bpf: Enable read/write access to skb metadata through a dynptr

Now that we can create a dynptr to skb metadata, make reads to the metadata
area possible with bpf_dynptr_read() or through a bpf_dynptr_slice(), and
make writes to the metadata area possible with bpf_dynptr_write() or
through a bpf_dynptr_slice_rdwr().

Note that for cloned skbs which share data with the original, we limit the
skb metadata dynptr to be read-only since we don't unclone on a
bpf_dynptr_write to metadata.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250814-skb-metadata-thru-dynptr-v7-2-8a39e636e0fb@cloudflare.com

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1e7fd3ee759e07534eee7d8b48cffa1dfea056fb..9ed21b65e2e9685672e7a46199e997fa652c2475 100644 (file)
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1784,6 +1784,7 @@ int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len);
 void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len);
 void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
                      void *buf, unsigned long len, bool flush);
+void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset);
 #else /* CONFIG_NET */
 static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset,
                                       void *to, u32 len)
@@ -1818,6 +1819,11 @@ static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, voi
                                    unsigned long len, bool flush)
 {
 }
+
+static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset)
+{
+       return NULL;
+}
 #endif /* CONFIG_NET */
 
 #endif /* __LINUX_FILTER_H__ */

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9552b32208c54171e2933c3d0aee72bcef214f32..cdffd74ddbe65d880af82419f872bf25976da28c 100644 (file)
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1781,7 +1781,8 @@ static int __bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr_kern *s
        case BPF_DYNPTR_TYPE_XDP:
                return __bpf_xdp_load_bytes(src->data, src->offset + offset, dst, len);
        case BPF_DYNPTR_TYPE_SKB_META:
-               return -EOPNOTSUPP; /* not implemented */
+               memmove(dst, bpf_skb_meta_pointer(src->data, src->offset + offset), len);
+               return 0;
        default:
                WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type);
                return -EFAULT;
@@ -1839,7 +1840,10 @@ int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, void *src,
                        return -EINVAL;
                return __bpf_xdp_store_bytes(dst->data, dst->offset + offset, src, len);
        case BPF_DYNPTR_TYPE_SKB_META:
-               return -EOPNOTSUPP; /* not implemented */
+               if (flags)
+                       return -EINVAL;
+               memmove(bpf_skb_meta_pointer(dst->data, dst->offset + offset), src, len);
+               return 0;
        default:
                WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type);
                return -EFAULT;
@@ -2716,7 +2720,7 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr *p, u32 offset,
                return buffer__opt;
        }
        case BPF_DYNPTR_TYPE_SKB_META:
-               return NULL; /* not implemented */
+               return bpf_skb_meta_pointer(ptr->data, ptr->offset + offset);
        default:
                WARN_ONCE(true, "unknown dynptr type %d\n", type);
                return NULL;

diff --git a/net/core/filter.c b/net/core/filter.c
index 31b4b50dbadf3f02ecc2f70ddf95a1c62caa5350..63f3baee2dafa7266594a51e2cf82768550d34ca 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -11990,6 +11990,16 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
        return func;
 }
 
+/**
+ * bpf_skb_meta_pointer() - Gets a mutable pointer within the skb metadata area.
+ * @skb: socket buffer carrying the metadata
+ * @offset: offset into the metadata area, must be <= skb_metadata_len()
+ */
+void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset)
+{
+       return skb_metadata_end(skb) - skb_metadata_len(skb) + offset;
+}
+
 __bpf_kfunc_start_defs();
 __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags,
                                    struct bpf_dynptr *ptr__uninit)
@@ -12017,6 +12027,9 @@ __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags,
  * XDP context with bpf_xdp_adjust_meta(). Serves as an alternative to
  * &__sk_buff->data_meta.
  *
+ * If passed @skb_ is a clone which shares the data with the original, the
+ * dynptr will be read-only. This limitation may be lifted in the future.
+ *
  * Return:
  * * %0         - dynptr ready to use
  * * %-EINVAL   - invalid flags, dynptr set to null
@@ -12034,6 +12047,9 @@ __bpf_kfunc int bpf_dynptr_from_skb_meta(struct __sk_buff *skb_, u64 flags,
 
        bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB_META, 0, skb_metadata_len(skb));
 
+       if (skb_cloned(skb))
+               bpf_dynptr_set_rdonly(ptr);
+
        return 0;
 }