summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c3
-rw-r--r--fs/buffer.c2
-rw-r--r--fs/crypto/keyinfo.c3
-rw-r--r--fs/crypto/policy.c5
-rw-r--r--fs/dax.c243
-rw-r--r--fs/ext2/inode.c3
-rw-r--r--fs/ext4/file.c48
-rw-r--r--fs/notify/mark.c12
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c3
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c9
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.h3
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c14
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.h3
-rw-r--r--fs/xfs/xfs_fsops.c14
-rw-r--r--fs/xfs/xfs_icache.c3
-rw-r--r--fs/xfs/xfs_refcount_item.c3
-rw-r--r--fs/xfs/xfs_sysfs.c4
17 files changed, 216 insertions, 159 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6254cee..5db5d13 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -328,6 +328,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
struct file *file = iocb->ki_filp;
struct inode *inode = bdev_file_inode(file);
struct block_device *bdev = I_BDEV(inode);
+ struct blk_plug plug;
struct blkdev_dio *dio;
struct bio *bio;
bool is_read = (iov_iter_rw(iter) == READ);
@@ -353,6 +354,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
dio->multi_bio = false;
dio->should_dirty = is_read && (iter->type == ITER_IOVEC);
+ blk_start_plug(&plug);
for (;;) {
bio->bi_bdev = bdev;
bio->bi_iter.bi_sector = pos >> 9;
@@ -394,6 +396,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
submit_bio(bio);
bio = bio_alloc(GFP_KERNEL, nr_pages);
}
+ blk_finish_plug(&plug);
if (!dio->is_sync)
return -EIOCBQUEUED;
diff --git a/fs/buffer.c b/fs/buffer.c
index d21771f..0e87401 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1660,7 +1660,7 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
head = page_buffers(page);
bh = head;
do {
- if (!buffer_mapped(bh))
+ if (!buffer_mapped(bh) || (bh->b_blocknr < block))
goto next;
if (bh->b_blocknr >= block + len)
break;
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 6eeea1d..95cd4c3 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -248,7 +248,8 @@ retry:
goto out;
if (fscrypt_dummy_context_enabled(inode)) {
- memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
+ memset(raw_key, 0x42, keysize/2);
+ memset(raw_key+keysize/2, 0x24, keysize - (keysize/2));
goto got_key;
}
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 6ed7c2e..d6cd7ea 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -179,6 +179,11 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
BUG_ON(1);
}
+ /* No restrictions on file types which are never encrypted */
+ if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
+ !S_ISLNK(child->i_mode))
+ return 1;
+
/* no restrictions if the parent directory is not encrypted */
if (!parent->i_sb->s_cop->is_encrypted(parent))
return 1;
diff --git a/fs/dax.c b/fs/dax.c
index a8732fb..5c74f60 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -451,16 +451,37 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
}
+static int __dax_invalidate_mapping_entry(struct address_space *mapping,
+ pgoff_t index, bool trunc)
+{
+ int ret = 0;
+ void *entry;
+ struct radix_tree_root *page_tree = &mapping->page_tree;
+
+ spin_lock_irq(&mapping->tree_lock);
+ entry = get_unlocked_mapping_entry(mapping, index, NULL);
+ if (!entry || !radix_tree_exceptional_entry(entry))
+ goto out;
+ if (!trunc &&
+ (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+ radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
+ goto out;
+ radix_tree_delete(page_tree, index);
+ mapping->nrexceptional--;
+ ret = 1;
+out:
+ put_unlocked_mapping_entry(mapping, index, entry);
+ spin_unlock_irq(&mapping->tree_lock);
+ return ret;
+}
/*
* Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
* entry to get unlocked before deleting it.
*/
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
- void *entry;
+ int ret = __dax_invalidate_mapping_entry(mapping, index, true);
- spin_lock_irq(&mapping->tree_lock);
- entry = get_unlocked_mapping_entry(mapping, index, NULL);
/*
* This gets called from truncate / punch_hole path. As such, the caller
* must hold locks protecting against concurrent modifications of the
@@ -468,16 +489,46 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
* caller has seen exceptional entry for this index, we better find it
* at that index as well...
*/
- if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
- spin_unlock_irq(&mapping->tree_lock);
- return 0;
- }
- radix_tree_delete(&mapping->page_tree, index);
+ WARN_ON_ONCE(!ret);
+ return ret;
+}
+
+/*
+ * Invalidate exceptional DAX entry if easily possible. This handles DAX
+ * entries for invalidate_inode_pages() so we evict the entry only if we can
+ * do so without blocking.
