* Re: [PATCH net-next] net: Fix truesize accounting in skb_gro_receive()
From: Alexander Duyck @ 2012-05-03 10:48 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, netdev, jeffrey.t.kirsher
In-Reply-To: <1336037601.3752.8.camel@edumazet-glaptop>
On 05/03/2012 02:33 AM, Eric Dumazet wrote:
> From: Eric Dumazet<edumazet@google.com>
>
> GRO is very optimistic in skb truesize estimates, only taking into
> account the used part of fragments.
>
> Be conservative, and use more precise computation, so that bloated GRO
> skbs can be collapsed eventually.
>
> Signed-off-by: Eric Dumazet<edumazet@google.com>
> Cc: Alexander Duyck<alexander.h.duyck@intel.com>
> Cc: Jeff Kirsher<jeffrey.t.kirsher@intel.com>
> ---
> net/core/skbuff.c | 11 ++++++++---
> 1 file changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 9e8caa0..e1f8bba 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -2871,6 +2871,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
> unsigned int len = skb_gro_len(skb);
> unsigned int offset = skb_gro_offset(skb);
> unsigned int headlen = skb_headlen(skb);
> + unsigned int delta_truesize;
>
> if (p->len + len>= 65536)
> return -E2BIG;
> @@ -2900,11 +2901,14 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
> frag->page_offset += offset;
> skb_frag_size_sub(frag, offset);
>
> + /* all fragments truesize : remove (head size + sk_buff) */
> + delta_truesize = skb->truesize - SKB_TRUESIZE(skb_end_pointer(skb) - skb->head);
> +
> skb->truesize -= skb->data_len;
> skb->len -= skb->data_len;
> skb->data_len = 0;
>
> - NAPI_GRO_CB(skb)->free = 1;
> + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE;
> goto done;
> } else if (skb->head_frag) {
> int nr_frags = pinfo->nr_frags;
> @@ -2929,6 +2933,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
> memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
> /* We dont need to clear skbinfo->nr_frags here */
>
> + delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
> NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
> goto done;
> } else if (skb_gro_len(p) != pinfo->gso_size)
> @@ -2971,7 +2976,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
> p = nskb;
>
> merge:
> - p->truesize += skb->truesize - len;
> + delta_truesize = skb->truesize;
> if (offset> headlen) {
> unsigned int eat = offset - headlen;
>
> @@ -2991,7 +2996,7 @@ merge:
> done:
> NAPI_GRO_CB(p)->count++;
> p->data_len += len;
> - p->truesize += len;
> + p->truesize += delta_truesize;
> p->len += len;
>
> NAPI_GRO_CB(skb)->same_flow = 1;
>
>
Couldn't sleep so I figured I would review some patches and maybe get a
few more written before the sun came up. I was actually thinking of
trying to get to this before I logged in. Looks like you have this one
taken care of already so I will go take care of skb_head_is_locked.
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
^ permalink raw reply
* Re: [net-next 5/9] e1000e: Disable ASPM L1 on 82574
From: Nix @ 2012-05-03 10:08 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: davem, Chris Boot, netdev, gospo, sassmann, Wyborny, Carolyn
In-Reply-To: <1336038992-3144-6-git-send-email-jeffrey.t.kirsher@intel.com>
On 3 May 2012, Jeff Kirsher spake thusly:
> From: Chris Boot <bootc@bootc.net>
>
> ASPM on the 82574 causes trouble. Currently the driver disables L0s for
> this NIC but only disables L1 if the MTU is >1500. This patch simply
> causes L1 to be disabled regardless of the MTU setting.
>
> Signed-off-by: Chris Boot <bootc@bootc.net>
> Cc: "Wyborny, Carolyn" <carolyn.wyborny@intel.com>
> Cc: Nix <nix@esperi.org.uk>
> Link: https://lkml.org/lkml/2012/3/19/362
> Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
(reminder: this is known not to fix the instance of this problem I am
experiencing, where ASPM is being re-enabled by something even if turned
off via setpci during boot, though it does fix those instances seen by
others where that doesn't happen. I'd have done more printf()-scattering
debugging to see where it's turned back on if it wasn't that this is
happening on an always-on server for which rebooting outside the dead of
night is a long-winded chore...)
FWIW I have also seen -- very rare -- lockups of the same nature on
82574L links in 100MbE mode using non-jumbo frames. However they are far
more common on GbE jumbo-framed links, normally taking less than an hour
to take the link down with a wildly corrupted register set (as shown by
ethtool).
(It's annoying this firmware isn't flashable so we could just *fix* this
bug rather than working around it. :( )
I think I might cheat a bit next and printk_once() the state of ASPM L1
on the errant PCI device from inside the scheduler when it flips from L1
off to L1 on again. At 100 tests per second that should indicate at what
time the thing is turned back on fairly tightly: even if not providing a
direct clue as to which bit of the kernel is doing it, if I combine it
with a set -x in userspace it should at least indicate what bit of the
boot process is happening at the same time. It'll be the weekend before
I can try that though.
--
NULL && (void)
^ permalink raw reply
* [net 2/2] ixgbe: dcb: BIT_APP_UPCHG not set by ixgbe_copy_dcb_cfg()
From: Jeff Kirsher @ 2012-05-03 10:08 UTC (permalink / raw)
To: davem; +Cc: John Fastabend, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336039717-12336-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: John Fastabend <john.r.fastabend@intel.com>
After this commit:
commit aacc1bea190d731755a65cb8ec31dd756f4e263e
Author: Multanen, Eric W <eric.w.multanen@intel.com>
Date: Wed Mar 28 07:49:09 2012 +0000
ixgbe: driver fix for link flap
The BIT_APP_UPCHG bit is no longer set when ixgbe_dcbnl_set_all() is
called. This results in the FCoE app user priority never getting set
and the driver will not configure the tx_rings correctly for FCoE
packets which use the SAN MTU and FCoE offloads.
