aboutsummaryrefslogtreecommitdiff
path: root/drivers/scsi/scsi_lib.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/scsi/scsi_lib.c')
-rw-r--r--drivers/scsi/scsi_lib.c1450
1 files changed, 786 insertions, 664 deletions
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index f40898dc2d1..3f50dfcb322 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -12,6 +12,7 @@
#include <linux/blkdev.h>
#include <linux/completion.h>
#include <linux/kernel.h>
+#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/init.h>
@@ -65,55 +66,32 @@ static struct scsi_host_sg_pool scsi_sg_pools[] = {
};
#undef SP
-static struct kmem_cache *scsi_bidi_sdb_cache;
-
-static void scsi_run_queue(struct request_queue *q);
+struct kmem_cache *scsi_sdb_cache;
/*
- * Function: scsi_unprep_request()
- *
- * Purpose: Remove all preparation done for a request, including its
- * associated scsi_cmnd, so that it can be requeued.
- *
- * Arguments: req - request to unprepare
- *
- * Lock status: Assumed that no locks are held upon entry.
- *
- * Returns: Nothing.
+ * When to reinvoke queueing after a resource shortage. It's 3 msecs to
+ * not change behaviour from the previous unplug mechanism, experimentation
+ * may prove this needs changing.
*/
-static void scsi_unprep_request(struct request *req)
-{
- struct scsi_cmnd *cmd = req->special;
-
- req->cmd_flags &= ~REQ_DONTPREP;
- req->special = NULL;
-
- scsi_put_command(cmd);
-}
+#define SCSI_QUEUE_DELAY 3
-/*
- * Function: scsi_queue_insert()
- *
- * Purpose: Insert a command in the midlevel queue.
- *
- * Arguments: cmd - command that we are adding to queue.
- * reason - why we are inserting command to queue.
- *
- * Lock status: Assumed that lock is not held upon entry.
- *
- * Returns: Nothing.
- *
- * Notes: We do this for one of two cases. Either the host is busy
- * and it cannot accept any more commands for the time being,
- * or the device returned QUEUE_FULL and can accept no more
- * commands.
- * Notes: This could be called either from an interrupt context or a
- * normal process context.
+/**
+ * __scsi_queue_insert - private queue insertion
+ * @cmd: The SCSI command being requeued
+ * @reason: The reason for the requeue
+ * @unbusy: Whether the queue should be unbusied
+ *
+ * This is a private queue insertion. The public interface
+ * scsi_queue_insert() always assumes the queue should be unbusied
+ * because it's always called before the completion. This function is
+ * for a requeue after completion, which should only occur in this
+ * file.
*/
-int scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
+static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy)
{
struct Scsi_Host *host = cmd->device->host;
struct scsi_device *device = cmd->device;
+ struct scsi_target *starget = scsi_target(device);
struct request_queue *q = device->request_queue;
unsigned long flags;
@@ -133,37 +111,62 @@ int scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
* if a command is requeued with no other commands outstanding
* either for the device or for the host.
*/
- if (reason == SCSI_MLQUEUE_HOST_BUSY)
+ switch (reason) {
+ case SCSI_MLQUEUE_HOST_BUSY:
host->host_blocked = host->max_host_blocked;
- else if (reason == SCSI_MLQUEUE_DEVICE_BUSY)
+ break;
+ case SCSI_MLQUEUE_DEVICE_BUSY:
+ case SCSI_MLQUEUE_EH_RETRY:
device->device_blocked = device->max_device_blocked;
+ break;
+ case SCSI_MLQUEUE_TARGET_BUSY:
+ starget->target_blocked = starget->max_target_blocked;
+ break;
+ }
/*
* Decrement the counters, since these commands are no longer
* active on the host/device.
*/
- scsi_device_unbusy(device);
+ if (unbusy)
+ scsi_device_unbusy(device);
/*
* Requeue this command. It will go before all other commands
- * that are already in the queue.
- *
- * NOTE: there is magic here about the way the queue is plugged if
- * we have no outstanding commands.
- *
- * Although we *don't* plug the queue, we call the request
- * function. The SCSI request function detects the blocked condition
- * and plugs the queue appropriately.
- */
+ * that are already in the queue. Schedule requeue work under
+ * lock such that the kblockd_schedule_work() call happens
+ * before blk_cleanup_queue() finishes.
+ */
+ cmd->result = 0;
spin_lock_irqsave(q->queue_lock, flags);
blk_requeue_request(q, cmd->request);
+ kblockd_schedule_work(&device->requeue_work);
spin_unlock_irqrestore(q->queue_lock, flags);
-
- scsi_run_queue(q);
-
- return 0;
}
+/*
+ * Function: scsi_queue_insert()
+ *
+ * Purpose: Insert a command in the midlevel queue.
+ *
+ * Arguments: cmd - command that we are adding to queue.
+ * reason - why we are inserting command to queue.
+ *
+ * Lock status: Assumed that lock is not held upon entry.
+ *
+ * Returns: Nothing.
+ *
+ * Notes: We do this for one of two cases. Either the host is busy
+ * and it cannot accept any more commands for the time being,
+ * or the device returned QUEUE_FULL and can accept no more
+ * commands.
+ * Notes: This could be called either from an interrupt context or a
+ * normal process context.
+ */
+void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
+{
+ __scsi_queue_insert(cmd, reason, 1);
+}
/**
* scsi_execute - insert request and wait for the result
* @sdev: scsi device
@@ -175,19 +178,24 @@ int scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
* @timeout: request timeout in seconds
* @retries: number of times to retry request
* @flags: or into request flags;
+ * @resid: optional residual length
*
* returns the req->errors value which is the scsi_cmnd result
* field.
*/
int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
int data_direction, void *buffer, unsigned bufflen,
- unsigned char *sense, int timeout, int retries, int flags)
+ unsigned char *sense, int timeout, int retries, u64 flags,
+ int *resid)
{
struct request *req;
int write = (data_direction == DMA_TO_DEVICE);
int ret = DRIVER_ERROR << 24;
req = blk_get_request(sdev->request_queue, write, __GFP_WAIT);
+ if (!req)
+ return ret;
+ blk_rq_set_block_pc(req);
if (bufflen && blk_rq_map_kern(sdev->request_queue, req,
buffer, bufflen, __GFP_WAIT))
@@ -199,7 +207,6 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
req->sense_len = 0;
req->retries = retries;
req->timeout = timeout;
- req->cmd_type = REQ_TYPE_BLOCK_PC;
req->cmd_flags |= flags | REQ_QUIET | REQ_PREEMPT;
/*
@@ -207,6 +214,17 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
*/
blk_execute_rq(req->q, NULL, req, 1);
+ /*
+ * Some devices (USB mass-storage in particular) may transfer
+ * garbage data together with a residue indicating that the data
+ * is invalid. Prevent the garbage from being misinterpreted
+ * and prevent security leaks by zeroing out the excess data.
+ */
+ if (unlikely(req->resid_len > 0 && req->resid_len <= bufflen))
+ memset(buffer + (bufflen - req->resid_len), 0, req->resid_len);
+
+ if (resid)
+ *resid = req->resid_len;
ret = req->errors;
out:
blk_put_request(req);
@@ -215,10 +233,10 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
}
EXPORT_SYMBOL(scsi_execute);
-
-int scsi_execute_req(struct scsi_device *sdev, const unsigned char *cmd,
+int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd,
int data_direction, void *buffer, unsigned bufflen,
- struct scsi_sense_hdr *sshdr, int timeout, int retries)
+ struct scsi_sense_hdr *sshdr, int timeout, int retries,
+ int *resid, u64 flags)
{
char *sense = NULL;
int result;
@@ -229,204 +247,14 @@ int scsi_execute_req(struct scsi_device *sdev, const unsigned char *cmd,
return DRIVER_ERROR << 24;
}
result = scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
- sense, timeout, retries, 0);
+ sense, timeout, retries, flags, resid);
if (sshdr)
scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, sshdr);
kfree(sense);
return result;
}
-EXPORT_SYMBOL(scsi_execute_req);
-
-struct scsi_io_context {
- void *data;
- void (*done)(void *data, char *sense, int result, int resid);
- char sense[SCSI_SENSE_BUFFERSIZE];
-};
-
-static struct kmem_cache *scsi_io_context_cache;
-
-static void scsi_end_async(struct request *req, int uptodate)
-{
- struct scsi_io_context *sioc = req->end_io_data;
-
- if (sioc->done)
- sioc->done(sioc->data, sioc->sense, req->errors, req->data_len);
-
- kmem_cache_free(scsi_io_context_cache, sioc);
- __blk_put_request(req->q, req);
-}
-
-static int scsi_merge_bio(struct request *rq, struct bio *bio)
-{
- struct request_queue *q = rq->q;
-
- bio->bi_flags &= ~(1 << BIO_SEG_VALID);
- if (rq_data_dir(rq) == WRITE)
- bio->bi_rw |= (1 << BIO_RW);
- blk_queue_bounce(q, &bio);
-
- return blk_rq_append_bio(q, rq, bio);
-}
-
-static void scsi_bi_endio(struct bio *bio, int error)
-{
- bio_put(bio);
-}
-
-/**
- * scsi_req_map_sg - map a scatterlist into a request
- * @rq: request to fill
- * @sgl: scatterlist
- * @nsegs: number of elements
- * @bufflen: len of buffer
- * @gfp: memory allocation flags
- *
- * scsi_req_map_sg maps a scatterlist into a request so that the
- * request can be sent to the block layer. We do not trust the scatterlist
- * sent to use, as some ULDs use that struct to only organize the pages.
