linux/drivers/scsi/device_handler/scsi_dh_alua.c

1130 lines
29 KiB
C
Raw Normal View History

/*
* Generic SCSI-3 ALUA SCSI Device Handler
*
* Copyright (C) 2007-2010 Hannes Reinecke, SUSE Linux Products GmbH.
* All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
*/
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <asm/unaligned.h>
#include <scsi/scsi.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_dh.h>
#define ALUA_DH_NAME "alua"
#define ALUA_DH_VER "2.0"
#define TPGS_SUPPORT_NONE 0x00
#define TPGS_SUPPORT_OPTIMIZED 0x01
#define TPGS_SUPPORT_NONOPTIMIZED 0x02
#define TPGS_SUPPORT_STANDBY 0x04
#define TPGS_SUPPORT_UNAVAILABLE 0x08
#define TPGS_SUPPORT_LBA_DEPENDENT 0x10
#define TPGS_SUPPORT_OFFLINE 0x40
#define TPGS_SUPPORT_TRANSITION 0x80
#define RTPG_FMT_MASK 0x70
#define RTPG_FMT_EXT_HDR 0x10
#define TPGS_MODE_UNINITIALIZED -1
#define TPGS_MODE_NONE 0x0
#define TPGS_MODE_IMPLICIT 0x1
#define TPGS_MODE_EXPLICIT 0x2
#define ALUA_RTPG_SIZE 128
#define ALUA_FAILOVER_TIMEOUT 60
#define ALUA_FAILOVER_RETRIES 5
#define ALUA_RTPG_DELAY_MSECS 5
/* device handler flags */
#define ALUA_OPTIMIZE_STPG 0x01
#define ALUA_RTPG_EXT_HDR_UNSUPP 0x02
#define ALUA_SYNC_STPG 0x04
/* State machine flags */
#define ALUA_PG_RUN_RTPG 0x10
#define ALUA_PG_RUN_STPG 0x20
#define ALUA_PG_RUNNING 0x40
static uint optimize_stpg;
module_param(optimize_stpg, uint, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than sending a STPG, when implicit TPGS is supported (0=No,1=Yes). Default is 0.");
static LIST_HEAD(port_group_list);
static DEFINE_SPINLOCK(port_group_lock);
static struct workqueue_struct *kaluad_wq;
static struct workqueue_struct *kaluad_sync_wq;
struct alua_port_group {
struct kref kref;
struct rcu_head rcu;
struct list_head node;
unsigned char device_id_str[256];
int device_id_len;
int group_id;
int tpgs;
int state;
int pref;
unsigned flags; /* used for optimizing STPG */
unsigned char transition_tmo;
unsigned long expiry;
unsigned long interval;
struct delayed_work rtpg_work;
spinlock_t lock;
struct list_head rtpg_list;
struct scsi_device *rtpg_sdev;
};
struct alua_dh_data {
struct alua_port_group *pg;
int group_id;
spinlock_t pg_lock;
struct scsi_device *sdev;
int init_error;
struct mutex init_mutex;
};
struct alua_queue_data {
struct list_head entry;
activate_complete callback_fn;
void *callback_data;
};
#define ALUA_POLICY_SWITCH_CURRENT 0
#define ALUA_POLICY_SWITCH_ALL 1
static void alua_rtpg_work(struct work_struct *work);
static void alua_rtpg_queue(struct alua_port_group *pg,
struct scsi_device *sdev,
struct alua_queue_data *qdata, bool force);
static void alua_check(struct scsi_device *sdev, bool force);
static void release_port_group(struct kref *kref)
{
struct alua_port_group *pg;
pg = container_of(kref, struct alua_port_group, kref);
if (pg->rtpg_sdev)
flush_delayed_work(&pg->rtpg_work);
spin_lock(&port_group_lock);
list_del(&pg->node);
spin_unlock(&port_group_lock);
kfree_rcu(pg, rcu);
}
/*
* submit_rtpg - Issue a REPORT TARGET GROUP STATES command
* @sdev: sdev the command should be sent to
*/
static int submit_rtpg(struct scsi_device *sdev, unsigned char *buff,
int bufflen, struct scsi_sense_hdr *sshdr, int flags)
{
u8 cdb[COMMAND_SIZE(MAINTENANCE_IN)];
int req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
REQ_FAILFAST_DRIVER;
/* Prepare the command. */
memset(cdb, 0x0, COMMAND_SIZE(MAINTENANCE_IN));
cdb[0] = MAINTENANCE_IN;
if (!(flags & ALUA_RTPG_EXT_HDR_UNSUPP))
cdb[1] = MI_REPORT_TARGET_PGS | MI_EXT_HDR_PARAM_FMT;
else
cdb[1] = MI_REPORT_TARGET_PGS;
put_unaligned_be32(bufflen, &cdb[6]);
return scsi_execute_req_flags(sdev, cdb, DMA_FROM_DEVICE,
buff, bufflen, sshdr,
ALUA_FAILOVER_TIMEOUT * HZ,
ALUA_FAILOVER_RETRIES, NULL, req_flags);
}
/*
* submit_stpg - Issue a SET TARGET PORT GROUP command
*
* Currently we're only setting the current target port group state
* to 'active/optimized' and let the array firmware figure out
* the states of the remaining groups.
*/
static int submit_stpg(struct scsi_device *sdev, int group_id,
struct scsi_sense_hdr *sshdr)
{
u8 cdb[COMMAND_SIZE(MAINTENANCE_OUT)];
unsigned char stpg_data[8];
int stpg_len = 8;
int req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
REQ_FAILFAST_DRIVER;
/* Prepare the data buffer */
memset(stpg_data, 0, stpg_len);
stpg_data[4] = SCSI_ACCESS_STATE_OPTIMAL;
put_unaligned_be16(group_id, &stpg_data[6]);
/* Prepare the command. */
memset(cdb, 0x0, COMMAND_SIZE(MAINTENANCE_OUT));
cdb[0] = MAINTENANCE_OUT;
cdb[1] = MO_SET_TARGET_PGS;
put_unaligned_be32(stpg_len, &cdb[6]);
return scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
stpg_data, stpg_len,
sshdr, ALUA_FAILOVER_TIMEOUT * HZ,
ALUA_FAILOVER_RETRIES, NULL, req_flags);
}
struct alua_port_group *alua_find_get_pg(char *id_str, size_t id_size,
int group_id)
{
struct alua_port_group *pg;
list_for_each_entry(pg, &port_group_list, node) {
if (pg->group_id != group_id)
continue;
if (pg->device_id_len != id_size)
continue;
if (strncmp(pg->device_id_str, id_str, id_size))
continue;
if (!kref_get_unless_zero(&pg->kref))
continue;
return pg;
}
return NULL;
}
/*
* alua_alloc_pg - Allocate a new port_group structure
* @sdev: scsi device
* @h: alua device_handler data
* @group_id: port group id
*
* Allocate a new port_group structure for a given
* device.
*/
struct alua_port_group *alua_alloc_pg(struct scsi_device *sdev,
int group_id, int tpgs)
{
struct alua_port_group *pg, *tmp_pg;
pg = kzalloc(sizeof(struct alua_port_group), GFP_KERNEL);
if (!pg)
return ERR_PTR(-ENOMEM);
pg->device_id_len = scsi_vpd_lun_id(sdev, pg->device_id_str,
sizeof(pg->device_id_str));
if (pg->device_id_len <= 0) {
/*
* Internal error: TPGS supported but no device
* identifcation found. Disable ALUA support.
*/
kfree(pg);
sdev_printk(KERN_INFO, sdev,
"%s: No device descriptors found\n",
ALUA_DH_NAME);
return ERR_PTR(-ENXIO);
}
pg->group_id = group_id;
pg->tpgs = tpgs;
pg->state = SCSI_ACCESS_STATE_OPTIMAL;
if (optimize_stpg)
pg->flags |= ALUA_OPTIMIZE_STPG;
kref_init(&pg->kref);
INIT_DELAYED_WORK(&pg->rtpg_work, alua_rtpg_work);
INIT_LIST_HEAD(&pg->rtpg_list);
INIT_LIST_HEAD(&pg->node);
spin_lock_init(&pg->lock);
spin_lock(&port_group_lock);
tmp_pg = alua_find_get_pg(pg->device_id_str, pg->device_id_len,
group_id);
if (tmp_pg) {
spin_unlock(&port_group_lock);
kfree(pg);
return tmp_pg;
}
list_add(&pg->node, &port_group_list);
spin_unlock(&port_group_lock);
return pg;
}
/*
* alua_check_tpgs - Evaluate TPGS setting
* @sdev: device to be checked
*
* Examine the TPGS setting of the sdev to find out if ALUA
* is supported.
*/
static int alua_check_tpgs(struct scsi_device *sdev)
{
int tpgs = TPGS_MODE_NONE;
/*
* ALUA support for non-disk devices is fraught with
* difficulties, so disable it for now.
