From: Robert Love <robert.w.love@intel.com>
To: james.bottomley@hansenpartnership.com, linux-scsi@vger.kernel.org
Subject: [PATCH 06/24] libfc: rport retry on LS_RJT from certain ELS
Date: Fri, 27 Feb 2009 10:55:02 -0800 [thread overview]
Message-ID: <20090227185502.25509.67814.stgit@fritz> (raw)
In-Reply-To: <20090227185430.25509.34309.stgit@fritz>
From: Chris Leech <christopher.leech@intel.com>
This allows any rport ELS to retry on LS_RJT.
The rport error handling would only retry on resource allocation failures
and exchange timeouts. I have a target that will occasionally reject PLOGI
when we do a quick LOGO/PLOGI. When a critical ELS was rejected, libfc would
fail silently leaving the rport in a dead state.
The retry count and delay are managed by fc_rport_error_retry. If the retry
count is exceeded fc_rport_error will be called. When retrying is not the
correct course of action, fc_rport_error can be called directly.
Signed-off-by: Chris Leech <christopher.leech@intel.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
---
drivers/scsi/libfc/fc_exch.c | 2 -
drivers/scsi/libfc/fc_rport.c | 111 ++++++++++++++++++++++++-----------------
include/scsi/fc/fc_fs.h | 5 ++
3 files changed, 69 insertions(+), 49 deletions(-)
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index dd269e5..8c40189 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -32,8 +32,6 @@
#include <scsi/libfc.h>
#include <scsi/fc_encode.h>
-#define FC_DEF_R_A_TOV (10 * 1000) /* resource allocation timeout */
-
/*
* fc_exch_debug can be set in debugger or at compile time to get more logs.
*/
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 7175759..600a8ff 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -81,6 +81,7 @@ static void fc_rport_recv_logo_req(struct fc_rport *,
struct fc_seq *, struct fc_frame *);
static void fc_rport_timeout(struct work_struct *);
static void fc_rport_error(struct fc_rport *, struct fc_frame *);
+static void fc_rport_error_retry(struct fc_rport *, struct fc_frame *);
static void fc_rport_work(struct work_struct *);
static const char *fc_rport_state_names[] = {
@@ -410,58 +411,74 @@ static void fc_rport_timeout(struct work_struct *work)
}
/**
- * fc_rport_error - Handler for any errors
+ * fc_rport_error - Error handler, called once retries have been exhausted
* @rport: The fc_rport object
* @fp: The frame pointer
*
- * If the error was caused by a resource allocation failure
- * then wait for half a second and retry, otherwise retry
- * immediately.
- *
* Locking Note: The rport lock is expected to be held before
* calling this routine
*/
static void fc_rport_error(struct fc_rport *rport, struct fc_frame *fp)
{
struct fc_rport_libfc_priv *rdata = rport->dd_data;
- unsigned long delay = 0;
FC_DEBUG_RPORT("Error %ld in state %s, retries %d\n",
PTR_ERR(fp), fc_rport_state(rport), rdata->retries);
- if (!fp || PTR_ERR(fp) == -FC_EX_TIMEOUT) {
- /*
- * Memory allocation failure, or the exchange timed out.
- * Retry after delay
- */
- if (rdata->retries < rdata->local_port->max_retry_count) {
- rdata->retries++;
- if (!fp)
- delay = msecs_to_jiffies(500);
- get_device(&rport->dev);
- schedule_delayed_work(&rdata->retry_work, delay);
- } else {
- switch (rdata->rp_state) {
- case RPORT_ST_PLOGI:
- case RPORT_ST_PRLI:
- case RPORT_ST_LOGO:
- rdata->event = RPORT_EV_FAILED;
- queue_work(rport_event_queue,
- &rdata->event_work);
- break;
- case RPORT_ST_RTV:
- fc_rport_enter_ready(rport);
- break;
- case RPORT_ST_NONE:
- case RPORT_ST_READY:
- case RPORT_ST_INIT:
- break;
- }
- }
+ switch (rdata->rp_state) {
+ case RPORT_ST_PLOGI:
+ case RPORT_ST_PRLI:
+ case RPORT_ST_LOGO:
+ rdata->event = RPORT_EV_FAILED;
+ queue_work(rport_event_queue,
+ &rdata->event_work);
+ break;
+ case RPORT_ST_RTV:
+ fc_rport_enter_ready(rport);
+ break;
+ case RPORT_ST_NONE:
+ case RPORT_ST_READY:
+ case RPORT_ST_INIT:
+ break;
}
}
/**
+ * fc_rport_error_retry - Error handler when retries are desired
+ * @rport: The fc_rport object
+ * @fp: The frame pointer
+ *
+ * If the error was an exchange timeout retry immediately,
+ * otherwise wait for E_D_TOV.
