1 files changed, 511 insertions, 157 deletions

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 3cc8416ec844..c3797701339c 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -17,61 +17,276 @@
  * This file contains the arch-independent routines.
  */
 
+#include <linux/hw_breakpoint.h>
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/cpu.h>
+#include <linux/export.h>
+#include <linux/init.h>
 #include <linux/irqflags.h>
-#include <linux/kallsyms.h>
-#include <linux/notifier.h>
-#include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/percpu-rwsem.h>
 #include <linux/percpu.h>
+#include <linux/rhashtable.h>
 #include <linux/sched.h>
-#include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/list.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/bug.h>
 
-#include <linux/hw_breakpoint.h>
 /*
- * Constraints data
+ * Datastructure to track the total uses of N slots across tasks or CPUs;
+ * bp_slots_histogram::count[N] is the number of assigned N+1 breakpoint slots.
+ */
+struct bp_slots_histogram {
+#ifdef hw_breakpoint_slots
+	atomic_t count[hw_breakpoint_slots(0)];
+#else
+	atomic_t *count;
+#endif
+};
+
+/*
+ * Per-CPU constraints data.
  */
 struct bp_cpuinfo {
-	/* Number of pinned cpu breakpoints in a cpu */
-	unsigned int	cpu_pinned;
-	/* tsk_pinned[n] is the number of tasks having n+1 breakpoints */
-	unsigned int	*tsk_pinned;
-	/* Number of non-pinned cpu/task breakpoints in a cpu */
-	unsigned int	flexible; /* XXX: placeholder, see fetch_this_slot() */
+	/* Number of pinned CPU breakpoints in a CPU. */
+	unsigned int			cpu_pinned;
+	/* Histogram of pinned task breakpoints in a CPU. */
+	struct bp_slots_histogram	tsk_pinned;
 };
 
 static DEFINE_PER_CPU(struct bp_cpuinfo, bp_cpuinfo[TYPE_MAX]);
-static int nr_slots[TYPE_MAX];
 
 static struct bp_cpuinfo *get_bp_info(int cpu, enum bp_type_idx type)
 {
 	return per_cpu_ptr(bp_cpuinfo + type, cpu);
 }
 
+/* Number of pinned CPU breakpoints globally. */
+static struct bp_slots_histogram cpu_pinned[TYPE_MAX];
+/* Number of pinned CPU-independent task breakpoints. */
+static struct bp_slots_histogram tsk_pinned_all[TYPE_MAX];
+
 /* Keep track of the breakpoints attached to tasks */
-static LIST_HEAD(bp_task_head);
+static struct rhltable task_bps_ht;
+static const struct rhashtable_params task_bps_ht_params = {
+	.head_offset = offsetof(struct hw_perf_event, bp_list),
+	.key_offset = offsetof(struct hw_perf_event, target),
+	.key_len = sizeof_field(struct hw_perf_event, target),
+	.automatic_shrinking = true,
+};
 
-static int constraints_initialized;
+static bool constraints_initialized __ro_after_init;
 
-/* Gather the number of total pinned and un-pinned bp in a cpuset */
-struct bp_busy_slots {
-	unsigned int pinned;
-	unsigned int flexible;
-};
+/*
+ * Synchronizes accesses to the per-CPU constraints; the locking rules are:
+ *
+ *  1. Atomic updates to bp_cpuinfo::tsk_pinned only require a held read-lock
+ *     (due to bp_slots_histogram::count being atomic, no update are lost).
+ *
+ *  2. Holding a write-lock is required for computations that require a
+ *     stable snapshot of all bp_cpuinfo::tsk_pinned.
+ *
+ *  3. In all other cases, non-atomic accesses require the appropriately held
+ *     lock (read-lock for read-only accesses; write-lock for reads/writes).
+ */
+DEFINE_STATIC_PERCPU_RWSEM(bp_cpuinfo_sem);
+
+/*
+ * Return mutex to serialize accesses to per-task lists in task_bps_ht. Since
+ * rhltable synchronizes concurrent insertions/deletions, independent tasks may
+ * insert/delete concurrently; therefore, a mutex per task is sufficient.
+ *
+ * Uses task_struct::perf_event_mutex, to avoid extending task_struct with a
+ * hw_breakpoint-only mutex, which may be infrequently used. The caveat here is
+ * that hw_breakpoint may contend with per-task perf event list management. The
+ * assumption is that perf usecases involving hw_breakpoints are very unlikely
+ * to result in unnecessary contention.
+ */
+static inline struct mutex *get_task_bps_mutex(struct perf_event *bp)
+{
+	struct task_struct *tsk = bp->hw.target;
 
