From: Taehee Yoo <ap420073@gmail.com>
To: davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com,
edumazet@google.com, almasrymina@google.com,
netdev@vger.kernel.org, linux-doc@vger.kernel.org,
donald.hunter@gmail.com, corbet@lwn.net,
michael.chan@broadcom.com
Cc: kory.maincent@bootlin.com, andrew@lunn.ch,
maxime.chevallier@bootlin.com, danieller@nvidia.com,
hengqi@linux.alibaba.com, ecree.xilinx@gmail.com,
przemyslaw.kitszel@intel.com, hkallweit1@gmail.com,
ahmed.zaki@intel.com, paul.greenwalt@intel.com,
rrameshbabu@nvidia.com, idosch@nvidia.com,
asml.silence@gmail.com, kaiyuanz@google.com, willemb@google.com,
aleksander.lobakin@intel.com, dw@davidwei.uk,
sridhar.samudrala@intel.com, bcreeley@amd.com,
ap420073@gmail.com
Subject: [PATCH net-next v3 7/7] bnxt_en: add support for device memory tcp
Date: Thu, 3 Oct 2024 16:06:20 +0000 [thread overview]
Message-ID: <20241003160620.1521626-8-ap420073@gmail.com> (raw)
In-Reply-To: <20241003160620.1521626-1-ap420073@gmail.com>
Currently, bnxt_en driver satisfies the requirements of Device memory
TCP, which is tcp-data-split.
So, it implements Device memory TCP for bnxt_en driver.
From now on, the aggregation ring handles netmem_ref instead of page
regardless of the on/off of netmem.
So, for the aggregation ring, memory will be handled with the netmem
page_pool API instead of generic page_pool API.
If Devmem is enabled, netmem_ref is used as-is and if Devmem is not
enabled, netmem_ref will be converted to page and that is used.
Driver recognizes whether the devmem is set or unset based on the
mp_params.mp_priv is not NULL.
Only if devmem is set, it passes PP_FLAG_ALLOW_UNREADABLE_NETMEM.
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
---
v3:
- Patch added
drivers/net/ethernet/broadcom/Kconfig | 1 +
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 98 +++++++++++++++--------
drivers/net/ethernet/broadcom/bnxt/bnxt.h | 2 +-
3 files changed, 66 insertions(+), 35 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 75ca3ddda1f5..f37ff12d4746 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -211,6 +211,7 @@ config BNXT
select FW_LOADER
select LIBCRC32C
select NET_DEVLINK
+ select NET_DEVMEM
select PAGE_POOL
select DIMLIB
select AUXILIARY_BUS
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 872b15842b11..64e07d247f97 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -55,6 +55,7 @@
#include <net/page_pool/helpers.h>
#include <linux/align.h>
#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
#include "bnxt_hsi.h"
#include "bnxt.h"
@@ -863,6 +864,22 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
bnapi->events &= ~BNXT_TX_CMP_EVENT;
}
+static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
+ struct bnxt_rx_ring_info *rxr,
+ unsigned int *offset,
+ gfp_t gfp)
+{
+ netmem_ref netmem;
+
+ netmem = page_pool_alloc_netmem(rxr->page_pool, GFP_ATOMIC);
+ if (!netmem)
+ return 0;
+ *offset = 0;
+
+ *mapping = page_pool_get_dma_addr_netmem(netmem) + *offset;
+ return netmem;
+}
+
static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
struct bnxt_rx_ring_info *rxr,
unsigned int *offset,
@@ -972,21 +989,21 @@ static inline u16 bnxt_find_next_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx)
return next;
}
-static inline int bnxt_alloc_rx_page(struct bnxt *bp,
- struct bnxt_rx_ring_info *rxr,
- u16 prod, gfp_t gfp)
+static inline int bnxt_alloc_rx_netmem(struct bnxt *bp,
+ struct bnxt_rx_ring_info *rxr,
+ u16 prod, gfp_t gfp)
{
struct rx_bd *rxbd =
&rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
struct bnxt_sw_rx_agg_bd *rx_agg_buf;
- struct page *page;
+ netmem_ref netmem;
dma_addr_t mapping;
u16 sw_prod = rxr->rx_sw_agg_prod;
unsigned int offset = 0;
- page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
+ netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, &offset, gfp);
- if (!page)
+ if (!netmem)
return -ENOMEM;
if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
@@ -996,7 +1013,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
- rx_agg_buf->page = page;
+ rx_agg_buf->netmem = netmem;
rx_agg_buf->offset = offset;
rx_agg_buf->mapping = mapping;
rxbd->rx_bd_haddr = cpu_to_le64(mapping);
@@ -1044,7 +1061,7 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
struct rx_agg_cmp *agg;
struct bnxt_sw_rx_agg_bd *cons_rx_buf, *prod_rx_buf;
struct rx_bd *prod_bd;
- struct page *page;
+ netmem_ref netmem;
if (p5_tpa)
agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i);
@@ -1061,11 +1078,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
cons_rx_buf = &rxr->rx_agg_ring[cons];
/* It is possible for sw_prod to be equal to cons, so
- * set cons_rx_buf->page to NULL first.