- */
-static int scsi_req_map_sg(struct request *rq, struct scatterlist *sgl,
- int nsegs, unsigned bufflen, gfp_t gfp)
-{
- struct request_queue *q = rq->q;
- int nr_pages = (bufflen + sgl[0].offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned int data_len = bufflen, len, bytes, off;
- struct scatterlist *sg;
- struct page *page;
- struct bio *bio = NULL;
- int i, err, nr_vecs = 0;
-
- for_each_sg(sgl, sg, nsegs, i) {
- page = sg_page(sg);
- off = sg->offset;
- len = sg->length;
-
- while (len > 0 && data_len > 0) {
- /*
- * sg sends a scatterlist that is larger than
- * the data_len it wants transferred for certain
- * IO sizes
- */
- bytes = min_t(unsigned int, len, PAGE_SIZE - off);
- bytes = min(bytes, data_len);
-
- if (!bio) {
- nr_vecs = min_t(int, BIO_MAX_PAGES, nr_pages);
- nr_pages -= nr_vecs;
-
- bio = bio_alloc(gfp, nr_vecs);
- if (!bio) {
- err = -ENOMEM;
- goto free_bios;
- }
- bio->bi_end_io = scsi_bi_endio;
- }
-
- if (bio_add_pc_page(q, bio, page, bytes, off) !=
- bytes) {
- bio_put(bio);
- err = -EINVAL;
- goto free_bios;
- }
-
- if (bio->bi_vcnt >= nr_vecs) {
- err = scsi_merge_bio(rq, bio);
- if (err) {
- bio_endio(bio, 0);
- goto free_bios;
- }
- bio = NULL;
- }
-
- page++;
- len -= bytes;
- data_len -=bytes;
- off = 0;
- }
- }
-
- rq->buffer = rq->data = NULL;
- rq->data_len = bufflen;
- return 0;
-
-free_bios:
- while ((bio = rq->bio) != NULL) {
- rq->bio = bio->bi_next;
- /*
- * call endio instead of bio_put incase it was bounced
- */
- bio_endio(bio, 0);
- }
-
- return err;
-}
-
-/**
- * scsi_execute_async - insert request
- * @sdev: scsi device
- * @cmd: scsi command
- * @cmd_len: length of scsi cdb
- * @data_direction: DMA_TO_DEVICE, DMA_FROM_DEVICE, or DMA_NONE
- * @buffer: data buffer (this can be a kernel buffer or scatterlist)
- * @bufflen: len of buffer
- * @use_sg: if buffer is a scatterlist this is the number of elements
- * @timeout: request timeout in seconds
- * @retries: number of times to retry request
- * @privdata: data passed to done()
- * @done: callback function when done
- * @gfp: memory allocation flags
- */
-int scsi_execute_async(struct scsi_device *sdev, const unsigned char *cmd,
- int cmd_len, int data_direction, void *buffer, unsigned bufflen,
- int use_sg, int timeout, int retries, void *privdata,
- void (*done)(void *, char *, int, int), gfp_t gfp)
-{
- struct request *req;
- struct scsi_io_context *sioc;
- int err = 0;
- int write = (data_direction == DMA_TO_DEVICE);
-
- sioc = kmem_cache_zalloc(scsi_io_context_cache, gfp);
- if (!sioc)
- return DRIVER_ERROR << 24;
-
- req = blk_get_request(sdev->request_queue, write, gfp);
- if (!req)
- goto free_sense;
- req->cmd_type = REQ_TYPE_BLOCK_PC;
- req->cmd_flags |= REQ_QUIET;
-
- if (use_sg)
- err = scsi_req_map_sg(req, buffer, use_sg, bufflen, gfp);
- else if (bufflen)
- err = blk_rq_map_kern(req->q, req, buffer, bufflen, gfp);
-
- if (err)
- goto free_req;
-
- req->cmd_len = cmd_len;
- memset(req->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
- memcpy(req->cmd, cmd, req->cmd_len);
- req->sense = sioc->sense;
- req->sense_len = 0;
- req->timeout = timeout;
- req->retries = retries;
- req->end_io_data = sioc;
-
- sioc->data = privdata;
- sioc->done = done;
-
- blk_execute_rq_nowait(req->q, NULL, req, 1, scsi_end_async);
- return 0;
-
-free_req:
- blk_put_request(req);
-free_sense:
- kmem_cache_free(scsi_io_context_cache, sioc);
- return DRIVER_ERROR << 24;
-}
-EXPORT_SYMBOL_GPL(scsi_execute_async);
+EXPORT_SYMBOL(scsi_execute_req_flags);
/*
* Function: scsi_init_cmd_errh()
@@ -445,16 +273,18 @@ static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
scsi_set_resid(cmd, 0);
memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
if (cmd->cmd_len == 0)
- cmd->cmd_len = COMMAND_SIZE(cmd->cmnd[0]);
+ cmd->cmd_len = scsi_command_size(cmd->cmnd);
}
void scsi_device_unbusy(struct scsi_device *sdev)
{
struct Scsi_Host *shost = sdev->host;
+ struct scsi_target *starget = scsi_target(sdev);
unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
shost->host_busy--;
+ starget->target_busy--;
if (unlikely(scsi_host_in_recovery(shost) &&
(shost->host_failed || shost->host_eh_scheduled)))
scsi_eh_wakeup(shost);
@@ -510,32 +340,42 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev)
spin_unlock_irqrestore(shost->host_lock, flags);
}
-/*
- * Function: scsi_run_queue()
- *
- * Purpose: Select a proper request queue to serve next
- *
- * Arguments: q - last request's queue
- *
- * Returns: Nothing
- *
- * Notes: The previous command was completely finished, start
- * a new one if possible.
- */
-static void scsi_run_queue(struct request_queue *q)
+static inline int scsi_device_is_busy(struct scsi_device *sdev)
{
- struct scsi_device *sdev = q->queuedata;
- struct Scsi_Host *shost = sdev->host;
- unsigned long flags;
+ if (sdev->device_busy >= sdev->queue_depth || sdev->device_blocked)
+ return 1;
- if (scsi_target(sdev)->single_lun)
- scsi_single_lun_run(sdev);
+ return 0;
+}
+
+static inline int scsi_target_is_busy(struct scsi_target *starget)
+{
+ return ((starget->can_queue > 0 &&
+ starget->target_busy >= starget->can_queue) ||
+ starget->target_blocked);
+}
+
+static inline int scsi_host_is_busy(struct Scsi_Host *shost)
+{
+ if ((shost->can_queue > 0 && shost->host_busy >= shost->can_queue) ||
+ shost->host_blocked || shost->host_self_blocked)
+ return 1;
+
+ return 0;
+}
+
+static void scsi_starved_list_run(struct Scsi_Host *shost)
+{
+ LIST_HEAD(starved_list);
+ struct scsi_device *sdev;
+ unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
- while (!list_empty(&shost->starved_list) &&
- !shost->host_blocked && !shost->host_self_blocked &&
- !((shost->can_queue > 0) &&
- (shost->host_busy >= shost->can_queue))) {
+ list_splice_init(&shost->starved_list, &starved_list);
+
+ while (!list_empty(&starved_list)) {
+ struct request_queue *slq;
+
/*
* As long as shost is accepting commands and we have
* starved queues, call blk_run_queue. scsi_request_fn
@@ -546,35 +386,77 @@ static void scsi_run_queue(struct request_queue *q)
* scsi_request_fn must get the host_lock before checking
* or modifying starved_list or starved_entry.
*/
- sdev = list_entry(shost->starved_list.next,
- struct scsi_device, starved_entry);
+ if (scsi_host_is_busy(shost))
+ break;
+
+ sdev = list_entry(starved_list.next,
+ struct scsi_device, starved_entry);
list_del_init(&sdev->starved_entry);
- spin_unlock_irqrestore(shost->host_lock, flags);
+ if (scsi_target_is_busy(scsi_target(sdev))) {
+ list_move_tail(&sdev->starved_entry,
+ &shost->starved_list);
+ continue;
+ }
+ /*
+ * Once we drop the host lock, a racing scsi_remove_device()
+ * call may remove the sdev from the starved list and destroy
+ * it and the queue. Mitigate by taking a reference to the
+ * queue and never touching the sdev again after we drop the
+ * host lock. Note: if __scsi_remove_device() invokes
+ * blk_cleanup_queue() before the queue is run from this
+ * function then blk_run_queue() will return immediately since
+ * blk_cleanup_queue() marks the queue with QUEUE_FLAG_DYING.
+ */
+ slq = sdev->request_queue;
+ if (!blk_get_queue(slq))
+ continue;
+ spin_unlock_irqrestore(shost->host_lock, flags);
- if (test_bit(QUEUE_FLAG_REENTER, &q->queue_flags) &&
- !test_and_set_bit(QUEUE_FLAG_REENTER,
- &sdev->request_queue->queue_flags)) {
- blk_run_queue(sdev->request_queue);
- clear_bit(QUEUE_FLAG_REENTER,
- &sdev->request_queue->queue_flags);
- } else
- blk_run_queue(sdev->request_queue);
+ blk_run_queue(slq);
+ blk_put_queue(slq);
spin_lock_irqsave(shost->host_lock, flags);
- if (unlikely(!list_empty(&sdev->starved_entry)))
- /*
- * sdev lost a race, and was put back on the
- * starved list. This is unlikely but without this
- * in theory we could loop forever.
