* [PATCH v2 3/7] via-velocity: Implement NAPI support
From: Simon Kagstrom @ 2009-11-23 14:31 UTC (permalink / raw)
To: netdev; +Cc: davem, davej, shemminger, romieu
In-Reply-To: <20091123152724.2871cf4d@marrow.netinsight.se>
This patch adds NAPI support for VIA velocity. The new velocity_poll
function also pairs tx/rx handling twice which improves perforamance on
some workloads (e.g., netperf UDP_STREAM) significantly (that part is
from the VIA driver).
Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
---
drivers/net/via-velocity.c | 81 +++++++++++++++++++++++++-------------------
drivers/net/via-velocity.h | 3 ++
2 files changed, 49 insertions(+), 35 deletions(-)
diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c
index 85ee898..668cdf6 100644
--- a/drivers/net/via-velocity.c
+++ b/drivers/net/via-velocity.c
@@ -354,12 +354,6 @@ VELOCITY_PARAM(ValPktLen, "Receiving or Drop invalid 802.3 frame");
*/
VELOCITY_PARAM(wol_opts, "Wake On Lan options");
-#define INT_WORKS_DEF 20
-#define INT_WORKS_MIN 10
-#define INT_WORKS_MAX 64
-
-VELOCITY_PARAM(int_works, "Number of packets per interrupt services");
-
static int rx_copybreak = 200;
module_param(rx_copybreak, int, 0644);
MODULE_PARM_DESC(rx_copybreak, "Copy breakpoint for copy-only-tiny-frames");
@@ -516,7 +510,6 @@ static void __devinit velocity_get_options(struct velocity_opt *opts, int index,
velocity_set_bool_opt(&opts->flags, ValPktLen[index], VAL_PKT_LEN_DEF, VELOCITY_FLAGS_VAL_PKT_LEN, "ValPktLen", devname);
velocity_set_int_opt((int *) &opts->spd_dpx, speed_duplex[index], MED_LNK_MIN, MED_LNK_MAX, MED_LNK_DEF, "Media link mode", devname);
velocity_set_int_opt((int *) &opts->wol_opts, wol_opts[index], WOL_OPT_MIN, WOL_OPT_MAX, WOL_OPT_DEF, "Wake On Lan options", devname);
- velocity_set_int_opt((int *) &opts->int_works, int_works[index], INT_WORKS_MIN, INT_WORKS_MAX, INT_WORKS_DEF, "Interrupt service works", devname);
opts->numrx = (opts->numrx & ~3);
}
@@ -2123,13 +2116,14 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx)
* any received packets from the receive queue. Hand the ring
* slots back to the adapter for reuse.
*/
-static int velocity_rx_srv(struct velocity_info *vptr, int status)
+static int velocity_rx_srv(struct velocity_info *vptr, int status,
+ int budget_left)
{
struct net_device_stats *stats = &vptr->dev->stats;
int rd_curr = vptr->rx.curr;
int works = 0;
- do {
+ while (works < budget_left) {
struct rx_desc *rd = vptr->rx.ring + rd_curr;
if (!vptr->rx.info[rd_curr].skb)
@@ -2160,7 +2154,8 @@ static int velocity_rx_srv(struct velocity_info *vptr, int status)
rd_curr++;
if (rd_curr >= vptr->options.numrx)
rd_curr = 0;
- } while (++works <= 15);
+ works++;
+ }
vptr->rx.curr = rd_curr;
@@ -2171,6 +2166,40 @@ static int velocity_rx_srv(struct velocity_info *vptr, int status)
return works;
}
+static int velocity_poll(struct napi_struct *napi, int budget)
+{
+ struct velocity_info *vptr = container_of(napi,
+ struct velocity_info, napi);
+ unsigned int rx_done;
+ u32 isr_status;
+
+ spin_lock(&vptr->lock);
+ isr_status = mac_read_isr(vptr->mac_regs);
+
+ /* Ack the interrupt */
+ mac_write_isr(vptr->mac_regs, isr_status);
+ if (isr_status & (~(ISR_PRXI | ISR_PPRXI | ISR_PTXI | ISR_PPTXI)))
+ velocity_error(vptr, isr_status);
+
+ /*
+ * Do rx and tx twice for performance (taken from the VIA
+ * out-of-tree driver).
+ */
+ rx_done = velocity_rx_srv(vptr, isr_status, budget / 2);
+ velocity_tx_srv(vptr, isr_status);
+ rx_done += velocity_rx_srv(vptr, isr_status, budget - rx_done);
+ velocity_tx_srv(vptr, isr_status);
+
+ spin_unlock(&vptr->lock);
+
+ /* If budget not fully consumed, exit the polling mode */
+ if (rx_done < budget) {
+ napi_complete(napi);
+ mac_enable_int(vptr->mac_regs);
+ }
+
+ return rx_done;
+}
/**
* velocity_intr - interrupt callback
@@ -2187,8 +2216,6 @@ static irqreturn_t velocity_intr(int irq, void *dev_instance)
struct net_device *dev = dev_instance;
struct velocity_info *vptr = netdev_priv(dev);
u32 isr_status;
- int max_count = 0;
-
spin_lock(&vptr->lock);
isr_status = mac_read_isr(vptr->mac_regs);
@@ -2199,32 +2226,13 @@ static irqreturn_t velocity_intr(int irq, void *dev_instance)
return IRQ_NONE;
}
- mac_disable_int(vptr->mac_regs);
-
- /*
- * Keep processing the ISR until we have completed
- * processing and the isr_status becomes zero
- */
-
- while (isr_status != 0) {
- mac_write_isr(vptr->mac_regs, isr_status);
- if (isr_status & (~(ISR_PRXI | ISR_PPRXI | ISR_PTXI | ISR_PPTXI)))
- velocity_error(vptr, isr_status);
- if (isr_status & (ISR_PRXI | ISR_PPRXI))
- max_count += velocity_rx_srv(vptr, isr_status);
- if (isr_status & (ISR_PTXI | ISR_PPTXI))
- max_count += velocity_tx_srv(vptr, isr_status);
- isr_status = mac_read_isr(vptr->mac_regs);
- if (max_count > vptr->options.int_works) {
- printk(KERN_WARNING "%s: excessive work at interrupt.\n",
- dev->name);
- max_count = 0;
- }
+ if (likely(napi_schedule_prep(&vptr->napi))) {
+ mac_disable_int(vptr->mac_regs);
+ __napi_schedule(&vptr->napi);
}
spin_unlock(&vptr->lock);
- mac_enable_int(vptr->mac_regs);
- return IRQ_HANDLED;
+ return IRQ_HANDLED;
}
/**
@@ -2264,6 +2272,7 @@ static int velocity_open(struct net_device *dev)
mac_enable_int(vptr->mac_regs);
netif_start_queue(dev);
+ napi_enable(&vptr->napi);
vptr->flags |= VELOCITY_FLAGS_OPENED;
out:
return ret;
@@ -2499,6 +2508,7 @@ static int velocity_close(struct net_device *dev)
{
struct velocity_info *vptr = netdev_priv(dev);
+ napi_disable(&vptr->napi);
netif_stop_queue(dev);
velocity_shutdown(vptr);
@@ -2818,6 +2828,7 @@ static int __devinit velocity_found1(struct pci_dev *pdev, const struct pci_devi
dev->irq = pdev->irq;
dev->netdev_ops = &velocity_netdev_ops;
dev->ethtool_ops = &velocity_ethtool_ops;
+ netif_napi_add(dev, &vptr->napi, velocity_poll, VELOCITY_NAPI_WEIGHT);
dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER |
NETIF_F_HW_VLAN_RX;
diff --git a/drivers/net/via-velocity.h b/drivers/net/via-velocity.h
index 6091946..22bfea4 100644
--- a/drivers/net/via-velocity.h
+++ b/drivers/net/via-velocity.h
@@ -32,6 +32,7 @@
#define VELOCITY_VERSION "1.14"
#define VELOCITY_IO_SIZE 256
+#define VELOCITY_NAPI_WEIGHT 64
#define PKT_BUF_SZ 1540
@@ -1564,6 +1565,8 @@ struct velocity_info {
u32 ticks;
u8 rev_id;
+
+ struct napi_struct napi;
};
/**
--
1.6.0.4
^ permalink raw reply related
* [PATCH v2 4/7] via-velocity: Change DMA_LENGTH_DEF (from the VIA driver)
From: Simon Kagstrom @ 2009-11-23 14:31 UTC (permalink / raw)
To: netdev; +Cc: davem, davej, shemminger, romieu
In-Reply-To: <20091123152724.2871cf4d@marrow.netinsight.se>
The VIA driver has changed the default for the DMA_LENGTH_DEF parameter.
Together with adaptive interrupt supression and NAPI support, this
improves performance quite a bit
Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
---
drivers/net/via-velocity.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c
index 668cdf6..06a6d80 100644
--- a/drivers/net/via-velocity.c
+++ b/drivers/net/via-velocity.c
@@ -275,7 +275,7 @@ VELOCITY_PARAM(rx_thresh, "Receive fifo threshold");
#define DMA_LENGTH_MIN 0
#define DMA_LENGTH_MAX 7
-#define DMA_LENGTH_DEF 0
+#define DMA_LENGTH_DEF 6
/* DMA_length[] is used for controlling the DMA length
0: 8 DWORDs
--
1.6.0.4
^ permalink raw reply related
* [PATCH v2 5/7] via-velocity: Re-enable transmit scatter-gather support
From: Simon Kagstrom @ 2009-11-23 14:31 UTC (permalink / raw)
To: netdev; +Cc: davem, davej, shemminger, romieu
In-Reply-To: <20091123152724.2871cf4d@marrow.netinsight.se>
The velocity hardware can handle up to 7 memory segments. This can be
turned on and off via ethtool.
Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
---
drivers/net/via-velocity.c | 88 +++++++++++++++++++++++++++++---------------
1 files changed, 58 insertions(+), 30 deletions(-)
diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c
index 06a6d80..92b41fc 100644
--- a/drivers/net/via-velocity.c
+++ b/drivers/net/via-velocity.c
@@ -9,7 +9,6 @@
*
* TODO
* rx_copybreak/alignment
- * Scatter gather
* More testing
*
* The changes are (c) Copyright 2004, Red Hat Inc. <alan@lxorguk.ukuu.org.uk>
@@ -1656,12 +1655,10 @@ out:
*/
static int velocity_init_td_ring(struct velocity_info *vptr)
{
- dma_addr_t curr;
int j;
/* Init the TD ring entries */
for (j = 0; j < vptr->tx.numq; j++) {
- curr = vptr->tx.pool_dma[j];
vptr->tx.infos[j] = kcalloc(vptr->options.numtx,
sizeof(struct velocity_td_info),
@@ -1727,21 +1724,27 @@ err_free_dma_rings_0:
* Release an transmit buffer. If the buffer was preallocated then
* recycle it, if not then unmap the buffer.
