Merge branch 'master' into next

11 files changed, 270 insertions, 243 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 2d053b584410..c3df30cfb3fc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -257,7 +257,6 @@ void __generic_unplug_device(struct request_queue *q)
 
         q->request_fn(q);
 }
-EXPORT_SYMBOL(__generic_unplug_device);
 
 /**
  * generic_unplug_device - fire a request queue
@@ -325,6 +324,9 @@ EXPORT_SYMBOL(blk_unplug);
 
 static void blk_invoke_request_fn(struct request_queue *q)
 {
+        if (unlikely(blk_queue_stopped(q)))
+                return;
+
         /*
          * one level of recursion is ok and is much faster than kicking
          * the unplug handling
@@ -399,8 +401,13 @@ void blk_sync_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_sync_queue);
 
 /**
- * blk_run_queue - run a single device queue
+ * __blk_run_queue - run a single device queue
  * @q:  The queue to run
+ *
+ * Description:
+ *    See @blk_run_queue. This variant must be called with the queue lock
+ *    held and interrupts disabled.
+ *
  */
 void __blk_run_queue(struct request_queue *q)
 {
@@ -418,6 +425,12 @@ EXPORT_SYMBOL(__blk_run_queue);
 /**
  * blk_run_queue - run a single device queue
  * @q: The queue to run
+ *
+ * Description:
+ *    Invoke request handling on this queue, if it has pending work to do.
+ *    May be used to restart queueing when a request has completed. Also
+ *    See @blk_start_queueing.
+ *
  */
 void blk_run_queue(struct request_queue *q)
 {
@@ -501,6 +514,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
         init_timer(&q->unplug_timer);
         setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
         INIT_LIST_HEAD(&q->timeout_list);
+        INIT_WORK(&q->unplug_work, blk_unplug_work);
 
         kobject_init(&q->kobj, &blk_queue_ktype);
 
@@ -884,7 +898,8 @@ EXPORT_SYMBOL(blk_get_request);
  *
  * This is basically a helper to remove the need to know whether a queue
  * is plugged or not if someone just wants to initiate dispatch of requests
- * for this queue.
+ * for this queue. Should be used to start queueing on a device outside
+ * of ->request_fn() context. Also see @blk_run_queue.
  *
  * The queue lock must be held with interrupts disabled.
  */
@@ -1003,8 +1018,9 @@ static void part_round_stats_single(int cpu, struct hd_struct *part,
 }
 
 /**
- * part_round_stats()   - Round off the performance stats on a struct
- * disk_stats.
+ * part_round_stats() - Round off the performance stats on a struct disk_stats.
+ * @cpu: cpu number for stats access
+ * @part: target partition
  *
  * The average IO queue length and utilisation statistics are maintained
  * by observing the current state of the queue length and the amount of
@@ -1075,8 +1091,15 @@ void init_request_from_bio(struct request *req, struct bio *bio)
         /*
          * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
          */
-        if (bio_rw_ahead(bio) || bio_failfast(bio))
-                req->cmd_flags |= REQ_FAILFAST;
+        if (bio_rw_ahead(bio))
+                req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+                                   REQ_FAILFAST_DRIVER);
+        if (bio_failfast_dev(bio))
+                req->cmd_flags |= REQ_FAILFAST_DEV;
+        if (bio_failfast_transport(bio))
+                req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+        if (bio_failfast_driver(bio))
+                req->cmd_flags |= REQ_FAILFAST_DRIVER;
 
         /*
          * REQ_BARRIER implies no merging, but lets make it explicit
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 908d3e11ac52..8681cd6f9911 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -77,12 +77,20 @@ void blk_recalc_rq_segments(struct request *rq)
                         continue;
                 }
 new_segment:
+                if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size)
+                        rq->bio->bi_seg_front_size = seg_size;
+
                 nr_phys_segs++;
                 bvprv = bv;
                 seg_size = bv->bv_len;
                 highprv = high;
         }
 
+        if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size)
+                rq->bio->bi_seg_front_size = seg_size;
+        if (seg_size > rq->biotail->bi_seg_back_size)
+                rq->biotail->bi_seg_back_size = seg_size;
+
         rq->nr_phys_segments = nr_phys_segs;
 }
 
@@ -106,7 +114,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
         if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
                 return 0;
 
-        if (bio->bi_size + nxt->bi_size > q->max_segment_size)
+        if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
+            q->max_segment_size)
                 return 0;
 
         if (!bio_has_data(bio))
@@ -309,6 +318,8 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
                                 struct request *next)
 {
         int total_phys_segments;
+        unsigned int seg_size =
+                req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
 
