10 files changed, 393 insertions, 8 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d61799949580..df6828570e87 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -121,3 +121,4 @@ xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
 xfs-$(CONFIG_PROC_FS)           += xfs_stats.o
 xfs-$(CONFIG_SYSCTL)            += xfs_sysctl.o
 xfs-$(CONFIG_COMPAT)            += xfs_ioctl32.o
+xfs-$(CONFIG_NFSD_PNFS)         += xfs_pnfs.o
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 5eb4a14e0a0f..b97359ba2648 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -30,6 +30,7 @@
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_log.h"
+#include "xfs_pnfs.h"
 
 /*
  * Note that we only accept fileids which are long enough rather than allow
@@ -245,4 +246,9 @@ const struct export_operations xfs_export_operations = {
         .fh_to_parent           = xfs_fs_fh_to_parent,
         .get_parent             = xfs_fs_get_parent,
         .commit_metadata        = xfs_fs_nfs_commit_metadata,
+#ifdef CONFIG_NFSD_PNFS
+        .get_uuid               = xfs_fs_get_uuid,
+        .map_blocks             = xfs_fs_map_blocks,
+        .commit_blocks          = xfs_fs_commit_blocks,
+#endif
 };
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 1cdba95c78cb..ce615d12fb44 100644
--- a/fs/xfs/xfs_file.c
+++ b/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 @@ restart:
         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;
 }
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index fba6532efba4..74efe5b760dc 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -602,6 +602,12 @@ xfs_growfs_data(
         if (!mutex_trylock(&mp->m_growlock))
                 return -EWOULDBLOCK;
         error = xfs_growfs_data_private(mp, in);
+        /*
+         * Increment the generation unconditionally, the error could be from
+         * updating the secondary superblocks, in which case the new size
+         * is live already.
+         */
+        mp->m_generation++;
         mutex_unlock(&mp->m_growlock);
         return error;
 }
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index f7afb86c9148..bf70a2affb05 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/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;
 }
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ce80eeb8faa4..d919ad7b16bf 100644
--- a/fs/xfs/xfs_iops.c
+++ b/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>
@@ -505,7 +506,7 @@ xfs_setattr_mode(
         inode->i_mode |= mode & ~S_IFMT;
 }
 
-static void
+void
 xfs_setattr_time(
         struct xfs_inode        *ip,
         struct iattr            *iattr)
@@ -979,9 +980,13 @@ xfs_vn_setattr(
         int                     error;
 
         if (iattr->ia_valid & ATTR_SIZE) {
-                xfs_ilock(ip, XFS_IOLOCK_EXCL);
-                error = xfs_setattr_size(ip, iattr);
-                xfs_iunlock(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, iolock);
         } else {
                 error = xfs_setattr_nonsize(ip, iattr, 0);
         }
diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h
index 1c34e4335920..ea7a98e9cb70 100644
--- a/fs/xfs/xfs_iops.h
+++ b/fs/xfs/xfs_iops.h
@@ -32,6 +32,7 @@ extern void xfs_setup_inode(struct xfs_inode *);
  */
 #define XFS_ATTR_NOACL          0x01    /* Don't call posix_acl_chmod */
 
+extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr);
 extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap,
                                int flags);
 extern int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index a5b2ff822653..0d8abd6364d9 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -174,6 +174,17 @@ typedef struct xfs_mount {
         struct workqueue_struct *m_reclaim_workqueue;
         struct workqueue_struct *m_log_workqueue;
         struct workqueue_struct *m_eofblocks_workqueue;
+
+        /*
+         * Generation of the filesysyem layout.  This is incremented by each
+         * growfs, and used by the pNFS server to ensure the client updates
+         * its view of the block device once it gets a layout that might
+         * reference the newly added blocks.  Does not need to be persistent
+         * as long as we only allow file system size increments, but if we
+         * ever support shrinks it would have to be persisted in addition
+         * to various other kinds of pain inflicted on the pNFS server.
+         */
+        __uint32_t              m_generation;
 } xfs_mount_t;
 
 /*
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
new file mode 100644
index 000000000000..4b33ef112400
--- /dev/null
+++ b/fs/xfs/xfs_pnfs.c
@@ -0,0 +1,322 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include "xfs.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_log.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_error.h"
+#include "xfs_iomap.h"
+#include "xfs_shared.h"
+#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.
+ */
+int
+xfs_fs_get_uuid(
+        struct super_block      *sb,
+        u8                      *buf,
+        u32                     *len,
+        u64                     *offset)
+{
+        struct xfs_mount        *mp = XFS_M(sb);
+
+        printk_once(KERN_NOTICE
+"XFS (%s): using experimental pNFS feature, use at your own risk!\n",
+                mp->m_fsname);
+
+        if (*len < sizeof(uuid_t))
+                return -EINVAL;
+
+        memcpy(buf, &mp->m_sb.sb_uuid, sizeof(uuid_t));
+        *len = sizeof(uuid_t);
+        *offset = offsetof(struct xfs_dsb, sb_uuid);
+        return 0;
+}
+
+static void
+xfs_bmbt_to_iomap(
+        struct xfs_inode        *ip,
+        struct iomap            *iomap,
+        struct xfs_bmbt_irec    *imap)
+{
+        struct xfs_mount        *mp = ip->i_mount;
+
+        if (imap->br_startblock == HOLESTARTBLOCK) {
+                iomap->blkno = IOMAP_NULL_BLOCK;
+                iomap->type = IOMAP_HOLE;
+        } else if (imap->br_startblock == DELAYSTARTBLOCK) {
+                iomap->blkno = IOMAP_NULL_BLOCK;
+                iomap->type = IOMAP_DELALLOC;
+        } else {
+                iomap->blkno =
+                        XFS_FSB_TO_DADDR(ip->i_mount, imap->br_startblock);
+                if (imap->br_state == XFS_EXT_UNWRITTEN)
+                        iomap->type = IOMAP_UNWRITTEN;
+                else
+                        iomap->type = IOMAP_MAPPED;
+        }
+        iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
+        iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
+}
+
+/*
+ * Get a layout for the pNFS client.
+ */
+int
+xfs_fs_map_blocks(
+        struct inode            *inode,
+        loff_t                  offset,
+        u64                     length,
+        struct iomap            *iomap,
+        bool                    write,
+        u32                     *device_generation)
+{
+        struct xfs_inode        *ip = XFS_I(inode);
+        struct xfs_mount        *mp = ip->i_mount;
+        struct xfs_bmbt_irec    imap;
+        xfs_fileoff_t           offset_fsb, end_fsb;
+        loff_t                  limit;
+        int                     bmapi_flags = XFS_BMAPI_ENTIRE;
+        int                     nimaps = 1;
+        uint                    lock_flags;
+        int                     error = 0;
+
+        if (XFS_FORCED_SHUTDOWN(mp))
+                return -EIO;
+
+        /*
+         * We can't export inodes residing on the realtime device.  The realtime
+         * device doesn't have a UUID to identify it, so the client has no way
+         * to find it.
+         */
+        if (XFS_IS_REALTIME_INODE(ip))
+                return -ENXIO;
+
+        /*
+         * 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.
+         */
+        xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+        error = -EINVAL;
+        limit = mp->m_super->s_maxbytes;
+        if (!write)
+                limit = max(limit, round_up(i_size_read(inode),
+                                     inode->i_sb->s_blocksize));
+        if (offset > limit)
+                goto out_unlock;
+        if (offset > limit - length)
+                length = limit - offset;
+
+        error = filemap_write_and_wait(inode->i_mapping);
+        if (error)
+                goto out_unlock;
+        error = invalidate_inode_pages2(inode->i_mapping);
+        if (WARN_ON_ONCE(error))
+                return error;
+
+        end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
+        offset_fsb = XFS_B_TO_FSBT(mp, offset);
+
+        lock_flags = xfs_ilock_data_map_shared(ip);
+        error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
+                                &imap, &nimaps, bmapi_flags);
+        xfs_iunlock(ip, lock_flags);
+
+        if (error)
+                goto out_unlock;
+
+        if (write) {
+                enum xfs_prealloc_flags flags = 0;
+
+                ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+
+                if (!nimaps || imap.br_startblock == HOLESTARTBLOCK) {
+                        error = xfs_iomap_write_direct(ip, offset, length,
+                                                       &imap, nimaps);
+                        if (error)
+                                goto out_unlock;
+
+                        /*
+                         * Ensure the next transaction is committed
+                         * synchronously so that the blocks allocated and
