2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2001, 2002 Sistina Software (UK) Limited.
|
2006-06-26 15:27:32 +08:00
|
|
|
* Copyright (C) 2004 - 2006 Red Hat, Inc. All rights reserved.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* This file is released under the GPL.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "dm.h"
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include <linux/miscdevice.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/wait.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/dm-ioctl.h>
|
2006-03-27 17:17:54 +08:00
|
|
|
#include <linux/hdreg.h>
|
2008-02-08 10:09:56 +08:00
|
|
|
#include <linux/compat.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
2006-06-26 15:27:35 +08:00
|
|
|
#define DM_MSG_PREFIX "ioctl"
|
2005-04-17 06:20:36 +08:00
|
|
|
#define DM_DRIVER_EMAIL "dm-devel@redhat.com"
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* The ioctl interface needs to be able to look up devices by
|
|
|
|
* name or uuid.
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
struct hash_cell {
|
|
|
|
struct list_head name_list;
|
|
|
|
struct list_head uuid_list;
|
|
|
|
|
|
|
|
char *name;
|
|
|
|
char *uuid;
|
|
|
|
struct mapped_device *md;
|
|
|
|
struct dm_table *new_map;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct vers_iter {
|
|
|
|
size_t param_size;
|
|
|
|
struct dm_target_versions *vers, *old_vers;
|
|
|
|
char *end;
|
|
|
|
uint32_t flags;
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
#define NUM_BUCKETS 64
|
|
|
|
#define MASK_BUCKETS (NUM_BUCKETS - 1)
|
|
|
|
static struct list_head _name_buckets[NUM_BUCKETS];
|
|
|
|
static struct list_head _uuid_buckets[NUM_BUCKETS];
|
|
|
|
|
2006-06-26 15:27:34 +08:00
|
|
|
static void dm_hash_remove_all(int keep_open_devices);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Guards access to both hash tables.
|
|
|
|
*/
|
|
|
|
static DECLARE_RWSEM(_hash_lock);
|
|
|
|
|
2009-12-11 07:51:52 +08:00
|
|
|
/*
|
|
|
|
* Protects use of mdptr to obtain hash cell name and uuid from mapped device.
|
|
|
|
*/
|
|
|
|
static DEFINE_MUTEX(dm_hash_cells_mutex);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static void init_buckets(struct list_head *buckets)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for (i = 0; i < NUM_BUCKETS; i++)
|
|
|
|
INIT_LIST_HEAD(buckets + i);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int dm_hash_init(void)
|
|
|
|
{
|
|
|
|
init_buckets(_name_buckets);
|
|
|
|
init_buckets(_uuid_buckets);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void dm_hash_exit(void)
|
|
|
|
{
|
2006-06-26 15:27:34 +08:00
|
|
|
dm_hash_remove_all(0);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* Hash function:
|
|
|
|
* We're not really concerned with the str hash function being
|
|
|
|
* fast since it's only used by the ioctl interface.
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
static unsigned int hash_str(const char *str)
|
|
|
|
{
|
|
|
|
const unsigned int hash_mult = 2654435387U;
|
|
|
|
unsigned int h = 0;
|
|
|
|
|
|
|
|
while (*str)
|
|
|
|
h = (h + (unsigned int) *str++) * hash_mult;
|
|
|
|
|
|
|
|
return h & MASK_BUCKETS;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* Code for looking up a device by name
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
static struct hash_cell *__get_name_cell(const char *str)
|
|
|
|
{
|
|
|
|
struct hash_cell *hc;
|
|
|
|
unsigned int h = hash_str(str);
|
|
|
|
|
|
|
|
list_for_each_entry (hc, _name_buckets + h, name_list)
|
2006-06-26 15:27:24 +08:00
|
|
|
if (!strcmp(hc->name, str)) {
|
|
|
|
dm_get(hc->md);
|
2005-04-17 06:20:36 +08:00
|
|
|
return hc;
|
2006-06-26 15:27:24 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct hash_cell *__get_uuid_cell(const char *str)
|
|
|
|
{
|
|
|
|
struct hash_cell *hc;
|
|
|
|
unsigned int h = hash_str(str);
|
|
|
|
|
|
|
|
list_for_each_entry (hc, _uuid_buckets + h, uuid_list)
|
2006-06-26 15:27:24 +08:00
|
|
|
if (!strcmp(hc->uuid, str)) {
|
|
|
|
dm_get(hc->md);
|
2005-04-17 06:20:36 +08:00
|
|
|
return hc;
|
2006-06-26 15:27:24 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* Inserting, removing and renaming a device.
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
static struct hash_cell *alloc_cell(const char *name, const char *uuid,
|
|
|
|
struct mapped_device *md)
|
|
|
|
{
|
|
|
|
struct hash_cell *hc;
|
|
|
|
|
|
|
|
hc = kmalloc(sizeof(*hc), GFP_KERNEL);
|
|
|
|
if (!hc)
|
|
|
|
return NULL;
|
|
|
|
|
2005-06-23 15:09:02 +08:00
|
|
|
hc->name = kstrdup(name, GFP_KERNEL);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!hc->name) {
|
|
|
|
kfree(hc);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!uuid)
|
|
|
|
hc->uuid = NULL;
|
|
|
|
|
|
|
|
else {
|
2005-06-23 15:09:02 +08:00
|
|
|
hc->uuid = kstrdup(uuid, GFP_KERNEL);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!hc->uuid) {
|
|
|
|
kfree(hc->name);
|
|
|
|
kfree(hc);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
INIT_LIST_HEAD(&hc->name_list);
|
|
|
|
INIT_LIST_HEAD(&hc->uuid_list);
|
|
|
|
hc->md = md;
|
|
|
|
hc->new_map = NULL;
|
|
|
|
return hc;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_cell(struct hash_cell *hc)
|
|
|
|
{
|
|
|
|
if (hc) {
|
|
|
|
kfree(hc->name);
|
|
|
|
kfree(hc->uuid);
|
|
|
|
kfree(hc);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The kdev_t and uuid of a device can never change once it is
|
|
|
|
* initially inserted.
|
|
|
|
*/
|
|
|
|
static int dm_hash_insert(const char *name, const char *uuid, struct mapped_device *md)
|
|
|
|
{
|
2006-06-26 15:27:24 +08:00
|
|
|
struct hash_cell *cell, *hc;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Allocate the new cells.
|
|
|
|
*/
|
|
|
|
cell = alloc_cell(name, uuid, md);
|
|
|
|
if (!cell)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Insert the cell into both hash tables.
|
|
|
|
*/
|
|
|
|
down_write(&_hash_lock);
|
2006-06-26 15:27:24 +08:00
|
|
|
hc = __get_name_cell(name);
|
|
|
|
if (hc) {
|
|
|
|
dm_put(hc->md);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto bad;
|
2006-06-26 15:27:24 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
list_add(&cell->name_list, _name_buckets + hash_str(name));
|
|
|
|
|
|
|
|
if (uuid) {
|
2006-06-26 15:27:24 +08:00
|
|
|
hc = __get_uuid_cell(uuid);
|
|
|
|
if (hc) {
|
2005-04-17 06:20:36 +08:00
|
|
|
list_del(&cell->name_list);
|
2006-06-26 15:27:24 +08:00
|
|
|
dm_put(hc->md);
|
2005-04-17 06:20:36 +08:00
|
|
|
goto bad;
|
|
|
|
}
|
|
|
|
list_add(&cell->uuid_list, _uuid_buckets + hash_str(uuid));
|
|
|
|
}
|
|
|
|
dm_get(md);
|
2009-12-11 07:51:52 +08:00
|
|
|
mutex_lock(&dm_hash_cells_mutex);
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_set_mdptr(md, cell);
|
2009-12-11 07:51:52 +08:00
|
|
|
mutex_unlock(&dm_hash_cells_mutex);
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
bad:
|
|
|
|
up_write(&_hash_lock);
|
|
|
|
free_cell(cell);
|
|
|
|
return -EBUSY;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __hash_remove(struct hash_cell *hc)
|
|
|
|
{
|
2005-09-28 12:45:44 +08:00
|
|
|
struct dm_table *table;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* remove from the dev hash */
|
|
|
|
list_del(&hc->uuid_list);
|
|
|
|
list_del(&hc->name_list);
|
2009-12-11 07:51:52 +08:00
|
|
|
mutex_lock(&dm_hash_cells_mutex);
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_set_mdptr(hc->md, NULL);
|
2009-12-11 07:51:52 +08:00
|
|
|
mutex_unlock(&dm_hash_cells_mutex);
|
2005-09-28 12:45:44 +08:00
|
|
|
|
2009-12-11 07:52:19 +08:00
|
|
|
table = dm_get_live_table(hc->md);
|
2005-09-28 12:45:44 +08:00
|
|
|
if (table) {
|
|
|
|
dm_table_event(table);
|
|
|
|
dm_table_put(table);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (hc->new_map)
|
dm table: rework reference counting
Rework table reference counting.
The existing code uses a reference counter. When the last reference is
dropped and the counter reaches zero, the table destructor is called.
Table reference counters are acquired/released from upcalls from other
kernel code (dm_any_congested, dm_merge_bvec, dm_unplug_all).
If the reference counter reaches zero in one of the upcalls, the table
destructor is called from almost random kernel code.
This leads to various problems:
* dm_any_congested being called under a spinlock, which calls the
destructor, which calls some sleeping function.
* the destructor attempting to take a lock that is already taken by the
same process.
* stale reference from some other kernel code keeps the table
constructed, which keeps some devices open, even after successful
return from "dmsetup remove". This can confuse lvm and prevent closing
of underlying devices or reusing device minor numbers.
The patch changes reference counting so that the table destructor can be
called only at predetermined places.
The table has always exactly one reference from either mapped_device->map
or hash_cell->new_map. After this patch, this reference is not counted
in table->holders. A pair of dm_create_table/dm_destroy_table functions
is used for table creation/destruction.
Temporary references from the other code increase table->holders. A pair
of dm_table_get/dm_table_put functions is used to manipulate it.
When the table is about to be destroyed, we wait for table->holders to
reach 0. Then, we call the table destructor. We use active waiting with
msleep(1), because the situation happens rarely (to one user in 5 years)
and removing the device isn't performance-critical task: the user doesn't
care if it takes one tick more or not.
This way, the destructor is called only at specific points
(dm_table_destroy function) and the above problems associated with lazy
destruction can't happen.
Finally remove the temporary protection added to dm_any_congested().
