Merge http://linux-isdn.bkbits.net/linux-2.5.make-next

into home.transmeta.com:/home/torvalds/v2.5/linux

drivers/md/md.c

@@ -436,14 +436,15 @@ static int alloc_array_sb(mddev_t * mddev)
 
 static int alloc_disk_sb(mdk_rdev_t * rdev)
 {
-	if (rdev->sb)
+	if (rdev->sb_page)
 		MD_BUG();
 
-	rdev->sb = (mdp_super_t *) __get_free_page(GFP_KERNEL);
-	if (!rdev->sb) {
+	rdev->sb_page = alloc_page(GFP_KERNEL);
+	if (!rdev->sb_page) {
 		printk(OUT_OF_MEM);
 		return -EINVAL;
 	}
+	rdev->sb = (mdp_super_t *) page_address(rdev->sb_page);
 	clear_page(rdev->sb);
 
 	return 0;
@@ -451,9 +452,10 @@ static int alloc_disk_sb(mdk_rdev_t * rdev)
 
 static void free_disk_sb(mdk_rdev_t * rdev)
 {
-	if (rdev->sb) {
-		free_page((unsigned long) rdev->sb);
+	if (rdev->sb_page) {
+		page_cache_release(rdev->sb_page);
 		rdev->sb = NULL;
+		rdev->sb_page = NULL;
 		rdev->sb_offset = 0;
 		rdev->size = 0;
 	} else {
@@ -462,13 +464,42 @@ static void free_disk_sb(mdk_rdev_t * rdev)
 	}
 }
 
+
+static void bi_complete(struct bio *bio)
+{
+	complete((struct completion*)bio->bi_private);
+}
+
+static int sync_page_io(struct block_device *bdev, sector_t sector, int size,
+		   struct page *page, int rw)
+{
+	struct bio bio;
+	struct bio_vec vec;
+	struct completion event;
+
+	bio_init(&bio);
+	bio.bi_io_vec = &vec;
+	vec.bv_page = page;
+	vec.bv_len = size;
+	vec.bv_offset = 0;
+	bio.bi_vcnt = 1;
+	bio.bi_idx = 0;
+	bio.bi_size = size;
+	bio.bi_bdev = bdev;
+	bio.bi_sector = sector;
+	init_completion(&event);
+	bio.bi_private = &event;
+	bio.bi_end_io = bi_complete;
+	submit_bio(rw, &bio);
+	run_task_queue(&tq_disk);
+	wait_for_completion(&event);
+
+	return test_bit(BIO_UPTODATE, &bio.bi_flags);
+}
+
 static int read_disk_sb(mdk_rdev_t * rdev)
 {
-	struct address_space *mapping = rdev->bdev->bd_inode->i_mapping;
-	struct page *page;
-	char *p;
 	unsigned long sb_offset;
-	int n = PAGE_CACHE_SIZE / BLOCK_SIZE;
 
 	if (!rdev->sb) {
 		MD_BUG();
@@ -483,24 +514,14 @@ static int read_disk_sb(mdk_rdev_t * rdev)
 	 */
 	sb_offset = calc_dev_sboffset(rdev->dev, rdev->mddev, 1);
 	rdev->sb_offset = sb_offset;
-	page = read_cache_page(mapping, sb_offset/n,
-			(filler_t *)mapping->a_ops->readpage, NULL);
-	if (IS_ERR(page))
-		goto out;
-	wait_on_page_locked(page);
-	if (!PageUptodate(page))
-		goto fail;
-	if (PageError(page))
+
+	if (!sync_page_io(rdev->bdev, sb_offset<<1, MD_SB_BYTES, rdev->sb_page, READ))
 		goto fail;
-	p = (char *)page_address(page) + BLOCK_SIZE * (sb_offset % n);
-	memcpy((char*)rdev->sb, p, MD_SB_BYTES);
-	page_cache_release(page);
+
 	printk(KERN_INFO " [events: %08lx]\n", (unsigned long)rdev->sb->events_lo);
 	return 0;
 
 fail:
-	page_cache_release(page);
-out:
 	printk(NO_SB,partition_name(rdev->dev));
 	return -EINVAL;
 }
@@ -893,11 +914,6 @@ static mdk_rdev_t * find_rdev_all(kdev_t dev)
 
 static int write_disk_sb(mdk_rdev_t * rdev)
 {
-	struct block_device *bdev = rdev->bdev;
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
-	struct page *page;
-	unsigned offs;
-	int error;
 	kdev_t dev = rdev->dev;
 	unsigned long sb_offset, size;
 
@@ -933,29 +949,11 @@ static int write_disk_sb(mdk_rdev_t * rdev)
 	}
 
 	printk(KERN_INFO "(write) %s's sb offset: %ld\n", partition_name(dev), sb_offset);
-	fsync_bdev(bdev);
-	page = grab_cache_page(mapping, sb_offset/(PAGE_CACHE_SIZE/BLOCK_SIZE));
-	offs = sb_offset % (PAGE_CACHE_SIZE/BLOCK_SIZE);
-	if (!page)
+
+	if (!sync_page_io(rdev->bdev, sb_offset<<1, MD_SB_BYTES, rdev->sb_page, WRITE))
 		goto fail;
-	error = mapping->a_ops->prepare_write(NULL, page, offs,
-						offs + MD_SB_BYTES);
-	if (error)
-		goto unlock;
-	memcpy((char *)page_address(page) + offs, rdev->sb, MD_SB_BYTES);
-	error = mapping->a_ops->commit_write(NULL, page, offs,
-						offs + MD_SB_BYTES);
-	if (error)
-		goto unlock;
-	unlock_page(page);
-	wait_on_page_locked(page);
-	page_cache_release(page);
-	fsync_bdev(bdev);
 skip:
 	return 0;
-unlock:
-	unlock_page(page);
-	page_cache_release(page);
 fail:
 	printk("md: write_disk_sb failed for device %s\n", partition_name(dev));
 	return 1;

drivers/md/xor.c

@@ -19,7 +19,6 @@
 #define BH_TRACE 0
 #include <linux/module.h>
 #include <linux/raid/md.h>
-#include <linux/raid/md_compatible.h>
 #include <linux/raid/xor.h>
 #include <asm/xor.h>
 
@@ -27,31 +26,30 @@
 static struct xor_block_template *active_template;
 
 void
-xor_block(unsigned int count, struct buffer_head **bh_ptr)
+xor_block(unsigned int count, unsigned int bytes, void **ptr)
 {
 	unsigned long *p0, *p1, *p2, *p3, *p4;
-	unsigned long bytes = bh_ptr[0]->b_size;
 
-	p0 = (unsigned long *) bh_ptr[0]->b_data;
-	p1 = (unsigned long *) bh_ptr[1]->b_data;
+	p0 = (unsigned long *) ptr[0];
+	p1 = (unsigned long *) ptr[1];
 	if (count == 2) {
 		active_template->do_2(bytes, p0, p1);
 		return;
 	}
 
-	p2 = (unsigned long *) bh_ptr[2]->b_data;
+	p2 = (unsigned long *) ptr[2];
 	if (count == 3) {
 		active_template->do_3(bytes, p0, p1, p2);
 		return;
 	}
 
-	p3 = (unsigned long *) bh_ptr[3]->b_data;
+	p3 = (unsigned long *) ptr[3];
 	if (count == 4) {
 		active_template->do_4(bytes, p0, p1, p2, p3);
 		return;
 	}
 
-	p4 = (unsigned long *) bh_ptr[4]->b_data;
+	p4 = (unsigned long *) ptr[4];
 	active_template->do_5(bytes, p0, p1, p2, p3, p4);
 }
 
@@ -103,7 +101,7 @@ calibrate_xor_block(void)
 	void *b1, *b2;
 	struct xor_block_template *f, *fastest;
 
-	b1 = (void *) md__get_free_pages(GFP_KERNEL, 2);
+	b1 = (void *) __get_free_pages(GFP_KERNEL, 2);
 	if (! b1) {
 		printk("raid5: Yikes!  No memory available.\n");
 		return -ENOMEM;
@@ -137,7 +135,7 @@ calibrate_xor_block(void)
 	return 0;
 }
 
-MD_EXPORT_SYMBOL(xor_block);
+EXPORT_SYMBOL(xor_block);
 MODULE_LICENSE("GPL");
 
 module_init(calibrate_xor_block);

fs/intermezzo/ext_attr.c

@@ -105,9 +105,8 @@ int presto_set_ext_attr(struct inode *inode,
                         printk("InterMezzo: out of memory!!!\n");
                         return -ENOMEM;
                 }
-                error = copy_from_user(buf, buffer, buffer_len);
-                if (error) 
-                        return error;
+                if (copy_from_user(buf, buffer, buffer_len))
+                        return -EFAULT;
             } else 
                 buf = buffer;
         } else

fs/intermezzo/kml.c

@@ -31,10 +31,9 @@ int begin_kml_reint (struct file *file, unsigned long arg)
 
         ENTRY;
         /* allocate buffer & copy it to kernel space */
-        error = copy_from_user(&input, (char *)arg, sizeof(input));
-        if ( error ) {
+        if (copy_from_user(&input, (char *)arg, sizeof(input))) {
                 EXIT;
-                return error;
+                return -EFAULT;
         }
 
         if (input.reclen > kml_fsdata->kml_maxsize)
@@ -45,11 +44,10 @@ int begin_kml_reint (struct file *file, unsigned long arg)
                 EXIT;
                 return -ENOMEM;
         }
-        error = copy_from_user(path, input.volname, input.namelen);
-        if ( error ) {
+        if (copy_from_user(path, input.volname, input.namelen)) {
                 PRESTO_FREE(path, input.namelen + 1);
                 EXIT;
-                return error;
+                return -EFAULT;
         }
         path[input.namelen] = '\0';
         fset = kml_getfset (path);
@@ -57,10 +55,9 @@ int begin_kml_reint (struct file *file, unsigned long arg)
 
         kml_fsdata = FSET_GET_KMLDATA(fset);
         /* read the buf from user memory here */
-        error = copy_from_user(kml_fsdata->kml_buf, input.recbuf, input.reclen);
-        if ( error ) {
+        if (copy_from_user(kml_fsdata->kml_buf, input.recbuf, input.reclen)) {
                 EXIT;
-                return error;
+                return -EFAULT;
         }
         kml_fsdata->kml_len = input.reclen;
 
@@ -94,21 +91,19 @@ int do_kml_reint (struct file *file, unsigned long arg)
         struct presto_file_set *fset;
 
         ENTRY;
-        error = copy_from_user(&input, (char *)arg, sizeof(input));
-        if ( error ) {
+        if (copy_from_user(&input, (char *)arg, sizeof(input))) {
                 EXIT;
-                return error;
+                return -EFAULT;
         }
         PRESTO_ALLOC(path, char *, input.namelen + 1);
         if ( !path ) {
                 EXIT;
                 return -ENOMEM;
         }
-        error = copy_from_user(path, input.volname, input.namelen);
-        if ( error ) {
+        if (copy_from_user(path, input.volname, input.namelen)) {
                 PRESTO_FREE(path, input.namelen + 1);
                 EXIT;
-                return error;
+                return -EFAULT;
         }
         path[input.namelen] = '\0';
         fset = kml_getfset (path);
@@ -138,7 +133,8 @@ int do_kml_reint (struct file *file, unsigned long arg)
                                 strlen (close->path) + 1, input.pathlen);
                         error = -ENOMEM;
                 }
-                copy_to_user((char *)arg, &input, sizeof (input));
+                if (copy_to_user((char *)arg, &input, sizeof (input)))
+			return -EFAULT;
         }
         return error;
 }
@@ -161,10 +157,9 @@ int end_kml_reint (struct file *file, unsigned long arg)
         char *path;
 
         ENTRY;
-        error = copy_from_user(&input, (char *)arg, sizeof(input));
-        if ( error ) {
+        if (copy_from_user(&input, (char *)arg, sizeof(input))) { 
                EXIT;
-               return error;
+               return -EFAULT;
         }
 
         PRESTO_ALLOC(path, char *, input.namelen + 1);
@@ -172,11 +167,11 @@ int end_kml_reint (struct file *file, unsigned long arg)
                 EXIT;
                 return -ENOMEM;
         }
-        error = copy_from_user(path, input.volname, input.namelen);
+        if (copy_from_user(path, input.volname, input.namelen)) {
         if ( error ) {
                 PRESTO_FREE(path, input.namelen + 1);
                 EXIT;
-                return error;
+                return -EFAULT;
         }
         path[input.namelen] = '\0';
         fset = kml_getfset (path);
@@ -193,7 +188,8 @@ int end_kml_reint (struct file *file, unsigned long arg)
 #if 0
         input.newpos = kml_upc->newpos;
         input.count = kml_upc->count;
-        copy_to_user((char *)arg, &input, sizeof (input));
+        if (copy_to_user((char *)arg, &input, sizeof (input)))
+		return -EFAULT;
 #endif
         return error;
 }

fs/nfsd/export.c

@@ -315,17 +315,19 @@ exp_export(struct nfsctl_export *nxp)
 	 * 2:  We must be able to find an inode from a filehandle.
 	 *       This means that s_export_op must be set.
 	 */
-	if (((inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV)
-	     || (nxp->ex_flags & NFSEXP_FSID))
-	    &&
-	    inode->i_sb->s_export_op)
-		/* Ok, we can export it */;
-	else {
+	if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV)) {
+		if (!(nxp->ex_flags & NFSEXP_FSID)) {
+			dprintk("exp_export: export of non-dev fs without fsid");
+			goto finish;
+		}
+	}
+	if (!inode->i_sb->s_export_op) {
 		dprintk("exp_export: export of invalid fs type.\n");
 		goto finish;
 	}
-	if (inode->i_sb->s_export_op &&
-	    !inode->i_sb->s_export_op->find_exported_dentry)
+
+	/* Ok, we can export it */;
+	if (!inode->i_sb->s_export_op->find_exported_dentry)
 		inode->i_sb->s_export_op->find_exported_dentry =
 			find_exported_dentry;
 

fs/nfsd/vfs.c

@@ -414,11 +414,13 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
-	int		err;
+	int		flags = O_RDONLY|O_LARGEFILE, mode = FMODE_READ, err;
 
-	/* If we get here, then the client has already done an "open", and (hopefully)
-	 * checked permission - so allow OWNER_OVERRIDE in case a chmod has now revoked
-	 * permission */
+	/*
+	 * If we get here, then the client has already done an "open",
+	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
+	 * in case a chmod has now revoked permission.
+	 */
 	err = fh_verify(rqstp, fhp, type, access | MAY_OWNER_OVERRIDE);
 	if (err)
 		goto out;
@@ -443,37 +445,24 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (err)
 		goto out_nfserr;
 
-	if ((access & MAY_WRITE) && (err = get_write_access(inode)) != 0)
-		goto out_nfserr;
-
-	memset(filp, 0, sizeof(*filp));
-	filp->f_op    = fops_get(inode->i_fop);
-	atomic_set(&filp->f_count, 1);
-	filp->f_dentry = dentry;
-	filp->f_vfsmnt = fhp->fh_export->ex_mnt;
 	if (access & MAY_WRITE) {
-		filp->f_flags = O_WRONLY|O_LARGEFILE;
-		filp->f_mode  = FMODE_WRITE;
+		err = get_write_access(inode);
+		if (err)
+			goto out_nfserr;
+
+		flags = O_WRONLY|O_LARGEFILE;
+		mode  = FMODE_WRITE;
+
 		DQUOT_INIT(inode);
-	} else {
-		filp->f_flags = O_RDONLY|O_LARGEFILE;
-		filp->f_mode  = FMODE_READ;
 	}
 
-	err = 0;
-	if (filp->f_op && filp->f_op->open) {
-		err = filp->f_op->open(inode, filp);
-		if (err) {
-			fops_put(filp->f_op);
-			if (access & MAY_WRITE)
-				put_write_access(inode);
-
-			/* I nearly added put_filp() call here, but this filp
-			 * is really on callers stack frame. -DaveM
-			 */
-			atomic_dec(&filp->f_count);
-		}
-	}
+	err = init_private_file(filp, dentry, mode);
+	if (!err) {
+		filp->f_flags = flags;
+		filp->f_vfsmnt = fhp->fh_export->ex_mnt;
+	} else if (access & MAY_WRITE)
+		put_write_access(inode);
+
 out_nfserr:
 	if (err)
 		err = nfserrno(err);
@@ -490,9 +479,8 @@ nfsd_close(struct file *filp)
 	struct dentry	*dentry = filp->f_dentry;
 	struct inode	*inode = dentry->d_inode;
 
-	if (filp->f_op && filp->f_op->release)
+	if (filp->f_op->release)
 		filp->f_op->release(inode, filp);
-	fops_put(filp->f_op);
 	if (filp->f_mode & FMODE_WRITE)
 		put_write_access(inode);
 }

fs/read_write.c

@@ -162,57 +162,107 @@ asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
 }
 #endif
 
-asmlinkage ssize_t sys_read(unsigned int fd, char * buf, size_t count)
+ssize_t vfs_read(struct file *file, char *buf, size_t count, loff_t *pos)
 {
+	struct inode *inode = file->f_dentry->d_inode;
 	ssize_t ret;
-	struct file * file;
 
-	ret = -EBADF;
-	file = fget(fd);
-	if (file) {
-		if (file->f_mode & FMODE_READ) {
-			ret = locks_verify_area(FLOCK_VERIFY_READ, file->f_dentry->d_inode,
-						file, file->f_pos, count);
-			if (!ret) {
-				ssize_t (*read)(struct file *, char *, size_t, loff_t *);
-				ret = -EINVAL;
-				if (file->f_op && (read = file->f_op->read) != NULL)
-					ret = read(file, buf, count, &file->f_pos);
-			}
-		}
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!file->f_op || !file->f_op->read)
+		return -EINVAL;
+	if (pos < 0)
+		return -EINVAL;
+
+	ret = locks_verify_area(FLOCK_VERIFY_READ, inode, file, *pos, count);
+	if (!ret) {
+		ret = file->f_op->read(file, buf, count, pos);
 		if (ret > 0)
 			dnotify_parent(file->f_dentry, DN_ACCESS);
+	}
+
+	return ret;
+}
+
+ssize_t vfs_write(struct file *file, const char *buf, size_t count, loff_t *pos)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EBADF;
+	if (!file->f_op || !file->f_op->write)
+		return -EINVAL;
+	if (pos < 0)
+		return -EINVAL;
+
+	ret = locks_verify_area(FLOCK_VERIFY_WRITE, inode, file, *pos, count);
+	if (!ret) {
+		ret = file->f_op->write(file, buf, count, pos);
+		if (ret > 0)
+			dnotify_parent(file->f_dentry, DN_MODIFY);
+	}
+
+	return ret;
+}
+
+asmlinkage ssize_t sys_read(unsigned int fd, char * buf, size_t count)
+{
+	struct file *file;
+	ssize_t ret = -EBADF;
+
+	file = fget(fd);
+	if (file) {
+		ret = vfs_read(file, buf, count, &file->f_pos);
 		fput(file);
 	}
+
 	return ret;
 }
 
 asmlinkage ssize_t sys_write(unsigned int fd, const char * buf, size_t count)
 {
-	ssize_t ret;
-	struct file * file;
+	struct file *file;
+	ssize_t ret = -EBADF;
 
-	ret = -EBADF;
 	file = fget(fd);
 	if (file) {
-		if (file->f_mode & FMODE_WRITE) {
-			struct inode *inode = file->f_dentry->d_inode;
-			ret = locks_verify_area(FLOCK_VERIFY_WRITE, inode, file,
-				file->f_pos, count);
-			if (!ret) {
-				ssize_t (*write)(struct file *, const char *, size_t, loff_t *);
-				ret = -EINVAL;
-				if (file->f_op && (write = file->f_op->write) != NULL)
-					ret = write(file, buf, count, &file->f_pos);
-			}
-		}
-		if (ret > 0)
-			dnotify_parent(file->f_dentry, DN_MODIFY);
+		ret = vfs_write(file, buf, count, &file->f_pos);
 		fput(file);
 	}
+
 	return ret;
 }
 
+asmlinkage ssize_t sys_pread(unsigned int fd, char *buf,
+			     size_t count, loff_t pos)
+{
+	struct file *file;
+	ssize_t ret = -EBADF;
+
+	file = fget(fd);
+	if (file) {
+		ret = vfs_read(file, buf, count, &pos);
+		fput(file);
+	}
+
+	return ret;
+}
+
+asmlinkage ssize_t sys_pwrite(unsigned int fd, const char *buf,
+			      size_t count, loff_t pos)
+{
+	struct file *file;
+	ssize_t ret = -EBADF;
+
+	file = fget(fd);
+	if (file) {
+		ret = vfs_write(file, buf, count, &pos);
+		fput(file);
+	}
+
+	return ret;
+}
 
 static ssize_t do_readv_writev(int type, struct file *file,
 			       const struct iovec * vector,
@@ -355,70 +405,3 @@ asmlinkage ssize_t sys_writev(unsigned long fd, const struct iovec * vector,
 bad_file:
 	return ret;
 }
-
-/* From the Single Unix Spec: pread & pwrite act like lseek to pos + op +
-   lseek back to original location.  They fail just like lseek does on
-   non-seekable files.  */
-
-asmlinkage ssize_t sys_pread(unsigned int fd, char * buf,
-			     size_t count, loff_t pos)
-{
-	ssize_t ret;
-	struct file * file;
-	ssize_t (*read)(struct file *, char *, size_t, loff_t *);
-
-	ret = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto bad_file;
-	if (!(file->f_mode & FMODE_READ))
-		goto out;
-	ret = locks_verify_area(FLOCK_VERIFY_READ, file->f_dentry->d_inode,
-				file, pos, count);
-	if (ret)
-		goto out;
-	ret = -EINVAL;
-	if (!file->f_op || !(read = file->f_op->read))
-		goto out;
-	if (pos < 0)
-		goto out;
-	ret = read(file, buf, count, &pos);
-	if (ret > 0)
-		dnotify_parent(file->f_dentry, DN_ACCESS);
-out:
-	fput(file);
-bad_file:
-	return ret;
-}
-
-asmlinkage ssize_t sys_pwrite(unsigned int fd, const char * buf,
-			      size_t count, loff_t pos)
-{
-	ssize_t ret;
-	struct file * file;
-	ssize_t (*write)(struct file *, const char *, size_t, loff_t *);
-
-	ret = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto bad_file;
-	if (!(file->f_mode & FMODE_WRITE))
-		goto out;
-	ret = locks_verify_area(FLOCK_VERIFY_WRITE, file->f_dentry->d_inode,
-				file, pos, count);
-	if (ret)
-		goto out;
-	ret = -EINVAL;
-	if (!file->f_op || !(write = file->f_op->write))
-		goto out;
-	if (pos < 0)
-		goto out;
-
-	ret = write(file, buf, count, &pos);
-	if (ret > 0)
-		dnotify_parent(file->f_dentry, DN_MODIFY);
-out:
-	fput(file);
-bad_file:
-	return ret;
-}

fs/reiserfs/inode.c

@@ -1484,13 +1484,19 @@ static int reiserfs_new_symlink (struct reiserfs_transaction_handle *th,
 /* inserts the stat data into the tree, and then calls
    reiserfs_new_directory (to insert ".", ".." item if new object is
    directory) or reiserfs_new_symlink (to insert symlink body if new
-   object is symlink) or nothing (if new object is regular file) */
-struct inode * reiserfs_new_inode (struct reiserfs_transaction_handle *th,
-				   struct inode * dir, int mode, 
-				   const char * symname, 
-				   int i_size, /* 0 for regular, EMTRY_DIR_SIZE for dirs,
-						  strlen (symname) for symlinks)*/
-				   struct dentry *dentry, struct inode *inode, int * err)
+   object is symlink) or nothing (if new object is regular file) 
+
+   NOTE! uid and gid must already be set in the inode.  If we return
+   non-zero due to an error, we have to drop the quota previously allocated
+   for the fresh inode.  This can only be done outside a transaction, so
+   if we return non-zero, we also end the transaction.  */
+int reiserfs_new_inode (struct reiserfs_transaction_handle *th,
+			struct inode * dir, int mode, 
+			const char * symname, 
+                        /* 0 for regular, EMTRY_DIR_SIZE for dirs, 
+			   strlen (symname) for symlinks)*/
+		         loff_t i_size, struct dentry *dentry, 
+			 struct inode *inode)
 {
     struct super_block * sb;
     INITIALIZE_PATH (path_to_key);
@@ -1498,72 +1504,40 @@ struct inode * reiserfs_new_inode (struct reiserfs_transaction_handle *th,
     struct item_head ih;
     struct stat_data sd;
     int retval;
+    int err;
   
     if (!dir || !dir->i_nlink) {
-	*err = -EPERM;
-	iput(inode) ;
-	return NULL;
+	err = -EPERM;
+	goto out_bad_inode;
     }
 
     sb = dir->i_sb;
-    inode->i_flags = 0;//inode->i_sb->s_flags;
 
     /* item head of new item */
     ih.ih_key.k_dir_id = INODE_PKEY (dir)->k_objectid;
     ih.ih_key.k_objectid = cpu_to_le32 (reiserfs_get_unused_objectid (th));
     if (!ih.ih_key.k_objectid) {
-	iput(inode) ;
-	*err = -ENOMEM;
-	return NULL;
+	err = -ENOMEM;
+	goto out_bad_inode ;
     }
     if (old_format_only (sb))
-      /* not a perfect generation count, as object ids can be reused, but this
-      ** is as good as reiserfs can do right now.
-      ** note that the private part of inode isn't filled in yet, we have
-      ** to use the directory.
-      */
-      inode->i_generation = le32_to_cpu (INODE_PKEY (dir)->k_objectid);
+	/* not a perfect generation count, as object ids can be reused, but 
+	** this is as good as reiserfs can do right now.
+	** note that the private part of inode isn't filled in yet, we have
+	** to use the directory.
+	*/
+	inode->i_generation = le32_to_cpu (INODE_PKEY (dir)->k_objectid);
     else
 #if defined( USE_INODE_GENERATION_COUNTER )
-      inode->i_generation = 
-	le32_to_cpu( REISERFS_SB(sb) -> s_rs -> s_inode_generation );
+	inode->i_generation = le32_to_cpu(REISERFS_SB(sb)->s_rs->s_inode_generation);
 #else
-      inode->i_generation = ++event;
+	inode->i_generation = ++event;
 #endif
-    if (old_format_only (sb))
-	make_le_item_head (&ih, 0, KEY_FORMAT_3_5, SD_OFFSET, TYPE_STAT_DATA, SD_V1_SIZE, MAX_US_INT);
-    else
-	make_le_item_head (&ih, 0, KEY_FORMAT_3_6, SD_OFFSET, TYPE_STAT_DATA, SD_SIZE, MAX_US_INT);
-
-
-    /* key to search for correct place for new stat data */
-    _make_cpu_key (&key, KEY_FORMAT_3_6, le32_to_cpu (ih.ih_key.k_dir_id),
-		   le32_to_cpu (ih.ih_key.k_objectid), SD_OFFSET, TYPE_STAT_DATA, 3/*key length*/);
-
-    /* find proper place for inserting of stat data */
-    retval = search_item (sb, &key, &path_to_key);
-    if (retval == IO_ERROR) {
-	iput (inode);
-	*err = -EIO;
-	return NULL;
-    }
-    if (retval == ITEM_FOUND) {
-	pathrelse (&path_to_key);
-	iput (inode);
-	*err = -EEXIST;
-	return NULL;
-    }
 
     /* fill stat data */
-    inode->i_mode = mode;
     inode->i_nlink = (S_ISDIR (mode) ? 2 : 1);
-    inode->i_uid = current->fsuid;
-    if (dir->i_mode & S_ISGID) {
-	inode->i_gid = dir->i_gid;
-	if (S_ISDIR(mode))
-	    inode->i_mode |= S_ISGID;
-    } else
-	inode->i_gid = current->fsgid;
+
+    /* uid and gid must already be set by the caller for quota init */
 
     inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
     inode->i_size = i_size;
@@ -1578,18 +1552,38 @@ struct inode * reiserfs_new_inode (struct reiserfs_transaction_handle *th,
     REISERFS_I(inode)->i_trans_id = 0;
     REISERFS_I(inode)->i_trans_index = 0;
 
+    if (old_format_only (sb))
+	make_le_item_head (&ih, 0, KEY_FORMAT_3_5, SD_OFFSET, TYPE_STAT_DATA, SD_V1_SIZE, MAX_US_INT);
+    else
+	make_le_item_head (&ih, 0, KEY_FORMAT_3_6, SD_OFFSET, TYPE_STAT_DATA, SD_SIZE, MAX_US_INT);
+
+    /* key to search for correct place for new stat data */
+    _make_cpu_key (&key, KEY_FORMAT_3_6, le32_to_cpu (ih.ih_key.k_dir_id),
+		   le32_to_cpu (ih.ih_key.k_objectid), SD_OFFSET, TYPE_STAT_DATA, 3/*key length*/);
+
+    /* find proper place for inserting of stat data */
+    retval = search_item (sb, &key, &path_to_key);
+    if (retval == IO_ERROR) {
+	err = -EIO;
+	goto out_bad_inode;
+    }
+    if (retval == ITEM_FOUND) {
+	pathrelse (&path_to_key);
+	err = -EEXIST;
+	goto out_bad_inode;
+    }
+
     if (old_format_only (sb)) {
 	if (inode->i_uid & ~0xffff || inode->i_gid & ~0xffff) {
 	    pathrelse (&path_to_key);
 	    /* i_uid or i_gid is too big to be stored in stat data v3.5 */
-	    iput (inode);
-	    *err = -EINVAL;
-	    return NULL;
+	    err = -EINVAL;
+	    goto out_bad_inode;
 	}
 	inode2sd_v1 (&sd, inode);
-    } else
+    } else {
 	inode2sd (&sd, inode);
-
+    }
     // these do not go to on-disk stat data
     inode->i_ino = le32_to_cpu (ih.ih_key.k_objectid);
     inode->i_blksize = PAGE_SIZE;
@@ -1610,10 +1604,9 @@ struct inode * reiserfs_new_inode (struct reiserfs_transaction_handle *th,
     /* insert the stat data into the tree */
     retval = reiserfs_insert_item (th, &path_to_key, &key, &ih, (char *)(&sd));
     if (retval) {
-	iput (inode);
-	*err = retval;
+	err = retval;
 	reiserfs_check_path(&path_to_key) ;
-	return NULL;
+	goto out_bad_inode;
     }
 
     if (S_ISDIR(mode)) {
@@ -1628,19 +1621,35 @@ struct inode * reiserfs_new_inode (struct reiserfs_transaction_handle *th,
 	retval = reiserfs_new_symlink (th, &ih, &path_to_key, symname, i_size);
     }
     if (retval) {
-      inode->i_nlink = 0;
-	iput (inode);
-	*err = retval;
+	err = retval;
 	reiserfs_check_path(&path_to_key) ;
-	return NULL;
+	journal_end(th, th->t_super, th->t_blocks_allocated);
+	goto out_inserted_sd;
     }
 
     insert_inode_hash (inode);
-    // we do not mark inode dirty: on disk content matches to the
-    // in-core one
+    reiserfs_update_sd(th, inode);
     reiserfs_check_path(&path_to_key) ;
 
-    return inode;
+    return 0;
+
+/* it looks like you can easily compress these two goto targets into
+ * one.  Keeping it like this doesn't actually hurt anything, and they
+ * are place holders for what the quota code actually needs.
+ */
+out_bad_inode:
+    /* Invalidate the object, nothing was inserted yet */
+    INODE_PKEY(inode)->k_objectid = 0;
+
+    /* dquot_drop must be done outside a transaction */
+    journal_end(th, th->t_super, th->t_blocks_allocated) ;
+    make_bad_inode(inode);
+
+out_inserted_sd:
+    inode->i_nlink = 0;
+    th->t_trans_id = 0; /* so the caller can't use this handle later */
+    iput(inode);
+    return err;
 }
 
 /*

fs/reiserfs/journal.c

@@ -204,7 +204,7 @@ static int set_bit_in_list_bitmap(struct super_block *p_s_sb, int block,
   if (!jb->bitmaps[bmap_nr]) {
     jb->bitmaps[bmap_nr] = get_bitmap_node(p_s_sb) ;
   }
-  set_bit(bit_nr, jb->bitmaps[bmap_nr]->data) ;
+  set_bit(bit_nr, (unsigned long *)jb->bitmaps[bmap_nr]->data) ;
   return 0 ;
 }
 
@@ -550,7 +550,7 @@ int reiserfs_in_journal(struct super_block *p_s_sb,
       PROC_INFO_INC( p_s_sb, journal.in_journal_bitmap );
       jb = SB_JOURNAL(p_s_sb)->j_list_bitmap + i ;
       if (jb->journal_list && jb->bitmaps[bmap_nr] &&
-          test_bit(bit_nr, jb->bitmaps[bmap_nr]->data)) {
+          test_bit(bit_nr, (unsigned long *)jb->bitmaps[bmap_nr]->data)) {
 	tmp_bit = find_next_zero_bit((unsigned long *)
 	                             (jb->bitmaps[bmap_nr]->data),
 	                             p_s_sb->s_blocksize << 3, bit_nr+1) ; 

fs/reiserfs/namei.c

@@ -248,7 +248,7 @@ static int linear_search_in_dir_item (struct cpu_key * key, struct reiserfs_dir_
    
 	/* mark, that this generation number is used */
 	if (de->de_gen_number_bit_string)
-	    set_bit (GET_GENERATION_NUMBER (deh_offset (deh)), de->de_gen_number_bit_string);
+	    set_bit (GET_GENERATION_NUMBER (deh_offset (deh)), (unsigned long *)de->de_gen_number_bit_string);
 
 	// calculate pointer to name and namelen
 	de->de_entry_num = i;
@@ -504,7 +504,7 @@ static int reiserfs_add_entry (struct reiserfs_transaction_handle *th, struct in
 	return -EEXIST;
     }
 
-    gen_number = find_first_zero_bit (bit_string, MAX_GENERATION_NUMBER + 1);
+    gen_number = find_first_zero_bit ((unsigned long *)bit_string, MAX_GENERATION_NUMBER + 1);
     if (gen_number > MAX_GENERATION_NUMBER) {
       /* there is no free generation number */
       reiserfs_warning ("reiserfs_add_entry: Congratulations! we have got hash function screwed up\n");
@@ -552,6 +552,40 @@ static int reiserfs_add_entry (struct reiserfs_transaction_handle *th, struct in
     return 0;
 }
 
+/* quota utility function, call if you've had to abort after calling
+** new_inode_init, and have not called reiserfs_new_inode yet.
+** This should only be called on inodes that do not hav stat data
+** inserted into the tree yet.
+*/
+static int drop_new_inode(struct inode *inode) {
+    make_bad_inode(inode) ;
+    iput(inode) ;
+    return 0 ;
+}
+
+/* utility function that does setup for reiserfs_new_inode.  
+** DQUOT_ALLOC_INODE cannot be called inside a transaction, so we had
+** to pull some bits of reiserfs_new_inode out into this func.
+** Yes, the actual quota calls are missing, they are part of the quota
+** patch.
+*/
+static int new_inode_init(struct inode *inode, struct inode *dir, int mode) {
+
+    /* the quota init calls have to know who to charge the quota to, so
+    ** we have to set uid and gid here
+    */
+    inode->i_uid = current->fsuid;
+    inode->i_mode = mode;
+
+    if (dir->i_mode & S_ISGID) {
+        inode->i_gid = dir->i_gid;
+        if (S_ISDIR(mode))
+            inode->i_mode |= S_ISGID;
+    } else {
+        inode->i_gid = current->fsgid;
+    }
+    return 0 ;
+}
 
 //
 // a portion of this function, particularly the VFS interface portion,
@@ -564,7 +598,6 @@ static int reiserfs_create (struct inode * dir, struct dentry *dentry, int mode)
 {
     int retval;
     struct inode * inode;
-    int windex ;
     int jbegin_count = JOURNAL_PER_BALANCE_CNT * 2 ;
     struct reiserfs_transaction_handle th ;
 
@@ -572,16 +605,16 @@ static int reiserfs_create (struct inode * dir, struct dentry *dentry, int mode)
     if (!inode) {
 	return -ENOMEM ;
     }
+    retval = new_inode_init(inode, dir, mode);
+    if (retval)
+        return retval;
+
     lock_kernel();
     journal_begin(&th, dir->i_sb, jbegin_count) ;
     th.t_caller = "create" ;
-    windex = push_journal_writer("reiserfs_create") ;
-    inode = reiserfs_new_inode (&th, dir, mode, 0, 0/*i_size*/, dentry, inode, &retval);
-    if (!inode) {
-	pop_journal_writer(windex) ;
-	journal_end(&th, dir->i_sb, jbegin_count) ;
-	unlock_kernel();
-	return retval;
+    retval = reiserfs_new_inode (&th, dir, mode, 0, 0/*i_size*/, dentry, inode);
+    if (retval) {
+        goto out_failed;
     }
 	
     inode->i_op = &reiserfs_file_inode_operations;
@@ -593,22 +626,19 @@ static int reiserfs_create (struct inode * dir, struct dentry *dentry, int mode)
     if (retval) {
 	inode->i_nlink--;
 	reiserfs_update_sd (&th, inode);
-	pop_journal_writer(windex) ;
-	// FIXME: should we put iput here and have stat data deleted
-	// in the same transactioin
 	journal_end(&th, dir->i_sb, jbegin_count) ;
 	iput (inode);
-	unlock_kernel();
-	return retval;
+	goto out_failed;
     }
     reiserfs_update_inode_transaction(inode) ;
     reiserfs_update_inode_transaction(dir) ;
 
     d_instantiate(dentry, inode);
-    pop_journal_writer(windex) ;
     journal_end(&th, dir->i_sb, jbegin_count) ;
+
+out_failed:
     unlock_kernel();
-    return 0;
+    return retval;
 }
 
 
@@ -623,7 +653,6 @@ static int reiserfs_mknod (struct inode * dir, struct dentry *dentry, int mode,
 {
     int retval;
     struct inode * inode;
-    int windex ;
     struct reiserfs_transaction_handle th ;
     int jbegin_count = JOURNAL_PER_BALANCE_CNT * 3; 
 
@@ -631,16 +660,16 @@ static int reiserfs_mknod (struct inode * dir, struct dentry *dentry, int mode,
     if (!inode) {
 	return -ENOMEM ;
     }
+    retval = new_inode_init(inode, dir, mode);
+    if (retval)
+        return retval;
+
     lock_kernel();
     journal_begin(&th, dir->i_sb, jbegin_count) ;
-    windex = push_journal_writer("reiserfs_mknod") ;
 
-    inode = reiserfs_new_inode (&th, dir, mode, 0, 0/*i_size*/, dentry, inode, &retval);
-    if (!inode) {
-	pop_journal_writer(windex) ;
-	journal_end(&th, dir->i_sb, jbegin_count) ;
-	unlock_kernel();
-	return retval;
+    retval = reiserfs_new_inode (&th, dir, mode, 0, 0/*i_size*/, dentry, inode);
+    if (retval) {
+        goto out_failed;
     }
 
     init_special_inode(inode, mode, rdev) ;
@@ -656,18 +685,17 @@ static int reiserfs_mknod (struct inode * dir, struct dentry *dentry, int mode,
     if (retval) {
 	inode->i_nlink--;
 	reiserfs_update_sd (&th, inode);
-	pop_journal_writer(windex) ;
 	journal_end(&th, dir->i_sb, jbegin_count) ;
 	iput (inode);
-	unlock_kernel();
-	return retval;
+	goto out_failed;
     }
 
     d_instantiate(dentry, inode);
-    pop_journal_writer(windex) ;
     journal_end(&th, dir->i_sb, jbegin_count) ;
+
+out_failed:
     unlock_kernel();
-    return 0;
+    return retval;
 }
 
 
@@ -682,33 +710,33 @@ static int reiserfs_mkdir (struct inode * dir, struct dentry *dentry, int mode)
 {
     int retval;
     struct inode * inode;
-    int windex ;
     struct reiserfs_transaction_handle th ;
     int jbegin_count = JOURNAL_PER_BALANCE_CNT * 3; 
 
+    mode = S_IFDIR | mode;
     inode = new_inode(dir->i_sb) ;
     if (!inode) {
 	return -ENOMEM ;
     }
+    retval = new_inode_init(inode, dir, mode);
+    if (retval)
+        return retval;
+
     lock_kernel();
     journal_begin(&th, dir->i_sb, jbegin_count) ;
-    windex = push_journal_writer("reiserfs_mkdir") ;
 
     /* inc the link count now, so another writer doesn't overflow it while
     ** we sleep later on.
     */
     INC_DIR_INODE_NLINK(dir)
 
-    mode = S_IFDIR | mode;
-    inode = reiserfs_new_inode (&th, dir, mode, 0/*symlink*/,
-				old_format_only (dir->i_sb) ? EMPTY_DIR_SIZE_V1 : EMPTY_DIR_SIZE,
-				dentry, inode, &retval);
-    if (!inode) {
-	pop_journal_writer(windex) ;
+    retval = reiserfs_new_inode (&th, dir, mode, 0/*symlink*/,
+				old_format_only (dir->i_sb) ? 
+				EMPTY_DIR_SIZE_V1 : EMPTY_DIR_SIZE,
+				dentry, inode);
+    if (retval) {
 	dir->i_nlink-- ;
-	journal_end(&th, dir->i_sb, jbegin_count) ;
-	unlock_kernel();
-	return retval;
+	goto out_failed;
     }
     reiserfs_update_inode_transaction(inode) ;
     reiserfs_update_inode_transaction(dir) ;
@@ -723,21 +751,19 @@ static int reiserfs_mkdir (struct inode * dir, struct dentry *dentry, int mode)
 	inode->i_nlink = 0;
 	DEC_DIR_INODE_NLINK(dir);
 	reiserfs_update_sd (&th, inode);
-	pop_journal_writer(windex) ;
 	journal_end(&th, dir->i_sb, jbegin_count) ;
 	iput (inode);
-	unlock_kernel();
-	return retval;
+	goto out_failed;
     }
 
     // the above add_entry did not update dir's stat data
     reiserfs_update_sd (&th, dir);
 
     d_instantiate(dentry, inode);
-    pop_journal_writer(windex) ;
     journal_end(&th, dir->i_sb, jbegin_count) ;
+out_failed:
     unlock_kernel();
-    return 0;
+    return retval;
 }
 
 static inline int reiserfs_empty_dir(struct inode *inode) {
@@ -942,43 +968,43 @@ static int reiserfs_symlink (struct inode * dir, struct dentry * dentry, const c
     struct inode * inode;
     char * name;
     int item_len;
-    int windex ;
     struct reiserfs_transaction_handle th ;
+    int mode = S_IFLNK | S_IRWXUGO;
     int jbegin_count = JOURNAL_PER_BALANCE_CNT * 3; 
 
-
     inode = new_inode(dir->i_sb) ;
     if (!inode) {
 	return -ENOMEM ;
     }
+    retval = new_inode_init(inode, dir, mode);
+    if (retval) {
+        return retval;
+    }
 
+    lock_kernel();
     item_len = ROUND_UP (strlen (symname));
     if (item_len > MAX_DIRECT_ITEM_LEN (dir->i_sb->s_blocksize)) {
-	iput(inode) ;
-	return -ENAMETOOLONG;
+	retval =  -ENAMETOOLONG;
+	drop_new_inode(inode);
+	goto out_failed;
     }
   
-    lock_kernel();
     name = reiserfs_kmalloc (item_len, GFP_NOFS, dir->i_sb);
     if (!name) {
-	iput(inode) ;
-	unlock_kernel();
-	return -ENOMEM;
+	drop_new_inode(inode);
+	retval =  -ENOMEM;
+	goto out_failed;
     }
     memcpy (name, symname, strlen (symname));
     padd_item (name, item_len, strlen (symname));
 
     journal_begin(&th, dir->i_sb, jbegin_count) ;
-    windex = push_journal_writer("reiserfs_symlink") ;
 
-    inode = reiserfs_new_inode (&th, dir, S_IFLNK | S_IRWXUGO, name, strlen (symname), dentry,
-				inode, &retval);
+    retval = reiserfs_new_inode (&th, dir, mode, name, strlen (symname), 
+                                 dentry, inode);
     reiserfs_kfree (name, item_len, dir->i_sb);
-    if (inode == 0) { /* reiserfs_new_inode iputs for us */
-	pop_journal_writer(windex) ;
-	journal_end(&th, dir->i_sb, jbegin_count) ;
-	unlock_kernel();
-	return retval;
+    if (retval) { /* reiserfs_new_inode iputs for us */
+	goto out_failed;
     }
 
     reiserfs_update_inode_transaction(inode) ;
@@ -996,18 +1022,16 @@ static int reiserfs_symlink (struct inode * dir, struct dentry * dentry, const c
     if (retval) {
 	inode->i_nlink--;
 	reiserfs_update_sd (&th, inode);
-	pop_journal_writer(windex) ;
 	journal_end(&th, dir->i_sb, jbegin_count) ;
 	iput (inode);
-	unlock_kernel();
-	return retval;
+	goto out_failed;
     }
 
     d_instantiate(dentry, inode);
-    pop_journal_writer(windex) ;
     journal_end(&th, dir->i_sb, jbegin_count) ;
+out_failed:
     unlock_kernel();
-    return 0;
+    return retval;
 }
 
 

include/asm-i386/xor.h

@@ -839,6 +839,8 @@ static struct xor_block_template xor_block_pIII_sse = {
 /* Also try the generic routines.  */
 #include <asm-generic/xor.h>
 
+#define cpu_has_mmx	(test_bit(X86_FEATURE_MMX,  boot_cpu_data.x86_capability))
+
 #undef XOR_TRY_TEMPLATES
 #define XOR_TRY_TEMPLATES				\
 	do {						\
@@ -846,7 +848,7 @@ static struct xor_block_template xor_block_pIII_sse = {
 		xor_speed(&xor_block_32regs);		\
 	        if (cpu_has_xmm)			\
 			xor_speed(&xor_block_pIII_sse);	\
-	        if (md_cpu_has_mmx()) {			\
+	        if (cpu_has_mmx) {			\
 	                xor_speed(&xor_block_pII_mmx);	\
 	                xor_speed(&xor_block_p5_mmx);	\
 	        }					\

include/linux/fs.h

@@ -759,6 +759,9 @@ struct inode_operations {
 
 struct seq_file;
 
+extern ssize_t vfs_read(struct file *, char *, size_t, loff_t *);
+extern ssize_t vfs_write(struct file *, const char *, size_t, loff_t *);
+
 /*
  * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called
  * without the big kernel lock held in all filesystems.

include/linux/raid/md_k.h

@@ -169,8 +169,9 @@ struct mdk_rdev_s
 
 	struct block_device *bdev;	/* block device handle */
 
-	mdp_super_t *sb;
-	unsigned long sb_offset;
+	struct page	*sb_page;
+	mdp_super_t	*sb;
+	unsigned long	sb_offset;
 
 	int alias_device;		/* device alias to the same disk */
 	int faulty;			/* if faulty do not issue IO requests */

include/linux/raid/raid5.h

@@ -7,21 +7,21 @@
 /*
  *
  * Each stripe contains one buffer per disc.  Each buffer can be in
- * one of a number of states determined by bh_state.  Changes between
+ * one of a number of states stored in "flags".  Changes between
  * these states happen *almost* exclusively under a per-stripe
- * spinlock.  Some very specific changes can happen in b_end_io, and
+ * spinlock.  Some very specific changes can happen in bi_end_io, and
  * these are not protected by the spin lock.
  *
- * The bh_state bits that are used to represent these states are:
- *   BH_Uptodate, BH_Lock
+ * The flag bits that are used to represent these states are:
+ *   R5_UPTODATE and R5_LOCKED
  *
- * State Empty == !Uptodate, !Lock
+ * State Empty == !UPTODATE, !LOCK
  *        We have no data, and there is no active request
- * State Want == !Uptodate, Lock
+ * State Want == !UPTODATE, LOCK
  *        A read request is being submitted for this block
- * State Dirty == Uptodate, Lock
+ * State Dirty == UPTODATE, LOCK
  *        Some new data is in this buffer, and it is being written out
- * State Clean == Uptodate, !Lock
+ * State Clean == UPTODATE, !LOCK
  *        We have valid data which is the same as on disc
  *
  * The possible state transitions are:
@@ -124,24 +124,29 @@
  * plus raid5d if it is handling it, plus one for each active request
  * on a cached buffer.
  */
+
 struct stripe_head {
 	struct stripe_head	*hash_next, **hash_pprev; /* hash pointers */
 	struct list_head	lru;			/* inactive_list or handle_list */
 	struct raid5_private_data	*raid_conf;
-	struct buffer_head	*bh_cache[MD_SB_DISKS];	/* buffered copy */
-	struct buffer_head	*bh_read[MD_SB_DISKS];	/* read request buffers of the MD device */
-	struct buffer_head	*bh_write[MD_SB_DISKS];	/* write request buffers of the MD device */
-	struct buffer_head	*bh_written[MD_SB_DISKS]; /* write request buffers of the MD device that have been scheduled for write */
-	struct page		*bh_page[MD_SB_DISKS];	/* saved bh_cache[n]->b_page when reading around the cache */
-	unsigned long		sector;			/* sector of this row */
-	int			size;			/* buffers size */
+	sector_t		sector;			/* sector of this row */
 	int			pd_idx;			/* parity disk index */
 	unsigned long		state;			/* state flags */
 	atomic_t		count;			/* nr of active thread/requests */
 	spinlock_t		lock;
-	int			sync_redone;
+	struct r5dev {
+		struct bio	req;
+		struct bio_vec	vec;
+		struct page	*page;
+		struct bio	*toread, *towrite, *written;
+		sector_t	sector;			/* sector of this page */
+		unsigned long	flags;
+	} dev[1]; /* allocated with extra space depending of RAID geometry */
 };
-
+/* Flags */
+#define	R5_UPTODATE	0	/* page contains current data */
+#define	R5_LOCKED	1	/* IO has been submitted on "req" */
+#define	R5_OVERWRITE	2	/* towrite covers whole page */
 
 /*
  * Write method
@@ -187,6 +192,7 @@ struct stripe_head {
 
 struct disk_info {
 	kdev_t	dev;
+	struct block_device *bdev;
 	int	operational;
 	int	number;
 	int	raid_disk;
@@ -201,7 +207,6 @@ struct raid5_private_data {
 	mdk_thread_t		*thread, *resync_thread;
 	struct disk_info	disks[MD_SB_DISKS];
 	struct disk_info	*spare;
-	int			buffer_size;
 	int			chunk_size, level, algorithm;
 	int			raid_disks, working_disks, failed_disks;
 	int			resync_parity;
@@ -210,16 +215,19 @@ struct raid5_private_data {
 	struct list_head	handle_list; /* stripes needing handling */
 	struct list_head	delayed_list; /* stripes that have plugged requests */
 	atomic_t		preread_active_stripes; /* stripes with scheduled io */
+
+	char			cache_name[20];
+	kmem_cache_t		*slab_cache; /* for allocating stripes */
 	/*
 	 * Free stripes pool
 	 */
 	atomic_t		active_stripes;
 	struct list_head	inactive_list;
-	md_wait_queue_head_t	wait_for_stripe;
+	wait_queue_head_t	wait_for_stripe;
 	int			inactive_blocked;	/* release of inactive stripes blocked,
 							 * waiting for 25% to be free
 							 */        
-	md_spinlock_t		device_lock;
+	spinlock_t		device_lock;
 
 	int			plugged;
 	struct tq_struct	plug_tq;

include/linux/raid/xor.h

@@ -5,7 +5,7 @@
 
 #define MAX_XOR_BLOCKS 5
 
-extern void xor_block(unsigned int count, struct buffer_head **bh_ptr);
+extern void xor_block(unsigned int count, unsigned int bytes, void **ptr);
 
 struct xor_block_template {
         struct xor_block_template *next;

include/linux/reiserfs_fs.h

@@ -1841,10 +1841,10 @@ struct inode * reiserfs_iget (struct super_block * s,
 			      const struct cpu_key * key);
 
 
-struct inode * reiserfs_new_inode (struct reiserfs_transaction_handle *th, 
+int reiserfs_new_inode (struct reiserfs_transaction_handle *th, 
 				   struct inode * dir, int mode, 
-				   const char * symname, int item_len,
-				   struct dentry *dentry, struct inode *inode, int * err);
+				   const char * symname, loff_t i_size,
+				   struct dentry *dentry, struct inode *inode);
 int reiserfs_sync_inode (struct reiserfs_transaction_handle *th, struct inode * inode);
 void reiserfs_update_sd (struct reiserfs_transaction_handle *th, struct inode * inode);
 

kernel/exit.c

@@ -231,7 +231,7 @@ void daemonize(void)
 
 /*
  * When we die, we re-parent all our children.
- * Try to give them to another thread in our process
+ * Try to give them to another thread in our thread
  * group, and if no such member exists, give it to
  * the global child reaper process (ie "init")
  */
@@ -241,8 +241,14 @@ static inline void forget_original_parent(struct task_struct * father)
 
 	read_lock(&tasklist_lock);
 
-	/* Next in our thread group */
-	reaper = next_thread(father);
+	/* Next in our thread group, if they're not already exiting */
+	reaper = father;
+	do {
+		reaper = next_thread(reaper);
+		if (!(reaper->flags & PF_EXITING))
+			break;
+	} while (reaper != father);
+
 	if (reaper == father)
 		reaper = child_reaper;
 

kernel/ksyms.c

@@ -243,6 +243,8 @@ EXPORT_SYMBOL(shrink_dcache_anon);
 EXPORT_SYMBOL(find_inode_number);
 EXPORT_SYMBOL(is_subdir);
 EXPORT_SYMBOL(get_unused_fd);
+EXPORT_SYMBOL(vfs_read);
+EXPORT_SYMBOL(vfs_write);
 EXPORT_SYMBOL(vfs_create);
 EXPORT_SYMBOL(vfs_mkdir);
 EXPORT_SYMBOL(vfs_mknod);

net/sunrpc/svcsock.c

@@ -949,12 +949,10 @@ svc_sock_update_bufs(struct svc_serv *serv)
 		if (sock->type == SOCK_DGRAM) {
 			/* udp sockets need large rcvbuf as all pending
 			 * requests are still in that buffer.
-			 * As outgoing requests do not wait for an
-			 * ACK, only a moderate sndbuf is needed
 			 */
 			svc_sock_setbufsize(sock,
-					    5 * serv->sv_bufsz,
-					    (serv->sv_nrthreads+2)* serv->sv_bufsz);
+					    (serv->sv_nrthreads+3) * serv->sv_bufsz,
+					    (serv->sv_nrthreads+3) * serv->sv_bufsz);
 		} else if (svsk->sk_sk->state != TCP_LISTEN) {
 			printk(KERN_ERR "RPC update_bufs: permanent sock neither UDP or TCP_LISTEN\n");
 		}