Merge branch 'perf/core' into perf/timer, before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/arm/kernel/hw_breakpoint.c

@@ -648,7 +648,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		 * Per-cpu breakpoints are not supported by our stepping
 		 * mechanism.
 		 */
-		if (!bp->hw.bp_target)
+		if (!bp->hw.target)
 			return -EINVAL;
 
 		/*

arch/arm64/kernel/hw_breakpoint.c

@@ -527,7 +527,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * Disallow per-task kernel breakpoints since these would
 	 * complicate the stepping code.
 	 */
-	if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.bp_target)
+	if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
 		return -EINVAL;
 
 	return 0;

arch/powerpc/perf/core-book3s.c

@@ -124,7 +124,7 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
 
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
-static void power_pmu_flush_branch_stack(void) {}
+static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {}
 static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
@@ -350,6 +350,7 @@ static void power_pmu_bhrb_enable(struct perf_event *event)
 		cpuhw->bhrb_context = event->ctx;
 	}
 	cpuhw->bhrb_users++;
+	perf_sched_cb_inc(event->ctx->pmu);
 }
 
 static void power_pmu_bhrb_disable(struct perf_event *event)
@@ -361,6 +362,7 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
 
 	cpuhw->bhrb_users--;
 	WARN_ON_ONCE(cpuhw->bhrb_users < 0);
+	perf_sched_cb_dec(event->ctx->pmu);
 
 	if (!cpuhw->disabled && !cpuhw->bhrb_users) {
 		/* BHRB cannot be turned off when other
@@ -375,9 +377,12 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
 /* Called from ctxsw to prevent one process's branch entries to
  * mingle with the other process's entries during context switch.
  */
-static void power_pmu_flush_branch_stack(void)
+static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
-	if (ppmu->bhrb_nr)
+	if (!ppmu->bhrb_nr)
+		return;
+
+	if (sched_in)
 		power_pmu_bhrb_reset();
 }
 /* Calculate the to address for a branch */
@@ -1901,7 +1906,7 @@ static struct pmu power_pmu = {
 	.cancel_txn	= power_pmu_cancel_txn,
 	.commit_txn	= power_pmu_commit_txn,
 	.event_idx	= power_pmu_event_idx,
-	.flush_branch_stack = power_pmu_flush_branch_stack,
+	.sched_task	= power_pmu_sched_task,
 };
 
 /*

arch/x86/include/asm/cpufeature.h

@@ -12,7 +12,7 @@
 #include <asm/disabled-features.h>
 #endif
 
-#define NCAPINTS	11	/* N 32-bit words worth of info */
+#define NCAPINTS	13	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -226,6 +226,7 @@
 #define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 #define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
 #define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
 #define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
@@ -242,6 +243,12 @@
 #define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
 #define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
 
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
+#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
+
 /*
  * BUG word(s)
  */

arch/x86/include/asm/processor.h

@@ -109,6 +109,9 @@ struct cpuinfo_x86 {
 	/* in KB - valid for CPUS which support this call: */
 	int			x86_cache_size;
 	int			x86_cache_alignment;	/* In bytes */
+	/* Cache QoS architectural values: */
+	int			x86_cache_max_rmid;	/* max index */
+	int			x86_cache_occ_scale;	/* scale to bytes */
 	int			x86_power;
 	unsigned long		loops_per_jiffy;
 	/* cpuid returned max cores value: */

arch/x86/kernel/cpu/Makefile

@@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
 endif
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_rapl.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_rapl.o perf_event_intel_cqm.o
 
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= perf_event_intel_uncore.o \
 					   perf_event_intel_uncore_snb.o \

arch/x86/kernel/cpu/common.c

@@ -646,6 +646,30 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[10] = eax;
 	}
 
+	/* Additional Intel-defined flags: level 0x0000000F */
+	if (c->cpuid_level >= 0x0000000F) {
+		u32 eax, ebx, ecx, edx;
+
+		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
+		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
+		c->x86_capability[11] = edx;
+		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
+			/* will be overridden if occupancy monitoring exists */
+			c->x86_cache_max_rmid = ebx;
+
+			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
+			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
+			c->x86_capability[12] = edx;
+			if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) {
+				c->x86_cache_max_rmid = ecx;
+				c->x86_cache_occ_scale = ebx;
+			}
+		} else {
+			c->x86_cache_max_rmid = -1;
+			c->x86_cache_occ_scale = -1;
+		}
+	}
+
 	/* AMD-defined flags: level 0x80000001 */
 	xlvl = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = xlvl;
@@ -834,6 +858,20 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	detect_nopl(c);
 }
 
+static void x86_init_cache_qos(struct cpuinfo_x86 *c)
+{
+	/*
+	 * The heavy lifting of max_rmid and cache_occ_scale are handled
+	 * in get_cpu_cap().  Here we just set the max_rmid for the boot_cpu
+	 * in case CQM bits really aren't there in this CPU.
+	 */
+	if (c != &boot_cpu_data) {
+		boot_cpu_data.x86_cache_max_rmid =
+			min(boot_cpu_data.x86_cache_max_rmid,
+			    c->x86_cache_max_rmid);
+	}
+}
+
 /*
  * This does the hard work of actually picking apart the CPU stuff...
  */
@@ -923,6 +961,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 
 	init_hypervisor(c);
 	x86_init_rdrand(c);
+	x86_init_cache_qos(c);
 
 	/*
 	 * Clear/Set all flags overriden by options, need do it

arch/x86/kernel/cpu/perf_event.c

@@ -399,39 +399,41 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
-		/*
-		 * check that PEBS LBR correction does not conflict with
-		 * whatever the user is asking with attr->branch_sample_type
-		 */
-		if (event->attr.precise_ip > 1 &&
-		    x86_pmu.intel_cap.pebs_format < 2) {
-			u64 *br_type = &event->attr.branch_sample_type;
-
-			if (has_branch_stack(event)) {
-				if (!precise_br_compat(event))
-					return -EOPNOTSUPP;
-
-				/* branch_sample_type is compatible */
-
-			} else {
-				/*
-				 * user did not specify  branch_sample_type
-				 *
-				 * For PEBS fixups, we capture all
-				 * the branches at the priv level of the
-				 * event.
-				 */
-				*br_type = PERF_SAMPLE_BRANCH_ANY;
-
-				if (!event->attr.exclude_user)
-					*br_type |= PERF_SAMPLE_BRANCH_USER;
-
-				if (!event->attr.exclude_kernel)
-					*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
-			}
+	}
+	/*
+	 * check that PEBS LBR correction does not conflict with
+	 * whatever the user is asking with attr->branch_sample_type
+	 */
+	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format < 2) {
+		u64 *br_type = &event->attr.branch_sample_type;
+
+		if (has_branch_stack(event)) {
+			if (!precise_br_compat(event))
+				return -EOPNOTSUPP;
+
+			/* branch_sample_type is compatible */
+
+		} else {
+			/*
+			 * user did not specify  branch_sample_type
+			 *
+			 * For PEBS fixups, we capture all
+			 * the branches at the priv level of the
+			 * event.
+			 */
+			*br_type = PERF_SAMPLE_BRANCH_ANY;
+
+			if (!event->attr.exclude_user)
+				*br_type |= PERF_SAMPLE_BRANCH_USER;
+
+			if (!event->attr.exclude_kernel)
+				*br_type |= PERF_SAMPLE_BRANCH_KERNEL;
 		}
 	}
 
+	if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK)
+		event->attach_state |= PERF_ATTACH_TASK_DATA;
+
 	/*
 	 * Generate PMC IRQs:
 	 * (keep 'enabled' bit clear for now)
@@ -449,6 +451,12 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == PERF_TYPE_RAW)
 		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
 
+	if (event->attr.sample_period && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, event->attr.sample_period) >
+				event->attr.sample_period)
+			return -EINVAL;
+	}
+
 	return x86_setup_perfctr(event);
 }
 
@@ -986,6 +994,9 @@ int x86_perf_event_set_period(struct perf_event *event)
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
+	if (x86_pmu.limit_period)
+		left = x86_pmu.limit_period(event, left);
+
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
@@ -1033,7 +1044,6 @@ static int x86_pmu_add(struct perf_event *event, int flags)
 
 	hwc = &event->hw;
 
-	perf_pmu_disable(event->pmu);
 	n0 = cpuc->n_events;
 	ret = n = collect_events(cpuc, event, false);
 	if (ret < 0)
@@ -1071,7 +1081,6 @@ done_collect:
 
 	ret = 0;
 out:
-	perf_pmu_enable(event->pmu);
 	return ret;
 }
 
@@ -1914,10 +1923,10 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
 	NULL,
 };
 
-static void x86_pmu_flush_branch_stack(void)
+static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
-	if (x86_pmu.flush_branch_stack)
-		x86_pmu.flush_branch_stack();
+	if (x86_pmu.sched_task)
+		x86_pmu.sched_task(ctx, sched_in);
 }
 
 void perf_check_microcode(void)
@@ -1949,7 +1958,8 @@ static struct pmu pmu = {
 	.commit_txn		= x86_pmu_commit_txn,
 
 	.event_idx		= x86_pmu_event_idx,
-	.flush_branch_stack	= x86_pmu_flush_branch_stack,
+	.sched_task		= x86_pmu_sched_task,
+	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 };
 
 void arch_perf_update_userpage(struct perf_event *event,

arch/x86/kernel/cpu/perf_event.h

@@ -451,6 +451,7 @@ struct x86_pmu {
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 	bool		late_ack;
+	unsigned	(*limit_period)(struct perf_event *event, unsigned l);
 
 	/*
 	 * sysfs attrs
@@ -472,7 +473,8 @@ struct x86_pmu {
 	void		(*cpu_dead)(int cpu);
 
 	void		(*check_microcode)(void);
-	void		(*flush_branch_stack)(void);
+	void		(*sched_task)(struct perf_event_context *ctx,
+				      bool sched_in);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -515,6 +517,13 @@ struct x86_pmu {
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
 };
 
+struct x86_perf_task_context {
+	u64 lbr_from[MAX_LBR_ENTRIES];
+	u64 lbr_to[MAX_LBR_ENTRIES];
+	int lbr_callstack_users;
+	int lbr_stack_state;
+};
+
 #define x86_add_quirk(func_)						\
 do {									\
 	static struct x86_pmu_quirk __quirk __initdata = {		\
@@ -546,6 +555,12 @@ static struct perf_pmu_events_attr event_attr_##v = {			\
 
 extern struct x86_pmu x86_pmu __read_mostly;
 
+static inline bool x86_pmu_has_lbr_callstack(void)
+{
+	return  x86_pmu.lbr_sel_map &&
+		x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0;
+}
+
 DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
 int x86_perf_event_set_period(struct perf_event *event);
@@ -727,6 +742,8 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_ds_init(void);
 
+void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
+
 void intel_pmu_lbr_reset(void);
 
 void intel_pmu_lbr_enable(struct perf_event *event);
@@ -747,6 +764,8 @@ void intel_pmu_lbr_init_atom(void);
 
 void intel_pmu_lbr_init_snb(void);
 
+void intel_pmu_lbr_init_hsw(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 int p4_pmu_init(void);

arch/x86/kernel/cpu/perf_event_amd_ibs.c

@@ -796,7 +796,7 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
  * the IBS interrupt vector is handled by perf_ibs_cpu_notifier that
  * is using the new offset.
  */
-static int force_ibs_eilvt_setup(void)
+static void force_ibs_eilvt_setup(void)
 {
 	int offset;
 	int ret;
@@ -811,26 +811,24 @@ static int force_ibs_eilvt_setup(void)
 
 	if (offset == APIC_EILVT_NR_MAX) {
 		printk(KERN_DEBUG "No EILVT entry available\n");
-		return -EBUSY;
+		return;
 	}
 
 	ret = setup_ibs_ctl(offset);
 	if (ret)
 		goto out;
 
-	if (!ibs_eilvt_valid()) {
-		ret = -EFAULT;
+	if (!ibs_eilvt_valid())
 		goto out;
-	}
 
 	pr_info("IBS: LVT offset %d assigned\n", offset);
 
-	return 0;
+	return;
 out:
 	preempt_disable();
 	put_eilvt(offset);
 	preempt_enable();
-	return ret;
+	return;
 }
 
 static void ibs_eilvt_setup(void)

arch/x86/kernel/cpu/perf_event_intel.c

@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -415,6 +424,202 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
+/*
+ * Notes on the events:
+ * - data reads do not include code reads (comparable to earlier tables)
+ * - data counts include speculative execution (except L1 write, dtlb, bpu)
+ * - remote node access includes remote memory, remote cache, remote mmio.
+ * - prefetches are not included in the counts because they are not
+ *   reliably counted.
+ */
+
+#define HSW_DEMAND_DATA_RD		BIT_ULL(0)
+#define HSW_DEMAND_RFO			BIT_ULL(1)
+#define HSW_ANY_RESPONSE		BIT_ULL(16)
+#define HSW_SUPPLIER_NONE		BIT_ULL(17)
+#define HSW_L3_MISS_LOCAL_DRAM		BIT_ULL(22)
+#define HSW_L3_MISS_REMOTE_HOP0		BIT_ULL(27)
+#define HSW_L3_MISS_REMOTE_HOP1		BIT_ULL(28)
+#define HSW_L3_MISS_REMOTE_HOP2P	BIT_ULL(29)
+#define HSW_L3_MISS			(HSW_L3_MISS_LOCAL_DRAM| \
+					 HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \
+					 HSW_L3_MISS_REMOTE_HOP2P)
+#define HSW_SNOOP_NONE			BIT_ULL(31)
+#define HSW_SNOOP_NOT_NEEDED		BIT_ULL(32)
+#define HSW_SNOOP_MISS			BIT_ULL(33)
+#define HSW_SNOOP_HIT_NO_FWD		BIT_ULL(34)
+#define HSW_SNOOP_HIT_WITH_FWD		BIT_ULL(35)
+#define HSW_SNOOP_HITM			BIT_ULL(36)
+#define HSW_SNOOP_NON_DRAM		BIT_ULL(37)
+#define HSW_ANY_SNOOP			(HSW_SNOOP_NONE| \
+					 HSW_SNOOP_NOT_NEEDED|HSW_SNOOP_MISS| \
+					 HSW_SNOOP_HIT_NO_FWD|HSW_SNOOP_HIT_WITH_FWD| \
+					 HSW_SNOOP_HITM|HSW_SNOOP_NON_DRAM)
+#define HSW_SNOOP_DRAM			(HSW_ANY_SNOOP & ~HSW_SNOOP_NON_DRAM)
+#define HSW_DEMAND_READ			HSW_DEMAND_DATA_RD
+#define HSW_DEMAND_WRITE		HSW_DEMAND_RFO
+#define HSW_L3_MISS_REMOTE		(HSW_L3_MISS_REMOTE_HOP0|\
+					 HSW_L3_MISS_REMOTE_HOP1|HSW_L3_MISS_REMOTE_HOP2P)
+#define HSW_LLC_ACCESS			HSW_ANY_RESPONSE
+
+#define BDW_L3_MISS_LOCAL		BIT(26)
+#define BDW_L3_MISS			(BDW_L3_MISS_LOCAL| \
+					 HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \
+					 HSW_L3_MISS_REMOTE_HOP2P)
+
+
+static __initconst const u64 hsw_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151,	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x280,	/* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x108,	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x149,	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x6085,	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0x185,	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4,	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5,	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7,	/* OFFCORE_RESPONSE */
+		[ C(RESULT_MISS)   ] = 0x1b7,	/* OFFCORE_RESPONSE */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
+static __initconst const u64 hsw_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = HSW_DEMAND_READ|
+				       HSW_LLC_ACCESS,
+		[ C(RESULT_MISS)   ] = HSW_DEMAND_READ|
+				       HSW_L3_MISS|HSW_ANY_SNOOP,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE|
+				       HSW_LLC_ACCESS,
+		[ C(RESULT_MISS)   ] = HSW_DEMAND_WRITE|
+				       HSW_L3_MISS|HSW_ANY_SNOOP,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = HSW_DEMAND_READ|
+				       HSW_L3_MISS_LOCAL_DRAM|
+				       HSW_SNOOP_DRAM,
+		[ C(RESULT_MISS)   ] = HSW_DEMAND_READ|
+				       HSW_L3_MISS_REMOTE|
+				       HSW_SNOOP_DRAM,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE|
+				       HSW_L3_MISS_LOCAL_DRAM|
+				       HSW_SNOOP_DRAM,
+		[ C(RESULT_MISS)   ] = HSW_DEMAND_WRITE|
+				       HSW_L3_MISS_REMOTE|
+				       HSW_SNOOP_DRAM,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -1029,20 +1234,6 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
-static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
-{
-	/* user explicitly requested branch sampling */
-	if (has_branch_stack(event))
-		return true;
-
-	/* implicit branch sampling to correct PEBS skid */
-	if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 &&
-	    x86_pmu.intel_cap.pebs_format < 2)
-		return true;
-
-	return false;
-}
-
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1207,7 +1398,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	 * must disable before any actual event
 	 * because any event may be combined with LBR
 	 */
-	if (intel_pmu_needs_lbr_smpl(event))
+	if (needs_branch_stack(event))
 		intel_pmu_lbr_disable(event);
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
@@ -1268,7 +1459,7 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	 * must enabled before any actual event
 	 * because any event may be combined with LBR
 	 */
-	if (intel_pmu_needs_lbr_smpl(event))
+	if (needs_branch_stack(event))
 		intel_pmu_lbr_enable(event);
 
 	if (event->attr.exclude_host)
@@ -1747,7 +1938,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
 		x86_pmu.pebs_aliases(event);
 
-	if (intel_pmu_needs_lbr_smpl(event)) {
+	if (needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
 		if (ret)
 			return ret;
@@ -1905,6 +2096,32 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	return c;
 }
 
+/*
+ * Broadwell:
+ *
+ * The INST_RETIRED.ALL period always needs to have lowest 6 bits cleared
+ * (BDM55) and it must not use a period smaller than 100 (BDM11). We combine
+ * the two to enforce a minimum period of 128 (the smallest value that has bits
+ * 0-5 cleared and >= 100).
+ *
+ * Because of how the code in x86_perf_event_set_period() works, the truncation
+ * of the lower 6 bits is 'harmless' as we'll occasionally add a longer period
+ * to make up for the 'lost' events due to carrying the 'error' in period_left.
+ *
+ * Therefore the effective (average) period matches the requested period,
+ * despite coarser hardware granularity.
+ */
+static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
+{
+	if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
+			X86_CONFIG(.event=0xc0, .umask=0x01)) {
+		if (left < 128)
+			left = 128;
+		left &= ~0x3fu;
+	}
+	return left;
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -2044,18 +2261,6 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
-static void intel_pmu_flush_branch_stack(void)
-{
-	/*
-	 * Intel LBR does not tag entries with the
-	 * PID of the current task, then we need to
-	 * flush it on ctxsw
-	 * For now, we simply reset it
-	 */
-	if (x86_pmu.lbr_nr)
-		intel_pmu_lbr_reset();
-}
-
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2107,7 +2312,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
-	.flush_branch_stack	= intel_pmu_flush_branch_stack,
+	.sched_task		= intel_pmu_lbr_sched_task,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -2546,10 +2751,10 @@ __init int intel_pmu_init(void)
 	case 69: /* 22nm Haswell ULT */
 	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 
-		intel_pmu_lbr_init_snb();
+		intel_pmu_lbr_init_hsw();
 
 		x86_pmu.event_constraints = intel_hsw_event_constraints;
 		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
@@ -2566,6 +2771,39 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* 14nm Broadwell Core-M */
+	case 86: /* 14nm Broadwell Xeon D */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		/* L3_MISS_LOCAL_DRAM is BIT(26) in Broadwell */
+		hw_cache_extra_regs[C(LL)][C(OP_READ)][C(RESULT_MISS)] = HSW_DEMAND_READ |
+									 BDW_L3_MISS|HSW_SNOOP_DRAM;
+		hw_cache_extra_regs[C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = HSW_DEMAND_WRITE|BDW_L3_MISS|
+									  HSW_SNOOP_DRAM;
+		hw_cache_extra_regs[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = HSW_DEMAND_READ|
+									     BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM;
+		hw_cache_extra_regs[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = HSW_DEMAND_WRITE|
+									      BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM;
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.limit_period = bdw_limit_period;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:

