1 files changed, 84 insertions, 23 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index bba502f7cd57..69f4ffc0a282 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -530,12 +530,14 @@ do_pass:
 			*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;
 
@@ -1181,7 +1183,7 @@ static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk)
 	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
 		return -ENOMEM;
 
-	if (sk_unhashed(sk)) {
+	if (sk_unhashed(sk) && sk->sk_reuseport) {
 		err = reuseport_alloc(sk);
 		if (err)
 			return err;
@@ -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;
@@ -1543,7 +1597,6 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
 	}
 
 	skb2->dev = dev;
-	skb_sender_cpu_clear(skb2);
 	return dev_queue_xmit(skb2);
 }
 
@@ -1596,7 +1649,6 @@ int skb_do_redirect(struct sk_buff *skb)
 	}
 
 	skb->dev = dev;
-	skb_sender_cpu_clear(skb);
 	return dev_queue_xmit(skb);
 }
 
@@ -1682,6 +1734,13 @@ 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;
 }
 
@@ -1851,6 +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: