summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-06-11 10:52:27 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-06-11 11:10:35 -0700
commitc9059598ea8981d02356eead3188bf7fa4d717b8 (patch)
tree03e73b20a30e988da7c6a3e0ad93b2dc5843274d /fs
parent0a33f80a8373eca7f4bea3961d1346c3815fa5ed (diff)
parentb0fd271d5fba0b2d00888363f3869e3f9b26caa9 (diff)
Merge branch 'for-2.6.31' of git://git.kernel.dk/linux-2.6-block
* 'for-2.6.31' of git://git.kernel.dk/linux-2.6-block: (153 commits) block: add request clone interface (v2) floppy: fix hibernation ramdisk: remove long-deprecated "ramdisk=" boot-time parameter fs/bio.c: add missing __user annotation block: prevent possible io_context->refcount overflow Add serial number support for virtio_blk, V4a block: Add missing bounce_pfn stacking and fix comments Revert "block: Fix bounce limit setting in DM" cciss: decode unit attention in SCSI error handling code cciss: Remove no longer needed sendcmd reject processing code cciss: change SCSI error handling routines to work with interrupts enabled. cciss: separate error processing and command retrying code in sendcmd_withirq_core() cciss: factor out fix target status processing code from sendcmd functions cciss: simplify interface of sendcmd() and sendcmd_withirq() cciss: factor out core of sendcmd_withirq() for use by SCSI error handling code cciss: Use schedule_timeout_uninterruptible in SCSI error handling code block: needs to set the residual length of a bidi request Revert "block: implement blkdev_readpages" block: Fix bounce limit setting in DM Removed reference to non-existing file Documentation/PCI/PCI-DMA-mapping.txt ... Manually fix conflicts with tracing updates in: block/blk-sysfs.c drivers/ide/ide-atapi.c drivers/ide/ide-cd.c drivers/ide/ide-floppy.c drivers/ide/ide-tape.c include/trace/events/block.h kernel/trace/blktrace.c
Diffstat (limited to 'fs')
-rw-r--r--fs/bio.c26
-rw-r--r--fs/block_dev.c6
-rw-r--r--fs/buffer.c6
-rw-r--r--fs/coda/file.c9
-rw-r--r--fs/direct-io.c2
-rw-r--r--fs/exofs/osd.c4
-rw-r--r--fs/ext3/super.c4
-rw-r--r--fs/ext4/super.c2
-rw-r--r--fs/gfs2/ops_fstype.c4
-rw-r--r--fs/gfs2/rgrp.c2
-rw-r--r--fs/nilfs2/the_nilfs.c2
-rw-r--r--fs/ntfs/super.c6
-rw-r--r--fs/ocfs2/cluster/heartbeat.c2
-rw-r--r--fs/ocfs2/super.c2
-rw-r--r--fs/partitions/check.c10
-rw-r--r--fs/partitions/ibm.c2
-rw-r--r--fs/partitions/msdos.c4
-rw-r--r--fs/pipe.c14
-rw-r--r--fs/read_write.c7
-rw-r--r--fs/splice.c338
-rw-r--r--fs/udf/super.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.c2
22 files changed, 389 insertions, 67 deletions
diff --git a/fs/bio.c b/fs/bio.c
index 740699c4f90..59000215e59 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -498,11 +498,11 @@ int bio_get_nr_vecs(struct block_device *bdev)
struct request_queue *q = bdev_get_queue(bdev);
int nr_pages;
- nr_pages = ((q->max_sectors << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (nr_pages > q->max_phys_segments)
- nr_pages = q->max_phys_segments;
- if (nr_pages > q->max_hw_segments)
- nr_pages = q->max_hw_segments;
+ nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (nr_pages > queue_max_phys_segments(q))
+ nr_pages = queue_max_phys_segments(q);
+ if (nr_pages > queue_max_hw_segments(q))
+ nr_pages = queue_max_hw_segments(q);
return nr_pages;
}
@@ -561,8 +561,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
* make this too complex.
