diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index e6b4ebb2b243..4443ce958862 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -1125,6 +1125,14 @@ pointer type. The types of pointers describe their base, as follows: PTR_TO_STACK Frame pointer. PTR_TO_PACKET skb->data. PTR_TO_PACKET_END skb->data + headlen; arithmetic forbidden. + PTR_TO_SOCKET Pointer to struct bpf_sock_ops, implicitly refcounted. + PTR_TO_SOCKET_OR_NULL + Either a pointer to a socket, or NULL; socket lookup + returns this type, which becomes a PTR_TO_SOCKET when + checked != NULL. PTR_TO_SOCKET is reference-counted, + so programs must release the reference through the + socket release function before the end of the program. + Arithmetic on these pointers is forbidden. However, a pointer may be offset from this base (as a result of pointer arithmetic), and this is tracked in two parts: the 'fixed offset' and 'variable offset'. The former is used when an exactly-known value (e.g. an immediate @@ -1171,6 +1179,13 @@ over the Ethernet header, then reads IHL and addes (IHL * 4), the resulting pointer will have a variable offset known to be 4n+2 for some n, so adding the 2 bytes (NET_IP_ALIGN) gives a 4-byte alignment and so word-sized accesses through that pointer are safe. +The 'id' field is also used on PTR_TO_SOCKET and PTR_TO_SOCKET_OR_NULL, common +to all copies of the pointer returned from a socket lookup. This has similar +behaviour to the handling for PTR_TO_MAP_VALUE_OR_NULL->PTR_TO_MAP_VALUE, but +it also handles reference tracking for the pointer. PTR_TO_SOCKET implicitly +represents a reference to the corresponding 'struct sock'. To ensure that the +reference is not leaked, it is imperative to NULL-check the reference and in +the non-NULL case, and pass the valid reference to the socket release function. Direct packet access -------------------- @@ -1444,6 +1459,55 @@ Error: 8: (7a) *(u64 *)(r0 +0) = 1 R0 invalid mem access 'imm' +Program that performs a socket lookup then sets the pointer to NULL without +checking it: +value: + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), +Error: + 0: (b7) r2 = 0 + 1: (63) *(u32 *)(r10 -8) = r2 + 2: (bf) r2 = r10 + 3: (07) r2 += -8 + 4: (b7) r3 = 4 + 5: (b7) r4 = 0 + 6: (b7) r5 = 0 + 7: (85) call bpf_sk_lookup_tcp#65 + 8: (b7) r0 = 0 + 9: (95) exit + Unreleased reference id=1, alloc_insn=7 + +Program that performs a socket lookup but does not NULL-check the returned +value: + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp), + BPF_EXIT_INSN(), +Error: + 0: (b7) r2 = 0 + 1: (63) *(u32 *)(r10 -8) = r2 + 2: (bf) r2 = r10 + 3: (07) r2 += -8 + 4: (b7) r3 = 4 + 5: (b7) r4 = 0 + 6: (b7) r5 = 0 + 7: (85) call bpf_sk_lookup_tcp#65 + 8: (95) exit + Unreleased reference id=1, alloc_insn=7 + Testing ------- diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 018299a595c8..027697b6a22f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -154,6 +154,7 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ + ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */ }; /* type of values returned from helper functions */ @@ -162,6 +163,7 @@ enum bpf_return_type { RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ + RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -213,6 +215,8 @@ enum bpf_reg_type { PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ + PTR_TO_SOCKET, /* reg points to struct bpf_sock */ + PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -343,6 +347,11 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); +typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, + const struct bpf_insn *src, + struct bpf_insn *dst, + struct bpf_prog *prog, + u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); @@ -836,4 +845,29 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +#if defined(CONFIG_NET) +bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); +u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); +#else +static inline bool bpf_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} +static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} +#endif + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b42b60a83e19..7b6fd2ab3263 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -58,6 +58,8 @@ struct bpf_reg_state { * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. + * For PTR_TO_SOCKET this is used to share which pointers retain the + * same reference to the socket, to determine proper reference freeing. */ u32 id; /* For scalar types (SCALAR_VALUE), this represents our knowledge of @@ -102,6 +104,17 @@ struct bpf_stack_state { u8 slot_type[BPF_REG_SIZE]; }; +struct bpf_reference_state { + /* Track each reference created with a unique id, even if the same + * instruction creates the reference multiple times (eg, via CALL). + */ + int id; + /* Instruction where the allocation of this reference occurred. This + * is used purely to inform the user of a reference leak. + */ + int insn_idx; +}; + /* state of the program: * type of all registers and stack info */ @@ -119,7 +132,9 @@ struct bpf_func_state { */ u32 subprogno; - /* should be second to last. See copy_func_state() */ + /* The following fields should be last. See copy_func_state() */ + int acquired_refs; + struct bpf_reference_state *refs; int allocated_stack; struct bpf_stack_state *stack; }; @@ -131,6 +146,17 @@ struct bpf_verifier_state { u32 curframe; }; +#define bpf_get_spilled_reg(slot, frame) \ + (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ + (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ? &frame->stack[slot].spilled_ptr : NULL) + +/* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ +#define bpf_for_each_spilled_reg(iter, frame, reg) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ + iter < frame->allocated_stack / BPF_REG_SIZE; \ + iter++, reg = bpf_get_spilled_reg(iter, frame)) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; @@ -204,11 +230,16 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); -static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; - return cur->frame[cur->curframe]->regs; + return cur->frame[cur->curframe]; +} + +static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +{ + return cur_func(env)->regs; } int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e2070d819e04..f9187b41dff6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2144,6 +2144,77 @@ union bpf_attr { * request in the skb. * Return * 0 on success, or a negative error in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * int bpf_sk_release(struct bpf_sock *sk) + * Description + * Release the reference held by *sock*. *sock* must be a non-NULL + * pointer that was returned from bpf_sk_lookup_xxx\ (). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2229,7 +2300,10 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2399,6 +2473,23 @@ struct bpf_sock { */ }; +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a8cc83a970d1..73c81bef6ae8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1,5 +1,6 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook + * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -80,8 +81,8 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register - * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer - * types recognized by check_mem_access() function. + * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are + * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. @@ -140,6 +141,24 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. + * + * The following reference types represent a potential reference to a kernel + * resource which, after first being allocated, must be checked and freed by + * the BPF program: + * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET + * + * When the verifier sees a helper call return a reference type, it allocates a + * pointer id for the reference and stores it in the current function state. + * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into + * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type + * passes through a NULL-check conditional. For the branch wherein the state is + * changed to CONST_IMM, the verifier releases the reference. + * + * For each helper function that allocates a reference, such as + * bpf_sk_lookup_tcp(), there is a corresponding release function, such as + * bpf_sk_release(). When a reference type passes into the release function, + * the verifier also releases the reference. If any unchecked or unreleased + * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ @@ -189,6 +208,7 @@ struct bpf_call_arg_meta { int access_size; s64 msize_smax_value; u64 msize_umax_value; + int ptr_id; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -249,6 +269,46 @@ static bool type_is_pkt_pointer(enum bpf_reg_type type) type == PTR_TO_PACKET_META; } +static bool reg_type_may_be_null(enum bpf_reg_type type) +{ + return type == PTR_TO_MAP_VALUE_OR_NULL || + type == PTR_TO_SOCKET_OR_NULL; +} + +static bool type_is_refcounted(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET; +} + +static bool type_is_refcounted_or_null(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL; +} + +static bool reg_is_refcounted(const struct bpf_reg_state *reg) +{ + return type_is_refcounted(reg->type); +} + +static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) +{ + return type_is_refcounted_or_null(reg->type); +} + +static bool arg_type_is_refcounted(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_SOCKET; +} + +/* Determine whether the function releases some resources allocated by another + * function call. The first reference type argument will be assumed to be + * released by release_reference(). + */ +static bool is_release_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_sk_release; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -262,6 +322,8 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", }; static char slot_type_char[] = { @@ -378,62 +440,158 @@ static void print_verifier_state(struct bpf_verifier_env *env, else verbose(env, "=%s", types_buf); } + if (state->acquired_refs && state->refs[0].id) { + verbose(env, " refs=%d", state->refs[0].id); + for (i = 1; i < state->acquired_refs; i++) + if (state->refs[i].id) + verbose(env, ",%d", state->refs[i].id); + } verbose(env, "\n"); } -static int copy_stack_state(struct bpf_func_state *dst, - const struct bpf_func_state *src) -{ - if (!src->stack) - return 0; - if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) { - /* internal bug, make state invalid to reject the program */ - memset(dst, 0, sizeof(*dst)); - return -EFAULT; - } - memcpy(dst->stack, src->stack, - sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE)); - return 0; +#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \ +static int copy_##NAME##_state(struct bpf_func_state *dst, \ + const struct bpf_func_state *src) \ +{ \ + if (!src->FIELD) \ + return 0; \ + if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \ + /* internal bug, make state invalid to reject the program */ \ + memset(dst, 0, sizeof(*dst)); \ + return -EFAULT; \ + } \ + memcpy(dst->FIELD, src->FIELD, \ + sizeof(*src->FIELD) * (src->COUNT / SIZE)); \ + return 0; \ } +/* copy_reference_state() */ +COPY_STATE_FN(reference, acquired_refs, refs, 1) +/* copy_stack_state() */ +COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) +#undef COPY_STATE_FN + +#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \ +static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \ + bool copy_old) \ +{ \ + u32 old_size = state->COUNT; \ + struct bpf_##NAME##_state *new_##FIELD; \ + int slot = size / SIZE; \ + \ + if (size <= old_size || !size) { \ + if (copy_old) \ + return 0; \ + state->COUNT = slot * SIZE; \ + if (!size && old_size) { \ + kfree(state->FIELD); \ + state->FIELD = NULL; \ + } \ + return 0; \ + } \ + new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \ + GFP_KERNEL); \ + if (!new_##FIELD) \ + return -ENOMEM; \ + if (copy_old) { \ + if (state->FIELD) \ + memcpy(new_##FIELD, state->FIELD, \ + sizeof(*new_##FIELD) * (old_size / SIZE)); \ + memset(new_##FIELD + old_size / SIZE, 0, \ + sizeof(*new_##FIELD) * (size - old_size) / SIZE); \ + } \ + state->COUNT = slot * SIZE; \ + kfree(state->FIELD); \ + state->FIELD = new_##FIELD; \ + return 0; \ +} +/* realloc_reference_state() */ +REALLOC_STATE_FN(reference, acquired_refs, refs, 1) +/* realloc_stack_state() */ +REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) +#undef REALLOC_STATE_FN /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from * the program calls into realloc_func_state() to grow the stack size. - * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state - * which this function copies over. It points to corresponding reg in previous - * bpf_verifier_state which is never reallocated + * Note there is a non-zero 'parent' pointer inside bpf_verifier_state + * which realloc_stack_state() copies over. It points to previous + * bpf_verifier_state which is never reallocated. */ -static int realloc_func_state(struct bpf_func_state *state, int size, - bool copy_old) +static int realloc_func_state(struct bpf_func_state *state, int stack_size, + int refs_size, bool copy_old) { - u32 old_size = state->allocated_stack; - struct bpf_stack_state *new_stack; - int slot = size / BPF_REG_SIZE; + int err = realloc_reference_state(state, refs_size, copy_old); + if (err) + return err; + return realloc_stack_state(state, stack_size, copy_old); +} - if (size <= old_size || !size) { - if (copy_old) +/* Acquire a pointer id from the env and update the state->refs to include + * this new pointer reference. + * On success, returns a valid pointer id to associate with the register + * On failure, returns a negative errno. + */ +static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) +{ + struct bpf_func_state *state = cur_func(env); + int new_ofs = state->acquired_refs; + int id, err; + + err = realloc_reference_state(state, state->acquired_refs + 1, true); + if (err) + return err; + id = ++env->id_gen; + state->refs[new_ofs].id = id; + state->refs[new_ofs].insn_idx = insn_idx; + + return id; +} + +/* release function corresponding to acquire_reference_state(). Idempotent. */ +static int __release_reference_state(struct bpf_func_state *state, int ptr_id) +{ + int i, last_idx; + + if (!ptr_id) + return -EFAULT; + + last_idx = state->acquired_refs - 1; + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].id == ptr_id) { + if (last_idx && i != last_idx) + memcpy(&state->refs[i], &state->refs[last_idx], + sizeof(*state->refs)); + memset(&state->refs[last_idx], 0, sizeof(*state->refs)); + state->acquired_refs--; return 0; - state->allocated_stack = slot * BPF_REG_SIZE; - if (!size && old_size) { - kfree(state->stack); - state->stack = NULL; } - return 0; } - new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state), - GFP_KERNEL); - if (!new_stack) - return -ENOMEM; - if (copy_old) { - if (state->stack) - memcpy(new_stack, state->stack, - sizeof(*new_stack) * (old_size / BPF_REG_SIZE)); - memset(new_stack + old_size / BPF_REG_SIZE, 0, - sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE); - } - state->allocated_stack = slot * BPF_REG_SIZE; - kfree(state->stack); - state->stack = new_stack; + return -EFAULT; +} + +/* variation on the above for cases where we expect that there must be an + * outstanding reference for the specified ptr_id. + */ +static int release_reference_state(struct bpf_verifier_env *env, int ptr_id) +{ + struct bpf_func_state *state = cur_func(env); + int err; + + err = __release_reference_state(state, ptr_id); + if (WARN_ON_ONCE(err != 0)) + verbose(env, "verifier internal error: can't release reference\n"); + return err; +} + +static int transfer_reference_state(struct bpf_func_state *dst, + struct bpf_func_state *src) +{ + int err = realloc_reference_state(dst, src->acquired_refs, false); + if (err) + return err; + err = copy_reference_state(dst, src); + if (err) + return err; return 0; } @@ -441,6 +599,7 @@ static void free_func_state(struct bpf_func_state *state) { if (!state) return; + kfree(state->refs); kfree(state->stack); kfree(state); } @@ -466,10 +625,14 @@ static int copy_func_state(struct bpf_func_state *dst, { int err; - err = realloc_func_state(dst, src->allocated_stack, false); + err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs, + false); + if (err) + return err; + memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); + err = copy_reference_state(dst, src); if (err) return err; - memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack)); return copy_stack_state(dst, src); } @@ -968,6 +1131,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: return true; default: return false; @@ -992,7 +1157,7 @@ static int check_stack_write(struct bpf_verifier_env *env, enum bpf_reg_type type; err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), - true); + state->acquired_refs, true); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, @@ -1336,6 +1501,28 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } +static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, + int size, enum bpf_access_type t) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + struct bpf_insn_access_aux info; + + if (reg->smin_value < 0) { + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + regno); + return -EACCES; + } + + if (!bpf_sock_is_valid_access(off, size, t, &info)) { + verbose(env, "invalid bpf_sock access off=%d size=%d\n", + off, size); + return -EACCES; + } + + return 0; +} + static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -1354,7 +1541,8 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = cur_regs(env) + regno; - return reg->type == PTR_TO_CTX; + return reg->type == PTR_TO_CTX || + reg->type == PTR_TO_SOCKET; } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) @@ -1454,6 +1642,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, */ strict = true; break; + case PTR_TO_SOCKET: + pointer_desc = "sock "; + break; default: break; } @@ -1721,6 +1912,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_SOCKET) { + if (t == BPF_WRITE) { + verbose(env, "cannot write into socket\n"); + return -EACCES; + } + err = check_sock_access(env, regno, off, size, t); + if (!err && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -1763,8 +1962,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg)) { verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", - insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ? - "context" : "packet"); + insn->dst_reg, reg_type_str[insn->dst_reg]); return -EACCES; } @@ -1944,6 +2142,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_ctx_reg(env, reg, regno); if (err < 0) return err; + } else if (arg_type == ARG_PTR_TO_SOCKET) { + expected_type = PTR_TO_SOCKET; + if (type != expected_type) + goto err_type; + if (meta->ptr_id || !reg->id) { + verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n", + meta->ptr_id, reg->id); + return -EFAULT; + } + meta->ptr_id = reg->id; } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2233,10 +2441,32 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) return true; } +static bool check_refcount_ok(const struct bpf_func_proto *fn) +{ + int count = 0; + + if (arg_type_is_refcounted(fn->arg1_type)) + count++; + if (arg_type_is_refcounted(fn->arg2_type)) + count++; + if (arg_type_is_refcounted(fn->arg3_type)) + count++; + if (arg_type_is_refcounted(fn->arg4_type)) + count++; + if (arg_type_is_refcounted(fn->arg5_type)) + count++; + + /* We only support one arg being unreferenced at the moment, + * which is sufficient for the helper functions we have right now. + */ + return count <= 1; +} + static int check_func_proto(const struct bpf_func_proto *fn) { return check_raw_mode_ok(fn) && - check_arg_pair_ok(fn) ? 0 : -EINVAL; + check_arg_pair_ok(fn) && + check_refcount_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2252,10 +2482,9 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(env, regs, i); - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg_is_pkt_pointer_any(reg)) __mark_reg_unknown(reg); } @@ -2270,12 +2499,45 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) __clear_all_pkt_pointers(env, vstate->frame[i]); } +static void release_reg_references(struct bpf_verifier_env *env, + struct bpf_func_state *state, int id) +{ + struct bpf_reg_state *regs = state->regs, *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) + if (regs[i].id == id) + mark_reg_unknown(env, regs, i); + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + if (reg_is_refcounted(reg) && reg->id == id) + __mark_reg_unknown(reg); + } +} + +/* The pointer with the specified id has released its reference to kernel + * resources. Identify all copies of the same pointer and clear the reference. + */ +static int release_reference(struct bpf_verifier_env *env, + struct bpf_call_arg_meta *meta) +{ + struct bpf_verifier_state *vstate = env->cur_state; + int i; + + for (i = 0; i <= vstate->curframe; i++) + release_reg_references(env, vstate->frame[i], meta->ptr_id); + + return release_reference_state(env, meta->ptr_id); +} + static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; - int i, subprog, target_insn; + int i, err, subprog, target_insn; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -2313,6 +2575,11 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); + /* Transfer references to the callee */ + err = transfer_reference_state(callee, caller); + if (err) + return err; + /* copy r1 - r5 args that callee can access. The copy includes parent * pointers, which connects us up to the liveness chain */ @@ -2345,6 +2612,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; + int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; @@ -2364,6 +2632,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; + /* Transfer references to the caller */ + err = transfer_reference_state(caller, callee); + if (err) + return err; + *insn_idx = callee->callsite + 1; if (env->log.level) { verbose(env, "returning from callee:\n"); @@ -2420,6 +2693,18 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } +static int check_reference_leak(struct bpf_verifier_env *env) +{ + struct bpf_func_state *state = cur_func(env); + int i; + + for (i = 0; i < state->acquired_refs; i++) { + verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", + state->refs[i].id, state->refs[i].insn_idx); + } + return state->acquired_refs ? -EINVAL : 0; +} + static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; @@ -2498,6 +2783,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + if (func_id == BPF_FUNC_tail_call) { + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + } else if (is_release_function(func_id)) { + err = release_reference(env, &meta); + if (err) + return err; + } + regs = cur_regs(env); /* check that flags argument in get_local_storage(map, flags) is 0, @@ -2540,6 +2837,13 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + int id = acquire_reference_state(env, insn_idx); + if (id < 0) + return id; + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; + regs[BPF_REG_0].id = id; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -2670,20 +2974,20 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", - dst); + switch (ptr_reg->type) { + case PTR_TO_MAP_VALUE_OR_NULL: + verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", + dst, reg_type_str[ptr_reg->type]); return -EACCES; - } - if (ptr_reg->type == CONST_PTR_TO_MAP) { - verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", - dst); - return -EACCES; - } - if (ptr_reg->type == PTR_TO_PACKET_END) { - verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", - dst); + case CONST_PTR_TO_MAP: + case PTR_TO_PACKET_END: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: + verbose(env, "R%d pointer arithmetic on %s prohibited\n", + dst, reg_type_str[ptr_reg->type]); return -EACCES; + default: + break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. @@ -3395,10 +3699,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg->type == type && reg->id == dst_reg->id) reg->range = max(reg->range, new_range); } @@ -3604,12 +3907,11 @@ static void reg_combine_min_max(struct bpf_reg_state *true_src, } } -static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, - bool is_null) +static void mark_ptr_or_null_reg(struct bpf_func_state *state, + struct bpf_reg_state *reg, u32 id, + bool is_null) { - struct bpf_reg_state *reg = ®s[regno]; - - if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) { + if (reg_type_may_be_null(reg->type) && reg->id == id) { /* Old offset (both fixed and variable parts) should * have been known-zero, because we don't allow pointer * arithmetic on pointers that might be NULL. @@ -3622,40 +3924,49 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, } if (is_null) { reg->type = SCALAR_VALUE; - } else if (reg->map_ptr->inner_map_meta) { - reg->type = CONST_PTR_TO_MAP; - reg->map_ptr = reg->map_ptr->inner_map_meta; - } else { - reg->type = PTR_TO_MAP_VALUE; + } else if (reg->type == PTR_TO_MAP_VALUE_OR_NULL) { + if (reg->map_ptr->inner_map_meta) { + reg->type = CONST_PTR_TO_MAP; + reg->map_ptr = reg->map_ptr->inner_map_meta; + } else { + reg->type = PTR_TO_MAP_VALUE; + } + } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { + reg->type = PTR_TO_SOCKET; + } + if (is_null || !reg_is_refcounted(reg)) { + /* We don't need id from this point onwards anymore, + * thus we should better reset it, so that state + * pruning has chances to take effect. + */ + reg->id = 0; } - /* We don't need id from this point onwards anymore, thus we - * should better reset it, so that state pruning has chances - * to take effect. - */ - reg->id = 0; } } /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ -static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno, - bool is_null) +static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, + bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *reg, *regs = state->regs; u32 id = regs[regno].id; int i, j; + if (reg_is_refcounted_or_null(®s[regno]) && is_null) + __release_reference_state(state, id); + for (i = 0; i < MAX_BPF_REG; i++) - mark_map_reg(regs, i, id, is_null); + mark_ptr_or_null_reg(state, ®s[i], id, is_null); for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null); + mark_ptr_or_null_reg(state, reg, id, is_null); } } } @@ -3857,12 +4168,14 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */ if (BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && - dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - /* Mark all identical map registers in each branch as either + reg_type_may_be_null(dst_reg->type)) { + /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ - mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); - mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); + mark_ptr_or_null_regs(this_branch, insn->dst_reg, + opcode == BPF_JNE); + mark_ptr_or_null_regs(other_branch, insn->dst_reg, + opcode == BPF_JEQ); } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], this_branch, other_branch) && is_pointer_value(env, insn->dst_reg)) { @@ -3985,6 +4298,16 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as + * gen_ld_abs() may terminate the program at runtime, leading to + * reference leak. + */ + err = check_reference_leak(env); + if (err) { + verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); + return err; + } + if (regs[BPF_REG_6].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -4400,6 +4723,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -4475,6 +4800,14 @@ static bool stacksafe(struct bpf_func_state *old, return true; } +static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) +{ + if (old->acquired_refs != cur->acquired_refs) + return false; + return !memcmp(old->refs, cur->refs, + sizeof(*old->refs) * old->acquired_refs); +} + /* compare two verifier states * * all states stored in state_list are known to be valid, since @@ -4520,6 +4853,9 @@ static bool func_states_equal(struct bpf_func_state *old, if (!stacksafe(old, cur, idmap)) goto out_free; + + if (!refsafe(old, cur)) + goto out_free; ret = true; out_free: kfree(idmap); @@ -4677,6 +5013,37 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 0; } +/* Return true if it's OK to have the same insn return a different type. */ +static bool reg_type_mismatch_ok(enum bpf_reg_type type) +{ + switch (type) { + case PTR_TO_CTX: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: + return false; + default: + return true; + } +} + +/* If an instruction was previously used with particular pointer types, then we + * need to be careful to avoid cases such as the below, where it may be ok + * for one branch accessing the pointer, but not ok for the other branch: + * + * R1 = sock_ptr + * goto X; + * ... + * R1 = some_other_valid_ptr; + * goto X; + * ... + * R2 = *(u32 *)(R1 + 0); + */ +static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) +{ + return src != prev && (!reg_type_mismatch_ok(src) || + !reg_type_mismatch_ok(prev)); +} + static int do_check(struct bpf_verifier_env *env) { struct bpf_verifier_state *state; @@ -4770,6 +5137,7 @@ static int do_check(struct bpf_verifier_env *env) regs = cur_regs(env); env->insn_aux_data[insn_idx].seen = true; + if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) @@ -4809,9 +5177,7 @@ static int do_check(struct bpf_verifier_env *env) */ *prev_src_type = src_reg_type; - } else if (src_reg_type != *prev_src_type && - (src_reg_type == PTR_TO_CTX || - *prev_src_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { /* ABuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: @@ -4856,9 +5222,7 @@ static int do_check(struct bpf_verifier_env *env) if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; - } else if (dst_reg_type != *prev_dst_type && - (dst_reg_type == PTR_TO_CTX || - *prev_dst_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -4875,8 +5239,8 @@ static int do_check(struct bpf_verifier_env *env) return err; if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_ST stores into R%d context is not allowed\n", - insn->dst_reg); + verbose(env, "BPF_ST stores into R%d %s is not allowed\n", + insn->dst_reg, reg_type_str[insn->dst_reg]); return -EACCES; } @@ -4938,6 +5302,10 @@ static int do_check(struct bpf_verifier_env *env) continue; } + err = check_reference_leak(env); + if (err) + return err; + /* eBPF calling convetion is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time @@ -5284,8 +5652,10 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) } } -/* convert load instructions that access fields of 'struct __sk_buff' - * into sequence of instructions that access fields of 'struct sk_buff' +/* convert load instructions that access fields of a context type into a + * sequence of instructions that access fields of the underlying structure: + * struct __sk_buff -> struct sk_buff + * struct bpf_sock_ops -> struct sock */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { @@ -5314,12 +5684,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { + bpf_convert_ctx_access_t convert_ctx_access; + if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || @@ -5361,8 +5733,18 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } - if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) + switch (env->insn_aux_data[i + delta].ptr_type) { + case PTR_TO_CTX: + if (!ops->convert_ctx_access) + continue; + convert_ctx_access = ops->convert_ctx_access; + break; + case PTR_TO_SOCKET: + convert_ctx_access = bpf_sock_convert_ctx_access; + break; + default: continue; + } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); @@ -5394,8 +5776,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } target_size = 0; - cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog, - &target_size); + cnt = convert_ctx_access(type, insn, insn_buf, env->prog, + &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); diff --git a/net/core/filter.c b/net/core/filter.c index 72db8afb7cb6..591c698bc517 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -58,13 +58,17 @@ #include #include #include +#include #include #include #include +#include +#include #include #include #include #include +#include #include #include #include @@ -4813,6 +4817,141 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { }; #endif /* CONFIG_IPV6_SEG6_BPF */ +struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, + struct sk_buff *skb, u8 family, u8 proto) +{ + int dif = skb->dev->ifindex; + bool refcounted = false; + struct sock *sk = NULL; + + if (family == AF_INET) { + __be32 src4 = tuple->ipv4.saddr; + __be32 dst4 = tuple->ipv4.daddr; + int sdif = inet_sdif(skb); + + if (proto == IPPROTO_TCP) + sk = __inet_lookup(net, &tcp_hashinfo, skb, 0, + src4, tuple->ipv4.sport, + dst4, tuple->ipv4.dport, + dif, sdif, &refcounted); + else + sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, + dst4, tuple->ipv4.dport, + dif, sdif, &udp_table, skb); +#if IS_ENABLED(CONFIG_IPV6) + } else { + struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; + struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; + int sdif = inet6_sdif(skb); + + if (proto == IPPROTO_TCP) + sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0, + src6, tuple->ipv6.sport, + dst6, tuple->ipv6.dport, + dif, sdif, &refcounted); + else + sk = __udp6_lib_lookup(net, src6, tuple->ipv6.sport, + dst6, tuple->ipv6.dport, + dif, sdif, &udp_table, skb); +#endif + } + + if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + sk = NULL; + } + return sk; +} + +/* bpf_sk_lookup performs the core lookup for different types of sockets, + * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. + * Returns the socket as an 'unsigned long' to simplify the casting in the + * callers to satisfy BPF_CALL declarations. + */ +static unsigned long +bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, + u8 proto, u64 netns_id, u64 flags) +{ + struct net *caller_net; + struct sock *sk = NULL; + u8 family = AF_UNSPEC; + struct net *net; + + family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6; + if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags)) + goto out; + + if (skb->dev) + caller_net = dev_net(skb->dev); + else + caller_net = sock_net(skb->sk); + if (netns_id) { + net = get_net_ns_by_id(caller_net, netns_id); + if (unlikely(!net)) + goto out; + sk = sk_lookup(net, tuple, skb, family, proto); + put_net(net); + } else { + net = caller_net; + sk = sk_lookup(net, tuple, skb, family, proto); + } + + if (sk) + sk = sk_to_full_sk(sk); +out: + return (unsigned long) sk; +} + +BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, + struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) +{ + return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { + .func = bpf_sk_lookup_tcp, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb, + struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) +{ + return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { + .func = bpf_sk_lookup_udp, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_1(bpf_sk_release, struct sock *, sk) +{ + if (!sock_flag(sk, SOCK_RCU_FREE)) + sock_gen_put(sk); + return 0; +} + +static const struct bpf_func_proto bpf_sk_release_proto = { + .func = bpf_sk_release, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_SOCKET, +}; + bool bpf_helper_changes_pkt_data(void *func) { if (func == bpf_skb_vlan_push || @@ -5019,6 +5158,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; #endif + case BPF_FUNC_sk_lookup_tcp: + return &bpf_sk_lookup_tcp_proto; + case BPF_FUNC_sk_lookup_udp: + return &bpf_sk_lookup_udp_proto; + case BPF_FUNC_sk_release: + return &bpf_sk_release_proto; default: return bpf_base_func_proto(func_id); } @@ -5119,6 +5264,12 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_redirect_hash_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_sk_lookup_tcp: + return &bpf_sk_lookup_tcp_proto; + case BPF_FUNC_sk_lookup_udp: + return &bpf_sk_lookup_udp_proto; + case BPF_FUNC_sk_release: + return &bpf_sk_release_proto; default: return bpf_base_func_proto(func_id); } @@ -5394,23 +5545,29 @@ static bool __sock_filter_check_size(int off, int size, return size == size_default; } -static bool sock_filter_is_valid_access(int off, int size, - enum bpf_access_type type, - const struct bpf_prog *prog, - struct bpf_insn_access_aux *info) +bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; - if (!__sock_filter_check_attach_type(off, type, - prog->expected_attach_type)) - return false; if (!__sock_filter_check_size(off, size, info)) return false; return true; } +static bool sock_filter_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (!bpf_sock_is_valid_access(off, size, type, info)) + return false; + return __sock_filter_check_attach_type(off, type, + prog->expected_attach_type); +} + static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog, int drop_verdict) { @@ -6122,10 +6279,10 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, - const struct bpf_insn *si, - struct bpf_insn *insn_buf, - struct bpf_prog *prog, u32 *target_size) +u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; @@ -7037,7 +7194,7 @@ const struct bpf_prog_ops lwt_seg6local_prog_ops = { const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, - .convert_ctx_access = sock_filter_convert_ctx_access, + .convert_ctx_access = bpf_sock_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_prog_ops = { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e2070d819e04..f9187b41dff6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2144,6 +2144,77 @@ union bpf_attr { * request in the skb. * Return * 0 on success, or a negative error in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * int bpf_sk_release(struct bpf_sock *sk) + * Description + * Release the reference held by *sock*. *sock* must be a non-NULL + * pointer that was returned from bpf_sk_lookup_xxx\ (). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2229,7 +2300,10 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2399,6 +2473,23 @@ struct bpf_sock { */ }; +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 425d5ca45c97..9e68fd9fcfca 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -228,7 +228,7 @@ struct bpf_object { }; #define obj_elf_valid(o) ((o)->efile.elf) -static void bpf_program__unload(struct bpf_program *prog) +void bpf_program__unload(struct bpf_program *prog) { int i; @@ -1375,7 +1375,7 @@ out: return ret; } -static int +int bpf_program__load(struct bpf_program *prog, char *license, u32 kern_version) { diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 511c1294dcbf..2ed24d3f80b3 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -128,10 +128,13 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); const char *bpf_program__title(struct bpf_program *prog, bool needs_copy); +int bpf_program__load(struct bpf_program *prog, char *license, + u32 kern_version); int bpf_program__fd(struct bpf_program *prog); int bpf_program__pin_instance(struct bpf_program *prog, const char *path, int instance); int bpf_program__pin(struct bpf_program *prog, const char *path); +void bpf_program__unload(struct bpf_program *prog); struct bpf_insn; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f802de526f57..1381ab81099c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -36,7 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \ test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \ get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \ - test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o + test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index e4be7730222d..1d407b3494f9 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -143,6 +143,18 @@ static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) = (void *) BPF_FUNC_skb_cgroup_id; static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) = (void *) BPF_FUNC_skb_ancestor_cgroup_id; +static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx, + struct bpf_sock_tuple *tuple, + int size, unsigned int netns_id, + unsigned long long flags) = + (void *) BPF_FUNC_sk_lookup_tcp; +static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx, + struct bpf_sock_tuple *tuple, + int size, unsigned int netns_id, + unsigned long long flags) = + (void *) BPF_FUNC_sk_lookup_udp; +static int (*bpf_sk_release)(struct bpf_sock *sk) = + (void *) BPF_FUNC_sk_release; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 63a671803ed6..e8becca9c521 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1698,6 +1698,43 @@ static void test_task_fd_query_tp(void) "sys_enter_read"); } +static void test_reference_tracking() +{ + const char *file = "./test_sk_lookup_kern.o"; + struct bpf_object *obj; + struct bpf_program *prog; + __u32 duration; + int err = 0; + + obj = bpf_object__open(file); + if (IS_ERR(obj)) { + error_cnt++; + return; + } + + bpf_object__for_each_program(prog, obj) { + const char *title; + + /* Ignore .text sections */ + title = bpf_program__title(prog, false); + if (strstr(title, ".text") != NULL) + continue; + + bpf_program__set_type(prog, BPF_PROG_TYPE_SCHED_CLS); + + /* Expect verifier failure if test name has 'fail' */ + if (strstr(title, "fail") != NULL) { + libbpf_set_print(NULL, NULL, NULL); + err = !bpf_program__load(prog, "GPL", 0); + libbpf_set_print(printf, printf, NULL); + } else { + err = bpf_program__load(prog, "GPL", 0); + } + CHECK(err, title, "\n"); + } + bpf_object__close(obj); +} + int main(void) { jit_enabled = is_jit_enabled(); @@ -1719,6 +1756,7 @@ int main(void) test_get_stack_raw_tp(); test_task_fd_query_rawtp(); test_task_fd_query_tp(); + test_reference_tracking(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/test_sk_lookup_kern.c new file mode 100644 index 000000000000..b745bdc08c2b --- /dev/null +++ b/tools/testing/selftests/bpf/test_sk_lookup_kern.c @@ -0,0 +1,180 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; + +/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ +static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off, + void *data_end, __u16 eth_proto, + bool *ipv4) +{ + struct bpf_sock_tuple *result; + __u8 proto = 0; + __u64 ihl_len; + + if (eth_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(data + nh_off); + + if (iph + 1 > data_end) + return NULL; + ihl_len = iph->ihl * 4; + proto = iph->protocol; + *ipv4 = true; + result = (struct bpf_sock_tuple *)&iph->saddr; + } else if (eth_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + nh_off); + + if (ip6h + 1 > data_end) + return NULL; + ihl_len = sizeof(*ip6h); + proto = ip6h->nexthdr; + *ipv4 = true; + result = (struct bpf_sock_tuple *)&ip6h->saddr; + } + + if (data + nh_off + ihl_len > data_end || proto != IPPROTO_TCP) + return NULL; + + return result; +} + +SEC("sk_lookup_success") +int bpf_sk_lookup_test0(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = (struct ethhdr *)(data); + struct bpf_sock_tuple *tuple; + struct bpf_sock *sk; + size_t tuple_len; + bool ipv4; + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + tuple = get_tuple(data, sizeof(*eth), data_end, eth->h_proto, &ipv4); + if (!tuple || tuple + sizeof *tuple > data_end) + return TC_ACT_SHOT; + + tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); + sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, 0, 0); + if (sk) + bpf_sk_release(sk); + return sk ? TC_ACT_OK : TC_ACT_UNSPEC; +} + +SEC("sk_lookup_success_simple") +int bpf_sk_lookup_test1(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + if (sk) + bpf_sk_release(sk); + return 0; +} + +SEC("fail_use_after_free") +int bpf_sk_lookup_uaf(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + __u32 family = 0; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + if (sk) { + bpf_sk_release(sk); + family = sk->family; + } + return family; +} + +SEC("fail_modify_sk_pointer") +int bpf_sk_lookup_modptr(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + __u32 family; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + if (sk) { + sk += 1; + bpf_sk_release(sk); + } + return 0; +} + +SEC("fail_modify_sk_or_null_pointer") +int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + __u32 family; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + sk += 1; + if (sk) + bpf_sk_release(sk); + return 0; +} + +SEC("fail_no_release") +int bpf_sk_lookup_test2(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + + bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + return 0; +} + +SEC("fail_release_twice") +int bpf_sk_lookup_test3(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + bpf_sk_release(sk); + bpf_sk_release(sk); + return 0; +} + +SEC("fail_release_unchecked") +int bpf_sk_lookup_test4(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + struct bpf_sock *sk; + + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + bpf_sk_release(sk); + return 0; +} + +void lookup_no_release(struct __sk_buff *skb) +{ + struct bpf_sock_tuple tuple = {}; + bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); +} + +SEC("fail_no_release_subcall") +int bpf_sk_lookup_test5(struct __sk_buff *skb) +{ + lookup_no_release(skb); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c7d25f23baf9..bc9cd8537467 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -3,6 +3,7 @@ * * Copyright (c) 2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2017 Facebook + * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -178,6 +179,24 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self) self->retval = (uint32_t)res; } +/* BPF_SK_LOOKUP contains 13 instructions, if you need to fix up maps */ +#define BPF_SK_LOOKUP \ + /* struct bpf_sock_tuple tuple = {} */ \ + BPF_MOV64_IMM(BPF_REG_2, 0), \ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -16), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -24), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -32), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -40), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -48), \ + /* sk = sk_lookup_tcp(ctx, &tuple, sizeof tuple, 0, 0) */ \ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), \ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -48), \ + BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)), \ + BPF_MOV64_IMM(BPF_REG_4, 0), \ + BPF_MOV64_IMM(BPF_REG_5, 0), \ + BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp) + static struct bpf_test tests[] = { { "add+sub+mul", @@ -2707,6 +2726,137 @@ static struct bpf_test tests[] = { .errstr = "same insn cannot be used with different pointers", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, + { + "unpriv: spill/fill of different pointers stx - ctx and sock", + .insns = { + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + /* struct bpf_sock *sock = bpf_sock_lookup(...); */ + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + /* u64 foo; */ + /* void *target = &foo; */ + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + /* if (skb == NULL) *target = sock; */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0), + /* else *target = skb; */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* struct __sk_buff *skb = *target; */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + /* skb->mark = 42; */ + BPF_MOV64_IMM(BPF_REG_3, 42), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct __sk_buff, mark)), + /* if (sk) bpf_sk_release(sk) */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "type=ctx expected=sock", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "unpriv: spill/fill of different pointers stx - leak sock", + .insns = { + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + /* struct bpf_sock *sock = bpf_sock_lookup(...); */ + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + /* u64 foo; */ + /* void *target = &foo; */ + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + /* if (skb == NULL) *target = sock; */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0), + /* else *target = skb; */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* struct __sk_buff *skb = *target; */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + /* skb->mark = 42; */ + BPF_MOV64_IMM(BPF_REG_3, 42), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + //.errstr = "same insn cannot be used with different pointers", + .errstr = "Unreleased reference", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "unpriv: spill/fill of different pointers stx - sock and ctx (read)", + .insns = { + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + /* struct bpf_sock *sock = bpf_sock_lookup(...); */ + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + /* u64 foo; */ + /* void *target = &foo; */ + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + /* if (skb) *target = skb */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* else *target = sock */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0), + /* struct bpf_sock *sk = *target; */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + /* if (sk) u32 foo = sk->mark; bpf_sk_release(sk); */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct bpf_sock, mark)), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "same insn cannot be used with different pointers", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "unpriv: spill/fill of different pointers stx - sock and ctx (write)", + .insns = { + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + /* struct bpf_sock *sock = bpf_sock_lookup(...); */ + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + /* u64 foo; */ + /* void *target = &foo; */ + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + /* if (skb) *target = skb */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* else *target = sock */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0), + /* struct bpf_sock *sk = *target; */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + /* if (sk) sk->mark = 42; bpf_sk_release(sk); */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 42), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct bpf_sock, mark)), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + //.errstr = "same insn cannot be used with different pointers", + .errstr = "cannot write into socket", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, { "unpriv: spill/fill of different pointers ldx", .insns = { @@ -3276,7 +3426,7 @@ static struct bpf_test tests[] = { BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0), BPF_EXIT_INSN(), }, - .errstr = "BPF_ST stores into R1 context is not allowed", + .errstr = "BPF_ST stores into R1 inv is not allowed", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -3288,7 +3438,7 @@ static struct bpf_test tests[] = { BPF_REG_0, offsetof(struct __sk_buff, mark), 0), BPF_EXIT_INSN(), }, - .errstr = "BPF_XADD stores into R1 context is not allowed", + .errstr = "BPF_XADD stores into R1 inv is not allowed", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -3638,7 +3788,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", + .errstr = "R3 pointer arithmetic on pkt_end", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -4896,7 +5046,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", + .errstr = "R4 pointer arithmetic on map_value_or_null", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -4917,7 +5067,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", + .errstr = "R4 pointer arithmetic on map_value_or_null", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -4938,7 +5088,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", + .errstr = "R4 pointer arithmetic on map_value_or_null", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -5266,7 +5416,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R2 leaks addr into mem", .result_unpriv = REJECT, .result = REJECT, - .errstr = "BPF_XADD stores into R1 context is not allowed", + .errstr = "BPF_XADD stores into R1 inv is not allowed", }, { "leak pointer into ctx 2", @@ -5281,7 +5431,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R10 leaks addr into mem", .result_unpriv = REJECT, .result = REJECT, - .errstr = "BPF_XADD stores into R1 context is not allowed", + .errstr = "BPF_XADD stores into R1 inv is not allowed", }, { "leak pointer into ctx 3", @@ -7253,7 +7403,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map_in_map = { 3 }, - .errstr = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited", + .errstr = "R1 pointer arithmetic on map_ptr prohibited", .result = REJECT, }, { @@ -8927,7 +9077,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", + .errstr = "R3 pointer arithmetic on pkt_end", .result = REJECT, .prog_type = BPF_PROG_TYPE_XDP, }, @@ -8946,7 +9096,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", + .errstr = "R3 pointer arithmetic on pkt_end", .result = REJECT, .prog_type = BPF_PROG_TYPE_XDP, }, @@ -12230,7 +12380,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "BPF_XADD stores into R2 packet", + .errstr = "BPF_XADD stores into R2 ctx", .prog_type = BPF_PROG_TYPE_XDP, }, { @@ -12557,6 +12707,214 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = ACCEPT, }, + { + "reference tracking: leak potential reference", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */ + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking: leak potential reference on stack", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking: leak potential reference on stack 2", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking: zero potential reference", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */ + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking: copy and zero potential references", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_7, 0), /* leak reference */ + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking: release reference without check", + .insns = { + BPF_SK_LOOKUP, + /* reference in r0 may be NULL */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "type=sock_or_null expected=sock", + .result = REJECT, + }, + { + "reference tracking: release reference", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking: release reference 2", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking: release reference twice", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "type=inv expected=sock", + .result = REJECT, + }, + { + "reference tracking: release reference twice inside branch", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), /* goto end */ + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "type=inv expected=sock", + .result = REJECT, + }, + { + "reference tracking: alloc, check, free in one subbranch", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16), + /* if (offsetof(skb, mark) > data_len) exit; */ + BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2, + offsetof(struct __sk_buff, mark)), + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 1), /* mark == 0? */ + /* Leak reference in R0 */ + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking: alloc, check, free in both subbranches", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16), + /* if (offsetof(skb, mark) > data_len) exit; */ + BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2, + offsetof(struct __sk_buff, mark)), + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4), /* mark == 0? */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking in call: free reference in subprog", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, { "pass modified ctx pointer to helper, 1", .insns = { @@ -12627,6 +12985,407 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = ACCEPT, }, + { + "reference tracking in call: free reference in subprog and outside", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "type=inv expected=sock", + .result = REJECT, + }, + { + "reference tracking in call: alloc & leak reference in