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2009-01-06 11:05:10 +08:00
|
|
|
dm_table_destroy(hc->new_map);
|
2006-03-27 17:17:54 +08:00
|
|
|
dm_put(hc->md);
|
2005-04-17 06:20:36 +08:00
|
|
|
free_cell(hc);
|
|
|
|
}
|
|
|
|
|
2006-06-26 15:27:34 +08:00
|
|
|
static void dm_hash_remove_all(int keep_open_devices)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2010-08-12 11:13:55 +08:00
|
|
|
int i, dev_skipped;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct hash_cell *hc;
|
2010-08-12 11:13:55 +08:00
|
|
|
struct mapped_device *md;
|
|
|
|
|
|
|
|
retry:
|
|
|
|
dev_skipped = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
down_write(&_hash_lock);
|
2006-06-26 15:27:34 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
for (i = 0; i < NUM_BUCKETS; i++) {
|
2010-08-12 11:13:55 +08:00
|
|
|
list_for_each_entry(hc, _name_buckets + i, name_list) {
|
|
|
|
md = hc->md;
|
|
|
|
dm_get(md);
|
2006-06-26 15:27:34 +08:00
|
|
|
|
2010-08-12 11:13:55 +08:00
|
|
|
if (keep_open_devices && dm_lock_for_deletion(md)) {
|
|
|
|
dm_put(md);
|
2006-06-26 15:27:34 +08:00
|
|
|
dev_skipped++;
|
|
|
|
continue;
|
|
|
|
}
|
2010-08-12 11:13:55 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
__hash_remove(hc);
|
2006-06-26 15:27:34 +08:00
|
|
|
|
2010-08-12 11:13:55 +08:00
|
|
|
up_write(&_hash_lock);
|
2006-06-26 15:27:34 +08:00
|
|
|
|
2010-08-12 11:13:55 +08:00
|
|
|
dm_put(md);
|
dm: separate device deletion from dm_put
This patch separates the device deletion code from dm_put()
to make sure the deletion happens in the process context.
By this patch, device deletion always occurs in an ioctl (process)
context and dm_put() can be called in interrupt context.
As a result, the request-based dm's bad dm_put() usage pointed out
by Mikulas below disappears.
http://marc.info/?l=dm-devel&m=126699981019735&w=2
Without this patch, I confirmed there is a case to crash the system:
dm_put() => dm_table_destroy() => vfree() => BUG_ON(in_interrupt())
Some more backgrounds and details:
In request-based dm, a device opener can remove a mapped_device
while the last request is still completing, because bios in the last
request complete first and then the device opener can close and remove
the mapped_device before the last request completes:
CPU0 CPU1
=================================================================
<<INTERRUPT>>
blk_end_request_all(clone_rq)
blk_update_request(clone_rq)
bio_endio(clone_bio) == end_clone_bio
blk_update_request(orig_rq)
bio_endio(orig_bio)
<<I/O completed>>
dm_blk_close()
dev_remove()
dm_put(md)
<<Free md>>
blk_finish_request(clone_rq)
....
dm_end_request(clone_rq)
free_rq_clone(clone_rq)
blk_end_request_all(orig_rq)
rq_completed(md)
So request-based dm used dm_get()/dm_put() to hold md for each I/O
until its request completion handling is fully done.
However, the final dm_put() can call the device deletion code which
must not be run in interrupt context and may cause kernel panic.
To solve the problem, this patch moves the device deletion code,
dm_destroy(), to predetermined places that is actually deleting
the mapped_device in ioctl (process) context, and changes dm_put()
just to decrement the reference count of the mapped_device.
By this change, dm_put() can be used in any context and the symmetric
model below is introduced:
dm_create(): create a mapped_device
dm_destroy(): destroy a mapped_device
dm_get(): increment the reference count of a mapped_device
dm_put(): decrement the reference count of a mapped_device
dm_destroy() waits for all references of the mapped_device to disappear,
then deletes the mapped_device.
dm_destroy() uses active waiting with msleep(1), since deleting
the mapped_device isn't performance-critical task.
And since at this point, nobody opens the mapped_device and no new
reference will be taken, the pending counts are just for racing
completing activity and will eventually decrease to zero.
For the unlikely case of the forced module unload, dm_destroy_immediate(),
which doesn't wait and forcibly deletes the mapped_device, is also
introduced and used in dm_hash_remove_all(). Otherwise, "rmmod -f"
may be stuck and never return.
And now, because the mapped_device is deleted at this point, subsequent
accesses to the mapped_device may cause NULL pointer references.
Cc: stable@kernel.org
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2010-08-12 11:13:56 +08:00
|
|
|
if (likely(keep_open_devices))
|
|
|
|
dm_destroy(md);
|
|
|
|
else
|
|
|
|
dm_destroy_immediate(md);
|
2010-08-12 11:13:55 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Some mapped devices may be using other mapped
|
|
|
|
* devices, so repeat until we make no further
|
|
|
|
* progress. If a new mapped device is created
|
|
|
|
* here it will also get removed.
|
|
|
|
*/
|
|
|
|
goto retry;
|
|
|
|
}
|
2006-06-26 15:27:34 +08:00
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
2010-08-12 11:13:55 +08:00
|
|
|
|
|
|
|
if (dev_skipped)
|
|
|
|
DMWARN("remove_all left %d open device(s)", dev_skipped);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2011-01-14 03:59:47 +08:00
|
|
|
/*
|
|
|
|
* Set the uuid of a hash_cell that isn't already set.
|
|
|
|
*/
|
|
|
|
static void __set_cell_uuid(struct hash_cell *hc, char *new_uuid)
|
|
|
|
{
|
|
|
|
mutex_lock(&dm_hash_cells_mutex);
|
|
|
|
hc->uuid = new_uuid;
|
|
|
|
mutex_unlock(&dm_hash_cells_mutex);
|
|
|
|
|
|
|
|
list_add(&hc->uuid_list, _uuid_buckets + hash_str(new_uuid));
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Changes the name of a hash_cell and returns the old name for
|
|
|
|
* the caller to free.
|
|
|
|
*/
|
|
|
|
static char *__change_cell_name(struct hash_cell *hc, char *new_name)
|
|
|
|
{
|
|
|
|
char *old_name;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Rename and move the name cell.
|
|
|
|
*/
|
|
|
|
list_del(&hc->name_list);
|
|
|
|
old_name = hc->name;
|
|
|
|
|
|
|
|
mutex_lock(&dm_hash_cells_mutex);
|
|
|
|
hc->name = new_name;
|
|
|
|
mutex_unlock(&dm_hash_cells_mutex);
|
|
|
|
|
|
|
|
list_add(&hc->name_list, _name_buckets + hash_str(new_name));
|
|
|
|
|
|
|
|
return old_name;
|
|
|
|
}
|
|
|
|
|
2010-08-12 11:13:53 +08:00
|
|
|
static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
|
|
|
|
const char *new)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2011-01-14 03:59:47 +08:00
|
|
|
char *new_data, *old_name = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct hash_cell *hc;
|
2006-01-06 16:20:01 +08:00
|
|
|
struct dm_table *table;
|
2010-08-12 11:13:53 +08:00
|
|
|
struct mapped_device *md;
|
2011-01-14 03:59:47 +08:00
|
|
|
unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* duplicate new.
|
|
|
|
*/
|
2011-01-14 03:59:47 +08:00
|
|
|
new_data = kstrdup(new, GFP_KERNEL);
|
|
|
|
if (!new_data)
|
2010-08-12 11:13:53 +08:00
|
|
|
return ERR_PTR(-ENOMEM);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
down_write(&_hash_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is new free ?
|
|
|
|
*/
|
2011-01-14 03:59:47 +08:00
|
|
|
if (change_uuid)
|
|
|
|
hc = __get_uuid_cell(new);
|
|
|
|
else
|
|
|
|
hc = __get_name_cell(new);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (hc) {
|
2011-01-14 03:59:47 +08:00
|
|
|
DMWARN("Unable to change %s on mapped device %s to one that "
|
|
|
|
"already exists: %s",
|
|
|
|
change_uuid ? "uuid" : "name",
|
2010-08-12 11:13:53 +08:00
|
|
|
param->name, new);
|
2006-06-26 15:27:24 +08:00
|
|
|
dm_put(hc->md);
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
2011-01-14 03:59:47 +08:00
|
|
|
kfree(new_data);
|
2010-08-12 11:13:53 +08:00
|
|
|
return ERR_PTR(-EBUSY);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Is there such a device as 'old' ?
|
|
|
|
*/
|
2010-08-12 11:13:53 +08:00
|
|
|
hc = __get_name_cell(param->name);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!hc) {
|
2011-01-14 03:59:47 +08:00
|
|
|
DMWARN("Unable to rename non-existent device, %s to %s%s",
|
|
|
|
param->name, change_uuid ? "uuid " : "", new);
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
2011-01-14 03:59:47 +08:00
|
|
|
kfree(new_data);
|
2010-08-12 11:13:53 +08:00
|
|
|
return ERR_PTR(-ENXIO);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2011-01-14 03:59:47 +08:00
|
|
|
* Does this device already have a uuid?
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2011-01-14 03:59:47 +08:00
|
|
|
if (change_uuid && hc->uuid) {
|
|
|
|
DMWARN("Unable to change uuid of mapped device %s to %s "
|
|
|
|
"because uuid is already set to %s",
|
|
|
|
param->name, new, hc->uuid);
|
|
|
|
dm_put(hc->md);
|
|
|
|
up_write(&_hash_lock);
|
|
|
|
kfree(new_data);
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (change_uuid)
|
|
|
|
__set_cell_uuid(hc, new_data);
|
|
|
|
else
|
|
|
|
old_name = __change_cell_name(hc, new_data);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-01-06 16:20:01 +08:00
|
|
|
/*
|
|
|
|
* Wake up any dm event waiters.
|
|
|
|
*/
|
2009-12-11 07:52:19 +08:00
|
|
|
table = dm_get_live_table(hc->md);
|
2006-01-06 16:20:01 +08:00
|
|
|
if (table) {
|
|
|
|
dm_table_event(table);
|
|
|
|
dm_table_put(table);
|
|
|
|
}
|
|
|
|
|
2010-08-12 11:13:53 +08:00
|
|
|
if (!dm_kobject_uevent(hc->md, KOBJ_CHANGE, param->event_nr))
|
|
|
|
param->flags |= DM_UEVENT_GENERATED_FLAG;
|
2007-12-13 22:15:57 +08:00
|
|
|
|
2010-08-12 11:13:53 +08:00
|
|
|
md = hc->md;
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
kfree(old_name);
|
2010-08-12 11:13:53 +08:00
|
|
|
|
|
|
|
return md;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* Implementation of the ioctl commands
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
/*
|
|
|
|
* All the ioctl commands get dispatched to functions with this
|
|
|
|
* prototype.