         /*
          * First check if the either of the requests are re-queued
@@ -324,8 +335,13 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
                 return 0;
 
         total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
-        if (blk_phys_contig_segment(q, req->biotail, next->bio))
+        if (blk_phys_contig_segment(q, req->biotail, next->bio)) {
+                if (req->nr_phys_segments == 1)
+                        req->bio->bi_seg_front_size = seg_size;
+                if (next->nr_phys_segments == 1)
+                        next->biotail->bi_seg_back_size = seg_size;
                 total_phys_segments--;
+        }
 
         if (total_phys_segments > q->max_phys_segments)
                 return 0;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index b21dcdb64151..41392fbe19ff 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -141,8 +141,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
         if (q->unplug_delay == 0)
                 q->unplug_delay = 1;
 
-        INIT_WORK(&q->unplug_work, blk_unplug_work);
-
         q->unplug_timer.function = blk_unplug_timeout;
         q->unplug_timer.data = (unsigned long)q;
 
diff --git a/block/blk.h b/block/blk.h
index e5c579769963..d2e49af90db5 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -20,6 +20,7 @@ void blk_unplug_timeout(unsigned long data);
 void blk_rq_timed_out_timer(unsigned long data);
 void blk_delete_timer(struct request *);
 void blk_add_timer(struct request *);
+void __generic_unplug_device(struct request_queue *);
 
 /*
  * Internal atomic flags for request handling
diff --git a/block/bsg.c b/block/bsg.c
index 56cb343c76d8..e8bd2475682a 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -173,7 +173,7 @@ unlock:
 
 static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
                                 struct sg_io_v4 *hdr, struct bsg_device *bd,
-                                int has_write_perm)
+                                fmode_t has_write_perm)
 {
         if (hdr->request_len > BLK_MAX_CDB) {
                 rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
@@ -242,7 +242,7 @@ bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw)
  * map sg_io_v4 to a request.
  */
 static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, int has_write_perm)
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
 {
         struct request_queue *q = bd->queue;
         struct request *rq, *next_rq = NULL;
@@ -601,7 +601,8 @@ bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 }
 
 static int __bsg_write(struct bsg_device *bd, const char __user *buf,
-                       size_t count, ssize_t *bytes_written, int has_write_perm)
+                       size_t count, ssize_t *bytes_written,
+                       fmode_t has_write_perm)
 {
         struct bsg_command *bc;
         struct request *rq;
@@ -913,7 +914,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
         case SG_EMULATED_HOST:
         case SCSI_IOCTL_SEND_COMMAND: {
                 void __user *uarg = (void __user *) arg;
-                return scsi_cmd_ioctl(file, bd->queue, NULL, cmd, uarg);
+                return scsi_cmd_ioctl(bd->queue, NULL, file->f_mode, cmd, uarg);
         }
         case SG_IO: {
                 struct request *rq;
@@ -1024,8 +1025,7 @@ int bsg_register_queue(struct request_queue *q, struct device *parent,
         bcd->release = release;
         kref_init(&bcd->ref);
         dev = MKDEV(bsg_major, bcd->minor);
-        class_dev = device_create_drvdata(bsg_class, parent, dev, NULL,
-                                          "%s", devname);
+        class_dev = device_create(bsg_class, parent, dev, NULL, "%s", devname);
         if (IS_ERR(class_dev)) {
                 ret = PTR_ERR(class_dev);
                 goto put_dev;
diff --git a/block/cmd-filter.c b/block/cmd-filter.c
index e669aed4c6bc..504b275e1b90 100644
--- a/block/cmd-filter.c
+++ b/block/cmd-filter.c
@@ -27,7 +27,7 @@
 #include <linux/cdrom.h>
 
 int blk_verify_command(struct blk_cmd_filter *filter,
-                       unsigned char *cmd, int has_write_perm)
+                       unsigned char *cmd, fmode_t has_write_perm)
 {
         /* root can do any command. */
         if (capable(CAP_SYS_RAWIO))
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 1e559fba7bdf..3d3e7a46f38c 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -71,8 +71,8 @@ static int compat_hdio_getgeo(struct gendisk *disk, struct block_device *bdev,
         return ret;
 }
 
-static int compat_hdio_ioctl(struct inode *inode, struct file *file,
-                struct gendisk *disk, unsigned int cmd, unsigned long arg)
+static int compat_hdio_ioctl(struct block_device *bdev, fmode_t mode,
+                unsigned int cmd, unsigned long arg)
 {
         mm_segment_t old_fs = get_fs();
         unsigned long kval;
@@ -80,7 +80,7 @@ static int compat_hdio_ioctl(struct inode *inode, struct file *file,
         int error;
 
         set_fs(KERNEL_DS);
-        error = blkdev_driver_ioctl(inode, file, disk,
+        error = __blkdev_driver_ioctl(bdev, mode,
                                 cmd, (unsigned long)(&kval));
         set_fs(old_fs);
 