+ * set cons_rx_buf->netmem to 0 first.
*/
- page = cons_rx_buf->page;
- cons_rx_buf->page = NULL;
- prod_rx_buf->page = page;
+ netmem = cons_rx_buf->netmem;
+ cons_rx_buf->netmem = 0;
+ prod_rx_buf->netmem = netmem;
prod_rx_buf->offset = cons_rx_buf->offset;
prod_rx_buf->mapping = cons_rx_buf->mapping;
@@ -1192,6 +1209,7 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
struct bnxt_cp_ring_info *cpr,
+ struct sk_buff *skb,
struct skb_shared_info *shinfo,
u16 idx, u32 agg_bufs, bool tpa,
struct xdp_buff *xdp)
@@ -1211,7 +1229,7 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
u16 cons, frag_len;
struct rx_agg_cmp *agg;
struct bnxt_sw_rx_agg_bd *cons_rx_buf;
- struct page *page;
+ netmem_ref netmem;
dma_addr_t mapping;
if (p5_tpa)
@@ -1223,9 +1241,15 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT;
cons_rx_buf = &rxr->rx_agg_ring[cons];
- skb_frag_fill_page_desc(frag, cons_rx_buf->page,
- cons_rx_buf->offset, frag_len);
- shinfo->nr_frags = i + 1;
+ if (skb) {
+ skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem,
+ cons_rx_buf->offset, frag_len,
+ BNXT_RX_PAGE_SIZE);
+ } else {
+ skb_frag_fill_page_desc(frag, netmem_to_page(cons_rx_buf->netmem),
+ cons_rx_buf->offset, frag_len);
+ shinfo->nr_frags = i + 1;
+ }
__clear_bit(cons, rxr->rx_agg_bmap);
/* It is possible for bnxt_alloc_rx_page() to allocate
@@ -1233,15 +1257,15 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
* need to clear the cons entry now.
*/
mapping = cons_rx_buf->mapping;
- page = cons_rx_buf->page;
- cons_rx_buf->page = NULL;
+ netmem = cons_rx_buf->netmem;
+ cons_rx_buf->netmem = 0;
- if (xdp && page_is_pfmemalloc(page))
+ if (xdp && page_is_pfmemalloc(netmem_to_page(netmem)))
xdp_buff_set_frag_pfmemalloc(xdp);
- if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) {
+ if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_ATOMIC) != 0) {
--shinfo->nr_frags;
- cons_rx_buf->page = page;
+ cons_rx_buf->netmem = netmem;
/* Update prod since possibly some pages have been
* allocated already.
@@ -1269,7 +1293,7 @@ static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
struct skb_shared_info *shinfo = skb_shinfo(skb);
u32 total_frag_len = 0;
- total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
+ total_frag_len = __bnxt_rx_agg_pages(bp, cpr, skb, shinfo, idx,
agg_bufs, tpa, NULL);
if (!total_frag_len) {
skb_mark_for_recycle(skb);
@@ -1277,9 +1301,6 @@ static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
return NULL;
}
- skb->data_len += total_frag_len;
- skb->len += total_frag_len;
- skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs;
return skb;
}
@@ -1294,7 +1315,7 @@ static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
if (!xdp_buff_has_frags(xdp))
shinfo->nr_frags = 0;
- total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo,
+ total_frag_len = __bnxt_rx_agg_pages(bp, cpr, NULL, shinfo,
idx, agg_bufs, tpa, xdp);
if (total_frag_len) {
xdp_buff_set_frags_flag(xdp);
@@ -3342,15 +3363,15 @@ static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info
for (i = 0; i < max_idx; i++) {
struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i];
- struct page *page = rx_agg_buf->page;
+ netmem_ref netmem = rx_agg_buf->netmem;
- if (!page)
+ if (!netmem)
continue;
- rx_agg_buf->page = NULL;
+ rx_agg_buf->netmem = 0;
__clear_bit(i, rxr->rx_agg_bmap);
- page_pool_recycle_direct(rxr->page_pool, page);
+ page_pool_put_full_netmem(rxr->page_pool, netmem, true);
}
}
@@ -3608,9 +3629,11 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
struct bnxt_rx_ring_info *rxr,
+ int queue_idx,
int numa_node)
{
struct page_pool_params pp = { 0 };
+ struct netdev_rx_queue *rxq;
pp.pool_size = bp->rx_agg_ring_size;
if (BNXT_RX_PAGE_MODE(bp))
@@ -3621,8 +3644,15 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
pp.dev = &bp->pdev->dev;
pp.dma_dir = bp->rx_dir;
pp.max_len = PAGE_SIZE;
- pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+ pp.order = 0;
+
+ rxq = __netif_get_rx_queue(bp->dev, queue_idx);
+ if (rxq->mp_params.mp_priv)
+ pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_ALLOW_UNREADABLE_NETMEM;
+ else
+ pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+ pp.queue_idx = queue_idx;
rxr->page_pool = page_pool_create(&pp);
if (IS_ERR(rxr->page_pool)) {
int err = PTR_ERR(rxr->page_pool);
@@ -3655,7 +3685,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
cpu_node = cpu_to_node(cpu);
netdev_dbg(bp->dev, "Allocating page pool for rx_ring[%d] on numa_node: %d\n",
i, cpu_node);
- rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node);
+ rc = bnxt_alloc_rx_page_pool(bp, rxr, i, cpu_node);
if (rc)
return rc;
@@ -4154,7 +4184,7 @@ static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp,
prod = rxr->rx_agg_prod;
for (i = 0; i < bp->rx_agg_ring_size; i++) {
- if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_KERNEL)) {
+ if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_KERNEL)) {
netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n",
ring_nr, i, bp->rx_ring_size);
break;
@@ -15063,7 +15093,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
clone->rx_sw_agg_prod = 0;
clone->rx_next_cons = 0;
- rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid);
+ rc = bnxt_alloc_rx_page_pool(bp, clone, idx, rxr->page_pool->p.nid);
if (rc)
return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 48f390519c35..3cf57a3c7664 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -895,7 +895,7 @@ struct bnxt_sw_rx_bd {
};
struct bnxt_sw_rx_agg_bd {
- struct page *page;
+ netmem_ref netmem;
unsigned int offset;
dma_addr_t mapping;
};
--
2.34.1
next prev parent reply other threads:[~2024-10-03 16:07 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-03 16:06 [PATCH net-next v3 0/7] bnxt_en: implement device memory TCP for bnxt Taehee Yoo
