From: xiaohui.xin@intel.com
To: netdev@vger.kernel.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, mst@redhat.com, mingo@elte.hu,
davem@davemloft.net, herbert@gondor.apana.org.au,
jdike@linux.intel.com
Cc: Xin Xiaohui <xiaohui.xin@intel.com>
Subject: [PATCH v14 16/17] An example how to modifiy NIC driver to use napi_gro_frags() interface
Date: Thu, 4 Nov 2010 17:05:12 +0800 [thread overview]
Message-ID: <d64cc2e937a784d64b79bddef50f8700343e8691.1288860478.git.xiaohui.xin@intel.com> (raw)
In-Reply-To: <1288861513-5707-1-git-send-email-xiaohui.xin@intel.com>
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1288860477.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
This example is made on ixgbe driver.
It provides API is_rx_buffer_mapped_as_page() to indicate
if the driver use napi_gro_frags() interface or not.
The example allocates 2 pages for DMA for one ring descriptor
using netdev_alloc_page(). When packets is coming, using
napi_gro_frags() to allocate skb and to receive the packets.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
---
drivers/net/ixgbe/ixgbe.h | 3 +
drivers/net/ixgbe/ixgbe_main.c | 163 +++++++++++++++++++++++++++++++---------
2 files changed, 131 insertions(+), 35 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 9e15eb9..89367ca 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -131,6 +131,9 @@ struct ixgbe_rx_buffer {
struct page *page;
dma_addr_t page_dma;
unsigned int page_offset;
+ u16 mapped_as_page;
+ struct page *page_skb;
+ unsigned int page_skb_offset;
};
struct ixgbe_queue_stats {
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index e32af43..a4a5263 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -1029,6 +1029,12 @@ static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw,
IXGBE_WRITE_REG(hw, IXGBE_RDT(rx_ring->reg_idx), val);
}
+static bool is_rx_buffer_mapped_as_page(struct ixgbe_rx_buffer *bi,
+ struct net_device *dev)
+{
+ return true;
+}
+
/**
* ixgbe_alloc_rx_buffers - Replace used receive buffers; packet split
* @adapter: address of board private structure
@@ -1045,13 +1051,17 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
i = rx_ring->next_to_use;
bi = &rx_ring->rx_buffer_info[i];
+
while (cleaned_count--) {
rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
+ bi->mapped_as_page =
+ is_rx_buffer_mapped_as_page(bi, adapter->netdev);
+
if (!bi->page_dma &&
(rx_ring->flags & IXGBE_RING_RX_PS_ENABLED)) {
if (!bi->page) {
- bi->page = alloc_page(GFP_ATOMIC);
+ bi->page = netdev_alloc_page(adapter->netdev);
if (!bi->page) {
adapter->alloc_rx_page_failed++;
goto no_buffers;
@@ -1068,7 +1078,7 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
DMA_FROM_DEVICE);
}
- if (!bi->skb) {
+ if (!bi->mapped_as_page && !bi->skb) {
struct sk_buff *skb;
/* netdev_alloc_skb reserves 32 bytes up front!! */
uint bufsz = rx_ring->rx_buf_len + SMP_CACHE_BYTES;
@@ -1088,6 +1098,19 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
}
+
+ if (bi->mapped_as_page && !bi->page_skb) {
+ bi->page_skb = netdev_alloc_page(adapter->netdev);
+ if (!bi->page_skb) {
+ adapter->alloc_rx_page_failed++;
+ goto no_buffers;
+ }
+ bi->page_skb_offset = 0;
+ bi->dma = dma_map_page(&pdev->dev, bi->page_skb,
+ bi->page_skb_offset,
+ (PAGE_SIZE / 2),
+ PCI_DMA_FROMDEVICE);
+ }
/* Refresh the desc even if buffer_addrs didn't change because
* each write-back erases this info. */
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
@@ -1165,6 +1188,13 @@ struct ixgbe_rsc_cb {
bool delay_unmap;
};
+static bool is_no_buffer(struct ixgbe_rx_buffer *rx_buffer_info)
+{
+ return (!rx_buffer_info->skb ||
+ !rx_buffer_info->page_skb) &&
+ !rx_buffer_info->page;
+}
+
#define IXGBE_RSC_CB(skb) ((struct ixgbe_rsc_cb *)(skb)->cb)
static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
@@ -1174,6 +1204,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_adapter *adapter = q_vector->adapter;
struct net_device *netdev = adapter->netdev;
struct pci_dev *pdev = adapter->pdev;
+ struct napi_struct *napi = &q_vector->napi;
union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
struct ixgbe_rx_buffer *rx_buffer_info, *next_buffer;
struct sk_buff *skb;
@@ -1211,32 +1242,68 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
len = le16_to_cpu(rx_desc->wb.upper.length);
}
+ if (is_no_buffer(rx_buffer_info))
+ break;
cleaned = true;
- skb = rx_buffer_info->skb;
- prefetch(skb->data);
- rx_buffer_info->skb = NULL;
- if (rx_buffer_info->dma) {
- if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
- (!(staterr & IXGBE_RXD_STAT_EOP)) &&
- (!(skb->prev))) {
- /*
- * When HWRSC is enabled, delay unmapping
- * of the first packet. It carries the
- * header information, HW may still
- * access the header after the writeback.
