From d8616ee2affcff37c5d315310da557a694a3303d Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Tue, 24 May 2022 15:53:11 +0800 Subject: bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues During TCP sockmap redirect pressure test, the following warning is triggered: WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0 CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G W 5.10.0+ #9 Call Trace: inet_csk_destroy_sock+0x55/0x110 inet_csk_listen_stop+0xbb/0x380 tcp_close+0x41b/0x480 inet_release+0x42/0x80 __sock_release+0x3d/0xa0 sock_close+0x11/0x20 __fput+0x9d/0x240 task_work_run+0x62/0x90 exit_to_user_mode_prepare+0x110/0x120 syscall_exit_to_user_mode+0x27/0x190 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason we observed is that: When the listener is closing, a connection may have completed the three-way handshake but not accepted, and the client has sent some packets. The child sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(), but psocks of child sks have not released. To fix, add sock_map_destroy to release psocks. Signed-off-by: Wang Yufen Signed-off-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@huawei.com --- include/linux/bpf.h | 1 + include/linux/skmsg.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2b914a56a2c5..8e6092d0ea95 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2104,6 +2104,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); void sock_map_unhash(struct sock *sk); +void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c5a2d6f50f25..153b6dec9b6a 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -95,6 +95,7 @@ struct sk_psock { spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); + void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); -- cgit v1.2.3 From 6089fb325cf737eeb2c4d236c94697112ca860da Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 6 Jun 2022 23:26:00 -0700 Subject: bpf: Add btf enum64 support Currently, BTF only supports upto 32bit enum value with BTF_KIND_ENUM. But in kernel, some enum indeed has 64bit values, e.g., in uapi bpf.h, we have enum { BPF_F_INDEX_MASK = 0xffffffffULL, BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, BPF_F_CTXLEN_MASK = (0xfffffULL << 32), }; In this case, BTF_KIND_ENUM will encode the value of BPF_F_CTXLEN_MASK as 0, which certainly is incorrect. This patch added a new btf kind, BTF_KIND_ENUM64, which permits 64bit value to cover the above use case. The BTF_KIND_ENUM64 has the following three fields followed by the common type: struct bpf_enum64 { __u32 nume_off; __u32 val_lo32; __u32 val_hi32; }; Currently, btf type section has an alignment of 4 as all element types are u32. Representing the value with __u64 will introduce a pad for bpf_enum64 and may also introduce misalignment for the 64bit value. Hence, two members of val_hi32 and val_lo32 are chosen to avoid these issues. The kflag is also introduced for BTF_KIND_ENUM and BTF_KIND_ENUM64 to indicate whether the value is signed or unsigned. The kflag intends to provide consistent output of BTF C fortmat with the original source code. For example, the original BTF_KIND_ENUM bit value is 0xffffffff. The format C has two choices, printing out 0xffffffff or -1 and current libbpf prints out as unsigned value. But if the signedness is preserved in btf, the value can be printed the same as the original source code. The kflag value 0 means unsigned values, which is consistent to the default by libbpf and should also cover most cases as well. The new BTF_KIND_ENUM64 is intended to support the enum value represented as 64bit value. But it can represent all BTF_KIND_ENUM values as well. The compiler ([1]) and pahole will generate BTF_KIND_ENUM64 only if the value has to be represented with 64 bits. In addition, a static inline function btf_kind_core_compat() is introduced which will be used later when libbpf relo_core.c changed. Here the kernel shares the same relo_core.c with libbpf. [1] https://reviews.llvm.org/D124641 Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20220607062600.3716578-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 2611cea2c2b6..1bfed7fa0428 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -177,6 +177,19 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM || + BTF_INFO_KIND(t->info) == BTF_KIND_ENUM64; +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return BTF_INFO_KIND(t1->info) == BTF_INFO_KIND(t2->info) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + static inline bool str_is_empty(const char *s) { return !s || !s[0]; @@ -192,6 +205,16 @@ static inline bool btf_is_enum(const struct btf_type *t) return btf_kind(t) == BTF_KIND_ENUM; } +static inline bool btf_is_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + +static inline u64 btf_enum64_value(const struct btf_enum64 *e) +{ + return ((u64)e->val_hi32 << 32) | e->val_lo32; +} + static inline bool btf_is_composite(const struct btf_type *t) { u16 kind = btf_kind(t); @@ -332,6 +355,11 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { -- cgit v1.2.3 From 6dbdc9f35360d4ef4704462c265f63b32fcb5354 Mon Sep 17 00:00:00 2001 From: Hongyi Lu Date: Mon, 13 Jun 2022 21:16:33 +0000 Subject: bpf: Fix spelling in bpf_verifier.h Minor spelling fix spotted in bpf_verifier.h. Spelling is no big deal, but it is still an improvement when reading through the code. Signed-off-by: Hongyi Lu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220613211633.58647-1-jwnhy0@gmail.com --- include/linux/bpf_verifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e8439f6cbe57..3930c963fa67 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -299,7 +299,7 @@ struct bpf_verifier_state { * If is_state_visited() sees a state with branches > 0 it means * there is a loop. If such state is exactly equal to the current state * it's an infinite loop. Note states_equal() checks for states - * equvalency, so two states being 'states_equal' does not mean + * equivalency, so two states being 'states_equal' does not mean * infinite loop. The exact comparison is provided by * states_maybe_looping() function. It's a stronger pre-check and * much faster than states_equal(). -- cgit v1.2.3 From d687f621c518d791b5fffde8add3112d869b0b1b Mon Sep 17 00:00:00 2001 From: Delyan Kratunov Date: Tue, 14 Jun 2022 23:10:42 +0000 Subject: bpf: move bpf_prog to bpf.h In order to add a version of bpf_prog_run_array which accesses the bpf_prog->aux member, bpf_prog needs to be more than a forward declaration inside bpf.h. Given that filter.h already includes bpf.h, this merely reorders the type declarations for filter.h users. bpf.h users now have access to bpf_prog internals. Signed-off-by: Delyan Kratunov Link: https://lore.kernel.org/r/3ed7824e3948f22d84583649ccac0ff0d38b6b58.1655248076.git.delyank@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 36 ++++++++++++++++++++++++++++++++++++ include/linux/filter.h | 34 ---------------------------------- 2 files changed, 36 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8e6092d0ea95..69106ae46464 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -5,6 +5,7 @@ #define _LINUX_BPF_H 1 #include +#include #include #include @@ -22,6 +23,7 @@ #include #include #include +#include #include #include @@ -1084,6 +1086,40 @@ struct bpf_prog_aux { }; }; +struct bpf_prog { + u16 pages; /* Number of allocated pages */ + u16 jited:1, /* Is our filter JIT'ed? */ + jit_requested:1,/* archs need to JIT the prog */ + gpl_compatible:1, /* Is filter GPL compatible? */ + cb_access:1, /* Is control block accessed? */ + dst_needed:1, /* Do we need dst entry? */ + blinding_requested:1, /* needs constant blinding */ + blinded:1, /* Was blinded */ + is_func:1, /* program is a bpf function */ + kprobe_override:1, /* Do we override a kprobe? */ + has_callchain_buf:1, /* callchain buffer allocated? */ + enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ + call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_func_ip:1, /* Do we call get_func_ip() */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ + enum bpf_prog_type type; /* Type of BPF program */ + enum bpf_attach_type expected_attach_type; /* For some prog types */ + u32 len; /* Number of filter blocks */ + u32 jited_len; /* Size of jited insns in bytes */ + u8 tag[BPF_TAG_SIZE]; + struct bpf_prog_stats __percpu *stats; + int __percpu *active; + unsigned int (*bpf_func)(const void *ctx, + const struct bpf_insn *insn); + struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ + /* Instructions for interpreter */ + union { + DECLARE_FLEX_ARRAY(struct sock_filter, insns); + DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); + }; +}; + struct bpf_array_aux { /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; diff --git a/include/linux/filter.h b/include/linux/filter.h index ed0c0ff42ad5..d0cbb31b1b4d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -559,40 +559,6 @@ struct bpf_prog_stats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); -struct bpf_prog { - u16 pages; /* Number of allocated pages */ - u16 jited:1, /* Is our filter JIT'ed? */ - jit_requested:1,/* archs need to JIT the prog */ - gpl_compatible:1, /* Is filter GPL compatible? */ - cb_access:1, /* Is control block accessed? */ - dst_needed:1, /* Do we need dst entry? */ - blinding_requested:1, /* needs constant blinding */ - blinded:1, /* Was blinded */ - is_func:1, /* program is a bpf function */ - kprobe_override:1, /* Do we override a kprobe? */ - has_callchain_buf:1, /* callchain buffer allocated? */ - enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ - call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ - call_get_func_ip:1, /* Do we call get_func_ip() */ - tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ - enum bpf_prog_type type; /* Type of BPF program */ - enum bpf_attach_type expected_attach_type; /* For some prog types */ - u32 len; /* Number of filter blocks */ - u32 jited_len; /* Size of jited insns in bytes */ - u8 tag[BPF_TAG_SIZE]; - struct bpf_prog_stats __percpu *stats; - int __percpu *active; - unsigned int (*bpf_func)(const void *ctx, - const struct bpf_insn *insn); - struct bpf_prog_aux *aux; /* Auxiliary fields */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ - /* Instructions for interpreter */ - union { - DECLARE_FLEX_ARRAY(struct sock_filter, insns); - DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); - }; -}; - struct sk_filter { refcount_t refcnt; struct rcu_head rcu; -- cgit v1.2.3 From 8c7dcb84e3b744b2b70baa7a44a9b1881c33a9c9 Mon Sep 17 00:00:00 2001 From: Delyan Kratunov Date: Tue, 14 Jun 2022 23:10:46 +0000 Subject: bpf: implement sleepable uprobes by chaining gps uprobes work by raising a trap, setting a task flag from within the interrupt handler, and processing the actual work for the uprobe on the way back to userspace. As a result, uprobe handlers already execute in a might_fault/_sleep context. The primary obstacle to sleepable bpf uprobe programs is therefore on the bpf side. Namely, the bpf_prog_array attached to the uprobe is protected by normal rcu. In order for uprobe bpf programs to become sleepable, it has to be protected by the tasks_trace rcu flavor instead (and kfree() called after a corresponding grace period). Therefore, the free path