Re: ST340823A disk size issue

[Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>]

On Friday 03 August 2007, Mikko Rapeli wrote:
> On Fri, Aug 03, 2007 at 12:34:13AM +0200, Bartlomiej Zolnierkiewicz wrote:
> > Mikko, please verify that the following patch fixes the issue.
> 
> A few oopses later and this actually works with vanilla 2.6.22.1 and Debian
> 2.6.18 (2.6.18.dfsg.1-12etch2), latter without EXPORT_SYMBOL_GPL since
> it's there already.
> 
> diff -X linux-2.6.22.1/Documentation/dontdiff -upr linux-2.6.22.1.orig/drivers/ide/ide-disk.c linux-2.6.22.1/drivers/ide/ide-disk.c
> --- linux-2.6.22.1.orig/drivers/ide/ide-disk.c	2007-07-10 21:56:30.000000000 +0300
> +++ linux-2.6.22.1/drivers/ide/ide-disk.c	2007-08-03 00:22:46.000000000 +0300
> @@ -481,6 +481,15 @@ static inline int idedisk_supports_lba48
>  	       && id->lba_capacity_2;
>  }
>  
> +/*
> + * Some disks report total number of sectors instead of
> + * maximum sector address.  We list them here.
> + */
> +static const struct drive_list_entry hpa_list[] = {
> +	{ "ST340823A",	"ALL" },

Doh, I forgot that the patch to change "ALL" to NULL was merged after 2.6.22.
I should have asked you from the beginning to test against 2.6.23-rc1 but it
is not that bad since now you have also working patches for 2.6.18 / 2.6.22.

;-)

> +	{ NULL       ,  NULL  }

Thanks, added this to the patch.

Final version (for completness) below.

[PATCH] ide-disk: workaround for buggy HPA support on ST340823A (take 3)

This disk reports total number of sectors instead of maximum sector address
in response to READ_NATIVE_MAX_ADDRESS command and also happily accepts
SET_MAX_ADDRESS command with the bogus value.  This results in +1 sector
capacity being used and errors on attempts to use the last sector.

...
hdd: Host Protected Area detected.
        current capacity is 78165360 sectors (40020 MB)
        native  capacity is 78165361 sectors (40020 MB)
hdd: Host Protected Area disabled.
...
hdd: reading: block=78165360, sectors=1, buffer=0xc1e63000
hdd: dma_intr: status=0x51 { DriveReady SeekComplete Error }
hdd: dma_intr: error=0x10 { SectorIdNotFound }, LBAsect=78165360, sector=78165360
...

Add hpa_list[] table and workaround the issue in idedisk_check_hpa().

v2:
* Add missing export and improve patch description a bit.

v3:
* Add list termination.  (From Mikko)

Fixes kernel bugzilla bug #8816.

Thanks to Mikko for investigating the issue and helping with this patch.

Cc: Mikko Rapeli <mikko.rapeli@iki.fi>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
This patch depends on CONFIG_BLK_DEV_IDEDMA=y but for testing purposes
it is OK.  Final version wouldn't depend on CONFIG_BLK_DEV_IDEDMA,
"[PATCH] ide: add cable detection for early UDMA66 devices (take 3)"
which is in IDE quilt tree moves ide_in_drive_list() out of ide-dma.c.

 drivers/ide/ide-disk.c |   18 ++++++++++++++++++
 drivers/ide/ide-dma.c  |    2 ++
 2 files changed, 20 insertions(+)

Index: b/drivers/ide/ide-disk.c
===================================================================
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -481,6 +481,15 @@ static inline int idedisk_supports_lba48
 	       && id->lba_capacity_2;
 }
 
+/*
+ * Some disks report total number of sectors instead of
+ * maximum sector address.  We list them here.
+ */
+static const struct drive_list_entry hpa_list[] = {
+	{ "ST340823A",	NULL },
+	{ NULL,		NULL }
+};
+
 static void idedisk_check_hpa(ide_drive_t *drive)
 {
 	unsigned long long capacity, set_max;
@@ -492,6 +501,15 @@ static void idedisk_check_hpa(ide_drive_
 	else
 		set_max = idedisk_read_native_max_address(drive);
 
+	if (ide_in_drive_list(drive->id, hpa_list)) {
+		/*
+		 * Since we are inclusive wrt to firmware revisions do this
+		 * extra check and apply the workaround only when needed.
+		 */
+		if (set_max == capacity + 1)
+			set_max--;
+	}
+
 	if (set_max <= capacity)
 		return;
 
Index: b/drivers/ide/ide-dma.c
===================================================================
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -153,6 +153,8 @@ int ide_in_drive_list(struct hd_driveid 
 	return 0;
 }
 
+EXPORT_SYMBOL_GPL(ide_in_drive_list);
+
 /**
  *	ide_dma_intr	-	IDE DMA interrupt handler
  *	@drive: the drive the interrupt is for