We resolve this regression by fixing ixgbe_copy_dcb_cfg() to also
check for FCoE application changes. Additionally, we can drop the
IEEE variants of get_dcb_app() because this path is never called
with the IEEE mode enabled.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 3 --
drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c | 43 ++++++++++------------
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 +-
3 files changed, 22 insertions(+), 28 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 74e1921..81b1555 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -574,9 +574,6 @@ extern struct ixgbe_info ixgbe_82599_info;
extern struct ixgbe_info ixgbe_X540_info;
#ifdef CONFIG_IXGBE_DCB
extern const struct dcbnl_rtnl_ops dcbnl_ops;
-extern int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg,
- struct ixgbe_dcb_config *dst_dcb_cfg,
- int tc_max);
#endif
extern char ixgbe_driver_name[];
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index 652e4b0..32e5c02 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -44,18 +44,26 @@
#define DCB_NO_HW_CHG 1 /* DCB configuration did not change */
#define DCB_HW_CHG 2 /* DCB configuration changed, no reset */
-int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *scfg,
- struct ixgbe_dcb_config *dcfg, int tc_max)
+static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max)
{
+ struct ixgbe_dcb_config *scfg = &adapter->temp_dcb_cfg;
+ struct ixgbe_dcb_config *dcfg = &adapter->dcb_cfg;
struct tc_configuration *src = NULL;
struct tc_configuration *dst = NULL;
int i, j;
int tx = DCB_TX_CONFIG;
int rx = DCB_RX_CONFIG;
int changes = 0;
+#ifdef IXGBE_FCOE
+ struct dcb_app app = {
+ .selector = DCB_APP_IDTYPE_ETHTYPE,
+ .protocol = ETH_P_FCOE,
+ };
+ u8 up = dcb_getapp(adapter->netdev, &app);
- if (!scfg || !dcfg)
- return changes;
+ if (up && !(up & (1 << adapter->fcoe.up)))
+ changes |= BIT_APP_UPCHG;
+#endif
for (i = DCB_PG_ATTR_TC_0; i < tc_max + DCB_PG_ATTR_TC_0; i++) {
src = &scfg->tc_config[i - DCB_PG_ATTR_TC_0];
@@ -332,28 +340,12 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
struct ixgbe_adapter *adapter = netdev_priv(netdev);
int ret = DCB_NO_HW_CHG;
int i;
-#ifdef IXGBE_FCOE
- struct dcb_app app = {
- .selector = DCB_APP_IDTYPE_ETHTYPE,
- .protocol = ETH_P_FCOE,
- };
- u8 up;
-
- /* In IEEE mode, use the IEEE Ethertype selector value */
- if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) {
- app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE;
- up = dcb_ieee_getapp_mask(netdev, &app);
- } else {
- up = dcb_getapp(netdev, &app);
- }
-#endif
/* Fail command if not in CEE mode */
if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
return ret;
- adapter->dcb_set_bitmap |= ixgbe_copy_dcb_cfg(&adapter->temp_dcb_cfg,
- &adapter->dcb_cfg,
+ adapter->dcb_set_bitmap |= ixgbe_copy_dcb_cfg(adapter,
MAX_TRAFFIC_CLASS);
if (!adapter->dcb_set_bitmap)
return ret;
@@ -440,8 +432,13 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
* FCoE is using changes. This happens if the APP info
* changes or the up2tc mapping is updated.
*/
- if ((up && !(up & (1 << adapter->fcoe.up))) ||
- (adapter->dcb_set_bitmap & BIT_APP_UPCHG)) {
+ if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
+ struct dcb_app app = {
+ .selector = DCB_APP_IDTYPE_ETHTYPE,
+ .protocol = ETH_P_FCOE,
+ };
+ u8 up = dcb_getapp(netdev, &app);
+
adapter->fcoe.up = ffs(up) - 1;
ixgbe_dcbnl_devreset(netdev);
ret = DCB_HW_CHG_RST;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index d9dbf87..50f0700 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4418,8 +4418,8 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
adapter->dcb_cfg.pfc_mode_enable = false;
adapter->dcb_set_bitmap = 0x00;
adapter->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_CEE;
- ixgbe_copy_dcb_cfg(&adapter->dcb_cfg, &adapter->temp_dcb_cfg,
- MAX_TRAFFIC_CLASS);
+ memcpy(&adapter->temp_dcb_cfg, &adapter->dcb_cfg,
+ sizeof(adapter->temp_dcb_cfg));
#endif
--
1.7.7.6
^ permalink raw reply related
* [net 1/2] ixgbe: fix race condition with shutdown
From: Jeff Kirsher @ 2012-05-03 10:08 UTC (permalink / raw)
To: davem
Cc: Don Skidmore, netdev, gospo, sassmann, Hariharan Nagarajan,
Jeff Kirsher
In-Reply-To: <1336039717-12336-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Don Skidmore <donald.c.skidmore@intel.com>
It was possible for shutdown to pull the rug out from other driver entry
points. Now we just grab the rtnl lock before taking everything apart.
Thanks to Hariharan for noticing this tight race condition.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Cc: Hariharan Nagarajan <hanagara@cisco.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 88f6b2e..d9dbf87 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4866,10 +4866,12 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
netif_device_detach(netdev);
if (netif_running(netdev)) {
+ rtnl_lock();
ixgbe_down(adapter);
ixgbe_free_irq(adapter);
ixgbe_free_all_tx_resources(adapter);
ixgbe_free_all_rx_resources(adapter);
+ rtnl_unlock();
}
ixgbe_clear_interrupt_scheme(adapter);
--
1.7.7.6
^ permalink raw reply related
* [net 0/2][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2012-05-03 10:08 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, sassmann
This series of patches contains fixes for ixgbe.
