linux/drivers/md/dm-table.c

2030 lines
47 KiB
C
Raw Normal View History

/*
* Copyright (C) 2001 Sistina Software (UK) Limited.
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 03:05:10 +00:00
* Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
#include "dm-core.h"
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/namei.h>
#include <linux/ctype.h>
tree-wide: convert open calls to remove spaces to skip_spaces() lib function Makes use of skip_spaces() defined in lib/string.c for removing leading spaces from strings all over the tree. It decreases lib.a code size by 47 bytes and reuses the function tree-wide: text data bss dec hex filename 64688 584 592 65864 10148 (TOTALS-BEFORE) 64641 584 592 65817 10119 (TOTALS-AFTER) Also, while at it, if we see (*str && isspace(*str)), we can be sure to remove the first condition (*str) as the second one (isspace(*str)) also evaluates to 0 whenever *str == 0, making it redundant. In other words, "a char equals zero is never a space". Julia Lawall tried the semantic patch (http://coccinelle.lip6.fr) below, and found occurrences of this pattern on 3 more files: drivers/leds/led-class.c drivers/leds/ledtrig-timer.c drivers/video/output.c @@ expression str; @@ ( // ignore skip_spaces cases while (*str && isspace(*str)) { \(str++;\|++str;\) } | - *str && isspace(*str) ) Signed-off-by: André Goddard Rosa <andre.goddard@gmail.com> Cc: Julia Lawall <julia@diku.dk> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Richard Purdie <rpurdie@rpsys.net> Cc: Neil Brown <neilb@suse.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Henrique de Moraes Holschuh <hmh@hmh.eng.br> Cc: David Howells <dhowells@redhat.com> Cc: <linux-ext4@vger.kernel.org> Cc: Samuel Ortiz <samuel@sortiz.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Takashi Iwai <tiwai@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:01:06 +00:00
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/mutex.h>
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 03:05:10 +00:00
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/lcm.h>
#include <linux/blk-mq.h>
dm table: fall back to getting device using name_to_dev_t() If a device is used as the root filesystem, it can't be built off of devices which are within the root filesystem (just like command line arguments to root=). For this reason, Linux has a pseudo-filesystem for root= and MD initialization (based on the function name_to_dev_t) which handles different ways of specifying devices including PARTUUID and major:minor. Switch to using name_to_dev_t() in dm_get_device(). Rather than having DM assume that all things which are not major:minor are paths in an already-mounted filesystem, change dm_get_device() to first attempt to look up the device in the filesystem, and if not found it will fall back to using name_to_dev_t(). In terms of backwards compatibility, there are some cases where behavior will be different: - If you have a file in the current working directory named 1:2 and you initialze DM there, then it will try to use that file rather than the disk with that major:minor pair as a backing device. - Similarly for other bdev types which name_to_dev_t() knows how to interpret, the previous behavior was to repeatedly check for the existence of the file (e.g., while waiting for rootfs to come up) but the new behavior is to use the name_to_dev_t() interpretation. For example, if you have a file named /dev/ubiblock0_0 which is a symlink to /dev/sda3, but it is not yet present when DM starts to initialize, then the name_to_dev_t() interpretation will take precedence. These incompatibilities would only show up in really strange setups with bad practices so we shouldn't have to worry about them. Signed-off-by: Dan Ehrenberg <dehrenberg@chromium.org> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2015-02-10 23:20:51 +00:00
#include <linux/mount.h>
#include <linux/dax.h>
#define DM_MSG_PREFIX "table"
#define NODE_SIZE L1_CACHE_BYTES
#define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
#define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
/*
* Similar to ceiling(log_size(n))
*/
static unsigned int int_log(unsigned int n, unsigned int base)
{
int result = 0;
while (n > 1) {
n = dm_div_up(n, base);
result++;
}
return result;
}
/*
* Calculate the index of the child node of the n'th node k'th key.
*/
static inline unsigned int get_child(unsigned int n, unsigned int k)
{
return (n * CHILDREN_PER_NODE) + k;
}
/*
* Return the n'th node of level l from table t.
*/
static inline sector_t *get_node(struct dm_table *t,
unsigned int l, unsigned int n)
{
return t->index[l] + (n * KEYS_PER_NODE);
}
/*
* Return the highest key that you could lookup from the n'th
* node on level l of the btree.
*/
static sector_t high(struct dm_table *t, unsigned int l, unsigned int n)
{
for (; l < t->depth - 1; l++)
n = get_child(n, CHILDREN_PER_NODE - 1);
if (n >= t->counts[l])
return (sector_t) - 1;
return get_node(t, l, n)[KEYS_PER_NODE - 1];
}
/*
* Fills in a level of the btree based on the highs of the level
* below it.
*/
static int setup_btree_index(unsigned int l, struct dm_table *t)
{
unsigned int n, k;
sector_t *node;
for (n = 0U; n < t->counts[l]; n++) {
node = get_node(t, l, n);
for (k = 0U; k < KEYS_PER_NODE; k++)
node[k] = high(t, l + 1, get_child(n, k));
}
return 0;
}
void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size)
{
unsigned long size;
void *addr;
/*
* Check that we're not going to overflow.
*/
if (nmemb > (ULONG_MAX / elem_size))
return NULL;
size = nmemb * elem_size;
addr = vzalloc(size);
return addr;
}
EXPORT_SYMBOL(dm_vcalloc);
/*
* highs, and targets are managed as dynamic arrays during a
* table load.
*/
static int alloc_targets(struct dm_table *t, unsigned int num)
{
sector_t *n_highs;
struct dm_target *n_targets;
/*
* Allocate both the target array and offset array at once.
*/
n_highs = (sector_t *) dm_vcalloc(num, sizeof(struct dm_target) +
sizeof(sector_t));
if (!n_highs)
return -ENOMEM;
n_targets = (struct dm_target *) (n_highs + num);
memset(n_highs, -1, sizeof(*n_highs) * num);
vfree(t->highs);
t->num_allocated = num;
t->highs = n_highs;
t->targets = n_targets;
return 0;
}
int dm_table_create(struct dm_table **result, fmode_t mode,
unsigned num_targets, struct mapped_device *md)
{
struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
if (!t)
return -ENOMEM;
INIT_LIST_HEAD(&t->devices);
if (!num_targets)
num_targets = KEYS_PER_NODE;
num_targets = dm_round_up(num_targets, KEYS_PER_NODE);
if (!num_targets) {
kfree(t);
return -ENOMEM;
}
if (alloc_targets(t, num_targets)) {
kfree(t);
return -ENOMEM;
}
t->type = DM_TYPE_NONE;
t->mode = mode;
t->md = md;
*result = t;
return 0;
}
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
static void free_devices(struct list_head *devices, struct mapped_device *md)
{
struct list_head *tmp, *next;
list_for_each_safe(tmp, next, devices) {
struct dm_dev_internal *dd =
list_entry(tmp, struct dm_dev_internal, list);
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
DMWARN("%s: dm_table_destroy: dm_put_device call missing for %s",
dm_device_name(md), dd->dm_dev->name);
dm_put_table_device(md, dd->dm_dev);
kfree(dd);
}
}
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 03:05:10 +00:00
void dm_table_destroy(struct dm_table *t)
{
unsigned int i;
if (!t)
return;
/* free the indexes */
if (t->depth >= 2)
vfree(t->index[t->depth - 2]);
/* free the targets */
for (i = 0; i < t->num_targets; i++) {
struct dm_target *tgt = t->targets + i;
if (tgt->type->dtr)
tgt->type->dtr(tgt);
dm_put_target_type(tgt->type);
}
vfree(t->highs);
/* free the device list */
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
free_devices(&t->devices, t->md);
dm_free_md_mempools(t->mempools);
kfree(t);
}
/*
* See if we've already got a device in the list.
*/
static struct dm_dev_internal *find_device(struct list_head *l, dev_t dev)
{
struct dm_dev_internal *dd;
list_for_each_entry (dd, l, list)
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
if (dd->dm_dev->bdev->bd_dev == dev)
return dd;
return NULL;
}
/*
* If possible, this checks an area of a destination device is invalid.
*/
static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct queue_limits *limits = data;
struct block_device *bdev = dev->bdev;
sector_t dev_size =
i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
unsigned short logical_block_size_sectors =
limits->logical_block_size >> SECTOR_SHIFT;
char b[BDEVNAME_SIZE];
if (!dev_size)
return 0;
if ((start >= dev_size) || (start + len > dev_size)) {
DMWARN("%s: %s too small for target: "
"start=%llu, len=%llu, dev_size=%llu",
dm_device_name(ti->table->md), bdevname(bdev, b),
(unsigned long long)start,
(unsigned long long)len,
(unsigned long long)dev_size);
return 1;
}
dm table: add zoned block devices validation 1) Introduce DM_TARGET_ZONED_HM feature flag: The target drivers currently available will not operate correctly if a table target maps onto a host-managed zoned block device. To avoid problems, introduce the new feature flag DM_TARGET_ZONED_HM to allow a target to explicitly state that it supports host-managed zoned block devices. This feature is checked for all targets in a table if any of the table's block devices are host-managed. Note that as host-aware zoned block devices are backward compatible with regular block devices, they can be used by any of the current target types. This new feature is thus restricted to host-managed zoned block devices. 2) Check device area zone alignment: If a target maps to a zoned block device, check that the device area is aligned on zone boundaries to avoid problems with REQ_OP_ZONE_RESET operations (resetting a partially mapped sequential zone would not be possible). This also facilitates the processing of zone report with REQ_OP_ZONE_REPORT bios. 3) Check block devices zone model compatibility When setting the DM device's queue limits, several possibilities exists for zoned block devices: 1) The DM target driver may want to expose a different zone model (e.g. host-managed device emulation or regular block device on top of host-managed zoned block devices) 2) Expose the underlying zone model of the devices as-is To allow both cases, the underlying block device zone model must be set in the target limits in dm_set_device_limits() and the compatibility of all devices checked similarly to the logical block size alignment. For this last check, introduce validate_hardware_zoned_model() to check that all targets of a table have the same zone model and that the zone size of the target devices are equal. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [Mike Snitzer refactored Damien's original work to simplify the code] Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2017-05-08 23:40:43 +00:00
/*
* If the target is mapped to zoned block device(s), check
* that the zones are not partially mapped.
