path: root/drivers/block/drbd/drbd_bitmap.c

/*
   drbd_bitmap.c

   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.

   Copyright (C) 2004-2008, LINBIT Information Technologies GmbH.
   Copyright (C) 2004-2008, Philipp Reisner <philipp.reisner@linbit.com>.
   Copyright (C) 2004-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.

   drbd is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2, or (at your option)
   any later version.

   drbd is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with drbd; see the file COPYING.  If not, write to
   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
 */

#include <linux/bitops.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/drbd.h>
#include <linux/slab.h>
#include <asm/kmap_types.h>

#include "drbd_int.h"


/* OPAQUE outside this file!
 * interface defined in drbd_int.h

 * convention:
 * function name drbd_bm_... => used elsewhere, "public".
 * function name      bm_... => internal to implementation, "private".
 */


/*
 * LIMITATIONS:
 * We want to support >= peta byte of backend storage, while for now still using
 * a granularity of one bit per 4KiB of storage.
 * 1 << 50		bytes backend storage (1 PiB)
 * 1 << (50 - 12)	bits needed
 *	38 --> we need u64 to index and count bits
 * 1 << (38 - 3)	bitmap bytes needed
 *	35 --> we still need u64 to index and count bytes
 *			(that's 32 GiB of bitmap for 1 PiB storage)
 * 1 << (35 - 2)	32bit longs needed
 *	33 --> we'd even need u64 to index and count 32bit long words.
 * 1 << (35 - 3)	64bit longs needed
 *	32 --> we could get away with a 32bit unsigned int to index and count
 *	64bit long words, but I rather stay with unsigned long for now.
 *	We probably should neither count nor point to bytes or long words
 *	directly, but either by bitnumber, or by page index and offset.
 * 1 << (35 - 12)
 *	22 --> we need that much 4KiB pages of bitmap.
 *	1 << (22 + 3) --> on a 64bit arch,
 *	we need 32 MiB to store the array of page pointers.
 *
 * Because I'm lazy, and because the resulting patch was too large, too ugly
 * and still incomplete, on 32bit we still "only" support 16 TiB (minus some),
 * (1 << 32) bits * 4k storage.
 *

 * bitmap storage and IO:
 *	Bitmap is stored little endian on disk, and is kept little endian in
 *	core memory. Currently we still hold the full bitmap in core as long
 *	as we are "attached" to a local disk, which at 32 GiB for 1PiB storage
 *	seems excessive.
 *
 *	We plan to reduce the amount of in-core bitmap pages by paging them in
 *	and out against their on-disk location as necessary, but need to make
 *	sure we don't cause too much meta data IO, and must not deadlock in
 *	tight memory situations. This needs some more work.
 */

/*
 * NOTE
 *  Access to the *bm_pages is protected by bm_lock.
 *  It is safe to read the other members within the lock.
 *
 *  drbd_bm_set_bits is called from bio_endio callbacks,
 *  We may be called with irq already disabled,
 *  so we need spin_lock_irqsave().
 *  And we need the kmap_atomic.
 */
struct drbd_bitmap {
	struct page **bm_pages;
	spinlock_t bm_lock;

	/* see LIMITATIONS: above */

	unsigned long bm_set;       /* nr of set bits; THINK maybe atomic_t? */
	unsigned long bm_bits;
	size_t   bm_words;
	size_t   bm_number_of_pages;
	sector_t bm_dev_capacity;
	struct mutex bm_change; /* serializes resize operations */

	wait_queue_head_t bm_io_wait; /* used to serialize IO of single pages */

	enum bm_flag bm_flags;

	/* debugging aid, in case we are still racy somewhere */
	char          *bm_why;
	struct task_struct *bm_task;
};

#define bm_print_lock_info(m) __bm_print_lock_info(m, __func__)
static void __bm_print_lock_info(struct drbd_conf *mdev, const char *func)
{
	struct drbd_bitmap *b = mdev->bitmap;
	if (!__ratelimit(&drbd_ratelimit_state))
		return;
	dev_err(DEV, "FIXME %s in %s, bitmap locked for '%s' by %s\n",
	    current == mdev->receiver.task ? "receiver" :
	    current == mdev->asender.task  ? "asender"  :
	    current == mdev->worker.task   ? "worker"   : current->comm,
	    func, b->bm_why ?: "?",
	    b->bm_task == mdev->receiver.task ? "receiver" :
	    b->bm_task == mdev->asender.task  ? "asender"  :
	    b->bm_task == mdev->worker.task   ? "worker"   : "?");
}

void drbd_bm_lock(struct drbd_conf *mdev, char *why, enum bm_flag flags)
{
	struct drbd_bitmap *b = mdev->bitmap;
	int trylock_failed;

	if (!b) {
		dev_err(DEV, "FIXME no bitmap in drbd_bm_lock!?\n");
		return;
	}

	trylock_failed = !mutex_trylock(&b->bm_change);

	if (trylock_failed) {
		dev_warn(DEV, "%s going to '%s' but bitmap already locked for '%s' by %s\n",
		    current == mdev->receiver.task ? "receiver" :
		    current == mdev->asender.task  ? "asender"  :
		    current == mdev->worker.task   ? "work