-/* Serialize accesses to the above constraints */
-static DEFINE_MUTEX(nr_bp_mutex);
+	return tsk ? &tsk->perf_event_mutex : NULL;
+}
 
-__weak int hw_breakpoint_weight(struct perf_event *bp)
+static struct mutex *bp_constraints_lock(struct perf_event *bp)
+{
+	struct mutex *tsk_mtx = get_task_bps_mutex(bp);
+
+	if (tsk_mtx) {
+		/*
+		 * Fully analogous to the perf_try_init_event() nesting
+		 * argument in the comment near perf_event_ctx_lock_nested();
+		 * this child->perf_event_mutex cannot ever deadlock against
+		 * the parent->perf_event_mutex usage from
+		 * perf_event_task_{en,dis}able().
+		 *
+		 * Specifically, inherited events will never occur on
+		 * ->perf_event_list.
+		 */
+		mutex_lock_nested(tsk_mtx, SINGLE_DEPTH_NESTING);
+		percpu_down_read(&bp_cpuinfo_sem);
+	} else {
+		percpu_down_write(&bp_cpuinfo_sem);
+	}
+
+	return tsk_mtx;
+}
+
+static void bp_constraints_unlock(struct mutex *tsk_mtx)
+{
+	if (tsk_mtx) {
+		percpu_up_read(&bp_cpuinfo_sem);
+		mutex_unlock(tsk_mtx);
+	} else {
+		percpu_up_write(&bp_cpuinfo_sem);
+	}
+}
+
+static bool bp_constraints_is_locked(struct perf_event *bp)
+{
+	struct mutex *tsk_mtx = get_task_bps_mutex(bp);
+
+	return percpu_is_write_locked(&bp_cpuinfo_sem) ||
+	       (tsk_mtx ? mutex_is_locked(tsk_mtx) :
+			  percpu_is_read_locked(&bp_cpuinfo_sem));
+}
+
+static inline void assert_bp_constraints_lock_held(struct perf_event *bp)
+{
+	struct mutex *tsk_mtx = get_task_bps_mutex(bp);
+
+	if (tsk_mtx)
+		lockdep_assert_held(tsk_mtx);
+	lockdep_assert_held(&bp_cpuinfo_sem);
+}
+
+#ifdef hw_breakpoint_slots
+/*
+ * Number of breakpoint slots is constant, and the same for all types.
+ */
+static_assert(hw_breakpoint_slots(TYPE_INST) == hw_breakpoint_slots(TYPE_DATA));
+static inline int hw_breakpoint_slots_cached(int type)	{ return hw_breakpoint_slots(type); }
+static inline int init_breakpoint_slots(void)		{ return 0; }
+#else
+/*
+ * Dynamic number of breakpoint slots.
+ */
+static int __nr_bp_slots[TYPE_MAX] __ro_after_init;
+
+static inline int hw_breakpoint_slots_cached(int type)
+{
+	return __nr_bp_slots[type];
+}
+
+static __init bool
+bp_slots_histogram_alloc(struct bp_slots_histogram *hist, enum bp_type_idx type)
+{
+	hist->count = kcalloc(hw_breakpoint_slots_cached(type), sizeof(*hist->count), GFP_KERNEL);
+	return hist->count;
+}
+
+static __init void bp_slots_histogram_free(struct bp_slots_histogram *hist)
+{
+	kfree(hist->count);
+}
+
+static __init int init_breakpoint_slots(void)
+{
+	int i, cpu, err_cpu;
+
+	for (i = 0; i < TYPE_MAX; i++)
+		__nr_bp_slots[i] = hw_breakpoint_slots(i);
+
+	for_each_possible_cpu(cpu) {
+		for (i = 0; i < TYPE_MAX; i++) {
+			struct bp_cpuinfo *info = get_bp_info(cpu, i);
+
+			if (!bp_slots_histogram_alloc(&info->tsk_pinned, i))
+				goto err;
+		}
+	}
+	for (i = 0; i < TYPE_MAX; i++) {
+		if (!bp_slots_histogram_alloc(&cpu_pinned[i], i))
+			goto err;
+		if (!bp_slots_histogram_alloc(&tsk_pinned_all[i], i))
+			goto err;
+	}
+
+	return 0;
+err:
+	for_each_possible_cpu(err_cpu) {
+		for (i = 0; i < TYPE_MAX; i++)
+			bp_slots_histogram_free(&get_bp_info(err_cpu, i)->tsk_pinned);
+		if (err_cpu == cpu)
+			break;
+	}
+	for (i = 0; i < TYPE_MAX; i++) {
+		bp_slots_histogram_free(&cpu_pinned[i]);
+		bp_slots_histogram_free(&tsk_pinned_all[i]);
+	}
+
+	return -ENOMEM;
+}
+#endif
+
+static inline void
+bp_slots_histogram_add(struct bp_slots_histogram *hist, int old, int val)
+{
+	const int old_idx = old - 1;
+	const int new_idx = old_idx + val;
+
+	if (old_idx >= 0)
+		WARN_ON(atomic_dec_return_relaxed(&hist->count[old_idx]) < 0);
+	if (new_idx >= 0)
+		WARN_ON(atomic_inc_return_relaxed(&hist->count[new_idx]) < 0);
+}
+
+static int
+bp_slots_histogram_max(struct bp_slots_histogram *hist, enum bp_type_idx type)
+{
+	for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) {
+		const int count = atomic_read(&hist->count[i]);
+
+		/* Catch unexpected writers; we want a stable snapshot. */
+		ASSERT_EXCLUSIVE_WRITER(hist->count[i]);
+		if (count > 0)
+			return i + 1;
+		WARN(count < 0, "inconsistent breakpoint slots histogram");
+	}
+
+	return 0;
+}
+
+static int
+bp_slots_histogram_max_merge(struct bp_slots_histogram *hist1, struct bp_slots_histogram *hist2,
+			     enum bp_type_idx type)
+{
+	for (int i = hw_breakpoint_slots_cached(type) - 1; i >= 0; i--) {
+		const int count1 = atomic_read(&hist1->count[i]);
+		const int count2 = atomic_read(&hist2->count[i]);
+
+		/* Catch unexpected writers; we want a stable snapshot. */
+		ASSERT_EXCLUSIVE_WRITER(hist1->count[i]);
+		ASSERT_EXCLUSIVE_WRITER(hist2->count[i]);
+		if (count1 + count2 > 0)
+			return i + 1;
+		WARN(count1 < 0, "inconsistent breakpoint slots histogram");
+		WARN(count2 < 0, "inconsistent breakpoint slots histogram");
+	}
+
+	return 0;
+}
+
+#ifndef hw_breakpoint_weight
+static inline int hw_breakpoint_weight(struct perf_event *bp)
 {
 	return 1;
 }
+#endif
 
 static inline enum bp_type_idx find_slot_idx(u64 bp_type)
 {
@@ -82,39 +297,61 @@ static inline enum bp_type_idx find_slot_idx(u64 bp_type)
 }
 
