR_REL_CALL	(1 << LBR_REL_CALL_BIT)
47#define LBR_IND_CALL	(1 << LBR_IND_CALL_BIT)
48#define LBR_RETURN	(1 << LBR_RETURN_BIT)
49#define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
50#define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
51#define LBR_FAR		(1 << LBR_FAR_BIT)
52#define LBR_CALL_STACK	(1 << LBR_CALL_STACK_BIT)
53#define LBR_NO_INFO	(1ULL << LBR_NO_INFO_BIT)
54
55#define LBR_PLM (LBR_KERNEL | LBR_USER)
56
57#define LBR_SEL_MASK	0x3ff	/* valid bits in LBR_SELECT */
58#define LBR_NOT_SUPP	-1	/* LBR filter not supported */
59#define LBR_IGN		0	/* ignored */
60
61#define LBR_ANY		 \
62	(LBR_JCC	|\
63	 LBR_REL_CALL	|\
64	 LBR_IND_CALL	|\
65	 LBR_RETURN	|\
66	 LBR_REL_JMP	|\
67	 LBR_IND_JMP	|\
68	 LBR_FAR)
69
70#define LBR_FROM_FLAG_MISPRED	BIT_ULL(63)
71#define LBR_FROM_FLAG_IN_TX	BIT_ULL(62)
72#define LBR_FROM_FLAG_ABORT	BIT_ULL(61)
73
74#define LBR_FROM_SIGNEXT_2MSB	(BIT_ULL(60) | BIT_ULL(59))
75
76/*
77 * x86control flow change classification
78 * x86control flow changes include branches, interrupts, traps, faults
79 */
80enum {
81	X86_BR_NONE		= 0,      /* unknown */
82
83	X86_BR_USER		= 1 << 0, /* branch target is user */
84	X86_BR_KERNEL		= 1 << 1, /* branch target is kernel */
85
86	X86_BR_CALL		= 1 << 2, /* call */
87	X86_BR_RET		= 1 << 3, /* return */
88	X86_BR_SYSCALL		= 1 << 4, /* syscall */
89	X86_BR_SYSRET		= 1 << 5, /* syscall return */
90	X86_BR_INT		= 1 << 6, /* sw interrupt */
91	X86_BR_IRET		= 1 << 7, /* return from interrupt */
92	X86_BR_JCC		= 1 << 8, /* conditional */
93	X86_BR_JMP		= 1 << 9, /* jump */
94	X86_BR_IRQ		= 1 << 10,/* hw interrupt or trap or fault */
95	X86_BR_IND_CALL		= 1 << 11,/* indirect calls */
96	X86_BR_ABORT		= 1 << 12,/* transaction abort */
97	X86_BR_IN_TX		= 1 << 13,/* in transaction */
98	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
99	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
100	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
101	X86_BR_IND_JMP		= 1 << 17,/* indirect jump */
102
103	X86_BR_TYPE_SAVE	= 1 << 18,/* indicate to save branch type */
104
105};
106
107#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
108#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX)
109
110#define X86_BR_ANY       \
111	(X86_BR_CALL    |\
112	 X86_BR_RET     |\
113	 X86_BR_SYSCALL |\
114	 X86_BR_SYSRET  |\
115	 X86_BR_INT     |\
116	 X86_BR_IRET    |\
117	 X86_BR_JCC     |\
118	 X86_BR_JMP	 |\
119	 X86_BR_IRQ	 |\
120	 X86_BR_ABORT	 |\
121	 X86_BR_IND_CALL |\
122	 X86_BR_IND_JMP  |\
123	 X86_BR_ZERO_CALL)
124
125#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
126
127#define X86_BR_ANY_CALL		 \
128	(X86_BR_CALL		|\
129	 X86_BR_IND_CALL	|\
130	 X86_BR_ZERO_CALL	|\
131	 X86_BR_SYSCALL		|\
132	 X86_BR_IRQ		|\
133	 X86_BR_INT)
134
135/*
136 * Intel LBR_CTL bits
137 *
138 * Hardware branch filter for Arch LBR
139 */
140#define ARCH_LBR_KERNEL_BIT		1  /* capture at ring0 */
141#define ARCH_LBR_USER_BIT		2  /* capture at ring > 0 */
142#define ARCH_LBR_CALL_STACK_BIT		3  /* enable call stack */
143#define ARCH_LBR_JCC_BIT		16 /* capture conditional branches */
144#define ARCH_LBR_REL_JMP_BIT		17 /* capture relative jumps */
145#define ARCH_LBR_IND_JMP_BIT		18 /* capture indirect jumps */
146#define ARCH_LBR_REL_CALL_BIT		19 /* capture relative calls */
147#define ARCH_LBR_IND_CALL_BIT		20 /* capture indirect calls */
148#define ARCH_LBR_RETURN_BIT		21 /* capture near returns */
149#define ARCH_LBR_OTHER_BRANCH_BIT	22 /* capture other branches */
150
151#define ARCH_LBR_KERNEL			(1ULL << ARCH_LBR_KERNEL_BIT)
152#define ARCH_LBR_USER			(1ULL << ARCH_LBR_USER_BIT)
153#define ARCH_LBR_CALL_STACK		(1ULL << ARCH_LBR_CALL_STACK_BIT)
154#define ARCH_LBR_JCC			(1ULL << ARCH_LBR_JCC_BIT)
155#define ARCH_LBR_REL_JMP		(1ULL << ARCH_LBR_REL_JMP_BIT)
156#define ARCH_LBR_IND_JMP		(1ULL << ARCH_LBR_IND_JMP_BIT)
157#define ARCH_LBR_REL_CALL		(1ULL << ARCH_LBR_REL_CALL_BIT)
158#define ARCH_LBR_IND_CALL		(1ULL << ARCH_LBR_IND_CALL_BIT)
159#define ARCH_LBR_RETURN			(1ULL << ARCH_LBR_RETURN_BIT)
160#define ARCH_LBR_OTHER_BRANCH		(1ULL << ARCH_LBR_OTHER_BRANCH_BIT)
161
162#define ARCH_LBR_ANY			 \
163	(ARCH_LBR_JCC			|\
164	 ARCH_LBR_REL_JMP		|\
165	 ARCH_LBR_IND_JMP		|\
166	 ARCH_LBR_REL_CALL		|\
167	 ARCH_LBR_IND_CALL		|\
168	 ARCH_LBR_RETURN		|\
169	 ARCH_LBR_OTHER_BRANCH)
170
171#define ARCH_LBR_CTL_MASK			0x7f000e
172
173static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
174
175static __always_inline bool is_lbr_call_stack_bit_set(u64 config)
176{
177	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
178		return !!(config & ARCH_LBR_CALL_STACK);
179
180	return !!(config & LBR_CALL_STACK);
181}
182
183/*
184 * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
185 * otherwise it becomes near impossible to get a reliable stack.
186 */
187
188static void __intel_pmu_lbr_enable(bool pmi)
189{
190	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
191	u64 debugctl, lbr_select = 0, orig_debugctl;
192
193	/*
194	 * No need to unfreeze manually, as v4 can do that as part
195	 * of the GLOBAL_STATUS ack.
196	 */
197	if (pmi && x86_pmu.version >= 4)
198		return;
199
200	/*
201	 * No need to reprogram LBR_SELECT in a PMI, as it
202	 * did not change.
203	 */
204	if (cpuc->lbr_sel)
205		lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
206	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && !pmi && cpuc->lbr_sel)
207		wrmsrl(MSR_LBR_SELECT, lbr_select);
208
209	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
210	orig_debugctl = debugctl;
211
212	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
213		debugctl |= DEBUGCTLMSR_LBR;
214	/*
215	 * LBR callstack does not work well with FREEZE_LBRS_ON_PMI.
216	 * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions
217	 * may cause superfluous increase/decrease of LBR_TOS.