- */
- break;
}
+ /* put any unprocessed entries back */
+ list_splice(&starved_list, &shost->starved_list);
spin_unlock_irqrestore(shost->host_lock, flags);
+}
+
+/*
+ * Function: scsi_run_queue()
+ *
+ * Purpose: Select a proper request queue to serve next
+ *
+ * Arguments: q - last request's queue
+ *
+ * Returns: Nothing
+ *
+ * Notes: The previous command was completely finished, start
+ * a new one if possible.
+ */
+static void scsi_run_queue(struct request_queue *q)
+{
+ struct scsi_device *sdev = q->queuedata;
+
+ if (scsi_target(sdev)->single_lun)
+ scsi_single_lun_run(sdev);
+ if (!list_empty(&sdev->host->starved_list))
+ scsi_starved_list_run(sdev->host);
blk_run_queue(q);
}
+void scsi_requeue_run_queue(struct work_struct *work)
+{
+ struct scsi_device *sdev;
+ struct request_queue *q;
+
+ sdev = container_of(work, struct scsi_device, requeue_work);
+ q = sdev->request_queue;
+ scsi_run_queue(q);
+}
+
/*
* Function: scsi_requeue_command()
*
@@ -595,15 +477,20 @@ static void scsi_run_queue(struct request_queue *q)
*/
static void scsi_requeue_command(struct request_queue *q, struct scsi_cmnd *cmd)
{
+ struct scsi_device *sdev = cmd->device;
struct request *req = cmd->request;
unsigned long flags;
- scsi_unprep_request(req);
spin_lock_irqsave(q->queue_lock, flags);
+ blk_unprep_request(req);
+ req->special = NULL;
+ scsi_put_command(cmd);
blk_requeue_request(q, req);
spin_unlock_irqrestore(q->queue_lock, flags);
scsi_run_queue(q);
+
+ put_device(&sdev->sdev_gendev);
}
void scsi_next_command(struct scsi_cmnd *cmd)
@@ -611,13 +498,9 @@ void scsi_next_command(struct scsi_cmnd *cmd)
struct scsi_device *sdev = cmd->device;
struct request_queue *q = sdev->request_queue;
- /* need to hold a reference on the device before we let go of the cmd */
- get_device(&sdev->sdev_gendev);
-
scsi_put_command(cmd);
scsi_run_queue(q);
- /* ok to remove device now */
put_device(&sdev->sdev_gendev);
}
@@ -629,69 +512,6 @@ void scsi_run_host_queues(struct Scsi_Host *shost)
scsi_run_queue(sdev->request_queue);
}
-/*
- * Function: scsi_end_request()
- *
- * Purpose: Post-processing of completed commands (usually invoked at end
- * of upper level post-processing and scsi_io_completion).
- *
- * Arguments: cmd - command that is complete.
- * error - 0 if I/O indicates success, < 0 for I/O error.
- * bytes - number of bytes of completed I/O
- * requeue - indicates whether we should requeue leftovers.
- *
- * Lock status: Assumed that lock is not held upon entry.
- *
- * Returns: cmd if requeue required, NULL otherwise.
- *
- * Notes: This is called for block device requests in order to
- * mark some number of sectors as complete.
- *
- * We are guaranteeing that the request queue will be goosed
- * at some point during this call.
- * Notes: If cmd was requeued, upon return it will be a stale pointer.
- */
-static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int error,
- int bytes, int requeue)
-{
- struct request_queue *q = cmd->device->request_queue;
- struct request *req = cmd->request;
-
- /*
- * If there are blocks left over at the end, set up the command
- * to queue the remainder of them.
- */
- if (blk_end_request(req, error, bytes)) {
- int leftover = (req->hard_nr_sectors << 9);
-
- if (blk_pc_request(req))
- leftover = req->data_len;
-
- /* kill remainder if no retrys */
- if (error && blk_noretry_request(req))
- blk_end_request(req, error, leftover);
- else {
- if (requeue) {
- /*
- * Bleah. Leftovers again. Stick the
- * leftovers in the front of the
- * queue, and goose the queue again.
- */
- scsi_requeue_command(q, cmd);
- cmd = NULL;
- }
- return cmd;
- }
- }
-
- /*
- * This will goose the queue request function at the end, so we don't
- * need to worry about launching another command.
- */
- scsi_next_command(cmd);
- return NULL;
-}
-
static inline unsigned int scsi_sgtable_index(unsigned short nents)
{
unsigned int index;
@@ -746,7 +566,7 @@ static void scsi_free_sgtable(struct scsi_data_buffer *sdb)
/*
* Function: scsi_release_buffers()
*
- * Purpose: Completion processing for block device I/O requests.
+ * Purpose: Free resources allocate for a scsi_command.
*
* Arguments: cmd - command that we are bailing.
*
@@ -757,8 +577,7 @@ static void scsi_free_sgtable(struct scsi_data_buffer *sdb)
* Notes: In the event that an upper level driver rejects a
* command, we must release resources allocated during
* the __init_io() function. Primarily this would involve
- * the scatter-gather table, and potentially any bounce
- * buffers.
+ * the scatter-gather table.
*/
void scsi_release_buffers(struct scsi_cmnd *cmd)
{
@@ -767,42 +586,64 @@ void scsi_release_buffers(struct scsi_cmnd *cmd)
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_bidi_sdb_cache, bidi_sdb);
- cmd->request->next_rq->special = NULL;
- }
+ if (scsi_prot_sg_count(cmd))
+ scsi_free_sgtable(cmd->prot_sdb);
}
EXPORT_SYMBOL(scsi_release_buffers);
-/*
- * Bidi commands Must be complete as a whole, both sides at once.
- * If part of the bytes were written and lld returned
- * scsi_in()->resid and/or scsi_out()->resid this information will be left
- * in req->data_len and req->next_rq->data_len. The upper-layer driver can
- * decide what to do with this information.
- */
-void scsi_end_bidi_request(struct scsi_cmnd *cmd)
+static void scsi_release_bidi_buffers(struct scsi_cmnd *cmd)
{
- struct request *req = cmd->request;
- unsigned int dlen = req->data_len;
- unsigned int next_dlen = req->next_rq->data_len;
+ struct scsi_data_buffer *bidi_sdb = cmd->request->next_rq->special;
- req->data_len = scsi_out(cmd)->resid;
- req->next_rq->data_len = scsi_in(cmd)->resid;
+ scsi_free_sgtable(bidi_sdb);
+ kmem_cache_free(scsi_sdb_cache, bidi_sdb);
+ cmd->request->next_rq->special = NULL;
+}
- /* The req and req->next_rq have not been completed */
- BUG_ON(blk_end_bidi_request(req, 0, dlen, next_dlen));
+/**
+ * __scsi_error_from_host_byte - translate SCSI error code into errno
+ * @cmd: SCSI command (unused)
+ * @result: scsi error code
+ *
+ * Translate SCSI error code into standard UNIX errno.
+ * Return values:
+ * -ENOLINK temporary transport failure
+ * -EREMOTEIO permanent target failure, do not retry
+ * -EBADE permanent nexus failure, retry on other path
+ * -ENOSPC No write space available
+ * -ENODATA Medium error
+ * -EIO unspecified I/O error
+ */
+static int __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result)
+{
+ int error = 0;
- scsi_release_buffers(cmd);
+ switch(host_byte(result)) {
+ case DID_TRANSPORT_FAILFAST:
+ error = -ENOLINK;
+ break;
+ case DID_TARGET_FAILURE:
+ set_host_byte(cmd, DID_OK);
+ error = -EREMOTEIO;
+ break;
+ case DID_NEXUS_FAILURE:
+ set_host_byte(cmd, DID_OK);
+ error = -EBADE;
+ break;
+ case DID_ALLOC_FAILURE:
+ set_host_byte(cmd, DID_OK);
+ error = -ENOSPC;
+ break;
+ case DID_MEDIUM_ERROR:
+ set_host_byte(cmd, DID_OK);
+ error = -ENODATA;
+ break;
+ default:
+ error = -EIO;
+ break;
+ }
- /*
- * This will goose the queue request function at the end, so we don't
- * need to worry about launching another command.
- */
- scsi_next_command(cmd);
+ return error;
}
/*
@@ -816,33 +657,37 @@ void scsi_end_bidi_request(struct scsi_cmnd *cmd)
*
* Returns: Nothing
*
- * Notes: This function is matched in terms of capabilities to
- * the function that created the scatter-gather list.
- * In other words, if there are no bounce buffers
- * (the normal case for most drivers), we don't need
- * the logic to deal with cleaning up afterwards.
+ * Notes: We will finish off the specified number of sectors. If we
+ * are done, the command block will be released and the queue
+ * function will be goosed. If we are not done then we have to
+ * figure out what to do next:
*
- * We must do one of several things here:
+ * a) We can call scsi_requeue_command(). The request
+ * will be unprepared and put back on the queue. Then
+ * a new command will be created for it. This should
+ * be used if we made forward progress, or if we want
+ * to switch from READ(10) to READ(6) for example.
*
- * a) Call scsi_end_request. This will finish off the
- * specified number of sectors. If we are done, the
- * command block will be released, and the queue
- * function will be goosed. If we are not done, then
- * scsi_end_request will directly goose the queue.
+ * b) We can call __scsi_queue_insert(). The request will
+ * be put back on the queue and retried using the same
+ * command as before, possibly after a delay.
*
- * b) We can just use scsi_requeue_command() here. This would
- * be used if we just wanted to retry, for example.
+ * c) We can call blk_end_request() with -EIO to fail
+ * the remainder of the request.
