summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/dax.c34
-rw-r--r--fs/ext2/file.c4
-rw-r--r--fs/ext4/file.c16
-rw-r--r--fs/ext4/inode.c21
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c8
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h2
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c41
-rw-r--r--fs/xfs/libxfs/xfs_format.h4
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c9
-rw-r--r--fs/xfs/xfs_aops.c152
-rw-r--r--fs/xfs/xfs_aops.h7
-rw-r--r--fs/xfs/xfs_attr_inactive.c83
-rw-r--r--fs/xfs/xfs_bmap_util.c23
-rw-r--r--fs/xfs/xfs_file.c164
-rw-r--r--fs/xfs/xfs_inode.c22
-rw-r--r--fs/xfs/xfs_iops.c30
-rw-r--r--fs/xfs/xfs_mount.c34
-rw-r--r--fs/xfs/xfs_mount.h2
-rw-r--r--fs/xfs/xfs_quota.h1
-rw-r--r--fs/xfs/xfs_super.c25
-rw-r--r--fs/xfs/xfs_trans_dquot.c32
21 files changed, 467 insertions, 247 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 6f65f00e58ec..99b5fbc38992 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -309,14 +309,21 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
out:
i_mmap_unlock_read(mapping);
- if (bh->b_end_io)
- bh->b_end_io(bh, 1);
-
return error;
}
-static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block)
+/**
+ * __dax_fault - handle a page fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * fault handler for DAX files. __dax_fault() assumes the caller has done all
+ * the necessary locking for the page fault to proceed successfully.
+ */
+int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+ get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
@@ -417,7 +424,19 @@ static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
page_cache_release(page);
}
+ /*
+ * If we successfully insert the new mapping over an unwritten extent,
+ * we need to ensure we convert the unwritten extent. If there is an
+ * error inserting the mapping, the filesystem needs to leave it as
+ * unwritten to prevent exposure of the stale underlying data to
+ * userspace, but we still need to call the completion function so
+ * the private resources on the mapping buffer can be released. We
+ * indicate what the callback should do via the uptodate variable, same
+ * as for normal BH based IO completions.
+ */
error = dax_insert_mapping(inode, &bh, vma, vmf);
+ if (buffer_unwritten(&bh))
+ complete_unwritten(&bh, !error);
out:
if (error == -ENOMEM)
@@ -434,6 +453,7 @@ static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
}
goto out;
}
+EXPORT_SYMBOL(__dax_fault);
/**
* dax_fault - handle a page fault on a DAX file
@@ -445,7 +465,7 @@ static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
* fault handler for DAX files.
*/
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- get_block_t get_block)
+ get_block_t get_block, dax_iodone_t complete_unwritten)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
@@ -454,7 +474,7 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
}
- result = do_dax_fault(vma, vmf, get_block);
+ result = __dax_fault(vma, vmf, get_block, complete_unwritten);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 3a0a6c6406d0..3b57c9f83c9b 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -28,12 +28,12 @@
#ifdef CONFIG_FS_DAX
static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return dax_fault(vma, vmf, ext2_get_block);
+ return dax_fault(vma, vmf, ext2_get_block, NULL);
}
static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return dax_mkwrite(vma, vmf, ext2_get_block);
+ return dax_mkwrite(vma, vmf, ext2_get_block, NULL);
}
static const struct vm_operations_struct ext2_dax_vm_ops = {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0613c256c344..f713cfcc43a2 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -192,15 +192,27 @@ out:
}
#ifdef CONFIG_FS_DAX
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+ struct inode *inode = bh->b_assoc_map->host;
+ /* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+ loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+ int err;
+ if (!uptodate)
+ return;
+ WARN_ON(!buffer_unwritten(bh));
+ err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return dax_fault(vma, vmf, ext4_get_block);
+ return dax_fault(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
/* Is this the right get_block? */
}
static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- return dax_mkwrite(vma, vmf, ext4_get_block);
+ return dax_mkwrite(vma, vmf, ext4_get_block, ext4_end_io_unwritten);
}
static const struct vm_operations_struct ext4_dax_vm_ops = {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 55b187c3bac1..7c38ed3494cb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -656,18 +656,6 @@ has_zeroout:
return retval;
}
-static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
-{
- struct inode *inode = bh->b_assoc_map->host;
- /* XXX: breaks on 32-bit > 16GB. Is that even supported? */
- loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
- int err;
- if (!uptodate)
- return;
- WARN_ON(!buffer_unwritten(bh));
- err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
-}
-
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
@@ -705,10 +693,15 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
- if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+ if (IS_DAX(inode) && buffer_unwritten(bh)) {
+ /*
+ * dgc: I suspect unwritten conversion on ext4+DAX is
+ * fundamentally broken here when there are concurrent
+ * read/write in progress on this inode.
+ */
+ WARN_ON_ONCE(io_end);
bh->b_assoc_map = inode->i_mapping;
bh->b_private = (void *)(unsigned long)iblock;
- bh->b_end_io = ext4_end_io_unwritten;
}
if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
set_buffer_defer_completion(bh);
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 04e79d57bca6..e9d401ce93bb 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -574,8 +574,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
* After the last attribute is removed revert to original inode format,
* making all literal area available to the data fork once more.
