Skip to contentSkip to conversation

e1000e: remove use of skb_dma_map from e1000e driver

PATCH In review Jeff Kirsher 3 participants 12 messages Dec 3, 2009

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/10 e1000e: remove use of skb_dma_map from e1000e driver

From: Alexander Duyck <[email protected]>

In testing we have found that skb_dma_map/unmap is incompatible with HW IOMMU due to the fact that multiple mappings will return different results. In order to correct this we need to remove skb_dma_map/unmap calls from the e1000e driver.

---

 drivers/net/e1000e/e1000.h  |    9 ++++---
 drivers/net/e1000e/netdev.c |   59 ++++++++++++++++++++++++++++++-------------
 2 files changed, 47 insertions(+), 21 deletions(-)
drivers/net/e1000e/e1000.h +6 -3
index c4e861f..b9f9e78 100644
@@ -194,12 +194,15 @@ struct e1000_buffer {
 			unsigned long time_stamp;
 			u16 length;
 			u16 next_to_watch;
+			u16 mapped_as_page;
 		};
 		/* Rx */
-		/* arrays of page information for packet split */
-		struct e1000_ps_page *ps_pages;
+		struct {
+			/* arrays of page information for packet split */
+			struct e1000_ps_page *ps_pages;
+			struct page *page;
+		};
 	};
-	struct page *page;
 };
 
 struct e1000_ring {
drivers/net/e1000e/netdev.c +41 -18

105 lines not on this page · raw message

#1 lore raw

PATCH 2/10 e1000: remove use of skb_dma_map from e1000 driver

From: Alexander Duyck <[email protected]>

Remove the use of skb_dma_map from the e1000 driver in order to avoid issues when HW iommu are in use.

---

 drivers/net/e1000/e1000.h      |    1 +
 drivers/net/e1000/e1000_main.c |   56 +++++++++++++++++++++++++++++-----------
 2 files changed, 41 insertions(+), 16 deletions(-)
drivers/net/e1000/e1000.h +1 -0
index a566528..2a567df 100644
@@ -167,6 +167,7 @@ struct e1000_buffer {
 	unsigned long time_stamp;
 	u16 length;
 	u16 next_to_watch;
+	u16 mapped_as_page;
 };
 
 struct e1000_tx_ring {
drivers/net/e1000/e1000_main.c +40 -16

99 lines not on this page · raw message

#2 lore raw

PATCH 3/10 ixgb: remove use of skb_dma_map from ixgb

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

skb_dma_map is incompatible with HW iommu due to the fact that multiple mappings can result in different results each time. For this reason it is best to just remove use of these function calls.

---

 drivers/net/ixgb/ixgb.h      |    1 +
 drivers/net/ixgb/ixgb_main.c |   60 +++++++++++++++++++++++++++++-------------
 2 files changed, 42 insertions(+), 19 deletions(-)
drivers/net/ixgb/ixgb.h +1 -0
index e95d9b6..5257ae0 100644
@@ -117,6 +117,7 @@ struct ixgb_buffer {
 	unsigned long time_stamp;
 	u16 length;
 	u16 next_to_watch;
+	u16 mapped_as_page;
 };
 
 struct ixgb_desc_ring {
drivers/net/ixgb/ixgb_main.c +41 -19

106 lines not on this page · raw message

#3 lore raw

PATCH 4/10 ixgbe: remove skb_dma_map/unmap calls from driver

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

This patch removes skb_dma_map/unmap calls from the ixgbe driver due to the fact that the calls don't work with HW IOMMU enabled systems. The problem is that multiple mappings will give different results when HW IOMMU is enabled and the skb_dma_map/unmap calls only have one location to store mappings.

---

 drivers/net/ixgbe/ixgbe.h      |    1 +
 drivers/net/ixgbe/ixgbe_main.c |   63 +++++++++++++++++++++++++++++++---------
 2 files changed, 50 insertions(+), 14 deletions(-)
drivers/net/ixgbe/ixgbe.h +1 -0
index 76b052f..7e35e97 100644
@@ -106,6 +106,7 @@ struct ixgbe_tx_buffer {
 	unsigned long time_stamp;
 	u16 length;
 	u16 next_to_watch;
+	u16 mapped_as_page;
 };
 
 struct ixgbe_rx_buffer {
drivers/net/ixgbe/ixgbe_main.c +49 -14

109 lines not on this page · raw message

#4 lore raw

PATCH 5/10 igb: remove use of skb_dma_map from driver

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

This change removes skb_dma_map/unmap calls from the igb driver due to the fact that the call is incompatible with iommu enabled kernels. In order to prevent warnings about using the wrong unmap call I have added a mapped_as_page value to the buffer_info structure to track if the mapped region is a page or a buffer.