*/
if (bdev_zoned_model(bdev) != BLK_ZONED_NONE) {
unsigned int zone_sectors = bdev_zone_sectors(bdev);
if (start & (zone_sectors - 1)) {
DMWARN("%s: start=%llu not aligned to h/w zone size %u of %s",
dm_device_name(ti->table->md),
(unsigned long long)start,
zone_sectors, bdevname(bdev, b));
return 1;
}
/*
* Note: The last zone of a zoned block device may be smaller
* than other zones. So for a target mapping the end of a
* zoned block device with such a zone, len would not be zone
* aligned. We do not allow such last smaller zone to be part
* of the mapping here to ensure that mappings with multiple
* devices do not end up with a smaller zone in the middle of
* the sector range.
*/
if (len & (zone_sectors - 1)) {
DMWARN("%s: len=%llu not aligned to h/w zone size %u of %s",
dm_device_name(ti->table->md),
(unsigned long long)len,
zone_sectors, bdevname(bdev, b));
return 1;
}
}
if (logical_block_size_sectors <= 1)
return 0;
if (start & (logical_block_size_sectors - 1)) {
DMWARN("%s: start=%llu not aligned to h/w "
"logical block size %u of %s",
dm_device_name(ti->table->md),
(unsigned long long)start,
limits->logical_block_size, bdevname(bdev, b));
return 1;
}
if (len & (logical_block_size_sectors - 1)) {
DMWARN("%s: len=%llu not aligned to h/w "
"logical block size %u of %s",
dm_device_name(ti->table->md),
(unsigned long long)len,
limits->logical_block_size, bdevname(bdev, b));
return 1;
}
return 0;
}
/*
* This upgrades the mode on an already open dm_dev, being
* careful to leave things as they were if we fail to reopen the
* device and not to touch the existing bdev field in case
* it is accessed concurrently.
*/
static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
struct mapped_device *md)
{
int r;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
struct dm_dev *old_dev, *new_dev;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
old_dev = dd->dm_dev;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
r = dm_get_table_device(md, dd->dm_dev->bdev->bd_dev,
dd->dm_dev->mode | new_mode, &new_dev);
if (r)
return r;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
dd->dm_dev = new_dev;
dm_put_table_device(md, old_dev);
return 0;
}
dm snapshot: disallow the COW and origin devices from being identical Otherwise loading a "snapshot" table using the same device for the origin and COW devices, e.g.: echo "0 20971520 snapshot 253:3 253:3 P 8" | dmsetup create snap will trigger: BUG: unable to handle kernel NULL pointer dereference at 0000000000000098 [ 1958.979934] IP: [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1958.989655] PGD 0 [ 1958.991903] Oops: 0000 [#1] SMP ... [ 1959.059647] CPU: 9 PID: 3556 Comm: dmsetup Tainted: G IO 4.5.0-rc5.snitm+ #150 ... [ 1959.083517] task: ffff8800b9660c80 ti: ffff88032a954000 task.ti: ffff88032a954000 [ 1959.091865] RIP: 0010:[<ffffffffa040efba>] [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.104295] RSP: 0018:ffff88032a957b30 EFLAGS: 00010246 [ 1959.110219] RAX: 0000000000000000 RBX: 0000000000000008 RCX: 0000000000000001 [ 1959.118180] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff880329334a00 [ 1959.126141] RBP: ffff88032a957b50 R08: 0000000000000000 R09: 0000000000000001 [ 1959.134102] R10: 000000000000000a R11: f000000000000000 R12: ffff880330884d80 [ 1959.142061] R13: 0000000000000008 R14: ffffc90001c13088 R15: ffff880330884d80 [ 1959.150021] FS: 00007f8926ba3840(0000) GS:ffff880333440000(0000) knlGS:0000000000000000 [ 1959.159047] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1959.165456] CR2: 0000000000000098 CR3: 000000032f48b000 CR4: 00000000000006e0 [ 1959.173415] Stack: [ 1959.175656] ffffc90001c13040 ffff880329334a00 ffff880330884ed0 ffff88032a957bdc [ 1959.183946] ffff88032a957bb8 ffffffffa040f225 ffff880329334a30 ffff880300000000 [ 1959.192233] ffffffffa04133e0 ffff880329334b30 0000000830884d58 00000000569c58cf [ 1959.200521] Call Trace: [ 1959.203248] [<ffffffffa040f225>] dm_exception_store_create+0x1d5/0x240 [dm_snapshot] [ 1959.211986] [<ffffffffa040d310>] snapshot_ctr+0x140/0x630 [dm_snapshot] [ 1959.219469] [<ffffffffa0005c44>] ? dm_split_args+0x64/0x150 [dm_mod] [ 1959.226656] [<ffffffffa0005ea7>] dm_table_add_target+0x177/0x440 [dm_mod] [ 1959.234328] [<ffffffffa0009203>] table_load+0x143/0x370 [dm_mod] [ 1959.241129] [<ffffffffa00090c0>] ? retrieve_status+0x1b0/0x1b0 [dm_mod] [ 1959.248607] [<ffffffffa0009e35>] ctl_ioctl+0x255/0x4d0 [dm_mod] [ 1959.255307] [<ffffffff813304e2>] ? memzero_explicit+0x12/0x20 [ 1959.261816] [<ffffffffa000a0c3>] dm_ctl_ioctl+0x13/0x20 [dm_mod] [ 1959.268615] [<ffffffff81215eb6>] do_vfs_ioctl+0xa6/0x5c0 [ 1959.274637] [<ffffffff81120d2f>] ? __audit_syscall_entry+0xaf/0x100 [ 1959.281726] [<ffffffff81003176>] ? do_audit_syscall_entry+0x66/0x70 [ 1959.288814] [<ffffffff81216449>] SyS_ioctl+0x79/0x90 [ 1959.294450] [<ffffffff8167e4ae>] entry_SYSCALL_64_fastpath+0x12/0x71 ... [ 1959.323277] RIP [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.333090] RSP <ffff88032a957b30> [ 1959.336978] CR2: 0000000000000098 [ 1959.344121] ---[ end trace b049991ccad1169e ]--- Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1195899 Cc: stable@vger.kernel.org Signed-off-by: Ding Xiang <dingxiang@huawei.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2016-02-02 04:29:18 +00:00
/*
* Convert the path to a device
*/
dev_t dm_get_dev_t(const char *path)
{
dev_t dev;
dm snapshot: disallow the COW and origin devices from being identical Otherwise loading a "snapshot" table using the same device for the origin and COW devices, e.g.: echo "0 20971520 snapshot 253:3 253:3 P 8" | dmsetup create snap will trigger: BUG: unable to handle kernel NULL pointer dereference at 0000000000000098 [ 1958.979934] IP: [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1958.989655] PGD 0 [ 1958.991903] Oops: 0000 [#1] SMP ... [ 1959.059647] CPU: 9 PID: 3556 Comm: dmsetup Tainted: G IO 4.5.0-rc5.snitm+ #150 ... [ 1959.083517] task: ffff8800b9660c80 ti: ffff88032a954000 task.ti: ffff88032a954000 [ 1959.091865] RIP: 0010:[<ffffffffa040efba>] [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.104295] RSP: 0018:ffff88032a957b30 EFLAGS: 00010246 [ 1959.110219] RAX: 0000000000000000 RBX: 0000000000000008 RCX: 0000000000000001 [ 1959.118180] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff880329334a00 [ 1959.126141] RBP: ffff88032a957b50 R08: 0000000000000000 R09: 0000000000000001 [ 1959.134102] R10: 000000000000000a R11: f000000000000000 R12: ffff880330884d80 [ 1959.142061] R13: 0000000000000008 R14: ffffc90001c13088 R15: ffff880330884d80 [ 1959.150021] FS: 00007f8926ba3840(0000) GS:ffff880333440000(0000) knlGS:0000000000000000 [ 1959.159047] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1959.165456] CR2: 0000000000000098 CR3: 000000032f48b000 CR4: 00000000000006e0 [ 1959.173415] Stack: [ 1959.175656] ffffc90001c13040 ffff880329334a00 ffff880330884ed0 ffff88032a957bdc [ 1959.183946] ffff88032a957bb8 ffffffffa040f225 ffff880329334a30 ffff880300000000 [ 1959.192233] ffffffffa04133e0 ffff880329334b30 0000000830884d58 00000000569c58cf [ 1959.200521] Call Trace: [ 1959.203248] [<ffffffffa040f225>] dm_exception_store_create+0x1d5/0x240 [dm_snapshot] [ 1959.211986] [<ffffffffa040d310>] snapshot_ctr+0x140/0x630 [dm_snapshot] [ 1959.219469] [<ffffffffa0005c44>] ? dm_split_args+0x64/0x150 [dm_mod] [ 1959.226656] [<ffffffffa0005ea7>] dm_table_add_target+0x177/0x440 [dm_mod] [ 1959.234328] [<ffffffffa0009203>] table_load+0x143/0x370 [dm_mod] [ 1959.241129] [<ffffffffa00090c0>] ? retrieve_status+0x1b0/0x1b0 [dm_mod] [ 1959.248607] [<ffffffffa0009e35>] ctl_ioctl+0x255/0x4d0 [dm_mod] [ 1959.255307] [<ffffffff813304e2>] ? memzero_explicit+0x12/0x20 [ 1959.261816] [<ffffffffa000a0c3>] dm_ctl_ioctl+0x13/0x20 [dm_mod] [ 1959.268615] [<ffffffff81215eb6>] do_vfs_ioctl+0xa6/0x5c0 [ 1959.274637] [<ffffffff81120d2f>] ? __audit_syscall_entry+0xaf/0x100 [ 1959.281726] [<ffffffff81003176>] ? do_audit_syscall_entry+0x66/0x70 [ 1959.288814] [<ffffffff81216449>] SyS_ioctl+0x79/0x90 [ 1959.294450] [<ffffffff8167e4ae>] entry_SYSCALL_64_fastpath+0x12/0x71 ... [ 1959.323277] RIP [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.333090] RSP <ffff88032a957b30> [ 1959.336978] CR2: 0000000000000098 [ 1959.344121] ---[ end trace b049991ccad1169e ]--- Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1195899 Cc: stable@vger.kernel.org Signed-off-by: Ding Xiang <dingxiang@huawei.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2016-02-02 04:29:18 +00:00
struct block_device *bdev;
bdev = lookup_bdev(path);
if (IS_ERR(bdev))
dev = name_to_dev_t(path);
else {
dev = bdev->bd_dev;
bdput(bdev);
}
return dev;
}
EXPORT_SYMBOL_GPL(dm_get_dev_t);
/*
* Add a device to the list, or just increment the usage count if
* it's already present.