@@ -111,8 +111,8 @@ struct compat_cdrom_generic_command {
         compat_caddr_t  reserved[1];
 };
 
-static int compat_cdrom_read_audio(struct inode *inode, struct file *file,
-                struct gendisk *disk, unsigned int cmd, unsigned long arg)
+static int compat_cdrom_read_audio(struct block_device *bdev, fmode_t mode,
+                unsigned int cmd, unsigned long arg)
 {
         struct cdrom_read_audio __user *cdread_audio;
         struct compat_cdrom_read_audio __user *cdread_audio32;
@@ -134,12 +134,12 @@ static int compat_cdrom_read_audio(struct inode *inode, struct file *file,
         if (put_user(datap, &cdread_audio->buf))
                 return -EFAULT;
 
-        return blkdev_driver_ioctl(inode, file, disk, cmd,
+        return __blkdev_driver_ioctl(bdev, mode, cmd,
                         (unsigned long)cdread_audio);
 }
 
-static int compat_cdrom_generic_command(struct inode *inode, struct file *file,
-                struct gendisk *disk, unsigned int cmd, unsigned long arg)
+static int compat_cdrom_generic_command(struct block_device *bdev, fmode_t mode,
+                unsigned int cmd, unsigned long arg)
 {
         struct cdrom_generic_command __user *cgc;
         struct compat_cdrom_generic_command __user *cgc32;
@@ -167,7 +167,7 @@ static int compat_cdrom_generic_command(struct inode *inode, struct file *file,
             put_user(compat_ptr(data), &cgc->reserved[0]))
                 return -EFAULT;
 
-        return blkdev_driver_ioctl(inode, file, disk, cmd, (unsigned long)cgc);
+        return __blkdev_driver_ioctl(bdev, mode, cmd, (unsigned long)cgc);
 }
 
 struct compat_blkpg_ioctl_arg {
@@ -177,7 +177,7 @@ struct compat_blkpg_ioctl_arg {
         compat_caddr_t data;
 };
 
-static int compat_blkpg_ioctl(struct inode *inode, struct file *file,
+static int compat_blkpg_ioctl(struct block_device *bdev, fmode_t mode,
                 unsigned int cmd, struct compat_blkpg_ioctl_arg __user *ua32)
 {
         struct blkpg_ioctl_arg __user *a = compat_alloc_user_space(sizeof(*a));
@@ -196,7 +196,7 @@ static int compat_blkpg_ioctl(struct inode *inode, struct file *file,
         if (err)
                 return err;
 
-        return blkdev_ioctl(inode, file, cmd, (unsigned long)a);
+        return blkdev_ioctl(bdev, mode, cmd, (unsigned long)a);
 }
 
 #define BLKBSZGET_32            _IOR(0x12, 112, int)
@@ -308,8 +308,8 @@ static struct {
 
 #define NR_FD_IOCTL_TRANS ARRAY_SIZE(fd_ioctl_trans_table)
 
-static int compat_fd_ioctl(struct inode *inode, struct file *file,
-                struct gendisk *disk, unsigned int cmd, unsigned long arg)
+static int compat_fd_ioctl(struct block_device *bdev, fmode_t mode,
+                unsigned int cmd, unsigned long arg)
 {
         mm_segment_t old_fs = get_fs();
         void *karg = NULL;
@@ -413,7 +413,7 @@ static int compat_fd_ioctl(struct inode *inode, struct file *file,
                 return -EINVAL;
         }
         set_fs(KERNEL_DS);
-        err = blkdev_driver_ioctl(inode, file, disk, kcmd, (unsigned long)karg);
+        err = __blkdev_driver_ioctl(bdev, mode, kcmd, (unsigned long)karg);
         set_fs(old_fs);
         if (err)
                 goto out;
@@ -579,11 +579,9 @@ static int compat_blk_trace_setup(struct block_device *bdev, char __user *arg)
         return 0;
 }
 
