[PATCH bpf-next v5 0/8] Add the the capability to load HW RX checksum in eBPF programs

[PATCH bpf-next v5 0/8] Add the the capability to load HW RX checksum in eBPF programs

[Lorenzo Bianconi]

Introduce bpf_xdp_metadata_rx_checksum() kfunc in order to load the HW
RX checksum results in the eBPF program binded to the NIC.
Implement xmo_rx_checksum callback for veth and ice drivers.

If the hardware detects a wrong/failed checksum, it will report
CHECKSUM_NONE in the packet metadata. Moreover, CHECKSUM_NONE will be
returned even if the NIC can't parse the packet (e.g. if it does not
support a specific protocol). A possible use case for
bpf_xdp_metadata_rx_checksum() would be to implement a XDP DDoS
application [1] combining the info from bpf_xdp_metadata_rx_checksum()
and bpf_xdp_metadata_rx_hash() kfuncs in order to filter packets with a
wrong/failed checksum.

[1] https://blog.cloudflare.com/unimog-cloudflares-edge-load-balancer/

---
Changes in v5:
- Add new kfunc to Documentation/networking/xdp-rx-metadata.rst
  documentation
- Introduce bpf_skb_rx_checksum kfunc and related selftest.
- Introduce selftest to check the driver invalidates the rx checksum if
  running in XDP mode.

Changes in v4:
- Report cusm and csum_level separately and convert ip_summed to a
  bitmask in bpf_xdp_metadata_rx_hash()
- Fix endianness issue in bpf selftests
- Add a comment about the driver expected behaviour if the the NIC reports
  CHECKSUM_UNNECESSARY or CHECKSUM_COMPLETE and the eBPF program modifes
  the packet
- Introduce bpf_get_skb_cksum kfunc and related selftest to load the
  checksum result to the SCHED_CLS eBPF program attached to the qdisc.
- Link to v3: https://lore.kernel.org/r/20260217-bpf-xdp-meta-rxcksum-v3-0-30024c50ba71@kernel.org

Changes in v3:
- Remoe leftover assignment from v2 in veth_xdp_rx_checksum()
- Fix typos
- Fix commit logs
- Link to v2: https://lore.kernel.org/r/20260213-bpf-xdp-meta-rxcksum-v2-0-a82c4802afbe@kernel.org

Changes in v2:
- Remove XDP_CHECKSUM_PARTIAL definition
- Improve veth_xdp_rx_checksum() callback
- Fix uninitialized case for cksum_meta in ice_get_rx_csum()
- Fix sparse warnings in ice driver
- Fix typos
- Link to v1: https://lore.kernel.org/r/20260210-bpf-xdp-meta-rxcksum-v1-0-e5d55caa0541@kernel.org

Changes in v1:
- Rebase on top of bpf-next
- Test ice driver using xdp_hw_metadata tool available in the bpf
  kernel selftest
- Improve cover letter with an use-case for
  bpf_xdp_metadata_rx_checksum()
- Link to RFC v2: https://lore.kernel.org/r/20250925-bpf-xdp-meta-rxcksum-v2-0-6b3fe987ce91@kernel.org

Changes in RFC v2:
- Squash patch 1/6 and 2/6
- Introduce enum xdp_checksum definitions
- Rework ice support to reuse ice_rx_csum codebase

---
Lorenzo Bianconi (8):
      netlink: specs: add XDP RX checksum capability to XDP metadata specs
      net: veth: add xmo_rx_checksum callback to veth driver
      net: ice: add xmo_rx_checksum callback
      selftests/bpf: add selftest support for bpf_xdp_metadata_rx_checksum
      selftests/bpf: add bpf_xdp_metadata_rx_checksum support to xdp_hw_metadat prog
      net: add bpf_skb_rx_checksum kfunc to read skb checksum metadata
      selftests/bpf: Add test for bpf_skb_rx_checksum kfunc
      selftests: net: add test for XDP_PASS skb checksum invalidation

 Documentation/netlink/specs/netdev.yaml            |   5 +
 Documentation/networking/xdp-rx-metadata.rst       |   8 ++
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c      | 123 ++++++++++++++-------
 drivers/net/veth.c                                 |  32 ++++++
 include/net/xdp.h                                  |  13 +++
 include/uapi/linux/netdev.h                        |   3 +
 net/core/filter.c                                  |  31 ++++++
 net/core/xdp.c                                     |  32 ++++++
 tools/include/uapi/linux/netdev.h                  |   3 +
 tools/testing/selftests/bpf/bpf_kfuncs.h           |   8 ++
 .../selftests/bpf/prog_tests/skb_rx_checksum.c     |  50 +++++++++
 .../selftests/bpf/prog_tests/xdp_metadata.c        |   9 ++
 .../testing/selftests/bpf/progs/skb_rx_checksum.c  |  33 ++++++
 .../testing/selftests/bpf/progs/xdp_hw_metadata.c  |   7 ++
 tools/testing/selftests/bpf/progs/xdp_metadata.c   |   2 +
 tools/testing/selftests/bpf/skb_rx_checksum.h      |   8 ++
 tools/testing/selftests/bpf/xdp_hw_metadata.c      |  31 ++++++
 tools/testing/selftests/bpf/xdp_metadata.h         |  13 +++
 .../selftests/drivers/net/hw/xdp_metadata.py       |  55 ++++++++-
 .../selftests/net/lib/skb_metadata_csum.bpf.c      |  73 ++++++++++++
 20 files changed, 496 insertions(+), 43 deletions(-)
---
base-commit: f6f3b36c15ed44de1fbb44e645e4fae8c4a4453e
change-id: 20250925-bpf-xdp-meta-rxcksum-900685e2909d

Best regards,
-- 
Lorenzo Bianconi <lorenzo@kernel.org>

[Intel-wired-lan] [PATCH bpf-next v5 0/8] Add the the capability to load HW RX checksum in eBPF programs

[Lorenzo Bianconi]

Introduce bpf_xdp_metadata_rx_checksum() kfunc in order to load the HW
RX checksum results in the eBPF program binded to the NIC.
Implement xmo_rx_checksum callback for veth and ice drivers.

If the hardware detects a wrong/failed checksum, it will report
CHECKSUM_NONE in the packet metadata. Moreover, CHECKSUM_NONE will be
returned even if the NIC can't parse the packet (e.g. if it does not
support a specific protocol). A possible use case for
bpf_xdp_metadata_rx_checksum() would be to implement a XDP DDoS
application [1] combining the info from bpf_xdp_metadata_rx_checksum()
and bpf_xdp_metadata_rx_hash() kfuncs in order to filter packets with a
wrong/failed checksum.

[1] https://blog.cloudflare.com/unimog-cloudflares-edge-load-balancer/

---
Changes in v5:
- Add new kfunc to Documentation/networking/xdp-rx-metadata.rst
  documentation
- Introduce bpf_skb_rx_checksum kfunc and related selftest.
- Introduce selftest to check the driver invalidates the rx checksum if
  running in XDP mode.

Changes in v4:
- Report cusm and csum_level separately and convert ip_summed to a
  bitmask in bpf_xdp_metadata_rx_hash()
- Fix endianness issue in bpf selftests
- Add a comment about the driver expected behaviour if the the NIC reports
  CHECKSUM_UNNECESSARY or CHECKSUM_COMPLETE and the eBPF program modifes
  the packet
- Introduce bpf_get_skb_cksum kfunc and related selftest to load the
  checksum result to the SCHED_CLS eBPF program attached to the qdisc.
- Link to v3: https://lore.kernel.org/r/20260217-bpf-xdp-meta-rxcksum-v3-0-30024c50ba71@kernel.org

Changes in v3:
- Remoe leftover assignment from v2 in veth_xdp_rx_checksum()
- Fix typos
- Fix commit logs
- Link to v2: https://lore.kernel.org/r/20260213-bpf-xdp-meta-rxcksum-v2-0-a82c4802afbe@kernel.org

Changes in v2:
- Remove XDP_CHECKSUM_PARTIAL definition
- Improve veth_xdp_rx_checksum() callback
- Fix uninitialized case for cksum_meta in ice_get_rx_csum()
- Fix sparse warnings in ice driver
- Fix typos
- Link to v1: https://lore.kernel.org/r/20260210-bpf-xdp-meta-rxcksum-v1-0-e5d55caa0541@kernel.org

Changes in v1:
- Rebase on top of bpf-next
- Test ice driver using xdp_hw_metadata tool available in the bpf
  kernel selftest
- Improve cover letter with an use-case for
  bpf_xdp_metadata_rx_checksum()
- Link to RFC v2: https://lore.kernel.org/r/20250925-bpf-xdp-meta-rxcksum-v2-0-6b3fe987ce91@kernel.org

Changes in RFC v2:
- Squash patch 1/6 and 2/6
- Introduce enum xdp_checksum definitions
- Rework ice support to reuse ice_rx_csum codebase

---
Lorenzo Bianconi (8):
      netlink: specs: add XDP RX checksum capability to XDP metadata specs
      net: veth: add xmo_rx_checksum callback to veth driver
      net: ice: add xmo_rx_checksum callback
      selftests/bpf: add selftest support for bpf_xdp_metadata_rx_checksum
      selftests/bpf: add bpf_xdp_metadata_rx_checksum support to xdp_hw_metadat prog
      net: add bpf_skb_rx_checksum kfunc to read skb checksum metadata
      selftests/bpf: Add test for bpf_skb_rx_checksum kfunc
      selftests: net: add test for XDP_PASS skb checksum invalidation

 Documentation/netlink/specs/netdev.yaml            |   5 +
 Documentation/networking/xdp-rx-metadata.rst       |   8 ++
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c      | 123 ++++++++++++++-------
 drivers/net/veth.c                                 |  32 ++++++
 include/net/xdp.h                                  |  13 +++
 include/uapi/linux/netdev.h                        |   3 +
 net/core/filter.c                                  |  31 ++++++
 net/core/xdp.c                                     |  32 ++++++
 tools/include/uapi/linux/netdev.h                  |   3 +
 tools/testing/selftests/bpf/bpf_kfuncs.h           |   8 ++
 .../selftests/bpf/prog_tests/skb_rx_checksum.c     |  50 +++++++++
 .../selftests/bpf/prog_tests/xdp_metadata.c        |   9 ++
 .../testing/selftests/bpf/progs/skb_rx_checksum.c  |  33 ++++++
 .../testing/selftests/bpf/progs/xdp_hw_metadata.c  |   7 ++
 tools/testing/selftests/bpf/progs/xdp_metadata.c   |   2 +
 tools/testing/selftests/bpf/skb_rx_checksum.h      |   8 ++
 tools/testing/selftests/bpf/xdp_hw_metadata.c      |  31 ++++++
 tools/testing/selftests/bpf/xdp_metadata.h         |  13 +++
 .../selftests/drivers/net/hw/xdp_metadata.py       |  55 ++++++++-
 .../selftests/net/lib/skb_metadata_csum.bpf.c      |  73 ++++++++++++
 20 files changed, 496 insertions(+), 43 deletions(-)
---
base-commit: f6f3b36c15ed44de1fbb44e645e4fae8c4a4453e
change-id: 20250925-bpf-xdp-meta-rxcksum-900685e2909d

Best regards,
-- 
Lorenzo Bianconi <lorenzo@kernel.org>

[PATCH bpf-next v5 1/8] netlink: specs: add XDP RX checksum capability to XDP metadata specs

[Lorenzo Bianconi]

Introduce XDP RX checksum capability to XDP metadata specs. XDP RX
checksum will be use by devices capable of exposing receive checksum
result via bpf_xdp_metadata_rx_checksum().
Moreover, introduce xmo_rx_checksum netdev callback in order to allow
the eBPF program bound to the device to retrieve the RX checksum result
computed by the hw NIC and reported via DMA descriptors.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml      |  5 +++++
 Documentation/networking/xdp-rx-metadata.rst |  3 +++
 include/net/xdp.h                            | 13 +++++++++++
 include/uapi/linux/netdev.h                  |  3 +++
 net/core/xdp.c                               | 32 ++++++++++++++++++++++++++++
 tools/include/uapi/linux/netdev.h            |  3 +++
 6 files changed, 59 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 5f143da7458c..6d0d90d3a614 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -61,6 +61,11 @@ definitions:
         doc: |
           Device is capable of exposing receive packet VLAN tag via
           bpf_xdp_metadata_rx_vlan_tag().
+      -
+        name: checksum
+        doc: |
+          Device is capable of exposing receive checksum result via
+          bpf_xdp_metadata_rx_checksum().
   -
     type: flags
     name: xsk-flags
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index efdf5eeb49e7..93918b3769a3 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -28,6 +28,9 @@ metadata is supported, this set will grow:
 .. kernel-doc:: net/core/xdp.c
    :identifiers: bpf_xdp_metadata_rx_vlan_tag
 
