9 files changed, 83 insertions, 57 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index e9754dc98ec4..775c8516abf5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -38,7 +38,7 @@ static int __make_request(struct request_queue *q, struct bio *bio);
 /*
  * For the allocated request tables
  */
-struct kmem_cache *request_cachep;
+static struct kmem_cache *request_cachep;
 
 /*
  * For queue allocation
@@ -127,6 +127,7 @@ void rq_init(struct request_queue *q, struct request *rq)
         rq->nr_hw_segments = 0;
         rq->ioprio = 0;
         rq->special = NULL;
+        rq->raw_data_len = 0;
         rq->buffer = NULL;
         rq->tag = -1;
         rq->errors = 0;
@@ -2015,6 +2016,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
         rq->hard_cur_sectors = rq->current_nr_sectors;
         rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
         rq->buffer = bio_data(bio);
+        rq->raw_data_len = bio->bi_size;
         rq->data_len = bio->bi_size;
 
         rq->bio = rq->biotail = bio;
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 80245dc30c75..e34df7c9fc36 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -17,17 +17,13 @@ static struct kmem_cache *iocontext_cachep;
 
 static void cfq_dtor(struct io_context *ioc)
 {
-        struct cfq_io_context *cic[1];
-        int r;
+        if (!hlist_empty(&ioc->cic_list)) {
+                struct cfq_io_context *cic;
 
-        /*
-         * We don't have a specific key to lookup with, so use the gang
-         * lookup to just retrieve the first item stored. The cfq exit
-         * function will iterate the full tree, so any member will do.
-         */
-        r = radix_tree_gang_lookup(&ioc->radix_root, (void **) cic, 0, 1);
-        if (r > 0)
-                cic[0]->dtor(ioc);
+                cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+                                                                cic_list);
+                cic->dtor(ioc);
+        }
 }
 
 /*
@@ -57,18 +53,16 @@ EXPORT_SYMBOL(put_io_context);
 
 static void cfq_exit(struct io_context *ioc)
 {
-        struct cfq_io_context *cic[1];
-        int r;
-
         rcu_read_lock();
-        /*
-         * See comment for cfq_dtor()
-         */
-        r = radix_tree_gang_lookup(&ioc->radix_root, (void **) cic, 0, 1);
-        rcu_read_unlock();
 
-        if (r > 0)
-                cic[0]->exit(ioc);
+        if (!hlist_empty(&ioc->cic_list)) {
+                struct cfq_io_context *cic;
+
+                cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+                                                                cic_list);
+                cic->exit(ioc);
+        }
+        rcu_read_unlock();
 }
 
 /* Called by the exitting task */
@@ -105,6 +99,7 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
                 ret->nr_batch_requests = 0; /* because this is 0 */
                 ret->aic = NULL;
                 INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
+                INIT_HLIST_HEAD(&ret->cic_list);
                 ret->ioc_data = NULL;
         }
 
@@ -176,7 +171,7 @@ void copy_io_context(struct io_context **pdst, struct io_context **psrc)
 }
 EXPORT_SYMBOL(copy_io_context);
 
-int __init blk_ioc_init(void)
+static int __init blk_ioc_init(void)
 {
         iocontext_cachep = kmem_cache_create("blkdev_ioc",
                         sizeof(struct io_context), 0, SLAB_PANIC, NULL);
diff --git a/block/blk-map.c b/block/blk-map.c
index 955d75c1a58f..09f7fd0bcb73 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -19,6 +19,7 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
                 rq->biotail->bi_next = bio;
                 rq->biotail = bio;
 
+                rq->raw_data_len += bio->bi_size;
                 rq->data_len += bio->bi_size;
         }
         return 0;
@@ -139,10 +140,29 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
                 ubuf += ret;
         }
 
