From: jszhang@marvell.com (Jisheng Zhang)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH net-next v3 1/4] net: mvneta: avoid getting status from rx_desc as much as possible
Date: Mon, 20 Feb 2017 20:53:41 +0800 [thread overview]
Message-ID: <20170220125344.3555-2-jszhang@marvell.com> (raw)
In-Reply-To: <20170220125344.3555-1-jszhang@marvell.com>
In hot code path mvneta_rx_hwbm(), the rx_desc->status is read twice.
The rx_desc is allocated by dma_alloc_coherent, it's uncacheable if
the device isn't cache-coherent, reading from uncached memory is
fairly slow. So reuse the read out rx_status to avoid the second
reading from uncached memory.
Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
drivers/net/ethernet/marvell/mvneta.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 61dd4462411c..06df72b8da85 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -313,8 +313,8 @@
((addr >= txq->tso_hdrs_phys) && \
(addr < txq->tso_hdrs_phys + txq->size * TSO_HEADER_SIZE))
-#define MVNETA_RX_GET_BM_POOL_ID(rxd) \
- (((rxd)->status & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)
+#define MVNETA_RX_GET_BM_POOL_ID(status) \
+ (((status) & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)
struct mvneta_statistic {
unsigned short offset;
@@ -1900,7 +1900,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
for (i = 0; i < rx_done; i++) {
struct mvneta_rx_desc *rx_desc =
mvneta_rxq_next_desc_get(rxq);
- u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
+ u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc->status);
struct mvneta_bm_pool *bm_pool;
bm_pool = &pp->bm_priv->bm_pools[pool_id];
@@ -2075,7 +2075,7 @@ static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo,
rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
data = (u8 *)(uintptr_t)rx_desc->buf_cookie;
phys_addr = rx_desc->buf_phys_addr;
- pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
+ pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_status);
bm_pool = &pp->bm_priv->bm_pools[pool_id];
if (!mvneta_rxq_desc_is_first_last(rx_status) ||
--
2.11.0
WARNING: multiple messages have this Message-ID (diff)
From: Jisheng Zhang <jszhang@marvell.com>
To: <thomas.petazzoni@free-electrons.com>, <davem@davemloft.net>,
<arnd@arndb.de>, <gregory.clement@free-electrons.com>,
<mw@semihalf.com>
Cc: <linux-arm-kernel@lists.infradead.org>, <netdev@vger.kernel.org>,
<linux-kernel@vger.kernel.org>,
Jisheng Zhang <jszhang@marvell.com>
Subject: [PATCH net-next v3 1/4] net: mvneta: avoid getting status from rx_desc as much as possible
Date: Mon, 20 Feb 2017 20:53:41 +0800 [thread overview]
Message-ID: <20170220125344.3555-2-jszhang@marvell.com> (raw)
In-Reply-To: <20170220125344.3555-1-jszhang@marvell.com>
In hot code path mvneta_rx_hwbm(), the rx_desc->status is read twice.
The rx_desc is allocated by dma_alloc_coherent, it's uncacheable if
the device isn't cache-coherent, reading from uncached memory is
fairly slow. So reuse the read out rx_status to avoid the second
reading from uncached memory.
Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
drivers/net/ethernet/marvell/mvneta.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 61dd4462411c..06df72b8da85 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -313,8 +313,8 @@
((addr >= txq->tso_hdrs_phys) && \
(addr < txq->tso_hdrs_phys + txq->size * TSO_HEADER_SIZE))
-#define MVNETA_RX_GET_BM_POOL_ID(rxd) \
- (((rxd)->status & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)
+#define MVNETA_RX_GET_BM_POOL_ID(status) \
+ (((status) & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)
struct mvneta_statistic {
unsigned short offset;
@@ -1900,7 +1900,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
for (i = 0; i < rx_done; i++) {
struct mvneta_rx_desc *rx_desc =
mvneta_rxq_next_desc_get(rxq);
- u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
+ u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc->status);
struct mvneta_bm_pool *bm_pool;
bm_pool = &pp->bm_priv->bm_pools[pool_id];
@@ -2075,7 +2075,7 @@ static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo,
rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
data = (u8 *)(uintptr_t)rx_desc->buf_cookie;
phys_addr = rx_desc->buf_phys_addr;
- pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
+ pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_status);
bm_pool = &pp->bm_priv->bm_pools[pool_id];
if (!mvneta_rxq_desc_is_first_last(rx_status) ||
--
2.11.0
WARNING: multiple messages have this Message-ID (diff)
From: Jisheng Zhang <jszhang@marvell.com>
To: <thomas.petazzoni@free-electrons.com>, <davem@davemloft.net>,
<arnd@arndb.de>, <gregory.clement@free-electrons.com>,
<mw@semihalf.com>
Cc: Jisheng Zhang <jszhang@marvell.com>,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-arm-kernel@lists.infradead.org
Subject: [PATCH net-next v3 1/4] net: mvneta: avoid getting status from rx_desc as much as possible
Date: Mon, 20 Feb 2017 20:53:41 +0800 [thread overview]
Message-ID: <20170220125344.3555-2-jszhang@marvell.com> (raw)
In-Reply-To: <20170220125344.3555-1-jszhang@marvell.com>
In hot code path mvneta_rx_hwbm(), the rx_desc->status is read twice.
