[PATCH bpf-next v2 2/3] libbpf: Support BPF_F_CPU for percpu_array maps

[Leon Hwang <leon.hwang@linux.dev>]

Add libbpf support for the BPF_F_CPU flag for percpu_array 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()

Behavior:

* If cpu is (u32)~0, the update is applied across all CPUs.
* Otherwise, it updates value only to the specified CPU.
* If cpu is (u32)~0, lookup values across all CPUs.
* Otherwise, it lookups value only from the specified CPU.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 tools/lib/bpf/bpf.h    |  5 +++++
 tools/lib/bpf/libbpf.c | 28 ++++++++++++++++++++++------
 tools/lib/bpf/libbpf.h | 17 ++++++-----------
 3 files changed, 33 insertions(+), 17 deletions(-)

diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 7252150e7ad35..8dea8216d5992 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -286,6 +286,11 @@ 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 map, the cpu info is embedded into the high 32 bits of
+ *    **opts->elem_flags**. Update value across all CPUs if cpu is (__u32)~0,
+ *    or on specified CPU otherwise.
+ *
  * @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 fb4d92c5c3394..29ada5d62ba26 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10593,8 +10593,10 @@ 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)
 {
+	__u32 cpu;
+
 	if (!map_is_created(map)) /* map is not yet created */
 		return -ENOENT;
 
@@ -10612,6 +10614,20 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 	if (!check_value_sz)
 		return 0;
 
+	if (flags & BPF_F_CPU) {
+		if (map->def.type != BPF_MAP_TYPE_PERCPU_ARRAY)
+			return -EINVAL;
+		cpu = flags >> 32;
+		if (cpu != BPF_ALL_CPUS && cpu >= libbpf_num_possible_cpus())
+			return -ERANGE;
+		if (map->def.value_size != value_sz) {
+			pr_warn("map '%s': unexpected value size %zu provided, expected %u\n",
+				map->name, value_sz, map->def.value_size);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
 	switch (map->def.type) {
 	case BPF_MAP_TYPE_PERCPU_ARRAY:
 	case BPF_MAP_TYPE_PERCPU_HASH:
@@ -10644,7 +10660,7 @@ 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);
 
@@ -10657,7 +10673,7 @@ 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);
 
@@ -10669,7 +10685,7 @@ 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);
 
@@ -10682,7 +10698,7 @@ 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);
 
@@ -10694,7 +10710,7 @@ 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 d1cf813a057bc..bde22b017a3ce 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1169,10 +1169,11 @@ 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
+ * definition's **value_size**. For per-CPU BPF maps, value size can be
+ * definition's **value_size** if **BPF_F_CPU** 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
@@ -1192,13 +1193,7 @@ 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