 /*
- * Report the maximum number of pinned breakpoints a task
- * have in this cpu
+ * Return the maximum number of pinned breakpoints a task has in this CPU.
  */
 static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
 {
-	unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
-	int i;
-
-	for (i = nr_slots[type] - 1; i >= 0; i--) {
-		if (tsk_pinned[i] > 0)
-			return i + 1;
-	}
+	struct bp_slots_histogram *tsk_pinned = &get_bp_info(cpu, type)->tsk_pinned;
 
-	return 0;
+	/*
+	 * At this point we want to have acquired the bp_cpuinfo_sem as a
+	 * writer to ensure that there are no concurrent writers in
+	 * toggle_bp_task_slot() to tsk_pinned, and we get a stable snapshot.
+	 */
+	lockdep_assert_held_write(&bp_cpuinfo_sem);
+	return bp_slots_histogram_max_merge(tsk_pinned, &tsk_pinned_all[type], type);
 }
 
 /*
  * Count the number of breakpoints of the same type and same task.
  * The given event must be not on the list.
+ *
+ * If @cpu is -1, but the result of task_bp_pinned() is not CPU-independent,
+ * returns a negative value.
  */
 static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type)
 {
-	struct task_struct *tsk = bp->hw.target;
+	struct rhlist_head *head, *pos;
 	struct perf_event *iter;
 	int count = 0;
 
-	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
-		if (iter->hw.target == tsk &&
-		    find_slot_idx(iter->attr.bp_type) == type &&
-		    (iter->cpu < 0 || cpu == iter->cpu))
-			count += hw_breakpoint_weight(iter);
+	/*
+	 * We need a stable snapshot of the per-task breakpoint list.
+	 */
+	assert_bp_constraints_lock_held(bp);
+
+	rcu_read_lock();
+	head = rhltable_lookup(&task_bps_ht, &bp->hw.target, task_bps_ht_params);
+	if (!head)
+		goto out;
+
+	rhl_for_each_entry_rcu(iter, pos, head, hw.bp_list) {
+		if (find_slot_idx(iter->attr.bp_type) != type)
+			continue;
+
+		if (iter->cpu >= 0) {
+			if (cpu == -1) {
+				count = -1;
+				goto out;
+			} else if (cpu != iter->cpu)
+				continue;
+		}
+
+		count += hw_breakpoint_weight(iter);
 	}
 
+out:
+	rcu_read_unlock();
 	return count;
 }
 
@@ -126,16 +363,29 @@ static const struct cpumask *cpumask_of_bp(struct perf_event *bp)
 }
 
 /*
- * Report the number of pinned/un-pinned breakpoints we have in
- * a given cpu (cpu > -1) or in all of them (cpu = -1).
+ * Returns the max pinned breakpoint slots in a given
+ * CPU (cpu > -1) or across all of them (cpu = -1).
  */
-static void
-fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
-		    enum bp_type_idx type)
+static int
+max_bp_pinned_slots(struct perf_event *bp, enum bp_type_idx type)
 {
 	const struct cpumask *cpumask = cpumask_of_bp(bp);
+	int pinned_slots = 0;
 	int cpu;
 
+	if (bp->hw.target && bp->cpu < 0) {
+		int max_pinned = task_bp_pinned(-1, bp, type);
+
+		if (max_pinned >= 0) {
+			/*
+			 * Fast path: task_bp_pinned() is CPU-independent and
+			 * returns the same value for any CPU.
+			 */
+			max_pinned += bp_slots_histogram_max(&cpu_pinned[type], type);
+			return max_pinned;
+		}
+	}
+
 	for_each_cpu(cpu, cpumask) {
 		struct bp_cpuinfo *info = get_bp_info(cpu, type);
 		int nr;
@@ -146,71 +396,140 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		else
 			nr += task_bp_pinned(cpu, bp, type);
 