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_checksum
+
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
 consumers, an XDP program can store it into the metadata area carried
diff --git a/include/net/xdp.h b/include/net/xdp.h
index aa742f413c35..d95e126f2426 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -586,6 +586,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   NETDEV_XDP_RX_METADATA_VLAN_TAG, \
 			   bpf_xdp_metadata_rx_vlan_tag, \
 			   xmo_rx_vlan_tag) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_CHECKSUM, \
+			   NETDEV_XDP_RX_METADATA_CHECKSUM, \
+			   bpf_xdp_metadata_rx_checksum, \
+			   xmo_rx_checksum)
 
 enum xdp_rx_metadata {
 #define XDP_METADATA_KFUNC(name, _, __, ___) name,
@@ -643,12 +647,21 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR,
 };
 
+enum xdp_checksum {
+	XDP_CHECKSUM_NONE		= BIT(CHECKSUM_NONE),
+	XDP_CHECKSUM_UNNECESSARY	= BIT(CHECKSUM_UNNECESSARY),
+	XDP_CHECKSUM_COMPLETE		= BIT(CHECKSUM_COMPLETE),
+};
+
 struct xdp_metadata_ops {
 	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
 	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
 			       enum xdp_rss_hash_type *rss_type);
 	int	(*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto,
 				   u16 *vlan_tci);
+	int	(*xmo_rx_checksum)(const struct xdp_md *ctx,
+				   enum xdp_checksum *ip_summed,
+				   u32 *cksum, u8 *cksum_level);
 };
 
 #ifdef CONFIG_NET
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 2f3ab75e8cc0..f8caade93c8c 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -47,11 +47,14 @@ enum netdev_xdp_act {
  *   hash via bpf_xdp_metadata_rx_hash().
  * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
  *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
+ * @NETDEV_XDP_RX_METADATA_CHECKSUM: Device is capable of exposing receive
+ *   checksum result via bpf_xdp_metadata_rx_checksum().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
 	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+	NETDEV_XDP_RX_METADATA_CHECKSUM = 8,
 };
 
 /**
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 9890a30584ba..9bcaa423ad17 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -961,6 +961,38 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_checksum - Read XDP frame RX checksum.
+ * @ctx: XDP context pointer.
+ * @ip_summed: Return value pointer to a bitmask indicating available checksums.
+ * @cksum: Return value pointer indicating the hw checksum value.
+ * @cksum_level: Return value pointer indicating the checksum level result.
+ *
+ * In case of success, ``ip_summed`` is set to the RX checksum result. Possible
+ * values are:
+ * ``XDP_CHECKSUM_NONE``
+ * ``XDP_CHECKSUM_UNNECESSARY``
+ * ``XDP_CHECKSUM_COMPLETE``
+ * ``XDP_CHECKSUM_COMPLETE`` | ``XDP_CHECKSUM_UNNECESSARY``
+ *
+ * In case of success, ``cksum`` contains the checksum value calculated by the
+ * NIC. ``cksum`` is valid only if ``XDP_CHECKSUM_COMPLETE`` is set in
+ * ``ip_summed``. ``cksum_level`` contains the checksum level reported by the
+ * hw. ``cksum_level`` can be considered valid only if
+ * ``XDP_CHECKSUM_UNNECESSARY`` is set in ``ip_summed``.
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc
+ * * ``-ENODATA``    : means no RX-checksum available for this frame
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_checksum(const struct xdp_md *ctx,
+					     enum xdp_checksum *ip_summed,
+					     u32 *cksum, u8 *cksum_level)
+{
+	return -EOPNOTSUPP;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(xdp_metadata_kfunc_ids)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 2f3ab75e8cc0..f8caade93c8c 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -47,11 +47,14 @@ enum netdev_xdp_act {
  *   hash via bpf_xdp_metadata_rx_hash().
  * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
  *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
+ * @NETDEV_XDP_RX_METADATA_CHECKSUM: Device is capable of exposing receive
+ *   checksum result via bpf_xdp_metadata_rx_checksum().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
 	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+	NETDEV_XDP_RX_METADATA_CHECKSUM = 8,
 };
 
 /**

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 1/8] netlink: specs: add XDP RX checksum capability to XDP metadata specs

[Lorenzo Bianconi]

Introduce XDP RX checksum capability to XDP metadata specs. XDP RX
checksum will be use by devices capable of exposing receive checksum
result via bpf_xdp_metadata_rx_checksum().
Moreover, introduce xmo_rx_checksum netdev callback in order to allow
the eBPF program bound to the device to retrieve the RX checksum result
computed by the hw NIC and reported via DMA descriptors.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml      |  5 +++++
 Documentation/networking/xdp-rx-metadata.rst |  3 +++
 include/net/xdp.h                            | 13 +++++++++++
 include/uapi/linux/netdev.h                  |  3 +++
 net/core/xdp.c                               | 32 ++++++++++++++++++++++++++++
 tools/include/uapi/linux/netdev.h            |  3 +++
 6 files changed, 59 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 5f143da7458c..6d0d90d3a614 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -61,6 +61,11 @@ definitions:
         doc: |
           Device is capable of exposing receive packet VLAN tag via
           bpf_xdp_metadata_rx_vlan_tag().
+      -
+        name: checksum
+        doc: |
+          Device is capable of exposing receive checksum result via
+          bpf_xdp_metadata_rx_checksum().
   -
     type: flags
     name: xsk-flags
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index efdf5eeb49e7..93918b3769a3 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -28,6 +28,9 @@ metadata is supported, this set will grow:
 .. kernel-doc:: net/core/xdp.c
    :identifiers: bpf_xdp_metadata_rx_vlan_tag
 
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_checksum
+
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
 consumers, an XDP program can store it into the metadata area carried
diff --git a/include/net/xdp.h b/include/net/xdp.h
index aa742f413c35..d95e126f2426 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -586,6 +586,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   NETDEV_XDP_RX_METADATA_VLAN_TAG, \
 			   bpf_xdp_metadata_rx_vlan_tag, \
 			   xmo_rx_vlan_tag) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_CHECKSUM, \
+			   NETDEV_XDP_RX_METADATA_CHECKSUM, \
+			   bpf_xdp_metadata_rx_checksum, \
+			   xmo_rx_checksum)
 
 enum xdp_rx_metadata {
 #define XDP_METADATA_KFUNC(name, _, __, ___) name,
@@ -643,12 +647,21 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR,
 };
 
+enum xdp_checksum {
+	XDP_CHECKSUM_NONE		= BIT(CHECKSUM_NONE),
+	XDP_CHECKSUM_UNNECESSARY	= BIT(CHECKSUM_UNNECESSARY),
+	XDP_CHECKSUM_COMPLETE		= BIT(CHECKSUM_COMPLETE),
+};
+
 struct xdp_metadata_ops {
 	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
 	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
 			       enum xdp_rss_hash_type *rss_type);
 	int	(*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto,
 				   u16 *vlan_tci);
+	int	(*xmo_rx_checksum)(const struct xdp_md *ctx,
+				   enum xdp_checksum *ip_summed,
+				   u32 *cksum, u8 *cksum_level);
 };
 
 #ifdef CONFIG_NET
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 2f3ab75e8cc0..f8caade93c8c 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -47,11 +47,14 @@ enum netdev_xdp_act {
  *   hash via bpf_xdp_metadata_rx_hash().
  * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
  *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
+ * @NETDEV_XDP_RX_METADATA_CHECKSUM: Device is capable of exposing receive
+ *   checksum result via bpf_xdp_metadata_rx_checksum().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
 	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+	NETDEV_XDP_RX_METADATA_CHECKSUM = 8,
 };
 
 /**
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 9890a30584ba..9bcaa423ad17 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -961,6 +961,38 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_checksum - Read XDP frame RX checksum.
+ * @ctx: XDP context pointer.
+ * @ip_summed: Return value pointer to a bitmask indicating available checksums.
+ * @cksum: Return value pointer indicating the hw checksum value.
+ * @cksum_level: Return value pointer indicating the checksum level result.
+ *
+ * In case of success, ``ip_summed`` is set to the RX checksum result. Possible
+ * values are:
+ * ``XDP_CHECKSUM_NONE``
+ * ``XDP_CHECKSUM_UNNECESSARY``
+ * ``XDP_CHECKSUM_COMPLETE``
+ * ``XDP_CHECKSUM_COMPLETE`` | ``XDP_CHECKSUM_UNNECESSARY``
+ *
+ * In case of success, ``cksum`` contains the checksum value calculated by the
+ * NIC. ``cksum`` is valid only if ``XDP_CHECKSUM_COMPLETE`` is set in
+ * ``ip_summed``. ``cksum_level`` contains the checksum level reported by the
+ * hw. ``cksum_level`` can be considered valid only if
+ * ``XDP_CHECKSUM_UNNECESSARY`` is set in ``ip_summed``.
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc
+ * * ``-ENODATA``    : means no RX-checksum available for this frame
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_checksum(const struct xdp_md *ctx,
+					     enum xdp_checksum *ip_summed,
+					     u32 *cksum, u8 *cksum_level)
+{
+	return -EOPNOTSUPP;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(xdp_metadata_kfunc_ids)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 2f3ab75e8cc0..f8caade93c8c 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -47,11 +47,14 @@ enum netdev_xdp_act {
  *   hash via bpf_xdp_metadata_rx_hash().
  * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
  *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
+ * @NETDEV_XDP_RX_METADATA_CHECKSUM: Device is capable of exposing receive
+ *   checksum result via bpf_xdp_metadata_rx_checksum().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
 	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
+	NETDEV_XDP_RX_METADATA_CHECKSUM = 8,
 };
 
 /**

-- 
2.55.0

[PATCH bpf-next v5 2/8] net: veth: add xmo_rx_checksum callback to veth driver

[Lorenzo Bianconi]

Implement xmo_rx_checksum callback in veth driver to report RX checksum
result to the eBPF program bounded to the veth device.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 drivers/net/veth.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8170bf33ccf9..dbf30089581c 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1701,6 +1701,37 @@ static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
 	return err;
 }
 
+static int veth_xdp_rx_checksum(const struct xdp_md *ctx,
+				enum xdp_checksum *ip_summed,
+				u32 *cksum, u8 *cksum_level)
+{
+	const struct veth_xdp_buff *_ctx = (void *)ctx;
+	const struct sk_buff *skb = _ctx->skb;
+
+	if (!skb)
+		return -ENODATA;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		*ip_summed = XDP_CHECKSUM_COMPLETE;
+		*cksum = skb->csum;
+		*cksum_level = 0;
+		break;
+	case CHECKSUM_UNNECESSARY:
+		*ip_summed = XDP_CHECKSUM_UNNECESSARY;
+		*cksum_level = skb->csum_level;
+		*cksum = 0;
+		break;
+	default:
+		*ip_summed = XDP_CHECKSUM_NONE;
+		*cksum_level = 0;
+		*cksum = 0;
+		break;
+	}
+
+	return 0;
+}
+
 static const struct net_device_ops veth_netdev_ops = {
 	.ndo_init            = veth_dev_init,
 	.ndo_open            = veth_open,
@@ -1726,6 +1757,7 @@ static const struct xdp_metadata_ops veth_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= veth_xdp_rx_timestamp,
 	.xmo_rx_hash			= veth_xdp_rx_hash,
 	.xmo_rx_vlan_tag		= veth_xdp_rx_vlan_tag,
+	.xmo_rx_checksum		= veth_xdp_rx_checksum,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 2/8] net: veth: add xmo_rx_checksum callback to veth driver

[Lorenzo Bianconi]

Implement xmo_rx_checksum callback in veth driver to report RX checksum
result to the eBPF program bounded to the veth device.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 drivers/net/veth.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8170bf33ccf9..dbf30089581c 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1701,6 +1701,37 @@ static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
 	return err;
 }
 
+static int veth_xdp_rx_checksum(const struct xdp_md *ctx,
+				enum xdp_checksum *ip_summed,
+				u32 *cksum, u8 *cksum_level)
+{
+	const struct veth_xdp_buff *_ctx = (void *)ctx;
+	const struct sk_buff *skb = _ctx->skb;
+
+	if (!skb)
+		return -ENODATA;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		*ip_summed = XDP_CHECKSUM_COMPLETE;
+		*cksum = skb->csum;
+		*cksum_level = 0;
+		break;
+	case CHECKSUM_UNNECESSARY:
+		*ip_summed = XDP_CHECKSUM_UNNECESSARY;
+		*cksum_level = skb->csum_level;
+		*cksum = 0;
+		break;
+	default:
+		*ip_summed = XDP_CHECKSUM_NONE;
+		*cksum_level = 0;
+		*cksum = 0;
+		break;
+	}
+
+	return 0;
+}
+
 static const struct net_device_ops veth_netdev_ops = {
 	.ndo_init            = veth_dev_init,
 	.ndo_open            = veth_open,
@@ -1726,6 +1757,7 @@ static const struct xdp_metadata_ops veth_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= veth_xdp_rx_timestamp,
 	.xmo_rx_hash			= veth_xdp_rx_hash,
 	.xmo_rx_vlan_tag		= veth_xdp_rx_vlan_tag,
+	.xmo_rx_checksum		= veth_xdp_rx_checksum,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \

-- 
2.55.0

[PATCH bpf-next v5 3/8] net: ice: add xmo_rx_checksum callback

[Lorenzo Bianconi]

Implement xmo_rx_checksum callback in ice driver to report RX checksum
result to the eBPF program bounded to the NIC.
Introduce ice_get_rx_csum utility routine in order to make the rx checksum
code reusable from ice_rx_csum()

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 123 +++++++++++++++++---------
 1 file changed, 81 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index e695a664e53d..3aa82ff03d9e 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -78,69 +78,48 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
 		libeth_rx_pt_set_hash(skb, hash, decoded);
 }
 
-/**
- * ice_rx_gcs - Set generic checksum in skb
- * @skb: skb currently being received and modified
- * @rx_desc: receive descriptor
- */
-static void ice_rx_gcs(struct sk_buff *skb,
-		       const union ice_32b_rx_flex_desc *rx_desc)
-{
-	const struct ice_32b_rx_flex_desc_nic *desc;
-	u16 csum;
-
-	desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	csum = (__force u16)desc->raw_csum;
-	skb->csum = csum_unfold((__force __sum16)swab16(csum));
-}
-
-/**
- * ice_rx_csum - Indicate in skb if checksum is good
- * @ring: the ring we care about
- * @skb: skb currently being received and modified
- * @rx_desc: the receive descriptor
- * @ptype: the packet type decoded by hardware
- *
- * skb->protocol must be set before this function is called
- */
 static void
-ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
-	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
+ice_get_rx_csum(const union ice_32b_rx_flex_desc *rx_desc, u16 ptype,
+		struct ice_rx_ring *ring, enum xdp_checksum *ip_summed,
+		u32 *cksum, u8 *cksum_level)
 {
-	struct libeth_rx_pt decoded;
+	struct libeth_rx_pt decoded = libie_rx_pt_parse(ptype);
 	u16 rx_status0, rx_status1;
 	bool ipv4, ipv6;
 
-	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
-	skb->ip_summed = CHECKSUM_NONE;
-
-	decoded = libie_rx_pt_parse(ptype);
 	if (!libeth_rx_pt_has_checksum(ring->netdev, decoded))
-		return;
+		goto checksum_none;
 
 	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
 	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
-
 	if ((ring->flags & ICE_RX_FLAGS_RING_GCS) &&
 	    rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC &&
 	    (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP ||
 	     decoded.inner_prot == LIBETH_RX_PT_INNER_UDP ||
 	     decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) {
-		ice_rx_gcs(skb, rx_desc);
+		const struct ice_32b_rx_flex_desc_nic *desc;
+		__wsum wcsum;
+		u16 csum;
+
+		desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+		*ip_summed = XDP_CHECKSUM_COMPLETE;
+		csum = (__force u16)desc->raw_csum;
+		wcsum = csum_unfold((__force __sum16)swab16(csum));
+		*cksum = (__force u32)wcsum;
+		*cksum_level = 0;
 		return;
 	}
 
 	/* check if HW has decoded the packet and checksum */
 	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
-		return;
+		goto checksum_none;
 
 	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
 	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
 
 	if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) {
 		ring->vsi->back->hw_rx_eipe_error++;
-		return;
+		goto checksum_none;
 	}
 
 	if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S))))
@@ -164,14 +143,51 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	 * we need to bump the checksum level by 1 to reflect the fact that
 	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT)
-		skb->csum_level = 1;
-
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	*cksum_level = decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT;
+	*ip_summed = XDP_CHECKSUM_UNNECESSARY;
+	*cksum = 0;
 	return;
 
 checksum_fail:
 	ring->vsi->back->hw_csum_rx_error++;
+checksum_none:
+	*ip_summed = XDP_CHECKSUM_NONE;
+	*cksum_level = 0;
+	*cksum = 0;
+}
+
+/**
+ * ice_rx_csum - Indicate in skb if checksum is good
+ * @ring: the ring we care about
+ * @skb: skb currently being received and modified
+ * @rx_desc: the receive descriptor
+ * @ptype: the packet type decoded by hardware
+ *
+ * skb->protocol must be set before this function is called
+ */
+static void
+ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
+	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
+{
+	enum xdp_checksum ip_summed;
+	u8 cksum_level;
+	u32 cksum;
+
+	ice_get_rx_csum(rx_desc, ptype, ring, &ip_summed, &cksum,
+			&cksum_level);
+	switch (ip_summed) {
+	case XDP_CHECKSUM_UNNECESSARY:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = cksum_level;
+		break;
+	case XDP_CHECKSUM_COMPLETE:
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = (__force __wsum)cksum;
+		break;
+	default:
+		skb->ip_summed = CHECKSUM_NONE;
+		break;
+	}
 }
 
 /**
@@ -566,6 +582,28 @@ static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return 0;
 }
 
+/**
+ * ice_xdp_rx_checksum - RX checksum XDP hint handler
+ * @ctx: XDP buff pointer
+ * @ip_summed: RX checksum result destination address
+ * @cksum: RX checksum value destination address
+ * @cksum_level: RX checksum level value destination address
+ */
+static int ice_xdp_rx_checksum(const struct xdp_md *ctx,
+			       enum xdp_checksum *ip_summed,
+			       u32 *cksum, u8 *cksum_level)
+{
+	const struct libeth_xdp_buff *xdp_ext = (void *)ctx;
+	const union ice_32b_rx_flex_desc *rx_desc = xdp_ext->desc;
+	struct ice_rx_ring *ring;
+
+	ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*ring), xdp_rxq);
+	ice_get_rx_csum(rx_desc, ice_get_ptype(rx_desc), ring, ip_summed,
+			cksum, cksum_level);
+
+	return 0;
+}
+
 /**
  * ice_xdp_rx_vlan_tag - VLAN tag XDP hint handler
  * @ctx: XDP buff pointer
@@ -598,4 +636,5 @@ const struct xdp_metadata_ops ice_xdp_md_ops = {
 	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
 	.xmo_rx_hash			= ice_xdp_rx_hash,
 	.xmo_rx_vlan_tag		= ice_xdp_rx_vlan_tag,
+	.xmo_rx_checksum		= ice_xdp_rx_checksum,
 };

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 3/8] net: ice: add xmo_rx_checksum callback

[Lorenzo Bianconi]

Implement xmo_rx_checksum callback in ice driver to report RX checksum
result to the eBPF program bounded to the NIC.
Introduce ice_get_rx_csum utility routine in order to make the rx checksum
code reusable from ice_rx_csum()

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 123 +++++++++++++++++---------
 1 file changed, 81 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index e695a664e53d..3aa82ff03d9e 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -78,69 +78,48 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
 		libeth_rx_pt_set_hash(skb, hash, decoded);
 }
 
-/**
- * ice_rx_gcs - Set generic checksum in skb
- * @skb: skb currently being received and modified
- * @rx_desc: receive descriptor
- */
-static void ice_rx_gcs(struct sk_buff *skb,
-		       const union ice_32b_rx_flex_desc *rx_desc)
-{
-	const struct ice_32b_rx_flex_desc_nic *desc;
-	u16 csum;
-
-	desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	csum = (__force u16)desc->raw_csum;
-	skb->csum = csum_unfold((__force __sum16)swab16(csum));
-}
-
-/**
- * ice_rx_csum - Indicate in skb if checksum is good
- * @ring: the ring we care about
- * @skb: skb currently being received and modified
- * @rx_desc: the receive descriptor
- * @ptype: the packet type decoded by hardware
- *
- * skb->protocol must be set before this function is called
- */
 static void
-ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
-	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
+ice_get_rx_csum(const union ice_32b_rx_flex_desc *rx_desc, u16 ptype,
+		struct ice_rx_ring *ring, enum xdp_checksum *ip_summed,
+		u32 *cksum, u8 *cksum_level)
 {
-	struct libeth_rx_pt decoded;
+	struct libeth_rx_pt decoded = libie_rx_pt_parse(ptype);
 	u16 rx_status0, rx_status1;
 	bool ipv4, ipv6;
 
-	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
-	skb->ip_summed = CHECKSUM_NONE;
-
-	decoded = libie_rx_pt_parse(ptype);
 	if (!libeth_rx_pt_has_checksum(ring->netdev, decoded))
-		return;
+		goto checksum_none;
 
 	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
 	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
-
 	if ((ring->flags & ICE_RX_FLAGS_RING_GCS) &&
 	    rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC &&
 	    (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP ||
 	     decoded.inner_prot == LIBETH_RX_PT_INNER_UDP ||
 	     decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) {
-		ice_rx_gcs(skb, rx_desc);
+		const struct ice_32b_rx_flex_desc_nic *desc;
+		__wsum wcsum;
+		u16 csum;
+
+		desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+		*ip_summed = XDP_CHECKSUM_COMPLETE;
+		csum = (__force u16)desc->raw_csum;
+		wcsum = csum_unfold((__force __sum16)swab16(csum));
+		*cksum = (__force u32)wcsum;
+		*cksum_level = 0;
 		return;
 	}
 
 	/* check if HW has decoded the packet and checksum */
 	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
-		return;
+		goto checksum_none;
 
 	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
 	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
 
 	if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) {
 		ring->vsi->back->hw_rx_eipe_error++;
-		return;
+		goto checksum_none;
 	}
 
 	if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S))))
@@ -164,14 +143,51 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	 * we need to bump the checksum level by 1 to reflect the fact that
 	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT)
-		skb->csum_level = 1;
-
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	*cksum_level = decoded.tunnel_type >= LIBETH_RX_PT_TUNNEL_IP_GRENAT;
+	*ip_summed = XDP_CHECKSUM_UNNECESSARY;
+	*cksum = 0;
 	return;
 
 checksum_fail:
 	ring->vsi->back->hw_csum_rx_error++;
+checksum_none:
+	*ip_summed = XDP_CHECKSUM_NONE;
+	*cksum_level = 0;
+	*cksum = 0;
+}
+
+/**
+ * ice_rx_csum - Indicate in skb if checksum is good
+ * @ring: the ring we care about
+ * @skb: skb currently being received and modified
+ * @rx_desc: the receive descriptor
+ * @ptype: the packet type decoded by hardware
+ *
+ * skb->protocol must be set before this function is called
+ */
+static void
+ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
+	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
+{
+	enum xdp_checksum ip_summed;
+	u8 cksum_level;
+	u32 cksum;
+
+	ice_get_rx_csum(rx_desc, ptype, ring, &ip_summed, &cksum,
+			&cksum_level);
+	switch (ip_summed) {
+	case XDP_CHECKSUM_UNNECESSARY:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = cksum_level;
+		break;
+	case XDP_CHECKSUM_COMPLETE:
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = (__force __wsum)cksum;
+		break;
+	default:
+		skb->ip_summed = CHECKSUM_NONE;
+		break;
+	}
 }
 
 /**
@@ -566,6 +582,28 @@ static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return 0;
 }
 
+/**
+ * ice_xdp_rx_checksum - RX checksum XDP hint handler
+ * @ctx: XDP buff pointer
+ * @ip_summed: RX checksum result destination address
+ * @cksum: RX checksum value destination address
+ * @cksum_level: RX checksum level value destination address
+ */
+static int ice_xdp_rx_checksum(const struct xdp_md *ctx,
+			       enum xdp_checksum *ip_summed,
+			       u32 *cksum, u8 *cksum_level)
+{
+	const struct libeth_xdp_buff *xdp_ext = (void *)ctx;
+	const union ice_32b_rx_flex_desc *rx_desc = xdp_ext->desc;
+	struct ice_rx_ring *ring;
+
+	ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*ring), xdp_rxq);
+	ice_get_rx_csum(rx_desc, ice_get_ptype(rx_desc), ring, ip_summed,
+			cksum, cksum_level);
+
+	return 0;
+}
+
 /**
  * ice_xdp_rx_vlan_tag - VLAN tag XDP hint handler
  * @ctx: XDP buff pointer
@@ -598,4 +636,5 @@ const struct xdp_metadata_ops ice_xdp_md_ops = {
 	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
 	.xmo_rx_hash			= ice_xdp_rx_hash,
 	.xmo_rx_vlan_tag		= ice_xdp_rx_vlan_tag,
+	.xmo_rx_checksum		= ice_xdp_rx_checksum,
 };

