From d623876646be119439999a229a2c3ce30fd197fb Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 8 Feb 2019 22:25:54 -0800 Subject: bpf: Fix narrow load on a bpf_sock returned from sk_lookup() By adding this test to test_verifier: { "reference tracking: access sk->src_ip4 (narrow load)", .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_H, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, src_ip4) + 2), 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, }, The above test loads 2 bytes from sk->src_ip4 where sk is obtained by bpf_sk_lookup_tcp(). It hits an internal verifier error from convert_ctx_accesses(): [root@arch-fb-vm1 bpf]# ./test_verifier 665 665 Failed to load prog 'Invalid argument'! 0: (b7) r2 = 0 1: (63) *(u32 *)(r10 -8) = r2 2: (7b) *(u64 *)(r10 -16) = r2 3: (7b) *(u64 *)(r10 -24) = r2 4: (7b) *(u64 *)(r10 -32) = r2 5: (7b) *(u64 *)(r10 -40) = r2 6: (7b) *(u64 *)(r10 -48) = r2 7: (bf) r2 = r10 8: (07) r2 += -48 9: (b7) r3 = 36 10: (b7) r4 = 0 11: (b7) r5 = 0 12: (85) call bpf_sk_lookup_tcp#84 13: (bf) r6 = r0 14: (15) if r0 == 0x0 goto pc+3 R0=sock(id=1,off=0,imm=0) R6=sock(id=1,off=0,imm=0) R10=fp0,call_-1 fp-8=????0000 fp-16=0000mmmm fp-24=mmmmmmmm fp-32=mmmmmmmm fp-40=mmmmmmmm fp-48=mmmmmmmm refs=1 15: (69) r2 = *(u16 *)(r0 +26) 16: (bf) r1 = r6 17: (85) call bpf_sk_release#86 18: (95) exit from 14 to 18: safe processed 20 insns (limit 131072), stack depth 48 bpf verifier is misconfigured Summary: 0 PASSED, 0 SKIPPED, 1 FAILED The bpf_sock_is_valid_access() is expecting src_ip4 can be narrowly loaded (meaning load any 1 or 2 bytes of the src_ip4) by marking info->ctx_field_size. However, this marked ctx_field_size is not used. This patch fixes it. Due to the recent refactoring in test_verifier, this new test will be added to the bpf-next branch (together with the bpf_tcp_sock patchset) to avoid merge conflict. Fixes: c64b7983288e ("bpf: Add PTR_TO_SOCKET verifier type") Cc: Joe Stringer Signed-off-by: Martin KaFai Lau Acked-by: Joe Stringer Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 56674a7c3778..8f295b790297 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1617,12 +1617,13 @@ 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) +static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, + 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; + 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", @@ -1636,6 +1637,8 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, return -EACCES; } + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + return 0; } @@ -2032,7 +2035,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn verbose(env, "cannot write into socket\n"); return -EACCES; } - err = check_sock_access(env, regno, off, size, t); + err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { -- cgit v1.3-14-g43fede From 3defaf2f15b2bfd86c6664181ac009e91985f8ac Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 10 Feb 2019 12:52:35 -0800 Subject: bpf: fix lockdep false positive in stackmap Lockdep warns about false positive: [ 11.211460] ------------[ cut here ]------------ [ 11.211936] DEBUG_LOCKS_WARN_ON(depth <= 0) [ 11.211985] WARNING: CPU: 0 PID: 141 at ../kernel/locking/lockdep.c:3592 lock_release+0x1ad/0x280 [ 11.213134] Modules linked in: [ 11.214954] RIP: 0010:lock_release+0x1ad/0x280 [ 11.223508] Call Trace: [ 11.223705] [ 11.223874] ? __local_bh_enable+0x7a/0x80 [ 11.224199] up_read+0x1c/0xa0 [ 11.224446] do_up_read+0x12/0x20 [ 11.224713] irq_work_run_list+0x43/0x70 [ 11.225030] irq_work_run+0x26/0x50 [ 11.225310] smp_irq_work_interrupt+0x57/0x1f0 [ 11.225662] irq_work_interrupt+0xf/0x20 since rw_semaphore is released in a different task vs task that locked the sema. It is expected behavior. Fix the warning with up_read_non_owner() and rwsem_release() annotation. Fixes: bae77c5eb5b2 ("bpf: enable stackmap with build_id in nmi context") Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/stackmap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index d43b14535827..950ab2f28922 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry) struct stack_map_irq_work *work; work = container_of(entry, struct stack_map_irq_work, irq_work); - up_read(work->sem); + up_read_non_owner(work->sem); work->sem = NULL; } @@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } else { work->sem = ¤t->mm->mmap_sem; irq_work_queue(&work->irq_work); + /* + * The irq_work will release the mmap_sem with + * up_read_non_owner(). The rwsem_release() is called + * here to release the lock from lockdep's perspective. + */ + rwsem_release(¤t->mm->mmap_sem.dep_map, 1, _RET_IP_); } } -- cgit v1.3-14-g43fede From 7c0cdf0b3940f63d9777c3fcf250a2f83859ca54 Mon Sep 17 00:00:00 2001 From: Alban Crequy Date: Fri, 22 Feb 2019 14:19:08 +0100 Subject: bpf, lpm: fix lookup bug in map_delete_elem trie_delete_elem() was deleting an entry even though it was not matching if the prefixlen was correct. This patch adds a check on matchlen. Reproducer: $ sudo bpftool map create /sys/fs/bpf/mylpm type lpm_trie key 8 value 1 entries 128 name mylpm flags 1 $ sudo bpftool map update pinned /sys/fs/bpf/mylpm key hex 10 00 00 00 aa bb cc dd value hex 01 $ sudo bpftool map dump pinned /sys/fs/bpf/mylpm key: 10 00 00 00 aa bb cc dd value: 01 Found 1 element $ sudo bpftool map delete pinned /sys/fs/bpf/mylpm key hex 10 00 00 00 ff ff ff ff $ echo $? 