*/
#include <linux/bio.h>
+#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/completion.h>
#include <linux/kernel.h>
#define SG_MEMPOOL_NR ARRAY_SIZE(scsi_sg_pools)
#define SG_MEMPOOL_SIZE 2
-/*
- * The maximum number of SG segments that we will put inside a scatterlist
- * (unless chaining is used). Should ideally fit inside a single page, to
- * avoid a higher order allocation.
- */
-#define SCSI_MAX_SG_SEGMENTS 128
-
struct scsi_host_sg_pool {
size_t size;
char *name;
mempool_t *pool;
};
-#define SP(x) { x, "sgpool-" #x }
+#define SP(x) { x, "sgpool-" __stringify(x) }
+#if (SCSI_MAX_SG_SEGMENTS < 32)
+#error SCSI_MAX_SG_SEGMENTS is too small (must be 32 or greater)
+#endif
static struct scsi_host_sg_pool scsi_sg_pools[] = {
SP(8),
SP(16),
-#if (SCSI_MAX_SG_SEGMENTS > 16)
- SP(32),
#if (SCSI_MAX_SG_SEGMENTS > 32)
- SP(64),
+ SP(32),
#if (SCSI_MAX_SG_SEGMENTS > 64)
+ SP(64),
+#if (SCSI_MAX_SG_SEGMENTS > 128)
SP(128),
+#if (SCSI_MAX_SG_SEGMENTS > 256)
+#error SCSI_MAX_SG_SEGMENTS is too large (256 MAX)
#endif
#endif
#endif
+#endif
+ SP(SCSI_MAX_SG_SEGMENTS)
};
#undef SP
+struct kmem_cache *scsi_sdb_cache;
+
static void scsi_run_queue(struct request_queue *q);
/*
{
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;
* 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:
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
*/
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->data_len > 0 && req->data_len <= bufflen))
+ memset(buffer + (bufflen - req->data_len), 0, req->data_len);
+
ret = req->errors;
out:
blk_put_request(req);
page = sg_page(sg);
off = sg->offset;
len = sg->length;
- data_len += len;
while (len > 0 && data_len > 0) {
/*
static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
{
cmd->serial_number = 0;
- cmd->resid = 0;
+ 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);
spin_unlock_irqrestore(shost->host_lock, flags);
}
+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);
+}
+
/*
* Function: scsi_run_queue()
*
*/
static void scsi_run_queue(struct request_queue *q)
{
- struct scsi_device *sdev = q->queuedata;
+ struct scsi_device *starved_head = NULL, *sdev = q->queuedata;
struct Scsi_Host *shost = sdev->host;
unsigned long flags;
!shost->host_blocked && !shost->host_self_blocked &&
!((shost->can_queue > 0) &&
(shost->host_busy >= shost->can_queue))) {
+
+ int flagset;
+
/*
* As long as shost is accepting commands and we have
* starved queues, call blk_run_queue. scsi_request_fn
*/
sdev = list_entry(shost->starved_list.next,
struct scsi_device, starved_entry);
- list_del_init(&sdev->starved_entry);
- spin_unlock_irqrestore(shost->host_lock, flags);
+ /*
+ * The *queue_ready functions can add a device back onto the
+ * starved list's tail, so we must check for a infinite loop.
+ */
+ if (sdev == starved_head)
+ break;
+ if (!starved_head)
+ starved_head = sdev;
+ if (scsi_target_is_busy(scsi_target(sdev))) {
+ list_move_tail(&sdev->starved_entry,
+ &shost->starved_list);
+ continue;
+ }
- 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);
+ list_del_init(&sdev->starved_entry);
+ spin_unlock(shost->host_lock);
+
+ spin_lock(sdev->request_queue->queue_lock);
+ flagset = test_bit(QUEUE_FLAG_REENTER, &q->queue_flags) &&
+ !test_bit(QUEUE_FLAG_REENTER,
+ &sdev->request_queue->queue_flags);
+ if (flagset)
+ queue_flag_set(QUEUE_FLAG_REENTER, sdev->request_queue);
+ __blk_run_queue(sdev->request_queue);
+ if (flagset)
+ queue_flag_clear(QUEUE_FLAG_REENTER, sdev->request_queue);
+ spin_unlock(sdev->request_queue->queue_lock);
- 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;
+ spin_lock(shost->host_lock);
}
spin_unlock_irqrestore(shost->host_lock, flags);
return NULL;
}
-/*
- * Like SCSI_MAX_SG_SEGMENTS, but for archs that have sg chaining. This limit
- * is totally arbitrary, a setting of 2048 will get you at least 8mb ios.