-		if (nr > slots->pinned)
-			slots->pinned = nr;
-
-		nr = info->flexible;
-		if (nr > slots->flexible)
-			slots->flexible = nr;
+		pinned_slots = max(nr, pinned_slots);
 	}
-}
 
-/*
- * For now, continue to consider flexible as pinned, until we can
- * ensure no flexible event can ever be scheduled before a pinned event
- * in a same cpu.
- */
-static void
-fetch_this_slot(struct bp_busy_slots *slots, int weight)
-{
-	slots->pinned += weight;
-}
-
-/*
- * Add a pinned breakpoint for the given task in our constraint table
- */
-static void toggle_bp_task_slot(struct perf_event *bp, int cpu,
-				enum bp_type_idx type, int weight)
-{
-	unsigned int *tsk_pinned = get_bp_info(cpu, type)->tsk_pinned;
-	int old_idx, new_idx;
-
-	old_idx = task_bp_pinned(cpu, bp, type) - 1;
-	new_idx = old_idx + weight;
-
-	if (old_idx >= 0)
-		tsk_pinned[old_idx]--;
-	if (new_idx >= 0)
-		tsk_pinned[new_idx]++;
+	return pinned_slots;
 }
 
 /*
  * Add/remove the given breakpoint in our constraint table
  */
-static void
-toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
-	       int weight)
+static int
+toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, int weight)
 {
-	const struct cpumask *cpumask = cpumask_of_bp(bp);
-	int cpu;
+	int cpu, next_tsk_pinned;
 
 	if (!enable)
 		weight = -weight;
 
-	/* Pinned counter cpu profiling */
 	if (!bp->hw.target) {
-		get_bp_info(bp->cpu, type)->cpu_pinned += weight;
-		return;
+		/*
+		 * Update the pinned CPU slots, in per-CPU bp_cpuinfo and in the
+		 * global histogram.
+		 */
+		struct bp_cpuinfo *info = get_bp_info(bp->cpu, type);
+
+		lockdep_assert_held_write(&bp_cpuinfo_sem);
+		bp_slots_histogram_add(&cpu_pinned[type], info->cpu_pinned, weight);
+		info->cpu_pinned += weight;
+		return 0;
+	}
+
+	/*
+	 * If bp->hw.target, tsk_pinned is only modified, but not used
+	 * otherwise. We can permit concurrent updates as long as there are no
+	 * other uses: having acquired bp_cpuinfo_sem as a reader allows
+	 * concurrent updates here. Uses of tsk_pinned will require acquiring
+	 * bp_cpuinfo_sem as a writer to stabilize tsk_pinned's value.
+	 */
+	lockdep_assert_held_read(&bp_cpuinfo_sem);
+
+	/*
+	 * Update the pinned task slots, in per-CPU bp_cpuinfo and in the global
+	 * histogram. We need to take care of 4 cases:
+	 *
+	 *  1. This breakpoint targets all CPUs (cpu < 0), and there may only
+	 *     exist other task breakpoints targeting all CPUs. In this case we
+	 *     can simply update the global slots histogram.
+	 *
+	 *  2. This breakpoint targets a specific CPU (cpu >= 0), but there may
+	 *     only exist other task breakpoints targeting all CPUs.
+	 *
+	 *     a. On enable: remove the existing breakpoints from the global
+	 *        slots histogram and use the per-CPU histogram.
+	 *
+	 *     b. On disable: re-insert the existing breakpoints into the global
+	 *        slots histogram and remove from per-CPU histogram.
+	 *
+	 *  3. Some other existing task breakpoints target specific CPUs. Only
+	 *     update the per-CPU slots histogram.
+	 */
+
+	if (!enable) {
+		/*
+		 * Remove before updating histograms so we can determine if this
+		 * was the last task breakpoint for a specific CPU.
+		 */
+		int ret = rhltable_remove(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params);
+
+		if (ret)
+			return ret;
+	}
+	/*
+	 * Note: If !enable, next_tsk_pinned will not count the to-be-removed breakpoint.
+	 */
+	next_tsk_pinned = task_bp_pinned(-1, bp, type);
+
+	if (next_tsk_pinned >= 0) {
+		if (bp->cpu < 0) { /* Case 1: fast path */
+			if (!enable)
+				next_tsk_pinned += hw_breakpoint_weight(bp);
+			bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned, weight);
+		} else if (enable) { /* Case 2.a: slow path */
+			/* Add existing to per-CPU histograms. */
+			for_each_possible_cpu(cpu) {
+				bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned,
+						       0, next_tsk_pinned);
+			}
+			/* Add this first CPU-pinned task breakpoint. */
+			bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned,
+					       next_tsk_pinned, weight);
+			/* Rebalance global task pinned histogram. */
+			bp_slots_histogram_add(&tsk_pinned_all[type], next_tsk_pinned,
+					       -next_tsk_pinned);
+		} else { /* Case 2.b: slow path */
+			/* Remove this last CPU-pinned task breakpoint. */
+			bp_slots_histogram_add(&get_bp_info(bp->cpu, type)->tsk_pinned,
+					       next_tsk_pinned + hw_breakpoint_weight(bp), weight);
+			/* Remove all from per-CPU histograms. */
+			for_each_possible_cpu(cpu) {
+				bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned,
+						       next_tsk_pinned, -next_tsk_pinned);
+			}
+			/* Rebalance global task pinned histogram. */
+			bp_slots_histogram_add(&tsk_pinned_all[type], 0, next_tsk_pinned);
+		}
+	} else { /* Case 3: slow path */
+		const struct cpumask *cpumask = cpumask_of_bp(bp);
+
+		for_each_cpu(cpu, cpumask) {
+			next_tsk_pinned = task_bp_pinned(cpu, bp, type);
+			if (!enable)
+				next_tsk_pinned += hw_breakpoint_weight(bp);
+			bp_slots_histogram_add(&get_bp_info(cpu, type)->tsk_pinned,
+					       next_tsk_pinned, weight);
+		}
 	}
 
