bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Larysa Zaremba <larysa.zaremba@intel.com>
To: bpf@vger.kernel.org
Cc: Larysa Zaremba <larysa.zaremba@intel.com>,
	ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
	martin.lau@linux.dev, song@kernel.org, yhs@fb.com,
	john.fastabend@gmail.com, kpsingh@kernel.org, sdf@google.com,
	haoluo@google.com, jolsa@kernel.org,
	David Ahern <dsahern@gmail.com>, Jakub Kicinski <kuba@kernel.org>,
	Willem de Bruijn <willemb@google.com>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Anatoly Burakov <anatoly.burakov@intel.com>,
	Alexander Lobakin <alexandr.lobakin@intel.com>,
	Magnus Karlsson <magnus.karlsson@gmail.com>,
	Maryam Tahhan <mtahhan@redhat.com>,
	xdp-hints@xdp-project.net, netdev@vger.kernel.org
Subject: [PATCH bpf-next v3 12/21] xdp: Add checksum hint
Date: Wed, 19 Jul 2023 20:37:25 +0200	[thread overview]
Message-ID: <20230719183734.21681-13-larysa.zaremba@intel.com> (raw)
In-Reply-To: <20230719183734.21681-1-larysa.zaremba@intel.com>

Implement functionality that enables drivers to expose to XDP code checksum
information that consists of:

- Checksum status - bitfield that consists of
  - number of consecutive validated checksums. This is almost the same as
    csum_level in skb, but starts with 1. Enum names for those bits still
    use checksum level concept, so it is less confusing for driver
    developers.
  - Is checksum partial? This bit cannot coexist with any other
  - Is there a complete checksum available?
- Additional checksum data, a union of:
  - checksum start and offset, if checksum is partial
  - complete checksum, if available

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 Documentation/networking/xdp-rx-metadata.rst |  3 ++
 include/linux/netdevice.h                    |  3 ++
 include/net/xdp.h                            | 46 ++++++++++++++++++++
 kernel/bpf/offload.c                         |  2 +
 net/core/xdp.c                               | 23 ++++++++++
 5 files changed, 77 insertions(+)

diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index ea6dd79a21d3..7f056a44f682 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -26,6 +26,9 @@ 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_csum
+
 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/linux/netdevice.h b/include/linux/netdevice.h
index 1749f4f75c64..4f6da36ac123 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1660,6 +1660,9 @@ struct xdp_metadata_ops {
 			       enum xdp_rss_hash_type *rss_type);
 	int	(*xmo_rx_vlan_tag)(const struct xdp_md *ctx, u16 *vlan_tci,
 				   __be16 *vlan_proto);
+	int	(*xmo_rx_csum)(const struct xdp_md *ctx,
+			       enum xdp_csum_status *csum_status,
+			       union xdp_csum_info *csum_info);
 };
 
 /**
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 89c58f56ffc6..2b7a7d678ff4 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -391,6 +391,8 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   bpf_xdp_metadata_rx_hash) \
 	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \
 			   bpf_xdp_metadata_rx_vlan_tag) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_CSUM, \
+			   bpf_xdp_metadata_rx_csum) \
 
 enum {
 #define XDP_METADATA_KFUNC(name, _) name,
@@ -448,6 +450,50 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR,
 };
 
+union xdp_csum_info {
+	/* Checksum referred to by ``csum_start + csum_offset`` is considered
+	 * valid, but was never calculated, TX device has to do this,
+	 * starting from csum_start packet byte.
+	 * Any preceding checksums are also considered valid.
+	 * Available, if ``status == XDP_CHECKSUM_PARTIAL``.
+	 */
+	struct {
+		u16 csum_start;
+		u16 csum_offset;
+	};
+
+	/* Checksum, calculated over the whole packet.
+	 * Available, if ``status & XDP_CHECKSUM_COMPLETE``.
+	 */
+	u32 checksum;
+};
+
+enum xdp_csum_status {
+	/* HW had parsed several transport headers and validated their
+	 * checksums, same as ``CHECKSUM_UNNECESSARY`` in ``sk_buff``.
+	 * 3 least significat bytes contain number of consecutive checksum,
+	 * starting with the outermost, reported by hardware as valid.
+	 * ``sk_buff`` checksum level (``csum_level``) notation is provided
+	 * for driver developers.
+	 */
+	XDP_CHECKSUM_VALID_LVL0		= 1,	/* 1 outermost checksum */
+	XDP_CHECKSUM_VALID_LVL1		= 2,	/* 2 outermost checksums */
+	XDP_CHECKSUM_VALID_LVL2		= 3,	/* 3 outermost checksums */
+	XDP_CHECKSUM_VALID_LVL3		= 4,	/* 4 outermost checksums */
+	XDP_CHECKSUM_VALID_NUM_MASK	= GENMASK(2, 0),
+	XDP_CHECKSUM_VALID		= XDP_CHECKSUM_VALID_NUM_MASK,
+
+	/* Occurs if packet is sent virtually (between Linux VMs / containers)
+	 * This status cannot coexist with any other.
+	 * Refer to ``csum_start`` and ``csum_offset`` in ``xdp_csum_info``
+	 * for more information.
+	 */
+	XDP_CHECKSUM_PARTIAL	= BIT(3),
+
+	/* Checksum, calculated over the entire packet is provided */
+	XDP_CHECKSUM_COMPLETE	= BIT(4),
+};
+
 #ifdef CONFIG_NET
 u32 bpf_xdp_metadata_kfunc_id(int id);
 bool bpf_dev_bound_kfunc_id(u32 btf_id);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 986e7becfd42..f60a6add5273 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -850,6 +850,8 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
 		p = ops->xmo_rx_hash;
 	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_VLAN_TAG))
 		p = ops->xmo_rx_vlan_tag;
+	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_CSUM))
+		p = ops->xmo_rx_csum;
 out:
 	up_read(&bpf_devs_lock);
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 8b55419d332e..d4ea54046afc 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -772,6 +772,29 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_csum - Get checksum status with additional info.
+ * @ctx: XDP context pointer.
+ * @csum_status: Destination for checksum status.
+ * @csum_info: Destination for complete checksum or partial checksum offset.
+ *
+ * Status (@csum_status) is a bitfield that informs, what checksum
+ * processing was performed. Additional results of such processing,
+ * such as complete checksum or partial checksum offsets,
+ * are passed as info (@csum_info).
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc
+ * * ``-ENODATA``    : Checksum status is unknown
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_csum(const struct xdp_md *ctx,
+					 enum xdp_csum_status *csum_status,
+					 union xdp_csum_info *csum_info)
+{
+	return -EOPNOTSUPP;
+}
+
 __diag_pop();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
-- 
2.41.0