*/
- while (bio->bi_phys_segments >= q->max_phys_segments
- || bio->bi_phys_segments >= q->max_hw_segments) {
+ while (bio->bi_phys_segments >= queue_max_phys_segments(q)
+ || bio->bi_phys_segments >= queue_max_hw_segments(q)) {
if (retried_segments)
return 0;
@@ -633,7 +633,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
- return __bio_add_page(q, bio, page, len, offset, q->max_hw_sectors);
+ return __bio_add_page(q, bio, page, len, offset,
+ queue_max_hw_sectors(q));
}
/**
@@ -653,7 +654,7 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
unsigned int offset)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- return __bio_add_page(q, bio, page, len, offset, q->max_sectors);
+ return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
}
struct bio_map_data {
@@ -720,7 +721,7 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
while (bv_len && iov_idx < iov_count) {
unsigned int bytes;
- char *iov_addr;
+ char __user *iov_addr;
bytes = min_t(unsigned int,
iov[iov_idx].iov_len - iov_off, bv_len);
@@ -1200,7 +1201,7 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
char *addr = page_address(bvec->bv_page);
int len = bmd->iovecs[i].bv_len;
- if (read && !err)
+ if (read)
memcpy(p, addr, len);
__free_page(bvec->bv_page);
@@ -1489,11 +1490,12 @@ struct bio_pair *bio_split(struct bio *bi, int first_sectors)
sector_t bio_sector_offset(struct bio *bio, unsigned short index,
unsigned int offset)
{
- unsigned int sector_sz = queue_hardsect_size(bio->bi_bdev->bd_disk->queue);
+ unsigned int sector_sz;
struct bio_vec *bv;
sector_t sectors;
int i;
+ sector_sz = queue_logical_block_size(bio->bi_bdev->bd_disk->queue);
sectors = 0;
if (index >= bio->bi_idx)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index f45dbc18dd1..2dfc6cdcebb 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -76,7 +76,7 @@ int set_blocksize(struct block_device *bdev, int size)
return -EINVAL;
/* Size cannot be smaller than the size supported by the device */
- if (size < bdev_hardsect_size(bdev))
+ if (size < bdev_logical_block_size(bdev))
return -EINVAL;
/* Don't change the size if it is same as current */
@@ -106,7 +106,7 @@ EXPORT_SYMBOL(sb_set_blocksize);
int sb_min_blocksize(struct super_block *sb, int size)
{
- int minsize = bdev_hardsect_size(sb->s_bdev);
+ int minsize = bdev_logical_block_size(sb->s_bdev);
if (size < minsize)
size = minsize;
return sb_set_blocksize(sb, size);
@@ -1111,7 +1111,7 @@ EXPORT_SYMBOL(check_disk_change);
void bd_set_size(struct block_device *bdev, loff_t size)
{
- unsigned bsize = bdev_hardsect_size(bdev);
+ unsigned bsize = bdev_logical_block_size(bdev);
bdev->bd_inode->i_size = size;
while (bsize < PAGE_CACHE_SIZE) {
diff --git a/fs/buffer.c b/fs/buffer.c
index 1864d0b6308..a3ef091a45b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1085,12 +1085,12 @@ static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block, int size)
{
/* Size must be multiple of hard sectorsize */
- if (unlikely(size & (bdev_hardsect_size(bdev)-1) ||
+ if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
(size < 512 || size > PAGE_SIZE))) {
printk(KERN_ERR "getblk(): invalid block size %d requested\n",
size);
- printk(KERN_ERR "hardsect size: %d\n",
- bdev_hardsect_size(bdev));
+ printk(KERN_ERR "logical block size: %d\n",
+ bdev_logical_block_size(bdev));
dump_stack();
return NULL;
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 6a347fbc998..ffd42815fda 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -47,6 +47,8 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t count,
unsigned int flags)
{
+ ssize_t (*splice_read)(struct file *, loff_t *,
+ struct pipe_inode_info *, size_t, unsigned int);
struct coda_file_info *cfi;
struct file *host_file;
@@ -54,10 +56,11 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos,
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
host_file = cfi->cfi_container;
- if (!host_file->f_op || !host_file->f_op->splice_read)
- return -EINVAL;
+ splice_read = host_file->f_op->splice_read;
+ if (!splice_read)
+ splice_read = default_file_splice_read;
- return host_file->f_op->splice_read(host_file, ppos, pipe, count,flags);
