10 files changed, 798 insertions, 30 deletions

diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 4a62ed593e84..e4352881e3fa 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -431,9 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
 static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
 {
 	bool augmented, do_output = false;
-	int zero = 0, size, aug_size, index,
-	    value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
+	int zero = 0, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
 	u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */
+	s64 aug_size, size;
 	unsigned int nr, *beauty_map;
 	struct beauty_payload_enter *payload;
 	void *arg, *payload_offset;
@@ -484,14 +484,11 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
 		} else if (size > 0 && size <= value_size) { /* struct */
 			if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg))
 				augmented = true;
-		} else if (size < 0 && size >= -6) { /* buffer */
+		} else if ((int)size < 0 && size >= -6) { /* buffer */
 			index = -(size + 1);
 			barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick.
 			index &= 7;	    // Satisfy the bounds checking with the verifier in some kernels.
-			aug_size = args->args[index];
-
-			if (aug_size > TRACE_AUG_MAX_BUF)
-				aug_size = TRACE_AUG_MAX_BUF;
+			aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index];
 
 			if (aug_size > 0) {
 				if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg))
diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c
index f613dc9cb123..e731a79a753a 100644
--- a/tools/perf/util/bpf_skel/func_latency.bpf.c
+++ b/tools/perf/util/bpf_skel/func_latency.bpf.c
@@ -38,9 +38,19 @@ struct {
 
 int enabled = 0;
 
+// stats
+__s64 total;
+__s64 count;
+__s64 max;
+__s64 min;
+
 const volatile int has_cpu = 0;
 const volatile int has_task = 0;
 const volatile int use_nsec = 0;
+const volatile unsigned int bucket_range;
+const volatile unsigned int min_latency;
+const volatile unsigned int max_latency;
+const volatile unsigned int bucket_num = NUM_BUCKET;
 
 SEC("kprobe/func")
 int BPF_PROG(func_begin)
@@ -92,7 +102,8 @@ int BPF_PROG(func_end)
 	start = bpf_map_lookup_elem(&functime, &tid);
 	if (start) {
 		__s64 delta = bpf_ktime_get_ns() - *start;
-		__u32 key;
+		__u64 val = delta;
+		__u32 key = 0;
 		__u64 *hist;
 
 		bpf_map_delete_elem(&functime, &tid);
@@ -100,17 +111,46 @@ int BPF_PROG(func_end)
 		if (delta < 0)
 			return 0;
 
+		if (bucket_range != 0) {
+			val = delta / cmp_base;
+
+			if (min_latency > 0) {
+				if (val > min_latency)
+					val -= min_latency;
+				else
+					goto do_lookup;
+			}
+
+			// Less than 1 unit (ms or ns), or, in the future,
+			// than the min latency desired.
+			if (val > 0) { // 1st entry: [ 1 unit .. bucket_range units )
+				key = val / bucket_range + 1;
+				if (key >= bucket_num)
+					key = bucket_num - 1;
+			}
+
+			goto do_lookup;
+		}
 		// calculate index using delta
-		for (key = 0; key < (NUM_BUCKET - 1); key++) {
+		for (key = 0; key < (bucket_num - 1); key++) {
 			if (delta < (cmp_base << key))
 				break;
 		}
 
+do_lookup:
 		hist = bpf_map_lookup_elem(&latency, &key);
 		if (!hist)
 			return 0;
 
-		*hist += 1;
+		__sync_fetch_and_add(hist, 1);
+
+		__sync_fetch_and_add(&total, delta); // always in nsec
+		__sync_fetch_and_add(&count, 1);
+
+		if (delta > max)
+			max = delta;
+		if (delta < min)
+			min = delta;
 	}
 
 	return 0;
diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c
index 594da91965a2..73e32e063030 100644
--- a/tools/perf/util/bpf_skel/kwork_top.bpf.c
+++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c
@@ -18,7 +18,9 @@ enum kwork_class_type {
 };
 
 #define MAX_ENTRIES     102400
-#define MAX_NR_CPUS     2048
+#ifndef MAX_NR_CPUS
+#define MAX_NR_CPUS     4096
+#endif
 #define PF_KTHREAD      0x00200000
 #define MAX_COMMAND_LEN 16
 
diff --git a/tools/perf/util/bpf_skel/kwork_trace.bpf.c b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
index cbd79bc4b330..9ce9c8dddc4b 100644
--- a/tools/perf/util/bpf_skel/kwork_trace.bpf.c
+++ b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
@@ -80,7 +80,7 @@ static __always_inline int local_strncmp(const char *s1,
 
 	for (i = 0; i < sz; i++) {
 		ret = (unsigned char)s1[i] - (unsigned char)s2[i];
-		if (ret || !s1[i] || !s2[i])
+		if (ret || !s1[i])
 			break;
 	}
 
