libata: improve EH internal command timeout handling

ATA_TMOUT_INTERNAL which was 30secs were used for all internal
commands which is way too long when something goes wrong.  This patch
implements command type based stepped timeouts.  Different command
types can use different timeouts and each command type can use
different timeout values after timeouts.

ie. the initial timeout is set to a value which should cover most of
the cases but not too long so that run away cases don't delay things
too much.  After the first try times out, the second try can use
longer timeout and if that one times out too, it can go for full 30sec
timeout.

IDENTIFYs use 5s - 10s - 30s timeout and all other commands use 5s -
10s timeouts.

This patch significantly cuts down the needed time to handle failure
cases while still allowing libata to work with nut job devices through
retries.

Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>

1 files changed, 7 insertions, 1 deletions

diff --git a/include/linux/libata.h b/include/linux/libata.h
index 9058c2a325a..035f8e1cd0a 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -237,7 +237,6 @@ enum {
 	/* various lengths of time */
 	ATA_TMOUT_BOOT		= 30000,	/* heuristic */
 	ATA_TMOUT_BOOT_QUICK	=  7000,	/* heuristic */
-	ATA_TMOUT_INTERNAL	= 30000,
 	ATA_TMOUT_INTERNAL_QUICK = 5000,
 
 	/* FIXME: GoVault needs 2s but we can't afford that without
@@ -341,6 +340,11 @@ enum {
 
 	SATA_PMP_RW_TIMEOUT	= 3000,		/* PMP read/write timeout */
 
+	/* This should match the actual table size of
+	 * ata_eh_cmd_timeout_table in libata-eh.c.
+	 */
+	ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 5,
+
 	/* Horkage types. May be set by libata or controller on drives
 	   (some horkage may be drive/controller pair dependant */
 
@@ -598,6 +602,8 @@ struct ata_eh_info {
 struct ata_eh_context {
 	struct ata_eh_info	i;
 	int			tries[ATA_MAX_DEVICES];
+	int			cmd_timeout_idx[ATA_MAX_DEVICES]
+					       [ATA_EH_CMD_TIMEOUT_TABLE_SIZE];
 	unsigned int		classes[ATA_MAX_DEVICES];
 	unsigned int		did_probe_mask;
 	unsigned int		saved_ncq_enabled;