It is to unify map flags checking for lookup, update, lookup_batch and
update_batch.

Therefore, it will be convenient to check BPF_F_CPU flag in this helper
function for them in next patch.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 kernel/bpf/syscall.c | 45 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 23 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0fbfa8532c392..19f7f5de5e7dc 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1654,6 +1654,17 @@ static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size)
 	return NULL;
 }
 
+static int check_map_flags(struct bpf_map *map, u64 flags, bool check_flag)
+{
+	if (check_flag && (flags & ~BPF_F_LOCK))
+		return -EINVAL;
+
+	if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
+		return -EINVAL;
+
+	return 0;
+}
+
 /* last field in 'union bpf_attr' used by this command */
 #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags
 
@@ -1669,9 +1680,6 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
 		return -EINVAL;
 
-	if (attr->flags & ~BPF_F_LOCK)
-		return -EINVAL;
-
 	CLASS(fd, f)(attr->map_fd);
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
@@ -1679,9 +1687,9 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ))
 		return -EPERM;
 
-	if ((attr->flags & BPF_F_LOCK) &&
-	    !btf_record_has_field(map->record, BPF_SPIN_LOCK))
-		return -EINVAL;
+	err = check_map_flags(map, attr->flags, true);
+	if (err)
+		return err;
 
 	key = __bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key))
@@ -1744,11 +1752,9 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 		goto err_put;
 	}
 
-	if ((attr->flags & BPF_F_LOCK) &&
-	    !btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
-		err = -EINVAL;
+	err = check_map_flags(map, attr->flags, false);
+	if (err)
 		goto err_put;
-	}
 
 	key = ___bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
@@ -1952,13 +1958,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 	void *key, *value;
 	int err = 0;
 
-	if (attr->batch.elem_flags & ~BPF_F_LOCK)
-		return -EINVAL;
-
-	if ((attr->batch.elem_flags & BPF_F_LOCK) &&
-	    !btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
-		return -EINVAL;
-	}
+	err = check_map_flags(map, attr->batch.elem_flags, true);
+	if (err)
+		return err;
 
 	value_size = bpf_map_value_size(map);
 
@@ -2015,12 +2017,9 @@ int generic_map_lookup_batch(struct bpf_map *map,
 	u32 value_size, cp, max_count;
 	int err;
 
-	if (attr->batch.elem_flags & ~BPF_F_LOCK)
-		return -EINVAL;
-
-	if ((attr->batch.elem_flags & BPF_F_LOCK) &&
-	    !btf_record_has_field(map->record, BPF_SPIN_LOCK))
-		return -EINVAL;
+	err = check_map_flags(map, attr->batch.elem_flags, true);
+	if (err)
+		return err;
 
 	value_size = bpf_map_value_size(map);
 
-- 
2.50.1

Introduce support for the BPF_F_ALL_CPUS flag in percpu_array maps to
allow updating values for all CPUs with a single value.

Introduce support for the BPF_F_CPU flag in percpu_array maps to allow
updating value for specified CPU.

This enhancement enables:

* Efficient update values across all CPUs with a single value when
  BPF_F_ALL_CPUS is set for update_elem and update_batch APIs.
* Targeted update or lookup for a specified CPU when BPF_F_CPU is set.

The BPF_F_CPU flag is passed via:

* map_flags of lookup_elem and update_elem APIs along with embedded cpu
  field.
* elem_flags of lookup_batch and update_batch APIs along with embedded
  cpu field.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 include/linux/bpf.h            |  3 +-
 include/uapi/linux/bpf.h       |  2 ++
 kernel/bpf/arraymap.c          | 56 ++++++++++++++++++++++++++--------
 kernel/bpf/syscall.c           | 27 ++++++++++------
 tools/include/uapi/linux/bpf.h |  2 ++
 5 files changed, 67 insertions(+), 23 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8f6e87f0f3a89..b2191b1e455a6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2697,7 +2697,8 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env,
 				   struct bpf_func_state *callee);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
-int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value,
+			  u64 flags);
 int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 			   u64 flags);
 int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 233de8677382e..be1fdc5042744 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1372,6 +1372,8 @@ enum {
 	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
 	BPF_EXIST	= 2, /* update existing element */
 	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
+	BPF_F_CPU	= 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
+	BPF_F_ALL_CPUS	= 16, /* update value across all CPUs for percpu maps */
 };
 
 /* flags for BPF_MAP_CREATE command */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 3d080916faf97..1efa730105e24 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -295,17 +295,24 @@ static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key,
 	return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu);
 }
 
-int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	u32 index = *(u32 *)key;
 	void __percpu *pptr;
-	int cpu, off = 0;
-	u32 size;
+	u32 size, cpu;
+	int off = 0;
 
 	if (unlikely(index >= array->map.max_entries))
 		return -ENOENT;
 
+	if (unlikely((u32)flags & ~BPF_F_CPU))
+		return -EINVAL;
+
+	cpu = flags >> 32;
+	if (unlikely((flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
+		return -ERANGE;
+
 	/* per_cpu areas are zero-filled and bpf programs can only
 	 * access 'value_size' of them, so copying rounded areas
 	 * will not leak any kernel data
@@ -313,10 +320,15 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
 	size = array->elem_size;
 	rcu_read_lock();
 	pptr = array->pptrs[index & array->index_mask];
-	for_each_possible_cpu(cpu) {
-		copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
-		check_and_init_map_value(map, value + off);
-		off += size;
+	if (flags & BPF_F_CPU) {
+		copy_map_value_long(map, value, per_cpu_ptr(pptr, cpu));
+		check_and_init_map_value(map, value);
+	} else {
+		for_each_possible_cpu(cpu) {
+			copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
+			check_and_init_map_value(map, value + off);
+			off += size;
+		}
 	}
 	rcu_read_unlock();
 	return 0;
@@ -385,14 +397,22 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 			    u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	const u64 cpu_flags = BPF_F_CPU | BPF_F_ALL_CPUS;
 	u32 index = *(u32 *)key;
 	void __percpu *pptr;
-	int cpu, off = 0;
-	u32 size;
+	u32 size, cpu;
+	int off = 0;
 