-- 
2.55.0

[PATCH bpf-next v5 4/8] selftests/bpf: add selftest support for bpf_xdp_metadata_rx_checksum

[Lorenzo Bianconi]

Introduce dedicated selftest for bpf_xdp_metadata_rx_checksum kfunc to
bpf selftest framework.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/xdp_metadata.c | 9 +++++++++
 tools/testing/selftests/bpf/progs/xdp_metadata.c      | 2 ++
 tools/testing/selftests/bpf/xdp_metadata.h            | 9 +++++++++
 3 files changed, 20 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 5c31054ad4a4..91de61c822f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -310,6 +310,15 @@ static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp)
 	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
 		return -1;
 
+	if (!ASSERT_EQ(meta->ip_summed, XDP_CHECKSUM_NONE, "rx_ip_summed"))
+		return -1;
+
+	if (!ASSERT_EQ(meta->cksum, 0, "rx_cksum"))
+		return -1;
+
+	if (!ASSERT_EQ(meta->cksum_level, 0, "rx_cksum_level"))
+		return -1;
+
 	if (!sent_from_af_xdp) {
 		if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type"))
 			return -1;
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c
index 09bb8a038d52..af1e19d48d67 100644
--- a/tools/testing/selftests/bpf/progs/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c
@@ -98,6 +98,8 @@ int rx(struct xdp_md *ctx)
 	bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
 	bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
 				     &meta->rx_vlan_tci);
+	bpf_xdp_metadata_rx_checksum(ctx, &meta->ip_summed, &meta->cksum,
+				     &meta->cksum_level);
 
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index 87318ad1117a..bca09b94af26 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -30,6 +30,10 @@ enum xdp_meta_field {
 	XDP_META_FIELD_VLAN_TAG	= BIT(2),
 };
 
+#define XDP_CHECKSUM_NONE		BIT(0)
+#define XDP_CHECKSUM_UNNECESSARY	BIT(1)
+#define XDP_CHECKSUM_COMPLETE		BIT(2)
+
 struct xdp_meta {
 	union {
 		__u64 rx_timestamp;
@@ -48,5 +52,10 @@ struct xdp_meta {
 		};
 		__s32 rx_vlan_tag_err;
 	};
+	struct {
+		__u32 ip_summed;
+		__u32 cksum;
+		__u8 cksum_level;
+	};
 	enum xdp_meta_field hint_valid;
 };

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 4/8] selftests/bpf: add selftest support for bpf_xdp_metadata_rx_checksum

[Lorenzo Bianconi]

Introduce dedicated selftest for bpf_xdp_metadata_rx_checksum kfunc to
bpf selftest framework.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/xdp_metadata.c | 9 +++++++++
 tools/testing/selftests/bpf/progs/xdp_metadata.c      | 2 ++
 tools/testing/selftests/bpf/xdp_metadata.h            | 9 +++++++++
 3 files changed, 20 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 5c31054ad4a4..91de61c822f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -310,6 +310,15 @@ static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp)
 	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
 		return -1;
 
+	if (!ASSERT_EQ(meta->ip_summed, XDP_CHECKSUM_NONE, "rx_ip_summed"))
+		return -1;
+
+	if (!ASSERT_EQ(meta->cksum, 0, "rx_cksum"))
+		return -1;
+
+	if (!ASSERT_EQ(meta->cksum_level, 0, "rx_cksum_level"))
+		return -1;
+
 	if (!sent_from_af_xdp) {
 		if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type"))
 			return -1;
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c
index 09bb8a038d52..af1e19d48d67 100644
--- a/tools/testing/selftests/bpf/progs/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c
@@ -98,6 +98,8 @@ int rx(struct xdp_md *ctx)
 	bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
 	bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
 				     &meta->rx_vlan_tci);
+	bpf_xdp_metadata_rx_checksum(ctx, &meta->ip_summed, &meta->cksum,
+				     &meta->cksum_level);
 
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index 87318ad1117a..bca09b94af26 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -30,6 +30,10 @@ enum xdp_meta_field {
 	XDP_META_FIELD_VLAN_TAG	= BIT(2),
 };
 
+#define XDP_CHECKSUM_NONE		BIT(0)
+#define XDP_CHECKSUM_UNNECESSARY	BIT(1)
+#define XDP_CHECKSUM_COMPLETE		BIT(2)
+
 struct xdp_meta {
 	union {
 		__u64 rx_timestamp;
@@ -48,5 +52,10 @@ struct xdp_meta {
 		};
 		__s32 rx_vlan_tag_err;
 	};
+	struct {
+		__u32 ip_summed;
+		__u32 cksum;
+		__u8 cksum_level;
+	};
 	enum xdp_meta_field hint_valid;
 };

-- 
2.55.0

[PATCH bpf-next v5 5/8] selftests/bpf: add bpf_xdp_metadata_rx_checksum support to xdp_hw_metadat prog

[Lorenzo Bianconi]

Introduce the capability to dump HW rx checksum in xdp_hw_metadata
program via bpf_xdp_metadata_rx_checksum() kfunc.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 .../testing/selftests/bpf/progs/xdp_hw_metadata.c  |  7 +++++
 tools/testing/selftests/bpf/xdp_hw_metadata.c      | 31 ++++++++++++++++++++++
 tools/testing/selftests/bpf/xdp_metadata.h         | 12 ++++++---
 3 files changed, 46 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index 330ece2eabdb..5eeadb7e27cf 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -110,6 +110,13 @@ int rx(struct xdp_md *ctx)
 	else
 		meta->hint_valid |= XDP_META_FIELD_VLAN_TAG;
 
+	err = bpf_xdp_metadata_rx_checksum(ctx, &meta->ip_summed,
+					   &meta->cksum, &meta->cksum_level);
+	if (err)
+		meta->rx_cksum_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_CHECKSUM;
+
 	__sync_add_and_fetch(&pkts_redir, 1);
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 6db3b5555a22..c63a70a54075 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -8,6 +8,7 @@
  * - Metadata verified:
  *   - rx_timestamp
  *   - rx_hash
+ *   - rx_checksum
  *
  * TX:
  * - UDP 9091 packets trigger TX reply
@@ -219,6 +220,30 @@ static void print_vlan_tci(__u16 tag)
 	printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id);
 }
 
+static void print_rx_cksum(__u8 ip_summed, __u32 cksum, __u8 cksum_level)
+{
+	const char *cksum_str;
+
+	switch (ip_summed) {
+	case XDP_CHECKSUM_COMPLETE | XDP_CHECKSUM_UNNECESSARY:
+		cksum_str = "CHECKSUM_COMPLETE,CHECKSUM_UNNECESSARY";
+		break;
+	case XDP_CHECKSUM_UNNECESSARY:
+		cksum_str = "CHECKSUM_UNNECESSARY";
+		break;
+	case XDP_CHECKSUM_COMPLETE:
+		cksum_str = "CHECKSUM_COMPLETE";
+		break;
+	case XDP_CHECKSUM_NONE:
+	default:
+		cksum_str = "CHECKSUM_NONE";
+		break;
+	}
+
+	printf("rx-cksum: %s, csum=0x%x, cksum_level=0x%x\n",
+	       cksum_str, cksum, cksum_level);
+}
+
 static void verify_xdp_metadata(void *data, clockid_t clock_id)
 {
 	struct xdp_meta *meta;
@@ -254,6 +279,12 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id)
 		printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n",
 		       meta->rx_vlan_tag_err);
 	}
+
+	if (meta->hint_valid & XDP_META_FIELD_CHECKSUM)
+		print_rx_cksum(meta->ip_summed, meta->cksum,
+			       meta->cksum_level);
+	else
+		printf("No rx_cksum, err=%d\n", meta->rx_cksum_err);
 }
 
 static void verify_skb_metadata(int fd)
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index bca09b94af26..f864d4a8bd8c 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -28,6 +28,7 @@ enum xdp_meta_field {
 	XDP_META_FIELD_TS	= BIT(0),
 	XDP_META_FIELD_RSS	= BIT(1),
 	XDP_META_FIELD_VLAN_TAG	= BIT(2),
+	XDP_META_FIELD_CHECKSUM = BIT(3),
 };
 
 #define XDP_CHECKSUM_NONE		BIT(0)
@@ -52,10 +53,13 @@ struct xdp_meta {
 		};
 		__s32 rx_vlan_tag_err;
 	};
-	struct {
-		__u32 ip_summed;
-		__u32 cksum;
-		__u8 cksum_level;
+	union {
+		struct {
+			__u32 ip_summed;
+			__u32 cksum;
+			__u8 cksum_level;
+		};
+		__s32 rx_cksum_err;
 	};
 	enum xdp_meta_field hint_valid;
 };

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 5/8] selftests/bpf: add bpf_xdp_metadata_rx_checksum support to xdp_hw_metadat prog

[Lorenzo Bianconi]

Introduce the capability to dump HW rx checksum in xdp_hw_metadata
program via bpf_xdp_metadata_rx_checksum() kfunc.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 .../testing/selftests/bpf/progs/xdp_hw_metadata.c  |  7 +++++
 tools/testing/selftests/bpf/xdp_hw_metadata.c      | 31 ++++++++++++++++++++++
 tools/testing/selftests/bpf/xdp_metadata.h         | 12 ++++++---
 3 files changed, 46 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index 330ece2eabdb..5eeadb7e27cf 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -110,6 +110,13 @@ int rx(struct xdp_md *ctx)
 	else
 		meta->hint_valid |= XDP_META_FIELD_VLAN_TAG;
 
+	err = bpf_xdp_metadata_rx_checksum(ctx, &meta->ip_summed,
+					   &meta->cksum, &meta->cksum_level);
+	if (err)
+		meta->rx_cksum_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_CHECKSUM;
+
 	__sync_add_and_fetch(&pkts_redir, 1);
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 6db3b5555a22..c63a70a54075 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -8,6 +8,7 @@
  * - Metadata verified:
  *   - rx_timestamp
  *   - rx_hash
+ *   - rx_checksum
  *
  * TX:
  * - UDP 9091 packets trigger TX reply
@@ -219,6 +220,30 @@ static void print_vlan_tci(__u16 tag)
 	printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id);
 }
 
+static void print_rx_cksum(__u8 ip_summed, __u32 cksum, __u8 cksum_level)
+{
+	const char *cksum_str;
+
+	switch (ip_summed) {
+	case XDP_CHECKSUM_COMPLETE | XDP_CHECKSUM_UNNECESSARY:
+		cksum_str = "CHECKSUM_COMPLETE,CHECKSUM_UNNECESSARY";
+		break;
+	case XDP_CHECKSUM_UNNECESSARY:
+		cksum_str = "CHECKSUM_UNNECESSARY";
+		break;
+	case XDP_CHECKSUM_COMPLETE:
+		cksum_str = "CHECKSUM_COMPLETE";
+		break;
+	case XDP_CHECKSUM_NONE:
+	default:
+		cksum_str = "CHECKSUM_NONE";
+		break;
+	}
+
+	printf("rx-cksum: %s, csum=0x%x, cksum_level=0x%x\n",
+	       cksum_str, cksum, cksum_level);
+}
+
 static void verify_xdp_metadata(void *data, clockid_t clock_id)
 {
 	struct xdp_meta *meta;
@@ -254,6 +279,12 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id)
 		printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n",
 		       meta->rx_vlan_tag_err);
 	}
+
+	if (meta->hint_valid & XDP_META_FIELD_CHECKSUM)
+		print_rx_cksum(meta->ip_summed, meta->cksum,
+			       meta->cksum_level);
+	else
+		printf("No rx_cksum, err=%d\n", meta->rx_cksum_err);
 }
 
 static void verify_skb_metadata(int fd)
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index bca09b94af26..f864d4a8bd8c 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -28,6 +28,7 @@ enum xdp_meta_field {
 	XDP_META_FIELD_TS	= BIT(0),
 	XDP_META_FIELD_RSS	= BIT(1),
 	XDP_META_FIELD_VLAN_TAG	= BIT(2),
+	XDP_META_FIELD_CHECKSUM = BIT(3),
 };
 
 #define XDP_CHECKSUM_NONE		BIT(0)
@@ -52,10 +53,13 @@ struct xdp_meta {
 		};
 		__s32 rx_vlan_tag_err;
 	};
-	struct {
-		__u32 ip_summed;
-		__u32 cksum;
-		__u8 cksum_level;
+	union {
+		struct {
+			__u32 ip_summed;
+			__u32 cksum;
+			__u8 cksum_level;
+		};
+		__s32 rx_cksum_err;
 	};
 	enum xdp_meta_field hint_valid;
 };

-- 
2.55.0

[PATCH bpf-next v5 6/8] net: add bpf_skb_rx_checksum kfunc to read skb checksum metadata

[Lorenzo Bianconi]

Add a new BPF kfunc, bpf_skb_rx_checksum(), that allows TC and other
skb-attached BPF programs to read the skb->ip_summed field and
associated checksum metadata. This is needed because the existing
bpf_csum_level() helper only distinguishes CHECKSUM_UNNECESSARY
from all other states, making it unsuitable when the caller needs
to differentiate CHECKSUM_NONE from CHECKSUM_COMPLETE (e.g. after
XDP_PASS where the driver may have set either).

