Merge branch 'for-next/perf-user-counter-access' into for-next/perf

* for-next/perf-user-counter-access:
  Documentation: arm64: Document PMU counters access from userspace
  arm64: perf: Enable PMU counter userspace access for perf event
  arm64: perf: Add userspace counter access disable switch
  perf: Add a counter for number of user access events in context
  x86: perf: Move RDPMC event flag to a common definition

Author: willdeacon

Documentation/admin-guide/sysctl/kernel.rst

@@ -905,6 +905,17 @@ enabled, otherwise writing to this file will return ``-EBUSY``.
 The default value is 8.
 
 
+perf_user_access (arm64 only)
+=================================
+
+Controls user space access for reading perf event counters. When set to 1,
+user space can read performance monitor counter registers directly.
+
+The default value is 0 (access disabled).
+
+See Documentation/arm64/perf.rst for more information.
+
+
 pid_max
 =======
 

Documentation/arm64/perf.rst

@@ -2,7 +2,10 @@
 
 .. _perf_index:
 
-=====================
+====
+Perf
+====
+
 Perf Event Attributes
 =====================
 
@@ -88,3 +91,76 @@ exclude_host. However when using !exclude_hv there is a small blackout
 window at the guest entry/exit where host events are not captured.
 
 On VHE systems there are no blackout windows.
+
+Perf Userspace PMU Hardware Counter Access
+==========================================
+
+Overview
+--------
+The perf userspace tool relies on the PMU to monitor events. It offers an
+abstraction layer over the hardware counters since the underlying
+implementation is cpu-dependent.
+Arm64 allows userspace tools to have access to the registers storing the
+hardware counters' values directly.
+
+This targets specifically self-monitoring tasks in order to reduce the overhead
+by directly accessing the registers without having to go through the kernel.
+
+How-to
+------
+The focus is set on the armv8 PMUv3 which makes sure that the access to the pmu
+registers is enabled and that the userspace has access to the relevant
+information in order to use them.
+
+In order to have access to the hardware counters, the global sysctl
+kernel/perf_user_access must first be enabled:
+
+.. code-block:: sh
+
+  echo 1 > /proc/sys/kernel/perf_user_access
+
+It is necessary to open the event using the perf tool interface with config1:1
+attr bit set: the sys_perf_event_open syscall returns a fd which can
+subsequently be used with the mmap syscall in order to retrieve a page of memory
+containing information about the event. The PMU driver uses this page to expose
+to the user the hardware counter's index and other necessary data. Using this
+index enables the user to access the PMU registers using the `mrs` instruction.
+Access to the PMU registers is only valid while the sequence lock is unchanged.
+In particular, the PMSELR_EL0 register is zeroed each time the sequence lock is
+changed.
+
+The userspace access is supported in libperf using the perf_evsel__mmap()
+and perf_evsel__read() functions. See `tools/lib/perf/tests/test-evsel.c`_ for
+an example.
+
+About heterogeneous systems
+---------------------------
+On heterogeneous systems such as big.LITTLE, userspace PMU counter access can
+only be enabled when the tasks are pinned to a homogeneous subset of cores and
+the corresponding PMU instance is opened by specifying the 'type' attribute.
+The use of generic event types is not supported in this case.
+
+Have a look at `tools/perf/arch/arm64/tests/user-events.c`_ for an example. It
+can be run using the perf tool to check that the access to the registers works
+correctly from userspace:
+
+.. code-block:: sh
+
+  perf test -v user
+
+About chained events and counter sizes
+--------------------------------------
+The user can request either a 32-bit (config1:0 == 0) or 64-bit (config1:0 == 1)
+counter along with userspace access. The sys_perf_event_open syscall will fail
+if a 64-bit counter is requested and the hardware doesn't support 64-bit
+counters. Chained events are not supported in conjunction with userspace counter
+access. If a 32-bit counter is requested on hardware with 64-bit counters, then
+userspace must treat the upper 32-bits read from the counter as UNKNOWN. The
+'pmc_width' field in the user page will indicate the valid width of the counter
+and should be used to mask the upper bits as needed.
+
+.. Links
+.. _tools/perf/arch/arm64/tests/user-events.c:
+   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/perf/arch/arm64/tests/user-events.c
+.. _tools/lib/perf/tests/test-evsel.c:
+   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/lib/perf/tests/test-evsel.c

arch/arm64/kernel/perf_event.c

@@ -285,15 +285,24 @@ static const struct attribute_group armv8_pmuv3_events_attr_group = {
 