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 1069bda5d733..96e7d853b9ed 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -11,6 +11,12 @@
 /* for collect_lock_syms().  4096 was rejected by the verifier */
 #define MAX_CPUS  1024
 
+/* for collect_zone_lock().  It should be more than the actual zones. */
+#define MAX_ZONES  10
+
+/* for do_lock_delay().  Arbitrarily set to 1 million. */
+#define MAX_LOOP  (1U << 20)
+
 /* lock contention flags from include/trace/events/lock.h */
 #define LCB_F_SPIN	(1U << 0)
 #define LCB_F_READ	(1U << 1)
@@ -27,6 +33,38 @@ struct {
 	__uint(max_entries, MAX_ENTRIES);
 } stacks SEC(".maps");
 
+/* buffer for owner stacktrace */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u64));
+	__uint(max_entries, 1);
+} stack_buf SEC(".maps");
+
+/* a map for tracing owner stacktrace to owner stack id */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64)); // owner stacktrace
+	__uint(value_size, sizeof(__s32)); // owner stack id
+	__uint(max_entries, 1);
+} owner_stacks SEC(".maps");
+
+/* a map for tracing lock address to owner data */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64)); // lock address
+	__uint(value_size, sizeof(struct owner_tracing_data));
+	__uint(max_entries, 1);
+} owner_data SEC(".maps");
+
+/* a map for contention_key (stores owner stack id) to contention data */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct contention_key));
+	__uint(value_size, sizeof(struct contention_data));
+	__uint(max_entries, 1);
+} owner_stat SEC(".maps");
+
 /* maintain timestamp at the beginning of contention */
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
@@ -100,6 +138,27 @@ struct {
 	__uint(max_entries, 1);
 } cgroup_filter SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(long));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} slab_filter SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(long));
+	__uint(value_size, sizeof(struct slab_cache_data));
+	__uint(max_entries, 1);
+} slab_caches SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64));
+	__uint(value_size, sizeof(__u64));
+	__uint(max_entries, 1);
+} lock_delays SEC(".maps");
+
 struct rw_semaphore___old {
 	struct task_struct *owner;
 } __attribute__((preserve_access_index));
@@ -116,16 +175,21 @@ struct mm_struct___new {
 	struct rw_semaphore mmap_lock;
 } __attribute__((preserve_access_index));
 
+extern struct kmem_cache *bpf_get_kmem_cache(u64 addr) __ksym __weak;
+
 /* control flags */
 const volatile int has_cpu;
 const volatile int has_task;
 const volatile int has_type;
 const volatile int has_addr;
 const volatile int has_cgroup;
+const volatile int has_slab;
 const volatile int needs_callstack;
 const volatile int stack_skip;
 const volatile int lock_owner;
 const volatile int use_cgroup_v2;
+const volatile int max_stack;
+const volatile int lock_delay;
 
 /* determine the key of lock stat */
 const volatile int aggr_mode;
@@ -136,6 +200,8 @@ int perf_subsys_id = -1;
 
 __u64 end_ts;
 
+__u32 slab_cache_id;
+
 /* error stat */
 int task_fail;
 int stack_fail;
@@ -145,6 +211,9 @@ int data_fail;
 int task_map_full;
 int data_map_full;
 
+struct task_struct *bpf_task_from_pid(s32 pid) __ksym __weak;
+void bpf_task_release(struct task_struct *p) __ksym __weak;
+
 static inline __u64 get_current_cgroup_id(void)
 {
 	struct task_struct *task;
@@ -202,7 +271,7 @@ static inline int can_record(u64 *ctx)
 		__u64 addr = ctx[0];
 
 		ok = bpf_map_lookup_elem(&addr_filter, &addr);
-		if (!ok)
+		if (!ok && !has_slab)
 			return 0;
 	}
 
@@ -215,6 +284,17 @@ static inline int can_record(u64 *ctx)
 			return 0;
 	}
 
+	if (has_slab && bpf_get_kmem_cache) {
+		__u8 *ok;
+		__u64 addr = ctx[0];
+		long kmem_cache_addr;
+
+		kmem_cache_addr = (long)bpf_get_kmem_cache(addr);
+		ok = bpf_map_lookup_elem(&slab_filter, &kmem_cache_addr);
+		if (!ok)
+			return 0;
+	}
+
 	return 1;
 }
 
@@ -318,6 +398,35 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags)
 	return 0;
 }
 
