diff options
author | Alan Stern <stern@rowland.harvard.edu> | 2005-10-24 02:38:56 (GMT) |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@suse.de> | 2005-10-28 23:47:50 (GMT) |
commit | b876aef7f890d8c59a45b78858a36cf60fddf522 (patch) | |
tree | c8211d093fc0ab4ec04d3adaf8388253aa73d0bf /drivers | |
parent | 423e489d704d05c6e8c2927fb1854db85914912a (diff) | |
download | linux-fsl-qoriq-b876aef7f890d8c59a45b78858a36cf60fddf522.tar.xz |
[PATCH] PATCH: usb-storage: move GetMaxLUN later in time
This patch is originally from Alan Stern (as557). It has been re-diffed
against a current tree, and I also corrected a minor merging error.
Some time ago we introduced a delay before device scanning, because many
devices do not like to receive SCSI commands right after enumeration.
Now it turns out there's a device that doesn't like to receive
Get-Max-LUN right after enumeration either. Accordingly this patch
delays the Get-Max-LUN request until the beginning of the scanning
procedure. This fixes Bugzilla entry #5010.
Three things are worth noting. First, I removed the locking code from
usb_stor_acquire_resources. It's not needed, because the locking is to
protect against disconnect events and acquire_resources is only called
during probe (so the disconnect routine can't be called). Second, I
initialized to 0 the buffer used for the Get-Max-LUN response. It's not
really necessary, but it will prevent random values from showing up in
the debugging log when the request fails. Third, I added a test against
the SINGLE_LUN flag. This will allow us to use the flag to indicate
Bulk-only devices that can't handle Get-Max-LUN.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Matthew Dharm <mdharm-usb@one-eyed-alien.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/usb/storage/transport.c | 1 | ||||
-rw-r--r-- | drivers/usb/storage/usb.c | 30 |
2 files changed, 14 insertions, 17 deletions
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index c1ba530..e89e945 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -923,6 +923,7 @@ int usb_stor_Bulk_max_lun(struct us_data *us) int result; /* issue the command */ + us->iobuf[0] = 0; result = usb_stor_control_msg(us, us->recv_ctrl_pipe, US_BULK_GET_MAX_LUN, USB_DIR_IN | USB_TYPE_CLASS | diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 5164900..92ee079 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -747,25 +747,13 @@ static int usb_stor_acquire_resources(struct us_data *us) return -ENOMEM; } - /* Lock the device while we carry out the next two operations */ - down(&us->dev_semaphore); - - /* For bulk-only devices, determine the max LUN value */ - if (us->protocol == US_PR_BULK) { - p = usb_stor_Bulk_max_lun(us); - if (p < 0) { - up(&us->dev_semaphore); - return p; - } - us->max_lun = p; - } - /* Just before we start our control thread, initialize * the device if it needs initialization */ - if (us->unusual_dev->initFunction) - us->unusual_dev->initFunction(us); - - up(&us->dev_semaphore); + if (us->unusual_dev->initFunction) { + p = us->unusual_dev->initFunction(us); + if (p) + return p; + } /* Start up our control thread */ p = kernel_thread(usb_stor_control_thread, us, CLONE_VM); @@ -904,6 +892,14 @@ retry: /* If the device is still connected, perform the scanning */ if (!test_bit(US_FLIDX_DISCONNECTING, &us->flags)) { + + /* For bulk-only devices, determine the max LUN value */ + if (us->protocol == US_PR_BULK && + !(us->flags & US_FL_SINGLE_LUN)) { + down(&us->dev_semaphore); + us->max_lun = usb_stor_Bulk_max_lun(us); + up(&us->dev_semaphore); + } scsi_scan_host(us_to_host(us)); printk(KERN_DEBUG "usb-storage: device scan complete\n"); |