218	 */
219	if (is_lbr_call_stack_bit_set(lbr_select))
220		debugctl &= ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
221	else
222		debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
223
224	if (orig_debugctl != debugctl)
225		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
226
227	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
228		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
229}
230
231static void __intel_pmu_lbr_disable(void)
232{
233	u64 debugctl;
234
235	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
236		wrmsrl(MSR_ARCH_LBR_CTL, 0);
237		return;
238	}
239
240	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
241	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
242	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
243}
244
245void intel_pmu_lbr_reset_32(void)
246{
247	int i;
248
249	for (i = 0; i < x86_pmu.lbr_nr; i++)
250		wrmsrl(x86_pmu.lbr_from + i, 0);
251}
252
253void intel_pmu_lbr_reset_64(void)
254{
255	int i;
256
257	for (i = 0; i < x86_pmu.lbr_nr; i++) {
258		wrmsrl(x86_pmu.lbr_from + i, 0);
259		wrmsrl(x86_pmu.lbr_to   + i, 0);
260		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
261			wrmsrl(x86_pmu.lbr_info + i, 0);
262	}
263}
264
265static void intel_pmu_arch_lbr_reset(void)
266{
267	/* Write to ARCH_LBR_DEPTH MSR, all LBR entries are reset to 0 */
268	wrmsrl(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
269}
270
271void intel_pmu_lbr_reset(void)
272{
273	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
274
275	if (!x86_pmu.lbr_nr)
276		return;
277
278	x86_pmu.lbr_reset();
279
280	cpuc->last_task_ctx = NULL;
281	cpuc->last_log_id = 0;
282}
283
284/*
285 * TOS = most recently recorded branch
286 */
287static inline u64 intel_pmu_lbr_tos(void)
288{
289	u64 tos;
290
291	rdmsrl(x86_pmu.lbr_tos, tos);
292	return tos;
293}
294
295enum {
296	LBR_NONE,
297	LBR_VALID,
298};
299
300/*
301 * For formats with LBR_TSX flags (e.g. LBR_FORMAT_EIP_FLAGS2), bits 61:62 in
302 * MSR_LAST_BRANCH_FROM_x are the TSX flags when TSX is supported, but when
303 * TSX is not supported they have no consistent behavior:
304 *
305 *   - For wrmsr(), bits 61:62 are considered part of the sign extension.
306 *   - For HW updates (branch captures) bits 61:62 are always OFF and are not
307 *     part of the sign extension.
308 *
309 * Therefore, if:
310 *
311 *   1) LBR has TSX format
312 *   2) CPU has no TSX support enabled
313 *
314 * ... then any value passed to wrmsr() must be sign extended to 63 bits and any
315 * value from rdmsr() must be converted to have a 61 bits sign extension,
316 * ignoring the TSX flags.
317 */
318static inline bool lbr_from_signext_quirk_needed(void)
319{
320	int lbr_format = x86_pmu.intel_cap.lbr_format;
321	bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) ||
322			   boot_cpu_has(X86_FEATURE_RTM);
323
324	return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX);
325}
326
327static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key);
328
329/* If quirk is enabled, ensure sign extension is 63 bits: */
330inline u64 lbr_from_signext_quirk_wr(u64 val)
331{
332	if (static_branch_unlikely(&lbr_from_quirk_key)) {
333		/*
334		 * Sign extend into bits 61:62 while preserving bit 63.
335		 *
336		 * Quirk is enabled when TSX is disabled. Therefore TSX bits
337		 * in val are always OFF and must be changed to be sign
338		 * extension bits. Since bits 59:60 are guaranteed to be
339		 * part of the sign extension bits, we can just copy them
340		 * to 61:62.
341		 */
342		val |= (LBR_FROM_SIGNEXT_2MSB & val) << 2;
343	}
344	return val;
345}
346
347/*
348 * If quirk is needed, ensure sign extension is 61 bits:
349 */
350static u64 lbr_from_signext_quirk_rd(u64 val)
351{
352	if (static_branch_unlikely(&lbr_from_quirk_key)) {
353		/*
354		 * Quirk is on when TSX is not enabled. Therefore TSX
355		 * flags must be read as OFF.
356		 */
357		val &= ~(LBR_FROM_FLAG_IN_TX | LBR_FROM_FLAG_ABORT);
358	}
359	return val;
360}
361
362static __always_inline void wrlbr_from(unsigned int idx, u64 val)
363{
364	val = lbr_from_signext_quirk_wr(val);
365	wrmsrl(x86_pmu.lbr_from + idx, val);
366}
367
368static __always_inline void wrlbr_to(unsigned int idx, u64 val)
369{
370	wrmsrl(x86_pmu.lbr_to + idx, val);
371}
372
373static __always_inline void wrlbr_info(unsigned int idx, u64 val)
374{
375	wrmsrl(x86_pmu.lbr_info + idx, val);
376}
377
378static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
379{
380	u64 val;
381
382	if (lbr)
383		return lbr->from;
384
385	rdmsrl(x86_pmu.lbr_from + idx, val);
386
387	return lbr_from_signext_quirk_rd(val);
388}
389
390static __always_inline u64 rdlbr_to(unsigned int idx, struct lbr_entry *lbr)
391{
392	u64 val;
393
394	if (lbr)
395		return lbr->to;
396
397	rdmsrl(x86_pmu.lbr_to + idx, val);
398
399	return val;
400}
401
402static __always_inline u64 rdlbr_info(unsigned int idx, struct lbr_entry *lbr)
403{
404	u64 val;
405
406	if (lbr)
407		return lbr->info;
408
409	rdmsrl(x86_pmu.lbr_info + idx, val);
410
411	return val;
412}
413
414static inline void
415wrlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
416{
417	wrlbr_from(idx, lbr->from);
418	wrlbr_to(idx, lbr->to);
419	if (need_info)
420		wrlbr_info(idx, lbr->info);
421}
422
423static inline bool
424rdlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
425{
426	u64 from = rdlbr_from(idx, NULL);
427
428	/* Don't read invalid entry */
429	if (!from)
430		return false;
431
432	lbr->from = from;
433	lbr->to = rdlbr_to(idx, NULL);
434	if (need_info)
435		lbr->info = rdlbr_info(idx, NULL);
436
437	return true;
438}
439
440void intel_pmu_lbr_restore(void *ctx)
441{
442	bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO;
443	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
444	struct x86_perf_task_context *task_ctx = ctx;
445	int i;
446	unsigned lbr_idx, mask;
447	u64 tos = task_ctx->tos;
448
449	mask = x86_pmu.lbr_nr - 1;
450	for (i = 0; i < task_ctx->valid_lbrs; i++) {
451		lbr_idx = (tos - i) & mask;
452		wrlbr_all(&task_ctx->lbr[i], lbr_idx, need_info);
453	}
454
455	for (; i < x86_pmu.lbr_nr; i++) {
456		lbr_idx = (tos - i) & mask;
457		wrlbr_from(lbr_idx, 0);
458		wrlbr_to(lbr_idx, 0);
459		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
460			wrlbr_info(lbr_idx, 0);
461	}
462
463	wrmsrl(x86_pmu.lbr_tos, tos);
464
465	if (cpuc->lbr_select)
466		wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
467}
468
469static void intel_pmu_arch_lbr_restore(void *ctx)
470{
471	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
472	struct lbr_entry *entries = task_ctx->entries;
473	int i;
474
475	/* Fast reset the LBRs before restore if the call stack is not full. */
476	if (!entries[x86_pmu.lbr_nr - 1].from)
477		intel_pmu_arch_lbr_reset();
478
479	for (i = 0; i < x86_pmu.lbr_nr; i++) {
480		if (!entries[i].from)
481			break;
482		wrlbr_all(&entries[i], i, true);
483	}
484}
485
486/*
487 * Restore the Architecture LBR state from the xsave area in the perf
488 * context data for the task via the XRSTORS instruction.