*/
-STATIC void
-xfs_attr_fork_reset(
+void
+xfs_attr_fork_remove(
struct xfs_inode *ip,
struct xfs_trans *tp)
{
@@ -641,7 +641,7 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
(mp->m_flags & XFS_MOUNT_ATTR2) &&
(dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
!(args->op_flags & XFS_DA_OP_ADDNAME)) {
- xfs_attr_fork_reset(dp, args->trans);
+ xfs_attr_fork_remove(dp, args->trans);
} else {
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
@@ -905,7 +905,7 @@ xfs_attr3_leaf_to_shortform(
if (forkoff == -1) {
ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
- xfs_attr_fork_reset(dp, args->trans);
+ xfs_attr_fork_remove(dp, args->trans);
goto out;
}
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 025c4b820c03..882c8d338891 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -53,7 +53,7 @@ int xfs_attr_shortform_remove(struct xfs_da_args *args);
int xfs_attr_shortform_list(struct xfs_attr_list_context *context);
int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
int xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
-
+void xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
/*
* Internal routines when attribute fork size == XFS_LBSIZE(mp).
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index aeffeaaac0ec..5cb3e85c9258 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3224,12 +3224,24 @@ xfs_bmap_extsize_align(
align_alen += temp;
align_off -= temp;
}
+
+ /* Same adjustment for the end of the requested area. */
+ temp = (align_alen % extsz);
+ if (temp)
+ align_alen += extsz - temp;
+
/*
- * Same adjustment for the end of the requested area.
+ * For large extent hint sizes, the aligned extent might be larger than
+ * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
+ * the length back under MAXEXTLEN. The outer allocation loops handle
+ * short allocation just fine, so it is safe to do this. We only want to
+ * do it when we are forced to, though, because it means more allocation
+ * operations are required.
*/
- if ((temp = (align_alen % extsz))) {
- align_alen += extsz - temp;
- }
+ while (align_alen > MAXEXTLEN)
+ align_alen -= extsz;
+ ASSERT(align_alen <= MAXEXTLEN);
+
/*
* If the previous block overlaps with this proposed allocation
* then move the start forward without adjusting the length.
@@ -3318,7 +3330,9 @@ xfs_bmap_extsize_align(
return -EINVAL;
} else {
ASSERT(orig_off >= align_off);
- ASSERT(orig_end <= align_off + align_alen);
+ /* see MAXEXTLEN handling above */
+ ASSERT(orig_end <= align_off + align_alen ||
+ align_alen + extsz > MAXEXTLEN);
}
#ifdef DEBUG
@@ -4099,13 +4113,6 @@ xfs_bmapi_reserve_delalloc(
/* Figure out the extent size, adjust alen */
extsz = xfs_get_extsz_hint(ip);
if (extsz) {
- /*
- * Make sure we don't exceed a single extent length when we
- * align the extent by reducing length we are going to
- * allocate by the maximum amount extent size aligment may
- * require.
- */
- alen = XFS_FILBLKS_MIN(len, MAXEXTLEN - (2 * extsz - 1));
error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
1, 0, &aoff, &alen);
ASSERT(!error);
@@ -4417,7 +4424,15 @@ xfs_bmapi_convert_unwritten(
error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx,
&bma->cur, mval, bma->firstblock, bma->flist,
&tmp_logflags);
- bma->logflags |= tmp_logflags;
+ /*
+ * Log the inode core unconditionally in the unwritten extent conversion
+ * path because the conversion might not have done so (e.g., if the
+ * extent count hasn't changed). We need to make sure the inode is dirty
+ * in the transaction for the sake of fsync(), even if nothing has
+ * changed, because fsync() will not force the log for this transaction
+ * unless it sees the inode pinned.
+ */
+ bma->logflags |= tmp_logflags | XFS_ILOG_CORE;
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 5ccc891cdd1a..815f61b02bc1 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1489,8 +1489,8 @@ struct xfs_acl {
sizeof(struct xfs_acl_entry) * XFS_ACL_MAX_ENTRIES((mp)))
/* On-disk XFS extended attribute names */
-#define SGI_ACL_FILE (unsigned char *)"SGI_ACL_FILE"
-#define SGI_ACL_DEFAULT (unsigned char *)"SGI_ACL_DEFAULT"
+#define SGI_ACL_FILE "SGI_ACL_FILE"
+#define SGI_ACL_DEFAULT "SGI_ACL_DEFAULT"
#define SGI_ACL_FILE_SIZE (sizeof(SGI_ACL_FILE)-1)
#define SGI_ACL_DEFAULT_SIZE (sizeof(SGI_ACL_DEFAULT)-1)
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 52553b854771..66efc702452a 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -626,7 +626,7 @@ xfs_ialloc_ag_alloc(
*/
newlen = args.mp->m_ialloc_inos;
if (args.mp->m_maxicount &&
- percpu_counter_read(&args.mp->m_icount) + newlen >
+ percpu_counter_read_positive(&args.mp->m_icount) + newlen >
args.mp->m_maxicount)
return -ENOSPC;
args.minlen = args.maxlen = args.mp->m_ialloc_blks;
@@ -1705,10 +1705,13 @@ xfs_dialloc(
* If we have already hit the ceiling of inode blocks then clear
* okalloc so we scan all available agi structures for a free
* inode.
+ *
+ * Read rough value of mp->m_icount by percpu_counter_read_positive,
+ * which will sacrifice the preciseness but improve the performance.