- */
-#define SCSI_MAX_SG_CHAIN_SEGMENTS 2048
-
static inline unsigned int scsi_sgtable_index(unsigned short nents)
{
unsigned int index;
- switch (nents) {
- case 1 ... 8:
+ BUG_ON(nents > SCSI_MAX_SG_SEGMENTS);
+
+ if (nents <= 8)
index = 0;
- break;
- case 9 ... 16:
- index = 1;
- break;
-#if (SCSI_MAX_SG_SEGMENTS > 16)
- case 17 ... 32:
- index = 2;
- break;
-#if (SCSI_MAX_SG_SEGMENTS > 32)
- case 33 ... 64:
- index = 3;
- break;
-#if (SCSI_MAX_SG_SEGMENTS > 64)
- case 65 ... 128:
- index = 4;
- break;
-#endif
-#endif
-#endif
- default:
- printk(KERN_ERR "scsi: bad segment count=%d\n", nents);
- BUG();
- }
+ else
+ index = get_count_order(nents) - 3;
return index;
}
-struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask)
+static void scsi_sg_free(struct scatterlist *sgl, unsigned int nents)
{
struct scsi_host_sg_pool *sgp;
- struct scatterlist *sgl, *prev, *ret;
- unsigned int index;
- int this, left;
-
- BUG_ON(!cmd->use_sg);
- left = cmd->use_sg;
- ret = prev = NULL;
- do {
- this = left;
- if (this > SCSI_MAX_SG_SEGMENTS) {
- this = SCSI_MAX_SG_SEGMENTS - 1;
- index = SG_MEMPOOL_NR - 1;
- } else
- index = scsi_sgtable_index(this);
-
- left -= this;
-
- sgp = scsi_sg_pools + index;
-
- sgl = mempool_alloc(sgp->pool, gfp_mask);
- if (unlikely(!sgl))
- goto enomem;
+ sgp = scsi_sg_pools + scsi_sgtable_index(nents);
+ mempool_free(sgl, sgp->pool);
+}
- sg_init_table(sgl, sgp->size);
+static struct scatterlist *scsi_sg_alloc(unsigned int nents, gfp_t gfp_mask)
+{
+ struct scsi_host_sg_pool *sgp;
- /*
- * first loop through, set initial index and return value
- */
- if (!ret)
- ret = sgl;
+ sgp = scsi_sg_pools + scsi_sgtable_index(nents);
+ return mempool_alloc(sgp->pool, gfp_mask);
+}
- /*
- * chain previous sglist, if any. we know the previous
- * sglist must be the biggest one, or we would not have
- * ended up doing another loop.
- */
- if (prev)
- sg_chain(prev, SCSI_MAX_SG_SEGMENTS, sgl);
+static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents,
+ gfp_t gfp_mask)
+{
+ int ret;
- /*
- * if we have nothing left, mark the last segment as
- * end-of-list
- */
- if (!left)
- sg_mark_end(&sgl[this - 1]);
+ BUG_ON(!nents);
- /*
- * don't allow subsequent mempool allocs to sleep, it would
- * violate the mempool principle.
- */
- gfp_mask &= ~__GFP_WAIT;
- gfp_mask |= __GFP_HIGH;
- prev = sgl;
- } while (left);
+ ret = __sg_alloc_table(&sdb->table, nents, SCSI_MAX_SG_SEGMENTS,
+ gfp_mask, scsi_sg_alloc);
+ if (unlikely(ret))
+ __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS,
+ scsi_sg_free);
- /*
- * ->use_sg may get modified after dma mapping has potentially
- * shrunk the number of segments, so keep a copy of it for free.