*/
void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
{
int result = cmd->result;
- int this_count = scsi_bufflen(cmd);
struct request_queue *q = cmd->device->request_queue;
struct request *req = cmd->request;
- int clear_errors = 1;
+ int error = 0;
struct scsi_sense_hdr sshdr;
int sense_valid = 0;
int sense_deferred = 0;
+ enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
+ ACTION_DELAYED_RETRY} action;
+ char *description = NULL;
+ unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
if (result) {
sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
@@ -850,10 +695,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
sense_deferred = scsi_sense_is_deferred(&sshdr);
}
- if (blk_pc_request(req)) { /* SG_IO ioctl from block level */
- req->errors = result;
+ if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */
if (result) {
- clear_errors = 0;
if (sense_valid && req->sense) {
/*
* SG_IO wants current and deferred errors
@@ -865,40 +708,102 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
memcpy(req->sense, cmd->sense_buffer, len);
req->sense_len = len;
}
+ if (!sense_deferred)
+ error = __scsi_error_from_host_byte(cmd, result);
}
+ /*
+ * __scsi_error_from_host_byte may have reset the host_byte
+ */
+ req->errors = cmd->result;
+
+ req->resid_len = scsi_get_resid(cmd);
+
if (scsi_bidi_cmnd(cmd)) {
- /* will also release_buffers */
- scsi_end_bidi_request(cmd);
+ /*
+ * Bidi commands Must be complete as a whole,
+ * both sides at once.
+ */
+ req->next_rq->resid_len = scsi_in(cmd)->resid;
+
+ scsi_release_buffers(cmd);
+ scsi_release_bidi_buffers(cmd);
+
+ blk_end_request_all(req, 0);
+
+ scsi_next_command(cmd);
return;
}
- req->data_len = scsi_get_resid(cmd);
+ } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
+ /*
+ * Certain non BLOCK_PC requests are commands that don't
+ * actually transfer anything (FLUSH), so cannot use
+ * good_bytes != blk_rq_bytes(req) as the signal for an error.
+ * This sets the error explicitly for the problem case.
+ */
+ error = __scsi_error_from_host_byte(cmd, result);
}
- BUG_ON(blk_bidi_rq(req)); /* bidi not support for !blk_pc_request yet */
- scsi_release_buffers(cmd);
+ /* no bidi support for !REQ_TYPE_BLOCK_PC yet */
+ BUG_ON(blk_bidi_rq(req));
/*
* Next deal with any sectors which we were able to correctly
* handle.
*/
- SCSI_LOG_HLCOMPLETE(1, printk("%ld sectors total, "
+ SCSI_LOG_HLCOMPLETE(1, printk("%u sectors total, "
"%d bytes done.\n",
- req->nr_sectors, good_bytes));
+ blk_rq_sectors(req), good_bytes));
+
+ /*
+ * Recovered errors need reporting, but they're always treated
+ * as success, so fiddle the result code here. For BLOCK_PC
+ * we already took a copy of the original into rq->errors which
+ * is what gets returned to the user
+ */
+ if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
+ /* if ATA PASS-THROUGH INFORMATION AVAILABLE skip
+ * print since caller wants ATA registers. Only occurs on
+ * SCSI ATA PASS_THROUGH commands when CK_COND=1
+ */
+ if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
+ ;
+ else if (!(req->cmd_flags & REQ_QUIET))
+ scsi_print_sense("", cmd);
+ result = 0;
+ /* BLOCK_PC may have set error */
+ error = 0;
+ }
- if (clear_errors)
- req->errors = 0;
+ /*
+ * If we finished all bytes in the request we are done now.
+ */
+ if (!blk_end_request(req, error, good_bytes))
+ goto next_command;
- /* A number of bytes were successfully read. If there
- * are leftovers and there is some kind of error
- * (result != 0), retry the rest.
+ /*
+ * Kill remainder if no retrys.
*/
- if (scsi_end_request(cmd, 0, good_bytes, result == 0) == NULL)
- return;
+ if (error && scsi_noretry_cmd(cmd)) {
+ blk_end_request_all(req, error);
+ goto next_command;
+ }
- /* good_bytes = 0, or (inclusive) there were leftovers and
- * result = 0, so scsi_end_request couldn't retry.
+ /*
+ * If there had been no error, but we have leftover bytes in the
+ * requeues just queue the command up again.
*/
- if (sense_valid && !sense_deferred) {
+ if (result == 0)
+ goto requeue;
+
+ error = __scsi_error_from_host_byte(cmd, result);
+
+ if (host_byte(result) == DID_RESET) {
+ /* Third party bus reset or reset for error recovery
+ * reasons. Just retry the command and see what
+ * happens.
+ */
+ action = ACTION_RETRY;
+ } else if (sense_valid && !sense_deferred) {
switch (sshdr.sense_key) {
case UNIT_ATTENTION:
if (cmd->device->removable) {
@@ -906,16 +811,15 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
* and quietly refuse further access.
*/
cmd->device->changed = 1;
- scsi_end_request(cmd, -EIO, this_count, 1);
- return;
+ description = "Media Changed";
+ action = ACTION_FAIL;
} else {
/* Must have been a power glitch, or a
* bus reset. Could not have been a
* media change, so we just retry the
- * request and see what happens.
+ * command and see what happens.
*/
- scsi_requeue_command(q, cmd);
- return;
+ action = ACTION_RETRY;
}
break;
case ILLEGAL_REQUEST:
@@ -931,15 +835,41 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
sshdr.asc == 0x20 && sshdr.ascq == 0x00) &&
(cmd->cmnd[0] == READ_10 ||
cmd->cmnd[0] == WRITE_10)) {
+ /* This will issue a new 6-byte command. */
cmd->device->use_10_for_rw = 0;
- /* This will cause a retry with a
- * 6-byte command.
- */
- scsi_requeue_command(q, cmd);
- return;
- } else {
- scsi_end_request(cmd, -EIO, this_count, 1);
- return;
+ action = ACTION_REPREP;
+ } else if (sshdr.asc == 0x10) /* DIX */ {
+ description = "Host Data Integrity Failure";
+ action = ACTION_FAIL;
+ error = -EILSEQ;
+ /* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
+ } else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
+ switch (cmd->cmnd[0]) {
+ case UNMAP:
+ description = "Discard failure";
+ break;
+ case WRITE_SAME:
+ case WRITE_SAME_16:
+ if (cmd->cmnd[1] & 0x8)
+ description = "Discard failure";
+ else
+ description =
+ "Write same failure";
+ break;
+ default:
+ description = "Invalid command failure";
+ break;
+ }
+ action = ACTION_FAIL;
+ error = -EREMOTEIO;
+ } else
+ action = ACTION_FAIL;
+ break;
+ case ABORTED_COMMAND:
+ action = ACTION_FAIL;
+ if (sshdr.asc == 0x10) { /* DIF */
+ description = "Target Data Integrity Failure";
+ error = -EILSEQ;
}
break;
case NOT_READY:
@@ -955,49 +885,76 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
case 0x07: /* operation in progress */
case 0x08: /* Long write in progress */
case 0x09: /* self test in progress */
- scsi_requeue_command(q, cmd);
- return;
+ case 0x14: /* space allocation in progress */
+ action = ACTION_DELAYED_RETRY;
+ break;
default:
+ description = "Device not ready";
+ action = ACTION_FAIL;
break;
}
+ } else {
+ description = "Device not ready";
+ action = ACTION_FAIL;
}
- if (!(req->cmd_flags & REQ_QUIET))
- scsi_cmd_print_sense_hdr(cmd,
- "Device not ready",
- &sshdr);
-
- scsi_end_request(cmd, -EIO, this_count, 1);
- return;
+ break;
case VOLUME_OVERFLOW:
- if (!(req->cmd_flags & REQ_QUIET)) {
- scmd_printk(KERN_INFO, cmd,
- "Volume overflow, CDB: ");
- __scsi_print_command(cmd->cmnd);
- scsi_print_sense("", cmd);
- }
/* See SSC3rXX or current. */
- scsi_end_request(cmd, -EIO, this_count, 1);
- return;
+ action = ACTION_FAIL;
+ break;
default:
+ description = "Unhandled sense code";
+ action = ACTION_FAIL;
break;
}
+ } else {
+ description = "Unhandled error code";
+ action = ACTION_FAIL;
}
- if (host_byte(result) == DID_RESET) {
- /* Third party bus reset or reset for error recovery
- * reasons. Just retry the request and see what
- * happens.
- */
- scsi_requeue_command(q, cmd);
- return;
+
+ if (action != ACTION_FAIL &&
+ time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
+ action = ACTION_FAIL;
+ description = "Command timed out";
}
- if (result) {
+
+ switch (action) {
+ case ACTION_FAIL:
+ /* Give up and fail the remainder of the request */
if (!(req->cmd_flags & REQ_QUIET)) {
+ if (description)
+ scmd_printk(KERN_INFO, cmd, "%s\n",
+ description);
scsi_print_result(cmd);
if (driver_byte(result) & DRIVER_SENSE)
scsi_print_sense("", cmd);
+ scsi_print_command(cmd);
}
+ if (!blk_end_request_err(req, error))
+ goto next_command;
+ /*FALLTHRU*/
+ case ACTION_REPREP:
+ requeue:
+ /* 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:
+ /* Retry the same command immediately */
+ __scsi_queue_insert(cmd, SCSI_MLQUEUE_EH_RETRY, 0);
+ break;
+ case ACTION_DELAYED_RETRY:
+ /* Retry the same command after a delay */
+ __scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, 0);
+ break;
}
- scsi_end_request(cmd, -EIO, this_count, !result);
+ return;
+
+next_command:
+ scsi_release_buffers(cmd);
+ scsi_next_command(cmd);
}
static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
@@ -1013,8 +970,6 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
return BLKPREP_DEFER;
}
- req->buffer = NULL;
-
/*
* Next, walk the list, and fill in the addresses and sizes of
* each segment.