|
|
|
|
*/
|
|
|
|
typedef int (*ioctl_fn)(struct dm_ioctl *param, size_t param_size);
|
|
|
|
|
|
|
|
static int remove_all(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
2006-06-26 15:27:34 +08:00
|
|
|
dm_hash_remove_all(1);
|
2005-04-17 06:20:36 +08:00
|
|
|
param->data_size = 0;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Round up the ptr to an 8-byte boundary.
|
|
|
|
*/
|
|
|
|
#define ALIGN_MASK 7
|
|
|
|
static inline void *align_ptr(void *ptr)
|
|
|
|
{
|
|
|
|
return (void *) (((size_t) (ptr + ALIGN_MASK)) & ~ALIGN_MASK);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Retrieves the data payload buffer from an already allocated
|
|
|
|
* struct dm_ioctl.
|
|
|
|
*/
|
|
|
|
static void *get_result_buffer(struct dm_ioctl *param, size_t param_size,
|
|
|
|
size_t *len)
|
|
|
|
{
|
|
|
|
param->data_start = align_ptr(param + 1) - (void *) param;
|
|
|
|
|
|
|
|
if (param->data_start < param_size)
|
|
|
|
*len = param_size - param->data_start;
|
|
|
|
else
|
|
|
|
*len = 0;
|
|
|
|
|
|
|
|
return ((void *) param) + param->data_start;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int list_devices(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
struct hash_cell *hc;
|
|
|
|
size_t len, needed = 0;
|
|
|
|
struct gendisk *disk;
|
|
|
|
struct dm_name_list *nl, *old_nl = NULL;
|
|
|
|
|
|
|
|
down_write(&_hash_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Loop through all the devices working out how much
|
|
|
|
* space we need.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < NUM_BUCKETS; i++) {
|
|
|
|
list_for_each_entry (hc, _name_buckets + i, name_list) {
|
|
|
|
needed += sizeof(struct dm_name_list);
|
|
|
|
needed += strlen(hc->name) + 1;
|
|
|
|
needed += ALIGN_MASK;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Grab our output buffer.
|
|
|
|
*/
|
|
|
|
nl = get_result_buffer(param, param_size, &len);
|
|
|
|
if (len < needed) {
|
|
|
|
param->flags |= DM_BUFFER_FULL_FLAG;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
param->data_size = param->data_start + needed;
|
|
|
|
|
|
|
|
nl->dev = 0; /* Flags no data */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now loop through filling out the names.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < NUM_BUCKETS; i++) {
|
|
|
|
list_for_each_entry (hc, _name_buckets + i, name_list) {
|
|
|
|
if (old_nl)
|
|
|
|
old_nl->next = (uint32_t) ((void *) nl -
|
|
|
|
(void *) old_nl);
|
|
|
|
disk = dm_disk(hc->md);
|
2008-09-03 15:01:48 +08:00
|
|
|
nl->dev = huge_encode_dev(disk_devt(disk));
|
2005-04-17 06:20:36 +08:00
|
|
|
nl->next = 0;
|
|
|
|
strcpy(nl->name, hc->name);
|
|
|
|
|
|
|
|
old_nl = nl;
|
|
|
|
nl = align_ptr(((void *) ++nl) + strlen(hc->name) + 1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
|
|
|
up_write(&_hash_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void list_version_get_needed(struct target_type *tt, void *needed_param)
|
|
|
|
{
|
|
|
|
size_t *needed = needed_param;
|
|
|
|
|
2005-11-22 13:32:33 +08:00
|
|
|
*needed += sizeof(struct dm_target_versions);
|
2005-04-17 06:20:36 +08:00
|
|
|
*needed += strlen(tt->name);
|
|
|
|
*needed += ALIGN_MASK;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void list_version_get_info(struct target_type *tt, void *param)
|
|
|
|
{
|
|
|
|
struct vers_iter *info = param;
|
|
|
|
|
|
|
|
/* Check space - it might have changed since the first iteration */
|
|
|
|
if ((char *)info->vers + sizeof(tt->version) + strlen(tt->name) + 1 >
|
|
|
|
info->end) {
|
|
|
|
|
|
|
|
info->flags = DM_BUFFER_FULL_FLAG;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (info->old_vers)
|
|
|
|
info->old_vers->next = (uint32_t) ((void *)info->vers -
|
|
|
|
(void *)info->old_vers);
|
|
|
|
info->vers->version[0] = tt->version[0];
|
|
|
|
info->vers->version[1] = tt->version[1];
|
|
|
|
info->vers->version[2] = tt->version[2];
|
|
|
|
info->vers->next = 0;
|
|
|
|
strcpy(info->vers->name, tt->name);
|
|
|
|
|
|
|
|
info->old_vers = info->vers;
|
|
|
|
info->vers = align_ptr(((void *) ++info->vers) + strlen(tt->name) + 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int list_versions(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
size_t len, needed = 0;
|
|
|
|
struct dm_target_versions *vers;
|
|
|
|
struct vers_iter iter_info;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Loop through all the devices working out how much
|
|
|
|
* space we need.
|
|
|
|
*/
|
|
|
|
dm_target_iterate(list_version_get_needed, &needed);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Grab our output buffer.
|
|
|
|
*/
|
|
|
|
vers = get_result_buffer(param, param_size, &len);
|
|
|
|
if (len < needed) {
|
|
|
|
param->flags |= DM_BUFFER_FULL_FLAG;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
param->data_size = param->data_start + needed;
|
|
|
|
|
|
|
|
iter_info.param_size = param_size;
|
|
|
|
iter_info.old_vers = NULL;
|
|
|
|
iter_info.vers = vers;
|
|
|
|
iter_info.flags = 0;
|
|
|
|
iter_info.end = (char *)vers+len;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Now loop through filling out the names & versions.
|
|
|
|
*/
|
|
|
|
dm_target_iterate(list_version_get_info, &iter_info);
|
|
|
|
param->flags |= iter_info.flags;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int check_name(const char *name)
|
|
|
|
{
|
|
|
|
if (strchr(name, '/')) {
|
|
|
|
DMWARN("invalid device name");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-12-11 07:52:22 +08:00
|
|
|
/*
|
|
|
|
* On successful return, the caller must not attempt to acquire
|
|
|
|
* _hash_lock without first calling dm_table_put, because dm_table_destroy
|
|
|
|
* waits for this dm_table_put and could be called under this lock.
|
|
|
|
*/
|
|
|
|
static struct dm_table *dm_get_inactive_table(struct mapped_device *md)
|
|
|
|
{
|
|
|
|
struct hash_cell *hc;
|
|
|
|
struct dm_table *table = NULL;
|
|
|
|
|
|
|
|
down_read(&_hash_lock);
|
|
|
|
hc = dm_get_mdptr(md);
|
|
|
|
if (!hc || hc->md != md) {
|
|
|
|
DMWARN("device has been removed from the dev hash table.");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
table = hc->new_map;
|
|
|
|
if (table)
|
|
|
|
dm_table_get(table);
|
|
|
|
|
|
|
|
out:
|
|
|
|
up_read(&_hash_lock);
|
|
|
|
|
|
|
|
return table;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct dm_table *dm_get_live_or_inactive_table(struct mapped_device *md,
|
|
|
|
struct dm_ioctl *param)
|
|
|
|
{
|
|
|
|
return (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) ?
|
|
|
|
dm_get_inactive_table(md) : dm_get_live_table(md);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Fills in a dm_ioctl structure, ready for sending back to
|
|
|
|
* userland.
|
|
|
|
*/
|
2010-08-12 11:13:52 +08:00
|
|
|
static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct gendisk *disk = dm_disk(md);
|
|
|
|
struct dm_table *table;
|
|
|
|
|
|
|
|
param->flags &= ~(DM_SUSPEND_FLAG | DM_READONLY_FLAG |
|
|
|
|
DM_ACTIVE_PRESENT_FLAG);
|
|
|
|
|
2009-12-11 07:52:26 +08:00
|
|
|
if (dm_suspended_md(md))
|
2005-04-17 06:20:36 +08:00
|
|
|
param->flags |= DM_SUSPEND_FLAG;
|
|
|
|
|
2008-09-03 15:01:48 +08:00
|
|
|
param->dev = huge_encode_dev(disk_devt(disk));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-06-26 15:27:34 +08:00
|
|
|
/*
|
|
|
|
* Yes, this will be out of date by the time it gets back
|
|
|
|
* to userland, but it is still very useful for
|
|
|
|
* debugging.
|
|
|
|
*/
|
|
|
|
param->open_count = dm_open_count(md);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
param->event_nr = dm_get_event_nr(md);
|
2009-12-11 07:52:22 +08:00
|
|
|
param->target_count = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-12-11 07:52:19 +08:00
|
|
|
table = dm_get_live_table(md);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (table) {
|
2009-12-11 07:52:22 +08:00
|
|
|
if (!(param->flags & DM_QUERY_INACTIVE_TABLE_FLAG)) {
|
|
|
|
if (get_disk_ro(disk))
|
|
|
|
param->flags |= DM_READONLY_FLAG;
|
|
|
|
param->target_count = dm_table_get_num_targets(table);
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_table_put(table);
|
2009-12-11 07:52:22 +08:00
|
|
|
|
|
|
|
param->flags |= DM_ACTIVE_PRESENT_FLAG;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) {
|
|
|
|
table = dm_get_inactive_table(md);
|
|
|
|
if (table) {
|
|
|
|
if (!(dm_table_get_mode(table) & FMODE_WRITE))
|
|
|
|
param->flags |= DM_READONLY_FLAG;
|
|
|
|
param->target_count = dm_table_get_num_targets(table);
|
|
|
|
dm_table_put(table);
|
|
|
|
}
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int dev_create(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
2006-06-26 15:27:32 +08:00
|
|
|
int r, m = DM_ANY_MINOR;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct mapped_device *md;
|
|
|
|
|
|
|
|
r = check_name(param->name);
|
|
|
|
if (r)
|
|
|
|
return r;
|
|
|
|
|
|
|
|
if (param->flags & DM_PERSISTENT_DEV_FLAG)
|
2006-06-26 15:27:32 +08:00
|
|
|
m = MINOR(huge_decode_dev(param->dev));
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-06-26 15:27:32 +08:00
|
|
|
r = dm_create(m, &md);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (r)
|
|
|
|
return r;
|
|
|
|
|
|
|
|
r = dm_hash_insert(param->name, *param->uuid ? param->uuid : NULL, md);
|
dm: separate device deletion from dm_put
This patch separates the device deletion code from dm_put()
to make sure the deletion happens in the process context.
By this patch, device deletion always occurs in an ioctl (process)
context and dm_put() can be called in interrupt context.
