From f56a653c1fd13a197076dec4461c656fd2adec73 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:56:01 -0700 Subject: bpf: btf: Add BPF_BTF_LOAD command This patch adds a BPF_BTF_LOAD command which 1) loads and verifies the BTF (implemented in earlier patches) 2) returns a BTF fd to userspace. In the next patch, the BTF fd can be specified during BPF_MAP_CREATE. It currently limits to CAP_SYS_ADMIN. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4ca46df19c9a..cd8ebadc66eb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -11,6 +11,7 @@ */ #include #include +#include #include #include #include @@ -2023,6 +2024,19 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } +#define BPF_BTF_LOAD_LAST_FIELD btf_log_level + +static int bpf_btf_load(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_BTF_LOAD)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return btf_new_fd(attr); +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -2103,6 +2117,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; + case BPF_BTF_LOAD: + err = bpf_btf_load(&attr); + break; default: err = -EINVAL; break; -- cgit From 60197cfb6e11ffc03aa0ed23765b2f7e70b2e2d4 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 18 Apr 2018 15:56:02 -0700 Subject: bpf: btf: Add BPF_OBJ_GET_INFO_BY_FD support to BTF fd This patch adds BPF_OBJ_GET_INFO_BY_FD support to BTF fd. The original BTF data, which was used to create the BTF fd during the earlier BPF_BTF_LOAD call, will be returned. The userspace is expected to allocate buffer to info.info and the buffer size is set to info.info_len before calling BPF_OBJ_GET_INFO_BY_FD. The original BTF data is copied to the userspace buffer (info.info). Only upto the user's specified info.info_len will be copied. The original BTF data size is set to info.info_len. The userspace needs to check if it is bigger than its allocated buffer size. If it is, the userspace should realloc with the kernel-returned info.info_len and call the BPF_OBJ_GET_INFO_BY_FD again. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cd8ebadc66eb..0a4924a0a8da 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2017,6 +2017,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, else if (f.file->f_op == &bpf_map_fops) err = bpf_map_get_info_by_fd(f.file->private_data, attr, uattr); + else if (f.file->f_op == &btf_fops) + err = btf_get_info_by_fd(f.file->private_data, attr, uattr); else err = -EINVAL; -- cgit 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/syscall.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0a4924a0a8da..fe23dc5a3ec4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -27,6 +27,7 @@ #include #include #include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -251,6 +252,7 @@ static void bpf_map_free_deferred(struct work_struct *work) bpf_map_uncharge_memlock(map); security_bpf_map_free(map); + btf_put(map->btf); /* implementation dependent freeing */ map->ops->map_free(map); } @@ -416,7 +418,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD map_ifindex +#define BPF_MAP_CREATE_LAST_FIELD btf_value_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -450,6 +452,33 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); + if (bpf_map_support_seq_show(map) && + (attr->btf_key_id || attr->btf_value_id)) { + struct btf *btf; + + if (!attr->btf_key_id || !attr->btf_value_id) { + err = -EINVAL; + goto free_map_nouncharge; + } + + btf = btf_get_by_fd(attr->btf_fd); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto free_map_nouncharge; + } + + err = map->ops->map_check_btf(map, btf, attr->btf_key_id, + attr->btf_value_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; + } + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; @@ -482,6 +511,7 @@ free_map: free_map_sec: security_bpf_map_free(map); free_map_nouncharge: + btf_put(map->btf); map->ops->map_free(map); return err; } -- cgit