diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0cadbb7456c0b9ff98dd2ce7fa950166aa12eee4..51e498e5470e8f501a8faa3dc71e6bc1b9ef4fda 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -65,6 +65,7 @@ enum bpf_arg_type {
*/
ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */
ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */
+ ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */
ARG_PTR_TO_CTX, /* pointer to context */
ARG_ANYTHING, /* any (initialized) argument is ok */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 89b536796e5350c769641824323caad7cae17a42..6a57757a86cf962e2b45fc8bf82a8b0e36f2546d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2630,6 +2630,13 @@ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len
skb_headroom(skb) + len <= skb->hdr_len;
}
+static inline int skb_try_make_writable(struct sk_buff *skb,
+ unsigned int write_len)
+{
+ return skb_cloned(skb) && !skb_clone_writable(skb, write_len) &&
+ pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+
static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom,
int cloned)
{
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d3e77da8e9e8f355693dc39b71f7c59e8c77c7b6..6496f98d3d681f5434950a294a1174ac4a275840 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -287,6 +287,17 @@ enum bpf_func_id {
* Return: >= 0 stackid on success or negative error
*/
BPF_FUNC_get_stackid,
+
+ /**
+ * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
+ * @from: raw from buffer
+ * @from_size: length of from buffer
+ * @to: raw to buffer
+ * @to_size: length of to buffer
+ * @seed: optional seed
+ * Return: csum result
+ */
+ BPF_FUNC_csum_diff,
__BPF_FUNC_MAX_ID,
};
@@ -302,6 +313,7 @@ enum bpf_func_id {
/* BPF_FUNC_l4_csum_replace flags. */
#define BPF_F_PSEUDO_HDR (1ULL << 4)
+#define BPF_F_MARK_MANGLED_0 (1ULL << 5)
/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
#define BPF_F_INGRESS (1ULL << 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 42ba4ccc020b5e9a0bcd5cac4ac7216b3a68ff6a..36dc497deaa3bc601ac39a21446c6aaa9461b893 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -779,15 +779,24 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
* bytes from that pointer, make sure that it's within stack boundary
* and all elements of stack are initialized
*/
-static int check_stack_boundary(struct verifier_env *env,
- int regno, int access_size)
+static int check_stack_boundary(struct verifier_env *env, int regno,
+ int access_size, bool zero_size_allowed)
{
struct verifier_state *state = &env->cur_state;
struct reg_state *regs = state->regs;
int off, i;
- if (regs[regno].type != PTR_TO_STACK)
+ if (regs[regno].type != PTR_TO_STACK) {
+ if (zero_size_allowed && access_size == 0 &&
+ regs[regno].type == CONST_IMM &&
+ regs[regno].imm == 0)
+ return 0;
+
+ verbose("R%d type=%s expected=%s\n", regno,
+ reg_type_str[regs[regno].type],
+ reg_type_str[PTR_TO_STACK]);
return -EACCES;
+ }
off = regs[regno].imm;
if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
@@ -830,15 +839,24 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
return 0;
}
- if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
+ if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE) {
expected_type = PTR_TO_STACK;
- } else if (arg_type == ARG_CONST_STACK_SIZE) {
+ } else if (arg_type == ARG_CONST_STACK_SIZE ||
+ arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) {
expected_type = CONST_IMM;
} else if (arg_type == ARG_CONST_MAP_PTR) {
expected_type = CONST_PTR_TO_MAP;
} else if (arg_type == ARG_PTR_TO_CTX) {
expected_type = PTR_TO_CTX;
+ } else if (arg_type == ARG_PTR_TO_STACK) {
+ expected_type = PTR_TO_STACK;
+ /* One exception here. In case function allows for NULL to be
+ * passed in as argument, it's a CONST_IMM type. Final test
+ * happens during stack boundary checking.