+ return splice_read(host_file, ppos, pipe, count, flags);
}
static ssize_t
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 05763bbc205..8b10b87dc01 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1127,7 +1127,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
rw = WRITE_ODIRECT;
if (bdev)
- bdev_blkbits = blksize_bits(bdev_hardsect_size(bdev));
+ bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev));
if (offset & blocksize_mask) {
if (bdev)
diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c
index b249ae97fb1..06ca92672eb 100644
--- a/fs/exofs/osd.c
+++ b/fs/exofs/osd.c
@@ -50,10 +50,10 @@ int exofs_check_ok_resid(struct osd_request *or, u64 *in_resid, u64 *out_resid)
/* FIXME: should be include in osd_sense_info */
if (in_resid)
- *in_resid = or->in.req ? or->in.req->data_len : 0;
+ *in_resid = or->in.req ? or->in.req->resid_len : 0;
if (out_resid)
- *out_resid = or->out.req ? or->out.req->data_len : 0;
+ *out_resid = or->out.req ? or->out.req->resid_len : 0;
return ret;
}
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index d8b73d4abe3..3c70d52afb1 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1696,7 +1696,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
goto failed_mount;
}
- hblock = bdev_hardsect_size(sb->s_bdev);
+ hblock = bdev_logical_block_size(sb->s_bdev);
if (sb->s_blocksize != blocksize) {
/*
* Make sure the blocksize for the filesystem is larger
@@ -2120,7 +2120,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
}
blocksize = sb->s_blocksize;
- hblock = bdev_hardsect_size(bdev);
+ hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
printk(KERN_ERR
"EXT3-fs: blocksize too small for journal device.\n");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c191d0f65fe..f016707597a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3035,7 +3035,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
}
blocksize = sb->s_blocksize;
- hblock = bdev_hardsect_size(bdev);
+ hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
ext4_msg(sb, KERN_ERR,
"blocksize too small for journal device");
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index f234aba36fb..cc34f271b3e 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -525,11 +525,11 @@ static int init_sb(struct gfs2_sbd *sdp, int silent)
}
/* Set up the buffer cache and SB for real */
- if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
+ if (sdp->sd_sb.sb_bsize < bdev_logical_block_size(sb->s_bdev)) {
ret = -EINVAL;
fs_err(sdp, "FS block size (%u) is too small for device "
"block size (%u)\n",
- sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
+ sdp->sd_sb.sb_bsize, bdev_logical_block_size(sb->s_bdev));
goto out;
}
if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 6122c7ee364..de3239731db 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -842,7 +842,7 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
struct super_block *sb = sdp->sd_vfs;
struct block_device *bdev = sb->s_bdev;
const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize /
- bdev_hardsect_size(sb->s_bdev);
+ bdev_logical_block_size(sb->s_bdev);
u64 blk;
sector_t start = 0;
sector_t nr_sects = 0;
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 7f65b3be4aa..a91f15b8673 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -515,7 +515,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, char *data)
blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size);
if (sb->s_blocksize != blocksize) {
- int hw_blocksize = bdev_hardsect_size(sb->s_bdev);
+ int hw_blocksize = bdev_logical_block_size(sb->s_bdev);
if (blocksize < hw_blocksize) {
printk(KERN_ERR
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index f76951dcd4a..6aa7c471353 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -25,7 +25,7 @@
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/spinlock.h>
-#include <linux/blkdev.h> /* For bdev_hardsect_size(). */
+#include <linux/blkdev.h> /* For bdev_logical_block_size(). */
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/vfs.h>
@@ -2785,13 +2785,13 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
goto err_out_now;