-static int compat_blkdev_driver_ioctl(struct inode *inode, struct file *file,
-                        struct gendisk *disk, unsigned cmd, unsigned long arg)
+static int compat_blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
+                        unsigned cmd, unsigned long arg)
 {
-        int ret;
-
         switch (cmd) {
         case HDIO_GET_UNMASKINTR:
         case HDIO_GET_MULTCOUNT:
@@ -596,7 +594,7 @@ static int compat_blkdev_driver_ioctl(struct inode *inode, struct file *file,
         case HDIO_GET_ACOUSTIC:
         case HDIO_GET_ADDRESS:
         case HDIO_GET_BUSSTATE:
-                return compat_hdio_ioctl(inode, file, disk, cmd, arg);
+                return compat_hdio_ioctl(bdev, mode, cmd, arg);
         case FDSETPRM32:
         case FDDEFPRM32:
         case FDGETPRM32:
@@ -606,11 +604,11 @@ static int compat_blkdev_driver_ioctl(struct inode *inode, struct file *file,
         case FDPOLLDRVSTAT32:
         case FDGETFDCSTAT32:
         case FDWERRORGET32:
-                return compat_fd_ioctl(inode, file, disk, cmd, arg);
+                return compat_fd_ioctl(bdev, mode, cmd, arg);
         case CDROMREADAUDIO:
-                return compat_cdrom_read_audio(inode, file, disk, cmd, arg);
+                return compat_cdrom_read_audio(bdev, mode, cmd, arg);
         case CDROM_SEND_PACKET:
-                return compat_cdrom_generic_command(inode, file, disk, cmd, arg);
+                return compat_cdrom_generic_command(bdev, mode, cmd, arg);
 
         /*
          * No handler required for the ones below, we just need to
@@ -679,55 +677,49 @@ static int compat_blkdev_driver_ioctl(struct inode *inode, struct file *file,
         case DVD_WRITE_STRUCT:
         case DVD_AUTH:
                 arg = (unsigned long)compat_ptr(arg);
-        /* These intepret arg as an unsigned long, not as a pointer,
-         * so we must not do compat_ptr() conversion. */
-        case HDIO_SET_MULTCOUNT:
-        case HDIO_SET_UNMASKINTR:
-        case HDIO_SET_KEEPSETTINGS:
-        case HDIO_SET_32BIT:
-        case HDIO_SET_NOWERR:
-        case HDIO_SET_DMA:
-        case HDIO_SET_PIO_MODE:
-        case HDIO_SET_NICE:
-        case HDIO_SET_WCACHE:
-        case HDIO_SET_ACOUSTIC:
-        case HDIO_SET_BUSSTATE:
-        case HDIO_SET_ADDRESS:
-        case CDROMEJECT_SW:
-        case CDROM_SET_OPTIONS:
-        case CDROM_CLEAR_OPTIONS:
-        case CDROM_SELECT_SPEED:
-        case CDROM_SELECT_DISC:
-        case CDROM_MEDIA_CHANGED:
-        case CDROM_DRIVE_STATUS:
-        case CDROM_LOCKDOOR:
-        case CDROM_DEBUG:
                 break;
         default:
                 /* unknown ioctl number */
                 return -ENOIOCTLCMD;
         }
 
-        if (disk->fops->unlocked_ioctl)
-                return disk->fops->unlocked_ioctl(file, cmd, arg);
-
-        if (disk->fops->ioctl) {
-                lock_kernel();
-                ret = disk->fops->ioctl(inode, file, cmd, arg);
-                unlock_kernel();
-                return ret;
-        }
-
-        return -ENOTTY;
+        return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 }
 
-static int compat_blkdev_locked_ioctl(struct inode *inode, struct file *file,
-                                struct block_device *bdev,
-                                unsigned cmd, unsigned long arg)
+/* Most of the generic ioctls are handled in the normal fallback path.
+   This assumes the blkdev's low level compat_ioctl always returns
+   ENOIOCTLCMD for unknown ioctls. */
+long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
+        int ret = -ENOIOCTLCMD;
+        struct inode *inode = file->f_mapping->host;
+        struct block_device *bdev = inode->i_bdev;
+        struct gendisk *disk = bdev->bd_disk;
+        fmode_t mode = file->f_mode;
         struct backing_dev_info *bdi;
+        loff_t size;
+
+        if (file->f_flags & O_NDELAY)
+                mode |= FMODE_NDELAY_NOW;
 
         switch (cmd) {
+        case HDIO_GETGEO:
+                return compat_hdio_getgeo(disk, bdev, compat_ptr(arg));
+        case BLKFLSBUF:
+        case BLKROSET:
+        case BLKDISCARD:
+        /*
+         * the ones below are implemented in blkdev_locked_ioctl,
+         * but we call blkdev_ioctl, which gets the lock for us
+         */
+        case BLKRRPART:
+                return blkdev_ioctl(bdev, mode, cmd,
+                                (unsigned long)compat_ptr(arg));
+        case BLKBSZSET_32:
+                return blkdev_ioctl(bdev, mode, BLKBSZSET,
+                                (unsigned long)compat_ptr(arg));
+        case BLKPG:
+                return compat_blkpg_ioctl(bdev, mode, cmd, compat_ptr(arg));
         case BLKRAGET:
         case BLKFRAGET:
                 if (!arg)
@@ -753,65 +745,36 @@ static int compat_blkdev_locked_ioctl(struct inode *inode, struct file *file,
                 bdi = blk_get_backing_dev_info(bdev);
                 if (bdi == NULL)
                         return -ENOTTY;
+                lock_kernel();
                 bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
+                unlock_kernel();
                 return 0;
         case BLKGETSIZE:
-                if ((bdev->bd_inode->i_size >> 9) > ~0UL)
+                size = bdev->bd_inode->i_size;
+                if ((size >> 9) > ~0UL)
                         return -EFBIG;
-                return compat_put_ulong(arg, bdev->bd_inode->i_size >> 9);
+                return compat_put_ulong(arg, size >> 9);
 