-	/* Pinned counter task profiling */
-	for_each_cpu(cpu, cpumask)
-		toggle_bp_task_slot(bp, cpu, type, weight);
+	/*
+	 * Readers want a stable snapshot of the per-task breakpoint list.
+	 */
+	assert_bp_constraints_lock_held(bp);
 
 	if (enable)
-		list_add_tail(&bp->hw.bp_list, &bp_task_head);
-	else
-		list_del(&bp->hw.bp_list);
+		return rhltable_insert(&task_bps_ht, &bp->hw.bp_list, task_bps_ht_params);
+
+	return 0;
+}
+
+__weak int arch_reserve_bp_slot(struct perf_event *bp)
+{
+	return 0;
+}
+
+__weak void arch_release_bp_slot(struct perf_event *bp)
+{
 }
 
 /*
@@ -225,7 +544,12 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
 }
 
 /*
- * Constraints to check before allowing this new breakpoint counter:
+ * Constraints to check before allowing this new breakpoint counter.
+ *
+ * Note: Flexible breakpoints are currently unimplemented, but outlined in the
+ * below algorithm for completeness.  The implementation treats flexible as
+ * pinned due to no guarantee that we currently always schedule flexible events
+ * before a pinned event in a same CPU.
  *
  *  == Non-pinned counter == (Considered as pinned for now)
  *
@@ -267,9 +591,10 @@ __weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
  */
 static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
 {
-	struct bp_busy_slots slots = {0};
 	enum bp_type_idx type;
+	int max_pinned_slots;
 	int weight;
+	int ret;
 
 	/* We couldn't initialize breakpoint constraints on boot */
 	if (!constraints_initialized)
@@ -283,32 +608,24 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
 	type = find_slot_idx(bp_type);
 	weight = hw_breakpoint_weight(bp);
 
-	fetch_bp_busy_slots(&slots, bp, type);
-	/*
-	 * Simulate the addition of this breakpoint to the constraints
-	 * and see the result.
-	 */
-	fetch_this_slot(&slots, weight);
-
-	/* Flexible counters need to keep at least one slot */
-	if (slots.pinned + (!!slots.flexible) > nr_slots[type])
+	/* Check if this new breakpoint can be satisfied across all CPUs. */
+	max_pinned_slots = max_bp_pinned_slots(bp, type) + weight;
+	if (max_pinned_slots > hw_breakpoint_slots_cached(type))
 		return -ENOSPC;
 
-	toggle_bp_slot(bp, true, type, weight);
+	ret = arch_reserve_bp_slot(bp);
+	if (ret)
+		return ret;
 
-	return 0;
+	return toggle_bp_slot(bp, true, type, weight);
 }
 
 int reserve_bp_slot(struct perf_event *bp)
 {
-	int ret;
-
-	mutex_lock(&nr_bp_mutex);
-
-	ret = __reserve_bp_slot(bp, bp->attr.bp_type);
-
-	mutex_unlock(&nr_bp_mutex);
+	struct mutex *mtx = bp_constraints_lock(bp);
+	int ret = __reserve_bp_slot(bp, bp->attr.bp_type);
 
+	bp_constraints_unlock(mtx);
 	return ret;
 }
 
@@ -317,19 +634,20 @@ static void __release_bp_slot(struct perf_event *bp, u64 bp_type)
 	enum bp_type_idx type;
 	int weight;
 
+	arch_release_bp_slot(bp);
+
 	type = find_slot_idx(bp_type);
 	weight = hw_breakpoint_weight(bp);
-	toggle_bp_slot(bp, false, type, weight);
+	WARN_ON(toggle_bp_slot(bp, false, type, weight));
 }
 
 void release_bp_slot(struct perf_event *bp)
 {
-	mutex_lock(&nr_bp_mutex);
+	struct mutex *mtx = bp_constraints_lock(bp);
 
 	arch_unregister_hw_breakpoint(bp);
 	__release_bp_slot(bp, bp->attr.bp_type);
-
-	mutex_unlock(&nr_bp_mutex);
+	bp_constraints_unlock(mtx);
 }
 
 static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
@@ -356,11 +674,10 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 
 static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
-	int ret;
+	struct mutex *mtx = bp_constraints_lock(bp);
+	int ret = __modify_bp_slot(bp, old_type, new_type);
 
-	mutex_lock(&nr_bp_mutex);
-	ret = __modify_bp_slot(bp, old_type, new_type);
-	mutex_unlock(&nr_bp_mutex);
+	bp_constraints_unlock(mtx);
 	return ret;
 }
 
@@ -371,18 +688,28 @@ static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
  */
 int dbg_reserve_bp_slot(struct perf_event *bp)
 {
-	if (mutex_is_locked(&nr_bp_mutex))
+	int ret;
+
+	if (bp_constraints_is_locked(bp))
 		return -1;
 
-	return __reserve_bp_slot(bp, bp->attr.bp_type);
+	/* Locks aren't held; disable lockdep assert checking. */
+	lockdep_off();
+	ret = __reserve_bp_slot(bp, bp->attr.bp_type);
+	lockdep_on();
+
+	return ret;
 }
 
 int dbg_release_bp_slot(struct perf_event *bp)
 {
-	if (mutex_is_locked(&nr_bp_mutex))
+	if (bp_constraints_is_locked(bp))
 		return -1;
 
