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]>,
Willem de Bruijn <[email protected]>,
Dragos Tatulea <[email protected]>
Subject: [PATCH 19/20] bnxt: use data pool
Date: Tue, 7 Nov 2023 13:40:44 -0800 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
The BNXT driver is modified to use data pool in order to support ZC Rx.
A setup function bnxt_zc_rx is added that is called on XDP_SETUP_ZC_RX
XDP command which initialises a data_pool in a netdev_rx_queue.
Co-developed-by: Pavel Begunkov <[email protected]>
Signed-off-by: Pavel Begunkov <[email protected]>
Signed-off-by: David Wei <[email protected]>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 61 ++++++++++++++++---
drivers/net/ethernet/broadcom/bnxt/bnxt.h | 5 ++
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 3 +
include/net/netdev_rx_queue.h | 2 +
4 files changed, 61 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ca1088f7107e..2787c1b474db 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -55,6 +55,8 @@
#include <net/page_pool/helpers.h>
#include <linux/align.h>
#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+#include <net/data_pool.h>
#include "bnxt_hsi.h"
#include "bnxt.h"
@@ -798,13 +800,7 @@ static struct page *__bnxt_alloc_rx_64k_page(struct bnxt *bp, dma_addr_t *mappin
if (!page)
return NULL;
- *mapping = dma_map_page_attrs(&bp->pdev->dev, page, offset,
- BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
- DMA_ATTR_WEAK_ORDERING);
- if (dma_mapping_error(&bp->pdev->dev, *mapping)) {
- page_pool_recycle_direct(rxr->page_pool, page);
- return NULL;
- }
+ *mapping = page_pool_get_dma_addr(page);
if (page_offset)
*page_offset = offset;
@@ -824,13 +820,13 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
page = page_pool_dev_alloc_frag(rxr->page_pool, offset,
BNXT_RX_PAGE_SIZE);
} else {
- page = page_pool_dev_alloc_pages(rxr->page_pool);
+ page = data_pool_alloc_page(&rxr->rx_dp);
*offset = 0;
}
if (!page)
return NULL;
- *mapping = page_pool_get_dma_addr(page) + *offset;
+ *mapping = data_pool_get_dma_addr(&rxr->rx_dp, page) + *offset;
return page;
}
@@ -1816,6 +1812,8 @@ static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
return;
}
skb_record_rx_queue(skb, bnapi->index);
+ if (bnapi->rx_ring->rx_dp.zc_uarg)
+ skb_zcopy_init(skb, bnapi->rx_ring->rx_dp.zc_uarg);
skb_mark_for_recycle(skb);
napi_gro_receive(&bnapi->napi, skb);
}
@@ -3100,7 +3098,7 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr)
rx_agg_buf->page = NULL;
__clear_bit(i, rxr->rx_agg_bmap);
- page_pool_recycle_direct(rxr->page_pool, page);
+ data_pool_put_page(&rxr->rx_dp, page);
}
skip_rx_agg_free:
@@ -3305,6 +3303,8 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
page_pool_destroy(rxr->page_pool);
rxr->page_pool = NULL;
+ rxr->rx_dp.page_pool = NULL;
+ rxr->rx_dp.zc_ifq = NULL;
kfree(rxr->rx_agg_bmap);
rxr->rx_agg_bmap = NULL;
@@ -3333,6 +3333,8 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
if (PAGE_SIZE > BNXT_RX_PAGE_SIZE)
pp.flags |= PP_FLAG_PAGE_FRAG;
+ pp.flags |= PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+ pp.max_len = PAGE_SIZE;
rxr->page_pool = page_pool_create(&pp);
if (IS_ERR(rxr->page_pool)) {
@@ -3341,6 +3343,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
rxr->page_pool = NULL;
return err;
}
+ rxr->rx_dp.page_pool = rxr->page_pool;
return 0;
}
@@ -3803,6 +3806,7 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr)
{
struct bnxt_rx_ring_info *rxr;
struct bnxt_ring_struct *ring;
+ struct netdev_rx_queue *rxq;
u32 type;
type = (bp->rx_buf_use_size << RX_BD_LEN_SHIFT) |
@@ -3831,6 +3835,12 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr)
bnxt_init_rxbd_pages(ring, type);
}
+ rxq = __netif_get_rx_queue(bp->dev, ring_nr);
+ if (rxq->data_pool.zc_ifq) {
+ rxr->rx_dp.zc_ifq = rxq->data_pool.zc_ifq;
+ rxr->rx_dp.zc_uarg = rxq->data_pool.zc_uarg;
+ }
+
return bnxt_alloc_one_rx_ring(bp, ring_nr);
}
@@ -13974,6 +13984,37 @@ void bnxt_print_device_info(struct bnxt *bp)
pcie_print_link_status(bp->pdev);
}
+int bnxt_zc_rx(struct bnxt *bp, struct netdev_bpf *xdp)
+{
+ unsigned ifq_idx = xdp->zc_rx.queue_id;
+
+ if (ifq_idx >= bp->rx_nr_rings)
+ return -EINVAL;
+
+ bnxt_rtnl_lock_sp(bp);