         case BLKGETSIZE64_32:
                 return compat_put_u64(arg, bdev->bd_inode->i_size);
 
         case BLKTRACESETUP32:
-                return compat_blk_trace_setup(bdev, compat_ptr(arg));
+                lock_kernel();
+                ret = compat_blk_trace_setup(bdev, compat_ptr(arg));
+                unlock_kernel();
+                return ret;
         case BLKTRACESTART: /* compatible */
         case BLKTRACESTOP:  /* compatible */
         case BLKTRACETEARDOWN: /* compatible */
-                return blk_trace_ioctl(bdev, cmd, compat_ptr(arg));
-        }
-        return -ENOIOCTLCMD;
-}
-
-/* Most of the generic ioctls are handled in the normal fallback path.
-   This assumes the blkdev's low level compat_ioctl always returns
-   ENOIOCTLCMD for unknown ioctls. */
-long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
-{
-        int ret = -ENOIOCTLCMD;
-        struct inode *inode = file->f_mapping->host;
-        struct block_device *bdev = inode->i_bdev;
-        struct gendisk *disk = bdev->bd_disk;
-
-        switch (cmd) {
-        case HDIO_GETGEO:
-                return compat_hdio_getgeo(disk, bdev, compat_ptr(arg));
-        case BLKFLSBUF:
-        case BLKROSET:
-        case BLKDISCARD:
-        /*
-         * the ones below are implemented in blkdev_locked_ioctl,
-         * but we call blkdev_ioctl, which gets the lock for us
-         */
-        case BLKRRPART:
-                return blkdev_ioctl(inode, file, cmd,
-                                (unsigned long)compat_ptr(arg));
-        case BLKBSZSET_32:
-                return blkdev_ioctl(inode, file, BLKBSZSET,
-                                (unsigned long)compat_ptr(arg));
-        case BLKPG:
-                return compat_blkpg_ioctl(inode, file, cmd, compat_ptr(arg));
-        }
-
-        lock_kernel();
-        ret = compat_blkdev_locked_ioctl(inode, file, bdev, cmd, arg);
-        /* FIXME: why do we assume -> compat_ioctl needs the BKL? */
-        if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
-                ret = disk->fops->compat_ioctl(file, cmd, arg);
-        unlock_kernel();
-
-        if (ret != -ENOIOCTLCMD)
+                lock_kernel();
+                ret = blk_trace_ioctl(bdev, cmd, compat_ptr(arg));
+                unlock_kernel();
                 return ret;
-
-        return compat_blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+        default:
+                if (disk->fops->compat_ioctl)
+                        ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
+                if (ret == -ENOIOCTLCMD)
+                        ret = compat_blkdev_driver_ioctl(bdev, mode, cmd, arg);
+                return ret;
+        }
 }
diff --git a/block/elevator.c b/block/elevator.c
index 04518921db31..59173a69ebdf 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -612,7 +612,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
                  *   processing.
                  */
                 blk_remove_plug(q);
-                q->request_fn(q);
+                blk_start_queueing(q);
                 break;
 
         case ELEVATOR_INSERT_SORT:
@@ -950,7 +950,7 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
                     blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
                     blk_ordered_req_seq(first_rq) > QUEUE_ORDSEQ_DRAIN) {
                         blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
-                        q->request_fn(q);
+                        blk_start_queueing(q);
                 }
         }
 }
@@ -1109,8 +1109,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
         elv_drain_elevator(q);
 
         while (q->rq.elvpriv) {
-                blk_remove_plug(q);
-                q->request_fn(q);
+                blk_start_queueing(q);
                 spin_unlock_irq(q->queue_lock);
                 msleep(10);
                 spin_lock_irq(q->queue_lock);
@@ -1166,15 +1165,10 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
                           size_t count)
 {
         char elevator_name[ELV_NAME_MAX];
-        size_t len;
         struct elevator_type *e;
 