+ */
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+ int ret = 0;
+ void *entry, **slot;
+ struct radix_tree_root *page_tree = &mapping->page_tree;
+
+ spin_lock_irq(&mapping->tree_lock);
+ entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
+ if (!entry || !radix_tree_exceptional_entry(entry) ||
+ slot_locked(mapping, slot))
+ goto out;
+ if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+ radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+ goto out;
+ radix_tree_delete(page_tree, index);
mapping->nrexceptional--;
+ ret = 1;
+out:
spin_unlock_irq(&mapping->tree_lock);
- dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+ if (ret)
+ dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+ return ret;
+}
- return 1;
+/*
+ * Invalidate exceptional DAX entry if it is clean.
+ */
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+ pgoff_t index)
+{
+ return __dax_invalidate_mapping_entry(mapping, index, false);
}
/*
@@ -488,15 +539,16 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
* otherwise it will simply fall out of the page cache under memory
* pressure without ever having been dirtied.
*/
-static int dax_load_hole(struct address_space *mapping, void *entry,
+static int dax_load_hole(struct address_space *mapping, void **entry,
struct vm_fault *vmf)
{
struct page *page;
+ int ret;
/* Hole page already exists? Return it... */
- if (!radix_tree_exceptional_entry(entry)) {
- vmf->page = entry;
- return VM_FAULT_LOCKED;
+ if (!radix_tree_exceptional_entry(*entry)) {
+ page = *entry;
+ goto out;
}
/* This will replace locked radix tree entry with a hole page */
@@ -504,8 +556,17 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
vmf->gfp_mask | __GFP_ZERO);
if (!page)
return VM_FAULT_OOM;
+ out:
vmf->page = page;
- return VM_FAULT_LOCKED;
+ ret = finish_fault(vmf);
+ vmf->page = NULL;
+ *entry = page;
+ if (!ret) {
+ /* Grab reference for PTE that is now referencing the page */
+ get_page(page);
+ return VM_FAULT_NOPAGE;
+ }
+ return ret;
}
static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
@@ -934,6 +995,17 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
return -EIO;
+ /*
+ * Write can allocate block for an area which has a hole page mapped
+ * into page tables. We have to tear down these mappings so that data
+ * written by write(2) is visible in mmap.
+ */
+ if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+ invalidate_inode_pages2_range(inode->i_mapping,
+ pos >> PAGE_SHIFT,
+ (end - 1) >> PAGE_SHIFT);
+ }
+
while (pos < end) {
unsigned offset = pos & (PAGE_SIZE - 1);
struct blk_dax_ctl dax = { 0 };
@@ -992,23 +1064,6 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
if (iov_iter_rw(iter) == WRITE)
flags |= IOMAP_WRITE;
- /*
- * Yes, even DAX files can have page cache attached to them: A zeroed
- * page is inserted into the pagecache when we have to serve a write
- * fault on a hole. It should never be dirtied and can simply be
- * dropped from the pagecache once we get real data for the page.
- *
- * XXX: This is racy against mmap, and there's nothing we can do about
- * it. We'll eventually need to shift this down even further so that
- * we can check if we allocated blocks over a hole first.
- */
- if (mapping->nrpages) {
- ret = invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT,
- (pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT);
- WARN_ON_ONCE(ret);
- }
-
while (iov_iter_count(iter)) {
ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
iter, dax_iomap_actor);
@@ -1023,6 +1078,15 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
}
EXPORT_SYMBOL_GPL(dax_iomap_rw);
+static int dax_fault_return(int error)
+{
+ if (error == 0)
+ return VM_FAULT_NOPAGE;
+ if (error == -ENOMEM)
+ return VM_FAULT_OOM;
+ return VM_FAULT_SIGBUS;
+}
+
/**
* dax_iomap_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
@@ -1055,12 +1119,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
if (pos >= i_size_read(inode))
return VM_FAULT_SIGBUS;
- entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
- if (IS_ERR(entry)) {
- error = PTR_ERR(entry);
- goto out;
- }
-
if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
flags |= IOMAP_WRITE;
@@ -1071,9 +1129,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
*/
error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
if (error)
- goto unlock_entry;
+ return dax_fault_return(error);
if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
- error = -EIO; /* fs corruption? */
+ vmf_ret = dax_fault_return(-EIO); /* fs corruption? */
+ goto finish_iomap;
+ }