*/
if (mp->m_maxicount &&
- percpu_counter_read(&mp->m_icount) + mp->m_ialloc_inos >
- mp->m_maxicount) {
+ percpu_counter_read_positive(&mp->m_icount) + mp->m_ialloc_inos
+ > mp->m_maxicount) {
noroom = 1;
okalloc = 0;
}
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index a56960dd1684..e5e9fc23f230 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1349,7 +1349,7 @@ __xfs_get_blocks(
sector_t iblock,
struct buffer_head *bh_result,
int create,
- int direct)
+ bool direct)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
@@ -1414,6 +1414,7 @@ __xfs_get_blocks(
if (error)
return error;
new = 1;
+
} else {
/*
* Delalloc reservations do not require a transaction,
@@ -1508,49 +1509,29 @@ xfs_get_blocks(
struct buffer_head *bh_result,
int create)
{
- return __xfs_get_blocks(inode, iblock, bh_result, create, 0);
+ return __xfs_get_blocks(inode, iblock, bh_result, create, false);
}
-STATIC int
+int
xfs_get_blocks_direct(
struct inode *inode,
sector_t iblock,
struct buffer_head *bh_result,
int create)
{
- return __xfs_get_blocks(inode, iblock, bh_result, create, 1);
+ return __xfs_get_blocks(inode, iblock, bh_result, create, true);
}
-/*
- * Complete a direct I/O write request.
- *
- * The ioend structure is passed from __xfs_get_blocks() to tell us what to do.
- * If no ioend exists (i.e. @private == NULL) then the write IO is an overwrite
- * wholly within the EOF and so there is nothing for us to do. Note that in this
- * case the completion can be called in interrupt context, whereas if we have an
- * ioend we will always be called in task context (i.e. from a workqueue).
- */
-STATIC void
-xfs_end_io_direct_write(
- struct kiocb *iocb,
+static void
+__xfs_end_io_direct_write(
+ struct inode *inode,
+ struct xfs_ioend *ioend,
loff_t offset,
- ssize_t size,
- void *private)
+ ssize_t size)
{
- struct inode *inode = file_inode(iocb->ki_filp);
- struct xfs_inode *ip = XFS_I(inode);
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_ioend *ioend = private;
-
- trace_xfs_gbmap_direct_endio(ip, offset, size,
- ioend ? ioend->io_type : 0, NULL);
+ struct xfs_mount *mp = XFS_I(inode)->i_mount;
- if (!ioend) {
- ASSERT(offset + size <= i_size_read(inode));
- return;
- }
-
- if (XFS_FORCED_SHUTDOWN(mp))
+ if (XFS_FORCED_SHUTDOWN(mp) || ioend->io_error)
goto out_end_io;
/*
@@ -1587,10 +1568,10 @@ xfs_end_io_direct_write(
* here can result in EOF moving backwards and Bad Things Happen when
* that occurs.
*/
- spin_lock(&ip->i_flags_lock);
+ spin_lock(&XFS_I(inode)->i_flags_lock);
if (offset + size > i_size_read(inode))
i_size_write(inode, offset + size);
- spin_unlock(&ip->i_flags_lock);
+ spin_unlock(&XFS_I(inode)->i_flags_lock);
/*
* If we are doing an append IO that needs to update the EOF on disk,
@@ -1607,6 +1588,98 @@ out_end_io:
return;
}
+/*
+ * Complete a direct I/O write request.
+ *
+ * The ioend structure is passed from __xfs_get_blocks() to tell us what to do.
+ * If no ioend exists (i.e. @private == NULL) then the write IO is an overwrite
+ * wholly within the EOF and so there is nothing for us to do. Note that in this
+ * case the completion can be called in interrupt context, whereas if we have an
+ * ioend we will always be called in task context (i.e. from a workqueue).
+ */
+STATIC void
+xfs_end_io_direct_write(
+ struct kiocb *iocb,
+ loff_t offset,
+ ssize_t size,
+ void *private)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct xfs_ioend *ioend = private;
+
+ trace_xfs_gbmap_direct_endio(XFS_I(inode), offset, size,
+ ioend ? ioend->io_type : 0, NULL);
+
+ if (!ioend) {
+ ASSERT(offset + size <= i_size_read(inode));
+ return;
+ }
+
+ __xfs_end_io_direct_write(inode, ioend, offset, size);
+}
+
+/*
+ * For DAX we need a mapping buffer callback for unwritten extent conversion
+ * when page faults allocate blocks and then zero them. Note that in this
+ * case the mapping indicated by the ioend may extend beyond EOF. We most
+ * definitely do not want to extend EOF here, so we trim back the ioend size to
+ * EOF.
+ */
+#ifdef CONFIG_FS_DAX
+void
+xfs_end_io_dax_write(
+ struct buffer_head *bh,
+ int uptodate)
+{
+ struct xfs_ioend *ioend = bh->b_private;
+ struct inode *inode = ioend->io_inode;
+ ssize_t size = ioend->io_size;
+
+ ASSERT(IS_DAX(ioend->io_inode));
+
+ /* if there was an error zeroing, then don't convert it */
+ if (!uptodate)
+ ioend->io_error = -EIO;
+
+ /*
+ * Trim update to EOF, so we don't extend EOF during unwritten extent
+ * conversion of partial EOF blocks.