The kfunc writes two output values:
  - ip_summed: the raw skb->ip_summed value
               (CHECKSUM_NONE=0, CHECKSUM_UNNECESSARY=1,
                CHECKSUM_COMPLETE=2, CHECKSUM_PARTIAL=3)
  - csum_meta: CHECKSUM_COMPLETE -> hardware checksum (skb->csum)
               CHECKSUM_UNNECESSARY -> checksum level (skb->csum_level)
               otherwise -> 0

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 net/core/filter.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index b446aa8be5c3..71d58ea53512 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -12546,6 +12546,36 @@ __bpf_kfunc int bpf_xdp_pull_data(struct xdp_md *x, u32 len)
 	return 0;
 }
 
+/**
+ * bpf_skb_rx_checksum() - Read skb RX checksum info.
+ * @skb_: socket buffer to read from
+ * @ip_summed: return value for skb->ip_summed
+ * @csum_meta: checksum metadata
+ *
+ * Reads the checksum-related fields from a socket buffer. For
+ * %CHECKSUM_COMPLETE, csum_meta reports the hardware checksum value.
+ * For %CHECKSUM_UNNECESSARY, csum_meta reports the checksum level.
+ * For %CHECKSUM_NONE, csum_meta is zero.
+ *
+ * Return:
+ * * %0 - success
+ */
+__bpf_kfunc int bpf_skb_rx_checksum(struct __sk_buff *skb_, u32 *ip_summed,
+				    u32 *csum_meta)
+{
+	struct sk_buff *skb = (struct sk_buff *)skb_;
+
+	*ip_summed = skb->ip_summed;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		*csum_meta = skb->csum;
+	else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
+		*csum_meta = skb->csum_level;
+	else
+		*csum_meta = 0;
+
+	return 0;
+}
+
 __bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12565,6 +12595,7 @@ int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_skb)
 BTF_ID_FLAGS(func, bpf_dynptr_from_skb)
+BTF_ID_FLAGS(func, bpf_skb_rx_checksum)
 BTF_KFUNCS_END(bpf_kfunc_check_set_skb)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_skb_meta)

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 6/8] net: add bpf_skb_rx_checksum kfunc to read skb checksum metadata

[Lorenzo Bianconi]

Add a new BPF kfunc, bpf_skb_rx_checksum(), that allows TC and other
skb-attached BPF programs to read the skb->ip_summed field and
associated checksum metadata. This is needed because the existing
bpf_csum_level() helper only distinguishes CHECKSUM_UNNECESSARY
from all other states, making it unsuitable when the caller needs
to differentiate CHECKSUM_NONE from CHECKSUM_COMPLETE (e.g. after
XDP_PASS where the driver may have set either).

The kfunc writes two output values:
  - ip_summed: the raw skb->ip_summed value
               (CHECKSUM_NONE=0, CHECKSUM_UNNECESSARY=1,
                CHECKSUM_COMPLETE=2, CHECKSUM_PARTIAL=3)
  - csum_meta: CHECKSUM_COMPLETE -> hardware checksum (skb->csum)
               CHECKSUM_UNNECESSARY -> checksum level (skb->csum_level)
               otherwise -> 0

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 net/core/filter.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index b446aa8be5c3..71d58ea53512 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -12546,6 +12546,36 @@ __bpf_kfunc int bpf_xdp_pull_data(struct xdp_md *x, u32 len)
 	return 0;
 }
 
+/**
+ * bpf_skb_rx_checksum() - Read skb RX checksum info.
+ * @skb_: socket buffer to read from
+ * @ip_summed: return value for skb->ip_summed
+ * @csum_meta: checksum metadata
+ *
+ * Reads the checksum-related fields from a socket buffer. For
+ * %CHECKSUM_COMPLETE, csum_meta reports the hardware checksum value.
+ * For %CHECKSUM_UNNECESSARY, csum_meta reports the checksum level.
+ * For %CHECKSUM_NONE, csum_meta is zero.
+ *
+ * Return:
+ * * %0 - success
+ */
+__bpf_kfunc int bpf_skb_rx_checksum(struct __sk_buff *skb_, u32 *ip_summed,
+				    u32 *csum_meta)
+{
+	struct sk_buff *skb = (struct sk_buff *)skb_;
+
+	*ip_summed = skb->ip_summed;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		*csum_meta = skb->csum;
+	else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
+		*csum_meta = skb->csum_level;
+	else
+		*csum_meta = 0;
+
+	return 0;
+}
+
 __bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12565,6 +12595,7 @@ int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_skb)
 BTF_ID_FLAGS(func, bpf_dynptr_from_skb)
+BTF_ID_FLAGS(func, bpf_skb_rx_checksum)
 BTF_KFUNCS_END(bpf_kfunc_check_set_skb)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_skb_meta)

-- 
2.55.0

[PATCH bpf-next v5 7/8] selftests/bpf: Add test for bpf_skb_rx_checksum kfunc

[Lorenzo Bianconi]

Add a selftest for the newly added bpf_skb_rx_checksum() kfunc.
The test consists of a TC BPF program that calls the kfunc and
records which checksum type each packet has in a per-type counter
map, and a userspace test runner that exercises two scenarios:

- csum_none: runs with bpf_prog_test_run_opts (no special flags),
  verifies all packets are reported as CHECKSUM_NONE.
- csum_complete: runs with BPF_F_TEST_SKB_CHECKSUM_COMPLETE flag,
  verifies all packets are reported as CHECKSUM_COMPLETE.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 tools/testing/selftests/bpf/bpf_kfuncs.h           |  8 ++++
 .../selftests/bpf/prog_tests/skb_rx_checksum.c     | 50 ++++++++++++++++++++++
 .../testing/selftests/bpf/progs/skb_rx_checksum.c  | 33 ++++++++++++++
 tools/testing/selftests/bpf/skb_rx_checksum.h      |  8 ++++
 4 files changed, 99 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index ae71e9b69051..d03572e26df2 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -64,6 +64,14 @@ struct bpf_tcp_req_attrs;
 extern int bpf_sk_assign_tcp_reqsk(struct __sk_buff *skb, struct sock *sk,
 				   struct bpf_tcp_req_attrs *attrs, int attrs__sz) __ksym;
 
+/* Description
+ *  Read skb RX checksum info (ip_summed and csum_meta).
+ * Returns
+ *  0 on success
+ */
+extern int bpf_skb_rx_checksum(struct __sk_buff *skb, __u32 *ip_summed,
+			       __u32 *csum_meta) __ksym;
+
 void *bpf_cast_to_kern_ctx(void *) __ksym;
 
 extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak;
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_rx_checksum.c b/tools/testing/selftests/bpf/prog_tests/skb_rx_checksum.c
new file mode 100644
index 000000000000..d71ab7c70b68
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skb_rx_checksum.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "skb_rx_checksum.skel.h"
+#include "skb_rx_checksum.h"
+
+#define TX_PACKETS 3
+
+static int run_test(__u32 flags, enum skb_csum expected_csum)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = TX_PACKETS,
+		.flags = flags,
+	);
+	int prog_fd, err, key = expected_csum;
+	struct skb_rx_checksum *skel;
+	__u64 cnt;
+
+	skel = skb_rx_checksum__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return -1;
+
+	prog_fd = bpf_program__fd(skel->progs.tc_rx_csum);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(topts.retval, 0, "retval"))
+		goto cleanup;
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.csum_cnt), &key, &cnt);
+	if (!ASSERT_OK(err, "map_lookup"))
+		goto cleanup;
+
+	ASSERT_EQ(cnt, TX_PACKETS, "csum_cnt");
+cleanup:
+	skb_rx_checksum__destroy(skel);
+	return 0;
+}
+
+void test_skb_rx_checksum(void)
+{
+	if (test__start_subtest("csum_none"))
+		run_test(0, SKB_CSUM_NONE);
+
+	if (test__start_subtest("csum_complete"))
+		run_test(BPF_F_TEST_SKB_CHECKSUM_COMPLETE, SKB_CSUM_COMPLETE);
+}
diff --git a/tools/testing/selftests/bpf/progs/skb_rx_checksum.c b/tools/testing/selftests/bpf/progs/skb_rx_checksum.c
new file mode 100644
index 000000000000..dc4e192905d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/skb_rx_checksum.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_kfuncs.h"
+#include "skb_rx_checksum.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, SKB_CSUM_PARTIAL);
+	__type(key, __u32);
+	__type(value, __u64);
+} csum_cnt SEC(".maps");
+
+SEC("tc")
+int tc_rx_csum(struct __sk_buff *skb)
+{
+	enum skb_csum ip_summed;
+	__u32 csum_meta;
+	__u64 *cnt;
+
+	bpf_skb_rx_checksum(skb, &ip_summed, &csum_meta);
+	if (ip_summed < SKB_CSUM_PARTIAL) {
+		cnt = bpf_map_lookup_elem(&csum_cnt, &ip_summed);
+		if (cnt)
+			__sync_fetch_and_add(cnt, 1);
+	}
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/skb_rx_checksum.h b/tools/testing/selftests/bpf/skb_rx_checksum.h
new file mode 100644
index 000000000000..60aad3561843
--- /dev/null
+++ b/tools/testing/selftests/bpf/skb_rx_checksum.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+enum skb_csum {
+	SKB_CSUM_NONE		= 0,
+	SKB_CSUM_UNNECESSARY	= 1,
+	SKB_CSUM_COMPLETE	= 2,
+	SKB_CSUM_PARTIAL	= 3,
+};

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 7/8] selftests/bpf: Add test for bpf_skb_rx_checksum kfunc

[Lorenzo Bianconi]

Add a selftest for the newly added bpf_skb_rx_checksum() kfunc.
The test consists of a TC BPF program that calls the kfunc and
records which checksum type each packet has in a per-type counter
map, and a userspace test runner that exercises two scenarios:

- csum_none: runs with bpf_prog_test_run_opts (no special flags),
  verifies all packets are reported as CHECKSUM_NONE.
- csum_complete: runs with BPF_F_TEST_SKB_CHECKSUM_COMPLETE flag,
  verifies all packets are reported as CHECKSUM_COMPLETE.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 tools/testing/selftests/bpf/bpf_kfuncs.h           |  8 ++++
 .../selftests/bpf/prog_tests/skb_rx_checksum.c     | 50 ++++++++++++++++++++++
 .../testing/selftests/bpf/progs/skb_rx_checksum.c  | 33 ++++++++++++++
 tools/testing/selftests/bpf/skb_rx_checksum.h      |  8 ++++
 4 files changed, 99 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index ae71e9b69051..d03572e26df2 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -64,6 +64,14 @@ struct bpf_tcp_req_attrs;
 extern int bpf_sk_assign_tcp_reqsk(struct __sk_buff *skb, struct sock *sk,
 				   struct bpf_tcp_req_attrs *attrs, int attrs__sz) __ksym;
 
