[PATCH] Sun ldom vnet driver dead lock

[Yongli He]

static irqreturn_t ldc_rx(int irq, void *dev_id){
...
out:
	spin_unlock_irqrestore(&lp->lock, flags);
                     << here run with out any lock
	send_events(lp, event_mask);
       //if 2 vnet attach to same vswitch, ldom
       //will report 2 irq then lead to dead lock
       //on the vio->lock or lp->lock
}

this version fix just serialize all the event.

Signed-off-by: Yongli He <heyongli@xxxxxxxxx>
---
 arch/sparc64/kernel/ldc.c |    5 ++++-
 1 files changed, 4 insertions(+), 1 deletions(-)

diff --git a/arch/sparc64/kernel/ldc.c b/arch/sparc64/kernel/ldc.c
index a6b75cd..8d7c9b5 100644
--- a/arch/sparc64/kernel/ldc.c
+++ b/arch/sparc64/kernel/ldc.c
@@ -785,6 +785,8 @@ static void send_events(struct ldc_channel *lp,
unsigned int event_mask)
 		lp->cfg.event(lp->event_arg, LDC_EVENT_DATA_READY);
 }

+static spinlock_t event_lock=__SPIN_LOCK_UNLOCKED("ldc_event lock");
+
 static irqreturn_t ldc_rx(int irq, void *dev_id)
 {
 	struct ldc_channel *lp = dev_id;
@@ -892,9 +894,10 @@ handshake_complete:
 	}

 out:
+	spin_lock_irqsave(&event_lock, flags);//serialize all events
 	spin_unlock_irqrestore(&lp->lock, flags);
-
 	send_events(lp, event_mask);
+        spin_unlock_irqrestore(&event_lock, flags);

 	return IRQ_HANDLED;
 }
-- 
1.5.5.1.dirty




2009/9/23 hyl <heyongli@xxxxxxxxx>:
> console output:
>
> e1000e: Intel(R) PRO/1000 Network Driver - 0.3.3.3-k6
> e1000e: Intel(R) PRO/1000 Network Driver - 0.3.3.3-k6
> e1000e: Copyright (c) 1999-2008 Intel Corporation.
> e1000e: Copyright (c) 1999-2008 Intel Corporation.
> sunvnet.c:v1.0 (June 25, 2007)
> sunvnet.c:v1.0 (June 25, 2007)
> eth0: Sun LDOM vnet 00:14:4f:f9:68:e0:t
> e0
> eth0: PORT ( remote-mac 00:14:4f:fa:03:81 switch-port )
> eth0: PORT ( remote-mac 00:14:4f:fa:03:81 switch-port )
> eth0: PORT ( remote-mac 00:14:4f:f9:84:06 )
> eth0: PORT ( remote-mac 00:14:4f:f9:84:06 )
> eth0: PORT ( remote-mac 00:14:4f:f9:9a:40 )
> eth0: PORT ( remote-mac 00:14:4f:f9:9a:40 )
> eth0: PORT ( remote-mac 00:14:4f:f8:c5:7b )
> eth0: PORT ( remote-mac 00:14:4f:f8:c5:7b )
> eth1: Sun LDOM vnet 00:14:4f:f8:c5:7b:t
> 7b
> eth1: PORT ( remote-mac 00:14:4f:fa:03:81 switch-port )
> eth1: PORT ( remote-mac 00:14:4f:fa:03:81 switch-port )
> eth1: PORT ( remote-mac 00:14:4f:f9:84:06 )
> eth1: PORT ( remote-mac 00:14:4f:f9:84:06 )
> eth1: PORT ( remote-mac 00:14:4f:f9:9a:40 )
> eth1: PORT ( remote-mac 00:14:4f:f9:9a:40 )
> eth1: PORT ( remote-mac 00:14:4f:f9:68:e0 )
> eth1: PORT ( remote-mac 00:14:4f:f9:68:e0 )
>
> two vnets bound to the same vswitch, then hang,
> ldm add-vnet vnet0 primary-vsw1 dom1
> ldm add-vnet vnet1 primary-vsw1 ldom1
>
> If 'eth1' and 'eth2' are bound to different vswitches, everything is fine.
>
>
> Yongli He
>
--
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/