489 */
490static void intel_pmu_arch_lbr_xrstors(void *ctx)
491{
492	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
493
494	copy_kernel_to_dynamic_supervisor(&task_ctx->xsave, XFEATURE_MASK_LBR);
495}
496
497static __always_inline bool lbr_is_reset_in_cstate(void *ctx)
498{
499	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
500		return x86_pmu.lbr_deep_c_reset && !rdlbr_from(0, NULL);
501
502	return !rdlbr_from(((struct x86_perf_task_context *)ctx)->tos, NULL);
503}
504
505static void __intel_pmu_lbr_restore(void *ctx)
506{
507	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
508
509	if (task_context_opt(ctx)->lbr_callstack_users == 0 ||
510	    task_context_opt(ctx)->lbr_stack_state == LBR_NONE) {
511		intel_pmu_lbr_reset();
512		return;
513	}
514
515	/*
516	 * Does not restore the LBR registers, if
517	 * - No one else touched them, and
518	 * - Was not cleared in Cstate
519	 */
520	if ((ctx == cpuc->last_task_ctx) &&
521	    (task_context_opt(ctx)->log_id == cpuc->last_log_id) &&
522	    !lbr_is_reset_in_cstate(ctx)) {
523		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
524		return;
525	}
526
527	x86_pmu.lbr_restore(ctx);
528
529	task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
530}
531
532void intel_pmu_lbr_save(void *ctx)
533{
534	bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO;
535	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
536	struct x86_perf_task_context *task_ctx = ctx;
537	unsigned lbr_idx, mask;
538	u64 tos;
539	int i;
540
541	mask = x86_pmu.lbr_nr - 1;
542	tos = intel_pmu_lbr_tos();
543	for (i = 0; i < x86_pmu.lbr_nr; i++) {
544		lbr_idx = (tos - i) & mask;
545		if (!rdlbr_all(&task_ctx->lbr[i], lbr_idx, need_info))
546			break;
547	}
548	task_ctx->valid_lbrs = i;
549	task_ctx->tos = tos;
550
551	if (cpuc->lbr_select)
552		rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
553}
554
555static void intel_pmu_arch_lbr_save(void *ctx)
556{
557	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
558	struct lbr_entry *entries = task_ctx->entries;
559	int i;
560
561	for (i = 0; i < x86_pmu.lbr_nr; i++) {
562		if (!rdlbr_all(&entries[i], i, true))
563			break;
564	}
565
566	/* LBR call stack is not full. Reset is required in restore. */
567	if (i < x86_pmu.lbr_nr)
568		entries[x86_pmu.lbr_nr - 1].from = 0;
569}
570
571/*
572 * Save the Architecture LBR state to the xsave area in the perf
573 * context data for the task via the XSAVES instruction.
574 */
575static void intel_pmu_arch_lbr_xsaves(void *ctx)
576{
577	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
578
579	copy_dynamic_supervisor_to_kernel(&task_ctx->xsave, XFEATURE_MASK_LBR);
580}
581
582static void __intel_pmu_lbr_save(void *ctx)
583{
584	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
585
586	if (task_context_opt(ctx)->lbr_callstack_users == 0) {
587		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
588		return;
589	}
590
591	x86_pmu.lbr_save(ctx);
592
593	task_context_opt(ctx)->lbr_stack_state = LBR_VALID;
594
595	cpuc->last_task_ctx = ctx;
596	cpuc->last_log_id = ++task_context_opt(ctx)->log_id;
597}
598
599void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
600				 struct perf_event_context *next)
601{
602	void *prev_ctx_data, *next_ctx_data;
603
604	swap(prev->task_ctx_data, next->task_ctx_data);
605
606	/*
607	 * Architecture specific synchronization makes sense in
608	 * case both prev->task_ctx_data and next->task_ctx_data
609	 * pointers are allocated.
610	 */
611
612	prev_ctx_data = next->task_ctx_data;
613	next_ctx_data = prev->task_ctx_data;
614
615	if (!prev_ctx_data || !next_ctx_data)
616		return;
617
618	swap(task_context_opt(prev_ctx_data)->lbr_callstack_users,
619	     task_context_opt(next_ctx_data)->lbr_callstack_users);
620}
621
622void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
623{
624	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
625	void *task_ctx;
626
627	if (!cpuc->lbr_users)
628		return;
629
630	/*
631	 * If LBR callstack feature is enabled and the stack was saved when
632	 * the task was scheduled out, restore the stack. Otherwise flush
633	 * the LBR stack.
634	 */
635	task_ctx = ctx ? ctx->task_ctx_data : NULL;
636	if (task_ctx) {
637		if (sched_in)
638			__intel_pmu_lbr_restore(task_ctx);
639		else
640			__intel_pmu_lbr_save(task_ctx);
641		return;
642	}
643
644	/*
645	 * Since a context switch can flip the address space and LBR entries
646	 * are not tagged with an identifier, we need to wipe the LBR, even for
647	 * per-cpu events. You simply cannot resolve the branches from the old
648	 * address space.
649	 */
650	if (sched_in)
651		intel_pmu_lbr_reset();
652}
653
654static inline bool branch_user_callstack(unsigned br_sel)
655{
656	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
657}
658
659void intel_pmu_lbr_add(struct perf_event *event)
660{
661	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
662
663	if (!x86_pmu.lbr_nr)
664		return;
665
666	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
667		cpuc->lbr_select = 1;
668
669	cpuc->br_sel = event->hw.branch_reg.reg;
670
671	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data)
672		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users++;
673
674	/*
675	 * Request pmu::sched_task() callback, which will fire inside the
676	 * regular perf event scheduling, so that call will:
677	 *
678	 *  - restore or wipe; when LBR-callstack,
679	 *  - wipe; otherwise,
680	 *
681	 * when this is from __perf_event_task_sched_in().
682	 *
683	 * However, if this is from perf_install_in_context(), no such callback
684	 * will follow and we'll need to reset the LBR here if this is the
685	 * first LBR event.
686	 *
687	 * The problem is, we cannot tell these cases apart... but we can
688	 * exclude the biggest chunk of cases by looking at
689	 * event->total_time_running. An event that has accrued runtime cannot
690	 * be 'new'. Conversely, a new event can get installed through the
691	 * context switch path for the first time.