*/
-static void velocity_free_tx_buf(struct velocity_info *vptr, struct velocity_td_info *tdinfo)
+static void velocity_free_tx_buf(struct velocity_info *vptr,
+ struct velocity_td_info *tdinfo, struct tx_desc *td)
{
struct sk_buff *skb = tdinfo->skb;
- int i;
- int pktlen;
/*
* Don't unmap the pre-allocated tx_bufs
*/
if (tdinfo->skb_dma) {
+ int i;
- pktlen = max_t(unsigned int, skb->len, ETH_ZLEN);
for (i = 0; i < tdinfo->nskb_dma; i++) {
- pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i], pktlen, PCI_DMA_TODEVICE);
- tdinfo->skb_dma[i] = 0;
+ size_t pktlen = max_t(size_t, skb->len, ETH_ZLEN);
+
+ /* For scatter-gather */
+ if (skb_shinfo(skb)->nr_frags > 0)
+ pktlen = max_t(size_t, pktlen,
+ td->td_buf[i].size & ~TD_QUEUE);
+
+ pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i],
+ le16_to_cpu(pktlen), PCI_DMA_TODEVICE);
}
}
dev_kfree_skb_irq(skb);
@@ -1943,7 +1946,7 @@ static int velocity_tx_srv(struct velocity_info *vptr, u32 status)
stats->tx_packets++;
stats->tx_bytes += tdinfo->skb->len;
}
- velocity_free_tx_buf(vptr, tdinfo);
+ velocity_free_tx_buf(vptr, tdinfo, td);
vptr->tx.used[qnum]--;
}
vptr->tx.tail[qnum] = idx;
@@ -2543,14 +2546,27 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb,
struct velocity_td_info *tdinfo;
unsigned long flags;
int pktlen;
- __le16 len;
- int index;
+ int index, prev;
+ int i = 0;
if (skb_padto(skb, ETH_ZLEN))
goto out;
- pktlen = max_t(unsigned int, skb->len, ETH_ZLEN);
- len = cpu_to_le16(pktlen);
+ /* The hardware can handle at most 7 memory segments, so merge
+ * the skb if there are more */
+ if (skb_shinfo(skb)->nr_frags > 6 && __skb_linearize(skb)) {
+ kfree_skb(skb);
+ return 0;
+ }
+ /* If it's still above 6 we can't do anything */
+ if (skb_shinfo(skb)->nr_frags > 6) {
+ dev_err(&vptr->pdev->dev,
+ "via-velocity: more than 6 frags, can't send.\n");
+ return 0;
+ }
+ pktlen = skb_shinfo(skb)->nr_frags == 0 ?
+ max_t(unsigned int, skb->len, ETH_ZLEN) :
+ skb_headlen(skb);
spin_lock_irqsave(&vptr->lock, flags);
@@ -2567,11 +2583,24 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb,
*/
tdinfo->skb = skb;
tdinfo->skb_dma[0] = pci_map_single(vptr->pdev, skb->data, pktlen, PCI_DMA_TODEVICE);
- td_ptr->tdesc0.len = len;
+ td_ptr->tdesc0.len = cpu_to_le16(pktlen);
td_ptr->td_buf[0].pa_low = cpu_to_le32(tdinfo->skb_dma[0]);
td_ptr->td_buf[0].pa_high = 0;
- td_ptr->td_buf[0].size = len;
- tdinfo->nskb_dma = 1;
+ td_ptr->td_buf[0].size = cpu_to_le16(pktlen);
+
+ /* Handle fragments */
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ tdinfo->skb_dma[i + 1] = pci_map_page(vptr->pdev, frag->page,
+ frag->page_offset, frag->size,
+ PCI_DMA_TODEVICE);
+
+ td_ptr->td_buf[i + 1].pa_low = cpu_to_le32(tdinfo->skb_dma[i + 1]);
+ td_ptr->td_buf[i + 1].pa_high = 0;
+ td_ptr->td_buf[i + 1].size = cpu_to_le16(frag->size);
+ }
+ tdinfo->nskb_dma = i + 1;
td_ptr->tdesc1.cmd = TCPLS_NORMAL + (tdinfo->nskb_dma + 1) * 16;
@@ -2592,23 +2621,21 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb,
td_ptr->tdesc1.TCR |= (TCR0_UDPCK);
td_ptr->tdesc1.TCR |= TCR0_IPCK;
}
- {
- int prev = index - 1;
+ prev = index - 1;
+ if (prev < 0)
+ prev = vptr->options.numtx - 1;
+ td_ptr->tdesc0.len |= OWNED_BY_NIC;
+ vptr->tx.used[qnum]++;
+ vptr->tx.curr[qnum] = (index + 1) % vptr->options.numtx;
- if (prev < 0)
- prev = vptr->options.numtx - 1;
- td_ptr->tdesc0.len |= OWNED_BY_NIC;
- vptr->tx.used[qnum]++;
- vptr->tx.curr[qnum] = (index + 1) % vptr->options.numtx;
+ if (AVAIL_TD(vptr, qnum) < 1)
+ netif_stop_queue(dev);
- if (AVAIL_TD(vptr, qnum) < 1)
- netif_stop_queue(dev);
+ td_ptr = &(vptr->tx.rings[qnum][prev]);
+ td_ptr->td_buf[0].size |= TD_QUEUE;
+ mac_tx_queue_wake(vptr->mac_regs, qnum);
- td_ptr = &(vptr->tx.rings[qnum][prev]);
- td_ptr->td_buf[0].size |= TD_QUEUE;
- mac_tx_queue_wake(vptr->mac_regs, qnum);
- }
dev->trans_start = jiffies;
spin_unlock_irqrestore(&vptr->lock, flags);
out:
@@ -3398,6 +3425,7 @@ static const struct ethtool_ops velocity_ethtool_ops = {
.set_wol = velocity_ethtool_set_wol,
.get_msglevel = velocity_get_msglevel,
.set_msglevel = velocity_set_msglevel,
+ .set_sg = ethtool_op_set_sg,
.get_link = velocity_get_link,
.get_coalesce = velocity_get_coalesce,
.set_coalesce = velocity_set_coalesce,
--
1.6.0.4
^ permalink raw reply related
* [PATCH v2 6/7] via-velocity: Set tx checksum from ethtool instead of module parameter
From: Simon Kagstrom @ 2009-11-23 14:31 UTC (permalink / raw)
To: netdev; +Cc: davem, davej, shemminger, romieu
In-Reply-To: <20091123152724.2871cf4d@marrow.netinsight.se>
Defaults to on (as before).
Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
---
drivers/net/via-velocity.c | 18 ++++--------------
drivers/net/via-velocity.h | 1 -
2 files changed, 4 insertions(+), 15 deletions(-)
diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c
index 92b41fc..4af16ba 100644
--- a/drivers/net/via-velocity.c
+++ b/drivers/net/via-velocity.c
@@ -297,14 +297,6 @@ VELOCITY_PARAM(DMA_length, "DMA length");
*/
VELOCITY_PARAM(IP_byte_align, "Enable IP header dword aligned");
-#define TX_CSUM_DEF 1
-/* txcsum_offload[] is used for setting the checksum offload ability of NIC.
- (We only support RX checksum offload now)
- 0: disable csum_offload[checksum offload
- 1: enable checksum offload. (Default)
-*/
-VELOCITY_PARAM(txcsum_offload, "Enable transmit packet checksum offload");
-
#define FLOW_CNTL_DEF 1
#define FLOW_CNTL_MIN 1
#define FLOW_CNTL_MAX 5
@@ -503,7 +495,6 @@ static void __devinit velocity_get_options(struct velocity_opt *opts, int index,
velocity_set_int_opt(&opts->numrx, RxDescriptors[index], RX_DESC_MIN, RX_DESC_MAX, RX_DESC_DEF, "RxDescriptors", devname);
velocity_set_int_opt(&opts->numtx, TxDescriptors[index], TX_DESC_MIN, TX_DESC_MAX, TX_DESC_DEF, "TxDescriptors", devname);
- velocity_set_bool_opt(&opts->flags, txcsum_offload[index], TX_CSUM_DEF, VELOCITY_FLAGS_TX_CSUM, "txcsum_offload", devname);
velocity_set_int_opt(&opts->flow_cntl, flow_control[index], FLOW_CNTL_MIN, FLOW_CNTL_MAX, FLOW_CNTL_DEF, "flow_control", devname);
velocity_set_bool_opt(&opts->flags, IP_byte_align[index], IP_ALIG_DEF, VELOCITY_FLAGS_IP_ALIGN, "IP_byte_align", devname);
velocity_set_bool_opt(&opts->flags, ValPktLen[index], VAL_PKT_LEN_DEF, VELOCITY_FLAGS_VAL_PKT_LEN, "ValPktLen", devname);
@@ -2612,7 +2603,7 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb,
/*
* Handle hardware checksum
*/
- if ((vptr->flags & VELOCITY_FLAGS_TX_CSUM)
+ if ( (dev->features & NETIF_F_IP_CSUM)
&& (skb->ip_summed == CHECKSUM_PARTIAL)) {
const struct iphdr *ip = ip_hdr(skb);
if (ip->protocol == IPPROTO_TCP)
@@ -2858,10 +2849,7 @@ static int __devinit velocity_found1(struct pci_dev *pdev, const struct pci_devi
netif_napi_add(dev, &vptr->napi, velocity_poll, VELOCITY_NAPI_WEIGHT);
dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER |
- NETIF_F_HW_VLAN_RX;
-
- if (vptr->flags & VELOCITY_FLAGS_TX_CSUM)
- dev->features |= NETIF_F_IP_CSUM;
+ NETIF_F_HW_VLAN_RX | NETIF_F_IP_CSUM;
ret = register_netdev(dev);
if (ret < 0)
@@ -3421,6 +3409,8 @@ static const struct ethtool_ops velocity_ethtool_ops = {
.get_settings = velocity_get_settings,
.set_settings = velocity_set_settings,
.get_drvinfo = velocity_get_drvinfo,
+ .set_tx_csum = ethtool_op_set_tx_csum,
+ .get_tx_csum = ethtool_op_get_tx_csum,
.get_wol = velocity_ethtool_get_wol,
.set_wol = velocity_ethtool_set_wol,
.get_msglevel = velocity_get_msglevel,
diff --git a/drivers/net/via-velocity.h b/drivers/net/via-velocity.h
index 22bfea4..cf10801 100644
--- a/drivers/net/via-velocity.h
+++ b/drivers/net/via-velocity.h
@@ -1423,7 +1423,6 @@ enum velocity_msg_level {
*/
#define VELOCITY_FLAGS_TAGGING 0x00000001UL
-#define VELOCITY_FLAGS_TX_CSUM 0x00000002UL
#define VELOCITY_FLAGS_RX_CSUM 0x00000004UL
#define VELOCITY_FLAGS_IP_ALIGN 0x00000008UL
#define VELOCITY_FLAGS_VAL_PKT_LEN 0x00000010UL
--
1.6.0.4
^ permalink raw reply related
* [PATCH v2 7/7] via-velocity: Bump version
From: Simon Kagstrom @ 2009-11-23 14:31 UTC (permalink / raw)
To: netdev; +Cc: davem, davej, shemminger, romieu
In-Reply-To: <20091123152724.2871cf4d@marrow.netinsight.se>
Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
---
drivers/net/via-velocity.h | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/via-velocity.h b/drivers/net/via-velocity.h
index cf10801..6b5fc51 100644
--- a/drivers/net/via-velocity.h
+++ b/drivers/net/via-velocity.h
@@ -29,7 +29,7 @@
#define VELOCITY_NAME "via-velocity"
#define VELOCITY_FULL_DRV_NAM "VIA Networking Velocity Family Gigabit Ethernet Adapter Driver"
-#define VELOCITY_VERSION "1.14"
+#define VELOCITY_VERSION "1.15"
#define VELOCITY_IO_SIZE 256
#define VELOCITY_NAPI_WEIGHT 64
--
1.6.0.4
^ permalink raw reply related
* Re: ixgbe question
From: Eric Dumazet @ 2009-11-23 14:38 UTC (permalink / raw)
To: Jesper Dangaard Brouer; +Cc: Peter P Waskiewicz Jr, Linux Netdev List
In-Reply-To: <Pine.LNX.4.64.0911231500060.24347@ask.diku.dk>
Jesper Dangaard Brouer a écrit :
> How is your smp_affinity mask's set?
>
> grep . /proc/irq/*/fiber1-*/../smp_affinity
First, I tried default affinities (ffff)
Then I tried irqbalance... no more success.
Driver seems to try to handle all queues on one cpu on low trafic,
and possibly dynamically switches to a multi-cpu mode,
but as all interrupts are masked, we stay in
a NAPI context handling all queues.
And we let one cpu in flood/drops mode.
>
>
>> But only one CPU (CPU1) had a softirq running, 100%, and many frames
>> were dropped
>
> Just a hint, I use 'ethtool -S fiber1' to see how the packets gets
> distributed across the rx and tx queues.