As a result, the request-based dm's bad dm_put() usage pointed out
by Mikulas below disappears.
http://marc.info/?l=dm-devel&m=126699981019735&w=2
Without this patch, I confirmed there is a case to crash the system:
dm_put() => dm_table_destroy() => vfree() => BUG_ON(in_interrupt())
Some more backgrounds and details:
In request-based dm, a device opener can remove a mapped_device
while the last request is still completing, because bios in the last
request complete first and then the device opener can close and remove
the mapped_device before the last request completes:
CPU0 CPU1
=================================================================
<<INTERRUPT>>
blk_end_request_all(clone_rq)
blk_update_request(clone_rq)
bio_endio(clone_bio) == end_clone_bio
blk_update_request(orig_rq)
bio_endio(orig_bio)
<<I/O completed>>
dm_blk_close()
dev_remove()
dm_put(md)
<<Free md>>
blk_finish_request(clone_rq)
....
dm_end_request(clone_rq)
free_rq_clone(clone_rq)
blk_end_request_all(orig_rq)
rq_completed(md)
So request-based dm used dm_get()/dm_put() to hold md for each I/O
until its request completion handling is fully done.
However, the final dm_put() can call the device deletion code which
must not be run in interrupt context and may cause kernel panic.
To solve the problem, this patch moves the device deletion code,
dm_destroy(), to predetermined places that is actually deleting
the mapped_device in ioctl (process) context, and changes dm_put()
just to decrement the reference count of the mapped_device.
By this change, dm_put() can be used in any context and the symmetric
model below is introduced:
dm_create(): create a mapped_device
dm_destroy(): destroy a mapped_device
dm_get(): increment the reference count of a mapped_device
dm_put(): decrement the reference count of a mapped_device
dm_destroy() waits for all references of the mapped_device to disappear,
then deletes the mapped_device.
dm_destroy() uses active waiting with msleep(1), since deleting
the mapped_device isn't performance-critical task.
And since at this point, nobody opens the mapped_device and no new
reference will be taken, the pending counts are just for racing
completing activity and will eventually decrease to zero.
For the unlikely case of the forced module unload, dm_destroy_immediate(),
which doesn't wait and forcibly deletes the mapped_device, is also
introduced and used in dm_hash_remove_all(). Otherwise, "rmmod -f"
may be stuck and never return.
And now, because the mapped_device is deleted at this point, subsequent
accesses to the mapped_device may cause NULL pointer references.
Cc: stable@kernel.org
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2010-08-12 11:13:56 +08:00
|
|
|
if (r) {
|
|
|
|
dm_put(md);
|
|
|
|
dm_destroy(md);
|
|
|
|
return r;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
param->flags &= ~DM_INACTIVE_PRESENT_FLAG;
|
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_put(md);
|
|
|
|
|
dm: separate device deletion from dm_put
This patch separates the device deletion code from dm_put()
to make sure the deletion happens in the process context.
By this patch, device deletion always occurs in an ioctl (process)
context and dm_put() can be called in interrupt context.
As a result, the request-based dm's bad dm_put() usage pointed out
by Mikulas below disappears.
http://marc.info/?l=dm-devel&m=126699981019735&w=2
Without this patch, I confirmed there is a case to crash the system:
dm_put() => dm_table_destroy() => vfree() => BUG_ON(in_interrupt())
Some more backgrounds and details:
In request-based dm, a device opener can remove a mapped_device
while the last request is still completing, because bios in the last
request complete first and then the device opener can close and remove
the mapped_device before the last request completes:
CPU0 CPU1
=================================================================
<<INTERRUPT>>
blk_end_request_all(clone_rq)
blk_update_request(clone_rq)
bio_endio(clone_bio) == end_clone_bio
blk_update_request(orig_rq)
bio_endio(orig_bio)
<<I/O completed>>
dm_blk_close()
dev_remove()
dm_put(md)
<<Free md>>
blk_finish_request(clone_rq)
....
dm_end_request(clone_rq)
free_rq_clone(clone_rq)
blk_end_request_all(orig_rq)
rq_completed(md)
So request-based dm used dm_get()/dm_put() to hold md for each I/O
until its request completion handling is fully done.
However, the final dm_put() can call the device deletion code which
must not be run in interrupt context and may cause kernel panic.
To solve the problem, this patch moves the device deletion code,
dm_destroy(), to predetermined places that is actually deleting
the mapped_device in ioctl (process) context, and changes dm_put()
just to decrement the reference count of the mapped_device.
By this change, dm_put() can be used in any context and the symmetric
model below is introduced:
dm_create(): create a mapped_device
dm_destroy(): destroy a mapped_device
dm_get(): increment the reference count of a mapped_device
dm_put(): decrement the reference count of a mapped_device
dm_destroy() waits for all references of the mapped_device to disappear,
then deletes the mapped_device.
dm_destroy() uses active waiting with msleep(1), since deleting
the mapped_device isn't performance-critical task.
And since at this point, nobody opens the mapped_device and no new
reference will be taken, the pending counts are just for racing
completing activity and will eventually decrease to zero.
For the unlikely case of the forced module unload, dm_destroy_immediate(),
which doesn't wait and forcibly deletes the mapped_device, is also
introduced and used in dm_hash_remove_all(). Otherwise, "rmmod -f"
may be stuck and never return.
And now, because the mapped_device is deleted at this point, subsequent
accesses to the mapped_device may cause NULL pointer references.
Cc: stable@kernel.org
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2010-08-12 11:13:56 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Always use UUID for lookups if it's present, otherwise use name or dev.
|
|
|
|
*/
|
2006-01-15 05:20:43 +08:00
|
|
|
static struct hash_cell *__find_device_hash_cell(struct dm_ioctl *param)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2006-03-27 17:17:53 +08:00
|
|
|
struct mapped_device *md;
|
|
|
|
void *mdptr = NULL;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (*param->uuid)
|
|
|
|
return __get_uuid_cell(param->uuid);
|
2006-03-27 17:17:53 +08:00
|
|
|
|
|
|
|
if (*param->name)
|
2005-04-17 06:20:36 +08:00
|
|
|
return __get_name_cell(param->name);
|
2006-03-27 17:17:53 +08:00
|
|
|
|
|
|
|
md = dm_get_md(huge_decode_dev(param->dev));
|
2006-11-09 09:44:42 +08:00
|
|
|
if (!md)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
mdptr = dm_get_mdptr(md);
|
|
|
|
if (!mdptr)
|
|
|
|
dm_put(md);
|
2006-03-27 17:17:53 +08:00
|
|
|
|
2006-11-09 09:44:42 +08:00
|
|
|
out:
|
2006-03-27 17:17:53 +08:00
|
|
|
return mdptr;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2006-01-15 05:20:43 +08:00
|
|
|
static struct mapped_device *find_device(struct dm_ioctl *param)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct hash_cell *hc;
|
|
|
|
struct mapped_device *md = NULL;
|
|
|
|
|
|
|
|
down_read(&_hash_lock);
|
|
|
|
hc = __find_device_hash_cell(param);
|
|
|
|
if (hc) {
|
|
|
|
md = hc->md;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Sneakily write in both the name and the uuid
|
|
|
|
* while we have the cell.
|
|
|
|
*/
|
2009-12-11 07:52:07 +08:00
|
|
|
strlcpy(param->name, hc->name, sizeof(param->name));
|
2005-04-17 06:20:36 +08:00
|
|
|
if (hc->uuid)
|
2009-12-11 07:52:07 +08:00
|
|
|
strlcpy(param->uuid, hc->uuid, sizeof(param->uuid));
|
2005-04-17 06:20:36 +08:00
|
|
|
else
|
|
|
|
param->uuid[0] = '\0';
|
|
|
|
|
|
|
|
if (hc->new_map)
|
|
|
|
param->flags |= DM_INACTIVE_PRESENT_FLAG;
|
|
|
|
else
|
|
|
|
param->flags &= ~DM_INACTIVE_PRESENT_FLAG;
|
|
|
|
}
|
|
|
|
up_read(&_hash_lock);
|
|
|
|
|
|
|
|
return md;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int dev_remove(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
struct hash_cell *hc;
|
2006-06-26 15:27:24 +08:00
|
|
|
struct mapped_device *md;
|
2006-06-26 15:27:34 +08:00
|
|
|
int r;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
down_write(&_hash_lock);
|
|
|
|
hc = __find_device_hash_cell(param);
|
|
|
|
|
|
|
|
if (!hc) {
|
2011-01-14 03:59:55 +08:00
|
|
|
DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table.");
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
return -ENXIO;
|
|
|
|
}
|
|
|
|
|
2006-06-26 15:27:24 +08:00
|
|
|
md = hc->md;
|
|
|
|
|
2006-06-26 15:27:34 +08:00
|
|
|
/*
|
|
|
|
* Ensure the device is not open and nothing further can open it.
|
|
|
|
*/
|
|
|
|
r = dm_lock_for_deletion(md);
|
|
|
|
if (r) {
|
2011-01-14 03:59:55 +08:00
|
|
|
DMDEBUG_LIMIT("unable to remove open device %s", hc->name);
|
2006-06-26 15:27:34 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
dm_put(md);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
__hash_remove(hc);
|
|
|
|
up_write(&_hash_lock);
|
2009-06-22 17:12:30 +08:00
|
|
|
|
2010-03-06 10:32:31 +08:00
|
|
|
if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr))
|
|
|
|
param->flags |= DM_UEVENT_GENERATED_FLAG;
|
2009-06-22 17:12:30 +08:00
|
|
|
|
2006-06-26 15:27:24 +08:00
|
|
|
dm_put(md);
|
dm: separate device deletion from dm_put
This patch separates the device deletion code from dm_put()
to make sure the deletion happens in the process context.
By this patch, device deletion always occurs in an ioctl (process)
context and dm_put() can be called in interrupt context.
As a result, the request-based dm's bad dm_put() usage pointed out
by Mikulas below disappears.
http://marc.info/?l=dm-devel&m=126699981019735&w=2
Without this patch, I confirmed there is a case to crash the system:
dm_put() => dm_table_destroy() => vfree() => BUG_ON(in_interrupt())
Some more backgrounds and details:
In request-based dm, a device opener can remove a mapped_device
while the last request is still completing, because bios in the last
request complete first and then the device opener can close and remove
the mapped_device before the last request completes:
CPU0 CPU1
=================================================================
<<INTERRUPT>>
blk_end_request_all(clone_rq)
blk_update_request(clone_rq)
bio_endio(clone_bio) == end_clone_bio
blk_update_request(orig_rq)
bio_endio(orig_bio)
<<I/O completed>>
dm_blk_close()
dev_remove()
dm_put(md)
<<Free md>>
blk_finish_request(clone_rq)
....
dm_end_request(clone_rq)
free_rq_clone(clone_rq)
blk_end_request_all(orig_rq)
rq_completed(md)
So request-based dm used dm_get()/dm_put() to hold md for each I/O
until its request completion handling is fully done.
However, the final dm_put() can call the device deletion code which
must not be run in interrupt context and may cause kernel panic.
To solve the problem, this patch moves the device deletion code,
dm_destroy(), to predetermined places that is actually deleting
the mapped_device in ioctl (process) context, and changes dm_put()
just to decrement the reference count of the mapped_device.
By this change, dm_put() can be used in any context and the symmetric
model below is introduced:
dm_create(): create a mapped_device
dm_destroy(): destroy a mapped_device
dm_get(): increment the reference count of a mapped_device
dm_put(): decrement the reference count of a mapped_device
dm_destroy() waits for all references of the mapped_device to disappear,
then deletes the mapped_device.
dm_destroy() uses active waiting with msleep(1), since deleting
the mapped_device isn't performance-critical task.
And since at this point, nobody opens the mapped_device and no new
reference will be taken, the pending counts are just for racing
completing activity and will eventually decrease to zero.
For the unlikely case of the forced module unload, dm_destroy_immediate(),
which doesn't wait and forcibly deletes the mapped_device, is also
introduced and used in dm_hash_remove_all(). Otherwise, "rmmod -f"
may be stuck and never return.
And now, because the mapped_device is deleted at this point, subsequent
accesses to the mapped_device may cause NULL pointer references.
Cc: stable@kernel.org
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2010-08-12 11:13:56 +08:00
|
|
|
dm_destroy(md);
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check a string doesn't overrun the chunk of
|
|
|
|
* memory we copied from userland.
|
|
|
|
*/
|
|
|
|
static int invalid_str(char *str, void *end)
|
|
|
|
{
|
|
|
|
while ((void *) str < end)
|
|
|
|
if (!*str++)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int dev_rename(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
int r;
|
2011-01-14 03:59:47 +08:00
|
|
|
char *new_data = (char *) param + param->data_start;
|
2010-08-12 11:13:53 +08:00
|
|
|
struct mapped_device *md;
|
2011-01-14 03:59:47 +08:00
|
|
|
unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-01-14 03:59:47 +08:00
|
|
|
if (new_data < param->data ||
|
|
|
|
invalid_str(new_data, (void *) param + param_size) ||
|
|
|
|
strlen(new_data) > (change_uuid ? DM_UUID_LEN - 1 : DM_NAME_LEN - 1)) {
|
|
|
|
DMWARN("Invalid new mapped device name or uuid string supplied.");
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2011-01-14 03:59:47 +08:00
|
|
|
if (!change_uuid) {
|
|
|
|
r = check_name(new_data);
|
|
|
|
if (r)
|
|
|
|
return r;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-01-14 03:59:47 +08:00
|
|
|
md = dm_hash_rename(param, new_data);
|
2010-08-12 11:13:53 +08:00
|
|
|
if (IS_ERR(md))
|
|
|
|
return PTR_ERR(md);
|
2010-03-06 10:32:31 +08:00
|
|
|
|
2010-08-12 11:13:53 +08:00
|
|
|
__dev_status(md, param);
|
|
|
|
dm_put(md);
|
|
|
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2006-03-27 17:17:54 +08:00
|
|
|
static int dev_set_geometry(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
int r = -EINVAL, x;
|
|
|
|
struct mapped_device *md;
|
|
|
|
struct hd_geometry geometry;
|
|
|
|
unsigned long indata[4];
|
|
|
|
char *geostr = (char *) param + param->data_start;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
2008-02-08 10:09:53 +08:00
|
|
|
if (geostr < param->data ||
|
2006-03-27 17:17:54 +08:00
|
|
|
invalid_str(geostr, (void *) param + param_size)) {
|
|
|
|
DMWARN("Invalid geometry supplied.");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
x = sscanf(geostr, "%lu %lu %lu %lu", indata,
|
|
|
|
indata + 1, indata + 2, indata + 3);
|
|
|
|
|
|
|
|
if (x != 4) {
|
|
|
|
DMWARN("Unable to interpret geometry settings.");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (indata[0] > 65535 || indata[1] > 255 ||
|
|
|
|
indata[2] > 255 || indata[3] > ULONG_MAX) {
|
|
|
|
DMWARN("Geometry exceeds range limits.");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
geometry.cylinders = indata[0];
|
|
|
|
geometry.heads = indata[1];
|
|
|
|
geometry.sectors = indata[2];
|
|
|
|
geometry.start = indata[3];
|
|
|
|
|
|
|
|
r = dm_set_geometry(md, &geometry);
|
|
|
|
|
|
|
|
param->data_size = 0;
|
|
|
|
|
|
|
|
out:
|
|
|
|
dm_put(md);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static int do_suspend(struct dm_ioctl *param)
|
|
|
|
{
|
|
|
|
int r = 0;
|
2006-12-08 18:41:04 +08:00
|
|
|
unsigned suspend_flags = DM_SUSPEND_LOCKFS_FLAG;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct mapped_device *md;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
2006-01-06 16:20:07 +08:00
|
|
|
if (param->flags & DM_SKIP_LOCKFS_FLAG)
|
2006-12-08 18:41:04 +08:00
|
|
|
suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG;
|
2006-12-08 18:41:07 +08:00
|
|
|
if (param->flags & DM_NOFLUSH_FLAG)
|
|
|
|
suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG;
|
2006-01-06 16:20:07 +08:00
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
if (!dm_suspended_md(md)) {
|
2006-12-08 18:41:04 +08:00
|
|
|
r = dm_suspend(md, suspend_flags);
|
2010-08-12 11:13:52 +08:00
|
|
|
if (r)
|
|
|
|
goto out;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
out:
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_put(md);
|
2010-08-12 11:13:52 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int do_resume(struct dm_ioctl *param)
|
|
|
|
{
|
|
|
|
int r = 0;
|
2006-12-08 18:41:04 +08:00
|
|
|
unsigned suspend_flags = DM_SUSPEND_LOCKFS_FLAG;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct hash_cell *hc;
|
|
|
|
struct mapped_device *md;
|
2009-12-11 07:52:24 +08:00
|
|
|
struct dm_table *new_map, *old_map = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
down_write(&_hash_lock);
|
|
|
|
|
|
|
|
hc = __find_device_hash_cell(param);
|
|
|
|
if (!hc) {
|
2011-01-14 03:59:55 +08:00
|
|
|
DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table.");
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
return -ENXIO;
|
|
|
|
}
|
|
|
|
|
|
|
|
md = hc->md;
|
|
|
|
|
|
|
|
new_map = hc->new_map;
|
|
|
|
hc->new_map = NULL;
|
|
|
|
param->flags &= ~DM_INACTIVE_PRESENT_FLAG;
|
|
|
|
|
|
|
|
up_write(&_hash_lock);
|
|
|
|
|
|
|
|
/* Do we need to load a new map ? */
|
|
|
|
if (new_map) {
|
|
|
|
/* Suspend if it isn't already suspended */
|
2006-01-06 16:20:07 +08:00
|
|
|
if (param->flags & DM_SKIP_LOCKFS_FLAG)
|
2006-12-08 18:41:04 +08:00
|
|
|
suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG;
|
2006-12-08 18:41:07 +08:00
|
|
|
if (param->flags & DM_NOFLUSH_FLAG)
|
|
|
|
suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG;
|
2009-12-11 07:52:26 +08:00
|
|
|
if (!dm_suspended_md(md))
|
2006-12-08 18:41:04 +08:00
|
|
|
dm_suspend(md, suspend_flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-12-11 07:52:24 +08:00
|
|
|
old_map = dm_swap_table(md, new_map);
|
|
|
|
if (IS_ERR(old_map)) {
|
dm table: rework reference counting
Rework table reference counting.
The existing code uses a reference counter. When the last reference is
dropped and the counter reaches zero, the table destructor is called.
Table reference counters are acquired/released from upcalls from other
kernel code (dm_any_congested, dm_merge_bvec, dm_unplug_all).
If the reference counter reaches zero in one of the upcalls, the table
destructor is called from almost random kernel code.
This leads to various problems:
* dm_any_congested being called under a spinlock, which calls the
destructor, which calls some sleeping function.
* the destructor attempting to take a lock that is already taken by the
same process.
* stale reference from some other kernel code keeps the table
constructed, which keeps some devices open, even after successful
return from "dmsetup remove". This can confuse lvm and prevent closing
of underlying devices or reusing device minor numbers.
The patch changes reference counting so that the table destructor can be
called only at predetermined places.
The table has always exactly one reference from either mapped_device->map
or hash_cell->new_map. After this patch, this reference is not counted
in table->holders. A pair of dm_create_table/dm_destroy_table functions
is used for table creation/destruction.
Temporary references from the other code increase table->holders. A pair
of dm_table_get/dm_table_put functions is used to manipulate it.
When the table is about to be destroyed, we wait for table->holders to
reach 0. Then, we call the table destructor. We use active waiting with
msleep(1), because the situation happens rarely (to one user in 5 years)
and removing the device isn't performance-critical task: the user doesn't
care if it takes one tick more or not.
This way, the destructor is called only at specific points
(dm_table_destroy function) and the above problems associated with lazy
destruction can't happen.
Finally remove the temporary protection added to dm_any_congested().
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2009-01-06 11:05:10 +08:00
|
|
|
dm_table_destroy(new_map);
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_put(md);
|
2009-12-11 07:52:24 +08:00
|
|
|
return PTR_ERR(old_map);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (dm_table_get_mode(new_map) & FMODE_WRITE)
|
|
|
|
set_disk_ro(dm_disk(md), 0);
|
|
|
|
else
|
|
|
|
set_disk_ro(dm_disk(md), 1);
|
|
|
|
}
|
|
|
|
|
2010-03-06 10:32:24 +08:00
|
|
|
if (dm_suspended_md(md)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
r = dm_resume(md);
|
2010-03-06 10:32:31 +08:00
|
|
|
if (!r && !dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr))
|
|
|
|
param->flags |= DM_UEVENT_GENERATED_FLAG;
|
2010-03-06 10:32:24 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-12-11 07:52:24 +08:00
|
|
|
if (old_map)
|
|
|
|
dm_table_destroy(old_map);
|
2009-06-22 17:12:30 +08:00
|
|
|
|
2010-03-06 10:32:24 +08:00
|
|
|
if (!r)
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
dm_put(md);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set or unset the suspension state of a device.
|
|
|
|
* If the device already is in the requested state we just return its status.
|
|
|
|
*/
|
|
|
|
static int dev_suspend(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
if (param->flags & DM_SUSPEND_FLAG)
|
|
|
|
return do_suspend(param);
|
|
|
|
|
|
|
|
return do_resume(param);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Copies device info back to user space, used by
|
|
|
|
* the create and info ioctls.
|
|
|
|
*/
|
|
|
|
static int dev_status(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
struct mapped_device *md;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_put(md);
|
2010-08-12 11:13:52 +08:00
|
|
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Build up the status struct for each target
|
|
|
|
*/
|
|
|
|
static void retrieve_status(struct dm_table *table,
|
|
|
|
struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
unsigned int i, num_targets;
|
|
|
|
struct dm_target_spec *spec;
|
|
|
|
char *outbuf, *outptr;
|
|
|
|
status_type_t type;
|
|
|
|
size_t remaining, len, used = 0;
|
|
|
|
|
|
|
|
outptr = outbuf = get_result_buffer(param, param_size, &len);
|
|
|
|
|
|
|
|
if (param->flags & DM_STATUS_TABLE_FLAG)
|
|
|
|
type = STATUSTYPE_TABLE;
|
|
|
|
else
|
|
|
|
type = STATUSTYPE_INFO;
|
|
|
|
|
|
|
|
/* Get all the target info */
|
|
|
|
num_targets = dm_table_get_num_targets(table);
|
|
|
|
for (i = 0; i < num_targets; i++) {
|
|
|
|
struct dm_target *ti = dm_table_get_target(table, i);
|
|
|
|
|
|
|
|
remaining = len - (outptr - outbuf);
|
|
|
|
if (remaining <= sizeof(struct dm_target_spec)) {
|
|
|
|
param->flags |= DM_BUFFER_FULL_FLAG;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
spec = (struct dm_target_spec *) outptr;
|
|
|
|
|
|
|
|
spec->status = 0;
|
|
|
|
spec->sector_start = ti->begin;
|
|
|
|
spec->length = ti->len;
|
|
|
|
strncpy(spec->target_type, ti->type->name,
|
|
|
|
sizeof(spec->target_type));
|
|
|
|
|
|
|
|
outptr += sizeof(struct dm_target_spec);
|
|
|
|
remaining = len - (outptr - outbuf);
|
|
|
|
if (remaining <= 0) {
|
|
|
|
param->flags |= DM_BUFFER_FULL_FLAG;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Get the status/table string from the target driver */
|
|
|
|
if (ti->type->status) {
|
|
|
|
if (ti->type->status(ti, type, outptr, remaining)) {
|
|
|
|
param->flags |= DM_BUFFER_FULL_FLAG;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
} else
|
|
|
|
outptr[0] = '\0';
|
|
|
|
|
|
|
|
outptr += strlen(outptr) + 1;
|
|
|
|
used = param->data_start + (outptr - outbuf);
|
|
|
|
|
|
|
|
outptr = align_ptr(outptr);
|
|
|
|
spec->next = outptr - outbuf;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (used)
|
|
|
|
param->data_size = used;
|
|
|
|
|
|
|
|
param->target_count = num_targets;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wait for a device to report an event
|
|
|
|
*/
|
|
|
|
static int dev_wait(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
2010-08-12 11:13:52 +08:00
|
|
|
int r = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct mapped_device *md;
|
|
|
|
struct dm_table *table;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wait for a notification event
|
|
|
|
*/
|
|
|
|
if (dm_wait_event(md, param->event_nr)) {
|
|
|
|
r = -ERESTARTSYS;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The userland program is going to want to know what
|
|
|
|
* changed to trigger the event, so we may as well tell
|
|
|
|
* him and save an ioctl.
|
|
|
|
*/
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-12-11 07:52:22 +08:00
|
|
|
table = dm_get_live_or_inactive_table(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (table) {
|
|
|
|
retrieve_status(table, param, param_size);
|
|
|
|
dm_table_put(table);
|
|
|
|
}
|
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
out:
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_put(md);
|
2010-08-12 11:13:52 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2008-09-03 03:28:45 +08:00
|
|
|
static inline fmode_t get_mode(struct dm_ioctl *param)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-09-03 03:28:45 +08:00
|
|
|
fmode_t mode = FMODE_READ | FMODE_WRITE;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if (param->flags & DM_READONLY_FLAG)
|
|
|
|
mode = FMODE_READ;
|
|
|
|
|
|
|
|
return mode;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int next_target(struct dm_target_spec *last, uint32_t next, void *end,
|
|
|
|
struct dm_target_spec **spec, char **target_params)
|
|
|
|
{
|
|
|
|
*spec = (struct dm_target_spec *) ((unsigned char *) last + next);
|
|
|
|
*target_params = (char *) (*spec + 1);
|
|
|
|
|
|
|
|
if (*spec < (last + 1))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
return invalid_str(*target_params, end);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int populate_table(struct dm_table *table,
|
|
|
|
struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
int r;
|
|
|
|
unsigned int i = 0;
|
|
|
|
struct dm_target_spec *spec = (struct dm_target_spec *) param;
|
|
|
|
uint32_t next = param->data_start;
|
|
|
|
void *end = (void *) param + param_size;
|
|
|
|
char *target_params;
|
|
|
|
|
|
|
|
if (!param->target_count) {
|
|
|
|
DMWARN("populate_table: no targets specified");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < param->target_count; i++) {
|
|
|
|
|
|
|
|
r = next_target(spec, next, end, &spec, &target_params);
|
|
|
|
if (r) {
|
|
|
|
DMWARN("unable to find target");
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
r = dm_table_add_target(table, spec->target_type,
|
|
|
|
(sector_t) spec->sector_start,
|
|
|
|
(sector_t) spec->length,
|
|
|
|
target_params);
|
|
|
|
if (r) {
|
|
|
|
DMWARN("error adding target to table");
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
next = spec->next;
|
|
|
|
}
|
|
|
|
|
|
|
|
return dm_table_complete(table);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int table_load(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
int r;
|
|
|
|
struct hash_cell *hc;
|
|
|
|
struct dm_table *t;
|
2006-03-27 17:17:54 +08:00
|
|
|
struct mapped_device *md;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-03-27 17:17:54 +08:00
|
|
|
r = dm_table_create(&t, get_mode(param), param->target_count, md);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (r)
|
2006-03-27 17:17:54 +08:00
|
|
|
goto out;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
r = populate_table(t, param, param_size);
|
|
|
|
if (r) {
|
2009-03-17 01:44:26 +08:00
|
|
|
dm_table_destroy(t);
|
2006-03-27 17:17:54 +08:00
|
|
|
goto out;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2010-08-12 11:14:02 +08:00
|
|
|
/* Protect md->type and md->queue against concurrent table loads. */
|
2010-08-12 11:14:01 +08:00
|
|
|
dm_lock_md_type(md);
|
|
|
|
if (dm_get_md_type(md) == DM_TYPE_NONE)
|
|
|
|
/* Initial table load: acquire type of table. */
|
|
|
|
dm_set_md_type(md, dm_table_get_type(t));
|
|
|
|
else if (dm_get_md_type(md) != dm_table_get_type(t)) {
|
|
|
|
DMWARN("can't change device type after initial table load.");
|
|
|
|
dm_table_destroy(t);
|
|
|
|
dm_unlock_md_type(md);
|
|
|
|
r = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
2010-08-12 11:14:02 +08:00
|
|
|
|
|
|
|
/* setup md->queue to reflect md's type (may block) */
|
|
|
|
r = dm_setup_md_queue(md);
|
|
|
|
if (r) {
|
|
|
|
DMWARN("unable to set up device queue for new table.");
|
|
|
|
dm_table_destroy(t);
|
|
|
|
dm_unlock_md_type(md);
|
|
|
|
goto out;
|
|
|
|
}
|
2010-08-12 11:14:01 +08:00
|
|
|
dm_unlock_md_type(md);
|
|
|
|
|
|
|
|
/* stage inactive table */
|
2005-04-17 06:20:36 +08:00
|
|
|
down_write(&_hash_lock);
|
2006-03-27 17:17:54 +08:00
|
|
|
hc = dm_get_mdptr(md);
|
|
|
|
if (!hc || hc->md != md) {
|
|
|
|
DMWARN("device has been removed from the dev hash table.");
|
2009-03-17 01:44:26 +08:00
|
|
|
dm_table_destroy(t);
|
2006-03-27 17:17:54 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
r = -ENXIO;
|
|
|
|
goto out;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (hc->new_map)
|
dm table: rework reference counting
Rework table reference counting.
The existing code uses a reference counter. When the last reference is
dropped and the counter reaches zero, the table destructor is called.
Table reference counters are acquired/released from upcalls from other
kernel code (dm_any_congested, dm_merge_bvec, dm_unplug_all).
If the reference counter reaches zero in one of the upcalls, the table
destructor is called from almost random kernel code.
This leads to various problems:
* dm_any_congested being called under a spinlock, which calls the
destructor, which calls some sleeping function.
* the destructor attempting to take a lock that is already taken by the
same process.
* stale reference from some other kernel code keeps the table
constructed, which keeps some devices open, even after successful
return from "dmsetup remove". This can confuse lvm and prevent closing
of underlying devices or reusing device minor numbers.
The patch changes reference counting so that the table destructor can be
called only at predetermined places.
The table has always exactly one reference from either mapped_device->map
or hash_cell->new_map. After this patch, this reference is not counted
in table->holders. A pair of dm_create_table/dm_destroy_table functions
is used for table creation/destruction.
Temporary references from the other code increase table->holders. A pair
of dm_table_get/dm_table_put functions is used to manipulate it.
When the table is about to be destroyed, we wait for table->holders to
reach 0. Then, we call the table destructor. We use active waiting with
msleep(1), because the situation happens rarely (to one user in 5 years)
and removing the device isn't performance-critical task: the user doesn't
care if it takes one tick more or not.
This way, the destructor is called only at specific points
(dm_table_destroy function) and the above problems associated with lazy
destruction can't happen.
Finally remove the temporary protection added to dm_any_congested().
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2009-01-06 11:05:10 +08:00
|
|
|
dm_table_destroy(hc->new_map);
|
2005-04-17 06:20:36 +08:00
|
|
|
hc->new_map = t;
|
2006-03-27 17:17:54 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
param->flags |= DM_INACTIVE_PRESENT_FLAG;
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
2006-03-27 17:17:54 +08:00
|
|
|
|
|
|
|
out:
|
|
|
|
dm_put(md);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int table_clear(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
struct hash_cell *hc;
|
2006-06-26 15:27:24 +08:00
|
|
|
struct mapped_device *md;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
down_write(&_hash_lock);
|
|
|
|
|
|
|
|
hc = __find_device_hash_cell(param);
|
|
|
|
if (!hc) {
|
2011-01-14 03:59:55 +08:00
|
|
|
DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table.");
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
|
|
|
return -ENXIO;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (hc->new_map) {
|
dm table: rework reference counting
Rework table reference counting.