692	 */
693	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
694		cpuc->lbr_pebs_users++;
695	perf_sched_cb_inc(event->ctx->pmu);
696	if (!cpuc->lbr_users++ && !event->total_time_running)
697		intel_pmu_lbr_reset();
698}
699
700void release_lbr_buffers(void)
701{
702	struct kmem_cache *kmem_cache;
703	struct cpu_hw_events *cpuc;
704	int cpu;
705
706	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
707		return;
708
709	for_each_possible_cpu(cpu) {
710		cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
711		kmem_cache = x86_get_pmu(cpu)->task_ctx_cache;
712		if (kmem_cache && cpuc->lbr_xsave) {
713			kmem_cache_free(kmem_cache, cpuc->lbr_xsave);
714			cpuc->lbr_xsave = NULL;
715		}
716	}
717}
718
719void reserve_lbr_buffers(void)
720{
721	struct kmem_cache *kmem_cache;
722	struct cpu_hw_events *cpuc;
723	int cpu;
724
725	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
726		return;
727
728	for_each_possible_cpu(cpu) {
729		cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
730		kmem_cache = x86_get_pmu(cpu)->task_ctx_cache;
731		if (!kmem_cache || cpuc->lbr_xsave)
732			continue;
733
734		cpuc->lbr_xsave = kmem_cache_alloc_node(kmem_cache,
735							GFP_KERNEL | __GFP_ZERO,
736							cpu_to_node(cpu));
737	}
738}
739
740void intel_pmu_lbr_del(struct perf_event *event)
741{
742	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
743
744	if (!x86_pmu.lbr_nr)
745		return;
746
747	if (branch_user_callstack(cpuc->br_sel) &&
748	    event->ctx->task_ctx_data)
749		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users--;
750
751	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
752		cpuc->lbr_select = 0;
753
754	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
755		cpuc->lbr_pebs_users--;
756	cpuc->lbr_users--;
757	WARN_ON_ONCE(cpuc->lbr_users < 0);
758	WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
759	perf_sched_cb_dec(event->ctx->pmu);
760}
761
762static inline bool vlbr_exclude_host(void)
763{
764	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
765
766	return test_bit(INTEL_PMC_IDX_FIXED_VLBR,
767		(unsigned long *)&cpuc->intel_ctrl_guest_mask);
768}
769
770void intel_pmu_lbr_enable_all(bool pmi)
771{
772	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
773
774	if (cpuc->lbr_users && !vlbr_exclude_host())
775		__intel_pmu_lbr_enable(pmi);
776}
777
778void intel_pmu_lbr_disable_all(void)
779{
780	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
781
782	if (cpuc->lbr_users && !vlbr_exclude_host())
783		__intel_pmu_lbr_disable();
784}
785
786void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
787{
788	unsigned long mask = x86_pmu.lbr_nr - 1;
789	u64 tos = intel_pmu_lbr_tos();
790	int i;
791
792	for (i = 0; i < x86_pmu.lbr_nr; i++) {
793		unsigned long lbr_idx = (tos - i) & mask;
794		union {
795			struct {
796				u32 from;
797				u32 to;
798			};
799			u64     lbr;
800		} msr_lastbranch;
801
802		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
803
804		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
805		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
806		cpuc->lbr_entries[i].mispred	= 0;
807		cpuc->lbr_entries[i].predicted	= 0;
808		cpuc->lbr_entries[i].in_tx	= 0;
809		cpuc->lbr_entries[i].abort	= 0;
810		cpuc->lbr_entries[i].cycles	= 0;
811		cpuc->lbr_entries[i].type	= 0;
812		cpuc->lbr_entries[i].reserved	= 0;
813	}
814	cpuc->lbr_stack.nr = i;
815	cpuc->lbr_stack.hw_idx = tos;
816}
817
818/*
819 * Due to lack of segmentation in Linux the effective address (offset)
820 * is the same as the linear address, allowing us to merge the LIP and EIP
821 * LBR formats.
822 */
823void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
824{
825	bool need_info = false, call_stack = false;
826	unsigned long mask = x86_pmu.lbr_nr - 1;
827	int lbr_format = x86_pmu.intel_cap.lbr_format;
828	u64 tos = intel_pmu_lbr_tos();
829	int i;
830	int out = 0;
831	int num = x86_pmu.lbr_nr;
832
833	if (cpuc->lbr_sel) {
834		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
835		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
836			call_stack = true;
837	}
838
839	for (i = 0; i < num; i++) {
840		unsigned long lbr_idx = (tos - i) & mask;
841		u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0;
842		int skip = 0;
843		u16 cycles = 0;
844		int lbr_flags = lbr_desc[lbr_format];
845
846		from = rdlbr_from(lbr_idx, NULL);
847		to   = rdlbr_to(lbr_idx, NULL);
848
849		/*
850		 * Read LBR call stack entries
851		 * until invalid entry (0s) is detected.
852		 */
853		if (call_stack && !from)
854			break;
855
856		if (lbr_format == LBR_FORMAT_INFO && need_info) {
857			u64 info;
858
859			info = rdlbr_info(lbr_idx, NULL);
860			mis = !!(info & LBR_INFO_MISPRED);
861			pred = !mis;
862			in_tx = !!(info & LBR_INFO_IN_TX);
863			abort = !!(info & LBR_INFO_ABORT);
864			cycles = (info & LBR_INFO_CYCLES);
865		}
866
867		if (lbr_format == LBR_FORMAT_TIME) {
868			mis = !!(from & LBR_FROM_FLAG_MISPRED);
869			pred = !mis;
870			skip = 1;
871			cycles = ((to >> 48) & LBR_INFO_CYCLES);
872
873			to = (u64)((((s64)to) << 16) >> 16);
874		}
875
876		if (lbr_flags & LBR_EIP_FLAGS) {
877			mis = !!(from & LBR_FROM_FLAG_MISPRED);
878			pred = !mis;
879			skip = 1;
880		}
881		if (lbr_flags & LBR_TSX) {
882			in_tx = !!(from & LBR_FROM_FLAG_IN_TX);
883			abort = !!(from & LBR_FROM_FLAG_ABORT);
884			skip = 3;
885		}
886		from = (u64)((((s64)from) << skip) >> skip);
887
888		/*
889		 * Some CPUs report duplicated abort records,
890		 * with the second entry not having an abort bit set.
891		 * Skip them here. This loop runs backwards,
892		 * so we need to undo the previous record.
893		 * If the abort just happened outside the window
894		 * the extra entry cannot be removed.
895		 */
896		if (abort && x86_pmu.lbr_double_abort && out > 0)
897			out--;
898
899		cpuc->lbr_entries[out].from	 = from;
900		cpuc->lbr_entries[out].to	 = to;
901		cpuc->lbr_entries[out].mispred	 = mis;
902		cpuc->lbr_entries[out].predicted = pred;
903		cpuc->lbr_entries[out].in_tx	 = in_tx;
904		cpuc->lbr_entries[out].abort	 = abort;
905		cpuc->lbr_entries[out].cycles	 = cycles;
906		cpuc->lbr_entries[out].type	 = 0;
907		cpuc->lbr_entries[out].reserved	 = 0;
908		out++;
909	}
910	cpuc->lbr_stack.nr = out;
911	cpuc->lbr_stack.hw_idx = tos;
912}
913
914static __always_inline int get_lbr_br_type(u64 info)
915{
916	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) || !x86_pmu.lbr_br_type)
917		return 0;
918
919	return (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET;
920}
921
922static __always_inline bool get_lbr_mispred(u64 info)
923{
924	if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred)
925		return 0;
926
927	return !!(info & LBR_INFO_MISPRED);
928}
929
930static __always_inline bool get_lbr_predicted(u64 info)
931{
932	if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred)
933		return 0;
934
935	return !(info & LBR_INFO_MISPRED);
936}
937
938static __always_inline u16 get_lbr_cycles(u64 info)
939{
940	if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
941	    !(x86_pmu.lbr_timed_lbr && info & LBR_INFO_CYC_CNT_VALID))
942		return 0;
943
944	return info & LBR_INFO_CYCLES;
945}
946
947static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
948				struct lbr_entry *entries)
949{
950	struct perf_branch_entry *e;
951	struct lbr_entry *lbr;
952	u64 from, to, info;
953	int i;
954
955	for (i = 0; i < x86_pmu.lbr_nr; i++) {
956		lbr = entries ? &entries[i] : NULL;
957		e = &cpuc->lbr_entries[i];
958
959		from = rdlbr_from(i, lbr);
960		/*
961		 * Read LBR entries until invalid entry (0s) is detected.
