On Sun, 2007-23-09 at 14:19 -0400, Jeff Garzik wrote:
>
> You should post at least a couple driver patches to see how its used on
> Real Hardware(tm)... :)
This is the tg3 patch i used for the testing - against whats in Daves
net-2.6.24 tree. Patch may be a bit hard to read.
For an example of an LLTX version look at the e1000 in the older git
tree at:
git://git.kernel.org/pub/scm/linux/kernel/git/hadi/batch-lin26.git
If the intel folks will accept the patch i'd really like to kill
the e1000 LLTX interface.
The tg3 in that tree used the old style batch_xmit() interface.
cheers,
jamal
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index d4ac6e9..ba0b49e 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -3103,6 +3103,13 @@ static inline u32 tg3_tx_avail(struct tg3 *tp)
((tp->tx_prod - tp->tx_cons) & (TG3_TX_RING_SIZE - 1)));
}
+static inline void tg3_set_win(struct tg3 *tp)
+{
+ tp->dev->xmit_win = tg3_tx_avail(tp) - (MAX_SKB_FRAGS + 1);
+ if (tp->dev->xmit_win < 1)
+ tp->dev->xmit_win = 1;
+}
+
/* Tigon3 never reports partial packet sends. So we do not
* need special logic to handle SKBs that have not had all
* of their frags sent yet, like SunGEM does.
@@ -3165,8 +3172,10 @@ static void tg3_tx(struct tg3 *tp)
(tg3_tx_avail(tp) > TG3_TX_WAKEUP_THRESH(tp)))) {
netif_tx_lock(tp->dev);
if (netif_queue_stopped(tp->dev) &&
- (tg3_tx_avail(tp) > TG3_TX_WAKEUP_THRESH(tp)))
+ (tg3_tx_avail(tp) > TG3_TX_WAKEUP_THRESH(tp))) {
+ tg3_set_win(tp);
netif_wake_queue(tp->dev);
+ }
netif_tx_unlock(tp->dev);
}
}
@@ -3910,47 +3919,67 @@ static void tg3_set_txd(struct tg3 *tp, int entry,
txd->vlan_tag = vlan_tag << TXD_VLAN_TAG_SHIFT;
}
-/* hard_start_xmit for devices that don't have any bugs and
- * support TG3_FLG2_HW_TSO_2 only.
- */
-static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+struct tg3_tx_cbdata {
+ u32 base_flags;
+ unsigned int mss;
+};
+#define TG3_SKB_CB(__skb) ((struct tg3_tx_cbdata *)&((__skb)->cb[0]))
+#define NETDEV_TX_DROPPED -5
+
+static int tg3_prep_bug_frame(struct sk_buff *skb, struct net_device *dev)
{
+ struct tg3_tx_cbdata *cb = TG3_SKB_CB(skb);
struct tg3 *tp = netdev_priv(dev);
- dma_addr_t mapping;
- u32 len, entry, base_flags, mss;
-
- len = skb_headlen(skb);
+ u32 vlantag = 0;
- /* We are running in BH disabled context with netif_tx_lock
- * and TX reclaim runs via tp->napi.poll inside of a software
- * interrupt. Furthermore, IRQ processing runs lockless so we have
- * no IRQ context deadlocks to worry about either. Rejoice!