The following are changes since commit 5a8887d39e1ba5ee2d4ccb94b14d6f2dce5ddfca:
sungem: Fix WakeOnLan
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net master`
Don Skidmore (1):
ixgbe: fix race condition with shutdown
John Fastabend (1):
ixgbe: dcb: BIT_APP_UPCHG not set by ixgbe_copy_dcb_cfg()
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 3 --
drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c | 43 ++++++++++------------
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ++-
3 files changed, 24 insertions(+), 28 deletions(-)
--
1.7.7.6
^ permalink raw reply
* [net-next 9/9] ixgbevf: Update version string
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 5a0e228..f69ec42 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -57,7 +57,7 @@ const char ixgbevf_driver_name[] = "ixgbevf";
static const char ixgbevf_driver_string[] =
"Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver";
-#define DRV_VERSION "2.2.0-k"
+#define DRV_VERSION "2.6.0-k"
const char ixgbevf_driver_version[] = DRV_VERSION;
static char ixgbevf_copyright[] =
"Copyright (c) 2009 - 2012 Intel Corporation.";
--
1.7.7.6
^ permalink raw reply related
* [net-next 8/9] ixgbevf: Make sure jumbo frames are set correctly after PF reset
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
If the Physical Function (PF) resets after the VF has set jumbo
frame MTU then the VF jumbo frame is overwritten. Make sure the
VF driver always requests proper MTU size after reset
synchronization.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 2 +-
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 28 ++++++++++----------
2 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index dfed420..0a1b992 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -287,7 +287,7 @@ extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops;
extern const char ixgbevf_driver_name[];
extern const char ixgbevf_driver_version[];
-extern int ixgbevf_up(struct ixgbevf_adapter *adapter);
+extern void ixgbevf_up(struct ixgbevf_adapter *adapter);
extern void ixgbevf_down(struct ixgbevf_adapter *adapter);
extern void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter);
extern void ixgbevf_reset(struct ixgbevf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 307611a..5a0e228 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1608,13 +1608,14 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter)
adapter->stats.base_vfmprc = adapter->stats.last_vfmprc;
}
-static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
+static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
int i, j = 0;
int num_rx_rings = adapter->num_rx_queues;
u32 txdctl, rxdctl;
+ u32 msg[2];
for (i = 0; i < adapter->num_tx_queues; i++) {
j = adapter->tx_ring[i].reg_idx;
@@ -1653,6 +1654,10 @@ static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0);
}
+ msg[0] = IXGBE_VF_SET_LPE;
+ msg[1] = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
+ hw->mbx.ops.write_posted(hw, msg, 2);
+
clear_bit(__IXGBEVF_DOWN, &adapter->state);
ixgbevf_napi_enable_all(adapter);
@@ -1667,24 +1672,20 @@ static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
adapter->link_check_timeout = jiffies;
mod_timer(&adapter->watchdog_timer, jiffies);
- return 0;
}
-int ixgbevf_up(struct ixgbevf_adapter *adapter)
+void ixgbevf_up(struct ixgbevf_adapter *adapter)
{
- int err;
struct ixgbe_hw *hw = &adapter->hw;
ixgbevf_configure(adapter);
- err = ixgbevf_up_complete(adapter);
+ ixgbevf_up_complete(adapter);
/* clear any pending interrupts, may auto mask */
IXGBE_READ_REG(hw, IXGBE_VTEICR);
ixgbevf_irq_enable(adapter, true, true);
-
- return err;
}
/**
@@ -2673,9 +2674,7 @@ static int ixgbevf_open(struct net_device *netdev)
*/
ixgbevf_map_rings_to_vectors(adapter);
- err = ixgbevf_up_complete(adapter);
- if (err)
- goto err_up;
+ ixgbevf_up_complete(adapter);
/* clear any pending interrupts, may auto mask */
IXGBE_READ_REG(hw, IXGBE_VTEICR);
@@ -2689,7 +2688,6 @@ static int ixgbevf_open(struct net_device *netdev)
err_req_irq:
ixgbevf_down(adapter);
-err_up:
ixgbevf_free_irq(adapter);
err_setup_rx:
ixgbevf_free_all_rx_resources(adapter);
@@ -3196,9 +3194,11 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
/* must set new MTU before calling down or up */
netdev->mtu = new_mtu;
- msg[0] = IXGBE_VF_SET_LPE;
- msg[1] = max_frame;
- hw->mbx.ops.write_posted(hw, msg, 2);
+ if (!netif_running(netdev)) {
+ msg[0] = IXGBE_VF_SET_LPE;
+ msg[1] = max_frame;
+ hw->mbx.ops.write_posted(hw, msg, 2);
+ }
if (netif_running(netdev))
ixgbevf_reinit_locked(adapter);
--
1.7.7.6
^ permalink raw reply related
* [net-next 7/9] ixgbevf: Add support to recognize 100mb link speed
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
The X540 10Gig controller is capable of linking at 100Mbits - add
support for reporting that link speed.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbevf/defines.h | 2 ++
drivers/net/ethernet/intel/ixgbevf/ethtool.c | 18 ++++++++++++++----
drivers/net/ethernet/intel/ixgbevf/vf.c | 12 +++++++++---
3 files changed, 25 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index 947b5c8..e09a6cc 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -40,6 +40,7 @@
typedef u32 ixgbe_link_speed;
#define IXGBE_LINK_SPEED_1GB_FULL 0x0020
#define IXGBE_LINK_SPEED_10GB_FULL 0x0080
+#define IXGBE_LINK_SPEED_100_FULL 0x0008
#define IXGBE_CTRL_RST 0x04000000 /* Reset (SW) */
#define IXGBE_RXDCTL_ENABLE 0x02000000 /* Enable specific Rx Queue */
@@ -48,6 +49,7 @@ typedef u32 ixgbe_link_speed;
#define IXGBE_LINKS_SPEED_82599 0x30000000
#define IXGBE_LINKS_SPEED_10G_82599 0x30000000
#define IXGBE_LINKS_SPEED_1G_82599 0x20000000
+#define IXGBE_LINKS_SPEED_100_82599 0x10000000
/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
#define IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE 8
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 2bfe0d1..e8dddf5 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -107,10 +107,20 @@ static int ixgbevf_get_settings(struct net_device *netdev,
hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
if (link_up) {
- ethtool_cmd_speed_set(
- ecmd,
- (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ?
- SPEED_10000 : SPEED_1000);
+ __u32 speed = SPEED_10000;
+ switch (link_speed) {
+ case IXGBE_LINK_SPEED_10GB_FULL:
+ speed = SPEED_10000;
+ break;
+ case IXGBE_LINK_SPEED_1GB_FULL:
+ speed = SPEED_1000;
+ break;
+ case IXGBE_LINK_SPEED_100_FULL:
+ speed = SPEED_100;
+ break;
+ }
+
+ ethtool_cmd_speed_set(ecmd, speed);
ecmd->duplex = DUPLEX_FULL;
} else {
ethtool_cmd_speed_set(ecmd, -1);
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 74be741..ec89b86 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -404,11 +404,17 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
else
*link_up = false;
- if ((links_reg & IXGBE_LINKS_SPEED_82599) ==
- IXGBE_LINKS_SPEED_10G_82599)
+ switch (links_reg & IXGBE_LINKS_SPEED_82599) {
+ case IXGBE_LINKS_SPEED_10G_82599:
*speed = IXGBE_LINK_SPEED_10GB_FULL;
- else
+ break;
+ case IXGBE_LINKS_SPEED_1G_82599:
*speed = IXGBE_LINK_SPEED_1GB_FULL;
+ break;
+ case IXGBE_LINKS_SPEED_100_82599:
+ *speed = IXGBE_LINK_SPEED_100_FULL;
+ break;
+ }
return 0;
}
--
1.7.7.6
^ permalink raw reply related
* [net-next 6/9] e1000e: Remove special case for 82573/82574 ASPM L1 disablement
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Chris Boot, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Chris Boot <bootc@bootc.net>
For the 82573, ASPM L1 gets disabled wholesale so this special-case code
is not required. For the 82574 the previous patch does the same as for
the 82573, disabling L1 on the adapter. Thus, this code is no longer
required and can be removed.
Signed-off-by: Chris Boot <bootc@bootc.net>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/netdev.c | 8 --------
1 files changed, 0 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index ab4505c..9c4576e 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5272,14 +5272,6 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
return -EINVAL;
}
- /* 82573 Errata 17 */
- if (((adapter->hw.mac.type == e1000_82573) ||
- (adapter->hw.mac.type == e1000_82574)) &&
- (max_frame > ETH_FRAME_LEN + ETH_FCS_LEN)) {
- adapter->flags2 |= FLAG2_DISABLE_ASPM_L1;
- e1000e_disable_aspm(adapter->pdev, PCIE_LINK_STATE_L1);
- }
-
while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
usleep_range(1000, 2000);
/* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */
--
1.7.7.6
^ permalink raw reply related
* [net-next 5/9] e1000e: Disable ASPM L1 on 82574
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem
Cc: Chris Boot, netdev, gospo, sassmann, Wyborny, Carolyn, Nix,
Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Chris Boot <bootc@bootc.net>
ASPM on the 82574 causes trouble. Currently the driver disables L0s for
this NIC but only disables L1 if the MTU is >1500. This patch simply
causes L1 to be disabled regardless of the MTU setting.