0 $ sudo bpftool map dump pinned /sys/fs/bpf/mylpm Found 0 elements A similar reproducer is added in the selftests. Without the patch: $ sudo ./tools/testing/selftests/bpf/test_lpm_map test_lpm_map: test_lpm_map.c:485: test_lpm_delete: Assertion `bpf_map_delete_elem(map_fd, key) == -1 && errno == ENOENT' failed. Aborted With the patch: test_lpm_map runs without errors. Fixes: e454cf595853 ("bpf: Implement map_delete_elem for BPF_MAP_TYPE_LPM_TRIE") Cc: Craig Gallek Signed-off-by: Alban Crequy Acked-by: Craig Gallek Signed-off-by: Daniel Borkmann --- kernel/bpf/lpm_trie.c | 1 + tools/testing/selftests/bpf/test_lpm_map.c | 10 ++++++++++ 2 files changed, 11 insertions(+) (limited to 'kernel/bpf') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index abf1002080df..93a5cbbde421 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -471,6 +471,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) } if (!node || node->prefixlen != key->prefixlen || + node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index 147e34cfceb7..02d7c871862a 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -474,6 +474,16 @@ static void test_lpm_delete(void) assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 && errno == ENOENT); + key->prefixlen = 30; // unused prefix so far + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + + key->prefixlen = 16; // same prefix as the root node + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + /* assert initial lookup */ key->prefixlen = 32; inet_pton(AF_INET, "192.168.0.1", key->data); -- cgit v1.3-14-g43fede From 781e62823cb81b972dc8652c1827205cda2ac9ac Mon Sep 17 00:00:00 2001 From: Peng Sun Date: Tue, 26 Feb 2019 22:15:37 +0800 Subject: bpf: decrease usercnt if bpf_map_new_fd() fails in bpf_map_get_fd_by_id() In bpf/syscall.c, bpf_map_get_fd_by_id() use bpf_map_inc_not_zero() to increase the refcount, both map->refcnt and map->usercnt. Then, if bpf_map_new_fd() fails, should handle map->usercnt too. Fixes: bd5f5f4ecb78 ("bpf: Add BPF_MAP_GET_FD_BY_ID") Signed-off-by: Peng Sun Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8577bb7f8be6..f98328abe8fa 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1986,7 +1986,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) fd = bpf_map_new_fd(map, f_flags); if (fd < 0) - bpf_map_put(map); + bpf_map_put_with_uref(map); return fd; } -- cgit v1.3-14-g43fede From 352d20d611414715353ee65fc206ee57ab1a6984 Mon Sep 17 00:00:00 2001 From: Peng Sun Date: Wed, 27 Feb 2019 22:36:25 +0800 Subject: bpf: drop refcount if bpf_map_new_fd() fails in map_create() In bpf/syscall.c, map_create() first set map->usercnt to 1, a file descriptor is supposed to return to userspace. When bpf_map_new_fd() fails, drop the refcount. Fixes: bd5f5f4ecb78 ("bpf: Add BPF_MAP_GET_FD_BY_ID") Signed-off-by: Peng Sun Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f98328abe8fa..84470d1480aa 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -559,12 +559,12 @@ static int map_create(union bpf_attr *attr) err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. - * bpf_map_put() is needed because the above + * bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ - bpf_map_put(map); + bpf_map_put_with_uref(map); return err; } -- cgit v1.3-14-g43fede From 3612af783cf52c74a031a2f11b82247b2599d3cd Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 1 Mar 2019 22:05:29 +0100 Subject: bpf: fix sanitation rewrite in case of non-pointers Marek reported that he saw an issue with the below snippet in that timing measurements where off when loaded as unpriv while results were reasonable when loaded as privileged: [...] uint64_t a = bpf_ktime_get_ns(); uint64_t b = bpf_ktime_get_ns(); uint64_t delta = b - a; if ((int64_t)delta > 0) { [...] Turns out there is a bug where a corner case is missing in the fix d3bd7413e0ca ("bpf: fix sanitation of alu op with pointer / scalar type from different paths"), namely fixup_bpf_calls() only checks whether aux has a non-zero alu_state, but it also needs to test for the case of BPF_ALU_NON_POINTER since in both occasions we need to skip the masking rewrite (as there is nothing to mask). Fixes: d3bd7413e0ca ("bpf: fix sanitation of alu op with pointer / scalar type from different paths") Reported-by: Marek Majkowski Reported-by: Arthur Fabre Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/netdev/CAJPywTJqP34cK20iLM5YmUMz9KXQOdu1-+BZrGMAGgLuBWz7fg@mail.gmail.com/T/ Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8f295b790297..5fcce2f4209d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6920,7 +6920,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) u32 off_reg; aux = &env->insn_aux_data[i + delta]; - if (!aux->alu_state) + if (!aux->alu_state || + aux->alu_state == BPF_ALU_NON_POINTER) continue; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; -- cgit v1.3-14-g43fede