- */
- if (unlikely(tg3_tx_avail(tp) <= (skb_shinfo(skb)->nr_frags + 1))) {
- if (!netif_queue_stopped(dev)) {
- netif_stop_queue(dev);
+#if TG3_VLAN_TAG_USED
+ if (tp->vlgrp != NULL && vlan_tx_tag_present(skb))
+ vlantag = (TXD_FLAG_VLAN | (vlan_tx_tag_get(skb) << 16));
+#endif
- /* This is a hard error, log it. */
- printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
- "queue awake!\n", dev->name);
+ cb->base_flags = vlantag;
+ cb->mss = skb_shinfo(skb)->gso_size;
+ if (cb->mss != 0) {
+ if (skb_header_cloned(skb) &&
+ pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) {
+ dev_kfree_skb(skb);
+ return NETDEV_TX_DROPPED;
}
- return NETDEV_TX_BUSY;
+
+ cb->base_flags |= (TXD_FLAG_CPU_PRE_DMA |
+ TXD_FLAG_CPU_POST_DMA);
}
- entry = tp->tx_prod;
- base_flags = 0;
- mss = 0;
- if ((mss = skb_shinfo(skb)->gso_size) != 0) {
+ if (skb->ip_summed == CHECKSUM_PARTIAL)
+ cb->base_flags |= TXD_FLAG_TCPUDP_CSUM;
+
+ return NETDEV_TX_OK;
+}
+
+static int tg3_prep_frame(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tg3_tx_cbdata *cb = TG3_SKB_CB(skb);
+ struct tg3 *tp = netdev_priv(dev);
+ u32 vlantag = 0;
+
+#if TG3_VLAN_TAG_USED
+ if (tp->vlgrp != NULL && vlan_tx_tag_present(skb))
+ vlantag = (TXD_FLAG_VLAN | (vlan_tx_tag_get(skb) << 16));
+#endif
+
+ cb->base_flags = vlantag;
+ cb->mss = skb_shinfo(skb)->gso_size;
+ if (cb->mss != 0) {
int tcp_opt_len, ip_tcp_len;
if (skb_header_cloned(skb) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) {
dev_kfree_skb(skb);
- goto out_unlock;
+ return NETDEV_TX_DROPPED;
}
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
- mss |= (skb_headlen(skb) - ETH_HLEN) << 9;
+ cb->mss |= (skb_headlen(skb) - ETH_HLEN) << 9;
else {
struct iphdr *iph = ip_hdr(skb);
@@ -3958,32 +3987,63 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
ip_tcp_len = ip_hdrlen(skb) + sizeof(struct tcphdr);
iph->check = 0;
- iph->tot_len = htons(mss + ip_tcp_len + tcp_opt_len);
- mss |= (ip_tcp_len + tcp_opt_len) << 9;
+ iph->tot_len = htons(cb->mss + ip_tcp_len
+ + tcp_opt_len);
+ cb->mss |= (ip_tcp_len + tcp_opt_len) << 9;
}
- base_flags |= (TXD_FLAG_CPU_PRE_DMA |
+ cb->base_flags |= (TXD_FLAG_CPU_PRE_DMA |
TXD_FLAG_CPU_POST_DMA);
tcp_hdr(skb)->check = 0;
}
else if (skb->ip_summed == CHECKSUM_PARTIAL)
- base_flags |= TXD_FLAG_TCPUDP_CSUM;
-#if TG3_VLAN_TAG_USED
- if (tp->vlgrp != NULL && vlan_tx_tag_present(skb))
- base_flags |= (TXD_FLAG_VLAN |
- (vlan_tx_tag_get(skb) << 16));
-#endif
+ cb->base_flags |= TXD_FLAG_TCPUDP_CSUM;
+
+ return NETDEV_TX_OK;
+}
+
+void tg3_kick_DMA(struct net_device *dev)
+{
+ struct tg3 *tp = netdev_priv(dev);
+ u32 entry = tp->tx_prod;
+
+ /* Packets are ready, update Tx producer idx local and on card. */
+ tw32_tx_mbox((MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW), entry);
+
+ if (unlikely(tg3_tx_avail(tp) <= (MAX_SKB_FRAGS + 1))) {
+ netif_stop_queue(dev);
+ dev->xmit_win = 1;
+ if (tg3_tx_avail(tp) >= TG3_TX_WAKEUP_THRESH(tp)) {
+ tg3_set_win(tp);
+ netif_wake_queue(dev);
+ }
+ } else {
+ tg3_set_win(tp);
+ }
+ mmiowb();
+ dev->trans_start = jiffies;
+}
+
+static int tg3_enqueue(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tg3 *tp = netdev_priv(dev);
+ dma_addr_t mapping;
+ u32 len, entry;
+ struct tg3_tx_cbdata *cb = TG3_SKB_CB(skb);
+
+ entry = tp->tx_prod;
+ 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);
tp->tx_buffers[entry].skb = skb;
pci_unmap_addr_set(&tp->tx_buffers[entry], mapping, mapping);
- tg3_set_txd(tp, entry, mapping, len, base_flags,
- (skb_shinfo(skb)->nr_frags == 0) | (mss << 1));
+ tg3_set_txd(tp, entry, mapping, len, cb->base_flags,
+ (skb_shinfo(skb)->nr_frags == 0) | (cb->mss << 1));
entry = NEXT_TX(entry);
@@ -4005,28 +4065,71 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
pci_unmap_addr_set(&tp->tx_buffers[entry], mapping, mapping);
tg3_set_txd(tp, entry, mapping, len,
- base_flags, (i == last) | (mss << 1));
+ cb->base_flags,
+ (i == last) | (cb->mss << 1));
entry = NEXT_TX(entry);
}
}
- /* Packets are ready, update Tx producer idx local and on card. */
- tw32_tx_mbox((MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW), entry);
-
tp->tx_prod = entry;
- if (unlikely(tg3_tx_avail(tp) <= (MAX_SKB_FRAGS + 1))) {
- netif_stop_queue(dev);
- if (tg3_tx_avail(tp) > TG3_TX_WAKEUP_THRESH(tp))
- netif_wake_queue(tp->dev);
+ return NETDEV_TX_OK;
+}
+
+/* hard_start_xmit for devices that don't have any bugs and
+ * support TG3_FLG2_HW_TSO_2 only.