/* We support sector sizes up to the PAGE_CACHE_SIZE. */
- if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
+ if (bdev_logical_block_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
if (!silent)
ntfs_error(sb, "Device has unsupported sector size "
"(%i). The maximum supported sector "
"size on this architecture is %lu "
"bytes.",
- bdev_hardsect_size(sb->s_bdev),
+ bdev_logical_block_size(sb->s_bdev),
PAGE_CACHE_SIZE);
goto err_out_now;
}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 4f85eceab37..09cc25d0461 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1371,7 +1371,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
bdevname(reg->hr_bdev, reg->hr_dev_name);
- sectsize = bdev_hardsect_size(reg->hr_bdev);
+ sectsize = bdev_logical_block_size(reg->hr_bdev);
if (sectsize != reg->hr_block_bytes) {
mlog(ML_ERROR,
"blocksize %u incorrect for device, expected %d",
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 79ff8d9d37e..5c6163f5503 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -713,7 +713,7 @@ static int ocfs2_sb_probe(struct super_block *sb,
*bh = NULL;
/* may be > 512 */
- *sector_size = bdev_hardsect_size(sb->s_bdev);
+ *sector_size = bdev_logical_block_size(sb->s_bdev);
if (*sector_size > OCFS2_MAX_BLOCKSIZE) {
mlog(ML_ERROR, "Hardware sector size too large: %d (max=%d)\n",
*sector_size, OCFS2_MAX_BLOCKSIZE);
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 99e33ef40be..0af36085eb2 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -219,6 +219,13 @@ ssize_t part_size_show(struct device *dev,
return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
}
+ssize_t part_alignment_offset_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
+}
+
ssize_t part_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -272,6 +279,7 @@ ssize_t part_fail_store(struct device *dev,
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(stat, S_IRUGO, part_stat_show, NULL);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static struct device_attribute dev_attr_fail =
@@ -282,6 +290,7 @@ static struct attribute *part_attrs[] = {
&dev_attr_partition.attr,
&dev_attr_start.attr,
&dev_attr_size.attr,
+ &dev_attr_alignment_offset.attr,
&dev_attr_stat.attr,
#ifdef CONFIG_FAIL_MAKE_REQUEST
&dev_attr_fail.attr,
@@ -383,6 +392,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
pdev = part_to_dev(p);
p->start_sect = start;
+ p->alignment_offset = queue_sector_alignment_offset(disk->queue, start);
p->nr_sects = len;
p->partno = partno;
p->policy = get_disk_ro(disk);
diff --git a/fs/partitions/ibm.c b/fs/partitions/ibm.c
index 46297683cd3..fc71aab0846 100644
--- a/fs/partitions/ibm.c
+++ b/fs/partitions/ibm.c
@@ -76,7 +76,7 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev)
Sector sect;
res = 0;
- blocksize = bdev_hardsect_size(bdev);
+ blocksize = bdev_logical_block_size(bdev);
if (blocksize <= 0)
goto out_exit;
i_size = i_size_read(bdev->bd_inode);
diff --git a/fs/partitions/msdos.c b/fs/partitions/msdos.c
index 796511886f2..0028d2ef066 100644
--- a/fs/partitions/msdos.c
+++ b/fs/partitions/msdos.c
@@ -110,7 +110,7 @@ parse_extended(struct parsed_partitions *state, struct block_device *bdev,
Sector sect;
unsigned char *data;
u32 this_sector, this_size;
- int sector_size = bdev_hardsect_size(bdev) / 512;
+ int sector_size = bdev_logical_block_size(bdev) / 512;
int loopct = 0; /* number of links followed
without finding a data partition */
int i;
@@ -415,7 +415,7 @@ static struct {
int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
{
- int sector_size = bdev_hardsect_size(bdev) / 512;
+ int sector_size = bdev_logical_block_size(bdev) / 512;
Sector sect;
unsigned char *data;
struct partition *p;
diff --git a/fs/pipe.c b/fs/pipe.c
index 13414ec45b8..f7dd21ad85a 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -302,6 +302,20 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *info,
return 0;
}
+/**
+ * generic_pipe_buf_release - put a reference to a &struct pipe_buffer
+ * @pipe: the pipe that the buffer belongs to
+ * @buf: the buffer to put a reference to
+ *
+ * Description:
+ * This function releases a reference to @buf.
+ */
+void generic_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ page_cache_release(buf->page);
+}
+
static const struct pipe_buf_operations anon_pipe_buf_ops = {
.can_merge = 1,
.map = generic_pipe_buf_map,
diff --git a/fs/read_write.c b/fs/read_write.c
index 9d1e76bb9ee..6c8c55dec2b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -805,12 +805,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
goto out;
if (!(in_file->f_mode & FMODE_READ))
goto fput_in;
- retval = -EINVAL;
- in_inode = in_file->f_path.dentry->d_inode;
- if (!in_inode)
- goto fput_in;
- if (!in_file->f_op || !in_file->f_op->splice_read)
- goto fput_in;
retval = -ESPIPE;
if (!ppos)
ppos = &in_file->f_pos;
@@ -834,6 +828,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
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);
if (retval < 0)
diff --git a/fs/splice.c b/fs/splice.c
index 666953d59a3..73766d24f97 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -507,9 +507,131 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
return ret;
}
-
EXPORT_SYMBOL(generic_file_splice_read);
+static const struct pipe_buf_operations default_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = generic_pipe_buf_release,
+ .steal = generic_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
+static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
+ unsigned long vlen, loff_t offset)
+{
+ mm_segment_t old_fs;
+ loff_t pos = offset;
+ ssize_t res;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ /* The cast to a user pointer is valid due to the set_fs() */
+ res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
+ set_fs(old_fs);
+
+ return res;
+}
+
+static ssize_t kernel_write(struct file *file, const char *buf, size_t count,
+ loff_t pos)
+{
+ mm_segment_t old_fs;
+ ssize_t res;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ /* The cast to a user pointer is valid due to the set_fs() */
+ res = vfs_write(file, (const char __user *)buf, count, &pos);
+ set_fs(old_fs);
+
+ return res;
+}
+
+ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ unsigned int nr_pages;
+ unsigned int nr_freed;
+ size_t offset;
+ struct page *pages[PIPE_BUFFERS];
+ struct partial_page partial[PIPE_BUFFERS];
+ struct iovec vec[PIPE_BUFFERS];
+ pgoff_t index;
+ ssize_t res;
+ size_t this_len;
+ int error;
+ int i;
+ struct splice_pipe_desc spd = {
+ .pages = pages,
+ .partial = partial,
+ .flags = flags,
+ .ops = &default_pipe_buf_ops,
+ .spd_release = spd_release_page,
+ };
+
+ index = *ppos >> PAGE_CACHE_SHIFT;
+ offset = *ppos & ~PAGE_CACHE_MASK;
+ nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+ for (i = 0; i < nr_pages && i < PIPE_BUFFERS && len; i++) {
+ struct page *page;
+
+ page = alloc_page(GFP_USER);
+ error = -ENOMEM;
+ if (!page)
+ goto err;
+
+ this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
+ vec[i].iov_base = (void __user *) page_address(page);
+ vec[i].iov_len = this_len;
+ pages[i] = page;
+ spd.nr_pages++;
+ len -= this_len;
+ offset = 0;
+ }
+
+ res = kernel_readv(in, vec, spd.nr_pages, *ppos);
+ if (res < 0) {
+ error = res;
+ goto err;
+ }
+
+ error = 0;
+ if (!res)
+ goto err;
+
+ nr_freed = 0;
+ for (i = 0; i < spd.nr_pages; i++) {
+ this_len = min_t(size_t, vec[i].iov_len, res);
+ partial[i].offset = 0;
+ partial[i].len = this_len;
+ if (!this_len) {
+ __free_page(pages[i]);
+ pages[i] = NULL;
+ nr_freed++;
+ }
+ res -= this_len;
+ }
+ spd.nr_pages -= nr_freed;
+
+ res = splice_to_pipe(pipe, &spd);
+ if (res > 0)
+ *ppos += res;
+
+ return res;
+
+err:
+ for (i = 0; i < spd.nr_pages; i++)
+ __free_page(pages[i]);
+
+ return error;
+}
+EXPORT_SYMBOL(default_file_splice_read);
+
/*
* Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
* using sendpage(). Return the number of bytes sent.
