diff options
Diffstat (limited to 'kernel/bpf')
| -rw-r--r-- | kernel/bpf/Kconfig | 1 | ||||
| -rw-r--r-- | kernel/bpf/Makefile | 3 | ||||
| -rw-r--r-- | kernel/bpf/bpf_lru_list.h | 1 | ||||
| -rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 21 | ||||
| -rw-r--r-- | kernel/bpf/btf.c | 25 | ||||
| -rw-r--r-- | kernel/bpf/core.c | 206 | ||||
| -rw-r--r-- | kernel/bpf/cpumap.c | 116 | ||||
| -rw-r--r-- | kernel/bpf/cpumask.c | 20 | ||||
| -rw-r--r-- | kernel/bpf/devmap.c | 2 | ||||
| -rw-r--r-- | kernel/bpf/disasm.c | 58 | ||||
| -rw-r--r-- | kernel/bpf/hashtab.c | 22 | ||||
| -rw-r--r-- | kernel/bpf/helpers.c | 65 | ||||
| -rw-r--r-- | kernel/bpf/map_iter.c | 42 | ||||
| -rw-r--r-- | kernel/bpf/memalloc.c | 388 | ||||
| -rw-r--r-- | kernel/bpf/mprog.c | 447 | ||||
| -rw-r--r-- | kernel/bpf/offload.c | 1 | ||||
| -rw-r--r-- | kernel/bpf/preload/iterators/Makefile | 2 | ||||
| -rw-r--r-- | kernel/bpf/preload/iterators/iterators.bpf.c | 9 | ||||
| -rw-r--r-- | kernel/bpf/preload/iterators/iterators.lskel-little-endian.h | 526 | ||||
| -rw-r--r-- | kernel/bpf/ringbuf.c | 26 | ||||
| -rw-r--r-- | kernel/bpf/syscall.c | 382 | ||||
| -rw-r--r-- | kernel/bpf/tcx.c | 352 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 516 |
23 files changed, 2466 insertions, 765 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; + break; + case 1: + AX = div64_s64(DST, IMM); + DST = DST - AX * IMM; + break; + } CONT; ALU_MOD_K: - AX = (u32) DST; - DST = do_div(AX, (u32) IMM); + switch (OFF) { + case 0: + AX = (u32) DST; + DST = do_div(AX, (u32) IMM); + break; + case 1: + AX = abs((s32)DST); + AX = do_div(AX, abs((s32)IMM)); + if ((s32)DST < 0) + DST = (u32)-AX; + else + DST = (u32)AX; + break; + } CONT; ALU64_DIV_X: - DST = div64_u64(DST, SRC); + switch (OFF) { + case 0: + DST = div64_u64(DST, SRC); + break; + case 1: + DST = div64_s64(DST, SRC); + break; + } CONT; ALU_DIV_X: - AX = (u32) DST; - do_div(AX, (u32) SRC); - DST = (u32) AX; + switch (OFF) { + case 0: + AX = (u32) DST; + do_div(AX, (u32) SRC); + DST = (u32) AX; + break; + case 1: + AX = abs((s32)DST); + do_div(AX, abs((s32)SRC)); + if (((s32)DST < 0) == ((s32)SRC < 0)) + DST = (u32)AX; + else + DST = (u32)-AX; + break; + } CONT; ALU64_DIV_K: - DST = div64_u64(DST, IMM); + switch (OFF) { + case 0: + DST = div64_u64(DST, IMM); + break; + case 1: + DST = div64_s64(DST, IMM); + break; + } CONT; ALU_DIV_K: - AX = (u32) DST; - do_div(AX, (u32) IMM); - DST = (u32) AX; + switch (OFF) { + case 0: + AX = (u32) DST; + do_div(AX, (u32) IMM); + DST = (u32) AX; + break; + case 1: + AX = abs((s32)DST); + do_div(AX, abs((s32)IMM)); + if (((s32)DST < 0) == ((s32)IMM < 0)) + DST = (u32)AX; + else + DST = (u32)-AX; + break; + } CONT; ALU_END_TO_BE: switch (IMM) { @@ -1818,6 +1931,19 @@ select_insn: break; } CONT; + ALU64_END_TO_LE: + switch (IMM) { + case 16: + DST = (__force u16) __swab16(DST); + break; + case 32: + DST = (__force u32) __swab32(DST); + break; + case 64: + DST = (__force u64) __swab64(DST); + break; + } + CONT; /* CALL */ JMP_CALL: @@ -1867,6 +1993,9 @@ out: JMP_JA: insn += insn->off; CONT; + JMP32_JA: + insn += insn->imm; + CONT; JMP_EXIT: return BPF_R0; /* JMP */ @@ -1931,8 +2060,8 @@ out: DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEM_##SIZEOP: \ - bpf_probe_read_kernel(&DST, sizeof(SIZE), \ - (const void *)(long) (SRC + insn->off)); \ + bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ + (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; @@ -1942,6 +2071,21 @@ out: LDST(DW, u64) #undef LDST +#define LDSX(SIZEOP, SIZE) \ + LDX_MEMSX_##SIZEOP: \ + DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ + CONT; \ + LDX_PROBE_MEMSX_##SIZEOP: \ + bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ + (const void *)(long) (SRC + insn->off)); \ + DST = *((SIZE *)&DST); \ + CONT; + + LDSX(B, s8) + LDSX(H, s16) + LDSX(W, s32) +#undef LDSX + #define ATOMIC_ALU_OP(BOP, KOP) \ case BOP: \ if (BPF_SIZE(insn->code) == BPF_W) \ diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 286ab3db0fde..e42a1bdb7f53 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -61,8 +61,6 @@ struct bpf_cpu_map_entry { /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ struct xdp_bulk_queue __percpu *bulkq; - struct bpf_cpu_map *cmap; - /* Queue with potential multi-producers, and single-consumer kthread */ struct ptr_ring *queue; struct task_struct *kthread; @@ -70,11 +68,8 @@ struct bpf_cpu_map_entry { struct bpf_cpumap_val value; struct bpf_prog *prog; - atomic_t refcnt; /* Control when this struct can be free'ed */ - struct rcu_head rcu; - - struct work_struct kthread_stop_wq; struct completion kthread_running; + struct rcu_work free_work; }; struct bpf_cpu_map { @@ -119,11 +114,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) return &cmap->map; } -static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - atomic_inc(&rcpu->refcnt); -} - static void __cpu_map_ring_cleanup(struct ptr_ring *ring) { /* The tear-down procedure should have made sure that queue is @@ -144,35 +134,6 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring) } } -static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - if (atomic_dec_and_test(&rcpu->refcnt)) { - if (rcpu->prog) - bpf_prog_put(rcpu->prog); - /* The queue should be empty at this point */ - __cpu_map_ring_cleanup(rcpu->queue); - ptr_ring_cleanup(rcpu->queue, NULL); - kfree(rcpu->queue); - kfree(rcpu); - } -} - -/* called from workqueue, to workaround syscall using preempt_disable */ -static void cpu_map_kthread_stop(struct work_struct *work) -{ - struct bpf_cpu_map_entry *rcpu; - - rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); - - /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, - * as it waits until all in-flight call_rcu() callbacks complete. - */ - rcu_barrier(); - - /* kthread_stop will wake_up_process and wait for it to complete */ - kthread_stop(rcpu->kthread); -} - static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, struct list_head *listp, struct xdp_cpumap_stats *stats) @@ -397,7 +358,6 @@ static int cpu_map_kthread_run(void *data) } __set_current_state(TASK_RUNNING); - put_cpu_map_entry(rcpu); return 0; } @@ -474,9 +434,6 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, if (IS_ERR(rcpu->kthread)) goto free_prog; - get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ - get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ - /* Make sure kthread runs on a single CPU */ kthread_bind(rcpu->kthread, cpu); wake_up_process(rcpu->kthread); @@ -503,40 +460,40 @@ free_rcu: return NULL; } -static void __cpu_map_entry_free(struct rcu_head *rcu) +static void __cpu_map_entry_free(struct work_struct *work) { struct bpf_cpu_map_entry *rcpu; /* This cpu_map_entry have been disconnected from map and one - * RCU grace-period have elapsed. Thus, XDP cannot queue any + * RCU grace-period have elapsed. Thus, XDP cannot queue any * new packets and cannot change/set flush_needed that can * find this entry. */ - rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); + rcpu = container_of(to_rcu_work(work), struct bpf_cpu_map_entry, free_work); + /* kthread_stop will wake_up_process and wait for it to complete. + * cpu_map_kthread_run() makes sure the pointer ring is empty + * before exiting. + */ + kthread_stop(rcpu->kthread); + + if (rcpu->prog) + bpf_prog_put(rcpu->prog); + /* The queue should be empty at this point */ + __cpu_map_ring_cleanup(rcpu->queue); + ptr_ring_cleanup(rcpu->queue, NULL); + kfree(rcpu->queue); free_percpu(rcpu->bulkq); - /* Cannot kthread_stop() here, last put free rcpu resources */ - put_cpu_map_entry(rcpu); + kfree(rcpu); } -/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to - * ensure any driver rcu critical sections have completed, but this - * does not guarantee a flush has happened yet. Because driver side - * rcu_read_lock/unlock only protects the running XDP program. The - * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a - * pending flush op doesn't fail. - * - * The bpf_cpu_map_entry is still used by the kthread, and there can - * still be pending packets (in queue and percpu bulkq). A refcnt - * makes sure to last user (kthread_stop vs. call_rcu) free memory - * resources. - * - * The rcu callback __cpu_map_entry_free flush remaining packets in - * percpu bulkq to queue. Due to caller map_delete_elem() disable - * preemption, cannot call kthread_stop() to make sure queue is empty. - * Instead a work_queue is started for stopping kthread, - * cpu_map_kthread_stop, which waits for an RCU grace period before - * stopping kthread, emptying the queue. +/* After the xchg of the bpf_cpu_map_entry pointer, we need to make sure the old + * entry is no longer in use before freeing. We use queue_rcu_work() to call + * __cpu_map_entry_free() in a separate workqueue after waiting for an RCU grace + * period. This means that (a) all pending enqueue and flush operations have + * completed (because of the RCU callback), and (b) we are in a workqueue + * context where we can stop the kthread and wait for it to exit before freeing + * everything. */ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, u32 key_cpu, struct bpf_cpu_map_entry *rcpu) @@ -545,9 +502,8 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu))); if (old_rcpu) { - call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); - INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); - schedule_work(&old_rcpu->kthread_stop_wq); + INIT_RCU_WORK(&old_rcpu->free_work, __cpu_map_entry_free); + queue_rcu_work(system_wq, &old_rcpu->free_work); } } @@ -559,7 +515,7 @@ static long cpu_map_delete_elem(struct bpf_map *map, void *key) if (key_cpu >= map->max_entries) return -EINVAL; - /* notice caller map_delete_elem() use preempt_disable() */ + /* notice caller map_delete_elem() uses rcu_read_lock() */ __cpu_map_entry_replace(cmap, key_cpu, NULL); return 0; } @@ -595,7 +551,6 @@ static long cpu_map_update_elem(struct bpf_map *map, void *key, void *value, rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu); if (!rcpu) return -ENOMEM; - rcpu->cmap = cmap; } rcu_read_lock(); __cpu_map_entry_replace(cmap, key_cpu, rcpu); @@ -611,16 +566,15 @@ static void cpu_map_free(struct bpf_map *map) /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the bpf programs (can be more than one that used this map) were * disconnected from events. Wait for outstanding critical sections in - * these programs to complete. The rcu critical section only guarantees - * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map. - * It does __not__ ensure pending flush operations (if any) are - * complete. + * these programs to complete. synchronize_rcu() below not only + * guarantees no further "XDP/bpf-side" reads against + * bpf_cpu_map->cpu_map, but also ensure pending flush operations + * (if any) are completed. */ - synchronize_rcu(); - /* For cpu_map the remote CPUs can still be using the entries - * (struct bpf_cpu_map_entry). + /* The only possible user of bpf_cpu_map_entry is + * cpu_map_kthread_run(). */ for (i = 0; i < cmap->map.max_entries; i++) { struct bpf_cpu_map_entry *rcpu; @@ -629,8 +583,8 @@ static void cpu_map_free(struct bpf_map *map) if (!rcpu) continue; - /* bq flush and cleanup happens after RCU grace-period */ - __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ + /* Stop kthread and cleanup entry directly */ + __cpu_map_entry_free(&rcpu->free_work.work); } bpf_map_area_free(cmap->cpu_map); bpf_map_area_free(cmap); diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 938a60ff4295..6983af8e093c 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -9,7 +9,6 @@ /** * struct bpf_cpumask - refcounted BPF cpumask wrapper structure * @cpumask: The actual cpumask embedded in the struct. - * @rcu: The RCU head used to free the cpumask with RCU safety. * @usage: Object reference counter. When the refcount goes to 0, the * memory is released back to the BPF allocator, which provides * RCU safety. @@ -25,7 +24,6 @@ */ struct bpf_cpumask { cpumask_t cpumask; - struct rcu_head rcu; refcount_t usage; }; @@ -82,16 +80,6 @@ __bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) return cpumask; } -static void cpumask_free_cb(struct rcu_head *head) -{ - struct bpf_cpumask *cpumask; - - cpumask = container_of(head, struct bpf_cpumask, rcu); - migrate_disable(); - bpf_mem_cache_free(&bpf_cpumask_ma, cpumask); - migrate_enable(); -} - /** * bpf_cpumask_release() - Release a previously acquired BPF cpumask. * @cpumask: The cpumask being released. @@ -102,8 +90,12 @@ static void cpumask_free_cb(struct rcu_head *head) */ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) { - if (refcount_dec_and_test(&cpumask->usage)) - call_rcu(&cpumask->rcu, cpumask_free_cb); + if (!refcount_dec_and_test(&cpumask->usage)) + return; + + migrate_disable(); + bpf_mem_cache_free_rcu(&bpf_cpumask_ma, cpumask); + migrate_enable(); } /** diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 49cc0b5671c6..4d42f6ed6c11 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -65,7 +65,6 @@ struct xdp_dev_bulk_queue { struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; - struct bpf_dtab *dtab; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; @@ -874,7 +873,6 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, } dev->idx = idx; - dev->dtab = dtab; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 7b4afb7d96db..49940c26a227 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -87,6 +87,17 @@ const char *const bpf_alu_string[16] = { [BPF_END >> 4] = "endian", }; +static const char *const bpf_alu_sign_string[16] = { + [BPF_DIV >> 4] = "s/=", + [BPF_MOD >> 4] = "s%=", +}; + +static const char *const bpf_movsx_string[4] = { + [0] = "(s8)", + [1] = "(s16)", + [3] = "(s32)", +}; + static const char *const bpf_atomic_alu_string[16] = { [BPF_ADD >> 4] = "add", [BPF_AND >> 4] = "and", @@ -101,6 +112,12 @@ static const char *const bpf_ldst_string[] = { [BPF_DW >> 3] = "u64", }; +static const char *const bpf_ldsx_string[] = { + [BPF_W >> 3] = "s32", + [BPF_H >> 3] = "s16", + [BPF_B >> 3] = "s8", +}; + static const char *const bpf_jmp_string[16] = { [BPF_JA >> 4] = "jmp", [BPF_JEQ >> 4] = "==", @@ -128,6 +145,27 @@ static void print_bpf_end_insn(bpf_insn_print_t verbose, insn->imm, insn->dst_reg); } +static void print_bpf_bswap_insn(bpf_insn_print_t verbose, + void *private_data, + const struct bpf_insn *insn) +{ + verbose(private_data, "(%02x) r%d = bswap%d r%d\n", + insn->code, insn->dst_reg, + insn->imm, insn->dst_reg); +} + +static bool is_sdiv_smod(const struct bpf_insn *insn) +{ + return (BPF_OP(insn->code) == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) && + insn->off == 1; +} + +static bool is_movsx(const struct bpf_insn *insn) +{ + return BPF_OP(insn->code) == BPF_MOV && + (insn->off == 8 || insn->off == 16 || insn->off == 32); +} + void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) @@ -138,7 +176,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, if (class == BPF_ALU || class == BPF_ALU64) { if (BPF_OP(insn->code) == BPF_END) { if (class == BPF_ALU64) - verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code); + print_bpf_bswap_insn(verbose, cbs->private_data, insn); else print_bpf_end_insn(verbose, cbs->private_data, insn); } else if (BPF_OP(insn->code) == BPF_NEG) { @@ -147,17 +185,20 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { - verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n", + verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], + is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] + : bpf_alu_string[BPF_OP(insn->code) >> 4], + is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "", class == BPF_ALU ? 'w' : 'r', insn->src_reg); } else { verbose(cbs->private_data, "(%02x) %c%d %s %d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], + is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] + : bpf_alu_string[BPF_OP(insn->code) >> 4], insn->imm); } } else if (class == BPF_STX) { @@ -218,13 +259,15 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); } } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM) { + if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); return; } verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n", insn->code, insn->dst_reg, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + BPF |