+/* Description
+ *  Read skb RX checksum info (ip_summed and csum_meta).
+ * Returns
+ *  0 on success
+ */
+extern int bpf_skb_rx_checksum(struct __sk_buff *skb, __u32 *ip_summed,
+			       __u32 *csum_meta) __ksym;
+
 void *bpf_cast_to_kern_ctx(void *) __ksym;
 
 extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak;
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_rx_checksum.c b/tools/testing/selftests/bpf/prog_tests/skb_rx_checksum.c
new file mode 100644
index 000000000000..d71ab7c70b68
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skb_rx_checksum.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "skb_rx_checksum.skel.h"
+#include "skb_rx_checksum.h"
+
+#define TX_PACKETS 3
+
+static int run_test(__u32 flags, enum skb_csum expected_csum)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = TX_PACKETS,
+		.flags = flags,
+	);
+	int prog_fd, err, key = expected_csum;
+	struct skb_rx_checksum *skel;
+	__u64 cnt;
+
+	skel = skb_rx_checksum__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return -1;
+
+	prog_fd = bpf_program__fd(skel->progs.tc_rx_csum);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(topts.retval, 0, "retval"))
+		goto cleanup;
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.csum_cnt), &key, &cnt);
+	if (!ASSERT_OK(err, "map_lookup"))
+		goto cleanup;
+
+	ASSERT_EQ(cnt, TX_PACKETS, "csum_cnt");
+cleanup:
+	skb_rx_checksum__destroy(skel);
+	return 0;
+}
+
+void test_skb_rx_checksum(void)
+{
+	if (test__start_subtest("csum_none"))
+		run_test(0, SKB_CSUM_NONE);
+
+	if (test__start_subtest("csum_complete"))
+		run_test(BPF_F_TEST_SKB_CHECKSUM_COMPLETE, SKB_CSUM_COMPLETE);
+}
diff --git a/tools/testing/selftests/bpf/progs/skb_rx_checksum.c b/tools/testing/selftests/bpf/progs/skb_rx_checksum.c
new file mode 100644
index 000000000000..dc4e192905d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/skb_rx_checksum.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_kfuncs.h"
+#include "skb_rx_checksum.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, SKB_CSUM_PARTIAL);
+	__type(key, __u32);
+	__type(value, __u64);
+} csum_cnt SEC(".maps");
+
+SEC("tc")
+int tc_rx_csum(struct __sk_buff *skb)
+{
+	enum skb_csum ip_summed;
+	__u32 csum_meta;
+	__u64 *cnt;
+
+	bpf_skb_rx_checksum(skb, &ip_summed, &csum_meta);
+	if (ip_summed < SKB_CSUM_PARTIAL) {
+		cnt = bpf_map_lookup_elem(&csum_cnt, &ip_summed);
+		if (cnt)
+			__sync_fetch_and_add(cnt, 1);
+	}
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/skb_rx_checksum.h b/tools/testing/selftests/bpf/skb_rx_checksum.h
new file mode 100644
index 000000000000..60aad3561843
--- /dev/null
+++ b/tools/testing/selftests/bpf/skb_rx_checksum.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+enum skb_csum {
+	SKB_CSUM_NONE		= 0,
+	SKB_CSUM_UNNECESSARY	= 1,
+	SKB_CSUM_COMPLETE	= 2,
+	SKB_CSUM_PARTIAL	= 3,
+};

-- 
2.55.0

[PATCH bpf-next v5 8/8] selftests: net: add test for XDP_PASS skb checksum invalidation

[Lorenzo Bianconi]

Add a test that verifies skb->ip_summed is set to CHECKSUM_NONE
when a device running in XDP mode creates an skb from a xdp_buff
if the attached ebpf program returns an XDP_PASS.
The test attaches an XDP program returning XDP_PASS, and a TC
ingress program that runs the bpf_skb_rx_checksum() kfunc to
inspect the resulting skb. After XDP_PASS the driver must invalidate
any previously computed hardware RX checksum since XDP may have
modified the packet data.
The BPF program counts packets per checksum type in a map, and the
test runner verifies that after sending traffic the CHECKSUM_NONE
counter is non-zero while CHECKSUM_UNNECESSARY and CHECKSUM_COMPLETE
counters are zero.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 Documentation/networking/xdp-rx-metadata.rst       |  5 ++
 .../selftests/drivers/net/hw/xdp_metadata.py       | 55 +++++++++++++++-
 .../selftests/net/lib/skb_metadata_csum.bpf.c      | 73 ++++++++++++++++++++++
 3 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index 93918b3769a3..7434ac98242a 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -90,6 +90,11 @@ conversion, and the XDP metadata is not used by the kernel when building
 ``skbs``. However, TC-BPF programs can access the XDP metadata area using
 the ``data_meta`` pointer.
 
+If a driver is running in XDP mode, any existing hardware RX checksum
+(``CHECKSUM_UNNECESSARY`` or ``CHECKSUM_COMPLETE``) must be invalidated
+by setting ``skb->ip_summed`` to ``CHECKSUM_NONE`` before passing the
+skb to the kernel, since XDP may have modified the packet data.
+
 In the future, we'd like to support a case where an XDP program
 can override some of the metadata used for building ``skbs``.
 
diff --git a/tools/testing/selftests/drivers/net/hw/xdp_metadata.py b/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
old mode 100644
new mode 100755
index 33a1985356d9..8ccd34b776b4
--- a/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
+++ b/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
@@ -8,12 +8,13 @@ These tests load device-bound XDP programs from xdp_metadata.bpf.o
 that call metadata kfuncs, send traffic, and verify the extracted
 metadata via BPF maps.
 """
+import json
 from lib.py import ksft_run, ksft_eq, ksft_exit, ksft_ge, ksft_ne, ksft_pr
 from lib.py import KsftNamedVariant, ksft_variants
 from lib.py import CmdExitFailure, KsftSkipEx, NetDrvEpEnv
 from lib.py import NetdevFamily
 from lib.py import bkg, cmd, rand_port, wait_port_listen
-from lib.py import ip, bpftool, defer
+from lib.py import ip, bpftool, defer, ethtool
 from lib.py import bpf_map_set, bpf_map_dump, bpf_prog_map_ids
 
 
@@ -130,6 +131,57 @@ def test_xdp_rss_hash(cfg, proto):
             f"RSS hash type should include L4 for {proto.upper()} traffic")
 
 
+def test_xdp_pass_rx_csum(cfg):
+    """Test xdp_pass sets CHECKSUM_NONE on the resulting skb.
+
+    Attaches an XDP program that returns XDP_PASS and a TC ingress
+    program that checks skb->ip_summed via bpf_skb_rx_checksum().
+    Verifies the value is CHECKSUM_NONE.
+    """
+
+    bpf_obj = cfg.net_lib_dir / "skb_metadata_csum.bpf.o"
+    xdp_obj = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+
+    # GRO may overwrite skb->ip_summed after the driver sets it,
+    # so disable it to preserve the checksum set by the driver.
+    ethtool(f"-K {cfg.ifname} gro off")
+    defer(ethtool, f"-K {cfg.ifname} gro on")
+    ip(f"link set dev {cfg.ifname} xdp obj {xdp_obj} sec xdp")
+    defer(ip, f"link set dev {cfg.ifname} xdp off")
+
+    qdiscs = json.loads(cmd(f"tc -j qdisc show dev {cfg.ifname}").stdout)
+    if not any(q['kind'] == 'clsact' for q in qdiscs):
+        cmd(f"tc qdisc add dev {cfg.ifname} clsact")
+        defer(cmd, f"tc qdisc del dev {cfg.ifname} clsact")
+    cmd(f"tc filter add dev {cfg.ifname} ingress bpf da obj {bpf_obj} sec tc")
+
+    progs = bpftool("prog list", json=True)
+    tc_prog_id = None
+    for p in progs:
+        if p.get("name") == "tc_check_csum":
+            tc_prog_id = p["id"]
+            break
+
+    if tc_prog_id is None:
+        raise KsftSkipEx("Could not find tc_check_csum BPF program")
+
+    maps = bpf_prog_map_ids(tc_prog_id)
+    csum_map_id = maps.get("map_csum_result")
+    if csum_map_id is None:
+        raise KsftSkipEx("Could not find map_csum_result map")
+
+    for _ in range(10):
+        _send_probe(cfg, 12345, proto="udp")
+
+    result = bpf_map_dump(csum_map_id)
+    csum_none = result.get(0, 0)
+    csum_unnecessary = result.get(1, 0)
+    csum_complete = result.get(2, 0)
+    ksft_ge(csum_none, 1, "skb->ip_summed should be CHECKSUM_NONE after XDP_PASS")
+    ksft_eq(csum_unnecessary, 0, "CHECKSUM_UNNECESSARY should not be set")
+    ksft_eq(csum_complete, 0, "CHECKSUM_COMPLETE should not be set")
+
+
 def main():
     """Run XDP metadata kfunc tests against a real device."""
     with NetDrvEpEnv(__file__) as cfg:
@@ -137,6 +189,7 @@ def main():
         ksft_run(
             [
                 test_xdp_rss_hash,
+                test_xdp_pass_rx_csum,
             ],
             args=(cfg,))
     ksft_exit()
diff --git a/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c b/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c
new file mode 100644
index 000000000000..6a953c4acfe7
--- /dev/null
+++ b/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/udp.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_PORT 12345
+
+enum skb_csum {
+	SKB_CSUM_NONE		= 0,
+	SKB_CSUM_UNNECESSARY	= 1,
+	SKB_CSUM_COMPLETE	= 2,
+	SKB_CSUM_PARTIAL	= 3,
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, SKB_CSUM_PARTIAL);
+	__type(key, __u32);
+	__type(value, __u64);
+} map_csum_result SEC(".maps");
+
+extern int bpf_skb_rx_checksum(struct __sk_buff *skb, __u32 *ip_summed,
+				__u32 *csum_meta) __ksym;
+
+SEC("tc")
+int tc_check_csum(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	__u32 ip_summed, csum_meta;
+	struct ethhdr *eth = data;
+	struct ipv6hdr *ip6;
+	struct udphdr *udp;
+
+	if ((void *)(eth + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
+		return TC_ACT_OK;
+
+	ip6 = (void *)(eth + 1);
+	if ((void *)(ip6 + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (ip6->nexthdr != IPPROTO_UDP)
+		return TC_ACT_OK;
+
+	udp = (void *)(ip6 + 1);
+	if ((void *)(udp + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (udp->dest != bpf_htons(UDP_PORT))
+		return TC_ACT_OK;
+
+	bpf_skb_rx_checksum(skb, &ip_summed, &csum_meta);
+	if (ip_summed < SKB_CSUM_PARTIAL) {
+		__u64 *cnt;
+
+		cnt = bpf_map_lookup_elem(&map_csum_result, &ip_summed);
+		if (cnt)
+			__sync_fetch_and_add(cnt, 1);
+	}
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";

-- 
2.55.0

[Intel-wired-lan] [PATCH bpf-next v5 8/8] selftests: net: add test for XDP_PASS skb checksum invalidation

[Lorenzo Bianconi]

Add a test that verifies skb->ip_summed is set to CHECKSUM_NONE
when a device running in XDP mode creates an skb from a xdp_buff
if the attached ebpf program returns an XDP_PASS.
The test attaches an XDP program returning XDP_PASS, and a TC
ingress program that runs the bpf_skb_rx_checksum() kfunc to
inspect the resulting skb. After XDP_PASS the driver must invalidate
any previously computed hardware RX checksum since XDP may have
modified the packet data.
The BPF program counts packets per checksum type in a map, and the
test runner verifies that after sending traffic the CHECKSUM_NONE
counter is non-zero while CHECKSUM_UNNECESSARY and CHECKSUM_COMPLETE
counters are zero.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 Documentation/networking/xdp-rx-metadata.rst       |  5 ++
 .../selftests/drivers/net/hw/xdp_metadata.py       | 55 +++++++++++++++-
 .../selftests/net/lib/skb_metadata_csum.bpf.c      | 73 ++++++++++++++++++++++
 3 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index 93918b3769a3..7434ac98242a 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -90,6 +90,11 @@ conversion, and the XDP metadata is not used by the kernel when building
 ``skbs``. However, TC-BPF programs can access the XDP metadata area using
 the ``data_meta`` pointer.
 
