From 4b3da77b72ad6b3c48c6fe4a395ace7db39a12c5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:54 +0100 Subject: bpf, x86: Generalize and extend bpf_arch_text_poke for direct jumps Add BPF_MOD_{NOP_TO_JUMP,JUMP_TO_JUMP,JUMP_TO_NOP} patching for x86 JIT in order to be able to patch direct jumps or nop them out. We need this facility in order to patch tail call jumps and in later work also BPF static keys. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/aa4784196a8e5e985af4b30a4fe5336bce6e9643.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e89e86122233..7978b617caa8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1284,10 +1284,16 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #endif /* CONFIG_INET */ enum bpf_text_poke_type { + /* All call-related pokes. */ BPF_MOD_NOP_TO_CALL, BPF_MOD_CALL_TO_CALL, BPF_MOD_CALL_TO_NOP, + /* All jump-related pokes. */ + BPF_MOD_NOP_TO_JUMP, + BPF_MOD_JUMP_TO_JUMP, + BPF_MOD_JUMP_TO_NOP, }; + int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); -- cgit v1.2.3 From 6332be04c039a72fca32ed0a4265bac58d606bb6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:55 +0100 Subject: bpf: Move bpf_free_used_maps into sleepable section We later on are going to need a sleepable context as opposed to plain RCU callback in order to untrack programs we need to poke at runtime and tracking as well as image update is performed under mutex. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/09823b1d5262876e9b83a8e75df04cf0467357a4.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7978b617caa8..561b920f0bf7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1031,6 +1031,10 @@ static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, { return -ENOTSUPP; } + +static inline void bpf_map_put(struct bpf_map *map) +{ +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, -- cgit v1.2.3 From 2beee5f57441413b64a9c2bd657e17beabb98d1c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:56 +0100 Subject: bpf: Move owner type, jited info into array auxiliary data We're going to extend this with further information which is only relevant for prog array at this point. Given this info is not used in critical path, move it into its own structure such that the main array map structure can be kept on diet. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/b9ddccdb0f6f7026489ee955f16c96381e1e7238.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 561b920f0bf7..c3b29061284e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -560,17 +560,21 @@ struct bpf_prog_aux { }; }; +struct bpf_array_aux { + /* 'Ownership' of prog array is claimed by the first program that + * is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have + * the same prog type and JITed flag. + */ + enum bpf_prog_type type; + bool jited; +}; + struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; - /* 'ownership' of prog_array is claimed by the first program that - * is going to use this map or by the first program which FD is stored - * in the map to make sure that all callers and callees have the same - * prog_type and JITed flag - */ - enum bpf_prog_type owner_prog_type; - bool owner_jited; + struct bpf_array_aux *aux; union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); -- cgit v1.2.3 From a66886fe6c24ebeeb6dc10fbd9b75158029eacf7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:57 +0100 Subject: bpf: Add initial poke descriptor table for jit images Add initial poke table data structures and management to the BPF prog that can later be used by JITs. Also add an instance of poke specific data for tail call maps; plan for later work is to extend this also for BPF static keys. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/1db285ec2ea4207ee0455b3f8e191a4fc58b9ade.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c3b29061284e..312983bf7faa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,6 +488,24 @@ struct bpf_func_info_aux { bool unreliable; }; +enum bpf_jit_poke_reason { + BPF_POKE_REASON_TAIL_CALL, +}; + +/* Descriptor of pokes pointing /into/ the JITed image. */ +struct bpf_jit_poke_descriptor { + void *ip; + union { + struct { + struct bpf_map *map; + u32 key; + } tail_call; + }; + bool ip_stable; + u8 adj_off; + u16 reason; +}; + struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; @@ -513,6 +531,8 @@ struct bpf_prog_aux { const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ + struct bpf_jit_poke_descriptor *poke_tab; + u32 size_poke_tab; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; -- cgit v1.2.3 From da765a2f599304a81a25e77908d1790414ecdbb6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:58 +0100 Subject: bpf: Add poke dependency tracking for prog array maps This work adds program tracking to prog array maps. This is needed such that upon prog array updates/deletions we can fix up all programs which make use of this tail call map. We add ops->map_poke_{un,}track() helpers to maps to maintain the list of programs and ops->map_poke_run() for triggering the actual update. bpf_array_aux is extended to contain the list head and poke_mutex in order to serialize program patching during updates/deletions. bpf_free_used_maps() will untrack the program shortly before dropping the reference to the map. For clearing out the prog array once all urefs are dropped we need to use schedule_work() to have a sleepable context. The prog_array_map_poke_run() is triggered during updates/deletions and walks the maintained prog list. It checks in their poke_tabs whether the map and key is matching and runs the actual bpf_arch_text_poke() for patching in the nop or new jmp location. Depending on the type of update, we use one of BPF_MOD_{NOP_TO_JUMP,JUMP_TO_NOP,JUMP_TO_JUMP}. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/1fb364bb3c565b3e415d5ea348f036ff379e779d.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 312983bf7faa..c2f07fd410c1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,7 @@ struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; +struct bpf_prog_aux; struct bpf_map; struct sock; struct seq_file; @@ -64,6 +65,12 @@ struct bpf_map_ops { const struct btf_type *key_type, const struct btf_type *value_type); + /* Prog poke tracking helpers. */ + int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); + void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); + void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, + struct bpf_prog *new); + /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); @@ -588,6 +595,11 @@ struct bpf_array_aux { */ enum bpf_prog_type type; bool jited; + /* Programs with direct jumps into programs part of this array. */ + struct list_head poke_progs; + struct bpf_map *map; + struct mutex poke_mutex; + struct work_struct work; }; struct bpf_array { -- cgit v1.2.3 From b553a6ec570044fc1ae300c6fb24f9ce204c5894 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 24 Nov 2019 01:39:42 +0100 Subject: bpf: Simplify __bpf_arch_text_poke poke type handling Given that we have BPF_MOD_NOP_TO_{CALL,JUMP}, BPF_MOD_{CALL,JUMP}_TO_NOP and BPF_MOD_{CALL,JUMP}_TO_{CALL,JUMP} poke types and that we also pass in old_addr as well as new_addr, it's a bit redundant and unnecessarily complicates __bpf_arch_text_poke() itself since we can derive the same from the *_addr that were passed in. Hence simplify and use BPF_MOD_{CALL,JUMP} as types which also allows to clean up call-sites. In addition to that, __bpf_arch_text_poke() currently verifies that text matches expected old_insn before we invoke text_poke_bp(). Also add a check on new_insn and skip rewrite if it already matches. Reason why this is rather useful is that it avoids making any special casing in prog_array_map_poke_run() when old and new prog were NULL and has the benefit that also for this case we perform a check on text whether it really matches our expectations. Suggested-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/fcb00a2b0b288d6c73de4ef58116a821c8fe8f2f.1574555798.git.daniel@iogearbox.net --- include/linux/bpf.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c2f07fd410c1..35903f148be5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1324,14 +1324,8 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #endif /* CONFIG_INET */ enum bpf_text_poke_type { - /* All call-related pokes. */ - BPF_MOD_NOP_TO_CALL, - BPF_MOD_CALL_TO_CALL, - BPF_MOD_CALL_TO_NOP, - /* All jump-related pokes. */ - BPF_MOD_NOP_TO_JUMP, - BPF_MOD_JUMP_TO_JUMP, - BPF_MOD_JUMP_TO_NOP, + BPF_MOD_CALL, + BPF_MOD_JUMP, }; int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, -- cgit v1.2.3