Merge branch 'for-4.5/block-dax' into for-4.5/libnvdimm

19 files changed, 190 insertions, 60 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 699941e90667..511078586fa1 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -451,9 +451,9 @@ void v9fs_evict_inode(struct inode *inode)
 {
         struct v9fs_inode *v9inode = V9FS_I(inode);
 
-        truncate_inode_pages_final(inode->i_mapping);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
-        filemap_fdatawrite(inode->i_mapping);
+        filemap_fdatawrite(&inode->i_data);
 
         v9fs_cache_inode_put_cookie(inode);
         /* clunk the fid stashed in writeback_fid */
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c25639e907bd..5c0b2cba870e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -156,11 +156,16 @@ blkdev_get_block(struct inode *inode, sector_t iblock,
         return 0;
 }
 
+static struct inode *bdev_file_inode(struct file *file)
+{
+        return file->f_mapping->host;
+}
+
 static ssize_t
 blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
         struct file *file = iocb->ki_filp;
-        struct inode *inode = file->f_mapping->host;
+        struct inode *inode = bdev_file_inode(file);
 
         if (IS_DAX(inode))
                 return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
@@ -338,7 +343,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
  */
 static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 {
-        struct inode *bd_inode = file->f_mapping->host;
+        struct inode *bd_inode = bdev_file_inode(file);
         loff_t retval;
 
         mutex_lock(&bd_inode->i_mutex);
@@ -349,7 +354,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence)
         
 int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 {
-        struct inode *bd_inode = filp->f_mapping->host;
+        struct inode *bd_inode = bdev_file_inode(filp);
         struct block_device *bdev = I_BDEV(bd_inode);
         int error;
         
@@ -1230,8 +1235,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                                 }
                         }
 
-                        if (!ret)
+                        if (!ret) {
                                 bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+                                if (!blkdev_dax_capable(bdev))
+                                        bdev->bd_inode->i_flags &= ~S_DAX;
+                        }
 
                         /*
                          * If the device is invalidated, rescan partition
@@ -1245,6 +1253,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                                 else if (ret == -ENOMEDIUM)
                                         invalidate_partitions(disk, bdev);
                         }
+
                         if (ret)
                                 goto out_clear;
                 } else {
@@ -1265,12 +1274,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                                 goto out_clear;
                         }
                         bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
-                        /*
-                         * If the partition is not aligned on a page
-                         * boundary, we can't do dax I/O to it.
-                         */
-                        if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) ||
-                            (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+                        if (!blkdev_dax_capable(bdev))
                                 bdev->bd_inode->i_flags &= ~S_DAX;
                 }
         } else {
@@ -1523,11 +1527,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
                 WARN_ON_ONCE(bdev->bd_holders);
                 sync_blockdev(bdev);
                 kill_bdev(bdev);
+
+                bdev_write_inode(bdev);
                 /*
-                 * ->release can cause the queue to disappear, so flush all
-                 * dirty data before.
+                 * Detaching bdev inode from its wb in __destroy_inode()
+                 * is too late: the queue which embeds its bdi (along with
+                 * root wb) can be gone as soon as we put_disk() below.
                  */
-                bdev_write_inode(bdev);
+                inode_detach_wb(bdev->bd_inode);
         }
         if (bdev->bd_contains == bdev) {
                 if (disk->fops->release)
@@ -1602,14 +1609,14 @@ EXPORT_SYMBOL(blkdev_put);
 
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
-        struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+        struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
         blkdev_put(bdev, filp->f_mode);
         return 0;
 }
 
 static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
-        struct block_device *bdev = I_BDEV(file->f_mapping->host);
+        struct block_device *bdev = I_BDEV(bdev_file_inode(file));
         fmode_t mode = file->f_mode;
 
         /*
@@ -1634,7 +1641,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
         struct file *file = iocb->ki_filp;
-        struct inode *bd_inode = file->f_mapping->host;
+        struct inode *bd_inode = bdev_file_inode(file);
         loff_t size = i_size_read(bd_inode);
         struct blk_plug plug;
         ssize_t ret;
@@ -1666,7 +1673,7 @@ EXPORT_SYMBOL_GPL(blkdev_write_iter);
 ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
         struct file *file = iocb->ki_filp;
-        struct inode *bd_inode = file->f_mapping->host;
+        struct inode *bd_inode = bdev_file_inode(file);
         loff_t size = i_size_read(bd_inode);
         loff_t pos = iocb->ki_pos;
 
@@ -1705,13 +1712,101 @@ static const struct address_space_operations def_blk_aops = {
         .is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
+#ifdef CONFIG_FS_DAX
+/*
+ * In the raw block case we do not need to contend with truncation nor
+ * unwritten file extents.  Without those concerns there is no need for
+ * additional locking beyond the mmap_sem context that these routines
+ * are already executing under.
+ *
+ * Note, there is no protection if the block device is dynamically
+ * resized (partition grow/shrink) during a fault. A stable block device
+ * size is already not enforced in the blkdev_direct_IO path.
+ *
+ * For DAX, it is the responsibility of the block device driver to
+ * ensure the whole-disk device size is stable while requests are in
+ * flight.
+ *
+ * Finally, unlike the filemap_page_mkwrite() case there is no
+ * filesystem superblock to sync against freezing.  We still include a
+ * pfn_mkwrite callback for dax drivers to receive write fault
+ * notifications.
+ */
+static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+        return __dax_fault(vma, vmf, blkdev_get_block, NULL);
+}
+
+static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+                pmd_t *pmd, unsigned int flags)
+{
+        return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
+}
+
+static void blkdev_vm_open(struct vm_area_struct *vma)
+{
+        struct inode *bd_inode = bdev_file_inode(vma->vm_file);
+        struct block_device *bdev = I_BDEV(bd_inode);
+
+        mutex_lock(&bd_inode->i_mutex);
+        bdev->bd_map_count++;
+        mutex_unlock(&bd_inode->i_mutex);
+}
+
+static void blkdev_vm_close(struct vm_area_struct *vma)
+{
+        struct inode *bd_inode = bdev_file_inode(vma->vm_file);
+        struct block_device *bdev = I_BDEV(bd_inode);
+
+        mutex_lock(&bd_inode->i_mutex);
+        bdev->bd_map_count--;
+        mutex_unlock(&bd_inode->i_mutex);
+}
+
+static const struct vm_operations_struct blkdev_dax_vm_ops = {
+        .open           = blkdev_vm_open,
+        .close          = blkdev_vm_close,
+        .fault          = blkdev_dax_fault,
+        .pmd_fault      = blkdev_dax_pmd_fault,
+        .pfn_mkwrite    = blkdev_dax_fault,
+};
+
+static const struct vm_operations_struct blkdev_default_vm_ops = {
+        .open           = blkdev_vm_open,
+        .close          = blkdev_vm_close,
+        .fault          = filemap_fault,
+        .map_pages      = filemap_map_pages,
+};
+
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+        struct inode *bd_inode = bdev_file_inode(file);
+        struct block_device *bdev = I_BDEV(bd_inode);
+
+        file_accessed(file);
+        mutex_lock(&bd_inode->i_mutex);
+        bdev->bd_map_count++;
+        if (IS_DAX(bd_inode)) {
+                vma->vm_ops = &blkdev_dax_vm_ops;
+                vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+        } else {
+                vma->vm_ops = &blkdev_default_vm_ops;
+        }
+        mutex_unlock(&bd_inode->i_mutex);
+
+        return 0;
+}
+#else
+#define blkdev_mmap generic_file_mmap
+#endif
+
 const struct file_operations def_blk_fops = {
         .open           = blkdev_open,
         .release        = blkdev_close,
         .llseek         = block_llseek,
         .read_iter      = blkdev_read_iter,
         .write_iter     = blkdev_write_iter,
-        .mmap           = generic_file_mmap,
+        .mmap           = blkdev_mmap,
         .fsync          = blkdev_fsync,
         .unlocked_ioctl = block_ioctl,
 #ifdef CONFIG_COMPAT
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 6b66dd5d1540..a329f5ba35aa 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1831,11 +1831,11 @@ cifs_invalidate_mapping(struct inode *inode)
  * @word: long word containing the bit lock
  */
 static int
-cifs_wait_bit_killable(struct wait_bit_key *key)
+cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-        if (fatal_signal_pending(current))
-                return -ERESTARTSYS;
         freezable_schedule_unsafe();
+        if (signal_pending_state(mode, current))
+                return -ERESTARTSYS;
         return 0;
 }
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 1c75a3a07f8f..602e8441bc0f 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1175,6 +1175,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
                 if (dio->flags & DIO_LOCKING)
                         mutex_unlock(&inode->i_mutex);
                 kmem_cache_free(dio_cache, dio);
+                retval = 0;
                 goto out;
         }
 
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 73c64daa0f55..60f03b78914e 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -592,10 +592,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
                         }
                         unlock_page(page);
                 }
-                if (PageDirty(page) || PageWriteback(page))
-                        *uptodate = true;
-                else
-                        *uptodate = PageUptodate(page);
+                *uptodate = PageUptodate(page);
                 EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate);
                 return page;
         } else {
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index af06830bfc00..1a0835073663 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -389,7 +389,7 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
         struct ext4_crypto_ctx  *ctx;
         struct page             *ciphertext_page = NULL;
         struct bio              *bio;
-        ext4_lblk_t             lblk = ex->ee_block;
+        ext4_lblk_t             lblk = le32_to_cpu(ex->ee_block);
         ext4_fsblk_t            pblk = ext4_ext_pblock(ex);
         unsigned int            len = ext4_ext_get_actual_len(ex);
         int                     ret, err = 0;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 750063f7a50c..cc7ca4e87144 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -26,6 +26,7 @@
 #include <linux/seqlock.h>
 #include <linux/mutex.h>
 #include <linux/timer.h>
+#include <linux/version.h>
 #include <linux/wait.h>
 #include <linux/blockgroup_lock.h>
 #include <linux/percpu_counter.h>
@@ -727,19 +728,55 @@ struct move_extent {
         <= (EXT4_GOOD_OLD_INODE_SIZE +                  \
             (einode)->i_extra_isize))                   \
 
+/*
+ * We use an encoding that preserves the times for extra epoch "00":
+ *
+ * extra  msb of                         adjust for signed
+ * epoch  32-bit                         32-bit tv_sec to
+ * bits   time    decoded 64-bit tv_sec  64-bit tv_sec      valid time range
+ * 0 0    1    -0x80000000..-0x00000001  0x000000000 1901-12-13..1969-12-31
+ * 0 0    0    0x000000000..0x07fffffff  0x000000000 1970-01-01..2038-01-19
+ * 0 1    1    0x080000000..0x0ffffffff  0x100000000 2038-01-19..2106-02-07
+ * 0 1    0    0x100000000..0x17fffffff  0x100000000 2106-02-07..2174-02-25
+ * 1 0    1    0x180000000..0x1ffffffff  0x200000000 2174-02-25..2242-03-16
+ * 1 0    0    0x200000000..0x27fffffff  0x200000000 2242-03-16..2310-04-04
+ * 1 1    1    0x280000000..0x2ffffffff  0x300000000 2310-04-04..2378-04-22
+ * 1 1    0    0x300000000..0x37fffffff  0x300000000 2378-04-22..2446-05-10
+ *
+ * Note that previous versions of the kernel on 64-bit systems would
+ * incorrectly use extra epoch bits 1,1 for dates between 1901 and
+ * 1970.  e2fsck will correct this, assuming that it is run on the
+ * affected filesystem before 2242.
+ */
+
 static inline __le32 ext4_encode_extra_time(struct timespec *time)
 {
-       return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
-                           (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
-                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
+        u32 extra = sizeof(time->tv_sec) > 4 ?
+                ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+        return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
 }
 
 static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
 {
-       if (sizeof(time->tv_sec) > 4)
-               time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
-                               << 32;
-       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
+        if (unlikely(sizeof(time->tv_sec) > 4 &&
+                        (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0)
+                /* Handle legacy encoding of pre-1970 dates with epoch
+                 * bits 1,1.  We assume that by kernel version 4.20,
+                 * everyone will have run fsck over the affected
+                 * filesystems to correct the problem.  (This
+                 * backwards compatibility may be removed before this
+                 * time, at the discretion of the ext4 developers.)
+                 */
+                u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK;
+                if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0)
+                        extra_bits = 0;
+                time->tv_sec += extra_bits << 32;
+#else
+                time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
+#endif
+        }
+        time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
 }
 
 #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)                          \
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index abe2401ce405..e8e7af62ac95 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -52,7 +52,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook
         /* Symlink is encrypted */
         sd = (struct ext4_encrypted_symlink_data *)caddr;
         cstr.name = sd->encrypted_path;
-        cstr.len  = le32_to_cpu(sd->len);
+        cstr.len  = le16_to_cpu(sd->len);
         if ((cstr.len +
              sizeof(struct ext4_encrypted_symlink_data) - 1) >
             max_size) {
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 1b57c72f4a00..1420a3c614af 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -358,7 +358,7 @@ static int name##_open(struct inode *inode, struct file *file) \
         return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \
 } \
 \
-const struct file_operations ext4_seq_##name##_fops = { \
+static const struct file_operations ext4_seq_##name##_fops = { \
         .owner          = THIS_MODULE, \
         .open           = name##_open, \
         .read           = seq_read, \
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index eae2c11268bc..8e3ee1936c7e 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -549,6 +549,8 @@ static int cuse_channel_release(struct inode *inode, struct file *file)
                 unregister_chrdev_region(cc->cdev->dev, 1);
                 cdev_del(cc->cdev);
         }
+        /* Base reference is now owned by "fud" */
+        fuse_conn_put(&cc->fc);
 
         rc = fuse_dev_release(inode, file);     /* puts the base reference */
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e0faf8f2c868..570ca4053c80 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1049,6 +1049,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
                 tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
                 flush_dcache_page(page);
 
+                iov_iter_advance(ii, tmp);
                 if (!tmp) {
                         unlock_page(page);
                         page_cache_release(page);
@@ -1061,7 +1062,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
                 req->page_descs[req->num_pages].length = tmp;
                 req->num_pages++;
 
-                iov_iter_advance(ii, tmp);
                 count += tmp;
                 pos += tmp;
                 offset += tmp;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 89463eee6791..ca181e81c765 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1009,7 +1009,8 @@ out:
 }
 
 /* Fast check whether buffer is already attached to the required transaction */
-static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh)
+static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh,
+                                                        bool undo)
 {
         struct journal_head *jh;
         bool ret = false;
@@ -1036,6 +1037,9 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh)
         jh = READ_ONCE(bh->b_private);
         if (!jh)
                 goto out;
+        /* For undo access buffer must have data copied */
+        if (undo && !jh->b_committed_data)
+                goto out;
         if (jh->b_transaction != handle->h_transaction &&
             jh->b_next_transaction != handle->h_transaction)
                 goto out;
@@ -1073,7 +1077,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
         struct journal_head *jh;
         int rc;
 
-        if (jbd2_write_access_granted(handle, bh))
+        if (jbd2_write_access_granted(handle, bh, false))
                 return 0;
 
         jh = jbd2_journal_add_journal_head(bh);
@@ -1210,7 +1214,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
         char *committed_data = NULL;
 
         JBUFFER_TRACE(jh, "entry");
-        if (jbd2_write_access_granted(handle, bh))
+        if (jbd2_write_access_granted(handle, bh, true))
                 return 0;
 
         jh = jbd2_journal_add_journal_head(bh);
@@ -2152,6 +2156,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 
                 if (!buffer_dirty(bh)) {
                         /* bdflush has written it.  We can drop it now */
+                        __jbd2_journal_remove_checkpoint(jh);
                         goto zap_buffer;
                 }
 
@@ -2181,6 +2186,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
                                 /* The orphan record's transaction has
                                  * committed.  We can cleanse this buffer */
                                 clear_buffer_jbddirty(bh);
+                                __jbd2_journal_remove_checkpoint(jh);
                                 goto zap_buffer;
                         }
                 }
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index beac58b0e09c..646cdac73488 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -78,8 +78,7 @@ static __be32 *read_buf(struct xdr_stream *xdr, int nbytes)
 
         p = xdr_inline_decode(xdr, nbytes);
         if (unlikely(p == NULL))
-                printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed "
-                                                        "or truncated request.\n");
+                printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n");
         return p;
 }
 
@@ -890,7 +889,6 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
         struct cb_compound_hdr_arg hdr_arg = { 0 };
         struct cb_compound_hdr_res hdr_res = { NULL };
         struct xdr_stream xdr_in, xdr_out;
-        struct xdr_buf *rq_arg = &rqstp->rq_arg;
         __be32 *p, status;
         struct cb_process_state cps = {
                 .drc_status = 0,
@@ -902,8 +900,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 
         dprintk("%s: start\n", __func__);
 
-        rq_arg->len = rq_arg->head[0].iov_len + rq_arg->page_len;
-        xdr_init_decode(&xdr_in, rq_arg, rq_arg->head[0].iov_base);
+        xdr_init_decode(&xdr_in, &rqstp->rq_arg, rqstp->rq_arg.head[0].iov_base);
 
         p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len);
         xdr_init_encode(&xdr_out, &rqstp->rq_res, p);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 31b0a52223a7..c7e8b87da5b2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -75,11 +75,11 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
  * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
  * @word: long word containing the bit lock
  */
-int nfs_wait_bit_killable(struct wait_bit_key *key)
+int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-        if (fatal_signal_pending(current))
-                return -ERESTARTSYS;
         freezable_schedule_unsafe();
+        if (signal_pending_state(mode, current))
+                return -ERESTARTSYS;
         return 0;
 }
 EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 56cfde26fb9c..9dea85f7f918 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -379,7 +379,7 @@ extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
-extern int nfs_wait_bit_killable(struct wait_bit_key *key);
+extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 
 /* super.c */
 extern const struct super_operations nfs_sops;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 5c0c6b58157f..9aebffb40505 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -476,10 +476,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
                 }
                 unlock_page(page);
         }
-        if (PageDirty(page) || PageWriteback(page))
-                *uptodate = true;
-        else
-                *uptodate = PageUptodate(page);
+        *uptodate = PageUptodate(page);
         dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
         return page;
 }
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index fe3ddd20ff89..452a011ba0d8 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -129,7 +129,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c)
                 set_bit(NFS_IO_INPROGRESS, &c->flags);
                 if (atomic_read(&c->io_count) == 0)
                         break;
-                ret = nfs_wait_bit_killable(&q.key);
+                ret = nfs_wait_bit_killable(&q.key, TASK_KILLABLE);
         } while (atomic_read(&c->io_count) != 0 && !ret);
         finish_wait(wq, &q.wait);
         return ret;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5a8ae2125b50..bec0384499f7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1466,11 +1466,11 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
 }
 
 /* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */
-static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key)
+static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key, int mode)
 {
         if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags))
                 return 1;
-        return nfs_wait_bit_killable(key);
+        return nfs_wait_bit_killable(key, mode);
 }
 
 static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index a03f6f433075..3123408da935 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -367,13 +367,11 @@ static int ocfs2_mknod(struct inode *dir,
                 goto leave;
         }
 
-        status = posix_acl_create(dir, &mode, &default_acl, &acl);
+        status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
         if (status) {
                 mlog_errno(status);
                 goto leave;
         }
-        /* update inode->i_mode after mask with "umask". */
-        inode->i_mode = mode;
 
         handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb,
                                                             S_ISDIR(mode),