They are correctly distributed
rx_queue_0_packets: 14119644
rx_queue_0_bytes: 847178640
rx_queue_1_packets: 14126315
rx_queue_1_bytes: 847578900
rx_queue_2_packets: 14115249
rx_queue_2_bytes: 846914940
rx_queue_3_packets: 14118146
rx_queue_3_bytes: 847088760
rx_queue_4_packets: 14130869
rx_queue_4_bytes: 847853268
rx_queue_5_packets: 14112239
rx_queue_5_bytes: 846734340
rx_queue_6_packets: 14128425
rx_queue_6_bytes: 847705500
rx_queue_7_packets: 14110587
rx_queue_7_bytes: 846635220
rx_queue_8_packets: 14117350
rx_queue_8_bytes: 847041000
rx_queue_9_packets: 14125992
rx_queue_9_bytes: 847559520
rx_queue_10_packets: 14121732
rx_queue_10_bytes: 847303920
rx_queue_11_packets: 14120997
rx_queue_11_bytes: 847259820
rx_queue_12_packets: 14125576
rx_queue_12_bytes: 847535854
rx_queue_13_packets: 14118512
rx_queue_13_bytes: 847110720
rx_queue_14_packets: 14118348
rx_queue_14_bytes: 847100880
rx_queue_15_packets: 14118647
rx_queue_15_bytes: 847118820
>
>
>
>> CLONE_SKB="clone_skb 15"
>
> Be careful with to high clone, as my experience is it will send a burst
> of clone_skb packets before the packet gets randomized again.
Yes, but 15 should be ok with 10Gb link :)
Thanks
^ permalink raw reply
* [patch]USB autosuspend for cdc-ether
From: Oliver Neukum @ 2009-11-23 15:21 UTC (permalink / raw)
To: David Brownell, stern-nwvwT67g6+6dFdvTe/nMLpVzexx5G7lz,
David S. Miller, linux-usb-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA,
"Torgny Johansson" <torgny
Hi David,
here's a new, tested version of autosuspend for cdc-ether with
a few glitches fixed. I think it addresses everything you mentioned.
Could you provide some feedback about what's wrong with it or
an acknowledgement?
Regards
Oliver
Signed-off-by: Oliver Neukum <oliver-GvhC2dPhHPQdnm+yROfE0A@public.gmane.org>
commit cb0634eee6f96fb24044c961d7dffefed7b6457e
Author: Oliver Neukum <oliver-GvhC2dPhHPQdnm+yROfE0A@public.gmane.org>
Date: Mon Nov 23 16:04:45 2009 +0100
usb:cdc-ether:implement power management for online devices
This implements USB autosuspend for cdc-ether devices that
support remote wakeup while they are online. For reception
remote wakeup and the last busy functionality of usbcore
is used.
Transmission is done with an anchor for deferred transmission
and the async pm methods of usbcore.
For devices that don't do remote wakeup power management while
offline is provided for.
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 21e1ba1..ed55024 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -411,6 +411,12 @@ static int cdc_bind(struct usbnet *dev, struct usb_interface *intf)
return 0;
}
+static int cdc_manage_power(struct usbnet *dev, int on)
+{
+ dev->intf->needs_remote_wakeup = on;
+ return 0;
+}
+
static const struct driver_info cdc_info = {
.description = "CDC Ethernet Device",
.flags = FLAG_ETHER,
@@ -418,6 +424,7 @@ static const struct driver_info cdc_info = {
.bind = cdc_bind,
.unbind = usbnet_cdc_unbind,
.status = cdc_status,
+ .manage_power = cdc_manage_power,
};
/*-------------------------------------------------------------------------*/
@@ -610,6 +617,7 @@ static struct usb_driver cdc_driver = {
.disconnect = usbnet_disconnect,
.suspend = usbnet_suspend,
.resume = usbnet_resume,
+ .supports_autosuspend = 1,
};
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index ca5ca5a..4c2d902 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -353,7 +353,8 @@ static void rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
if (netif_running (dev->net)
&& netif_device_present (dev->net)
- && !test_bit (EVENT_RX_HALT, &dev->flags)) {
+ && !test_bit (EVENT_RX_HALT, &dev->flags)
+ && !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) {
switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) {
case -EPIPE:
usbnet_defer_kevent (dev, EVENT_RX_HALT);
@@ -611,15 +612,39 @@ EXPORT_SYMBOL_GPL(usbnet_unlink_rx_urbs);
/*-------------------------------------------------------------------------*/
// precondition: never called in_interrupt
+static void usbnet_terminate_urbs(struct usbnet *dev)
+{
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK (unlink_wakeup);
+ DECLARE_WAITQUEUE (wait, current);
+ int temp;
+
+ /* ensure there are no more active urbs */
+ add_wait_queue(&unlink_wakeup, &wait);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ dev->wait = &unlink_wakeup;
+ temp = unlink_urbs(dev, &dev->txq) +
+ unlink_urbs(dev, &dev->rxq);
+
+ /* maybe wait for deletions to finish. */
+ while (!skb_queue_empty(&dev->rxq)
+ && !skb_queue_empty(&dev->txq)
+ && !skb_queue_empty(&dev->done)) {
+ schedule_timeout(UNLINK_TIMEOUT_MS);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ if (netif_msg_ifdown(dev))
+ devdbg(dev, "waited for %d urb completions",
+ temp);
+ }
+ set_current_state(TASK_RUNNING);
+ dev->wait = NULL;
+ remove_wait_queue(&unlink_wakeup, &wait);
+}
int usbnet_stop (struct net_device *net)
{
struct usbnet *dev = netdev_priv(net);
struct driver_info *info = dev->driver_info;
- int temp;
int retval;
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK (unlink_wakeup);
- DECLARE_WAITQUEUE (wait, current);
netif_stop_queue (net);
@@ -641,25 +666,8 @@ int usbnet_stop (struct net_device *net)
info->description);
}
- if (!(info->flags & FLAG_AVOID_UNLINK_URBS)) {
- /* ensure there are no more active urbs */
- add_wait_queue(&unlink_wakeup, &wait);
- dev->wait = &unlink_wakeup;
- temp = unlink_urbs(dev, &dev->txq) +
- unlink_urbs(dev, &dev->rxq);
-
- /* maybe wait for deletions to finish. */
- while (!skb_queue_empty(&dev->rxq)
- && !skb_queue_empty(&dev->txq)
- && !skb_queue_empty(&dev->done)) {
- msleep(UNLINK_TIMEOUT_MS);
- if (netif_msg_ifdown(dev))
- devdbg(dev, "waited for %d urb completions",
- temp);
- }
- dev->wait = NULL;
- remove_wait_queue(&unlink_wakeup, &wait);
- }
+ if (!(info->flags & FLAG_AVOID_UNLINK_URBS))
+ usbnet_terminate_urbs(dev);
usb_kill_urb(dev->interrupt);
@@ -672,7 +680,10 @@ int usbnet_stop (struct net_device *net)
dev->flags = 0;
del_timer_sync (&dev->delay);
tasklet_kill (&dev->bh);
- usb_autopm_put_interface(dev->intf);
+ if (info->manage_power)
+ info->manage_power(dev, 0);
+ else
+ usb_autopm_put_interface(dev->intf);
return 0;
}
@@ -753,6 +764,12 @@ int usbnet_open (struct net_device *net)
// delay posting reads until we're fully open
tasklet_schedule (&dev->bh);
+ if (info->manage_power) {
+ retval = info->manage_power(dev, 1);
+ if (retval < 0)
+ goto done;
+ usb_autopm_put_interface(dev->intf);
+ }
return retval;
done:
usb_autopm_put_interface(dev->intf);
@@ -881,11 +898,16 @@ kevent (struct work_struct *work)
/* usb_clear_halt() needs a thread context */
if (test_bit (EVENT_TX_HALT, &dev->flags)) {
unlink_urbs (dev, &dev->txq);
+ status = usb_autopm_get_interface(dev->intf);
+ if (status < 0)
+ goto fail_pipe;
status = usb_clear_halt (dev->udev, dev->out);
+ usb_autopm_put_interface(dev->intf);
if (status < 0
&& status != -EPIPE
&& status != -ESHUTDOWN) {
if (netif_msg_tx_err (dev))
+fail_pipe:
deverr (dev, "can't clear tx halt, status %d",
status);
} else {
@@ -896,11 +918,16 @@ kevent (struct work_struct *work)
}
if (test_bit (EVENT_RX_HALT, &dev->flags)) {
unlink_urbs (dev, &dev->rxq);
+ status = usb_autopm_get_interface(dev->intf);
+ if (status < 0)
+ goto fail_halt;
status = usb_clear_halt (dev->udev, dev->in);
+ usb_autopm_put_interface(dev->intf);
if (status < 0
&& status != -EPIPE
&& status != -ESHUTDOWN) {
if (netif_msg_rx_err (dev))
+fail_halt:
deverr (dev, "can't clear rx halt, status %d",
status);
} else {
@@ -919,7 +946,12 @@ kevent (struct work_struct *work)
clear_bit (EVENT_RX_MEMORY, &dev->flags);
if (urb != NULL) {
clear_bit (EVENT_RX_MEMORY, &dev->flags);
+ status = usb_autopm_get_interface(dev->intf);
+ if (status < 0)
+ goto fail_lowmem;
rx_submit (dev, urb, GFP_KERNEL);
+ usb_autopm_put_interface(dev->intf);
+fail_lowmem:
tasklet_schedule (&dev->bh);
}
}
@@ -929,7 +961,11 @@ kevent (struct work_struct *work)
int retval = 0;
clear_bit (EVENT_LINK_RESET, &dev->flags);
+ status = usb_autopm_get_interface(dev->intf);
+ if (status < 0)
+ goto skip_reset;
if(info->link_reset && (retval = info->link_reset(dev)) < 0) {
+skip_reset:
devinfo(dev, "link reset failed (%d) usbnet usb-%s-%s, %s",
retval,
dev->udev->bus->bus_name, dev->udev->devpath,
@@ -958,7 +994,7 @@ static void tx_complete (struct urb *urb)
switch (urb->status) {
case -EPIPE:
- usbnet_defer_kevent (dev, EVENT_TX_HALT);
+ usbnet_defer_kevent (dev, EVENT_TX_HALT);
break;
/* software-driven interface shutdown */
@@ -971,6 +1007,7 @@ static void tx_complete (struct urb *urb)
case -EPROTO:
case -ETIME:
case -EILSEQ:
+ usb_mark_last_busy(dev->udev);
if (!timer_pending (&dev->delay)) {
mod_timer (&dev->delay,
jiffies + THROTTLE_JIFFIES);
@@ -987,6 +1024,7 @@ static void tx_complete (struct urb *urb)
}
}
+ usb_autopm_put_interface_async(dev->intf);
urb->dev = NULL;
entry->state = tx_done;
defer_bh(dev, skb, &dev->txq);
@@ -1058,13 +1096,33 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb,
}
spin_lock_irqsave (&dev->txq.lock, flags);
+ retval = usb_autopm_get_interface_async(dev->intf);
+ if (retval < 0) {
+ spin_unlock_irqrestore (&dev->txq.lock, flags);
+ goto drop;
+ }
+
+#ifdef CONFIG_PM
+ /* if this triggers the device is still a sleep */
+ if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) {
+ /* transmission will be done in resume */
+ usb_anchor_urb(urb, &dev->deferred);
+ /* no use to process more packets */
+ netif_stop_queue(net);
+ spin_unlock_irqrestore(&dev->txq.lock, flags);
+ devdbg(dev, "Delaying transmission for resumption");
+ goto deferred;
+ }
+#endif
switch ((retval = usb_submit_urb (urb, GFP_ATOMIC))) {
case -EPIPE:
netif_stop_queue (net);
usbnet_defer_kevent (dev, EVENT_TX_HALT);
+ usb_autopm_put_interface_async(dev->intf);
break;
default:
+ usb_autopm_put_interface_async(dev->intf);
if (netif_msg_tx_err (dev))
devdbg (dev, "tx: submit urb err %d", retval);
break;
@@ -1088,6 +1146,7 @@ drop:
devdbg (dev, "> tx, len %d, type 0x%x",
length, skb->protocol);
}
+deferred:
return NETDEV_TX_OK;
}
EXPORT_SYMBOL_GPL(usbnet_start_xmit);
@@ -1255,6 +1314,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
dev->bh.func = usbnet_bh;
dev->bh.data = (unsigned long) dev;
INIT_WORK (&dev->kevent, kevent);
+ init_usb_anchor(&dev->deferred);
dev->delay.function = usbnet_bh;
dev->delay.data = (unsigned long) dev;
init_timer (&dev->delay);
@@ -1363,13 +1423,23 @@ int usbnet_suspend (struct usb_interface *intf, pm_message_t message)
struct usbnet *dev = usb_get_intfdata(intf);
if (!dev->suspend_count++) {
+ spin_lock_irq(&dev->txq.lock);
+ /* don't autosuspend while transmitting */
+ if (dev->txq.qlen && (message.event & PM_EVENT_AUTO)) {
+ spin_unlock_irq(&dev->txq.lock);
+ return -EBUSY;
+ } else {
+ set_bit(EVENT_DEV_ASLEEP, &dev->flags);
+ spin_unlock_irq(&dev->txq.lock);
+ }
/*
* accelerate emptying of the rx and queues, to avoid
* having everything error out.