arch/x86/kernel/cpu/perf_event_intel_cqm.c

@@ -0,0 +1,1379 @@
+/*
+ * Intel Cache Quality-of-Service Monitoring (CQM) support.
+ *
+ * Based very, very heavily on work by Peter Zijlstra.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+#include <asm/cpu_device_id.h>
+#include "perf_event.h"
+
+#define MSR_IA32_PQR_ASSOC	0x0c8f
+#define MSR_IA32_QM_CTR		0x0c8e
+#define MSR_IA32_QM_EVTSEL	0x0c8d
+
+static unsigned int cqm_max_rmid = -1;
+static unsigned int cqm_l3_scale; /* supposedly cacheline size */
+
+struct intel_cqm_state {
+	raw_spinlock_t		lock;
+	int			rmid;
+	int			cnt;
+};
+
+static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+
+/*
+ * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
+ * Also protects event->hw.cqm_rmid
+ *
+ * Hold either for stability, both for modification of ->hw.cqm_rmid.
+ */
+static DEFINE_MUTEX(cache_mutex);
+static DEFINE_RAW_SPINLOCK(cache_lock);
+
+/*
+ * Groups of events that have the same target(s), one RMID per group.
+ */
+static LIST_HEAD(cache_groups);
+
+/*
+ * Mask of CPUs for reading CQM values. We only need one per-socket.
+ */
+static cpumask_t cqm_cpumask;
+
+#define RMID_VAL_ERROR		(1ULL << 63)
+#define RMID_VAL_UNAVAIL	(1ULL << 62)
+
+#define QOS_L3_OCCUP_EVENT_ID	(1 << 0)
+
+#define QOS_EVENT_MASK	QOS_L3_OCCUP_EVENT_ID
+
+/*
+ * This is central to the rotation algorithm in __intel_cqm_rmid_rotate().
+ *
+ * This rmid is always free and is guaranteed to have an associated
+ * near-zero occupancy value, i.e. no cachelines are tagged with this
+ * RMID, once __intel_cqm_rmid_rotate() returns.
+ */
+static unsigned int intel_cqm_rotation_rmid;
+
+#define INVALID_RMID		(-1)
+
+/*
+ * Is @rmid valid for programming the hardware?
+ *
+ * rmid 0 is reserved by the hardware for all non-monitored tasks, which
+ * means that we should never come across an rmid with that value.
+ * Likewise, an rmid value of -1 is used to indicate "no rmid currently
+ * assigned" and is used as part of the rotation code.
+ */
+static inline bool __rmid_valid(unsigned int rmid)
+{
+	if (!rmid || rmid == INVALID_RMID)
+		return false;
+
+	return true;
+}
+
+static u64 __rmid_read(unsigned int rmid)
+{
+	u64 val;
+
+	/*
+	 * Ignore the SDM, this thing is _NOTHING_ like a regular perfcnt,
+	 * it just says that to increase confusion.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, QOS_L3_OCCUP_EVENT_ID, rmid);
+	rdmsrl(MSR_IA32_QM_CTR, val);
+
+	/*
+	 * Aside from the ERROR and UNAVAIL bits, assume this thing returns
+	 * the number of cachelines tagged with @rmid.
+	 */
+	return val;
+}
+
+enum rmid_recycle_state {
+	RMID_YOUNG = 0,
+	RMID_AVAILABLE,
+	RMID_DIRTY,
+};
+
+struct cqm_rmid_entry {
+	unsigned int rmid;
+	enum rmid_recycle_state state;
+	struct list_head list;
+	unsigned long queue_time;
+};
+
+/*
+ * cqm_rmid_free_lru - A least recently used list of RMIDs.
+ *
+ * Oldest entry at the head, newest (most recently used) entry at the
+ * tail. This list is never traversed, it's only used to keep track of
+ * the lru order. That is, we only pick entries of the head or insert
+ * them on the tail.
+ *
+ * All entries on the list are 'free', and their RMIDs are not currently
+ * in use. To mark an RMID as in use, remove its entry from the lru
+ * list.
+ *
+ *
+ * cqm_rmid_limbo_lru - list of currently unused but (potentially) dirty RMIDs.
+ *
+ * This list is contains RMIDs that no one is currently using but that
+ * may have a non-zero occupancy value associated with them. The
+ * rotation worker moves RMIDs from the limbo list to the free list once
+ * the occupancy value drops below __intel_cqm_threshold.
+ *
+ * Both lists are protected by cache_mutex.
+ */
+static LIST_HEAD(cqm_rmid_free_lru);
+static LIST_HEAD(cqm_rmid_limbo_lru);
+
+/*
+ * We use a simple array of pointers so that we can lookup a struct
+ * cqm_rmid_entry in O(1). This alleviates the callers of __get_rmid()
+ * and __put_rmid() from having to worry about dealing with struct
+ * cqm_rmid_entry - they just deal with rmids, i.e. integers.
+ *
+ * Once this array is initialized it is read-only. No locks are required
+ * to access it.
+ *
+ * All entries for all RMIDs can be looked up in the this array at all
+ * times.
+ */
+static struct cqm_rmid_entry **cqm_rmid_ptrs;
+
+static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+{
+	struct cqm_rmid_entry *entry;
+
+	entry = cqm_rmid_ptrs[rmid];
+	WARN_ON(entry->rmid != rmid);
+
+	return entry;
+}
+
+/*
+ * Returns < 0 on fail.
+ *
+ * We expect to be called with cache_mutex held.
+ */
+static int __get_rmid(void)
+{
+	struct cqm_rmid_entry *entry;
+
+	lockdep_assert_held(&cache_mutex);
+
+	if (list_empty(&cqm_rmid_free_lru))
+		return INVALID_RMID;
+
+	entry = list_first_entry(&cqm_rmid_free_lru, struct cqm_rmid_entry, list);
+	list_del(&entry->list);
+
+	return entry->rmid;
+}
+
+static void __put_rmid(unsigned int rmid)
+{
+	struct cqm_rmid_entry *entry;
+
+	lockdep_assert_held(&cache_mutex);
+
+	WARN_ON(!__rmid_valid(rmid));
+	entry = __rmid_entry(rmid);
+
+	entry->queue_time = jiffies;
+	entry->state = RMID_YOUNG;
+
+	list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
+}
+
+static int intel_cqm_setup_rmid_cache(void)
+{
+	struct cqm_rmid_entry *entry;
+	unsigned int nr_rmids;
+	int r = 0;
+
+	nr_rmids = cqm_max_rmid + 1;
+	cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
+				nr_rmids, GFP_KERNEL);
+	if (!cqm_rmid_ptrs)
+		return -ENOMEM;
+
+	for (; r <= cqm_max_rmid; r++) {
+		struct cqm_rmid_entry *entry;
+
+		entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+		if (!entry)
+			goto fail;
+
+		INIT_LIST_HEAD(&entry->list);
+		entry->rmid = r;
+		cqm_rmid_ptrs[r] = entry;
+
+		list_add_tail(&entry->list, &cqm_rmid_free_lru);
+	}
+
+	/*
+	 * RMID 0 is special and is always allocated. It's used for all
+	 * tasks that are not monitored.
+	 */
+	entry = __rmid_entry(0);
+	list_del(&entry->list);
+
+	mutex_lock(&cache_mutex);
+	intel_cqm_rotation_rmid = __get_rmid();
+	mutex_unlock(&cache_mutex);
+
+	return 0;
+fail:
+	while (r--)
+		kfree(cqm_rmid_ptrs[r]);
+
+	kfree(cqm_rmid_ptrs);
+	return -ENOMEM;
+}
+
+/*
+ * Determine if @a and @b measure the same set of tasks.
+ *
+ * If @a and @b measure the same set of tasks then we want to share a
+ * single RMID.
+ */
+static bool __match_event(struct perf_event *a, struct perf_event *b)
+{
+	/* Per-cpu and task events don't mix */
+	if ((a->attach_state & PERF_ATTACH_TASK) !=
+	    (b->attach_state & PERF_ATTACH_TASK))
+		return false;
+
+#ifdef CONFIG_CGROUP_PERF
+	if (a->cgrp != b->cgrp)
+		return false;
+#endif
+
+	/* If not task event, we're machine wide */
+	if (!(b->attach_state & PERF_ATTACH_TASK))
+		return true;
+
+	/*
+	 * Events that target same task are placed into the same cache group.
+	 */
+	if (a->hw.target == b->hw.target)
+		return true;
+
+	/*
+	 * Are we an inherited event?
+	 */
+	if (b->parent == a)
+		return true;
+
+	return false;
+}
+
+#ifdef CONFIG_CGROUP_PERF
+static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
+{
+	if (event->attach_state & PERF_ATTACH_TASK)
+		return perf_cgroup_from_task(event->hw.target);
+
+	return event->cgrp;
+}
+#endif
+
+/*
+ * Determine if @a's tasks intersect with @b's tasks
+ *
+ * There are combinations of events that we explicitly prohibit,
+ *
+ *		   PROHIBITS
+ *     system-wide    -> 	cgroup and task
+ *     cgroup 	      ->	system-wide
+ *     		      ->	task in cgroup
+ *     task 	      -> 	system-wide
+ *     		      ->	task in cgroup
+ *
+ * Call this function before allocating an RMID.
+ */
+static bool __conflict_event(struct perf_event *a, struct perf_event *b)
+{
+#ifdef CONFIG_CGROUP_PERF
+	/*
+	 * We can have any number of cgroups but only one system-wide
+	 * event at a time.
+	 */
+	if (a->cgrp && b->cgrp) {
+		struct perf_cgroup *ac = a->cgrp;
+		struct perf_cgroup *bc = b->cgrp;
+
+		/*
+		 * This condition should have been caught in
+		 * __match_event() and we should be sharing an RMID.
+		 */
+		WARN_ON_ONCE(ac == bc);
+
+		if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) ||
+		    cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup))
+			return true;
+
+		return false;
+	}
+
+	if (a->cgrp || b->cgrp) {
+		struct perf_cgroup *ac, *bc;
+
+		/*
+		 * cgroup and system-wide events are mutually exclusive
+		 */
+		if ((a->cgrp && !(b->attach_state & PERF_ATTACH_TASK)) ||
+		    (b->cgrp && !(a->attach_state & PERF_ATTACH_TASK)))
+			return true;
+
+		/*
+		 * Ensure neither event is part of the other's cgroup
+		 */
+		ac = event_to_cgroup(a);
+		bc = event_to_cgroup(b);
+		if (ac == bc)
+			return true;
+
+		/*
+		 * Must have cgroup and non-intersecting task events.
+		 */
+		if (!ac || !bc)
+			return false;
+
+		/*
+		 * We have cgroup and task events, and the task belongs
+		 * to a cgroup. Check for for overlap.
+		 */
+		if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) ||
+		    cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup))
+			return true;
+
+		return false;
+	}
+#endif
+	/*
+	 * If one of them is not a task, same story as above with cgroups.
+	 */
+	if (!(a->attach_state & PERF_ATTACH_TASK) ||
+	    !(b->attach_state & PERF_ATTACH_TASK))
+		return true;
+
+	/*
+	 * Must be non-overlapping.
+	 */
+	return false;
+}
+
+struct rmid_read {
+	unsigned int rmid;
+	atomic64_t value;
+};
+
+static void __intel_cqm_event_count(void *info);
+
+/*
+ * Exchange the RMID of a group of events.
+ */
+static unsigned int
+intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid)
+{
+	struct perf_event *event;
+	unsigned int old_rmid = group->hw.cqm_rmid;
+	struct list_head *head = &group->hw.cqm_group_entry;
+
+	lockdep_assert_held(&cache_mutex);
+
+	/*
+	 * If our RMID is being deallocated, perform a read now.
+	 */
+	if (__rmid_valid(old_rmid) && !__rmid_valid(rmid)) {
+		struct rmid_read rr = {
+			.value = ATOMIC64_INIT(0),
+			.rmid = old_rmid,
+		};
+
+		on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count,
+				 &rr, 1);
+		local64_set(&group->count, atomic64_read(&rr.value));
+	}
+
+	raw_spin_lock_irq(&cache_lock);
+
+	group->hw.cqm_rmid = rmid;
+	list_for_each_entry(event, head, hw.cqm_group_entry)
+		event->hw.cqm_rmid = rmid;
+
+	raw_spin_unlock_irq(&cache_lock);
+
+	return old_rmid;
+}
+
+/*
+ * If we fail to assign a new RMID for intel_cqm_rotation_rmid because
+ * cachelines are still tagged with RMIDs in limbo, we progressively
+ * increment the threshold until we find an RMID in limbo with <=
+ * __intel_cqm_threshold lines tagged. This is designed to mitigate the
+ * problem where cachelines tagged with an RMID are not steadily being
+ * evicted.
+ *
+ * On successful rotations we decrease the threshold back towards zero.
+ *
+ * __intel_cqm_max_threshold provides an upper bound on the threshold,
+ * and is measured in bytes because it's exposed to userland.
+ */
+static unsigned int __intel_cqm_threshold;
+static unsigned int __intel_cqm_max_threshold;
+
+/*
+ * Test whether an RMID has a zero occupancy value on this cpu.
+ */
+static void intel_cqm_stable(void *arg)
+{
+	struct cqm_rmid_entry *entry;
+
+	list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) {
+		if (entry->state != RMID_AVAILABLE)
+			break;
+
+		if (__rmid_read(entry->rmid) > __intel_cqm_threshold)
+			entry->state = RMID_DIRTY;
+	}
+}
+
+/*
+ * If we have group events waiting for an RMID that don't conflict with
+ * events already running, assign @rmid.
+ */
+static bool intel_cqm_sched_in_event(unsigned int rmid)
+{
+	struct perf_event *leader, *event;
+
+	lockdep_assert_held(&cache_mutex);
+
+	leader = list_first_entry(&cache_groups, struct perf_event,
+				  hw.cqm_groups_entry);
+	event = leader;
+
+	list_for_each_entry_continue(event, &cache_groups,
+				     hw.cqm_groups_entry) {
+		if (__rmid_valid(event->hw.cqm_rmid))
+			continue;
+
+		if (__conflict_event(event, leader))
+			continue;
+
+		intel_cqm_xchg_rmid(event, rmid);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Initially use this constant for both the limbo queue time and the
+ * rotation timer interval, pmu::hrtimer_interval_ms.
+ *
+ * They don't need to be the same, but the two are related since if you
+ * rotate faster than you recycle RMIDs, you may run out of available
+ * RMIDs.
+ */
+#define RMID_DEFAULT_QUEUE_TIME 250	/* ms */
+
+static unsigned int __rmid_queue_time_ms = RMID_DEFAULT_QUEUE_TIME;
+
+/*
+ * intel_cqm_rmid_stabilize - move RMIDs from limbo to free list
+ * @nr_available: number of freeable RMIDs on the limbo list
+ *
+ * Quiescent state; wait for all 'freed' RMIDs to become unused, i.e. no
+ * cachelines are tagged with those RMIDs. After this we can reuse them
+ * and know that the current set of active RMIDs is stable.
+ *
+ * Return %true or %false depending on whether stabilization needs to be
+ * reattempted.
+ *
+ * If we return %true then @nr_available is updated to indicate the
+ * number of RMIDs on the limbo list that have been queued for the
+ * minimum queue time (RMID_AVAILABLE), but whose data occupancy values
+ * are above __intel_cqm_threshold.
+ */
+static bool intel_cqm_rmid_stabilize(unsigned int *available)
+{
+	struct cqm_rmid_entry *entry, *tmp;
+
+	lockdep_assert_held(&cache_mutex);
+
+	*available = 0;
+	list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) {
+		unsigned long min_queue_time;
+		unsigned long now = jiffies;
+
+		/*
+		 * We hold RMIDs placed into limbo for a minimum queue
+		 * time. Before the minimum queue time has elapsed we do
+		 * not recycle RMIDs.
+		 *
+		 * The reasoning is that until a sufficient time has
+		 * passed since we stopped using an RMID, any RMID
+		 * placed onto the limbo list will likely still have
+		 * data tagged in the cache, which means we'll probably
+		 * fail to recycle it anyway.
+		 *
+		 * We can save ourselves an expensive IPI by skipping
+		 * any RMIDs that have not been queued for the minimum
+		 * time.
+		 */
+		min_queue_time = entry->queue_time +
+			msecs_to_jiffies(__rmid_queue_time_ms);
+
+		if (time_after(min_queue_time, now))
+			break;
+
+		entry->state = RMID_AVAILABLE;
+		(*available)++;
+	}
+
+	/*
+	 * Fast return if none of the RMIDs on the limbo list have been
+	 * sitting on the queue for the minimum queue time.
+	 */
+	if (!*available)
+		return false;
+
+	/*
+	 * Test whether an RMID is free for each package.
+	 */
+	on_each_cpu_mask(&cqm_cpumask, intel_cqm_stable, NULL, true);
+
+	list_for_each_entry_safe(entry, tmp, &cqm_rmid_limbo_lru, list) {
+		/*
+		 * Exhausted all RMIDs that have waited min queue time.
+		 */
+		if (entry->state == RMID_YOUNG)
+			break;
+
+		if (entry->state == RMID_DIRTY)
+			continue;
+
+		list_del(&entry->list);	/* remove from limbo */
+
+		/*
+		 * The rotation RMID gets priority if it's
+		 * currently invalid. In which case, skip adding
+		 * the RMID to the the free lru.
+		 */
+		if (!__rmid_valid(intel_cqm_rotation_rmid)) {
+			intel_cqm_rotation_rmid = entry->rmid;
+			continue;
+		}
+
+		/*
+		 * If we have groups waiting for RMIDs, hand
+		 * them one now provided they don't conflict.
+		 */
+		if (intel_cqm_sched_in_event(entry->rmid))
+			continue;
+
+		/*
+		 * Otherwise place it onto the free list.
+		 */
+		list_add_tail(&entry->list, &cqm_rmid_free_lru);
+	}
+
+
+	return __rmid_valid(intel_cqm_rotation_rmid);
+}
+
+/*
+ * Pick a victim group and move it to the tail of the group list.
+ * @next: The first group without an RMID
+ */
+static void __intel_cqm_pick_and_rotate(struct perf_event *next)
+{
+	struct perf_event *rotor;
+	unsigned int rmid;
+
+	lockdep_assert_held(&cache_mutex);
+
+	rotor = list_first_entry(&cache_groups, struct perf_event,
+				 hw.cqm_groups_entry);
+
+	/*
+	 * The group at the front of the list should always have a valid
+	 * RMID. If it doesn't then no groups have RMIDs assigned and we
+	 * don't need to rotate the list.
+	 */
+	if (next == rotor)
+		return;
+
+	rmid = intel_cqm_xchg_rmid(rotor, INVALID_RMID);
+	__put_rmid(rmid);
+
+	list_rotate_left(&cache_groups);
+}
+
+/*
+ * Deallocate the RMIDs from any events that conflict with @event, and
+ * place them on the back of the group list.
+ */
+static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
+{
+	struct perf_event *group, *g;
+	unsigned int rmid;
+
+	lockdep_assert_held(&cache_mutex);
+
+	list_for_each_entry_safe(group, g, &cache_groups, hw.cqm_groups_entry) {
+		if (group == event)
+			continue;
+
+		rmid = group->hw.cqm_rmid;
+
+		/*
+		 * Skip events that don't have a valid RMID.
+		 */
+		if (!__rmid_valid(rmid))
+			continue;
+
+		/*
+		 * No conflict? No problem! Leave the event alone.
+		 */
+		if (!__conflict_event(group, event))
+			continue;
+
+		intel_cqm_xchg_rmid(group, INVALID_RMID);
+		__put_rmid(rmid);
+	}
+}
+
+/*
+ * Attempt to rotate the groups and assign new RMIDs.
+ *
+ * We rotate for two reasons,
+ *   1. To handle the scheduling of conflicting events
+ *   2. To recycle RMIDs
+ *
+ * Rotating RMIDs is complicated because the hardware doesn't give us
+ * any clues.
+ *
+ * There's problems with the hardware interface; when you change the
+ * task:RMID map cachelines retain their 'old' tags, giving a skewed
+ * picture. In order to work around this, we must always keep one free
+ * RMID - intel_cqm_rotation_rmid.
+ *
+ * Rotation works by taking away an RMID from a group (the old RMID),
+ * and assigning the free RMID to another group (the new RMID). We must
+ * then wait for the old RMID to not be used (no cachelines tagged).
+ * This ensure that all cachelines are tagged with 'active' RMIDs. At
+ * this point we can start reading values for the new RMID and treat the
+ * old RMID as the free RMID for the next rotation.
+ *
+ * Return %true or %false depending on whether we did any rotating.
+ */
+static bool __intel_cqm_rmid_rotate(void)
+{
+	struct perf_event *group, *start = NULL;
+	unsigned int threshold_limit;
+	unsigned int nr_needed = 0;
+	unsigned int nr_available;
+	bool rotated = false;
+
+	mutex_lock(&cache_mutex);
+
+again:
+	/*
+	 * Fast path through this function if there are no groups and no
+	 * RMIDs that need cleaning.
+	 */
+	if (list_empty(&cache_groups) && list_empty(&cqm_rmid_limbo_lru))
+		goto out;
+
+	list_for_each_entry(group, &cache_groups, hw.cqm_groups_entry) {
+		if (!__rmid_valid(group->hw.cqm_rmid)) {
+			if (!start)
+				start = group;
+			nr_needed++;
+		}
+	}
+
+	/*
+	 * We have some event groups, but they all have RMIDs assigned
+	 * and no RMIDs need cleaning.
+	 */
+	if (!nr_needed && list_empty(&cqm_rmid_limbo_lru))
+		goto out;
+
+	if (!nr_needed)
+		goto stabilize;
+
+	/*
+	 * We have more event groups without RMIDs than available RMIDs,
+	 * or we have event groups that conflict with the ones currently
+	 * scheduled.
+	 *
+	 * We force deallocate the rmid of the group at the head of
+	 * cache_groups. The first event group without an RMID then gets
+	 * assigned intel_cqm_rotation_rmid. This ensures we always make
+	 * forward progress.
+	 *
+	 * Rotate the cache_groups list so the previous head is now the
+	 * tail.
+	 */
+	__intel_cqm_pick_and_rotate(start);
+
+	/*
+	 * If the rotation is going to succeed, reduce the threshold so
+	 * that we don't needlessly reuse dirty RMIDs.
+	 */
+	if (__rmid_valid(intel_cqm_rotation_rmid)) {
+		intel_cqm_xchg_rmid(start, intel_cqm_rotation_rmid);
+		intel_cqm_rotation_rmid = __get_rmid();
+
+		intel_cqm_sched_out_conflicting_events(start);
+
+		if (__intel_cqm_threshold)
+			__intel_cqm_threshold--;
+	}
+
+	rotated = true;
+
+stabilize:
+	/*
+	 * We now need to stablize the RMID we freed above (if any) to
+	 * ensure that the next time we rotate we have an RMID with zero
+	 * occupancy value.
+	 *
+	 * Alternatively, if we didn't need to perform any rotation,
+	 * we'll have a bunch of RMIDs in limbo that need stabilizing.
+	 */
+	threshold_limit = __intel_cqm_max_threshold / cqm_l3_scale;
+
+	while (intel_cqm_rmid_stabilize(&nr_available) &&
+	       __intel_cqm_threshold < threshold_limit) {
+		unsigned int steal_limit;
+
+		/*
+		 * Don't spin if nobody is actively waiting for an RMID,
+		 * the rotation worker will be kicked as soon as an
+		 * event needs an RMID anyway.
+		 */
+		if (!nr_needed)
+			break;
+
+		/* Allow max 25% of RMIDs to be in limbo. */
+		steal_limit = (cqm_max_rmid + 1) / 4;
+
+		/*
+		 * We failed to stabilize any RMIDs so our rotation
+		 * logic is now stuck. In order to make forward progress
+		 * we have a few options:
+		 *
+		 *   1. rotate ("steal") another RMID
+		 *   2. increase the threshold
+		 *   3. do nothing
+		 *
+		 * We do both of 1. and 2. until we hit the steal limit.
+		 *
+		 * The steal limit prevents all RMIDs ending up on the
+		 * limbo list. This can happen if every RMID has a
+		 * non-zero occupancy above threshold_limit, and the
+		 * occupancy values aren't dropping fast enough.
+		 *
+		 * Note that there is prioritisation at work here - we'd
+		 * rather increase the number of RMIDs on the limbo list
+		 * than increase the threshold, because increasing the
+		 * threshold skews the event data (because we reuse
+		 * dirty RMIDs) - threshold bumps are a last resort.
+		 */
+		if (nr_available < steal_limit)
+			goto again;
+
+		__intel_cqm_threshold++;
+	}
+
+out:
+	mutex_unlock(&cache_mutex);
+	return rotated;
+}
+
+static void intel_cqm_rmid_rotate(struct work_struct *work);
+
+static DECLARE_DELAYED_WORK(intel_cqm_rmid_work, intel_cqm_rmid_rotate);
+
+static struct pmu intel_cqm_pmu;
+
+static void intel_cqm_rmid_rotate(struct work_struct *work)
+{
+	unsigned long delay;
+
+	__intel_cqm_rmid_rotate();
+
+	delay = msecs_to_jiffies(intel_cqm_pmu.hrtimer_interval_ms);
+	schedule_delayed_work(&intel_cqm_rmid_work, delay);
+}
+
+/*
+ * Find a group and setup RMID.
+ *
+ * If we're part of a group, we use the group's RMID.
+ */
+static void intel_cqm_setup_event(struct perf_event *event,
+				  struct perf_event **group)
+{
+	struct perf_event *iter;
+	unsigned int rmid;
+	bool conflict = false;
+
+	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
+		rmid = iter->hw.cqm_rmid;
+
+		if (__match_event(iter, event)) {
+			/* All tasks in a group share an RMID */
+			event->hw.cqm_rmid = rmid;
+			*group = iter;
+			return;
+		}
+
+		/*
+		 * We only care about conflicts for events that are
+		 * actually scheduled in (and hence have a valid RMID).
+		 */
+		if (__conflict_event(iter, event) && __rmid_valid(rmid))
+			conflict = true;
+	}
+
+	if (conflict)
+		rmid = INVALID_RMID;
+	else
+		rmid = __get_rmid();
+
+	event->hw.cqm_rmid = rmid;
+}
+
+static void intel_cqm_event_read(struct perf_event *event)
+{
+	unsigned long flags;
+	unsigned int rmid;
+	u64 val;
+
+	/*
+	 * Task events are handled by intel_cqm_event_count().
+	 */
+	if (event->cpu == -1)
+		return;
+
+	raw_spin_lock_irqsave(&cache_lock, flags);
+	rmid = event->hw.cqm_rmid;
+
+	if (!__rmid_valid(rmid))
+		goto out;
+
+	val = __rmid_read(rmid);
+
+	/*
+	 * Ignore this reading on error states and do not update the value.
+	 */
+	if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
+		goto out;
+
+	local64_set(&event->count, val);
+out:
+	raw_spin_unlock_irqrestore(&cache_lock, flags);
+}
+
+static void __intel_cqm_event_count(void *info)
+{
+	struct rmid_read *rr = info;
+	u64 val;
+
+	val = __rmid_read(rr->rmid);
+
+	if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
+		return;
+
+	atomic64_add(val, &rr->value);
+}
+
+static inline bool cqm_group_leader(struct perf_event *event)
+{
+	return !list_empty(&event->hw.cqm_groups_entry);
+}
+
+static u64 intel_cqm_event_count(struct perf_event *event)
+{
+	unsigned long flags;
+	struct rmid_read rr = {
+		.value = ATOMIC64_INIT(0),
+	};
+
+	/*
+	 * We only need to worry about task events. System-wide events
+	 * are handled like usual, i.e. entirely with
+	 * intel_cqm_event_read().
+	 */
+	if (event->cpu != -1)
+		return __perf_event_count(event);
+
+	/*
+	 * Only the group leader gets to report values. This stops us
+	 * reporting duplicate values to userspace, and gives us a clear
+	 * rule for which task gets to report the values.
+	 *
+	 * Note that it is impossible to attribute these values to
+	 * specific packages - we forfeit that ability when we create
+	 * task events.
+	 */
+	if (!cqm_group_leader(event))
+		return 0;
+
+	/*
+	 * Notice that we don't perform the reading of an RMID
+	 * atomically, because we can't hold a spin lock across the
+	 * IPIs.
+	 *
+	 * Speculatively perform the read, since @event might be
+	 * assigned a different (possibly invalid) RMID while we're
+	 * busying performing the IPI calls. It's therefore necessary to
+	 * check @event's RMID afterwards, and if it has changed,
+	 * discard the result of the read.
+	 */
+	rr.rmid = ACCESS_ONCE(event->hw.cqm_rmid);
+
+	if (!__rmid_valid(rr.rmid))
+		goto out;
+
+	on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, &rr, 1);
+
+	raw_spin_lock_irqsave(&cache_lock, flags);
+	if (event->hw.cqm_rmid == rr.rmid)
+		local64_set(&event->count, atomic64_read(&rr.value));
+	raw_spin_unlock_irqrestore(&cache_lock, flags);
+out:
+	return __perf_event_count(event);
+}
+
+static void intel_cqm_event_start(struct perf_event *event, int mode)
+{
+	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
+	unsigned int rmid = event->hw.cqm_rmid;
+	unsigned long flags;
+
+	if (!(event->hw.cqm_state & PERF_HES_STOPPED))
+		return;
+
+	event->hw.cqm_state &= ~PERF_HES_STOPPED;
+
+	raw_spin_lock_irqsave(&state->lock, flags);
+
+	if (state->cnt++)
+		WARN_ON_ONCE(state->rmid != rmid);
+	else
+		WARN_ON_ONCE(state->rmid);
+
+	state->rmid = rmid;
+	wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
+
+	raw_spin_unlock_irqrestore(&state->lock, flags);
+}
+
+static void intel_cqm_event_stop(struct perf_event *event, int mode)
+{
+	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
+	unsigned long flags;
+
+	if (event->hw.cqm_state & PERF_HES_STOPPED)
+		return;
+
+	event->hw.cqm_state |= PERF_HES_STOPPED;
+
+	raw_spin_lock_irqsave(&state->lock, flags);
+	intel_cqm_event_read(event);
+
+	if (!--state->cnt) {
+		state->rmid = 0;
+		wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+	} else {
+		WARN_ON_ONCE(!state->rmid);
+	}
+
+	raw_spin_unlock_irqrestore(&state->lock, flags);
+}
+
+static int intel_cqm_event_add(struct perf_event *event, int mode)
+{
+	unsigned long flags;
+	unsigned int rmid;
+
+	raw_spin_lock_irqsave(&cache_lock, flags);
+
+	event->hw.cqm_state = PERF_HES_STOPPED;
+	rmid = event->hw.cqm_rmid;
+
+	if (__rmid_valid(rmid) && (mode & PERF_EF_START))
+		intel_cqm_event_start(event, mode);
+
+	raw_spin_unlock_irqrestore(&cache_lock, flags);
+
+	return 0;
+}
+
+static void intel_cqm_event_del(struct perf_event *event, int mode)
+{
+	intel_cqm_event_stop(event, mode);
+}
+
+static void intel_cqm_event_destroy(struct perf_event *event)
+{
+	struct perf_event *group_other = NULL;
+
+	mutex_lock(&cache_mutex);
+
+	/*
+	 * If there's another event in this group...
+	 */
+	if (!list_empty(&event->hw.cqm_group_entry)) {
+		group_other = list_first_entry(&event->hw.cqm_group_entry,
+					       struct perf_event,
+					       hw.cqm_group_entry);
+		list_del(&event->hw.cqm_group_entry);
+	}
+
+	/*
+	 * And we're the group leader..
+	 */
+	if (cqm_group_leader(event)) {
+		/*
+		 * If there was a group_other, make that leader, otherwise
+		 * destroy the group and return the RMID.
+		 */
+		if (group_other) {
+			list_replace(&event->hw.cqm_groups_entry,
+				     &group_other->hw.cqm_groups_entry);
+		} else {
+			unsigned int rmid = event->hw.cqm_rmid;
+
+			if (__rmid_valid(rmid))
+				__put_rmid(rmid);
+			list_del(&event->hw.cqm_groups_entry);
+		}
+	}
+
+	mutex_unlock(&cache_mutex);
+}
+
+static int intel_cqm_event_init(struct perf_event *event)
+{
+	struct perf_event *group = NULL;
+	bool rotate = false;
+
+	if (event->attr.type != intel_cqm_pmu.type)
+		return -ENOENT;
+
+	if (event->attr.config & ~QOS_EVENT_MASK)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	INIT_LIST_HEAD(&event->hw.cqm_group_entry);
+	INIT_LIST_HEAD(&event->hw.cqm_groups_entry);
+
+	event->destroy = intel_cqm_event_destroy;
+
+	mutex_lock(&cache_mutex);
+
+	/* Will also set rmid */
+	intel_cqm_setup_event(event, &group);
+
+	if (group) {
+		list_add_tail(&event->hw.cqm_group_entry,
+			      &group->hw.cqm_group_entry);
+	} else {
+		list_add_tail(&event->hw.cqm_groups_entry,
+			      &cache_groups);
+
+		/*
+		 * All RMIDs are either in use or have recently been
+		 * used. Kick the rotation worker to clean/free some.
+		 *
+		 * We only do this for the group leader, rather than for
+		 * every event in a group to save on needless work.
+		 */
+		if (!__rmid_valid(event->hw.cqm_rmid))
+			rotate = true;
+	}
+
+	mutex_unlock(&cache_mutex);
+
+	if (rotate)
+		schedule_delayed_work(&intel_cqm_rmid_work, 0);
+
+	return 0;
+}
+
+EVENT_ATTR_STR(llc_occupancy, intel_cqm_llc, "event=0x01");
+EVENT_ATTR_STR(llc_occupancy.per-pkg, intel_cqm_llc_pkg, "1");
+EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes");
+EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL);
+EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1");
+
+static struct attribute *intel_cqm_events_attr[] = {
+	EVENT_PTR(intel_cqm_llc),
+	EVENT_PTR(intel_cqm_llc_pkg),
+	EVENT_PTR(intel_cqm_llc_unit),
+	EVENT_PTR(intel_cqm_llc_scale),
+	EVENT_PTR(intel_cqm_llc_snapshot),
+	NULL,
+};
+
+static struct attribute_group intel_cqm_events_group = {
+	.name = "events",
+	.attrs = intel_cqm_events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-7");
+static struct attribute *intel_cqm_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group intel_cqm_format_group = {
+	.name = "format",
+	.attrs = intel_cqm_formats_attr,
+};
+
+static ssize_t
+max_recycle_threshold_show(struct device *dev, struct device_attribute *attr,
+			   char *page)
+{
+	ssize_t rv;
+
+	mutex_lock(&cache_mutex);
+	rv = snprintf(page, PAGE_SIZE-1, "%u\n", __intel_cqm_max_threshold);
+	mutex_unlock(&cache_mutex);
+
+	return rv;
+}
+
+static ssize_t
+max_recycle_threshold_store(struct device *dev,
+			    struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	unsigned int bytes, cachelines;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &bytes);
+	if (ret)
+		return ret;
+
+	mutex_lock(&cache_mutex);
+
+	__intel_cqm_max_threshold = bytes;
+	cachelines = bytes / cqm_l3_scale;
+
+	/*
+	 * The new maximum takes effect immediately.
+	 */
+	if (__intel_cqm_threshold > cachelines)
+		__intel_cqm_threshold = cachelines;
+
+	mutex_unlock(&cache_mutex);
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(max_recycle_threshold);
+
+static struct attribute *intel_cqm_attrs[] = {
+	&dev_attr_max_recycle_threshold.attr,
+	NULL,
+};
+
+static const struct attribute_group intel_cqm_group = {
+	.attrs = intel_cqm_attrs,
+};
+
+static const struct attribute_group *intel_cqm_attr_groups[] = {
+	&intel_cqm_events_group,
+	&intel_cqm_format_group,
+	&intel_cqm_group,
+	NULL,
+};
+
+static struct pmu intel_cqm_pmu = {
+	.hrtimer_interval_ms = RMID_DEFAULT_QUEUE_TIME,
+	.attr_groups	     = intel_cqm_attr_groups,
+	.task_ctx_nr	     = perf_sw_context,
+	.event_init	     = intel_cqm_event_init,
+	.add		     = intel_cqm_event_add,
+	.del		     = intel_cqm_event_del,
+	.start		     = intel_cqm_event_start,
+	.stop		     = intel_cqm_event_stop,
+	.read		     = intel_cqm_event_read,
+	.count		     = intel_cqm_event_count,
+};
+
+static inline void cqm_pick_event_reader(int cpu)
+{
+	int phys_id = topology_physical_package_id(cpu);
+	int i;
+
+	for_each_cpu(i, &cqm_cpumask) {
+		if (phys_id == topology_physical_package_id(i))
+			return;	/* already got reader for this socket */
+	}
+
+	cpumask_set_cpu(cpu, &cqm_cpumask);
+}
+
+static void intel_cqm_cpu_prepare(unsigned int cpu)
+{
+	struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	raw_spin_lock_init(&state->lock);
+	state->rmid = 0;
+	state->cnt  = 0;
+
+	WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
+	WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
+}
+
+static void intel_cqm_cpu_exit(unsigned int cpu)
+{
+	int phys_id = topology_physical_package_id(cpu);
+	int i;
+
+	/*
+	 * Is @cpu a designated cqm reader?
+	 */
+	if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask))
+		return;
+
+	for_each_online_cpu(i) {
+		if (i == cpu)
+			continue;
+
+		if (phys_id == topology_physical_package_id(i)) {
+			cpumask_set_cpu(i, &cqm_cpumask);
+			break;
+		}
+	}
+}
+
+static int intel_cqm_cpu_notifier(struct notifier_block *nb,
+				  unsigned long action, void *hcpu)
+{
+	unsigned int cpu  = (unsigned long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		intel_cqm_cpu_prepare(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		intel_cqm_cpu_exit(cpu);
+		break;
+	case CPU_STARTING:
+		cqm_pick_event_reader(cpu);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static const struct x86_cpu_id intel_cqm_match[] = {
+	{ .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_OCCUP_LLC },
+	{}
+};
+
+static int __init intel_cqm_init(void)
+{
+	char *str, scale[20];
+	int i, cpu, ret;
+
+	if (!x86_match_cpu(intel_cqm_match))
+		return -ENODEV;
+
+	cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale;
+
+	/*
+	 * It's possible that not all resources support the same number
+	 * of RMIDs. Instead of making scheduling much more complicated
+	 * (where we have to match a task's RMID to a cpu that supports
+	 * that many RMIDs) just find the minimum RMIDs supported across
+	 * all cpus.
+	 *
+	 * Also, check that the scales match on all cpus.
+	 */
+	cpu_notifier_register_begin();
+
+	for_each_online_cpu(cpu) {
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+		if (c->x86_cache_max_rmid < cqm_max_rmid)
+			cqm_max_rmid = c->x86_cache_max_rmid;
+
+		if (c->x86_cache_occ_scale != cqm_l3_scale) {
+			pr_err("Multiple LLC scale values, disabling\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	/*
+	 * A reasonable upper limit on the max threshold is the number
+	 * of lines tagged per RMID if all RMIDs have the same number of
+	 * lines tagged in the LLC.
+	 *
+	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
+	 */
+	__intel_cqm_max_threshold =
+		boot_cpu_data.x86_cache_size * 1024 / (cqm_max_rmid + 1);
+
+	snprintf(scale, sizeof(scale), "%u", cqm_l3_scale);
+	str = kstrdup(scale, GFP_KERNEL);
+	if (!str) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	event_attr_intel_cqm_llc_scale.event_str = str;
+
+	ret = intel_cqm_setup_rmid_cache();
+	if (ret)
+		goto out;
+
+	for_each_online_cpu(i) {
+		intel_cqm_cpu_prepare(i);
+		cqm_pick_event_reader(i);
+	}
+
+	__perf_cpu_notifier(intel_cqm_cpu_notifier);
+
+	ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
+	if (ret)
+		pr_err("Intel CQM perf registration failed: %d\n", ret);
+	else
+		pr_info("Intel CQM monitoring enabled\n");
+
+out:
+	cpu_notifier_register_done();
+
+	return ret;
+}
+device_initcall(intel_cqm_init);