+If a driver is running in XDP mode, any existing hardware RX checksum
+(``CHECKSUM_UNNECESSARY`` or ``CHECKSUM_COMPLETE``) must be invalidated
+by setting ``skb->ip_summed`` to ``CHECKSUM_NONE`` before passing the
+skb to the kernel, since XDP may have modified the packet data.
+
 In the future, we'd like to support a case where an XDP program
 can override some of the metadata used for building ``skbs``.
 
diff --git a/tools/testing/selftests/drivers/net/hw/xdp_metadata.py b/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
old mode 100644
new mode 100755
index 33a1985356d9..8ccd34b776b4
--- a/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
+++ b/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
@@ -8,12 +8,13 @@ These tests load device-bound XDP programs from xdp_metadata.bpf.o
 that call metadata kfuncs, send traffic, and verify the extracted
 metadata via BPF maps.
 """
+import json
 from lib.py import ksft_run, ksft_eq, ksft_exit, ksft_ge, ksft_ne, ksft_pr
 from lib.py import KsftNamedVariant, ksft_variants
 from lib.py import CmdExitFailure, KsftSkipEx, NetDrvEpEnv
 from lib.py import NetdevFamily
 from lib.py import bkg, cmd, rand_port, wait_port_listen
-from lib.py import ip, bpftool, defer
+from lib.py import ip, bpftool, defer, ethtool
 from lib.py import bpf_map_set, bpf_map_dump, bpf_prog_map_ids
 
 
@@ -130,6 +131,57 @@ def test_xdp_rss_hash(cfg, proto):
             f"RSS hash type should include L4 for {proto.upper()} traffic")
 
 
+def test_xdp_pass_rx_csum(cfg):
+    """Test xdp_pass sets CHECKSUM_NONE on the resulting skb.
+
+    Attaches an XDP program that returns XDP_PASS and a TC ingress
+    program that checks skb->ip_summed via bpf_skb_rx_checksum().
+    Verifies the value is CHECKSUM_NONE.
+    """
+
+    bpf_obj = cfg.net_lib_dir / "skb_metadata_csum.bpf.o"
+    xdp_obj = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+
+    # GRO may overwrite skb->ip_summed after the driver sets it,
+    # so disable it to preserve the checksum set by the driver.
+    ethtool(f"-K {cfg.ifname} gro off")
+    defer(ethtool, f"-K {cfg.ifname} gro on")
+    ip(f"link set dev {cfg.ifname} xdp obj {xdp_obj} sec xdp")
+    defer(ip, f"link set dev {cfg.ifname} xdp off")
+
+    qdiscs = json.loads(cmd(f"tc -j qdisc show dev {cfg.ifname}").stdout)
+    if not any(q['kind'] == 'clsact' for q in qdiscs):
+        cmd(f"tc qdisc add dev {cfg.ifname} clsact")
+        defer(cmd, f"tc qdisc del dev {cfg.ifname} clsact")
+    cmd(f"tc filter add dev {cfg.ifname} ingress bpf da obj {bpf_obj} sec tc")
+
+    progs = bpftool("prog list", json=True)
+    tc_prog_id = None
+    for p in progs:
+        if p.get("name") == "tc_check_csum":
+            tc_prog_id = p["id"]
+            break
+
+    if tc_prog_id is None:
+        raise KsftSkipEx("Could not find tc_check_csum BPF program")
+
+    maps = bpf_prog_map_ids(tc_prog_id)
+    csum_map_id = maps.get("map_csum_result")
+    if csum_map_id is None:
+        raise KsftSkipEx("Could not find map_csum_result map")
+
+    for _ in range(10):
+        _send_probe(cfg, 12345, proto="udp")
+
+    result = bpf_map_dump(csum_map_id)
+    csum_none = result.get(0, 0)
+    csum_unnecessary = result.get(1, 0)
+    csum_complete = result.get(2, 0)
+    ksft_ge(csum_none, 1, "skb->ip_summed should be CHECKSUM_NONE after XDP_PASS")
+    ksft_eq(csum_unnecessary, 0, "CHECKSUM_UNNECESSARY should not be set")
+    ksft_eq(csum_complete, 0, "CHECKSUM_COMPLETE should not be set")
+
+
 def main():
     """Run XDP metadata kfunc tests against a real device."""
     with NetDrvEpEnv(__file__) as cfg:
@@ -137,6 +189,7 @@ def main():
         ksft_run(
             [
                 test_xdp_rss_hash,
+                test_xdp_pass_rx_csum,
             ],
             args=(cfg,))
     ksft_exit()
diff --git a/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c b/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c
new file mode 100644
index 000000000000..6a953c4acfe7
--- /dev/null
+++ b/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/udp.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_PORT 12345
+
+enum skb_csum {
+	SKB_CSUM_NONE		= 0,
+	SKB_CSUM_UNNECESSARY	= 1,
+	SKB_CSUM_COMPLETE	= 2,
+	SKB_CSUM_PARTIAL	= 3,
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, SKB_CSUM_PARTIAL);
+	__type(key, __u32);
+	__type(value, __u64);
+} map_csum_result SEC(".maps");
+
+extern int bpf_skb_rx_checksum(struct __sk_buff *skb, __u32 *ip_summed,
+				__u32 *csum_meta) __ksym;
+
+SEC("tc")
+int tc_check_csum(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	__u32 ip_summed, csum_meta;
+	struct ethhdr *eth = data;
+	struct ipv6hdr *ip6;
+	struct udphdr *udp;
+
+	if ((void *)(eth + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
+		return TC_ACT_OK;
+
+	ip6 = (void *)(eth + 1);
+	if ((void *)(ip6 + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (ip6->nexthdr != IPPROTO_UDP)
+		return TC_ACT_OK;
+
+	udp = (void *)(ip6 + 1);
+	if ((void *)(udp + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (udp->dest != bpf_htons(UDP_PORT))
+		return TC_ACT_OK;
+
+	bpf_skb_rx_checksum(skb, &ip_summed, &csum_meta);
+	if (ip_summed < SKB_CSUM_PARTIAL) {
+		__u64 *cnt;
+
+		cnt = bpf_map_lookup_elem(&map_csum_result, &ip_summed);
+		if (cnt)
+			__sync_fetch_and_add(cnt, 1);
+	}
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";

-- 
2.55.0

Re: [PATCH bpf-next v5 3/8] net: ice: add xmo_rx_checksum callback

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The `ice_xdp_rx_checksum()` XDP metadata getter calls `ice_get_rx_csum()`, which has side effects that artificially inflate hardware error statistics and cause double-counting.
--

--- Patch [3]: [PATCH bpf-next v5 3/8] net: ice: add xmo_rx_checksum callback ---
commit 741cd60a0647d5876e42a8815bc6526c4da474e1
Author: Lorenzo Bianconi <lorenzo@kernel.org>

net: ice: add xmo_rx_checksum callback

This patch implements the xmo_rx_checksum callback in the ice driver to report
RX checksum results to eBPF programs. It introduces the ice_get_rx_csum utility
routine to make the RX checksum code reusable from both ice_rx_csum() and
ice_xdp_rx_checksum().

> diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
> index e695a664e53d1..3aa82ff03d9e2 100644
> --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
> +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
[ ... ]
>  static void
> -ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
> -	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
> +ice_get_rx_csum(const union ice_32b_rx_flex_desc *rx_desc, u16 ptype,
> +		struct ice_rx_ring *ring, enum xdp_checksum *ip_summed,
> +		u32 *cksum, u8 *cksum_level)
>  {
[ ... ]
>  	if (ipv4 && (rx_status0 & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))) {
>  		ring->vsi->back->hw_rx_eipe_error++;
> -		return;
> +		goto checksum_none;
>  	}
[ ... ]
>  checksum_fail:
>  	ring->vsi->back->hw_csum_rx_error++;
> +checksum_none:
> +	*ip_summed = XDP_CHECKSUM_NONE;
> +	*cksum_level = 0;
> +	*cksum = 0;
> +}
[ ... ]
> +static int ice_xdp_rx_checksum(const struct xdp_md *ctx,
> +			       enum xdp_checksum *ip_summed,
> +			       u32 *cksum, u8 *cksum_level)
> +{
> +	const struct libeth_xdp_buff *xdp_ext = (void *)ctx;
> +	const union ice_32b_rx_flex_desc *rx_desc = xdp_ext->desc;
> +	struct ice_rx_ring *ring;
> +
> +	ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*ring), xdp_rxq);
> +	ice_get_rx_csum(rx_desc, ice_get_ptype(rx_desc), ring, ip_summed,
> +			cksum, cksum_level);

[Severity: Medium]
Since ice_get_rx_csum() increments hw_rx_eipe_error and hw_csum_rx_error, does
calling it from the XDP metadata getter artificially inflate these statistics?

An eBPF program can call the metadata getter multiple times on a single packet,
which would cause multi-counting. Furthermore, if the program returns XDP_PASS,
the networking stack will process the packet and call ice_rx_csum() which
calls ice_get_rx_csum() again, resulting in double-counting for the error.

> +
> +	return 0;
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-bpf-xdp-meta-rxcksum-v5-0-623d5c0d0ab7@kernel.org?part=3

Re: [PATCH bpf-next v5 8/8] selftests: net: add test for XDP_PASS skb checksum invalidation

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] The `tc_check_csum` BPF program strictly requires IPv6 traffic, but the python test probe can send IPv4 traffic depending on the environment configuration, causing the test to falsely fail.
- [Medium] The test leaks a `tc filter` and its associated BPF program if the interface already had a `clsact` qdisc.
--

--- Patch [8]: [PATCH bpf-next v5 8/8] selftests: net: add test for XDP_PASS skb checksum invalidation ---
commit 2b96bd0af0eb846efe81e2f0246ecebcc855acd6
Author: Lorenzo Bianconi <lorenzo@kernel.org>

selftests: net: add test for XDP_PASS skb checksum invalidation

This commit adds a selftest to verify that a device running in XDP mode
correctly invalidates the hardware RX checksum when an attached XDP program
returns XDP_PASS. It checks this by attaching an XDP program and a TC
ingress program to inspect the resulting skb via the bpf_skb_rx_checksum()
kfunc.

> diff --git a/tools/testing/selftests/drivers/net/hw/xdp_metadata.py b/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
> index 33a1985356d90..8ccd34b776b4d 100755
> --- a/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
> +++ b/tools/testing/selftests/drivers/net/hw/xdp_metadata.py
[ ... ]
> @@ -130,6 +131,57 @@ def test_xdp_rss_hash(cfg, proto):
>              f"RSS hash type should include L4 for {proto.upper()} traffic")
>  
>  
> +def test_xdp_pass_rx_csum(cfg):
> +    """Test xdp_pass sets CHECKSUM_NONE on the resulting skb.
> +
> +    Attaches an XDP program that returns XDP_PASS and a TC ingress
> +    program that checks skb->ip_summed via bpf_skb_rx_checksum().
> +    Verifies the value is CHECKSUM_NONE.
> +    """
> +
> +    bpf_obj = cfg.net_lib_dir / "skb_metadata_csum.bpf.o"
> +    xdp_obj = cfg.net_lib_dir / "xdp_dummy.bpf.o"
> +
> +    # GRO may overwrite skb->ip_summed after the driver sets it,
> +    # so disable it to preserve the checksum set by the driver.
> +    ethtool(f"-K {cfg.ifname} gro off")
> +    defer(ethtool, f"-K {cfg.ifname} gro on")
> +    ip(f"link set dev {cfg.ifname} xdp obj {xdp_obj} sec xdp")
> +    defer(ip, f"link set dev {cfg.ifname} xdp off")
> +
> +    qdiscs = json.loads(cmd(f"tc -j qdisc show dev {cfg.ifname}").stdout)
> +    if not any(q['kind'] == 'clsact' for q in qdiscs):
> +        cmd(f"tc qdisc add dev {cfg.ifname} clsact")
> +        defer(cmd, f"tc qdisc del dev {cfg.ifname} clsact")
> +    cmd(f"tc filter add dev {cfg.ifname} ingress bpf da obj {bpf_obj} sec tc")

[Severity: Medium]
Does this leak the tc filter and BPF program if the interface already had a
clsact qdisc?

Since the filter deletion is not explicitly deferred here, it appears the
filter will remain active if the test bypassed the qdisc creation and
deletion. This could cause subsequent test runs to falsely fail if they
discover and query the leaked BPF program instead of the newly attached one.

> +
> +    progs = bpftool("prog list", json=True)
> +    tc_prog_id = None
> +    for p in progs:
> +        if p.get("name") == "tc_check_csum":
> +            tc_prog_id = p["id"]
> +            break
> +
> +    if tc_prog_id is None:
> +        raise KsftSkipEx("Could not find tc_check_csum BPF program")
> +
> +    maps = bpf_prog_map_ids(tc_prog_id)
> +    csum_map_id = maps.get("map_csum_result")
> +    if csum_map_id is None:
> +        raise KsftSkipEx("Could not find map_csum_result map")
> +
> +    for _ in range(10):
> +        _send_probe(cfg, 12345, proto="udp")

[Severity: Medium]
Will this cause spurious test failures if the test environment defaults
to IPv4?

The _send_probe() method will send IPv4 traffic if the environment's
cfg.addr_ipver defaults to 4. However, the BPF program tc_check_csum
explicitly ignores non-IPv6 traffic. If IPv4 packets are sent, the counters
will remain at zero and the test will fail.

> +
> +    result = bpf_map_dump(csum_map_id)
[ ... ]
> diff --git a/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c b/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c
> new file mode 100644
> index 0000000000000..6a953c4acfe78
> --- /dev/null
> +++ b/tools/testing/selftests/net/lib/skb_metadata_csum.bpf.c
[ ... ]
> @@ -0,0 +1,73 @@
[ ... ]
> +SEC("tc")
> +int tc_check_csum(struct __sk_buff *skb)
> +{
> +	void *data_end = (void *)(long)skb->data_end;
> +	void *data = (void *)(long)skb->data;
> +	__u32 ip_summed, csum_meta;
> +	struct ethhdr *eth = data;
> +	struct ipv6hdr *ip6;
> +	struct udphdr *udp;
> +
> +	if ((void *)(eth + 1) > data_end)
> +		return TC_ACT_OK;
> +
> +	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
> +		return TC_ACT_OK;

[Severity: Medium]
Can this strict IPv6 check cause a mismatch with the python script?