- * Only unmap it when EOP is reached
- */
- IXGBE_RSC_CB(skb)->delay_unmap = true;
- IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
- } else {
- dma_unmap_single(&pdev->dev,
- rx_buffer_info->dma,
- rx_ring->rx_buf_len,
- DMA_FROM_DEVICE);
+ if (!rx_buffer_info->mapped_as_page) {
+ skb = rx_buffer_info->skb;
+ prefetch(skb->data);
+ rx_buffer_info->skb = NULL;
+
+ if (rx_buffer_info->dma) {
+ if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
+ (!(staterr & IXGBE_RXD_STAT_EOP)) &&
+ (!(skb->prev))) {
+ /*
+ * When HWRSC is enabled, delay unmapping
+ * of the first packet. It carries the
+ * header information, HW may still
+ * access the header after the writeback.
+ * Only unmap it when EOP is reached
+ */
+ IXGBE_RSC_CB(skb)->delay_unmap = true;
+ IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
+ } else
+ dma_unmap_single(&pdev->dev,
+ rx_buffer_info->dma,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ rx_buffer_info->dma = 0;
+ skb_put(skb, len);
+ }
+ } else {
+ skb = napi_get_frags(napi);
+ prefetch(rx_buffer_info->page_skb_offset);
+ rx_buffer_info->skb = NULL;
+ if (rx_buffer_info->dma) {
+ if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
+ (!(staterr & IXGBE_RXD_STAT_EOP)) &&
+ (!(skb->prev))) {
+ /*
+ * When HWRSC is enabled, delay unmapping
+ * of the first packet. It carries the
+ * header information, HW may still
+ * access the header after the writeback.
+ * Only unmap it when EOP is reached
+ */
+ IXGBE_RSC_CB(skb)->delay_unmap = true;
+ IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
+ } else
+ dma_unmap_page(&pdev->dev, rx_buffer_info->dma,
+ PAGE_SIZE / 2,
+ PCI_DMA_FROMDEVICE);
+ rx_buffer_info->dma = 0;
+ skb_fill_page_desc(skb,
+ skb_shinfo(skb)->nr_frags,
+ rx_buffer_info->page_skb,
+ rx_buffer_info->page_skb_offset,
+ len);
+ rx_buffer_info->page_skb = NULL;
+ skb->len += len;
+ skb->data_len += len;
+ skb->truesize += len;
}
- rx_buffer_info->dma = 0;
- skb_put(skb, len);
}
if (upper_len) {
@@ -1283,10 +1350,16 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
skb = ixgbe_transform_rsc_queue(skb, &(rx_ring->rsc_count));
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
if (IXGBE_RSC_CB(skb)->delay_unmap) {
- dma_unmap_single(&pdev->dev,
- IXGBE_RSC_CB(skb)->dma,
- rx_ring->rx_buf_len,
- DMA_FROM_DEVICE);
+ if (!rx_buffer_info->mapped_as_page)
+ dma_unmap_single(&pdev->dev,
+ IXGBE_RSC_CB(skb)->dma,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ else
+ dma_unmap_page(&pdev->dev,
+ IXGBE_RSC_CB(skb)->dma,
+ PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
IXGBE_RSC_CB(skb)->dma = 0;
IXGBE_RSC_CB(skb)->delay_unmap = false;
}
@@ -1304,6 +1377,11 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
rx_buffer_info->dma = next_buffer->dma;
next_buffer->skb = skb;
next_buffer->dma = 0;
+ if (rx_buffer_info->mapped_as_page) {
+ rx_buffer_info->page_skb =
+ next_buffer->page_skb;
+ next_buffer->page_skb = NULL;
+ }
} else {
skb->next = next_buffer->skb;
skb->next->prev = skb;
@@ -1323,7 +1401,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
total_rx_bytes += skb->len;
total_rx_packets++;
- skb->protocol = eth_type_trans(skb, adapter->netdev);
+ if (!rx_buffer_info->mapped_as_page)
+ skb->protocol = eth_type_trans(skb, adapter->netdev);
#ifdef IXGBE_FCOE
/* if ddp, not passing to ULD unless for FCP_RSP or error */
if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
@@ -1332,7 +1411,14 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
goto next_desc;
}
#endif /* IXGBE_FCOE */