962		 */
963		if (!from)
964			break;
965
966		to = rdlbr_to(i, lbr);
967		info = rdlbr_info(i, lbr);
968
969		e->from		= from;
970		e->to		= to;
971		e->mispred	= get_lbr_mispred(info);
972		e->predicted	= get_lbr_predicted(info);
973		e->in_tx	= !!(info & LBR_INFO_IN_TX);
974		e->abort	= !!(info & LBR_INFO_ABORT);
975		e->cycles	= get_lbr_cycles(info);
976		e->type		= get_lbr_br_type(info);
977		e->reserved	= 0;
978	}
979
980	cpuc->lbr_stack.nr = i;
981}
982
983static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc)
984{
985	intel_pmu_store_lbr(cpuc, NULL);
986}
987
988static void intel_pmu_arch_lbr_read_xsave(struct cpu_hw_events *cpuc)
989{
990	struct x86_perf_task_context_arch_lbr_xsave *xsave = cpuc->lbr_xsave;
991
992	if (!xsave) {
993		intel_pmu_store_lbr(cpuc, NULL);
994		return;
995	}
996	copy_dynamic_supervisor_to_kernel(&xsave->xsave, XFEATURE_MASK_LBR);
997
998	intel_pmu_store_lbr(cpuc, xsave->lbr.entries);
999}
1000
1001void intel_pmu_lbr_read(void)
1002{
1003	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
1004
1005	/*
1006	 * Don't read when all LBRs users are using adaptive PEBS.
1007	 *
1008	 * This could be smarter and actually check the event,
1009	 * but this simple approach seems to work for now.
1010	 */
1011	if (!cpuc->lbr_users || vlbr_exclude_host() ||
1012	    cpuc->lbr_users == cpuc->lbr_pebs_users)
1013		return;
1014
1015	x86_pmu.lbr_read(cpuc);
1016
1017	intel_pmu_lbr_filter(cpuc);
1018}
1019
1020/*
1021 * SW filter is used:
1022 * - in case there is no HW filter
1023 * - in case the HW filter has errata or limitations
1024 */
1025static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
1026{
1027	u64 br_type = event->attr.branch_sample_type;
1028	int mask = 0;
1029
1030	if (br_type & PERF_SAMPLE_BRANCH_USER)
1031		mask |= X86_BR_USER;
1032
1033	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
1034		mask |= X86_BR_KERNEL;
1035
1036	/* we ignore BRANCH_HV here */
1037
1038	if (br_type & PERF_SAMPLE_BRANCH_ANY)
1039		mask |= X86_BR_ANY;
1040
1041	if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL)
1042		mask |= X86_BR_ANY_CALL;
1043
1044	if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
1045		mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET;
1046
1047	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
1048		mask |= X86_BR_IND_CALL;
1049
1050	if (br_type & PERF_SAMPLE_BRANCH_ABORT_TX)
1051		mask |= X86_BR_ABORT;
1052
1053	if (br_type & PERF_SAMPLE_BRANCH_IN_TX)
1054		mask |= X86_BR_IN_TX;
1055
1056	if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
1057		mask |= X86_BR_NO_TX;
1058
1059	if (br_type & PERF_SAMPLE_BRANCH_COND)
1060		mask |= X86_BR_JCC;
1061
1062	if (br_type & PERF_SAMPLE_BRANCH_CALL_STACK) {
1063		if (!x86_pmu_has_lbr_callstack())
1064			return -EOPNOTSUPP;
1065		if (mask & ~(X86_BR_USER | X86_BR_KERNEL))
1066			return -EINVAL;
1067		mask |= X86_BR_CALL | X86_BR_IND_CALL | X86_BR_RET |
1068			X86_BR_CALL_STACK;
1069	}
1070
1071	if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
1072		mask |= X86_BR_IND_JMP;
1073
1074	if (br_type & PERF_SAMPLE_BRANCH_CALL)
1075		mask |= X86_BR_CALL | X86_BR_ZERO_CALL;
1076
1077	if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE)
1078		mask |= X86_BR_TYPE_SAVE;
1079
1080	/*
1081	 * stash actual user request into reg, it may
1082	 * be used by fixup code for some CPU
1083	 */
1084	event->hw.branch_reg.reg = mask;
1085	return 0;
1086}
1087
1088/*
1089 * setup the HW LBR filter
1090 * Used only when available, may not be enough to disambiguate
1091 * all branches, may need the help of the SW filter
1092 */
1093static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
1094{
1095	struct hw_perf_event_extra *reg;
1096	u64 br_type = event->attr.branch_sample_type;
1097	u64 mask = 0, v;
1098	int i;
1099
1100	for (i = 0; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) {
1101		if (!(br_type & (1ULL << i)))
1102			continue;
1103
1104		v = x86_pmu.lbr_sel_map[i];
1105		if (v == LBR_NOT_SUPP)
1106			return -EOPNOTSUPP;
1107
1108		if (v != LBR_IGN)
1109			mask |= v;
1110	}
1111
1112	reg = &event->hw.branch_reg;
1113	reg->idx = EXTRA_REG_LBR;
1114
1115	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
1116		reg->config = mask;
1117
1118		/*
1119		 * The Arch LBR HW can retrieve the common branch types
1120		 * from the LBR_INFO. It doesn't require the high overhead
1121		 * SW disassemble.
1122		 * Enable the branch type by default for the Arch LBR.
1123		 */
1124		reg->reg |= X86_BR_TYPE_SAVE;
1125		return 0;
1126	}
1127
1128	/*
1129	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
1130	 * in suppress mode. So LBR_SELECT should be set to
1131	 * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK)
1132	 * But the 10th bit LBR_CALL_STACK does not operate
1133	 * in suppress mode.
1134	 */
1135	reg->config = mask ^ (x86_pmu.lbr_sel_mask & ~LBR_CALL_STACK);
1136
1137	if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&
1138	    (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&
1139	    (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO))
1140		reg->config |= LBR_NO_INFO;
1141
1142	return 0;
1143}
1144
1145int intel_pmu_setup_lbr_filter(struct perf_event *event)
1146{
1147	int ret = 0;
1148
1149	/*
1150	 * no LBR on this PMU
1151	 */
1152	if (!x86_pmu.lbr_nr)
1153		return -EOPNOTSUPP;
1154
1155	/*
1156	 * setup SW LBR filter
1157	 */
1158	ret = intel_pmu_setup_sw_lbr_filter(event);
1159	if (ret)
1160		return ret;
1161
1162	/*
1163	 * setup HW LBR filter, if any
1164	 */
1165	if (x86_pmu.lbr_sel_map)
1166		ret = intel_pmu_setup_hw_lbr_filter(event);
1167
1168	return ret;
1169}
1170
1171/*
1172 * return the type of control flow change at address "from"
1173 * instruction is not necessarily a branch (in case of interrupt).
1174 *
1175 * The branch type returned also includes the priv level of the
1176 * target of the control flow change (X86_BR_USER, X86_BR_KERNEL).
1177 *
1178 * If a branch type is unknown OR the instruction cannot be
1179 * decoded (e.g., text page not present), then X86_BR_NONE is
1180 * returned.
1181 */
1182static int branch_type(unsigned long from, unsigned long to, int abort)
1183{
1184	struct insn insn;
1185	void *addr;
1186	int bytes_read, bytes_left;
1187	int ret = X86_BR_NONE;
1188	int ext, to_plm, from_plm;
1189	u8 buf[MAX_INSN_SIZE];
1190	int is64 = 0;
1191
1192	to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
1193	from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER;
1194
1195	/*
1196	 * maybe zero if lbr did not fill up after a reset by the time
1197	 * we get a PMU interrupt
1198	 */
1199	if (from == 0 || to == 0)
1200		return X86_BR_NONE;
1201
1202	if (abort)
1203		return X86_BR_ABORT | to_plm;
1204
1205	if (from_plm == X86_BR_USER) {
1206		/*
1207		 * can happen if measuring at the user level only
1208		 * and we interrupt in a kernel thread, e.g., idle.
1209		 */
1210		if (!current->mm)
1211			return X86_BR_NONE;
1212
1213		/* may fail if text not present */
1214		bytes_left = copy_from_user_nmi(buf, (void __user *)from,
1215						MAX_INSN_SIZE);
1216		bytes_read = MAX_INSN_SIZE - bytes_left;
1217		if (!bytes_read)
1218			return X86_BR_NONE;
1219
1220		addr = buf;
1221	} else {
1222		/*
1223		 * The LBR logs any address in the IP, even if the IP just
1224		 * faulted. This means userspace can control the from address.