Signed-off-by: Chris Boot <bootc@bootc.net>
Cc: "Wyborny, Carolyn" <carolyn.wyborny@intel.com>
Cc: Nix <nix@esperi.org.uk>
Link: https://lkml.org/lkml/2012/3/19/362
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/82571.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index 98632f4..6a8a908 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -2072,8 +2072,9 @@ const struct e1000_info e1000_82574_info = {
| FLAG_HAS_SMART_POWER_DOWN
| FLAG_HAS_AMT
| FLAG_HAS_CTRLEXT_ON_LOAD,
- .flags2 = FLAG2_CHECK_PHY_HANG
+ .flags2 = FLAG2_CHECK_PHY_HANG
| FLAG2_DISABLE_ASPM_L0S
+ | FLAG2_DISABLE_ASPM_L1
| FLAG2_NO_DISABLE_RX
| FLAG2_DMA_BURST,
.pba = 32,
--
1.7.7.6
^ permalink raw reply related
* [net-next 2/9] e1000e: cleanup long [read|write]_reg_locked PHY ops function pointers
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Bruce Allan, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Bruce Allan <bruce.w.allan@intel.com>
Calling the locked versions of the read/write PHY ops function pointers
often produces excessively long lines. Shorten these as is done with
the non-locked versions of the PHY register read/write functions.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/e1000.h | 10 ++++++
drivers/net/ethernet/intel/e1000e/ich8lan.c | 47 +++++++++++----------------
2 files changed, 29 insertions(+), 28 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 1da9bfa..c960cf8 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -673,11 +673,21 @@ static inline s32 e1e_rphy(struct e1000_hw *hw, u32 offset, u16 *data)
return hw->phy.ops.read_reg(hw, offset, data);
}
+static inline s32 e1e_rphy_locked(struct e1000_hw *hw, u32 offset, u16 *data)
+{
+ return hw->phy.ops.read_reg_locked(hw, offset, data);
+}
+
static inline s32 e1e_wphy(struct e1000_hw *hw, u32 offset, u16 data)
{
return hw->phy.ops.write_reg(hw, offset, data);
}
+static inline s32 e1e_wphy_locked(struct e1000_hw *hw, u32 offset, u16 data)
+{
+ return hw->phy.ops.write_reg_locked(hw, offset, data);
+}
+
static inline s32 e1000_get_cable_length(struct e1000_hw *hw)
{
return hw->phy.ops.get_cable_length(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index ca34ebf..c58ed26 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -304,9 +304,9 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw)
u16 phy_reg;
u32 phy_id;
- hw->phy.ops.read_reg_locked(hw, PHY_ID1, &phy_reg);
+ e1e_rphy_locked(hw, PHY_ID1, &phy_reg);
phy_id = (u32)(phy_reg << 16);
- hw->phy.ops.read_reg_locked(hw, PHY_ID2, &phy_reg);
+ e1e_rphy_locked(hw, PHY_ID2, &phy_reg);
phy_id |= (u32)(phy_reg & PHY_REVISION_MASK);
if (hw->phy.id) {
@@ -1271,8 +1271,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
reg_addr &= PHY_REG_MASK;
reg_addr |= phy_page;
- ret_val = phy->ops.write_reg_locked(hw, (u32)reg_addr,
- reg_data);
+ ret_val = e1e_wphy_locked(hw, (u32)reg_addr, reg_data);
if (ret_val)
goto release;
}
@@ -1309,8 +1308,8 @@ static s32 e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link)
/* Disable K1 when link is 1Gbps, otherwise use the NVM setting */
if (link) {
if (hw->phy.type == e1000_phy_82578) {
- ret_val = hw->phy.ops.read_reg_locked(hw, BM_CS_STATUS,
- &status_reg);
+ ret_val = e1e_rphy_locked(hw, BM_CS_STATUS,
+ &status_reg);
if (ret_val)
goto release;
@@ -1325,8 +1324,7 @@ static s32 e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link)
}
if (hw->phy.type == e1000_phy_82577) {
- ret_val = hw->phy.ops.read_reg_locked(hw, HV_M_STATUS,
- &status_reg);
+ ret_val = e1e_rphy_locked(hw, HV_M_STATUS, &status_reg);
if (ret_val)
goto release;
@@ -1341,15 +1339,13 @@ static s32 e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link)
}
/* Link stall fix for link up */
- ret_val = hw->phy.ops.write_reg_locked(hw, PHY_REG(770, 19),
- 0x0100);
+ ret_val = e1e_wphy_locked(hw, PHY_REG(770, 19), 0x0100);
if (ret_val)
goto release;
} else {
/* Link stall fix for link down */
- ret_val = hw->phy.ops.write_reg_locked(hw, PHY_REG(770, 19),
- 0x4100);
+ ret_val = e1e_wphy_locked(hw, PHY_REG(770, 19), 0x4100);
if (ret_val)
goto release;
}
@@ -1448,7 +1444,7 @@ static s32 e1000_oem_bits_config_ich8lan(struct e1000_hw *hw, bool d0_state)
mac_reg = er32(PHY_CTRL);
- ret_val = hw->phy.ops.read_reg_locked(hw, HV_OEM_BITS, &oem_reg);
+ ret_val = e1e_rphy_locked(hw, HV_OEM_BITS, &oem_reg);
if (ret_val)
goto release;
@@ -1475,7 +1471,7 @@ static s32 e1000_oem_bits_config_ich8lan(struct e1000_hw *hw, bool d0_state)
!hw->phy.ops.check_reset_block(hw))
oem_reg |= HV_OEM_BITS_RESTART_AN;
- ret_val = hw->phy.ops.write_reg_locked(hw, HV_OEM_BITS, oem_reg);
+ ret_val = e1e_wphy_locked(hw, HV_OEM_BITS, oem_reg);
release:
hw->phy.ops.release(hw);
@@ -1571,11 +1567,10 @@ static s32 e1000_hv_phy_workarounds_ich8lan(struct e1000_hw *hw)
ret_val = hw->phy.ops.acquire(hw);
if (ret_val)
return ret_val;
- ret_val = hw->phy.ops.read_reg_locked(hw, BM_PORT_GEN_CFG, &phy_data);
+ ret_val = e1e_rphy_locked(hw, BM_PORT_GEN_CFG, &phy_data);
if (ret_val)
goto release;
- ret_val = hw->phy.ops.write_reg_locked(hw, BM_PORT_GEN_CFG,
- phy_data & 0x00FF);
+ ret_val = e1e_wphy_locked(hw, BM_PORT_GEN_CFG, phy_data & 0x00FF);
release:
hw->phy.ops.release(hw);
@@ -1807,20 +1802,18 @@ static s32 e1000_lv_phy_workarounds_ich8lan(struct e1000_hw *hw)