-	if (unlikely(map_flags > BPF_EXIST))
+	if (unlikely((u32)map_flags > BPF_F_ALL_CPUS))
 		/* unknown flags */
 		return -EINVAL;
+	if (unlikely((map_flags & cpu_flags) == cpu_flags))
+		return -EINVAL;
+
+	cpu = map_flags >> 32;
+	if (unlikely((map_flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
+		/* invalid cpu */
+		return -ERANGE;
 
 	if (unlikely(index >= array->map.max_entries))
 		/* all elements were pre-allocated, cannot insert a new one */
@@ -411,10 +431,20 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 	size = array->elem_size;
 	rcu_read_lock();
 	pptr = array->pptrs[index & array->index_mask];
-	for_each_possible_cpu(cpu) {
-		copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
+	if (map_flags & BPF_F_CPU) {
+		copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value);
 		bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
-		off += size;
+	} else {
+		for_each_possible_cpu(cpu) {
+			copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off);
+			/* same user-provided value is used if
+			 * BPF_F_ALL_CPUS is specified, otherwise value is
+			 * an array of per-cpu values.
+			 */
+			if (!(map_flags & BPF_F_ALL_CPUS))
+				off += size;
+			bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
+		}
 	}
 	rcu_read_unlock();
 	return 0;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 19f7f5de5e7dc..6251ac9bc7e42 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -131,9 +131,11 @@ bool bpf_map_write_active(const struct bpf_map *map)
 	return atomic64_read(&map->writecnt) != 0;
 }
 
-static u32 bpf_map_value_size(const struct bpf_map *map)
+static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags)
 {
-	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY && (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)))
+		return round_up(map->value_size, 8);
+	else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
 	    map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
@@ -314,7 +316,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
-		err = bpf_percpu_array_copy(map, key, value);
+		err = bpf_percpu_array_copy(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
 		err = bpf_percpu_cgroup_storage_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
@@ -1656,12 +1658,19 @@ static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size)
 
 static int check_map_flags(struct bpf_map *map, u64 flags, bool check_flag)
 {
-	if (check_flag && (flags & ~BPF_F_LOCK))
+	if (check_flag && ((u32)flags & ~(BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS)))
 		return -EINVAL;
 
 	if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
 		return -EINVAL;
 
+	if (!(flags & BPF_F_CPU) && flags >> 32)
+		return -EINVAL;
+
+	if ((flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) &&
+		map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -1695,7 +1704,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (IS_ERR(key))
 		return PTR_ERR(key);
 
-	value_size = bpf_map_value_size(map);
+	value_size = bpf_map_value_size(map, attr->flags);
 
 	err = -ENOMEM;
 	value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN);
@@ -1762,7 +1771,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 		goto err_put;
 	}
 
-	value_size = bpf_map_value_size(map);
+	value_size = bpf_map_value_size(map, attr->flags);
 	value = kvmemdup_bpfptr(uvalue, value_size);
 	if (IS_ERR(value)) {
 		err = PTR_ERR(value);
@@ -1962,7 +1971,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 	if (err)
 		return err;
 
-	value_size = bpf_map_value_size(map);
+	value_size = bpf_map_value_size(map, attr->batch.elem_flags);
 
 	max_count = attr->batch.count;
 	if (!max_count)
@@ -2021,7 +2030,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
 	if (err)
 		return err;
 
-	value_size = bpf_map_value_size(map);
+	value_size = bpf_map_value_size(map, attr->batch.elem_flags);
 
 	max_count = attr->batch.count;
 	if (!max_count)
@@ -2143,7 +2152,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
-	value_size = bpf_map_value_size(map);
+	value_size = bpf_map_value_size(map, 0);
 
 	err = -ENOMEM;
 	value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 233de8677382e..be1fdc5042744 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1372,6 +1372,8 @@ enum {
 	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
 	BPF_EXIST	= 2, /* update existing element */
 	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
+	BPF_F_CPU	= 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
+	BPF_F_ALL_CPUS	= 16, /* update value across all CPUs for percpu maps */
 };
 
 /* flags for BPF_MAP_CREATE command */
-- 
2.50.1

Introduce BPF_F_ALL_CPUS flag support for percpu_hash and lru_percpu_hash
maps to allow updating values for all CPUs with a single value.

Introduce BPF_F_CPU flag support for percpu_hash and lru_percpu_hash
maps to allow updating value for specified CPU.

This enhancement enables:

* Efficient update values across all CPUs with a single value when
  BPF_F_ALL_CPUS is set for update_elem and update_batch APIs.
* Targeted update or lookup for a specified CPU when BPF_F_CPU is set.

The BPF_F_CPU flag is passed via:

* map_flags of lookup_elem and update_elem APIs along with embedded cpu
  field.
* elem_flags of lookup_batch and update_batch APIs along with embedded
  cpu field.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 include/linux/bpf.h   |  54 +++++++++++++++++++-
 kernel/bpf/arraymap.c |  29 ++++-------
 kernel/bpf/hashtab.c  | 111 +++++++++++++++++++++++++++++-------------
 kernel/bpf/syscall.c  |  30 +++---------
 4 files changed, 147 insertions(+), 77 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b2191b1e455a6..dc715eef9cbf4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2696,7 +2696,7 @@ int map_set_for_each_callback_args(struct bpf_verifier_env *env,
 				   struct bpf_func_state *caller,
 				   struct bpf_func_state *callee);
 
-int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value, u64 flags);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value,
 			  u64 flags);
 int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
@@ -3710,4 +3710,56 @@ int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char *
 			   const char **linep, int *nump);
 struct bpf_prog *bpf_prog_find_from_stack(void);
 
+static inline int bpf_map_check_cpu_flags(u64 flags, bool check_all_cpus)
+{
+	const u64 cpu_flags = BPF_F_CPU | BPF_F_ALL_CPUS;
+	u32 cpu;
+
+	if (check_all_cpus) {
+		if (unlikely((u32)flags > BPF_F_ALL_CPUS))
+			/* unknown flags */
+			return -EINVAL;
+		if (unlikely((flags & cpu_flags) == cpu_flags))
+			return -EINVAL;
+	} else {
+		if (unlikely((u32)flags & ~BPF_F_CPU))
+			return -EINVAL;
+	}
+
+	cpu = flags >> 32;
+	if (unlikely((flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
+		return -ERANGE;
+
+	return 0;
+}
+
+static inline bool bpf_map_support_cpu_flags(enum bpf_map_type map_type)
+{
+	switch (map_type) {
+	case BPF_MAP_TYPE_PERCPU_ARRAY:
+	case BPF_MAP_TYPE_PERCPU_HASH:
+	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline int bpf_map_check_flags(struct bpf_map *map, u64 flags, bool check_flag)
+{
+	if (check_flag && ((u32)flags & ~(BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS)))
+		return -EINVAL;
+
+	if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
+		return -EINVAL;
+
+	if (!(flags & BPF_F_CPU) && flags >> 32)
+		return -EINVAL;
+
+	if ((flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) && !bpf_map_support_cpu_flags(map->map_type))
+		return -EINVAL;
+
+	return 0;
+}
+
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1efa730105e24..f7646bcabb3c8 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -300,18 +300,15 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 flags
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	u32 index = *(u32 *)key;
 	void __percpu *pptr;
+	int off = 0, err;
 	u32 size, cpu;
-	int off = 0;
 
 	if (unlikely(index >= array->map.max_entries))
 		return -ENOENT;
 
-	if (unlikely((u32)flags & ~BPF_F_CPU))
-		return -EINVAL;
-
-	cpu = flags >> 32;
-	if (unlikely((flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
-		return -ERANGE;
+	err = bpf_map_check_cpu_flags(flags, false);
+	if (unlikely(err))
+		return err;
 
 	/* per_cpu areas are zero-filled and bpf programs can only
 	 * access 'value_size' of them, so copying rounded areas
@@ -321,6 +318,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 flags
 	rcu_read_lock();
 	pptr = array->pptrs[index & array->index_mask];
 	if (flags & BPF_F_CPU) {
+		cpu = flags >> 32;
 		copy_map_value_long(map, value, per_cpu_ptr(pptr, cpu));
 		check_and_init_map_value(map, value);
 	} else {
@@ -397,22 +395,14 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 			    u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	const u64 cpu_flags = BPF_F_CPU | BPF_F_ALL_CPUS;
 	u32 index = *(u32 *)key;
 	void __percpu *pptr;
+	int off = 0, err;
 	u32 size, cpu;
-	int off = 0;
-
-	if (unlikely((u32)map_flags > BPF_F_ALL_CPUS))
-		/* unknown flags */
-		return -EINVAL;
-	if (unlikely((map_flags & cpu_flags) == cpu_flags))
-		return -EINVAL;
 
-	cpu = map_flags >> 32;
-	if (unlikely((map_flags & BPF_F_CPU) && cpu >= num_possible_cpus()))
-		/* invalid cpu */
-		return -ERANGE;
+	err = bpf_map_check_cpu_flags(map_flags, true);
+	if (unlikely(err))
+		return err;
 
 	if (unlikely(index >= array->map.max_entries))
 		/* all elements were pre-allocated, cannot insert a new one */
@@ -432,6 +422,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 	rcu_read_lock();
 	pptr = array->pptrs[index & array->index_mask];
 	if (map_flags & BPF_F_CPU) {
+		cpu = map_flags >> 32;
 		copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value);
 		bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu));
 	} else {
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 71f9931ac64cd..34a35cdade425 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -937,24 +937,39 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 }
 
 static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
-			    void *value, bool onallcpus)
+			    void *value, bool onallcpus, u64 map_flags)
 {
+	int cpu = map_flags & BPF_F_CPU ? map_flags >> 32 : 0;
+	int current_cpu = raw_smp_processor_id();
+
 	if (!onallcpus) {
 		/* copy true value_size bytes */
-		copy_map_value(&htab->map, this_cpu_ptr(pptr), value);
+		copy_map_value(&htab->map, (map_flags & BPF_F_CPU) && cpu != current_cpu ?
+			       per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), value);
 	} else {
 		u32 size = round_up(htab->map.value_size, 8);
-		int off = 0, cpu;
+		int off = 0;
+
+		if (map_flags & BPF_F_CPU) {
+			copy_map_value_long(&htab->map, cpu != current_cpu ?
+					    per_cpu_ptr(pptr, cpu) : this_cpu_ptr(pptr), value);
+			return;
+		}
 
 		for_each_possible_cpu(cpu) {
 			copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value + off);
-			off += size;
+			/* same user-provided value is used if
+			 * BPF_F_ALL_CPUS is specified, otherwise value is
+			 * an array of per-cpu values.
+			 */
+			if (!(map_flags & BPF_F_ALL_CPUS))
+				off += size;
 		}
 	}
 }
 
 static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
-			    void *value, bool onallcpus)
+			    void *value, bool onallcpus, u64 map_flags)
 {
 	/* When not setting the initial value on all cpus, zero-fill element
 	 * values for other cpus. Otherwise, bpf program has no way to ensure
@@ -972,7 +987,7 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
 				zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu));
 		}
 	} else {
-		pcpu_copy_value(htab, pptr, value, onallcpus);
+		pcpu_copy_value(htab, pptr, value, onallcpus, map_flags);
 	}
 }
 
@@ -984,7 +999,7 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
 static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 					 void *value, u32 key_size, u32 hash,
 					 bool percpu, bool onallcpus,
-					 struct htab_elem *old_elem)
+					 struct htab_elem *old_elem, u64 map_flags)
 {
 	u32 size = htab->map.value_size;
 	bool prealloc = htab_is_prealloc(htab);
@@ -1042,7 +1057,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			pptr = *(void __percpu **)ptr;
 		}
 
-		pcpu_init_value(htab, pptr, value, onallcpus);
+		pcpu_init_value(htab, pptr, value, onallcpus, map_flags);
 
 		if (!prealloc)
 			htab_elem_set_ptr(l_new, key_size, pptr);
@@ -1147,7 +1162,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	}
 
 	l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
-				l_old);
+				l_old, map_flags);
 	if (IS_ERR(l_new)) {
 		/* all pre-allocated elements are in use or memory exhausted */
 		ret = PTR_ERR(l_new);
@@ -1263,9 +1278,15 @@ static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
 	u32 key_size, hash;
 	int ret;
 
-	if (unlikely(map_flags > BPF_EXIST))
-		/* unknown flags */
-		return -EINVAL;
+	if (percpu) {
+		ret = bpf_map_check_cpu_flags(map_flags, true);
+		if (unlikely(ret))
+			return ret;
+	} else {
+		if (unlikely(map_flags > BPF_EXIST))
+			/* unknown flags */
+			return -EINVAL;
+	}
 
 	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
 		     !rcu_read_lock_bh_held());
@@ -1291,7 +1312,7 @@ static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
 		/* Update value in-place */
 		if (percpu) {
 			pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
-					value, onallcpus);
+					value, onallcpus, map_flags);
 		} else {
 			void **inner_map_pptr = htab_elem_value(l_old, key_size);
 
@@ -1300,7 +1321,7 @@ static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
 		}
 	} else {
 		l_new = alloc_htab_elem(htab, key, value, key_size,
-					hash, percpu, onallcpus, NULL);
+					hash, percpu, onallcpus, NULL, map_flags);
 		if (IS_ERR(l_new)) {
 			ret = PTR_ERR(l_new);
 			goto err;
@@ -1326,9 +1347,9 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 	u32 key_size, hash;
 	int ret;
 
-	if (unlikely(map_flags > BPF_EXIST))
-		/* unknown flags */
-		return -EINVAL;
+	ret = bpf_map_check_cpu_flags(map_flags, true);
+	if (unlikely(ret))
+		return ret;
 
 	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
 		     !rcu_read_lock_bh_held());
@@ -1366,10 +1387,10 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 
 		/* per-cpu hash map can update value in-place */
 		pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
-				value, onallcpus);
+				value, onallcpus, map_flags);
 	} else {
 		pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size),
-				value, onallcpus);
+				value, onallcpus, map_flags);
 		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 		l_new = NULL;
 	}
@@ -1698,9 +1719,16 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 	int ret = 0;
 
 	elem_map_flags = attr->batch.elem_flags;
-	if ((elem_map_flags & ~BPF_F_LOCK) ||
-	    ((elem_map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)))
-		return -EINVAL;
+	if (!do_delete && is_percpu) {
+		ret = bpf_map_check_flags(map, elem_map_flags, false);
+		if (ret)
+			return ret;
+	} else {
+		if ((elem_map_flags & ~BPF_F_LOCK) ||
+		    ((elem_map_flags & BPF_F_LOCK) &&
+		     !btf_record_has_field(map->record, BPF_SPIN_LOCK)))
+			return -EINVAL;
+	}
 
 	map_flags = attr->batch.flags;
 	if (map_flags)
@@ -1806,10 +1834,17 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 			void __percpu *pptr;
 
 			pptr = htab_elem_get_ptr(l, map->key_size);
-			for_each_possible_cpu(cpu) {
-				copy_map_value_long(&htab->map, dst_val + off, per_cpu_ptr(pptr, cpu));
-				check_and_init_map_value(&htab->map, dst_val + off);
-				off += size;
+			if (!do_delete && (elem_map_flags & BPF_F_CPU)) {
+				cpu = elem_map_flags >> 32;
+				copy_map_value_long(&htab->map, dst_val, per_cpu_ptr(pptr, cpu));
+				check_and_init_map_value(&htab->map, dst_val);
+			} else {
+				for_each_possible_cpu(cpu) {
+					copy_map_value_long(&htab->map, dst_val + off,
+							    per_cpu_ptr(pptr, cpu));
+					check_and_init_map_value(&htab->map, dst_val + off);
+					off += size;
+				}
 			}
 		} else {
 			value = htab_elem_value(l, key_size);
@@ -2365,14 +2400,18 @@ static void *htab_lru_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *k
 	return NULL;
 }
 
-int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value, u64 map_flags)
 {
+	int ret, cpu, off = 0;
 	struct htab_elem *l;
 	void __percpu *pptr;
-	int ret = -ENOENT;
-	int cpu, off = 0;
 	u32 size;
 
+	ret = bpf_map_check_cpu_flags(map_flags, false);
+	if (unlikely(ret))
+		return ret;
+	ret = -ENOENT;
+
 	/* per_cpu areas are zero-filled and bpf programs can only
 	 * access 'value_size' of them, so copying rounded areas
 	 * will not leak any kernel data
@@ -2386,10 +2425,16 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
 	 * eviction heuristics when user space does a map walk.
 	 */
 	pptr = htab_elem_get_ptr(l, map->key_size);
-	for_each_possible_cpu(cpu) {
-		copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
-		check_and_init_map_value(map, value + off);
-		off += size;
+	if (map_flags & BPF_F_CPU) {
+		cpu = map_flags >> 32;
+		copy_map_value_long(map, value, per_cpu_ptr(pptr, cpu));
+		check_and_init_map_value(map, value);
+	} else {
+		for_each_possible_cpu(cpu) {
+			copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
+			check_and_init_map_value(map, value + off);
+			off += size;
+		}
 	}
 	ret = 0;
 out:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6251ac9bc7e42..430f013f38f06 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -133,7 +133,7 @@ bool bpf_map_write_active(const struct bpf_map *map)
 
 static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags)
 {
-	if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY && (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)))
+	if (bpf_map_support_cpu_flags(map->map_type) && (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)))
 		return round_up(map->value_size, 8);
 	else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
@@ -314,7 +314,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	bpf_disable_instrumentation();
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
-		err = bpf_percpu_hash_copy(map, key, value);
+		err = bpf_percpu_hash_copy(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_copy(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
@@ -1656,24 +1656,6 @@ static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size)
 	return NULL;
 }
 
-static int check_map_flags(struct bpf_map *map, u64 flags, bool check_flag)
-{
-	if (check_flag && ((u32)flags & ~(BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS)))
-		return -EINVAL;
-
-	if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
-		return -EINVAL;
-
-	if (!(flags & BPF_F_CPU) && flags >> 32)
-		return -EINVAL;
-
-	if ((flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) &&
-		map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY)
-		return -EINVAL;
-
-	return 0;
-}
-
 /* last field in 'union bpf_attr' used by this command */
 #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags
 
