diff options
author | David S. Miller <davem@davemloft.net> | 2017-10-22 13:36:53 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-10-22 13:39:14 +0100 |
commit | f8ddadc4db6c7b7029b6d0e0d9af24f74ad27ca2 (patch) | |
tree | 0a6432aba336bae42313613f4c891bcfce02bd4e /kernel/bpf | |
parent | bdd091bab8c631bd2801af838e344fad34566410 (diff) | |
parent | b5ac3beb5a9f0ef0ea64cd85faf94c0dc4de0e42 (diff) | |
download | linux-stable-f8ddadc4db6c7b7029b6d0e0d9af24f74ad27ca2.tar.gz linux-stable-f8ddadc4db6c7b7029b6d0e0d9af24f74ad27ca2.tar.bz2 linux-stable-f8ddadc4db6c7b7029b6d0e0d9af24f74ad27ca2.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
There were quite a few overlapping sets of changes here.
Daniel's bug fix for off-by-ones in the new BPF branch instructions,
along with the added allowances for "data_end > ptr + x" forms
collided with the metadata additions.
Along with those three changes came veritifer test cases, which in
their final form I tried to group together properly. If I had just
trimmed GIT's conflict tags as-is, this would have split up the
meta tests unnecessarily.
In the socketmap code, a set of preemption disabling changes
overlapped with the rename of bpf_compute_data_end() to
bpf_compute_data_pointers().
Changes were made to the mv88e6060.c driver set addr method
which got removed in net-next.
The hyperv transport socket layer had a locking change in 'net'
which overlapped with a change of socket state macro usage
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/arraymap.c | 2 | ||||
-rw-r--r-- | kernel/bpf/devmap.c | 10 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 4 | ||||
-rw-r--r-- | kernel/bpf/sockmap.c | 28 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 82 |
5 files changed, 90 insertions, 36 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 988c04c91e10..7c25426d3cf5 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -102,7 +102,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); if (array_size >= U32_MAX - PAGE_SIZE || - elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { + bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index e5d3de7cff2e..ebdef54bf7df 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -72,7 +72,7 @@ static LIST_HEAD(dev_map_list); static u64 dev_map_bitmap_size(const union bpf_attr *attr) { - return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); + return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long); } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) @@ -81,6 +81,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) @@ -114,8 +117,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) err = -ENOMEM; /* A per cpu bitfield with a bit per possible net device */ - dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), - __alignof__(unsigned long)); + dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr), + __alignof__(unsigned long), + GFP_KERNEL | __GFP_NOWARN); if (!dtab->flush_needed) goto free_dtab; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 919955236e63..e469e05c8e83 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -318,10 +318,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ goto free_htab; - if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE) - /* make sure the size for pcpu_alloc() is reasonable */ - goto free_htab; - htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 86ec846f2d5e..eef843c3b419 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -39,6 +39,7 @@ #include <linux/workqueue.h> #include <linux/list.h> #include <net/strparser.h> +#include <net/tcp.h> #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) @@ -104,9 +105,16 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) return SK_DROP; skb_orphan(skb); + /* We need to ensure that BPF metadata for maps is also cleared + * when we orphan the skb so that we don't have the possibility + * to reference a stale map. + */ + TCP_SKB_CB(skb)->bpf.map = NULL; skb->sk = psock->sock; bpf_compute_data_pointers(skb); + preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); + preempt_enable(); skb->sk = NULL; return rc; @@ -117,17 +125,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) struct sock *sk; int rc; - /* Because we use per cpu values to feed input from sock redirect - * in BPF program to do_sk_redirect_map() call we need to ensure we - * are not preempted. RCU read lock is not sufficient in this case - * with CONFIG_PREEMPT_RCU enabled so we must be explicit here. - */ - preempt_disable(); rc = smap_verdict_func(psock, skb); switch (rc) { case SK_REDIRECT: - sk = do_sk_redirect_map(); - preempt_enable(); + sk = do_sk_redirect_map(skb); if (likely(sk)) { struct smap_psock *peer = smap_psock_sk(sk); @@ -144,8 +145,6 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) /* Fall through and free skb otherwise */ case SK_DROP: default: - if (rc != SK_REDIRECT) - preempt_enable(); kfree_skb(skb); } } @@ -490,6 +489,9 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) @@ -843,6 +845,12 @@ static int sock_map_update_elem(struct bpf_map *map, return -EINVAL; } + if (skops.sk->sk_type != SOCK_STREAM || + skops.sk->sk_protocol != IPPROTO_TCP) { + fput(socket->file); + return -EOPNOTSUPP; + } + err = sock_map_ctx_update_elem(&skops, map, key, flags); fput(socket->file); return err; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 545b8c45a578..d906775e12c1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1006,7 +1006,13 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn /* ctx accesses must be at a fixed offset, so that we can * determine what type of data were returned. */ - if (!tnum_is_const(reg->var_off)) { + if (reg->off) { + verbose(env, + "dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n", + regno, reg->off, off - reg->off); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); @@ -1015,7 +1021,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn tn_buf, off, size); return -EACCES; } - off += reg->var_off.value; err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a @@ -2341,12 +2346,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) static void find_good_pkt_pointers(struct bpf_verifier_state *state, struct bpf_reg_state *dst_reg, - enum bpf_reg_type type) + enum bpf_reg_type type, + bool range_right_open) { struct bpf_reg_state *regs = state->regs, *reg; + u16 new_range; int i; - if (dst_reg->off < 0) + if (dst_reg->off < 0 || + (dst_reg->off == 0 && range_right_open)) /* This doesn't give us any range */ return; @@ -2357,9 +2365,13 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, */ return; - /* LLVM can generate four kind of checks: + new_range = dst_reg->off; + if (range_right_open) + new_range--; + + /* Examples for register markings: * - * Type 1/2: + * pkt_data in dst register: * * r2 = r3; * r2 += 8; @@ -2376,7 +2388,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * - * Type 3/4: + * pkt_data in src register: * * r2 = r3; * r2 += 8; @@ -2394,7 +2406,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) - * so that range of bytes [r3, r3 + 8) is safe to access. + * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) + * and [r3, r3 + 8-1) respectively is safe to access depending on + * the check. */ /* If our ids match, then we must have the same max_value. And we @@ -2405,14 +2419,14 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].type == type && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ - regs[i].range = max_t(u16, regs[i].range, dst_reg->off); + regs[i].range = max(regs[i].range, new_range); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; if (reg->type == type && reg->id == dst_reg->id) - reg->range = max_t(u16, reg->range, dst_reg->off); + reg->range = max_t(u16, reg->range, new_range); } } @@ -2776,39 +2790,71 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET); + /* pkt_data' > pkt_end */ + find_good_pkt_pointers(this_branch, dst_reg, + PTR_TO_PACKET, false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_END && + regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end > pkt_data' */ + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET, true); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET && + regs[insn->src_reg].type == PTR_TO_PACKET_END) { + /* pkt_data' < pkt_end */ + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET, + true); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_END && + regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end < pkt_data' */ + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET, false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET); + /* pkt_data' >= pkt_end */ + find_good_pkt_pointers(this_branch, dst_reg, + PTR_TO_PACKET, true); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end >= pkt_data' */ find_good_pkt_pointers(other_branch, ®s[insn->src_reg], - PTR_TO_PACKET); + PTR_TO_PACKET, false); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + dst_reg->type == PTR_TO_PACKET && + regs[insn->src_reg].type == PTR_TO_PACKET_END) { + /* pkt_data' <= pkt_end */ + find_good_pkt_pointers(other_branch, dst_reg, + PTR_TO_PACKET, false); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { + /* pkt_end <= pkt_data' */ find_good_pkt_pointers(this_branch, ®s[insn->src_reg], - PTR_TO_PACKET); + PTR_TO_PACKET, true); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { - find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET_META); + find_good_pkt_pointers(this_branch, dst_reg, + PTR_TO_PACKET_META, false); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { - find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET_META); + find_good_pkt_pointers(other_branch, dst_reg, + PTR_TO_PACKET_META, false); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && regs[insn->src_reg].type == PTR_TO_PACKET_META) { find_good_pkt_pointers(other_branch, ®s[insn->src_reg], - PTR_TO_PACKET_META); + PTR_TO_PACKET_META, false); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && regs[insn->src_reg].type == PTR_TO_PACKET_META) { find_good_pkt_pointers(this_branch, ®s[insn->src_reg], - PTR_TO_PACKET_META); + PTR_TO_PACKET_META, false); } else if (is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->dst_reg); |