ret_val = hw->phy.ops.acquire(hw);
if (ret_val)
return ret_val;
- ret_val = hw->phy.ops.write_reg_locked(hw, I82579_EMI_ADDR,
- I82579_MSE_THRESHOLD);
+ ret_val = e1e_wphy_locked(hw, I82579_EMI_ADDR, I82579_MSE_THRESHOLD);
if (ret_val)
goto release;
/* set MSE higher to enable link to stay up when noise is high */
- ret_val = hw->phy.ops.write_reg_locked(hw, I82579_EMI_DATA, 0x0034);
+ ret_val = e1e_wphy_locked(hw, I82579_EMI_DATA, 0x0034);
if (ret_val)
goto release;
- ret_val = hw->phy.ops.write_reg_locked(hw, I82579_EMI_ADDR,
- I82579_MSE_LINK_DOWN);
+ ret_val = e1e_wphy_locked(hw, I82579_EMI_ADDR, I82579_MSE_LINK_DOWN);
if (ret_val)
goto release;
/* drop link after 5 times MSE threshold was reached */
- ret_val = hw->phy.ops.write_reg_locked(hw, I82579_EMI_DATA, 0x0005);
+ ret_val = e1e_wphy_locked(hw, I82579_EMI_DATA, 0x0005);
release:
hw->phy.ops.release(hw);
@@ -1995,12 +1988,10 @@ static s32 e1000_post_phy_reset_ich8lan(struct e1000_hw *hw)
ret_val = hw->phy.ops.acquire(hw);
if (ret_val)
return ret_val;
- ret_val = hw->phy.ops.write_reg_locked(hw, I82579_EMI_ADDR,
- I82579_LPI_UPDATE_TIMER);
+ ret_val = e1e_wphy_locked(hw, I82579_EMI_ADDR,
+ I82579_LPI_UPDATE_TIMER);
if (!ret_val)
- ret_val = hw->phy.ops.write_reg_locked(hw,
- I82579_EMI_DATA,
- 0x1387);
+ ret_val = e1e_wphy_locked(hw, I82579_EMI_DATA, 0x1387);
hw->phy.ops.release(hw);
}
--
1.7.7.6
^ permalink raw reply related
* [net-next 3/9] e1000e: Resolve intermittent negotiation issue on 82574/82583.
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Matthew Vick, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Matthew Vick <matthew.vick@intel.com>
For 82574 and 82583 devices, resolve an intermittent link issue where
the link negotiates to 100Mbps rather than 1Gbps when powering off the
PHY and powering on the PHY after several seconds.
Signed-off-by: Matthew Vick <matthew.vick@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/phy.c | 18 +++++++++++++++++-
1 files changed, 17 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index bd5ef64..ad22b8c 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -722,8 +722,24 @@ s32 e1000e_copper_link_setup_m88(struct e1000_hw *hw)
phy_data |= M88E1000_PSCR_POLARITY_REVERSAL;
/* Enable downshift on BM (disabled by default) */
- if (phy->type == e1000_phy_bm)
+ if (phy->type == e1000_phy_bm) {
+ /* For 82574/82583, first disable then enable downshift */
+ if (phy->id == BME1000_E_PHY_ID_R2) {
+ phy_data &= ~BME1000_PSCR_ENABLE_DOWNSHIFT;
+ ret_val = e1e_wphy(hw, M88E1000_PHY_SPEC_CTRL,
+ phy_data);
+ if (ret_val)
+ return ret_val;
+ /* Commit the changes. */
+ ret_val = e1000e_commit_phy(hw);
+ if (ret_val) {
+ e_dbg("Error committing the PHY changes\n");
+ return ret_val;
+ }
+ }
+
phy_data |= BME1000_PSCR_ENABLE_DOWNSHIFT;
+ }
ret_val = e1e_wphy(hw, M88E1000_PHY_SPEC_CTRL, phy_data);
if (ret_val)
--
1.7.7.6
^ permalink raw reply related
* [net-next 4/9] e1000e: Driver workaround for IPv6 Header Extension Erratum.
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Matthew Vick, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Matthew Vick <matthew.vick@intel.com>
Previously, IPv6 extension header parsing was disabled for all devices
supported by e1000e when using packet split mode. However, as per a
silicon errata, only certain devices need this restriction and will need
to disable IPv6 extension header parsing for all modes.
Signed-off-by: Matthew Vick <matthew.vick@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/80003es2lan.c | 8 ++++++++
drivers/net/ethernet/intel/e1000e/82571.c | 10 ++++++++++
drivers/net/ethernet/intel/e1000e/ich8lan.c | 7 +++++++
drivers/net/ethernet/intel/e1000e/netdev.c | 9 +--------
4 files changed, 26 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 66f9877..4dd18a1 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -944,6 +944,14 @@ static void e1000_initialize_hw_bits_80003es2lan(struct e1000_hw *hw)
else
reg |= (1 << 28);
ew32(TARC(1), reg);
+
+ /*
+ * Disable IPv6 extension header parsing because some malformed
+ * IPv6 headers can hang the Rx.
+ */
+ reg = er32(RFCTL);
+ reg |= (E1000_RFCTL_IPV6_EX_DIS | E1000_RFCTL_NEW_IPV6_EXT_DIS);
+ ew32(RFCTL, reg);
}
/**
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index 7b02e87..98632f4 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -1279,6 +1279,16 @@ static void e1000_initialize_hw_bits_82571(struct e1000_hw *hw)
ew32(CTRL_EXT, reg);
}
+ /*
+ * Disable IPv6 extension header parsing because some malformed
+ * IPv6 headers can hang the Rx.
+ */
+ if (hw->mac.type <= e1000_82573) {
+ reg = er32(RFCTL);
+ reg |= (E1000_RFCTL_IPV6_EX_DIS | E1000_RFCTL_NEW_IPV6_EXT_DIS);
+ ew32(RFCTL, reg);
+ }
+
/* PCI-Ex Control Registers */
switch (hw->mac.type) {
case e1000_82574:
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index c58ed26..dfff441 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -3468,6 +3468,13 @@ static void e1000_initialize_hw_bits_ich8lan(struct e1000_hw *hw)
*/
reg = er32(RFCTL);
reg |= (E1000_RFCTL_NFSW_DIS | E1000_RFCTL_NFSR_DIS);
+
+ /*
+ * Disable IPv6 extension header parsing because some malformed
+ * IPv6 headers can hang the Rx.