+ if (netif_running(bp->dev)) {
+ struct netdev_rx_queue *rxq;
+ int rc, napi_id;
+
+ bnxt_ulp_stop(bp);
+ bnxt_close_nic(bp, true, false);
+
+ rxq = __netif_get_rx_queue(bp->dev, ifq_idx);
+ rxq->data_pool.zc_ifq = xdp->zc_rx.ifq;
+ rxq->data_pool.zc_uarg = xdp->zc_rx.uarg;
+
+ rc = bnxt_open_nic(bp, true, false);
+ bnxt_ulp_start(bp, rc);
+
+ if (xdp->zc_rx.ifq) {
+ napi_id = bp->bnapi[ifq_idx]->napi.napi_id;
+ io_zc_rx_set_napi(xdp->zc_rx.ifq, napi_id);
+ }
+ }
+ bnxt_rtnl_unlock_sp(bp);
+ return 0;
+}
+
static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
struct net_device *dev;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index d95d0ca91f3f..7f3b03fa5960 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -33,6 +33,7 @@
#ifdef CONFIG_TEE_BNXT_FW
#include <linux/firmware/broadcom/tee_bnxt_fw.h>
#endif
+#include <net/data_pool.h>
extern struct list_head bnxt_block_cb_list;
@@ -946,6 +947,7 @@ struct bnxt_rx_ring_info {
struct bnxt_ring_struct rx_agg_ring_struct;
struct xdp_rxq_info xdp_rxq;
struct page_pool *page_pool;
+ struct data_pool rx_dp;
};
struct bnxt_rx_sw_stats {
@@ -2485,4 +2487,7 @@ int bnxt_get_port_parent_id(struct net_device *dev,
void bnxt_dim_work(struct work_struct *work);
int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi);
void bnxt_print_device_info(struct bnxt *bp);
+
+int bnxt_zc_rx(struct bnxt *bp, struct netdev_bpf *xdp);
+
#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 96f5ca778c67..b7ef2e551334 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -465,6 +465,9 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
case XDP_SETUP_PROG:
rc = bnxt_xdp_set(bp, xdp->prog);
break;
+ case XDP_SETUP_ZC_RX:
+ return bnxt_zc_rx(bp, xdp);
+ break;
default:
rc = -EINVAL;
break;
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index cdcafb30d437..1b2944e61e19 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -6,6 +6,7 @@
#include <linux/netdevice.h>
#include <linux/sysfs.h>
#include <net/xdp.h>
+#include <net/data_pool.h>
/* This structure contains an instance of an RX queue. */
struct netdev_rx_queue {
@@ -18,6 +19,7 @@ struct netdev_rx_queue {
struct net_device *dev;
netdevice_tracker dev_tracker;
+ struct data_pool data_pool;
#ifdef CONFIG_XDP_SOCKETS
struct xsk_buff_pool *pool;
#endif
--
2.39.3
next prev parent reply other threads:[~2023-11-07 21:41 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-07 21:40 [RFC PATCH v2 00/20] Zero copy Rx using io_uring David Wei
2023-11-07 21:40 ` [PATCH 01/20] io_uring: add interface queue David Wei
2023-11-07 21:40 ` [PATCH 02/20] io_uring: add mmap support for shared ifq ringbuffers David Wei
2023-11-07 21:40 ` [PATCH 03/20] netdev: add XDP_SETUP_ZC_RX command David Wei
2023-11-07 21:40 ` [PATCH 04/20] io_uring: setup ZC for an Rx queue when registering an ifq David Wei
2023-11-07 21:40 ` [PATCH 05/20] io_uring/zcrx: implement socket registration David Wei
2023-11-07 21:40 ` [PATCH 06/20] io_uring: add ZC buf and pool David Wei
2023-11-07 21:40 ` [PATCH 07/20] io_uring: add ZC pool API David Wei
2023-11-07 21:40 ` [PATCH 08/20] skbuff: add SKBFL_FIXED_FRAG and skb_fixed() David Wei
2023-11-07 21:40 ` [PATCH 09/20] io_uring: allocate a uarg for freeing zero copy skbs David Wei
2023-11-07 21:40 ` [PATCH 10/20] io_uring: delay ZC pool destruction David Wei
2023-11-07 21:40 ` [PATCH 11/20] net: add data pool David Wei
2023-11-07 21:40 ` [PATCH 12/20] io_uring: add io_recvzc request David Wei
2023-11-07 21:40 ` [PATCH 13/20] io_uring/zcrx: propagate ifq down the stack David Wei
2023-11-07 21:40 ` [PATCH 14/20] io_uring/zcrx: introduce io_zc_get_rbuf_cqe David Wei
2023-11-07 21:40 ` [PATCH 15/20] io_uring/zcrx: add copy fallback David Wei
2023-11-07 21:40 ` [PATCH 16/20] net: execute custom callback from napi David Wei
2023-11-07 21:40 ` [PATCH 17/20] io_uring/zcrx: copy fallback to ring buffers David Wei
2023-11-07 21:40 ` [PATCH 18/20] veth: add support for io_uring zc rx David Wei
2023-11-07 21:40 ` David Wei [this message]
2023-11-07 21:40 ` [PATCH 20/20] io_uring/zcrx: add multi socket support per Rx queue 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] \
/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