+static inline long delay_callback(__u64 idx, void *arg)
+{
+	__u64 target = *(__u64 *)arg;
+
+	if (target <= bpf_ktime_get_ns())
+		return 1;
+
+	/* just to kill time */
+	(void)bpf_get_prandom_u32();
+
+	return 0;
+}
+
+static inline void do_lock_delay(__u64 duration)
+{
+	__u64 target = bpf_ktime_get_ns() + duration;
+
+	bpf_loop(MAX_LOOP, delay_callback, &target, /*flags=*/0);
+}
+
+static inline void check_lock_delay(__u64 lock)
+{
+	__u64 *delay;
+
+	delay = bpf_map_lookup_elem(&lock_delays, &lock);
+	if (delay)
+		do_lock_delay(*delay);
+}
+
 static inline struct tstamp_data *get_tstamp_elem(__u32 flags)
 {
 	__u32 pid;
@@ -357,6 +466,61 @@ static inline struct tstamp_data *get_tstamp_elem(__u32 flags)
 	return pelem;
 }
 
+static inline s32 get_owner_stack_id(u64 *stacktrace)
+{
+	s32 *id, new_id;
+	static s64 id_gen = 1;
+
+	id = bpf_map_lookup_elem(&owner_stacks, stacktrace);
+	if (id)
+		return *id;
+
+	new_id = (s32)__sync_fetch_and_add(&id_gen, 1);
+
+	bpf_map_update_elem(&owner_stacks, stacktrace, &new_id, BPF_NOEXIST);
+
+	id = bpf_map_lookup_elem(&owner_stacks, stacktrace);
+	if (id)
+		return *id;
+
+	return -1;
+}
+
+static inline void update_contention_data(struct contention_data *data, u64 duration, u32 count)
+{
+	__sync_fetch_and_add(&data->total_time, duration);
+	__sync_fetch_and_add(&data->count, count);
+
+	/* FIXME: need atomic operations */
+	if (data->max_time < duration)
+		data->max_time = duration;
+	if (data->min_time > duration)
+		data->min_time = duration;
+}
+
+static inline void update_owner_stat(u32 id, u64 duration, u32 flags)
+{
+	struct contention_key key = {
+		.stack_id = id,
+		.pid = 0,
+		.lock_addr_or_cgroup = 0,
+	};
+	struct contention_data *data = bpf_map_lookup_elem(&owner_stat, &key);
+
+	if (!data) {
+		struct contention_data first = {
+			.total_time = duration,
+			.max_time = duration,
+			.min_time = duration,
+			.count = 1,
+			.flags = flags,
+		};
+		bpf_map_update_elem(&owner_stat, &key, &first, BPF_NOEXIST);
+	} else {
+		update_contention_data(data, duration, 1);
+	}
+}
+
 SEC("tp_btf/contention_begin")
 int contention_begin(u64 *ctx)
 {
@@ -374,6 +538,72 @@ int contention_begin(u64 *ctx)
 	pelem->flags = (__u32)ctx[1];
 
 	if (needs_callstack) {
+		u32 i = 0;
+		u32 id = 0;
+		int owner_pid;
+		u64 *buf;
+		struct task_struct *task;
+		struct owner_tracing_data *otdata;
+
+		if (!lock_owner)
+			goto skip_owner;
+
+		task = get_lock_owner(pelem->lock, pelem->flags);
+		if (!task)
+			goto skip_owner;
+
+		owner_pid = BPF_CORE_READ(task, pid);
+
+		buf = bpf_map_lookup_elem(&stack_buf, &i);
+		if (!buf)
+			goto skip_owner;
+		for (i = 0; i < max_stack; i++)
+			buf[i] = 0x0;
+
+		if (!bpf_task_from_pid)
+			goto skip_owner;
+
+		task = bpf_task_from_pid(owner_pid);
+		if (!task)
+			goto skip_owner;
+
+		bpf_get_task_stack(task, buf, max_stack * sizeof(unsigned long), 0);
+		bpf_task_release(task);
+
+		otdata = bpf_map_lookup_elem(&owner_data, &pelem->lock);
+		id = get_owner_stack_id(buf);
+
+		/*
+		 * Contention just happens, or corner case `lock` is owned by process not
+		 * `owner_pid`. For the corner case we treat it as unexpected internal error and
+		 * just ignore the precvious tracing record.
+		 */
+		if (!otdata || otdata->pid != owner_pid) {
+			struct owner_tracing_data first = {
+				.pid = owner_pid,
+				.timestamp = pelem->timestamp,
+				.count = 1,
+				.stack_id = id,
+			};
+			bpf_map_update_elem(&owner_data, &pelem->lock, &first, BPF_ANY);
+		}
+		/* Contention is ongoing and new waiter joins */
+		else {
+			__sync_fetch_and_add(&otdata->count, 1);
+
+			/*
+			 * The owner is the same, but stacktrace might be changed. In this case we
+			 * store/update `owner_stat` based on current owner stack id.
+			 */
+			if (id != otdata->stack_id) {
+				update_owner_stat(id, pelem->timestamp - otdata->timestamp,
+						  pelem->flags);
+
+				otdata->timestamp = pelem->timestamp;
+				otdata->stack_id = id;
+			}
+		}
+skip_owner:
 		pelem->stack_id = bpf_get_stackid(ctx, &stacks,
 						  BPF_F_FAST_STACK_CMP | stack_skip);
 		if (pelem->stack_id < 0)
@@ -410,6 +640,7 @@ int contention_end(u64 *ctx)
 	struct tstamp_data *pelem;
 	struct contention_key key = {};
 	struct contention_data *data;
+	__u64 timestamp;
 	__u64 duration;
 	bool need_delete = false;
 