-        elevator_name[sizeof(elevator_name) - 1] = '\0';
-        strncpy(elevator_name, name, sizeof(elevator_name) - 1);
-        len = strlen(elevator_name);
-
-        if (len && elevator_name[len - 1] == '\n')
-                elevator_name[len - 1] = '\0';
+        strlcpy(elevator_name, name, sizeof(elevator_name));
+        strstrip(elevator_name);
 
         e = elevator_get(elevator_name);
         if (!e) {
diff --git a/block/genhd.c b/block/genhd.c
index 4cd3433c99ac..4e5e7493f676 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -10,6 +10,7 @@
 #include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
@@ -358,7 +359,6 @@ static int blk_mangle_minor(int minor)
 /**
  * blk_alloc_devt - allocate a dev_t for a partition
  * @part: partition to allocate dev_t for
- * @gfp_mask: memory allocation flag
  * @devt: out parameter for resulting dev_t
  *
  * Allocate a dev_t for block device.
@@ -535,7 +535,7 @@ void unlink_gendisk(struct gendisk *disk)
 /**
  * get_gendisk - get partitioning information for a given device
  * @devt: device to get partitioning information for
- * @part: returned partition index
+ * @partno: returned partition index
  *
  * This function gets the structure containing partitioning
  * information for the given device @devt.
@@ -728,12 +728,24 @@ static int show_partition(struct seq_file *seqf, void *v)
         return 0;
 }
 
-const struct seq_operations partitions_op = {
+static const struct seq_operations partitions_op = {
         .start  = show_partition_start,
         .next   = disk_seqf_next,
         .stop   = disk_seqf_stop,
         .show   = show_partition
 };
+
+static int partitions_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &partitions_op);
+}
+
+static const struct file_operations proc_partitions_operations = {
+        .open           = partitions_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
 #endif
 
 
@@ -993,12 +1005,32 @@ static int diskstats_show(struct seq_file *seqf, void *v)
         return 0;
 }
 
-const struct seq_operations diskstats_op = {
+static const struct seq_operations diskstats_op = {
         .start  = disk_seqf_start,
         .next   = disk_seqf_next,
         .stop   = disk_seqf_stop,
         .show   = diskstats_show
 };
+
+static int diskstats_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &diskstats_op);
+}
+
+static const struct file_operations proc_diskstats_operations = {
+        .open           = diskstats_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+static int __init proc_genhd_init(void)
+{
+        proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
+        proc_create("partitions", 0, NULL, &proc_partitions_operations);
+        return 0;
+}
+module_init(proc_genhd_init);
 #endif /* CONFIG_PROC_FS */
 
 static void media_change_notify_thread(struct work_struct *work)
diff --git a/block/ioctl.c b/block/ioctl.c
index 38bee321e1fa..c832d639b6e2 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -201,97 +201,41 @@ static int put_u64(unsigned long arg, u64 val)
         return put_user(val, (u64 __user *)arg);
 }
 
-static int blkdev_locked_ioctl(struct file *file, struct block_device *bdev,
-                                unsigned cmd, unsigned long arg)
-{
-        struct backing_dev_info *bdi;
-        int ret, n;
-
-        switch (cmd) {
-        case BLKRAGET:
-        case BLKFRAGET:
-                if (!arg)
-                        return -EINVAL;
-                bdi = blk_get_backing_dev_info(bdev);
-                if (bdi == NULL)
-                        return -ENOTTY;
-                return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
-        case BLKROGET:
-                return put_int(arg, bdev_read_only(bdev) != 0);
-        case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */
-                return put_int(arg, block_size(bdev));
-        case BLKSSZGET: /* get block device hardware sector size */
-                return put_int(arg, bdev_hardsect_size(bdev));
-        case BLKSECTGET:
-                return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
-        case BLKRASET:
-        case BLKFRASET:
-                if(!capable(CAP_SYS_ADMIN))
-                        return -EACCES;
-                bdi = blk_get_backing_dev_info(bdev);
-                if (bdi == NULL)
-                        return -ENOTTY;
-                bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
-                return 0;
-        case BLKBSZSET:
-                /* set the logical block size */
-                if (!capable(CAP_SYS_ADMIN))
-                        return -EACCES;
-                if (!arg)
-                        return -EINVAL;
-                if (get_user(n, (int __user *) arg))
-                        return -EFAULT;
-                if (bd_claim(bdev, file) < 0)
-                        return -EBUSY;
-                ret = set_blocksize(bdev, n);
-                bd_release(bdev);
-                return ret;
-        case BLKPG:
-                return blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
-        case BLKRRPART:
-                return blkdev_reread_part(bdev);
-        case BLKGETSIZE:
-                if ((bdev->bd_inode->i_size >> 9) > ~0UL)
-                        return -EFBIG;
-                return put_ulong(arg, bdev->bd_inode->i_size >> 9);
-        case BLKGETSIZE64:
-                return put_u64(arg, bdev->bd_inode->i_size);
-        case BLKTRACESTART:
-        case BLKTRACESTOP:
-        case BLKTRACESETUP:
-        case BLKTRACETEARDOWN:
-                return blk_trace_ioctl(bdev, cmd, (char __user *) arg);
-        }
-        return -ENOIOCTLCMD;
-}
-
-int blkdev_driver_ioctl(struct inode *inode, struct file *file,
-                        struct gendisk *disk, unsigned cmd, unsigned long arg)
+int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
+                        unsigned cmd, unsigned long arg)
 {
+        struct gendisk *disk = bdev->bd_disk;
         int ret;
-        if (disk->fops->unlocked_ioctl)
-                return disk->fops->unlocked_ioctl(file, cmd, arg);
 