+                         * handed out to the client are guaranteed to be
+                         * present even after a server crash.
+                         */
+                        flags |= XFS_PREALLOC_SET | XFS_PREALLOC_SYNC;
+                }
+
+                error = xfs_update_prealloc_flags(ip, flags);
+                if (error)
+                        goto out_unlock;
+        }
+        xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+
+        xfs_bmbt_to_iomap(ip, iomap, &imap);
+        *device_generation = mp->m_generation;
+        return error;
+out_unlock:
+        xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+        return error;
+}
+
+/*
+ * Ensure the size update falls into a valid allocated block.
+ */
+static int
+xfs_pnfs_validate_isize(
+        struct xfs_inode        *ip,
+        xfs_off_t               isize)
+{
+        struct xfs_bmbt_irec    imap;
+        int                     nimaps = 1;
+        int                     error = 0;
+
+        xfs_ilock(ip, XFS_ILOCK_SHARED);
+        error = xfs_bmapi_read(ip, XFS_B_TO_FSBT(ip->i_mount, isize - 1), 1,
+                                &imap, &nimaps, 0);
+        xfs_iunlock(ip, XFS_ILOCK_SHARED);
+        if (error)
+                return error;
+
+        if (imap.br_startblock == HOLESTARTBLOCK ||
+            imap.br_startblock == DELAYSTARTBLOCK ||
+            imap.br_state == XFS_EXT_UNWRITTEN)
+                return -EIO;
+        return 0;
+}
+
+/*
+ * Make sure the blocks described by maps are stable on disk.  This includes
+ * converting any unwritten extents, flushing the disk cache and updating the
+ * time stamps.
+ *
+ * Note that we rely on the caller to always send us a timestamp update so that
+ * we always commit a transaction here.  If that stops being true we will have
+ * to manually flush the cache here similar to what the fsync code path does
+ * for datasyncs on files that have no dirty metadata.
+ */
+int
+xfs_fs_commit_blocks(
+        struct inode            *inode,
+        struct iomap            *maps,
+        int                     nr_maps,
+        struct iattr            *iattr)
+{
+        struct xfs_inode        *ip = XFS_I(inode);
+        struct xfs_mount        *mp = ip->i_mount;
+        struct xfs_trans        *tp;
+        bool                    update_isize = false;
+        int                     error, i;
+        loff_t                  size;
+
+        ASSERT(iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME));
+
+        xfs_ilock(ip, XFS_IOLOCK_EXCL);
+
+        size = i_size_read(inode);
+        if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size > size) {
+                update_isize = true;
+                size = iattr->ia_size;
+        }
+
+        for (i = 0; i < nr_maps; i++) {
+                u64 start, length, end;
+
+                start = maps[i].offset;
+                if (start > size)
+                        continue;
+
+                end = start + maps[i].length;
+                if (end > size)
+                        end = size;
+
+                length = end - start;
+                if (!length)
+                        continue;
+        
+                /*
+                 * Make sure reads through the pagecache see the new data.
+                 */
+                error = invalidate_inode_pages2_range(inode->i_mapping,
+                                        start >> PAGE_CACHE_SHIFT,
+                                        (end - 1) >> PAGE_CACHE_SHIFT);
+                WARN_ON_ONCE(error);
+
+                error = xfs_iomap_write_unwritten(ip, start, length);
+                if (error)
+                        goto out_drop_iolock;
+        }
+
+        if (update_isize) {
+                error = xfs_pnfs_validate_isize(ip, size);
+                if (error)
+                        goto out_drop_iolock;
+        }
+
+        tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+        error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+        if (error)
+                goto out_drop_iolock;
+
+        xfs_ilock(ip, XFS_ILOCK_EXCL);
+        xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+        xfs_setattr_time(ip, iattr);
+        if (update_isize) {
+                i_size_write(inode, iattr->ia_size);
+                ip->i_d.di_size = iattr->ia_size;
+        }
+
+        xfs_trans_set_sync(tp);
+        error = xfs_trans_commit(tp, 0);
+
+out_drop_iolock:
+        xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+        return error;
+}
diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h
new file mode 100644
index 000000000000..b7fbfce660f6
--- /dev/null
+++ b/fs/xfs/xfs_pnfs.h
@@ -0,0 +1,18 @@
+#ifndef _XFS_PNFS_H
+#define _XFS_PNFS_H 1
+
+#ifdef CONFIG_NFSD_PNFS
+int xfs_fs_get_uuid(struct super_block *sb, u8 *buf, u32 *len, u64 *offset);
+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 */