*/
int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
struct dm_dev **result)
{
int r;
dm snapshot: disallow the COW and origin devices from being identical Otherwise loading a "snapshot" table using the same device for the origin and COW devices, e.g.: echo "0 20971520 snapshot 253:3 253:3 P 8" | dmsetup create snap will trigger: BUG: unable to handle kernel NULL pointer dereference at 0000000000000098 [ 1958.979934] IP: [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1958.989655] PGD 0 [ 1958.991903] Oops: 0000 [#1] SMP ... [ 1959.059647] CPU: 9 PID: 3556 Comm: dmsetup Tainted: G IO 4.5.0-rc5.snitm+ #150 ... [ 1959.083517] task: ffff8800b9660c80 ti: ffff88032a954000 task.ti: ffff88032a954000 [ 1959.091865] RIP: 0010:[<ffffffffa040efba>] [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.104295] RSP: 0018:ffff88032a957b30 EFLAGS: 00010246 [ 1959.110219] RAX: 0000000000000000 RBX: 0000000000000008 RCX: 0000000000000001 [ 1959.118180] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff880329334a00 [ 1959.126141] RBP: ffff88032a957b50 R08: 0000000000000000 R09: 0000000000000001 [ 1959.134102] R10: 000000000000000a R11: f000000000000000 R12: ffff880330884d80 [ 1959.142061] R13: 0000000000000008 R14: ffffc90001c13088 R15: ffff880330884d80 [ 1959.150021] FS: 00007f8926ba3840(0000) GS:ffff880333440000(0000) knlGS:0000000000000000 [ 1959.159047] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1959.165456] CR2: 0000000000000098 CR3: 000000032f48b000 CR4: 00000000000006e0 [ 1959.173415] Stack: [ 1959.175656] ffffc90001c13040 ffff880329334a00 ffff880330884ed0 ffff88032a957bdc [ 1959.183946] ffff88032a957bb8 ffffffffa040f225 ffff880329334a30 ffff880300000000 [ 1959.192233] ffffffffa04133e0 ffff880329334b30 0000000830884d58 00000000569c58cf [ 1959.200521] Call Trace: [ 1959.203248] [<ffffffffa040f225>] dm_exception_store_create+0x1d5/0x240 [dm_snapshot] [ 1959.211986] [<ffffffffa040d310>] snapshot_ctr+0x140/0x630 [dm_snapshot] [ 1959.219469] [<ffffffffa0005c44>] ? dm_split_args+0x64/0x150 [dm_mod] [ 1959.226656] [<ffffffffa0005ea7>] dm_table_add_target+0x177/0x440 [dm_mod] [ 1959.234328] [<ffffffffa0009203>] table_load+0x143/0x370 [dm_mod] [ 1959.241129] [<ffffffffa00090c0>] ? retrieve_status+0x1b0/0x1b0 [dm_mod] [ 1959.248607] [<ffffffffa0009e35>] ctl_ioctl+0x255/0x4d0 [dm_mod] [ 1959.255307] [<ffffffff813304e2>] ? memzero_explicit+0x12/0x20 [ 1959.261816] [<ffffffffa000a0c3>] dm_ctl_ioctl+0x13/0x20 [dm_mod] [ 1959.268615] [<ffffffff81215eb6>] do_vfs_ioctl+0xa6/0x5c0 [ 1959.274637] [<ffffffff81120d2f>] ? __audit_syscall_entry+0xaf/0x100 [ 1959.281726] [<ffffffff81003176>] ? do_audit_syscall_entry+0x66/0x70 [ 1959.288814] [<ffffffff81216449>] SyS_ioctl+0x79/0x90 [ 1959.294450] [<ffffffff8167e4ae>] entry_SYSCALL_64_fastpath+0x12/0x71 ... [ 1959.323277] RIP [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.333090] RSP <ffff88032a957b30> [ 1959.336978] CR2: 0000000000000098 [ 1959.344121] ---[ end trace b049991ccad1169e ]--- Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1195899 Cc: stable@vger.kernel.org Signed-off-by: Ding Xiang <dingxiang@huawei.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2016-02-02 04:29:18 +00:00
dev_t dev;
struct dm_dev_internal *dd;
struct dm_table *t = ti->table;
BUG_ON(!t);
dm snapshot: disallow the COW and origin devices from being identical Otherwise loading a "snapshot" table using the same device for the origin and COW devices, e.g.: echo "0 20971520 snapshot 253:3 253:3 P 8" | dmsetup create snap will trigger: BUG: unable to handle kernel NULL pointer dereference at 0000000000000098 [ 1958.979934] IP: [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1958.989655] PGD 0 [ 1958.991903] Oops: 0000 [#1] SMP ... [ 1959.059647] CPU: 9 PID: 3556 Comm: dmsetup Tainted: G IO 4.5.0-rc5.snitm+ #150 ... [ 1959.083517] task: ffff8800b9660c80 ti: ffff88032a954000 task.ti: ffff88032a954000 [ 1959.091865] RIP: 0010:[<ffffffffa040efba>] [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.104295] RSP: 0018:ffff88032a957b30 EFLAGS: 00010246 [ 1959.110219] RAX: 0000000000000000 RBX: 0000000000000008 RCX: 0000000000000001 [ 1959.118180] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff880329334a00 [ 1959.126141] RBP: ffff88032a957b50 R08: 0000000000000000 R09: 0000000000000001 [ 1959.134102] R10: 000000000000000a R11: f000000000000000 R12: ffff880330884d80 [ 1959.142061] R13: 0000000000000008 R14: ffffc90001c13088 R15: ffff880330884d80 [ 1959.150021] FS: 00007f8926ba3840(0000) GS:ffff880333440000(0000) knlGS:0000000000000000 [ 1959.159047] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1959.165456] CR2: 0000000000000098 CR3: 000000032f48b000 CR4: 00000000000006e0 [ 1959.173415] Stack: [ 1959.175656] ffffc90001c13040 ffff880329334a00 ffff880330884ed0 ffff88032a957bdc [ 1959.183946] ffff88032a957bb8 ffffffffa040f225 ffff880329334a30 ffff880300000000 [ 1959.192233] ffffffffa04133e0 ffff880329334b30 0000000830884d58 00000000569c58cf [ 1959.200521] Call Trace: [ 1959.203248] [<ffffffffa040f225>] dm_exception_store_create+0x1d5/0x240 [dm_snapshot] [ 1959.211986] [<ffffffffa040d310>] snapshot_ctr+0x140/0x630 [dm_snapshot] [ 1959.219469] [<ffffffffa0005c44>] ? dm_split_args+0x64/0x150 [dm_mod] [ 1959.226656] [<ffffffffa0005ea7>] dm_table_add_target+0x177/0x440 [dm_mod] [ 1959.234328] [<ffffffffa0009203>] table_load+0x143/0x370 [dm_mod] [ 1959.241129] [<ffffffffa00090c0>] ? retrieve_status+0x1b0/0x1b0 [dm_mod] [ 1959.248607] [<ffffffffa0009e35>] ctl_ioctl+0x255/0x4d0 [dm_mod] [ 1959.255307] [<ffffffff813304e2>] ? memzero_explicit+0x12/0x20 [ 1959.261816] [<ffffffffa000a0c3>] dm_ctl_ioctl+0x13/0x20 [dm_mod] [ 1959.268615] [<ffffffff81215eb6>] do_vfs_ioctl+0xa6/0x5c0 [ 1959.274637] [<ffffffff81120d2f>] ? __audit_syscall_entry+0xaf/0x100 [ 1959.281726] [<ffffffff81003176>] ? do_audit_syscall_entry+0x66/0x70 [ 1959.288814] [<ffffffff81216449>] SyS_ioctl+0x79/0x90 [ 1959.294450] [<ffffffff8167e4ae>] entry_SYSCALL_64_fastpath+0x12/0x71 ... [ 1959.323277] RIP [<ffffffffa040efba>] dm_exception_store_set_chunk_size+0x7a/0x110 [dm_snapshot] [ 1959.333090] RSP <ffff88032a957b30> [ 1959.336978] CR2: 0000000000000098 [ 1959.344121] ---[ end trace b049991ccad1169e ]--- Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1195899 Cc: stable@vger.kernel.org Signed-off-by: Ding Xiang <dingxiang@huawei.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2016-02-02 04:29:18 +00:00
dev = dm_get_dev_t(path);
if (!dev)
return -ENODEV;
dd = find_device(&t->devices, dev);
if (!dd) {
dd = kmalloc(sizeof(*dd), GFP_KERNEL);
if (!dd)
return -ENOMEM;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
if ((r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev))) {
kfree(dd);
return r;
}
refcount_set(&dd->count, 1);
list_add(&dd->list, &t->devices);
goto out;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
} else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) {
r = upgrade_mode(dd, mode, t->md);
if (r)
return r;
}
refcount_inc(&dd->count);
out:
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
*result = dd->dm_dev;
return 0;
}
EXPORT_SYMBOL(dm_get_device);
static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct queue_limits *limits = data;
struct block_device *bdev = dev->bdev;
struct request_queue *q = bdev_get_queue(bdev);
char b[BDEVNAME_SIZE];
if (unlikely(!q)) {
DMWARN("%s: Cannot set limits for nonexistent device %s",
dm_device_name(ti->table->md), bdevname(bdev, b));
return 0;
}
if (blk_stack_limits(limits, &q->limits,
get_start_sect(bdev) + start) < 0)
DMWARN("%s: adding target device %s caused an alignment inconsistency: "
"physical_block_size=%u, logical_block_size=%u, "
"alignment_offset=%u, start=%llu",
dm_device_name(ti->table->md), bdevname(bdev, b),
q->limits.physical_block_size,
q->limits.logical_block_size,
q->limits.alignment_offset,
(unsigned long long) start << SECTOR_SHIFT);
return 0;
}
/*
* Decrement a device's use count and remove it if necessary.
*/
void dm_put_device(struct dm_target *ti, struct dm_dev *d)
{
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
int found = 0;
struct list_head *devices = &ti->table->devices;
struct dm_dev_internal *dd;
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
list_for_each_entry(dd, devices, list) {
if (dd->dm_dev == d) {
found = 1;
break;
}
}
if (!found) {
DMWARN("%s: device %s not in table devices list",
dm_device_name(ti->table->md), d->name);
return;
}
if (refcount_dec_and_test(&dd->count)) {
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
dm_put_table_device(ti->table->md, d);
list_del(&dd->list);
kfree(dd);
}
}
EXPORT_SYMBOL(dm_put_device);
/*
* Checks to see if the target joins onto the end of the table.