arch/x86/kernel/cpu/perf_event_intel_lbr.c

@@ -39,6 +39,7 @@ static enum {
 #define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
 #define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
 #define LBR_FAR_BIT		8 /* do not capture far branches */
+#define LBR_CALL_STACK_BIT	9 /* enable call stack */
 
 #define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
 #define LBR_USER	(1 << LBR_USER_BIT)
@@ -49,6 +50,7 @@ static enum {
 #define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
 #define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
 #define LBR_FAR		(1 << LBR_FAR_BIT)
+#define LBR_CALL_STACK	(1 << LBR_CALL_STACK_BIT)
 
 #define LBR_PLM (LBR_KERNEL | LBR_USER)
 
@@ -69,33 +71,31 @@ static enum {
 #define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
 #define LBR_FROM_FLAG_ABORT    (1ULL << 61)
 
-#define for_each_branch_sample_type(x) \
-	for ((x) = PERF_SAMPLE_BRANCH_USER; \
-	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
-
 /*
  * x86control flow change classification
  * x86control flow changes include branches, interrupts, traps, faults
  */
 enum {
-	X86_BR_NONE     = 0,      /* unknown */
-
-	X86_BR_USER     = 1 << 0, /* branch target is user */
-	X86_BR_KERNEL   = 1 << 1, /* branch target is kernel */
-
-	X86_BR_CALL     = 1 << 2, /* call */
-	X86_BR_RET      = 1 << 3, /* return */
-	X86_BR_SYSCALL  = 1 << 4, /* syscall */
-	X86_BR_SYSRET   = 1 << 5, /* syscall return */
-	X86_BR_INT      = 1 << 6, /* sw interrupt */
-	X86_BR_IRET     = 1 << 7, /* return from interrupt */
-	X86_BR_JCC      = 1 << 8, /* conditional */
-	X86_BR_JMP      = 1 << 9, /* jump */
-	X86_BR_IRQ      = 1 << 10,/* hw interrupt or trap or fault */
-	X86_BR_IND_CALL = 1 << 11,/* indirect calls */
-	X86_BR_ABORT    = 1 << 12,/* transaction abort */
-	X86_BR_IN_TX    = 1 << 13,/* in transaction */
-	X86_BR_NO_TX    = 1 << 14,/* not in transaction */
+	X86_BR_NONE		= 0,      /* unknown */
+
+	X86_BR_USER		= 1 << 0, /* branch target is user */
+	X86_BR_KERNEL		= 1 << 1, /* branch target is kernel */
+
+	X86_BR_CALL		= 1 << 2, /* call */
+	X86_BR_RET		= 1 << 3, /* return */
+	X86_BR_SYSCALL		= 1 << 4, /* syscall */
+	X86_BR_SYSRET		= 1 << 5, /* syscall return */
+	X86_BR_INT		= 1 << 6, /* sw interrupt */
+	X86_BR_IRET		= 1 << 7, /* return from interrupt */
+	X86_BR_JCC		= 1 << 8, /* conditional */
+	X86_BR_JMP		= 1 << 9, /* jump */
+	X86_BR_IRQ		= 1 << 10,/* hw interrupt or trap or fault */
+	X86_BR_IND_CALL		= 1 << 11,/* indirect calls */
+	X86_BR_ABORT		= 1 << 12,/* transaction abort */
+	X86_BR_IN_TX		= 1 << 13,/* in transaction */
+	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
+	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
+	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -112,13 +112,15 @@ enum {
 	 X86_BR_JMP	 |\
 	 X86_BR_IRQ	 |\
 	 X86_BR_ABORT	 |\
-	 X86_BR_IND_CALL)
+	 X86_BR_IND_CALL |\
+	 X86_BR_ZERO_CALL)
 
 #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
 
 #define X86_BR_ANY_CALL		 \
 	(X86_BR_CALL		|\
 	 X86_BR_IND_CALL	|\
+	 X86_BR_ZERO_CALL	|\
 	 X86_BR_SYSCALL		|\
 	 X86_BR_IRQ		|\
 	 X86_BR_INT)
@@ -132,14 +134,23 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 
 static void __intel_pmu_lbr_enable(void)
 {
-	u64 debugctl;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 debugctl, lbr_select = 0;
 
-	if (cpuc->lbr_sel)
-		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
+	if (cpuc->lbr_sel) {
+		lbr_select = cpuc->lbr_sel->config;
+		wrmsrl(MSR_LBR_SELECT, lbr_select);
+	}
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-	debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	debugctl |= DEBUGCTLMSR_LBR;
+	/*
+	 * LBR callstack does not work well with FREEZE_LBRS_ON_PMI.
+	 * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions
+	 * may cause superfluous increase/decrease of LBR_TOS.
+	 */
+	if (!(lbr_select & LBR_CALL_STACK))
+		debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
 }
 
@@ -181,9 +192,116 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_64();
 }
 
+/*
+ * TOS = most recently recorded branch
+ */
+static inline u64 intel_pmu_lbr_tos(void)
+{
+	u64 tos;
+
+	rdmsrl(x86_pmu.lbr_tos, tos);
+	return tos;
+}
+
+enum {
+	LBR_NONE,
+	LBR_VALID,
+};
+
+static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
+{
+	int i;
+	unsigned lbr_idx, mask;
+	u64 tos;
+
+	if (task_ctx->lbr_callstack_users == 0 ||
+	    task_ctx->lbr_stack_state == LBR_NONE) {
+		intel_pmu_lbr_reset();
+		return;
+	}
+
+	mask = x86_pmu.lbr_nr - 1;
+	tos = intel_pmu_lbr_tos();
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
+		wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+	}
+	task_ctx->lbr_stack_state = LBR_NONE;
+}
+
+static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
+{
+	int i;
+	unsigned lbr_idx, mask;
+	u64 tos;
+
+	if (task_ctx->lbr_callstack_users == 0) {
+		task_ctx->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	mask = x86_pmu.lbr_nr - 1;
+	tos = intel_pmu_lbr_tos();
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
+		rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+	}
+	task_ctx->lbr_stack_state = LBR_VALID;
+}
+
+void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_task_context *task_ctx;
+
+	if (!x86_pmu.lbr_nr)
+		return;
+
+	/*
+	 * If LBR callstack feature is enabled and the stack was saved when
+	 * the task was scheduled out, restore the stack. Otherwise flush
+	 * the LBR stack.
+	 */
+	task_ctx = ctx ? ctx->task_ctx_data : NULL;
+	if (task_ctx) {
+		if (sched_in) {
+			__intel_pmu_lbr_restore(task_ctx);
+			cpuc->lbr_context = ctx;
+		} else {
+			__intel_pmu_lbr_save(task_ctx);
+		}
+		return;
+	}
+
+	/*
+	 * When sampling the branck stack in system-wide, it may be
+	 * necessary to flush the stack on context switch. This happens
+	 * when the branch stack does not tag its entries with the pid
+	 * of the current task. Otherwise it becomes impossible to
+	 * associate a branch entry with a task. This ambiguity is more
+	 * likely to appear when the branch stack supports priv level
+	 * filtering and the user sets it to monitor only at the user
+	 * level (which could be a useful measurement in system-wide
+	 * mode). In that case, the risk is high of having a branch
+	 * stack with branch from multiple tasks.
+ 	 */
+	if (sched_in) {
+		intel_pmu_lbr_reset();
+		cpuc->lbr_context = ctx;
+	}
+}
+
+static inline bool branch_user_callstack(unsigned br_sel)
+{
+	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
+}
+
 void intel_pmu_lbr_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
@@ -198,18 +316,33 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 	}
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
+	if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
+					event->ctx->task_ctx_data) {
+		task_ctx = event->ctx->task_ctx_data;
+		task_ctx->lbr_callstack_users++;
+	}
+
 	cpuc->lbr_users++;
+	perf_sched_cb_inc(event->ctx->pmu);
 }
 
 void intel_pmu_lbr_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_task_context *task_ctx;
 
 	if (!x86_pmu.lbr_nr)
 		return;
 