---

 drivers/net/igb/igb.h      |    5 ++-
 drivers/net/igb/igb_main.c |   69 ++++++++++++++++++++++++++++++++++----------
 2 files changed, 56 insertions(+), 18 deletions(-)
drivers/net/igb/igb.h +3 -2
index c458d9b..b1c1eb8 100644
@@ -137,12 +137,13 @@ struct igb_buffer {
 			unsigned long time_stamp;
 			u16 length;
 			u16 next_to_watch;
+			u16 mapped_as_page;
 		};
 		/* RX */
 		struct {
 			struct page *page;
-			u64 page_dma;
-			unsigned int page_offset;
+			dma_addr_t page_dma;
+			u16 page_offset;
 		};
 	};
 };
drivers/net/igb/igb_main.c +53 -16

113 lines not on this page · raw message

#5 lore raw

PATCH 6/10 igbvf: remove skb_dma_map/unmap call from drivers

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

This patch removes the skb_dma_map/unmap calls from the igbvf driver due to the fact that it does not play well with HW IOMMU when combined with transmitting cloned skbs.

---

 drivers/net/igbvf/igbvf.h  |    1 +
 drivers/net/igbvf/netdev.c |   65 +++++++++++++++++++++++++++++++++++---------
 2 files changed, 52 insertions(+), 14 deletions(-)
drivers/net/igbvf/igbvf.h +1 -0
index 8e9b67e..3d1ee7a 100644
@@ -117,6 +117,7 @@ struct igbvf_buffer {
 			unsigned long time_stamp;
 			u16 length;
 			u16 next_to_watch;
+			u16 mapped_as_page;
 		};
 		/* Rx */
 		struct {
drivers/net/igbvf/netdev.c +51 -14

102 lines not on this page · raw message

#6 lore raw

PATCH 7/10 bnx2: remove skb_dma_map/unmap calls from driver

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

Due to the fact that skb_dma_map/unmap do not work correctly when a HW IOMMU is enabled it has been recommended to go about removing the calls from the network device drivers.

[ Fix bnx2_free_tx_skbs() ring indexing and use NETDEV_TX_OK return
code in bnx2_start_xmit() after cleaning up DMA mapping errors. -Mchan ]

---

 drivers/net/bnx2.c |   72 +++++++++++++++++++++++++++++++++++++++++++---------
 drivers/net/bnx2.h |    1 +
 2 files changed, 61 insertions(+), 12 deletions(-)
drivers/net/bnx2.c +60 -12
index 539d23b..f47bf50 100644
@@ -2815,13 +2815,21 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 			}
 		}
 
-		skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE);
+		pci_unmap_single(bp->pdev, pci_unmap_addr(tx_buf, mapping),
+			skb_headlen(skb), PCI_DMA_TODEVICE);
 
 		tx_buf->skb = NULL;
 		last = tx_buf->nr_frags;
 
 		for (i = 0; i < last; i++) {
 			sw_cons = NEXT_TX_BD(sw_cons);
+
+			pci_unmap_page(bp->pdev,
+				pci_unmap_addr(
+					&txr->tx_buf_ring[TX_RING_IDX(sw_cons)],
+					mapping),
+				skb_shinfo(skb)->frags[i].size,
+				PCI_DMA_TODEVICE);
 		}
 
 		sw_cons = NEXT_TX_BD(sw_cons);
@@ -5295,17 +5303,29 @@ bnx2_free_tx_skbs(struct bnx2 *bp)
 		for (j = 0; j < TX_DESC_CNT; ) {
 			struct sw_tx_bd *tx_buf = &txr->tx_buf_ring[j];
 			struct sk_buff *skb = tx_buf->skb;
+			int k, last;
 
 			if (skb == NULL) {
 				j++;
 				continue;
 			}
 
-			skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE);
+			pci_unmap_single(bp->pdev,
+					 pci_unmap_addr(tx_buf, mapping),
+					 skb_headlen(skb),
+					 PCI_DMA_TODEVICE);
 
 			tx_buf->skb = NULL;
 
