aoe: allow user to disable target failure timeout

With this change, the aoe driver treats the value zero as special for
the aoe_deadsecs module parameter.  Normally, this value specifies the
number of seconds during which the driver will continue to attempt
retransmits to an unresponsive AoE target.  After aoe_deadsecs has
elapsed, the aoe driver marks the aoe device as "down" and fails all
I/O.

The new meaning of an aoe_deadsecs of zero is for the driver to
retransmit commands indefinitely.

Signed-off-by: Ed Cashin <ecashin@coraid.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 6 insertions, 2 deletions

diff --git a/Documentation/aoe/aoe.txt b/Documentation/aoe/aoe.txt
index bfc9cb19abcd..c71487d399d1 100644
--- a/Documentation/aoe/aoe.txt
+++ b/Documentation/aoe/aoe.txt
@@ -125,7 +125,9 @@ DRIVER OPTIONS
   The aoe_deadsecs module parameter determines the maximum number of
   seconds that the driver will wait for an AoE device to provide a
   response to an AoE command.  After aoe_deadsecs seconds have
-  elapsed, the AoE device will be marked as "down".
+  elapsed, the AoE device will be marked as "down".  A value of zero
+  is supported for testing purposes and makes the aoe driver keep
+  trying AoE commands forever.
 
   The aoe_maxout module parameter has a default of 128.  This is the
   maximum number of unresponded packets that will be sent to an AoE
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index da360f95c8ea..abf4ad2d3e18 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -812,7 +812,9 @@ rexmit_timer(ulong vp)
                 since = tsince_hr(f);
                 n = f->waited_total + since;
                 n /= USEC_PER_SEC;
-                if (n > aoe_deadsecs && !(f->flags & FFL_PROBE)) {
+                if (aoe_deadsecs
+                && n > aoe_deadsecs
+                && !(f->flags & FFL_PROBE)) {
                         /* Waited too long.  Device failure.
                          * Hang all frames on first hash bucket for downdev
                          * to clean up.