X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=fs%2Fnfs%2Ffile.c;h=ef57a5ae5904663d4ab20c974e920e711f921436;hb=cbc89dcfd24fd161f7a8e262266177db160a58fb;hp=c87dc713b5d75828e53f2f305083004c0440ed17;hpb=e6f194d8f6f50da6837af637b2fd839c34185f7a;p=linux-2.6-omap-h63xx.git

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index c87dc713b5d..ef57a5ae590 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -33,6 +33,7 @@
 #include <asm/system.h>
 
 #include "delegation.h"
+#include "internal.h"
 #include "iostat.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
@@ -55,6 +56,8 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
 static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
 static int nfs_setlease(struct file *file, long arg, struct file_lock **fl);
 
+static struct vm_operations_struct nfs_file_vm_ops;
+
 const struct file_operations nfs_file_operations = {
 	.llseek		= nfs_file_llseek,
 	.read		= do_sync_read,
@@ -128,7 +131,7 @@ nfs_file_release(struct inode *inode, struct file *filp)
 {
 	/* Ensure that dirty pages are flushed out with the right creds */
 	if (filp->f_mode & FMODE_WRITE)
-		filemap_fdatawrite(filp->f_mapping);
+		nfs_wb_all(filp->f_path.dentry->d_inode);
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
 	return NFS_PROTO(inode)->file_release(inode, filp);
 }
@@ -173,6 +176,31 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 	return remote_llseek(filp, offset, origin);
 }
 
+/*
+ * Helper for nfs_file_flush() and nfs_fsync()
+ *
+ * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
+ * disk, but it retrieves and clears ctx->error after synching, despite
+ * the two being set at the same time in nfs_context_set_write_error().
+ * This is because the former is used to notify the _next_ call to
+ * nfs_file_write() that a write error occured, and hence cause it to
+ * fall back to doing a synchronous write.
+ */
+static int nfs_do_fsync(struct nfs_open_context *ctx, struct inode *inode)
+{
+	int have_error, status;
+	int ret = 0;
+
+	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
+	status = nfs_wb_all(inode);
+	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
+	if (have_error)
+		ret = xchg(&ctx->error, 0);
+	if (!ret)
+		ret = status;
+	return ret;
+}
+
 /*
  * Flush all dirty pages, and check for write errors.
  *
@@ -180,7 +208,7 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 static int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
-	struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
+	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode	*inode = file->f_path.dentry->d_inode;
 	int		status;
 
@@ -189,16 +217,11 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 	if ((file->f_mode & FMODE_WRITE) == 0)
 		return 0;
 	nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
-	lock_kernel();
+
 	/* Ensure that data+attribute caches are up to date after close() */
-	status = nfs_wb_all(inode);
-	if (!status) {
-		status = ctx->error;
-		ctx->error = 0;
-		if (!status)
-			nfs_revalidate_inode(NFS_SERVER(inode), inode);
-	}
-	unlock_kernel();
+	status = nfs_do_fsync(ctx, inode);
+	if (!status)
+		nfs_revalidate_inode(NFS_SERVER(inode), inode);
 	return status;
 }
 
@@ -257,8 +280,11 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
 	status = nfs_revalidate_mapping(inode, file->f_mapping);
-	if (!status)
-		status = generic_file_mmap(file, vma);
+	if (!status) {
+		vma->vm_ops = &nfs_file_vm_ops;
+		vma->vm_flags |= VM_CAN_NONLINEAR;
+		file_accessed(file);
+	}
 	return status;
 }
 
@@ -270,45 +296,62 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 static int
 nfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 {
-	struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
+	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode *inode = dentry->d_inode;
-	int status;
 
 	dfprintk(VFS, "nfs: fsync(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);
 
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
-	lock_kernel();
-	status = nfs_wb_all(inode);
-	if (!status) {
-		status = ctx->error;
-		ctx->error = 0;
-	}
-	unlock_kernel();
-	return status;
+	return nfs_do_fsync(ctx, inode);
 }
 
 /*
- * This does the "real" work of the write. The generic routine has
- * allocated the page, locked it, done all the page alignment stuff
- * calculations etc. Now we should just copy the data from user
- * space and write it back to the real medium..
+ * This does the "real" work of the write. We must allocate and lock the
+ * page to be sent back to the generic routine, which then copies the
+ * data from user space.
  *
  * If the writer ends up delaying the write, the writer needs to
  * increment the page use counts until he is done with the page.
  */
-static int nfs_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
+static int nfs_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata)
 {
-	return nfs_flush_incompatible(file, page);
+	int ret;
+	pgoff_t index;
+	struct page *page;
+	index = pos >> PAGE_CACHE_SHIFT;
+
+	page = __grab_cache_page(mapping, index);
+	if (!page)
+		return -ENOMEM;
+	*pagep = page;
+
+	ret = nfs_flush_incompatible(file, page);
+	if (ret) {
+		unlock_page(page);
+		page_cache_release(page);
+	}
+	return ret;
 }
 
-static int nfs_commit_write(struct file *file, struct page *page, unsigned offset, unsigned to)
+static int nfs_write_end(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
 {
-	long status;
+	unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+	int status;
 
 	lock_kernel();
-	status = nfs_updatepage(file, page, offset, to-offset);
+	status = nfs_updatepage(file, page, offset, copied);
 	unlock_kernel();
-	return status;
+
+	unlock_page(page);
+	page_cache_release(page);
+
+	if (status < 0)
+		return status;
+	return copied;
 }
 
 static void nfs_invalidate_page(struct page *page, unsigned long offset)
@@ -316,7 +359,7 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 	if (offset != 0)
 		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_page_priority(page->mapping->host, page, FLUSH_INVALIDATE);
+	nfs_wb_page_cancel(page->mapping->host, page);
 }
 
 static int nfs_release_page(struct page *page, gfp_t gfp)
@@ -333,11 +376,11 @@ static int nfs_launder_page(struct page *page)
 const struct address_space_operations nfs_file_aops = {
 	.readpage = nfs_readpage,
 	.readpages = nfs_readpages,
-	.set_page_dirty = nfs_set_page_dirty,
+	.set_page_dirty = __set_page_dirty_nobuffers,
 	.writepage = nfs_writepage,
 	.writepages = nfs_writepages,
-	.prepare_write = nfs_prepare_write,
-	.commit_write = nfs_commit_write,
+	.write_begin = nfs_write_begin,
+	.write_end = nfs_write_end,
 	.invalidatepage = nfs_invalidate_page,
 	.releasepage = nfs_release_page,
 #ifdef CONFIG_NFS_DIRECTIO
@@ -346,6 +389,52 @@ const struct address_space_operations nfs_file_aops = {
 	.launder_page = nfs_launder_page,
 };
 
+static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+{
+	struct file *filp = vma->vm_file;
+	unsigned pagelen;
+	int ret = -EINVAL;
+	struct address_space *mapping;
+
+	lock_page(page);
+	mapping = page->mapping;
+	if (mapping != vma->vm_file->f_path.dentry->d_inode->i_mapping)
+		goto out_unlock;
+
+	ret = 0;
+	pagelen = nfs_page_length(page);
+	if (pagelen == 0)
+		goto out_unlock;
+
+	ret = nfs_flush_incompatible(filp, page);
+	if (ret != 0)
+		goto out_unlock;
+
+	ret = nfs_updatepage(filp, page, 0, pagelen);
+	if (ret == 0)
+		ret = pagelen;
+out_unlock:
+	unlock_page(page);
+	return ret;
+}
+
+static struct vm_operations_struct nfs_file_vm_ops = {
+	.fault = filemap_fault,
+	.page_mkwrite = nfs_vm_page_mkwrite,
+};
+
+static int nfs_need_sync_write(struct file *filp, struct inode *inode)
+{
+	struct nfs_open_context *ctx;
+
+	if (IS_SYNC(inode) || (filp->f_flags & O_SYNC))
+		return 1;
+	ctx = nfs_file_open_context(filp);
+	if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags))
+		return 1;
+	return 0;
+}
+
 static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos)
 {
@@ -382,8 +471,8 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
 	result = generic_file_aio_write(iocb, iov, nr_segs, pos);
 	/* Return error values for O_SYNC and IS_SYNC() */
-	if (result >= 0 && (IS_SYNC(inode) || (iocb->ki_filp->f_flags & O_SYNC))) {
-		int err = nfs_fsync(iocb->ki_filp, dentry, 1);
+	if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
+		int err = nfs_do_fsync(nfs_file_open_context(iocb->ki_filp), inode);
 		if (err < 0)
 			result = err;
 	}
@@ -522,8 +611,7 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	nfs_inc_stats(inode, NFSIOS_VFSLOCK);
 
 	/* No mandatory locks over NFS */
-	if ((inode->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID &&
-	    fl->fl_type != F_UNLCK)
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
 		return -ENOLCK;
 
 	if (IS_GETLK(cmd))