-			j += skb_shinfo(skb)->nr_frags + 1;
+			last = tx_buf->nr_frags;
+			j++;
+			for (k = 0; k < last; k++, j++) {
+				tx_buf = &txr->tx_buf_ring[TX_RING_IDX(j)];
+				pci_unmap_page(bp->pdev,
+					pci_unmap_addr(tx_buf, mapping),
+					skb_shinfo(skb)->frags[k].size,
+					PCI_DMA_TODEVICE);
+			}
 			dev_kfree_skb(skb);
 		}
 	}
@@ -5684,11 +5704,12 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 	for (i = 14; i < pkt_size; i++)
 		packet[i] = (unsigned char) (i & 0xff);
 
-	if (skb_dma_map(&bp->pdev->dev, skb, DMA_TO_DEVICE)) {
+	map = pci_map_single(bp->pdev, skb->data, pkt_size,
+		PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(bp->pdev, map)) {
 		dev_kfree_skb(skb);
 		return -EIO;
 	}
-	map = skb_shinfo(skb)->dma_head;
 
 	REG_WR(bp, BNX2_HC_COMMAND,
 	       bp->hc_cmd | BNX2_HC_COMMAND_COAL_NOW_WO_INT);
@@ -5723,7 +5744,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 
 	udelay(5);
 
-	skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE);
+	pci_unmap_single(bp->pdev, map, pkt_size, PCI_DMA_TODEVICE);
 	dev_kfree_skb(skb);
 
 	if (bnx2_get_hw_tx_cons(tx_napi) != txr->tx_prod)
@@ -6302,7 +6323,6 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct bnx2_napi *bnapi;
 	struct bnx2_tx_ring_info *txr;
 	struct netdev_queue *txq;
-	struct skb_shared_info *sp;
 
 	/*  Determine which tx ring we will be placed on */
 	i = skb_get_queue_mapping(skb);
@@ -6367,16 +6387,15 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else
 		mss = 0;
 
-	if (skb_dma_map(&bp->pdev->dev, skb, DMA_TO_DEVICE)) {
+	mapping = pci_map_single(bp->pdev, skb->data, len, PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(bp->pdev, mapping)) {
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
-	sp = skb_shinfo(skb);
-	mapping = sp->dma_head;
-
 	tx_buf = &txr->tx_buf_ring[ring_prod];
 	tx_buf->skb = skb;
+	pci_unmap_addr_set(tx_buf, mapping, mapping);
 
 	txbd = &txr->tx_desc_ring[ring_prod];
 
@@ -6397,7 +6416,12 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		txbd = &txr->tx_desc_ring[ring_prod];
 
 		len = frag->size;
-		mapping = sp->dma_maps[i];
+		mapping = pci_map_page(bp->pdev, frag->page, frag->page_offset,
+			len, PCI_DMA_TODEVICE);
+		if (pci_dma_mapping_error(bp->pdev, mapping))
+			goto dma_error;
+		pci_unmap_addr_set(&txr->tx_buf_ring[ring_prod], mapping,
+				   mapping);
 
 		txbd->tx_bd_haddr_hi = (u64) mapping >> 32;
 		txbd->tx_bd_haddr_lo = (u64) mapping & 0xffffffff;
@@ -6424,6 +6448,30 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	return NETDEV_TX_OK;
+dma_error:
+	/* save value of frag that failed */
+	last_frag = i;
+
+	/* start back at beginning and unmap skb */
+	prod = txr->tx_prod;
+	ring_prod = TX_RING_IDX(prod);
+	tx_buf = &txr->tx_buf_ring[ring_prod];
+	tx_buf->skb = NULL;
+	pci_unmap_single(bp->pdev, pci_unmap_addr(tx_buf, mapping),
+			 skb_headlen(skb), PCI_DMA_TODEVICE);
+
+	/* unmap remaining mapped pages */
+	for (i = 0; i < last_frag; i++) {
+		prod = NEXT_TX_BD(prod);
+		ring_prod = TX_RING_IDX(prod);
+		tx_buf = &txr->tx_buf_ring[ring_prod];
+		pci_unmap_page(bp->pdev, pci_unmap_addr(tx_buf, mapping),
+			       skb_shinfo(skb)->frags[i].size,
+			       PCI_DMA_TODEVICE);
+	}
+
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 /* Called with rtnl_lock */
drivers/net/bnx2.h +1 -0
index a4d8340..4908b9f 100644
@@ -6559,6 +6559,7 @@ struct sw_pg {
 