@@ -881,6 +1003,36 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
EXPORT_SYMBOL(generic_file_splice_write);
+static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+ struct splice_desc *sd)
+{
+ int ret;
+ void *data;
+
+ ret = buf->ops->confirm(pipe, buf);
+ if (ret)
+ return ret;
+
+ data = buf->ops->map(pipe, buf, 0);
+ ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+ buf->ops->unmap(pipe, buf, data);
+
+ return ret;
+}
+
+static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos,
+ size_t len, unsigned int flags)
+{
+ ssize_t ret;
+
+ ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
+ if (ret > 0)
+ *ppos += ret;
+
+ return ret;
+}
+
/**
* generic_splice_sendpage - splice data from a pipe to a socket
* @pipe: pipe to splice from
@@ -908,11 +1060,10 @@ EXPORT_SYMBOL(generic_splice_sendpage);
static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
+ ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
+ loff_t *, size_t, unsigned int);
int ret;
- if (unlikely(!out->f_op || !out->f_op->splice_write))
- return -EINVAL;
-
if (unlikely(!(out->f_mode & FMODE_WRITE)))
return -EBADF;
@@ -923,7 +1074,11 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
if (unlikely(ret < 0))
return ret;
- return out->f_op->splice_write(pipe, out, ppos, len, flags);
+ splice_write = out->f_op->splice_write;
+ if (!splice_write)
+ splice_write = default_file_splice_write;
+
+ return splice_write(pipe, out, ppos, len, flags);
}
/*
@@ -933,11 +1088,10 @@ static long do_splice_to(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
+ ssize_t (*splice_read)(struct file *, loff_t *,
+ struct pipe_inode_info *, size_t, unsigned int);
int ret;
- if (unlikely(!in->f_op || !in->f_op->splice_read))
- return -EINVAL;
-
if (unlikely(!(in->f_mode & FMODE_READ)))
return -EBADF;
@@ -945,7 +1099,11 @@ static long do_splice_to(struct file *in, loff_t *ppos,
if (unlikely(ret < 0))
return ret;
- return in->f_op->splice_read(in, ppos, pipe, len, flags);
+ splice_read = in->f_op->splice_read;
+ if (!splice_read)
+ splice_read = default_file_splice_read;
+
+ return splice_read(in, ppos, pipe, len, flags);
}
/**
@@ -1112,6 +1270,9 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
return ret;
}
+static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
+ struct pipe_inode_info *opipe,
+ size_t len, unsigned int flags);
/*
* After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same
* location, so checking ->i_pipe is not enough to verify that this is a
@@ -1132,12 +1293,32 @@ static long do_splice(struct file *in, loff_t __user *off_in,
struct file *out, loff_t __user *off_out,
size_t len, unsigned int flags)
{
- struct pipe_inode_info *pipe;
+ struct pipe_inode_info *ipipe;
+ struct pipe_inode_info *opipe;
loff_t offset, *off;
long ret;
- pipe = pipe_info(in->f_path.dentry->d_inode);
- if (pipe) {
+ ipipe = pipe_info(in->f_path.dentry->d_inode);
+ opipe = pipe_info(out->f_path.dentry->d_inode);
+
+ if (ipipe && opipe) {
+ if (off_in || off_out)
+ return -ESPIPE;
+
+ if (!(in->f_mode & FMODE_READ))
+ return -EBADF;
+
+ if (!(out->f_mode & FMODE_WRITE))
+ return -EBADF;
+
+ /* Splicing to self would be fun, but... */
+ if (ipipe == opipe)
+ return -EINVAL;
+
+ return splice_pipe_to_pipe(ipipe, opipe, len, flags);
+ }
+
+ if (ipipe) {
if (off_in)
return -ESPIPE;
if (off_out) {
@@ -1149,7 +1330,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
} else
off = &out->f_pos;
- ret = do_splice_from(pipe, out, off, len, flags);
+ ret = do_splice_from(ipipe, out, off, len, flags);
if (off_out && copy_to_user(off_out, off, sizeof(loff_t)))
ret = -EFAULT;
@@ -1157,8 +1338,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
return ret;
}
- pipe = pipe_info(out->f_path.dentry->d_inode);
- if (pipe) {
+ if (opipe) {
if (off_out)
return -ESPIPE;
if (off_in) {
@@ -1170,7 +1350,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
} else
off = &in->f_pos;
- ret = do_splice_to(in, off, pipe, len, flags);
+ ret = do_splice_to(in, off, opipe, len, flags);
if (off_in && copy_to_user(off_in, off, sizeof(loff_t)))
ret = -EFAULT;
@@ -1511,7 +1691,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
* Make sure there's data to read. Wait for input if we can, otherwise
* return an appropriate error.
*/
-static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
+static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
{
int ret;
@@ -1549,7 +1729,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
* Make sure there's writeable room. Wait for room if we can, otherwise
* return an appropriate error.
*/
-static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
+static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
{
int ret;
@@ -1587,6 +1767,124 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
}
/*
+ * Splice contents of ipipe to opipe.
+ */
+static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
+ struct pipe_inode_info *opipe,
+ size_t len, unsigned int flags)
+{
+ struct pipe_buffer *ibuf, *obuf;
+ int ret = 0, nbuf;
+ bool input_wakeup = false;
+
+
+retry:
+ ret = ipipe_prep(ipipe, flags);
+ if (ret)
+ return ret;
+
+ ret = opipe_prep(opipe, flags);
+ if (ret)
+ return ret;
+
+ /*
+ * Potential ABBA deadlock, work around it by ordering lock
+ * grabbing by pipe info address. Otherwise two different processes
+ * could deadlock (one doing tee from A -> B, the other from B -> A).