+ *
+ * Locking Note: The rport lock is expected to be held before
+ * calling this routine
+ */
+static void fc_rport_error_retry(struct fc_rport *rport, struct fc_frame *fp)
+{
+ struct fc_rport_libfc_priv *rdata = rport->dd_data;
+ unsigned long delay = FC_DEF_E_D_TOV;
+
+ /* make sure this isn't an FC_EX_CLOSED error, never retry those */
+ if (PTR_ERR(fp) == -FC_EX_CLOSED)
+ return fc_rport_error(rport, fp);
+
+ if (rdata->retries < rdata->local_port->max_retry_count) {
+ FC_DEBUG_RPORT("Error %ld in state %s, retrying\n",
+ PTR_ERR(fp), fc_rport_state(rport));
+ rdata->retries++;
+ /* no additional delay on exchange timeouts */
+ if (PTR_ERR(fp) == -FC_EX_TIMEOUT)
+ delay = 0;
+ get_device(&rport->dev);
+ schedule_delayed_work(&rdata->retry_work, delay);
+ return;
+ }
+
+ return fc_rport_error(rport, fp);
+}
+
+/**
* fc_rport_plogi_recv_resp - Handle incoming ELS PLOGI response
* @sp: current sequence in the PLOGI exchange
* @fp: response frame
@@ -495,7 +512,7 @@ static void fc_rport_plogi_resp(struct fc_seq *sp, struct fc_frame *fp,
}
if (IS_ERR(fp)) {
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
goto err;
}
@@ -527,7 +544,7 @@ static void fc_rport_plogi_resp(struct fc_seq *sp, struct fc_frame *fp,
else
fc_rport_enter_prli(rport);
} else
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
out:
fc_frame_free(fp);
@@ -557,14 +574,14 @@ static void fc_rport_enter_plogi(struct fc_rport *rport)
rport->maxframe_size = FC_MIN_MAX_PAYLOAD;
fp = fc_frame_alloc(lport, sizeof(struct fc_els_flogi));
if (!fp) {
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
return;
}
rdata->e_d_tov = lport->e_d_tov;
if (!lport->tt.elsct_send(lport, rport, fp, ELS_PLOGI,
fc_rport_plogi_resp, rport, lport->e_d_tov))
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
else
get_device(&rport->dev);
}
@@ -604,7 +621,7 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
}
if (IS_ERR(fp)) {
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
goto err;
}
@@ -662,7 +679,7 @@ static void fc_rport_logo_resp(struct fc_seq *sp, struct fc_frame *fp,
rport->port_id);
if (IS_ERR(fp)) {
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
goto err;
}
@@ -712,13 +729,13 @@ static void fc_rport_enter_prli(struct fc_rport *rport)
fp = fc_frame_alloc(lport, sizeof(*pp));
if (!fp) {
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
return;
}
if (!lport->tt.elsct_send(lport, rport, fp, ELS_PRLI,
fc_rport_prli_resp, rport, lport->e_d_tov))
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
else
get_device(&rport->dev);
}
@@ -809,13 +826,13 @@ static void fc_rport_enter_rtv(struct fc_rport *rport)
fp = fc_frame_alloc(lport, sizeof(struct fc_els_rtv));
if (!fp) {
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
return;
}
if (!lport->tt.elsct_send(lport, rport, fp, ELS_RTV,
fc_rport_rtv_resp, rport, lport->e_d_tov))
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
else
get_device(&rport->dev);
}
@@ -840,13 +857,13 @@ static void fc_rport_enter_logo(struct fc_rport *rport)
fp = fc_frame_alloc(lport, sizeof(struct fc_els_logo));
if (!fp) {
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
return;
}
if (!lport->tt.elsct_send(lport, rport, fp, ELS_LOGO,
fc_rport_logo_resp, rport, lport->e_d_tov))
- fc_rport_error(rport, fp);
+ fc_rport_error_retry(rport, fp);
else
get_device(&rport->dev);
}
diff --git a/include/scsi/fc/fc_fs.h b/include/scsi/fc/fc_fs.h
index 3e4801d..1b7af3a 100644
--- a/include/scsi/fc/fc_fs.h
+++ b/include/scsi/fc/fc_fs.h
@@ -337,4 +337,9 @@ enum fc_pf_rjt_reason {
FC_RJT_VENDOR = 0xff, /* vendor specific reject */
};
+/* default timeout values */
+
+#define FC_DEF_E_D_TOV 2000UL
+#define FC_DEF_R_A_TOV 10000UL
+
#endif /* _FC_FS_H_ */
next prev parent reply other threads:[~2009-02-27 18:55 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-02-27 18:54 [PATCH 00/24] libfc and fcoe fixes for 2.6.29-rc Robert Love
2009-02-27 18:54 ` [PATCH 01/24] libfc: Pass lport in exch_mgr_reset Robert Love
2009-02-27 18:54 ` [PATCH 02/24] libfc: when rport goes away (re-plogi), clean up exchanges to/from rport Robert Love
2009-02-27 18:54 ` [PATCH 03/24] libfc: handle RRQ exch timeout Robert Love
2009-02-27 18:54 ` [PATCH 04/24] libfc: fixed a soft lockup issue in fc_exch_recv_abts Robert Love
2009-02-27 18:54 ` [PATCH 05/24] libfc, fcoe: fixed locking issues with lport->lp_mutex around lport->link_status Robert Love
2009-02-27 18:55 ` Robert Love [this message]
2009-02-27 18:55 ` [PATCH 07/24] libfc: fixed a read IO data integrity issue when a IO data frame lost Robert Love
2009-02-27 18:55 ` [PATCH 08/24] libfc: exch mgr is freed while lport still retrying sequences Robert Love
2009-02-27 18:55 ` [PATCH 09/24] libfc: Don't violate transport template for rogue port creation Robert Love
2009-02-27 18:55 ` [PATCH 10/24] libfc: correct RPORT_TO_PRIV usage Robert Love
2009-02-27 18:55 ` [PATCH 11/24] libfc: rename rp to rdata in fc_disc_new_target() Robert Love
2009-02-27 18:55 ` [PATCH 12/24] libfc: check for err when recv and state is incorrect Robert Love
2009-02-27 18:55 ` [PATCH 13/24] libfc: Cleanup libfc_function_template comments Robert Love
2009-02-27 18:55 ` [PATCH 14/24] libfc, fcoe: Fix kerneldoc comments Robert Love
2009-02-27 18:55 ` [PATCH 15/24] libfc, fcoe: Cleanup function formatting and minor typos Robert Love
2009-02-27 18:55 ` [PATCH 16/24] libfc, fcoe: Remove unnecessary cast by removing inline wrapper Robert Love
2009-02-27 18:56 ` [PATCH 17/24] fcoe: Use setup_timer() and mod_timer() Robert Love
2009-02-27 18:56 ` [PATCH 18/24] fcoe: Correct fcoe_transports initialization vs. registration Robert Love
2009-02-27 18:56 ` [PATCH 19/24] libfc: do not change the fh_rx_id of a recevied frame Robert Love
2009-02-27 18:56 ` [PATCH 20/24] fcoe: ETH_P_8021Q is already in if_ether and fcoe is not using it anyway Robert Love
2009-02-27 18:56 ` [PATCH 21/24] fcoe: fix kfree(skb) Robert Love
2009-02-27 18:56 ` [PATCH 22/24] fcoe: Out of order tx frames was causing several check condition SCSI status Robert Love
2009-02-27 18:56 ` [PATCH 23/24] fcoe: fix handling of pending queue, prevent out of order frames (v3) Robert Love
2009-02-27 18:56 ` [PATCH 24/24] fcoe: Change fcoe receive thread nice value from 19 (lowest priority) to -20 Robert Love
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20090227185502.25509.67814.stgit@fritz \
--to=robert.w.love@intel.com \
--cc=james.bottomley@hansenpartnership.com \
--cc=linux-scsi@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.