From a9c676bc8fc58d00eea9836fb14ee43c0346416a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 4 Sep 2018 19:13:44 -0700 Subject: bpf/verifier: fix verifier instability Edward Cree says: In check_mem_access(), for the PTR_TO_CTX case, after check_ctx_access() has supplied a reg_type, the other members of the register state are set appropriately. Previously reg.range was set to 0, but as it is in a union with reg.map_ptr, which is larger, upper bytes of the latter were left in place. This then caused the memcmp() in regsafe() to fail, preventing some branches from being pruned (and occasionally causing the same program to take a varying number of processed insns on repeated verifier runs). Fix the instability by clearing bpf_reg_state in __mark_reg_[un]known() Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Debugged-by: Edward Cree Acked-by: Edward Cree Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f4ff0c569e54..6ff1bac1795d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -570,7 +570,9 @@ static void __mark_reg_not_init(struct bpf_reg_state *reg); */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { - reg->id = 0; + /* Clear id, off, and union(map_ptr, range) */ + memset(((u8 *)reg) + sizeof(reg->type), 0, + offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); reg->var_off = tnum_const(imm); reg->smin_value = (s64)imm; reg->smax_value = (s64)imm; @@ -589,7 +591,6 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) static void __mark_reg_const_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); - reg->off = 0; reg->type = SCALAR_VALUE; } @@ -700,9 +701,12 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) /* Mark a register as having a completely unknown (scalar) value. */ static void __mark_reg_unknown(struct bpf_reg_state *reg) { + /* + * Clear type, id, off, and union(map_ptr, range) and + * padding between 'type' and union + */ + memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; - reg->id = 0; - reg->off = 0; reg->var_off = tnum_unknown; reg->frameno = 0; __mark_reg_unbounded(reg); @@ -1640,9 +1644,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn else mark_reg_known_zero(env, regs, value_regno); - regs[value_regno].id = 0; - regs[value_regno].off = 0; - regs[value_regno].range = 0; regs[value_regno].type = reg_type; } @@ -2495,7 +2496,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].off = 0; /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() -- cgit From a7c19db38d62fc1ce797dba19936e9f81cf2b9fb Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 6 Sep 2018 17:26:04 -0700 Subject: bpf: add bpffs pretty print for program array map Added bpffs pretty print for program array map. For a particular array index, if the program array points to a valid program, the ": " will be printed out like 0: 6 which means bpf program with id "6" is installed at index "0". Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- kernel/bpf/arraymap.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index f9d24121be99..dded84cbe814 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -553,6 +553,29 @@ static void bpf_fd_array_map_clear(struct bpf_map *map) fd_array_map_delete_elem(map, &i); } +static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void **elem, *ptr; + u32 prog_id; + + rcu_read_lock(); + + elem = array_map_lookup_elem(map, key); + if (elem) { + ptr = READ_ONCE(*elem); + if (ptr) { + seq_printf(m, "%u: ", *(u32 *)key); + prog_id = prog_fd_array_sys_lookup_elem(ptr); + btf_type_seq_show(map->btf, map->btf_value_type_id, + &prog_id, m); + seq_puts(m, "\n"); + } + } + + rcu_read_unlock(); +} + const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, @@ -564,7 +587,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = bpf_fd_array_map_clear, - .map_check_btf = map_check_no_btf, + .map_seq_show_elem = prog_array_map_seq_show_elem, }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, -- cgit From d58e468b1112dcd1d5193c0a89ff9f98b5a3e8b9 Mon Sep 17 00:00:00 2001 From: Petar Penkov Date: Fri, 14 Sep 2018 07:46:18 -0700 Subject: flow_dissector: implements flow dissector BPF hook Adds a hook for programs of type BPF_PROG_TYPE_FLOW_DISSECTOR and attach type BPF_FLOW_DISSECTOR that is executed in the flow dissector path. The BPF program is per-network namespace. Signed-off-by: Petar Penkov Signed-off-by: Willem de Bruijn Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 8 ++++++++ kernel/bpf/verifier.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'kernel/bpf') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3c9636f03bb2..b3c2d09bcf7a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1615,6 +1615,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_LIRC_MODE2: ptype = BPF_PROG_TYPE_LIRC_MODE2; break; + case BPF_FLOW_DISSECTOR: + ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; + break; default: return -EINVAL; } @@ -1636,6 +1639,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; + case BPF_PROG_TYPE_FLOW_DISSECTOR: + ret = skb_flow_dissector_bpf_prog_attach(attr, prog); + break; default: ret = cgroup_bpf_prog_attach(attr, ptype, prog); } @@ -1688,6 +1694,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); + case BPF_FLOW_DISSECTOR: + return skb_flow_dissector_bpf_prog_detach(attr); default: return -EINVAL; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6ff1bac1795d..8ccbff4fff93 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -261,6 +261,7 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", }; static char slot_type_char[] = { @@ -965,6 +966,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: + case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: return true; default: @@ -1238,6 +1240,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_FLOW_DISSECTOR: if (meta) return meta->pkt_access; @@ -1321,6 +1324,18 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, return -EACCES; } +static int check_flow_keys_access(struct bpf_verifier_env *env, int off, + int size) +{ + if (size < 0 || off < 0 || + (u64)off + size > sizeof(struct bpf_flow_keys)) { + verbose(env, "invalid access to flow keys 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) { @@ -1422,6 +1437,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, * right in front, treat it the very same way. */ return check_pkt_ptr_alignment(env, reg, off, size, strict); + case PTR_TO_FLOW_KEYS: + pointer_desc = "flow keys "; + break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; @@ -1692,6 +1710,17 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_packet_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_FLOW_KEYS) { + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose(env, "R%d leaks addr into flow keys\n", + value_regno); + return -EACCES; + } + + err = check_flow_keys_access(env, off, size); + if (!err && t == BPF_READ && 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]); @@ -1839,6 +1868,8 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); + case PTR_TO_FLOW_KEYS: + return check_flow_keys_access(env, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size, zero_size_allowed); @@ -4366,6 +4397,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_CTX: case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: + case PTR_TO_FLOW_KEYS: /* Only valid matches are exact, which memcmp() above * would have accepted */ -- cgit From 788758d1fe874fd20ecb0ab490552d94c024a9de Mon Sep 17 00:00:00 2001 From: zhong jiang Date: Thu, 20 Sep 2018 17:46:12 +0800 Subject: bpf: remove redundant null pointer check before consume_skb consume_skb has taken the null pointer into account. hence it is safe to remove the redundant null pointer check before consume_skb. Signed-off-by: zhong jiang Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- kernel/bpf/sockmap.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 488ef9663c01..a9359cbc3f93 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -590,8 +590,7 @@ static int free_sg(struct sock *sk, int start, if (i == MAX_SKB_FRAGS) i = 0; } - if (md->skb) - consume_skb(md->skb); + consume_skb(md->skb); return free; } @@ -973,8 +972,7 @@ bytes_ready: if (!sg->length && md->sg_start == md->sg_end) { list_del(&md->list); - if (md->skb) - consume_skb(md->skb); + consume_skb(md->skb); kfree(md); } } -- cgit