 struct sw_tx_bd {
 	struct sk_buff		*skb;
+	DECLARE_PCI_UNMAP_ADDR(mapping)
 	unsigned short		is_gso;
 	unsigned short		nr_frags;
 };
#7 lore raw

PATCH 8/10 be2net: remove use of skb_dma_map/unmap

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

Due to the fact that skb_dma_map/unmap do not work correctly when a HW IOMMU is enabled it has been recommended to go about removing the calls from the network device drivers.

---

 drivers/net/benet/be_main.c |   37 ++++++++++++++++++++++++++-----------
 1 files changed, 26 insertions(+), 11 deletions(-)
drivers/net/benet/be_main.c +26 -11
index 7959364..f6d8a88 100644
@@ -390,15 +390,11 @@ static int make_tx_wrbs(struct be_adapter *adapter,
 	atomic_add(wrb_cnt, &txq->used);
 	queue_head_inc(txq);
 
-	if (skb_dma_map(&pdev->dev, skb, DMA_TO_DEVICE)) {
-		dev_err(&pdev->dev, "TX DMA mapping failed\n");
-		return 0;
-	}
-
 	if (skb->len > skb->data_len) {
 		int len = skb->len - skb->data_len;
+		busaddr = pci_map_single(pdev, skb->data, len,
+					 PCI_DMA_TODEVICE);
 		wrb = queue_head_node(txq);
-		busaddr = skb_shinfo(skb)->dma_head;
 		wrb_fill(wrb, busaddr, len);
 		be_dws_cpu_to_le(wrb, sizeof(*wrb));
 		queue_head_inc(txq);
@@ -408,8 +404,9 @@ static int make_tx_wrbs(struct be_adapter *adapter,
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		struct skb_frag_struct *frag =
 			&skb_shinfo(skb)->frags[i];
-
-		busaddr = skb_shinfo(skb)->dma_maps[i];
+		busaddr = pci_map_page(pdev, frag->page,
+				       frag->page_offset,
+				       frag->size, PCI_DMA_TODEVICE);
 		wrb = queue_head_node(txq);
 		wrb_fill(wrb, busaddr, frag->size);
 		be_dws_cpu_to_le(wrb, sizeof(*wrb));
@@ -982,23 +979,41 @@ static struct be_eth_tx_compl *be_tx_compl_get(struct be_queue_info *tx_cq)
 static void be_tx_compl_process(struct be_adapter *adapter, u16 last_index)
 {
 	struct be_queue_info *txq = &adapter->tx_obj.q;
+	struct be_eth_wrb *wrb;
 	struct sk_buff **sent_skbs = adapter->tx_obj.sent_skb_list;
 	struct sk_buff *sent_skb;
+	u64 busaddr;
 	u16 cur_index, num_wrbs = 0;
 
 	cur_index = txq->tail;
 	sent_skb = sent_skbs[cur_index];
 	BUG_ON(!sent_skb);
 	sent_skbs[cur_index] = NULL;
+	wrb = queue_tail_node(txq);
+	be_dws_le_to_cpu(wrb, sizeof(*wrb));
+	busaddr = ((u64)wrb->frag_pa_hi << 32) | (u64)wrb->frag_pa_lo;
+	if (busaddr != 0) {
+		pci_unmap_single(adapter->pdev, busaddr,
+				 wrb->frag_len, PCI_DMA_TODEVICE);
+	}
+	num_wrbs++;
+	queue_tail_inc(txq);
 