- ixgbe_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc);
+
+ if (!rx_buffer_info->mapped_as_page)
+ ixgbe_receive_skb(q_vector, skb, staterr,
+ rx_ring, rx_desc);
+ else {
+ skb_record_rx_queue(skb, rx_ring->queue_index);
+ napi_gro_frags(napi);
+ }
next_desc:
rx_desc->wb.upper.status_error = 0;
@@ -3622,9 +3708,16 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
rx_buffer_info = &rx_ring->rx_buffer_info[i];
if (rx_buffer_info->dma) {
- dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
- rx_ring->rx_buf_len,
- DMA_FROM_DEVICE);
+ if (!rx_buffer_info->mapped_as_page)
+ dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
+ rx_ring->rx_buf_len,
+ PCI_DMA_FROMDEVICE);
+ else {
+ dma_unmap_page(&pdev->dev, rx_buffer_info->dma,
+ PAGE_SIZE / 2,
+ PCI_DMA_FROMDEVICE);
+ rx_buffer_info->page_skb = NULL;
+ }
rx_buffer_info->dma = 0;
}
if (rx_buffer_info->skb) {
@@ -3651,7 +3744,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
PAGE_SIZE / 2, DMA_FROM_DEVICE);
rx_buffer_info->page_dma = 0;
}
- put_page(rx_buffer_info->page);
+ netdev_free_page(adapter->netdev, rx_buffer_info->page);
rx_buffer_info->page = NULL;
rx_buffer_info->page_offset = 0;
}
--
1.7.3
next prev parent reply other threads:[~2010-11-04 8:44 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-04 9:04 [PATCH v14 00/17] Provide a zero-copy method on KVM virtio-net xiaohui.xin
2010-11-04 9:04 ` [PATCH v14 01/17] Add a new structure for skb buffer from external xiaohui.xin
2010-11-04 9:04 ` [PATCH v14 02/17] Add a new struct for device to manipulate external buffer xiaohui.xin
2010-11-04 9:04 ` [PATCH v14 03/17] Add a ndo_mp_port_prep pointer to net_device_ops xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 04/17] Add a function make external buffer owner to query capability xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 05/17] Add a function to indicate if device use external buffer xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 06/17] Use callback to deal with skb_release_data() specially xiaohui.xin
2010-11-04 9:04 ` Eric Dumazet
2010-11-04 9:07 ` Eric Dumazet
2010-11-08 8:03 ` xiaohui.xin
2010-11-08 8:24 ` Eric Dumazet
2010-11-08 8:39 ` Xin, Xiaohui
2010-11-04 9:05 ` [PATCH v14 07/17]Modify netdev_alloc_page() to get external buffer xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 08/17] Modify netdev_free_page() to release " xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 09/17] Don't do skb recycle, if device use " xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 10/17] If device is in zero-copy mode first, bonding will fail xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 11/17] Add a hook to intercept external buffers from NIC driver xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 12/17] Add header file for mp device xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 13/17] Add mp(mediate passthru) device xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 14/17] Add a kconfig entry and make entry for mp device xiaohui.xin
2010-11-04 9:05 ` [PATCH v14 15/17]Provides multiple submits and asynchronous notifications xiaohui.xin
2010-11-04 9:05 ` xiaohui.xin [this message]
2010-11-04 9:05 ` [PATCH v14 17/17] An example how to alloc user buffer based on napi_gro_frags() interface xiaohui.xin
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=d64cc2e937a784d64b79bddef50f8700343e8691.1288860478.git.xiaohui.xin@intel.com \
--to=xiaohui.xin@intel.com \
--cc=davem@davemloft.net \
--cc=herbert@gondor.apana.org.au \
--cc=jdike@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox