From a26ca7c982cb576749cbdd01e8ecde4bf010d60a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:56:03 -0700 Subject: bpf: btf: Add pretty print support to the basic arraymap This patch adds pretty print support to the basic arraymap. Support for other bpf maps can be added later. This patch adds new attrs to the BPF_MAP_CREATE command to allow specifying the btf_fd, btf_key_id and btf_value_id. The BPF_MAP_CREATE can then associate the btf to the map if the creating map supports BTF. A BTF supported map needs to implement two new map ops, map_seq_show_elem() and map_check_btf(). This patch has implemented these new map ops for the basic arraymap. It also adds file_operations, bpffs_map_fops, to the pinned map such that the pinned map can be opened and read. After that, the user has an intuitive way to do "cat bpffs/pathto/a-pinned-map" instead of getting an error. bpffs_map_fops should not be extended further to support other operations. Other operations (e.g. write/key-lookup...) should be realized by the userspace tools (e.g. bpftool) through the BPF_OBJ_GET_INFO_BY_FD, map's lookup/update interface...etc. Follow up patches will allow the userspace to obtain the BTF from a map-fd. Here is a sample output when reading a pinned arraymap with the following map's value: struct map_value { int count_a; int count_b; }; cat /sys/fs/bpf/pinned_array_map: 0: {1,2} 1: {3,4} 2: {5,6} ... Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/arraymap.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'kernel/bpf/arraymap.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 14750e7c5ee4..02a189339381 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,11 +11,13 @@ * General Public License for more details. */ #include +#include #include #include #include #include #include +#include #include "map_in_map.h" @@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map) bpf_map_area_free(array); } +static void array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void *value; + + rcu_read_lock(); + + value = array_map_lookup_elem(map, key); + if (!value) { + rcu_read_unlock(); + return; + } + + seq_printf(m, "%u: ", *(u32 *)key); + btf_type_seq_show(map->btf, map->btf_value_id, value, m); + seq_puts(m, "\n"); + + rcu_read_unlock(); +} + +static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, + u32 btf_key_id, u32 btf_value_id) +{ + const struct btf_type *key_type, *value_type; + u32 key_size, value_size; + u32 int_data; + + key_type = btf_type_id_size(btf, &btf_key_id, &key_size); + if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + /* bpf array can only take a u32 key. This check makes + * sure that the btf matches the attr used during map_create. + */ + if (BTF_INT_BITS(int_data) != 32 || key_size != 4 || + BTF_INT_OFFSET(int_data)) + return -EINVAL; + + value_type = btf_type_id_size(btf, &btf_value_id, &value_size); + if (!value_type || value_size > map->value_size) + return -EINVAL; + + return 0; +} + const struct bpf_map_ops array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, @@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = { .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, .map_gen_lookup = array_map_gen_lookup, + .map_seq_show_elem = array_map_seq_show_elem, + .map_check_btf = array_map_check_btf, }; const struct bpf_map_ops percpu_array_map_ops = { -- cgit From ba6b8de423f8d0dee48d6030288ed81c03ddf9f0 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 23 Apr 2018 15:39:23 -0700 Subject: bpf: sockmap, map_release does not hold refcnt for pinned maps Relying on map_release hook to decrement the reference counts when a map is removed only works if the map is not being pinned. In the pinned case the ref is decremented immediately and the BPF programs released. After this BPF programs may not be in-use which is not what the user would expect. This patch moves the release logic into bpf_map_put_uref() and brings sockmap in-line with how a similar case is handled in prog array maps. Fixes: 3d9e952697de ("bpf: sockmap, fix leaking maps with attached but not detached progs") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 +- kernel/bpf/arraymap.c | 3 ++- kernel/bpf/sockmap.c | 4 ++-- kernel/bpf/syscall.c | 4 ++-- 4 files changed, 7 insertions(+), 6 deletions(-) (limited to 'kernel/bpf/arraymap.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index dc586cc64bc2..469b20e1dd7e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -31,6 +31,7 @@ struct bpf_map_ops { void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); + void (*map_release_uref)(struct bpf_map *map); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); @@ -436,7 +437,6 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); -void bpf_fd_array_map_clear(struct bpf_map *map); int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 14750e7c5ee4..027107f4be53 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -476,7 +476,7 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr) } /* decrement refcnt of all bpf_progs that are stored in this map */ -void bpf_fd_array_map_clear(struct bpf_map *map) +static void bpf_fd_array_map_clear(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; @@ -495,6 +495,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_get_ptr = prog_fd_array_get_ptr, .