#include <linux/uio.h>
#include <linux/vmstat.h>
+ /*
+ * dax_clear_blocks() is called from within transaction context from XFS,
+ * and hence this means the stack from this point must follow GFP_NOFS
+ * semantics for all operations.
+ */
int dax_clear_blocks(struct inode *inode, sector_t block, long size)
{
struct block_device *bdev = inode->i_sb->s_bdev;
static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
+ struct address_space *mapping = inode->i_mapping;
sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
unsigned long vaddr = (unsigned long)vmf->virtual_address;
void __pmem *addr;
pgoff_t size;
int error;
+ i_mmap_lock_read(mapping);
+
/*
* Check truncate didn't happen while we were allocating a block.
* If it did, this block may or may not be still allocated to the
error = vm_insert_mixed(vma, vaddr, pfn);
out:
+ i_mmap_unlock_read(mapping);
+
return error;
}
* from a read fault and we've raced with a truncate
*/
error = -EIO;
- goto unlock;
+ goto unlock_page;
}
- } else {
- i_mmap_lock_write(mapping);
}
error = get_block(inode, block, &bh, 0);
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO; /* fs corruption? */
if (error)
- goto unlock;
+ goto unlock_page;
if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
if (vmf->flags & FAULT_FLAG_WRITE) {
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO;
if (error)
- goto unlock;
+ goto unlock_page;
} else {
- i_mmap_unlock_write(mapping);
return dax_load_hole(mapping, page, vmf);
}
}
else
clear_user_highpage(new_page, vaddr);
if (error)
- goto unlock;
+ goto unlock_page;
vmf->page = page;
if (!page) {
+ i_mmap_lock_read(mapping);
/* Check we didn't race with truncate */
size = (i_size_read(inode) + PAGE_SIZE - 1) >>
PAGE_SHIFT;
if (vmf->pgoff >= size) {
+ i_mmap_unlock_read(mapping);
error = -EIO;
- goto unlock;
+ goto out;
}
}
return VM_FAULT_LOCKED;
WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
}
- if (!page)
- i_mmap_unlock_write(mapping);
out:
if (error == -ENOMEM)
return VM_FAULT_OOM | major;
return VM_FAULT_SIGBUS | major;
return VM_FAULT_NOPAGE | major;
- unlock:
+ unlock_page:
if (page) {
unlock_page(page);
page_cache_release(page);
- } else {
- i_mmap_unlock_write(mapping);
}
-
goto out;
}
EXPORT_SYMBOL(__dax_fault);
block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
bh.b_size = PMD_SIZE;
- i_mmap_lock_write(mapping);
length = get_block(inode, block, &bh, write);
if (length)
return VM_FAULT_SIGBUS;
+ i_mmap_lock_read(mapping);
/*
* If the filesystem isn't willing to tell us the length of a hole,
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
goto fallback;
- if (buffer_unwritten(&bh) || buffer_new(&bh)) {
- int i;
- for (i = 0; i < PTRS_PER_PMD; i++)
- clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
- wmb_pmem();
- count_vm_event(PGMAJFAULT);
- mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
- result |= VM_FAULT_MAJOR;
- }
-
/*
* If we allocated new storage, make sure no process has any
* zero pages covering this hole
*/
if (buffer_new(&bh)) {
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_read(mapping);
unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
- i_mmap_lock_write(mapping);
+ i_mmap_lock_read(mapping);
}
/*
if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
goto fallback;
+ if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+ int i;
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
+ wmb_pmem();
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ result |= VM_FAULT_MAJOR;
+ }
+
result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
}
out:
+ i_mmap_unlock_read(mapping);
+
if (buffer_unwritten(&bh))
complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
- i_mmap_unlock_write(mapping);
-
return result;
fallback:
}
/*
- * All metadata updates are logged, which means that we just have
- * to flush the log up to the latest LSN that touched the inode.
+ * All metadata updates are logged, which means that we just have to
+ * flush the log up to the latest LSN that touched the inode. If we have
+ * concurrent fsync/fdatasync() calls, we need them to all block on the
+ * log force before we clear the ili_fsync_fields field. This ensures
+ * that we don't get a racing sync operation that does not wait for the
+ * metadata to hit the journal before returning. If we race with
+ * clearing the ili_fsync_fields, then all that will happen is the log
+ * force will do nothing as the lsn will already be on disk. We can't
+ * race with setting ili_fsync_fields because that is done under
+ * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
+ * until after the ili_fsync_fields is cleared.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_ipincount(ip)) {
if (!datasync ||
- (ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
+ (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
lsn = ip->i_itemp->ili_last_lsn;
}
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- if (lsn)
+ if (lsn) {
error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
+ ip->i_itemp->ili_fsync_fields = 0;
+ }
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
/*
* If we only have a single device, and the log force about was
xfs_fsize_t n;
loff_t pos = iocb->ki_pos;
- XFS_STATS_INC(xs_read_calls);
+ XFS_STATS_INC(mp, xs_read_calls);
if (unlikely(iocb->ki_flags & IOCB_DIRECT))
ioflags |= XFS_IO_ISDIRECT;
ret = generic_file_read_iter(iocb, to);
if (ret > 0)
- XFS_STATS_ADD(xs_read_bytes, ret);
+ XFS_STATS_ADD(mp, xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
int ioflags = 0;
ssize_t ret;
- XFS_STATS_INC(xs_read_calls);
+ XFS_STATS_INC(ip->i_mount, xs_read_calls);
if (infilp->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
else
ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
if (ret > 0)
- XFS_STATS_ADD(xs_read_bytes, ret);
+ XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(offset > isize);
+ trace_xfs_zero_eof(ip, isize, offset - isize);
+
/*
* First handle zeroing the block on which isize resides.