2024-10-03 16:06 ` [PATCH net-next v3 1/7] bnxt_en: add support for rx-copybreak ethtool command Taehee Yoo
2024-10-03 16:57 ` Brett Creeley
2024-10-03 17:15 ` Taehee Yoo
2024-10-03 17:13 ` Michael Chan
2024-10-03 17:22 ` Taehee Yoo
2024-10-03 17:43 ` Michael Chan
2024-10-03 18:28 ` Taehee Yoo
2024-10-03 18:34 ` Andrew Lunn
2024-10-05 6:29 ` Taehee Yoo
2024-10-08 18:10 ` Jakub Kicinski
2024-10-08 19:38 ` Michael Chan
2024-10-08 19:53 ` Jakub Kicinski
2024-10-08 20:35 ` Michael Chan
2024-10-03 16:06 ` [PATCH net-next v3 2/7] bnxt_en: add support for tcp-data-split " Taehee Yoo
2024-10-08 18:19 ` Jakub Kicinski
2024-10-09 13:54 ` Taehee Yoo
2024-10-09 15:28 ` Jakub Kicinski
2024-10-09 17:47 ` Taehee Yoo
2024-10-31 17:34 ` Taehee Yoo
2024-10-31 23:56 ` Jakub Kicinski
2024-11-01 17:11 ` Taehee Yoo
2024-10-03 16:06 ` [PATCH net-next v3 3/7] net: ethtool: add support for configuring tcp-data-split-thresh Taehee Yoo
2024-10-03 18:25 ` Mina Almasry
2024-10-03 19:33 ` Taehee Yoo
2024-10-04 1:47 ` Mina Almasry
2024-10-05 6:11 ` Taehee Yoo
2024-10-08 18:33 ` Jakub Kicinski
2024-10-09 14:25 ` Taehee Yoo
2024-10-09 15:46 ` Jakub Kicinski
2024-10-09 17:49 ` Taehee Yoo
2024-10-03 16:06 ` [PATCH net-next v3 4/7] bnxt_en: add support for tcp-data-split-thresh ethtool command Taehee Yoo
2024-10-03 18:13 ` Brett Creeley
2024-10-03 19:13 ` Taehee Yoo
2024-10-08 18:35 ` Jakub Kicinski
2024-10-09 14:31 ` Taehee Yoo
2024-10-03 16:06 ` [PATCH net-next v3 5/7] net: devmem: add ring parameter filtering Taehee Yoo
2024-10-03 18:29 ` Mina Almasry
2024-10-04 3:57 ` Taehee Yoo
2024-10-03 18:35 ` Brett Creeley
2024-10-03 18:49 ` Mina Almasry
2024-10-08 19:28 ` Jakub Kicinski
2024-10-09 14:35 ` Taehee Yoo
2024-10-04 4:01 ` Taehee Yoo
2024-10-03 16:06 ` [PATCH net-next v3 6/7] net: ethtool: " Taehee Yoo
2024-10-03 18:32 ` Mina Almasry
2024-10-03 19:35 ` Taehee Yoo
2024-10-03 16:06 ` Taehee Yoo [this message]
2024-10-03 18:43 ` [PATCH net-next v3 7/7] bnxt_en: add support for device memory tcp Mina Almasry
2024-10-04 10:34 ` Taehee Yoo
2024-10-08 2:57 ` David Wei
2024-10-09 15:02 ` Taehee Yoo
2024-10-08 19:50 ` Jakub Kicinski
2024-10-09 15:37 ` Taehee Yoo
2024-10-10 0:01 ` Jakub Kicinski
2024-10-10 17:44 ` Mina Almasry
2024-10-11 1:34 ` Jakub Kicinski
2024-10-11 17:33 ` Mina Almasry
2024-10-11 23:42 ` Jason Gunthorpe
2024-10-14 22:38 ` Mina Almasry
2024-10-15 0:16 ` Jakub Kicinski
2024-10-15 1:10 ` Mina Almasry
2024-10-15 12:44 ` Jason Gunthorpe
2024-10-18 8:25 ` Mina Almasry
2024-10-19 13:55 ` Taehee Yoo
2024-10-15 14:29 ` Pavel Begunkov
2024-10-15 17:38 ` David Wei
2024-10-05 3:48 ` kernel test robot
2024-10-08 2:45 ` David Wei
2024-10-08 3:54 ` Taehee Yoo
2024-10-08 3:58 ` Taehee Yoo
2024-10-16 20:17 ` [PATCH net-next v3 0/7] bnxt_en: implement device memory TCP for bnxt Stanislav Fomichev
2024-10-17 8:58 ` Taehee Yoo
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=20241003160620.1521626-8-ap420073@gmail.com \
--to=ap420073@gmail.com \
--cc=ahmed.zaki@intel.com \
--cc=aleksander.lobakin@intel.com \
--cc=almasrymina@google.com \
--cc=andrew@lunn.ch \
--cc=asml.silence@gmail.com \
--cc=bcreeley@amd.com \
--cc=corbet@lwn.net \
--cc=danieller@nvidia.com \
--cc=davem@davemloft.net \
--cc=donald.hunter@gmail.com \
--cc=dw@davidwei.uk \
--cc=ecree.xilinx@gmail.com \
--cc=edumazet@google.com \
--cc=hengqi@linux.alibaba.com \
--cc=hkallweit1@gmail.com \
--cc=idosch@nvidia.com \
--cc=kaiyuanz@google.com \
--cc=kory.maincent@bootlin.com \
--cc=kuba@kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=maxime.chevallier@bootlin.com \
--cc=michael.chan@broadcom.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=paul.greenwalt@intel.com \
--cc=przemyslaw.kitszel@intel.com \
--cc=rrameshbabu@nvidia.com \
--cc=sridhar.samudrala@intel.com \
--cc=willemb@google.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).