+ */
+ spin_lock(&XFS_I(inode)->i_flags_lock);
+ if (ioend->io_offset + size > i_size_read(inode))
+ size = i_size_read(inode) - ioend->io_offset;
+ spin_unlock(&XFS_I(inode)->i_flags_lock);
+
+ __xfs_end_io_direct_write(inode, ioend, ioend->io_offset, size);
+
+}
+#else
+void xfs_end_io_dax_write(struct buffer_head *bh, int uptodate) { }
+#endif
+
+static inline ssize_t
+xfs_vm_do_dio(
+ struct inode *inode,
+ struct kiocb *iocb,
+ struct iov_iter *iter,
+ loff_t offset,
+ void (*endio)(struct kiocb *iocb,
+ loff_t offset,
+ ssize_t size,
+ void *private),
+ int flags)
+{
+ struct block_device *bdev;
+
+ if (IS_DAX(inode))
+ return dax_do_io(iocb, inode, iter, offset,
+ xfs_get_blocks_direct, endio, 0);
+
+ bdev = xfs_find_bdev_for_inode(inode);
+ return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
+ xfs_get_blocks_direct, endio, NULL, flags);
+}
+
STATIC ssize_t
xfs_vm_direct_IO(
struct kiocb *iocb,
@@ -1614,16 +1687,11 @@ xfs_vm_direct_IO(
loff_t offset)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
- struct block_device *bdev = xfs_find_bdev_for_inode(inode);
- if (iov_iter_rw(iter) == WRITE) {
- return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
- xfs_get_blocks_direct,
- xfs_end_io_direct_write, NULL,
- DIO_ASYNC_EXTEND);
- }
- return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
- xfs_get_blocks_direct, NULL, NULL, 0);
+ if (iov_iter_rw(iter) == WRITE)
+ return xfs_vm_do_dio(inode, iocb, iter, offset,
+ xfs_end_io_direct_write, DIO_ASYNC_EXTEND);
+ return xfs_vm_do_dio(inode, iocb, iter, offset, NULL, 0);
}
/*
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index ac644e0137a4..86afd1ac7895 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -53,7 +53,12 @@ typedef struct xfs_ioend {
} xfs_ioend_t;
extern const struct address_space_operations xfs_address_space_operations;
-extern int xfs_get_blocks(struct inode *, sector_t, struct buffer_head *, int);
+
+int xfs_get_blocks(struct inode *inode, sector_t offset,
+ struct buffer_head *map_bh, int create);
+int xfs_get_blocks_direct(struct inode *inode, sector_t offset,
+ struct buffer_head *map_bh, int create);
+void xfs_end_io_dax_write(struct buffer_head *bh, int uptodate);
extern void xfs_count_page_state(struct page *, int *, int *);
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index f9c1c64782d3..3fbf167cfb4c 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -380,23 +380,31 @@ xfs_attr3_root_inactive(
return error;
}
+/*
+ * xfs_attr_inactive kills all traces of an attribute fork on an inode. It
+ * removes both the on-disk and in-memory inode fork. Note that this also has to
+ * handle the condition of inodes without attributes but with an attribute fork
+ * configured, so we can't use xfs_inode_hasattr() here.
+ *
+ * The in-memory attribute fork is removed even on error.
+ */
int
-xfs_attr_inactive(xfs_inode_t *dp)
+xfs_attr_inactive(
+ struct xfs_inode *dp)
{
- xfs_trans_t *trans;
- xfs_mount_t *mp;
- int error;
+ struct xfs_trans *trans;
+ struct xfs_mount *mp;
+ int cancel_flags = 0;
+ int lock_mode = XFS_ILOCK_SHARED;
+ int error = 0;
mp = dp->i_mount;
ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
- xfs_ilock(dp, XFS_ILOCK_SHARED);
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
- return 0;
- }
- xfs_iunlock(dp, XFS_ILOCK_SHARED);
+ xfs_ilock(dp, lock_mode);
+ if (!XFS_IFORK_Q(dp))
+ goto out_destroy_fork;
+ xfs_iunlock(dp, lock_mode);
/*
* Start our first transaction of the day.
@@ -408,13 +416,18 @@ xfs_attr_inactive(xfs_inode_t *dp)
* the inode in every transaction to let it float upward through
* the log.
*/
+ lock_mode = 0;
trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
- if (error) {
- xfs_trans_cancel(trans, 0);
- return error;
- }
- xfs_ilock(dp, XFS_ILOCK_EXCL);
+ if (error)
+ goto out_cancel;
+
+ lock_mode = XFS_ILOCK_EXCL;
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT;
+ xfs_ilock(dp, lock_mode);
+
+ if (!XFS_IFORK_Q(dp))
+ goto out_cancel;
/*
* No need to make quota reservations here. We expect to release some
@@ -422,29 +435,31 @@ xfs_attr_inactive(xfs_inode_t *dp)
*/
xfs_trans_ijoin(trans, dp, 0);
- /*
- * Decide on what work routines to call based on the inode size.
- */
- if (!xfs_inode_hasattr(dp) ||
- dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
- error = 0;
- goto out;
+ /* invalidate and truncate the attribute fork extents */
+ if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) {
+ error = xfs_attr3_root_inactive(&trans, dp);
+ if (error)
+ goto out_cancel;
+
+ error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
+ if (error)
+ goto out_cancel;
}
- error = xfs_attr3_root_inactive(&trans, dp);
- if (error)
- goto out;
- error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
- if (error)
- goto out;
+ /* Reset the attribute fork - this also destroys the in-core fork */
+ xfs_attr_fork_remove(dp, trans);
error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
+ xfs_iunlock(dp, lock_mode);
return error;
-out:
- xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
+out_cancel:
+ xfs_trans_cancel(trans, cancel_flags);
+out_destroy_fork:
+ /* kill the in-core attr fork before we drop the inode lock */
+ if (dp->i_afp)
+ xfs_idestroy_fork(dp, XFS_ATTR_FORK);
+ if (lock_mode)
+ xfs_iunlock(dp, lock_mode);
return error;
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index a52bbd3abc7d..4a2965515ca8 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1133,14 +1133,29 @@ xfs_zero_remaining_bytes(
break;
ASSERT(imap.br_blockcount >= 1);
ASSERT(imap.br_startoff == offset_fsb);
+ ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+
+ if (imap.br_startblock == HOLESTARTBLOCK ||
+ imap.br_state == XFS_EXT_UNWRITTEN) {
+ /* skip the entire extent */
+ lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff +
+ imap.br_blockcount) - 1;
+ continue;
+ }
+
lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
if (lastoffset > endoff)
lastoffset = endoff;
- if (imap.br_startblock == HOLESTARTBLOCK)
- continue;
- ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
- if (imap.br_state == XFS_EXT_UNWRITTEN)
+
+ /* DAX can just zero the backing device directly */
+ if (IS_DAX(VFS_I(ip))) {
+ error = dax_zero_page_range(VFS_I(ip), offset,
+ lastoffset - offset + 1,
+ xfs_get_blocks_direct);
+ if (error)
+ return error;
continue;
+ }
error = xfs_buf_read_uncached(XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp,
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8121e75352ee..84b2421b22ae 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -79,14 +79,15 @@ xfs_rw_ilock_demote(
}
/*
- * xfs_iozero
+ * xfs_iozero clears the specified range supplied via the page cache (except in
+ * the DAX case). Writes through the page cache will allocate blocks over holes,
+ * though the callers usually map the holes first and avoid them. If a block is
+ * not completely zeroed, then it will be read from disk before being partially
+ * zeroed.