*/
netif_device_detach (dev->net);
- (void) unlink_urbs (dev, &dev->rxq);
- (void) unlink_urbs (dev, &dev->txq);
+ usbnet_terminate_urbs(dev);
+ usb_kill_urb(dev->interrupt);
+
/*
* reattach so runtime management can use and
* wake the device
@@ -1383,10 +1453,34 @@ EXPORT_SYMBOL_GPL(usbnet_suspend);
int usbnet_resume (struct usb_interface *intf)
{
struct usbnet *dev = usb_get_intfdata(intf);
+ struct sk_buff *skb;
+ struct urb *res;
+ int retval;
+
+ if (!--dev->suspend_count) {
+ spin_lock_irq(&dev->txq.lock);
+ while ((res = usb_get_from_anchor(&dev->deferred))) {
+
+ printk(KERN_INFO"Called %s with delayed data\n", __func__);
+ skb = (struct sk_buff *)res->context;
+ retval = usb_submit_urb(res, GFP_ATOMIC);
+ if (retval < 0) {
+ dev_kfree_skb_any(skb);
+ usb_free_urb(res);
+ usb_autopm_put_interface_async(dev->intf);
+ } else {
+ dev->net->trans_start = jiffies;
+ __skb_queue_tail (&dev->txq, skb);
+ }
+ }
- if (!--dev->suspend_count)
+ smp_mb();
+ clear_bit(EVENT_DEV_ASLEEP, &dev->flags);
+ spin_unlock_irq(&dev->txq.lock);
+ if (!(dev->txq.qlen >= TX_QLEN(dev)))
+ netif_start_queue(dev->net);
tasklet_schedule (&dev->bh);
-
+ }
return 0;
}
EXPORT_SYMBOL_GPL(usbnet_resume);
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index f814730..e75ba0e 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -55,6 +55,7 @@ struct usbnet {
struct sk_buff_head done;
struct sk_buff_head rxq_pause;
struct urb *interrupt;
+ struct usb_anchor deferred;
struct tasklet_struct bh;
struct work_struct kevent;
@@ -65,6 +66,8 @@ struct usbnet {
# define EVENT_STS_SPLIT 3
# define EVENT_LINK_RESET 4
# define EVENT_RX_PAUSED 5
+# define EVENT_DEV_WAKING 6
+# define EVENT_DEV_ASLEEP 7
};
static inline struct usb_driver *driver_of(struct usb_interface *intf)
@@ -107,6 +110,9 @@ struct driver_info {
/* see if peer is connected ... can sleep */
int (*check_connect)(struct usbnet *);
+ /* (dis)activate runtime power management */
+ int (*manage_power)(struct usbnet *, int);
+
/* for status polling */
void (*status)(struct usbnet *, struct urb *);
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: [PATCH] pktgen: Fix device name compares
From: Eric Dumazet @ 2009-11-23 15:22 UTC (permalink / raw)
To: robert; +Cc: David S. Miller, Linux Netdev List, Robert Olsson
In-Reply-To: <19210.40927.13011.176740@gargle.gargle.HOWL>
robert@herjulf.net a écrit :
> Ok. So the duplicate test got wrong when the multiqueue stuff was
> added.
>
> Signed-off-by: Robert Olsson <robert.olsson@its.uu.se>
>
> Cheers
Thanks Robert
Here is an updated version because the netdev unregister event also needed some changes.
[PATCH] pktgen: Fix device name compares
Commit e6fce5b916cd7f7f7 (pktgen: multiqueue etc.) tried to relax
the pktgen restriction of one device per kernel thread, adding a '@'
tag to device names.
Problem is we dont perform check on full pktgen device name.
This allows adding many time same 'device' to pktgen thread
pgset "add_device eth0@0"
one session later :
pgset "add_device eth0@0"
(This doesnt find previous device)
This consumes ~1.5 MBytes of vmalloc memory per round and also triggers
this warning :
[ 673.186380] proc_dir_entry 'pktgen/eth0@0' already registered
[ 673.186383] Modules linked in: pktgen ixgbe ehci_hcd psmouse mdio mousedev evdev [last unloaded: pktgen]
[ 673.186406] Pid: 6219, comm: bash Tainted: G W 2.6.32-rc7-03302-g41cec6f-dirty #16
[ 673.186410] Call Trace:
[ 673.186417] [<ffffffff8104a29b>] warn_slowpath_common+0x7b/0xc0
[ 673.186422] [<ffffffff8104a341>] warn_slowpath_fmt+0x41/0x50
[ 673.186426] [<ffffffff8114e789>] proc_register+0x109/0x210
[ 673.186433] [<ffffffff8100bf2e>] ? apic_timer_interrupt+0xe/0x20
[ 673.186438] [<ffffffff8114e905>] proc_create_data+0x75/0xd0
[ 673.186444] [<ffffffffa006ad38>] pktgen_thread_write+0x568/0x640 [pktgen]
[ 673.186449] [<ffffffffa006a7d0>] ? pktgen_thread_write+0x0/0x640 [pktgen]
[ 673.186453] [<ffffffff81149144>] proc_reg_write+0x84/0xc0
[ 673.186458] [<ffffffff810f5a58>] vfs_write+0xb8/0x180
[ 673.186463] [<ffffffff810f5c11>] sys_write+0x51/0x90
[ 673.186468] [<ffffffff8100b51b>] system_call_fastpath+0x16/0x1b
[ 673.186470] ---[ end trace ccbb991b0a8d994d ]---
Solution to this problem is to use a odevname field (includes @ tag and suffix),
instead of using netdevice name.
This also permits clean unloading of NIC drivers.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/core/pktgen.c | 30 +++++++++++++++++++-----------
1 file changed, 19 insertions(+), 11 deletions(-)
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index d38470a..e23f494 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -364,6 +364,7 @@ struct pktgen_dev {
* device name (not when the inject is
* started as it used to do.)
*/
+ char odevname[32];
struct flow_state *flows;
unsigned cflows; /* Concurrent flows (config) */
unsigned lflow; /* Flow length (config) */
@@ -427,7 +428,7 @@ static const char version[] =
static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i);
static int pktgen_add_device(struct pktgen_thread *t, const char *ifname);
static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
- const char *ifname);
+ const char *ifname, bool exact);
static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
static void pktgen_run_all_threads(void);
static void pktgen_reset_all_threads(void);
@@ -529,7 +530,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
seq_printf(seq,
" frags: %d delay: %llu clone_skb: %d ifname: %s\n",
pkt_dev->nfrags, (unsigned long long) pkt_dev->delay,
- pkt_dev->clone_skb, pkt_dev->odev->name);
+ pkt_dev->clone_skb, pkt_dev->odevname);
seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows,
pkt_dev->lflow);
@@ -1689,13 +1690,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
if_lock(t);
list_for_each_entry(pkt_dev, &t->if_list, list)
if (pkt_dev->running)
- seq_printf(seq, "%s ", pkt_dev->odev->name);
+ seq_printf(seq, "%s ", pkt_dev->odevname);
seq_printf(seq, "\nStopped: ");
list_for_each_entry(pkt_dev, &t->if_list, list)
if (!pkt_dev->running)
- seq_printf(seq, "%s ", pkt_dev->odev->name);
+ seq_printf(seq, "%s ", pkt_dev->odevname);
if (t->result[0])
seq_printf(seq, "\nResult: %s\n", t->result);
@@ -1818,9 +1819,10 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove)
{
struct pktgen_thread *t;
struct pktgen_dev *pkt_dev = NULL;
+ bool exact = (remove == FIND);
list_for_each_entry(t, &pktgen_threads, th_list) {
- pkt_dev = pktgen_find_dev(t, ifname);
+ pkt_dev = pktgen_find_dev(t, ifname, exact);
if (pkt_dev) {
if (remove) {
if_lock(t);
@@ -1995,7 +1997,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
"queue_map_min (zero-based) (%d) exceeds valid range "
"[0 - %d] for (%d) queues on %s, resetting\n",
pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq,
- pkt_dev->odev->name);
+ pkt_dev->odevname);
pkt_dev->queue_map_min = ntxq - 1;
}
if (pkt_dev->queue_map_max >= ntxq) {
@@ -2003,7 +2005,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
"queue_map_max (zero-based) (%d) exceeds valid range "
"[0 - %d] for (%d) queues on %s, resetting\n",
pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq,
- pkt_dev->odev->name);
+ pkt_dev->odevname);
pkt_dev->queue_map_max = ntxq - 1;
}
@@ -3263,7 +3265,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev)
if (!pkt_dev->running) {
printk(KERN_WARNING "pktgen: interface: %s is already "
- "stopped\n", pkt_dev->odev->name);
+ "stopped\n", pkt_dev->odevname);
return -EINVAL;
}
@@ -3467,7 +3469,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
default: /* Drivers are not supposed to return other values! */
if (net_ratelimit())
pr_info("pktgen: %s xmit error: %d\n",
- odev->name, ret);
+ pkt_dev->odevname, ret);
pkt_dev->errors++;
/* fallthru */
case NETDEV_TX_LOCKED:
@@ -3570,13 +3572,18 @@ static int pktgen_thread_worker(void *arg)
}
static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
- const char *ifname)
+ const char *ifname, bool exact)
{
struct pktgen_dev *p, *pkt_dev = NULL;
+ size_t len = strlen(ifname);
if_lock(t);
list_for_each_entry(p, &t->if_list, list)
- if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) {
+ if (strncmp(p->odevname, ifname, len) == 0) {
+ if (p->odevname[len]) {
+ if (exact || p->odevname[len] != '@')
+ continue;
+ }
pkt_dev = p;
break;
}
@@ -3632,6 +3639,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
if (!pkt_dev)
return -ENOMEM;
+ strcpy(pkt_dev->odevname, ifname);
pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state));
if (pkt_dev->flows == NULL) {
kfree(pkt_dev);
^ permalink raw reply related
* Re: [PATCH 1/1] Defer skb allocation for both mergeable buffers and big packets in virtio_net
From: Shirley Ma @ 2009-11-23 16:07 UTC (permalink / raw)
To: Rusty Russell
Cc: Eric Dumazet, Michael S. Tsirkin, Avi Kivity, netdev, kvm,
linux-kernel
In-Reply-To: <200911231138.30755.rusty@rustcorp.com.au>
On Mon, 2009-11-23 at 11:38 +1030, Rusty Russell wrote:
> How about:
> struct page *end;
>
> /* Find end of list, sew whole thing into vi->pages. */
> for (end = page; end->private; end = (struct page
> *)end->private);
> end->private = (unsigned long)vi->pages;
> vi->pages = page;
Yes, this looks nicer.
> > +void virtio_free_pages(void *buf)
>
> This is a terrible name; it's specific to virtio_net, plus it should
> be
> static. Just "free_pages" should be sufficient here I think.
>
> This smells a lot like a for loop to me?
>
> struct page *i, *next;
>
> for (i = buf; next; i = next) {
> next = (struct page *)i->private;
> __free_pages(i, 0);
> }
Agree, will change it.
> > +static int set_skb_frags(struct sk_buff *skb, struct page *page,
> > + int offset, int len)
>
> A better name might be "skb_add_frag()"?
OK.