+ */
+ if (hw->mac.type == e1000_ich8lan)
+ reg |= (E1000_RFCTL_IPV6_EX_DIS | E1000_RFCTL_NEW_IPV6_EXT_DIS);
ew32(RFCTL, reg);
}
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index e86b524..ab4505c 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2939,6 +2939,7 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter)
/* Enable Extended Status in all Receive Descriptors */
rfctl = er32(RFCTL);
rfctl |= E1000_RFCTL_EXTEN;
+ ew32(RFCTL, rfctl);
/*
* 82571 and greater support packet-split where the protocol
@@ -2964,13 +2965,6 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter)
if (adapter->rx_ps_pages) {
u32 psrctl = 0;
- /*
- * disable packet split support for IPv6 extension headers,
- * because some malformed IPv6 headers can hang the Rx
- */
- rfctl |= (E1000_RFCTL_IPV6_EX_DIS |
- E1000_RFCTL_NEW_IPV6_EXT_DIS);
-
/* Enable Packet split descriptors */
rctl |= E1000_RCTL_DTYP_PS;
@@ -3009,7 +3003,6 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter)
*/
}
- ew32(RFCTL, rfctl);
ew32(RCTL, rctl);
/* just started the receive unit, no need to restart */
adapter->flags &= ~FLAG_RX_RESTART_NOW;
--
1.7.7.6
^ permalink raw reply related
* [net-next 1/9] e1000e: suggest a possible workaround to a device hang on 82577/8
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Bruce Allan, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1336038992-3144-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Bruce Allan <bruce.w.allan@intel.com>
There is a known issue in the 82577 and 82578 device that can cause a hang
in the device hardware during traffic stress; the current workaround in the
driver is to disable transmit flow control by default. If the user enables
transmit flow control and the device hang occurs, provide a message in the
syslog suggesting to re-enable the workaround.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/netdev.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index c0e211b..e86b524 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1084,6 +1084,10 @@ static void e1000_print_hw_hang(struct work_struct *work)
phy_1000t_status,
phy_ext_status,
pci_status);
+
+ /* Suggest workaround for known h/w issue */
+ if ((hw->mac.type == e1000_pchlan) && (er32(CTRL) & E1000_CTRL_TFCE))
+ e_err("Try turning off Tx pause (flow control) via ethtool\n");
}
/**
--
1.7.7.6
^ permalink raw reply related
* [net-next 0/9][pull request] Intel Wired LAN Dirver Updates
From: Jeff Kirsher @ 2012-05-03 9:56 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, sassmann
This series of patches contains updates for e1000e and ixgbevf.
The following are changes since commit af94bf6db1d58d26f1cdab145b6312ad363254a6:
ixgbe: Fix use after free on module remove
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next master
Bruce Allan (2):
e1000e: suggest a possible workaround to a device hang on 82577/8
e1000e: cleanup long [read|write]_reg_locked PHY ops function
pointers
Chris Boot (2):
e1000e: Disable ASPM L1 on 82574
e1000e: Remove special case for 82573/82574 ASPM L1 disablement
Greg Rose (3):
ixgbevf: Add support to recognize 100mb link speed
ixgbevf: Make sure jumbo frames are set correctly after PF reset
ixgbevf: Update version string
Matthew Vick (2):
e1000e: Resolve intermittent negotiation issue on 82574/82583.
e1000e: Driver workaround for IPv6 Header Extension Erratum.
drivers/net/ethernet/intel/e1000e/80003es2lan.c | 8 +++
drivers/net/ethernet/intel/e1000e/82571.c | 13 +++++-
drivers/net/ethernet/intel/e1000e/e1000.h | 10 ++++
drivers/net/ethernet/intel/e1000e/ich8lan.c | 54 ++++++++++-----------
drivers/net/ethernet/intel/e1000e/netdev.c | 21 ++------
drivers/net/ethernet/intel/e1000e/phy.c | 18 +++++++-
drivers/net/ethernet/intel/ixgbevf/defines.h | 2 +
drivers/net/ethernet/intel/ixgbevf/ethtool.c | 18 +++++--
drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 2 +-
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 30 ++++++------
drivers/net/ethernet/intel/ixgbevf/vf.c | 12 ++++-
11 files changed, 119 insertions(+), 69 deletions(-)
--
1.7.7.6
^ permalink raw reply
* Re: [GIT] Networking
From: Jeff Kirsher @ 2012-05-03 9:44 UTC (permalink / raw)
To: Srivatsa S. Bhat
Cc: David Miller, torvalds, akpm, netdev, linux-kernel, bpoirier, rjw,
linux-pm, stephen.s.ko
In-Reply-To: <4FA251B5.8080109@linux.vnet.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 976 bytes --]
On Thu, 2012-05-03 at 15:06 +0530, Srivatsa S. Bhat wrote:
> On 05/03/2012 03:02 PM, David Miller wrote:
>
> > From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
> > Date: Thu, 03 May 2012 14:36:57 +0530
> >
> >> https://lkml.org/lkml/2012/4/5/197
> >
> > Networking patches not posted to netdev and the Intel ethernet driver
> > maintainers will be ignored.
> >
>
>
> Jeff Kirsher (Intel ethernet driver maintainer) already acked that
> patchset (both patches).
>
> https://lkml.org/lkml/2012/4/5/376
> https://lkml.org/lkml/2012/4/5/377
>
> One went upstream, the other didn't (yet). That's my concern.
>
> Regards,
> Srivatsa S. Bhat
>
The second has not been ignored or dropped. I pushed one of the patches
and we are finishing up the validation on the second patch. I should
have the second patch pushed here in the next day or so. I apologize
for not being able to push both patches at the same time.
Cheers,
Jeff
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: sky2 still badly broken
From: Niccolò Belli @ 2012-05-03 9:40 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
In-Reply-To: <20120502115618.04ab8ff9@s6510.linuxnetplumber.net>
Il 02/05/2012 20:56, Stephen Hemminger ha scritto:
> It could be that your switch doesn't do autonegotiation or flow
> control. You are getting receive fifo overflow errors.
I don't have this problem with other NICs. Also transfer rate is very
low (even 2 MB/s sometimes) while I get ~110MB/s with other NICs (and
the same switch of course).
Niccolò
^ permalink raw reply
* Re: [GIT] Networking
From: Srivatsa S. Bhat @ 2012-05-03 9:36 UTC (permalink / raw)
To: David Miller
Cc: torvalds, akpm, netdev, linux-kernel, bpoirier, jeffrey.t.kirsher,
rjw, linux-pm, stephen.s.ko
In-Reply-To: <20120503.053246.92708809581536438.davem@davemloft.net>
On 05/03/2012 03:02 PM, David Miller wrote:
> From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
> Date: Thu, 03 May 2012 14:36:57 +0530
>
>> https://lkml.org/lkml/2012/4/5/197
>
> Networking patches not posted to netdev and the Intel ethernet driver
> maintainers will be ignored.
