From 5311591fbb349fe9f5c555dcba3b13a5831aa72d Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Tue, 26 Mar 2024 10:17:40 +0000 Subject: bpf: Add support for passing mark with bpf_fib_lookup Extend the bpf_fib_lookup() helper by making it to utilize mark if the BPF_FIB_LOOKUP_MARK flag is set. In order to pass the mark the four bytes of struct bpf_fib_lookup are used, shared with the output-only smac/dmac fields. Signed-off-by: Anton Protopopov Signed-off-by: Daniel Borkmann Reviewed-by: David Ahern Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240326101742.17421-2-aspsk@isovalent.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9585f5345353..96d57e483133 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3394,6 +3394,10 @@ union bpf_attr { * for the nexthop. If the src addr cannot be derived, * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this * case, *params*->dmac and *params*->smac are not set either. + * **BPF_FIB_LOOKUP_MARK** + * Use the mark present in *params*->mark for the fib lookup. + * This option should not be used with BPF_FIB_LOOKUP_DIRECT, + * as it only has meaning for full lookups. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -7120,6 +7124,7 @@ enum { BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), + BPF_FIB_LOOKUP_MARK = (1U << 5), }; enum { @@ -7197,8 +7202,19 @@ struct bpf_fib_lookup { __u32 tbid; }; - __u8 smac[6]; /* ETH_ALEN */ - __u8 dmac[6]; /* ETH_ALEN */ + union { + /* input */ + struct { + __u32 mark; /* policy routing */ + /* 2 4-byte holes for input */ + }; + + /* output: source and dest mac */ + struct { + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ + }; + }; }; struct bpf_redir_neigh { -- cgit v1.2.3 From 3124591f686115aca25d772c2ccb7b1e202c3197 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 26 Mar 2024 09:21:50 -0700 Subject: bpf: add bpf_modify_return_test_tp() kfunc triggering tracepoint Add a simple bpf_modify_return_test_tp() kfunc, available to all program types, that is useful for various testing and benchmarking scenarios, as it allows to trigger most tracing BPF program types from BPF side, allowing to do complex testing and benchmarking scenarios. It is also attachable to for fmod_ret programs, making it a good and simple way to trigger fmod_ret program under test/benchmark. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240326162151.3981687-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/trace/events/bpf_test_run.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/trace/events/bpf_test_run.h b/include/trace/events/bpf_test_run.h index 265447e3f71a..0c924d39b7cb 100644 --- a/include/trace/events/bpf_test_run.h +++ b/include/trace/events/bpf_test_run.h @@ -7,6 +7,23 @@ #include +TRACE_EVENT(bpf_trigger_tp, + + TP_PROTO(int nonce), + + TP_ARGS(nonce), + + TP_STRUCT__entry( + __field(int, nonce) + ), + + TP_fast_assign( + __entry->nonce = nonce; + ), + + TP_printk("nonce %d", __entry->nonce) +); + DECLARE_EVENT_CLASS(bpf_test_finish, TP_PROTO(int *err), -- cgit v1.2.3 From ca4ddc26f8acaa9cb451fcb20f7ab0f02e4970cb Mon Sep 17 00:00:00 2001 From: David Lechner Date: Fri, 29 Mar 2024 10:28:46 -0500 Subject: bpf: Fix typo in uapi doc comments In a few places in the bpf uapi headers, EOPNOTSUPP is missing a "P" in the doc comments. This adds the missing "P". Signed-off-by: David Lechner Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240329152900.398260-2-dlechner@baylibre.com --- include/uapi/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 96d57e483133..79c548276b6b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5026,7 +5026,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. * * struct socket *bpf_sock_from_file(struct file *file) @@ -5512,7 +5512,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * * void *bpf_kptr_xchg(void *map_value, void *ptr) -- cgit v1.2.3 From ce09cbdd988887662546a1175bcfdfc6c8fdd150 Mon Sep 17 00:00:00 2001 From: Jose Fernandez Date: Mon, 1 Apr 2024 21:40:10 -0600 Subject: bpf: Improve program stats run-time calculation This patch improves the run-time calculation for program stats by capturing the duration as soon as possible after the program returns. Previously, the duration included u64_stats_t operations. While the instrumentation overhead is part of the total time spent when stats are enabled, distinguishing between the program's native execution time and the time spent due to instrumentation is crucial for accurate performance analysis. By making this change, the patch facilitates more precise optimization of BPF programs, enabling users to understand their performance in environments without stats enabled. I used a virtualized environment to measure the run-time over one minute for a basic