[bpf-next,v3,1/3] bpf: Support kptrs in percpu hashmap and percpu LRU hashmap

Commit Message

Kumar Kartikeya Dwivedi Feb. 25, 2023, 3:40 p.m. UTC

Enable support for kptrs in percpu BPF hashmap and percpu BPF LRU
hashmap by wiring up the freeing of these kptrs from percpu map
elements.

Signed-off-by: Kumar Kartikeya Dwivedi <[e-mail]>
---
 kernel/bpf/hashtab.c | 59 +++++++++++++++++++++++++++-----------------
 kernel/bpf/syscall.c |  2 ++
 2 files changed, 39 insertions(+), 22 deletions(-)

Patch

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5dfcb5ad0d06..653aeb481c79 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -249,7 +249,18 @@  static void htab_free_prealloced_fields(struct bpf_htab *htab)
 		struct htab_elem *elem;
 
 		elem = get_htab_elem(htab, i);
-		bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8));
+		if (htab_is_percpu(htab)) {
+			void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size);
+			int cpu;
+
+			for_each_possible_cpu(cpu) {
+				bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu));
+				cond_resched();
+			}
+		} else {
+			bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8));
+			cond_resched();
+		}
 		cond_resched();
 	}
 }
@@ -759,9 +770,17 @@  static int htab_lru_map_gen_lookup(struct bpf_map *map,
 static void check_and_free_fields(struct bpf_htab *htab,
 				  struct htab_elem *elem)
 {
-	void *map_value = elem->key + round_up(htab->map.key_size, 8);
+	if (htab_is_percpu(htab)) {
+		void __percpu *pptr = htab_elem_get_ptr(elem, htab->map.key_size);
+		int cpu;
 
-	bpf_obj_free_fields(htab->map.record, map_value);
+		for_each_possible_cpu(cpu)
+			bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu));
+	} else {
+		void *map_value = elem->key + round_up(htab->map.key_size, 8);
+
+		bpf_obj_free_fields(htab->map.record, map_value);
+	}
 }
 
 /* It is called from the bpf_lru_list when the LRU needs to delete
@@ -858,9 +877,9 @@  static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 
 static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
 {
+	check_and_free_fields(htab, l);
 	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
 		bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr);
-	check_and_free_fields(htab, l);
 	bpf_mem_cache_free(&htab->ma, l);
 }
 
@@ -918,14 +937,13 @@  static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 {
 	if (!onallcpus) {
 		/* copy true value_size bytes */
-		memcpy(this_cpu_ptr(pptr), value, htab->map.value_size);
+		copy_map_value(&htab->map, this_cpu_ptr(pptr), value);
 	} else {
 		u32 size = round_up(htab->map.value_size, 8);
 		int off = 0, cpu;
 
 		for_each_possible_cpu(cpu) {
-			bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
-					value + off, size);
+			copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value + off);
 			off += size;
 		}
 	}
@@ -940,16 +958,14 @@  static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
 	 * (onallcpus=false always when coming from bpf prog).
 	 */
 	if (!onallcpus) {
-		u32 size = round_up(htab->map.value_size, 8);
 		int current_cpu = raw_smp_processor_id();
 		int cpu;
 
 		for_each_possible_cpu(cpu) {
 			if (cpu == current_cpu)
-				bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value,
-						size);
-			else
-				memset(per_cpu_ptr(pptr, cpu), 0, size);
+				copy_map_value_long(&htab->map, per_cpu_ptr(pptr, cpu), value);
+			else /* Since elem is preallocated, we cannot touch special fields */
+				zero_map_value(&htab->map, per_cpu_ptr(pptr, cpu));
 		}
 	} else {
 		pcpu_copy_value(htab, pptr, value, onallcpus);
@@ -1575,9 +1591,8 @@  static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
 
 			pptr = htab_elem_get_ptr(l, key_size);
 			for_each_possible_cpu(cpu) {
-				bpf_long_memcpy(value + off,
-						per_cpu_ptr(pptr, cpu),
-						roundup_value_size);
+				copy_map_value_long(&htab->map, value + off, per_cpu_ptr(pptr, cpu));
+				check_and_init_map_value(&htab->map, value + off);
 				off += roundup_value_size;
 			}
 		} else {
@@ -1772,8 +1787,8 @@  __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 
 			pptr = htab_elem_get_ptr(l, map->key_size);
 			for_each_possible_cpu(cpu) {
-				bpf_long_memcpy(dst_val + off,
-						per_cpu_ptr(pptr, cpu), size);
+				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 {
@@ -2046,9 +2061,9 @@  static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem)
 				roundup_value_size = round_up(map->value_size, 8);
 				pptr = htab_elem_get_ptr(elem, map->key_size);
 				for_each_possible_cpu(cpu) {
-					bpf_long_memcpy(info->percpu_value_buf + off,
-							per_cpu_ptr(pptr, cpu),
-							roundup_value_size);
+					copy_map_value_long(map, info->percpu_value_buf + off,
+							    per_cpu_ptr(pptr, cpu));
+					check_and_init_map_value(map, info->percpu_value_buf + off);
 					off += roundup_value_size;
 				}
 				ctx.value = info->percpu_value_buf;
@@ -2292,8 +2307,8 @@  int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
 	 */
 	pptr = htab_elem_get_ptr(l, map->key_size);
 	for_each_possible_cpu(cpu) {
-		bpf_long_memcpy(value + off,
-				per_cpu_ptr(pptr, cpu), size);
+		copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu));
+		check_and_init_map_value(map, value + off);
 		off += size;
 	}
 	ret = 0;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e3fcdc9836a6..da117a2a83b2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1059,7 +1059,9 @@  static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 			case BPF_KPTR_UNREF:
 			case BPF_KPTR_REF:
 				if (map->map_type != BPF_MAP_TYPE_HASH &&
+				    map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
 				    map->map_type != BPF_MAP_TYPE_LRU_HASH &&
+				    map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH &&
 				    map->map_type != BPF_MAP_TYPE_ARRAY &&
 				    map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) {
 					ret = -EOPNOTSUPP;