- */
- cmd->__use_sg = cmd->use_sg;
return ret;
-enomem:
- if (ret) {
- /*
- * Free entries chained off ret. Since we were trying to
- * allocate another sglist, we know that all entries are of
- * the max size.
- */
- sgp = scsi_sg_pools + SG_MEMPOOL_NR - 1;
- prev = ret;
- ret = &ret[SCSI_MAX_SG_SEGMENTS - 1];
-
- while ((sgl = sg_chain_ptr(ret)) != NULL) {
- ret = &sgl[SCSI_MAX_SG_SEGMENTS - 1];
- mempool_free(sgl, sgp->pool);
- }
-
- mempool_free(prev, sgp->pool);
- }
- return NULL;
}
-EXPORT_SYMBOL(scsi_alloc_sgtable);
-
-void scsi_free_sgtable(struct scsi_cmnd *cmd)
+static void scsi_free_sgtable(struct scsi_data_buffer *sdb)
{
- struct scatterlist *sgl = cmd->request_buffer;
- struct scsi_host_sg_pool *sgp;
-
- /*
- * if this is the biggest size sglist, check if we have
- * chained parts we need to free
- */
- if (cmd->__use_sg > SCSI_MAX_SG_SEGMENTS) {
- unsigned short this, left;
- struct scatterlist *next;
- unsigned int index;
-
- left = cmd->__use_sg - (SCSI_MAX_SG_SEGMENTS - 1);
- next = sg_chain_ptr(&sgl[SCSI_MAX_SG_SEGMENTS - 1]);
- while (left && next) {
- sgl = next;
- this = left;
- if (this > SCSI_MAX_SG_SEGMENTS) {
- this = SCSI_MAX_SG_SEGMENTS - 1;
- index = SG_MEMPOOL_NR - 1;
- } else
- index = scsi_sgtable_index(this);
-
- left -= this;
-
- sgp = scsi_sg_pools + index;
-
- if (left)
- next = sg_chain_ptr(&sgl[sgp->size - 1]);
-
- mempool_free(sgl, sgp->pool);
- }
-
- /*
- * Restore original, will be freed below
- */
- sgl = cmd->request_buffer;
- sgp = scsi_sg_pools + SG_MEMPOOL_NR - 1;
- } else
- sgp = scsi_sg_pools + scsi_sgtable_index(cmd->__use_sg);
-
- mempool_free(sgl, sgp->pool);
+ __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free);
}
-EXPORT_SYMBOL(scsi_free_sgtable);
-
/*
* Function: scsi_release_buffers()
*
* the scatter-gather table, and potentially any bounce
* buffers.
*/
-static void scsi_release_buffers(struct scsi_cmnd *cmd)
+void scsi_release_buffers(struct scsi_cmnd *cmd)
+{
+ if (cmd->sdb.table.nents)
+ scsi_free_sgtable(&cmd->sdb);
+
+ memset(&cmd->sdb, 0, sizeof(cmd->sdb));
+
+ if (scsi_bidi_cmnd(cmd)) {
+ struct scsi_data_buffer *bidi_sdb =
+ cmd->request->next_rq->special;
+ scsi_free_sgtable(bidi_sdb);
+ kmem_cache_free(scsi_sdb_cache, bidi_sdb);
+ cmd->request->next_rq->special = NULL;
+ }
+
+ if (scsi_prot_sg_count(cmd))
+ scsi_free_sgtable(cmd->prot_sdb);
+}
+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.
+ */
+static void scsi_end_bidi_request(struct scsi_cmnd *cmd)
{
- if (cmd->use_sg)
- scsi_free_sgtable(cmd);
+ struct request *req = cmd->request;
+ unsigned int dlen = req->data_len;
+ unsigned int next_dlen = req->next_rq->data_len;
+
+ req->data_len = scsi_out(cmd)->resid;
+ req->next_rq->data_len = scsi_in(cmd)->resid;
+
+ /* The req and req->next_rq have not been completed */
+ BUG_ON(blk_end_bidi_request(req, 0, dlen, next_dlen));
+
+ scsi_release_buffers(cmd);
/*
- * Zero these out. They now point to freed memory, and it is
- * dangerous to hang onto the pointers.