+	if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
+					event->ctx->task_ctx_data) {
+		task_ctx = event->ctx->task_ctx_data;
+		task_ctx->lbr_callstack_users--;
+	}
+
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
+	perf_sched_cb_dec(event->ctx->pmu);
 
 	if (cpuc->enabled && !cpuc->lbr_users) {
 		__intel_pmu_lbr_disable();
@@ -234,18 +367,6 @@ void intel_pmu_lbr_disable_all(void)
 		__intel_pmu_lbr_disable();
 }
 
-/*
- * TOS = most recently recorded branch
- */
-static inline u64 intel_pmu_lbr_tos(void)
-{
-	u64 tos;
-
-	rdmsrl(x86_pmu.lbr_tos, tos);
-
-	return tos;
-}
-
 static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 {
 	unsigned long mask = x86_pmu.lbr_nr - 1;
@@ -350,7 +471,7 @@ void intel_pmu_lbr_read(void)
  * - in case there is no HW filter
  * - in case the HW filter has errata or limitations
  */
-static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 {
 	u64 br_type = event->attr.branch_sample_type;
 	int mask = 0;
@@ -387,11 +508,21 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 	if (br_type & PERF_SAMPLE_BRANCH_COND)
 		mask |= X86_BR_JCC;
 
+	if (br_type & PERF_SAMPLE_BRANCH_CALL_STACK) {
+		if (!x86_pmu_has_lbr_callstack())
+			return -EOPNOTSUPP;
+		if (mask & ~(X86_BR_USER | X86_BR_KERNEL))
+			return -EINVAL;
+		mask |= X86_BR_CALL | X86_BR_IND_CALL | X86_BR_RET |
+			X86_BR_CALL_STACK;
+	}
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
 	 */
 	event->hw.branch_reg.reg = mask;
+	return 0;
 }
 
 /*
@@ -403,14 +534,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 {
 	struct hw_perf_event_extra *reg;
 	u64 br_type = event->attr.branch_sample_type;
-	u64 mask = 0, m;
-	u64 v;
+	u64 mask = 0, v;
+	int i;
 
-	for_each_branch_sample_type(m) {
-		if (!(br_type & m))
+	for (i = 0; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) {
+		if (!(br_type & (1ULL << i)))
 			continue;
 
-		v = x86_pmu.lbr_sel_map[m];
+		v = x86_pmu.lbr_sel_map[i];
 		if (v == LBR_NOT_SUPP)
 			return -EOPNOTSUPP;
 
@@ -420,8 +551,12 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	reg = &event->hw.branch_reg;
 	reg->idx = EXTRA_REG_LBR;
 
-	/* LBR_SELECT operates in suppress mode so invert mask */
-	reg->config = ~mask & x86_pmu.lbr_sel_mask;
+	/*
+	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
+	 * in suppress mode. So LBR_SELECT should be set to
+	 * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK)
+	 */
+	reg->config = mask ^ x86_pmu.lbr_sel_mask;
 
 	return 0;
 }
@@ -439,7 +574,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
 	/*
 	 * setup SW LBR filter
 	 */
-	intel_pmu_setup_sw_lbr_filter(event);
+	ret = intel_pmu_setup_sw_lbr_filter(event);
+	if (ret)
+		return ret;
 
 	/*
 	 * setup HW LBR filter, if any
@@ -568,6 +705,12 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 		ret = X86_BR_INT;
 		break;
 	case 0xe8: /* call near rel */
+		insn_get_immediate(&insn);
+		if (insn.immediate1.value == 0) {
+			/* zero length call */
+			ret = X86_BR_ZERO_CALL;
+			break;
+		}
 	case 0x9a: /* call far absolute */
 		ret = X86_BR_CALL;
 		break;
@@ -678,35 +821,49 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 /*
  * Map interface branch filters onto LBR filters
  */
-static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
-	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
-	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
-	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
-	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
-	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_REL_JMP
-					| LBR_IND_JMP | LBR_FAR,
+static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_REL_JMP
+						| LBR_IND_JMP | LBR_FAR,
 	/*
 	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
 	 */
-	[PERF_SAMPLE_BRANCH_ANY_CALL] =
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] =
 	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
 	/*
 	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
 	 */
-	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
-	[PERF_SAMPLE_BRANCH_COND]     = LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
+	[PERF_SAMPLE_BRANCH_COND_SHIFT]     = LBR_JCC,
 };
 
-static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
-	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
-	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
-	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
-	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
-	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_FAR,
-	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
-					| LBR_FAR,
-	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
-	[PERF_SAMPLE_BRANCH_COND]       = LBR_JCC,
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
+						| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
+	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
+};
+
+static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
+						| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
+	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
+	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
+						| LBR_RETURN | LBR_CALL_STACK,
 };
 
 /* core */
@@ -765,6 +922,20 @@ void __init intel_pmu_lbr_init_snb(void)
 	pr_cont("16-deep LBR, ");
 }
 
+/* haswell */
+void intel_pmu_lbr_init_hsw(void)
+{
+	x86_pmu.lbr_nr	 = 16;
+	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
+	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
+
+	pr_cont("16-deep LBR, ");
+}
+
 /* atom */
 void __init intel_pmu_lbr_init_atom(void)
 {

arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c

@@ -1132,8 +1132,7 @@ static int snbep_pci2phy_map_init(int devid)
 		}
 	}
 
-	if (ubox_dev)
-		pci_dev_put(ubox_dev);
+	pci_dev_put(ubox_dev);
 
 	return err ? pcibios_err_to_errno(err) : 0;
 }

arch/x86/kernel/kprobes/core.c

@@ -354,6 +354,7 @@ int __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
+	int length;
 	unsigned long recovered_insn =
 		recover_probed_instruction(buf, (unsigned long)src);
 
@@ -361,16 +362,18 @@ int __copy_instruction(u8 *dest, u8 *src)
 		return 0;
 	kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 	insn_get_length(&insn);
+	length = insn.length;
+
 	/* Another subsystem puts a breakpoint, failed to recover */
 	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
-	memcpy(dest, insn.kaddr, insn.length);
+	memcpy(dest, insn.kaddr, length);
 
 #ifdef CONFIG_X86_64
 	if (insn_rip_relative(&insn)) {
 		s64 newdisp;
 		u8 *disp;
-		kernel_insn_init(&insn, dest, insn.length);
+		kernel_insn_init(&insn, dest, length);
 		insn_get_displacement(&insn);
 		/*
 		 * The copied instruction uses the %rip-relative addressing
@@ -394,7 +397,7 @@ int __copy_instruction(u8 *dest, u8 *src)
 		*(s32 *) disp = (s32) newdisp;
 	}
 #endif
-	return insn.length;
+	return length;
 }
 
 static int arch_copy_kprobe(struct kprobe *p)

include/linux/perf_event.h

@@ -53,6 +53,7 @@ struct perf_guest_info_callbacks {
 #include <linux/sysfs.h>
 #include <linux/perf_regs.h>
 #include <linux/workqueue.h>
+#include <linux/cgroup.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -118,10 +119,16 @@ struct hw_perf_event {
 			struct hrtimer	hrtimer;
 		};
 		struct { /* tracepoint */
-			struct task_struct	*tp_target;
 			/* for tp_event->class */
 			struct list_head	tp_list;
 		};
+		struct { /* intel_cqm */
+			int			cqm_state;
+			int			cqm_rmid;
+			struct list_head	cqm_events_entry;
+			struct list_head	cqm_groups_entry;
+			struct list_head	cqm_group_entry;
+		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		struct { /* breakpoint */
 			/*
@@ -129,12 +136,12 @@ struct hw_perf_event {
 			 * problem hw_breakpoint has with context
 			 * creation and event initalization.
 			 */
-			struct task_struct		*bp_target;
 			struct arch_hw_breakpoint	info;
 			struct list_head		bp_list;
 		};
 #endif
 	};
+	struct task_struct		*target;
 	int				state;
 	local64_t			prev_count;
 	u64				sample_period;
@@ -262,9 +269,20 @@ struct pmu {
 	int (*event_idx)		(struct perf_event *event); /*optional */
 
 	/*
-	 * flush branch stack on context-switches (needed in cpu-wide mode)
+	 * context-switches callback
+	 */
+	void (*sched_task)		(struct perf_event_context *ctx,
+					bool sched_in);
+	/*
+	 * PMU specific data size
+	 */
+	size_t				task_ctx_size;
+
+
+	/*
+	 * Return the count value for a counter.
 	 */
-	void (*flush_branch_stack)	(void);
+	u64 (*count)			(struct perf_event *event); /*optional*/
 };
 
 /**
@@ -300,6 +318,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_CONTEXT	0x01
 #define PERF_ATTACH_GROUP	0x02
 #define PERF_ATTACH_TASK	0x04
+#define PERF_ATTACH_TASK_DATA	0x08
 
 struct perf_cgroup;
 struct ring_buffer;
@@ -504,7 +523,7 @@ struct perf_event_context {
 	u64				generation;
 	int				pin_count;
 	int				nr_cgroups;	 /* cgroup evts */
-	int				nr_branch_stack; /* branch_stack evt */
+	void				*task_ctx_data; /* pmu specific data */
 	struct rcu_head			rcu_head;
 
 	struct delayed_work		orphans_remove;
@@ -540,6 +559,35 @@ struct perf_output_handle {
 	int				page;
 };
 
+#ifdef CONFIG_CGROUP_PERF
+
+/*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+	u64				time;
+	u64				timestamp;
+};
+
+struct perf_cgroup {
+	struct cgroup_subsys_state	css;
+	struct perf_cgroup_info	__percpu *info;
+};
+
+/*
+ * Must ensure cgroup is pinned (css_get) before calling
+ * this function. In other words, we cannot call this function
+ * if there is no cgroup event for the current CPU context.
+ */
+static inline struct perf_cgroup *
+perf_cgroup_from_task(struct task_struct *task)
+{
+	return container_of(task_css(task, perf_event_cgrp_id),
+			    struct perf_cgroup, css);
+}
+#endif /* CONFIG_CGROUP_PERF */
+
 #ifdef CONFIG_PERF_EVENTS
 
 extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
@@ -558,6 +606,8 @@ extern void perf_event_delayed_put(struct task_struct *task);
 extern void perf_event_print_debug(void);
 extern void perf_pmu_disable(struct pmu *pmu);
 extern void perf_pmu_enable(struct pmu *pmu);
+extern void perf_sched_cb_dec(struct pmu *pmu);
+extern void perf_sched_cb_inc(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern int perf_event_refresh(struct perf_event *event, int refresh);
@@ -731,6 +781,11 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 		__perf_event_task_sched_out(prev, next);
 }
 
+static inline u64 __perf_event_count(struct perf_event *event)
+{
+	return local64_read(&event->count) + atomic64_read(&event->child_count);
+}
+
 extern void perf_event_mmap(struct vm_area_struct *vma);
 extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
@@ -800,6 +855,11 @@ static inline bool has_branch_stack(struct perf_event *event)
 	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
 }
 
+static inline bool needs_branch_stack(struct perf_event *event)
+{
+	return event->attr.branch_sample_type != 0;
+}
+
 extern int perf_output_begin(struct perf_output_handle *handle,
 			     struct perf_event *event, unsigned int size);
 extern void perf_output_end(struct perf_output_handle *handle);

include/uapi/linux/perf_event.h

@@ -152,21 +152,42 @@ enum perf_event_sample_format {
  * The branch types can be combined, however BRANCH_ANY covers all types
  * of branches and therefore it supersedes all the other types.
  */
+enum perf_branch_sample_type_shift {
+	PERF_SAMPLE_BRANCH_USER_SHIFT		= 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL_SHIFT		= 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV_SHIFT		= 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY_SHIFT		= 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT	= 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT	= 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL_SHIFT	= 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT	= 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX_SHIFT		= 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX_SHIFT		= 9, /* not in transaction */
+	PERF_SAMPLE_BRANCH_COND_SHIFT		= 10, /* conditional branches */
+
+	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT	= 11, /* call/ret stack */
+
+	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
+};
+
 enum perf_branch_sample_type {
-	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
-	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
-	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */
-
-	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
-	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
-	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
-	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
-	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
-	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
-	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
-	PERF_SAMPLE_BRANCH_COND		= 1U << 10, /* conditional branches */
-
-	PERF_SAMPLE_BRANCH_MAX		= 1U << 11, /* non-ABI */
+	PERF_SAMPLE_BRANCH_USER		= 1U << PERF_SAMPLE_BRANCH_USER_SHIFT,
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT,
+	PERF_SAMPLE_BRANCH_HV		= 1U << PERF_SAMPLE_BRANCH_HV_SHIFT,
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_IN_TX	= 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_TX	= 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_COND		= 1U << PERF_SAMPLE_BRANCH_COND_SHIFT,
+
+	PERF_SAMPLE_BRANCH_CALL_STACK	= 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
 #define PERF_SAMPLE_BRANCH_PLM_ALL \

kernel/events/core.c

@@ -34,11 +34,11 @@
 #include <linux/syscalls.h>
 #include <linux/anon_inodes.h>
 #include <linux/kernel_stat.h>
+#include <linux/cgroup.h>
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/mm_types.h>
-#include <linux/cgroup.h>
 #include <linux/module.h>
 #include <linux/mman.h>
 #include <linux/compat.h>
@@ -153,7 +153,7 @@ enum event_type_t {
  */
 struct static_key_deferred perf_sched_events __read_mostly;
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
-static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -351,32 +351,6 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
 
 #ifdef CONFIG_CGROUP_PERF
 
-/*
- * perf_cgroup_info keeps track of time_enabled for a cgroup.
- * This is a per-cpu dynamically allocated data structure.
- */
-struct perf_cgroup_info {
-	u64				time;
-	u64				timestamp;
-};
-
-struct perf_cgroup {
-	struct cgroup_subsys_state	css;
-	struct perf_cgroup_info	__percpu *info;
-};
-
-/*
- * Must ensure cgroup is pinned (css_get) before calling
- * this function. In other words, we cannot call this function
- * if there is no cgroup event for the current CPU context.
- */
-static inline struct perf_cgroup *
-perf_cgroup_from_task(struct task_struct *task)
-{
-	return container_of(task_css(task, perf_event_cgrp_id),
-			    struct perf_cgroup, css);
-}
-
 static inline bool
 perf_cgroup_match(struct perf_event *event)
 {
@@ -905,6 +879,15 @@ static void get_ctx(struct perf_event_context *ctx)
 	WARN_ON(!atomic_inc_not_zero(&ctx->refcount));
 }
 
+static void free_ctx(struct rcu_head *head)
+{
+	struct perf_event_context *ctx;
+
+	ctx = container_of(head, struct perf_event_context, rcu_head);
+	kfree(ctx->task_ctx_data);
+	kfree(ctx);
+}
+
 static void put_ctx(struct perf_event_context *ctx)
 {
 	if (atomic_dec_and_test(&ctx->refcount)) {
@@ -912,7 +895,7 @@ static void put_ctx(struct perf_event_context *ctx)
 			put_ctx(ctx->parent_ctx);
 		if (ctx->task)
 			put_task_struct(ctx->task);
-		kfree_rcu(ctx, rcu_head);
+		call_rcu(&ctx->rcu_head, free_ctx);
 	}
 }
 
@@ -1239,9 +1222,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (is_cgroup_event(event))
 		ctx->nr_cgroups++;
 
-	if (has_branch_stack(event))
-		ctx->nr_branch_stack++;
-
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	ctx->nr_events++;
 	if (event->attr.inherit_stat)
@@ -1408,9 +1388,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 			cpuctx->cgrp = NULL;
 	}
 
-	if (has_branch_stack(event))
-		ctx->nr_branch_stack--;
-
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -1881,6 +1858,10 @@ event_sched_in(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_running += tstamp - event->tstamp_stopped;
+
+	perf_set_shadow_time(event, ctx, tstamp);
+
 	if (event->pmu->add(event, PERF_EF_START)) {
 		event->state = PERF_EVENT_STATE_INACTIVE;
 		event->oncpu = -1;
@@ -1888,10 +1869,6 @@ event_sched_in(struct perf_event *event,
 		goto out;
 	}
 
-	event->tstamp_running += tstamp - event->tstamp_stopped;
-
-	perf_set_shadow_time(event, ctx, tstamp);
-
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	if (!ctx->nr_active++)
@@ -2559,6 +2536,9 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 			next->perf_event_ctxp[ctxn] = ctx;
 			ctx->task = next;
 			next_ctx->task = task;
+
+			swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
+
 			do_switch = 0;
 
 			perf_event_sync_stat(ctx, next_ctx);
@@ -2577,6 +2557,56 @@ unlock:
 	}
 }
 
+void perf_sched_cb_dec(struct pmu *pmu)
+{
+	this_cpu_dec(perf_sched_cb_usages);
+}
+
+void perf_sched_cb_inc(struct pmu *pmu)
+{
+	this_cpu_inc(perf_sched_cb_usages);
+}
+
+/*
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when the context switch callback is enabled.
+ */
+static void perf_pmu_sched_task(struct task_struct *prev,
+				struct task_struct *next,
+				bool sched_in)
+{
+	struct perf_cpu_context *cpuctx;
+	struct pmu *pmu;
+	unsigned long flags;
+
+	if (prev == next)
+		return;
+
+	local_irq_save(flags);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		if (pmu->sched_task) {
+			cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+			perf_pmu_disable(pmu);
+
+			pmu->sched_task(cpuctx->task_ctx, sched_in);
+
+			perf_pmu_enable(pmu);
+
+			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+		}
+	}
+
+	rcu_read_unlock();
+
+	local_irq_restore(flags);
+}
+
 #define for_each_task_context_nr(ctxn)					\
 	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)
 
@@ -2596,6 +2626,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(task, next, false);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 
@@ -2754,64 +2787,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	perf_ctx_unlock(cpuctx, ctx);
 }
 
-/*
- * When sampling the branck stack in system-wide, it may be necessary
- * to flush the stack on context switch. This happens when the branch
- * stack does not tag its entries with the pid of the current task.
- * Otherwise it becomes impossible to associate a branch entry with a
- * task. This ambiguity is more likely to appear when the branch stack
- * supports priv level filtering and the user sets it to monitor only
- * at the user level (which could be a useful measurement in system-wide
- * mode). In that case, the risk is high of having a branch stack with
- * branch from multiple tasks. Flushing may mean dropping the existing
- * entries or stashing them somewhere in the PMU specific code layer.
- *
- * This function provides the context switch callback to the lower code
- * layer. It is invoked ONLY when there is at least one system-wide context
- * with at least one active event using taken branch sampling.
- */
-static void perf_branch_stack_sched_in(struct task_struct *prev,
-				       struct task_struct *task)
-{
-	struct perf_cpu_context *cpuctx;
-	struct pmu *pmu;
-	unsigned long flags;
-
-	/* no need to flush branch stack if not changing task */
-	if (prev == task)
-		return;
-
-	local_irq_save(flags);
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-		/*
-		 * check if the context has at least one
-		 * event using PERF_SAMPLE_BRANCH_STACK
-		 */
-		if (cpuctx->ctx.nr_branch_stack > 0
-		    && pmu->flush_branch_stack) {
-
-			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
-
-			perf_pmu_disable(pmu);
-
-			pmu->flush_branch_stack();
-
-			perf_pmu_enable(pmu);
-
-			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
-		}
-	}
-
-	rcu_read_unlock();
-
-	local_irq_restore(flags);
-}
-
 /*
  * Called from scheduler to add the events of the current task
  * with interrupts disabled.
@@ -2844,9 +2819,8 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
 
-	/* check for system-wide branch_stack events */
-	if (atomic_read(this_cpu_ptr(&perf_branch_stack_events)))
-		perf_branch_stack_sched_in(prev, task);
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(prev, task, true);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -3220,7 +3194,10 @@ static void __perf_event_read(void *info)
 
 static inline u64 perf_event_count(struct perf_event *event)
 {
-	return local64_read(&event->count) + atomic64_read(&event->child_count);
+	if (event->pmu->count)
+		return event->pmu->count(event);
+
+	return __perf_event_count(event);
 }
 
 static u64 perf_event_read(struct perf_event *event)
@@ -3321,12 +3298,15 @@ errout:
  * Returns a matching context with refcount and pincount.
  */
 static struct perf_event_context *
-find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
+find_get_context(struct pmu *pmu, struct task_struct *task,
+		struct perf_event *event)
 {
 	struct perf_event_context *ctx, *clone_ctx = NULL;
 	struct perf_cpu_context *cpuctx;
+	void *task_ctx_data = NULL;
 	unsigned long flags;
 	int ctxn, err;
+	int cpu = event->cpu;
 
 	if (!task) {
 		/* Must be root to operate on a CPU event: */
@@ -3354,11 +3334,24 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 	if (ctxn < 0)
 		goto errout;
 
+	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
+		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+		if (!task_ctx_data) {
+			err = -ENOMEM;
+			goto errout;
+		}
+	}
+
 retry:
 	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		clone_ctx = unclone_ctx(ctx);
 		++ctx->pin_count;
+
+		if (task_ctx_data && !ctx->task_ctx_data) {
+			ctx->task_ctx_data = task_ctx_data;
+			task_ctx_data = NULL;
+		}
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 
 		if (clone_ctx)
@@ -3369,6 +3362,11 @@ retry:
 		if (!ctx)
 			goto errout;
 
+		if (task_ctx_data) {
+			ctx->task_ctx_data = task_ctx_data;
+			task_ctx_data = NULL;
+		}
+
 		err = 0;
 		mutex_lock(&task->perf_event_mutex);
 		/*
@@ -3395,9 +3393,11 @@ retry:
 		}
 	}
 
+	kfree(task_ctx_data);
 	return ctx;
 
 errout:
+	kfree(task_ctx_data);
 	return ERR_PTR(err);
 }
 
@@ -3423,10 +3423,6 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu)
 	if (event->parent)
 		return;
 
