summaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/arraymap.c2
-rw-r--r--kernel/bpf/core.c2
-rw-r--r--kernel/bpf/devmap.c10
-rw-r--r--kernel/bpf/hashtab.c4
-rw-r--r--kernel/bpf/inode.c1
-rw-r--r--kernel/bpf/sockmap.c57
-rw-r--r--kernel/bpf/verifier.c70
7 files changed, 107 insertions, 39 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 98c0f00c3f5e..e2636737b69b 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -98,7 +98,7 @@ 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/core.c b/kernel/bpf/core.c
index 917cc04a0a94..7b62df86be1d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1022,7 +1022,7 @@ select_insn:
struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog;
- u64 index = BPF_R3;
+ u32 index = BPF_R3;
if (unlikely(index >= array->map.max_entries))
goto out;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index e093d9a2c4dd..e745d6a88224 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -69,7 +69,7 @@ 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)
@@ -78,6 +78,9 @@ 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 & ~BPF_F_NUMA_NODE)
@@ -111,8 +114,9 @@ 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 431126f31ea3..6533f08d1238 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -317,10 +317,6 @@ 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/inode.c b/kernel/bpf/inode.c
index e833ed914358..be1dde967208 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -363,6 +363,7 @@ out:
putname(pname);
return ret;
}
+EXPORT_SYMBOL_GPL(bpf_obj_get_user);
static void bpf_evict_inode(struct inode *inode)
{
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 6424ce0e4969..dbd7b322a86b 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>
struct bpf_stab {
struct bpf_map map;
@@ -92,21 +93,45 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
return rcu_dereference_sk_user_data(sk);
}
+/* compute the linear packet data range [data, data_end) for skb when
+ * sk_skb type programs are in use.
+ */
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+ TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
+
+enum __sk_action {
+ __SK_DROP = 0,
+ __SK_PASS,
+ __SK_REDIRECT,
+};
+
static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
{
struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
int rc;
if (unlikely(!prog))
- return SK_DROP;
+ 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_end(skb);
+ bpf_compute_data_end_sk_skb(skb);
+ preempt_disable();
rc = (*prog->bpf_func)(skb, prog->insnsi);
+ preempt_enable();
skb->sk = NULL;
- return rc;
+ /* Moving return codes from UAPI namespace into internal namespace */
+ return rc == SK_PASS ?
+ (TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) :
+ __SK_DROP;
}
static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
@@ -114,17 +139,10 @@ 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();
+ case __SK_REDIRECT:
+ sk = do_sk_redirect_map(skb);
if (likely(sk)) {
struct smap_psock *peer = smap_psock_sk(sk);
@@ -139,10 +157,8 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
}
}
/* Fall through and free skb otherwise */
- case SK_DROP:
+ case __SK_DROP:
default:
- if (rc != SK_REDIRECT)
- preempt_enable();
kfree_skb(skb);
}
}
@@ -369,7 +385,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
* any socket yet.
*/
skb->sk = psock->sock;
- bpf_compute_data_end(skb);
+ bpf_compute_data_end_sk_skb(skb);
rc = (*prog->bpf_func)(skb, prog->insnsi);
skb->sk = NULL;
rcu_read_unlock();
@@ -487,6 +503,9 @@ 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 & ~BPF_F_NUMA_NODE)
@@ -840,6 +859,12 @@ 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 b914fbe1383e..c48ca2a34b5e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -653,6 +653,10 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno)
{
struct bpf_verifier_state *parent = state->parent;
+ if (regno == BPF_REG_FP)
+ /* We don't need to worry about FP liveness because it's read-only */
+ return;
+
while (parent) {
/* if read wasn't screened by an earlier write ... */
if (state->regs[regno].live & REG_LIVE_WRITTEN)
@@ -1112,7 +1116,12 @@ 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("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);
@@ -1120,7 +1129,6 @@ 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, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
/* ctx access returns either a scalar, or a
@@ -2345,6 +2353,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
* copy register state to dest reg
*/
regs[insn->dst_reg] = regs[insn->src_reg];
+ regs[insn->dst_reg].live |= REG_LIVE_WRITTEN;
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
@@ -2421,12 +2430,15 @@ 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)
+ struct bpf_reg_state *dst_reg,
+ 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;
@@ -2437,9 +2449,13 @@ 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;
@@ -2456,7 +2472,7 @@ 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;
@@ -2474,7 +2490,9 @@ 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
@@ -2485,14 +2503,14 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
for (i = 0; i < MAX_BPF_REG; i++)
if (regs[i].type == PTR_TO_PACKET && 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 == PTR_TO_PACKET && reg->id == dst_reg->id)
- reg->range = max_t(u16, reg->range, dst_reg->off);
+ reg->range = max(reg->range, new_range);
}
}
@@ -2856,19 +2874,43 @@ 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);
+ /* pkt_data' > pkt_end */
+ find_good_pkt_pointers(this_branch, dst_reg, 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, &regs[insn->src_reg], 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) {
- find_good_pkt_pointers(other_branch, dst_reg);
+ /* pkt_data' < pkt_end */
+ find_good_pkt_pointers(other_branch, dst_reg, 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, &regs[insn->src_reg], 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) {
+ /* pkt_data' >= pkt_end */
+ find_good_pkt_pointers(this_branch, dst_reg, 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) {
- find_good_pkt_pointers(other_branch, &regs[insn->src_reg]);
+ /* pkt_end >= pkt_data' */
+ find_good_pkt_pointers(other_branch, &regs[insn->src_reg], 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, 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) {
- find_good_pkt_pointers(this_branch, &regs[insn->src_reg]);
+ /* pkt_end <= pkt_data' */
+ find_good_pkt_pointers(this_branch, &regs[insn->src_reg], true);
} else if (is_pointer_value(env, insn->dst_reg)) {
verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
return -EACCES;
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-11 23:32:58 +0000