for bpf_prog_array now chains a tasks_trace and normal grace periods one after the other. Users who iterate under tasks_trace read section would be safe, as would users who iterate under normal read sections (from non-sleepable locations). The downside is that the tasks_trace latency affects all perf_event-attached bpf programs (and not just uprobe ones). This is deemed safe given the possible attach rates for kprobe/uprobe/tp programs. Separately, non-sleepable programs need access to dynamically sized rcu-protected maps, so bpf_run_prog_array_sleepables now conditionally takes an rcu read section, in addition to the overarching tasks_trace section. Signed-off-by: Delyan Kratunov Link: https://lore.kernel.org/r/ce844d62a2fd0443b08c5ab02e95bc7149f9aeb1.1655248076.git.delyank@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 69106ae46464..f3e88afdaffe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -26,6 +26,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -1372,6 +1373,8 @@ extern struct bpf_empty_prog_array bpf_empty_prog_array; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); +/* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ +void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, @@ -1463,6 +1466,55 @@ bpf_prog_run_array(const struct bpf_prog_array *array, return ret; } +/* Notes on RCU design for bpf_prog_arrays containing sleepable programs: + * + * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array + * overall. As a result, we must use the bpf_prog_array_free_sleepable + * in order to use the tasks_trace rcu grace period. + * + * When a non-sleepable program is inside the array, we take the rcu read + * section and disable preemption for that program alone, so it can access + * rcu-protected dynamically sized maps. + */ +static __always_inline u32 +bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; + u32 ret = 1; + + might_fault(); + + rcu_read_lock_trace(); + migrate_disable(); + + array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); + if (unlikely(!array)) + goto out; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + if (!prog->aux->sleepable) + rcu_read_lock(); + + run_ctx.bpf_cookie = item->bpf_cookie; + ret &= run_prog(prog, ctx); + item++; + + if (!prog->aux->sleepable) + rcu_read_unlock(); + } + bpf_reset_run_ctx(old_run_ctx); +out: + migrate_enable(); + rcu_read_unlock_trace(); + return ret; +} + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; -- cgit v1.2.3 From 508362ac66b0478affb4e52cb8da98478312d72d Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 15 Jun 2022 16:48:43 +0300 Subject: bpf: Allow helpers to accept pointers with a fixed size Before this commit, the BPF verifier required ARG_PTR_TO_MEM arguments to be followed by ARG_CONST_SIZE holding the size of the memory region. The helpers had to check that size in runtime. There are cases where the size expected by a helper is a compile-time constant. Checking it in runtime is an unnecessary overhead and waste of BPF registers. This commit allows helpers to accept pointers to memory without the corresponding ARG_CONST_SIZE, given that they define the memory region size in struct bpf_func_proto and use ARG_PTR_TO_FIXED_SIZE_MEM type. arg_size is unionized with arg_btf_id to reduce the kernel image size, and it's valid because they are used by different argument types. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Link: https://lore.kernel.org/r/20220615134847.3753567-3-maximmi@nvidia.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f3e88afdaffe..a94531971a7a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -401,6 +401,9 @@ enum bpf_type_flag { /* DYNPTR points to a ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), + /* Size is known at compile time. */ + MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -464,6 +467,8 @@ enum bpf_arg_type { * all bytes or clear them in error case. */ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + /* Pointer to valid memory of size known at compile time. */ + ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. @@ -529,6 +534,14 @@ struct bpf_func_proto { u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; + struct { + size_t arg1_size; + size_t arg2_size; + size_t arg3_size; + size_t arg4_size; + size_t arg5_size; + }; + size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); -- cgit v1.2.3 From dc368e1c658e4f478a45e8d1d5b0c8392ca87506 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Thu, 16 Jun 2022 15:54:07 -0700 Subject: bpf: Fix non-static bpf_func_proto struct definitions This patch does two things: 1) Marks the dynptr bpf_func_proto structs that were added in [1] as static, as pointed out by the kernel test robot in [2]. 2) There are some bpf_func_proto structs marked as extern which can instead be statically defined. [1] https://lore.kernel.org/bpf/20220523210712.3641569-1-joannelkoong@gmail.com/ [2] https://lore.kernel.org/bpf/62ab89f2.Pko7sI08RAKdF8R6%25lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Joanne Koong Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220616225407.1878436-1-joannelkoong@gmail.com --- include/linux/bpf.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a94531971a7a..0edd7d2c0064 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2363,12 +2363,9 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; -extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; -extern const struct bpf_func_proto bpf_strncmp_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; -extern const struct bpf_func_proto bpf_kptr_xchg_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3