bpf: Introduce BPF_F_CPU and BPF_F_ALL_CPUS flags for percpu_hash and lru_percpu_hash maps

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 for both
update_elem and update_batch APIs.

Introduce BPF_F_CPU flag support for percpu_hash and lru_percpu_hash
maps to allow:

* update value for specified CPU for both update_elem and update_batch
  APIs.
* lookup value for specified CPU for both lookup_elem and lookup_batch
  APIs.

The BPF_F_CPU flag is passed via:

* map_flags along with embedded cpu info.
* elem_flags along with embedded cpu info.

Signed-off-by: Leon Hwang <[email protected]>

Author: Asphaltt

include/linux/bpf.h

@@ -2745,7 +2745,7 @@ 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,
@@ -3763,6 +3763,8 @@ static inline bool bpf_map_supports_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;

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_lookup_flags(map, elem_map_flags);
+		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)
@@ -1802,15 +1830,10 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 		memcpy(dst_key, l->key, key_size);
 
 		if (is_percpu) {
-			int off = 0, cpu;
 			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;
-			}
+			bpf_percpu_copy_to_user(&htab->map, pptr, dst_val, size, elem_map_flags);
 		} else {
 			value = htab_elem_value(l, key_size);
 			if (is_fd_htab(htab)) {
@@ -2365,13 +2388,17 @@ 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)
 {
 	struct htab_elem *l;
 	void __percpu *pptr;
-	int ret = -ENOENT;
-	int cpu, off = 0;
 	u32 size;
+	int ret;
+
+	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
@@ -2386,11 +2413,7 @@ 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;
-	}
+	bpf_percpu_copy_to_user(map, pptr, value, size, map_flags);
 	ret = 0;
 out:
 	rcu_read_unlock();

kernel/bpf/syscall.c

@@ -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) {