1225		 * Ensure we don't blindy read any address by validating it is
1226		 * a known text address.
1227		 */
1228		if (kernel_text_address(from)) {
1229			addr = (void *)from;
1230			/*
1231			 * Assume we can get the maximum possible size
1232			 * when grabbing kernel data.  This is not
1233			 * _strictly_ true since we could possibly be
1234			 * executing up next to a memory hole, but
1235			 * it is very unlikely to be a problem.
1236			 */
1237			bytes_read = MAX_INSN_SIZE;
1238		} else {
1239			return X86_BR_NONE;
1240		}
1241	}
1242
1243	/*
1244	 * decoder needs to know the ABI especially
1245	 * on 64-bit systems running 32-bit apps
1246	 */
1247#ifdef CONFIG_X86_64
1248	is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
1249#endif
1250	insn_init(&insn, addr, bytes_read, is64);
1251	insn_get_opcode(&insn);
1252	if (!insn.opcode.got)
1253		return X86_BR_ABORT;
1254
1255	switch (insn.opcode.bytes[0]) {
1256	case 0xf:
1257		switch (insn.opcode.bytes[1]) {
1258		case 0x05: /* syscall */
1259		case 0x34: /* sysenter */
1260			ret = X86_BR_SYSCALL;
1261			break;
1262		case 0x07: /* sysret */
1263		case 0x35: /* sysexit */
1264			ret = X86_BR_SYSRET;
1265			break;
1266		case 0x80 ... 0x8f: /* conditional */
1267			ret = X86_BR_JCC;
1268			break;
1269		default:
1270			ret = X86_BR_NONE;
1271		}
1272		break;
1273	case 0x70 ... 0x7f: /* conditional */
1274		ret = X86_BR_JCC;
1275		break;
1276	case 0xc2: /* near ret */
1277	case 0xc3: /* near ret */
1278	case 0xca: /* far ret */
1279	case 0xcb: /* far ret */
1280		ret = X86_BR_RET;
1281		break;
1282	case 0xcf: /* iret */
1283		ret = X86_BR_IRET;
1284		break;
1285	case 0xcc ... 0xce: /* int */
1286		ret = X86_BR_INT;
1287		break;
1288	case 0xe8: /* call near rel */
1289		insn_get_immediate(&insn);
1290		if (insn.immediate1.value == 0) {
1291			/* zero length call */
1292			ret = X86_BR_ZERO_CALL;
1293			break;
1294		}
1295		fallthrough;
1296	case 0x9a: /* call far absolute */
1297		ret = X86_BR_CALL;
1298		break;
1299	case 0xe0 ... 0xe3: /* loop jmp */
1300		ret = X86_BR_JCC;
1301		break;
1302	case 0xe9 ... 0xeb: /* jmp */
1303		ret = X86_BR_JMP;
1304		break;
1305	case 0xff: /* call near absolute, call far absolute ind */
1306		insn_get_modrm(&insn);
1307		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
1308		switch (ext) {
1309		case 2: /* near ind call */
1310		case 3: /* far ind call */
1311			ret = X86_BR_IND_CALL;
1312			break;
1313		case 4:
1314		case 5:
1315			ret = X86_BR_IND_JMP;
1316			break;
1317		}
1318		break;
1319	default:
1320		ret = X86_BR_NONE;
1321	}
1322	/*
1323	 * interrupts, traps, faults (and thus ring transition) may
1324	 * occur on any instructions. Thus, to classify them correctly,
1325	 * we need to first look at the from and to priv levels. If they
1326	 * are different and to is in the kernel, then it indicates
1327	 * a ring transition. If the from instruction is not a ring
1328	 * transition instr (syscall, systenter, int), then it means
1329	 * it was a irq, trap or fault.
1330	 *
1331	 * we have no way of detecting kernel to kernel faults.
1332	 */
1333	if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL
1334	    && ret != X86_BR_SYSCALL && ret != X86_BR_INT)
1335		ret = X86_BR_IRQ;
1336
1337	/*
1338	 * branch priv level determined by target as
1339	 * is done by HW when LBR_SELECT is implemented
1340	 */
1341	if (ret != X86_BR_NONE)
1342		ret |= to_plm;
1343
1344	return ret;
1345}
1346
1347#define X86_BR_TYPE_MAP_MAX	16
1348
1349static int branch_map[X86_BR_TYPE_MAP_MAX] = {
1350	PERF_BR_CALL,		/* X86_BR_CALL */
1351	PERF_BR_RET,		/* X86_BR_RET */
1352	PERF_BR_SYSCALL,	/* X86_BR_SYSCALL */
1353	PERF_BR_SYSRET,		/* X86_BR_SYSRET */
1354	PERF_BR_UNKNOWN,	/* X86_BR_INT */
1355	PERF_BR_UNKNOWN,	/* X86_BR_IRET */
1356	PERF_BR_COND,		/* X86_BR_JCC */
1357	PERF_BR_UNCOND,		/* X86_BR_JMP */
1358	PERF_BR_UNKNOWN,	/* X86_BR_IRQ */
1359	PERF_BR_IND_CALL,	/* X86_BR_IND_CALL */
1360	PERF_BR_UNKNOWN,	/* X86_BR_ABORT */
1361	PERF_BR_UNKNOWN,	/* X86_BR_IN_TX */
1362	PERF_BR_UNKNOWN,	/* X86_BR_NO_TX */
1363	PERF_BR_CALL,		/* X86_BR_ZERO_CALL */
1364	PERF_BR_UNKNOWN,	/* X86_BR_CALL_STACK */
1365	PERF_BR_IND,		/* X86_BR_IND_JMP */
1366};
1367
1368static int
1369common_branch_type(int type)
1370{
1371	int i;
1372
1373	type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */
1374
1375	if (type) {
1376		i = __ffs(type);
1377		if (i < X86_BR_TYPE_MAP_MAX)
1378			return branch_map[i];
1379	}
1380
1381	return PERF_BR_UNKNOWN;
1382}
1383
1384enum {
1385	ARCH_LBR_BR_TYPE_JCC			= 0,
1386	ARCH_LBR_BR_TYPE_NEAR_IND_JMP		= 1,
1387	ARCH_LBR_BR_TYPE_NEAR_REL_JMP		= 2,
1388	ARCH_LBR_BR_TYPE_NEAR_IND_CALL		= 3,
1389	ARCH_LBR_BR_TYPE_NEAR_REL_CALL		= 4,
1390	ARCH_LBR_BR_TYPE_NEAR_RET		= 5,
1391	ARCH_LBR_BR_TYPE_KNOWN_MAX		= ARCH_LBR_BR_TYPE_NEAR_RET,
1392
1393	ARCH_LBR_BR_TYPE_MAP_MAX		= 16,
1394};
1395
1396static const int arch_lbr_br_type_map[ARCH_LBR_BR_TYPE_MAP_MAX] = {
1397	[ARCH_LBR_BR_TYPE_JCC]			= X86_BR_JCC,
1398	[ARCH_LBR_BR_TYPE_NEAR_IND_JMP]		= X86_BR_IND_JMP,
1399	[ARCH_LBR_BR_TYPE_NEAR_REL_JMP]		= X86_BR_JMP,
1400	[ARCH_LBR_BR_TYPE_NEAR_IND_CALL]	= X86_BR_IND_CALL,
1401	[ARCH_LBR_BR_TYPE_NEAR_REL_CALL]	= X86_BR_CALL,
1402	[ARCH_LBR_BR_TYPE_NEAR_RET]		= X86_BR_RET,
1403};
1404
1405/*
1406 * implement actual branch filter based on user demand.
1407 * Hardware may not exactly satisfy that request, thus
1408 * we need to inspect opcodes. Mismatched branches are
1409 * discarded. Therefore, the number of branches returned
1410 * in PERF_SAMPLE_BRANCH_STACK sample may vary.