*/
if (sdev->type != TYPE_DISK) {
sdev_printk(KERN_INFO, sdev,
"%s: disable for non-disk devices\n",
ALUA_DH_NAME);
return tpgs;
}
tpgs = scsi_device_tpgs(sdev);
switch (tpgs) {
case TPGS_MODE_EXPLICIT|TPGS_MODE_IMPLICIT:
sdev_printk(KERN_INFO, sdev,
"%s: supports implicit and explicit TPGS\n",
ALUA_DH_NAME);
break;
case TPGS_MODE_EXPLICIT:
sdev_printk(KERN_INFO, sdev, "%s: supports explicit TPGS\n",
ALUA_DH_NAME);
break;
case TPGS_MODE_IMPLICIT:
sdev_printk(KERN_INFO, sdev, "%s: supports implicit TPGS\n",
ALUA_DH_NAME);
break;
case TPGS_MODE_NONE:
sdev_printk(KERN_INFO, sdev, "%s: not supported\n",
ALUA_DH_NAME);
break;
default:
sdev_printk(KERN_INFO, sdev,
"%s: unsupported TPGS setting %d\n",
ALUA_DH_NAME, tpgs);
tpgs = TPGS_MODE_NONE;
break;
}
return tpgs;
}
/*
* alua_check_vpd - Evaluate INQUIRY vpd page 0x83
* @sdev: device to be checked
*
* Extract the relative target port and the target port group
* descriptor from the list of identificators.
*/
static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h,
int tpgs)
{
int rel_port = -1, group_id;
struct alua_port_group *pg, *old_pg = NULL;
group_id = scsi_vpd_tpg_id(sdev, &rel_port);
if (group_id < 0) {
/*
* Internal error; TPGS supported but required
* VPD identification descriptors not present.
* Disable ALUA support
*/
sdev_printk(KERN_INFO, sdev,
"%s: No target port descriptors found\n",
ALUA_DH_NAME);
return SCSI_DH_DEV_UNSUPP;
}
pg = alua_alloc_pg(sdev, group_id, tpgs);
if (IS_ERR(pg)) {
if (PTR_ERR(pg) == -ENOMEM)
return SCSI_DH_NOMEM;
return SCSI_DH_DEV_UNSUPP;
}
sdev_printk(KERN_INFO, sdev,
"%s: device %s port group %x rel port %x\n",
ALUA_DH_NAME, pg->device_id_str, group_id, rel_port);
/* Check for existing port group references */
spin_lock(&h->pg_lock);
old_pg = h->pg;
if (old_pg != pg) {
/* port group has changed. Update to new port group */
rcu_assign_pointer(h->pg, pg);
}
if (sdev->synchronous_alua)
pg->flags |= ALUA_SYNC_STPG;
alua_rtpg_queue(h->pg, sdev, NULL, true);
spin_unlock(&h->pg_lock);
if (old_pg)
kref_put(&old_pg->kref, release_port_group);
return SCSI_DH_OK;
}
static char print_alua_state(unsigned char state)
{
switch (state) {
case SCSI_ACCESS_STATE_OPTIMAL:
return 'A';
case SCSI_ACCESS_STATE_ACTIVE:
return 'N';
case SCSI_ACCESS_STATE_STANDBY:
return 'S';
case SCSI_ACCESS_STATE_UNAVAILABLE:
return 'U';
case SCSI_ACCESS_STATE_LBA:
return 'L';
case SCSI_ACCESS_STATE_OFFLINE:
return 'O';
case SCSI_ACCESS_STATE_TRANSITIONING:
return 'T';
default:
return 'X';
}
}
static int alua_check_sense(struct scsi_device *sdev,
struct scsi_sense_hdr *sense_hdr)
{
switch (sense_hdr->sense_key) {
case NOT_READY:
if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) {
/*
* LUN Not Accessible - ALUA state transition
*/
alua_check(sdev, false);
return NEEDS_RETRY;
}
break;
case UNIT_ATTENTION:
if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) {
/*
* Power On, Reset, or Bus Device Reset.
* Might have obscured a state transition,
* so schedule a recheck.
*/
alua_check(sdev, true);
return ADD_TO_MLQUEUE;
}
if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x04)
/*
* Device internal reset
*/
return ADD_TO_MLQUEUE;
if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x01)
/*
* Mode Parameters Changed
*/
return ADD_TO_MLQUEUE;
if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x06) {
/*
* ALUA state changed
*/
alua_check(sdev, true);
return ADD_TO_MLQUEUE;
}
if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x07) {
/*
* Implicit ALUA state transition failed
*/
alua_check(sdev, true);
return ADD_TO_MLQUEUE;
}
if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x03)
/*
* Inquiry data has changed
*/
return ADD_TO_MLQUEUE;
if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x0e)
/*
* REPORTED_LUNS_DATA_HAS_CHANGED is reported
* when switching controllers on targets like
* Intel Multi-Flex. We can just retry.