@@ -1022,10 +977,7 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
count = blk_rq_map_sg(req->q, req, sdb->table.sgl);
BUG_ON(count > sdb->table.nents);
sdb->table.nents = count;
- if (blk_pc_request(req))
- sdb->length = req->data_len;
- else
- sdb->length = req->nr_sectors << 9;
+ sdb->length = blk_rq_bytes(req);
return BLKPREP_OK;
}
@@ -1042,34 +994,55 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
*/
int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
{
- int error = scsi_init_sgtable(cmd->request, &cmd->sdb, gfp_mask);
+ struct scsi_device *sdev = cmd->device;
+ struct request *rq = cmd->request;
+
+ int error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask);
if (error)
goto err_exit;
- if (blk_bidi_rq(cmd->request)) {
+ if (blk_bidi_rq(rq)) {
struct scsi_data_buffer *bidi_sdb = kmem_cache_zalloc(
- scsi_bidi_sdb_cache, GFP_ATOMIC);
+ scsi_sdb_cache, GFP_ATOMIC);
if (!bidi_sdb) {
error = BLKPREP_DEFER;
goto err_exit;
}
- cmd->request->next_rq->special = bidi_sdb;
- error = scsi_init_sgtable(cmd->request->next_rq, bidi_sdb,
- GFP_ATOMIC);
+ rq->next_rq->special = bidi_sdb;
+ error = scsi_init_sgtable(rq->next_rq, bidi_sdb, GFP_ATOMIC);
if (error)
goto err_exit;
}
+ if (blk_integrity_rq(rq)) {
+ struct scsi_data_buffer *prot_sdb = cmd->prot_sdb;
+ int ivecs, count;
+
+ BUG_ON(prot_sdb == NULL);
+ ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
+
+ if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask)) {
+ error = BLKPREP_DEFER;
+ goto err_exit;
+ }
+
+ count = blk_rq_map_integrity_sg(rq->q, rq->bio,
+ prot_sdb->table.sgl);
+ BUG_ON(unlikely(count > ivecs));
+ BUG_ON(unlikely(count > queue_max_integrity_segments(rq->q)));
+
+ cmd->prot_sdb = prot_sdb;
+ cmd->prot_sdb->table.nents = count;
+ }
+
return BLKPREP_OK ;
err_exit:
scsi_release_buffers(cmd);
- if (error == BLKPREP_KILL)
- scsi_put_command(cmd);
- else /* BLKPREP_DEFER */
- scsi_unprep_request(cmd->request);
-
+ cmd->request->special = NULL;
+ scsi_put_command(cmd);
+ put_device(&sdev->sdev_gendev);
return error;
}
EXPORT_SYMBOL(scsi_init_io);
@@ -1080,9 +1053,15 @@ static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev,
struct scsi_cmnd *cmd;
if (!req->special) {
+ /* Bail if we can't get a reference to the device */
+ if (!get_device(&sdev->sdev_gendev))
+ return NULL;
+
cmd = scsi_get_command(sdev, GFP_ATOMIC);
- if (unlikely(!cmd))
+ if (unlikely(!cmd)) {
+ put_device(&sdev->sdev_gendev);
return NULL;
+ }
req->special = cmd;
} else {
cmd = req->special;
@@ -1092,20 +1071,15 @@ static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev,
cmd->tag = req->tag;
cmd->request = req;
+ cmd->cmnd = req->cmd;
+ cmd->prot_op = SCSI_PROT_NORMAL;
+
return cmd;
}
int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
{
- struct scsi_cmnd *cmd;
- int ret = scsi_prep_state_check(sdev, req);
-
- if (ret != BLKPREP_OK)
- return ret;
-
- cmd = scsi_get_cmd_from_req(sdev, req);
- if (unlikely(!cmd))
- return BLKPREP_DEFER;
+ struct scsi_cmnd *cmd = req->special;
/*
* BLOCK_PC requests may transfer data, in which case they must
@@ -1122,26 +1096,21 @@ int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
if (unlikely(ret))
return ret;
} else {
- BUG_ON(req->data_len);
- BUG_ON(req->data);
+ BUG_ON(blk_rq_bytes(req));
memset(&cmd->sdb, 0, sizeof(cmd->sdb));
- req->buffer = NULL;
}
- BUILD_BUG_ON(sizeof(req->cmd) > sizeof(cmd->cmnd));
- memcpy(cmd->cmnd, req->cmd, sizeof(cmd->cmnd));
cmd->cmd_len = req->cmd_len;
- if (!req->data_len)
+ if (!blk_rq_bytes(req))
cmd->sc_data_direction = DMA_NONE;
else if (rq_data_dir(req) == WRITE)
cmd->sc_data_direction = DMA_TO_DEVICE;
else
cmd->sc_data_direction = DMA_FROM_DEVICE;
- cmd->transfersize = req->data_len;
+ cmd->transfersize = blk_rq_bytes(req);
cmd->allowed = req->retries;
- cmd->timeout_per_command = req->timeout;
return BLKPREP_OK;
}
EXPORT_SYMBOL(scsi_setup_blk_pc_cmnd);
@@ -1153,25 +1122,27 @@ EXPORT_SYMBOL(scsi_setup_blk_pc_cmnd);
*/
int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req)
{
- struct scsi_cmnd *cmd;
- int ret = scsi_prep_state_check(sdev, req);
+ struct scsi_cmnd *cmd = req->special;
+
+ if (unlikely(sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh
+ && sdev->scsi_dh_data->scsi_dh->prep_fn)) {
+ int ret = sdev->scsi_dh_data->scsi_dh->prep_fn(sdev, req);
+ if (ret != BLKPREP_OK)
+ return ret;
+ }
- if (ret != BLKPREP_OK)
- return ret;
/*
* Filesystem requests must transfer data.
*/
BUG_ON(!req->nr_phys_segments);
- cmd = scsi_get_cmd_from_req(sdev, req);
- if (unlikely(!cmd))
- return BLKPREP_DEFER;
-
+ memset(cmd->cmnd, 0, BLK_MAX_CDB);
return scsi_init_io(cmd, GFP_ATOMIC);
}
EXPORT_SYMBOL(scsi_setup_fs_cmnd);
-int scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
+static int
+scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
{
int ret = BLKPREP_OK;
@@ -1182,6 +1153,7 @@ int scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
if (unlikely(sdev->sdev_state != SDEV_RUNNING)) {
switch (sdev->sdev_state) {
case SDEV_OFFLINE:
+ case SDEV_TRANSPORT_OFFLINE:
/*
* If the device is offline we refuse to process any
* commands. The device must be brought online
@@ -1202,6 +1174,7 @@ int scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
break;
case SDEV_QUIESCE:
case SDEV_BLOCK:
+ case SDEV_CREATED_BLOCK:
/*
* If the devices is blocked we defer normal commands.
*/
@@ -1221,9 +1194,9 @@ int scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
}
return ret;
}
-EXPORT_SYMBOL(scsi_prep_state_check);
-int scsi_prep_return(struct request_queue *q, struct request *req, int ret)
+static int
+scsi_prep_return(struct request_queue *q, struct request *req, int ret)
{
struct scsi_device *sdev = q->queuedata;
@@ -1235,17 +1208,18 @@ int scsi_prep_return(struct request_queue *q, struct request *req, int ret)
struct scsi_cmnd *cmd = req->special;
scsi_release_buffers(cmd);
scsi_put_command(cmd);
+ put_device(&sdev->sdev_gendev);
req->special = NULL;
}
break;
case BLKPREP_DEFER:
/*
- * If we defer, the elv_next_request() returns NULL, but the
- * queue must be restarted, so we plug here if no returning
- * command will automatically do that.
+ * If we defer, the blk_peek_request() returns NULL, but the
+ * queue must be restarted, so we schedule a callback to happen
+ * shortly.
*/
if (sdev->device_busy == 0)
- blk_plug_device(q);
+ blk_delay_queue(q, SCSI_QUEUE_DELAY);
break;
default:
req->cmd_flags |= REQ_DONTPREP;
@@ -1253,18 +1227,45 @@ int scsi_prep_return(struct request_queue *q, struct request *req, int ret)
return ret;
}
-EXPORT_SYMBOL(scsi_prep_return);
-int scsi_prep_fn(struct request_queue *q, struct request *req)
+static int scsi_prep_fn(struct request_queue *q, struct request *req)
{
struct scsi_device *sdev = q->queuedata;
- int ret = BLKPREP_KILL;
+ struct scsi_cmnd *cmd;
+ int ret;
+
+ ret = scsi_prep_state_check(sdev, req);
+ if (ret != BLKPREP_OK)
+ goto out;
- if (req->cmd_type == REQ_TYPE_BLOCK_PC)
+ cmd = scsi_get_cmd_from_req(sdev, req);
+ if (unlikely(!cmd)) {
+ ret = BLKPREP_DEFER;
+ goto out;
+ }
+
+ if (req->cmd_type == REQ_TYPE_FS)
+ ret = scsi_cmd_to_driver(cmd)->init_command(cmd);
+ else if (req->cmd_type == REQ_TYPE_BLOCK_PC)
ret = scsi_setup_blk_pc_cmnd(sdev, req);
+ else
+ ret = BLKPREP_KILL;
+
+out:
return scsi_prep_return(q, req, ret);
}
+static void scsi_unprep_fn(struct request_queue *q, struct request *req)
+{
+ if (req->cmd_type == REQ_TYPE_FS) {
+ struct scsi_cmnd *cmd = req->special;
+ struct scsi_driver *drv = scsi_cmd_to_driver(cmd);
+
+ if (drv->uninit_command)
+ drv->uninit_command(cmd);
+ }
+}
+
/*
* scsi_dev_queue_ready: if we can send requests to sdev, return 1 else
* return 0.
@@ -1274,8 +1275,6 @@ int scsi_prep_fn(struct request_queue *q, struct request *req)
static inline int scsi_dev_queue_ready(struct request_queue *q,
struct scsi_device *sdev)
{
- if (sdev->device_busy >= sdev->queue_depth)
- return 0;
if (sdev->device_busy == 0 && sdev->device_blocked) {
/*
* unblock after device_blocked iterates to zero
@@ -1285,12 +1284,50 @@ static inline int scsi_dev_queue_ready(struct request_queue *q,
sdev_printk(KERN_INFO, sdev,
"unblocking device at zero depth\n"));
} else {
- blk_plug_device(q);
+ blk_delay_queue(q, SCSI_QUEUE_DELAY);
return 0;
}
}
- if (sdev->device_blocked)
+ if (scsi_device_is_busy(sdev))
+ return 0;
+
+ return 1;
+}
+
+
+/*
+ * scsi_target_queue_ready: checks if there we can send commands to target
+ * @sdev: scsi device on starget to check.
+ *
+ * Called with the host lock held.
+ */
+static inline int scsi_target_queue_ready(struct Scsi_Host *shost,
+ struct scsi_device *sdev)
+{
+ struct scsi_target *starget = scsi_target(sdev);
+
+ if (starget->single_lun) {
+ if (starget->starget_sdev_user &&
+ starget->starget_sdev_user != sdev)
+ return 0;
+ starget->starget_sdev_user = sdev;
+ }
+
+ if (starget->target_busy == 0 && starget->target_blocked) {
+ /*
+ * unblock after target_blocked iterates to zero
+ */
+ if (--starget->target_blocked == 0) {
+ SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget,
+ "unblocking target at zero depth\n"));
+ } else
+ return 0;
+ }
+
+ if (scsi_target_is_busy(starget)) {
+ list_move_tail(&sdev->starved_entry, &shost->starved_list);
return 0;
+ }
return 1;
}
@@ -1317,12 +1354,10 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
printk("scsi%d unblocking host at zero depth\n",
shost->host_no));
} else {
- blk_plug_device(q);
return 0;
}
}
- if ((shost->can_queue > 0 && shost->host_busy >= shost->can_queue) ||
- shost->host_blocked || shost->host_self_blocked) {
+ if (scsi_host_is_busy(shost)) {
if (list_empty(&sdev->starved_entry))
list_add_tail(&sdev->starved_entry, &shost->starved_list);
return 0;
@@ -1336,22 +1371,56 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
}
/*
+ * Busy state exporting function for request stacking drivers.
+ *
+ * For efficiency, no lock is taken to check the busy state of
+ * shost/starget/sdev, since the returned value is not guaranteed and
+ * may be changed after request stacking drivers call the function,
+ * regardless of taking lock or not.
+ *
+ * When scsi can't dispatch I/Os anymore and needs to kill I/Os scsi
+ * needs to return 'not busy'. Otherwise, request stacking drivers
+ * may hold requests forever.
+ */
+static int scsi_lld_busy(struct request_queue *q)
+{
+ struct scsi_device *sdev = q->queuedata;
+ struct Scsi_Host *shost;
+
+ if (blk_queue_dying(q))
+ return 0;
+
+ shost = sdev->host;
+
+ /*
+ * Ignore host/starget busy state.
+ * Since block layer does not have a concept of fairness across
+ * multiple queues, congestion of host/starget needs to be handled
+ * in SCSI layer.
+ */
+ if (scsi_host_in_recovery(shost) || scsi_device_is_busy(sdev))
+ return 1;
+
+ return 0;
+}
+
+/*
* Kill a request for a dead device
*/
static void scsi_kill_request(struct request *req, struct request_queue *q)
{
struct scsi_cmnd *cmd = req->special;
- struct scsi_device *sdev = cmd->device;
- struct Scsi_Host *shost = sdev->host;
+ struct scsi_device *sdev;
+ struct scsi_target *starget;
+ struct Scsi_Host *shost;
- blkdev_dequeue_request(req);
+ blk_start_request(req);
- if (unlikely(cmd == NULL)) {
- printk(KERN_CRIT "impossible request in %s.\n",
- __FUNCTION__);
- BUG();
- }
+ scmd_printk(KERN_INFO, cmd, "killing request\n");
+ sdev = cmd->device;
+ starget = scsi_target(sdev);
+ shost = sdev->host;
scsi_init_cmd_errh(cmd);
cmd->result = DID_NO_CONNECT << 16;
atomic_inc(&cmd->device->iorequest_cnt);
@@ -1365,20 +1434,25 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
spin_unlock(sdev->request_queue->queue_lock);
spin_lock(shost->host_lock);
shost->host_busy++;
+ starget->target_busy++;
spin_unlock(shost->host_lock);
spin_lock(sdev->request_queue->queue_lock);
- __scsi_done(cmd);
+ blk_complete_request(req);
}
static void scsi_softirq_done(struct request *rq)
{
- struct scsi_cmnd *cmd = rq->completion_data;
- unsigned long wait_for = (cmd->allowed + 1) * cmd->timeout_per_command;
+ struct scsi_cmnd *cmd = rq->special;
+ unsigned long wait_for = (cmd->allowed + 1) * rq->timeout;
int disposition;
INIT_LIST_HEAD(&cmd->eh_entry);
+ atomic_inc(&cmd->device->iodone_cnt);
+ if (cmd->result)
+ atomic_inc(&cmd->device->ioerr_cnt);
+
disposition = scsi_decide_disposition(cmd);
if (disposition != SUCCESS &&
time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
@@ -1418,36 +1492,27 @@ static void scsi_softirq_done(struct request *rq)
* Lock status: IO request lock assumed to be held when called.
*/
static void scsi_request_fn(struct request_queue *q)
+ __releases(q->queue_lock)
+ __acquires(q->queue_lock)
{
struct scsi_device *sdev = q->queuedata;
struct Scsi_Host *shost;
struct scsi_cmnd *cmd;
struct request *req;
- if (!sdev) {
- printk("scsi: killing requests for dead queue\n");
- while ((req = elv_next_request(q)) != NULL)
- scsi_kill_request(req, q);
- return;
- }
-
- if(!get_device(&sdev->sdev_gendev))
- /* We must be tearing the block queue down already */
- return;
-
/*
* To start with, we keep looping until the queue is empty, or until
* the host is no longer able to accept any more requests.
*/
shost = sdev->host;
- while (!blk_queue_plugged(q)) {
+ for (;;) {
int rtn;
/*
* get next queueable request. We do this early to make sure
* that the request is fully prepared even if we cannot
* accept it.
*/
- req = elv_next_request(q);
+ req = blk_peek_request(q);
if (!req || !scsi_dev_queue_ready(q, sdev))
break;
@@ -1463,7 +1528,7 @@ static void scsi_request_fn(struct request_queue *q)
* Remove the request from the request list.
*/
if (!(blk_queue_tagged(q) && !blk_queue_start_tag(q, req)))
- blkdev_dequeue_request(req);
+ blk_start_request(req);
sdev->device_busy++;
spin_unlock(q->queue_lock);
@@ -1472,20 +1537,34 @@ static void scsi_request_fn(struct request_queue *q)
printk(KERN_CRIT "impossible request in %s.\n"
"please mail a stack trace to "
"linux-scsi@vger.kernel.org\n",
- __FUNCTION__);
+ __func__);
blk_dump_rq_flags(req, "foo");
BUG();
}
spin_lock(shost->host_lock);
- if (!scsi_host_queue_ready(q, shost, sdev))
+ /*
+ * We hit this when the driver is using a host wide
+ * tag map. For device level tag maps the queue_depth check
+ * in the device ready fn would prevent us from trying
+ * to allocate a tag. Since the map is a shared host resource
+ * we add the dev to the starved list so it eventually gets
+ * a run when a tag is freed.
+ */
+ if (blk_queue_tagged(q) && !blk_rq_tagged(req)) {
+ if (list_empty(&sdev->starved_entry))
+ list_add_tail(&sdev->starved_entry,
+ &shost->starved_list);
goto not_ready;
- if (scsi_target(sdev)->single_lun) {
- if (scsi_target(sdev)->starget_sdev_user &&
- scsi_target(sdev)->starget_sdev_user != sdev)
- goto not_ready;
- scsi_target(sdev)->starget_sdev_user = sdev;
}
+
+ if (!scsi_target_queue_ready(shost, sdev))
+ goto not_ready;
+
+ if (!scsi_host_queue_ready(q, shost, sdev))
+ goto not_ready;
+
+ scsi_target(sdev)->target_busy++;
shost->host_busy++;
/*
@@ -1505,18 +1584,11 @@ static void scsi_request_fn(struct request_queue *q)
*/
rtn = scsi_dispatch_cmd(cmd);
spin_lock_irq(q->queue_lock);
- if(rtn) {
- /* we're refusing the command; because of
- * the way locks get dropped, we need to
- * check here if plugging is required */
- if(sdev->device_busy == 0)
- blk_plug_device(q);
-
- break;
- }
+ if (rtn)
+ goto out_delay;
}
- goto out;
+ return;
not_ready:
spin_unlock_irq(shost->host_lock);
@@ -1532,14 +1604,9 @@ static void scsi_request_fn(struct request_queue *q)
spin_lock_irq(q->queue_lock);
blk_requeue_request(q, req);
sdev->device_busy--;
- if(sdev->device_busy == 0)
- blk_plug_device(q);
- out:
- /* must be careful here...if we trigger the ->remove() function
- * we cannot be holding the q lock */
- spin_unlock_irq(q->queue_lock);
- put_device(&sdev->sdev_gendev);
- spin_lock_irq(q->queue_lock);
+out_delay:
+ if (sdev->device_busy == 0)
+ blk_delay_queue(q, SCSI_QUEUE_DELAY);
}
u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
@@ -1558,7 +1625,7 @@ u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
host_dev = scsi_get_device(shost);
if (host_dev && host_dev->dma_mask)
- bounce_limit = *host_dev->dma_mask;
+ bounce_limit = (u64)dma_max_pfn(host_dev) << PAGE_SHIFT;
return bounce_limit;
}
@@ -1568,7 +1635,7 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
request_fn_proc *request_fn)
{
struct request_queue *q;
- struct device *dev = shost->shost_gendev.parent;
+ struct device *dev = shost->dma_dev;
q = blk_init_queue(request_fn, NULL);
if (!q)
@@ -1577,10 +1644,18 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
/*
* this limit is imposed by hardware restrictions
*/
- blk_queue_max_hw_segments(q, shost->sg_tablesize);
- blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS);
+ blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize,
+ SCSI_MAX_SG_CHAIN_SEGMENTS));
+
+ if (scsi_host_prot_dma(shost)) {
+ shost->sg_prot_tablesize =
+ min_not_zero(shost->sg_prot_tablesize,
+ (unsigned short)SCSI_MAX_PROT_SG_SEGMENTS);
+ BUG_ON(shost->sg_prot_tablesize < shost->sg_tablesize);
+ blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
+ }
- blk_queue_max_sectors(q, shost->max_sectors);
+ blk_queue_max_hw_sectors(q, shost->max_sectors);
blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost));
blk_queue_segment_boundary(q, shost->dma_boundary);
dma_set_seg_boundary(dev, shost->dma_boundary);
@@ -1588,7 +1663,7 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
if (!shost->use_clustering)
- clear_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+ q->limits.cluster = 0;
/*
* set a reasonable default alignment on word boundaries: the
@@ -1610,15 +1685,13 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
return NULL;
blk_queue_prep_rq(q, scsi_prep_fn);
+ blk_queue_unprep_rq(q, scsi_unprep_fn);
blk_queue_softirq_done(q, scsi_softirq_done);
+ blk_queue_rq_timed_out(q, scsi_times_out);
+ blk_queue_lld_busy(q, scsi_lld_busy);
return q;
}
-void scsi_free_queue(struct request_queue *q)
-{
- blk_cleanup_queue(q);
-}
-
/*
* Function: scsi_block_requests()
*
@@ -1672,22 +1745,14 @@ int __init scsi_init_queue(void)
{
int i;
- scsi_io_context_cache = kmem_cache_create("scsi_io_context",
- sizeof(struct scsi_io_context),
- 0, 0, NULL);
- if (!scsi_io_context_cache) {
- printk(KERN_ERR "SCSI: can't init scsi io context cache\n");
+ scsi_sdb_cache = kmem_cache_create("scsi_data_buffer",
+ sizeof(struct scsi_data_buffer),
+ 0, 0, NULL);
+ if (!scsi_sdb_cache) {
+ printk(KERN_ERR "SCSI: can't init scsi sdb cache\n");
return -ENOMEM;
}
- scsi_bidi_sdb_cache = kmem_cache_create("scsi_bidi_sdb",
- sizeof(struct scsi_data_buffer),
- 0, 0, NULL);
- if (!scsi_bidi_sdb_cache) {
- printk(KERN_ERR "SCSI: can't init scsi bidi sdb cache\n");
- goto cleanup_io_context;
- }
-
for (i = 0; i < SG_MEMPOOL_NR; i++) {
struct scsi_host_sg_pool *sgp = scsi_sg_pools + i;
int size = sgp->size * sizeof(struct scatterlist);
@@ -1697,7 +1762,7 @@ int __init scsi_init_queue(void)
if (!sgp->slab) {
printk(KERN_ERR "SCSI: can't init sg slab %s\n",
sgp->name);
- goto cleanup_bidi_sdb;
+ goto cleanup_sdb;
}
sgp->pool = mempool_create_slab_pool(SG_MEMPOOL_SIZE,
@@ -1705,13 +1770,13 @@ int __init scsi_init_queue(void)
if (!sgp->pool) {
printk(KERN_ERR "SCSI: can't init sg mempool %s\n",
sgp->name);
- goto cleanup_bidi_sdb;
+ goto cleanup_sdb;
}
}
return 0;
-cleanup_bidi_sdb:
+cleanup_sdb:
for (i = 0; i < SG_MEMPOOL_NR; i++) {
struct scsi_host_sg_pool *sgp = scsi_sg_pools + i;
if (sgp->pool)
@@ -1719,9 +1784,7 @@ cleanup_bidi_sdb:
if (sgp->slab)
kmem_cache_destroy(sgp->slab);
}
- kmem_cache_destroy(scsi_bidi_sdb_cache);
-cleanup_io_context:
- kmem_cache_destroy(scsi_io_context_cache);
+ kmem_cache_destroy(scsi_sdb_cache);
return -ENOMEM;
}
@@ -1730,8 +1793,7 @@ void scsi_exit_queue(void)
{
int i;
- kmem_cache_destroy(scsi_io_context_cache);
- kmem_cache_destroy(scsi_bidi_sdb_cache);
+ kmem_cache_destroy(scsi_sdb_cache);
for (i = 0; i < SG_MEMPOOL_NR; i++) {
struct scsi_host_sg_pool *sgp = scsi_sg_pools + i;
@@ -1811,7 +1873,7 @@ scsi_mode_select(struct scsi_device *sdev, int pf, int sp, int modepage,
}
ret = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, real_buffer, len,
- sshdr, timeout, retries);
+ sshdr, timeout, retries, NULL);
kfree(real_buffer);
return ret;
}
@@ -1876,7 +1938,7 @@ scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage,
memset(buffer, 0, len);
result = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buffer, len,
- sshdr, timeout, retries);
+ sshdr, timeout, retries, NULL);
/* This code looks awful: what it's doing is making sure an
* ILLEGAL REQUEST sense return identifies the actual command
@@ -1937,8 +1999,7 @@ EXPORT_SYMBOL(scsi_mode_sense);
* in.
*
* Returns zero if unsuccessful or an error if TUR failed. For
- * removable media, a return of NOT_READY or UNIT_ATTENTION is
- * translated to success, with the ->changed flag updated.
+ * removable media, UNIT_ATTENTION sets ->changed flag.
**/
int
scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries,
@@ -1958,24 +2019,13 @@ scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries,
/* try to eat the UNIT_ATTENTION if there are enough retries */
do {
result = scsi_execute_req(sdev, cmd, DMA_NONE, NULL, 0, sshdr,
- timeout, retries);
- } while ((driver_byte(result) & DRIVER_SENSE) &&
- sshdr && sshdr->sense_key == UNIT_ATTENTION &&
- --retries);
-
- if (!sshdr)
- /* could not allocate sense buffer, so can't process it */
- return result;
-
- if ((driver_byte(result) & DRIVER_SENSE) && sdev->removable) {
-
- if ((scsi_sense_valid(sshdr)) &&
- ((sshdr->sense_key == UNIT_ATTENTION) ||
- (sshdr->sense_key == NOT_READY))) {
+ timeout, retries, NULL);
+ if (sdev->removable && scsi_sense_valid(sshdr) &&
+ sshdr->sense_key == UNIT_ATTENTION)
sdev->changed = 1;
- result = 0;
- }
- }
+ } while (scsi_sense_valid(sshdr) &&
+ sshdr->sense_key == UNIT_ATTENTION && --retries);
+
if (!sshdr_external)
kfree(sshdr);
return result;
@@ -2000,15 +2050,19 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
switch (state) {
case SDEV_CREATED:
- /* There are no legal states that come back to
- * created. This is the manually initialised start
- * state */
- goto illegal;
+ switch (oldstate) {
+ case SDEV_CREATED_BLOCK:
+ break;
+ default:
+ goto illegal;
+ }
+ break;
case SDEV_RUNNING:
switch (oldstate) {
case SDEV_CREATED:
case SDEV_OFFLINE:
+ case SDEV_TRANSPORT_OFFLINE:
case SDEV_QUIESCE:
case SDEV_BLOCK:
break;
@@ -2021,6 +2075,7 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
switch (oldstate) {
case SDEV_RUNNING:
case SDEV_OFFLINE:
+ case SDEV_TRANSPORT_OFFLINE:
break;
default:
goto illegal;
@@ -2028,6 +2083,7 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
break;
case SDEV_OFFLINE:
+ case SDEV_TRANSPORT_OFFLINE:
switch (oldstate) {
case SDEV_CREATED:
case SDEV_RUNNING:
@@ -2041,8 +2097,17 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
case SDEV_BLOCK:
switch (oldstate) {
- case SDEV_CREATED:
case SDEV_RUNNING:
+ case SDEV_CREATED_BLOCK:
+ break;
+ default:
+ goto illegal;
+ }
+ break;
+
+ case SDEV_CREATED_BLOCK:
+ switch (oldstate) {
+ case SDEV_CREATED:
break;
default:
goto illegal;
@@ -2055,6 +2120,7 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
case SDEV_RUNNING:
case SDEV_QUIESCE:
case SDEV_OFFLINE:
+ case SDEV_TRANSPORT_OFFLINE:
case SDEV_BLOCK:
break;
default:
@@ -2067,7 +2133,9 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
case SDEV_CREATED:
case SDEV_RUNNING:
case SDEV_OFFLINE:
+ case SDEV_TRANSPORT_OFFLINE:
case SDEV_CANCEL:
+ case SDEV_CREATED_BLOCK:
break;
default:
goto illegal;
@@ -2105,7 +2173,21 @@ static void scsi_evt_emit(struct scsi_device *sdev, struct scsi_event *evt)
case SDEV_EVT_MEDIA_CHANGE:
envp[idx++] = "SDEV_MEDIA_CHANGE=1";
break;
-
+ case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
+ envp[idx++] = "SDEV_UA=INQUIRY_DATA_HAS_CHANGED";
+ break;
+ case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
+ envp[idx++] = "SDEV_UA=CAPACITY_DATA_HAS_CHANGED";
+ break;
+ case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED:
+ envp[idx++] = "SDEV_UA=THIN_PROVISIONING_SOFT_THRESHOLD_REACHED";
+ break;
+ case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED:
+ envp[idx++] = "SDEV_UA=MODE_PARAMETERS_CHANGED";
+ break;
+ case SDEV_EVT_LUN_CHANGE_REPORTED:
+ envp[idx++] = "SDEV_UA=REPORTED_LUNS_DATA_HAS_CHANGED";
+ break;
default:
/* do nothing */
break;
@@ -2126,10 +2208,15 @@ static void scsi_evt_emit(struct scsi_device *sdev, struct scsi_event *evt)
void scsi_evt_thread(struct work_struct *work)
{
struct scsi_device *sdev;
+ enum scsi_device_event evt_type;
LIST_HEAD(event_list);
sdev = container_of(work, struct scsi_device, event_work);
+ for (evt_type = SDEV_EVT_FIRST; evt_type <= SDEV_EVT_LAST; evt_type++)
+ if (test_and_clear_bit(evt_type, sdev->pending_events))
+ sdev_evt_send_simple(sdev, evt_type, GFP_KERNEL);
+
while (1) {
struct scsi_event *evt;
struct list_head *this, *tmp;
@@ -2199,6 +2286,11 @@ struct scsi_event *sdev_evt_alloc(enum scsi_device_event evt_type,
/* evt_type-specific initialization, if any */
switch (evt_type) {
case SDEV_EVT_MEDIA_CHANGE:
+ case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
+ case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
+ case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED:
+ case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED:
+ case SDEV_EVT_LUN_CHANGE_REPORTED:
default:
/* do nothing */
break;
@@ -2270,10 +2362,14 @@ EXPORT_SYMBOL(scsi_device_quiesce);
*
* Must be called with user context, may sleep.
*/
-void
-scsi_device_resume(struct scsi_device *sdev)
+void scsi_device_resume(struct scsi_device *sdev)
{
- if(scsi_device_set_state(sdev, SDEV_RUNNING))
+ /* check if the device state was mutated prior to resume, and if
+ * so assume the state is being managed elsewhere (for example
+ * device deleted during suspend)
+ */
+ if (sdev->sdev_state != SDEV_QUIESCE ||
+ scsi_device_set_state(sdev, SDEV_RUNNING))
return;
scsi_run_queue(sdev->request_queue);
}
@@ -2320,7 +2416,6 @@ EXPORT_SYMBOL(scsi_target_resume);
* (which must be a legal transition). When the device is in this
* state, all commands are deferred until the scsi lld reenables
* the device with scsi_device_unblock or device_block_tmo fires.
- * This routine assumes the host_lock is held on entry.
*/
int
scsi_internal_device_block(struct scsi_device *sdev)
@@ -2330,8 +2425,12 @@ scsi_internal_device_block(struct scsi_device *sdev)
int err = 0;
err = scsi_device_set_state(sdev, SDEV_BLOCK);
- if (err)
- return err;
+ if (err) {
+ err = scsi_device_set_state(sdev, SDEV_CREATED_BLOCK);
+
+ if (err)
+ return err;
+ }
/*
* The device has transitioned to SDEV_BLOCK. Stop the
@@ -2349,6 +2448,7 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_block);
/**
* scsi_internal_device_unblock - resume a device after a block request
* @sdev: device to resume
+ * @new_state: state to set devices to after unblocking
*
* Called by scsi lld's or the midlayer to restart the device queue
* for the previously suspended scsi device. Called from interrupt or
@@ -2358,24 +2458,32 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_block);
*
* Notes:
* This routine transitions the device to the SDEV_RUNNING state
- * (which must be a legal transition) allowing the midlayer to
- * goose the queue for this device. This routine assumes the
- * host_lock is held upon entry.
+ * or to one of the offline states (which must be a legal transition)
+ * allowing the midlayer to goose the queue for this device.
*/
int
-scsi_internal_device_unblock(struct scsi_device *sdev)
+scsi_internal_device_unblock(struct scsi_device *sdev,
+ enum scsi_device_state new_state)
{
struct request_queue *q = sdev->request_queue;
- int err;
unsigned long flags;
-
- /*
- * Try to transition the scsi device to SDEV_RUNNING
- * and goose the device queue if successful.
+
+ /*
+ * Try to transition the scsi device to SDEV_RUNNING or one of the
+ * offlined states and goose the device queue if successful.
*/
- err = scsi_device_set_state(sdev, SDEV_RUNNING);
- if (err)
- return err;
+ if ((sdev->sdev_state == SDEV_BLOCK) ||
+ (sdev->sdev_state == SDEV_TRANSPORT_OFFLINE))
+ sdev->sdev_state = new_state;
+ else if (sdev->sdev_state == SDEV_CREATED_BLOCK) {
+ if (new_state == SDEV_TRANSPORT_OFFLINE ||
+ new_state == SDEV_OFFLINE)
+ sdev->sdev_state = new_state;
+ else
+ sdev->sdev_state = SDEV_CREATED;
+ } else if (sdev->sdev_state != SDEV_CANCEL &&
+ sdev->sdev_state != SDEV_OFFLINE)
+ return -EINVAL;
spin_lock_irqsave(q->queue_lock, flags);
blk_start_queue(q);
@@ -2414,26 +2522,26 @@ EXPORT_SYMBOL_GPL(scsi_target_block);
static void
device_unblock(struct scsi_device *sdev, void *data)
{
- scsi_internal_device_unblock(sdev);
+ scsi_internal_device_unblock(sdev, *(enum scsi_device_state *)data);
}
static int
target_unblock(struct device *dev, void *data)
{
if (scsi_is_target_device(dev))
- starget_for_each_device(to_scsi_target(dev), NULL,
+ starget_for_each_device(to_scsi_target(dev), data,
device_unblock);
return 0;
}
void
-scsi_target_unblock(struct device *dev)
+scsi_target_unblock(struct device *dev, enum scsi_device_state new_state)
{
if (scsi_is_target_device(dev))
- starget_for_each_device(to_scsi_target(dev), NULL,
+ starget_for_each_device(to_scsi_target(dev), &new_state,
device_unblock);
else
- device_for_each_child(dev, NULL, target_unblock);
+ device_for_each_child(dev, &new_state, target_unblock);
}
EXPORT_SYMBOL_GPL(scsi_target_unblock);
@@ -2466,7 +2574,7 @@ void *scsi_kmap_atomic_sg(struct scatterlist *sgl, int sg_count,
if (unlikely(i == sg_count)) {
printk(KERN_ERR "%s: Bytes in sg: %zu, requested offset %zu, "
"elements %d\n",
- __FUNCTION__, sg_len, *offset, sg_count);
+ __func__, sg_len, *offset, sg_count);
WARN_ON(1);
return NULL;
}
@@ -2483,7 +2591,7 @@ void *scsi_kmap_atomic_sg(struct scatterlist *sgl, int sg_count,
if (*len > sg_len)
*len = sg_len;
- return kmap_atomic(page, KM_BIO_SRC_IRQ);
+ return kmap_atomic(page);
}
EXPORT_SYMBOL(scsi_kmap_atomic_sg);
@@ -2493,6 +2601,20 @@ EXPORT_SYMBOL(scsi_kmap_atomic_sg);
*/
void scsi_kunmap_atomic_sg(void *virt)
{
- kunmap_atomic(virt, KM_BIO_SRC_IRQ);
+ kunmap_atomic(virt);
}
EXPORT_SYMBOL(scsi_kunmap_atomic_sg);
+
+void sdev_disable_disk_events(struct scsi_device *sdev)
+{
+ atomic_inc(&sdev->disk_events_disable_depth);
+}
+EXPORT_SYMBOL(sdev_disable_disk_events);
+
+void sdev_enable_disk_events(struct scsi_device *sdev)
+{
+ if (WARN_ON_ONCE(atomic_read(&sdev->disk_events_disable_depth) <= 0))
+ return;
+ atomic_dec(&sdev->disk_events_disable_depth);
+}
+EXPORT_SYMBOL(sdev_enable_disk_events);