*
- * xfs_iozero clears the specified range of buffer supplied,
- * and marks all the affected blocks as valid and modified. If
- * an affected block is not allocated, it will be allocated. If
- * an affected block is not completely overwritten, and is not
- * valid before the operation, it will be read from disk before
- * being partially zeroed.
+ * In the DAX case, we can just directly write to the underlying pages. This
+ * will not allocate blocks, but will avoid holes and unwritten extents and so
+ * not do unnecessary work.
*/
int
xfs_iozero(
@@ -96,7 +97,8 @@ xfs_iozero(
{
struct page *page;
struct address_space *mapping;
- int status;
+ int status = 0;
+
mapping = VFS_I(ip)->i_mapping;
do {
@@ -108,23 +110,30 @@ xfs_iozero(
if (bytes > count)
bytes = count;
- status = pagecache_write_begin(NULL, mapping, pos, bytes,
- AOP_FLAG_UNINTERRUPTIBLE,
- &page, &fsdata);
- if (status)
- break;
+ if (IS_DAX(VFS_I(ip))) {
+ status = dax_zero_page_range(VFS_I(ip), pos, bytes,
+ xfs_get_blocks_direct);
+ if (status)
+ break;
+ } else {
+ status = pagecache_write_begin(NULL, mapping, pos, bytes,
+ AOP_FLAG_UNINTERRUPTIBLE,
+ &page, &fsdata);
+ if (status)
+ break;
- zero_user(page, offset, bytes);
+ zero_user(page, offset, bytes);
- status = pagecache_write_end(NULL, mapping, pos, bytes, bytes,
- page, fsdata);
- WARN_ON(status <= 0); /* can't return less than zero! */
+ status = pagecache_write_end(NULL, mapping, pos, bytes,
+ bytes, page, fsdata);
+ WARN_ON(status <= 0); /* can't return less than zero! */
+ status = 0;
+ }
pos += bytes;
count -= bytes;
- status = 0;
} while (count);
- return (-status);
+ return status;
}
int
@@ -284,7 +293,7 @@ xfs_file_read_iter(
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
- if (unlikely(ioflags & XFS_IO_ISDIRECT)) {
+ if ((ioflags & XFS_IO_ISDIRECT) && !IS_DAX(inode)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
@@ -378,7 +387,11 @@ xfs_file_splice_read(
trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
- ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
+ /* for dax, we need to avoid the page cache */
+ if (IS_DAX(VFS_I(ip)))
+ ret = default_file_splice_read(infilp, ppos, pipe, count, flags);
+ else
+ ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
@@ -672,7 +685,7 @@ xfs_file_dio_aio_write(
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
- if ((pos | count) & target->bt_logical_sectormask)
+ if (!IS_DAX(inode) && ((pos | count) & target->bt_logical_sectormask))
return -EINVAL;
/* "unaligned" here means not aligned to a filesystem block */
@@ -758,8 +771,11 @@ xfs_file_dio_aio_write(
out:
xfs_rw_iunlock(ip, iolock);
- /* No fallback to buffered IO on errors for XFS. */
- ASSERT(ret < 0 || ret == count);
+ /*
+ * No fallback to buffered IO on errors for XFS. DAX can result in
+ * partial writes, but direct IO will either complete fully or fail.
+ */
+ ASSERT(ret < 0 || ret == count || IS_DAX(VFS_I(ip)));
return ret;
}
@@ -842,7 +858,7 @@ xfs_file_write_iter(
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
- if (unlikely(iocb->ki_flags & IOCB_DIRECT))
+ if ((iocb->ki_flags & IOCB_DIRECT) || IS_DAX(inode))
ret = xfs_file_dio_aio_write(iocb, from);
else
ret = xfs_file_buffered_aio_write(iocb, from);
@@ -1063,17 +1079,6 @@ xfs_file_readdir(
return xfs_readdir(ip, ctx, bufsize);
}
-STATIC int
-xfs_file_mmap(
- struct file *filp,
- struct vm_area_struct *vma)
-{
- vma->vm_ops = &xfs_file_vm_ops;
-
- file_accessed(filp);
- return 0;
-}
-
/*
* This type is designed to indicate the type of offset we would like
* to search from page cache for xfs_seek_hole_data().