+ * This will goose the queue request function at the end, so we don't
+ * need to worry about launching another command.
*/
- cmd->request_buffer = NULL;
- cmd->request_bufflen = 0;
+ scsi_next_command(cmd);
}
/*
void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
{
int result = cmd->result;
- int this_count = cmd->request_bufflen;
+ int this_count;
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;
- scsi_release_buffers(cmd);
-
if (result) {
sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
if (sense_valid)
if (blk_pc_request(req)) { /* SG_IO ioctl from block level */
req->errors = result;
if (result) {
- clear_errors = 0;
if (sense_valid && req->sense) {
/*
* SG_IO wants current and deferred errors
memcpy(req->sense, cmd->sense_buffer, len);
req->sense_len = len;
}
+ if (!sense_deferred)
+ error = -EIO;
+ }
+ if (scsi_bidi_cmnd(cmd)) {
+ /* will also release_buffers */
+ scsi_end_bidi_request(cmd);
+ return;
}
- req->data_len = cmd->resid;
+ req->data_len = scsi_get_resid(cmd);
}
+ BUG_ON(blk_bidi_rq(req)); /* bidi not support for !blk_pc_request yet */
+ scsi_release_buffers(cmd);
+
/*
* Next deal with any sectors which we were able to correctly
* handle.
SCSI_LOG_HLCOMPLETE(1, printk("%ld sectors total, "
"%d bytes done.\n",
req->nr_sectors, good_bytes));
- SCSI_LOG_HLCOMPLETE(1, printk("use_sg is %d\n", cmd->use_sg));
-
- if (clear_errors)
- req->errors = 0;
/* A number of bytes were successfully read. If there
* are leftovers and there is some kind of error
* (result != 0), retry the rest.
*/
- if (scsi_end_request(cmd, 0, good_bytes, result == 0) == NULL)
+ if (scsi_end_request(cmd, error, good_bytes, result == 0) == NULL)
return;
+ this_count = blk_rq_bytes(req);
/* good_bytes = 0, or (inclusive) there were leftovers and
* result = 0, so scsi_end_request couldn't retry.
* 6-byte command.
*/
scsi_requeue_command(q, cmd);
- return;
- } else {
+ } else if (sshdr.asc == 0x10) /* DIX */
+ scsi_end_request(cmd, -EIO, this_count, 0);
+ else
scsi_end_request(cmd, -EIO, this_count, 1);
+ return;
+ case ABORTED_COMMAND:
+ if (sshdr.asc == 0x10) { /* DIF */
+ scsi_end_request(cmd, -EIO, this_count, 0);
return;
}
break;
scsi_end_request(cmd, -EIO, this_count, !result);
}
-/*
- * Function: scsi_init_io()
- *
- * Purpose: SCSI I/O initialize function.
- *
- * Arguments: cmd - Command descriptor we wish to initialize
- *
- * Returns: 0 on success
- * BLKPREP_DEFER if the failure is retryable
- */
-static int scsi_init_io(struct scsi_cmnd *cmd)
+static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
+ gfp_t gfp_mask)
{
- struct request *req = cmd->request;
- int count;
-
- /*
- * We used to not use scatter-gather for single segment request,
- * but now we do (it makes highmem I/O easier to support without
- * kmapping pages)
- */
- cmd->use_sg = req->nr_phys_segments;
+ int count;
/*
* If sg table allocation fails, requeue request later.
*/
- cmd->request_buffer = scsi_alloc_sgtable(cmd, GFP_ATOMIC);
- if (unlikely(!cmd->request_buffer)) {
- scsi_unprep_request(req);
+ if (unlikely(scsi_alloc_sgtable(sdb, req->nr_phys_segments,
+ gfp_mask))) {
return BLKPREP_DEFER;
}
req->buffer = NULL;
- if (blk_pc_request(req))
- cmd->request_bufflen = req->data_len;
- else
- cmd->request_bufflen = req->nr_sectors << 9;
/*
* Next, walk the list, and fill in the addresses and sizes of
* each segment.