> > + skb = (struct sk_buff *)buf;
> This cast is unnecessary, but a comment would be nice:
> /* Simple case: the pointer is the 1514-byte skb */
>
> > + } else {
Without this cast there is a compile warning.
> And a matching comment here:
>
> /* The pointer is a chain of pages. */
>
OK.
> > + if (unlikely(!skb)) {
> > + dev->stats.rx_dropped++;
>
> Does this mean we leak all those pages? Shouldn't we give_pages()
> here?
Yes, it should call give_pages here.
> > + offset = hdr_len + 6;
>
> Really? I can't see where the current driver does this 6 byte offset.
> There
> should be a header, then the packet...
> Ah, I see below that you set things up this way. The better way to do
> this
> is to create a new structure to use in various places.
>
> struct padded_vnet_hdr {
> struct virtio_net_hdr hdr;
> /* This padding makes our packet 16 byte aligned */
> char padding[6];
> };
>
> However, I question whether making it 16 byte is the right thing: the
> ethernet header is 14 bytes long, so don't we want 8 bytes of padding?
Because in QEMU it requires 10 bytes header in a separately, so one page
is used to share between virtio_net_hdr header which is 10 bytes head
and rest of data. So I put 6 bytes offset here between two buffers. I
didn't look at the reason why a seperate buf is used for virtio_net_hdr
in QEMU.
> > + }
>
> I think you can move the memcpy outside the if, like so:
>
> memcpy(&hdr, p, hdr_len);
I didn't move it out, because num_buf = hdr->mhdr.num_buffers;
> > + if (!len)
> > + give_pages(vi, page);
> > + else {
> > + len = set_skb_frags(skb, page, copy + offset,
> len);
> > + /* process big packets */
> > + while (len > 0) {
> > + page = (struct page *)page->private;
> > + if (!page)
> > + break;
> > + len = set_skb_frags(skb, page, 0,
> len);
> > + }
> > + if (page && page->private)
> > + give_pages(vi, (struct page
> *)page->private);
> > }
>
> I can't help but think this statement should be one loop somehow.
> Something
> like:
>
> offset += copy;
>
> while (len) {
> len = skb_add_frag(skb, page, offset, len);
> page = (struct page *)page->private;
> offset = 0;
> }
> if (page)
> give_pages(vi, page);
I was little bit worried about qemu messed up len (i saw code in
mergeable buffer checking len > PAGE_SIZE), so I put page checking
inside. I will change it outside if checking len is enough.
> > -static bool try_fill_recv_maxbufs(struct virtnet_info *vi, gfp_t
> gfp)
> > +/* Returns false if we couldn't fill entirely (OOM). */
> > +static bool try_fill_recv(struct virtnet_info *vi, gfp_t gfp)
>
> The result of trying to merge all the cases here is messy. I'd split
> it
> inside the loop into: add_recvbuf_small(vi, gfp), add_recvbuf_big(vi,
> gfp)
> and add_recvbuf_mergeable(vi, gfp).
>
> It'll also be easier for me to review each case then, as well as
> getting
> rid of the big packets if we decide to do that later. You could even
> do
> that split as a separate patch, before this one.
Ok, will separate it.
> destroy_buf should really be called destroy_bufs(). And I don't think
> you
> use the vi->recv skb list in this case at all, so the loop which
> purges those
> should be under an "else {" of this branch.
Yes.
> This new parameter should be introduced as a separate patch. It
> should also be
> called destroy_bufs. It also returns an unsigned int. I would call
> the callback
> something a little more informative, such as "destroy"; here and in
> the header.
Ok.
> ret is a bad name for this; how about buf?
Sure.
> Overall, the patch looks good. But it would have been nicer if it
> were
> split into several parts: cleanups, new infrastructure, then the
> actual
> allocation change.
I will try to separate this patch.
Thanks
Shirley
^ permalink raw reply
* Re: [PATCH 1/1] Defer skb allocation for both mergeable buffers and big packets in virtio_net
From: Shirley Ma @ 2009-11-23 16:18 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Eric Dumazet, Avi Kivity, Rusty Russell, netdev, kvm,
linux-kernel
In-Reply-To: <20091123094323.GA3748@redhat.com>
On Mon, 2009-11-23 at 11:43 +0200, Michael S. Tsirkin wrote:
> should be !npage->private
> and nesting is too deep here:
> this is cleaner in a give_a_page subroutine
> as it was.
This will be addressed with Rusty's comment.
> > + /* use private to chain big packets */
>
> packets? or pages?
Will change it to chain pages for big packets
> > + p->private = (unsigned long)0;
>
> the comment is not really helpful:
> you say you use private to chain but 0 does not
> chain anything. You also do not need the cast to long?
Ok.
> > + if (len > (PAGE_SIZE - f->page_offset))
>
> brackets around math are not needed.
OK.
> typo
>
> > + * header and data */
Got it.
> please think of a way to get rid of magic constants like 6 and 2
> here and elsewhere.
Will do.
> replace MAX_SKB_FRAGS + 2 with something symbolic? We have it in 2 palces now.
> And comment.
Ok, I can change it.
> terrible goto based loop
> move stuff into subfunction, it will be much
> more manageable, and convert this to a simple
> for loop.
Will change it to different functions based on Rusty's comment.
> and here it is MAX_SKB_FRAGS + 1
I think I should use MAX_SKB_FRAGS + 2 instead. Now I only use
MAX_SKB_FRAGS + 1 but allocated + 2.
> > + page->private = (unsigned long)first_page;
> > + first_page = page;
> > + if (--i == 1) {
>
> this is pretty hairy ... has to be this way?
> What you are trying to do here
> is fill buffer with pages, in a loop, with first one
> using a partial page, and then add it.
> Is that it?
Yes.
> So please code this in a straight forward manner.
> it should be as simple as:
> offset = XXX
> for (i = 0; i < MAX_SKB_FRAGS + 2; ++i) {
>
> sg_set_buf(sg + i, p + offset, PAGE_SIZE - offset);
> offset = 0;
>
> }
Ok, looks more neat.
> space around +
> sg + 1 here is same as &sg[i] in fact?
Ok.
> callback -> destructor?
Ok.
I will integrate these comments with Rusty's and resubmit the patch set.
Thanks
Shirley
^ permalink raw reply
* Re: A generic kernel compatibilty code
From: Luis R. Rodriguez @ 2009-11-23 16:20 UTC (permalink / raw)
To: Ben Hutchings; +Cc: linux-kernel, linux-wireless, netdev
In-Reply-To: <1258982793.2845.13.camel@achroite.uk.solarflarecom.com>
On Mon, Nov 23, 2009 at 5:26 AM, Ben Hutchings
<bhutchings@solarflare.com> wrote:
> On Fri, 2009-11-20 at 13:07 -0800, Luis R. Rodriguez wrote:
>> On Fri, Nov 20, 2009 at 1:00 PM, Ben Hutchings
>> <bhutchings@solarflare.com> wrote:
>> > On Fri, 2009-11-20 at 12:45 -0800, Luis R. Rodriguez wrote:
>> >> Everyone and their mother reinvents the wheel when it comes to
>> >> backporting kernel modules. It a painful job and it seems to me an
>> >> alternative is possible. If we can write generic compatibilty code for
>> >> a new routine introduced on the next kernel how about just merging it
>> >> to the kernel under some generic compat module. This would be
>> >> completey ignored by everyone using the stable kernel but can be
>> >> copied by anyone doing backport work.
>> >>
>> >> So I'm thinking something as simple as a generic compat/comat.ko with
>> >> compat-2.6.32.[ch] files.
>> >>
>> >> We've already backported everything needed for wireless drivers under
>> >> compat-wireless under this format down to even 2.6.25.
>> > [...]
>> >
>> > If you think 2.6.25 is old then I don't think you understand the scale
>> > of the problem.
>> >
>> > OEMs still expect us to support RHEL 4 (2.6.9) and SLES 9 (2.6.5) though
>> > the latter will probably be dropped soon. Some other vendors apparently
>> > still need to support even 2.4 kernels!
>>
>> Heh understood. Well shouldn't this help with that then? Sure I'd love
>> to see the Enteprise Linux releases on 2.6.31 but that's not going to
>> happen right? Shouldn't this help then?
>
> You'd really have to ask the 'enterprise' vendors whether they'd be
> interested in working on some sort of shared forward-compat library.
OK will do thanks.
> If the library is to include a module rather than being statically linked
> into each module that needs it then there can only be one instance in
> the system.
Sure, that's the idea.
Luis
^ permalink raw reply
* Re: ixgbe question
From: robert @ 2009-11-23 18:30 UTC (permalink / raw)
To: Eric Dumazet
Cc: Jesper Dangaard Brouer, Peter P Waskiewicz Jr, Linux Netdev List
In-Reply-To: <4B0A9E4E.9010804@gmail.com>
Eric Dumazet writes:
> Jesper Dangaard Brouer a écrit :
>
> > How is your smp_affinity mask's set?
> >
> > grep . /proc/irq/*/fiber1-*/../smp_affinity
>
Weird... set clone_skb to 1 to be sure and vary dst or something so
the HW classifier selects different queues and with proper RX affinty.
You should see in /proc/net/softnet_stat something like:
012a7bb9 00000000 000000ae 00000000 00000000 00000000 00000000 00000000 00000000
01288d4c 00000000 00000049 00000000 00000000 00000000 00000000 00000000 00000000
0128fe28 00000000 00000043 00000000 00000000 00000000 00000000 00000000 00000000
01295387 00000000 00000047 00000000 00000000 00000000 00000000 00000000 00000000
0129a722 00000000 0000004a 00000000 00000000 00000000 00000000 00000000 00000000
0128c5e4 00000000 00000046 00000000 00000000 00000000 00000000 00000000 00000000
0128f718 00000000 00000043 00000000 00000000 00000000 00000000 00000000 00000000
012993e3 00000000 0000004a 00000000 00000000 00000000 00000000 00000000 00000000
Or something is...
Cheers
--ro
^ permalink raw reply
* Re: [PATCH 0/7] via-velocity performance fixes
From: Stephen Hemminger @ 2009-11-23 16:27 UTC (permalink / raw)
To: Simon Kagstrom; +Cc: netdev, davem, davej, romieu
In-Reply-To: <20091123143922.273d13f9@marrow.netinsight.se>
On Mon, 23 Nov 2009 14:39:22 +0100
Simon Kagstrom <simon.kagstrom@netinsight.net> wrote:
> while the VIA driver does
>
> ip_summed = CHECKSUM_NONE;
> if (hardware sees that this is an IP packet):
> if (hw IP checksum is OK):
> if (hw sees that this is a TCP/UDP packet):
> if (hw TCP/UDP checksum is NOT OK):
> return # Returning CHECKSUM_NONE
> ip_summed = CHECKSUM_UNNECESSARY
>
> i.e., it will return CHECKSUM_NONE also for non-TCP/UDP IP packets.
That is correct assuming hardware can only checksum TCP/UDP.
--
^ permalink raw reply
* [net-next-2.6 PATCH 1/3] ixgbe: Modify 82599 HWRSC statistics counters
From: Jeff Kirsher @ 2009-11-23 16:32 UTC (permalink / raw)
To: davem
Cc: netdev, gospo, Mallikarjuna R Chilakala, Peter P Waskiewicz Jr,
Jeff Kirsher
From: Mallikarjuna R Chilakala <mallikarjuna.chilakala@intel.com>
Divide 82599 HWRSC counters into aggregated and flushed to count number of
packets getting coalesced per TCP connection.
