Merge branch 'for-2.6.33' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.33' of git://git.kernel.dk/linux-2.6-block: (113 commits)
  cfq-iosched: Do not access cfqq after freeing it
  block: include linux/err.h to use ERR_PTR
  cfq-iosched: use call_rcu() instead of doing grace period stall on queue exit
  blkio: Allow CFQ group IO scheduling even when CFQ is a module
  blkio: Implement dynamic io controlling policy registration
  blkio: Export some symbols from blkio as its user CFQ can be a module
  block: Fix io_context leak after failure of clone with CLONE_IO
  block: Fix io_context leak after clone with CLONE_IO
  cfq-iosched: make nonrot check logic consistent
  io controller: quick fix for blk-cgroup and modular CFQ
  cfq-iosched: move IO controller declerations to a header file
  cfq-iosched: fix compile problem with !CONFIG_CGROUP
  blkio: Documentation
  blkio: Wait on sync-noidle queue even if rq_noidle = 1
  blkio: Implement group_isolation tunable
  blkio: Determine async workload length based on total number of queues
  blkio: Wait for cfq queue to get backlogged if group is empty
  blkio: Propagate cgroup weight updation to cfq groups
  blkio: Drop the reference to queue once the task changes cgroup
  blkio: Provide some isolation between groups
  ...

12 files changed, 143 insertions, 68 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 02a2c93..c30dfc0 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -15,6 +15,7 @@
 #include <linux/aio_abi.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
+#include <linux/backing-dev.h>
 #include <linux/uio.h>
 
 #define DEBUG 0
@@ -32,6 +33,9 @@
 #include <linux/workqueue.h>
 #include <linux/security.h>
 #include <linux/eventfd.h>
+#include <linux/blkdev.h>
+#include <linux/mempool.h>
+#include <linux/hash.h>
 
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
@@ -60,6 +64,14 @@ static DECLARE_WORK(fput_work, aio_fput_routine);
 static DEFINE_SPINLOCK(fput_lock);
 static LIST_HEAD(fput_head);
 
+#define AIO_BATCH_HASH_BITS	3 /* allocated on-stack, so don't go crazy */
+#define AIO_BATCH_HASH_SIZE	(1 << AIO_BATCH_HASH_BITS)
+struct aio_batch_entry {
+	struct hlist_node list;
+	struct address_space *mapping;
+};
+mempool_t *abe_pool;
+
 static void aio_kick_handler(struct work_struct *);
 static void aio_queue_work(struct kioctx *);
 
@@ -73,6 +85,8 @@ static int __init aio_setup(void)
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
 	aio_wq = create_workqueue("aio");
+	abe_pool = mempool_create_kmalloc_pool(1, sizeof(struct aio_batch_entry));
+	BUG_ON(!abe_pool);
 
 	pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
 
@@ -1531,8 +1545,44 @@ static int aio_wake_function(wait_queue_t *wait, unsigned mode,
 	return 1;
 }
 