-	if (has_branch_stack(event)) {
-		if (!(event->attach_state & PERF_ATTACH_TASK))
-			atomic_dec(&per_cpu(perf_branch_stack_events, cpu));
-	}
 	if (is_cgroup_event(event))
 		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
 }
@@ -4574,6 +4570,13 @@ static void perf_pending_event(struct irq_work *entry)
 {
 	struct perf_event *event = container_of(entry,
 			struct perf_event, pending);
+	int rctx;
+
+	rctx = perf_swevent_get_recursion_context();
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
 
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -4584,6 +4587,9 @@ static void perf_pending_event(struct irq_work *entry)
 		event->pending_wakeup = 0;
 		perf_event_wakeup(event);
 	}
+
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
 }
 
 /*
@@ -6123,6 +6129,7 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
@@ -6592,6 +6599,7 @@ static int cpu_clock_event_add(struct perf_event *event, int flags)
 {
 	if (flags & PERF_EF_START)
 		cpu_clock_event_start(event, flags);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
@@ -6666,6 +6674,7 @@ static int task_clock_event_add(struct perf_event *event, int flags)
 {
 	if (flags & PERF_EF_START)
 		task_clock_event_start(event, flags);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
@@ -7027,12 +7036,23 @@ EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
 static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 {
+	struct perf_event_context *ctx = NULL;
 	int ret;
 
 	if (!try_module_get(pmu->module))
 		return -ENODEV;
+
+	if (event->group_leader != event) {
+		ctx = perf_event_ctx_lock(event->group_leader);
+		BUG_ON(!ctx);
+	}
+
 	event->pmu = pmu;
 	ret = pmu->event_init(event);
+
+	if (ctx)
+		perf_event_ctx_unlock(event->group_leader, ctx);
+
 	if (ret)
 		module_put(pmu->module);
 
@@ -7079,10 +7099,6 @@ static void account_event_cpu(struct perf_event *event, int cpu)
 	if (event->parent)
 		return;
 
-	if (has_branch_stack(event)) {
-		if (!(event->attach_state & PERF_ATTACH_TASK))
-			atomic_inc(&per_cpu(perf_branch_stack_events, cpu));
-	}
 	if (is_cgroup_event(event))
 		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
 }
@@ -7121,7 +7137,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		 struct perf_event *group_leader,
 		 struct perf_event *parent_event,
 		 perf_overflow_handler_t overflow_handler,
-		 void *context)
+		 void *context, int cgroup_fd)
 {
 	struct pmu *pmu;
 	struct perf_event *event;
@@ -7176,16 +7192,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	if (task) {
 		event->attach_state = PERF_ATTACH_TASK;
-
-		if (attr->type == PERF_TYPE_TRACEPOINT)
-			event->hw.tp_target = task;
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
 		/*
-		 * hw_breakpoint is a bit difficult here..
+		 * XXX pmu::event_init needs to know what task to account to
+		 * and we cannot use the ctx information because we need the
+		 * pmu before we get a ctx.
 		 */
-		else if (attr->type == PERF_TYPE_BREAKPOINT)
-			event->hw.bp_target = task;
-#endif
+		event->hw.target = task;
 	}
 
 	if (!overflow_handler && parent_event) {
@@ -7214,6 +7226,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
 		goto err_ns;
 
+	if (!has_branch_stack(event))
+		event->attr.branch_sample_type = 0;
+
+	if (cgroup_fd != -1) {
+		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
+		if (err)
+			goto err_ns;
+	}
+
 	pmu = perf_init_event(event);
 	if (!pmu)
 		goto err_ns;
@@ -7237,6 +7258,8 @@ err_pmu:
 		event->destroy(event);
 	module_put(pmu->module);
 err_ns:
+	if (is_cgroup_event(event))
+		perf_detach_cgroup(event);
 	if (event->ns)
 		put_pid_ns(event->ns);
 	kfree(event);
@@ -7455,6 +7478,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int move_group = 0;
 	int err;
 	int f_flags = O_RDWR;
+	int cgroup_fd = -1;
 
 	/* for future expandability... */
 	if (flags & ~PERF_FLAG_ALL)
@@ -7520,21 +7544,16 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	get_online_cpus();
 
+	if (flags & PERF_FLAG_PID_CGROUP)
+		cgroup_fd = pid;
+
 	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
-				 NULL, NULL);
+				 NULL, NULL, cgroup_fd);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
 		goto err_cpus;
 	}
 
-	if (flags & PERF_FLAG_PID_CGROUP) {
-		err = perf_cgroup_connect(pid, event, &attr, group_leader);
-		if (err) {
-			__free_event(event);
-			goto err_cpus;
-		}
-	}
-
 	if (is_sampling_event(event)) {
 		if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) {
 			err = -ENOTSUPP;
@@ -7576,7 +7595,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	/*
 	 * Get the target context (task or percpu):
 	 */
-	ctx = find_get_context(pmu, task, event->cpu);
+	ctx = find_get_context(pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto err_alloc;
@@ -7771,7 +7790,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	 */
 
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
-				 overflow_handler, context);
+				 overflow_handler, context, -1);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
 		goto err;
@@ -7782,7 +7801,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	account_event(event);
 
-	ctx = find_get_context(event->pmu, task, cpu);
+	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto err_free;
@@ -8132,7 +8151,7 @@ inherit_event(struct perf_event *parent_event,
 					   parent_event->cpu,
 					   child,
 					   group_leader, parent_event,
-				           NULL, NULL);
+					   NULL, NULL, -1);
 	if (IS_ERR(child_event))
 		return child_event;
 

kernel/events/hw_breakpoint.c

@@ -116,12 +116,12 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
  */
 static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
 {
-	struct task_struct *tsk = bp->hw.bp_target;
+	struct task_struct *tsk = bp->hw.target;
 	struct perf_event *iter;
 	int count = 0;
 
 	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
-		if (iter->hw.bp_target == tsk &&
+		if (iter->hw.target == tsk &&
 		    find_slot_idx(iter) == type &&
 		    (iter->cpu < 0 || cpu == iter->cpu))
 			count += hw_breakpoint_weight(iter);
@@ -153,7 +153,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		int nr;
 
 		nr = info->cpu_pinned;
-		if (!bp->hw.bp_target)
+		if (!bp->hw.target)
 			nr += max_task_bp_pinned(cpu, type);
 		else
 			nr += task_bp_pinned(cpu, bp, type);
@@ -210,7 +210,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
 		weight = -weight;
 
 	/* Pinned counter cpu profiling */
-	if (!bp->hw.bp_target) {
+	if (!bp->hw.target) {
 		get_bp_info(bp->cpu, type)->cpu_pinned += weight;
 		return;
 	}

kernel/trace/trace_uprobe.c

@@ -1005,7 +1005,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
 		return true;
 
 	list_for_each_entry(event, &filter->perf_events, hw.tp_list) {
-		if (event->hw.tp_target->mm == mm)
+		if (event->hw.target->mm == mm)
 			return true;
 	}
 
@@ -1015,7 +1015,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
 static inline bool
 uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
 {
-	return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
+	return __uprobe_perf_filter(&tu->filter, event->hw.target->mm);
 }
 
 static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
@@ -1023,10 +1023,10 @@ static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
 	bool done;
 
 	write_lock(&tu->filter.rwlock);
-	if (event->hw.tp_target) {
+	if (event->hw.target) {
 		list_del(&event->hw.tp_list);
 		done = tu->filter.nr_systemwide ||
-			(event->hw.tp_target->flags & PF_EXITING) ||
+			(event->hw.target->flags & PF_EXITING) ||
 			uprobe_filter_event(tu, event);
 	} else {
 		tu->filter.nr_systemwide--;
@@ -1046,7 +1046,7 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
 	int err;
 
 	write_lock(&tu->filter.rwlock);
-	if (event->hw.tp_target) {
+	if (event->hw.target) {
 		/*
 		 * event->parent != NULL means copy_process(), we can avoid
 		 * uprobe_apply(). current->mm must be probed and we can rely

tools/build/Build.include

@@ -0,0 +1,81 @@
+###
+# build: Generic definitions
+#
+#  Lots of this code have been borrowed or heavily inspired from parts
+#  of kbuild code, which is not credited, but mostly developed by:
+#
+#  Copyright (C) Sam Ravnborg <sam@mars.ravnborg.org>, 2015
+#  Copyright (C) Linus Torvalds <torvalds@linux-foundation.org>, 2015
+#
+
+###
+# Convenient variables
+comma   := ,
+squote  := '
+
+###
+# Name of target with a '.' as filename prefix. foo/bar.o => foo/.bar.o
+dot-target = $(dir $@).$(notdir $@)
+
+###
+# filename of target with directory and extension stripped
+basetarget = $(basename $(notdir $@))
+
+###
+# The temporary file to save gcc -MD generated dependencies must not
+# contain a comma
+depfile = $(subst $(comma),_,$(dot-target).d)
+
+###
+# Check if both arguments has same arguments. Result is empty string if equal.
+arg-check = $(strip $(filter-out $(cmd_$(1)), $(cmd_$@)) \
+                    $(filter-out $(cmd_$@),   $(cmd_$(1))) )
+
+###
+# Escape single quote for use in echo statements
+escsq = $(subst $(squote),'\$(squote)',$1)
+
+# Echo command
+# Short version is used, if $(quiet) equals `quiet_', otherwise full one.
+echo-cmd = $(if $($(quiet)cmd_$(1)),\
+           echo '  $(call escsq,$($(quiet)cmd_$(1)))';)
+
+###
+# Replace >$< with >$$< to preserve $ when reloading the .cmd file
+# (needed for make)
+# Replace >#< with >\#< to avoid starting a comment in the .cmd file
+# (needed for make)
+# Replace >'< with >'\''< to be able to enclose the whole string in '...'
+# (needed for the shell)
+make-cmd = $(call escsq,$(subst \#,\\\#,$(subst $$,$$$$,$(cmd_$(1)))))
+
+###
+# Find any prerequisites that is newer than target or that does not exist.
+# PHONY targets skipped in both cases.
+any-prereq = $(filter-out $(PHONY),$?) $(filter-out $(PHONY) $(wildcard $^),$^)
+
+###
+# if_changed_dep  - execute command if any prerequisite is newer than
+#                   target, or command line has changed and update
+#                   dependencies in the cmd file
+if_changed_dep = $(if $(strip $(any-prereq) $(arg-check)),         \
+	@set -e;                                                   \
+	$(echo-cmd) $(cmd_$(1));                                   \
+	cat $(depfile) > $(dot-target).cmd;                        \
+	printf '%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
+
+# if_changed      - execute command if any prerequisite is newer than
+#                   target, or command line has changed
+if_changed = $(if $(strip $(any-prereq) $(arg-check)),             \
+	@set -e;                                                   \
+	$(echo-cmd) $(cmd_$(1));                                   \
+	printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd)
+
+###
+# C flags to be used in rule definitions, includes:
+# - depfile generation
+# - global $(CFLAGS)
+# - per target C flags
+# - per object C flags
+# - BUILD_STR macro to allow '-D"$(variable)"' constructs
+c_flags = -Wp,-MD,$(depfile),-MT,$@ $(CFLAGS) -D"BUILD_STR(s)=\#s" $(CFLAGS_$(basetarget).o) $(CFLAGS_$(obj))

tools/build/Documentation/Build.txt

@@ -0,0 +1,139 @@
+Build Framework
+===============
+
+The perf build framework was adopted from the kernel build system, hence the
+idea and the way how objects are built is the same.
+
+Basically the user provides set of 'Build' files that list objects and
+directories to nest for specific target to be build.
+
+Unlike the kernel we don't have a single build object 'obj-y' list that where
+we setup source objects, but we support more. This allows one 'Build' file to
+carry a sources list for multiple build objects.
+
+a) Build framework makefiles
+----------------------------
+
+The build framework consists of 2 Makefiles:
+
+  Build.include
+  Makefile.build
+
+While the 'Build.include' file contains just some generic definitions, the
+'Makefile.build' file is the makefile used from the outside. It's
+interface/usage is following:
+
+  $ make -f tools/build/Makefile srctree=$(KSRC) dir=$(DIR) obj=$(OBJECT)
+
+where:
+
+  KSRC   - is the path to kernel sources
+  DIR    - is the path to the project to be built
+  OBJECT - is the name of the build object
+
+When succefully finished the $(DIR) directory contains the final object file
+called $(OBJECT)-in.o:
+
+  $ ls $(DIR)/$(OBJECT)-in.o
+
+which includes all compiled sources described in 'Build' makefiles.
+
+a) Build makefiles
+------------------
+
+The user supplies 'Build' makefiles that contains a objects list, and connects
+the build to nested directories.
+
+Assume we have the following project structure:
+
+  ex/a.c
+    /b.c
+    /c.c
+    /d.c
+    /arch/e.c
+    /arch/f.c
+
+Out of which you build the 'ex' binary ' and the 'libex.a' library:
+
+  'ex'      - consists of 'a.o', 'b.o' and libex.a
+  'libex.a' - consists of 'c.o', 'd.o', 'e.o' and 'f.o'
+
+The build framework does not create the 'ex' and 'libex.a' binaries for you, it
+only prepares proper objects to be compiled and grouped together.
+
+To follow the above example, the user provides following 'Build' files:
+
+  ex/Build:
+    ex-y += a.o
+    ex-y += b.o
+
+    libex-y += c.o
+    libex-y += d.o
+    libex-y += arch/
+
+  ex/arch/Build:
+    libex-y += e.o
+    libex-y += f.o
+
+and runs:
+
+  $ make -f tools/build/Makefile.build dir=. obj=ex
+  $ make -f tools/build/Makefile.build dir=. obj=libex
+
+which creates the following objects:
+
+  ex/ex-in.o
+  ex/libex-in.o
+
+that contain request objects names in Build files.
+
+It's only a matter of 2 single commands to create the final binaries:
+
+  $ ar  rcs libex.a libex-in.o
+  $ gcc -o ex ex-in.o libex.a
+
+You can check the 'ex' example in 'tools/build/tests/ex' for more details.
+
+b) Rules
+--------
+
+The build framework provides standard compilation rules to handle .S and .c
+compilation.
+
+It's possible to include special rule if needed (like we do for flex or bison
+code generation).
+
+c) CFLAGS
+---------
+
+It's possible to alter the standard object C flags in the following way:
+
+  CFLAGS_perf.o += '...' - alters CFLAGS for perf.o object
+  CFLAGS_gtk += '...'    - alters CFLAGS for gtk build object
+
+This C flags changes has the scope of the Build makefile they are defined in.
+
+
+d) Dependencies
+---------------
+
+For each built object file 'a.o' the '.a.cmd' is created and holds:
+
+  - Command line used to built that object
+    (for each object)
+
+  - Dependency rules generated by 'gcc -Wp,-MD,...'
+    (for compiled object)
+
+All existing '.cmd' files are included in the Build process to follow properly
+the dependencies and trigger a rebuild when necessary.
+
+
+e) Single rules
+---------------
+
+It's possible to build single object file by choice, like:
+
+  $ make util/map.o    # objects
+  $ make util/map.i    # preprocessor
+  $ make util/map.s    # assembly

tools/build/Makefile.build

@@ -0,0 +1,130 @@
+###
+# Main build makefile.
+#
+#  Lots of this code have been borrowed or heavily inspired from parts
+#  of kbuild code, which is not credited, but mostly developed by:
+#
+#  Copyright (C) Sam Ravnborg <sam@mars.ravnborg.org>, 2015
+#  Copyright (C) Linus Torvalds <torvalds@linux-foundation.org>, 2015
+#
+
+PHONY := __build
+__build:
+
+ifeq ($(V),1)
+  quiet =
+  Q =
+else
+  quiet=quiet_
+  Q=@
+endif
+
+build-dir := $(srctree)/tools/build
+
+# Generic definitions
+include $(build-dir)/Build.include
+
+# do not force detected configuration
+-include .config-detected
+
+# Init all relevant variables used in build files so
+# 1) they have correct type
+# 2) they do not inherit any value from the environment
+subdir-y     :=
+obj-y        :=
+subdir-y     :=
+subdir-obj-y :=
+
+# Build definitions
+build-file := $(dir)/Build
+include $(build-file)
+
+quiet_cmd_flex  = FLEX     $@
+quiet_cmd_bison = BISON    $@
+
+# Create directory unless it exists
+quiet_cmd_mkdir = MKDIR    $(dir $@)
+      cmd_mkdir = mkdir -p $(dir $@)
+     rule_mkdir = $(if $(wildcard $(dir $@)),,@$(call echo-cmd,mkdir) $(cmd_mkdir))
+
+# Compile command
+quiet_cmd_cc_o_c = CC       $@
+      cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
+
+quiet_cmd_cc_i_c = CPP      $@
+      cmd_cc_i_c = $(CC) $(c_flags) -E -o $@ $<
+
+quiet_cmd_cc_s_c = AS       $@
+      cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
+
+# Link agregate command
+# If there's nothing to link, create empty $@ object.
+quiet_cmd_ld_multi = LD       $@
+      cmd_ld_multi = $(if $(strip $(obj-y)),\
+		       $(LD) -r -o $@ $(obj-y),rm -f $@; $(AR) rcs $@)
+
+# Build rules
+$(OUTPUT)%.o: %.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)%.o: %.S FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)%.i: %.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_i_c)
+
+$(OUTPUT)%.i: %.S FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_i_c)
+
+$(OUTPUT)%.s: %.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_s_c)
+
+# Gather build data:
+#   obj-y        - list of build objects
+#   subdir-y     - list of directories to nest
+#   subdir-obj-y - list of directories objects 'dir/$(obj)-in.o'
+obj-y        := $($(obj)-y)
+subdir-y     := $(patsubst %/,%,$(filter %/, $(obj-y)))
+obj-y        := $(patsubst %/, %/$(obj)-in.o, $(obj-y))
+subdir-obj-y := $(filter %/$(obj)-in.o, $(obj-y))
+
+# '$(OUTPUT)/dir' prefix to all objects
+prefix       := $(subst ./,,$(OUTPUT)$(dir)/)
+obj-y        := $(addprefix $(prefix),$(obj-y))
+subdir-obj-y := $(addprefix $(prefix),$(subdir-obj-y))
+
+# Final '$(obj)-in.o' object
+in-target := $(prefix)$(obj)-in.o
+
+PHONY += $(subdir-y)
+
+$(subdir-y):
+	$(Q)$(MAKE) -f $(build-dir)/Makefile.build dir=$(dir)/$@ obj=$(obj)
+
+$(sort $(subdir-obj-y)): $(subdir-y) ;
+
+$(in-target): $(obj-y) FORCE
+	$(call rule_mkdir)
+	$(call if_changed,ld_multi)
+
+__build: $(in-target)
+	@:
+
+PHONY += FORCE
+FORCE:
+
+# Include all cmd files to get all the dependency rules
+# for all objects included
+targets   := $(wildcard $(sort $(obj-y) $(in-target) $(MAKECMDGOALS)))
+cmd_files := $(wildcard $(foreach f,$(targets),$(dir $(f)).$(notdir $(f)).cmd))
+
+ifneq ($(cmd_files),)
+  include $(cmd_files)
+endif
+
+.PHONY: $(PHONY)

tools/build/Makefile.feature

@@ -0,0 +1,171 @@
+feature_dir := $(srctree)/tools/build/feature
+
+ifneq ($(OUTPUT),)
+  OUTPUT_FEATURES = $(OUTPUT)feature/
+  $(shell mkdir -p $(OUTPUT_FEATURES))
+endif
+
+feature_check = $(eval $(feature_check_code))
+define feature_check_code
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+endef
+
+feature_set = $(eval $(feature_set_code))
+define feature_set_code
+  feature-$(1) := 1
+endef
+
+#
+# Build the feature check binaries in parallel, ignore errors, ignore return value and suppress output:
+#
+
+#
+# Note that this is not a complete list of all feature tests, just
+# those that are typically built on a fully configured system.
+#
+# [ Feature tests not mentioned here have to be built explicitly in
+#   the rule that uses them - an example for that is the 'bionic'
+#   feature check. ]
+#
+FEATURE_TESTS =			\
+	backtrace			\
+	dwarf				\
+	fortify-source			\
+	sync-compare-and-swap		\
+	glibc				\
+	gtk2				\
+	gtk2-infobar			\
+	libaudit			\
+	libbfd				\
+	libelf				\
+	libelf-getphdrnum		\
+	libelf-mmap			\
+	libnuma				\
+	libperl				\
+	libpython			\
+	libpython-version		\
+	libslang			\
+	libunwind			\
+	pthread-attr-setaffinity-np	\
+	stackprotector-all		\
+	timerfd				\
+	libdw-dwarf-unwind		\
+	zlib				\
+	lzma
+
+FEATURE_DISPLAY =			\
+	dwarf				\
+	glibc				\
+	gtk2				\
+	libaudit			\
+	libbfd				\
+	libelf				\
+	libnuma				\
+	libperl				\
+	libpython			\
+	libslang			\
+	libunwind			\
+	libdw-dwarf-unwind		\
+	zlib				\
+	lzma
+
+# Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
+# If in the future we need per-feature checks/flags for features not
+# mentioned in this list we need to refactor this ;-).
+set_test_all_flags = $(eval $(set_test_all_flags_code))
+define set_test_all_flags_code
+  FEATURE_CHECK_CFLAGS-all  += $(FEATURE_CHECK_CFLAGS-$(1))
+  FEATURE_CHECK_LDFLAGS-all += $(FEATURE_CHECK_LDFLAGS-$(1))
+endef
+
+$(foreach feat,$(FEATURE_TESTS),$(call set_test_all_flags,$(feat)))
+
+#
+# Special fast-path for the 'all features are available' case:
+#
+$(call feature_check,all,$(MSG))
+
+#
+# Just in case the build freshly failed, make sure we print the
+# feature matrix:
+#
+ifeq ($(feature-all), 1)
+  #
+  # test-all.c passed - just set all the core feature flags to 1:
+  #
+  $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat)))
+else
+  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C $(feature_dir) $(addsuffix .bin,$(FEATURE_TESTS)) >/dev/null 2>&1)
+  $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
+endif
+
+#
+# Print the result of the feature test:
+#
+feature_print_status = $(eval $(feature_print_status_code)) $(info $(MSG))
+
+define feature_print_status_code
+  ifeq ($(feature-$(1)), 1)
+    MSG = $(shell printf '...%30s: [ \033[32mon\033[m  ]' $(1))
+  else
+    MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1))
+  endif
+endef
+
+feature_print_text = $(eval $(feature_print_text_code)) $(info $(MSG))
+define feature_print_text_code
+    MSG = $(shell printf '...%30s: %s' $(1) $(2))
+endef
+
+FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),feature-$(feat)($(feature-$(feat))))
+FEATURE_DUMP_FILE := $(shell touch $(OUTPUT)FEATURE-DUMP; cat $(OUTPUT)FEATURE-DUMP)
+
+ifeq ($(dwarf-post-unwind),1)
+  FEATURE_DUMP += dwarf-post-unwind($(dwarf-post-unwind-text))
+endif
+
+# The $(feature_display) controls the default detection message
+# output. It's set if:
+# - detected features differes from stored features from
+#   last build (in FEATURE-DUMP file)
+# - one of the $(FEATURE_DISPLAY) is not detected
+# - VF is enabled
+
+ifneq ("$(FEATURE_DUMP)","$(FEATURE_DUMP_FILE)")
+  $(shell echo "$(FEATURE_DUMP)" > $(OUTPUT)FEATURE-DUMP)
+  feature_display := 1
+endif
+
+feature_display_check = $(eval $(feature_check_code))
+define feature_display_check_code
+  ifneq ($(feature-$(1)), 1)
+    feature_display := 1
+  endif
+endef
+
+$(foreach feat,$(FEATURE_DISPLAY),$(call feature_display_check,$(feat)))
+
+ifeq ($(VF),1)
+  feature_display := 1
+  feature_verbose := 1
+endif
+
+ifeq ($(feature_display),1)
+  $(info )
+  $(info Auto-detecting system features:)
+  $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),))
+
+  ifeq ($(dwarf-post-unwind),1)
+    $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))
+  endif
+
+  ifneq ($(feature_verbose),1)
+    $(info )
+  endif
+endif
+
+ifeq ($(feature_verbose),1)
+  TMP := $(filter-out $(FEATURE_DISPLAY),$(FEATURE_TESTS))
+  $(foreach feat,$(TMP),$(call feature_print_status,$(feat),))
+  $(info )
+endif

tools/perf/config/feature-checks/.gitignore → tools/build/feature/.gitignore

@@ -1,2 +1,3 @@
 *.d
 *.bin
+*.output

tools/perf/config/feature-checks/Makefile → tools/build/feature/Makefile

@@ -29,33 +29,36 @@ FILES=					\
 	test-stackprotector-all.bin	\
 	test-timerfd.bin		\
 	test-libdw-dwarf-unwind.bin	\
+	test-libbabeltrace.bin		\
 	test-compile-32.bin		\
 	test-compile-x32.bin		\
-	test-zlib.bin
+	test-zlib.bin			\
+	test-lzma.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
 
 all: $(FILES)
 
-BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
+__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
+  BUILD = $(__BUILD) > $(OUTPUT)$(@:.bin=.make.output) 2>&1
 
 ###############################
 
 test-all.bin:
-	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz
+	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma
 
 test-hello.bin:
 	$(BUILD)
 
 test-pthread-attr-setaffinity-np.bin:
-	$(BUILD) -D_GNU_SOURCE -Werror -lpthread
+	$(BUILD) -D_GNU_SOURCE -lpthread
 
 test-stackprotector-all.bin:
-	$(BUILD) -Werror -fstack-protector-all
+	$(BUILD) -fstack-protector-all
 
 test-fortify-source.bin:
-	$(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2
+	$(BUILD) -O2 -D_FORTIFY_SOURCE=2
 
 test-bionic.bin:
 	$(BUILD)
@@ -118,10 +121,10 @@ test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
 
 test-liberty.bin:
-	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
+	$(CC) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
 
 test-liberty-z.bin:
-	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz
+	$(CC) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz
 
 test-cplus-demangle.bin:
 	$(BUILD) -liberty
@@ -133,10 +136,13 @@ test-timerfd.bin:
 	$(BUILD)
 
 test-libdw-dwarf-unwind.bin:
-	$(BUILD)
+	$(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind)
+
+test-libbabeltrace.bin:
+	$(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace)
 
 test-sync-compare-and-swap.bin:
-	$(BUILD) -Werror
+	$(BUILD)
 
 test-compile-32.bin:
 	$(CC) -m32 -o $(OUTPUT)$@ test-compile.c
@@ -147,9 +153,12 @@ test-compile-x32.bin:
 test-zlib.bin:
 	$(BUILD) -lz
 
+test-lzma.bin:
+	$(BUILD) -llzma
+
 -include *.d
 
 ###############################
 
 clean:
-	rm -f $(FILES) *.d
+	rm -f $(FILES) *.d $(FILES:.bin=.make.output)

tools/perf/config/feature-checks/test-all.c → tools/build/feature/test-all.c

@@ -98,7 +98,23 @@
 #undef main
 
 #define main main_test_pthread_attr_setaffinity_np
-# include "test-pthread_attr_setaffinity_np.c"
+# include "test-pthread-attr-setaffinity-np.c"
+#undef main
+
+# if 0
+/*
+ * Disable libbabeltrace check for test-all, because the requested
+ * library version is not released yet in most distributions. Will
+ * reenable later.
+ */
+
+#define main main_test_libbabeltrace
+# include "test-libbabeltrace.c"
+#undef main
+#endif
+
+#define main main_test_lzma
+# include "test-lzma.c"
 #undef main
 
 int main(int argc, char *argv[])
@@ -126,6 +142,7 @@ int main(int argc, char *argv[])
 	main_test_sync_compare_and_swap(argc, argv);
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
+	main_test_lzma();
 
 	return 0;
 }

tools/build/feature/test-libbabeltrace.c

@@ -0,0 +1,9 @@
+
+#include <babeltrace/ctf-writer/writer.h>
+#include <babeltrace/ctf-ir/stream-class.h>
+
+int main(void)
+{
+	bt_ctf_stream_class_get_packet_context_type((void *) 0);
+	return 0;
+}

tools/build/feature/test-lzma.c

@@ -0,0 +1,10 @@
+#include <lzma.h>
+
+int main(void)
+{
+	lzma_stream strm = LZMA_STREAM_INIT;
+	int ret;
+
+	ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED);
+	return ret ? -1 : 0;
+}

tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c → tools/build/feature/test-pthread-attr-setaffinity-np.c

@@ -1,5 +1,6 @@
 #include <stdint.h>
 #include <pthread.h>
+#include <sched.h>
 
 int main(void)
 {
@@ -8,7 +9,8 @@ int main(void)
 	cpu_set_t cs;
 
 	pthread_attr_init(&thread_attr);
-	/* don't care abt exact args, just the API itself in libpthread */
+	CPU_ZERO(&cs);
+
 	ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cs), &cs);
 
 	return ret;

tools/build/tests/ex/Build

@@ -0,0 +1,8 @@
+ex-y += ex.o
+ex-y += a.o
+ex-y += b.o
+ex-y += empty/
+
+libex-y += c.o
+libex-y += d.o
+libex-y += arch/

tools/build/tests/ex/Makefile

@@ -0,0 +1,23 @@
+export srctree := ../../../..
+export CC      := gcc
+export LD      := ld
+export AR      := ar
+
+build := -f $(srctree)/tools/build/Makefile.build dir=. obj
+ex: ex-in.o libex-in.o
+	gcc -o $@ $^
+
+ex.%: FORCE
+	make -f $(srctree)/tools/build/Makefile.build dir=. $@
+
+ex-in.o: FORCE
+	make $(build)=ex
+
+libex-in.o: FORCE
+	make $(build)=libex
+
+clean:
+	find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	rm -f ex ex.i ex.s
+
+.PHONY: FORCE

tools/build/tests/ex/a.c

@@ -0,0 +1,5 @@
+
+int a(void)
+{
+	return 0;
+}

tools/build/tests/ex/arch/Build

@@ -0,0 +1,2 @@
+libex-y += e.o
+libex-y += f.o

tools/build/tests/ex/arch/e.c

@@ -0,0 +1,5 @@
+
+int e(void)
+{
+	return 0;
+}

tools/build/tests/ex/arch/f.c

@@ -0,0 +1,5 @@
+
+int f(void)
+{
+	return 0;
+}

tools/build/tests/ex/b.c

@@ -0,0 +1,5 @@
+
+int b(void)
+{
+	return 0;
+}

tools/build/tests/ex/c.c

@@ -0,0 +1,5 @@
+
+int c(void)
+{
+	return 0;
+}

tools/build/tests/ex/d.c

@@ -0,0 +1,5 @@
+
+int d(void)
+{
+	return 0;
+}

tools/build/tests/ex/ex.c

@@ -0,0 +1,19 @@
+
+int a(void);
+int b(void);
+int c(void);
+int d(void);
+int e(void);
+int f(void);
+
+int main(void)
+{
+	a();
+	b();
+	c();
+	d();
+	e();
+	f();
+
+	return 0;
+}

tools/build/tests/run.sh

@@ -0,0 +1,42 @@
+#!/bin/sh
+
+function test_ex {
+	make -C ex V=1 clean > ex.out 2>&1
+	make -C ex V=1 >> ex.out 2>&1
+
+	if [ ! -x ./ex/ex ]; then
+	  echo FAILED
+	  exit -1
+	fi
+
+	make -C ex V=1 clean > /dev/null 2>&1
+	rm -f ex.out
+}
+
+function test_ex_suffix {
+	make -C ex V=1 clean > ex.out 2>&1
+
+	# use -rR to disable make's builtin rules
+	make -rR -C ex V=1 ex.o >> ex.out 2>&1
+	make -rR -C ex V=1 ex.i >> ex.out 2>&1
+	make -rR -C ex V=1 ex.s >> ex.out 2>&1
+
+	if [ -x ./ex/ex ]; then
+	  echo FAILED
+	  exit -1
+	fi
+
+	if [ ! -f ./ex/ex.o -o ! -f ./ex/ex.i -o ! -f ./ex/ex.s ]; then
+	  echo FAILED
+	  exit -1
+	fi
+
+	make -C ex V=1 clean > /dev/null 2>&1
+	rm -f ex.out
+}
+echo -n Testing..
+
+test_ex
+test_ex_suffix
+
+echo OK

tools/lib/api/Build

@@ -0,0 +1,2 @@
+libapi-y += fd/
+libapi-y += fs/

tools/lib/api/Makefile

@@ -1,49 +1,43 @@
 include ../../scripts/Makefile.include
 include ../../perf/config/utilities.mak		# QUIET_CLEAN
 
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
 
-# guard against environment variables
-LIB_H=
-LIB_OBJS=
-
-LIB_H += fs/debugfs.h
-LIB_H += fs/fs.h
-# See comment below about piggybacking...
-LIB_H += fd/array.h
-
-LIB_OBJS += $(OUTPUT)fs/debugfs.o
-LIB_OBJS += $(OUTPUT)fs/fs.o
-# XXX piggybacking here, need to introduce libapikfd, or rename this
-# to plain libapik.a and make it have it all api goodies
-LIB_OBJS += $(OUTPUT)fd/array.o
+MAKEFLAGS += --no-print-directory
 
-LIBFILE = libapikfs.a
+LIBFILE = $(OUTPUT)libapi.a
 
-CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
-EXTLIBS = -lelf -lpthread -lrt -lm
-ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
-ALL_LDFLAGS = $(LDFLAGS)
+CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 
 RM = rm -f
 
-$(LIBFILE): $(LIB_OBJS)
-	$(QUIET_AR)$(RM) $@ && $(AR) rcs $(OUTPUT)$@ $(LIB_OBJS)
+build  := -f $(srctree)/tools/build/Makefile.build dir=. obj
+API_IN := $(OUTPUT)libapi-in.o
 
-$(LIB_OBJS): $(LIB_H)
+export srctree OUTPUT CC LD CFLAGS V
 
-libapi_dirs:
-	$(QUIET_MKDIR)mkdir -p $(OUTPUT)fd $(OUTPUT)fs
+all: $(LIBFILE)
 
-$(OUTPUT)%.o: %.c libapi_dirs
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
-$(OUTPUT)%.s: %.c libapi_dirs
-	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
-$(OUTPUT)%.o: %.S libapi_dirs
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(API_IN): FORCE
+	@$(MAKE) $(build)=libapi
+
+$(LIBFILE): $(API_IN)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(API_IN)
 
 clean:
-	$(call QUIET_CLEAN, libapi) $(RM) $(LIB_OBJS) $(LIBFILE)
+	$(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \
+	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o | xargs $(RM)
+
+FORCE:
 
-.PHONY: clean
+.PHONY: clean FORCE

tools/lib/api/fd/Build

@@ -0,0 +1 @@
+libapi-y += array.o

tools/lib/api/fs/Build

@@ -0,0 +1,4 @@
+libapi-y += fs.o
+libapi-y += debugfs.o
+libapi-y += findfs.o
+libapi-y += tracefs.o

tools/lib/api/fs/debugfs.c

@@ -3,75 +3,50 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <unistd.h>
 #include <stdbool.h>
 #include <sys/vfs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
 #include <sys/mount.h>
 #include <linux/kernel.h>
 
 #include "debugfs.h"
 
-char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
+#ifndef DEBUGFS_DEFAULT_PATH
+#define DEBUGFS_DEFAULT_PATH		"/sys/kernel/debug"
+#endif
+
+char debugfs_mountpoint[PATH_MAX + 1] = DEBUGFS_DEFAULT_PATH;
 
 static const char * const debugfs_known_mountpoints[] = {
-	"/sys/kernel/debug",
+	DEBUGFS_DEFAULT_PATH,
 	"/debug",
 	0,
 };
 
 static bool debugfs_found;
 
+bool debugfs_configured(void)
+{
+	return debugfs_find_mountpoint() != NULL;
+}
+
 /* find the path to the mounted debugfs */
 const char *debugfs_find_mountpoint(void)
 {
-	const char * const *ptr;
-	char type[100];
-	FILE *fp;
+	const char *ret;
 
 	if (debugfs_found)
 		return (const char *)debugfs_mountpoint;
 
-	ptr = debugfs_known_mountpoints;
-	while (*ptr) {
-		if (debugfs_valid_mountpoint(*ptr) == 0) {
-			debugfs_found = true;
-			strcpy(debugfs_mountpoint, *ptr);
-			return debugfs_mountpoint;
-		}
-		ptr++;
-	}
-
-	/* give up and parse /proc/mounts */
-	fp = fopen("/proc/mounts", "r");
-	if (fp == NULL)
-		return NULL;
-
-	while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
-		      debugfs_mountpoint, type) == 2) {
-		if (strcmp(type, "debugfs") == 0)
-			break;
-	}
-	fclose(fp);
+	ret = find_mountpoint("debugfs", (long) DEBUGFS_MAGIC,
+			      debugfs_mountpoint, PATH_MAX + 1,
+			      debugfs_known_mountpoints);
+	if (ret)
+		debugfs_found = true;
 
-	if (strcmp(type, "debugfs") != 0)
-		return NULL;
-
-	debugfs_found = true;
-
-	return debugfs_mountpoint;
-}
-
-/* verify that a mountpoint is actually a debugfs instance */
-
-int debugfs_valid_mountpoint(const char *debugfs)
-{
-	struct statfs st_fs;
-
-	if (statfs(debugfs, &st_fs) < 0)
-		return -ENOENT;
-	else if ((long)st_fs.f_type != (long)DEBUGFS_MAGIC)
-		return -ENOENT;
-
-	return 0;
+	return ret;
 }
 
 /* mount the debugfs somewhere if it's not mounted */
@@ -87,7 +62,7 @@ char *debugfs_mount(const char *mountpoint)
 		mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT);
 		/* if no environment variable, use default */
 		if (mountpoint == NULL)
-			mountpoint = "/sys/kernel/debug";
+			mountpoint = DEBUGFS_DEFAULT_PATH;
 	}
 
 	if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)

tools/lib/api/fs/debugfs.h

@@ -1,16 +1,7 @@
 #ifndef __API_DEBUGFS_H__
 #define __API_DEBUGFS_H__
 
-#define _STR(x) #x
-#define STR(x) _STR(x)
-
-/*
- * On most systems <limits.h> would have given us this, but  not on some systems
- * (e.g. GNU/Hurd).
- */
-#ifndef PATH_MAX
-#define PATH_MAX 4096
-#endif
+#include "findfs.h"
 
 #ifndef DEBUGFS_MAGIC
 #define DEBUGFS_MAGIC          0x64626720
@@ -20,8 +11,8 @@
 #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
 #endif
 
+bool debugfs_configured(void);
 const char *debugfs_find_mountpoint(void);
-int debugfs_valid_mountpoint(const char *debugfs);
 char *debugfs_mount(const char *mountpoint);
 
 extern char debugfs_mountpoint[];

tools/lib/api/fs/findfs.c

@@ -0,0 +1,63 @@
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+#include <sys/vfs.h>
+
+#include "findfs.h"
+
+/* verify that a mountpoint is actually the type we want */
+
+int valid_mountpoint(const char *mount, long magic)
+{
+	struct statfs st_fs;
+
+	if (statfs(mount, &st_fs) < 0)
+		return -ENOENT;
+	else if ((long)st_fs.f_type != magic)
+		return -ENOENT;
+
+	return 0;
+}
+
+/* find the path to a mounted file system */
+const char *find_mountpoint(const char *fstype, long magic,
+			    char *mountpoint, int len,
+			    const char * const *known_mountpoints)
+{
+	const char * const *ptr;
+	char format[128];
+	char type[100];
+	FILE *fp;
+
+	if (known_mountpoints) {
+		ptr = known_mountpoints;
+		while (*ptr) {
+			if (valid_mountpoint(*ptr, magic) == 0) {
+				strncpy(mountpoint, *ptr, len - 1);
+				mountpoint[len-1] = 0;
+				return mountpoint;
+			}
+			ptr++;
+		}
+	}
+
+	/* give up and parse /proc/mounts */
+	fp = fopen("/proc/mounts", "r");
+	if (fp == NULL)
+		return NULL;
+
+	snprintf(format, 128, "%%*s %%%ds %%99s %%*s %%*d %%*d\n", len);
+
+	while (fscanf(fp, format, mountpoint, type) == 2) {
+		if (strcmp(type, fstype) == 0)
+			break;
+	}
+	fclose(fp);
+
+	if (strcmp(type, fstype) != 0)
+		return NULL;
+
+	return mountpoint;
+}

tools/lib/api/fs/findfs.h

@@ -0,0 +1,23 @@
+#ifndef __API_FINDFS_H__
+#define __API_FINDFS_H__
+
+#include <stdbool.h>
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
+/*
+ * On most systems <limits.h> would have given us this, but  not on some systems
+ * (e.g. GNU/Hurd).
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+const char *find_mountpoint(const char *fstype, long magic,
+			    char *mountpoint, int len,
+			    const char * const *known_mountpoints);
+
+int valid_mountpoint(const char *mount, long magic);
+
+#endif /* __API_FINDFS_H__ */

tools/lib/api/fs/tracefs.c

@@ -0,0 +1,78 @@
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <sys/vfs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <linux/kernel.h>
+
+#include "tracefs.h"
+
+#ifndef TRACEFS_DEFAULT_PATH
+#define TRACEFS_DEFAULT_PATH		"/sys/kernel/tracing"
+#endif
+
+char tracefs_mountpoint[PATH_MAX + 1] = TRACEFS_DEFAULT_PATH;
+
+static const char * const tracefs_known_mountpoints[] = {
+	TRACEFS_DEFAULT_PATH,
+	"/sys/kernel/debug/tracing",
+	"/tracing",
+	"/trace",
+	0,
+};
+
+static bool tracefs_found;
+
+bool tracefs_configured(void)
+{
+	return tracefs_find_mountpoint() != NULL;
+}
+
+/* find the path to the mounted tracefs */
+const char *tracefs_find_mountpoint(void)
+{
+	const char *ret;
+
+	if (tracefs_found)
+		return (const char *)tracefs_mountpoint;
+
+	ret = find_mountpoint("tracefs", (long) TRACEFS_MAGIC,
+			      tracefs_mountpoint, PATH_MAX + 1,
+			      tracefs_known_mountpoints);
+
+	if (ret)
+		tracefs_found = true;
+
+	return ret;
+}
+
+/* mount the tracefs somewhere if it's not mounted */
+char *tracefs_mount(const char *mountpoint)
+{
+	/* see if it's already mounted */
+	if (tracefs_find_mountpoint())
+		goto out;
+
+	/* if not mounted and no argument */
+	if (mountpoint == NULL) {
+		/* see if environment variable set */
+		mountpoint = getenv(PERF_TRACEFS_ENVIRONMENT);
+		/* if no environment variable, use default */
+		if (mountpoint == NULL)
+			mountpoint = TRACEFS_DEFAULT_PATH;
+	}
+
+	if (mount(NULL, mountpoint, "tracefs", 0, NULL) < 0)
+		return NULL;
+
+	/* save the mountpoint */
+	tracefs_found = true;
+	strncpy(tracefs_mountpoint, mountpoint, sizeof(tracefs_mountpoint));
+out:
+	return tracefs_mountpoint;
+}

tools/lib/api/fs/tracefs.h

@@ -0,0 +1,21 @@
+#ifndef __API_TRACEFS_H__
+#define __API_TRACEFS_H__
+
+#include "findfs.h"
+
+#ifndef TRACEFS_MAGIC
+#define TRACEFS_MAGIC          0x74726163
+#endif
+
+#ifndef PERF_TRACEFS_ENVIRONMENT
+#define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
+#endif
+
+bool tracefs_configured(void);
+const char *tracefs_find_mountpoint(void);
+int tracefs_valid_mountpoint(const char *debugfs);
+char *tracefs_mount(const char *mountpoint);
+
+extern char tracefs_mountpoint[];
+
+#endif /* __API_DEBUGFS_H__ */

tools/lib/lockdep/Build

@@ -0,0 +1 @@
+liblockdep-y += common.o lockdep.o preload.o rbtree.o

tools/lib/lockdep/Makefile

@@ -35,6 +35,10 @@ bindir = $(prefix)/$(bindir_relative)
 
 export DESTDIR DESTDIR_SQ INSTALL
 
+MAKEFLAGS += --no-print-directory
+
+include ../../scripts/Makefile.include
+
 # copy a bit from Linux kbuild
 
 ifeq ("$(origin V)", "command line")
@@ -44,56 +48,21 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-ifeq ("$(origin O)", "command line")
-  BUILD_OUTPUT := $(O)
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
 endif
 
