Skip to contentSkip to conversation

staging: hv: Gracefully handle SCSI resets - RESEND

PATCH In review Hank Janssen 3 participants 3 messages Aug 31, 2010 – Sep 2, 2010

Subsystems (2)
Staging virtio core
lore
Share & tools
lore

Hank Janssen

author
#0 lore raw

PATCH 5/5 staging: hv: Gracefully handle SCSI resets - RESEND

(Send from a linux machine, not routed through exchange)

If we get a SCSI host bus reset we now gracefully handle it, and we take the device offline. This before sometimes caused hangs.

Signed-off-by Hank Janssen <[email protected]
Signed-off-by Haiyang Zhang <[email protected]
---
 drivers/staging/hv/storvsc.c |   36 +++++++++++++++++++++++++++++++++++-
 1 files changed, 35 insertions(+), 1 deletions(-)
drivers/staging/hv/storvsc.c +35 -1
index 6bd2ff1..5f222cf 100644
@@ -48,7 +48,9 @@ struct storvsc_device {
 
 	/* 0 indicates the device is being destroyed */
 	atomic_t RefCount;
-
+	
+	int reset;
+	spinlock_t lock;
 	atomic_t NumOutstandingRequests;
 
 	/*

@@ -93,6 +95,9 @@ static inline struct storvsc_device *AllocStorDevice(struct hv_device *Device)
 	atomic_cmpxchg(&storDevice->RefCount, 0, 2);
 
 	storDevice->Device = Device;
+	storDevice->reset  = 0;
+	spin_lock_init(&storDevice->lock);
+
 	Device->Extension = storDevice;
 
 	return storDevice;

@@ -101,6 +106,7 @@ static inline struct storvsc_device *AllocStorDevice(struct hv_device *Device)
 static inline void FreeStorDevice(struct storvsc_device *Device)
 {
 	/* ASSERT(atomic_read(&Device->RefCount) == 0); */
+	/*kfree(Device->lock);*/
 	kfree(Device);
 }
 

@@ -108,13 +114,24 @@ static inline void FreeStorDevice(struct storvsc_device *Device)
 static inline struct storvsc_device *GetStorDevice(struct hv_device *Device)
 {
 	struct storvsc_device *storDevice;
+	unsigned long flags;
 
 	storDevice = (struct storvsc_device *)Device->Extension;
+
+	spin_lock_irqsave(&storDevice->lock, flags);
+
+	if (storDevice->reset == 1) {
+		spin_unlock_irqrestore(&storDevice->lock, flags);
+		return NULL;
+	}
+
 	if (storDevice && atomic_read(&storDevice->RefCount) > 1)
 		atomic_inc(&storDevice->RefCount);
 	else
 		storDevice = NULL;
 
+	spin_unlock_irqrestore(&storDevice->lock, flags);
+
 	return storDevice;
 }
 

@@ -122,13 +139,19 @@ static inline struct storvsc_device *GetStorDevice(struct hv_device *Device)
 static inline struct storvsc_device *MustGetStorDevice(struct hv_device *Device)
 {
 	struct storvsc_device *storDevice;
+	unsigned long flags;
 
 	storDevice = (struct storvsc_device *)Device->Extension;
+
+	spin_lock_irqsave(&storDevice->lock, flags);
+
 	if (storDevice && atomic_read(&storDevice->RefCount))
 		atomic_inc(&storDevice->RefCount);
 	else
 		storDevice = NULL;
 
+	spin_unlock_irqrestore(&storDevice->lock, flags);
+
 	return storDevice;
 }
 

@@ -614,6 +637,7 @@ int StorVscOnHostReset(struct hv_device *Device)
 	struct storvsc_device *storDevice;
 	struct storvsc_request_extension *request;
 	struct vstor_packet *vstorPacket;
+	unsigned long flags;
 	int ret;
 
 	DPRINT_INFO(STORVSC, "resetting host adapter...");

@@ -625,6 +649,16 @@ int StorVscOnHostReset(struct hv_device *Device)
 		return -1;
 	}
 
+	spin_lock_irqsave(&storDevice->lock, flags);
+	storDevice->reset = 1;
+	spin_unlock_irqrestore(&storDevice->lock, flags);
+
+	/*
+	 * Wait for traffic in transit to complete
+	 */
+	while (atomic_read(&storDevice->NumOutstandingRequests))
+		udelay(1000);
+
 	request = &storDevice->ResetRequest;
 	vstorPacket = &request->VStorPacket;
Signature · 1 line
1.6.0.2
#1 lore raw
Quoted 4 lines · Hank Janssen

If we get a SCSI host bus reset we now gracefully handle it, and we take the device offline. This before sometimes caused hangs.

---
 drivers/staging/hv/storvsc.c |   36 +++++++++++++++++++++++++++++++++++-

[]

drivers/staging/hv/storvsc.c int StorVscOnHostReset(struct hv_device *Device) · line 661

Quoted 6 lines
drivers/staging/hv/storvsc.c +6 -0
+	/*
+	 * Wait for traffic in transit to complete
+	 */
+	while (atomic_read(&storDevice->NumOutstandingRequests))
+		udelay(1000);
+

Is it useful to have a maximum check or timeout?
Maybe use usleep_range?

#2 lore raw
Quoted 6 lines · Joe Perches
Quoted 4 lines · Hank Janssen

If we get a SCSI host bus reset we now gracefully handle it, and we take the device offline. This before sometimes caused hangs.

---
 drivers/staging/hv/storvsc.c |   36 +++++++++++++++++++++++++++++++++++-

[]

Quoted 9 lines

drivers/staging/hv/storvsc.c int StorVscOnHostReset(struct hv_device *Device) · line 661

Quoted 6 lines
drivers/staging/hv/storvsc.c +6 -0
+	/*
+	 * Wait for traffic in transit to complete
+	 */
+	while (atomic_read(&storDevice->NumOutstandingRequests))
+		udelay(1000);
+

Is it useful to have a maximum check or timeout?
Maybe use usleep_range?

Yeah, that's not good, you need to have some way to get out of here in case something bad happens and that number never goes down.

Why not just use a completion function instead of a busy loop?

thanks,

greg k-h