[PATCH] gianfar: Fix TX ring processing on SMP machines

Subsystems: networking drivers, the rest

STALE5905d REVIEWED: 2 (0M)

2 review trailers.

4 messages, 4 authors, 2010-06-11 · open the first message on its own page

[PATCH] gianfar: Fix TX ring processing on SMP machines

From: Anton Vorontsov <hidden>
Date: 2010-03-03 18:19:01

Starting with commit a3bc1f11e9b867a4f49505 ("gianfar: Revive SKB
recycling") gianfar driver sooner or later stops transmitting any
packets on SMP machines.

start_xmit() prepares new skb for transmitting, generally it does
three things:

1. sets up all BDs (marks them ready to send), except the first one.
2. stores skb into tx_queue->tx_skbuff so that clean_tx_ring()
   would cleanup it later.
3. sets up the first BD, i.e. marks it ready.

Here is what clean_tx_ring() does:

1. reads skbs from tx_queue->tx_skbuff
2. checks if the *last* BD is ready. If it's still ready [to send]
   then it it isn't transmitted, so clean_tx_ring() returns.
   Otherwise it actually cleanups BDs. All is OK.

Now, if there is just one BD, code flow:

- start_xmit(): stores skb into tx_skbuff. Note that the first BD
  (which is also the last one) isn't marked as ready, yet.
- clean_tx_ring(): sees that skb is not null, *and* its lstatus
  says that it is NOT ready (like if BD was sent), so it cleans
  it up (bad!)
- start_xmit(): marks BD as ready [to send], but it's too late.

We can fix this simply by reordering lstatus/tx_skbuff writes.

Reported-by: Martyn Welch <redacted>
Bisected-by: Paul Gortmaker [off-list ref]
Signed-off-by: Anton Vorontsov <redacted>
Tested-by: Paul Gortmaker <redacted>
Tested-by: Martyn Welch <redacted>
Cc: Sandeep Gopalpet <redacted>
Cc: Stable <redacted> [2.6.33]
---
 drivers/net/gianfar.c |    5 ++++-
 1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index 8bd3c9f..cccb409 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -2021,7 +2021,6 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/* setup the TxBD length and buffer pointer for the first BD */
-	tx_queue->tx_skbuff[tx_queue->skb_curtx] = skb;
 	txbdp_start->bufPtr = dma_map_single(&priv->ofdev->dev, skb->data,
 			skb_headlen(skb), DMA_TO_DEVICE);
 
@@ -2053,6 +2052,10 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	txbdp_start->lstatus = lstatus;
 
+	eieio(); /* force lstatus write before tx_skbuff */
+
+	tx_queue->tx_skbuff[tx_queue->skb_curtx] = skb;
+
 	/* Update the current skb pointer to the next entry we will use
 	 * (wrapping if necessary) */
 	tx_queue->skb_curtx = (tx_queue->skb_curtx + 1) &
-- 
1.7.0

Re: [PATCH] gianfar: Fix TX ring processing on SMP machines

From: David Miller <davem@davemloft.net>
Date: 2010-03-04 08:41:39

From: Anton Vorontsov <redacted>
Date: Wed, 3 Mar 2010 21:18:58 +0300
Starting with commit a3bc1f11e9b867a4f49505 ("gianfar: Revive SKB
recycling") gianfar driver sooner or later stops transmitting any
packets on SMP machines.

start_xmit() prepares new skb for transmitting, generally it does
three things:

1. sets up all BDs (marks them ready to send), except the first one.
2. stores skb into tx_queue->tx_skbuff so that clean_tx_ring()
   would cleanup it later.
3. sets up the first BD, i.e. marks it ready.

Here is what clean_tx_ring() does:

1. reads skbs from tx_queue->tx_skbuff
2. checks if the *last* BD is ready. If it's still ready [to send]
   then it it isn't transmitted, so clean_tx_ring() returns.
   Otherwise it actually cleanups BDs. All is OK.

Now, if there is just one BD, code flow:

- start_xmit(): stores skb into tx_skbuff. Note that the first BD
  (which is also the last one) isn't marked as ready, yet.
- clean_tx_ring(): sees that skb is not null, *and* its lstatus
  says that it is NOT ready (like if BD was sent), so it cleans
  it up (bad!)
- start_xmit(): marks BD as ready [to send], but it's too late.

We can fix this simply by reordering lstatus/tx_skbuff writes.

Reported-by: Martyn Welch <redacted>
Bisected-by: Paul Gortmaker [off-list ref]
Signed-off-by: Anton Vorontsov <redacted>
Tested-by: Paul Gortmaker <redacted>
Tested-by: Martyn Welch <redacted>
Applied.