*/
- count = blk_rq_map_sg(req->q, req, cmd->request_buffer);
- BUG_ON(count > cmd->use_sg);
- cmd->use_sg = count;
+ 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;
return BLKPREP_OK;
}
+/*
+ * Function: scsi_init_io()
+ *
+ * Purpose: SCSI I/O initialize function.
+ *
+ * Arguments: cmd - Command descriptor we wish to initialize
+ *
+ * Returns: 0 on success
+ * BLKPREP_DEFER if the failure is retryable
+ * BLKPREP_KILL if the failure is fatal
+ */
+int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
+{
+ int error = scsi_init_sgtable(cmd->request, &cmd->sdb, gfp_mask);
+ if (error)
+ goto err_exit;
+
+ if (blk_bidi_rq(cmd->request)) {
+ struct scsi_data_buffer *bidi_sdb = kmem_cache_zalloc(
+ 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);
+ if (error)
+ goto err_exit;
+ }
+
+ if (blk_integrity_rq(cmd->request)) {
+ struct scsi_data_buffer *prot_sdb = cmd->prot_sdb;
+ int ivecs, count;
+
+ BUG_ON(prot_sdb == NULL);
+ ivecs = blk_rq_count_integrity_sg(cmd->request);
+
+ if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask)) {
+ error = BLKPREP_DEFER;
+ goto err_exit;
+ }
+
+ count = blk_rq_map_integrity_sg(cmd->request,
+ prot_sdb->table.sgl);
+ BUG_ON(unlikely(count > ivecs));
+
+ 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);
+
+ return error;
+}
+EXPORT_SYMBOL(scsi_init_io);
+
static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev,
struct request *req)
{
cmd->tag = req->tag;
cmd->request = req;
+ cmd->cmnd = req->cmd;
+
return cmd;
}
BUG_ON(!req->nr_phys_segments);
- ret = scsi_init_io(cmd);
+ ret = scsi_init_io(cmd, GFP_ATOMIC);
if (unlikely(ret))
return ret;
} else {
BUG_ON(req->data_len);
BUG_ON(req->data);
- cmd->request_bufflen = 0;
- cmd->request_buffer = NULL;
- cmd->use_sg = 0;
+ 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)
cmd->sc_data_direction = DMA_NONE;
cmd->transfersize = req->data_len;
cmd->allowed = req->retries;
- cmd->timeout_per_command = req->timeout;
return BLKPREP_OK;
}
EXPORT_SYMBOL(scsi_setup_blk_pc_cmnd);
if (ret != BLKPREP_OK)
return ret;
+
+ if (unlikely(sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh
+ && sdev->scsi_dh_data->scsi_dh->prep_fn)) {
+ ret = sdev->scsi_dh_data->scsi_dh->prep_fn(sdev, req);
+ if (ret != BLKPREP_OK)
+ return ret;
+ }
+
/*
* Filesystem requests must transfer data.
*/
if (unlikely(!cmd))
return BLKPREP_DEFER;
- return scsi_init_io(cmd);
+ memset(cmd->cmnd, 0, BLK_MAX_CDB);
+ return scsi_init_io(cmd, GFP_ATOMIC);
}
EXPORT_SYMBOL(scsi_setup_fs_cmnd);
break;
case SDEV_QUIESCE:
case SDEV_BLOCK:
+ case SDEV_CREATED_BLOCK:
/*
* If the devices is blocked we defer normal commands.
*/
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 {
+ blk_plug_device(sdev->request_queue);
+ return 0;
+ }
+ }
+
+ if (scsi_target_is_busy(starget)) {
+ if (list_empty(&sdev->starved_entry)) {
+ list_add_tail(&sdev->starved_entry,
+ &shost->starved_list);
+ return 0;
+ }
+ }
+
+ /* We're OK to process the command, so we can't be starved */
+ if (!list_empty(&sdev->starved_entry))
+ list_del_init(&sdev->starved_entry);
+ return 1;
+}
+
/*
* scsi_host_queue_ready: if we can send requests to shost, return 1 else
* return 0. We must end up running the queue again whenever 0 is
printk("scsi%d unblocking host at zero depth\n",
shost->host_no));
} else {
- blk_plug_device(q);
return 0;
}
}
{
struct scsi_cmnd *cmd = req->special;
struct scsi_device *sdev = cmd->device;
+ struct scsi_target *starget = scsi_target(sdev);
struct Scsi_Host *shost = sdev->host;
blkdev_dequeue_request(req);
if (unlikely(cmd == NULL)) {
printk(KERN_CRIT "impossible request in %s.\n",
- __FUNCTION__);
+ __func__);
BUG();
}
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);
+ /*
+ * Set the serial numbers back to zero
+ */
+ cmd->serial_number = 0;
+
+ 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)) {
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++;
/*
request_fn_proc *request_fn)
{
struct request_queue *q;
+ struct device *dev = shost->shost_gendev.parent;
q = blk_init_queue(request_fn, NULL);
if (!q)
* this limit is imposed by hardware restrictions
*/
blk_queue_max_hw_segments(q, shost->sg_tablesize);
-
- /*
- * In the future, sg chaining support will be mandatory and this
- * ifdef can then go away. Right now we don't have all archs
- * converted, so better keep it safe.
- */
-#ifdef ARCH_HAS_SG_CHAIN
- if (shost->use_sg_chaining)
- blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS);
- else
- blk_queue_max_phys_segments(q, SCSI_MAX_SG_SEGMENTS);
-#else
- blk_queue_max_phys_segments(q, SCSI_MAX_SG_SEGMENTS);
-#endif
+ blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS);
blk_queue_max_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);
+
+ blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
+ /* New queue, no concurrency on queue_flags */
if (!shost->use_clustering)
- clear_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+ queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
/*
* set a reasonable default alignment on word boundaries: the
blk_queue_prep_rq(q, scsi_prep_fn);
blk_queue_softirq_done(q, scsi_softirq_done);
+ blk_queue_rq_timed_out(q, scsi_times_out);
return q;
}
return -ENOMEM;
}
+ 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");
+ 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);
if (!sgp->slab) {
printk(KERN_ERR "SCSI: can't init sg slab %s\n",
sgp->name);
+ goto cleanup_sdb;
}
sgp->pool = mempool_create_slab_pool(SG_MEMPOOL_SIZE,
if (!sgp->pool) {
printk(KERN_ERR "SCSI: can't init sg mempool %s\n",
sgp->name);
+ goto cleanup_sdb;
}
}
return 0;
+
+cleanup_sdb:
+ for (i = 0; i < SG_MEMPOOL_NR; i++) {
+ struct scsi_host_sg_pool *sgp = scsi_sg_pools + i;
+ if (sgp->pool)
+ mempool_destroy(sgp->pool);
+ if (sgp->slab)
+ kmem_cache_destroy(sgp->slab);
+ }
+ kmem_cache_destroy(scsi_sdb_cache);
+cleanup_io_context:
+ kmem_cache_destroy(scsi_io_context_cache);
+
+ return -ENOMEM;
}
void scsi_exit_queue(void)
int i;
kmem_cache_destroy(scsi_io_context_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;
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_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;
{
unsigned long flags;
+#if 0
+ /* FIXME: currently this check eliminates all media change events
+ * for polled devices. Need to update to discriminate between AN
+ * and polled events */
if (!test_bit(evt->evt_type, sdev->supported_events)) {
kfree(evt);
return;
}
+#endif
spin_lock_irqsave(&sdev->list_lock, flags);
list_add_tail(&evt->node, &sdev->event_list);
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
* and goose the device queue if successful.
*/
err = scsi_device_set_state(sdev, SDEV_RUNNING);
- if (err)
- return err;
+ if (err) {
+ err = scsi_device_set_state(sdev, SDEV_CREATED);
+
+ if (err)
+ return err;
+ }
spin_lock_irqsave(q->queue_lock, flags);
blk_start_queue(q);
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;
}