*
struct xfs_inode *ip = XFS_I(inode);
ssize_t error = 0;
size_t count = iov_iter_count(from);
+ bool drained_dio = false;
restart:
error = generic_write_checks(iocb, from);
bool zero = false;
spin_unlock(&ip->i_flags_lock);
- if (*iolock == XFS_IOLOCK_SHARED) {
- xfs_rw_iunlock(ip, *iolock);
- *iolock = XFS_IOLOCK_EXCL;
- xfs_rw_ilock(ip, *iolock);
- iov_iter_reexpand(from, count);
-
+ if (!drained_dio) {
+ if (*iolock == XFS_IOLOCK_SHARED) {
+ xfs_rw_iunlock(ip, *iolock);
+ *iolock = XFS_IOLOCK_EXCL;
+ xfs_rw_ilock(ip, *iolock);
+ iov_iter_reexpand(from, count);
+ }
/*
* We now have an IO submission barrier in place, but
* AIO can do EOF updates during IO completion and hence
* no-op.
*/
inode_dio_wait(inode);
+ drained_dio = true;
goto restart;
}
error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
ssize_t ret;
size_t ocount = iov_iter_count(from);
- XFS_STATS_INC(xs_write_calls);
+ XFS_STATS_INC(ip->i_mount, xs_write_calls);
if (ocount == 0)
return 0;
if (ret > 0) {
ssize_t err;
- XFS_STATS_ADD(xs_write_bytes, ret);
+ XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
/* Handle various SYNC-type writes */
err = generic_write_sync(file, iocb->ki_pos - ret, ret);
*
* mmap_sem (MM)
* sb_start_pagefault(vfs, freeze)
- * i_mmap_lock (XFS - truncate serialisation)
+ * i_mmaplock (XFS - truncate serialisation)
* page_lock (MM)
* i_lock (XFS - extent map serialisation)
*/
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct,
- xfs_end_io_dax_write);
+ ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
} else {
- ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);
+ ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
ret = block_page_mkwrite_return(ret);
}
* changes to xfs_get_blocks_direct() to map unwritten extent
* ioend for conversion on read-only mappings.
*/
- ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+ ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
} else
ret = filemap_fault(vma, vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
return ret;
}
+ /*
+ * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
+ * both read and write faults. Hence we need to handle both cases. There is no
+ * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * handle both cases here. @flags carries the information on the type of fault
+ * occuring.
+ */
STATIC int
xfs_filemap_pmd_fault(
struct vm_area_struct *vma,
trace_xfs_filemap_pmd_fault(ip);
- sb_start_pagefault(inode->i_sb);
- file_update_time(vma->vm_file);
+ if (flags & FAULT_FLAG_WRITE) {
+ sb_start_pagefault(inode->i_sb);
+ file_update_time(vma->vm_file);
+ }
+
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct,
- xfs_end_io_dax_write);
+ ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
+ NULL);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
- sb_end_pagefault(inode->i_sb);
+ if (flags & FAULT_FLAG_WRITE)
+ sb_end_pagefault(inode->i_sb);
+
+ return ret;
+ }
+
+ /*
+ * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * updates on write faults. In reality, it's need to serialise against
+ * truncate similar to page_mkwrite. Hence we open-code dax_pfn_mkwrite()
+ * here and cycle the XFS_MMAPLOCK_SHARED to ensure we serialise the fault
+ * barrier in place.
+ */
+ static int
+ xfs_filemap_pfn_mkwrite(
+ struct vm_area_struct *vma,
+ struct vm_fault *vmf)
+ {
+
+ struct inode *inode = file_inode(vma->vm_file);
+ struct xfs_inode *ip = XFS_I(inode);
+ int ret = VM_FAULT_NOPAGE;
+ loff_t size;
+
+ trace_xfs_filemap_pfn_mkwrite(ip);
+
+ sb_start_pagefault(inode->i_sb);
+ file_update_time(vma->vm_file);
+
+ /* check if the faulting page hasn't raced with truncate */
+ xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (vmf->pgoff >= size)
+ ret = VM_FAULT_SIGBUS;
+ xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+ sb_end_pagefault(inode->i_sb);
return ret;
+
}
static const struct vm_operations_struct xfs_file_vm_ops = {
.pmd_fault = xfs_filemap_pmd_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = xfs_filemap_page_mkwrite,
+ .pfn_mkwrite = xfs_filemap_pfn_mkwrite,
};
STATIC int