*/
return ADD_TO_MLQUEUE;
break;
}
return SCSI_RETURN_NOT_HANDLED;
}
/*
* alua_tur - Send a TEST UNIT READY
* @sdev: device to which the TEST UNIT READY command should be send
*
* Send a TEST UNIT READY to @sdev to figure out the device state
* Returns SCSI_DH_RETRY if the sense code is NOT READY/ALUA TRANSITIONING,
* SCSI_DH_OK if no error occurred, and SCSI_DH_IO otherwise.
*/
static int alua_tur(struct scsi_device *sdev)
{
struct scsi_sense_hdr sense_hdr;
int retval;
retval = scsi_test_unit_ready(sdev, ALUA_FAILOVER_TIMEOUT * HZ,
ALUA_FAILOVER_RETRIES, &sense_hdr);
if (sense_hdr.sense_key == NOT_READY &&
sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a)
return SCSI_DH_RETRY;
else if (retval)
return SCSI_DH_IO;
else
return SCSI_DH_OK;
}
/*
* alua_rtpg - Evaluate REPORT TARGET GROUP STATES
* @sdev: the device to be evaluated.
*
* Evaluate the Target Port Group State.
* Returns SCSI_DH_DEV_OFFLINED if the path is
* found to be unusable.
*/
static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
{
struct scsi_sense_hdr sense_hdr;
struct alua_port_group *tmp_pg;
int len, k, off, valid_states = 0, bufflen = ALUA_RTPG_SIZE;
unsigned char *desc, *buff;
unsigned err, retval;
unsigned int tpg_desc_tbl_off;
unsigned char orig_transition_tmo;
unsigned long flags;
if (!pg->expiry) {
unsigned long transition_tmo = ALUA_FAILOVER_TIMEOUT * HZ;
if (pg->transition_tmo)
transition_tmo = pg->transition_tmo * HZ;
pg->expiry = round_jiffies_up(jiffies + transition_tmo);
}
buff = kzalloc(bufflen, GFP_KERNEL);
if (!buff)
return SCSI_DH_DEV_TEMP_BUSY;
retry:
retval = submit_rtpg(sdev, buff, bufflen, &sense_hdr, pg->flags);
if (retval) {
if (!scsi_sense_valid(&sense_hdr)) {
sdev_printk(KERN_INFO, sdev,
"%s: rtpg failed, result %d\n",
ALUA_DH_NAME, retval);
kfree(buff);
if (driver_byte(retval) == DRIVER_ERROR)
return SCSI_DH_DEV_TEMP_BUSY;
return SCSI_DH_IO;
}
/*
* submit_rtpg() has failed on existing arrays
* when requesting extended header info, and
* the array doesn't support extended headers,
* even though it shouldn't according to T10.
* The retry without rtpg_ext_hdr_req set
* handles this.
*/
if (!(pg->flags & ALUA_RTPG_EXT_HDR_UNSUPP) &&
sense_hdr.sense_key == ILLEGAL_REQUEST &&
sense_hdr.asc == 0x24 && sense_hdr.ascq == 0) {
pg->flags |= ALUA_RTPG_EXT_HDR_UNSUPP;
goto retry;
}
/*
* Retry on ALUA state transition or if any
* UNIT ATTENTION occurred.