+
+ entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+ if (IS_ERR(entry)) {
+ vmf_ret = dax_fault_return(PTR_ERR(entry));
goto finish_iomap;
}
@@ -1096,13 +1160,13 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
}
if (error)
- goto finish_iomap;
+ goto error_unlock_entry;
__SetPageUptodate(vmf->cow_page);
vmf_ret = finish_fault(vmf);
if (!vmf_ret)
vmf_ret = VM_FAULT_DONE_COW;
- goto finish_iomap;
+ goto unlock_entry;
}
switch (iomap.type) {
@@ -1114,12 +1178,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
}
error = dax_insert_mapping(mapping, iomap.bdev, sector,
PAGE_SIZE, &entry, vma, vmf);
+ /* -EBUSY is fine, somebody else faulted on the same PTE */
+ if (error == -EBUSY)
+ error = 0;
break;
case IOMAP_UNWRITTEN:
case IOMAP_HOLE:
if (!(vmf->flags & FAULT_FLAG_WRITE)) {
- vmf_ret = dax_load_hole(mapping, entry, vmf);
- break;
+ vmf_ret = dax_load_hole(mapping, &entry, vmf);
+ goto unlock_entry;
}
/*FALLTHRU*/
default:
@@ -1128,31 +1195,25 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
break;
}
+ error_unlock_entry:
+ vmf_ret = dax_fault_return(error) | major;
+ unlock_entry:
+ put_locked_mapping_entry(mapping, vmf->pgoff, entry);
finish_iomap:
if (ops->iomap_end) {
- if (error || (vmf_ret & VM_FAULT_ERROR)) {
- /* keep previous error */
- ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
- &iomap);
- } else {
- error = ops->iomap_end(inode, pos, PAGE_SIZE,
- PAGE_SIZE, flags, &iomap);
- }
- }
- unlock_entry:
- if (vmf_ret != VM_FAULT_LOCKED || error)
- put_locked_mapping_entry(mapping, vmf->pgoff, entry);
- out:
- if (error == -ENOMEM)
- return VM_FAULT_OOM | major;
- /* -EBUSY is fine, somebody else faulted on the same PTE */
- if (error < 0 && error != -EBUSY)
- return VM_FAULT_SIGBUS | major;
- if (vmf_ret) {
- WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
- return vmf_ret;
+ int copied = PAGE_SIZE;
+
+ if (vmf_ret & VM_FAULT_ERROR)
+ copied = 0;
+ /*
+ * The fault is done by now and there's no way back (other
+ * thread may be already happily using PTE we have installed).
+ * Just ignore error from ->iomap_end since we cannot do much
+ * with it.
+ */
+ ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
}
- return VM_FAULT_NOPAGE | major;
+ return vmf_ret;
}
EXPORT_SYMBOL_GPL(dax_iomap_fault);
@@ -1277,16 +1338,6 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
goto fallback;
/*
- * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
- * PMD or a HZP entry. If it can't (because a 4k page is already in
- * the tree, for instance), it will return -EEXIST and we just fall
- * back to 4k entries.
- */
- entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
- if (IS_ERR(entry))
- goto fallback;
-
- /*
* Note that we don't use iomap_apply here. We aren't doing I/O, only
* setting up a mapping, so really we're using iomap_begin() as a way
* to look up our filesystem block.
@@ -1294,10 +1345,21 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pos = (loff_t)pgoff << PAGE_SHIFT;
error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
if (error)
- goto unlock_entry;
+ goto fallback;
+
if (iomap.offset + iomap.length < pos + PMD_SIZE)
goto finish_iomap;
+ /*
+ * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+ * PMD or a HZP entry. If it can't (because a 4k page is already in
+ * the tree, for instance), it will return -EEXIST and we just fall
+ * back to 4k entries.
+ */
+ entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+ if (IS_ERR(entry))
+ goto finish_iomap;
+
vmf.pgoff = pgoff;
vmf.flags = flags;
vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
@@ -1310,7 +1372,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
case IOMAP_UNWRITTEN:
case IOMAP_HOLE:
if (WARN_ON_ONCE(write))
- goto finish_iomap;
+ goto unlock_entry;
result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
&entry);
break;
@@ -1319,20 +1381,23 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
break;
}
+ unlock_entry:
+ put_locked_mapping_entry(mapping, pgoff, entry);
finish_iomap:
if (ops->iomap_end) {
- if (result == VM_FAULT_FALLBACK) {
- ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags,
- &iomap);
- } else {
- error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE,
- iomap_flags, &iomap);
- if (error)
- result = VM_FAULT_FALLBACK;
- }
+ int copied = PMD_SIZE;
+
+ if (result == VM_FAULT_FALLBACK)
+ copied = 0;
+ /*
+ * The fault is done by now and there's no way back (other
+ * thread may be already happily using PMD we have installed).
+ * Just ignore error from ->iomap_end since we cannot do much
+ * with it.