1411 */
1412static void
1413intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
1414{
1415	u64 from, to;
1416	int br_sel = cpuc->br_sel;
1417	int i, j, type, to_plm;
1418	bool compress = false;
1419
1420	/* if sampling all branches, then nothing to filter */
1421	if (((br_sel & X86_BR_ALL) == X86_BR_ALL) &&
1422	    ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE))
1423		return;
1424
1425	for (i = 0; i < cpuc->lbr_stack.nr; i++) {
1426
1427		from = cpuc->lbr_entries[i].from;
1428		to = cpuc->lbr_entries[i].to;
1429		type = cpuc->lbr_entries[i].type;
1430
1431		/*
1432		 * Parse the branch type recorded in LBR_x_INFO MSR.
1433		 * Doesn't support OTHER_BRANCH decoding for now.
1434		 * OTHER_BRANCH branch type still rely on software decoding.
1435		 */
1436		if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
1437		    type <= ARCH_LBR_BR_TYPE_KNOWN_MAX) {
1438			to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
1439			type = arch_lbr_br_type_map[type] | to_plm;
1440		} else
1441			type = branch_type(from, to, cpuc->lbr_entries[i].abort);
1442		if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) {
1443			if (cpuc->lbr_entries[i].in_tx)
1444				type |= X86_BR_IN_TX;
1445			else
1446				type |= X86_BR_NO_TX;
1447		}
1448
1449		/* if type does not correspond, then discard */
1450		if (type == X86_BR_NONE || (br_sel & type) != type) {
1451			cpuc->lbr_entries[i].from = 0;
1452			compress = true;
1453		}
1454
1455		if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE)
1456			cpuc->lbr_entries[i].type = common_branch_type(type);
1457	}
1458
1459	if (!compress)
1460		return;
1461
1462	/* remove all entries with from=0 */
1463	for (i = 0; i < cpuc->lbr_stack.nr; ) {
1464		if (!cpuc->lbr_entries[i].from) {
1465			j = i;
1466			while (++j < cpuc->lbr_stack.nr)
1467				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
1468			cpuc->lbr_stack.nr--;
1469			if (!cpuc->lbr_entries[i].from)
1470				continue;
1471		}
1472		i++;
1473	}
1474}
1475
1476void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr)
1477{
1478	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
1479
1480	/* Cannot get TOS for large PEBS and Arch LBR */
1481	if (static_cpu_has(X86_FEATURE_ARCH_LBR) ||
1482	    (cpuc->n_pebs == cpuc->n_large_pebs))
1483		cpuc->lbr_stack.hw_idx = -1ULL;
1484	else
1485		cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();
1486
1487	intel_pmu_store_lbr(cpuc, lbr);
1488	intel_pmu_lbr_filter(cpuc);
1489}
1490
1491/*
1492 * Map interface branch filters onto LBR filters
1493 */
1494static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
1495	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
1496	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
1497	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
1498	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
1499	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_REL_JMP
1500						| LBR_IND_JMP | LBR_FAR,
1501	/*
1502	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
1503	 */
1504	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] =
1505	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
1506	/*
1507	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
1508	 */
1509	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
1510	[PERF_SAMPLE_BRANCH_COND_SHIFT]     = LBR_JCC,
1511	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
1512};
1513
1514static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
1515	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
1516	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
1517	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
1518	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
1519	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
1520	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
1521						| LBR_FAR,
1522	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
1523	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
1524	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
1525	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= LBR_REL_CALL,
1526};
1527
1528static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
1529	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
1530	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
1531	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
1532	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
1533	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
1534	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
1535						| LBR_FAR,
1536	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
1537	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
1538	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
1539						| LBR_RETURN | LBR_CALL_STACK,
1540	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
1541	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= LBR_REL_CALL,
1542};
1543
1544static int arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
1545	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= ARCH_LBR_ANY,
1546	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= ARCH_LBR_USER,
1547	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= ARCH_LBR_KERNEL,
1548	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
1549	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= ARCH_LBR_RETURN |
1550						  ARCH_LBR_OTHER_BRANCH,
1551	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]     = ARCH_LBR_REL_CALL |
1552						  ARCH_LBR_IND_CALL |
1553						  ARCH_LBR_OTHER_BRANCH,
1554	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]     = ARCH_LBR_IND_CALL,
1555	[PERF_SAMPLE_BRANCH_COND_SHIFT]         = ARCH_LBR_JCC,
1556	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]   = ARCH_LBR_REL_CALL |
1557						  ARCH_LBR_IND_CALL |
1558						  ARCH_LBR_RETURN |
1559						  ARCH_LBR_CALL_STACK,
1560	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= ARCH_LBR_IND_JMP,
1561	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= ARCH_LBR_REL_CALL,
1562};
1563
1564/* core */
1565void __init intel_pmu_lbr_init_core(void)
1566{
1567	x86_pmu.lbr_nr     = 4;
1568	x86_pmu.lbr_tos    = MSR_LBR_TOS;
1569	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
1570	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
1571
1572	/*
1573	 * SW branch filter usage:
1574	 * - compensate for lack of HW filter
1575	 */
1576}
1577
1578/* nehalem/westmere */
1579void __init intel_pmu_lbr_init_nhm(void)
1580{
1581	x86_pmu.lbr_nr     = 16;
1582	x86_pmu.lbr_tos    = MSR_LBR_TOS;
1583	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
1584	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
1585
1586	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
1587	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
1588
1589	/*
1590	 * SW branch filter usage:
1591	 * - workaround LBR_SEL errata (see above)
1592	 * - support syscall, sysret capture.
1593	 *   That requires LBR_FAR but that means far
1594	 *   jmp need to be filtered out
1595	 */
1596}
1597
1598/* sandy bridge */
1599void __init intel_pmu_lbr_init_snb(void)
1600{
1601	x86_pmu.lbr_nr	 = 16;
1602	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
1603	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
1604	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
1605
1606	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
1607	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
1608
1609	/*
1610	 * SW branch filter usage:
1611	 * - support syscall, sysret capture.
1612	 *   That requires LBR_FAR but that means far
1613	 *   jmp need to be filtered out
1614	 */
1615}
1616
1617static inline struct kmem_cache *
1618create_lbr_kmem_cache(size_t size, size_t align)
1619{
1620	return kmem_cache_create("x86_lbr", size, align, 0, NULL);
1621}
1622
1623/* haswell */
1624void intel_pmu_lbr_init_hsw(void)
1625{
1626	size_t size = sizeof(struct x86_perf_task_context);
1627
1628	x86_pmu.lbr_nr	 = 16;
1629	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
1630	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
1631	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
1632
1633	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
1634	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
1635
1636	x86_get_pmu(smp_processor_id())->task_ctx_cache = create_lbr_kmem_cache(size, 0);
1637
1638	if (lbr_from_signext_quirk_needed())
1639		static_branch_enable(&lbr_from_quirk_key);
1640}
1641
1642/* skylake */
1643__init void intel_pmu_lbr_init_skl(void)
1644{
1645	size_t size = sizeof(struct x86_perf_task_context);
1646
1647	x86_pmu.lbr_nr	 = 32;
1648	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
1649	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
1650	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
1651	x86_pmu.lbr_info = MSR_LBR_INFO_0;
1652
1653	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
1654	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
1655
1656	x86_get_pmu(smp_processor_id())->task_ctx_cache = create_lbr_kmem_cache(size, 0);
1657
1658	/*
1659	 * SW branch filter usage:
1660	 * - support syscall, sysret capture.
