public inbox for [email protected]
 help / color / mirror / Atom feed
From: David Wei <[email protected]>
To: [email protected], [email protected]
Cc: Jens Axboe <[email protected]>,
	Pavel Begunkov <[email protected]>,
	Jakub Kicinski <[email protected]>, Paolo Abeni <[email protected]>,
	"David S. Miller" <[email protected]>,
	Eric Dumazet <[email protected]>,
	Jesper Dangaard Brouer <[email protected]>,
	David Ahern <[email protected]>,
	Mina Almasry <[email protected]>,
	Stanislav Fomichev <[email protected]>,
	Joe Damato <[email protected]>,
	Pedro Tammela <[email protected]>
Subject: [PATCH v7 10/15] io_uring/zcrx: add io_zcrx_area
Date: Tue, 29 Oct 2024 16:05:13 -0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

From: David Wei <[email protected]>

Add io_zcrx_area that represents a region of userspace memory that is
used for zero copy. During ifq registration, userspace passes in the
uaddr and len of userspace memory, which is then pinned by the kernel.
Each net_iov is mapped to one of these pages.

The freelist is a spinlock protected list that keeps track of all the
net_iovs/pages that aren't used.

For now, there is only one area per ifq and area registration happens
implicitly as part of ifq registration. There is no API for
adding/removing areas yet. The struct for area registration is there for
future extensibility once we support multiple areas and TCP devmem.

Signed-off-by: Pavel Begunkov <[email protected]>
Signed-off-by: David Wei <[email protected]>
---
 include/uapi/linux/io_uring.h |  9 ++++
 io_uring/rsrc.c               |  2 +-
 io_uring/rsrc.h               |  1 +
 io_uring/zcrx.c               | 93 ++++++++++++++++++++++++++++++++++-
 io_uring/zcrx.h               | 16 ++++++
 5 files changed, 118 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index d398e19f8eea..d43183264dcf 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -874,6 +874,15 @@ struct io_uring_zcrx_offsets {
 	__u64	__resv[2];
 };
 
+struct io_uring_zcrx_area_reg {
+	__u64	addr;
+	__u64	len;
+	__u64	rq_area_token;
+	__u32	flags;
+	__u32	__resv1;
+	__u64	__resv2[2];
+};
+
 /*
  * Argument for IORING_REGISTER_ZCRX_IFQ
  */
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index fa5f27496aef..a6d44d81f1a1 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -86,7 +86,7 @@ static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
 	return 0;
 }
 
-static int io_buffer_validate(struct iovec *iov)
+int io_buffer_validate(struct iovec *iov)
 {
 	unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1);
 
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index c50d4be4aa6d..9cc9b1b320e3 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -83,6 +83,7 @@ int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
 			    unsigned size, unsigned type);
 int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
 			unsigned int size, unsigned int type);
+int io_buffer_validate(struct iovec *iov);
 
 static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
 {
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 4c53fd4f7bb3..a276572fe953 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -10,6 +10,7 @@
 #include "kbuf.h"
 #include "memmap.h"
 #include "zcrx.h"
+#include "rsrc.h"
 
 #define IO_RQ_MAX_ENTRIES		32768
 
@@ -38,6 +39,83 @@ static void io_free_rbuf_ring(struct io_zcrx_ifq *ifq)
 	ifq->rqes = NULL;
 }
 
+static void io_zcrx_free_area(struct io_zcrx_area *area)
+{
+	if (area->freelist)
+		kvfree(area->freelist);
+	if (area->nia.niovs)
+		kvfree(area->nia.niovs);
+	if (area->pages) {
+		unpin_user_pages(area->pages, area->nia.num_niovs);
+		kvfree(area->pages);
+	}
+	kfree(area);
+}
+
+static int io_zcrx_create_area(struct io_ring_ctx *ctx,
+			       struct io_zcrx_ifq *ifq,
+			       struct io_zcrx_area **res,
+			       struct io_uring_zcrx_area_reg *area_reg)
+{
+	struct io_zcrx_area *area;
+	int i, ret, nr_pages;
+	struct iovec iov;
+
+	if (area_reg->flags || area_reg->rq_area_token)
+		return -EINVAL;
+	if (area_reg->__resv1 || area_reg->__resv2[0] || area_reg->__resv2[1])
+		return -EINVAL;
+	if (area_reg->addr & ~PAGE_MASK || area_reg->len & ~PAGE_MASK)
+		return -EINVAL;
+
+	iov.iov_base = u64_to_user_ptr(area_reg->addr);
+	iov.iov_len = area_reg->len;
+	ret = io_buffer_validate(&iov);
+	if (ret)
+		return ret;
+
+	ret = -ENOMEM;
+	area = kzalloc(sizeof(*area), GFP_KERNEL);
+	if (!area)
+		goto err;
+
+	area->pages = io_pin_pages((unsigned long)area_reg->addr, area_reg->len,
+				   &nr_pages);
+	if (IS_ERR(area->pages)) {
+		ret = PTR_ERR(area->pages);
+		area->pages = NULL;
+		goto err;
+	}
+	area->nia.num_niovs = nr_pages;
+
+	area->nia.niovs = kvmalloc_array(nr_pages, sizeof(area->nia.niovs[0]),
+					 GFP_KERNEL | __GFP_ZERO);
+	if (!area->nia.niovs)
+		goto err;
+
+	area->freelist = kvmalloc_array(nr_pages, sizeof(area->freelist[0]),
+					GFP_KERNEL | __GFP_ZERO);
+	if (!area->freelist)
+		goto err;
+
+	for (i = 0; i < nr_pages; i++) {
+		area->freelist[i] = i;
+	}
+
+	area->free_count = nr_pages;
+	area->ifq = ifq;
+	/* we're only supporting one area per ifq for now */
+	area->area_id = 0;
+	area_reg->rq_area_token = (u64)area->area_id << IORING_ZCRX_AREA_SHIFT;
+	spin_lock_init(&area->freelist_lock);
+	*res = area;
+	return 0;
+err:
+	if (area)
+		io_zcrx_free_area(area);
+	return ret;
+}
+
 static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
 {
 	struct io_zcrx_ifq *ifq;
@@ -53,6 +131,9 @@ static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
 