*/
if (sense_hdr.sense_key == NOT_READY &&
sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a)
err = SCSI_DH_RETRY;
else if (sense_hdr.sense_key == UNIT_ATTENTION)
err = SCSI_DH_RETRY;
if (err == SCSI_DH_RETRY &&
pg->expiry != 0 && time_before(jiffies, pg->expiry)) {
sdev_printk(KERN_ERR, sdev, "%s: rtpg retry\n",
ALUA_DH_NAME);
scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr);
return err;
}
sdev_printk(KERN_ERR, sdev, "%s: rtpg failed\n",
ALUA_DH_NAME);
scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr);
kfree(buff);
pg->expiry = 0;
return SCSI_DH_IO;
}
len = get_unaligned_be32(&buff[0]) + 4;
if (len > bufflen) {
/* Resubmit with the correct length */
kfree(buff);
bufflen = len;
buff = kmalloc(bufflen, GFP_KERNEL);
if (!buff) {
sdev_printk(KERN_WARNING, sdev,
"%s: kmalloc buffer failed\n",__func__);
/* Temporary failure, bypass */
pg->expiry = 0;
return SCSI_DH_DEV_TEMP_BUSY;
}
goto retry;
}
orig_transition_tmo = pg->transition_tmo;
if ((buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR && buff[5] != 0)
pg->transition_tmo = buff[5];
else
pg->transition_tmo = ALUA_FAILOVER_TIMEOUT;
if (orig_transition_tmo != pg->transition_tmo) {
sdev_printk(KERN_INFO, sdev,
"%s: transition timeout set to %d seconds\n",
ALUA_DH_NAME, pg->transition_tmo);
pg->expiry = jiffies + pg->transition_tmo * HZ;
}
if ((buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR)
tpg_desc_tbl_off = 8;
else
tpg_desc_tbl_off = 4;
for (k = tpg_desc_tbl_off, desc = buff + tpg_desc_tbl_off;
k < len;
k += off, desc += off) {
u16 group_id = get_unaligned_be16(&desc[2]);
spin_lock_irqsave(&port_group_lock, flags);
tmp_pg = alua_find_get_pg(pg->device_id_str, pg->device_id_len,
group_id);
spin_unlock_irqrestore(&port_group_lock, flags);
if (tmp_pg) {
if (spin_trylock_irqsave(&tmp_pg->lock, flags)) {
if ((tmp_pg == pg) ||
!(tmp_pg->flags & ALUA_PG_RUNNING)) {
tmp_pg->state = desc[0] & 0x0f;
tmp_pg->pref = desc[0] >> 7;
}
if (tmp_pg == pg)
valid_states = desc[1];
spin_unlock_irqrestore(&tmp_pg->lock, flags);
}
kref_put(&tmp_pg->kref, release_port_group);
}
off = 8 + (desc[7] * 4);
}
spin_lock_irqsave(&pg->lock, flags);
sdev_printk(KERN_INFO, sdev,
"%s: port group %02x state %c %s supports %c%c%c%c%c%c%c\n",
ALUA_DH_NAME, pg->group_id, print_alua_state(pg->state),
pg->pref ? "preferred" : "non-preferred",
valid_states&TPGS_SUPPORT_TRANSITION?'T':'t',
valid_states&TPGS_SUPPORT_OFFLINE?'O':'o',
valid_states&TPGS_SUPPORT_LBA_DEPENDENT?'L':'l',
valid_states&TPGS_SUPPORT_UNAVAILABLE?'U':'u',
valid_states&TPGS_SUPPORT_STANDBY?'S':'s',
valid_states&TPGS_SUPPORT_NONOPTIMIZED?'N':'n',
valid_states&TPGS_SUPPORT_OPTIMIZED?'A':'a');
switch (pg->state) {
case SCSI_ACCESS_STATE_TRANSITIONING:
if (time_before(jiffies, pg->expiry)) {
/* State transition, retry */
pg->interval = 2;
err = SCSI_DH_RETRY;
} else {
/* Transitioning time exceeded, set port to standby */
err = SCSI_DH_IO;
pg->state = SCSI_ACCESS_STATE_STANDBY;
pg->expiry = 0;
}
break;
case SCSI_ACCESS_STATE_OFFLINE:
/* Path unusable */
err = SCSI_DH_DEV_OFFLINED;
pg->expiry = 0;
break;
default:
/* Useable path if active */
err = SCSI_DH_OK;
pg->expiry = 0;
break;
}
spin_unlock_irqrestore(&pg->lock, flags);
kfree(buff);
return err;
}
/*
* alua_stpg - Issue a SET TARGET PORT GROUP command
*
* Issue a SET TARGET PORT GROUP command and evaluate the
* response. Returns SCSI_DH_RETRY per default to trigger
* a re-evaluation of the target group state or SCSI_DH_OK
* if no further action needs to be taken.
*/
static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg)
{
int retval;
struct scsi_sense_hdr sense_hdr;
if (!(pg->tpgs & TPGS_MODE_EXPLICIT)) {
/* Only implicit ALUA supported, retry */
return SCSI_DH_RETRY;
}
switch (pg->state) {
case SCSI_ACCESS_STATE_OPTIMAL:
return SCSI_DH_OK;
case SCSI_ACCESS_STATE_ACTIVE:
if ((pg->flags & ALUA_OPTIMIZE_STPG) &&
!pg->pref &&
(pg->tpgs & TPGS_MODE_IMPLICIT))
return SCSI_DH_OK;
break;
case SCSI_ACCESS_STATE_STANDBY:
case SCSI_ACCESS_STATE_UNAVAILABLE:
break;
case SCSI_ACCESS_STATE_OFFLINE:
return SCSI_DH_IO;
case SCSI_ACCESS_STATE_TRANSITIONING:
break;
default:
sdev_printk(KERN_INFO, sdev,
"%s: stpg failed, unhandled TPGS state %d",
ALUA_DH_NAME, pg->state);
return SCSI_DH_NOSYS;
}
retval = submit_stpg(sdev, pg->group_id, &sense_hdr);
if (retval) {
if (!scsi_sense_valid(&sense_hdr)) {
sdev_printk(KERN_INFO, sdev,
"%s: stpg failed, result %d",
ALUA_DH_NAME, retval);
if (driver_byte(retval) == DRIVER_ERROR)
return SCSI_DH_DEV_TEMP_BUSY;
} else {
sdev_printk(KERN_INFO, sdev, "%s: stpg failed\n",
ALUA_DH_NAME);
scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr);
}
}
/* Retry RTPG */
return SCSI_DH_RETRY;
}
static void alua_rtpg_work(struct work_struct *work)
{
struct alua_port_group *pg =
container_of(work, struct alua_port_group, rtpg_work.work);
struct scsi_device *sdev;
LIST_HEAD(qdata_list);
int err = SCSI_DH_OK;
struct alua_queue_data *qdata, *tmp;
unsigned long flags;
struct workqueue_struct *alua_wq = kaluad_wq;
spin_lock_irqsave(&pg->lock, flags);
sdev = pg->rtpg_sdev;
if (!sdev) {
WARN_ON(pg->flags & ALUA_PG_RUN_RTPG);
WARN_ON(pg->flags & ALUA_PG_RUN_STPG);
spin_unlock_irqrestore(&pg->lock, flags);
return;
}
if (pg->flags & ALUA_SYNC_STPG)
alua_wq = kaluad_sync_wq;
pg->flags |= ALUA_PG_RUNNING;
if (pg->flags & ALUA_PG_RUN_RTPG) {
int state = pg->state;
pg->flags &= ~ALUA_PG_RUN_RTPG;
spin_unlock_irqrestore(&pg->lock, flags);
if (state == SCSI_ACCESS_STATE_TRANSITIONING) {
if (alua_tur(sdev) == SCSI_DH_RETRY) {
spin_lock_irqsave(&pg->lock, flags);
pg->flags &= ~ALUA_PG_RUNNING;
pg->flags |= ALUA_PG_RUN_RTPG;
spin_unlock_irqrestore(&pg->lock, flags);
queue_delayed_work(alua_wq, &pg->rtpg_work,
pg->interval * HZ);
return;
}
/* Send RTPG on failure or if TUR indicates SUCCESS */
}
err = alua_rtpg(sdev, pg);
spin_lock_irqsave(&pg->lock, flags);
if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) {
pg->flags &= ~ALUA_PG_RUNNING;
pg->flags |= ALUA_PG_RUN_RTPG;
spin_unlock_irqrestore(&pg->lock, flags);
queue_delayed_work(alua_wq, &pg->rtpg_work,
pg->interval * HZ);
return;
}
if (err != SCSI_DH_OK)
pg->flags &= ~ALUA_PG_RUN_STPG;
}
if (pg->flags & ALUA_PG_RUN_STPG) {
pg->flags &= ~ALUA_PG_RUN_STPG;
spin_unlock_irqrestore(&pg->lock, flags);
err = alua_stpg(sdev, pg);
spin_lock_irqsave(&pg->lock, flags);
if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) {
pg->flags |= ALUA_PG_RUN_RTPG;
pg->interval = 0;
pg->flags &= ~ALUA_PG_RUNNING;
spin_unlock_irqrestore(&pg->lock, flags);
queue_delayed_work(alua_wq, &pg->rtpg_work,
pg->interval * HZ);
return;
}
}
list_splice_init(&pg->rtpg_list, &qdata_list);
pg->rtpg_sdev = NULL;
spin_unlock_irqrestore(&pg->lock, flags);
list_for_each_entry_safe(qdata, tmp, &qdata_list, entry) {
list_del(&qdata->entry);
if (qdata->callback_fn)
qdata->callback_fn(qdata->callback_data, err);
kfree(qdata);
}
spin_lock_irqsave(&pg->lock, flags);
pg->flags &= ~ALUA_PG_RUNNING;
spin_unlock_irqrestore(&pg->lock, flags);
scsi_device_put(sdev);
kref_put(&pg->kref, release_port_group);
}
static void alua_rtpg_queue(struct alua_port_group *pg,
struct scsi_device *sdev,
struct alua_queue_data *qdata, bool force)
{
int start_queue = 0;
unsigned long flags;
struct workqueue_struct *alua_wq = kaluad_wq;
if (!pg)
return;
spin_lock_irqsave(&pg->lock, flags);
if (qdata) {
list_add_tail(&qdata->entry, &pg->rtpg_list);
pg->flags |= ALUA_PG_RUN_STPG;
force = true;
}
if (pg->rtpg_sdev == NULL) {
pg->interval = 0;
pg->flags |= ALUA_PG_RUN_RTPG;
kref_get(&pg->kref);
pg->rtpg_sdev = sdev;
scsi_device_get(sdev);
start_queue = 1;
} else if (!(pg->flags & ALUA_PG_RUN_RTPG) && force) {
pg->flags |= ALUA_PG_RUN_RTPG;
/* Do not queue if the worker is already running */
if (!(pg->flags & ALUA_PG_RUNNING)) {
kref_get(&pg->kref);
start_queue = 1;
}
}
if (pg->flags & ALUA_SYNC_STPG)
alua_wq = kaluad_sync_wq;
spin_unlock_irqrestore(&pg->lock, flags);
if (start_queue &&
!queue_delayed_work(alua_wq, &pg->rtpg_work,
msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS))) {
scsi_device_put(sdev);
kref_put(&pg->kref, release_port_group);
}
}
/*
* alua_initialize - Initialize ALUA state
* @sdev: the device to be initialized
*
* For the prep_fn to work correctly we have
* to initialize the ALUA state for the device.