-	do {
+	while (cur_index != last_index) {
 		cur_index = txq->tail;
+		wrb = queue_tail_node(txq);
+		be_dws_le_to_cpu(wrb, sizeof(*wrb));
+		busaddr = ((u64)wrb->frag_pa_hi << 32) | (u64)wrb->frag_pa_lo;
+		if (busaddr != 0) {
+			pci_unmap_page(adapter->pdev, busaddr,
+				       wrb->frag_len, PCI_DMA_TODEVICE);
+		}
 		num_wrbs++;
 		queue_tail_inc(txq);
-	} while (cur_index != last_index);
+	}
 
 	atomic_sub(num_wrbs, &txq->used);
-	skb_dma_unmap(&adapter->pdev->dev, sent_skb, DMA_TO_DEVICE);
+
 	kfree_skb(sent_skb);
 }
 
#8 lore raw

PATCH 9/10 tg3: remove use of skb_dma_map/unmap

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

Due to the fact that skb_dma_map/unmap do not work correctly when a HW IOMMU is enabled it has been recommended to go about removing the calls from the network device drivers.

---

 drivers/net/tg3.c |  173 ++++++++++++++++++++++++++++++++++++++++-------------
 drivers/net/tg3.h |    6 --
 2 files changed, 132 insertions(+), 47 deletions(-)
drivers/net/tg3.c +131 -42
index 6e6db95..302ea0b 100644
@@ -4357,7 +4357,7 @@ static void tg3_tx(struct tg3_napi *tnapi)
 	txq = netdev_get_tx_queue(tp->dev, index);
 
 	while (sw_idx != hw_idx) {
-		struct tx_ring_info *ri = &tnapi->tx_buffers[sw_idx];
+		struct ring_info *ri = &tnapi->tx_buffers[sw_idx];
 		struct sk_buff *skb = ri->skb;
 		int i, tx_bug = 0;
 
@@ -4366,7 +4366,10 @@ static void tg3_tx(struct tg3_napi *tnapi)
 			return;
 		}
 
-		skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE);
+		pci_unmap_single(tp->pdev,
+				 pci_unmap_addr(ri, mapping),
+				 skb_headlen(skb),
+				 PCI_DMA_TODEVICE);
 
 		ri->skb = NULL;
 
@@ -4376,6 +4379,11 @@ static void tg3_tx(struct tg3_napi *tnapi)
 			ri = &tnapi->tx_buffers[sw_idx];
 			if (unlikely(ri->skb != NULL || sw_idx == hw_idx))
 				tx_bug = 1;
+
+			pci_unmap_page(tp->pdev,
+				       pci_unmap_addr(ri, mapping),
+				       skb_shinfo(skb)->frags[i].size,
+				       PCI_DMA_TODEVICE);
 			sw_idx = NEXT_TX(sw_idx);
 		}
 
@@ -5334,17 +5342,21 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	} else {
 		/* New SKB is guaranteed to be linear. */
 		entry = *start;
-		ret = skb_dma_map(&tp->pdev->dev, new_skb, DMA_TO_DEVICE);
-		new_addr = skb_shinfo(new_skb)->dma_head;
+		new_addr = pci_map_single(tp->pdev, new_skb->data, new_skb->len,
+					  PCI_DMA_TODEVICE);
+		/* Make sure the mapping succeeded */
+		if (pci_dma_mapping_error(tp->pdev, new_addr)) {
+			ret = -1;
+			dev_kfree_skb(new_skb);
+			new_skb = NULL;
 
 		/* Make sure new skb does not cross any 4G boundaries.
 		 * Drop the packet if it does.
 		 */
-		if (ret || ((tp->tg3_flags3 & TG3_FLG3_4G_DMA_BNDRY_BUG) &&
-			    tg3_4g_overflow_test(new_addr, new_skb->len))) {
-			if (!ret)
-				skb_dma_unmap(&tp->pdev->dev, new_skb,
-					      DMA_TO_DEVICE);
+		} else if ((tp->tg3_flags3 & TG3_FLG3_4G_DMA_BNDRY_BUG) &&
+			    tg3_4g_overflow_test(new_addr, new_skb->len)) {
+			pci_unmap_single(tp->pdev, new_addr, new_skb->len,
+					 PCI_DMA_TODEVICE);
 			ret = -1;
 			dev_kfree_skb(new_skb);
 			new_skb = NULL;
@@ -5358,15 +5370,28 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	/* Now clean up the sw ring entries. */
 	i = 0;
 	while (entry != last_plus_one) {
+		int len;
+
 		if (i == 0)
-			tnapi->tx_buffers[entry].skb = new_skb;
+			len = skb_headlen(skb);
 		else
+			len = skb_shinfo(skb)->frags[i-1].size;
+
+		pci_unmap_single(tp->pdev,
+				 pci_unmap_addr(&tnapi->tx_buffers[entry],
+						mapping),
+				 len, PCI_DMA_TODEVICE);
+		if (i == 0) {
+			tnapi->tx_buffers[entry].skb = new_skb;
+			pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping,
+					   new_addr);
+		} else {
 			tnapi->tx_buffers[entry].skb = NULL;
+		}
 		entry = NEXT_TX(entry);
 		i++;
 	}
 