-        if (disk->fops->ioctl) {
+        if (disk->fops->ioctl)
+                return disk->fops->ioctl(bdev, mode, cmd, arg);
+
+        if (disk->fops->locked_ioctl) {
                 lock_kernel();
-                ret = disk->fops->ioctl(inode, file, cmd, arg);
+                ret = disk->fops->locked_ioctl(bdev, mode, cmd, arg);
                 unlock_kernel();
                 return ret;
         }
 
         return -ENOTTY;
 }
-EXPORT_SYMBOL_GPL(blkdev_driver_ioctl);
+/*
+ * For the record: _GPL here is only because somebody decided to slap it
+ * on the previous export.  Sheer idiocy, since it wasn't copyrightable
+ * at all and could be open-coded without any exports by anybody who cares.
+ */
+EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
 
 /*
  * always keep this in sync with compat_blkdev_ioctl() and
  * compat_blkdev_locked_ioctl()
  */
-int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
                         unsigned long arg)
 {
-        struct block_device *bdev = inode->i_bdev;
         struct gendisk *disk = bdev->bd_disk;
+        struct backing_dev_info *bdi;
+        loff_t size;
         int ret, n;
 
         switch(cmd) {
@@ -299,7 +243,7 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
                 if (!capable(CAP_SYS_ADMIN))
                         return -EACCES;
 
-                ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+                ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
                 /* -EINVAL to handle old uncorrected drivers */
                 if (ret != -EINVAL && ret != -ENOTTY)
                         return ret;
@@ -311,7 +255,7 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
                 return 0;
 
         case BLKROSET:
-                ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+                ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
                 /* -EINVAL to handle old uncorrected drivers */
                 if (ret != -EINVAL && ret != -ENOTTY)
                         return ret;
@@ -327,7 +271,7 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
         case BLKDISCARD: {
                 uint64_t range[2];
 
-                if (!(file->f_mode & FMODE_WRITE))
+                if (!(mode & FMODE_WRITE))
                         return -EBADF;
 
                 if (copy_from_user(range, (void __user *)arg, sizeof(range)))
@@ -357,14 +301,75 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
                         return -EFAULT;
                 return 0;
         }
-        }
-
-        lock_kernel();
-        ret = blkdev_locked_ioctl(file, bdev, cmd, arg);
-        unlock_kernel();
-        if (ret != -ENOIOCTLCMD)
+        case BLKRAGET:
+        case BLKFRAGET:
+                if (!arg)
+                        return -EINVAL;
+                bdi = blk_get_backing_dev_info(bdev);
+                if (bdi == NULL)
+                        return -ENOTTY;
+                return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
+        case BLKROGET:
+                return put_int(arg, bdev_read_only(bdev) != 0);
+        case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */
+                return put_int(arg, block_size(bdev));
+        case BLKSSZGET: /* get block device hardware sector size */
+                return put_int(arg, bdev_hardsect_size(bdev));
+        case BLKSECTGET:
+                return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
+        case BLKRASET:
+        case BLKFRASET:
+                if(!capable(CAP_SYS_ADMIN))
+                        return -EACCES;
+                bdi = blk_get_backing_dev_info(bdev);
+                if (bdi == NULL)
+                        return -ENOTTY;
+                lock_kernel();
+                bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
+                unlock_kernel();
+                return 0;
+        case BLKBSZSET:
+                /* set the logical block size */
+                if (!capable(CAP_SYS_ADMIN))
+                        return -EACCES;
+                if (!arg)
+                        return -EINVAL;
+                if (get_user(n, (int __user *) arg))
+                        return -EFAULT;
+                if (!(mode & FMODE_EXCL) && bd_claim(bdev, &bdev) < 0)
+                        return -EBUSY;
+                ret = set_blocksize(bdev, n);
+                if (!(mode & FMODE_EXCL))
+                        bd_release(bdev);
                 return ret;
-
-        return blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+        case BLKPG:
+                lock_kernel();
+                ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
+                unlock_kernel();
+                break;
+        case BLKRRPART:
+                lock_kernel();
+                ret = blkdev_reread_part(bdev);
+                unlock_kernel();
+                break;
+        case BLKGETSIZE:
+                size = bdev->bd_inode->i_size;
+                if ((size >> 9) > ~0UL)
+                        return -EFBIG;
+                return put_ulong(arg, size >> 9);
+        case BLKGETSIZE64:
+                return put_u64(arg, bdev->bd_inode->i_size);
+        case BLKTRACESTART:
+        case BLKTRACESTOP:
+        case BLKTRACESETUP:
+        case BLKTRACETEARDOWN:
+                lock_kernel();
+                ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
+                unlock_kernel();
+                break;
+        default:
+                ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+        }
+        return ret;
 }
 EXPORT_SYMBOL_GPL(blkdev_ioctl);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index c34272a348fe..5963cf91a3a0 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -190,12 +190,11 @@ void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 EXPORT_SYMBOL_GPL(blk_set_cmd_filter_defaults);
 