Signed-off-by: Mallikarjuna R Chilakala <mallikarjuna.chilakala@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ixgbe/ixgbe.h | 4 +++-
drivers/net/ixgbe/ixgbe_ethtool.c | 3 ++-
drivers/net/ixgbe/ixgbe_main.c | 25 +++++++++++++++++++------
3 files changed, 24 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 7eb08a6..76b052f 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -159,6 +159,7 @@ struct ixgbe_ring {
struct ixgbe_queue_stats stats;
unsigned long reinit_state;
u64 rsc_count; /* stat for coalesced packets */
+ u64 rsc_flush; /* stats for flushed packets */
unsigned int size; /* length in bytes */
dma_addr_t dma; /* phys. address of descriptor ring */
@@ -375,7 +376,8 @@ struct ixgbe_adapter {
#ifdef IXGBE_FCOE
struct ixgbe_fcoe fcoe;
#endif /* IXGBE_FCOE */
- u64 rsc_count;
+ u64 rsc_total_count;
+ u64 rsc_total_flush;
u32 wol;
u16 eeprom_version;
};
diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c
index 74f04e1..84ab4db 100644
--- a/drivers/net/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ixgbe/ixgbe_ethtool.c
@@ -79,7 +79,8 @@ static struct ixgbe_stats ixgbe_gstrings_stats[] = {
{"rx_over_errors", IXGBE_NETDEV_STAT(stats.rx_over_errors)},
{"rx_crc_errors", IXGBE_NETDEV_STAT(stats.rx_crc_errors)},
{"rx_frame_errors", IXGBE_NETDEV_STAT(stats.rx_frame_errors)},
- {"hw_rsc_count", IXGBE_STAT(rsc_count)},
+ {"hw_rsc_aggregated", IXGBE_STAT(rsc_total_count)},
+ {"hw_rsc_flushed", IXGBE_STAT(rsc_total_flush)},
{"fdir_match", IXGBE_STAT(stats.fdirmatch)},
{"fdir_miss", IXGBE_STAT(stats.fdirmiss)},
{"rx_fifo_errors", IXGBE_NETDEV_STAT(stats.rx_fifo_errors)},
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index ebcec30..ffd1f16 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -729,12 +729,14 @@ static inline u32 ixgbe_get_rsc_count(union ixgbe_adv_rx_desc *rx_desc)
/**
* ixgbe_transform_rsc_queue - change rsc queue into a full packet
* @skb: pointer to the last skb in the rsc queue
+ * @count: pointer to number of packets coalesced in this context
*
* This function changes a queue full of hw rsc buffers into a completed
* packet. It uses the ->prev pointers to find the first packet and then
* turns it into the frag list owner.
**/
-static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb)
+static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb,
+ u64 *count)
{
unsigned int frag_list_size = 0;
@@ -743,6 +745,7 @@ static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb)
frag_list_size += skb->len;
skb->prev = NULL;
skb = prev;
+ *count += 1;
}
skb_shinfo(skb)->frag_list = skb->next;
@@ -845,14 +848,20 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
u32 nextp = (staterr & IXGBE_RXDADV_NEXTP_MASK) >>
IXGBE_RXDADV_NEXTP_SHIFT;
next_buffer = &rx_ring->rx_buffer_info[nextp];
- rx_ring->rsc_count += (rsc_count - 1);
} else {
next_buffer = &rx_ring->rx_buffer_info[i];
}
if (staterr & IXGBE_RXD_STAT_EOP) {
if (skb->prev)
- skb = ixgbe_transform_rsc_queue(skb);
+ skb = ixgbe_transform_rsc_queue(skb, &(rx_ring->rsc_count));
+ if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
+ if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED)
+ rx_ring->rsc_count += skb_shinfo(skb)->nr_frags;
+ else
+ rx_ring->rsc_count++;
+ rx_ring->rsc_flush++;
+ }
rx_ring->stats.packets++;
rx_ring->stats.bytes += skb->len;
} else {
@@ -4474,14 +4483,18 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
u64 total_mpc = 0;
u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot;
- if (hw->mac.type == ixgbe_mac_82599EB) {
+ if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
u64 rsc_count = 0;
+ u64 rsc_flush = 0;
for (i = 0; i < 16; i++)
adapter->hw_rx_no_dma_resources +=
IXGBE_READ_REG(hw, IXGBE_QPRDC(i));
- for (i = 0; i < adapter->num_rx_queues; i++)
+ for (i = 0; i < adapter->num_rx_queues; i++) {
rsc_count += adapter->rx_ring[i].rsc_count;
- adapter->rsc_count = rsc_count;
+ rsc_flush += adapter->rx_ring[i].rsc_flush;
+ }
+ adapter->rsc_total_count = rsc_count;
+ adapter->rsc_total_flush = rsc_flush;
}
adapter->stats.crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS);
^ permalink raw reply related
* [net-next-2.6 PATCH 3/3] ixgbe: Only set/clear VFE in ixgbe_set_rx_mode
From: Jeff Kirsher @ 2009-11-23 16:32 UTC (permalink / raw)
To: davem
Cc: netdev, gospo, Mallikarjuna R Chilakala, Peter P Waskiewicz Jr,
Jeff Kirsher
In-Reply-To: <20091123163145.19706.37720.stgit@localhost.localdomain>
From: Alexander Duyck <alexander.h.duyck@intel.com>
There appears to be a stray setting of the VFE bit when registering vlans.
This should not be done as vlan filtering should be enabled any time the
interface is not in promiscous mode
Signed-off-by: Mallikarjuna R Chilakala <mallikarjuna.chilakala@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ixgbe/ixgbe_main.c | 18 ++++++++++--------
1 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index a3a2a9a..5182b28 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -2336,23 +2336,25 @@ static void ixgbe_vlan_rx_register(struct net_device *netdev,
* not in DCB mode.
*/
ctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_VLNCTRL);
+
+ /* Disable CFI check */
+ ctrl &= ~IXGBE_VLNCTRL_CFIEN;
+
+ /* enable VLAN tag stripping */
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
- ctrl |= IXGBE_VLNCTRL_VME | IXGBE_VLNCTRL_VFE;
- ctrl &= ~IXGBE_VLNCTRL_CFIEN;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_VLNCTRL, ctrl);
+ ctrl |= IXGBE_VLNCTRL_VME;
} else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
- ctrl |= IXGBE_VLNCTRL_VFE;
- /* enable VLAN tag insert/strip */
- ctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_VLNCTRL);
- ctrl &= ~IXGBE_VLNCTRL_CFIEN;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_VLNCTRL, ctrl);
for (i = 0; i < adapter->num_rx_queues; i++) {
+ u32 ctrl;
j = adapter->rx_ring[i].reg_idx;
ctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_RXDCTL(j));
ctrl |= IXGBE_RXDCTL_VME;
IXGBE_WRITE_REG(&adapter->hw, IXGBE_RXDCTL(j), ctrl);
}
}
+
+ IXGBE_WRITE_REG(&adapter->hw, IXGBE_VLNCTRL, ctrl);
+
ixgbe_vlan_rx_add_vid(netdev, 0);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
^ permalink raw reply related
* Re: ixgbe question
From: Eric Dumazet @ 2009-11-23 16:59 UTC (permalink / raw)
To: robert; +Cc: Jesper Dangaard Brouer, Peter P Waskiewicz Jr, Linux Netdev List
In-Reply-To: <19210.54486.353397.804028@gargle.gargle.HOWL>
robert@herjulf.net a écrit :
> Eric Dumazet writes:
>
> > Jesper Dangaard Brouer a écrit :
> >
> > > How is your smp_affinity mask's set?
> > >
> > > grep . /proc/irq/*/fiber1-*/../smp_affinity
> >
>
> Weird... set clone_skb to 1 to be sure and vary dst or something so
> the HW classifier selects different queues and with proper RX affinty.
>
> You should see in /proc/net/softnet_stat something like:
>
> 012a7bb9 00000000 000000ae 00000000 00000000 00000000 00000000 00000000 00000000
> 01288d4c 00000000 00000049 00000000 00000000 00000000 00000000 00000000 00000000
> 0128fe28 00000000 00000043 00000000 00000000 00000000 00000000 00000000 00000000
> 01295387 00000000 00000047 00000000 00000000 00000000 00000000 00000000 00000000
> 0129a722 00000000 0000004a 00000000 00000000 00000000 00000000 00000000 00000000
> 0128c5e4 00000000 00000046 00000000 00000000 00000000 00000000 00000000 00000000
> 0128f718 00000000 00000043 00000000 00000000 00000000 00000000 00000000 00000000
> 012993e3 00000000 0000004a 00000000 00000000 00000000 00000000 00000000 00000000
>
slone_skb set to 1, this changes nothing but slows down pktgen (obviously)
Result: OK: 117614452(c117608705+d5746) nsec, 100000000 (60byte,0frags)
850235pps 408Mb/sec (408112800bps) errors: 0
All RX processing of 16 RX queues done by CPU 1 only.
# cat /proc/net/softnet_stat ; sleep 2 ; echo "--------------";cat /proc/net/softnet_stat
0039f331 00000000 00002e10 00000000 00000000 00000000 00000000 00000000 00000000
03f2ed19 00000000 00037ca2 00000000 00000000 00000000 00000000 00000000 00000000
00000024 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000041 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000028 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000000b 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
000000c5 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000010d 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000250 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000498 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000616 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000012c 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
000000d2 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000025d 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000003c 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000127 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
--------------
0039f331 00000000 00002e10 00000000 00000000 00000000 00000000 00000000 00000000
03f66737 00000000 00038015 00000000 00000000 00000000 00000000 00000000 00000000
00000024 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000041 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000028 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000000b 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
000000c5 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000110 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000250 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000499 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000616 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000012c 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
000000d2 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000263 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0000003c 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
00000129 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
ethtool -S fiber1 (to show how my trafic is equally distributed to 16 RX queues)
rx_queue_0_packets: 4867706
rx_queue_0_bytes: 292062360
rx_queue_1_packets: 4862472
rx_queue_1_bytes: 291748320
rx_queue_2_packets: 4867111
rx_queue_2_bytes: 292026660
rx_queue_3_packets: 4859897
rx_queue_3_bytes: 291593820
rx_queue_4_packets: 4862267
rx_queue_4_bytes: 291740814
rx_queue_5_packets: 4861517
rx_queue_5_bytes: 291691020
rx_queue_6_packets: 4862699
rx_queue_6_bytes: 291761940
rx_queue_7_packets: 4860523
rx_queue_7_bytes: 291631380
rx_queue_8_packets: 4856891
rx_queue_8_bytes: 291413460
rx_queue_9_packets: 4868794
rx_queue_9_bytes: 292127640
rx_queue_10_packets: 4859099
rx_queue_10_bytes: 291545940
rx_queue_11_packets: 4867599
rx_queue_11_bytes: 292055940
rx_queue_12_packets: 4861868
rx_queue_12_bytes: 291713374
rx_queue_13_packets: 4862655
rx_queue_13_bytes: 291759300
rx_queue_14_packets: 4860798
rx_queue_14_bytes: 291647880
rx_queue_15_packets: 4860951
rx_queue_15_bytes: 291657060
perf top -C 1 -E 25
------------------------------------------------------------------------------
PerfTop: 24419 irqs/sec kernel:100.0% [100000 cycles], (all, cpu: 1)
------------------------------------------------------------------------------
samples pcnt kernel function
_______ _____ _______________
46234.00 - 24.3% : ixgbe_clean_tx_irq [ixgbe]
21134.00 - 11.1% : __slab_free
17838.00 - 9.4% : _raw_spin_lock
17086.00 - 9.0% : skb_release_head_state
9410.00 - 5.0% : ixgbe_clean_rx_irq [ixgbe]
8639.00 - 4.5% : kmem_cache_free
6910.00 - 3.6% : kfree
5743.00 - 3.0% : __ip_route_output_key
5321.00 - 2.8% : ip_route_input
3138.00 - 1.7% : ip_rcv
2179.00 - 1.1% : kmem_cache_alloc_node
2002.00 - 1.1% : __kmalloc_node_track_caller
1907.00 - 1.0% : skb_put
1807.00 - 1.0% : __xfrm_lookup
1742.00 - 0.9% : get_partial_node
1727.00 - 0.9% : csum_partial_copy_generic
1541.00 - 0.8% : add_partial
1516.00 - 0.8% : __kfree_skb
1465.00 - 0.8% : __netdev_alloc_skb
1420.00 - 0.7% : icmp_send
1222.00 - 0.6% : dev_gro_receive
1159.00 - 0.6% : fib_table_lookup
1155.00 - 0.6% : __phys_addr
1050.00 - 0.6% : skb_release_data
982.00 - 0.5% : _raw_spin_unlock
^ permalink raw reply
* Re: [PATCH] irq: Add node_affinity CPU masks for smarter irqbalance hints
From: Peter Zijlstra @ 2009-11-23 17:05 UTC (permalink / raw)
To: Peter P Waskiewicz Jr
Cc: Yong Zhang, linux-kernel@vger.kernel.org,
arjan@linux.jf.intel.com, davem@davemloft.net,
netdev@vger.kernel.org
In-Reply-To: <1258968980.2697.9.camel@ppwaskie-mobl2>
On Mon, 2009-11-23 at 01:36 -0800, Peter P Waskiewicz Jr wrote:
> This mechanism isn't going to be used by any internal kernel mechanism
> for determining interrupt placement or operation. It's purely something
> that either a driver can modify, or external script (through /proc),
> that irqbalance will make use of. If irqbalance isn't running, or the
> current version of irqbalance doesn't support reading node_affinity,
> then it won't affect the system's operation.