 static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
 {
+	if (ifq->area)
+		io_zcrx_free_area(ifq->area);
+
 	io_free_rbuf_ring(ifq);
 	kfree(ifq);
 }
@@ -60,6 +141,7 @@ static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
 int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 			  struct io_uring_zcrx_ifq_reg __user *arg)
 {
+	struct io_uring_zcrx_area_reg area;
 	struct io_uring_zcrx_ifq_reg reg;
 	struct io_zcrx_ifq *ifq;
 	size_t ring_sz, rqes_sz;
@@ -91,7 +173,7 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 	}
 	reg.rq_entries = roundup_pow_of_two(reg.rq_entries);
 
-	if (!reg.area_ptr)
+	if (copy_from_user(&area, u64_to_user_ptr(reg.area_ptr), sizeof(area)))
 		return -EFAULT;
 
 	ifq = io_zcrx_ifq_alloc(ctx);
@@ -102,6 +184,10 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 	if (ret)
 		goto err;
 
+	ret = io_zcrx_create_area(ctx, ifq, &ifq->area, &area);
+	if (ret)
+		goto err;
+
 	ifq->rq_entries = reg.rq_entries;
 	ifq->if_rxq = reg.if_rxq;
 
@@ -116,7 +202,10 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 		ret = -EFAULT;
 		goto err;
 	}
-
+	if (copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) {
+		ret = -EFAULT;
+		goto err;
+	}
 	ctx->ifq = ifq;
 	return 0;
 err:
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index 1f76eecac5fd..a8db61498c67 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -3,10 +3,26 @@
 #define IOU_ZC_RX_H
 
 #include <linux/io_uring_types.h>
+#include <net/page_pool/types.h>
+
+struct io_zcrx_area {
+	struct net_iov_area	nia;
+	struct io_zcrx_ifq	*ifq;
+
+	u16			area_id;
+	struct page		**pages;
+
+	/* freelist */
+	spinlock_t		freelist_lock ____cacheline_aligned_in_smp;
+	u32			free_count;
+	u32			*freelist;
+};
 
 struct io_zcrx_ifq {
 	struct io_ring_ctx		*ctx;
 	struct net_device		*dev;
+	struct io_zcrx_area		*area;
+
 	struct io_uring			*rq_ring;
 	struct io_uring_zcrx_rqe 	*rqes;
 	u32				rq_entries;
-- 
2.43.5


  parent reply	other threads:[~2024-10-29 23:06 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-29 23:05 [PATCH v7 00/15] io_uring zero copy rx David Wei
2024-10-29 23:05 ` [PATCH v7 01/15] net: prefix devmem specific helpers David Wei
2024-10-29 23:05 ` [PATCH v7 02/15] net: generalise net_iov chunk owners David Wei
2024-10-29 23:05 ` [PATCH v7 03/15] net: page_pool: create hooks for custom page providers David Wei
2024-10-29 23:05 ` [PATCH v7 04/15] net: prepare for non devmem TCP memory providers David Wei
2024-10-29 23:05 ` [PATCH v7 05/15] net: page_pool: add ->scrub mem provider callback David Wei
2024-10-29 23:05 ` [PATCH v7 06/15] net: page pool: add helper creating area from pages David Wei
2024-10-29 23:05 ` [PATCH v7 07/15] net: page_pool: introduce page_pool_mp_return_in_cache David Wei
2024-10-29 23:05 ` [PATCH v7 08/15] net: add helper executing custom callback from napi David Wei
2024-10-29 23:05 ` [PATCH v7 09/15] io_uring/zcrx: add interface queue and refill queue David Wei
2024-10-29 23:05 ` David Wei [this message]
2024-10-29 23:05 ` [PATCH v7 11/15] io_uring/zcrx: implement zerocopy receive pp memory provider David Wei
2024-10-29 23:05 ` [PATCH v7 12/15] io_uring/zcrx: add io_recvzc request David Wei
2024-10-29 23:05 ` [PATCH v7 13/15] io_uring/zcrx: set pp memory provider for an rx queue David Wei
2024-10-29 23:05 ` [PATCH v7 14/15] io_uring/zcrx: add copy fallback David Wei
2024-10-29 23:05 ` [PATCH v7 15/15] io_uring/zcrx: throttle receive requests David Wei

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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