>
Jeff Kirsher (Intel ethernet driver maintainer) already acked that
patchset (both patches).
https://lkml.org/lkml/2012/4/5/376
https://lkml.org/lkml/2012/4/5/377
One went upstream, the other didn't (yet). That's my concern.
Regards,
Srivatsa S. Bhat
^ permalink raw reply
* [PATCH net-next] net: Fix truesize accounting in skb_gro_receive()
From: Eric Dumazet @ 2012-05-03 9:33 UTC (permalink / raw)
To: Alexander Duyck, David Miller; +Cc: netdev, jeffrey.t.kirsher
In-Reply-To: <20120503071859.13636.30050.stgit@gitlad.jf.intel.com>
From: Eric Dumazet <edumazet@google.com>
GRO is very optimistic in skb truesize estimates, only taking into
account the used part of fragments.
Be conservative, and use more precise computation, so that bloated GRO
skbs can be collapsed eventually.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/core/skbuff.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9e8caa0..e1f8bba 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2871,6 +2871,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
unsigned int len = skb_gro_len(skb);
unsigned int offset = skb_gro_offset(skb);
unsigned int headlen = skb_headlen(skb);
+ unsigned int delta_truesize;
if (p->len + len >= 65536)
return -E2BIG;
@@ -2900,11 +2901,14 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
frag->page_offset += offset;
skb_frag_size_sub(frag, offset);
+ /* all fragments truesize : remove (head size + sk_buff) */
+ delta_truesize = skb->truesize - SKB_TRUESIZE(skb_end_pointer(skb) - skb->head);
+
skb->truesize -= skb->data_len;
skb->len -= skb->data_len;
skb->data_len = 0;
- NAPI_GRO_CB(skb)->free = 1;
+ NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE;
goto done;
} else if (skb->head_frag) {
int nr_frags = pinfo->nr_frags;
@@ -2929,6 +2933,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
/* We dont need to clear skbinfo->nr_frags here */
+ delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
goto done;
} else if (skb_gro_len(p) != pinfo->gso_size)
@@ -2971,7 +2976,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
p = nskb;
merge:
- p->truesize += skb->truesize - len;
+ delta_truesize = skb->truesize;
if (offset > headlen) {
unsigned int eat = offset - headlen;
@@ -2991,7 +2996,7 @@ merge:
done:
NAPI_GRO_CB(p)->count++;
p->data_len += len;
- p->truesize += len;
+ p->truesize += delta_truesize;
p->len += len;
NAPI_GRO_CB(skb)->same_flow = 1;
^ permalink raw reply related
* Re: [GIT] Networking
From: David Miller @ 2012-05-03 9:32 UTC (permalink / raw)
To: srivatsa.bhat
Cc: torvalds, akpm, netdev, linux-kernel, bpoirier, jeffrey.t.kirsher,
rjw, linux-pm, stephen.s.ko
In-Reply-To: <4FA24AB1.9010108@linux.vnet.ibm.com>
From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Date: Thu, 03 May 2012 14:36:57 +0530
> https://lkml.org/lkml/2012/4/5/197
Networking patches not posted to netdev and the Intel ethernet driver
maintainers will be ignored.
^ permalink raw reply
* Re: [PATCH 4/6] tcp: Repair socket queues
From: David Miller @ 2012-05-03 9:31 UTC (permalink / raw)
To: xemul; +Cc: eric.dumazet, netdev
In-Reply-To: <4FA248E4.7060501@parallels.com>
From: Pavel Emelyanov <xemul@parallels.com>
Date: Thu, 03 May 2012 12:59:16 +0400
> Well, yes, but this ability is given to CAP_SYS_NET_ADMIN users only.
> Do you think it's nonetheless worth accounting this allocation into
> the socket's rmem?
Often such too large lengths can be a bug in the application, so best
to catch it than let it silently succeed.
Also, restricting an operation to "privileged" entities does not mean
we should forego resource utilization checks.
^ permalink raw reply
* Re: [PATCH 4/6] tcp: Repair socket queues
From: Pavel Emelyanov @ 2012-05-03 9:15 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Linux Netdev List, David Miller
In-Reply-To: <1336036120.10187.7.camel@edumazet-glaptop>
On 05/03/2012 01:08 PM, Eric Dumazet wrote:
> On Thu, 2012-05-03 at 12:59 +0400, Pavel Emelyanov wrote:
>> On 05/02/2012 03:11 PM, Eric Dumazet wrote:
>
>>> I am not sure any check is performed on 'size' ?
>>
>> No, no checks here.
>>
>>> A caller might trigger OOM or wrap bug.
>>
>> Well, yes, but this ability is given to CAP_SYS_NET_ADMIN users only.
>> Do you think it's nonetheless worth accounting this allocation into
>> the socket's rmem?
>
> Yes, something must be done...
>
> Might be a good reason to un-inline tcp_try_rmem_schedule(), this fat
> thing...
OK, will try to look at it.
Thanks,
Pavel
^ permalink raw reply
* Re: [PATCH 4/6] tcp: Repair socket queues
From: Eric Dumazet @ 2012-05-03 9:08 UTC (permalink / raw)
To: Pavel Emelyanov; +Cc: Linux Netdev List, David Miller
In-Reply-To: <4FA248E4.7060501@parallels.com>
On Thu, 2012-05-03 at 12:59 +0400, Pavel Emelyanov wrote:
> On 05/02/2012 03:11 PM, Eric Dumazet wrote:
> > I am not sure any check is performed on 'size' ?
>
> No, no checks here.
>
> > A caller might trigger OOM or wrap bug.
>
> Well, yes, but this ability is given to CAP_SYS_NET_ADMIN users only.
> Do you think it's nonetheless worth accounting this allocation into
> the socket's rmem?
Yes, something must be done...
Might be a good reason to un-inline tcp_try_rmem_schedule(), this fat
thing...
^ permalink raw reply
* Re: vhost-net: is there a race for sock in handle_tx/rx?
From: Liu ping fan @ 2012-05-03 9:08 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: netdev, kvm, linux-kernel
In-Reply-To: <20120503084115.GM8266@redhat.com>
Oh, got it. It is a very interesting implement.