@@ -1454,48 +1459,83 @@ xfs_file_llseek(
* ordering of:
*
* mmap_sem (MM)
- * i_mmap_lock (XFS - truncate serialisation)
- * page_lock (MM)
- * i_lock (XFS - extent map serialisation)
+ * sb_start_pagefault(vfs, freeze)
+ * i_mmap_lock (XFS - truncate serialisation)
+ * page_lock (MM)
+ * i_lock (XFS - extent map serialisation)
+ */
+
+/*
+ * mmap()d file has taken write protection fault and is being made writable. We
+ * can set the page state up correctly for a writable page, which means we can
+ * do correct delalloc accounting (ENOSPC checking!) and unwritten extent
+ * mapping.
*/
STATIC int
-xfs_filemap_fault(
+xfs_filemap_page_mkwrite(
struct vm_area_struct *vma,
struct vm_fault *vmf)
{
- struct xfs_inode *ip = XFS_I(vma->vm_file->f_mapping->host);
- int error;
+ struct inode *inode = file_inode(vma->vm_file);
+ int ret;
- trace_xfs_filemap_fault(ip);
+ trace_xfs_filemap_page_mkwrite(XFS_I(inode));
- xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
- error = filemap_fault(vma, vmf);
- xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+ sb_start_pagefault(inode->i_sb);
+ file_update_time(vma->vm_file);
+ xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- return error;
+ if (IS_DAX(inode)) {
+ ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct,
+ xfs_end_io_dax_write);
+ } else {
+ ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);
+ ret = block_page_mkwrite_return(ret);
+ }
+
+ xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+ sb_end_pagefault(inode->i_sb);
+
+ return ret;
}
-/*
- * mmap()d file has taken write protection fault and is being made writable. We
- * can set the page state up correctly for a writable page, which means we can
- * do correct delalloc accounting (ENOSPC checking!) and unwritten extent
- * mapping.
- */
STATIC int
-xfs_filemap_page_mkwrite(
+xfs_filemap_fault(
struct vm_area_struct *vma,
struct vm_fault *vmf)
{
- struct xfs_inode *ip = XFS_I(vma->vm_file->f_mapping->host);
- int error;
+ struct xfs_inode *ip = XFS_I(file_inode(vma->vm_file));
+ int ret;
+
+ trace_xfs_filemap_fault(ip);
- trace_xfs_filemap_page_mkwrite(ip);
+ /* DAX can shortcut the normal fault path on write faults! */
+ if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(VFS_I(ip)))
+ return xfs_filemap_page_mkwrite(vma, vmf);
xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
- error = block_page_mkwrite(vma, vmf, xfs_get_blocks);
+ ret = filemap_fault(vma, vmf);
xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
- return error;
+ return ret;
+}
+
+static const struct vm_operations_struct xfs_file_vm_ops = {
+ .fault = xfs_filemap_fault,
+ .map_pages = filemap_map_pages,
+ .page_mkwrite = xfs_filemap_page_mkwrite,
+};
+
+STATIC int
+xfs_file_mmap(
+ struct file *filp,
+ struct vm_area_struct *vma)
+{
+ file_accessed(filp);
+ vma->vm_ops = &xfs_file_vm_ops;
+ if (IS_DAX(file_inode(filp)))
+ vma->vm_flags |= VM_MIXEDMAP;
+ return 0;
}
const struct file_operations xfs_file_operations = {
@@ -1526,9 +1566,3 @@ const struct file_operations xfs_dir_file_operations = {
#endif
.fsync = xfs_dir_fsync,
};
-
-static const struct vm_operations_struct xfs_file_vm_ops = {
- .fault = xfs_filemap_fault,
- .map_pages = filemap_map_pages,
- .page_mkwrite = xfs_filemap_page_mkwrite,
-};
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a17cf1f16498..17cd90c19634 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1946,21 +1946,17 @@ xfs_inactive(
/*
* If there are attributes associated with the file then blow them away
* now. The code calls a routine that recursively deconstructs the
- * attribute fork. We need to just commit the current transaction
- * because we can't use it for xfs_attr_inactive().
+ * attribute fork. If also blows away the in-core attribute fork.
*/
- if (ip->i_d.di_anextents > 0) {
- ASSERT(ip->i_d.di_forkoff != 0);
-
+ if (XFS_IFORK_Q(ip)) {
error = xfs_attr_inactive(ip);
if (error)
return;
}
- if (ip->i_afp)
- xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
+ ASSERT(!ip->i_afp);
ASSERT(ip->i_d.di_anextents == 0);
+ ASSERT(ip->i_d.di_forkoff == 0);
/*
* Free the inode.
@@ -2896,7 +2892,13 @@ xfs_rename_alloc_whiteout(
if (error)
return error;
- /* Satisfy xfs_bumplink that this is a real tmpfile */
+ /*
+ * Prepare the tmpfile inode as if it were created through the VFS.
+ * Otherwise, the link increment paths will complain about nlink 0->1.
+ * Drop the link count as done by d_tmpfile(), complete the inode setup
+ * and flag it as linkable.
+ */
+ drop_nlink(VFS_I(tmpfile));
xfs_finish_inode_setup(tmpfile);
VFS_I(tmpfile)->i_state |= I_LINKABLE;
@@ -3164,7 +3166,7 @@ xfs_rename(
* intermediate state on disk.
*/
if (wip) {
- ASSERT(wip->i_d.di_nlink == 0);
+ ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
error = xfs_bumplink(tp, wip);
if (error)
goto out_trans_abort;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index f4cd7204e236..3e8d32d41f35 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -851,7 +851,11 @@ xfs_setattr_size(
* to hope that the caller sees ENOMEM and retries the truncate
* operation.
*/
- error = block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
+ if (IS_DAX(inode))
+ error = dax_truncate_page(inode, newsize, xfs_get_blocks_direct);
+ else
+ error = block_truncate_page(inode->i_mapping, newsize,
+ xfs_get_blocks);
if (error)
return error;
truncate_setsize(inode, newsize);
@@ -1191,22 +1195,22 @@ xfs_diflags_to_iflags(
struct inode *inode,
struct xfs_inode *ip)
{
- if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+ uint16_t flags = ip->i_d.di_flags;
+
+ inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC |
+ S_NOATIME | S_DAX);
+
+ if (flags & XFS_DIFLAG_IMMUTABLE)
inode->i_flags |= S_IMMUTABLE;
- else
- inode->i_flags &= ~S_IMMUTABLE;
- if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+ if (flags & XFS_DIFLAG_APPEND)
inode->i_flags |= S_APPEND;
- else
- inode->i_flags &= ~S_APPEND;
- if (ip->i_d.di_flags & XFS_DIFLAG_SYNC)
+ if (flags & XFS_DIFLAG_SYNC)
inode->i_flags |= S_SYNC;
- else
- inode->i_flags &= ~S_SYNC;
- if (ip->i_d.di_flags & XFS_DIFLAG_NOATIME)
+ if (flags & XFS_DIFLAG_NOATIME)
inode->i_flags |= S_NOATIME;
- else
- inode->i_flags &= ~S_NOATIME;
+ /* XXX: Also needs an on-disk per inode flag! */
+ if (ip->i_mount->m_flags & XFS_MOUNT_DAX)
+ inode->i_flags |= S_DAX;
}
/*
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 02f827fab829..461e791efad7 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1100,14 +1100,18 @@ xfs_log_sbcount(xfs_mount_t *mp)
return xfs_sync_sb(mp, true);
}
+/*
+ * Deltas for the inode count are +/-64, hence we use a large batch size
+ * of 128 so we don't need to take the counter lock on every update.
+ */
+#define XFS_ICOUNT_BATCH 128
int
xfs_mod_icount(
struct xfs_mount *mp,
int64_t delta)
{
- /* deltas are +/-64, hence the large batch size of 128. */
- __percpu_counter_add(&mp->m_icount, delta, 128);
- if (percpu_counter_compare(&mp->m_icount, 0) < 0) {
+ __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+ if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
ASSERT(0);
percpu_counter_add(&mp->m_icount, -delta);
return -EINVAL;
@@ -1129,6 +1133,14 @@ xfs_mod_ifree(
return 0;
}
+/*
+ * Deltas for the block count can vary from 1 to very large, but lock contention
+ * only occurs on frequent small block count updates such as in the delayed
+ * allocation path for buffered writes (page a time updates). Hence we set
+ * a large batch count (1024) to minimise global counter updates except when
+ * we get near to ENOSPC and we have to be very accurate with our updates.
+ */
+#define XFS_FDBLOCKS_BATCH 1024
int
xfs_mod_fdblocks(
struct xfs_mount *mp,
@@ -1167,25 +1179,19 @@ xfs_mod_fdblocks(
* Taking blocks away, need to be more accurate the closer we
* are to zero.
*
- * batch size is set to a maximum of 1024 blocks - if we are
- * allocating of freeing extents larger than this then we aren't
- * going to be hammering the counter lock so a lock per update
- * is not a problem.
- *
* If the counter has a value of less than 2 * max batch size,
* then make everything serialise as we are real close to
* ENOSPC.
*/
-#define __BATCH 1024
- if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0)
+ if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH,
+ XFS_FDBLOCKS_BATCH) < 0)
batch = 1;
else
- batch = __BATCH;
-#undef __BATCH
+ batch = XFS_FDBLOCKS_BATCH;
__percpu_counter_add(&mp->m_fdblocks, delta, batch);
- if (percpu_counter_compare(&mp->m_fdblocks,
- XFS_ALLOC_SET_ASIDE(mp)) >= 0) {
+ if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp),
+ XFS_FDBLOCKS_BATCH) >= 0) {
/* we had space! */
return 0;
}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index df209c290258..7999e91cd49a 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -181,6 +181,8 @@ typedef struct xfs_mount {
allocator */
#define XFS_MOUNT_NOATTR2 (1ULL << 25) /* disable use of attr2 format */
+#define XFS_MOUNT_DAX (1ULL << 62) /* TEST ONLY! */
+
/*
* Default minimum read and write sizes.
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 5376dd406ba2..ce6506adab7b 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -55,7 +55,6 @@ struct xfs_trans;
typedef struct xfs_dqtrx {
struct xfs_dquot *qt_dquot; /* the dquot this refers to */
ulong qt_blk_res; /* blks reserved on a dquot */
- ulong qt_blk_res_used; /* blks used from the reservation */
ulong qt_ino_res; /* inode reserved on a dquot */
ulong qt_ino_res_used; /* inodes used from the reservation */
long qt_bcount_delta; /* dquot blk count changes */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 858e1e62bbaa..1fb16562c159 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -112,6 +112,8 @@ static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */
#define MNTOPT_DISCARD "discard" /* Discard unused blocks */
#define MNTOPT_NODISCARD "nodiscard" /* Do not discard unused blocks */
+#define MNTOPT_DAX "dax" /* Enable direct access to bdev pages */
+
/*
* Table driven mount option parser.
