Merge branch 'perf/x86' into perf/core, because it's ready

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/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

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;
@@ -271,6 +278,11 @@ struct pmu {
 	 */
 	size_t				task_ctx_size;
 
+
+	/*
+	 * Return the count value for a counter.
+	 */
+	u64 (*count)			(struct perf_event *event); /*optional*/
 };
 
 /**
@@ -547,6 +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);
@@ -740,6 +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);

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>
@@ -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)
 {
@@ -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)
@@ -7149,7 +7126,7 @@ 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;
@@ -7204,16 +7181,12 @@ 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) {
@@ -7245,6 +7218,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	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;
@@ -7268,6 +7247,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		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);
@@ -7486,6 +7467,7 @@ 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)
@@ -7551,21 +7533,16 @@ 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;
@@ -7802,7 +7779,7 @@ 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;
@@ -8163,7 +8140,7 @@ 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