raw_tracepoint/sys_enter program, which just increments a local counter. Although the virtualization introduced some performance degradation that could affect the results, I observed approximately a 16% decrease in average run-time reported by stats with this change (310 -> 260 nsec). Signed-off-by: Jose Fernandez Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240402034010.25060-1-josef@netflix.com --- include/linux/filter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 44934b968b57..531b36090122 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -654,14 +654,16 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; - u64 start = sched_clock(); + u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + + duration = sched_clock() - start; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); - u64_stats_add(&stats->nsecs, sched_clock() - start); + u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); -- cgit v1.2.3 From 7bdbf7446305cb65c510c16d57cde82bc76b234a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 1 Apr 2024 19:13:02 -0700 Subject: bpf: add special internal-only MOV instruction to resolve per-CPU addrs Add a new BPF instruction for resolving absolute addresses of per-CPU data from their per-CPU offsets. This instruction is internal-only and users are not allowed to use them directly. They will only be used for internal inlining optimizations for now between BPF verifier and BPF JITs. We use a special BPF_MOV | BPF_ALU64 | BPF_X form with insn->off field set to BPF_ADDR_PERCPU = -1. I used negative offset value to distinguish them from positive ones used by user-exposed instructions. Such instruction performs a resolution of a per-CPU offset stored in a register to a valid kernel address which can be dereferenced. It is useful in any use case where absolute address of a per-CPU data has to be resolved (e.g., in inlining bpf_map_lookup_elem()). BPF disassembler is also taught to recognize them to support dumping final BPF assembly code (non-JIT'ed version). Add arch-specific way for BPF JITs to mark support for this instructions. This patch also adds support for these instructions in x86-64 BPF JIT. Signed-off-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/r/20240402021307.1012571-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 531b36090122..161d5f7b64ed 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -178,6 +178,25 @@ struct ctl_table_header; .off = 0, \ .imm = 0 }) +/* Special (internal-only) form of mov, used to resolve per-CPU addrs: + * dst_reg = src_reg + + * BPF_ADDR_PERCPU is used as a special insn->off value. + */ +#define BPF_ADDR_PERCPU (-1) + +#define BPF_MOV64_PERCPU_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = BPF_ADDR_PERCPU, \ + .imm = 0 }) + +static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; +} + /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ @@ -972,6 +991,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_jit_supports_subprog_tailcalls(void); +bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); -- cgit v1.2.3 From f91717007217d975aa975ddabd91ae1a107b9bff Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 3 Apr 2024 14:33:03 +0200 Subject: bpf: Pack struct bpf_fib_lookup The struct bpf_fib_lookup is supposed to be of size 64. A recent commit 59b418c7063d ("bpf: Add a check for struct bpf_fib_lookup size") added a static assertion to check this property so that future changes to the structure will not accidentally break this assumption. As it immediately turned out, on some 32-bit arm systems, when AEABI=n, the total size of the structure was equal to 68, see [1]. This happened because the bpf_fib_lookup structure contains a union of two 16-bit fields: union { __u16 tot_len; __u16 mtu_result; }; which was supposed to compile to a 16-bit-aligned 16-bit field. On the aforementioned setups it was instead both aligned and padded to 32-bits. Declare this inner union as __attribute__((packed, aligned(2))) such that it always is of size 2 and is aligned to 16 bits. [1] https://lore.kernel.org/all/CA+G9fYtsoP51f-oP_Sp5MOq-Ffv8La2RztNpwvE6+R1VtFiLrw@mail.gmail.com/#t Reported-by: Naresh Kamboju Fixes: e1850ea9bd9e ("bpf: bpf_fib_lookup return MTU value as output when looked up") Signed-off-by: Anton Protopopov Signed-off-by: Andrii Nakryiko Reviewed-by: Alexander Lobakin Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240403123303.1452184-1-aspsk@isovalent.com --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 79c548276b6b..6fe9f11c8abe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7157,7 +7157,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ -- cgit v1.2.3 From 0a525621b7e5b49202b19d8f75382c6778fdd0c1 Mon Sep 17 00:00:00 2001 From: Philo Lu Date: Fri, 5 Apr 2024 10:55:34 +0800 Subject: bpf: store both map ptr and state in bpf_insn_aux_data Currently, bpf_insn_aux_data->map_ptr_state is used to store either map_ptr or its poison state (i.e., BPF_MAP_PTR_POISON). Thus BPF_MAP_PTR_POISON must be checked before reading map_ptr. In certain cases, we may need valid map_ptr even in case of poison state. This will be explained in next patch with bpf_for_each_map_elem() helper. This patch changes map_ptr_state into a new struct including both map pointer and its state (poison/unpriv). It's in the same union with struct bpf_loop_inline_state, so there is no extra memory overhead. Besides, macros BPF_MAP_PTR_UNPRIV/BPF_MAP_PTR_POISON/BPF_MAP_PTR are no longer needed. This patch does not change any existing functionality. Signed-off-by: Philo Lu Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20240405025536.18113-2-lulie@linux.alibaba.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7cb1b75eee38..36d19cd32eb5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -502,6 +502,13 @@ struct bpf_loop_inline_state { u32 callback_subprogno; /* valid when fit_for_inline is true */ }; +/* pointer and state for maps */ +struct bpf_map_ptr_state { + struct bpf_map *map_ptr; + bool poison; + bool unpriv; +}; + /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) @@ -514,7 +521,7 @@ struct bpf_loop_inline_state { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - unsigned long map_ptr_state; /* pointer/poison value for maps */ + struct bpf_map_ptr_state map_ptr_state; s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { -- cgit v1.2.3 From d503a04f8bc0c75dc9db9452d8cc79d748afb752 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 5 Apr 2024 16:11:33 -0700 Subject: bpf: Add support for certain atomics in bpf_arena to x86 JIT Support atomics in bpf_arena that can be JITed as a single x86 instruction. Instructions that are JITed as loops are not supported at the moment, since they require more complex extable and loop logic. JITs can choose to do smarter things with bpf_jit_supports_insn(). Like arm64 may decide to support all bpf atomics instructions when emit_lse_atomic is available and none in ll_sc mode. bpf_jit_supports_percpu_insn(), bpf_jit_supports_ptr_xchg() and other such callbacks can be replaced with bpf_jit_supports_insn() in the future. Signed-off-by: Alexei Starovoitov Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240405231134.17274-1-alexei.starovoitov@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/filter.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 161d5f7b64ed..7a27f19bf44d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -75,6 +75,9 @@ struct ctl_table_header; /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 +/* unused opcode to mark special atomic instruction */ +#define BPF_PROBE_ATOMIC 0xe0 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -997,6 +1000,7 @@ bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); -- cgit v1.2.3 From 699c23f02c65cbfc3e638f14ce0d70c23a2e1f02 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 9 Apr 2024 21:35:27 -0700 Subject: bpf: Add bpf_link support for sk_msg and sk_skb progs Add bpf_link support for sk_msg and sk_skb programs. We have an internal request to support bpf_link for sk_msg programs so user space can have a uniform handling with bpf_link based libbpf APIs. Using bpf_link based libbpf API also has a benefit which makes system robust by decoupling prog life cycle and attachment life cycle. Reviewed-by: John Fastabend Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20240410043527.3737160-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++++ include/linux/skmsg.h | 4 ++++ include/uapi/linux/bpf.h | 5 +++++ 3 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 62762390c93d..5034c1b4ded7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2996,6 +2996,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); @@ -3094,6 +3095,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd2799..9c8dd4c01412 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -58,6 +58,10 @@ struct sk_psock_progs { struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; + struct bpf_link *msg_parser_link; + struct bpf_link *stream_parser_link; + struct bpf_link *stream_verdict_link; + struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6fe9f11c8abe..cee0a7915c08 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1135,6 +1135,7 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, + BPF_LINK_TYPE_SOCKMAP = 14, __MAX_BPF_LINK_TYPE, }; @@ -6724,6 +6725,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; }; } __attribute__((aligned(8))); -- cgit v1.2.3 From d56b63cf0c0f71e1b2e04dd8220b408f049e67ff Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Sat, 20 Apr 2024 11:09:05 +0200 Subject: bpf: add support for bpf_wq user type Mostly a copy/paste from the bpf_timer API, without the initialization and free, as they will be done in a separate patch. Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20240420-bpf_wq-v2-5-6c986a5a741f@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 ++++++++++- include/uapi/linux/bpf.h | 4 ++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5034c1b4ded7..c7dcfd395555 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -185,7 +185,7 @@ struct bpf_map_ops { enum { /* Support at most 10 fields in a BTF type */ - BTF_FIELDS_MAX = 10, + BTF_FIELDS_MAX = 11, }; enum btf_field_type { @@ -202,6 +202,7 @@ enum btf_field_type { BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), + BPF_WORKQUEUE = (1 << 10), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -238,6 +239,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int wq_off; int refcount_off; struct btf_field fields[]; }; @@ -312,6 +314,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; + case BPF_WORKQUEUE: + return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; @@ -340,6 +344,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); + case BPF_WORKQUEUE: + return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -367,6 +373,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); + case BPF_WORKQUEUE: + return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -406,6 +414,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cee0a7915c08..e4ae83550fb3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7306,6 +7306,10 @@ struct bpf_timer { __u64 __opaque[2]; } __attribute__((aligned(8))); +struct bpf_wq { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + struct bpf_dynptr { __u64 __opaque[2]; } __attribute__((aligned(8))); -- cgit v1.2.3 From 246331e3f1eac905170a923f0ec76725c2558232 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Sat, 20 Apr 2024 11:09:09 +0200 Subject: bpf: allow struct bpf_wq to be embedded in arraymaps and hashmaps Currently bpf_wq_cancel_and_free() is just a placeholder as there is no memory allocation for bpf_wq just yet. Again, duplication of the bpf_timer approach Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20240420-bpf_wq-v2-9-6c986a5a741f@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c7dcfd395555..64bf0cf3ee95 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -534,6 +534,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); +void bpf_wq_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, @@ -2204,6 +2205,7 @@ void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); +void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); -- cgit v1.2.3 From 81f1d7a583fa1fa14f0c4e6140d34b5e3d08d227 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Sat, 20 Apr 2024 11:09:13 +0200 Subject: bpf: wq: add bpf_wq_set_callback_impl To support sleepable async callbacks, we need to tell push_async_cb() whether the cb is sleepable or not. The verifier now detects that we are in bpf_wq_set_callback_impl and can allow a sleepable callback to happen. Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20240420-bpf_wq-v2-13-6c986a5a741f@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 36d19cd32eb5..9db35530c878 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -426,6 +426,7 @@ struct bpf_verifier_state { * while they are still in use. */ bool used_as_loop_entry; + bool in_sleepable; /* first and last insn idx of this verifier state */ u32 first_insn_idx; -- cgit v1.2.3 From fc7566ad0a826cdc8886c5dbbb39ce72a0dc6333 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Wed, 24 Apr 2024 03:13:14 +0000 Subject: bpf: Introduce bpf_preempt_[disable,enable] kfuncs Introduce two new BPF kfuncs, bpf_preempt_disable and bpf_preempt_enable. These kfuncs allow disabling preemption in BPF programs. Nesting is allowed, since the intended use cases includes building native BPF spin locks without kernel helper involvement. Apart from that, this can be used to per-CPU data structures for cases where programs (or userspace) may preempt one or the other. Currently, while per-CPU access is stable, whether it will be consistent is not guaranteed, as only migration is disabled for BPF programs. Global functions are disallowed from being called, but support for them will be added as a follow up not just preempt kfuncs, but rcu_read_lock kfuncs as well. Static subprog calls are permitted. Sleepable helpers and kfuncs are disallowed in non-preemptible regions. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20240424031315.2757363-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 9db35530c878..50aa87f8d77f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -421,6 +421,7 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + u32 active_preempt_lock; /* If this state was ever pointed-to by other state's loop_entry field * this flag would be set to true. Used to avoid freeing such states * while they are still in use. -- cgit v1.2.3 From 95c07d58250ca3ed01855c20be568cf04e15382f Mon Sep 17 00:00:00 2001 From: Haiyue Wang Date: Wed, 24 Apr 2024 13:45:07 +0800 Subject: bpf: update the comment for BTF_FIELDS_MAX The commit d56b63cf0c0f ("bpf: add support for bpf_wq user type") changes the fields support number to 11, just sync the comment. Signed-off-by: Haiyue Wang Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20240424054526.8031-1-haiyue.wang@intel.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 64bf0cf3ee95..978200f6d925 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -184,7 +184,7 @@ struct bpf_map_ops { }; enum { - /* Support at most 10 fields in a BTF type */ + /* Support at most 11 fields in a BTF type */ BTF_FIELDS_MAX = 11, }; -- cgit v1.2.3 From 3e1c6f35409f9e447bf37f64840f5b65576bfb78 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Mon, 22 Apr 2024 15:50:21 -0700 Subject: bpf: make common crypto API for TC/XDP programs Add crypto API support to BPF to be able to decrypt or encrypt packets in TC/XDP BPF programs. Special care should be taken for initialization part of crypto algo because crypto alloc) doesn't work with preemtion disabled, it can be run only in sleepable BPF program. Also async crypto is not supported because of the very same issue - TC/XDP BPF programs are not sleepable. Signed-off-by: Vadim Fedorenko Link: https://lore.kernel.org/r/20240422225024.2847039-2-vadfed@meta.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 1 + include/linux/bpf_crypto.h | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) create mode 100644 include/linux/bpf_crypto.h (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 978200f6d925..364563b74db6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1275,6 +1275,7 @@ int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); +bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); diff --git a/include/linux/bpf_crypto.h b/include/linux/bpf_crypto.h new file mode 100644 index 000000000000..a41e71d4e2d9 --- /dev/null +++ b/include/linux/bpf_crypto.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#ifndef _BPF_CRYPTO_H +#define _BPF_CRYPTO_H + +struct bpf_crypto_type { + void *(*alloc_tfm)(const char *algo); + void (*free_tfm)(void *tfm); + int (*has_algo)(const char *algo); + int (*setkey)(void *tfm, const u8 *key, unsigned int keylen); + int (*setauthsize)(void *tfm, unsigned int authsize); + int (*encrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + int (*decrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + unsigned int (*ivsize)(void *tfm); + unsigned int (*statesize)(void *tfm); + u32 (*get_flags)(void *tfm); + struct module *owner; + char name[14]; +}; + +int bpf_crypto_register_type(const struct bpf_crypto_type *type); +int bpf_crypto_unregister_type(const struct bpf_crypto_type *type); + +#endif /* _BPF_CRYPTO_H */ -- cgit v1.2.3 From 48e2cd3e3dcfe04f212df4fb189fa04c2a87b980 Mon Sep 17 00:00:00 2001 From: Philo Lu Date: Fri, 26 Apr 2024 00:17:23 +0800 Subject: bpf: add mrtt and srtt as BPF_SOCK_OPS_RTT_CB args Two important arguments in RTT estimation, mrtt and srtt, are passed to tcp_bpf_rtt(), so that bpf programs get more information about RTT computation in BPF_SOCK_OPS_RTT_CB. The difference between bpf_sock_ops->srtt_us and the srtt here is: the former is an old rtt before update, while srtt passed by tcp_bpf_rtt() is that after update. Signed-off-by: Philo Lu Link: https://lore.kernel.org/r/20240425161724.73707-2-lulie@linux.alibaba.com Signed-off-by: Martin KaFai Lau --- include/net/tcp.h | 4 ++-- include/uapi/linux/bpf.h | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 6ae35199d3b3..0f75d03287c2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2706,10 +2706,10 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } -static inline void tcp_bpf_rtt(struct sock *sk) +static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) - tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); + tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt); } #if IS_ENABLED(CONFIG_SMC) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e4ae83550fb3..d94a72593ead 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6947,6 +6947,8 @@ enum { * socket transition to LISTEN state. */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + * Arg1: measured RTT input (mrtt) + * Arg2: updated srtt */ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. * It will be called to handle -- cgit v1.2.3