bpf: Add hwtstamp field for the sockops prog

The bpf-tc prog has already been able to access the
skb_hwtstamps(skb)->hwtstamp.  This patch extends the same hwtstamp
access to the sockops prog.

In sockops, the skb is also available to the bpf prog during
the BPF_SOCK_OPS_PARSE_HDR_OPT_CB event.  There is a use case
that the hwtstamp will be useful to the sockops prog to better
measure the one-way-delay when the sender has put the tx
timestamp in the tcp header option.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20221107230420.4192307-2-martin.lau@linux.dev

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 94659f6..fb4c911 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6445,6 +6445,7 @@ struct bpf_sock_ops {
                                 * the outgoing header has not
                                 * been written yet.
                                 */
+       __u64 skb_hwtstamp;
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */

diff --git a/net/core/filter.c b/net/core/filter.c
index cb3b635..cd667cd 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8925,6 +8925,10 @@ static bool sock_ops_is_valid_access(int off, int size,
                        bpf_ctx_record_field_size(info, size_default);
                        return bpf_ctx_narrow_access_ok(off, size,
                                                        size_default);
+               case offsetof(struct bpf_sock_ops, skb_hwtstamp):
+                       if (size != sizeof(__u64))
+                               return false;
+                       break;
                default:
                        if (size != size_default)
                                return false;
@@ -9108,21 +9112,21 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si,
        return insn;
 }
 
-static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si,
+static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg,
                                                  struct bpf_insn *insn)
 {
        /* si->dst_reg = skb_shinfo(SKB); */
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
        *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
-                             BPF_REG_AX, si->src_reg,
+                             BPF_REG_AX, skb_reg,
                              offsetof(struct sk_buff, end));
        *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
-                             si->dst_reg, si->src_reg,
+                             dst_reg, skb_reg,
                              offsetof(struct sk_buff, head));
-       *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
+       *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX);
 #else
        *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
-                             si->dst_reg, si->src_reg,
+                             dst_reg, skb_reg,
                              offsetof(struct sk_buff, end));
 #endif
 
@@ -9515,7 +9519,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
                break;
 
        case offsetof(struct __sk_buff, gso_segs):
-               insn = bpf_convert_shinfo_access(si, insn);
+               insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn);
                *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs),
                                      si->dst_reg, si->dst_reg,
                                      bpf_target_off(struct skb_shared_info,
@@ -9523,7 +9527,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
                                                     target_size));
                break;
        case offsetof(struct __sk_buff, gso_size):
-               insn = bpf_convert_shinfo_access(si, insn);
+               insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn);
                *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size),
                                      si->dst_reg, si->dst_reg,
                                      bpf_target_off(struct skb_shared_info,
@@ -9550,7 +9554,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
                BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8);
                BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0);
 
-               insn = bpf_convert_shinfo_access(si, insn);
+               insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn);
                *insn++ = BPF_LDX_MEM(BPF_DW,
                                      si->dst_reg, si->dst_reg,
                                      bpf_target_off(struct skb_shared_info,
@@ -10400,6 +10404,25 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
                                                       tcp_flags),
                                      si->dst_reg, si->dst_reg, off);
                break;
+       case offsetof(struct bpf_sock_ops, skb_hwtstamp): {
+               struct bpf_insn *jmp_on_null_skb;
+
+               *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+                                                      skb),
+                                     si->dst_reg, si->src_reg,
+                                     offsetof(struct bpf_sock_ops_kern,
+                                              skb));
+               /* Reserve one insn to test skb == NULL */
+               jmp_on_null_skb = insn++;
+               insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn);
+               *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg,
+                                     bpf_target_off(struct skb_shared_info,
+                                                    hwtstamps, 8,
+                                                    target_size));
+               *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0,
+                                              insn - jmp_on_null_skb - 1);
+               break;
+       }
        }
        return insn - insn_buf;
 }

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 94659f6..fb4c911 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6445,6 +6445,7 @@ struct bpf_sock_ops {
                                 * the outgoing header has not
                                 * been written yet.
                                 */
+       __u64 skb_hwtstamp;
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */