Merge tag 'nfs-for-4.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  New features:
   - RDMA client backchannel from Chuck
   - Support for NFSv4.2 file CLONE using the btrfs ioctl

  Bugfixes + cleanups:
   - Move socket data receive out of the bottom halves and into a
     workqueue
   - Refactor NFSv4 error handling so synchronous and asynchronous RPC
     handles errors identically.
   - Fix a panic when blocks or object layouts reads return a bad data
     length
   - Fix nfsroot so it can handle a 1024 byte long path.
   - Fix bad usage of page offset in bl_read_pagelist
   - Various NFSv4 callback cleanups+fixes
   - Fix GETATTR bitmap verification
   - Support hexadecimal number for sunrpc debug sysctl files"

* tag 'nfs-for-4.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (53 commits)
  Sunrpc: Supports hexadecimal number for sysctl files of sunrpc debug
  nfs: Fix GETATTR bitmap verification
  nfs: Remove unused xdr page offsets in getacl/setacl arguments
  fs/nfs: remove unnecessary new_valid_dev check
  SUNRPC: fix variable type
  NFS: Enable client side NFSv4.1 backchannel to use other transports
  pNFS/flexfiles: Add support for FF_FLAGS_NO_IO_THRU_MDS
  pNFS/flexfiles: When mirrored, retry failed reads by switching mirrors
  SUNRPC: Remove the TCP-only restriction in bc_svc_process()
  svcrdma: Add backward direction service for RPC/RDMA transport
  xprtrdma: Handle incoming backward direction RPC calls
  xprtrdma: Add support for sending backward direction RPC replies
  xprtrdma: Pre-allocate Work Requests for backchannel
  xprtrdma: Pre-allocate backward rpc_rqst and send/receive buffers
  SUNRPC: Abstract backchannel operations
  xprtrdma: Saving IRQs no longer needed for rb_lock
  xprtrdma: Remove reply tasklet
  xprtrdma: Use workqueue to process RPC/RDMA replies
  xprtrdma: Replace send and receive arrays
  xprtrdma: Refactor reply handler error handling
  ...

1 files changed, 136 insertions, 0 deletions

diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index b0dbe0abed53..4aa571956cd6 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 1992  Rick Sladkey
  */
 #include <linux/fs.h>
+#include <linux/file.h>
 #include <linux/falloc.h>
 #include <linux/nfs_fs.h>
 #include "delegation.h"
@@ -192,8 +193,138 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
                 return nfs42_proc_deallocate(filep, offset, len);
         return nfs42_proc_allocate(filep, offset, len);
 }
+
+static noinline long
+nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
+                  u64 src_off, u64 dst_off, u64 count)
+{
+        struct inode *dst_inode = file_inode(dst_file);
+        struct nfs_server *server = NFS_SERVER(dst_inode);
+        struct fd src_file;
+        struct inode *src_inode;
+        unsigned int bs = server->clone_blksize;
+        int ret;
+
+        /* dst file must be opened for writing */
+        if (!(dst_file->f_mode & FMODE_WRITE))
+                return -EINVAL;
+
+        ret = mnt_want_write_file(dst_file);
+        if (ret)
+                return ret;
+
+        src_file = fdget(srcfd);
+        if (!src_file.file) {
+                ret = -EBADF;
+                goto out_drop_write;
+        }
+
+        src_inode = file_inode(src_file.file);
+
+        /* src and dst must be different files */
+        ret = -EINVAL;
+        if (src_inode == dst_inode)
+                goto out_fput;
+
+        /* src file must be opened for reading */
+        if (!(src_file.file->f_mode & FMODE_READ))
+                goto out_fput;
+
+        /* src and dst must be regular files */
+        ret = -EISDIR;
+        if (!S_ISREG(src_inode->i_mode) || !S_ISREG(dst_inode->i_mode))
+                goto out_fput;
+
+        ret = -EXDEV;
+        if (src_file.file->f_path.mnt != dst_file->f_path.mnt ||
+            src_inode->i_sb != dst_inode->i_sb)
+                goto out_fput;
+
+        /* check alignment w.r.t. clone_blksize */
+        ret = -EINVAL;
+        if (bs) {
+                if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
+                        goto out_fput;
+                if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
+                        goto out_fput;
+        }
+
+        /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
+        if (dst_inode < src_inode) {
+                mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_PARENT);
+                mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD);
+        } else {
+                mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT);
+                mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_CHILD);
+        }
+
+        /* flush all pending writes on both src and dst so that server
+         * has the latest data */
+        ret = nfs_sync_inode(src_inode);
+        if (ret)
+                goto out_unlock;
+        ret = nfs_sync_inode(dst_inode);
+        if (ret)
+                goto out_unlock;
+
+        ret = nfs42_proc_clone(src_file.file, dst_file, src_off, dst_off, count);
+
+        /* truncate inode page cache of the dst range so that future reads can fetch
+         * new data from server */
+        if (!ret)
+                truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
+
+out_unlock:
+        if (dst_inode < src_inode) {
+                mutex_unlock(&src_inode->i_mutex);
+                mutex_unlock(&dst_inode->i_mutex);
+        } else {
+                mutex_unlock(&dst_inode->i_mutex);
+                mutex_unlock(&src_inode->i_mutex);
+        }
+out_fput:
+        fdput(src_file);
+out_drop_write:
+        mnt_drop_write_file(dst_file);
+        return ret;
+}
+
+static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
+{
+        struct nfs_ioctl_clone_range_args args;
+
+        if (copy_from_user(&args, argp, sizeof(args)))
+                return -EFAULT;
+
+        return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_off, args.dst_off, args.count);
+}
+#else
+static long nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
+                u64 src_off, u64 dst_off, u64 count)
+{
+        return -ENOTTY;
+}
+
+static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
+{
+        return -ENOTTY;
+}
 #endif /* CONFIG_NFS_V4_2 */
 
+long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+        void __user *argp = (void __user *)arg;
+
+        switch (cmd) {
+        case NFS_IOC_CLONE:
+                return nfs42_ioctl_clone(file, arg, 0, 0, 0);
+        case NFS_IOC_CLONE_RANGE:
+                return nfs42_ioctl_clone_range(file, argp);
+        }
+
+        return -ENOTTY;
+}
+
 const struct file_operations nfs4_file_operations = {
 #ifdef CONFIG_NFS_V4_2
         .llseek         = nfs4_file_llseek,
@@ -216,4 +347,9 @@ const struct file_operations nfs4_file_operations = {
 #endif /* CONFIG_NFS_V4_2 */
         .check_flags    = nfs_check_flags,
         .setlease       = simple_nosetlease,
+#ifdef CONFIG_COMPAT
+        .unlocked_ioctl = nfs4_ioctl,
+#else
+        .compat_ioctl   = nfs4_ioctl,
+#endif /* CONFIG_COMPAT */
 };