+ */
+ ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
+ &iomap);
}
- unlock_entry:
- put_locked_mapping_entry(mapping, pgoff, entry);
fallback:
if (result == VM_FAULT_FALLBACK) {
split_huge_pmd(vma, pmd, address);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0093ea2..f073bfc 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -751,9 +751,8 @@ static int ext2_get_blocks(struct inode *inode,
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
- } else {
- *new = true;
}
+ *new = true;
ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
mutex_unlock(&ei->truncate_mutex);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b5f1844..d663d3d 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -258,7 +258,6 @@ out:
static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int result;
- handle_t *handle = NULL;
struct inode *inode = file_inode(vma->vm_file);
struct super_block *sb = inode->i_sb;
bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -266,24 +265,12 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
if (write) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
- handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
- EXT4_DATA_TRANS_BLOCKS(sb));
- } else
- down_read(&EXT4_I(inode)->i_mmap_sem);
-
- if (IS_ERR(handle))
- result = VM_FAULT_SIGBUS;
- else
- result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
-
- if (write) {
- if (!IS_ERR(handle))
- ext4_journal_stop(handle);
- up_read(&EXT4_I(inode)->i_mmap_sem);
+ }
+ down_read(&EXT4_I(inode)->i_mmap_sem);
+ result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+ if (write)
sb_end_pagefault(sb);
- } else
- up_read(&EXT4_I(inode)->i_mmap_sem);
return result;
}
@@ -292,7 +279,6 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, unsigned int flags)
{
int result;
- handle_t *handle = NULL;
struct inode *inode = file_inode(vma->vm_file);
struct super_block *sb = inode->i_sb;
bool write = flags & FAULT_FLAG_WRITE;
@@ -300,27 +286,13 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
if (write) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
- down_read(&EXT4_I(inode)->i_mmap_sem);
- handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
- ext4_chunk_trans_blocks(inode,
- PMD_SIZE / PAGE_SIZE));
- } else
- down_read(&EXT4_I(inode)->i_mmap_sem);
-
- if (IS_ERR(handle))
- result = VM_FAULT_SIGBUS;
- else {
- result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
- &ext4_iomap_ops);
}
-
- if (write) {
- if (!IS_ERR(handle))
- ext4_journal_stop(handle);
- up_read(&EXT4_I(inode)->i_mmap_sem);
+ down_read(&EXT4_I(inode)->i_mmap_sem);
+ result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
+ &ext4_iomap_ops);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+ if (write)
sb_end_pagefault(sb);
- } else
- up_read(&EXT4_I(inode)->i_mmap_sem);
return result;
}
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d3fea0b..6043306 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -510,18 +510,6 @@ void fsnotify_detach_group_marks(struct fsnotify_group *group)
}
}
-void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old)
-{
- assert_spin_locked(&old->lock);
- new->inode = old->inode;
- new->mnt = old->mnt;
- if (old->group)
- fsnotify_get_group(old->group);
- new->group = old->group;
- new->mask = old->mask;
- new->free_mark = old->free_mark;
-}
-
/*
* Nothing fancy, just initialize lists and locks and counters.
*/
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index e5ebc37..d346d42 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -256,6 +256,9 @@ xfs_ag_resv_init(
goto out;
}
+ ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
+ xfs_perag_resv(pag, XFS_AG_RESV_AGFL)->ar_reserved <=
+ pag->pagf_freeblks + pag->pagf_flcount);
out:
return error;
}
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 6fb2215..50add52 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -409,13 +409,14 @@ xfs_refcountbt_calc_size(
*/
xfs_extlen_t
xfs_refcountbt_max_size(
- struct xfs_mount *mp)
+ struct xfs_mount *mp,
+ xfs_agblock_t agblocks)
{
/* Bail out if we're uninitialized, which can happen in mkfs. */
if (mp->m_refc_mxr[0] == 0)
return 0;
- return xfs_refcountbt_calc_size(mp, mp->m_sb.sb_agblocks);
+ return xfs_refcountbt_calc_size(mp, agblocks);
}
/*
@@ -430,22 +431,24 @@ xfs_refcountbt_calc_reserves(
{
struct xfs_buf *agbp;
struct xfs_agf *agf;
+ xfs_agblock_t agblocks;
xfs_extlen_t tree_len;
int error;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return 0;
- *ask += xfs_refcountbt_max_size(mp);
error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
if (error)
return error;
agf = XFS_BUF_TO_AGF(agbp);
+ agblocks = be32_to_cpu(agf->agf_length);