+static void aio_batch_add(struct address_space *mapping,
+			  struct hlist_head *batch_hash)
+{
+	struct aio_batch_entry *abe;
+	struct hlist_node *pos;
+	unsigned bucket;
+
+	bucket = hash_ptr(mapping, AIO_BATCH_HASH_BITS);
+	hlist_for_each_entry(abe, pos, &batch_hash[bucket], list) {
+		if (abe->mapping == mapping)
+			return;
+	}
+
+	abe = mempool_alloc(abe_pool, GFP_KERNEL);
+	BUG_ON(!igrab(mapping->host));
+	abe->mapping = mapping;
+	hlist_add_head(&abe->list, &batch_hash[bucket]);
+	return;
+}
+
+static void aio_batch_free(struct hlist_head *batch_hash)
+{
+	struct aio_batch_entry *abe;
+	struct hlist_node *pos, *n;
+	int i;
+
+	for (i = 0; i < AIO_BATCH_HASH_SIZE; i++) {
+		hlist_for_each_entry_safe(abe, pos, n, &batch_hash[i], list) {
+			blk_run_address_space(abe->mapping);
+			iput(abe->mapping->host);
+			hlist_del(&abe->list);
+			mempool_free(abe, abe_pool);
+		}
+	}
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-			 struct iocb *iocb)
+			 struct iocb *iocb, struct hlist_head *batch_hash)
 {
 	struct kiocb *req;
 	struct file *file;
@@ -1608,6 +1658,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			;
 	}
 	spin_unlock_irq(&ctx->ctx_lock);
+	if (req->ki_opcode == IOCB_CMD_PREAD ||
+	    req->ki_opcode == IOCB_CMD_PREADV ||
+	    req->ki_opcode == IOCB_CMD_PWRITE ||
+	    req->ki_opcode == IOCB_CMD_PWRITEV)
+		aio_batch_add(file->f_mapping, batch_hash);
+
 	aio_put_req(req);	/* drop extra ref to req */
 	return 0;
 
@@ -1635,6 +1691,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 	struct kioctx *ctx;
 	long ret = 0;
 	int i;
+	struct hlist_head batch_hash[AIO_BATCH_HASH_SIZE] = { { 0, }, };
 
 	if (unlikely(nr < 0))
 		return -EINVAL;
@@ -1666,10 +1723,11 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 			break;
 		}
 
-		ret = io_submit_one(ctx, user_iocb, &tmp);
+		ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash);
 		if (ret)
 			break;
 	}
+	aio_batch_free(batch_hash);
 
 	put_ioctx(ctx);
 	return i ? i : ret;
diff --git a/fs/bio.c b/fs/bio.c
index 12da5db..e23a63f 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1393,6 +1393,18 @@ void bio_check_pages_dirty(struct bio *bio)
 	}
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+void bio_flush_dcache_pages(struct bio *bi)
+{
+	int i;
+	struct bio_vec *bvec;
+
+	bio_for_each_segment(bvec, bi, i)
+		flush_dcache_page(bvec->bv_page);
+}
+EXPORT_SYMBOL(bio_flush_dcache_pages);
+#endif
+
 /**
  * bio_endio - end I/O on a bio
  * @bio:	bio
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8bed055..73d6a73 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -405,7 +405,17 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
  
 static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
 {
-	return sync_blockdev(I_BDEV(filp->f_mapping->host));
+	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+	int error;
+
+	error = sync_blockdev(bdev);
+	if (error)
+		return error;
+	
+	error = blkdev_issue_flush(bdev, NULL);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+	return error;
 }
 
 /*
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 8b10b87..b912270 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1028,9 +1028,6 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
 	if (dio->bio)
 		dio_bio_submit(dio);
 
-	/* All IO is now issued, send it on its way */
-	blk_run_address_space(inode->i_mapping);
-
 	/*
 	 * It is possible that, we return short IO due to end of file.
 	 * In that case, we need to release all the pages we got hold on.
@@ -1057,8 +1054,11 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
 	    ((rw & READ) || (dio->result == dio->size)))
 		ret = -EIOCBQUEUED;
 
-	if (ret != -EIOCBQUEUED)
+	if (ret != -EIOCBQUEUED) {
+		/* All IO is now issued, send it on its way */
+		blk_run_address_space(inode->i_mapping);
 		dio_await_completion(dio);
+	}
 
 	/*
 	 * Sync will always be dropping the final ref and completing the
@@ -1124,7 +1124,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	int acquire_i_mutex = 0;
 
 	if (rw & WRITE)
-		rw = WRITE_ODIRECT;
+		rw = WRITE_ODIRECT_PLUG;
 
 	if (bdev)
 		bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev));
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 9d5360c..49bc1b8 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -614,7 +614,6 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
 				struct writeback_control *wbc)
 {
 	struct super_block *sb = wbc->sb, *pin_sb = NULL;
-	const int is_blkdev_sb = sb_is_blkdev_sb(sb);
 	const unsigned long start = jiffies;	/* livelock avoidance */
 
 	spin_lock(&inode_lock);
@@ -635,36 +634,11 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
 			continue;
 		}
 