*/
static int alua_initialize(struct scsi_device *sdev, struct alua_dh_data *h)
{
int err = SCSI_DH_DEV_UNSUPP, tpgs;
mutex_lock(&h->init_mutex);
tpgs = alua_check_tpgs(sdev);
if (tpgs != TPGS_MODE_NONE)
err = alua_check_vpd(sdev, h, tpgs);
h->init_error = err;
mutex_unlock(&h->init_mutex);
return err;
}
/*
* alua_set_params - set/unset the optimize flag
* @sdev: device on the path to be activated
* params - parameters in the following format
* "no_of_params\0param1\0param2\0param3\0...\0"
* For example, to set the flag pass the following parameters
* from multipath.conf
* hardware_handler "2 alua 1"
*/
static int alua_set_params(struct scsi_device *sdev, const char *params)
{
struct alua_dh_data *h = sdev->handler_data;
struct alua_port_group __rcu *pg = NULL;
unsigned int optimize = 0, argc;
const char *p = params;
int result = SCSI_DH_OK;
unsigned long flags;
if ((sscanf(params, "%u", &argc) != 1) || (argc != 1))
return -EINVAL;
while (*p++)
;
if ((sscanf(p, "%u", &optimize) != 1) || (optimize > 1))
return -EINVAL;
rcu_read_lock();
pg = rcu_dereference(h->pg);
if (!pg) {
rcu_read_unlock();
return -ENXIO;
}
spin_lock_irqsave(&pg->lock, flags);
if (optimize)
pg->flags |= ALUA_OPTIMIZE_STPG;
else
pg->flags &= ~ALUA_OPTIMIZE_STPG;
spin_unlock_irqrestore(&pg->lock, flags);
rcu_read_unlock();
return result;
}
/*
* alua_activate - activate a path
* @sdev: device on the path to be activated
*
* We're currently switching the port group to be activated only and
* let the array figure out the rest.
* There may be other arrays which require us to switch all port groups
* based on a certain policy. But until we actually encounter them it
* should be okay.
*/
static int alua_activate(struct scsi_device *sdev,
activate_complete fn, void *data)
{
struct alua_dh_data *h = sdev->handler_data;
int err = SCSI_DH_OK;
struct alua_queue_data *qdata;
struct alua_port_group __rcu *pg;
qdata = kzalloc(sizeof(*qdata), GFP_KERNEL);
if (!qdata) {
err = SCSI_DH_RES_TEMP_UNAVAIL;
goto out;
}
qdata->callback_fn = fn;
qdata->callback_data = data;
mutex_lock(&h->init_mutex);
rcu_read_lock();
pg = rcu_dereference(h->pg);
if (!pg || !kref_get_unless_zero(&pg->kref)) {
rcu_read_unlock();
kfree(qdata);
err = h->init_error;
mutex_unlock(&h->init_mutex);
goto out;
}
fn = NULL;
rcu_read_unlock();
mutex_unlock(&h->init_mutex);
alua_rtpg_queue(pg, sdev, qdata, true);
kref_put(&pg->kref, release_port_group);
out:
if (fn)
fn(data, err);
return 0;
}
/*
* alua_check - check path status
* @sdev: device on the path to be checked
*
* Check the device status
*/
static void alua_check(struct scsi_device *sdev, bool force)
{
struct alua_dh_data *h = sdev->handler_data;
struct alua_port_group *pg;
rcu_read_lock();
pg = rcu_dereference(h->pg);
if (!pg || !kref_get_unless_zero(&pg->kref)) {
rcu_read_unlock();
return;
}
rcu_read_unlock();
alua_rtpg_queue(pg, sdev, NULL, force);
kref_put(&pg->kref, release_port_group);
}
/*
* alua_prep_fn - request callback
*
* Fail I/O to all paths not in state
* active/optimized or active/non-optimized.