As noted above, the python script calling _send_probe() might send IPv4 UDP
packets depending on the environment configuration, which would be silently
dropped here, bypassing the counter updates entirely.

> +
> +	ip6 = (void *)(eth + 1);
> +	if ((void *)(ip6 + 1) > data_end)
> +		return TC_ACT_OK;
> +

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-bpf-xdp-meta-rxcksum-v5-0-623d5c0d0ab7@kernel.org?part=8

Re: [PATCH bpf-next v5 7/8] selftests/bpf: Add test for bpf_skb_rx_checksum kfunc

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [Medium] The `csum_cnt` array map is sized incorrectly and explicitly drops valid `SKB_CSUM_PARTIAL` checksum states.
- [Low] Passing an `enum skb_csum *` to a kfunc expecting a `__u32 *` causes an incompatible pointer type warning.
- [Low] The multi-line comment for `bpf_skb_rx_checksum` violates the required BPF subsystem comment style.
--

--- Patch [7]: [PATCH bpf-next v5 7/8] selftests/bpf: Add test for bpf_skb_rx_checksum kfunc ---
commit b45897a4d5ef22742e4af5ab8e7a00ba0c92d2f2
Author: Lorenzo Bianconi <lorenzo@kernel.org>

selftests/bpf: Add test for bpf_skb_rx_checksum kfunc

This commit adds a selftest for the newly added bpf_skb_rx_checksum() kfunc.
The test consists of a TC BPF program that calls the kfunc and records the
checksum type, along with a userspace test runner.

> diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
> index ae71e9b690518..d03572e26df2d 100644
> --- a/tools/testing/selftests/bpf/bpf_kfuncs.h
> +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
> @@ -64,6 +64,14 @@ struct bpf_tcp_req_attrs;
>  extern int bpf_sk_assign_tcp_reqsk(struct __sk_buff *skb, struct sock *sk,
>  				   struct bpf_tcp_req_attrs *attrs, int attrs__sz) __ksym;
>  
> +/* Description
> + *  Read skb RX checksum info (ip_summed and csum_meta).

[Severity: Low]
This isn't a bug, but does this multi-line comment follow the BPF subsystem
comment style? The guidelines require the opening /* to be on its own line.

> + * Returns
> + *  0 on success
> + */
> +extern int bpf_skb_rx_checksum(struct __sk_buff *skb, __u32 *ip_summed,
> +			       __u32 *csum_meta) __ksym;
> +

[ ... ]

> diff --git a/tools/testing/selftests/bpf/progs/skb_rx_checksum.c b/tools/testing/selftests/bpf/progs/skb_rx_checksum.c
> new file mode 100644
> index 0000000000000..dc4e192905d53
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/skb_rx_checksum.c
> @@ -0,0 +1,33 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +#include <linux/bpf.h>
> +#include <linux/pkt_cls.h>
> +#include <bpf/bpf_helpers.h>
> +#include "bpf_kfuncs.h"
> +#include "skb_rx_checksum.h"
> +
> +struct {
> +	__uint(type, BPF_MAP_TYPE_ARRAY);
> +	__uint(max_entries, SKB_CSUM_PARTIAL);

[Severity: Medium]
Does this incorrectly restrict the map size? SKB_CSUM_PARTIAL is defined as
3, which means the map can only hold entries for 0, 1, and 2, leaving no
room to track the SKB_CSUM_PARTIAL state itself.

> +	__type(key, __u32);
> +	__type(value, __u64);
> +} csum_cnt SEC(".maps");
> +
> +SEC("tc")
> +int tc_rx_csum(struct __sk_buff *skb)
> +{
> +	enum skb_csum ip_summed;
> +	__u32 csum_meta;
> +	__u64 *cnt;
> +
> +	bpf_skb_rx_checksum(skb, &ip_summed, &csum_meta);

[Severity: Low]
Will this cause an incompatible pointer type compiler warning in
tc_rx_csum()? The kfunc bpf_skb_rx_checksum() expects a __u32 * for its
second argument, but &ip_summed is a pointer to an enum skb_csum.

> +	if (ip_summed < SKB_CSUM_PARTIAL) {

[Severity: Medium]
By using strictly less than SKB_CSUM_PARTIAL, does this silently drop valid
packets that have the SKB_CSUM_PARTIAL state?

> +		cnt = bpf_map_lookup_elem(&csum_cnt, &ip_summed);
> +		if (cnt)
> +			__sync_fetch_and_add(cnt, 1);
> +	}
> +
> +	return TC_ACT_OK;
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-bpf-xdp-meta-rxcksum-v5-0-623d5c0d0ab7@kernel.org?part=7

Re: [PATCH bpf-next v5 2/8] net: veth: add xmo_rx_checksum callback to veth driver

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] veth_xdp_rx_checksum incorrectly maps CHECKSUM_PARTIAL to XDP_CHECKSUM_NONE, causing XDP programs to drop valid locally-generated packets.
--

--- Patch [2]: [PATCH bpf-next v5 2/8] net: veth: add xmo_rx_checksum callback to veth driver ---
commit 34eae1c96706424d6fb3ab7f5a60445ee0f6dd08
Author: Lorenzo Bianconi <lorenzo@kernel.org>

net: veth: add xmo_rx_checksum callback to veth driver

Implement xmo_rx_checksum callback in veth driver to report RX checksum
result to the eBPF program bounded to the veth device.

> diff --git a/drivers/net/veth.c b/drivers/net/veth.c
> index 8170bf33ccf95..dbf30089581c8 100644
> --- a/drivers/net/veth.c
> +++ b/drivers/net/veth.c
> @@ -1701,6 +1701,37 @@ static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
>  	return err;
>  }
>  
> +static int veth_xdp_rx_checksum(const struct xdp_md *ctx,
> +				enum xdp_checksum *ip_summed,
> +				u32 *cksum, u8 *cksum_level)
> +{
> +	const struct veth_xdp_buff *_ctx = (void *)ctx;
> +	const struct sk_buff *skb = _ctx->skb;
> +
> +	if (!skb)
> +		return -ENODATA;
> +
> +	switch (skb->ip_summed) {
> +	case CHECKSUM_COMPLETE:
> +		*ip_summed = XDP_CHECKSUM_COMPLETE;
> +		*cksum = skb->csum;
> +		*cksum_level = 0;
> +		break;
> +	case CHECKSUM_UNNECESSARY:
> +		*ip_summed = XDP_CHECKSUM_UNNECESSARY;
> +		*cksum_level = skb->csum_level;
> +		*cksum = 0;
> +		break;
> +	default:
> +		*ip_summed = XDP_CHECKSUM_NONE;
> +		*cksum_level = 0;
> +		*cksum = 0;
> +		break;
> +	}

[Severity: High]
Is there a missing case for CHECKSUM_PARTIAL in this switch statement inside
veth_xdp_rx_checksum()?

When a local process sends traffic over a veth pair with checksum offload
enabled, the packet is passed to the receiving veth with skb->ip_summed
set to CHECKSUM_PARTIAL.

By falling through to the default case, this maps CHECKSUM_PARTIAL to
XDP_CHECKSUM_NONE. An attached XDP program that validates checksums will see
XDP_CHECKSUM_NONE and attempt to compute a software checksum. The software
computation will fail because the TCP/UDP checksum field only contains a
pseudo-header checksum at this point, leading to dropped packets.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260715-bpf-xdp-meta-rxcksum-v5-0-623d5c0d0ab7@kernel.org?part=2

Re: [PATCH bpf-next v5 1/8] netlink: specs: add XDP RX checksum capability to XDP metadata specs

[bot+bpf-ci]

[-- Attachment #1: Type: text/plain, Size: 2470 bytes --]

> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index 9890a30584ba..9bcaa423ad17 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -961,6 +961,38 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
>  	return -EOPNOTSUPP;
>  }
>
> +/**
> + * bpf_xdp_metadata_rx_checksum - Read XDP frame RX checksum.
> + * @ctx: XDP context pointer.
> + * @ip_summed: Return value pointer to a bitmask indicating available checksums.
> + * @cksum: Return value pointer indicating the hw checksum value.
> + * @cksum_level: Return value pointer indicating the checksum level result.
> + *
> + * In case of success, ``ip_summed`` is set to the RX checksum result. Possible
> + * values are:
> + * ``XDP_CHECKSUM_NONE``
> + * ``XDP_CHECKSUM_UNNECESSARY``
> + * ``XDP_CHECKSUM_COMPLETE``
> + * ``XDP_CHECKSUM_COMPLETE`` | ``XDP_CHECKSUM_UNNECESSARY``
> + *
> + * In case of success, ``cksum`` contains the checksum value calculated by the
> + * NIC. ``cksum`` is valid only if ``XDP_CHECKSUM_COMPLETE`` is set in
> + * ``ip_summed``. ``cksum_level`` contains the checksum level reported by the
> + * hw. ``cksum_level`` can be considered valid only if
> + * ``XDP_CHECKSUM_UNNECESSARY`` is set in ``ip_summed``.

Earlier review of this series raised the case where the NIC reports
COMPLETE or UNNECESSARY, the XDP program then modifies the packet and
returns XDP_PASS.  In that situation the reported checksum is stale.

It was noted on the list that drivers today do not invalidate the
checksum in this case, they only stop reporting COMPLETE while an XDP
program is attached.

Would it help to document that expected driver behavior here (how it
works today versus what is expected), and possibly add a kselftest that
checks it?  If this is handled in a later patch of the series, please
disregard.

> + *
> + * Return:
> + * * Returns 0 on success or ``-errno`` on error.
> + * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc
> + * * ``-ENODATA``    : means no RX-checksum available for this frame
> + */
> +__bpf_kfunc int bpf_xdp_metadata_rx_checksum(const struct xdp_md *ctx,
> +					     enum xdp_checksum *ip_summed,
> +					     u32 *cksum, u8 *cksum_level)
> +{
> +	return -EOPNOTSUPP;
> +}


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/29453967825

Re: [Intel-wired-lan] [PATCH bpf-next v5 1/8] netlink: specs: add XDP RX checksum capability to XDP metadata specs

[bot+bpf-ci]

[-- Attachment #1: Type: text/plain, Size: 2470 bytes --]

> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index 9890a30584ba..9bcaa423ad17 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -961,6 +961,38 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
>  	return -EOPNOTSUPP;
>  }
>
> +/**
> + * bpf_xdp_metadata_rx_checksum - Read XDP frame RX checksum.
> + * @ctx: XDP context pointer.
> + * @ip_summed: Return value pointer to a bitmask indicating available checksums.
> + * @cksum: Return value pointer indicating the hw checksum value.
> + * @cksum_level: Return value pointer indicating the checksum level result.
> + *
> + * In case of success, ``ip_summed`` is set to the RX checksum result. Possible
> + * values are:
> + * ``XDP_CHECKSUM_NONE``
> + * ``XDP_CHECKSUM_UNNECESSARY``
> + * ``XDP_CHECKSUM_COMPLETE``
> + * ``XDP_CHECKSUM_COMPLETE`` | ``XDP_CHECKSUM_UNNECESSARY``
> + *
> + * In case of success, ``cksum`` contains the checksum value calculated by the
> + * NIC. ``cksum`` is valid only if ``XDP_CHECKSUM_COMPLETE`` is set in
> + * ``ip_summed``. ``cksum_level`` contains the checksum level reported by the
> + * hw. ``cksum_level`` can be considered valid only if
> + * ``XDP_CHECKSUM_UNNECESSARY`` is set in ``ip_summed``.

Earlier review of this series raised the case where the NIC reports
COMPLETE or UNNECESSARY, the XDP program then modifies the packet and
returns XDP_PASS.  In that situation the reported checksum is stale.

It was noted on the list that drivers today do not invalidate the
checksum in this case, they only stop reporting COMPLETE while an XDP
program is attached.

Would it help to document that expected driver behavior here (how it
works today versus what is expected), and possibly add a kselftest that
checks it?  If this is handled in a later patch of the series, please
disregard.

> + *
> + * Return:
> + * * Returns 0 on success or ``-errno`` on error.
> + * * ``-EOPNOTSUPP`` : means device driver does not implement kfunc
> + * * ``-ENODATA``    : means no RX-checksum available for this frame
> + */
> +__bpf_kfunc int bpf_xdp_metadata_rx_checksum(const struct xdp_md *ctx,
> +					     enum xdp_checksum *ip_summed,
> +					     u32 *cksum, u8 *cksum_level)
> +{
> +	return -EOPNOTSUPP;
> +}


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/29453967825