xfs: recall pNFS layouts on conflicting access

Recall all outstanding pNFS layouts and truncates, writes and similar extent
list modifying operations.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/xfs_file.c

@@ -36,6 +36,7 @@
 #include "xfs_trace.h"
 #include "xfs_log.h"
 #include "xfs_icache.h"
+#include "xfs_pnfs.h"
 
 #include <linux/aio.h>
 #include <linux/dcache.h>
@@ -554,6 +555,10 @@ xfs_file_aio_write_checks(
 	if (error)
 		return error;
 
+	error = xfs_break_layouts(inode, iolock);
+	if (error)
+		return error;
+
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
@@ -822,6 +827,7 @@ xfs_file_fallocate(
 	struct xfs_inode	*ip = XFS_I(inode);
 	long			error;
 	enum xfs_prealloc_flags	flags = 0;
+	uint			iolock = XFS_IOLOCK_EXCL;
 	loff_t			new_size = 0;
 
 	if (!S_ISREG(inode->i_mode))
@@ -830,7 +836,11 @@ xfs_file_fallocate(
 		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
 		return -EOPNOTSUPP;
 
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+	xfs_ilock(ip, iolock);
+	error = xfs_break_layouts(inode, &iolock);
+	if (error)
+		goto out_unlock;
+
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		error = xfs_free_file_space(ip, offset, len);
 		if (error)
@@ -894,7 +904,7 @@ xfs_file_fallocate(
 	}
 
 out_unlock:
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	xfs_iunlock(ip, iolock);
 	return error;
 }
 

fs/xfs/xfs_ioctl.c

@@ -39,6 +39,7 @@
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
 #include "xfs_trans.h"
+#include "xfs_pnfs.h"
 
 #include <linux/capability.h>
 #include <linux/dcache.h>
@@ -608,6 +609,7 @@ xfs_ioc_space(
 {
 	struct iattr		iattr;
 	enum xfs_prealloc_flags	flags = 0;
+	uint			iolock = XFS_IOLOCK_EXCL;
 	int			error;
 
 	/*
@@ -636,7 +638,10 @@ xfs_ioc_space(
 	if (error)
 		return error;
 
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+	xfs_ilock(ip, iolock);
+	error = xfs_break_layouts(inode, &iolock);
+	if (error)
+		goto out_unlock;
 
 	switch (bf->l_whence) {
 	case 0: /*SEEK_SET*/
@@ -725,7 +730,7 @@ xfs_ioc_space(
 	error = xfs_update_prealloc_flags(ip, flags);
 
 out_unlock:
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	xfs_iunlock(ip, iolock);
 	mnt_drop_write_file(filp);
 	return error;
 }

fs/xfs/xfs_iops.c

@@ -37,6 +37,7 @@
 #include "xfs_da_btree.h"
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
+#include "xfs_pnfs.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -979,9 +980,13 @@ xfs_vn_setattr(
 	int			error;
 
 	if (iattr->ia_valid & ATTR_SIZE) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
+		uint		iolock = XFS_IOLOCK_EXCL;
+
+		xfs_ilock(ip, iolock);
+		error = xfs_break_layouts(dentry->d_inode, &iolock);
+		if (!error)
 			error = xfs_setattr_size(ip, iattr);
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+		xfs_iunlock(ip, iolock);
 	} else {
 		error = xfs_setattr_nonsize(ip, iattr, 0);
 	}

fs/xfs/xfs_pnfs.c

@@ -18,6 +18,36 @@
 #include "xfs_bit.h"
 #include "xfs_pnfs.h"
 
+/*
+ * Ensure that we do not have any outstanding pNFS layouts that can be used by
+ * clients to directly read from or write to this inode.  This must be called
+ * before every operation that can remove blocks from the extent map.
+ * Additionally we call it during the write operation, where aren't concerned
+ * about exposing unallocated blocks but just want to provide basic
+ * synchronization between a local writer and pNFS clients.  mmap writes would
+ * also benefit from this sort of synchronization, but due to the tricky locking
+ * rules in the page fault path we don't bother.
+ */
+int
+xfs_break_layouts(
+	struct inode		*inode,
+	uint			*iolock)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			error;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+	while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
+		xfs_iunlock(ip, *iolock);
+		error = break_layout(inode, true);
+		*iolock = XFS_IOLOCK_EXCL;
+		xfs_ilock(ip, *iolock);
+	}
+
+	return error;
+}
+
 /*
  * Get a unique ID including its location so that the client can identify
  * the exported device.

fs/xfs/xfs_pnfs.h

@@ -7,5 +7,12 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
 		struct iomap *iomap, bool write, u32 *device_generation);
 int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps,
 		struct iattr *iattr);
+
+int xfs_break_layouts(struct inode *inode, uint *iolock);
+#else
+static inline int xfs_break_layouts(struct inode *inode, uint *iolock)
+{
+	return 0;
+}
 #endif /* CONFIG_NFSD_PNFS */
 #endif /* _XFS_PNFS_H */