+ */
+static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tg3 *tp = netdev_priv(dev);
+ int ret = tg3_prep_frame(skb, dev);
+ /* XXX: original code did mmiowb(); on failure,
+ * I dont think thats necessary
+ */
+ if (unlikely(ret != NETDEV_TX_OK))
+ return NETDEV_TX_OK;
+
+ /* We are running in BH disabled context with netif_tx_lock
+ * and TX reclaim runs via tp->poll inside of a software
+ * interrupt. Furthermore, IRQ processing runs lockless so we have
+ * no IRQ context deadlocks to worry about either. Rejoice!
+ */
+ if (unlikely(tg3_tx_avail(tp) <= (skb_shinfo(skb)->nr_frags + 1))) {
+ if (!netif_queue_stopped(dev)) {
+ netif_stop_queue(dev);
+ tp->dev->xmit_win = 1;
+
+ /* This is a hard error, log it. */
+ printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
+ "queue awake!\n", dev->name);
+ }
+ return NETDEV_TX_BUSY;
}
-out_unlock:
- mmiowb();
+ ret = tg3_enqueue(skb, dev);
+ if (ret == NETDEV_TX_OK)
+ tg3_kick_DMA(dev);
- dev->trans_start = jiffies;
+ return ret;
+}
- return NETDEV_TX_OK;
+static int tg3_start_bxmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tg3 *tp = netdev_priv(dev);
+
+ if (unlikely(tg3_tx_avail(tp) <= (skb_shinfo(skb)->nr_frags + 1))) {
+ if (!netif_queue_stopped(dev)) {
+ netif_stop_queue(dev);
+ dev->xmit_win = 1;
+
+ /* This is a hard error, log it. */
+ printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
+ "queue awake!\n", dev->name);
+ }
+ return NETDEV_TX_BUSY;
+ }
+
+ return tg3_enqueue(skb, dev);
}
static int tg3_start_xmit_dma_bug(struct sk_buff *, struct net_device *);
@@ -4041,9 +4144,11 @@ static int tg3_tso_bug(struct tg3 *tp, struct sk_buff *skb)
/* Estimate the number of fragments in the worst case */
if (unlikely(tg3_tx_avail(tp) <= (skb_shinfo(skb)->gso_segs * 3))) {
netif_stop_queue(tp->dev);
+ tp->dev->xmit_win = 1;
if (tg3_tx_avail(tp) <= (skb_shinfo(skb)->gso_segs * 3))
return NETDEV_TX_BUSY;
+ tg3_set_win(tp);
netif_wake_queue(tp->dev);
}
@@ -4067,46 +4172,19 @@ tg3_tso_bug_end:
/* hard_start_xmit for devices that have the 4G bug and/or 40-bit bug and
* support TG3_FLG2_HW_TSO_1 or firmware TSO only.