-	skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE);
 	dev_kfree_skb(skb);
 
 	return ret;
@@ -5403,10 +5428,11 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb,
 {
 	struct tg3 *tp = netdev_priv(dev);
 	u32 len, entry, base_flags, mss;
-	struct skb_shared_info *sp;
 	dma_addr_t mapping;
 	struct tg3_napi *tnapi;
 	struct netdev_queue *txq;
+	unsigned int i, last;
+
 
 	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
 	tnapi = &tp->napi[skb_get_queue_mapping(skb)];
@@ -5477,18 +5503,17 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb,
 			       (vlan_tx_tag_get(skb) << 16));
 #endif
 
-	if (skb_dma_map(&tp->pdev->dev, skb, DMA_TO_DEVICE)) {
+	len = skb_headlen(skb);
+
+	/* Queue skb data, a.k.a. the main skb fragment. */
+	mapping = pci_map_single(tp->pdev, skb->data, len, PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(tp->pdev, mapping)) {
 		dev_kfree_skb(skb);
 		goto out_unlock;
 	}
 
-	sp = skb_shinfo(skb);
-
-	mapping = sp->dma_head;
-
 	tnapi->tx_buffers[entry].skb = skb;
-
-	len = skb_headlen(skb);
+	pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping, mapping);
 
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 &&
 	    !mss && skb->len > ETH_DATA_LEN)
@@ -5501,15 +5526,21 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb,
 
 	/* Now loop through additional data fragments, and queue them. */
 	if (skb_shinfo(skb)->nr_frags > 0) {
-		unsigned int i, last;
-
 		last = skb_shinfo(skb)->nr_frags - 1;
 		for (i = 0; i <= last; i++) {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 			len = frag->size;
-			mapping = sp->dma_maps[i];
+			mapping = pci_map_page(tp->pdev,
+					       frag->page,
+					       frag->page_offset,
+					       len, PCI_DMA_TODEVICE);
+			if (pci_dma_mapping_error(tp->pdev, mapping))
+				goto dma_error;
+
 			tnapi->tx_buffers[entry].skb = NULL;
+			pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping,
+					   mapping);
 
 			tg3_set_txd(tnapi, entry, mapping, len,
 				    base_flags, (i == last) | (mss << 1));
@@ -5532,6 +5563,27 @@ out_unlock:
 	mmiowb();
 
 	return NETDEV_TX_OK;
+
+dma_error:
+	last = i;
+	entry = tnapi->tx_prod;
+	tnapi->tx_buffers[entry].skb = NULL;
+	pci_unmap_single(tp->pdev,
+			 pci_unmap_addr(&tnapi->tx_buffers[entry], mapping),
+			 skb_headlen(skb),
+			 PCI_DMA_TODEVICE);
+	for (i = 0; i <= last; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		entry = NEXT_TX(entry);
+
+		pci_unmap_page(tp->pdev,
+			       pci_unmap_addr(&tnapi->tx_buffers[entry],
+					      mapping),
+			       frag->size, PCI_DMA_TODEVICE);
+	}
+
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *,
@@ -5579,11 +5631,12 @@ static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *skb,
 {
 	struct tg3 *tp = netdev_priv(dev);
 	u32 len, entry, base_flags, mss;
-	struct skb_shared_info *sp;
 	int would_hit_hwbug;
 	dma_addr_t mapping;
 	struct tg3_napi *tnapi;
 	struct netdev_queue *txq;
+	unsigned int i, last;
+
 
 	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
 	tnapi = &tp->napi[skb_get_queue_mapping(skb)];
@@ -5678,21 +5731,19 @@ static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *skb,
 	    !mss && skb->len > ETH_DATA_LEN)
 		base_flags |= TXD_FLAG_JMB_PKT;
 