+	/* Locks aren't held; disable lockdep assert checking. */
+	lockdep_off();
 	__release_bp_slot(bp, bp->attr.bp_type);
+	lockdep_on();
 
 	return 0;
 }
@@ -435,6 +762,7 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
  * register_user_hw_breakpoint - register a hardware breakpoint for user space
  * @attr: breakpoint attributes
  * @triggered: callback to trigger when we hit the breakpoint
+ * @context: context data could be used in the triggered callback
  * @tsk: pointer to 'task_struct' of the process to which the address belongs
  */
 struct perf_event *
@@ -534,6 +862,7 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
  * register_wide_hw_breakpoint - register a wide breakpoint in the kernel
  * @attr: breakpoint attributes
  * @triggered: callback to trigger when we hit the breakpoint
+ * @context: context data could be used in the triggered callback
  *
  * @return a set of per_cpu pointers to perf events
  */
@@ -550,7 +879,7 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 	if (!cpu_events)
 		return (void __percpu __force *)ERR_PTR(-ENOMEM);
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		bp = perf_event_create_kernel_counter(attr, cpu, NULL,
 						      triggered, context);
@@ -561,7 +890,7 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 
 		per_cpu(*cpu_events, cpu) = bp;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (likely(!err))
 		return cpu_events;
@@ -586,6 +915,50 @@ void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)
 }
 EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint);
 
+/**
+ * hw_breakpoint_is_used - check if breakpoints are currently used
+ *
+ * Returns: true if breakpoints are used, false otherwise.
+ */
+bool hw_breakpoint_is_used(void)
+{
+	int cpu;
+
+	if (!constraints_initialized)
+		return false;
+
+	for_each_possible_cpu(cpu) {
+		for (int type = 0; type < TYPE_MAX; ++type) {
+			struct bp_cpuinfo *info = get_bp_info(cpu, type);
+
+			if (info->cpu_pinned)
+				return true;
+
+			for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) {
+				if (atomic_read(&info->tsk_pinned.count[slot]))
+					return true;
+			}
+		}
+	}
+
+	for (int type = 0; type < TYPE_MAX; ++type) {
+		for (int slot = 0; slot < hw_breakpoint_slots_cached(type); ++slot) {
+			/*
+			 * Warn, because if there are CPU pinned counters,
+			 * should never get here; bp_cpuinfo::cpu_pinned should
+			 * be consistent with the global cpu_pinned histogram.
+			 */
+			if (WARN_ON(atomic_read(&cpu_pinned[type].count[slot])))
+				return true;
+
+			if (atomic_read(&tsk_pinned_all[type].count[slot]))
+				return true;
+		}
+	}
+
+	return false;
+}
+
 static struct notifier_block hw_breakpoint_exceptions_nb = {
 	.notifier_call = hw_breakpoint_exceptions_notify,
 	/* we need to be notified first */
@@ -660,38 +1033,19 @@ static struct pmu perf_breakpoint = {
 
 int __init init_hw_breakpoint(void)
 {
-	int cpu, err_cpu;
-	int i;
-
-	for (i = 0; i < TYPE_MAX; i++)
-		nr_slots[i] = hw_breakpoint_slots(i);
+	int ret;
 
-	for_each_possible_cpu(cpu) {
-		for (i = 0; i < TYPE_MAX; i++) {
-			struct bp_cpuinfo *info = get_bp_info(cpu, i);
+	ret = rhltable_init(&task_bps_ht, &task_bps_ht_params);
+	if (ret)
+		return ret;
 
-			info->tsk_pinned = kcalloc(nr_slots[i], sizeof(int),
-							GFP_KERNEL);
-			if (!info->tsk_pinned)
-				goto err_alloc;
-		}
-	}
+	ret = init_breakpoint_slots();
+	if (ret)
+		return ret;
 
-	constraints_initialized = 1;
+	constraints_initialized = true;
 
 	perf_pmu_register(&perf_breakpoint, "breakpoint", PERF_TYPE_BREAKPOINT);
 
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
-
- err_alloc:
-	for_each_possible_cpu(err_cpu) {
-		for (i = 0; i < TYPE_MAX; i++)
-			kfree(get_bp_info(err_cpu, i)->tsk_pinned);
-		if (err_cpu == cpu)
-			break;
-	}
-
-	return -ENOMEM;
 }
-
-