*/
static int adjoin(struct dm_table *table, struct dm_target *ti)
{
struct dm_target *prev;
if (!table->num_targets)
return !ti->begin;
prev = &table->targets[table->num_targets - 1];
return (ti->begin == (prev->begin + prev->len));
}
/*
* Used to dynamically allocate the arg array.
*
* We do first allocation with GFP_NOIO because dm-mpath and dm-thin must
* process messages even if some device is suspended. These messages have a
* small fixed number of arguments.
*
* On the other hand, dm-switch needs to process bulk data using messages and
* excessive use of GFP_NOIO could cause trouble.
*/
static char **realloc_argv(unsigned *size, char **old_argv)
{
char **argv;
unsigned new_size;
gfp_t gfp;
if (*size) {
new_size = *size * 2;
gfp = GFP_KERNEL;
} else {
new_size = 8;
gfp = GFP_NOIO;
}
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 20:55:00 +00:00
argv = kmalloc_array(new_size, sizeof(*argv), gfp);
if (argv && old_argv) {
memcpy(argv, old_argv, *size * sizeof(*argv));
*size = new_size;
}
kfree(old_argv);
return argv;
}
/*
* Destructively splits up the argument list to pass to ctr.
*/
int dm_split_args(int *argc, char ***argvp, char *input)
{
char *start, *end = input, *out, **argv = NULL;
unsigned array_size = 0;
*argc = 0;
if (!input) {
*argvp = NULL;
return 0;
}
argv = realloc_argv(&array_size, argv);
if (!argv)
return -ENOMEM;
while (1) {
/* Skip whitespace */
tree-wide: convert open calls to remove spaces to skip_spaces() lib function Makes use of skip_spaces() defined in lib/string.c for removing leading spaces from strings all over the tree. It decreases lib.a code size by 47 bytes and reuses the function tree-wide: text data bss dec hex filename 64688 584 592 65864 10148 (TOTALS-BEFORE) 64641 584 592 65817 10119 (TOTALS-AFTER) Also, while at it, if we see (*str && isspace(*str)), we can be sure to remove the first condition (*str) as the second one (isspace(*str)) also evaluates to 0 whenever *str == 0, making it redundant. In other words, "a char equals zero is never a space". Julia Lawall tried the semantic patch (http://coccinelle.lip6.fr) below, and found occurrences of this pattern on 3 more files: drivers/leds/led-class.c drivers/leds/ledtrig-timer.c drivers/video/output.c @@ expression str; @@ ( // ignore skip_spaces cases while (*str && isspace(*str)) { \(str++;\|++str;\) } | - *str && isspace(*str) ) Signed-off-by: André Goddard Rosa <andre.goddard@gmail.com> Cc: Julia Lawall <julia@diku.dk> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Richard Purdie <rpurdie@rpsys.net> Cc: Neil Brown <neilb@suse.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Henrique de Moraes Holschuh <hmh@hmh.eng.br> Cc: David Howells <dhowells@redhat.com> Cc: <linux-ext4@vger.kernel.org> Cc: Samuel Ortiz <samuel@sortiz.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Takashi Iwai <tiwai@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 02:01:06 +00:00
start = skip_spaces(end);
if (!*start)
break; /* success, we hit the end */
/* 'out' is used to remove any back-quotes */
end = out = start;
while (*end) {
/* Everything apart from '\0' can be quoted */
if (*end == '\\' && *(end + 1)) {
*out++ = *(end + 1);
end += 2;
continue;
}
if (isspace(*end))
break; /* end of token */
*out++ = *end++;
}
/* have we already filled the array ? */
if ((*argc + 1) > array_size) {
argv = realloc_argv(&array_size, argv);
if (!argv)
return -ENOMEM;
}
/* we know this is whitespace */
if (*end)
end++;
/* terminate the string and put it in the array */
*out = '\0';
argv[*argc] = start;
(*argc)++;
}
*argvp = argv;
return 0;
}
/*
* Impose necessary and sufficient conditions on a devices's table such
* that any incoming bio which respects its logical_block_size can be
* processed successfully. If it falls across the boundary between
* two or more targets, the size of each piece it gets split into must
* be compatible with the logical_block_size of the target processing it.
*/
static int validate_hardware_logical_block_alignment(struct dm_table *table,
struct queue_limits *limits)
{
/*
* This function uses arithmetic modulo the logical_block_size
* (in units of 512-byte sectors).
*/
unsigned short device_logical_block_size_sects =
limits->logical_block_size >> SECTOR_SHIFT;
/*
* Offset of the start of the next table entry, mod logical_block_size.
*/
unsigned short next_target_start = 0;
/*
* Given an aligned bio that extends beyond the end of a
* target, how many sectors must the next target handle?
*/
unsigned short remaining = 0;
treewide: Remove uninitialized_var() usage Using uninitialized_var() is dangerous as it papers over real bugs[1] (or can in the future), and suppresses unrelated compiler warnings (e.g. "unused variable"). If the compiler thinks it is uninitialized, either simply initialize the variable or make compiler changes. In preparation for removing[2] the[3] macro[4], remove all remaining needless uses with the following script: git grep '\buninitialized_var\b' | cut -d: -f1 | sort -u | \ xargs perl -pi -e \ 's/\buninitialized_var\(([^\)]+)\)/\1/g; s:\s*/\* (GCC be quiet|to make compiler happy) \*/$::g;' drivers/video/fbdev/riva/riva_hw.c was manually tweaked to avoid pathological white-space. No outstanding warnings were found building allmodconfig with GCC 9.3.0 for x86_64, i386, arm64, arm, powerpc, powerpc64le, s390x, mips, sparc64, alpha, and m68k. [1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/ [2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/ [3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/ [4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/ Reviewed-by: Leon Romanovsky <leonro@mellanox.com> # drivers/infiniband and mlx4/mlx5 Acked-by: Jason Gunthorpe <jgg@mellanox.com> # IB Acked-by: Kalle Valo <kvalo@codeaurora.org> # wireless drivers Reviewed-by: Chao Yu <yuchao0@huawei.com> # erofs Signed-off-by: Kees Cook <keescook@chromium.org>
2020-06-03 20:09:38 +00:00
struct dm_target *ti;
struct queue_limits ti_limits;
unsigned i;
/*
* Check each entry in the table in turn.
*/
for (i = 0; i < dm_table_get_num_targets(table); i++) {
ti = dm_table_get_target(table, i);
blk_set_stacking_limits(&ti_limits);
/* combine all target devices' limits */
if (ti->type->iterate_devices)
ti->type->iterate_devices(ti, dm_set_device_limits,
&ti_limits);
/*
* If the remaining sectors fall entirely within this
* table entry are they compatible with its logical_block_size?
*/
if (remaining < ti->len &&
remaining & ((ti_limits.logical_block_size >>
SECTOR_SHIFT) - 1))
break; /* Error */
next_target_start =
(unsigned short) ((next_target_start + ti->len) &
(device_logical_block_size_sects - 1));
remaining = next_target_start ?
device_logical_block_size_sects - next_target_start : 0;
}
if (remaining) {
DMWARN("%s: table line %u (start sect %llu len %llu) "
"not aligned to h/w logical block size %u",
dm_device_name(table->md), i,
(unsigned long long) ti->begin,
(unsigned long long) ti->len,
limits->logical_block_size);
return -EINVAL;
}
return 0;
}
int dm_table_add_target(struct dm_table *t, const char *type,
sector_t start, sector_t len, char *params)
{
int r = -EINVAL, argc;
char **argv;
struct dm_target *tgt;
if (t->singleton) {
DMERR("%s: target type %s must appear alone in table",
dm_device_name(t->md), t->targets->type->name);
return -EINVAL;
}
BUG_ON(t->num_targets >= t->num_allocated);
tgt = t->targets + t->num_targets;
memset(tgt, 0, sizeof(*tgt));
if (!len) {
DMERR("%s: zero-length target", dm_device_name(t->md));
return -EINVAL;
}
tgt->type = dm_get_target_type(type);
if (!tgt->type) {
DMERR("%s: %s: unknown target type", dm_device_name(t->md), type);
return -EINVAL;
}
if (dm_target_needs_singleton(tgt->type)) {
if (t->num_targets) {
tgt->error = "singleton target type must appear alone in table";
goto bad;
}
t->singleton = true;
}
if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
tgt->error = "target type may not be included in a read-only table";
goto bad;
}
if (t->immutable_target_type) {
if (t->immutable_target_type != tgt->type) {
tgt->error = "immutable target type cannot be mixed with other target types";
goto bad;
}
} else if (dm_target_is_immutable(tgt->type)) {
if (t->num_targets) {
tgt->error = "immutable target type cannot be mixed with other target types";
goto bad;
}
t->immutable_target_type = tgt->type;
}
if (dm_target_has_integrity(tgt->type))
t->integrity_added = 1;
tgt->table = t;
tgt->begin = start;
tgt->len = len;
tgt->error = "Unknown error";
/*
* Does this target adjoin the previous one ?
*/
if (!adjoin(t, tgt)) {
tgt->error = "Gap in table";
goto bad;
}
r = dm_split_args(&argc, &argv, params);
if (r) {
tgt->error = "couldn't split parameters (insufficient memory)";
goto bad;
}
r = tgt->type->ctr(tgt, argc, argv);
kfree(argv);
if (r)
goto bad;
t->highs[t->num_targets++] = tgt->begin + tgt->len - 1;
if (!tgt->num_discard_bios && tgt->discards_supported)
DMWARN("%s: %s: ignoring discards_supported because num_discard_bios is zero.",
dm_device_name(t->md), type);
return 0;
bad:
DMERR("%s: %s: %s", dm_device_name(t->md), type, tgt->error);
dm_put_target_type(tgt->type);
return r;
}
/*
* Target argument parsing helpers.
*/
static int validate_next_arg(const struct dm_arg *arg,
struct dm_arg_set *arg_set,
unsigned *value, char **error, unsigned grouped)
{
const char *arg_str = dm_shift_arg(arg_set);
char dummy;
if (!arg_str ||
(sscanf(arg_str, "%u%c", value, &dummy) != 1) ||
(*value < arg->min) ||
(*value > arg->max) ||
(grouped && arg_set->argc < *value)) {
*error = arg->error;
return -EINVAL;
}
return 0;
}
int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set,
unsigned *value, char **error)
{
return validate_next_arg(arg, arg_set, value, error, 0);
}
EXPORT_SYMBOL(dm_read_arg);
int dm_read_arg_group(const struct dm_arg *arg, struct dm_arg_set *arg_set,
unsigned *value, char **error)
{
return validate_next_arg(arg, arg_set, value, error, 1);
}
EXPORT_SYMBOL(dm_read_arg_group);
const char *dm_shift_arg(struct dm_arg_set *as)
{
char *r;
if (as->argc) {
as->argc--;
r = *as->argv;
as->argv++;
return r;
}
return NULL;
}
EXPORT_SYMBOL(dm_shift_arg);
void dm_consume_args(struct dm_arg_set *as, unsigned num_args)
{
BUG_ON(as->argc < num_args);
as->argc -= num_args;
as->argv += num_args;
}
EXPORT_SYMBOL(dm_consume_args);
static bool __table_type_bio_based(enum dm_queue_mode table_type)
{
return (table_type == DM_TYPE_BIO_BASED ||
table_type == DM_TYPE_DAX_BIO_BASED);
}
static bool __table_type_request_based(enum dm_queue_mode table_type)
{
return table_type == DM_TYPE_REQUEST_BASED;
}
void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
{
t->type = type;
}
EXPORT_SYMBOL_GPL(dm_table_set_type);
dax: Arrange for dax_supported check to span multiple devices Pankaj reports that starting with commit ad428cdb525a "dax: Check the end of the block-device capacity with dax_direct_access()" device-mapper no longer allows dax operation. This results from the stricter checks in __bdev_dax_supported() that validate that the start and end of a block-device map to the same 'pagemap' instance. Teach the dax-core and device-mapper to validate the 'pagemap' on a per-target basis. This is accomplished by refactoring the bdev_dax_supported() internals into generic_fsdax_supported() which takes a sector range to validate. Consequently generic_fsdax_supported() is suitable to be used in a device-mapper ->iterate_devices() callback. A new ->dax_supported() operation is added to allow composite devices to split and route upper-level bdev_dax_supported() requests. Fixes: ad428cdb525a ("dax: Check the end of the block-device...") Cc: <stable@vger.kernel.org> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Reviewed-by: Jan Kara <jack@suse.cz> Reported-by: Pankaj Gupta <pagupta@redhat.com> Reviewed-by: Pankaj Gupta <pagupta@redhat.com> Tested-by: Pankaj Gupta <pagupta@redhat.com> Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-05-16 20:26:29 +00:00
/* validate the dax capability of the target device span */
int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
int blocksize = *(int *) data, id;
bool rc;
dax: Arrange for dax_supported check to span multiple devices Pankaj reports that starting with commit ad428cdb525a "dax: Check the end of the block-device capacity with dax_direct_access()" device-mapper no longer allows dax operation. This results from the stricter checks in __bdev_dax_supported() that validate that the start and end of a block-device map to the same 'pagemap' instance. Teach the dax-core and device-mapper to validate the 'pagemap' on a per-target basis. This is accomplished by refactoring the bdev_dax_supported() internals into generic_fsdax_supported() which takes a sector range to validate. Consequently generic_fsdax_supported() is suitable to be used in a device-mapper ->iterate_devices() callback. A new ->dax_supported() operation is added to allow composite devices to split and route upper-level bdev_dax_supported() requests. Fixes: ad428cdb525a ("dax: Check the end of the block-device...") Cc: <stable@vger.kernel.org> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Reviewed-by: Jan Kara <jack@suse.cz> Reported-by: Pankaj Gupta <pagupta@redhat.com> Reviewed-by: Pankaj Gupta <pagupta@redhat.com> Tested-by: Pankaj Gupta <pagupta@redhat.com> Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-05-16 20:26:29 +00:00
id = dax_read_lock();
rc = dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
dax_read_unlock(id);
return rc;
}
/* Check devices support synchronous DAX */
static int device_dax_synchronous(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
return dev->dax_dev && dax_synchronous(dev->dax_dev);
}
bool dm_table_supports_dax(struct dm_table *t,
iterate_devices_callout_fn iterate_fn, int *blocksize)
{
struct dm_target *ti;
unsigned i;
/* Ensure that all targets support DAX. */
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!ti->type->direct_access)
return false;
if (!ti->type->iterate_devices ||
!ti->type->iterate_devices(ti, iterate_fn, blocksize))
return false;
}
return true;
}
static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct block_device *bdev = dev->bdev;
struct request_queue *q = bdev_get_queue(bdev);
/* request-based cannot stack on partitions! */
if (bdev_is_partition(bdev))
return false;
return queue_is_mq(q);
}
static int dm_table_determine_type(struct dm_table *t)
{
unsigned i;
unsigned bio_based = 0, request_based = 0, hybrid = 0;
struct dm_target *tgt;
struct list_head *devices = dm_table_get_devices(t);
enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
int page_size = PAGE_SIZE;
if (t->type != DM_TYPE_NONE) {
/* target already set the table's type */
if (t->type == DM_TYPE_BIO_BASED) {
/* possibly upgrade to a variant of bio-based */
goto verify_bio_based;
}
BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
goto verify_rq_based;
}
for (i = 0; i < t->num_targets; i++) {
tgt = t->targets + i;
if (dm_target_hybrid(tgt))
hybrid = 1;
else if (dm_target_request_based(tgt))
request_based = 1;
else
bio_based = 1;
if (bio_based && request_based) {
DMERR("Inconsistent table: different target types"
" can't be mixed up");
return -EINVAL;
}
}
if (hybrid && !bio_based && !request_based) {
/*
* The targets can work either way.
* Determine the type from the live device.
* Default to bio-based if device is new.
*/
if (__table_type_request_based(live_md_type))
request_based = 1;
else
bio_based = 1;
}
if (bio_based) {
verify_bio_based:
/* We must use this table as bio-based */
t->type = DM_TYPE_BIO_BASED;
if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
(list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
t->type = DM_TYPE_DAX_BIO_BASED;
}
return 0;
}
BUG_ON(!request_based); /* No targets in this table */
t->type = DM_TYPE_REQUEST_BASED;
verify_rq_based:
/*
* Request-based dm supports only tables that have a single target now.
* To support multiple targets, request splitting support is needed,
* and that needs lots of changes in the block-layer.
* (e.g. request completion process for partial completion.)
*/
if (t->num_targets > 1) {
DMERR("request-based DM doesn't support multiple targets");
return -EINVAL;
}
if (list_empty(devices)) {
int srcu_idx;
struct dm_table *live_table = dm_get_live_table(t->md, &srcu_idx);
/* inherit live table's type */
if (live_table)
t->type = live_table->type;
dm_put_live_table(t->md, srcu_idx);
return 0;
}
tgt = dm_table_get_immutable_target(t);
if (!tgt) {
DMERR("table load rejected: immutable target is required");
return -EINVAL;
} else if (tgt->max_io_len) {
DMERR("table load rejected: immutable target that splits IO is not supported");
return -EINVAL;
}
/* Non-request-stackable devices can't be used for request-based dm */
if (!tgt->type->iterate_devices ||
!tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) {
DMERR("table load rejected: including non-request-stackable devices");
return -EINVAL;
2014-12-18 02:08:12 +00:00
}
return 0;
}
enum dm_queue_mode dm_table_get_type(struct dm_table *t)
{
return t->type;
}
struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
{
return t->immutable_target_type;
}
struct dm_target *dm_table_get_immutable_target(struct dm_table *t)
{
/* Immutable target is implicitly a singleton */
if (t->num_targets > 1 ||
!dm_target_is_immutable(t->targets[0].type))
return NULL;
return t->targets;
}
struct dm_target *dm_table_get_wildcard_target(struct dm_table *t)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (dm_target_is_wildcard(ti->type))
return ti;
}
return NULL;
}
bool dm_table_bio_based(struct dm_table *t)
{
return __table_type_bio_based(dm_table_get_type(t));
}
bool dm_table_request_based(struct dm_table *t)
{
return __table_type_request_based(dm_table_get_type(t));
2014-12-18 02:08:12 +00:00
}
static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
{
enum dm_queue_mode type = dm_table_get_type(t);
unsigned per_io_data_size = 0;
unsigned min_pool_size = 0;
struct dm_target *ti;
unsigned i;
if (unlikely(type == DM_TYPE_NONE)) {
DMWARN("no table type is set, can't allocate mempools");
return -EINVAL;
}
if (__table_type_bio_based(type))
for (i = 0; i < t->num_targets; i++) {
ti = t->targets + i;
per_io_data_size = max(per_io_data_size, ti->per_io_data_size);
min_pool_size = max(min_pool_size, ti->num_flush_bios);
}
t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported,
per_io_data_size, min_pool_size);
if (!t->mempools)
return -ENOMEM;
return 0;
}
void dm_table_free_md_mempools(struct dm_table *t)
{
dm_free_md_mempools(t->mempools);
t->mempools = NULL;
}
struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t)
{
return t->mempools;
}
static int setup_indexes(struct dm_table *t)
{
int i;
unsigned int total = 0;
sector_t *indexes;
/* allocate the space for *all* the indexes */
for (i = t->depth - 2; i >= 0; i--) {
t->counts[i] = dm_div_up(t->counts[i + 1], CHILDREN_PER_NODE);
total += t->counts[i];
}
indexes = (sector_t *) dm_vcalloc(total, (unsigned long) NODE_SIZE);
if (!indexes)
return -ENOMEM;
/* set up internal nodes, bottom-up */
for (i = t->depth - 2; i >= 0; i--) {
t->index[i] = indexes;
indexes += (KEYS_PER_NODE * t->counts[i]);
setup_btree_index(i, t);
}
return 0;
}
/*
* Builds the btree to index the map.
*/
static int dm_table_build_index(struct dm_table *t)
{
int r = 0;
unsigned int leaf_nodes;
/* how many indexes will the btree have ? */
leaf_nodes = dm_div_up(t->num_targets, KEYS_PER_NODE);
t->depth = 1 + int_log(leaf_nodes, CHILDREN_PER_NODE);
/* leaf layer has already been set up */
t->counts[t->depth - 1] = leaf_nodes;
t->index[t->depth - 1] = t->highs;
if (t->depth >= 2)
r = setup_indexes(t);
return r;
}
static bool integrity_profile_exists(struct gendisk *disk)
{
return !!blk_get_integrity(disk);
}
/*
* Get a disk whose integrity profile reflects the table's profile.
* Returns NULL if integrity support was inconsistent or unavailable.
*/
static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t)
{
struct list_head *devices = dm_table_get_devices(t);
struct dm_dev_internal *dd = NULL;
struct gendisk *prev_disk = NULL, *template_disk = NULL;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
struct dm_target *ti = dm_table_get_target(t, i);
if (!dm_target_passes_integrity(ti->type))
goto no_integrity;
}
list_for_each_entry(dd, devices, list) {
dm: allow active and inactive tables to share dm_devs Until this change, when loading a new DM table, DM core would re-open all of the devices in the DM table. Now, DM core will avoid redundant device opens (and closes when destroying the old table) if the old table already has a device open using the same mode. This is achieved by managing reference counts on the table_devices that DM core now stores in the mapped_device structure (rather than in the dm_table structure). So a mapped_device's active and inactive dm_tables' dm_dev lists now just point to the dm_devs stored in the mapped_device's table_devices list. This improvement in DM core's device reference counting has the side-effect of fixing a long-standing limitation of the multipath target: a DM multipath table couldn't include any paths that were unusable (failed). For example: if all paths have failed and you add a new, working, path to the table; you can't use it since the table load would fail due to it still containing failed paths. Now a re-load of a multipath table can include failed devices and when those devices become active again they can be used instantly. The device list code in dm.c isn't a straight copy/paste from the code in dm-table.c, but it's very close (aside from some variable renames). One subtle difference is that find_table_device for the tables_devices list will only match devices with the same name and mode. This is because we don't want to upgrade a device's mode in the active table when an inactive table is loaded. Access to the mapped_device structure's tables_devices list requires a mutex (tables_devices_lock), so that tables cannot be created and destroyed concurrently. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-08-13 18:53:43 +00:00
template_disk = dd->dm_dev->bdev->bd_disk;
if (!integrity_profile_exists(template_disk))
goto no_integrity;
else if (prev_disk &&
blk_integrity_compare(prev_disk, template_disk) < 0)
goto no_integrity;
prev_disk = template_disk;
}
return template_disk;
no_integrity:
if (prev_disk)
DMWARN("%s: integrity not set: %s and %s profile mismatch",
dm_device_name(t->md),
prev_disk->disk_name,
template_disk->disk_name);
return NULL;
}
/*
* Register the mapped device for blk_integrity support if the
* underlying devices have an integrity profile. But all devices may
* not have matching profiles (checking all devices isn't reliable
* during table load because this table may use other DM device(s) which
* must be resumed before they will have an initialized integity
* profile). Consequently, stacked DM devices force a 2 stage integrity
* profile validation: First pass during table load, final pass during
* resume.
*/
static int dm_table_register_integrity(struct dm_table *t)
{
struct mapped_device *md = t->md;
struct gendisk *template_disk = NULL;
/* If target handles integrity itself do not register it here. */
if (t->integrity_added)
return 0;
template_disk = dm_table_get_integrity_disk(t);
if (!template_disk)
return 0;
if (!integrity_profile_exists(dm_disk(md))) {
t->integrity_supported = true;
/*
* Register integrity profile during table load; we can do
* this because the final profile must match during resume.
*/
blk_integrity_register(dm_disk(md),
blk_get_integrity(template_disk));
return 0;
}
/*
* If DM device already has an initialized integrity
* profile the new profile should not conflict.
*/
if (blk_integrity_compare(dm_disk(md), template_disk) < 0) {
DMWARN("%s: conflict with existing integrity profile: "
"%s profile mismatch",
dm_device_name(t->md),
template_disk->disk_name);
return 1;
}
/* Preserve existing integrity profile */
t->integrity_supported = true;
return 0;
}
/*
* Prepares the table for use by building the indices,
* setting the type, and allocating mempools.
*/
int dm_table_complete(struct dm_table *t)
{
int r;
r = dm_table_determine_type(t);
if (r) {
DMERR("unable to determine table type");
return r;
}
r = dm_table_build_index(t);
if (r) {
DMERR("unable to build btrees");
return r;
}
r = dm_table_register_integrity(t);
if (r) {
DMERR("could not register integrity profile.");
return r;
}
r = dm_table_alloc_md_mempools(t, t->md);
if (r)
DMERR("unable to allocate mempools");
return r;
}
static DEFINE_MUTEX(_event_lock);
void dm_table_event_callback(struct dm_table *t,
void (*fn)(void *), void *context)
{
mutex_lock(&_event_lock);
t->event_fn = fn;
t->event_context = context;
mutex_unlock(&_event_lock);
}
void dm_table_event(struct dm_table *t)
{
/*
* You can no longer call dm_table_event() from interrupt
* context, use a bottom half instead.
*/
BUG_ON(in_interrupt());
mutex_lock(&_event_lock);
if (t->event_fn)
t->event_fn(t->event_context);
mutex_unlock(&_event_lock);
}
EXPORT_SYMBOL(dm_table_event);
inline sector_t dm_table_get_size(struct dm_table *t)
{
return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0;
}
EXPORT_SYMBOL(dm_table_get_size);
struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index)
{
if (index >= t->num_targets)
return NULL;
return t->targets + index;
}
/*
* Search the btree for the correct target.
*
* Caller should check returned pointer for NULL
* to trap I/O beyond end of device.
*/
struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
{
unsigned int l, n = 0, k = 0;
sector_t *node;
if (unlikely(sector >= dm_table_get_size(t)))
return NULL;
for (l = 0; l < t->depth; l++) {
n = get_child(n, k);
node = get_node(t, l, n);
for (k = 0; k < KEYS_PER_NODE; k++)
if (node[k] >= sector)
break;
}
return &t->targets[(KEYS_PER_NODE * n) + k];
}
static int count_device(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
unsigned *num_devices = data;
(*num_devices)++;
return 0;
}
/*
* Check whether a table has no data devices attached using each
* target's iterate_devices method.
* Returns false if the result is unknown because a target doesn't
* support iterate_devices.
*/
bool dm_table_has_no_data_devices(struct dm_table *table)
{
struct dm_target *ti;
unsigned i, num_devices;
for (i = 0; i < dm_table_get_num_targets(table); i++) {
ti = dm_table_get_target(table, i);
if (!ti->type->iterate_devices)
return false;
num_devices = 0;
ti->type->iterate_devices(ti, count_device, &num_devices);
if (num_devices)
return false;
}
return true;
}
dm table: add zoned block devices validation 1) Introduce DM_TARGET_ZONED_HM feature flag: The target drivers currently available will not operate correctly if a table target maps onto a host-managed zoned block device. To avoid problems, introduce the new feature flag DM_TARGET_ZONED_HM to allow a target to explicitly state that it supports host-managed zoned block devices. This feature is checked for all targets in a table if any of the table's block devices are host-managed. Note that as host-aware zoned block devices are backward compatible with regular block devices, they can be used by any of the current target types. This new feature is thus restricted to host-managed zoned block devices. 2) Check device area zone alignment: If a target maps to a zoned block device, check that the device area is aligned on zone boundaries to avoid problems with REQ_OP_ZONE_RESET operations (resetting a partially mapped sequential zone would not be possible). This also facilitates the processing of zone report with REQ_OP_ZONE_REPORT bios. 3) Check block devices zone model compatibility When setting the DM device's queue limits, several possibilities exists for zoned block devices: 1) The DM target driver may want to expose a different zone model (e.g. host-managed device emulation or regular block device on top of host-managed zoned block devices) 2) Expose the underlying zone model of the devices as-is To allow both cases, the underlying block device zone model must be set in the target limits in dm_set_device_limits() and the compatibility of all devices checked similarly to the logical block size alignment. For this last check, introduce validate_hardware_zoned_model() to check that all targets of a table have the same zone model and that the zone size of the target devices are equal. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [Mike Snitzer refactored Damien's original work to simplify the code] Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2017-05-08 23:40:43 +00:00
static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
enum blk_zoned_model *zoned_model = data;
return q && blk_queue_zoned_model(q) == *zoned_model;
}
static bool dm_table_supports_zoned_model(struct dm_table *t,
enum blk_zoned_model zoned_model)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (zoned_model == BLK_ZONED_HM &&
!dm_target_supports_zoned_hm(ti->type))
return false;
if (!ti->type->iterate_devices ||
!ti->type->iterate_devices(ti, device_is_zoned_model, &zoned_model))
return false;
}
return true;
}
static int device_matches_zone_sectors(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
unsigned int *zone_sectors = data;
return q && blk_queue_zone_sectors(q) == *zone_sectors;
}
static bool dm_table_matches_zone_sectors(struct dm_table *t,
unsigned int zone_sectors)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!ti->type->iterate_devices ||
!ti->type->iterate_devices(ti, device_matches_zone_sectors, &zone_sectors))
return false;
}
return true;
}
static int validate_hardware_zoned_model(struct dm_table *table,
enum blk_zoned_model zoned_model,
unsigned int zone_sectors)
{
if (zoned_model == BLK_ZONED_NONE)
return 0;
if (!dm_table_supports_zoned_model(table, zoned_model)) {
DMERR("%s: zoned model is not consistent across all devices",
dm_device_name(table->md));
return -EINVAL;
}
/* Check zone size validity and compatibility */
if (!zone_sectors || !is_power_of_2(zone_sectors))
return -EINVAL;
if (!dm_table_matches_zone_sectors(table, zone_sectors)) {
DMERR("%s: zone sectors is not consistent across all devices",
dm_device_name(table->md));
return -EINVAL;
}
return 0;
}
/*
* Establish the new table's queue_limits and validate them.
*/
int dm_calculate_queue_limits(struct dm_table *table,
struct queue_limits *limits)
{
struct dm_target *ti;
struct queue_limits ti_limits;
unsigned i;
dm table: add zoned block devices validation 1) Introduce DM_TARGET_ZONED_HM feature flag: The target drivers currently available will not operate correctly if a table target maps onto a host-managed zoned block device. To avoid problems, introduce the new feature flag DM_TARGET_ZONED_HM to allow a target to explicitly state that it supports host-managed zoned block devices. This feature is checked for all targets in a table if any of the table's block devices are host-managed. Note that as host-aware zoned block devices are backward compatible with regular block devices, they can be used by any of the current target types. This new feature is thus restricted to host-managed zoned block devices. 2) Check device area zone alignment: If a target maps to a zoned block device, check that the device area is aligned on zone boundaries to avoid problems with REQ_OP_ZONE_RESET operations (resetting a partially mapped sequential zone would not be possible). This also facilitates the processing of zone report with REQ_OP_ZONE_REPORT bios. 3) Check block devices zone model compatibility When setting the DM device's queue limits, several possibilities exists for zoned block devices: 1) The DM target driver may want to expose a different zone model (e.g. host-managed device emulation or regular block device on top of host-managed zoned block devices) 2) Expose the underlying zone model of the devices as-is To allow both cases, the underlying block device zone model must be set in the target limits in dm_set_device_limits() and the compatibility of all devices checked similarly to the logical block size alignment. For this last check, introduce validate_hardware_zoned_model() to check that all targets of a table have the same zone model and that the zone size of the target devices are equal. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [Mike Snitzer refactored Damien's original work to simplify the code] Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2017-05-08 23:40:43 +00:00
enum blk_zoned_model zoned_model = BLK_ZONED_NONE;
unsigned int zone_sectors = 0;
blk_set_stacking_limits(limits);
for (i = 0; i < dm_table_get_num_targets(table); i++) {
blk_set_stacking_limits(&ti_limits);
ti = dm_table_get_target(table, i);
if (!ti->type->iterate_devices)
goto combine_limits;
/*
* Combine queue limits of all the devices this target uses.