-	if (skb_dma_map(&tp->pdev->dev, skb, DMA_TO_DEVICE)) {
+	len = skb_headlen(skb);
+
+	mapping = pci_map_single(tp->pdev, skb->data, len, PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(tp->pdev, mapping)) {
 		dev_kfree_skb(skb);
 		goto out_unlock;
 	}
 
-	sp = skb_shinfo(skb);
-
-	mapping = sp->dma_head;
-
 	tnapi->tx_buffers[entry].skb = skb;
+	pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping, mapping);
 
 	would_hit_hwbug = 0;
 
-	len = skb_headlen(skb);
-
 	if ((tp->tg3_flags3 & TG3_FLG3_SHORT_DMA_BUG) && len <= 8)
 		would_hit_hwbug = 1;
 
@@ -5714,16 +5765,21 @@ static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *skb,
 
 	/* Now loop through additional data fragments, and queue them. */
 	if (skb_shinfo(skb)->nr_frags > 0) {
-		unsigned int i, last;
-
 		last = skb_shinfo(skb)->nr_frags - 1;
 		for (i = 0; i <= last; i++) {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 			len = frag->size;
-			mapping = sp->dma_maps[i];
+			mapping = pci_map_page(tp->pdev,
+					       frag->page,
+					       frag->page_offset,
+					       len, PCI_DMA_TODEVICE);
 
 			tnapi->tx_buffers[entry].skb = NULL;
+			pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping,
+					   mapping);
+			if (pci_dma_mapping_error(tp->pdev, mapping))
+				goto dma_error;
 
 			if ((tp->tg3_flags3 & TG3_FLG3_SHORT_DMA_BUG) &&
 			    len <= 8)
@@ -5779,6 +5835,27 @@ out_unlock:
 	mmiowb();
 
 	return NETDEV_TX_OK;
+
+dma_error:
+	last = i;
+	entry = tnapi->tx_prod;
+	tnapi->tx_buffers[entry].skb = NULL;
+	pci_unmap_single(tp->pdev,
+			 pci_unmap_addr(&tnapi->tx_buffers[entry], mapping),
+			 skb_headlen(skb),
+			 PCI_DMA_TODEVICE);
+	for (i = 0; i <= last; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		entry = NEXT_TX(entry);
+
+		pci_unmap_page(tp->pdev,
+			       pci_unmap_addr(&tnapi->tx_buffers[entry],
+					      mapping),
+			       frag->size, PCI_DMA_TODEVICE);
+	}
+
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static inline void tg3_set_mtu(struct net_device *dev, struct tg3 *tp,
@@ -6046,8 +6123,9 @@ static void tg3_free_rings(struct tg3 *tp)
 			continue;
 
 		for (i = 0; i < TG3_TX_RING_SIZE; ) {
-			struct tx_ring_info *txp;
+			struct ring_info *txp;
 			struct sk_buff *skb;
+			unsigned int k;
 
 			txp = &tnapi->tx_buffers[i];
 			skb = txp->skb;
@@ -6057,11 +6135,22 @@ static void tg3_free_rings(struct tg3 *tp)
 				continue;
 			}
 
-			skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE);
-
+			pci_unmap_single(tp->pdev,
+					 pci_unmap_addr(txp, mapping),
+					 skb_headlen(skb),
+					 PCI_DMA_TODEVICE);
 			txp->skb = NULL;
 
-			i += skb_shinfo(skb)->nr_frags + 1;
+			i++;
+
+			for (k = 0; k < skb_shinfo(skb)->nr_frags; k++) {
+				txp = &tnapi->tx_buffers[i & (TG3_TX_RING_SIZE - 1)];
+				pci_unmap_page(tp->pdev,
+					       pci_unmap_addr(txp, mapping),
+					       skb_shinfo(skb)->frags[k].size,
+					       PCI_DMA_TODEVICE);
+				i++;
+			}
 
 			dev_kfree_skb_any(skb);
 		}
@@ -6231,7 +6320,7 @@ static int tg3_alloc_consistent(struct tg3 *tp)
 
 		memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp));
 
-		tnapi->tx_buffers = kzalloc(sizeof(struct tx_ring_info) *
+		tnapi->tx_buffers = kzalloc(sizeof(struct ring_info) *
 					    TG3_TX_RING_SIZE, GFP_KERNEL);
 		if (!tnapi->tx_buffers)
 			goto err_out;
@@ -10637,7 +10726,8 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode)
 	for (i = 14; i < tx_len; i++)
 		tx_data[i] = (u8) (i & 0xff);
 
-	if (skb_dma_map(&tp->pdev->dev, skb, DMA_TO_DEVICE)) {
+	map = pci_map_single(tp->pdev, skb->data, tx_len, PCI_DMA_TODEVICE);
+	if (pci_dma_mapping_error(tp->pdev, map)) {
 		dev_kfree_skb(skb);
 		return -EIO;
 	}
@@ -10651,8 +10741,7 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode)
 
 	num_pkts = 0;
 
-	tg3_set_txd(tnapi, tnapi->tx_prod,
-		    skb_shinfo(skb)->dma_head, tx_len, 0, 1);
+	tg3_set_txd(tnapi, tnapi->tx_prod, map, tx_len, 0, 1);
 
 	tnapi->tx_prod++;
 	num_pkts++;
@@ -10676,7 +10765,7 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode)
 			break;
 	}
 
-	skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE);
+	pci_unmap_single(tp->pdev, map, tx_len, PCI_DMA_TODEVICE);
 	dev_kfree_skb(skb);
 
 	if (tx_idx != tnapi->tx_prod)
drivers/net/tg3.h +1 -5
index 453a34f..8972523 100644
@@ -2441,10 +2441,6 @@ struct ring_info {
 	DECLARE_PCI_UNMAP_ADDR(mapping)
 };
 
-struct tx_ring_info {
-	struct sk_buff			*skb;
-};
-
 struct tg3_config_info {
 	u32				flags;
 };
@@ -2608,7 +2604,7 @@ struct tg3_napi {
 
 	struct tg3_rx_buffer_desc	*rx_rcb;
 	struct tg3_tx_buffer_desc	*tx_ring;
-	struct tx_ring_info		*tx_buffers;
+	struct ring_info		*tx_buffers;
 
 	dma_addr_t			status_mapping;
 	dma_addr_t			rx_rcb_mapping;
#9 lore raw

PATCH 10/10 skbuff: remove skb_dma_map/unmap

In reply to Jeff Kirsher

From: Alexander Duyck <[email protected]>

The two functions skb_dma_map/unmap are unsafe to use as they cause problems when packets are cloned and sent to multiple devices while a HW IOMMU is enabled. Due to this it is best to remove the code so it is not used by any other network driver maintainters.

---

 include/linux/skbuff.h |    8 ------
 net/core/Makefile      |    1 -
 net/core/skb_dma_map.c |   65 ------------------------------------------------
 3 files changed, 0 insertions(+), 74 deletions(-)
 delete mode 100644 net/core/skb_dma_map.c
include/linux/skbuff.h +0 -8
index 89eed8c..ae836fd 100644
@@ -416,14 +416,6 @@ struct sk_buff {
 
 #include <asm/system.h>
 
-#ifdef CONFIG_HAS_DMA
-#include <linux/dma-mapping.h>
-extern int skb_dma_map(struct device *dev, struct sk_buff *skb,
-		       enum dma_data_direction dir);
-extern void skb_dma_unmap(struct device *dev, struct sk_buff *skb,
-			  enum dma_data_direction dir);
-#endif
-
 static inline struct dst_entry *skb_dst(const struct sk_buff *skb)
 {
 	return (struct dst_entry *)skb->_skb_dst;
net/core/Makefile +0 -1
index 796f46e..08791ac 100644
@@ -6,7 +6,6 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
 	 gen_stats.o gen_estimator.o net_namespace.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
-obj-$(CONFIG_HAS_DMA) += skb_dma_map.o
 
 obj-y		     += dev.o ethtool.o dev_mcast.o dst.o netevent.o \
 			neighbour.o rtnetlink.o utils.o link_watch.o filter.o
net/core/skb_dma_map.c deleted +0 -65

65 lines not on this page · raw message

#11 lore raw
Quoted 3 lines · David Miller

All 10 patches applied.

Alexander et al., thanks for following up on this.

Excellent, time for new benchs :)