mirror of
https://github.com/torvalds/linux.git
synced 2024-12-28 13:51:44 +00:00
dax: fix conversion of holes to PMDs
When we get a DAX PMD fault for a write it is possible that there could be some number of 4k zero pages already present for the same range that were inserted to service reads from a hole. These 4k zero pages need to be unmapped from the VMAs and removed from the struct address_space radix tree before the real DAX PMD entry can be inserted. For PTE faults this same use case also exists and is handled by a combination of unmap_mapping_range() to unmap the VMAs and delete_from_page_cache() to remove the page from the address_space radix tree. For PMD faults we do have a call to unmap_mapping_range() (protected by a buffer_new() check), but nothing clears out the radix tree entry. The buffer_new() check is also incorrect as the current ext4 and XFS filesystem code will never return a buffer_head with BH_New set, even when allocating new blocks over a hole. Instead the filesystem will zero the blocks manually and return a buffer_head with only BH_Mapped set. Fix this situation by removing the buffer_new() check and adding a call to truncate_inode_pages_range() to clear out the radix tree entries before we insert the DAX PMD. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reported-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeff Layton <jlayton@poochiereds.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
d4bbe7068b
commit
de14b9cb5e
20
fs/dax.c
20
fs/dax.c
@ -589,6 +589,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
|
||||
bool write = flags & FAULT_FLAG_WRITE;
|
||||
struct block_device *bdev;
|
||||
pgoff_t size, pgoff;
|
||||
loff_t lstart, lend;
|
||||
sector_t block;
|
||||
int result = 0;
|
||||
|
||||
@ -643,15 +644,13 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
|
||||
goto fallback;
|
||||
}
|
||||
|
||||
/*
|
||||
* If we allocated new storage, make sure no process has any
|
||||
* zero pages covering this hole
|
||||
*/
|
||||
if (buffer_new(&bh)) {
|
||||
i_mmap_unlock_read(mapping);
|
||||
unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
|
||||
i_mmap_lock_read(mapping);
|
||||
}
|
||||
/* make sure no process has any zero pages covering this hole */
|
||||
lstart = pgoff << PAGE_SHIFT;
|
||||
lend = lstart + PMD_SIZE - 1; /* inclusive */
|
||||
i_mmap_unlock_read(mapping);
|
||||
unmap_mapping_range(mapping, lstart, PMD_SIZE, 0);
|
||||
truncate_inode_pages_range(mapping, lstart, lend);
|
||||
i_mmap_lock_read(mapping);
|
||||
|
||||
/*
|
||||
* If a truncate happened while we were allocating blocks, we may
|
||||
@ -665,7 +664,8 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
|
||||
goto out;
|
||||
}
|
||||
if ((pgoff | PG_PMD_COLOUR) >= size) {
|
||||
dax_pmd_dbg(&bh, address, "pgoff unaligned");
|
||||
dax_pmd_dbg(&bh, address,
|
||||
"offset + huge page size > file size");
|
||||
goto fallback;
|
||||
}
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user