+ */
+ if (reg->type == CONST_IMM && reg->imm == 0)
+ expected_type = CONST_IMM;
} else {
verbose("unsupported arg_type %d\n", arg_type);
return -EFAULT;
@@ -868,8 +886,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
verbose("invalid map_ptr to access map->key\n");
return -EACCES;
}
- err = check_stack_boundary(env, regno, (*mapp)->key_size);
-
+ err = check_stack_boundary(env, regno, (*mapp)->key_size,
+ false);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
@@ -879,9 +897,12 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
verbose("invalid map_ptr to access map->value\n");
return -EACCES;
}
- err = check_stack_boundary(env, regno, (*mapp)->value_size);
+ err = check_stack_boundary(env, regno, (*mapp)->value_size,
+ false);
+ } else if (arg_type == ARG_CONST_STACK_SIZE ||
+ arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) {
+ bool zero_size_allowed = (arg_type == ARG_CONST_STACK_SIZE_OR_ZERO);
- } else if (arg_type == ARG_CONST_STACK_SIZE) {
/* bpf_xxx(..., buf, len) call will access 'len' bytes
* from stack pointer 'buf'. Check it
* note: regno == len, regno - 1 == buf
@@ -891,7 +912,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
verbose("ARG_CONST_STACK_SIZE cannot be first argument\n");
return -EACCES;
}
- err = check_stack_boundary(env, regno - 1, reg->imm);
+ err = check_stack_boundary(env, regno - 1, reg->imm,
+ zero_size_allowed);
}
return err;
diff --git a/net/core/filter.c b/net/core/filter.c
index 2a6e9562f1ab0c57b78e025c59a118524137fb1e..a3aba15a802544ee87d768637c54054db9f914c2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -530,12 +530,14 @@ static int bpf_convert_filter(struct sock_filter *prog, int len,
*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
break;
- /* RET_K, RET_A are remaped into 2 insns. */
+ /* RET_K is remaped into 2 insns. RET_A case doesn't need an
+ * extra mov as BPF_REG_0 is already mapped into BPF_REG_A.
+ */
case BPF_RET | BPF_A:
case BPF_RET | BPF_K:
- *insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ?
- BPF_K : BPF_X, BPF_REG_0,
- BPF_REG_A, fp->k);
+ if (BPF_RVAL(fp->code) == BPF_K)
+ *insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0,
+ 0, fp->k);
*insn = BPF_EXIT_INSN();
break;
@@ -1333,15 +1335,22 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
return 0;
}
-#define BPF_LDST_LEN 16U
+struct bpf_scratchpad {
+ union {
+ __be32 diff[MAX_BPF_STACK / sizeof(__be32)];
+ u8 buff[MAX_BPF_STACK];
+ };
+};
+
+static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp);
static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
{
+ struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
struct sk_buff *skb = (struct sk_buff *) (long) r1;
int offset = (int) r2;
void *from = (void *) (long) r3;
unsigned int len = (unsigned int) r4;
- char buf[BPF_LDST_LEN];
void *ptr;
if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM)))
@@ -1355,14 +1364,12 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
*
* so check for invalid 'offset' and too large 'len'
*/
- if (unlikely((u32) offset > 0xffff || len > sizeof(buf)))
+ if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff)))
return -EFAULT;
-
- if (unlikely(skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + len)))
+ if (unlikely(skb_try_make_writable(skb, offset + len)))
return -EFAULT;
- ptr = skb_header_pointer(skb, offset, len, buf);
+ ptr = skb_header_pointer(skb, offset, len, sp->buff);
if (unlikely(!ptr))
return -EFAULT;
@@ -1371,7 +1378,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
memcpy(ptr, from, len);
- if (ptr == buf)
+ if (ptr == sp->buff)
/* skb_store_bits cannot return -EFAULT here */
skb_store_bits(skb, offset, ptr, len);
@@ -1400,7 +1407,7 @@ static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
unsigned int len = (unsigned int) r4;
void *ptr;
- if (unlikely((u32) offset > 0xffff || len > BPF_LDST_LEN))
+ if (unlikely((u32) offset > 0xffff || len > MAX_BPF_STACK))
return -EFAULT;
ptr = skb_header_pointer(skb, offset, len, to);
@@ -1432,9 +1439,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
return -EINVAL;
if (unlikely((u32) offset > 0xffff))
return -EFAULT;
-
- if (unlikely(skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(sum))))
+ if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum))))
return -EFAULT;
ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1474,23 +1479,31 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1;
bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
+ bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
int offset = (int) r2;
__sum16 sum, *ptr;
- if (unlikely(flags & ~(BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK)))
+ if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR |
+ BPF_F_HDR_FIELD_MASK)))
return -EINVAL;
if (unlikely((u32) offset > 0xffff))
return -EFAULT;
-
- if (unlikely(skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(sum))))
+ if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum))))
return -EFAULT;
ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
if (unlikely(!ptr))
return -EFAULT;
+ if (is_mmzero && !*ptr)
+ return 0;
switch (flags & BPF_F_HDR_FIELD_MASK) {
+ case 0:
+ if (unlikely(from != 0))
+ return -EINVAL;
+
+ inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo);
+ break;
case 2:
inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo);
break;
@@ -1501,6 +1514,8 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
return -EINVAL;
}
+ if (is_mmzero && !*ptr)
+ *ptr = CSUM_MANGLED_0;
if (ptr == &sum)
/* skb_store_bits guaranteed to not return -EFAULT here */
skb_store_bits(skb, offset, ptr, sizeof(sum));
@@ -1519,6 +1534,45 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = {
.arg5_type = ARG_ANYTHING,
};
+static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed)
+{
+ struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
+ u64 diff_size = from_size + to_size;
+ __be32 *from = (__be32 *) (long) r1;
+ __be32 *to = (__be32 *) (long) r3;
+ int i, j = 0;
+
+ /* This is quite flexible, some examples:
+ *
+ * from_size == 0, to_size > 0, seed := csum --> pushing data
+ * from_size > 0, to_size == 0, seed := csum --> pulling data
+ * from_size > 0, to_size > 0, seed := 0 --> diffing data
+ *
+ * Even for diffing, from_size and to_size don't need to be equal.
