diff options
Diffstat (limited to 'kernel')
86 files changed, 4999 insertions, 2121 deletions
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index 2dfe1079f772..6a906ff93006 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -31,6 +31,7 @@ config BPF_SYSCALL select TASKS_TRACE_RCU select BINARY_PRINTF select NET_SOCK_MSG if NET + select NET_XGRESS if NET select PAGE_POOL if NET default n help diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 1d3892168d32..f526b7573e97 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -12,7 +12,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o -obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o obj-$(CONFIG_BPF_JIT) += dispatcher.o @@ -21,6 +21,7 @@ obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o obj-$(CONFIG_BPF_SYSCALL) += offload.o obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o +obj-$(CONFIG_BPF_SYSCALL) += tcx.o endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 8f3c8b2b4490..cbd8d3720c2b 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -75,6 +75,5 @@ void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, void bpf_lru_destroy(struct bpf_lru *lru); struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash); void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node); -void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node); #endif diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 116a0ce378ec..fdc3e8705a3c 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -374,9 +374,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_struct_ops_value *uvalue, *kvalue; const struct btf_member *member; const struct btf_type *t = st_ops->type; - struct bpf_tramp_links *tlinks = NULL; + struct bpf_tramp_links *tlinks; void *udata, *kdata; - int prog_fd, err = 0; + int prog_fd, err; void *image, *image_end; u32 i; @@ -509,9 +509,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, } if (st_map->map.map_flags & BPF_F_LINK) { - err = st_ops->validate(kdata); - if (err) - goto reset_unlock; + err = 0; + if (st_ops->validate) { + err = st_ops->validate(kdata); + if (err) + goto reset_unlock; + } set_memory_rox((long)st_map->image, 1); /* Let bpf_link handle registration & unregistration. * @@ -663,9 +666,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) if (attr->value_size != vt->size) return ERR_PTR(-EINVAL); - if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update)) - return ERR_PTR(-EOPNOTSUPP); - t = st_ops->type; st_map_size = sizeof(*st_map) + @@ -815,7 +815,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map struct bpf_struct_ops_map *st_map, *old_st_map; struct bpf_map *old_map; struct bpf_struct_ops_link *st_link; - int err = 0; + int err; st_link = container_of(link, struct bpf_struct_ops_link, link); st_map = container_of(new_map, struct bpf_struct_ops_map, map); @@ -823,6 +823,9 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map if (!bpf_struct_ops_valid_to_reg(new_map)) return -EINVAL; + if (!st_map->st_ops->update) + return -EOPNOTSUPP; + mutex_lock(&update_mutex); old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex)); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 817204d53372..249657c466dd 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -29,6 +29,7 @@ #include <net/netfilter/nf_bpf_link.h> #include <net/sock.h> +#include <net/xdp.h> #include "../tools/lib/bpf/relo_core.h" /* BTF (BPF Type Format) is the meta data format which describes @@ -6133,8 +6134,9 @@ static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const char *tname, *mname, *tag_value; u32 vlen, elem_id, mid; - *flag = 0; again: + if (btf_type_is_modifier(t)) + t = btf_type_skip_modifiers(btf, t->type, NULL); tname = __btf_name_by_offset(btf, t->name_off); if (!btf_type_is_struct(t)) { bpf_log(log, "Type '%s' is not a struct\n", tname); @@ -6142,6 +6144,14 @@ again: } vlen = btf_type_vlen(t); + if (BTF_INFO_KIND(t->info) == BTF_KIND_UNION && vlen != 1 && !