*/
-static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
+static int tg3_enqueue_buggy(struct sk_buff *skb, struct net_device *dev)
{
struct tg3 *tp = netdev_priv(dev);
dma_addr_t mapping;
- u32 len, entry, base_flags, mss;
+ u32 len, entry;
int would_hit_hwbug;
+ struct tg3_tx_cbdata *cb = TG3_SKB_CB(skb);
- len = skb_headlen(skb);
-
- /* We are running in BH disabled context with netif_tx_lock
- * and TX reclaim runs via tp->napi.poll inside of a software
- * interrupt. Furthermore, IRQ processing runs lockless so we have
- * no IRQ context deadlocks to worry about either. Rejoice!
- */
- if (unlikely(tg3_tx_avail(tp) <= (skb_shinfo(skb)->nr_frags + 1))) {
- if (!netif_queue_stopped(dev)) {
- netif_stop_queue(dev);
-
- /* This is a hard error, log it. */
- printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
- "queue awake!\n", dev->name);
- }
- return NETDEV_TX_BUSY;
- }
- entry = tp->tx_prod;
- base_flags = 0;
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- base_flags |= TXD_FLAG_TCPUDP_CSUM;
- mss = 0;
- if ((mss = skb_shinfo(skb)->gso_size) != 0) {
+ if (cb->mss != 0) {
struct iphdr *iph;
int tcp_opt_len, ip_tcp_len, hdr_len;
- if (skb_header_cloned(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) {
- dev_kfree_skb(skb);
- goto out_unlock;
- }
-
tcp_opt_len = tcp_optlen(skb);
ip_tcp_len = ip_hdrlen(skb) + sizeof(struct tcphdr);
@@ -4115,15 +4193,13 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
(tp->tg3_flags2 & TG3_FLG2_TSO_BUG))
return (tg3_tso_bug(tp, skb));
- base_flags |= (TXD_FLAG_CPU_PRE_DMA |
- TXD_FLAG_CPU_POST_DMA);
iph = ip_hdr(skb);
iph->check = 0;
- iph->tot_len = htons(mss + hdr_len);
+ iph->tot_len = htons(cb->mss + hdr_len);
if (tp->tg3_flags2 & TG3_FLG2_HW_TSO) {
tcp_hdr(skb)->check = 0;
- base_flags &= ~TXD_FLAG_TCPUDP_CSUM;
+ cb->base_flags &= ~TXD_FLAG_TCPUDP_CSUM;
} else
tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
iph->daddr, 0,
@@ -4136,22 +4212,19 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
int tsflags;
tsflags = (iph->ihl - 5) + (tcp_opt_len >> 2);
- mss |= (tsflags << 11);
+ cb->mss |= (tsflags << 11);
}
} else {
if (tcp_opt_len || iph->ihl > 5) {
int tsflags;
tsflags = (iph->ihl - 5) + (tcp_opt_len >> 2);
- base_flags |= tsflags << 12;
+ cb->base_flags |= tsflags << 12;
}
}
}
-#if TG3_VLAN_TAG_USED
- if (tp->vlgrp != NULL && vlan_tx_tag_present(skb))
- base_flags |= (TXD_FLAG_VLAN |
- (vlan_tx_tag_get(skb) << 16));
-#endif
+ len = skb_headlen(skb);
+ entry = tp->tx_prod;
/* Queue skb data, a.k.a. the main skb fragment. */
mapping = pci_map_single(tp->pdev, skb->data, len, PCI_DMA_TODEVICE);
@@ -4164,8 +4237,8 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
if (tg3_4g_overflow_test(mapping, len))
would_hit_hwbug = 1;
- tg3_set_txd(tp, entry, mapping, len, base_flags,
- (skb_shinfo(skb)->nr_frags == 0) | (mss << 1));
+ tg3_set_txd(tp, entry, mapping, len, cb->base_flags,
+ (skb_shinfo(skb)->nr_frags == 0) | (cb->mss << 1));
entry = NEXT_TX(entry);
@@ -4194,10 +4267,11 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
if (tp->tg3_flags2 & TG3_FLG2_HW_TSO)
tg3_set_txd(tp, entry, mapping, len,
- base_flags, (i == last)|(mss << 1));
+ cb->base_flags,
+ (i == last)|(cb->mss << 1));
else
tg3_set_txd(tp, entry, mapping, len,
- base_flags, (i == last));
+ cb->base_flags, (i == last));
entry = NEXT_TX(entry);
}
@@ -4214,28 +4288,68 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
* failure, silently drop this packet.