*/
ti->type->iterate_devices(ti, dm_set_device_limits,
&ti_limits);
dm table: add zoned block devices validation 1) Introduce DM_TARGET_ZONED_HM feature flag: The target drivers currently available will not operate correctly if a table target maps onto a host-managed zoned block device. To avoid problems, introduce the new feature flag DM_TARGET_ZONED_HM to allow a target to explicitly state that it supports host-managed zoned block devices. This feature is checked for all targets in a table if any of the table's block devices are host-managed. Note that as host-aware zoned block devices are backward compatible with regular block devices, they can be used by any of the current target types. This new feature is thus restricted to host-managed zoned block devices. 2) Check device area zone alignment: If a target maps to a zoned block device, check that the device area is aligned on zone boundaries to avoid problems with REQ_OP_ZONE_RESET operations (resetting a partially mapped sequential zone would not be possible). This also facilitates the processing of zone report with REQ_OP_ZONE_REPORT bios. 3) Check block devices zone model compatibility When setting the DM device's queue limits, several possibilities exists for zoned block devices: 1) The DM target driver may want to expose a different zone model (e.g. host-managed device emulation or regular block device on top of host-managed zoned block devices) 2) Expose the underlying zone model of the devices as-is To allow both cases, the underlying block device zone model must be set in the target limits in dm_set_device_limits() and the compatibility of all devices checked similarly to the logical block size alignment. For this last check, introduce validate_hardware_zoned_model() to check that all targets of a table have the same zone model and that the zone size of the target devices are equal. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [Mike Snitzer refactored Damien's original work to simplify the code] Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2017-05-08 23:40:43 +00:00
if (zoned_model == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
/*
* After stacking all limits, validate all devices
* in table support this zoned model and zone sectors.
*/
zoned_model = ti_limits.zoned;
zone_sectors = ti_limits.chunk_sectors;
}
/* Stack chunk_sectors if target-specific splitting is required */
if (ti->max_io_len)
ti_limits.chunk_sectors = lcm_not_zero(ti->max_io_len,
ti_limits.chunk_sectors);
/* Set I/O hints portion of queue limits */
if (ti->type->io_hints)
ti->type->io_hints(ti, &ti_limits);
/*
* Check each device area is consistent with the target's
* overall queue limits.
*/
if (ti->type->iterate_devices(ti, device_area_is_invalid,
&ti_limits))
return -EINVAL;
combine_limits:
/*
* Merge this target's queue limits into the overall limits
* for the table.
*/
if (blk_stack_limits(limits, &ti_limits, 0) < 0)
DMWARN("%s: adding target device "
"(start sect %llu len %llu) "
"caused an alignment inconsistency",
dm_device_name(table->md),
(unsigned long long) ti->begin,
(unsigned long long) ti->len);
}
dm table: add zoned block devices validation 1) Introduce DM_TARGET_ZONED_HM feature flag: The target drivers currently available will not operate correctly if a table target maps onto a host-managed zoned block device. To avoid problems, introduce the new feature flag DM_TARGET_ZONED_HM to allow a target to explicitly state that it supports host-managed zoned block devices. This feature is checked for all targets in a table if any of the table's block devices are host-managed. Note that as host-aware zoned block devices are backward compatible with regular block devices, they can be used by any of the current target types. This new feature is thus restricted to host-managed zoned block devices. 2) Check device area zone alignment: If a target maps to a zoned block device, check that the device area is aligned on zone boundaries to avoid problems with REQ_OP_ZONE_RESET operations (resetting a partially mapped sequential zone would not be possible). This also facilitates the processing of zone report with REQ_OP_ZONE_REPORT bios. 3) Check block devices zone model compatibility When setting the DM device's queue limits, several possibilities exists for zoned block devices: 1) The DM target driver may want to expose a different zone model (e.g. host-managed device emulation or regular block device on top of host-managed zoned block devices) 2) Expose the underlying zone model of the devices as-is To allow both cases, the underlying block device zone model must be set in the target limits in dm_set_device_limits() and the compatibility of all devices checked similarly to the logical block size alignment. For this last check, introduce validate_hardware_zoned_model() to check that all targets of a table have the same zone model and that the zone size of the target devices are equal. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [Mike Snitzer refactored Damien's original work to simplify the code] Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2017-05-08 23:40:43 +00:00
/*
* Verify that the zoned model and zone sectors, as determined before
* any .io_hints override, are the same across all devices in the table.
* - this is especially relevant if .io_hints is emulating a disk-managed
* zoned model (aka BLK_ZONED_NONE) on host-managed zoned block devices.
* BUT...
*/
if (limits->zoned != BLK_ZONED_NONE) {
/*
* ...IF the above limits stacking determined a zoned model
* validate that all of the table's devices conform to it.
*/
zoned_model = limits->zoned;
zone_sectors = limits->chunk_sectors;
}
if (validate_hardware_zoned_model(table, zoned_model, zone_sectors))
return -EINVAL;
return validate_hardware_logical_block_alignment(table, limits);
}
/*
* Verify that all devices have an integrity profile that matches the
* DM device's registered integrity profile. If the profiles don't
* match then unregister the DM device's integrity profile.
*/
static void dm_table_verify_integrity(struct dm_table *t)
{
struct gendisk *template_disk = NULL;
if (t->integrity_added)
return;
if (t->integrity_supported) {
/*
* Verify that the original integrity profile
* matches all the devices in this table.
*/
template_disk = dm_table_get_integrity_disk(t);
if (template_disk &&
blk_integrity_compare(dm_disk(t->md), template_disk) >= 0)
return;
}
if (integrity_profile_exists(dm_disk(t->md))) {
DMWARN("%s: unable to establish an integrity profile",
dm_device_name(t->md));
blk_integrity_unregister(dm_disk(t->md));
}
}
static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
unsigned long flush = (unsigned long) data;
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && (q->queue_flags & flush);
}
static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush)
{
struct dm_target *ti;
unsigned i;
/*
* Require at least one underlying device to support flushes.
* t->devices includes internal dm devices such as mirror logs
* so we need to use iterate_devices here, which targets
* supporting flushes must provide.
*/
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!ti->num_flush_bios)
continue;
if (ti->flush_supported)
return true;
if (ti->type->iterate_devices &&
ti->type->iterate_devices(ti, device_flush_capable, (void *) flush))
return true;
}
return false;
}
static int device_dax_write_cache_enabled(struct dm_target *ti,
struct dm_dev *dev, sector_t start,
sector_t len, void *data)
{
struct dax_device *dax_dev = dev->dax_dev;
if (!dax_dev)
return false;
if (dax_write_cache_enabled(dax_dev))
return true;
return false;
}
static int dm_table_supports_dax_write_cache(struct dm_table *t)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (ti->type->iterate_devices &&
ti->type->iterate_devices(ti,
device_dax_write_cache_enabled, NULL))
return true;
}
return false;
}
static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && blk_queue_nonrot(q);
}
static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && !blk_queue_add_random(q);
}
static bool dm_table_all_devices_attribute(struct dm_table *t,
iterate_devices_callout_fn func)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!ti->type->iterate_devices ||
!ti->type->iterate_devices(ti, func, NULL))
return false;
}
return true;
}
static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && !q->limits.max_write_same_sectors;
}
static bool dm_table_supports_write_same(struct dm_table *t)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!ti->num_write_same_bios)
return false;
if (!ti->type->iterate_devices ||
ti->type->iterate_devices(ti, device_not_write_same_capable, NULL))
return false;
}
return true;
}
static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && !q->limits.max_write_zeroes_sectors;
}
static bool dm_table_supports_write_zeroes(struct dm_table *t)
{
struct dm_target *ti;
unsigned i = 0;
while (i < dm_table_get_num_targets(t)) {
ti = dm_table_get_target(t, i++);
if (!ti->num_write_zeroes_bios)
return false;
if (!ti->type->iterate_devices ||
ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL))
return false;
}
return true;
}
static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && !blk_queue_nowait(q);
}
static bool dm_table_supports_nowait(struct dm_table *t)
{
struct dm_target *ti;
unsigned i = 0;
while (i < dm_table_get_num_targets(t)) {
ti = dm_table_get_target(t, i++);
if (!dm_target_supports_nowait(ti->type))
return false;
if (!ti->type->iterate_devices ||
ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
return false;
}
return true;
}
static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && !blk_queue_discard(q);
}
static bool dm_table_supports_discards(struct dm_table *t)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!ti->num_discard_bios)
return false;
/*
* Either the target provides discard support (as implied by setting
* 'discards_supported') or it relies on _all_ data devices having
* discard support.
*/
if (!ti->discards_supported &&
(!ti->type->iterate_devices ||
ti->type->iterate_devices(ti, device_not_discard_capable, NULL)))
return false;
}
return true;
}
static int device_not_secure_erase_capable(struct dm_target *ti,
struct dm_dev *dev, sector_t start,
sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && !blk_queue_secure_erase(q);
}
static bool dm_table_supports_secure_erase(struct dm_table *t)
{
struct dm_target *ti;
unsigned int i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!ti->num_secure_erase_bios)
return false;
if (!ti->type->iterate_devices ||
ti->type->iterate_devices(ti, device_not_secure_erase_capable, NULL))
return false;
}
return true;
}
static int device_requires_stable_pages(struct dm_target *ti,
struct dm_dev *dev, sector_t start,
sector_t len, void *data)
{
struct request_queue *q = bdev_get_queue(dev->bdev);
return q && blk_queue_stable_writes(q);
}
/*
* If any underlying device requires stable pages, a table must require
* them as well. Only targets that support iterate_devices are considered:
* don't want error, zero, etc to require stable pages.
