Re: [PATCH] af_packet: Don't use skb after dev_queue_xmit()

From: Michael Breuer
Date: Wed Jan 06 2010 - 23:01:51 EST

Next message: Valdis . Kletnieks: "Re: mmotm 2010-01-06-14-34 uploaded"
Previous message: Matt Mackall: "Re: [PATCH] netpoll: allow execution of multiple rx_hooks perinterface"
In reply to: Michael Breuer: "Re: [PATCH] af_packet: Don't use skb after dev_queue_xmit()"
Next in thread: Stephen Hemminger: "Re: [PATCH] af_packet: Don't use skb after dev_queue_xmit()"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On 1/6/2010 9:42 PM, Michael Breuer wrote:

On 1/6/2010 6:26 PM, Michael Breuer wrote:
On 1/6/2010 4:10 PM, Stephen Hemminger wrote:
On Wed, 06 Jan 2010 14:49:38 -0500
Michael Breuer<mbreuer@xxxxxxxxxx> wrote:

This patch at first behaved similarly to the previous one - seemed to be
running a bit better... until the adapter went down :(

This is the syslog output at the time the network failed:
Jan 6 14:11:01 mail kernel: sky2 0000:06:00.0: error interrupt
status=0x40000008
Jan 6 14:11:01 mail kernel: sky2 software interrupt status 0x40000008

Could you go back to baseline sky2 driver. The display code might be buggy.
These bits indicate an error in the MAC. The interrupt source enabled
is Transmit FIFO underrun.

Looking at how vendor driver handles this.
It looks like the Yukon EC_U chip doesn't really do Jumbo frames correctly.
Maybe not enough internal buffering to ensure that the whole packet
is in the chip. Of course, none of this is in the chip manual.

Does this help
--------------
--- a/drivers/net/sky2.c 2010-01-06 12:48:43.012318966 -0800
+++ b/drivers/net/sky2.c 2010-01-06 13:05:31.273987255 -0800
@@ -792,33 +792,21 @@ static void sky2_set_tx_stfwd(struct sky
{
struct net_device *dev = hw->dev[port];

- if ( (hw->chip_id == CHIP_ID_YUKON_EX&&
- hw->chip_rev != CHIP_REV_YU_EX_A0) ||
- hw->chip_id>= CHIP_ID_YUKON_FE_P) {
- /* Yukon-Extreme B0 and further Extreme devices */
- /* enable Store& Forward mode for TX */
-
- if (dev->mtu<= ETH_DATA_LEN)
- sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T),
- TX_JUMBO_DIS | TX_STFW_ENA);
-
- else
- sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T),
- TX_JUMBO_ENA| TX_STFW_ENA);
- } else {
- if (dev->mtu<= ETH_DATA_LEN)
- sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_ENA);
- else {
- /* set Tx GMAC FIFO Almost Empty Threshold */
- sky2_write32(hw, SK_REG(port, TX_GMF_AE_THR),
- (ECU_JUMBO_WM<< 16) | ECU_AE_THR);
-
- sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_DIS);
-
- /* Can't do offload because of lack of store/forward */
- dev->features&= ~(NETIF_F_TSO | NETIF_F_SG | NETIF_F_ALL_CSUM);
- }
- }
+ if ( (hw->chip_id == CHIP_ID_YUKON_EX&& hw->chip_rev != CHIP_REV_YU_EX_A0) ||
+ hw->chip_id>= CHIP_ID_YUKON_FE_P) {
+ /* Yukon-Extreme B0 and further Extreme devices */
+ /* enable Store& Forward mode for TX */
+ sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_ENA);
+ } else if (dev->mtu> ETH_DATA_LEN) {
+ /* set Tx GMAC FIFO Almost Empty Threshold */
+ sky2_write32(hw, SK_REG(port, TX_GMF_AE_THR),
+ (ECU_JUMBO_WM<< 16) | ECU_AE_THR);
+ /* disable Store& Forward mode for TX */
+ sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_DIS);
+ } else {
+ /* enable Store& Forward mode for TX */
+ sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_ENA);
+ }
}

static void sky2_mac_init(struct sky2_hw *hw, unsigned port)
@@ -2185,11 +2173,16 @@ static int sky2_change_mtu(struct net_de
if (new_mtu< ETH_ZLEN || new_mtu> ETH_JUMBO_MTU)
return -EINVAL;

+ /* MTU> 1500 on yukon FE and FE+ not allowed */
if (new_mtu> ETH_DATA_LEN&&
(hw->chip_id == CHIP_ID_YUKON_FE ||
hw->chip_id == CHIP_ID_YUKON_FE_P))
return -EINVAL;