@@ -1696,7 +1678,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ))
 		return -EPERM;
 
-	err = check_map_flags(map, attr->flags, true);
+	err = bpf_map_check_flags(map, attr->flags, true);
 	if (err)
 		return err;
 
@@ -1761,7 +1743,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 		goto err_put;
 	}
 
-	err = check_map_flags(map, attr->flags, false);
+	err = bpf_map_check_flags(map, attr->flags, false);
 	if (err)
 		goto err_put;
 
@@ -1967,7 +1949,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 	void *key, *value;
 	int err = 0;
 
-	err = check_map_flags(map, attr->batch.elem_flags, true);
+	err = bpf_map_check_flags(map, attr->batch.elem_flags, true);
 	if (err)
 		return err;
 
@@ -2026,7 +2008,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
 	u32 value_size, cp, max_count;
 	int err;
 
-	err = check_map_flags(map, attr->batch.elem_flags, true);
+	err = bpf_map_check_flags(map, attr->batch.elem_flags, true);
 	if (err)
 		return err;
 
-- 
2.50.1

Introduce BPF_F_ALL_CPUS flag support for percpu_cgroup_storage maps to
allow updating values for all CPUs with a single value.

Introduce BPF_F_CPU flag support for percpu_cgroup_storage maps to allow
updating value for specified CPU.

This enhancement enables:

* Efficient update values across all CPUs with a single value when
  BPF_F_ALL_CPUS is set for update_elem API.
* Targeted update or lookup for a specified CPU when BPF_F_CPU is set.

The BPF_F_CPU flag is passed via map_flags of lookup_elem and update_elem
APIs along with embedded cpu field.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 include/linux/bpf-cgroup.h |  5 ++--
 include/linux/bpf.h        |  5 ++--
 kernel/bpf/local_storage.c | 47 +++++++++++++++++++++++++++++---------
 kernel/bpf/syscall.c       | 12 ++++------
 4 files changed, 46 insertions(+), 23 deletions(-)

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index aedf573bdb426..1cb28660aa866 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -172,7 +172,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
 void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
 int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map);
 
-int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value,
+				   u64 flags);
 int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 				     void *value, u64 flags);
 
@@ -467,7 +468,7 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
 static inline void bpf_cgroup_storage_free(
 	struct bpf_cgroup_storage *storage) {}
 static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key,
-						 void *value) {
+						 void *value, u64 flags) {
 	return 0;
 }
 static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index dc715eef9cbf4..2684ba32bba0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3733,12 +3733,13 @@ static inline int bpf_map_check_cpu_flags(u64 flags, bool check_all_cpus)
 	return 0;
 }
 
-static inline bool bpf_map_support_cpu_flags(enum bpf_map_type map_type)
+static inline bool bpf_map_is_percpu(enum bpf_map_type map_type)
 {
 	switch (map_type) {
 	case BPF_MAP_TYPE_PERCPU_ARRAY:
 	case BPF_MAP_TYPE_PERCPU_HASH:
 	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
 		return true;
 	default:
 		return false;
@@ -3756,7 +3757,7 @@ static inline int bpf_map_check_flags(struct bpf_map *map, u64 flags, bool check
 	if (!(flags & BPF_F_CPU) && flags >> 32)
 		return -EINVAL;
 
-	if ((flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) && !bpf_map_support_cpu_flags(map->map_type))
+	if ((flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) && !bpf_map_is_percpu(map->map_type))
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c93a756e035c0..ee60b8cee4e90 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -180,18 +180,22 @@ static long cgroup_storage_update_elem(struct bpf_map *map, void *key,
 }
 
 int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
-				   void *value)
+				   void *value, u64 map_flags)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
 	struct bpf_cgroup_storage *storage;
-	int cpu, off = 0;
+	int cpu, off = 0, err;
 	u32 size;
 
+	err = bpf_map_check_cpu_flags(map_flags, false);
+	if (err)
+		return err;
+
 	rcu_read_lock();
 	storage = cgroup_storage_lookup(map, key, false);
 	if (!storage) {
-		rcu_read_unlock();
-		return -ENOENT;
+		err = -ENOENT;
+		goto unlock;
 	}
 
 	/* per_cpu areas are zero-filled and bpf programs can only
@@ -199,13 +203,19 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
 	 * will not leak any kernel data
 	 */
 	size = round_up(_map->value_size, 8);
+	if (map_flags & BPF_F_CPU) {
+		cpu = map_flags >> 32;
+		bpf_long_memcpy(value, per_cpu_ptr(storage->percpu_buf, cpu), size);
+		goto unlock;
+	}
 	for_each_possible_cpu(cpu) {
 		bpf_long_memcpy(value + off,
 				per_cpu_ptr(storage->percpu_buf, cpu), size);
 		off += size;
 	}
+unlock:
 	rcu_read_unlock();
-	return 0;
+	return err;
 }
 
 int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
@@ -213,17 +223,21 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
 	struct bpf_cgroup_storage *storage;
-	int cpu, off = 0;
+	int cpu, off = 0, err;
 	u32 size;
 
-	if (map_flags != BPF_ANY && map_flags != BPF_EXIST)
+	if ((u32)map_flags & ~(BPF_ANY | BPF_EXIST | BPF_F_CPU | BPF_F_ALL_CPUS))
 		return -EINVAL;
 
+	err = bpf_map_check_cpu_flags(map_flags, true);
+	if (err)
+		return err;
+
 	rcu_read_lock();
 	storage = cgroup_storage_lookup(map, key, false);
 	if (!storage) {
-		rcu_read_unlock();
-		return -ENOENT;
+		err = -ENOENT;
+		goto unlock;
 	}
 