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
-                             struct sg_io_hdr *hdr, struct file *file)
+                             struct sg_io_hdr *hdr, fmode_t mode)
 {
         if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
                 return -EFAULT;
-        if (blk_verify_command(&q->cmd_filter, rq->cmd,
-                               file->f_mode & FMODE_WRITE))
+        if (blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE))
                 return -EPERM;
 
         /*
@@ -260,8 +259,8 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
         return r;
 }
 
-static int sg_io(struct file *file, struct request_queue *q,
-                struct gendisk *bd_disk, struct sg_io_hdr *hdr)
+static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
+                struct sg_io_hdr *hdr, fmode_t mode)
 {
         unsigned long start_time;
         int writing = 0, ret = 0;
@@ -293,7 +292,7 @@ static int sg_io(struct file *file, struct request_queue *q,
         if (!rq)
                 return -ENOMEM;
 
-        if (blk_fill_sghdr_rq(q, rq, hdr, file)) {
+        if (blk_fill_sghdr_rq(q, rq, hdr, mode)) {
                 blk_put_request(rq);
                 return -EFAULT;
         }
@@ -380,11 +379,11 @@ out:
  *      bytes in one int) where the lowest byte is the SCSI status.
  */
 #define OMAX_SB_LEN 16          /* For backward compatibility */
-int sg_scsi_ioctl(struct file *file, struct request_queue *q,
-                  struct gendisk *disk, struct scsi_ioctl_command __user *sic)
+int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
+                struct scsi_ioctl_command __user *sic)
 {
         struct request *rq;
-        int err, write_perm = 0;
+        int err;
         unsigned int in_len, out_len, bytes, opcode, cmdlen;
         char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
 
@@ -426,11 +425,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
         if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
                 goto error;
 
-        /* scsi_ioctl passes NULL */
-        if (file && (file->f_mode & FMODE_WRITE))
-                write_perm = 1;
-
-        err = blk_verify_command(&q->cmd_filter, rq->cmd, write_perm);
+        err = blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE);
         if (err)
                 goto error;
 
@@ -522,8 +517,8 @@ static inline int blk_send_start_stop(struct request_queue *q,
         return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data);
 }
 
-int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
-                   struct gendisk *bd_disk, unsigned int cmd, void __user *arg)
+int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mode,
+                   unsigned int cmd, void __user *arg)
 {
         int err;
 
@@ -564,7 +559,7 @@ int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
                         err = -EFAULT;
                         if (copy_from_user(&hdr, arg, sizeof(hdr)))
                                 break;
-                        err = sg_io(file, q, bd_disk, &hdr);
+                        err = sg_io(q, bd_disk, &hdr, mode);
                         if (err == -EFAULT)
                                 break;
 
@@ -612,7 +607,7 @@ int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
                         hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd;
                         hdr.cmd_len = sizeof(cgc.cmd);
 
-                        err = sg_io(file, q, bd_disk, &hdr);
+                        err = sg_io(q, bd_disk, &hdr, mode);
                         if (err == -EFAULT)
                                 break;
 
@@ -636,7 +631,7 @@ int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
                         if (!arg)
                                 break;
 
-                        err = sg_scsi_ioctl(file, q, bd_disk, arg);
+                        err = sg_scsi_ioctl(q, bd_disk, mode, arg);
                         break;
                 case CDROMCLOSETRAY:
                         err = blk_send_start_stop(q, bd_disk, 0x03);