tree_len = be32_to_cpu(agf->agf_refcount_blocks);
xfs_buf_relse(agbp);
+ *ask += xfs_refcountbt_max_size(mp, agblocks);
*used += tree_len;
return error;
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index 3be7768..9db008b 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -66,7 +66,8 @@ extern void xfs_refcountbt_compute_maxlevels(struct xfs_mount *mp);
extern xfs_extlen_t xfs_refcountbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
-extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp);
+extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp,
+ xfs_agblock_t agblocks);
extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index de25771..74e5a54 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -550,13 +550,14 @@ xfs_rmapbt_calc_size(
*/
xfs_extlen_t
xfs_rmapbt_max_size(
- struct xfs_mount *mp)
+ struct xfs_mount *mp,
+ xfs_agblock_t agblocks)
{
/* Bail out if we're uninitialized, which can happen in mkfs. */
if (mp->m_rmap_mxr[0] == 0)
return 0;
- return xfs_rmapbt_calc_size(mp, mp->m_sb.sb_agblocks);
+ return xfs_rmapbt_calc_size(mp, agblocks);
}
/*
@@ -571,25 +572,24 @@ xfs_rmapbt_calc_reserves(
{
struct xfs_buf *agbp;
struct xfs_agf *agf;
- xfs_extlen_t pool_len;
+ xfs_agblock_t agblocks;
xfs_extlen_t tree_len;
int error;
if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
return 0;
- /* Reserve 1% of the AG or enough for 1 block per record. */
- pool_len = max(mp->m_sb.sb_agblocks / 100, xfs_rmapbt_max_size(mp));
- *ask += pool_len;
-
error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
if (error)
return error;
agf = XFS_BUF_TO_AGF(agbp);
+ agblocks = be32_to_cpu(agf->agf_length);
tree_len = be32_to_cpu(agf->agf_rmap_blocks);
xfs_buf_relse(agbp);
+ /* Reserve 1% of the AG or enough for 1 block per record. */
+ *ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks));
*used += tree_len;
return error;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 2a9ac47..19c08e9 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -60,7 +60,8 @@ extern void xfs_rmapbt_compute_maxlevels(struct xfs_mount *mp);
extern xfs_extlen_t xfs_rmapbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
-extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp);
+extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
+ xfs_agblock_t agblocks);
extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp,
xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 93d12fa..242e809 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -631,6 +631,20 @@ xfs_growfs_data_private(
xfs_set_low_space_thresholds(mp);
mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
+ /*
+ * If we expanded the last AG, free the per-AG reservation
+ * so we can reinitialize it with the new size.
+ */
+ if (new) {
+ struct xfs_perag *pag;
+
+ pag = xfs_perag_get(mp, agno);
+ error = xfs_ag_resv_free(pag);
+ xfs_perag_put(pag);
+ if (error)
+ goto out;
+ }
+
/* Reserve AG metadata blocks. */
error = xfs_fs_reserve_ag_blocks(mp);
if (error && error != -ENOSPC)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index ff4d631..70ca4f6 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1597,7 +1597,8 @@ xfs_inode_free_cowblocks(
* If the mapping is dirty or under writeback we cannot touch the
* CoW fork. Leave it alone if we're in the midst of a directio.
*/
- if (mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
+ if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) ||
+ mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
atomic_read(&VFS_I(ip)->i_dio_count))
return 0;
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index fe86a66..6e4c744 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -526,13 +526,14 @@ xfs_cui_recover(
xfs_refcount_finish_one_cleanup(tp, rcur, error);
error = xfs_defer_finish(&tp, &dfops, NULL);
if (error)
- goto abort_error;
+ goto abort_defer;
set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
error = xfs_trans_commit(tp);
return error;
abort_error:
xfs_refcount_finish_one_cleanup(tp, rcur, error);
+abort_defer:
xfs_defer_cancel(&dfops);
xfs_trans_cancel(tp);
return error;
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 276d302..de6195e 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -396,7 +396,7 @@ max_retries_show(
int retries;
struct xfs_error_cfg *cfg = to_error_cfg(kobject);
- if (cfg->retry_timeout == XFS_ERR_RETRY_FOREVER)
+ if (cfg->max_retries == XFS_ERR_RETRY_FOREVER)
retries = -1;
else
retries = cfg->max_retries;
@@ -422,7 +422,7 @@ max_retries_store(
return -EINVAL;
if (val == -1)
- cfg->retry_timeout = XFS_ERR_RETRY_FOREVER;
+ cfg->max_retries = XFS_ERR_RETRY_FOREVER;
else
cfg->max_retries = val;
return count;
OpenPOWER on IntegriCloud