-		if (!bdi_cap_writeback_dirty(wb->bdi)) {
-			redirty_tail(inode);
-			if (is_blkdev_sb) {
-				/*
-				 * Dirty memory-backed blockdev: the ramdisk
-				 * driver does this.  Skip just this inode
-				 */
-				continue;
-			}
-			/*
-			 * Dirty memory-backed inode against a filesystem other
-			 * than the kernel-internal bdev filesystem.  Skip the
-			 * entire superblock.
-			 */
-			break;
-		}
-
 		if (inode->i_state & (I_NEW | I_WILL_FREE)) {
 			requeue_io(inode);
 			continue;
 		}
 
-		if (wbc->nonblocking && bdi_write_congested(wb->bdi)) {
-			wbc->encountered_congestion = 1;
-			if (!is_blkdev_sb)
-				break;		/* Skip a congested fs */
-			requeue_io(inode);
-			continue;		/* Skip a congested blockdev */
-		}
-
 		/*
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
@@ -756,6 +730,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		.sync_mode		= args->sync_mode,
 		.older_than_this	= NULL,
 		.for_kupdate		= args->for_kupdate,
+		.for_background		= args->for_background,
 		.range_cyclic		= args->range_cyclic,
 	};
 	unsigned long oldest_jif;
@@ -787,7 +762,6 @@ static long wb_writeback(struct bdi_writeback *wb,
 			break;
 
 		wbc.more_io = 0;
-		wbc.encountered_congestion = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		wbc.pages_skipped = 0;
 		writeback_inodes_wb(wb, &wbc);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 53eb26c..c84b5cc 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -178,7 +178,7 @@ static int wb_priority(struct writeback_control *wbc)
 {
 	if (wbc->for_reclaim)
 		return FLUSH_HIGHPRI | FLUSH_STABLE;
-	if (wbc->for_kupdate)
+	if (wbc->for_kupdate || wbc->for_background)
 		return FLUSH_LOWPRI;
 	return 0;
 }
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 7b685e1..64bc899 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -226,6 +226,13 @@ ssize_t part_alignment_offset_show(struct device *dev,
 	return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
 }
 
+ssize_t part_discard_alignment_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	return sprintf(buf, "%u\n", p->discard_alignment);
+}
+
 ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
@@ -288,6 +295,8 @@ static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
 static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
+		   NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -300,6 +309,7 @@ static struct attribute *part_attrs[] = {
 	&dev_attr_start.attr,
 	&dev_attr_size.attr,
 	&dev_attr_alignment_offset.attr,
+	&dev_attr_discard_alignment.attr,
 	&dev_attr_stat.attr,
 	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -403,6 +413,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	p->start_sect = start;
 	p->alignment_offset = queue_sector_alignment_offset(disk->queue, start);
+	p->discard_alignment = queue_sector_discard_alignment(disk->queue,
+							      start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c
index 038a602..49cfd5f 100644
--- a/fs/partitions/efi.c
+++ b/fs/partitions/efi.c
@@ -1,7 +1,9 @@
 /************************************************************
  * EFI GUID Partition Table handling
- * Per Intel EFI Specification v1.02
- * http://developer.intel.com/technology/efi/efi.htm
+ *
+ * http://www.uefi.org/specs/
+ * http://www.intel.com/technology/efi/
+ *
  * efi.[ch] by Matt Domsch <Matt_Domsch@dell.com>
  *   Copyright 2000,2001,2002,2004 Dell Inc.
  *
@@ -92,6 +94,7 @@
  *
  ************************************************************/
 #include <linux/crc32.h>
+#include <linux/math64.h>
 #include "check.h"
 #include "efi.h"
 