Re: [PATCH] gianfar: Fix TX ring processing on SMP machines

From: Kumar Gala <hidden>
Date: 2010-03-04 16:34:29

On Mar 4, 2010, at 2:41 AM, David Miller wrote:
From: Anton Vorontsov <redacted>
Date: Wed, 3 Mar 2010 21:18:58 +0300
=20
quoted
Starting with commit a3bc1f11e9b867a4f49505 ("gianfar: Revive SKB
recycling") gianfar driver sooner or later stops transmitting any
packets on SMP machines.
=20
start_xmit() prepares new skb for transmitting, generally it does
three things:
=20
1. sets up all BDs (marks them ready to send), except the first one.
2. stores skb into tx_queue->tx_skbuff so that clean_tx_ring()
  would cleanup it later.
3. sets up the first BD, i.e. marks it ready.
=20
Here is what clean_tx_ring() does:
=20
1. reads skbs from tx_queue->tx_skbuff
2. checks if the *last* BD is ready. If it's still ready [to send]
  then it it isn't transmitted, so clean_tx_ring() returns.
  Otherwise it actually cleanups BDs. All is OK.
=20
Now, if there is just one BD, code flow:
=20
- start_xmit(): stores skb into tx_skbuff. Note that the first BD
 (which is also the last one) isn't marked as ready, yet.
- clean_tx_ring(): sees that skb is not null, *and* its lstatus
 says that it is NOT ready (like if BD was sent), so it cleans
 it up (bad!)
- start_xmit(): marks BD as ready [to send], but it's too late.
=20
We can fix this simply by reordering lstatus/tx_skbuff writes.
=20
Reported-by: Martyn Welch <redacted>
Bisected-by: Paul Gortmaker [off-list ref]
Signed-off-by: Anton Vorontsov <redacted>
Tested-by: Paul Gortmaker <redacted>
Tested-by: Martyn Welch <redacted>
=20
Applied.
Anton,

Once this makes it into Linus's tree can you make sure we get it added =
to -stable.

- k=

Re: [PATCH] gianfar: Fix TX ring processing on SMP machines

From: Esben Haabendal <hidden>
Date: 2010-06-11 08:45:27

On Wed, Mar 3, 2010 at 8:18 PM, Anton Vorontsov
[off-list ref] wrote:
quoted hunk
Starting with commit a3bc1f11e9b867a4f49505 ("gianfar: Revive SKB
recycling") gianfar driver sooner or later stops transmitting any
packets on SMP machines.

start_xmit() prepares new skb for transmitting, generally it does
three things:

1. sets up all BDs (marks them ready to send), except the first one.
2. stores skb into tx_queue->tx_skbuff so that clean_tx_ring()
=A0 would cleanup it later.
3. sets up the first BD, i.e. marks it ready.

Here is what clean_tx_ring() does:

1. reads skbs from tx_queue->tx_skbuff
2. checks if the *last* BD is ready. If it's still ready [to send]
=A0 then it it isn't transmitted, so clean_tx_ring() returns.
=A0 Otherwise it actually cleanups BDs. All is OK.

Now, if there is just one BD, code flow:

- start_xmit(): stores skb into tx_skbuff. Note that the first BD
=A0(which is also the last one) isn't marked as ready, yet.
- clean_tx_ring(): sees that skb is not null, *and* its lstatus
=A0says that it is NOT ready (like if BD was sent), so it cleans
=A0it up (bad!)
- start_xmit(): marks BD as ready [to send], but it's too late.

We can fix this simply by reordering lstatus/tx_skbuff writes.

Reported-by: Martyn Welch <redacted>
Bisected-by: Paul Gortmaker [off-list ref]
Signed-off-by: Anton Vorontsov <redacted>
Tested-by: Paul Gortmaker <redacted>
Tested-by: Martyn Welch <redacted>
Cc: Sandeep Gopalpet <redacted>
Cc: Stable <redacted> [2.6.33]
---
=A0drivers/net/gianfar.c | =A0 =A05 ++++-
=A01 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index 8bd3c9f..cccb409 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -2021,7 +2021,6 @@ static int gfar_start_xmit(struct sk_buff *skb, str=
uct net_device *dev)
=A0 =A0 =A0 =A0}

=A0 =A0 =A0 =A0/* setup the TxBD length and buffer pointer for the first =
BD */
- =A0 =A0 =A0 tx_queue->tx_skbuff[tx_queue->skb_curtx] =3D skb;
=A0 =A0 =A0 =A0txbdp_start->bufPtr =3D dma_map_single(&priv->ofdev->dev, =
skb->data,
=A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0skb_headlen(skb), DMA_TO_D=
EVICE);
quoted hunk
@@ -2053,6 +2052,10 @@ static int gfar_start_xmit(struct sk_buff *skb, st=
ruct net_device *dev)
=A0 =A0 =A0 =A0txbdp_start->lstatus =3D lstatus;

+ =A0 =A0 =A0 eieio(); /* force lstatus write before tx_skbuff */
+
+ =A0 =A0 =A0 tx_queue->tx_skbuff[tx_queue->skb_curtx] =3D skb;
+
=A0 =A0 =A0 =A0/* Update the current skb pointer to the next entry we wil=
l use
=A0 =A0 =A0 =A0 * (wrapping if necessary) */
=A0 =A0 =A0 =A0tx_queue->skb_curtx =3D (tx_queue->skb_curtx + 1) &
This patch also makes gianfar work stable on mpc8313 with 2.6.33/RT_PREEMPT=
.
WIthout it, I see exactly the same problems as reported by Anton on SMP.

/Esben
--=20
Esben Haabendal, Senior Software Consultant
Dor=E9Development ApS, Ved Stranden 1, 9560 Hadsund, DK-Denmark
Phone: +45 51 92 53 93, E-mail: eha@doredevelopment.dk
WWW: http://www.doredevelopment.dk
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help