The rx_desc is allocated by dma_alloc_coherent, it's uncacheable if
the device isn't cache-coherent, reading from uncached memory is
fairly slow. So reuse the read out rx_status to avoid the second
reading from uncached memory.
Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
---
drivers/net/ethernet/marvell/mvneta.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 61dd4462411c..06df72b8da85 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -313,8 +313,8 @@
((addr >= txq->tso_hdrs_phys) && \
(addr < txq->tso_hdrs_phys + txq->size * TSO_HEADER_SIZE))
-#define MVNETA_RX_GET_BM_POOL_ID(rxd) \
- (((rxd)->status & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)
+#define MVNETA_RX_GET_BM_POOL_ID(status) \
+ (((status) & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)
struct mvneta_statistic {
unsigned short offset;
@@ -1900,7 +1900,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
for (i = 0; i < rx_done; i++) {
struct mvneta_rx_desc *rx_desc =
mvneta_rxq_next_desc_get(rxq);
- u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
+ u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc->status);
struct mvneta_bm_pool *bm_pool;
bm_pool = &pp->bm_priv->bm_pools[pool_id];
@@ -2075,7 +2075,7 @@ static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo,
rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
data = (u8 *)(uintptr_t)rx_desc->buf_cookie;
phys_addr = rx_desc->buf_phys_addr;
- pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
+ pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_status);
bm_pool = &pp->bm_priv->bm_pools[pool_id];
if (!mvneta_rxq_desc_is_first_last(rx_status) ||
--
2.11.0
next prev parent reply other threads:[~2017-02-20 12:53 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-20 12:53 [PATCH net-next v3 0/4] net: mvneta: improve rx/tx performance Jisheng Zhang
2017-02-20 12:53 ` Jisheng Zhang
2017-02-20 12:53 ` Jisheng Zhang [this message]
2017-02-20 12:53 ` [PATCH net-next v3 1/4] net: mvneta: avoid getting status from rx_desc as much as possible Jisheng Zhang
2017-02-20 12:53 ` Jisheng Zhang
2017-02-20 12:53 ` [PATCH net-next v3 2/4] net: mvneta: avoid getting buf_phys_addr from rx_desc again Jisheng Zhang
2017-02-20 12:53 ` Jisheng Zhang
2017-02-20 12:53 ` [PATCH net-next v3 3/4] net: mvneta: avoid reading from tx_desc as much as possible Jisheng Zhang
2017-02-20 12:53 ` Jisheng Zhang
2017-02-20 12:53 ` [PATCH net-next v3 4/4] net: mvneta: Use cacheable memory to store the rx buffer DMA address Jisheng Zhang
2017-02-20 12:53 ` Jisheng Zhang
2017-02-20 14:21 ` [PATCH net-next v3 0/4] net: mvneta: improve rx/tx performance Gregory CLEMENT
2017-02-20 14:21 ` Gregory CLEMENT
2017-02-21 4:37 ` Jisheng Zhang
2017-02-21 4:37 ` Jisheng Zhang
2017-02-21 4:37 ` Jisheng Zhang
2017-02-21 16:16 ` David Miller
2017-02-21 16:16 ` David Miller
2017-02-21 16:35 ` Marcin Wojtas
2017-02-21 16:35 ` Marcin Wojtas
2017-02-24 11:56 ` Jisheng Zhang
2017-02-24 11:56 ` Jisheng Zhang
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=20170220125344.3555-2-jszhang@marvell.com \
--to=jszhang@marvell.com \
--cc=linux-arm-kernel@lists.infradead.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.