 PMU_FORMAT_ATTR(event, "config:0-15");
 PMU_FORMAT_ATTR(long, "config1:0");
+PMU_FORMAT_ATTR(rdpmc, "config1:1");
+
+static int sysctl_perf_user_access __read_mostly;
 
 static inline bool armv8pmu_event_is_64bit(struct perf_event *event)
 {
 	return event->attr.config1 & 0x1;
 }
 
+static inline bool armv8pmu_event_want_user_access(struct perf_event *event)
+{
+	return event->attr.config1 & 0x2;
+}
+
 static struct attribute *armv8_pmuv3_format_attrs[] = {
 	&format_attr_event.attr,
 	&format_attr_long.attr,
+	&format_attr_rdpmc.attr,
 	NULL,
 };
 
@@ -362,7 +371,7 @@ static const struct attribute_group armv8_pmuv3_caps_attr_group = {
  */
 #define	ARMV8_IDX_CYCLE_COUNTER	0
 #define	ARMV8_IDX_COUNTER0	1
-
+#define	ARMV8_IDX_CYCLE_COUNTER_USER	32
 
 /*
  * We unconditionally enable ARMv8.5-PMU long event counter support
@@ -374,18 +383,22 @@ static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu)
 	return (cpu_pmu->pmuver >= ID_AA64DFR0_PMUVER_8_5);
 }
 
+static inline bool armv8pmu_event_has_user_read(struct perf_event *event)
+{
+	return event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT;
+}
+
 /*
  * We must chain two programmable counters for 64 bit events,
  * except when we have allocated the 64bit cycle counter (for CPU
- * cycles event). This must be called only when the event has
- * a counter allocated.
+ * cycles event) or when user space counter access is enabled.
  */
 static inline bool armv8pmu_event_is_chained(struct perf_event *event)
 {
 	int idx = event->hw.idx;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 
-	return !WARN_ON(idx < 0) &&
+	return !armv8pmu_event_has_user_read(event) &&
 	       armv8pmu_event_is_64bit(event) &&
 	       !armv8pmu_has_long_event(cpu_pmu) &&
 	       (idx != ARMV8_IDX_CYCLE_COUNTER);
@@ -718,6 +731,28 @@ static inline u32 armv8pmu_getreset_flags(void)
 	return value;
 }
 
+static void armv8pmu_disable_user_access(void)
+{
+	write_sysreg(0, pmuserenr_el0);
+}
+
+static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
+{
+	int i;
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
+
+	/* Clear any unused counters to avoid leaking their contents */
+	for_each_clear_bit(i, cpuc->used_mask, cpu_pmu->num_events) {
+		if (i == ARMV8_IDX_CYCLE_COUNTER)
+			write_sysreg(0, pmccntr_el0);
+		else
+			armv8pmu_write_evcntr(i, 0);
+	}
+
+	write_sysreg(0, pmuserenr_el0);
+	write_sysreg(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR, pmuserenr_el0);
+}
+
 static void armv8pmu_enable_event(struct perf_event *event)
 {
 	/*
@@ -761,6 +796,14 @@ static void armv8pmu_disable_event(struct perf_event *event)
 
 static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 {
+	struct perf_event_context *task_ctx =
+		this_cpu_ptr(cpu_pmu->pmu.pmu_cpu_context)->task_ctx;
+
+	if (sysctl_perf_user_access && task_ctx && task_ctx->nr_user)
+		armv8pmu_enable_user_access(cpu_pmu);
+	else
+		armv8pmu_disable_user_access();
+
 	/* Enable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
 }
@@ -878,13 +921,16 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	if (evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) {
 		if (!test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
 			return ARMV8_IDX_CYCLE_COUNTER;
+		else if (armv8pmu_event_is_64bit(event) &&
+			   armv8pmu_event_want_user_access(event) &&
+			   !armv8pmu_has_long_event(cpu_pmu))
+				return -EAGAIN;
 	}
 
 	/*
 	 * Otherwise use events counters
 	 */
-	if (armv8pmu_event_is_64bit(event) &&
-	    !armv8pmu_has_long_event(cpu_pmu))
+	if (armv8pmu_event_is_chained(event))
 		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
 	else
 		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
@@ -900,6 +946,22 @@ static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 		clear_bit(idx - 1, cpuc->used_mask);
 }
 