-ifeq ($(BUILD_SRC),)
-ifneq ($(BUILD_OUTPUT),)
-
-define build_output
-	$(if $(VERBOSE:1=),@)$(MAKE) -C $(BUILD_OUTPUT)	\
-	BUILD_SRC=$(CURDIR) -f $(CURDIR)/Makefile $1
-endef
-
-saved-output := $(BUILD_OUTPUT)
-BUILD_OUTPUT := $(shell cd $(BUILD_OUTPUT) && /bin/pwd)
-$(if $(BUILD_OUTPUT),, \
-     $(error output directory "$(saved-output)" does not exist))
-
-all: sub-make
-
-gui: force
-	$(call build_output, all_cmd)
-
-$(filter-out gui,$(MAKECMDGOALS)): sub-make
-
-sub-make: force
-	$(call build_output, $(MAKECMDGOALS))
-
-
-# Leave processing to above invocation of make
-skip-makefile := 1
-
-endif # BUILD_OUTPUT
-endif # BUILD_SRC
-
-# We process the rest of the Makefile if this is the final invocation of make
-ifeq ($(skip-makefile),)
-
-srctree		:= $(realpath $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)))
-objtree		:= $(realpath $(CURDIR))
-src		:= $(srctree)
-obj		:= $(objtree)
-
-export prefix libdir bindir src obj
-
 # Shell quotes
 libdir_SQ = $(subst ','\'',$(libdir))
 bindir_SQ = $(subst ','\'',$(bindir))
 
-LIB_FILE = liblockdep.a liblockdep.so.$(LIBLOCKDEP_VERSION)
+LIB_IN := $(OUTPUT)liblockdep-in.o
+
 BIN_FILE = lockdep
+LIB_FILE = $(OUTPUT)liblockdep.a $(OUTPUT)liblockdep.so.$(LIBLOCKDEP_VERSION)
 
 CONFIG_INCLUDES =
 CONFIG_LIBS	=
@@ -108,33 +77,23 @@ INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
+CFLAGS += -fPIC
 
 override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
 
 ifeq ($(VERBOSE),1)
   Q =
-  print_compile =
-  print_app_build =
-  print_fpic_compile =
   print_shared_lib_compile =
   print_install =
 else
   Q = @
-  print_compile =		echo '  CC                 '$(OBJ);
-  print_app_build =		echo '  BUILD              '$(OBJ);
-  print_fpic_compile =		echo '  CC FPIC            '$(OBJ);
-  print_shared_lib_compile =	echo '  BUILD SHARED LIB   '$(OBJ);
-  print_static_lib_build =	echo '  BUILD STATIC LIB   '$(OBJ);
-  print_install =		echo '  INSTALL     '$1'	to	$(DESTDIR_SQ)$2';
+  print_shared_lib_compile =	echo '  LD       '$(OBJ);
+  print_static_lib_build =	echo '  LD       '$(OBJ);
+  print_install =		echo '  INSTALL  '$1'	to	$(DESTDIR_SQ)$2';
 endif
 
-do_fpic_compile =					\
-	($(print_fpic_compile)				\
-	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
-
-do_app_build =						\
-	($(print_app_build)				\
-	$(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS))
+export srctree OUTPUT CC LD CFLAGS V
+build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 do_compile_shared_library =			\
 	($(print_shared_lib_compile)		\
@@ -144,22 +103,6 @@ do_build_static_lib =				\
 	($(print_static_lib_build)		\
 	$(RM) $@;  $(AR) rcs $@ $^)
 
-
-define do_compile
-	$(print_compile)						\
-	$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
-endef
-
-$(obj)/%.o: $(src)/%.c
-	$(Q)$(call do_compile)
-
-%.o: $(src)/%.c
-	$(Q)$(call do_compile)
-
-PEVENT_LIB_OBJS = common.o lockdep.o preload.o rbtree.o
-
-ALL_OBJS = $(PEVENT_LIB_OBJS)
-
 CMD_TARGETS = $(LIB_FILE)
 
 TARGETS = $(CMD_TARGETS)
@@ -169,42 +112,15 @@ all: all_cmd
 
 all_cmd: $(CMD_TARGETS)
 
-liblockdep.so.$(LIBLOCKDEP_VERSION): $(PEVENT_LIB_OBJS)
+$(LIB_IN): force
+	$(Q)$(MAKE) $(build)=liblockdep
+
+liblockdep.so.$(LIBLOCKDEP_VERSION): $(LIB_IN)
 	$(Q)$(do_compile_shared_library)
 
-liblockdep.a: $(PEVENT_LIB_OBJS)
+liblockdep.a: $(LIB_IN)
 	$(Q)$(do_build_static_lib)
 
-$(PEVENT_LIB_OBJS): %.o: $(src)/%.c
-	$(Q)$(do_fpic_compile)
-
-## make deps
-
-all_objs := $(sort $(ALL_OBJS))
-all_deps := $(all_objs:%.o=.%.d)
-
-# let .d file also depends on the source and header files
-define check_deps
-		@set -e; $(RM) $@; \
-		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
-		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
-		$(RM) $@.$$$$
-endef
-
-$(all_deps): .%.d: $(src)/%.c
-	$(Q)$(call check_deps)
-
-$(all_objs) : %.o : .%.d
-
-dep_includes := $(wildcard $(all_deps))
-
-ifneq ($(dep_includes),)
- include $(dep_includes)
-endif
-
-### Detect environment changes
-TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
-
 tags:	force
 	$(RM) tags
 	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
@@ -233,8 +149,6 @@ clean:
 	$(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d
 	$(RM) tags TAGS
 
-endif # skip-makefile
-
 PHONY += force
 force:
 

tools/lib/traceevent/Build

@@ -0,0 +1,17 @@
+libtraceevent-y += event-parse.o
+libtraceevent-y += event-plugin.o
+libtraceevent-y += trace-seq.o
+libtraceevent-y += parse-filter.o
+libtraceevent-y += parse-utils.o
+libtraceevent-y += kbuffer-parse.o
+
+plugin_jbd2-y         += plugin_jbd2.o
+plugin_hrtimer-y      += plugin_hrtimer.o
+plugin_kmem-y         += plugin_kmem.o
+plugin_kvm-y          += plugin_kvm.o
+plugin_mac80211-y     += plugin_mac80211.o
+plugin_sched_switch-y += plugin_sched_switch.o
+plugin_function-y     += plugin_function.o
+plugin_xen-y          += plugin_xen.o
+plugin_scsi-y         += plugin_scsi.o
+plugin_cfg80211-y     += plugin_cfg80211.o

tools/lib/traceevent/Makefile

@@ -67,7 +67,7 @@ PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)"
 PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
 endif
 
-include $(if $(BUILD_SRC),$(BUILD_SRC)/)../../scripts/Makefile.include
+include ../../scripts/Makefile.include
 
 # copy a bit from Linux kbuild
 
@@ -78,40 +78,13 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-ifeq ("$(origin O)", "command line")
-  BUILD_OUTPUT := $(O)
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
 endif
 
-ifeq ($(BUILD_SRC),)
-ifneq ($(OUTPUT),)
-
-define build_output
-  $(if $(VERBOSE:1=),@)+$(MAKE) -C $(OUTPUT) \
-  BUILD_SRC=$(CURDIR)/ -f $(CURDIR)/Makefile $1
-endef
-
-all: sub-make
-
-$(MAKECMDGOALS): sub-make
-
-sub-make: force
-	$(call build_output, $(MAKECMDGOALS))
-
-
-# Leave processing to above invocation of make
-skip-makefile := 1
-
-endif # OUTPUT
-endif # BUILD_SRC
-
-# We process the rest of the Makefile if this is the final invocation of make
-ifeq ($(skip-makefile),)
-
-srctree		:= $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
-objtree		:= $(CURDIR)
-src		:= $(srctree)
-obj		:= $(objtree)
-
 export prefix bindir src obj
 
 # Shell quotes
@@ -132,16 +105,19 @@ EXTRAVERSION	= $(EP_EXTRAVERSION)
 OBJ		= $@
 N		=
 
-export Q VERBOSE
-
 EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
 
-INCLUDES = -I. -I $(srctree)/../../include $(CONFIG_INCLUDES)
+INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
 
-# Set compile option CFLAGS if not set elsewhere
-CFLAGS ?= -g -Wall
+# Set compile option CFLAGS
+ifdef EXTRA_CFLAGS
+  CFLAGS := $(EXTRA_CFLAGS)
+else
+  CFLAGS := -g -Wall
+endif
 
 # Append required CFLAGS
+override CFLAGS += -fPIC
 override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
 override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 
@@ -151,74 +127,58 @@ else
   Q = @
 endif
 
-do_compile_shared_library =			\
-	($(print_shared_lib_compile)		\
-	$(CC) --shared $^ -o $@)
-
-do_plugin_build =				\
-	($(print_plugin_build)			\
-	$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<)
-
-do_build_static_lib =				\
-	($(print_static_lib_build)		\
-	$(RM) $@;  $(AR) rcs $@ $^)
-
-
-do_compile = $(QUIET_CC)$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
+# Disable command line variables (CFLAGS) overide from top
+# level Makefile (perf), otherwise build Makefile will get
+# the same command line setup.
+MAKEOVERRIDES=
 
-$(obj)/%.o: $(src)/%.c
-	$(call do_compile)
+export srctree OUTPUT CC LD CFLAGS V
+build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
-%.o: $(src)/%.c
-	$(call do_compile)
+PLUGINS  = plugin_jbd2.so
+PLUGINS += plugin_hrtimer.so
+PLUGINS += plugin_kmem.so
+PLUGINS += plugin_kvm.so
+PLUGINS += plugin_mac80211.so
+PLUGINS += plugin_sched_switch.so
+PLUGINS += plugin_function.so
+PLUGINS += plugin_xen.so
+PLUGINS += plugin_scsi.so
+PLUGINS += plugin_cfg80211.so
 
-PEVENT_LIB_OBJS  = event-parse.o
-PEVENT_LIB_OBJS += event-plugin.o
-PEVENT_LIB_OBJS += trace-seq.o
-PEVENT_LIB_OBJS += parse-filter.o
-PEVENT_LIB_OBJS += parse-utils.o
-PEVENT_LIB_OBJS += kbuffer-parse.o
+PLUGINS    := $(addprefix $(OUTPUT),$(PLUGINS))
+PLUGINS_IN := $(PLUGINS:.so=-in.o)
 
-PLUGIN_OBJS  = plugin_jbd2.o
-PLUGIN_OBJS += plugin_hrtimer.o
-PLUGIN_OBJS += plugin_kmem.o
-PLUGIN_OBJS += plugin_kvm.o
-PLUGIN_OBJS += plugin_mac80211.o
-PLUGIN_OBJS += plugin_sched_switch.o
-PLUGIN_OBJS += plugin_function.o
-PLUGIN_OBJS += plugin_xen.o
-PLUGIN_OBJS += plugin_scsi.o
-PLUGIN_OBJS += plugin_cfg80211.o
-
-PLUGINS := $(PLUGIN_OBJS:.o=.so)
-
-ALL_OBJS = $(PEVENT_LIB_OBJS) $(PLUGIN_OBJS)
+TE_IN    := $(OUTPUT)libtraceevent-in.o
+LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
 
 CMD_TARGETS = $(LIB_FILE) $(PLUGINS)
 
 TARGETS = $(CMD_TARGETS)
 
-
 all: all_cmd
 
 all_cmd: $(CMD_TARGETS)
 
-libtraceevent.so: $(PEVENT_LIB_OBJS)
+$(TE_IN): force
+	$(Q)$(MAKE) $(build)=libtraceevent
+
+$(OUTPUT)libtraceevent.so: $(TE_IN)
 	$(QUIET_LINK)$(CC) --shared $^ -o $@
 
-libtraceevent.a: $(PEVENT_LIB_OBJS)
+$(OUTPUT)libtraceevent.a: $(TE_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
 plugins: $(PLUGINS)
 
-$(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
-	$(QUIET_CC_FPIC)$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@
+__plugin_obj = $(notdir $@)
+  plugin_obj = $(__plugin_obj:-in.o=)
 
-$(PLUGIN_OBJS): %.o : $(src)/%.c
-	$(QUIET_CC_FPIC)$(CC) -c $(CFLAGS) -fPIC -o $@ $<
+$(PLUGINS_IN): force
+	$(Q)$(MAKE) $(build)=$(plugin_obj)
 
-$(PLUGINS): %.so: %.o
-	$(QUIET_LINK)$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<
+$(OUTPUT)%.so: $(OUTPUT)%-in.o
+	$(QUIET_LINK)$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $^
 
 define make_version.h
   (echo '/* This file is automatically generated. Do not modify. */';		\
@@ -255,40 +215,6 @@ define update_dir
    fi);
 endef
 
-## make deps
-
-all_objs := $(sort $(ALL_OBJS))
-all_deps := $(all_objs:%.o=.%.d)
-
-# let .d file also depends on the source and header files
-define check_deps
-  @set -e; $(RM) $@; \
-  $(CC) -MM $(CFLAGS) $< > $@.$$$$; \
-  sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
-  $(RM) $@.$$$$
-endef
-
-$(all_deps): .%.d: $(src)/%.c
-	$(Q)$(call check_deps)
-
-$(all_objs) : %.o : .%.d
-
-dep_includes := $(wildcard $(all_deps))
-
-ifneq ($(dep_includes),)
- include $(dep_includes)
-endif
-
-### Detect environment changes
-TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
-
-TRACEEVENT-CFLAGS: force
-	@FLAGS='$(TRACK_CFLAGS)'; \
-	    if test x"$$FLAGS" != x"`cat TRACEEVENT-CFLAGS 2>/dev/null`" ; then \
-		echo 1>&2 "  FLAGS:   * new build flags or cross compiler"; \
-		echo "$$FLAGS" >TRACEEVENT-CFLAGS; \
-            fi
-
 tags:	force
 	$(RM) tags
 	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
@@ -327,14 +253,9 @@ clean:
 		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
 		$(RM) TRACEEVENT-CFLAGS tags TAGS
 
-endif # skip-makefile
-
 PHONY += force plugins
 force:
 
-plugins:
-	@echo > /dev/null
-
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)

tools/lib/traceevent/event-parse.c

@@ -304,7 +304,10 @@ int pevent_register_comm(struct pevent *pevent, const char *comm, int pid)
 	if (!item)
 		return -1;
 
-	item->comm = strdup(comm);
+	if (comm)
+		item->comm = strdup(comm);
+	else
+		item->comm = strdup("<...>");
 	if (!item->comm) {
 		free(item);
 		return -1;
@@ -318,9 +321,14 @@ int pevent_register_comm(struct pevent *pevent, const char *comm, int pid)
 	return 0;
 }
 
-void pevent_register_trace_clock(struct pevent *pevent, char *trace_clock)
+int pevent_register_trace_clock(struct pevent *pevent, const char *trace_clock)
 {
-	pevent->trace_clock = trace_clock;
+	pevent->trace_clock = strdup(trace_clock);
+	if (!pevent->trace_clock) {
+		errno = ENOMEM;
+		return -1;
+	}
+	return 0;
 }
 
 struct func_map {
@@ -758,6 +766,11 @@ static void free_arg(struct print_arg *arg)
 		free_arg(arg->hex.field);
 		free_arg(arg->hex.size);
 		break;
+	case PRINT_INT_ARRAY:
+		free_arg(arg->int_array.field);
+		free_arg(arg->int_array.count);
+		free_arg(arg->int_array.el_size);
+		break;
 	case PRINT_TYPE:
 		free(arg->typecast.type);
 		free_arg(arg->typecast.item);
@@ -2014,6 +2027,38 @@ process_entry(struct event_format *event __maybe_unused, struct print_arg *arg,
 	return EVENT_ERROR;
 }
 
+static int alloc_and_process_delim(struct event_format *event, char *next_token,
+				   struct print_arg **print_arg)
+{
+	struct print_arg *field;
+	enum event_type type;
+	char *token;
+	int ret = 0;
+
+	field = alloc_arg();
+	if (!field) {
+		do_warning_event(event, "%s: not enough memory!", __func__);
+		errno = ENOMEM;
+		return -1;
+	}
+
+	type = process_arg(event, field, &token);
+
+	if (test_type_token(type, token, EVENT_DELIM, next_token)) {
+		errno = EINVAL;
+		ret = -1;
+		free_arg(field);
+		goto out_free_token;
+	}
+
+	*print_arg = field;
+
+out_free_token:
+	free_token(token);
+
+	return ret;
+}
+
 static char *arg_eval (struct print_arg *arg);
 
 static unsigned long long
@@ -2486,49 +2531,46 @@ out_free:
 static enum event_type
 process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 {
-	struct print_arg *field;
-	enum event_type type;
-	char *token = NULL;
-
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_HEX;
 
-	field = alloc_arg();
-	if (!field) {
-		do_warning_event(event, "%s: not enough memory!", __func__);
-		goto out_free;
-	}
-
-	type = process_arg(event, field, &token);
+	if (alloc_and_process_delim(event, ",", &arg->hex.field))
+		goto out;
 
-	if (test_type_token(type, token, EVENT_DELIM, ","))
-		goto out_free;
+	if (alloc_and_process_delim(event, ")", &arg->hex.size))
+		goto free_field;
 
-	arg->hex.field = field;
+	return read_token_item(tok);
 
-	free_token(token);
+free_field:
+	free_arg(arg->hex.field);
+out:
+	*tok = NULL;
+	return EVENT_ERROR;
+}
 
-	field = alloc_arg();
-	if (!field) {
-		do_warning_event(event, "%s: not enough memory!", __func__);
-		*tok = NULL;
-		return EVENT_ERROR;
-	}
+static enum event_type
+process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
+{
+	memset(arg, 0, sizeof(*arg));
+	arg->type = PRINT_INT_ARRAY;
 
-	type = process_arg(event, field, &token);
+	if (alloc_and_process_delim(event, ",", &arg->int_array.field))
+		goto out;
 
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
-		goto out_free;
+	if (alloc_and_process_delim(event, ",", &arg->int_array.count))
+		goto free_field;
 
-	arg->hex.size = field;
+	if (alloc_and_process_delim(event, ")", &arg->int_array.el_size))
+		goto free_size;
 
-	free_token(token);
-	type = read_token_item(tok);
-	return type;
+	return read_token_item(tok);
 
- out_free:
-	free_arg(field);
-	free_token(token);
+free_size:
+	free_arg(arg->int_array.count);
+free_field:
+	free_arg(arg->int_array.field);
+out:
 	*tok = NULL;
 	return EVENT_ERROR;
 }
@@ -2828,6 +2870,10 @@ process_function(struct event_format *event, struct print_arg *arg,
 		free_token(token);
 		return process_hex(event, arg, tok);
 	}
+	if (strcmp(token, "__print_array") == 0) {
+		free_token(token);
+		return process_int_array(event, arg, tok);
+	}
 	if (strcmp(token, "__get_str") == 0) {
 		free_token(token);
 		return process_str(event, arg, tok);
@@ -3356,6 +3402,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		break;
 	case PRINT_FLAGS:
 	case PRINT_SYMBOL:
+	case PRINT_INT_ARRAY:
 	case PRINT_HEX:
 		break;
 	case PRINT_TYPE:
@@ -3568,7 +3615,7 @@ static const struct flag flags[] = {
 	{ "HRTIMER_RESTART", 1 },
 };
 
-static unsigned long long eval_flag(const char *flag)
+static long long eval_flag(const char *flag)
 {
 	int i;
 
@@ -3584,7 +3631,7 @@ static unsigned long long eval_flag(const char *flag)
 		if (strcmp(flags[i].name, flag) == 0)
 			return flags[i].value;
 
-	return 0;
+	return -1LL;
 }
 
 static void print_str_to_seq(struct trace_seq *s, const char *format,
@@ -3658,7 +3705,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	struct print_flag_sym *flag;
 	struct format_field *field;
 	struct printk_map *printk;
-	unsigned long long val, fval;
+	long long val, fval;
 	unsigned long addr;
 	char *str;
 	unsigned char *hex;
@@ -3717,11 +3764,11 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		print = 0;
 		for (flag = arg->flags.flags; flag; flag = flag->next) {
 			fval = eval_flag(flag->value);
-			if (!val && !fval) {
+			if (!val && fval < 0) {
 				print_str_to_seq(s, format, len_arg, flag->str);
 				break;
 			}
-			if (fval && (val & fval) == fval) {
+			if (fval > 0 && (val & fval) == fval) {
 				if (print && arg->flags.delim)
 					trace_seq_puts(s, arg->flags.delim);
 				print_str_to_seq(s, format, len_arg, flag->str);
@@ -3766,6 +3813,54 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		}
 		break;
 
+	case PRINT_INT_ARRAY: {
+		void *num;
+		int el_size;
+
+		if (arg->int_array.field->type == PRINT_DYNAMIC_ARRAY) {
+			unsigned long offset;
+			struct format_field *field =
+				arg->int_array.field->dynarray.field;
+			offset = pevent_read_number(pevent,
+						    data + field->offset,
+						    field->size);
+			num = data + (offset & 0xffff);
+		} else {
+			field = arg->int_array.field->field.field;
+			if (!field) {
+				str = arg->int_array.field->field.name;
+				field = pevent_find_any_field(event, str);
+				if (!field)
+					goto out_warning_field;
+				arg->int_array.field->field.field = field;
+			}
+			num = data + field->offset;
+		}
+		len = eval_num_arg(data, size, event, arg->int_array.count);
+		el_size = eval_num_arg(data, size, event,
+				       arg->int_array.el_size);
+		for (i = 0; i < len; i++) {
+			if (i)
+				trace_seq_putc(s, ' ');
+
+			if (el_size == 1) {
+				trace_seq_printf(s, "%u", *(uint8_t *)num);
+			} else if (el_size == 2) {
+				trace_seq_printf(s, "%u", *(uint16_t *)num);
+			} else if (el_size == 4) {
+				trace_seq_printf(s, "%u", *(uint32_t *)num);
+			} else if (el_size == 8) {
+				trace_seq_printf(s, "%lu", *(uint64_t *)num);
+			} else {
+				trace_seq_printf(s, "BAD SIZE:%d 0x%x",
+						 el_size, *(uint8_t *)num);
+				el_size = 1;
+			}
+
+			num += el_size;
+		}
+		break;
+	}
 	case PRINT_TYPE:
 		break;
 	case PRINT_STRING: {
@@ -3997,6 +4092,10 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc
 				goto process_again;
 			case '.':
 				goto process_again;
+			case 'z':
+			case 'Z':
+				ls = 1;
+				goto process_again;
 			case 'p':
 				ls = 1;
 				/* fall through */
@@ -4939,6 +5038,96 @@ const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid)
 	return comm;
 }
 