Thanks and regards,
pingfan
On Thu, May 3, 2012 at 4:41 PM, Michael S. Tsirkin <mst@redhat.com> wrote:
> On Thu, May 03, 2012 at 04:33:55PM +0800, Liu ping fan wrote:
>> Hi,
>>
>> During reading the vhost-net code, I find the following,
>>
>> static void handle_tx(struct vhost_net *net)
>> {
>> struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
>> unsigned out, in, s;
>> int head;
>> struct msghdr msg = {
>> .msg_name = NULL,
>> .msg_namelen = 0,
>> .msg_control = NULL,
>> .msg_controllen = 0,
>> .msg_iov = vq->iov,
>> .msg_flags = MSG_DONTWAIT,
>> };
>> size_t len, total_len = 0;
>> int err, wmem;
>> size_t hdr_size;
>> struct socket *sock;
>> struct vhost_ubuf_ref *uninitialized_var(ubufs);
>> bool zcopy;
>>
>> /* TODO: check that we are running from vhost_worker? */
>> sock = rcu_dereference_check(vq->private_data, 1);
>> if (!sock)
>> return;
>>
>> --------------------------------> Qemu calls
>> vhost_net_set_backend() to set a new backend fd, and close
>> @oldsock->file. And sock->file refcnt==0.
>>
>> Can vhost_worker prevent
>> itself from such situation? And how?
>>
>> wmem = atomic_read(&sock->sk->sk_wmem_alloc);
>> .........................................................................
>>
>> Is it a race?
>>
>> Thanks and regards,
>> pingfan
>
> See comment before void __rcu *private_data in vhost.h
>
>
^ permalink raw reply
* Re: [GIT] Networking
From: Srivatsa S. Bhat @ 2012-05-03 9:06 UTC (permalink / raw)
To: David Miller
Cc: torvalds, akpm, netdev, linux-kernel, bpoirier, jeffrey.t.kirsher,
Rafael J. Wysocki, Linux PM mailing list, stephen.s.ko
In-Reply-To: <20120503.025951.1393913795357644010.davem@davemloft.net>
On 05/03/2012 12:29 PM, David Miller wrote:
>
> It's the usual jumble of small fixes, mostly in drivers, but a few in
> core infrastructure parts and TCP.
>
> 1) Transfer padding was wrong for full-speed USB in ASIX driver,
> fix from Ingo van Lil.
>
> 2) Propagate the negative packet offset fix into the PowerPC BPF JIT.
> From Jan Seiffert.
>
> 3) dl2k driver's private ioctls were letting unprivileged tasks make
> MII writes and other ugly bits like that. Fix from Jeff Mahoney.
>
> 4) Fix TX VLAN and RX packet drops in ucc_geth, from Joakim Tjernlund.
>
> 5) OOPS and network namespace fixes in IPVS from Hans Schillstrom and
> Julian Anastasov.
>
> 6) Fix races and sleeping in locked context bugs in drop_monitor, from
> Neil Horman.
>
> 7) Fix link status indication in smsc95xx driver, from Paolo Pisati.
>
> 8) Fix bridge netfilter OOPS, from Peter Huang.
>
> 9) L2TP sendmsg can return on error conditions with the socket lock
> held, oops. Fix from Sasha Levin.
>
> 10) udp_diag should return meaningful values for socket memory usage,
> from Shan Wei.
>
> 11) Eric Dumazet is so awesome he gets his own section:
>
> Socket memory cgroup code (I never should have applied those
> patches, grumble...) made erroneous changes to
> sk_sockets_allocated_read_positive(). It was changed to
> use percpu_counter_sum_positive (which requires BH disabling)
> instead of percpu_counter_read_positive (which does not).
> Revert back to avoid crashes and lockdep warnings.
>
> Adjust the default tcp_adv_win_scale and tcp_rmem[2] values
> to fix throughput regressions. This is necessary as a result
> of our more precise skb->truesize tracking.
>
> Fix SKB leak in netem packet scheduler.
>
> 12) New device IDs for various bluetooth devices, from Manoj Iyer,
> AceLan Kao, and Steven Harms.
>
> 13) Fix command completion race in ipw2200, from Stanislav Yakovlev.
>
> 14) Fix rtlwifi oops on unload, from Larry Finger.
>
> 15) Fix hard_mtu when adjusting hard_header_len in smsc95xx driver. From
> Stephane Fillod.
>
> 16) ehea driver registers it's IRQ before all the necessary state is
> setup, resulting in crashes. Fix from Thadeu Lima de Souza
> Cascardo.
>
> 17) Fix PHY connection failures in davinci_emac driver, from Anatolij
> Gustschin.
>
> 18) Missing break; in switch statement in bluetooth's
> hci_cmd_complete_evt(). Fix from Szymon Janc.
>
> 19) Fix queue programming in iwlwifi, from Johannes Berg.
>
> 20) Interrupt throttling defaults not being actually programmed
> into the hardware, fix from Jeff Kirsher and Ying Cai.
>
> 21) TLAN driver SKB encoding in descriptor busted on 64-bit, fix
> from Benjamin Poirier.
>
> 22) Fix blind status block RX producer pointer deref in TG3 driver,
> from Matt Carlson.
>
> 23) Promisc and multicast are busted on ehea, fixes from Thadeu Lima
> de Souza Cascardo.
>
> 24) Fix crashes in 6lowpan, from Alexander Smirnov.
>
> 25) tcp_complete_cwr() needs to be careful to not rewind the CWND to
> ssthresh if ssthresh has the "infinite" value. Fix from Yuchung
> Cheng.
>
> Please pull, thanks a lot.
>
> The following changes since commit 4d634ca35a8b38530b134ae92bc9e3cc9c23c030:
>
> Merge branch 'rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild (2012-04-23 19:45:19 -0700)
>
> are available in the git repository at:
>
>
> git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git master
>
> for you to fetch changes up to 5a8887d39e1ba5ee2d4ccb94b14d6f2dce5ddfca:
>
> sungem: Fix WakeOnLan (2012-05-03 01:42:55 -0400)
>
> ----------------------------------------------------------------
> AceLan Kao (2):
> Bluetooth: Add support for Atheros [13d3:3362]
> Bluetooth: Add support for AR3012 [0cf3:e004]
>
> Alexander Duyck (1):
> ixgbe: Fix a memory leak in IEEE DCB
>
> Anatolij Gustschin (1):
> net/davinci_emac: fix failing PHY connect attempts
>
> Benjamin Poirier (1):
> tlan: add cast needed for proper 64 bit operation
>
Oh, looks like even this pull request missed the igb fix from Benjamin.
https://lkml.org/lkml/2012/4/5/197
I don't mean to rush things, but my only concern here is to ensure that
this patch doesn't get lost, because the fix is important, is stable
material (I see warnings/stacktraces during suspend/resume in stable
kernels very frequently and this patch fixes it) and a similar fix for
ixgbe (patch 2/2 in that patchset, https://lkml.org/lkml/2012/4/5/198)
went upstream in a previous -rc (commit 34948a947d), while this one got
left out...
In case the above mentioned patch is already in the pipeline, sorry for
the noise..
Regards,
Srivatsa S. Bhat
IBM Linux Technology Center
^ permalink raw reply
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