@@ -437,12 +668,88 @@ int contention_end(u64 *ctx)
 		need_delete = true;
 	}
 
-	duration = bpf_ktime_get_ns() - pelem->timestamp;
+	timestamp = bpf_ktime_get_ns();
+	duration = timestamp - pelem->timestamp;
 	if ((__s64)duration < 0) {
 		__sync_fetch_and_add(&time_fail, 1);
 		goto out;
 	}
 
+	if (needs_callstack && lock_owner) {
+		struct owner_tracing_data *otdata = bpf_map_lookup_elem(&owner_data, &pelem->lock);
+
+		if (!otdata)
+			goto skip_owner;
+
+		/* Update `owner_stat` */
+		update_owner_stat(otdata->stack_id, timestamp - otdata->timestamp, pelem->flags);
+
+		/* No contention is occurring, delete `lock` entry in `owner_data` */
+		if (otdata->count <= 1)
+			bpf_map_delete_elem(&owner_data, &pelem->lock);
+		/*
+		 * Contention is still ongoing, with a new owner (current task). `owner_data`
+		 * should be updated accordingly.
+		 */
+		else {
+			u32 i = 0;
+			s32 ret = (s32)ctx[1];
+			u64 *buf;
+
+			otdata->timestamp = timestamp;
+			__sync_fetch_and_add(&otdata->count, -1);
+
+			buf = bpf_map_lookup_elem(&stack_buf, &i);
+			if (!buf)
+				goto skip_owner;
+			for (i = 0; i < (u32)max_stack; i++)
+				buf[i] = 0x0;
+
+			/*
+			 * `ret` has the return code of the lock function.
+			 * If `ret` is negative, the current task terminates lock waiting without
+			 * acquiring it. Owner is not changed, but we still need to update the owner
+			 * stack.
+			 */
+			if (ret < 0) {
+				s32 id = 0;
+				struct task_struct *task;
+
+				if (!bpf_task_from_pid)
+					goto skip_owner;
+
+				task = bpf_task_from_pid(otdata->pid);
+				if (!task)
+					goto skip_owner;
+
+				bpf_get_task_stack(task, buf,
+						   max_stack * sizeof(unsigned long), 0);
+				bpf_task_release(task);
+
+				id = get_owner_stack_id(buf);
+
+				/*
+				 * If owner stack is changed, update owner stack id for this lock.
+				 */
+				if (id != otdata->stack_id)
+					otdata->stack_id = id;
+			}
+			/*
+			 * Otherwise, update tracing data with the current task, which is the new
+			 * owner.
+			 */
+			else {
+				otdata->pid = pid;
+				/*
+				 * We don't want to retrieve callstack here, since it is where the
+				 * current task acquires the lock and provides no additional
+				 * information. We simply assign -1 to invalidate it.
+				 */
+				otdata->stack_id = -1;
+			}
+		}
+	}
+skip_owner:
 	switch (aggr_mode) {
 	case LOCK_AGGR_CALLER:
 		key.stack_id = pelem->stack_id;
@@ -487,8 +794,28 @@ int contention_end(u64 *ctx)
 		};
 		int err;
 