+ */
+ if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) ||
+ diff_size > sizeof(sp->diff)))
+ return -EINVAL;
+
+ for (i = 0; i < from_size / sizeof(__be32); i++, j++)
+ sp->diff[j] = ~from[i];
+ for (i = 0; i < to_size / sizeof(__be32); i++, j++)
+ sp->diff[j] = to[i];
+
+ return csum_partial(sp->diff, diff_size, seed);
+}
+
+const struct bpf_func_proto bpf_csum_diff_proto = {
+ .func = bpf_csum_diff,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_STACK,
+ .arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO,
+ .arg3_type = ARG_PTR_TO_STACK,
+ .arg4_type = ARG_CONST_STACK_SIZE_OR_ZERO,
+ .arg5_type = ARG_ANYTHING,
+};
+
static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2;
@@ -1682,6 +1736,13 @@ bool bpf_helper_changes_skb_data(void *func)
return true;
if (func == bpf_skb_vlan_pop)
return true;
+ if (func == bpf_skb_store_bytes)
+ return true;
+ if (func == bpf_l3_csum_replace)
+ return true;
+ if (func == bpf_l4_csum_replace)
+ return true;
+
return false;
}
@@ -1849,6 +1910,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
return &bpf_skb_store_bytes_proto;
case BPF_FUNC_skb_load_bytes:
return &bpf_skb_load_bytes_proto;
+ case BPF_FUNC_csum_diff:
+ return &bpf_csum_diff_proto;
case BPF_FUNC_l3_csum_replace:
return &bpf_l3_csum_replace_proto;
case BPF_FUNC_l4_csum_replace:
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index b07c535ba8e7c6f8dcbc52f4eb69cf4a1ab3d0c2..eeb3eb3ea9ebac1ab55ca9b34e3e6eeb72c1421e 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -105,9 +105,7 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
int hl = ihl + jhl;
if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) ||
- (skb_cloned(skb) &&
- !skb_clone_writable(skb, hl + ntkoff) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+ skb_try_make_writable(skb, hl + ntkoff))
return NULL;
else
return (void *)(skb_network_header(skb) + ihl);
@@ -365,9 +363,7 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
}
if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, sizeof(*iph) + ntkoff) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
goto fail;
ip_send_check(ip_hdr(skb));
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index b7c4ead8b5a8e863d87f8c1c4c1e37840fe50577..27607b863aba39c8fa1a567e2834d432eeb5a7c7 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -126,9 +126,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
addr = iph->daddr;
if (!((old_addr ^ addr) & mask)) {
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, sizeof(*iph) + noff) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_try_make_writable(skb, sizeof(*iph) + noff))
goto drop;
new_addr &= mask;
@@ -156,9 +154,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
struct tcphdr *tcph;
if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
- (skb_cloned(skb) &&
- !skb_clone_writable(skb, ihl + sizeof(*tcph) + noff) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+ skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
goto drop;
tcph = (void *)(skb_network_header(skb) + ihl);
@@ -171,9 +167,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
struct udphdr *udph;
if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
- (skb_cloned(skb) &&
- !skb_clone_writable(skb, ihl + sizeof(*udph) + noff) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+ skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
goto drop;
udph = (void *)(skb_network_header(skb) + ihl);
@@ -213,10 +207,8 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
if ((old_addr ^ addr) & mask)
break;
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, ihl + sizeof(*icmph) +
- sizeof(*iph) + noff) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
+ sizeof(*iph) + noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);