subprog", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_4), + BPF_SK_LOOKUP, + /* spill unchecked sk_ptr into stack of caller */ + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking in call: alloc in subprog, release outside", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_SK_LOOKUP, + BPF_EXIT_INSN(), /* return sk */ + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = POINTER_VALUE, + .result = ACCEPT, + }, + { + "reference tracking in call: sk_ptr leak into caller stack", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5), + /* spill unchecked sk_ptr into stack of caller */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 2 */ + BPF_SK_LOOKUP, + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, + }, + { + "reference tracking in call: sk_ptr spill into caller stack", + .insns = { + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + + /* subprog 1 */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8), + /* spill unchecked sk_ptr into stack of caller */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + /* now the sk_ptr is verified, free the reference */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_4, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + + /* subprog 2 */ + BPF_SK_LOOKUP, + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking: allow LD_ABS", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking: forbid LD_ABS while holding reference", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_SK_LOOKUP, + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references", + .result = REJECT, + }, + { + "reference tracking: allow LD_IND", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_IMM(BPF_REG_7, 1), + BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 1, + }, + { + "reference tracking: forbid LD_IND while holding reference", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_7, 1), + BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_7), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references", + .result = REJECT, + }, + { + "reference tracking: check reference or tail call", + .insns = { + BPF_MOV64_REG(BPF_REG_7, BPF_REG_1), + BPF_SK_LOOKUP, + /* if (sk) bpf_sk_release() */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7), + /* bpf_tail_call() */ + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 17 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking: release reference then tail call", + .insns = { + BPF_MOV64_REG(BPF_REG_7, BPF_REG_1), + BPF_SK_LOOKUP, + /* if (sk) bpf_sk_release() */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + /* bpf_tail_call() */ + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 18 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking: leak possible reference over tail call", + .insns = { + BPF_MOV64_REG(BPF_REG_7, BPF_REG_1), + /* Look up socket and store in REG_6 */ + BPF_SK_LOOKUP, + /* bpf_tail_call() */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + /* if (sk) bpf_sk_release() */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 16 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "tail_call would lead to reference leak", + .result = REJECT, + }, + { + "reference tracking: leak checked reference over tail call", + .insns = { + BPF_MOV64_REG(BPF_REG_7, BPF_REG_1), + /* Look up socket and store in REG_6 */ + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* if (!sk) goto end */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + /* bpf_tail_call() */ + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .fixup_prog1 = { 17 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "tail_call would lead to reference leak", + .result = REJECT, + }, + { + "reference tracking: mangle and release sock_or_null", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "R1 pointer arithmetic on sock_or_null prohibited", + .result = REJECT, + }, + { + "reference tracking: mangle and release sock", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "R1 pointer arithmetic on sock prohibited", + .result = REJECT, + }, + { + "reference tracking: access member", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "reference tracking: write to member", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_LD_IMM64(BPF_REG_2, 42), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_2, + offsetof(struct bpf_sock, mark)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "cannot write into socket", + .result = REJECT, + }, + { + "reference tracking: invalid 64-bit access of member", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "invalid bpf_sock access off=0 size=8", + .result = REJECT, + }, + { + "reference tracking: access after release", + .insns = { + BPF_SK_LOOKUP, + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "!read_ok", + .result = REJECT, + }, + { + "reference tracking: direct access for lookup", + .insns = { + /* Check that the packet is at least 64B long */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 64), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 9), + /* sk = sk_lookup_tcp(ctx, skb->data, ...) */ + BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -12652,18 +13411,18 @@ static int create_map(uint32_t type, uint32_t size_key, return fd; } -static int create_prog_dummy1(void) +static int create_prog_dummy1(enum bpf_map_type prog_type) { struct bpf_insn prog[] = { BPF_MOV64_IMM(BPF_REG_0, 42), BPF_EXIT_INSN(), }; - return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, + return bpf_load_program(prog_type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_dummy2(int mfd, int idx) +static int create_prog_dummy2(enum bpf_map_type prog_type, int mfd, int idx) { struct bpf_insn prog[] = { BPF_MOV64_IMM(BPF_REG_3, idx), @@ -12674,11 +13433,12 @@ static int create_prog_dummy2(int mfd, int idx) BPF_EXIT_INSN(), }; - return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, + return bpf_load_program(prog_type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_array(uint32_t max_elem, int p1key) +static int create_prog_array(enum bpf_map_type prog_type, uint32_t max_elem, + int p1key) { int p2key = 1; int mfd, p1fd, p2fd; @@ -12690,8 +13450,8 @@ static int create_prog_array(uint32_t max_elem, int p1key) return -1; } - p1fd = create_prog_dummy1(); - p2fd = create_prog_dummy2(mfd, p2key); + p1fd = create_prog_dummy1(prog_type); + p2fd = create_prog_dummy2(prog_type, mfd, p2key); if (p1fd < 0 || p2fd < 0) goto out; if (bpf_map_update_elem(mfd, &p1key, &p1fd, BPF_ANY) < 0) @@ -12748,8 +13508,8 @@ static int create_cgroup_storage(bool percpu) static char bpf_vlog[UINT_MAX >> 8]; -static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, - int *map_fds) +static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type, + struct bpf_insn *prog, int *map_fds) { int *fixup_map1 = test->fixup_map1; int *fixup_map2 = test->fixup_map2; @@ -12805,7 +13565,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, } if (*fixup_prog1) { - map_fds[4] = create_prog_array(4, 0); + map_fds[4] = create_prog_array(prog_type, 4, 0); do { prog[*fixup_prog1].imm = map_fds[4]; fixup_prog1++; @@ -12813,7 +13573,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, } if (*fixup_prog2) { - map_fds[5] = create_prog_array(8, 7); + map_fds[5] = create_prog_array(prog_type, 8, 7); do { prog[*fixup_prog2].imm = map_fds[5]; fixup_prog2++; @@ -12859,11 +13619,13 @@ static void do_test_single(struct bpf_test *test, bool unpriv, for (i = 0; i < MAX_NR_MAPS; i++) map_fds[i] = -1; - do_test_fixup(test, prog, map_fds); + if (!prog_type) + prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + do_test_fixup(test, prog_type, prog, map_fds); prog_len = probe_filter_length(prog); - fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, - prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, + fd_prog = bpf_verify_program(prog_type, prog, prog_len, + test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1); expected_ret = unpriv && test->result_unpriv != UNDEF ?