The existing code uses a reference counter. When the last reference is
dropped and the counter reaches zero, the table destructor is called.
Table reference counters are acquired/released from upcalls from other
kernel code (dm_any_congested, dm_merge_bvec, dm_unplug_all).
If the reference counter reaches zero in one of the upcalls, the table
destructor is called from almost random kernel code.
This leads to various problems:
* dm_any_congested being called under a spinlock, which calls the
destructor, which calls some sleeping function.
* the destructor attempting to take a lock that is already taken by the
same process.
* stale reference from some other kernel code keeps the table
constructed, which keeps some devices open, even after successful
return from "dmsetup remove". This can confuse lvm and prevent closing
of underlying devices or reusing device minor numbers.
The patch changes reference counting so that the table destructor can be
called only at predetermined places.
The table has always exactly one reference from either mapped_device->map
or hash_cell->new_map. After this patch, this reference is not counted
in table->holders. A pair of dm_create_table/dm_destroy_table functions
is used for table creation/destruction.
Temporary references from the other code increase table->holders. A pair
of dm_table_get/dm_table_put functions is used to manipulate it.
When the table is about to be destroyed, we wait for table->holders to
reach 0. Then, we call the table destructor. We use active waiting with
msleep(1), because the situation happens rarely (to one user in 5 years)
and removing the device isn't performance-critical task: the user doesn't
care if it takes one tick more or not.
This way, the destructor is called only at specific points
(dm_table_destroy function) and the above problems associated with lazy
destruction can't happen.
Finally remove the temporary protection added to dm_any_congested().
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
2009-01-06 11:05:10 +08:00
|
|
|
dm_table_destroy(hc->new_map);
|
2005-04-17 06:20:36 +08:00
|
|
|
hc->new_map = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
param->flags &= ~DM_INACTIVE_PRESENT_FLAG;
|
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(hc->md, param);
|
2006-06-26 15:27:24 +08:00
|
|
|
md = hc->md;
|
2005-04-17 06:20:36 +08:00
|
|
|
up_write(&_hash_lock);
|
2006-06-26 15:27:24 +08:00
|
|
|
dm_put(md);
|
2010-08-12 11:13:52 +08:00
|
|
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Retrieves a list of devices used by a particular dm device.
|
|
|
|
*/
|
|
|
|
static void retrieve_deps(struct dm_table *table,
|
|
|
|
struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
unsigned int count = 0;
|
|
|
|
struct list_head *tmp;
|
|
|
|
size_t len, needed;
|
2008-10-10 20:37:09 +08:00
|
|
|
struct dm_dev_internal *dd;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct dm_target_deps *deps;
|
|
|
|
|
|
|
|
deps = get_result_buffer(param, param_size, &len);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Count the devices.
|
|
|
|
*/
|
|
|
|
list_for_each (tmp, dm_table_get_devices(table))
|
|
|
|
count++;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check we have enough space.
|
|
|
|
*/
|
|
|
|
needed = sizeof(*deps) + (sizeof(*deps->dev) * count);
|
|
|
|
if (len < needed) {
|
|
|
|
param->flags |= DM_BUFFER_FULL_FLAG;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Fill in the devices.
|
|
|
|
*/
|
|
|
|
deps->count = count;
|
|
|
|
count = 0;
|
|
|
|
list_for_each_entry (dd, dm_table_get_devices(table), list)
|
2008-10-10 20:37:09 +08:00
|
|
|
deps->dev[count++] = huge_encode_dev(dd->dm_dev.bdev->bd_dev);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
param->data_size = param->data_start + needed;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int table_deps(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
struct mapped_device *md;
|
|
|
|
struct dm_table *table;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-12-11 07:52:22 +08:00
|
|
|
table = dm_get_live_or_inactive_table(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (table) {
|
|
|
|
retrieve_deps(table, param, param_size);
|
|
|
|
dm_table_put(table);
|
|
|
|
}
|
|
|
|
|
|
|
|
dm_put(md);
|
2010-08-12 11:13:52 +08:00
|
|
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Return the status of a device as a text string for each
|
|
|
|
* target.
|
|
|
|
*/
|
|
|
|
static int table_status(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
struct mapped_device *md;
|
|
|
|
struct dm_table *table;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
2010-08-12 11:13:52 +08:00
|
|
|
__dev_status(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-12-11 07:52:22 +08:00
|
|
|
table = dm_get_live_or_inactive_table(md, param);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (table) {
|
|
|
|
retrieve_status(table, param, param_size);
|
|
|
|
dm_table_put(table);
|
|
|
|
}
|
|
|
|
|
|
|
|
dm_put(md);
|
2010-08-12 11:13:52 +08:00
|
|
|
|
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Pass a message to the target that's at the supplied device offset.
|
|
|
|
*/
|
|
|
|
static int target_message(struct dm_ioctl *param, size_t param_size)
|
|
|
|
{
|
|
|
|
int r, argc;
|
|
|
|
char **argv;
|
|
|
|
struct mapped_device *md;
|
|
|
|
struct dm_table *table;
|
|
|
|
struct dm_target *ti;
|
|
|
|
struct dm_target_msg *tmsg = (void *) param + param->data_start;
|
|
|
|
|
|
|
|
md = find_device(param);
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
2007-10-20 05:38:36 +08:00
|
|
|
if (tmsg < (struct dm_target_msg *) param->data ||
|
2005-04-17 06:20:36 +08:00
|
|
|
invalid_str(tmsg->message, (void *) param + param_size)) {
|
|
|
|
DMWARN("Invalid target message parameters.");
|
|
|
|
r = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
r = dm_split_args(&argc, &argv, tmsg->message);
|
|
|
|
if (r) {
|
|
|
|
DMWARN("Failed to split target message parameters");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2009-12-11 07:52:19 +08:00
|
|
|
table = dm_get_live_table(md);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (!table)
|
|
|
|
goto out_argv;
|
|
|
|
|
2009-12-11 07:52:20 +08:00
|
|
|
if (dm_deleting_md(md)) {
|
|
|
|
r = -ENXIO;
|
|
|
|
goto out_table;
|
|
|
|
}
|
|
|
|
|
2007-12-13 22:15:25 +08:00
|
|
|
ti = dm_table_find_target(table, tmsg->sector);
|
|
|
|
if (!dm_target_is_valid(ti)) {
|
2005-04-17 06:20:36 +08:00
|
|
|
DMWARN("Target message sector outside device.");
|
|
|
|
r = -EINVAL;
|
2007-12-13 22:15:25 +08:00
|
|
|
} else if (ti->type->message)
|
2005-04-17 06:20:36 +08:00
|
|
|
r = ti->type->message(ti, argc, argv);
|
|
|
|
else {
|
|
|
|
DMWARN("Target type does not support messages");
|
|
|
|
r = -EINVAL;
|
|
|
|
}
|
|
|
|
|
2009-12-11 07:52:20 +08:00
|
|
|
out_table:
|
2005-04-17 06:20:36 +08:00
|
|
|
dm_table_put(table);
|
|
|
|
out_argv:
|
|
|
|
kfree(argv);
|
|
|
|
out:
|
|
|
|
param->data_size = 0;
|
|
|
|
dm_put(md);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*-----------------------------------------------------------------
|
|
|
|
* Implementation of open/close/ioctl on the special char
|
|
|
|
* device.
|
|
|
|
*---------------------------------------------------------------*/
|
|
|
|
static ioctl_fn lookup_ioctl(unsigned int cmd)
|
|
|
|
{
|
|
|
|
static struct {
|
|
|
|
int cmd;
|
|
|
|
ioctl_fn fn;
|
|
|
|
} _ioctls[] = {
|
|
|
|
{DM_VERSION_CMD, NULL}, /* version is dealt with elsewhere */
|
|
|
|
{DM_REMOVE_ALL_CMD, remove_all},
|
|
|
|
{DM_LIST_DEVICES_CMD, list_devices},
|
|
|
|
|
|
|
|
{DM_DEV_CREATE_CMD, dev_create},
|
|
|
|
{DM_DEV_REMOVE_CMD, dev_remove},
|
|
|
|
{DM_DEV_RENAME_CMD, dev_rename},
|
|
|
|
{DM_DEV_SUSPEND_CMD, dev_suspend},
|
|
|
|
{DM_DEV_STATUS_CMD, dev_status},
|
|
|
|
{DM_DEV_WAIT_CMD, dev_wait},
|
|
|
|
|
|
|
|
{DM_TABLE_LOAD_CMD, table_load},
|
|
|
|
{DM_TABLE_CLEAR_CMD, table_clear},
|
|
|
|
{DM_TABLE_DEPS_CMD, table_deps},
|
|
|
|
{DM_TABLE_STATUS_CMD, table_status},
|
|
|
|
|
|
|
|
{DM_LIST_VERSIONS_CMD, list_versions},
|
|
|
|
|
2006-03-27 17:17:54 +08:00
|
|
|
{DM_TARGET_MSG_CMD, target_message},
|
|
|
|
{DM_DEV_SET_GEOMETRY_CMD, dev_set_geometry}
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
return (cmd >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[cmd].fn;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* As well as checking the version compatibility this always
|
|
|
|
* copies the kernel interface version out.
|
|
|
|
*/
|
|
|
|
static int check_version(unsigned int cmd, struct dm_ioctl __user *user)
|
|
|
|
{
|
|
|
|
uint32_t version[3];
|
|
|
|
int r = 0;
|
|
|
|
|
|
|
|
if (copy_from_user(version, user->version, sizeof(version)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
if ((DM_VERSION_MAJOR != version[0]) ||
|
|
|
|
(DM_VERSION_MINOR < version[1])) {
|
|
|
|
DMWARN("ioctl interface mismatch: "
|
|
|
|
"kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)",
|
|
|
|
DM_VERSION_MAJOR, DM_VERSION_MINOR,
|
|
|
|
DM_VERSION_PATCHLEVEL,
|
|
|
|
version[0], version[1], version[2], cmd);
|
|
|
|
r = -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Fill in the kernel version.
