[SCSI] scsi_lib: fix DID_RESET status problems

Andrew Vaszquez said:
> There's a problem that is causing commands returned by the LLD with
> a DID_RESET status to be reissued with cleared cmd->sdb data which
> in our tests are manifesting in firmware detected overruns.  Here's
> a snippet of a READ_10 scsi_cmnd upon completion by the storage

The problem is caused by:

commit b60af5b0adf0da24c673598c8d3fb4d4189a15ce
Author: Alan Stern <stern@rowland.harvard.edu>
Date:   Mon Nov 3 15:56:47 2008 -0500

    [SCSI] simplify scsi_io_completion()

Because scsi_release_buffers() is called before commands that go
through the ACTION_RETRY and ACTION_DELAYED_RETRY legs are requeued.
However, they're not re-prepared, so nothing ever reallocates the
buffer resources to them.  Fix this by releasing the buffers only if
we're not going to go down these legs (but scsi_release_buffers() on
all legs including two in scsi_end_request(); this latter needs a
special version __scsi_release_buffers() because the final one can be
called after the request has been freed, so the bidi test in
scsi_release_buffers(), which touches the request has to be skipped).

Reported-by: Andrew Vasquez <andrew.vasquez@qlogic.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index cc613bae4ad3699d5ee8d7b33dd79bc26a65cb74..940dc32ff0dc731523c0e02849e3772950260ef0 100644 (file)
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -701,6 +701,8 @@ void scsi_run_host_queues(struct Scsi_Host *shost)
                scsi_run_queue(sdev->request_queue);
 }
 
+static void __scsi_release_buffers(struct scsi_cmnd *, int);
+
 /*
  * Function:    scsi_end_request()
  *
@@ -749,6 +751,7 @@ static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int error,
                                 * leftovers in the front of the
                                 * queue, and goose the queue again.
                                 */
+                               scsi_release_buffers(cmd);
                                scsi_requeue_command(q, cmd);
                                cmd = NULL;
                        }
@@ -760,6 +763,7 @@ static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int error,
         * This will goose the queue request function at the end, so we don't
         * need to worry about launching another command.
         */
+       __scsi_release_buffers(cmd, 0);
        scsi_next_command(cmd);
        return NULL;
 }
@@ -815,6 +819,26 @@ static void scsi_free_sgtable(struct scsi_data_buffer *sdb)
        __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free);
 }
 
+static void __scsi_release_buffers(struct scsi_cmnd *cmd, int do_bidi_check)
+{
+
+       if (cmd->sdb.table.nents)
+               scsi_free_sgtable(&cmd->sdb);
+
+       memset(&cmd->sdb, 0, sizeof(cmd->sdb));
+
+       if (do_bidi_check && scsi_bidi_cmnd(cmd)) {
+               struct scsi_data_buffer *bidi_sdb =
+                       cmd->request->next_rq->special;
+               scsi_free_sgtable(bidi_sdb);
+               kmem_cache_free(scsi_sdb_cache, bidi_sdb);
+               cmd->request->next_rq->special = NULL;
+       }
+
+       if (scsi_prot_sg_count(cmd))
+               scsi_free_sgtable(cmd->prot_sdb);
+}
+
 /*
  * Function:    scsi_release_buffers()
  *
@@ -834,21 +858,7 @@ static void scsi_free_sgtable(struct scsi_data_buffer *sdb)
  */
 void scsi_release_buffers(struct scsi_cmnd *cmd)
 {
-       if (cmd->sdb.table.nents)
-               scsi_free_sgtable(&cmd->sdb);
-
-       memset(&cmd->sdb, 0, sizeof(cmd->sdb));
-
-       if (scsi_bidi_cmnd(cmd)) {
-               struct scsi_data_buffer *bidi_sdb =
-                       cmd->request->next_rq->special;
-               scsi_free_sgtable(bidi_sdb);
-               kmem_cache_free(scsi_sdb_cache, bidi_sdb);
-               cmd->request->next_rq->special = NULL;
-       }
-
-       if (scsi_prot_sg_count(cmd))
-               scsi_free_sgtable(cmd->prot_sdb);
+       __scsi_release_buffers(cmd, 1);
 }
 EXPORT_SYMBOL(scsi_release_buffers);
 
@@ -962,7 +972,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
        }
 
        BUG_ON(blk_bidi_rq(req)); /* bidi not support for !blk_pc_request yet */
-       scsi_release_buffers(cmd);
 
        /*
         * Next deal with any sectors which we were able to correctly
@@ -1080,6 +1089,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
        switch (action) {
        case ACTION_FAIL:
                /* Give up and fail the remainder of the request */
+               scsi_release_buffers(cmd);
                if (!(req->cmd_flags & REQ_QUIET)) {
                        if (description)
                                scmd_printk(KERN_INFO, cmd, "%s\n",
@@ -1095,6 +1105,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
                /* Unprep the request and put it back at the head of the queue.
                 * A new command will be prepared and issued.
                 */
+               scsi_release_buffers(cmd);
                scsi_requeue_command(q, cmd);
                break;
        case ACTION_RETRY: