XDP hardware hints discussion mail archive
 help / color / mirror / Atom feed
From: Stanislav Fomichev <sdf@google.com>
To: bpf@vger.kernel.org
Cc: 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, kuba@kernel.org,
	toke@kernel.org, willemb@google.com, dsahern@kernel.org,
	magnus.karlsson@intel.com, bjorn@kernel.org,
	maciej.fijalkowski@intel.com, hawk@kernel.org,
	netdev@vger.kernel.org, xdp-hints@xdp-project.net
Subject: [xdp-hints] [RFC bpf-next v3 03/14] xsk: Support XDP_TX_METADATA_LEN
Date: Fri,  7 Jul 2023 12:29:55 -0700	[thread overview]
Message-ID: <20230707193006.1309662-4-sdf@google.com> (raw)
In-Reply-To: <20230707193006.1309662-1-sdf@google.com>

For zerocopy mode, tx_desc->addr can point to the arbitrary offset
and carry some TX metadata in the headroom. For copy mode, there
is no way currently to populate skb metadata.

Introduce new XDP_TX_METADATA_LEN that indicates how many bytes
to treat as metadata. Metadata bytes come prior to tx_desc address
(same as in RX case).

Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
 include/net/xdp_sock.h      |  1 +
 include/net/xsk_buff_pool.h |  1 +
 include/uapi/linux/if_xdp.h |  1 +
 net/xdp/xsk.c               | 35 +++++++++++++++++++++++++++++++++--
 net/xdp/xsk_buff_pool.c     |  1 +
 net/xdp/xsk_queue.h         |  7 ++++---
 6 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index e96a1151ec75..30018b3b862d 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -51,6 +51,7 @@ struct xdp_sock {
 	struct list_head flush_node;
 	struct xsk_buff_pool *pool;
 	u16 queue_id;
+	u8 tx_metadata_len;
 	bool zc;
 	enum {
 		XSK_READY = 0,
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index a8d7b8a3688a..751fea51a6af 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -75,6 +75,7 @@ struct xsk_buff_pool {
 	u32 chunk_size;
 	u32 chunk_shift;
 	u32 frame_len;
+	u8 tx_metadata_len; /* inherited from xsk_sock */
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
 	bool dma_need_sync;
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index a78a8096f4ce..2374eafff7db 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -63,6 +63,7 @@ struct xdp_mmap_offsets {
 #define XDP_UMEM_COMPLETION_RING	6
 #define XDP_STATISTICS			7
 #define XDP_OPTIONS			8
+#define XDP_TX_METADATA_LEN		9
 
 struct xdp_umem_reg {
 	__u64 addr; /* Start of packet data area */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5a8c0dd250af..6ef7bc4f514c 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -485,6 +485,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 		int err;
 
 		hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
+		hr = max(hr, L1_CACHE_ALIGN((u32)xs->tx_metadata_len));
 		tr = dev->needed_tailroom;
 		len = desc->len;
 
@@ -493,14 +494,21 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			return ERR_PTR(err);
 
 		skb_reserve(skb, hr);
-		skb_put(skb, len);
+		skb_put(skb, len + xs->tx_metadata_len);
 
 		buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
-		err = skb_store_bits(skb, 0, buffer, len);
+		buffer -= xs->tx_metadata_len;
+
+		err = skb_store_bits(skb, 0, buffer, len + xs->tx_metadata_len);
 		if (unlikely(err)) {
 			kfree_skb(skb);
 			return ERR_PTR(err);
 		}
+
+		if (xs->tx_metadata_len) {
+			skb_metadata_set(skb, xs->tx_metadata_len);
+			__skb_pull(skb, xs->tx_metadata_len);
+		}
 	}
 