>
> If irqbalance does support it, it'll read whatever the supplied mask is,
> and then will try and balance interrupts within that mask. It will bail
> if the mask is invalid, or won't apply to the running system, just like
> how putting a bogus mask into smp_affinity is ignored.
>
> If there's something I'm missing beyond this with the two suggestions
> you've made (I looked into those two parameters and tried to draw
> conclusions), please let me know.
I don't see the point in adding it, if the driver wants to set a node
cpu mask it can already do that using the regular smp affinity settings.
Same for userspace.
^ permalink raw reply
* Re: [net-next-2.6 PATCH v7 5/7 RFC] TCPCT part 1e: implement socket option TCP_COOKIE_TRANSACTIONS
From: Joe Perches @ 2009-11-23 17:25 UTC (permalink / raw)
To: William Allen Simpson; +Cc: David Miller, netdev
In-Reply-To: <4B0A6EF3.8040302@gmail.com>
On Mon, 2009-11-23 at 06:16 -0500, William Allen Simpson wrote:
> Therefore, it's plain as can be that this is just more jumping through
> arbitrary and capricious hoops that others are not required to follow.
> At *thousands* of examples, including in the tcp*.c files themselves, it
> really becomes obvious that that may be a personal preference of David,
> but is *not* a tree-wide or even a net-wide coding style.
It seems similar kernel source uses are mostly historic.
Relatively little new code is added with leading || or &&.
There is some in staging/, but it normally gets removed.
> So, I'll try again now, with the assurance that this is the final hoop.
Once more into the breach or men of few words are the best men?
I'll stop typing now...
^ permalink raw reply
* Re: [net-next-2.6 PATCH v7 5/7 RFC] TCPCT part 1e: implement socket option TCP_COOKIE_TRANSACTIONS
From: David Miller @ 2009-11-23 17:49 UTC (permalink / raw)
To: william.allen.simpson; +Cc: joe, netdev
In-Reply-To: <4B0A6EF3.8040302@gmail.com>
From: William Allen Simpson <william.allen.simpson@gmail.com>
Date: Mon, 23 Nov 2009 06:16:03 -0500
> Therefore, it's plain as can be that this is just more jumping through
> arbitrary and capricious hoops that others are not required to follow.
Others, like Eric and Ilpo, don't have to jump through these hoops
because when they submit patches their code doesn't have coding
style issues like your's does.
Trust me, it's not about you, and you're not being picked out
specifically. These things would be enforced upon anyone. The only
unique aspect about you is that you seem to respond to these
requirements in the most sour manner possible rather than pleasantly
complying and thus getting your changes added to the tree.
^ permalink raw reply
* Re: netfilter: xt_limit: fix invalid return code in limit_mt_check()
From: David Miller @ 2009-11-23 17:53 UTC (permalink / raw)
To: kaber; +Cc: netfilter-devel, netdev
In-Reply-To: <4B0A838D.3020907@trash.net>
From: Patrick McHardy <kaber@trash.net>
Date: Mon, 23 Nov 2009 13:43:57 +0100
> This patch fixes an invalid return value in the limit match.
> Please apply or pull from:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6.git master
Pulled, thanks Patrick.
^ permalink raw reply
* RE: [Bug #14252] WARNING: at include/linux/skbuff.h:1382 w/ e1000
From: Tantilov, Emil S @ 2009-11-23 18:02 UTC (permalink / raw)
To: David Miller, rjw-KKrjLPT3xs0@public.gmane.org
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
kernel-testers-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
skraw-DcQCyzbjH0jQT0dZR+AlfA@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <20091119.120721.252464351.davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
David Miller wrote:
> From: "Rafael J. Wysocki" <rjw-KKrjLPT3xs0@public.gmane.org>
> Date: Tue, 17 Nov 2009 00:01:18 +0100 (CET)
>
>> This message has been generated automatically as a part of a report
>> of regressions introduced between 2.6.30 and 2.6.31.
>>
>> The following bug entry is on the current list of known regressions
>> introduced between 2.6.30 and 2.6.31. Please verify if it still
>> should be listed and let me know (either way).
>>
>>
>> Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=14252
>> Subject : WARNING: at include/linux/skbuff.h:1382 w/ e1000
>> Submitter : Stephan von Krawczynski <skraw-DcQCyzbjH0jQT0dZR+AlfA@public.gmane.org>
>> Date : 2009-09-20 11:26 (58 days old)
>> References : http://marc.info/?l=linux-kernel&m=125344599006033&w=4
>
> Please CC: netdev when reporting networking problems, thank you.
>
> Intel folks can you please take a look at this? Thanks.
I have not been able to reproduce this issue so far. I don't have the exact same HW, but I tested on stock 2.6.31 with 82541 based NIC. More than 3 days now of stress without a problem.
If the reporter can provide some additional information that may be of help:
1. cat /proc/interrupts
2. ethtool -i ethX (where ethX is the interface that is causing the problem
3. lspci -vvv
4. ethtool -e ethX
5. specific settings that may deviate from the default configuration (like MTU)
6. type of traffic that is causing the issue.
Thanks,
Emil--
To unsubscribe from this list: send the line "unsubscribe kernel-testers" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: linux-next: manual merge of the net tree with the net-current tree
From: Amit Salecha @ 2009-11-23 18:09 UTC (permalink / raw)
To: Stephen Rothwell, David Miller, netdev@vger.kernel.org
Cc: linux-next@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <20091123120043.24cf5c12.sfr@canb.auug.org.au>
Hi Stephen
This merge looks ok and I have tested it.
Thanks
Amit Salecha
-----Original Message-----
From: Stephen Rothwell [mailto:sfr@canb.auug.org.au]
Sent: Sunday, November 22, 2009 5:01 PM
To: David Miller; netdev@vger.kernel.org
Cc: linux-next@vger.kernel.org; linux-kernel@vger.kernel.org; Amit Salecha
Subject: linux-next: manual merge of the net tree with the net-current tree
Hi all,
Today's linux-next merge of the net tree got a conflict in
drivers/net/netxen/netxen_nic_init.c between commit
5d521fd36de4e61ab16a358df54c5babe153396c ("netxen: fix memory
initialization") from the net-current tree and commit
0be367bd5d10634c0836f57a684432fee935d929 ("netxen: reset sequence
changes") from the net tree.
Just context changes. I fixed it up (see below) and can carry the fix as
necessary.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
diff --cc drivers/net/netxen/netxen_nic_init.c
index 8a09043,6ee27a6..0000000
--- a/drivers/net/netxen/netxen_nic_init.c
+++ b/drivers/net/netxen/netxen_nic_init.c
@@@ -544,9 -528,8 +528,10 @@@ int netxen_pinit_from_rom(struct netxen
continue;
if (off == (ROMUSB_GLB + 0x1c)) /* MS clock */
continue;
+ if ((off & 0x0ff00000) == NETXEN_CRB_DDR_NET)
+ continue;
- if (off == (NETXEN_CRB_PEG_NET_1 + 0x18))
+ if (off == (NETXEN_CRB_PEG_NET_1 + 0x18) &&
+ !NX_IS_REVISION_P3P(adapter->ahw.revision_id))
buf[i].data = 0x1020;
/* skip the function enable register */
if (off == NETXEN_PCIE_REG(PCIE_SETUP_FUNCTION))
^ permalink raw reply
* Re: macvlan: fix gso_max_size setting
From: David Miller @ 2009-11-23 18:10 UTC (permalink / raw)
To: kaber; +Cc: netdev
In-Reply-To: <4B0A64E2.8090203@trash.net>
From: Patrick McHardy <kaber@trash.net>
Date: Mon, 23 Nov 2009 11:33:06 +0100
> Fix macvlan gso_max_size setting. Based on net-next-2.6.git.
Pretty serious defect, maybe net-2.6 material?
If someone hits this, it's going to trigger something awful.
^ permalink raw reply
* Performance of bonding driver with e1000
From: J.A. Magallón @ 2009-11-23 18:06 UTC (permalink / raw)
To: NetDev
Hi...
I have two boxes which I linked together via 2x gigabit interfaces and a
3Com switch. Each interface is:
02:0a.0 Ethernet controller: Intel Corporation 82541EI Gigabit Ethernet Controller
02:0b.0 Ethernet controller: Intel Corporation 82541EI Gigabit Ethernet Controller
I use the e1000 driver.
The switch is private for them, so there is no more taffic.
Boxes are P4-HT@2.8, 3Gb of RAM.
Both interfaces alone work pretty well (performance measured with iperf):
[ 5] local 192.168.1.2 port 5001 connected with 192.168.1.1 port 41252
[ ID] Interval Transfer Bandwidth
[ 5] 0.0-10.0 sec 1.00 GBytes 860 Mbits/sec
[ 4] local 192.168.2.2 port 5001 connected with 192.168.2.1 port 39275
[ ID] Interval Transfer Bandwidth
[ 4] 0.0-10.0 sec 1024 MBytes 858 Mbits/sec
I loaded bonding driver with no parameters, and using iperf I get:
[ 4] local 192.168.1.2 port 5001 connected with 192.168.1.1 port 41254
[ ID] Interval Transfer Bandwidth
[ 4] 0.0-10.0 sec 741 MBytes 621 Mbits/sec
In the node which receives, two instances of iftop on slave interfaces
show that load is balanced, but none flies higher than about 300 Mb/s.
Any ideas ?
If you guess something and need more info, I will provide it.
TIA
--
J.A. Magallon <jamagallon()ono!com> \ Software is like sex:
\ It's better when it's free
Mandriva Linux release 2010.0 (Cooker) for x86_64
Linux 2.6.29.3-desktop-1mnb (gcc 4.3.2 (GCC) #1 Wed May
^ permalink raw reply
* [net-next-2.6 PATCH] net/ipv4: Move && and || to end of previous line
From: Joe Perches @ 2009-11-23 18:28 UTC (permalink / raw)
To: David Miller; +Cc: william.allen.simpson, netdev
In-Reply-To: <20091122.163112.80105623.davem@davemloft.net>
On Sun, 2009-11-22 at 16:31 -0800, David Miller wrote:
> It should be of the form:
> if (x &&
> y)
>
> or:
> if (x && y)
>
> Fix patches, rather than complaints, for existing cases where things
> do not follow this pattern are certainly welcome.
Also collapsed some multiple tabs to single space.