|
|
|
|
*/
|
|
|
|
version[0] = DM_VERSION_MAJOR;
|
|
|
|
version[1] = DM_VERSION_MINOR;
|
|
|
|
version[2] = DM_VERSION_PATCHLEVEL;
|
|
|
|
if (copy_to_user(user->version, version, sizeof(version)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl **param)
|
|
|
|
{
|
|
|
|
struct dm_ioctl tmp, *dmi;
|
2011-03-24 21:54:30 +08:00
|
|
|
int secure_data;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-02-08 10:09:56 +08:00
|
|
|
if (copy_from_user(&tmp, user, sizeof(tmp) - sizeof(tmp.data)))
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EFAULT;
|
|
|
|
|
2008-02-08 10:09:56 +08:00
|
|
|
if (tmp.data_size < (sizeof(tmp) - sizeof(tmp.data)))
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
2011-03-24 21:54:30 +08:00
|
|
|
secure_data = tmp.flags & DM_SECURE_DATA_FLAG;
|
|
|
|
|
2007-10-20 05:38:54 +08:00
|
|
|
dmi = vmalloc(tmp.data_size);
|
2011-03-24 21:54:30 +08:00
|
|
|
if (!dmi) {
|
|
|
|
if (secure_data && clear_user(user, tmp.data_size))
|
|
|
|
return -EFAULT;
|
2005-04-17 06:20:36 +08:00
|
|
|
return -ENOMEM;
|
2011-03-24 21:54:30 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-03-24 21:54:28 +08:00
|
|
|
if (copy_from_user(dmi, user, tmp.data_size))
|
|
|
|
goto bad;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-03-24 21:54:30 +08:00
|
|
|
/* Wipe the user buffer so we do not return it to userspace */
|
|
|
|
if (secure_data && clear_user(user, tmp.data_size))
|
|
|
|
goto bad;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
*param = dmi;
|
|
|
|
return 0;
|
2011-03-24 21:54:28 +08:00
|
|
|
|
|
|
|
bad:
|
2011-03-24 21:54:30 +08:00
|
|
|
if (secure_data)
|
|
|
|
memset(dmi, 0, tmp.data_size);
|
2011-03-24 21:54:28 +08:00
|
|
|
vfree(dmi);
|
|
|
|
return -EFAULT;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int validate_params(uint cmd, struct dm_ioctl *param)
|
|
|
|
{
|
|
|
|
/* Always clear this flag */
|
|
|
|
param->flags &= ~DM_BUFFER_FULL_FLAG;
|
2010-03-06 10:32:31 +08:00
|
|
|
param->flags &= ~DM_UEVENT_GENERATED_FLAG;
|
2011-03-24 21:54:30 +08:00
|
|
|
param->flags &= ~DM_SECURE_DATA_FLAG;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Ignores parameters */
|
|
|
|
if (cmd == DM_REMOVE_ALL_CMD ||
|
|
|
|
cmd == DM_LIST_DEVICES_CMD ||
|
|
|
|
cmd == DM_LIST_VERSIONS_CMD)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if ((cmd == DM_DEV_CREATE_CMD)) {
|
|
|
|
if (!*param->name) {
|
|
|
|
DMWARN("name not supplied when creating device");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
} else if ((*param->uuid && *param->name)) {
|
|
|
|
DMWARN("only supply one of name or uuid, cmd(%u)", cmd);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Ensure strings are terminated */
|
|
|
|
param->name[DM_NAME_LEN - 1] = '\0';
|
|
|
|
param->uuid[DM_UUID_LEN - 1] = '\0';
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-02-08 10:09:53 +08:00
|
|
|
static int ctl_ioctl(uint command, struct dm_ioctl __user *user)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
int r = 0;
|
2011-03-24 21:54:30 +08:00
|
|
|
int wipe_buffer;
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned int cmd;
|
2008-02-08 10:10:16 +08:00
|
|
|
struct dm_ioctl *uninitialized_var(param);
|
2005-04-17 06:20:36 +08:00
|
|
|
ioctl_fn fn = NULL;
|
2011-03-24 21:54:28 +08:00
|
|
|
size_t input_param_size;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* only root can play with this */
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
|
|
return -EACCES;
|
|
|
|
|
|
|
|
if (_IOC_TYPE(command) != DM_IOCTL)
|
|
|
|
return -ENOTTY;
|
|
|
|
|
|
|
|
cmd = _IOC_NR(command);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check the interface version passed in. This also
|
|
|
|
* writes out the kernel's interface version.
|
|
|
|
*/
|
|
|
|
r = check_version(cmd, user);
|
|
|
|
if (r)
|
|
|
|
return r;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Nothing more to do for the version command.
|
|
|
|
*/
|
|
|
|
if (cmd == DM_VERSION_CMD)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
fn = lookup_ioctl(cmd);
|
|
|
|
if (!fn) {
|
|
|
|
DMWARN("dm_ctl_ioctl: unknown command 0x%x", command);
|
|
|
|
return -ENOTTY;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Trying to avoid low memory issues when a device is
|
|
|
|
* suspended.
|
|
|
|
*/
|
|
|
|
current->flags |= PF_MEMALLOC;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Copy the parameters into kernel space.
|
|
|
|
*/
|
|
|
|
r = copy_params(user, ¶m);
|
|
|
|
|
2006-02-01 19:04:52 +08:00
|
|
|
current->flags &= ~PF_MEMALLOC;
|
|
|
|
|
|
|
|
if (r)
|
|
|
|
return r;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-03-24 21:54:30 +08:00
|
|
|
input_param_size = param->data_size;
|
|
|
|
wipe_buffer = param->flags & DM_SECURE_DATA_FLAG;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
r = validate_params(cmd, param);
|
|
|
|
if (r)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
param->data_size = sizeof(*param);
|
2011-03-24 21:54:28 +08:00
|
|
|
r = fn(param, input_param_size);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Copy the results back to userland.
|
|
|
|
*/
|
|
|
|
if (!r && copy_to_user(user, param, param->data_size))
|
|
|
|
r = -EFAULT;
|
|
|
|
|
2011-03-24 21:54:28 +08:00
|
|
|
out:
|
2011-03-24 21:54:30 +08:00
|
|
|
if (wipe_buffer)
|
|
|
|
memset(param, 0, input_param_size);
|
|
|
|
|
2011-03-24 21:54:28 +08:00
|
|
|
vfree(param);
|
2005-04-17 06:20:36 +08:00
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2008-02-08 10:09:53 +08:00
|
|
|
static long dm_ctl_ioctl(struct file *file, uint command, ulong u)
|
|
|
|
{
|
|
|
|
return (long)ctl_ioctl(command, (struct dm_ioctl __user *)u);
|
|
|
|
}
|
|
|
|
|
2008-02-08 10:09:56 +08:00
|
|
|
#ifdef CONFIG_COMPAT
|
|
|
|
static long dm_compat_ctl_ioctl(struct file *file, uint command, ulong u)
|
|
|
|
{
|
|
|
|
return (long)dm_ctl_ioctl(file, command, (ulong) compat_ptr(u));
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
#define dm_compat_ctl_ioctl NULL
|
|
|
|
#endif
|
|
|
|
|
2007-02-12 16:55:33 +08:00
|
|
|
static const struct file_operations _ctl_fops = {
|
2010-08-12 11:13:57 +08:00
|
|
|
.open = nonseekable_open,
|
2008-02-08 10:09:53 +08:00
|
|
|
.unlocked_ioctl = dm_ctl_ioctl,
|
2008-02-08 10:09:56 +08:00
|
|
|
.compat_ioctl = dm_compat_ctl_ioctl,
|
2005-04-17 06:20:36 +08:00
|
|
|
.owner = THIS_MODULE,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
|
|
|
.llseek = noop_llseek,
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
static struct miscdevice _dm_misc = {
|
2010-08-12 11:14:05 +08:00
|
|
|
.minor = MAPPER_CTRL_MINOR,
|
2005-04-17 06:20:36 +08:00
|
|
|
.name = DM_NAME,
|
2010-08-12 11:14:05 +08:00
|
|
|
.nodename = DM_DIR "/" DM_CONTROL_NODE,
|
2005-04-17 06:20:36 +08:00
|
|
|
.fops = &_ctl_fops
|
|
|
|
};
|
|
|
|
|
2010-08-12 11:14:05 +08:00
|
|
|
MODULE_ALIAS_MISCDEV(MAPPER_CTRL_MINOR);
|
|
|
|
MODULE_ALIAS("devname:" DM_DIR "/" DM_CONTROL_NODE);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Create misc character device and link to DM_DIR/control.
|
|
|
|
*/
|
|
|
|
int __init dm_interface_init(void)
|
|
|
|
{
|
|
|
|
int r;
|
|
|
|
|
|
|
|
r = dm_hash_init();
|
|
|
|
if (r)
|
|
|
|
return r;
|
|
|
|
|
|
|
|
r = misc_register(&_dm_misc);
|
|
|
|
if (r) {
|
|
|
|
DMERR("misc_register failed for control device");
|
|
|
|
dm_hash_exit();
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
DMINFO("%d.%d.%d%s initialised: %s", DM_VERSION_MAJOR,
|
|
|
|
DM_VERSION_MINOR, DM_VERSION_PATCHLEVEL, DM_VERSION_EXTRA,
|
|
|
|
DM_DRIVER_EMAIL);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void dm_interface_exit(void)
|
|
|
|
{
|
|
|
|
if (misc_deregister(&_dm_misc) < 0)
|
|
|
|
DMERR("misc_deregister failed for control device");
|
|
|
|
|
|
|
|
dm_hash_exit();
|
|
|
|
}
|
2007-10-20 05:47:59 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* dm_copy_name_and_uuid - Copy mapped device name & uuid into supplied buffers
|
|
|
|
* @md: Pointer to mapped_device
|
|
|
|
* @name: Buffer (size DM_NAME_LEN) for name
|
|
|
|
* @uuid: Buffer (size DM_UUID_LEN) for uuid or empty string if uuid not defined
|
|
|
|
*/
|
|
|
|
int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid)
|
|
|
|
{
|
|
|
|
int r = 0;
|
|
|
|
struct hash_cell *hc;
|
|
|
|
|
|
|
|
if (!md)
|
|
|
|
return -ENXIO;
|
|
|
|
|
2009-12-11 07:51:52 +08:00
|
|
|
mutex_lock(&dm_hash_cells_mutex);
|
2007-10-20 05:47:59 +08:00
|
|
|
hc = dm_get_mdptr(md);
|
|
|
|
if (!hc || hc->md != md) {
|
|
|
|
r = -ENXIO;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2009-01-06 11:05:04 +08:00
|
|
|
if (name)
|
|
|
|
strcpy(name, hc->name);
|
|
|
|
if (uuid)
|
|
|
|
strcpy(uuid, hc->uuid ? : "");
|
2007-10-20 05:47:59 +08:00
|
|
|
|
|
|
|
out:
|
2009-12-11 07:51:52 +08:00
|
|
|
mutex_unlock(&dm_hash_cells_mutex);
|
2007-10-20 05:47:59 +08:00
|
|
|
|
|
|
|
return r;
|
|
|
|
}
|