*
@@ -363,6 +365,10 @@ xfs_parseargs(
mp->m_flags |= XFS_MOUNT_DISCARD;
} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
mp->m_flags &= ~XFS_MOUNT_DISCARD;
+#ifdef CONFIG_FS_DAX
+ } else if (!strcmp(this_char, MNTOPT_DAX)) {
+ mp->m_flags |= XFS_MOUNT_DAX;
+#endif
} else {
xfs_warn(mp, "unknown mount option [%s].", this_char);
return -EINVAL;
@@ -452,8 +458,8 @@ done:
}
struct proc_xfs_info {
- int flag;
- char *str;
+ uint64_t flag;
+ char *str;
};
STATIC int
@@ -474,6 +480,7 @@ xfs_showargs(
{ XFS_MOUNT_GRPID, "," MNTOPT_GRPID },
{ XFS_MOUNT_DISCARD, "," MNTOPT_DISCARD },
{ XFS_MOUNT_SMALL_INUMS, "," MNTOPT_32BITINODE },
+ { XFS_MOUNT_DAX, "," MNTOPT_DAX },
{ 0, NULL }
};
static struct proc_xfs_info xfs_info_unset[] = {
@@ -1507,6 +1514,20 @@ xfs_fs_fill_super(
if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
sb->s_flags |= MS_I_VERSION;
+ if (mp->m_flags & XFS_MOUNT_DAX) {
+ xfs_warn(mp,
+ "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+ if (sb->s_blocksize != PAGE_SIZE) {
+ xfs_alert(mp,
+ "Filesystem block size invalid for DAX Turning DAX off.");
+ mp->m_flags &= ~XFS_MOUNT_DAX;
+ } else if (!sb->s_bdev->bd_disk->fops->direct_access) {
+ xfs_alert(mp,
+ "Block device does not support DAX Turning DAX off.");
+ mp->m_flags &= ~XFS_MOUNT_DAX;
+ }
+ }
+
error = xfs_mountfs(mp);
if (error)
goto out_filestream_unmount;
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 76a16df55ef7..ce78534a047e 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -90,8 +90,9 @@ xfs_trans_dup_dqinfo(
xfs_trans_t *ntp)
{
xfs_dqtrx_t *oq, *nq;
- int i,j;
+ int i, j;
xfs_dqtrx_t *oqa, *nqa;
+ ulong blk_res_used;
if (!otp->t_dqinfo)
return;
@@ -102,18 +103,23 @@ xfs_trans_dup_dqinfo(
* Because the quota blk reservation is carried forward,
* it is also necessary to carry forward the DQ_DIRTY flag.
*/
- if(otp->t_flags & XFS_TRANS_DQ_DIRTY)
+ if (otp->t_flags & XFS_TRANS_DQ_DIRTY)
ntp->t_flags |= XFS_TRANS_DQ_DIRTY;
for (j = 0; j < XFS_QM_TRANS_DQTYPES; j++) {
oqa = otp->t_dqinfo->dqs[j];
nqa = ntp->t_dqinfo->dqs[j];
for (i = 0; i < XFS_QM_TRANS_MAXDQS; i++) {
+ blk_res_used = 0;
+
if (oqa[i].qt_dquot == NULL)
break;
oq = &oqa[i];
nq = &nqa[i];
+ if (oq->qt_blk_res && oq->qt_bcount_delta > 0)
+ blk_res_used = oq->qt_bcount_delta;
+
nq->qt_dquot = oq->qt_dquot;
nq->qt_bcount_delta = nq->qt_icount_delta = 0;
nq->qt_rtbcount_delta = 0;
@@ -121,8 +127,8 @@ xfs_trans_dup_dqinfo(
/*
* Transfer whatever is left of the reservations.
*/
- nq->qt_blk_res = oq->qt_blk_res - oq->qt_blk_res_used;
- oq->qt_blk_res = oq->qt_blk_res_used;
+ nq->qt_blk_res = oq->qt_blk_res - blk_res_used;
+ oq->qt_blk_res = blk_res_used;
nq->qt_rtblk_res = oq->qt_rtblk_res -
oq->qt_rtblk_res_used;
@@ -239,10 +245,6 @@ xfs_trans_mod_dquot(
* disk blocks used.
*/
case XFS_TRANS_DQ_BCOUNT:
- if (qtrx->qt_blk_res && delta > 0) {
- qtrx->qt_blk_res_used += (ulong)delta;
- ASSERT(qtrx->qt_blk_res >= qtrx->qt_blk_res_used);
- }
qtrx->qt_bcount_delta += delta;
break;
@@ -423,15 +425,19 @@ xfs_trans_apply_dquot_deltas(
* reservation that a transaction structure knows of.
*/
if (qtrx->qt_blk_res != 0) {
- if (qtrx->qt_blk_res != qtrx->qt_blk_res_used) {
- if (qtrx->qt_blk_res >
- qtrx->qt_blk_res_used)
+ ulong blk_res_used = 0;
+
+ if (qtrx->qt_bcount_delta > 0)
+ blk_res_used = qtrx->qt_bcount_delta;
+
+ if (qtrx->qt_blk_res != blk_res_used) {
+ if (qtrx->qt_blk_res > blk_res_used)
dqp->q_res_bcount -= (xfs_qcnt_t)
(qtrx->qt_blk_res -
- qtrx->qt_blk_res_used);
+ blk_res_used);
else
dqp->q_res_bcount -= (xfs_qcnt_t)
- (qtrx->qt_blk_res_used -
+ (blk_res_used -
qtrx->qt_blk_res);
}
} else {
generated by cgit v1.2.3 (git 2.0.4) at 2025-02-13 08:33:20 +0000