+ /* TSO on Yukon Ultra and MTU> 1500 not supported */
+ if (new_mtu> ETH_DATA_LEN&& hw->chip_id == CHIP_ID_YUKON_EC_U)
+ dev->features&= ~NETIF_F_TSO;
+
if (!netif_running(dev)) {
dev->mtu = new_mtu;
return 0;
@@ -2233,6 +2226,15 @@ static int sky2_change_mtu(struct net_de
if (err)
dev_close(dev);
else {
+ /* WA for dev. #4.209 */
+ if (hw->chip_id == CHIP_ID_YUKON_EC_U&&
+ hw->chip_rev == CHIP_REV_YU_EC_U_A1) {
+ /* enable/disable Store& Forward mode for TX */
+ sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T),
+ sky2->speed != SPEED_1000
+ ? TX_STFW_ENA : TX_STFW_DIS);
+ }
+
gma_write16(hw, port, GM_GP_CTRL, ctl);

netif_wake_queue(dev);
--- a/drivers/net/sky2.h 2010-01-06 12:48:48.632247424 -0800
+++ b/drivers/net/sky2.h 2010-01-06 12:59:57.322078964 -0800
@@ -1901,8 +1901,8 @@ enum {
TX_VLAN_TAG_ON = 1<<25,/* enable VLAN tagging */
TX_VLAN_TAG_OFF = 1<<24,/* disable VLAN tagging */

- TX_JUMBO_ENA = 1<<23,/* PCI Jumbo Mode enable (Yukon-EC Ultra) */
- TX_JUMBO_DIS = 1<<22,/* PCI Jumbo Mode enable (Yukon-EC Ultra) */
+ TX_PCI_JUM_ENA = 1<<23,/* Enable PCI Jumbo Mode (Yukon-EC Ultra) */
+ TX_PCI_JUM_DIS = 1<<22,/* Disable PCI Jumbo Mode (Yukon-EC Ultra) */

GMF_WSP_TST_ON = 1<<18,/* Write Shadow Pointer Test On */
GMF_WSP_TST_OFF = 1<<17,/* Write Shadow Pointer Test Off */

Ok ... results - and maybe some more clues...

Running with this patch; Jarek's "alternative 1", and the patch from the other thread. Not so good.