+ */
+ pipe_double_lock(ipipe, opipe);
+
+ do {
+ if (!opipe->readers) {
+ send_sig(SIGPIPE, current, 0);
+ if (!ret)
+ ret = -EPIPE;
+ break;
+ }
+
+ if (!ipipe->nrbufs && !ipipe->writers)
+ break;
+
+ /*
+ * Cannot make any progress, because either the input
+ * pipe is empty or the output pipe is full.
+ */
+ if (!ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS) {
+ /* Already processed some buffers, break */
+ if (ret)
+ break;
+
+ if (flags & SPLICE_F_NONBLOCK) {
+ ret = -EAGAIN;
+ break;
+ }
+
+ /*
+ * We raced with another reader/writer and haven't
+ * managed to process any buffers. A zero return
+ * value means EOF, so retry instead.
+ */
+ pipe_unlock(ipipe);
+ pipe_unlock(opipe);
+ goto retry;
+ }
+
+ ibuf = ipipe->bufs + ipipe->curbuf;
+ nbuf = (opipe->curbuf + opipe->nrbufs) % PIPE_BUFFERS;
+ obuf = opipe->bufs + nbuf;
+
+ if (len >= ibuf->len) {
+ /*
+ * Simply move the whole buffer from ipipe to opipe
+ */
+ *obuf = *ibuf;
+ ibuf->ops = NULL;
+ opipe->nrbufs++;
+ ipipe->curbuf = (ipipe->curbuf + 1) % PIPE_BUFFERS;
+ ipipe->nrbufs--;
+ input_wakeup = true;
+ } else {
+ /*
+ * Get a reference to this pipe buffer,
+ * so we can copy the contents over.
+ */
+ ibuf->ops->get(ipipe, ibuf);
+ *obuf = *ibuf;
+
+ /*
+ * Don't inherit the gift flag, we need to
+ * prevent multiple steals of this page.
+ */
+ obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
+
+ obuf->len = len;
+ opipe->nrbufs++;
+ ibuf->offset += obuf->len;
+ ibuf->len -= obuf->len;
+ }
+ ret += obuf->len;
+ len -= obuf->len;
+ } while (len);
+
+ pipe_unlock(ipipe);
+ pipe_unlock(opipe);
+
+ /*
+ * If we put data in the output pipe, wakeup any potential readers.
+ */
+ if (ret > 0) {
+ smp_mb();
+ if (waitqueue_active(&opipe->wait))
+ wake_up_interruptible(&opipe->wait);
+ kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
+ }
+ if (input_wakeup)
+ wakeup_pipe_writers(ipipe);
+
+ return ret;
+}
+
+/*
* Link contents of ipipe to opipe.
*/
static int link_pipe(struct pipe_inode_info *ipipe,
@@ -1690,9 +1988,9 @@ static long do_tee(struct file *in, struct file *out, size_t len,
* Keep going, unless we encounter an error. The ipipe/opipe
* ordering doesn't really matter.
*/
- ret = link_ipipe_prep(ipipe, flags);
+ ret = ipipe_prep(ipipe, flags);
if (!ret) {
- ret = link_opipe_prep(opipe, flags);
+ ret = opipe_prep(opipe, flags);
if (!ret)
ret = link_pipe(ipipe, opipe, len, flags);
}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 72348cc855a..0ba44107d8f 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -1915,7 +1915,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
if (uopt.flags & (1 << UDF_FLAG_BLOCKSIZE_SET)) {
ret = udf_load_vrs(sb, &uopt, silent, &fileset);
} else {
- uopt.blocksize = bdev_hardsect_size(sb->s_bdev);
+ uopt.blocksize = bdev_logical_block_size(sb->s_bdev);
ret = udf_load_vrs(sb, &uopt, silent, &fileset);
if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
if (!silent)
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index e28800a9f2b..1418b916fc2 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1501,7 +1501,7 @@ xfs_setsize_buftarg_early(
struct block_device *bdev)
{
return xfs_setsize_buftarg_flags(btp,
- PAGE_CACHE_SIZE, bdev_hardsect_size(bdev), 0);
+ PAGE_CACHE_SIZE, bdev_logical_block_size(bdev), 0);
}
int