+static struct cmdline *
+pid_from_cmdlist(struct pevent *pevent, const char *comm, struct cmdline *next)
+{
+	struct cmdline_list *cmdlist = (struct cmdline_list *)next;
+
+	if (cmdlist)
+		cmdlist = cmdlist->next;
+	else
+		cmdlist = pevent->cmdlist;
+
+	while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
+		cmdlist = cmdlist->next;
+
+	return (struct cmdline *)cmdlist;
+}
+
+/**
+ * pevent_data_pid_from_comm - return the pid from a given comm
+ * @pevent: a handle to the pevent
+ * @comm: the cmdline to find the pid from
+ * @next: the cmdline structure to find the next comm
+ *
+ * This returns the cmdline structure that holds a pid for a given
+ * comm, or NULL if none found. As there may be more than one pid for
+ * a given comm, the result of this call can be passed back into
+ * a recurring call in the @next paramater, and then it will find the
+ * next pid.
+ * Also, it does a linear seach, so it may be slow.
+ */
+struct cmdline *pevent_data_pid_from_comm(struct pevent *pevent, const char *comm,
+					  struct cmdline *next)
+{
+	struct cmdline *cmdline;
+
+	/*
+	 * If the cmdlines have not been converted yet, then use
+	 * the list.
+	 */
+	if (!pevent->cmdlines)
+		return pid_from_cmdlist(pevent, comm, next);
+
+	if (next) {
+		/*
+		 * The next pointer could have been still from
+		 * a previous call before cmdlines were created
+		 */
+		if (next < pevent->cmdlines ||
+		    next >= pevent->cmdlines + pevent->cmdline_count)
+			next = NULL;
+		else
+			cmdline  = next++;
+	}
+
+	if (!next)
+		cmdline = pevent->cmdlines;
+
+	while (cmdline < pevent->cmdlines + pevent->cmdline_count) {
+		if (strcmp(cmdline->comm, comm) == 0)
+			return cmdline;
+		cmdline++;
+	}
+	return NULL;
+}
+
+/**
+ * pevent_cmdline_pid - return the pid associated to a given cmdline
+ * @cmdline: The cmdline structure to get the pid from
+ *
+ * Returns the pid for a give cmdline. If @cmdline is NULL, then
+ * -1 is returned.
+ */
+int pevent_cmdline_pid(struct pevent *pevent, struct cmdline *cmdline)
+{
+	struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
+
+	if (!cmdline)
+		return -1;
+
+	/*
+	 * If cmdlines have not been created yet, or cmdline is
+	 * not part of the array, then treat it as a cmdlist instead.
+	 */
+	if (!pevent->cmdlines ||
+	    cmdline < pevent->cmdlines ||
+	    cmdline >= pevent->cmdlines + pevent->cmdline_count)
+		return cmdlist->pid;
+
+	return cmdline->pid;
+}
+
 /**
  * pevent_data_comm_from_pid - parse the data into the print format
  * @s: the trace_seq to write to
@@ -5256,6 +5445,15 @@ static void print_args(struct print_arg *args)
 		print_args(args->hex.size);
 		printf(")");
 		break;
+	case PRINT_INT_ARRAY:
+		printf("__print_array(");
+		print_args(args->int_array.field);
+		printf(", ");
+		print_args(args->int_array.count);
+		printf(", ");
+		print_args(args->int_array.el_size);
+		printf(")");
+		break;
 	case PRINT_STRING:
 	case PRINT_BSTRING:
 		printf("__get_str(%s)", args->string.string);
@@ -6228,15 +6426,20 @@ void pevent_ref(struct pevent *pevent)
 	pevent->ref_count++;
 }
 
+void pevent_free_format_field(struct format_field *field)
+{
+	free(field->type);
+	free(field->name);
+	free(field);
+}
+
 static void free_format_fields(struct format_field *field)
 {
 	struct format_field *next;
 
 	while (field) {
 		next = field->next;
-		free(field->type);
-		free(field->name);
-		free(field);
+		pevent_free_format_field(field);
 		field = next;
 	}
 }
@@ -6341,6 +6544,7 @@ void pevent_free(struct pevent *pevent)
 		free_handler(handle);
 	}
 
+	free(pevent->trace_clock);
 	free(pevent->events);
 	free(pevent->sort_events);
 

tools/lib/traceevent/event-parse.h

@@ -22,6 +22,7 @@
 
 #include <stdbool.h>
 #include <stdarg.h>
+#include <stdio.h>
 #include <regex.h>
 #include <string.h>
 
@@ -91,6 +92,7 @@ extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
 
 extern void trace_seq_terminate(struct trace_seq *s);
 
+extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
 extern int trace_seq_do_printf(struct trace_seq *s);
 
 
@@ -114,7 +116,7 @@ struct pevent_plugin_option {
 	char				*name;
 	char				*plugin_alias;
 	char				*description;
-	char				*value;
+	const char			*value;
 	void				*priv;
 	int				set;
 };
@@ -152,6 +154,10 @@ struct pevent_plugin_option {
  *   .plugin_alias is used to give a shorter name to access
  *   the vairable. Useful if a plugin handles more than one event.
  *
+ *   If .value is not set, then it is considered a boolean and only
+ *   .set will be processed. If .value is defined, then it is considered
+ *   a string option and .set will be ignored.
+ *
  * PEVENT_PLUGIN_ALIAS: (optional)
  *   The name to use for finding options (uses filename if not defined)
  */
@@ -245,6 +251,12 @@ struct print_arg_hex {
 	struct print_arg	*size;
 };
 
+struct print_arg_int_array {
+	struct print_arg	*field;
+	struct print_arg	*count;
+	struct print_arg	*el_size;
+};
+
 struct print_arg_dynarray {
 	struct format_field	*field;
 	struct print_arg	*index;
@@ -273,6 +285,7 @@ enum print_arg_type {
 	PRINT_FLAGS,
 	PRINT_SYMBOL,
 	PRINT_HEX,
+	PRINT_INT_ARRAY,
 	PRINT_TYPE,
 	PRINT_STRING,
 	PRINT_BSTRING,
@@ -292,6 +305,7 @@ struct print_arg {
 		struct print_arg_flags		flags;
 		struct print_arg_symbol		symbol;
 		struct print_arg_hex		hex;
+		struct print_arg_int_array	int_array;
 		struct print_arg_func		func;
 		struct print_arg_string		string;
 		struct print_arg_bitmask	bitmask;
@@ -597,7 +611,7 @@ enum trace_flag_type {
 };
 
 int pevent_register_comm(struct pevent *pevent, const char *comm, int pid);
-void pevent_register_trace_clock(struct pevent *pevent, char *trace_clock);
+int pevent_register_trace_clock(struct pevent *pevent, const char *trace_clock);
 int pevent_register_function(struct pevent *pevent, char *name,
 			     unsigned long long addr, char *mod);
 int pevent_register_print_string(struct pevent *pevent, const char *fmt,
@@ -617,6 +631,7 @@ enum pevent_errno pevent_parse_format(struct pevent *pevent,
 				      const char *buf,
 				      unsigned long size, const char *sys);
 void pevent_free_format(struct event_format *event);
+void pevent_free_format_field(struct format_field *field);
 
 void *pevent_get_field_raw(struct trace_seq *s, struct event_format *event,
 			   const char *name, struct pevent_record *record,
@@ -675,6 +690,11 @@ int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
 struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type);
 int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec);
 const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid);
+struct cmdline;
+struct cmdline *pevent_data_pid_from_comm(struct pevent *pevent, const char *comm,
+					  struct cmdline *next);
+int pevent_cmdline_pid(struct pevent *pevent, struct cmdline *cmdline);
+
 void pevent_event_info(struct trace_seq *s, struct event_format *event,
 		       struct pevent_record *record);
 int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,

tools/lib/traceevent/event-plugin.c

@@ -18,6 +18,7 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#include <ctype.h>
 #include <stdio.h>
 #include <string.h>
 #include <dlfcn.h>
@@ -49,6 +50,52 @@ struct plugin_list {
 	void			*handle;
 };
 
+static void lower_case(char *str)
+{
+	if (!str)
+		return;
+	for (; *str; str++)
+		*str = tolower(*str);
+}
+
+static int update_option_value(struct pevent_plugin_option *op, const char *val)
+{
+	char *op_val;
+
+	if (!val) {
+		/* toggle, only if option is boolean */
+		if (op->value)
+			/* Warn? */
+			return 0;
+		op->set ^= 1;
+		return 0;
+	}
+
+	/*
+	 * If the option has a value then it takes a string
+	 * otherwise the option is a boolean.
+	 */
+	if (op->value) {
+		op->value = val;
+		return 0;
+	}
+
+	/* Option is boolean, must be either "1", "0", "true" or "false" */
+
+	op_val = strdup(val);
+	if (!op_val)
+		return -1;
+	lower_case(op_val);
+
+	if (strcmp(val, "1") == 0 || strcmp(val, "true") == 0)
+		op->set = 1;
+	else if (strcmp(val, "0") == 0 || strcmp(val, "false") == 0)
+		op->set = 0;
+	free(op_val);
+
+	return 0;
+}
+
 /**
  * traceevent_plugin_list_options - get list of plugin options
  *
@@ -120,6 +167,7 @@ update_option(const char *file, struct pevent_plugin_option *option)
 {
 	struct trace_plugin_options *op;
 	char *plugin;
+	int ret = 0;
 
 	if (option->plugin_alias) {
 		plugin = strdup(option->plugin_alias);
@@ -144,9 +192,10 @@ update_option(const char *file, struct pevent_plugin_option *option)
 		if (strcmp(op->option, option->name) != 0)
 			continue;
 
-		option->value = op->value;
-		option->set ^= 1;
-		goto out;
+		ret = update_option_value(option, op->value);
+		if (ret)
+			goto out;
+		break;
 	}
 
 	/* first look for unnamed options */
@@ -156,14 +205,13 @@ update_option(const char *file, struct pevent_plugin_option *option)
 		if (strcmp(op->option, option->name) != 0)
 			continue;
 
-		option->value = op->value;
-		option->set ^= 1;
+		ret = update_option_value(option, op->value);
 		break;
 	}
 
  out:
 	free(plugin);
-	return 0;
+	return ret;
 }
 
 /**

tools/lib/traceevent/kbuffer-parse.c

@@ -372,7 +372,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr,
 	switch (type_len) {
 	case KBUFFER_TYPE_PADDING:
 		*length = read_4(kbuf, data);
-		data += *length;
 		break;
 
 	case KBUFFER_TYPE_TIME_EXTEND:
@@ -730,3 +729,14 @@ void kbuffer_set_old_format(struct kbuffer *kbuf)
 
 	kbuf->next_event = __old_next_event;
 }
+
+/**
+ * kbuffer_start_of_data - return offset of where data starts on subbuffer
+ * @kbuf:	The kbuffer
+ *
+ * Returns the location on the subbuffer where the data starts.
+ */
+int kbuffer_start_of_data(struct kbuffer *kbuf)
+{
+	return kbuf->start;
+}

tools/lib/traceevent/kbuffer.h

@@ -63,5 +63,6 @@ int kbuffer_missed_events(struct kbuffer *kbuf);
 int kbuffer_subbuffer_size(struct kbuffer *kbuf);
 
 void kbuffer_set_old_format(struct kbuffer *kbuf);
+int kbuffer_start_of_data(struct kbuffer *kbuf);
 
 #endif /* _K_BUFFER_H */

tools/lib/traceevent/parse-filter.c

@@ -1058,6 +1058,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 					*parg = current_op;
 				else
 					*parg = current_exp;
+				free(token);
 				return PEVENT_ERRNO__UNBALANCED_PAREN;
 			}
 			break;
@@ -1168,6 +1169,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 	*parg = current_op;
 
+	free(token);
 	return 0;
 
  fail_alloc:

tools/lib/traceevent/trace-seq.c

@@ -231,19 +231,24 @@ void trace_seq_terminate(struct trace_seq *s)
 	s->buffer[s->len] = 0;
 }
 
-int trace_seq_do_printf(struct trace_seq *s)
+int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp)
 {
 	TRACE_SEQ_CHECK(s);
 
 	switch (s->state) {
 	case TRACE_SEQ__GOOD:
-		return printf("%.*s", s->len, s->buffer);
+		return fprintf(fp, "%.*s", s->len, s->buffer);
 	case TRACE_SEQ__BUFFER_POISONED:
-		puts("Usage of trace_seq after it was destroyed");
+		fprintf(fp, "%s\n", "Usage of trace_seq after it was destroyed");
 		break;
 	case TRACE_SEQ__MEM_ALLOC_FAILED:
-		puts("Can't allocate trace_seq buffer memory");
+		fprintf(fp, "%s\n", "Can't allocate trace_seq buffer memory");
 		break;
 	}
 	return -1;
 }
+
+int trace_seq_do_printf(struct trace_seq *s)
+{
+	return trace_seq_do_fprintf(s, stdout);
+}

tools/perf/.gitignore

@@ -1,6 +1,7 @@
 PERF-CFLAGS
 PERF-GUI-VARS
 PERF-VERSION-FILE
+FEATURE-DUMP
 perf
 perf-read-vdso32
 perf-read-vdsox32

tools/perf/Build

@@ -0,0 +1,44 @@
+perf-y += builtin-bench.o
+perf-y += builtin-annotate.o
+perf-y += builtin-diff.o
+perf-y += builtin-evlist.o
+perf-y += builtin-help.o
+perf-y += builtin-sched.o
+perf-y += builtin-buildid-list.o
+perf-y += builtin-buildid-cache.o
+perf-y += builtin-list.o
+perf-y += builtin-record.o
+perf-y += builtin-report.o
+perf-y += builtin-stat.o
+perf-y += builtin-timechart.o
+perf-y += builtin-top.o
+perf-y += builtin-script.o
+perf-y += builtin-kmem.o
+perf-y += builtin-lock.o
+perf-y += builtin-kvm.o
+perf-y += builtin-inject.o
+perf-y += builtin-mem.o
+perf-y += builtin-data.o
+
+perf-$(CONFIG_AUDIT) += builtin-trace.o
+perf-$(CONFIG_LIBELF) += builtin-probe.o
+
+perf-y += bench/
+perf-y += tests/
+
+perf-y += perf.o
+
+paths += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"
+paths += -DPERF_INFO_PATH="BUILD_STR($(infodir_SQ))"
+paths += -DPERF_MAN_PATH="BUILD_STR($(mandir_SQ))"
+
+CFLAGS_builtin-help.o      += $(paths)
+CFLAGS_builtin-timechart.o += $(paths)
+CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" -include $(OUTPUT)PERF-VERSION-FILE
+
+libperf-y += util/
+libperf-y += arch/
+libperf-y += ui/
+libperf-y += scripts/
+
+gtk-y += ui/gtk/

tools/perf/Documentation/Build.txt

@@ -0,0 +1,49 @@
+
+1) perf build
+=============
+The perf build process consists of several separated building blocks,
+which are linked together to form the perf binary:
+  - libperf library (static)
+  - perf builtin commands
+  - traceevent library (static)
+  - GTK ui library
+
+Several makefiles govern the perf build:
+
+  - Makefile
+    top level Makefile working as a wrapper that calls the main
+    Makefile.perf with a -j option to do parallel builds.
+
+  - Makefile.perf
+    main makefile that triggers build of all perf objects including
+    installation and documentation processing.
+
+  - tools/build/Makefile.build
+    main makefile of the build framework
+
+  - tools/build/Build.include
+    build framework generic definitions
+
+  - Build makefiles
+    makefiles that defines build objects
+
+Please refer to tools/build/Documentation/Build.txt for more
+information about build framework.
+
+
+2) perf build
+=============
+The Makefile.perf triggers the build framework for build objects:
+   perf, libperf, gtk
+
+resulting in following objects:
+  $ ls  *-in.o
+  gtk-in.o  libperf-in.o  perf-in.o
+
+Those objects are then used in final linking:
+  libperf-gtk.so <- gtk-in.o  libperf-in.o
+  perf           <- perf-in.o libperf-in.o
+
+
+NOTE this description is omitting other libraries involved, only
+     focusing on build framework outcomes

tools/perf/Documentation/perf-buildid-cache.txt

@@ -12,9 +12,9 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command manages the build-id cache. It can add and remove files to/from
-the cache. In the future it should as well purge older entries, set upper
-limits for the space used by the cache, etc.
+This command manages the build-id cache. It can add, remove, update and purge
+files to/from the cache. In the future it should as well set upper limits for
+the space used by the cache, etc.
 
 OPTIONS
 -------
@@ -36,14 +36,24 @@ OPTIONS
         actually made.
 -r::
 --remove=::
-        Remove specified file from the cache.
+        Remove a cached binary which has same build-id of specified file
+        from the cache.
+-p::
+--purge=::
+        Purge all cached binaries including older caches which have specified
+	path from the cache.
 -M::
 --missing=::
 	List missing build ids in the cache for the specified file.
 -u::
---update::
-	Update specified file of the cache. It can be used to update kallsyms
-	kernel dso to vmlinux in order to support annotation.
+--update=::
+	Update specified file of the cache. Note that this doesn't remove
+	older entires since those may be still needed for annotating old
+	(or remote) perf.data. Only if there is already a cache which has
+	exactly same build-id, that is replaced by new one. It can be used
+	to update kallsyms and kernel dso to vmlinux in order to support
+	annotation.
+
 -v::
 --verbose::
 	Be more verbose.

tools/perf/Documentation/perf-data.txt

@@ -0,0 +1,40 @@
+perf-data(1)
+==============
+
+NAME
+----
+perf-data - Data file related processing
+
+SYNOPSIS
+--------
+[verse]
+'perf data' [<common options>] <command> [<options>]",
+
+DESCRIPTION
+-----------
+Data file related processing.
+
+COMMANDS
+--------
+convert::
+	Converts perf data file into another format (only CTF [1] format is support by now).
+	It's possible to set data-convert debug variable to get debug messages from conversion,
+	like:
+	  perf --debug data-convert data convert ...
+
+OPTIONS for 'convert'
+---------------------
+--to-ctf::
+	Triggers the CTF conversion, specify the path of CTF data directory.
+
+-i::
+	Specify input perf data file path.
+
+-v::
+--verbose::
+        Be more verbose (show counter open errors, etc).
+
+SEE ALSO
+--------
+linkperf:perf[1]
+[1] Common Trace Format - http://www.efficios.com/ctf

tools/perf/Documentation/perf-diff.txt

@@ -20,12 +20,20 @@ If no parameters are passed it will assume perf.data.old and perf.data.
 The differential profile is displayed only for events matching both
 specified perf.data files.
 
+If no parameters are passed the samples will be sorted by dso and symbol.
+As the perf.data files could come from different binaries, the symbols addresses
+could vary. So perf diff is based on the comparison of the files and
+symbols name.
+
 OPTIONS
 -------
 -D::
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
+--kallsyms=<file>::
+        kallsyms pathname
+
 -m::
 --modules::
         Load module symbols. WARNING: use only with -k and LIVE kernel

tools/perf/Documentation/perf-kmem.txt

@@ -25,6 +25,10 @@ OPTIONS
 --input=<file>::
 	Select the input file (default: perf.data unless stdin is a fifo)
 
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 --caller::
 	Show per-callsite statistics
 

tools/perf/Documentation/perf-list.txt

@@ -127,6 +127,12 @@ To limit the list use:
 One or more types can be used at the same time, listing the events for the
 types specified.
 
+Support raw format:
+
+. '--raw-dump', shows the raw-dump of all the events.
+. '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of
+  a certain kind of events.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-top[1],

tools/perf/Documentation/perf-probe.txt

@@ -47,6 +47,12 @@ OPTIONS
 -v::
 --verbose::
         Be more verbose (show parsed arguments, etc).
+	Can not use with -q.
+
+-q::
+--quiet::
+	Be quiet (do not show any messages including errors).
+	Can not use with -v.
 
 -a::
 --add=::
@@ -96,7 +102,7 @@ OPTIONS
 	Dry run. With this option, --add and --del doesn't execute actual
 	adding and removal operations.
 
---max-probes::
+--max-probes=NUM::
 	Set the maximum number of probe points for an event. Default is 128.
 
 -x::
@@ -104,8 +110,13 @@ OPTIONS
 	Specify path to the executable or shared library file for user
 	space tracing. Can also be used with --funcs option.
 
+--demangle::
+	Demangle application symbols. --no-demangle is also available
+	for disabling demangling.
+
 --demangle-kernel::
-	Demangle kernel symbols.
+	Demangle kernel symbols. --no-demangle-kernel is also available
+	for disabling kernel demangling.
 
 In absence of -m/-x options, perf probe checks if the first argument after
 the options is an absolute path name. If its an absolute path, perf probe
@@ -137,6 +148,7 @@ Each probe argument follows below syntax.
  [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
 
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
+'$vars' special argument is also available for NAME, it is expanded to the local variables which can access at given probe point.
 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
 
 On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.

tools/perf/Documentation/perf-record.txt

@@ -55,6 +55,11 @@ OPTIONS
           If you want to profile write accesses in [0x1000~1008), just set
           'mem:0x1000/8:w'.
 
+	- a group of events surrounded by a pair of brace ("{event1,event2,...}").
+	  Each event is separated by commas and the group should be quoted to
+	  prevent the shell interpretation.  You also need to use --group on
+	  "perf report" to view group events together.
+
 --filter=<filter>::
         Event filter.
 
@@ -62,9 +67,6 @@ OPTIONS
 --all-cpus::
         System-wide collection from all CPUs.
 
--l::
-        Scale counter values.
-
 -p::
 --pid=::
 	Record events on existing process ID (comma separated list).
@@ -107,6 +109,10 @@ OPTIONS
 	specification with appended unit character - B/K/M/G. The
 	size is rounded up to have nearest pages power of two value.
 
+--group::
+	Put all events in a single event group.  This precedes the --event
+	option and remains only for backward compatibility.  See --event.
+
 -g::
 	Enables call-graph (stack chain/backtrace) recording.
 
@@ -115,13 +121,19 @@ OPTIONS
 	implies -g.
 
 	Allows specifying "fp" (frame pointer) or "dwarf"
-	(DWARF's CFI - Call Frame Information) as the method to collect
+	(DWARF's CFI - Call Frame Information) or "lbr"
+	(Hardware Last Branch Record facility) as the method to collect
 	the information used to show the call graphs.
 
 	In some systems, where binaries are build with gcc
 	--fomit-frame-pointer, using the "fp" method will produce bogus
 	call graphs, using "dwarf", if available (perf tools linked to
 	the libunwind library) should be used instead.
+	Using the "lbr" method doesn't require any compiler options. It
+	will produce call graphs from the hardware LBR registers. The
+	main limition is that it is only available on new Intel
+	platforms, such as Haswell. It can only get user call chain. It
+	doesn't work with branch stack sampling at the same time.
 
 -q::
 --quiet::
@@ -235,6 +247,9 @@ Capture machine state (registers) at interrupt, i.e., on counter overflows for
 each sample. List of captured registers depends on the architecture. This option
 is off by default.
 
+--running-time::
+Record running and enabled time for read events (:S)
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]