No reported errors (sky2, etc.) - however with mtu=9000, lots of stuff broke: XDMCP; http via MASQ/netfilter, ssh connections intermittently (when large frames involved perhaps), etc. Tried to change mtu to 1500 on the fly, got a bunch of errors - and network watchdog kicked in. Have now rebooted with the same patches and mtu=1500.
... with mtu=1500, Everything is again working (i.e., XDMCP, netfilter, etc.)
Load test with mtu=1500 went well for a while - high throughput sustained for a few minutes - then similar crash as before... but no interrup error messages this time until after the oops:
<nothing of note before this>
Jan 6 18:17:54 mail kernel: DRHD: handling fault status reg 2
Jan 6 18:17:54 mail kernel: DMAR:[DMA Read] Request device [06:00.0] fault addr 1bbfe000
Jan 6 18:17:54 mail kernel: DMAR:[fault reason 06] PTE Read access is not set
Jan 6 18:17:54 mail kernel: sky2 0000:06:00.0: error interrupt status=0x80000000
Jan 6 18:17:54 mail kernel: sky2 0000:06:00.0: PCI hardware error (0x2010)
Jan 6 18:18:04 mail kernel: ------------[ cut here ]------------
Jan 6 18:18:04 mail kernel: WARNING: at net/sched/sch_generic.c:261 dev_watchdog+0xf3/0x164()
Jan 6 18:18:04 mail kernel: Hardware name: System Product Name
Jan 6 18:18:04 mail kernel: NETDEV WATCHDOG: eth0 (sky2): transmit queue 0 timed out
Jan 6 18:18:04 mail kernel: Modules linked in: ip6table_filter ip6table_mangle ip6_tables ipt_MASQUERADE iptable_nat nf_nat iptable_mangle iptable_raw bridge stp appletalk psnap llc nfsd lockd nfs_acl auth_rpcgss exportfs hwmon_vid coretemp sunrpc acpi_cpufreq sit tunnel4 ipt_LOG nf_conntrack_netbios_ns nf_conntrack_ftp xt_DSCP xt_dscp xt_MARK nf_conntrack_ipv6 xt_multiport ipv6 dm_multipath kvm_intel kvm snd_hda_codec_analog snd_ens1371 gameport snd_rawmidi snd_ac97_codec snd_hda_intel snd_hda_codec ac97_bus snd_hwdep snd_seq snd_seq_device gspca_spca505 gspca_main videodev v4l1_compat snd_pcm v4l2_compat_ioctl32 pcspkr asus_atk0110 hwmon i2c_i801 iTCO_wdt firewire_ohci iTCO_vendor_support firewire_core crc_itu_t snd_timer snd sky2 soundcore wmi snd_page_alloc fbcon tileblit font bitblit softcursor raid456 async_raid6_recov async_pq raid6_pq async_xor xor async_memcpy async_tx raid1 ata_generic pata_acpi pata_marvell nouveau ttm drm_kms_helper drm agpgart fb i2c_algo_bit cfbcopyarea i2c_core cfbimgblt cfbfil
Jan 6 18:18:04 mail kernel: lrect [last unloaded: microcode]
Jan 6 18:18:04 mail kernel: Pid: 0, comm: swapper Tainted: G W 2.6.32-00840-gec8257c-dirty #41
Jan 6 18:18:04 mail kernel: Call Trace:
Jan 6 18:18:04 mail kernel: <IRQ> [<ffffffff8105365a>] warn_slowpath_common+0x7c/0x94
Jan 6 18:18:04 mail kernel: [<ffffffff810536c9>] warn_slowpath_fmt+0x41/0x43
Jan 6 18:18:04 mail kernel: [<ffffffff813e12bf>] ? netif_tx_lock+0x44/0x6c
Jan 6 18:18:04 mail kernel: [<ffffffff813e1427>] dev_watchdog+0xf3/0x164
Jan 6 18:18:04 mail kernel: [<ffffffff81077696>] ? sched_clock_cpu+0x47/0xd1
Jan 6 18:18:04 mail kernel: [<ffffffff8106316b>] run_timer_softirq+0x1c8/0x270
Jan 6 18:18:04 mail kernel: [<ffffffff8105ae3b>] __do_softirq+0xf8/0x1cd
Jan 6 18:18:04 mail kernel: [<ffffffff8107ef33>] ? tick_program_event+0x2a/0x2c
Jan 6 18:18:04 mail kernel: [<ffffffff81012e1c>] call_softirq+0x1c/0x30
Jan 6 18:18:04 mail kernel: [<ffffffff810143a3>] do_softirq+0x4b/0xa6
Jan 6 18:18:04 mail kernel: [<ffffffff8105aa1b>] irq_exit+0x4a/0x8c
Jan 6 18:18:04 mail kernel: [<ffffffff8146dd32>] smp_apic_timer_interrupt+0x86/0x94
Jan 6 18:18:04 mail kernel: [<ffffffff810127e3>] apic_timer_interrupt+0x13/0x20
Jan 6 18:18:04 mail kernel: <EOI> [<ffffffff812c4a06>] ? acpi_idle_enter_c1+0xb2/0xd0
Jan 6 18:18:04 mail kernel: [<ffffffff812c49ff>] ? acpi_idle_enter_c1+0xab/0xd0
Jan 6 18:18:04 mail kernel: [<ffffffff813a43b8>] ? cpuidle_idle_call+0x9e/0xfa
Jan 6 18:18:04 mail kernel: [<ffffffff81010c90>] ? cpu_idle+0xb4/0xf6
Jan 6 18:18:04 mail kernel: [<ffffffff81463312>] ? start_secondary+0x201/0x242
Jan 6 18:18:04 mail kernel: ---[ end trace 57f7151f6a5def07 ]---
Jan 6 18:18:04 mail kernel: sky2 eth0: tx timeout
Jan 6 18:18:04 mail kernel: sky2 eth0: transmit ring 21 .. 108 report=21 done=21
Jan 6 18:18:04 mail kernel: sky2 eth0: disabling interface
Jan 6 18:18:04 mail kernel: sky2 eth0: enabling interface
<eth0 dead after this>
Walked through the code based on Jarek's patches... came upon NET_CLS_ACT. At least in some cases (sch_cbq.c for example), the net transmit error could be returned from here... after releasing the skb. A quick scan of the various files in net/sched suggests that with NET_CLS_ACT the skb may or may not have been freed in the event of an error. If I have time later I'll see if I can bypass NET_CLS_ACT and see whether this is even relevant.

Ok - so rerunning with Jarek's alternative #2 patch (the one that doesn't re-free the skb after the net_dev_enqueue error) and all else as above (your mtu patch on a clean 2.6.32.2 sky2.c, plus the devtpts inode patch) with an MTU of 1500 I can run without errors (including the interrupt errors previously reported).

Changing MTU to 9000, everything basically breaks - Can't use X11 (local or remote - get X11 screen after gdm login locally, but then goes back to greeter; remote gets no greeter); ssh sessions hang; etc. This time I was able to reset the MTU back to 1500 without a reboot - but I did have to ifconfig eth0 down and then up. Looking at the sk98lin code, it looks to me like they do a bit more work with existing buffers before completing the MTU switch. Note that even doing this, X11 did not work (it did with the old mtu change code). Tried changing to mtu 4500 - same effect as 9000... but when I switched back to 1500, ksoftirqd started spinning using 100% of one core.

Running with these patches and 1500 MTU seems stable, but the network is running rather slow. Latency is OK, but peak transfer rates seem to be running about 20% of what I saw while receiving the interrupt errors with earlier patches.

I'll leave this running overnight to confirm that at least the errors and hangs are resolved with this patch set.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Valdis . Kletnieks: "Re: mmotm 2010-01-06-14-34 uploaded"
Previous message: Matt Mackall: "Re: [PATCH] netpoll: allow execution of multiple rx_hooks perinterface"
In reply to: Michael Breuer: "Re: [PATCH] af_packet: Don't use skb after dev_queue_xmit()"
Next in thread: Stephen Hemminger: "Re: [PATCH] af_packet: Don't use skb after dev_queue_xmit()"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]