 	/* the user space will provide round_up(value_size, 8) bytes that
@@ -233,13 +247,24 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
 	 * so no kernel data leaks possible
 	 */
 	size = round_up(_map->value_size, 8);
+	if (map_flags & BPF_F_CPU) {
+		cpu = map_flags >> 32;
+		bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu), value, size);
+		goto unlock;
+	}
 	for_each_possible_cpu(cpu) {
 		bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
 				value + off, size);
-		off += size;
+		/* same user-provided value is used if
+		 * BPF_F_ALL_CPUS is specified, otherwise value is
+		 * an array of per-cpu values.
+		 */
+		if (!(map_flags & BPF_F_ALL_CPUS))
+			off += size;
 	}
+unlock:
 	rcu_read_unlock();
-	return 0;
+	return err;
 }
 
 static int cgroup_storage_get_next_key(struct bpf_map *_map, void *key,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 430f013f38f06..3fc52cd0c12de 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -133,13 +133,9 @@ bool bpf_map_write_active(const struct bpf_map *map)
 
 static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags)
 {
-	if (bpf_map_support_cpu_flags(map->map_type) && (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)))
-		return round_up(map->value_size, 8);
-	else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
-	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
-	    map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
-	    map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
-		return round_up(map->value_size, 8) * num_possible_cpus();
+	if (bpf_map_is_percpu(map->map_type))
+		return flags & (BPF_F_CPU | BPF_F_ALL_CPUS) ? round_up(map->value_size, 8) :
+			round_up(map->value_size, 8) * num_possible_cpus();
 	else if (IS_FD_MAP(map))
 		return sizeof(u32);
 	else
@@ -318,7 +314,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_copy(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
-		err = bpf_percpu_cgroup_storage_copy(map, key, value);
+		err = bpf_percpu_cgroup_storage_copy(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
 		err = bpf_stackmap_copy(map, key, value);
 	} else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
-- 
2.50.1

Add libbpf support for the BPF_F_CPU flag for percpu maps by embedding the
cpu info into the high 32 bits of:

1. **flags**: bpf_map_lookup_elem_flags(), bpf_map__lookup_elem(),
   bpf_map_update_elem() and bpf_map__update_elem()
2. **opts->elem_flags**: bpf_map_lookup_batch() and
   bpf_map_update_batch()

And the flag can be BPF_F_ALL_CPUS, but cannot be
'BPF_F_CPU | BPF_F_ALL_CPUS'.

Behavior:

* If the flag is BPF_F_ALL_CPUS, the update is applied across all CPUs.
* If the flag is BPF_F_CPU, it updates value only to the specified CPU.
* If the flag is BPF_F_CPU, lookup value only from the specified CPU.
* lookup does not support BPF_F_ALL_CPUS.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 tools/lib/bpf/bpf.h    |  8 ++++++++
 tools/lib/bpf/libbpf.c | 25 +++++++++++++++++++------
 tools/lib/bpf/libbpf.h | 21 ++++++++-------------
 3 files changed, 35 insertions(+), 19 deletions(-)

diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 7252150e7ad35..28acb15e982b3 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -286,6 +286,14 @@ LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
  *    Update spin_lock-ed map elements. This must be
  *    specified if the map value contains a spinlock.
  *
+ * **BPF_F_CPU**
+ *    As for percpu maps, update value on the specified CPU. And the cpu
+ *    info is embedded into the high 32 bits of **opts->elem_flags**.
+ *
+ * **BPF_F_ALL_CPUS**
+ *    As for percpu maps, update value across all CPUs. This flag cannot
+ *    be used with BPF_F_CPU at the same time.
+ *
  * @param fd BPF map file descriptor
  * @param keys pointer to an array of *count* keys
  * @param values pointer to an array of *count* values
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fe4fc5438678c..c949281984880 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10603,7 +10603,7 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
 }
 
 static int validate_map_op(const struct bpf_map *map, size_t key_sz,
-			   size_t value_sz, bool check_value_sz)
+			   size_t value_sz, bool check_value_sz, __u64 flags)
 {
 	if (!map_is_created(map)) /* map is not yet created */
 		return -ENOENT;
@@ -10630,6 +10630,19 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 		int num_cpu = libbpf_num_possible_cpus();
 		size_t elem_sz = roundup(map->def.value_size, 8);
 
+		if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) {
+			if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS))
+				return -EINVAL;
+			if ((flags >> 32) >= num_cpu)
+				return -ERANGE;
+			if (value_sz != elem_sz) {
+				pr_warn("map '%s': unexpected value size %zu provided for per-CPU map, expected %zu\n",
+					map->name, value_sz, elem_sz);
+				return -EINVAL;
+			}
+			break;
+		}
+
 		if (value_sz != num_cpu * elem_sz) {
 			pr_warn("map '%s': unexpected value size %zu provided for per-CPU map, expected %d * %zu = %zd\n",
 				map->name, value_sz, num_cpu, elem_sz, num_cpu * elem_sz);
@@ -10654,7 +10667,7 @@ int bpf_map__lookup_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, value_sz, true);
+	err = validate_map_op(map, key_sz, value_sz, true, flags);
 	if (err)
 		return libbpf_err(err);
 
@@ -10667,7 +10680,7 @@ int bpf_map__update_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, value_sz, true);
+	err = validate_map_op(map, key_sz, value_sz, true, flags);
 	if (err)
 		return libbpf_err(err);
 
@@ -10679,7 +10692,7 @@ int bpf_map__delete_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */);
+	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */, 0);
 	if (err)
 		return libbpf_err(err);
 
@@ -10692,7 +10705,7 @@ int bpf_map__lookup_and_delete_elem(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, value_sz, true);
+	err = validate_map_op(map, key_sz, value_sz, true, 0);
 	if (err)
 		return libbpf_err(err);
 
@@ -10704,7 +10717,7 @@ int bpf_map__get_next_key(const struct bpf_map *map,
 {
 	int err;
 
-	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */);
+	err = validate_map_op(map, key_sz, 0, false /* check_value_sz */, 0);
 	if (err)
 		return libbpf_err(err);
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 2e91148d9b44d..6a972a8d060c3 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1196,12 +1196,13 @@ LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map);
  * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size**
  * @param value pointer to memory in which looked up value will be stored
  * @param value_sz size in byte of value data memory; it has to match BPF map
- * definition's **value_size**. For per-CPU BPF maps value size has to be
- * a product of BPF map value size and number of possible CPUs in the system
- * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for
- * per-CPU values value size has to be aligned up to closest 8 bytes for
- * alignment reasons, so expected size is: `round_up(value_size, 8)
- * * libbpf_num_possible_cpus()`.
+ * definition's **value_size**. For per-CPU BPF maps, value size can be
+ * definition's **value_size** if **BPF_F_CPU** or **BPF_F_ALL_CPUS** is
+ * specified in **flags**, otherwise a product of BPF map value size and number
+ * of possible CPUs in the system (could be fetched with
+ * **libbpf_num_possible_cpus()**). Note else that for per-CPU values value
+ * size has to be aligned up to closest 8 bytes for alignment reasons, so
+ * expected size is: `round_up(value_size, 8) * libbpf_num_possible_cpus()`.
  * @flags extra flags passed to kernel for this operation
  * @return 0, on success; negative error, otherwise
  *
@@ -1219,13 +1220,7 @@ LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map,
  * @param key pointer to memory containing bytes of the key
  * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size**
  * @param value pointer to memory containing bytes of the value
- * @param value_sz size in byte of value data memory; it has to match BPF map
- * definition's **value_size**. For per-CPU BPF maps value size has to be
- * a product of BPF map value size and number of possible CPUs in the system
- * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for
- * per-CPU values value size has to be aligned up to closest 8 bytes for
- * alignment reasons, so expected size is: `round_up(value_size, 8)
- * * libbpf_num_possible_cpus()`.
+ * @param value_sz refer to **bpf_map__lookup_elem**'s description.'
  * @flags extra flags passed to kernel for this operation
  * @return 0, on success; negative error, otherwise
  *
-- 
2.50.1

Add test coverage for the new BPF_F_CPU flag support in percpu maps. The
following APIs are exercised:

* bpf_map_update_batch()
* bpf_map_lookup_batch()
* bpf_map_update_elem()
* bpf_map__update_elem()
* bpf_map_lookup_elem_flags()
* bpf_map__lookup_elem()

cd tools/testing/selftests/bpf/
./test_progs -t percpu_alloc
253/13  percpu_alloc/cpu_flag_percpu_array:OK
253/14  percpu_alloc/cpu_flag_percpu_hash:OK
253/15  percpu_alloc/cpu_flag_lru_percpu_hash:OK
253/16  percpu_alloc/cpu_flag_percpu_cgroup_storage:OK
253     percpu_alloc:OK
Summary: 1/16 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 .../selftests/bpf/prog_tests/percpu_alloc.c   | 224 ++++++++++++++++++
 .../selftests/bpf/progs/percpu_alloc_array.c  |  32 +++
 2 files changed, 256 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
index 343da65864d6d..98b6e8cc7ae60 100644
--- a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "cgroup_helpers.h"
 #include "percpu_alloc_array.skel.h"
 #include "percpu_alloc_cgrp_local_storage.skel.h"
 #include "percpu_alloc_fail.skel.h"
@@ -115,6 +116,221 @@ static void test_failure(void) {
 	RUN_TESTS(percpu_alloc_fail);
 }
 