(*flag & PTR_UNTRUSTED)) + /* + * walking unions yields untrusted pointers + * with exception of __bpf_md_ptr and other + * unions with a single member + */ + *flag |= PTR_UNTRUSTED; + if (off + size > t->size) { /* If the last element is a variable size array, we may * need to relax the rule. @@ -6302,15 +6312,6 @@ error: * of this field or inside of this struct */ if (btf_type_is_struct(mtype)) { - if (BTF_INFO_KIND(mtype->info) == BTF_KIND_UNION && - btf_type_vlen(mtype) != 1) - /* - * walking unions yields untrusted pointers - * with exception of __bpf_md_ptr and other - * unions with a single member - */ - *flag |= PTR_UNTRUSTED; - /* our field must be inside that union or struct */ t = mtype; @@ -6368,7 +6369,7 @@ error: * that also allows using an array of int as a scratch * space. e.g. skb->cb[]. */ - if (off + size > mtrue_end) { + if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) { bpf_log(log, "access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n", mname, mtrue_end, tname, off, size); @@ -6476,7 +6477,7 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log, bool strict) { const struct btf_type *type; - enum bpf_type_flag flag; + enum bpf_type_flag flag = 0; int err; /* Are we already done? */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index dc85240a0134..0f8f036d8bd1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -61,6 +61,7 @@ #define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] +#define OFF insn->off #define IMM insn->imm struct bpf_mem_alloc bpf_global_ma; @@ -372,7 +373,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, { const s32 off_min = S16_MIN, off_max = S16_MAX; s32 delta = end_new - end_old; - s32 off = insn->off; + s32 off; + + if (insn->code == (BPF_JMP32 | BPF_JA)) + off = insn->imm; + else + off = insn->off; if (curr < pos && curr + off + 1 >= end_old) off += delta; @@ -380,8 +386,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, off -= delta; if (off < off_min || off > off_max) return -ERANGE; - if (!probe_pass) - insn->off = off; + if (!probe_pass) { + if (insn->code == (BPF_JMP32 | BPF_JA)) + insn->imm = off; + else + insn->off = off; + } return 0; } @@ -1271,7 +1281,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX); + *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_ALU64 | BPF_ADD | BPF_K: @@ -1285,7 +1295,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX); + *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_JMP | BPF_JEQ | BPF_K: @@ -1523,6 +1533,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(ALU64, DIV, X), \ INSN_3(ALU64, MOD, X), \ INSN_2(ALU64, NEG), \ + INSN_3(ALU64, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU64, ADD, K), \ INSN_3(ALU64, SUB, K), \ @@ -1591,6 +1602,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ + INSN_2(JMP32, JA), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ @@ -1610,6 +1622,9 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(LDX, MEM, H), \ INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ + INSN_3(LDX, MEMSX, B), \ + INSN_3(LDX, MEMSX, H), \ + INSN_3(LDX, MEMSX, W), \ /* Immediate based. */ \ INSN_3(LD, IMM, DW) @@ -1635,12 +1650,6 @@ bool bpf_opcode_in_insntable(u8 code) } #ifndef CONFIG_BPF_JIT_ALWAYS_ON -u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) -{ - memset(dst, 0, size); - return -EFAULT; -} - /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers @@ -1666,6 +1675,9 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H, + [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL @@ -1733,13 +1745,36 @@ select_insn: DST = -DST; CONT; ALU_MOV_X: - DST = (u32) SRC; + switch (OFF) { + case 0: + DST = (u32) SRC; + break; + case 8: + DST = (u32)(s8) SRC; + break; + case 16: + DST = (u32)(s16) SRC; + break; + } CONT; ALU_MOV_K: DST = (u32) IMM; CONT; ALU64_MOV_X: - DST = SRC; + switch (OFF) { + case 0: + DST = SRC; + break; + case 8: + DST = (s8) SRC; + break; + case 16: + DST = (s16) SRC; + break; + case 32: + DST = (s32) SRC; + break; + } CONT; ALU64_MOV_K: DST = IMM; @@ -1761,36 +1796,114 @@ select_insn: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: - div64_u64_rem(DST, SRC, &AX); - DST = AX; + switch (OFF) { + case 0: + div64_u64_rem(DST, SRC, &AX); + DST = AX; + break; + case 1: + AX = div64_s64(DST, SRC); + DST = DST - AX * SRC; + break; + } CONT; ALU_MOD_X: - AX = (u32) DST; - DST = do_div(AX, (u32) SRC); + switch (OFF) { + case 0: + AX = (u32) DST; + DST = do_div(AX, (u32) SRC); + break; + case 1: + AX = abs((s32)DST); + AX = do_div(AX, abs((s32)SRC)); + if ((s32)DST < 0) + DST = (u32)-AX; + else + DST = (u32)AX; + break; + } CONT; ALU64_MOD_K: - div64_u64_rem(DST, IMM, &AX); - DST = AX; + switch (OFF) { + case 0: + div64_u64_rem(DST, IMM, &AX); + DST = AX;< |