*/
if (tigon3_dma_hwbug_workaround(tp, skb, last_plus_one,
- &start, base_flags, mss))
- goto out_unlock;
+ &start, cb->base_flags,
+ cb->mss)) {
+ mmiowb();
+ return NETDEV_TX_OK;
+ }
entry = start;
}
- /* Packets are ready, update Tx producer idx local and on card. */
- tw32_tx_mbox((MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW), entry);
-
tp->tx_prod = entry;
- if (unlikely(tg3_tx_avail(tp) <= (MAX_SKB_FRAGS + 1))) {
- netif_stop_queue(dev);
- if (tg3_tx_avail(tp) > TG3_TX_WAKEUP_THRESH(tp))
- netif_wake_queue(tp->dev);
+ return NETDEV_TX_OK;
+}
+
+static int tg3_start_bxmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tg3 *tp = netdev_priv(dev);
+
+ if (unlikely(tg3_tx_avail(tp) <= (skb_shinfo(skb)->nr_frags + 1))) {
+ if (!netif_queue_stopped(dev)) {
+ netif_stop_queue(dev);
+ dev->xmit_win = 1;
+
+ /* This is a hard error, log it. */
+ printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
+ "queue awake!\n", dev->name);
+ }
+ return NETDEV_TX_BUSY;
}
-out_unlock:
- mmiowb();
+ return tg3_enqueue_buggy(skb, dev);
+}
- dev->trans_start = jiffies;
+static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tg3 *tp = netdev_priv(dev);
+ int ret = tg3_prep_bug_frame(skb, dev);
- return NETDEV_TX_OK;
+ if (unlikely(ret != NETDEV_TX_OK))
+ return NETDEV_TX_OK;
+
+ /* We are running in BH disabled context with netif_tx_lock
+ * and TX reclaim runs via tp->poll inside of a software
+ * interrupt. Furthermore, IRQ processing runs lockless so we have
+ * no IRQ context deadlocks to worry about either. Rejoice!
+ */
+ if (unlikely(tg3_tx_avail(tp) <= (skb_shinfo(skb)->nr_frags + 1))) {
+ if (!netif_queue_stopped(dev)) {
+ netif_stop_queue(dev);
+ dev->xmit_win = 1;
+
+ /* This is a hard error, log it. */
+ printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
+ "queue awake!\n", dev->name);
+ }
+ return NETDEV_TX_BUSY;
+ }
+
+ ret = tg3_enqueue_buggy(skb, dev);
+ if (ret == NETDEV_TX_OK)
+ tg3_kick_DMA(dev);
+
+ return ret;
}
static inline void tg3_set_mtu(struct net_device *dev, struct tg3 *tp,
@@ -11039,15 +11153,19 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
else
tp->tg3_flags &= ~TG3_FLAG_POLL_SERDES;
+ tp->dev->hard_end_xmit = tg3_kick_DMA;
/* All chips before 5787 can get confused if TX buffers
* straddle the 4GB address boundary in some cases.
*/
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906)
- tp->dev->hard_start_xmit = tg3_start_xmit;
- else
- tp->dev->hard_start_xmit = tg3_start_xmit_dma_bug;
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) {
+ tp->dev->hard_start_xmit = tg3_start_bxmit;
+ tp->dev->hard_prep_xmit = tg3_prep_frame;
+ } else {
+ tp->dev->hard_start_xmit = tg3_start_bxmit_dma_bug;
+ tp->dev->hard_prep_xmit = tg3_prep_bug_frame;
+ }
tp->rx_offset = 2;
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5701 &&
@@ -11895,6 +12013,8 @@ static int __devinit tg3_init_one(struct pci_dev *pdev,
dev->watchdog_timeo = TG3_TX_TIMEOUT;
dev->change_mtu = tg3_change_mtu;
dev->irq = pdev->irq;
+ dev->features |= NETIF_F_BTX;
+ dev->xmit_win = tp->tx_pending >> 2;
#ifdef CONFIG_NET_POLL_CONTROLLER
dev->poll_controller = tg3_poll_controller;
#endif