+        /*
+         * __blk_rq_map_user() copies the buffers if starting address
+         * or length isn't aligned.  As the copied buffer is always
+         * page aligned, we know that there's enough room for padding.
+         * Extend the last bio and update rq->data_len accordingly.
+         *
+         * On unmap, bio_uncopy_user() will use unmodified
+         * bio_map_data pointed to by bio->bi_private.
+         */
+        if (len & queue_dma_alignment(q)) {
+                unsigned int pad_len = (queue_dma_alignment(q) & ~len) + 1;
+                struct bio *bio = rq->biotail;
+
+                bio->bi_io_vec[bio->bi_vcnt - 1].bv_len += pad_len;
+                bio->bi_size += pad_len;
+                rq->data_len += pad_len;
+        }
+
         rq->buffer = rq->data = NULL;
         return 0;
 unmap_rq:
         blk_rq_unmap_user(bio);
+        rq->bio = NULL;
         return ret;
 }
 EXPORT_SYMBOL(blk_rq_map_user);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index d3b84bbb776a..7506c4fe0264 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -220,7 +220,10 @@ new_segment:
                 bvprv = bvec;
         } /* segments in rq */
 
-        if (q->dma_drain_size) {
+        if (q->dma_drain_size && q->dma_drain_needed(rq)) {
+                if (rq->cmd_flags & REQ_RW)
+                        memset(q->dma_drain_buffer, 0, q->dma_drain_size);
+
                 sg->page_link &= ~0x02;
                 sg = sg_next(sg);
                 sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
@@ -228,6 +231,7 @@ new_segment:
                             ((unsigned long)q->dma_drain_buffer) &
                             (PAGE_SIZE - 1));
                 nsegs++;
+                rq->data_len += q->dma_drain_size;
         }
 
         if (sg)
diff --git a/block/blk-settings.c b/block/blk-settings.c
index c8d0c5724098..9a8ffdd0ce3d 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -296,6 +296,7 @@ EXPORT_SYMBOL(blk_queue_stack_limits);
  * blk_queue_dma_drain - Set up a drain buffer for excess dma.
  *
  * @q:  the request queue for the device
+ * @dma_drain_needed: fn which returns non-zero if drain is necessary
  * @buf:        physically contiguous buffer
  * @size:       size of the buffer in bytes
  *
@@ -315,14 +316,16 @@ EXPORT_SYMBOL(blk_queue_stack_limits);
  * device can support otherwise there won't be room for the drain
  * buffer.
  */
-int blk_queue_dma_drain(struct request_queue *q, void *buf,
-                                unsigned int size)
+extern int blk_queue_dma_drain(struct request_queue *q,
+                               dma_drain_needed_fn *dma_drain_needed,
+                               void *buf, unsigned int size)
 {
         if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
                 return -EINVAL;
         /* make room for appending the drain */
         --q->max_hw_segments;
         --q->max_phys_segments;
+        q->dma_drain_needed = dma_drain_needed;
         q->dma_drain_buffer = buf;
         q->dma_drain_size = size;
 
@@ -386,7 +389,7 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
 }
 EXPORT_SYMBOL(blk_queue_update_dma_alignment);
 
-int __init blk_settings_init(void)
+static int __init blk_settings_init(void)
 {
         blk_max_low_pfn = max_low_pfn - 1;
         blk_max_pfn = max_pfn - 1;
diff --git a/block/bsg.c b/block/bsg.c
index 8917c5174dc2..7f3c09549e4b 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -437,14 +437,14 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
         }
 
         if (rq->next_rq) {
-                hdr->dout_resid = rq->data_len;
-                hdr->din_resid = rq->next_rq->data_len;
+                hdr->dout_resid = rq->raw_data_len;
+                hdr->din_resid = rq->next_rq->raw_data_len;
                 blk_rq_unmap_user(bidi_bio);
                 blk_put_request(rq->next_rq);
         } else if (rq_data_dir(rq) == READ)
-                hdr->din_resid = rq->data_len;
+                hdr->din_resid = rq->raw_data_len;
         else
-                hdr->dout_resid = rq->data_len;
+                hdr->dout_resid = rq->raw_data_len;
 
         /*
          * If the request generated a negative error number, return it
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ca198e61fa65..0f962ecae91f 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1145,38 +1145,19 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 /*
  * Call func for each cic attached to this ioc. Returns number of cic's seen.
  */
-#define CIC_GANG_NR     16
 static unsigned int
 call_for_each_cic(struct io_context *ioc,
                   void (*func)(struct io_context *, struct cfq_io_context *))
 {
-        struct cfq_io_context *cics[CIC_GANG_NR];
-        unsigned long index = 0;
-        unsigned int called = 0;
-        int nr;
+        struct cfq_io_context *cic;
+        struct hlist_node *n;
+        int called = 0;
 
         rcu_read_lock();
-
-        do {
-                int i;
-
-                /*
-                 * Perhaps there's a better way - this just gang lookups from
-                 * 0 to the end, restarting after each CIC_GANG_NR from the
-                 * last key + 1.
-                 */
-                nr = radix_tree_gang_lookup(&ioc->radix_root, (void **) cics,
-                                                index, CIC_GANG_NR);
-                if (!nr)
-                        break;
-
-                called += nr;
-                index = 1 + (unsigned long) cics[nr - 1]->key;
-
-                for (i = 0; i < nr; i++)
-                        func(ioc, cics[i]);
-        } while (nr == CIC_GANG_NR);
-
+        hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list) {
+                func(ioc, cic);
+                called++;
+        }
         rcu_read_unlock();
 
         return called;
@@ -1190,6 +1171,7 @@ static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
 
         spin_lock_irqsave(&ioc->lock, flags);
         radix_tree_delete(&ioc->radix_root, cic->dead_key);
+        hlist_del_rcu(&cic->cic_list);
         spin_unlock_irqrestore(&ioc->lock, flags);
 
         kmem_cache_free(cfq_ioc_pool, cic);
@@ -1280,6 +1262,7 @@ cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
         if (cic) {
                 cic->last_end_request = jiffies;
                 INIT_LIST_HEAD(&cic->queue_list);
+                INIT_HLIST_NODE(&cic->cic_list);
                 cic->dtor = cfq_free_io_context;
                 cic->exit = cfq_exit_io_context;
                 elv_ioc_count_inc(ioc_count);
@@ -1501,6 +1484,7 @@ cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc,
                 rcu_assign_pointer(ioc->ioc_data, NULL);
 
         radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
+        hlist_del_rcu(&cic->cic_list);
         spin_unlock_irqrestore(&ioc->lock, flags);
 
         cfq_cic_free(cic);
@@ -1561,6 +1545,8 @@ static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
                 spin_lock_irqsave(&ioc->lock, flags);
                 ret = radix_tree_insert(&ioc->radix_root,
                                                 (unsigned long) cfqd, cic);
+                if (!ret)
+                        hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list);
                 spin_unlock_irqrestore(&ioc->lock, flags);
 
                 radix_tree_preload_end();
diff --git a/block/elevator.c b/block/elevator.c
index bafbae0344d3..88318c383608 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -134,6 +134,21 @@ static struct elevator_type *elevator_get(const char *name)
         spin_lock(&elv_list_lock);
 
         e = elevator_find(name);
+        if (!e) {
+                char elv[ELV_NAME_MAX + strlen("-iosched")];
+
+                spin_unlock(&elv_list_lock);
+
+                if (!strcmp(name, "anticipatory"))
+                        sprintf(elv, "as-iosched");
+                else
+                        sprintf(elv, "%s-iosched", name);
+
+                request_module(elv);
+                spin_lock(&elv_list_lock);
+                e = elevator_find(name);
+        }
+
         if (e && !try_module_get(e->elevator_owner))
                 e = NULL;
 
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 9675b34638d4..e993cac4911d 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -266,7 +266,7 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
         hdr->info = 0;
         if (hdr->masked_status || hdr->host_status || hdr->driver_status)
                 hdr->info |= SG_INFO_CHECK;
-        hdr->resid = rq->data_len;
+        hdr->resid = rq->raw_data_len;
         hdr->sb_len_wr = 0;
 
         if (rq->sense_len && hdr->sbp) {
@@ -528,6 +528,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
         rq = blk_get_request(q, WRITE, __GFP_WAIT);
         rq->cmd_type = REQ_TYPE_BLOCK_PC;
         rq->data = NULL;
+        rq->raw_data_len = 0;
         rq->data_len = 0;
         rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
         memset(rq->cmd, 0, sizeof(rq->cmd));