Patchwork [net-next,v2] igb: remove skb_orphan calls

login
register
mail settings
Submitter Jeff Kirsher
Date March 2, 2009, 11:44 p.m.
Message ID <20090302234337.12241.52123.stgit@lost.foo-projects.org>
Download mbox | patch
Permalink /patch/23971/
State Accepted
Delegated to: David Miller
Headers show

Comments

Jeff Kirsher - March 2, 2009, 11:44 p.m.
From: Alexander Duyck <alexander.h.duyck@intel.com>

Remove skb_orphan call from igb driver as it can cause multiple issues due
to the fact that it is calling the desctructor and removing the skb from
the socket prior to transmission.

The call was added to improve performance but did so by allowing the skb to
be removed from the socket which gave the socket more window space to
transmit.  The performance gain is not worth the extra problems that this
kind of workaround can introduce as this could lead to a potential DoS if a
UDP stream decided to monopolize the transmit path.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/igb/igb_main.c |   11 -----------
 1 files changed, 0 insertions(+), 11 deletions(-)


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
David Miller - March 3, 2009, 12:02 a.m.
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Mon, 02 Mar 2009 15:44:04 -0800

> From: Alexander Duyck <alexander.h.duyck@intel.com>
> 
> Remove skb_orphan call from igb driver as it can cause multiple issues due
> to the fact that it is calling the desctructor and removing the skb from
> the socket prior to transmission.
> 
> The call was added to improve performance but did so by allowing the skb to
> be removed from the socket which gave the socket more window space to
> transmit.  The performance gain is not worth the extra problems that this
> kind of workaround can introduce as this could lead to a potential DoS if a
> UDP stream decided to monopolize the transmit path.
> 
> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
> Acked-by: Mitch Williams <mitch.a.williams@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

Applied.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 6cae258..78558f8 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -3258,14 +3258,6 @@  static int igb_xmit_frame_ring_adv(struct sk_buff *skb,
 	if (unlikely(shtx->hardware)) {
 		shtx->in_progress = 1;
 		tx_flags |= IGB_TX_FLAGS_TSTAMP;
-	} else if (likely(!shtx->software)) {
-		/*
-		 * TODO: can this be solved in dev.c:dev_hard_start_xmit()?
-		 * There are probably unmodified driver which do something
-		 * like this and thus don't work in combination with
-		 * SOF_TIMESTAMPING_TX_SOFTWARE.
-		 */
-		skb_orphan(skb);
 	}
 
 	if (adapter->vlgrp && vlan_tx_tag_present(skb)) {
@@ -4253,9 +4245,6 @@  static void igb_tx_hwtstamp(struct igb_adapter *adapter, struct sk_buff *skb)
 				timecompare_transform(&adapter->compare, ns);
 			skb_tstamp_tx(skb, &shhwtstamps);
 		}
-
-		/* delayed orphaning: skb_tstamp_tx() needs the socket */
-		skb_orphan(skb);
 	}
 }