Compiled tested only:
net/ipv4/inet_lro.c | 36 ++++++++++++++++++------------------
net/ipv4/ip_output.c | 6 ++++--
net/ipv4/ipconfig.c | 13 ++++++-------
net/ipv4/route.c | 19 ++++++++++---------
net/ipv4/tcp_htcp.c | 10 +++++-----
net/ipv4/tcp_input.c | 4 ++--
net/ipv4/tcp_lp.c | 4 ++--
net/ipv4/tcp_output.c | 4 ++--
net/ipv4/tcp_probe.c | 4 ++--
net/ipv4/tcp_veno.c | 5 ++---
net/ipv4/tcp_yeah.c | 4 ++--
net/ipv4/udp.c | 36 ++++++++++++++++++------------------
12 files changed, 73 insertions(+), 72 deletions(-)
diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c
index 6a667da..47038cb 100644
--- a/net/ipv4/inet_lro.c
+++ b/net/ipv4/inet_lro.c
@@ -64,15 +64,15 @@ static int lro_tcp_ip_check(struct iphdr *iph, struct tcphdr *tcph,
if (iph->ihl != IPH_LEN_WO_OPTIONS)
return -1;
- if (tcph->cwr || tcph->ece || tcph->urg || !tcph->ack
- || tcph->rst || tcph->syn || tcph->fin)
+ if (tcph->cwr || tcph->ece || tcph->urg || !tcph->ack ||
+ tcph->rst || tcph->syn || tcph->fin)
return -1;
if (INET_ECN_is_ce(ipv4_get_dsfield(iph)))
return -1;
- if (tcph->doff != TCPH_LEN_WO_OPTIONS
- && tcph->doff != TCPH_LEN_W_TIMESTAMP)
+ if (tcph->doff != TCPH_LEN_WO_OPTIONS &&
+ tcph->doff != TCPH_LEN_W_TIMESTAMP)
return -1;
/* check tcp options (only timestamp allowed) */
@@ -262,10 +262,10 @@ static int lro_check_tcp_conn(struct net_lro_desc *lro_desc,
struct iphdr *iph,
struct tcphdr *tcph)
{
- if ((lro_desc->iph->saddr != iph->saddr)
- || (lro_desc->iph->daddr != iph->daddr)
- || (lro_desc->tcph->source != tcph->source)
- || (lro_desc->tcph->dest != tcph->dest))
+ if ((lro_desc->iph->saddr != iph->saddr) ||
+ (lro_desc->iph->daddr != iph->daddr) ||
+ (lro_desc->tcph->source != tcph->source) ||
+ (lro_desc->tcph->dest != tcph->dest))
return -1;
return 0;
}
@@ -339,9 +339,9 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb,
u64 flags;
int vlan_hdr_len = 0;
- if (!lro_mgr->get_skb_header
- || lro_mgr->get_skb_header(skb, (void *)&iph, (void *)&tcph,
- &flags, priv))
+ if (!lro_mgr->get_skb_header ||
+ lro_mgr->get_skb_header(skb, (void *)&iph, (void *)&tcph,
+ &flags, priv))
goto out;
if (!(flags & LRO_IPV4) || !(flags & LRO_TCP))
@@ -351,8 +351,8 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb,
if (!lro_desc)
goto out;
- if ((skb->protocol == htons(ETH_P_8021Q))
- && !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID))
+ if ((skb->protocol == htons(ETH_P_8021Q)) &&
+ !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID))
vlan_hdr_len = VLAN_HLEN;
if (!lro_desc->active) { /* start new lro session */
@@ -446,9 +446,9 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr,
int hdr_len = LRO_MAX_PG_HLEN;
int vlan_hdr_len = 0;
- if (!lro_mgr->get_frag_header
- || lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph,
- (void *)&tcph, &flags, priv)) {
+ if (!lro_mgr->get_frag_header ||
+ lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph,
+ (void *)&tcph, &flags, priv)) {
mac_hdr = page_address(frags->page) + frags->page_offset;
goto out1;
}
@@ -472,8 +472,8 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr,
if (!skb)
goto out;
- if ((skb->protocol == htons(ETH_P_8021Q))
- && !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID))
+ if ((skb->protocol == htons(ETH_P_8021Q)) &&
+ !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID))
vlan_hdr_len = VLAN_HLEN;
iph = (void *)(skb->data + vlan_hdr_len);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 322b408..b78e615 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -264,9 +264,11 @@ int ip_mc_output(struct sk_buff *skb)
This check is duplicated in ip_mr_input at the moment.
*/
- && ((rt->rt_flags&RTCF_LOCAL) || !(IPCB(skb)->flags&IPSKB_FORWARDED))
+ &&
+ ((rt->rt_flags & RTCF_LOCAL) ||
+ !(IPCB(skb)->flags & IPSKB_FORWARDED))
#endif
- ) {
+ ) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb,
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index f8d04c2..4e08b7f 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1172,10 +1172,9 @@ static int __init ic_dynamic(void)
schedule_timeout_uninterruptible(1);
#ifdef IPCONFIG_DHCP
/* DHCP isn't done until we get a DHCPACK. */
- if ((ic_got_reply & IC_BOOTP)
- && (ic_proto_enabled & IC_USE_DHCP)
- && ic_dhcp_msgtype != DHCPACK)
- {
+ if ((ic_got_reply & IC_BOOTP) &&
+ (ic_proto_enabled & IC_USE_DHCP) &&
+ ic_dhcp_msgtype != DHCPACK) {
ic_got_reply = 0;
printk(",");
continue;
@@ -1344,9 +1343,9 @@ static int __init ip_auto_config(void)
*/
if (ic_myaddr == NONE ||
#ifdef CONFIG_ROOT_NFS
- (root_server_addr == NONE
- && ic_servaddr == NONE
- && ROOT_DEV == Root_NFS) ||
+ (root_server_addr == NONE &&
+ ic_servaddr == NONE &&
+ ROOT_DEV == Root_NFS) ||
#endif
ic_first_dev->next) {
#ifdef IPCONFIG_DYNAMIC
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 4284cee..7547944 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1346,9 +1346,9 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
return;
net = dev_net(dev);
- if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
- || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw)
- || ipv4_is_zeronet(new_gw))
+ if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) ||
+ ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) ||
+ ipv4_is_zeronet(new_gw))
goto reject_redirect;
if (!rt_caching(net))
@@ -2311,10 +2311,11 @@ skip_cache:
ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
- || (!ipv4_is_local_multicast(daddr) &&
- IN_DEV_MFORWARD(in_dev))
+ ||
+ (!ipv4_is_local_multicast(daddr) &&
+ IN_DEV_MFORWARD(in_dev))
#endif
- ) {
+ ) {
rcu_read_unlock();
return ip_route_input_mc(skb, daddr, saddr,
tos, dev, our);
@@ -2511,9 +2512,9 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
of another iface. --ANK
*/
- if (oldflp->oif == 0
- && (ipv4_is_multicast(oldflp->fl4_dst) ||
- oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+ if (oldflp->oif == 0 &&
+ (ipv4_is_multicast(oldflp->fl4_dst) ||
+ oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
dev_out = ip_dev_find(net, oldflp->fl4_src);
if (dev_out == NULL)
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 26d5c7f..7c94a49 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -92,8 +92,8 @@ static inline void measure_rtt(struct sock *sk, u32 srtt)
if (icsk->icsk_ca_state == TCP_CA_Open) {
if (ca->maxRTT < ca->minRTT)
ca->maxRTT = ca->minRTT;
- if (ca->maxRTT < srtt
- && srtt <= ca->maxRTT + msecs_to_jiffies(20))
+ if (ca->maxRTT < srtt &&
+ srtt <= ca->maxRTT + msecs_to_jiffies(20))
ca->maxRTT = srtt;
}
}
@@ -123,9 +123,9 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, s32 rtt
ca->packetcount += pkts_acked;
- if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1)
- && now - ca->lasttime >= ca->minRTT
- && ca->minRTT > 0) {
+ if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1) &&
+ now - ca->lasttime >= ca->minRTT &&
+ ca->minRTT > 0) {
__u32 cur_Bi = ca->packetcount * HZ / (now - ca->lasttime);
if (htcp_ccount(ca) <= 3) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc306ac..be166e0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4852,11 +4852,11 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
struct tcp_sock *tp = tcp_sk(sk);
/* More than one full frame received... */
- if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss
+ if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss &&
/* ... and right edge of window advances far enough.
* (tcp_recvmsg() will send ACK otherwise). Or...
*/
- && __tcp_select_window(sk) >= tp->rcv_wnd) ||
+ __tcp_select_window(sk) >= tp->rcv_wnd) ||
/* We ACK each frame or... */
tcp_in_quickack_mode(sk) ||
/* We have out of order data. */
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index ce3c41f..de87037 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -143,8 +143,8 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk)
goto out;
/* we can't calc remote HZ with no different!! */
- if (tp->rx_opt.rcv_tsval == lp->remote_ref_time
- || tp->rx_opt.rcv_tsecr == lp->local_ref_time)
+ if (tp->rx_opt.rcv_tsval == lp->remote_ref_time ||
+ tp->rx_opt.rcv_tsecr == lp->local_ref_time)
goto out;
m = HZ * (tp->rx_opt.rcv_tsval -
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 616c686..875bc6d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1923,8 +1923,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
* case, when window is shrunk to zero. In this case
* our retransmit serves as a zero window probe.
*/
- if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))
- && TCP_SKB_CB(skb)->seq != tp->snd_una)
+ if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
+ TCP_SKB_CB(skb)->seq != tp->snd_una)
return -EAGAIN;
if (skb->len > cur_mss) {
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 7a3cc2f..bb110c5 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -95,8 +95,8 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
/* Only update if port matches */
if ((port == 0 || ntohs(inet->inet_dport) == port ||
- ntohs(inet->inet_sport) == port)
- && (full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
+ ntohs(inet->inet_sport) == port) &&
+ (full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
spin_lock(&tcp_probe.lock);
/* If log fills, just silently drop */
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index e9bbff7..b612acf 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -165,9 +165,8 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
* every other rtt.
*/
if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- if (veno->inc
- && tp->snd_cwnd <
- tp->snd_cwnd_clamp) {
+ if (veno->inc &&
+ tp->snd_cwnd < tp->snd_cwnd_clamp) {
tp->snd_cwnd++;
veno->inc = 0;
} else
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 66b6821..a0f2403 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -157,8 +157,8 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
if (queue > TCP_YEAH_ALPHA ||
rtt - yeah->vegas.baseRTT > (yeah->vegas.baseRTT / TCP_YEAH_PHY)) {
- if (queue > TCP_YEAH_ALPHA
- && tp->snd_cwnd > yeah->reno_count) {
+ if (queue > TCP_YEAH_ALPHA &&
+ tp->snd_cwnd > yeah->reno_count) {
u32 reduction = min(queue / TCP_YEAH_GAMMA ,
tp->snd_cwnd >> TCP_YEAH_EPSILON);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1eaf575..1f95348 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -136,12 +136,12 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
struct hlist_nulls_node *node;
sk_nulls_for_each(sk2, node, &hslot->head)
- if (net_eq(sock_net(sk2), net) &&
- sk2 != sk &&
+ if (net_eq(sock_net(sk2), net) &&
+ sk2 != sk &&
(bitmap || udp_sk(sk2)->udp_port_hash == num) &&
- (!sk2->sk_reuse || !sk->sk_reuse) &&
- (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
- || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+ (!sk2->sk_reuse || !sk->sk_reuse) &&
+ (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
+ sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
(*saddr_comp)(sk, sk2)) {
if (bitmap)
__set_bit(udp_sk(sk2)->udp_port_hash >> log,
@@ -168,12 +168,12 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
spin_lock(&hslot2->lock);
udp_portaddr_for_each_entry(sk2, node, &hslot2->head)
- if (net_eq(sock_net(sk2), net) &&
- sk2 != sk &&
- (udp_sk(sk2)->udp_port_hash == num) &&
- (!sk2->sk_reuse || !sk->sk_reuse) &&
- (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
- || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+ if (net_eq(sock_net(sk2), net) &&
+ sk2 != sk &&
+ (udp_sk(sk2)->udp_port_hash == num) &&
+ (!sk2->sk_reuse || !sk->sk_reuse) &&
+ (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
+ sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
(*saddr_comp)(sk, sk2)) {
res = 1;
break;
@@ -545,13 +545,13 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
sk_nulls_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s);
- if (!net_eq(sock_net(s), net) ||
- udp_sk(s)->udp_port_hash != hnum ||
- (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
- (inet->inet_dport != rmt_port && inet->inet_dport) ||
- (inet->inet_rcv_saddr &&
- inet->inet_rcv_saddr != loc_addr) ||
- ipv6_only_sock(s) ||
+ if (!net_eq(sock_net(s), net) ||
+ udp_sk(s)->udp_port_hash != hnum ||
+ (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
+ (inet->inet_dport != rmt_port && inet->inet_dport) ||
+ (inet->inet_rcv_saddr &&
+ inet->inet_rcv_saddr != loc_addr) ||
+ ipv6_only_sock(s) ||
(s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
continue;
if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox