BPF List
 help / color / mirror / Atom feed
From: Alexander Lobakin <aleksander.lobakin@intel.com>
To: Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: "Alexander Lobakin" <aleksander.lobakin@intel.com>,
	"Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Andrii Nakryiko" <andrii@kernel.org>,
	"Jose E. Marchesi" <jose.marchesi@oracle.com>,
	"Toke Høiland-Jørgensen" <toke@redhat.com>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>,
	"Maciej Fijalkowski" <maciej.fijalkowski@intel.com>,
	"Przemek Kitszel" <przemyslaw.kitszel@intel.com>,
	"Jason Baron" <jbaron@akamai.com>,
	"Casey Schaufler" <casey@schaufler-ca.com>,
	"Nathan Chancellor" <nathan@kernel.org>,
	bpf@vger.kernel.org, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH net-next 6/7] xsk: add helper to get &xdp_desc's DMA and meta pointer in one go
Date: Wed, 18 Dec 2024 18:44:34 +0100	[thread overview]
Message-ID: <20241218174435.1445282-7-aleksander.lobakin@intel.com> (raw)
In-Reply-To: <20241218174435.1445282-1-aleksander.lobakin@intel.com>

Currently, when you send an XSk frame with metadata, you need to do
the following:

* call external xsk_buff_raw_get_dma();
* call inline xsk_buff_get_metadata(), which calls external
  xsk_buff_raw_get_data() and then do some inline checks.

This effectively means that the following piece:

addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;

is done twice per frame, plus you have 2 external calls per frame, plus
this:

	meta = pool->addrs + addr - pool->tx_metadata_len;
	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))

is always inlined, even if there's no meta or it's invalid.

Add xsk_buff_raw_get_ctx() (xp_raw_get_ctx() to be precise) to do that
in one go. It returns a small structure with 2 fields: DMA address,
filled unconditionally, and metadata pointer, valid only if it's
present. The address correction is performed only once and you also
have only 1 external call per XSk frame, which does all the calculations
and checks outside of your hotpath. You only need to check
`if (ctx.meta)` for the metadata presence.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
 include/net/xdp_sock_drv.h  | 23 +++++++++++++++++++++
 include/net/xsk_buff_pool.h |  8 ++++++++
 net/xdp/xsk_buff_pool.c     | 40 +++++++++++++++++++++++++++++++++++++
 3 files changed, 71 insertions(+)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 86620c818965..7fd1709deef5 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -205,6 +205,23 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return xp_raw_get_data(pool, addr);
 }
 
+/**
+ * xsk_buff_raw_get_ctx - get &xdp_desc context
+ * @pool: XSk buff pool desc address belongs to
+ * @addr: desc address (from userspace)
+ *
+ * Wrapper for xp_raw_get_ctx() to be used in drivers, see its kdoc for
+ * details.
+ *
+ * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
+ * pointer, if it is present and valid (initialized to %NULL otherwise).
+ */
+static inline struct xdp_desc_ctx
+xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return xp_raw_get_ctx(pool, addr);
+}
+
 #define XDP_TXMD_FLAGS_VALID ( \
 		XDP_TXMD_FLAGS_TIMESTAMP | \
 		XDP_TXMD_FLAGS_CHECKSUM | \
@@ -402,6 +419,12 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return NULL;
 }
 
+static inline struct xdp_desc_ctx
+xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return (struct xdp_desc_ctx){ };
+}
+
 static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
 {
 	return false;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 50779406bc2d..1dcd4d71468a 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -141,6 +141,14 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max);
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count);
 void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr);
 dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr);
+
+struct xdp_desc_ctx {
+	dma_addr_t dma;
+	struct xsk_tx_metadata *meta;
+};
+
+struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr);
+
 static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb)
 {
 	return xskb->dma;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 1f7975b49657..4ea742da304d 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -714,3 +714,43 @@ dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
 		(addr & ~PAGE_MASK);
 }
 EXPORT_SYMBOL(xp_raw_get_dma);
+
+/**
+ * xp_raw_get_ctx - get &xdp_desc context
+ * @pool: XSk buff pool desc address belongs to
+ * @addr: desc address (from userspace)
+ *
+ * Helper for getting desc's DMA address and metadata pointer, if present.
+ * Saves one call on hotpath, double calculation of the actual address,
+ * and inline checks for metadata presence and sanity.
+ * Please use xsk_buff_raw_get_ctx() in drivers instead.
+ *
+ * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
+ * pointer, if it is present and valid (initialized to %NULL otherwise).
+ */
+struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+{
+	struct xsk_tx_metadata *meta;
+	struct xdp_desc_ctx ret;
+
+	addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
+	ret = (typeof(ret)){
+		/* Same logic as in xp_raw_get_dma() */
+		.dma	= (pool->dma_pages[addr >> PAGE_SHIFT] &
+			   ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK),
+	};
+
+	if (!pool->tx_metadata_len)
+		goto out;
+
+	/* Same logic as in xp_raw_get_data() + xsk_buff_get_metadata() */
+	meta = pool->addrs + addr - pool->tx_metadata_len;
+	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))
+		goto out;
+
+	ret.meta = meta;
+
+out:
+	return ret;
+}
+EXPORT_SYMBOL(xp_raw_get_ctx);
-- 
2.47.1


  parent reply	other threads:[~2024-12-18 17:45 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-18 17:44 [PATCH net-next 0/7] xdp: a fistful of generic changes pt. III Alexander Lobakin
2024-12-18 17:44 ` [PATCH net-next 1/7] page_pool: add page_pool_dev_alloc_netmem() Alexander Lobakin
2024-12-18 17:44 ` [PATCH net-next 2/7] xdp: add generic xdp_buff_add_frag() Alexander Lobakin
2024-12-18 17:44 ` [PATCH net-next 3/7] xdp: add generic xdp_build_skb_from_buff() Alexander Lobakin
2024-12-18 17:44 ` [PATCH net-next 4/7] xsk: make xsk_buff_add_frag() really add the frag via __xdp_buff_add_frag() Alexander Lobakin
2024-12-18 17:44 ` [PATCH net-next 5/7] xsk: add generic XSk &xdp_buff -> skb conversion Alexander Lobakin
2024-12-18 17:44 ` Alexander Lobakin [this message]
2024-12-20  3:50   ` [PATCH net-next 6/7] xsk: add helper to get &xdp_desc's DMA and meta pointer in one go Jakub Kicinski
2024-12-20 15:58     ` Alexander Lobakin
2024-12-20 17:26       ` Jakub Kicinski
2024-12-23 13:50         ` Alexander Lobakin
2024-12-18 17:44 ` [PATCH net-next 7/7] unroll: add generic loop unroll helpers Alexander Lobakin
2024-12-20  4:00 ` [PATCH net-next 0/7] xdp: a fistful of generic changes pt. III patchwork-bot+netdevbpf

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=20241218174435.1445282-7-aleksander.lobakin@intel.com \
    --to=aleksander.lobakin@intel.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=casey@schaufler-ca.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=jbaron@akamai.com \
    --cc=john.fastabend@gmail.com \
    --cc=jose.marchesi@oracle.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@intel.com \
    --cc=nathan@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=przemyslaw.kitszel@intel.com \
    --cc=toke@redhat.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