@@ -141,7 +144,8 @@ last_lba(struct block_device *bdev)
 {
 	if (!bdev || !bdev->bd_inode)
 		return 0;
-	return (bdev->bd_inode->i_size >> 9) - 1ULL;
+	return div_u64(bdev->bd_inode->i_size,
+		       bdev_logical_block_size(bdev)) - 1ULL;
 }
 
 static inline int
@@ -188,6 +192,7 @@ static size_t
 read_lba(struct block_device *bdev, u64 lba, u8 * buffer, size_t count)
 {
 	size_t totalreadcount = 0;
+	sector_t n = lba * (bdev_logical_block_size(bdev) / 512);
 
 	if (!bdev || !buffer || lba > last_lba(bdev))
                 return 0;
@@ -195,7 +200,7 @@ read_lba(struct block_device *bdev, u64 lba, u8 * buffer, size_t count)
 	while (count) {
 		int copied = 512;
 		Sector sect;
-		unsigned char *data = read_dev_sector(bdev, lba++, &sect);
+		unsigned char *data = read_dev_sector(bdev, n++, &sect);
 		if (!data)
 			break;
 		if (copied > count)
@@ -257,15 +262,16 @@ static gpt_header *
 alloc_read_gpt_header(struct block_device *bdev, u64 lba)
 {
 	gpt_header *gpt;
+	unsigned ssz = bdev_logical_block_size(bdev);
+
 	if (!bdev)
 		return NULL;
 
-	gpt = kzalloc(sizeof (gpt_header), GFP_KERNEL);
+	gpt = kzalloc(ssz, GFP_KERNEL);
 	if (!gpt)
 		return NULL;
 
-	if (read_lba(bdev, lba, (u8 *) gpt,
-		     sizeof (gpt_header)) < sizeof (gpt_header)) {
+	if (read_lba(bdev, lba, (u8 *) gpt, ssz) < ssz) {
 		kfree(gpt);
                 gpt=NULL;
 		return NULL;
@@ -601,6 +607,7 @@ efi_partition(struct parsed_partitions *state, struct block_device *bdev)
 	gpt_header *gpt = NULL;
 	gpt_entry *ptes = NULL;
 	u32 i;
+	unsigned ssz = bdev_logical_block_size(bdev) / 512;
 
 	if (!find_valid_gpt(bdev, &gpt, &ptes) || !gpt || !ptes) {
 		kfree(gpt);
@@ -611,13 +618,14 @@ efi_partition(struct parsed_partitions *state, struct block_device *bdev)
 	pr_debug("GUID Partition Table is valid!  Yea!\n");
 
 	for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
+		u64 start = le64_to_cpu(ptes[i].starting_lba);
+		u64 size = le64_to_cpu(ptes[i].ending_lba) -
+			   le64_to_cpu(ptes[i].starting_lba) + 1ULL;
+
 		if (!is_pte_valid(&ptes[i], last_lba(bdev)))
 			continue;
 
-		put_partition(state, i+1, le64_to_cpu(ptes[i].starting_lba),
-				 (le64_to_cpu(ptes[i].ending_lba) -
-                                  le64_to_cpu(ptes[i].starting_lba) +
-				  1ULL));
+		put_partition(state, i+1, start * ssz, size * ssz);
 
 		/* If this is a RAID volume, tell md */
 		if (!efi_guidcmp(ptes[i].partition_type_guid,
diff --git a/fs/partitions/efi.h b/fs/partitions/efi.h
index 2cc89d0..6998b58 100644
--- a/fs/partitions/efi.h
+++ b/fs/partitions/efi.h
@@ -37,7 +37,6 @@
 #define EFI_PMBR_OSTYPE_EFI 0xEF
 #define EFI_PMBR_OSTYPE_EFI_GPT 0xEE
 