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, + .map_release_uref = bpf_fd_array_map_clear, }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index a3b21385e947..a73d484b6e4c 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1831,7 +1831,7 @@ static int sock_map_update_elem(struct bpf_map *map, return err; } -static void sock_map_release(struct bpf_map *map, struct file *map_file) +static void sock_map_release(struct bpf_map *map) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); struct bpf_prog *orig; @@ -1855,7 +1855,7 @@ const struct bpf_map_ops sock_map_ops = { .map_get_next_key = sock_map_get_next_key, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, - .map_release = sock_map_release, + .map_release_uref = sock_map_release, }; BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4ca46df19c9a..ebfe9f29dae8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -257,8 +257,8 @@ static void bpf_map_free_deferred(struct work_struct *work) static void bpf_map_put_uref(struct bpf_map *map) { if (atomic_dec_and_test(&map->usercnt)) { - if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) - bpf_fd_array_map_clear(map); + if (map->ops->map_release_uref) + map->ops->map_release_uref(map); } } -- cgit From 9b2cf328b2eccf761537a06bef914d2a0700fba7 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 22 May 2018 14:57:21 -0700 Subject: bpf: btf: Rename btf_key_id and btf_value_id in bpf_map_info In "struct bpf_map_info", the name "btf_id", "btf_key_id" and "btf_value_id" could cause confusion because the "id" of "btf_id" means the BPF obj id given to the BTF object while "btf_key_id" and "btf_value_id" means the BTF type id within that BTF object. To make it clear, btf_key_id and btf_value_id are renamed to btf_key_type_id and btf_value_type_id. Suggested-by: Daniel Borkmann Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 4 ++-- include/uapi/linux/bpf.h | 8 ++++---- kernel/bpf/arraymap.c | 2 +- kernel/bpf/syscall.c | 18 +++++++++--------- 4 files changed, 16 insertions(+), 16 deletions(-) (limited to 'kernel/bpf/arraymap.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f6fe3c719ca8..1795eeee846c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -69,8 +69,8 @@ struct bpf_map { u32 pages; u32 id; int numa_node; - u32 btf_key_id; - u32 btf_value_id; + u32 btf_key_type_id; + u32 btf_value_type_id; struct btf *btf; bool unpriv_array; /* 55 bytes hole */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 97446bbe2ca5..c3e502d06bc3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -284,8 +284,8 @@ union bpf_attr { char map_name[BPF_OBJ_NAME_LEN]; __u32 map_ifindex; /* ifindex of netdev to create on */ __u32 btf_fd; /* fd pointing to a BTF type data */ - __u32 btf_key_id; /* BTF type_id of the key */ - __u32 btf_value_id; /* BTF type_id of the value */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -2219,8 +2219,8 @@ struct bpf_map_info { __u64 netns_dev; __u64 netns_ino; __u32 btf_id; - __u32 btf_key_id; - __u32 btf_value_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0fd8d8f1a398..544e58f5f642 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -352,7 +352,7 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, } seq_printf(m, "%u: ", *(u32 *)key); - btf_type_seq_show(map->btf, map->btf_value_id, value, m); + btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); seq_puts(m, "\n"); rcu_read_unlock(); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2b29ef84ded3..0b4c94551001 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -422,7 +422,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD btf_value_id +#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -457,10 +457,10 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->usercnt, 1); if (bpf_map_support_seq_show(map) && - (attr->btf_key_id || attr->btf_value_id)) { + (attr->btf_key_type_id || attr->btf_value_type_id)) { struct btf *btf; - if (!attr->btf_key_id || !attr->btf_value_id) { + if (!attr->btf_key_type_id || !attr->btf_value_type_id) { err = -EINVAL; goto free_map_nouncharge; } @@ -471,16 +471,16 @@ static int map_create(union bpf_attr *attr) goto free_map_nouncharge; } - err = map->ops->map_check_btf(map, btf, attr->btf_key_id, - attr->btf_value_id); + err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id, + attr->btf_value_type_id); if (err) { btf_put(btf); goto free_map_nouncharge; } map->btf = btf; - map->btf_key_id = attr->btf_key_id; - map->btf_value_id = attr->btf_value_id; + map->btf_key_type_id = attr->btf_key_type_id; + map->btf_value_type_id = attr->btf_value_type_id; } err = security_bpf_map_alloc(map); @@ -2013,8 +2013,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, if (map->btf) { info.btf_id = btf_id(map->btf); - info.btf_key_id = map->btf_key_id; - info.btf_value_id = map->btf_value_id; + info.btf_key_type_id = map->btf_key_type_id; + info.btf_value_type_id = map->btf_value_type_id; } if (bpf_map_is_dev_bound(map)) { -- cgit