 	skb->dev = dev;
@@ -1137,6 +1145,29 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 		mutex_unlock(&xs->mutex);
 		return err;
 	}
+	case XDP_TX_METADATA_LEN:
+	{
+		int val;
+
+		if (optlen < sizeof(val))
+			return -EINVAL;
+		if (copy_from_sockptr(&val, optval, sizeof(val)))
+			return -EFAULT;
+
+		if (val >= 256)
+			return -EINVAL;
+		if (val % 4)
+			return -EINVAL;
+
+		mutex_lock(&xs->mutex);
+		if (xs->state != XSK_READY) {
+			mutex_unlock(&xs->mutex);
+			return -EBUSY;
+		}
+		xs->tx_metadata_len = val;
+		mutex_unlock(&xs->mutex);
+		return 0;
+	}
 	default:
 		break;
 	}
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 26f6d304451e..66ff9c345a67 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -85,6 +85,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
+	pool->tx_metadata_len = xs->tx_metadata_len;
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
 	spin_lock_init(&pool->xsk_tx_list_lock);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 6d40a77fccbe..c8d287c18d64 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -133,12 +133,13 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
-	u64 offset = desc->addr & (pool->chunk_size - 1);
+	u64 addr = desc->addr - pool->tx_metadata_len;
+	u64 offset = addr & (pool->chunk_size - 1);
 
 	if (offset + desc->len > pool->chunk_size)
 		return false;
 
-	if (desc->addr >= pool->addrs_cnt)
+	if (addr >= pool->addrs_cnt)
 		return false;
 
 	if (desc->options)
@@ -149,7 +150,7 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 					      struct xdp_desc *desc)
 {
-	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
+	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len;
 
 	if (desc->len > pool->chunk_size)
 		return false;
-- 
2.41.0.255.g8b1d071c50-goog


  parent reply	other threads:[~2023-07-07 19:30 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-07 19:29 [xdp-hints] [RFC bpf-next v3 00/14] bpf: Netdev TX metadata Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 01/14] bpf: Rename some xdp-metadata functions into dev-bound Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 02/14] bpf: Make it easier to add new metadata kfunc Stanislav Fomichev
2023-07-07 19:29 ` Stanislav Fomichev [this message]
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 04/14] bpf: Implement devtx hook points Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 05/14] bpf: Implement devtx timestamp kfunc Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 06/14] net: veth: Implement devtx timestamp kfuncs Stanislav Fomichev
2023-07-07 19:29 ` [xdp-hints] [RFC bpf-next v3 07/14] bpf: Introduce tx checksum devtx kfuncs Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 08/14] net: veth: Implement devtx tx checksum Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 09/14] net/mlx5e: Implement devtx kfuncs Stanislav Fomichev
2023-07-11 22:56   ` [xdp-hints] " Alexei Starovoitov
2023-07-11 23:24     ` Stanislav Fomichev
2023-07-11 23:45       ` Alexei Starovoitov
2023-07-12  0:14         ` Stanislav Fomichev
2023-07-12  2:50           ` Alexei Starovoitov
2023-07-12  3:29             ` Stanislav Fomichev
2023-07-12  4:59               ` Alexei Starovoitov
2023-07-12  5:36                 ` Stanislav Fomichev
2023-07-12 15:16                   ` Willem de Bruijn
2023-07-12 16:28                     ` Willem de Bruijn
2023-07-12 19:03                     ` Alexei Starovoitov
2023-07-12 19:11                       ` Willem de Bruijn
2023-07-12 19:42                         ` Alexei Starovoitov
2023-07-12 20:09                           ` Jakub Kicinski
2023-07-12 20:53                             ` Stanislav Fomichev
2023-07-12  0:32     ` Jakub Kicinski
2023-07-12  2:37       ` Alexei Starovoitov
2023-07-12  3:07         ` Jakub Kicinski
2023-07-12  3:23           ` Alexei Starovoitov
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 10/14] selftests/xsk: Support XDP_TX_METADATA_LEN Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 11/14] selftests/bpf: Add helper to query current netns cookie Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 12/14] selftests/bpf: Add csum helpers Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 13/14] selftests/bpf: Extend xdp_metadata with devtx kfuncs Stanislav Fomichev
2023-07-07 19:30 ` [xdp-hints] [RFC bpf-next v3 14/14] selftests/bpf: Extend xdp_hw_metadata " 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

  List information: https://lists.xdp-project.net/postorius/lists/xdp-hints.xdp-project.net/

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

  git send-email \
    --in-reply-to=20230707193006.1309662-4-sdf@google.com \
    --to=sdf@google.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bjorn@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=dsahern@kernel.org \
    --cc=haoluo@google.com \
    --cc=hawk@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@intel.com \
    --cc=martin.lau@linux.dev \
    --cc=netdev@vger.kernel.org \
    --cc=song@kernel.org \
    --cc=toke@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