  parent reply	other threads:[~2023-07-19 18:42 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-19 18:37 [PATCH bpf-next v3 00/21] XDP metadata via kfuncs for ice Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 01/21] ice: make RX hash reading code more reusable Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 02/21] ice: make RX HW timestamp " Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 03/21] ice: make RX checksum checking " Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 04/21] ice: Make ptype internal to descriptor info processing Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 05/21] ice: Introduce ice_xdp_buff Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 06/21] ice: Support HW timestamp hint Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 07/21] ice: Support RX hash XDP hint Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 08/21] ice: Support XDP hints in AF_XDP ZC mode Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 09/21] xdp: Add VLAN tag hint Larysa Zaremba
2023-07-20 21:49   ` Stanislav Fomichev
2023-07-19 18:37 ` [PATCH bpf-next v3 10/21] ice: Implement " Larysa Zaremba
2023-07-20 18:50   ` Simon Horman
2023-07-21  7:38     ` Zaremba, Larysa
2023-07-19 18:37 ` [PATCH bpf-next v3 11/21] ice: use VLAN proto from ring packet context in skb path Larysa Zaremba
2023-07-19 18:37 ` Larysa Zaremba [this message]
2023-07-19 21:42   ` [PATCH bpf-next v3 12/21] xdp: Add checksum hint Willem de Bruijn
2023-07-20  9:57     ` Zaremba, Larysa
2023-07-20 10:10       ` Zaremba, Larysa
2023-07-20 13:55         ` Willem de Bruijn
2023-07-20 16:03           ` Zaremba, Larysa
2023-07-20 22:27             ` Willem de Bruijn
2023-07-21  8:01               ` Zaremba, Larysa
2023-07-19 18:37 ` [PATCH bpf-next v3 13/21] ice: Implement " Larysa Zaremba
2023-07-19 18:59   ` Alexei Starovoitov
2023-07-19 21:51     ` Willem de Bruijn
2023-07-20  9:47       ` Zaremba, Larysa
2023-07-20 15:14         ` Alexei Starovoitov
2023-07-20 15:41           ` Zaremba, Larysa
2023-07-20 21:58             ` Stanislav Fomichev
2023-07-20 22:24               ` Willem de Bruijn
2023-07-19 18:37 ` [PATCH bpf-next v3 14/21] selftests/bpf: Allow VLAN packets in xdp_hw_metadata Larysa Zaremba
2023-07-20 21:58   ` Stanislav Fomichev
2023-07-19 18:37 ` [PATCH bpf-next v3 15/21] net, xdp: allow metadata > 32 Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 16/21] selftests/bpf: Add flags and new hints to xdp_hw_metadata Larysa Zaremba
2023-07-20 22:00   ` Stanislav Fomichev
2023-07-21  7:41     ` Zaremba, Larysa
2023-07-19 18:37 ` [PATCH bpf-next v3 17/21] veth: Implement VLAN tag and checksum XDP hint Larysa Zaremba
2023-07-20 22:02   ` Stanislav Fomichev
2023-07-19 18:37 ` [PATCH bpf-next v3 18/21] net: make vlan_get_tag() return -ENODATA instead of -EINVAL Larysa Zaremba
2023-07-20 22:02   ` Stanislav Fomichev
2023-07-19 18:37 ` [PATCH bpf-next v3 19/21] selftests/bpf: Use AF_INET for TX in xdp_metadata Larysa Zaremba
2023-07-20 22:05   ` Stanislav Fomichev
2023-07-19 18:37 ` [PATCH bpf-next v3 20/21] selftests/bpf: Check VLAN tag and proto " Larysa Zaremba
2023-07-20 22:14   ` Stanislav Fomichev
2023-07-21  7:46     ` Zaremba, Larysa
2023-07-21 16:44       ` Stanislav Fomichev
2023-07-25  7:11         ` Larysa Zaremba
2023-07-19 18:37 ` [PATCH bpf-next v3 21/21] selftests/bpf: check checksum state " Larysa Zaremba
2023-07-20 22:14   ` Stanislav Fomichev

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230719183734.21681-13-larysa.zaremba@intel.com \
    --to=larysa.zaremba@intel.com \
    --cc=alexandr.lobakin@intel.com \
    --cc=anatoly.burakov@intel.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=dsahern@gmail.com \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=magnus.karlsson@gmail.com \
    --cc=martin.lau@linux.dev \
    --cc=mtahhan@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=sdf@google.com \
    --cc=song@kernel.org \
    --cc=willemb@google.com \
    --cc=xdp-hints@xdp-project.net \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).