-#define GPT_BLOCK_SIZE 512
 #define GPT_HEADER_SIGNATURE 0x5452415020494645ULL
 #define GPT_HEADER_REVISION_V1 0x00010000
 #define GPT_PRIMARY_PARTITION_TABLE_LBA 1
@@ -79,7 +78,12 @@ typedef struct _gpt_header {
 	__le32 num_partition_entries;
 	__le32 sizeof_partition_entry;
 	__le32 partition_entry_array_crc32;
-	u8 reserved2[GPT_BLOCK_SIZE - 92];
+
+	/* The rest of the logical block is reserved by UEFI and must be zero.
+	 * EFI standard handles this by:
+	 *
+	 * uint8_t		reserved2[ BlockSize - 92 ];
+	 */
 } __attribute__ ((packed)) gpt_header;
 
 typedef struct _gpt_entry_attributes {
diff --git a/fs/read_write.c b/fs/read_write.c
index 3ac2898..b7f4a1f 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -826,8 +826,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	if (!(out_file->f_mode & FMODE_WRITE))
 		goto fput_out;
 	retval = -EINVAL;
-	if (!out_file->f_op || !out_file->f_op->sendpage)
-		goto fput_out;
 	in_inode = in_file->f_path.dentry->d_inode;
 	out_inode = out_file->f_path.dentry->d_inode;
 	retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
diff --git a/fs/splice.c b/fs/splice.c
index 7394e9e..3920866 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -648,9 +648,11 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 	ret = buf->ops->confirm(pipe, buf);
 	if (!ret) {
 		more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
-
-		ret = file->f_op->sendpage(file, buf->page, buf->offset,
-					   sd->len, &pos, more);
+		if (file->f_op && file->f_op->sendpage)
+			ret = file->f_op->sendpage(file, buf->page, buf->offset,
+						   sd->len, &pos, more);
+		else
+			ret = -EINVAL;
 	}
 
 	return ret;
@@ -1068,8 +1070,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 	if (unlikely(ret < 0))
 		return ret;
 
-	splice_write = out->f_op->splice_write;
-	if (!splice_write)
+	if (out->f_op && out->f_op->splice_write)
+		splice_write = out->f_op->splice_write;
+	else
 		splice_write = default_file_splice_write;
 
 	return splice_write(pipe, out, ppos, len, flags);
@@ -1093,8 +1096,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(ret < 0))
 		return ret;
 
-	splice_read = in->f_op->splice_read;
-	if (!splice_read)
+	if (in->f_op && in->f_op->splice_read)
+		splice_read = in->f_op->splice_read;
+	else
 		splice_read = default_file_splice_read;
 
 	return splice_read(in, ppos, pipe, len, flags);
@@ -1316,7 +1320,8 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_in)
 			return -ESPIPE;
 		if (off_out) {
-			if (out->f_op->llseek == no_llseek)
+			if (!out->f_op || !out->f_op->llseek ||
+			    out->f_op->llseek == no_llseek)
 				return -EINVAL;
 			if (copy_from_user(&offset, off_out, sizeof(loff_t)))
 				return -EFAULT;
@@ -1336,7 +1341,8 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_out)
 			return -ESPIPE;
 		if (off_in) {
-			if (in->f_op->llseek == no_llseek)
+			if (!in->f_op || !in->f_op->llseek ||
+			    in->f_op->llseek == no_llseek)
 				return -EINVAL;
 			if (copy_from_user(&offset, off_in, sizeof(loff_t)))
 				return -EFAULT;
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index c2e30ee..70f9898 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -904,16 +904,9 @@ xfs_convert_page(
 
 	if (startio) {
 		if (count) {
-			struct backing_dev_info *bdi;
-
-			bdi = inode->i_mapping->backing_dev_info;
 			wbc->nr_to_write--;
-			if (bdi_write_congested(bdi)) {
-				wbc->encountered_congestion = 1;
-				done = 1;
-			} else if (wbc->nr_to_write <= 0) {
+			if (wbc->nr_to_write <= 0)
 				done = 1;
-			}
 		}
 		xfs_start_page_writeback(page, !page_dirty, count);
 	}