*/
static bool dm_table_requires_stable_pages(struct dm_table *t)
{
struct dm_target *ti;
unsigned i;
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (ti->type->iterate_devices &&
ti->type->iterate_devices(ti, device_requires_stable_pages, NULL))
return true;
}
return false;
}
void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
struct queue_limits *limits)
{
bool wc = false, fua = false;
int page_size = PAGE_SIZE;
/*
* Copy table's limits to the DM device's request_queue
*/
q->limits = *limits;
if (dm_table_supports_nowait(t))
blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
else
blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
if (!dm_table_supports_discards(t)) {
blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
/* Must also clear discard limits... */
q->limits.max_discard_sectors = 0;
q->limits.max_hw_discard_sectors = 0;
q->limits.discard_granularity = 0;
q->limits.discard_alignment = 0;
q->limits.discard_misaligned = 0;
} else
blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
if (dm_table_supports_secure_erase(t))
- DM core passthrough ioctl fix to retain reference to DM table, and that table's block devices, while issuing the ioctl to one of those block devices. - DM core passthrough ioctl fix to _not_ override the fmode_t used to issue the ioctl. Overriding by using the fmode_t that the block device was originally open with during DM table load is a liability. - Add DM core support for secure erase forwarding and update the DM linear and DM striped targets to support them. - A DM core 4.16 stable fix to allow abnormal IO (e.g. discard, write same, write zeroes) for targets that make use of the non-splitting IO variant (as is done for multipath or thinp when layered directly on NVMe). - Allow DM targets to return a payload in response to a DM message that they are sent. This is useful for DM targets that would like to provide statistics data in response to DM messages. - Update DM bufio to support non-power-of-2 block sizes. Numerous other related changes prepare the DM bufio code for this support. - Fix DM crypt to use a bounded amount of memory across the entire system. This is to avoid OOM that can otherwise occur in response to certain pathological IO workloads (e.g. discarding a large DM crypt device). - Add a 'check_at_most_once' feature to the DM verity target to allow verity to be used on mobile devices that have very limited resources. - Fix the DM integrity target to fail early if a keyed algorithm (e.g. HMAC) is to be used but the key isn't set. - Add non-power-of-2 support to the DM unstripe target. - Eliminate the use of a Variable Length Array in the DM stripe target. - Update the DM log-writes target to record metadata (REQ_META flag). - DM raid fixes for its nosync status and some variable range issues. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQEcBAABAgAGBQJaxjrCAAoJEMUj8QotnQNaEW8IAMeb6dWbxBgCleafK7GV5I0B jdm6NWDGoGrhz5TyZXbd6pLXD6fbU51O2Jn/LyQ7KOY1lRlS66TBprR60gNyzPQn bQVVEbKnSMwNAnkVpStiVZSs2e9HyNIRsM0yvwZXPfcVw6Q8XttiJQHRdGu4A5jm i+/aoyAf1iJowe5ituyE569gFGnOzPmesKZoF2/A36ik3yq3HF4FR0IPxWKseSpt gCeGTPpBv3aRonRBDxT9uOwb3SXC8TGrStRLm1I6UFwmHKs7nWx/o/P1ghbSOgSt Gu+GdoXnG5qtzAZ1t3sR2Iw3zEmpO1t5Jht5VqR7T+1145DaoPkW5M8vyjHll5o= =H7V5 -----END PGP SIGNATURE----- Merge tag 'for-4.17/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm Pull device mapper updates from Mike Snitzer: - DM core passthrough ioctl fix to retain reference to DM table, and that table's block devices, while issuing the ioctl to one of those block devices. - DM core passthrough ioctl fix to _not_ override the fmode_t used to issue the ioctl. Overriding by using the fmode_t that the block device was originally open with during DM table load is a liability. - Add DM core support for secure erase forwarding and update the DM linear and DM striped targets to support them. - A DM core 4.16 stable fix to allow abnormal IO (e.g. discard, write same, write zeroes) for targets that make use of the non-splitting IO variant (as is done for multipath or thinp when layered directly on NVMe). - Allow DM targets to return a payload in response to a DM message that they are sent. This is useful for DM targets that would like to provide statistics data in response to DM messages. - Update DM bufio to support non-power-of-2 block sizes. Numerous other related changes prepare the DM bufio code for this support. - Fix DM crypt to use a bounded amount of memory across the entire system. This is to avoid OOM that can otherwise occur in response to certain pathological IO workloads (e.g. discarding a large DM crypt device). - Add a 'check_at_most_once' feature to the DM verity target to allow verity to be used on mobile devices that have very limited resources. - Fix the DM integrity target to fail early if a keyed algorithm (e.g. HMAC) is to be used but the key isn't set. - Add non-power-of-2 support to the DM unstripe target. - Eliminate the use of a Variable Length Array in the DM stripe target. - Update the DM log-writes target to record metadata (REQ_META flag). - DM raid fixes for its nosync status and some variable range issues. * tag 'for-4.17/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (28 commits) dm: remove fmode_t argument from .prepare_ioctl hook dm: hold DM table for duration of ioctl rather than use blkdev_get dm raid: fix parse_raid_params() variable range issue dm verity: make verity_for_io_block static dm verity: add 'check_at_most_once' option to only validate hashes once dm bufio: don't embed a bio in the dm_buffer structure dm bufio: support non-power-of-two block sizes dm bufio: use slab cache for dm_buffer structure allocations dm bufio: reorder fields in dm_buffer structure dm bufio: relax alignment constraint on slab cache dm bufio: remove code that merges slab caches dm bufio: get rid of slab cache name allocations dm bufio: move dm-bufio.h to include/linux/ dm bufio: delete outdated comment dm: add support for secure erase forwarding dm: backfill abnormal IO support to non-splitting IO submission dm raid: fix nosync status dm mpath: use DM_MAPIO_SUBMITTED instead of magic number 0 in process_queued_bios() dm stripe: get rid of a Variable Length Array (VLA) dm log writes: record metadata flag for better flags record ...
2018-04-06 18:50:19 +00:00
blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
wc = true;
if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_FUA)))
fua = true;
}
blk_queue_write_cache(q, wc, fua);
if (dm_table_supports_dax(t, device_supports_dax, &page_size)) {
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
if (dm_table_supports_dax(t, device_dax_synchronous, NULL))
set_dax_synchronous(t->md->dax_dev);
}
else
blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
if (dm_table_supports_dax_write_cache(t))
dax_write_cache(t->md->dax_dev, true);
/* Ensure that all underlying devices are non-rotational. */
if (dm_table_all_devices_attribute(t, device_is_nonrot))
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
else
blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
if (!dm_table_supports_write_same(t))
q->limits.max_write_same_sectors = 0;
if (!dm_table_supports_write_zeroes(t))
q->limits.max_write_zeroes_sectors = 0;
dm_table_verify_integrity(t);
/*
* Some devices don't use blk_integrity but still want stable pages
* because they do their own checksumming.
*/
if (dm_table_requires_stable_pages(t))
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
else
blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
/*
* Determine whether or not this queue's I/O timings contribute
* to the entropy pool, Only request-based targets use this.
* Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not
* have it set.
*/
if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random))
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 10:08:50 +00:00
/*
* For a zoned target, the number of zones should be updated for the
* correct value to be exposed in sysfs queue/nr_zones. For a BIO based
* target, this is all that is needed.
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 10:08:50 +00:00
*/
#ifdef CONFIG_BLK_DEV_ZONED
if (blk_queue_is_zoned(q)) {
WARN_ON_ONCE(queue_is_mq(q));
q->nr_zones = blkdev_nr_zones(t->md->disk);
}
#endif
blk_queue_update_readahead(q);
}
unsigned int dm_table_get_num_targets(struct dm_table *t)
{
return t->num_targets;
}
struct list_head *dm_table_get_devices(struct dm_table *t)
{
return &t->devices;
}
fmode_t dm_table_get_mode(struct dm_table *t)
{
return t->mode;
}
EXPORT_SYMBOL(dm_table_get_mode);
enum suspend_mode {
PRESUSPEND,
PRESUSPEND_UNDO,
POSTSUSPEND,
};
static void suspend_targets(struct dm_table *t, enum suspend_mode mode)
{
int i = t->num_targets;
struct dm_target *ti = t->targets;
lockdep_assert_held(&t->md->suspend_lock);
while (i--) {
switch (mode) {
case PRESUSPEND:
if (ti->type->presuspend)
ti->type->presuspend(ti);
break;
case PRESUSPEND_UNDO:
if (ti->type->presuspend_undo)
ti->type->presuspend_undo(ti);
break;
case POSTSUSPEND:
if (ti->type->postsuspend)
ti->type->postsuspend(ti);
break;
}
ti++;
}
}
void dm_table_presuspend_targets(struct dm_table *t)
{
if (!t)
return;
suspend_targets(t, PRESUSPEND);
}
void dm_table_presuspend_undo_targets(struct dm_table *t)
{
if (!t)
return;
suspend_targets(t, PRESUSPEND_UNDO);
}
void dm_table_postsuspend_targets(struct dm_table *t)
{
if (!t)
return;
suspend_targets(t, POSTSUSPEND);
}
int dm_table_resume_targets(struct dm_table *t)
{
int i, r = 0;
lockdep_assert_held(&t->md->suspend_lock);
for (i = 0; i < t->num_targets; i++) {
struct dm_target *ti = t->targets + i;
if (!ti->type->preresume)
continue;
r = ti->type->preresume(ti);
if (r) {
DMERR("%s: %s: preresume failed, error = %d",
dm_device_name(t->md), ti->type->name, r);
return r;
}
}
for (i = 0; i < t->num_targets; i++) {
struct dm_target *ti = t->targets + i;
if (ti->type->resume)
ti->type->resume(ti);
}
return 0;
}
struct mapped_device *dm_table_get_md(struct dm_table *t)
{
return t->md;
}
EXPORT_SYMBOL(dm_table_get_md);
const char *dm_table_device_name(struct dm_table *t)
{
return dm_device_name(t->md);
}
EXPORT_SYMBOL_GPL(dm_table_device_name);
void dm_table_run_md_queue_async(struct dm_table *t)
{
if (!dm_table_request_based(t))
return;
if (t->md->queue)
blk_mq_run_hw_queues(t->md->queue, true);
}
EXPORT_SYMBOL(dm_table_run_md_queue_async);