Revision 475049809977bf3975d78f2d2fd992e19ce2d59e authored by Roel Kluin on 10 March 2009, 19:55:45 UTC, committed by Linus Torvalds on 10 March 2009, 22:55:10 UTC
get_nid_for_pfn() returns int

Presumably the (nid < 0) case has never happened.

We do know that it is happening on one system while creating a symlink for
a memory section so it should also happen on the same system if
unregister_mem_sect_under_nodes() were called to remove the same symlink.

The test was actually added in response to a problem with an earlier
version reported by Yasunori Goto where one or more of the leading pages
of a memory section on the 2nd node of one of his systems was
uninitialized because I believe they coincided with a memory hole.

That earlier version did not ignore uninitialized pages and determined
the nid by considering only the 1st page of each memory section.  This
caused the symlink to the 1st memory section on the 2nd node to be
incorrectly created in /sys/devices/system/node/node0 instead of
/sys/devices/system/node/node1.  The problem was fixed by adding the
test to skip over uninitialized pages.

I suspect we have not seen any reports of the non-removal
of a symlink due to the incorrect declaration of the nid
variable in unregister_mem_sect_under_nodes() because
  - systems where a memory section could have an uninitialized
    range of leading pages are probably rare.
  - memory remove is probably not done very frequently on the
    systems that are capable of demonstrating the problem.
  - lingering symlink(s) that should have been removed may
    have simply gone unnoticed.

[garyhade@us.ibm.com: wrote changelog]
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Cc: Gary Hade <garyhade@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 1abaf33
Raw File
dm-snap.h
/*
 * Copyright (C) 2001-2002 Sistina Software (UK) Limited.
 *
 * This file is released under the GPL.
 */

#ifndef DM_SNAPSHOT_H
#define DM_SNAPSHOT_H

#include <linux/device-mapper.h>
#include "dm-exception-store.h"
#include "dm-bio-list.h"
#include <linux/blkdev.h>
#include <linux/workqueue.h>

struct exception_table {
	uint32_t hash_mask;
	unsigned hash_shift;
	struct list_head *table;
};

#define DM_TRACKED_CHUNK_HASH_SIZE	16
#define DM_TRACKED_CHUNK_HASH(x)	((unsigned long)(x) & \
					 (DM_TRACKED_CHUNK_HASH_SIZE - 1))

struct dm_snapshot {
	struct rw_semaphore lock;
	struct dm_target *ti;

	struct dm_dev *origin;
	struct dm_dev *cow;

	/* List of snapshots per Origin */
	struct list_head list;

	/* Size of data blocks saved - must be a power of 2 */
	chunk_t chunk_size;
	chunk_t chunk_mask;
	chunk_t chunk_shift;

	/* You can't use a snapshot if this is 0 (e.g. if full) */
	int valid;

	/* Origin writes don't trigger exceptions until this is set */
	int active;

	/* Used for display of table */
	char type;

	mempool_t *pending_pool;

	atomic_t pending_exceptions_count;

	struct exception_table pending;
	struct exception_table complete;

	/*
	 * pe_lock protects all pending_exception operations and access
	 * as well as the snapshot_bios list.
	 */
	spinlock_t pe_lock;

	/* The on disk metadata handler */
	struct dm_exception_store store;

	struct dm_kcopyd_client *kcopyd_client;

	/* Queue of snapshot writes for ksnapd to flush */
	struct bio_list queued_bios;
	struct work_struct queued_bios_work;

	/* Chunks with outstanding reads */
	mempool_t *tracked_chunk_pool;
	spinlock_t tracked_chunk_lock;
	struct hlist_head tracked_chunk_hash[DM_TRACKED_CHUNK_HASH_SIZE];
};

/*
 * Return the number of sectors in the device.
 */
static inline sector_t get_dev_size(struct block_device *bdev)
{
	return bdev->bd_inode->i_size >> SECTOR_SHIFT;
}

static inline chunk_t sector_to_chunk(struct dm_snapshot *s, sector_t sector)
{
	return (sector & ~s->chunk_mask) >> s->chunk_shift;
}

static inline sector_t chunk_to_sector(struct dm_snapshot *s, chunk_t chunk)
{
	return chunk << s->chunk_shift;
}

static inline int bdev_equal(struct block_device *lhs, struct block_device *rhs)
{
	/*
	 * There is only ever one instance of a particular block
	 * device so we can compare pointers safely.
	 */
	return lhs == rhs;
}

#endif
back to top