6 files changed, 53 insertions, 15 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 35309bd046be..4774c7172ef4 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -312,7 +312,7 @@ restart:
         if (error <= 0)
                 return error;
 
-        error = xfs_break_layouts(inode, iolock);
+        error = xfs_break_layouts(inode, iolock, BREAK_WRITE);
         if (error)
                 return error;
 
@@ -718,6 +718,28 @@ buffered:
         return ret;
 }
 
+int
+xfs_break_layouts(
+        struct inode            *inode,
+        uint                    *iolock,
+        enum layout_break_reason reason)
+{
+        bool                    retry;
+
+        ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+        switch (reason) {
+        case BREAK_UNMAP:
+                ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
+                /* fall through */
+        case BREAK_WRITE:
+                return xfs_break_leased_layouts(inode, iolock, &retry);
+        default:
+                WARN_ON_ONCE(1);
+                return -EINVAL;
+        }
+}
+
 #define XFS_FALLOC_FL_SUPPORTED                                         \
                 (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |           \
                  FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |      \
@@ -744,7 +766,7 @@ xfs_file_fallocate(
                 return -EOPNOTSUPP;
 
         xfs_ilock(ip, iolock);
-        error = xfs_break_layouts(inode, &iolock);
+        error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
         if (error)
                 goto out_unlock;
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1eebc53df7d7..e5b849815ce1 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -379,6 +379,20 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
                                         >> XFS_ILOCK_SHIFT)
 
 /*
+ * Layouts are broken in the BREAK_WRITE case to ensure that
+ * layout-holders do not collide with local writes. Additionally,
+ * layouts are broken in the BREAK_UNMAP case to make sure the
+ * layout-holder has a consistent view of the file's extent map. While
+ * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases,
+ * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to
+ * go idle.
+ */
+enum layout_break_reason {
+        BREAK_WRITE,
+        BREAK_UNMAP,
+};
+
+/*
  * For multiple groups support: if S_ISGID bit is set in the parent
  * directory, group of new file is set to that of the parent, and
  * new subdirectory gets S_ISGID bit from parent.
@@ -443,6 +457,8 @@ enum xfs_prealloc_flags {
 
 int     xfs_update_prealloc_flags(struct xfs_inode *ip,
                                   enum xfs_prealloc_flags flags);
+int     xfs_break_layouts(struct inode *inode, uint *iolock,
+                enum layout_break_reason reason);
 
 /* from xfs_iops.c */
 extern void xfs_setup_inode(struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 4151fade4bb1..91e73d663099 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -39,7 +39,6 @@
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
 #include "xfs_trans.h"
-#include "xfs_pnfs.h"
 #include "xfs_acl.h"
 #include "xfs_btree.h"
 #include <linux/fsmap.h>
@@ -644,7 +643,7 @@ xfs_ioc_space(
                 return error;
 
         xfs_ilock(ip, iolock);
-        error = xfs_break_layouts(inode, &iolock);
+        error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
         if (error)
                 goto out_unlock;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 138fb36ca875..ce0c1f9466a8 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -37,7 +37,6 @@
 #include "xfs_da_btree.h"
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
-#include "xfs_pnfs.h"
 #include "xfs_iomap.h"
 
 #include <linux/capability.h>
@@ -1030,13 +1029,14 @@ xfs_vn_setattr(
         int                     error;
 
         if (iattr->ia_valid & ATTR_SIZE) {
-                struct xfs_inode        *ip = XFS_I(d_inode(dentry));
+                struct inode            *inode = d_inode(dentry);
+                struct xfs_inode        *ip = XFS_I(inode);
                 uint                    iolock;
 
                 xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
                 iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 
-                error = xfs_break_layouts(d_inode(dentry), &iolock);
+                error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
                 if (error) {
                         xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
                         return error;
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 6ea7b0b55d02..f44c3599527d 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -31,17 +31,17 @@
  * rules in the page fault path we don't bother.
  */
 int
-xfs_break_layouts(
+xfs_break_leased_layouts(
         struct inode            *inode,
-        uint                    *iolock)
+        uint                    *iolock,
+        bool                    *did_unlock)
 {
         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);
+                *did_unlock = true;
                 error = break_layout(inode, true);
                 *iolock &= ~XFS_IOLOCK_SHARED;
                 *iolock |= XFS_IOLOCK_EXCL;
@@ -121,8 +121,8 @@ xfs_fs_map_blocks(
          * Lock out any other I/O before we flush and invalidate the pagecache,
          * and then hand out a layout to the remote system.  This is very
          * similar to direct I/O, except that the synchronization is much more
-         * complicated.  See the comment near xfs_break_layouts for a detailed
-         * explanation.
+         * complicated.  See the comment near xfs_break_leased_layouts
+         * for a detailed explanation.
          */
         xfs_ilock(ip, XFS_IOLOCK_EXCL);
 
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
index bf45951e28fe..940c6c2ad88c 100644
--- a/fs/xfs/xfs_pnfs.h
+++ b/fs/xfs/xfs_pnfs.h
@@ -9,10 +9,11 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
 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);
+int xfs_break_leased_layouts(struct inode *inode, uint *iolock,
+                bool *did_unlock);
 #else
 static inline int
-xfs_break_layouts(struct inode *inode, uint *iolock)
+xfs_break_leased_layouts(struct inode *inode, uint *iolock, bool *did_unlock)
 {
         return 0;
 }