+static int armv8pmu_user_event_idx(struct perf_event *event)
+{
+	if (!sysctl_perf_user_access || !armv8pmu_event_has_user_read(event))
+		return 0;
+
+	/*
+	 * We remap the cycle counter index to 32 to
+	 * match the offset applied to the rest of
+	 * the counter indices.
+	 */
+	if (event->hw.idx == ARMV8_IDX_CYCLE_COUNTER)
+		return ARMV8_IDX_CYCLE_COUNTER_USER;
+
+	return event->hw.idx;
+}
+
 /*
  * Add an event filter to a given event.
  */
@@ -996,6 +1058,25 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
 	if (armv8pmu_event_is_64bit(event))
 		event->hw.flags |= ARMPMU_EVT_64BIT;
 
+	/*
+	 * User events must be allocated into a single counter, and so
+	 * must not be chained.
+	 *
+	 * Most 64-bit events require long counter support, but 64-bit
+	 * CPU_CYCLES events can be placed into the dedicated cycle
+	 * counter when this is free.
+	 */
+	if (armv8pmu_event_want_user_access(event)) {
+		if (!(event->attach_state & PERF_ATTACH_TASK))
+			return -EINVAL;
+		if (armv8pmu_event_is_64bit(event) &&
+		    (hw_event_id != ARMV8_PMUV3_PERFCTR_CPU_CYCLES) &&
+		    !armv8pmu_has_long_event(armpmu))
+			return -EOPNOTSUPP;
+
+		event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT;
+	}
+
 	/* Only expose micro/arch events supported by this PMU */
 	if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS)
 	    && test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
@@ -1104,6 +1185,35 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 	return probe.present ? 0 : -ENODEV;
 }
 
+static void armv8pmu_disable_user_access_ipi(void *unused)
+{
+	armv8pmu_disable_user_access();
+}
+
+static int armv8pmu_proc_user_access_handler(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret || !write || sysctl_perf_user_access)
+		return ret;
+
+	on_each_cpu(armv8pmu_disable_user_access_ipi, NULL, 1);
+	return 0;
+}
+
+static struct ctl_table armv8_pmu_sysctl_table[] = {
+	{
+		.procname       = "perf_user_access",
+		.data		= &sysctl_perf_user_access,
+		.maxlen		= sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler	= armv8pmu_proc_user_access_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+
 static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			  int (*map_event)(struct perf_event *event),
 			  const struct attribute_group *events,
@@ -1127,6 +1237,8 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
+	cpu_pmu->pmu.event_idx		= armv8pmu_user_event_idx;
+
 	cpu_pmu->name			= name;
 	cpu_pmu->map_event		= map_event;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ?
@@ -1136,6 +1248,8 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ?
 			caps : &armv8_pmuv3_caps_attr_group;
 
+	register_sysctl("kernel", armv8_pmu_sysctl_table);
+
 	return 0;
 }
 
@@ -1301,6 +1415,14 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
 	userpg->cap_user_time_short = 0;
+	userpg->cap_user_rdpmc = armv8pmu_event_has_user_read(event);
+
+	if (userpg->cap_user_rdpmc) {
+		if (event->hw.flags & ARMPMU_EVT_64BIT)
+			userpg->pmc_width = 64;
+		else
+			userpg->pmc_width = 32;
+	}
 
 	do {
 		rd = sched_clock_read_begin(&seq);

arch/x86/events/core.c

@@ -2476,7 +2476,7 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 	if (READ_ONCE(x86_pmu.attr_rdpmc) &&
 	    !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
-		event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
+		event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT;
 
 	return err;
 }
@@ -2510,7 +2510,7 @@ void perf_clear_dirty_counters(void)
 
 static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 {
-	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
+	if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT))
 		return;
 
 	/*
@@ -2531,7 +2531,7 @@ static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 
 static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
 {
-	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
+	if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT))
 		return;
 
 	if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed))
@@ -2542,7 +2542,7 @@ static int x86_pmu_event_idx(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!(hwc->flags & PERF_X86_EVENT_RDPMC_ALLOWED))
+	if (!(hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
 		return 0;
 
 	if (is_metric_idx(hwc->idx))
@@ -2725,7 +2725,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
 	userpg->cap_user_rdpmc =
-		!!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED);
+		!!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT);
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
 	if (!using_native_sched_clock() || !sched_clock_stable())