1661	 *   That requires LBR_FAR but that means far
1662	 *   jmp need to be filtered out
1663	 */
1664}
1665
1666/* atom */
1667void __init intel_pmu_lbr_init_atom(void)
1668{
1669	/*
1670	 * only models starting at stepping 10 seems
1671	 * to have an operational LBR which can freeze
1672	 * on PMU interrupt
1673	 */
1674	if (boot_cpu_data.x86_model == 28
1675	    && boot_cpu_data.x86_stepping < 10) {
1676		pr_cont("LBR disabled due to erratum");
1677		return;
1678	}
1679
1680	x86_pmu.lbr_nr	   = 8;
1681	x86_pmu.lbr_tos    = MSR_LBR_TOS;
1682	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
1683	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
1684
1685	/*
1686	 * SW branch filter usage:
1687	 * - compensate for lack of HW filter
1688	 */
1689}
1690
1691/* slm */
1692void __init intel_pmu_lbr_init_slm(void)
1693{
1694	x86_pmu.lbr_nr	   = 8;
1695	x86_pmu.lbr_tos    = MSR_LBR_TOS;
1696	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
1697	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
1698
1699	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
1700	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
1701
1702	/*
1703	 * SW branch filter usage:
1704	 * - compensate for lack of HW filter
1705	 */
1706	pr_cont("8-deep LBR, ");
1707}
1708
1709/* Knights Landing */
1710void intel_pmu_lbr_init_knl(void)
1711{
1712	x86_pmu.lbr_nr	   = 8;
1713	x86_pmu.lbr_tos    = MSR_LBR_TOS;
1714	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
1715	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
1716
1717	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
1718	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
1719
1720	/* Knights Landing does have MISPREDICT bit */
1721	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
1722		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
1723}
1724
1725/*
1726 * LBR state size is variable based on the max number of registers.
1727 * This calculates the expected state size, which should match
1728 * what the hardware enumerates for the size of XFEATURE_LBR.
1729 */
1730static inline unsigned int get_lbr_state_size(void)
1731{
1732	return sizeof(struct arch_lbr_state) +
1733	       x86_pmu.lbr_nr * sizeof(struct lbr_entry);
1734}
1735
1736static bool is_arch_lbr_xsave_available(void)
1737{
1738	if (!boot_cpu_has(X86_FEATURE_XSAVES))
1739		return false;
1740
1741	/*
1742	 * Check the LBR state with the corresponding software structure.
1743	 * Disable LBR XSAVES support if the size doesn't match.
1744	 */
1745	if (xfeature_size(XFEATURE_LBR) == 0)
1746		return false;
1747
1748	if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size()))
1749		return false;
1750
1751	return true;
1752}
1753
1754void __init intel_pmu_arch_lbr_init(void)
1755{
1756	struct pmu *pmu = x86_get_pmu(smp_processor_id());
1757	union cpuid28_eax eax;
1758	union cpuid28_ebx ebx;
1759	union cpuid28_ecx ecx;
1760	unsigned int unused_edx;
1761	bool arch_lbr_xsave;
1762	size_t size;
1763	u64 lbr_nr;
1764
1765	/* Arch LBR Capabilities */
1766	cpuid(28, &eax.full, &ebx.full, &ecx.full, &unused_edx);
1767
1768	lbr_nr = fls(eax.split.lbr_depth_mask) * 8;
1769	if (!lbr_nr)
1770		goto clear_arch_lbr;
1771
1772	/* Apply the max depth of Arch LBR */
1773	if (wrmsrl_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
1774		goto clear_arch_lbr;
1775
1776	x86_pmu.lbr_depth_mask = eax.split.lbr_depth_mask;
1777	x86_pmu.lbr_deep_c_reset = eax.split.lbr_deep_c_reset;
1778	x86_pmu.lbr_lip = eax.split.lbr_lip;
1779	x86_pmu.lbr_cpl = ebx.split.lbr_cpl;
1780	x86_pmu.lbr_filter = ebx.split.lbr_filter;
1781	x86_pmu.lbr_call_stack = ebx.split.lbr_call_stack;
1782	x86_pmu.lbr_mispred = ecx.split.lbr_mispred;
1783	x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr;
1784	x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
1785	x86_pmu.lbr_nr = lbr_nr;
1786
1787
1788	arch_lbr_xsave = is_arch_lbr_xsave_available();
1789	if (arch_lbr_xsave) {
1790		size = sizeof(struct x86_perf_task_context_arch_lbr_xsave) +
1791		       get_lbr_state_size();
1792		pmu->task_ctx_cache = create_lbr_kmem_cache(size,
1793							    XSAVE_ALIGNMENT);
1794	}
1795
1796	if (!pmu->task_ctx_cache) {
1797		arch_lbr_xsave = false;
1798
1799		size = sizeof(struct x86_perf_task_context_arch_lbr) +
1800		       lbr_nr * sizeof(struct lbr_entry);
1801		pmu->task_ctx_cache = create_lbr_kmem_cache(size, 0);
1802	}
1803
1804	x86_pmu.lbr_from = MSR_ARCH_LBR_FROM_0;
1805	x86_pmu.lbr_to = MSR_ARCH_LBR_TO_0;
1806	x86_pmu.lbr_info = MSR_ARCH_LBR_INFO_0;
1807
1808	/* LBR callstack requires both CPL and Branch Filtering support */
1809	if (!x86_pmu.lbr_cpl ||
1810	    !x86_pmu.lbr_filter ||
1811	    !x86_pmu.lbr_call_stack)
1812		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_NOT_SUPP;
1813
1814	if (!x86_pmu.lbr_cpl) {
1815		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_NOT_SUPP;
1816		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_NOT_SUPP;
1817	} else if (!x86_pmu.lbr_filter) {
1818		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_NOT_SUPP;
1819		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_NOT_SUPP;
1820		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_NOT_SUPP;
1821		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_NOT_SUPP;
1822		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_NOT_SUPP;
1823		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_NOT_SUPP;
1824		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_NOT_SUPP;
1825	}
1826
1827	x86_pmu.lbr_ctl_mask = ARCH_LBR_CTL_MASK;
1828	x86_pmu.lbr_ctl_map  = arch_lbr_ctl_map;
1829
1830	if (!x86_pmu.lbr_cpl && !x86_pmu.lbr_filter)
1831		x86_pmu.lbr_ctl_map = NULL;
1832
1833	x86_pmu.lbr_reset = intel_pmu_arch_lbr_reset;
1834	if (arch_lbr_xsave) {
1835		x86_pmu.lbr_save = intel_pmu_arch_lbr_xsaves;
1836		x86_pmu.lbr_restore = intel_pmu_arch_lbr_xrstors;
1837		x86_pmu.lbr_read = intel_pmu_arch_lbr_read_xsave;
1838		pr_cont("XSAVE ");
1839	} else {
1840		x86_pmu.lbr_save = intel_pmu_arch_lbr_save;
1841		x86_pmu.lbr_restore = intel_pmu_arch_lbr_restore;
1842		x86_pmu.lbr_read = intel_pmu_arch_lbr_read;
1843	}
1844
1845	pr_cont("Architectural LBR, ");
1846
1847	return;
1848
1849clear_arch_lbr:
1850	setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR);
1851}
1852
1853/**
1854 * x86_perf_get_lbr - get the LBR records information
1855 *
1856 * @lbr: the caller's memory to store the LBR records information
1857 *
1858 * Returns: 0 indicates the LBR info has been successfully obtained
1859 */
1860int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
1861{
1862	int lbr_fmt = x86_pmu.intel_cap.lbr_format;
1863
1864	lbr->nr = x86_pmu.lbr_nr;
1865	lbr->from = x86_pmu.lbr_from;
1866	lbr->to = x86_pmu.lbr_to;
1867	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;
1868
1869	return 0;
1870}
1871EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
1872
1873struct event_constraint vlbr_constraint =
1874	__EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, (1ULL << INTEL_PMC_IDX_FIXED_VLBR),
1875			  FIXED_EVENT_FLAGS, 1, 0, PERF_X86_EVENT_LBR_SELECT);
1876