*/
static int alua_prep_fn(struct scsi_device *sdev, struct request *req)
{
struct alua_dh_data *h = sdev->handler_data;
struct alua_port_group __rcu *pg;
unsigned char state = SCSI_ACCESS_STATE_OPTIMAL;
int ret = BLKPREP_OK;
rcu_read_lock();
pg = rcu_dereference(h->pg);
if (pg)
state = pg->state;
rcu_read_unlock();
if (state == SCSI_ACCESS_STATE_TRANSITIONING)
ret = BLKPREP_DEFER;
else if (state != SCSI_ACCESS_STATE_OPTIMAL &&
state != SCSI_ACCESS_STATE_ACTIVE &&
state != SCSI_ACCESS_STATE_LBA) {
ret = BLKPREP_KILL;
req->cmd_flags |= REQ_QUIET;
}
return ret;
}
static void alua_rescan(struct scsi_device *sdev)
{
struct alua_dh_data *h = sdev->handler_data;
alua_initialize(sdev, h);
}
/*
* alua_bus_attach - Attach device handler
* @sdev: device to be attached to
*/
static int alua_bus_attach(struct scsi_device *sdev)
{
struct alua_dh_data *h;
int err, ret = -EINVAL;
h = kzalloc(sizeof(*h) , GFP_KERNEL);
if (!h)
return -ENOMEM;
spin_lock_init(&h->pg_lock);
rcu_assign_pointer(h->pg, NULL);
h->init_error = SCSI_DH_OK;
h->sdev = sdev;
mutex_init(&h->init_mutex);
err = alua_initialize(sdev, h);
if (err == SCSI_DH_NOMEM)
ret = -ENOMEM;
if (err != SCSI_DH_OK && err != SCSI_DH_DEV_OFFLINED)
goto failed;
sdev->handler_data = h;
return 0;
failed:
kfree(h);
return ret;
}
/*
* alua_bus_detach - Detach device handler
* @sdev: device to be detached from
*/
static void alua_bus_detach(struct scsi_device *sdev)
{
struct alua_dh_data *h = sdev->handler_data;
struct alua_port_group *pg;
spin_lock(&h->pg_lock);
pg = h->pg;
rcu_assign_pointer(h->pg, NULL);
h->sdev = NULL;
spin_unlock(&h->pg_lock);
if (pg)
kref_put(&pg->kref, release_port_group);
sdev->handler_data = NULL;
kfree(h);
}
static struct scsi_device_handler alua_dh = {
.name = ALUA_DH_NAME,
.module = THIS_MODULE,
.attach = alua_bus_attach,
.detach = alua_bus_detach,
.prep_fn = alua_prep_fn,
.check_sense = alua_check_sense,
.activate = alua_activate,
.rescan = alua_rescan,
.set_params = alua_set_params,
};
static int __init alua_init(void)
{
int r;
kaluad_wq = alloc_workqueue("kaluad", WQ_MEM_RECLAIM, 0);
if (!kaluad_wq) {
/* Temporary failure, bypass */
return SCSI_DH_DEV_TEMP_BUSY;
}
kaluad_sync_wq = create_workqueue("kaluad_sync");
if (!kaluad_sync_wq) {
destroy_workqueue(kaluad_wq);
return SCSI_DH_DEV_TEMP_BUSY;
}
r = scsi_register_device_handler(&alua_dh);
if (r != 0) {
printk(KERN_ERR "%s: Failed to register scsi device handler",
ALUA_DH_NAME);
destroy_workqueue(kaluad_sync_wq);
destroy_workqueue(kaluad_wq);
}
return r;
}
static void __exit alua_exit(void)
{
scsi_unregister_device_handler(&alua_dh);
destroy_workqueue(kaluad_sync_wq);
destroy_workqueue(kaluad_wq);
}
module_init(alua_init);
module_exit(alua_exit);
MODULE_DESCRIPTION("DM Multipath ALUA support");
MODULE_AUTHOR("Hannes Reinecke <hare@suse.de>");
MODULE_LICENSE("GPL");
MODULE_VERSION(ALUA_DH_VER);