+static void test_percpu_map_op_cpu_flag(struct bpf_map *map, void *keys, size_t key_sz,
+					u32 max_entries, bool test_batch)
+{
+	int i, j, cpu, map_fd, value_size, nr_cpus, err;
+	u64 *values = NULL, batch = 0, flags;
+	const u64 value = 0xDEADC0DE;
+	size_t value_sz = sizeof(u64);
+	u32 count;
+	LIBBPF_OPTS(bpf_map_batch_opts, batch_opts);
+
+	nr_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(nr_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	value_size = value_sz * nr_cpus;
+	values = calloc(max_entries, value_size);
+	if (!ASSERT_OK_PTR(values, "calloc values"))
+		goto out;
+	memset(values, 0, value_size * max_entries);
+
+	map_fd = bpf_map__fd(map);
+	flags = (u64)nr_cpus << 32 | BPF_F_CPU;
+	err = bpf_map_update_elem(map_fd, keys, values, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map_update_elem_opts -ERANGE"))
+		goto out;
+
+	err = bpf_map__update_elem(map, keys, key_sz, values, value_sz, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map__update_elem_opts -ERANGE"))
+		goto out;
+
+	err = bpf_map_lookup_elem_flags(map_fd, keys, values, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map_lookup_elem_opts -ERANGE"))
+		goto out;
+
+	err = bpf_map__lookup_elem(map, keys, key_sz, values, value_sz, flags);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map__lookup_elem_opts -ERANGE"))
+		goto out;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		/* clear value on all cpus */
+		values[0] = 0;
+		flags = BPF_F_ALL_CPUS;
+		for (i = 0; i < max_entries; i++) {
+			err = bpf_map__update_elem(map, keys + i * key_sz, key_sz, values,
+						   value_sz, flags);
+			if (!ASSERT_OK(err, "bpf_map__update_elem"))
+				goto out;
+		}
+
+		/* update value on specified cpu */
+		for (i = 0; i < max_entries; i++) {
+			values[0] = value;
+			flags = (u64)cpu << 32 | BPF_F_CPU;
+			err = bpf_map__update_elem(map, keys + i * key_sz, key_sz, values,
+						   value_sz, flags);
+			if (!ASSERT_OK(err, "bpf_map__update_elem specified cpu"))
+				goto out;
+
+			/* lookup then check value on CPUs */
+			for (j = 0; j < nr_cpus; j++) {
+				flags = (u64)j << 32 | BPF_F_CPU;
+				err = bpf_map__lookup_elem(map, keys + i * key_sz, key_sz, values,
+							   value_sz, flags);
+				if (!ASSERT_OK(err, "bpf_map__lookup_elem specified cpu"))
+					goto out;
+				if (!ASSERT_EQ(values[0], j != cpu ? 0 : value,
+					       "bpf_map__lookup_elem value on specified cpu"))
+					goto out;
+			}
+		}
+	}
+
+	if (!test_batch)
+		goto out;
+
+	batch_opts.elem_flags = (u64)nr_cpus << 32 | BPF_F_CPU;
+	err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &batch_opts);
+	if (!ASSERT_EQ(err, -ERANGE, "bpf_map_update_batch -ERANGE"))
+		goto out;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		memset(values, 0, max_entries * value_size);
+
+		/* clear values across all CPUs */
+		batch_opts.elem_flags = BPF_F_ALL_CPUS;
+		err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &batch_opts);
+		if (!ASSERT_OK(err, "bpf_map_update_batch all cpus"))
+			goto out;
+
+		/* update values on specified CPU */
+		for (i = 0; i < max_entries; i++)
+			values[i] = value;
+
+		batch_opts.elem_flags = (u64)cpu << 32 | BPF_F_CPU;
+		err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &batch_opts);
+		if (!ASSERT_OK(err, "bpf_map_update_batch specified cpu"))
+			goto out;
+
+		/* lookup values on specified CPU */
+		memset(values, 0, max_entries * value_sz);
+		err = bpf_map_lookup_batch(map_fd, NULL, &batch, keys, values, &count, &batch_opts);
+		if (!ASSERT_TRUE(!err || err == -ENOENT, "bpf_map_lookup_batch specified cpu"))
+			goto out;
+
+		for (i = 0; i < max_entries; i++)
+			if (!ASSERT_EQ(values[i], value, "value on specified cpu"))
+				goto out;
+
+		/* lookup values from all CPUs */
+		batch_opts.elem_flags = 0;
+		memset(values, 0, max_entries * value_size);
+		err = bpf_map_lookup_batch(map_fd, NULL, &batch, keys, values, &count, &batch_opts);
+		if (!ASSERT_TRUE(!err || err == -ENOENT, "bpf_map_lookup_batch all cpus"))
+			goto out;
+
+		for (i = 0; i < max_entries; i++) {
+			for (j = 0; j < nr_cpus; j++) {
+				if (!ASSERT_EQ(values[i*nr_cpus + j], j != cpu ? 0 : value,
+					       "value on specified cpu"))
+					goto out;
+			}
+		}
+	}
+
+out:
+	if (values)
+		free(values);
+}
+
+static void test_percpu_map_cpu_flag(enum bpf_map_type map_type)
+{
+	struct percpu_alloc_array *skel;
+	size_t key_sz = sizeof(int);
+	int *keys = NULL, i, err;
+	struct bpf_map *map;
+	u32 max_entries;
+
+	skel = percpu_alloc_array__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open"))
+		return;
+
+	map = skel->maps.percpu;
+	bpf_map__set_type(map, map_type);
+
+	err = percpu_alloc_array__load(skel);
+	if (!ASSERT_OK(err, "test_percpu_alloc__load"))
+		goto out;
+
+	max_entries = bpf_map__max_entries(map);
+	keys = calloc(max_entries, key_sz);
+	if (!ASSERT_OK_PTR(keys, "calloc keys"))
+		goto out;
+
+	for (i = 0; i < max_entries; i++)
+		keys[i] = i;
+
+	test_percpu_map_op_cpu_flag(map, keys, key_sz, max_entries, true);
+out:
+	if (keys)
+		free(keys);
+	percpu_alloc_array__destroy(skel);
+}
+
+static void test_percpu_array_cpu_flag(void)
+{
+	test_percpu_map_cpu_flag(BPF_MAP_TYPE_PERCPU_ARRAY);
+}
+
+static void test_percpu_hash_cpu_flag(void)
+{
+	test_percpu_map_cpu_flag(BPF_MAP_TYPE_PERCPU_HASH);
+}
+
+static void test_lru_percpu_hash_cpu_flag(void)
+{
+	test_percpu_map_cpu_flag(BPF_MAP_TYPE_LRU_PERCPU_HASH);
+}
+
+static void test_percpu_cgroup_storage_cpu_flag(void)
+{
+	struct bpf_cgroup_storage_key key;
+	struct percpu_alloc_array *skel;
+	int cgroup = -1, prog_fd, err;
+	struct bpf_map *map;
+
+	skel = percpu_alloc_array__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open_and_load"))
+		return;
+
+	cgroup = create_and_get_cgroup("/cg_percpu");
+	if (!ASSERT_GE(cgroup, 0, "create_and_get_cgroup"))
+		goto out;
+
+	err = join_cgroup("/cg_percpu");
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.cgroup_egress);
+	err = bpf_prog_attach(prog_fd, cgroup, BPF_CGROUP_INET_EGRESS, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	map = skel->maps.percpu_cgroup_storage;
+	err = bpf_map_get_next_key(bpf_map__fd(map), NULL, &key);
+	if (!ASSERT_OK(err, "bpf_map_get_next_key"))
+		goto out;
+
+	test_percpu_map_op_cpu_flag(map, &key, sizeof(key), 1, false);
+out:
+	bpf_prog_detach2(-1, cgroup, BPF_CGROUP_INET_EGRESS);
+	close(cgroup);
+	cleanup_cgroup_environment();
+	percpu_alloc_array__destroy(skel);
+}
+
 void test_percpu_alloc(void)
 {
 	if (test__start_subtest("array"))
@@ -125,4 +341,12 @@ void test_percpu_alloc(void)
 		test_cgrp_local_storage();
 	if (test__start_subtest("failure_tests"))
 		test_failure();
+	if (test__start_subtest("cpu_flag_percpu_array"))
+		test_percpu_array_cpu_flag();
+	if (test__start_subtest("cpu_flag_percpu_hash"))
+		test_percpu_hash_cpu_flag();
+	if (test__start_subtest("cpu_flag_lru_percpu_hash"))
+		test_lru_percpu_hash_cpu_flag();
+	if (test__start_subtest("cpu_flag_percpu_cgroup_storage"))
+		test_percpu_cgroup_storage_cpu_flag();
 }
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
index 37c2d2608ec0b..427301909c349 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -187,4 +187,36 @@ int BPF_PROG(test_array_map_10)
 	return 0;
 }
 
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, u64);
+} percpu SEC(".maps");
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test_percpu_array, int x)
+{
+	u64 value = 0xDEADC0DE;
+	int key = 0;
+
+	bpf_map_update_elem(&percpu, &key, &value, BPF_ANY);
+	return 0;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, u64);
+} percpu_cgroup_storage SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int cgroup_egress(struct __sk_buff *skb)
+{
+	u64 *val = bpf_get_local_storage(&percpu_cgroup_storage, 0);
+
+	__sync_fetch_and_add(val, 1);
+	return 1;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
2.50.1