-		if (aggr_mode == LOCK_AGGR_ADDR)
-			first.flags |= check_lock_type(pelem->lock, pelem->flags);
+		if (aggr_mode == LOCK_AGGR_ADDR) {
+			first.flags |= check_lock_type(pelem->lock,
+						       pelem->flags & LCB_F_TYPE_MASK);
+
+			/* Check if it's from a slab object */
+			if (bpf_get_kmem_cache) {
+				struct kmem_cache *s;
+				struct slab_cache_data *d;
+
+				s = bpf_get_kmem_cache(pelem->lock);
+				if (s != NULL) {
+					/*
+					 * Save the ID of the slab cache in the flags
+					 * (instead of full address) to reduce the
+					 * space in the contention_data.
+					 */
+					d = bpf_map_lookup_elem(&slab_caches, &s);
+					if (d != NULL)
+						first.flags |= d->id;
+				}
+			}
+		}
 
 		err = bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST);
 		if (err < 0) {
@@ -506,16 +833,12 @@ int contention_end(u64 *ctx)
 	}
 
 found:
-	__sync_fetch_and_add(&data->total_time, duration);
-	__sync_fetch_and_add(&data->count, 1);
-
-	/* FIXME: need atomic operations */
-	if (data->max_time < duration)
-		data->max_time = duration;
-	if (data->min_time > duration)
-		data->min_time = duration;
+	update_contention_data(data, duration, 1);
 
 out:
+	if (lock_delay)
+		check_lock_delay(pelem->lock);
+
 	pelem->lock = 0;
 	if (need_delete)
 		bpf_map_delete_elem(&tstamp, &pid);
@@ -524,6 +847,11 @@ out:
 
 extern struct rq runqueues __ksym;
 
+const volatile __u64 contig_page_data_addr;
+const volatile __u64 node_data_addr;
+const volatile int nr_nodes;
+const volatile int sizeof_zone;
+
 struct rq___old {
 	raw_spinlock_t lock;
 } __attribute__((preserve_access_index));
@@ -532,6 +860,59 @@ struct rq___new {
 	raw_spinlock_t __lock;
 } __attribute__((preserve_access_index));
 
+static void collect_zone_lock(void)
+{
+	__u64 nr_zones, zone_off;
+	__u64 lock_addr, lock_off;
+	__u32 lock_flag = LOCK_CLASS_ZONE_LOCK;
+
+	zone_off = offsetof(struct pglist_data, node_zones);
+	lock_off = offsetof(struct zone, lock);
+
+	if (contig_page_data_addr) {
+		struct pglist_data *contig_page_data;
+
+		contig_page_data = (void *)(long)contig_page_data_addr;
+		nr_zones = BPF_CORE_READ(contig_page_data, nr_zones);
+
+		for (int i = 0; i < MAX_ZONES; i++) {
+			__u64 zone_addr;
+
+			if (i >= nr_zones)
+				break;
+
+			zone_addr = contig_page_data_addr + (sizeof_zone * i) + zone_off;
+			lock_addr = zone_addr + lock_off;
+
+			bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY);
+		}
+	} else if (nr_nodes > 0) {
+		struct pglist_data **node_data = (void *)(long)node_data_addr;
+
+		for (int i = 0; i < nr_nodes; i++) {
+			struct pglist_data *pgdat = NULL;
+			int err;
+
+			err = bpf_core_read(&pgdat, sizeof(pgdat), &node_data[i]);
+			if (err < 0 || pgdat == NULL)
+				break;
+
+			nr_zones = BPF_CORE_READ(pgdat, nr_zones);
+			for (int k = 0; k < MAX_ZONES; k++) {
+				__u64 zone_addr;
+
+				if (k >= nr_zones)
+					break;
+
+				zone_addr = (__u64)(void *)pgdat + (sizeof_zone * k) + zone_off;
+				lock_addr = zone_addr + lock_off;
+
+				bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY);
+			}
+		}
+	}
+}
+
 SEC("raw_tp/bpf_test_finish")
 int BPF_PROG(collect_lock_syms)
 {
@@ -553,6 +934,9 @@ int BPF_PROG(collect_lock_syms)
 		lock_flag = LOCK_CLASS_RQLOCK;
 		bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY);
 	}
+
+	collect_zone_lock();
+
 	return 0;
 }
 
@@ -563,4 +947,43 @@ int BPF_PROG(end_timestamp)
 	return 0;
 }
 
+/*
+ * bpf_iter__kmem_cache added recently so old kernels don't have it in the
+ * vmlinux.h.  But we cannot add it here since it will cause a compiler error
+ * due to redefinition of the struct on later kernels.
+ *
+ * So it uses a CO-RE trick to access the member only if it has the type.
+ * This will support both old and new kernels without compiler errors.
+ */
+struct bpf_iter__kmem_cache___new {
+	struct kmem_cache *s;
+} __attribute__((preserve_access_index));
+
+SEC("iter/kmem_cache")
+int slab_cache_iter(void *ctx)
+{
+	struct kmem_cache *s = NULL;
+	struct slab_cache_data d;
+	const char *nameptr;
+
+	if (bpf_core_type_exists(struct bpf_iter__kmem_cache)) {
+		struct bpf_iter__kmem_cache___new *iter = ctx;
+
+		s = iter->s;
+	}
+
+	if (s == NULL)
+		return 0;
+
+	nameptr = s->name;
+	bpf_probe_read_kernel_str(d.name, sizeof(d.name), nameptr);
+
+	d.id = ++slab_cache_id << LCB_F_SLAB_ID_SHIFT;
+	if (d.id >= LCB_F_SLAB_ID_END)
+		return 0;
+
+	bpf_map_update_elem(&slab_caches, &s, &d, BPF_NOEXIST);
+	return 0;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h
index de12892f992f..28c5e5aced7f 100644
--- a/tools/perf/util/bpf_skel/lock_data.h
+++ b/tools/perf/util/bpf_skel/lock_data.h
@@ -3,6 +3,13 @@
 #ifndef UTIL_BPF_SKEL_LOCK_DATA_H
 #define UTIL_BPF_SKEL_LOCK_DATA_H
 
+struct owner_tracing_data {
+	u32 pid; // Who has the lock.
+	u32 count; // How many waiters for this lock.
+	u64 timestamp; // The time while the owner acquires lock and contention is going on.
+	s32 stack_id; // Identifier for `owner_stat`, which stores as value in `owner_stacks`
+};
+
 struct tstamp_data {
 	u64 timestamp;
 	u64 lock;
@@ -32,7 +39,15 @@ struct contention_task_data {
 #define LCD_F_MMAP_LOCK		(1U << 31)
 #define LCD_F_SIGHAND_LOCK	(1U << 30)
 
-#define LCB_F_MAX_FLAGS		(1U << 7)
+#define LCB_F_SLAB_ID_SHIFT	16
+#define LCB_F_SLAB_ID_START	(1U << 16)
+#define LCB_F_SLAB_ID_END	(1U << 26)
+#define LCB_F_SLAB_ID_MASK	0x03FF0000U
+
+#define LCB_F_TYPE_MAX		(1U << 7)
+#define LCB_F_TYPE_MASK		0x0000007FU
+
+#define SLAB_NAME_MAX  28
 
 struct contention_data {
 	u64 total_time;
@@ -52,6 +67,12 @@ enum lock_aggr_mode {
 enum lock_class_sym {
 	LOCK_CLASS_NONE,
 	LOCK_CLASS_RQLOCK,
+	LOCK_CLASS_ZONE_LOCK,
+};
+
+struct slab_cache_data {
+	u32 id;
+	char name[SLAB_NAME_MAX];
 };
 
 #endif /* UTIL_BPF_SKEL_LOCK_DATA_H */
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index c152116df72f..72763bb8d1de 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -18,10 +18,19 @@
 #define MAX_STACKS   32
 #define MAX_ENTRIES  102400
 
+#define MAX_CPUS  4096
+#define MAX_OFFCPU_LEN 37
+
+// We have a 'struct stack' in vmlinux.h when building with GEN_VMLINUX_H=1
+struct __stack {
+	u64 array[MAX_STACKS];
+};
+
 struct tstamp_data {
 	__u32 stack_id;
 	__u32 state;
 	__u64 timestamp;
+	struct __stack stack;
 };
 
 struct offcpu_key {
@@ -39,6 +48,24 @@ struct {
 	__uint(max_entries, MAX_ENTRIES);
 } stacks SEC(".maps");
 
+struct offcpu_data {
+	u64 array[MAX_OFFCPU_LEN];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, MAX_CPUS);
+} offcpu_output SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct offcpu_data));
+	__uint(max_entries, 1);
+} offcpu_payload SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
 	__uint(map_flags, BPF_F_NO_PREALLOC);
@@ -97,6 +124,8 @@ const volatile bool uses_cgroup_v1 = false;
 
 int perf_subsys_id = -1;
 
+__u64 offcpu_thresh_ns;
+
 /*
  * Old kernel used to call it task_struct->state and now it's '__state'.
  * Use BPF CO-RE "ignored suffix rule" to deal with it like below:
@@ -183,6 +212,47 @@ static inline int can_record(struct task_struct *t, int state)
 	return 1;
 }
 
+static inline int copy_stack(struct __stack *from, struct offcpu_data *to, int n)
+{
+	int len = 0;
+
+	for (int i = 0; i < MAX_STACKS && from->array[i]; ++i, ++len)
+		to->array[n + 2 + i] = from->array[i];
+
+	return len;
+}
+
+/**
+ * off_cpu_dump - dump off-cpu samples to ring buffer
+ * @data: payload for dumping off-cpu samples
+ * @key: off-cpu data
+ * @stack: stack trace of the task before being scheduled out
+ *
+ * If the threshold of off-cpu time is reached, acquire tid, period, callchain, and cgroup id
+ * information of the task, and dump it as a raw sample to perf ring buffer
+ */
+static int off_cpu_dump(void *ctx, struct offcpu_data *data, struct offcpu_key *key,
+			struct __stack *stack, __u64 delta)
+{
+	int n = 0, len = 0;
+
+	data->array[n++] = (u64)key->tgid << 32 | key->pid;
+	data->array[n++] = delta;
+
+	/* data->array[n] is callchain->nr (updated later) */
+	data->array[n + 1] = PERF_CONTEXT_USER;
+	data->array[n + 2] = 0;
+	len = copy_stack(stack, data, n);
+
+	/* update length of callchain */
+	data->array[n] = len + 1;
+	n += len + 2;
+
+	data->array[n++] = key->cgroup_id;
+
+	return bpf_perf_event_output(ctx, &offcpu_output, BPF_F_CURRENT_CPU, data, n * sizeof(u64));
+}
+
 static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 			struct task_struct *next, int state)
 {
@@ -207,6 +277,16 @@ static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
 	pelem->state = state;
 	pelem->stack_id = stack_id;
 
+	/*
+	 * If stacks are successfully collected by bpf_get_stackid(), collect them once more
+	 * in task_storage for direct off-cpu sample dumping
+	 */
+	if (stack_id > 0 && bpf_get_stack(ctx, &pelem->stack, MAX_STACKS * sizeof(u64), BPF_F_USER_STACK)) {
+		/*
+		 * This empty if block is used to avoid 'result unused warning' from bpf_get_stack().
+		 * If the collection fails, continue with the logic for the next task.
+		 */
+	}
 next:
 	pelem = bpf_task_storage_get(&tstamp, next, NULL, 0);
 
@@ -221,11 +301,19 @@ next:
 		__u64 delta = ts - pelem->timestamp;
 		__u64 *total;
 
-		total = bpf_map_lookup_elem(&off_cpu, &key);
-		if (total)
-			*total += delta;
-		else
-			bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY);
+		if (delta >= offcpu_thresh_ns) {
+			int zero = 0;
+			struct offcpu_data *data = bpf_map_lookup_elem(&offcpu_payload, &zero);
+
+			if (data)
+				off_cpu_dump(ctx, data, &key, &pelem->stack, delta);
+		} else {
+			total = bpf_map_lookup_elem(&off_cpu, &key);
+			if (total)
+				*total += delta;
+			else
+				bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY);
+		}
 
 		/* prevent to reuse the timestamp later */
 		pelem->timestamp = 0;
diff --git a/tools/perf/util/bpf_skel/syscall_summary.bpf.c b/tools/perf/util/bpf_skel/syscall_summary.bpf.c
new file mode 100644
index 000000000000..1bcd066a5199
--- /dev/null
+++ b/tools/perf/util/bpf_skel/syscall_summary.bpf.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Trace raw_syscalls tracepoints to collect system call statistics.
+ */
+
+#include "vmlinux.h"
+#include "syscall_summary.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+/* This is to calculate a delta between sys-enter and sys-exit for each thread */
+struct syscall_trace {
+	int nr; /* syscall number is only available at sys-enter */
+	int unused;
+	u64 timestamp;
+};
+
+#define MAX_ENTRIES	(128 * 1024)
+
+struct syscall_trace_map {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, int); /* tid */
+	__type(value, struct syscall_trace);
+	__uint(max_entries, MAX_ENTRIES);
+} syscall_trace_map SEC(".maps");
+
+struct syscall_stats_map {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct syscall_key);
+	__type(value, struct syscall_stats);
+	__uint(max_entries, MAX_ENTRIES);
+} syscall_stats_map SEC(".maps");
+
+int enabled; /* controlled from userspace */
+
+const volatile enum syscall_aggr_mode aggr_mode;
+const volatile int use_cgroup_v2;
+
+int perf_subsys_id = -1;
+
+static inline __u64 get_current_cgroup_id(void)
+{
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	if (use_cgroup_v2)
+		return bpf_get_current_cgroup_id();
+
+	task = bpf_get_current_task_btf();
+
+	if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+		perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+						     perf_event_cgrp_id);
+#else
+		perf_subsys_id = perf_event_cgrp_id;
+#endif
+	}
+
+	cgrp = BPF_CORE_READ(task, cgroups, subsys[perf_subsys_id], cgroup);
+	return BPF_CORE_READ(cgrp, kn, id);
+}
+
+static void update_stats(int cpu_or_tid, u64 cgroup_id, int nr, s64 duration,
+			 long ret)
+{
+	struct syscall_key key = {
+		.cpu_or_tid = cpu_or_tid,
+		.cgroup = cgroup_id,
+		.nr = nr,
+	};
+	struct syscall_stats *stats;
+
+	stats = bpf_map_lookup_elem(&syscall_stats_map, &key);
+	if (stats == NULL) {
+		struct syscall_stats zero = {};
+
+		bpf_map_update_elem(&syscall_stats_map, &key, &zero, BPF_NOEXIST);
+		stats = bpf_map_lookup_elem(&syscall_stats_map, &key);
+		if (stats == NULL)
+			return;
+	}
+
+	__sync_fetch_and_add(&stats->count, 1);
+	if (ret < 0)
+		__sync_fetch_and_add(&stats->error, 1);
+
+	if (duration > 0) {
+		__sync_fetch_and_add(&stats->total_time, duration);
+		__sync_fetch_and_add(&stats->squared_sum, duration * duration);
+		if (stats->max_time < duration)
+			stats->max_time = duration;
+		if (stats->min_time > duration || stats->min_time == 0)
+			stats->min_time = duration;
+	}
+
+	return;
+}
+
+SEC("tp_btf/sys_enter")
+int sys_enter(u64 *ctx)
+{
+	int tid;
+	struct syscall_trace st;
+
+	if (!enabled)
+		return 0;
+
+	st.nr = ctx[1]; /* syscall number */
+	st.unused = 0;
+	st.timestamp = bpf_ktime_get_ns();
+
+	tid = bpf_get_current_pid_tgid();
+	bpf_map_update_elem(&syscall_trace_map, &tid, &st, BPF_ANY);
+
+	return 0;
+}
+
+SEC("tp_btf/sys_exit")
+int sys_exit(u64 *ctx)
+{
+	int tid;
+	int key = 0;
+	u64 cgroup = 0;
+	long ret = ctx[1]; /* return value of the syscall */
+	struct syscall_trace *st;
+	s64 delta;
+
+	if (!enabled)
+		return 0;
+
+	tid = bpf_get_current_pid_tgid();
+	st = bpf_map_lookup_elem(&syscall_trace_map, &tid);
+	if (st == NULL)
+		return 0;
+
+	if (aggr_mode == SYSCALL_AGGR_THREAD)
+		key = tid;
+	else if (aggr_mode == SYSCALL_AGGR_CGROUP)
+		cgroup = get_current_cgroup_id();
+	else
+		key = bpf_get_smp_processor_id();
+
+	delta = bpf_ktime_get_ns() - st->timestamp;
+	update_stats(key, cgroup, st->nr, delta, ret);
+
+	bpf_map_delete_elem(&syscall_trace_map, &tid);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/perf/util/bpf_skel/syscall_summary.h b/tools/perf/util/bpf_skel/syscall_summary.h
new file mode 100644
index 000000000000..72ccccb45925
--- /dev/null
+++ b/tools/perf/util/bpf_skel/syscall_summary.h
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Data structures shared between BPF and tools. */
+#ifndef UTIL_BPF_SKEL_SYSCALL_SUMMARY_H
+#define UTIL_BPF_SKEL_SYSCALL_SUMMARY_H
+
+enum syscall_aggr_mode {
+	SYSCALL_AGGR_THREAD,
+	SYSCALL_AGGR_CPU,
+	SYSCALL_AGGR_CGROUP,
+};
+
+struct syscall_key {
+	u64 cgroup;
+	int cpu_or_tid;
+	int nr;
+};
+
+struct syscall_stats {
+	u64 total_time;
+	u64 squared_sum;
+	u64 max_time;
+	u64 min_time;
+	u32 count;
+	u32 error;
+};
+
+#endif /* UTIL_BPF_SKEL_SYSCALL_SUMMARY_H */
diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
index 4dcad7b682bd..a59ce912be18 100644
--- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
+++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
@@ -195,4 +195,21 @@ struct bpf_perf_event_data_kern {
  */
 struct rq {};
 
+struct kmem_cache {
+	const char *name;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__kmem_cache {
+	struct kmem_cache *s;
+} __attribute__((preserve_access_index));
+
+struct zone {
+	spinlock_t lock;
+} __attribute__((preserve_access_index));
+
+struct pglist_data {
+	struct zone node_zones[6]; /* value for all possible config */
+	int nr_zones;
+} __attribute__((preserve_access_index));
+
 #endif // __VMLINUX_H