kernel-fxtec-pro1x/fs/partitions/check.c

773 lines
19 KiB
C
Raw Normal View History

/*
* fs/partitions/check.c
*
* Code extracted from drivers/block/genhd.c
* Copyright (C) 1991-1998 Linus Torvalds
* Re-organised Feb 1998 Russell King
*
* We now have independent partition support from the
* block drivers, which allows all the partition code to
* be grouped in one location, and it to be mostly self
* contained.
*
* Added needed MAJORS for new pairs, {hdi,hdj}, {hdk,hdl}
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
#include <linux/blktrace_api.h>
#include "check.h"
#include "acorn.h"
#include "amiga.h"
#include "atari.h"
#include "ldm.h"
#include "mac.h"
#include "msdos.h"
#include "osf.h"
#include "sgi.h"
#include "sun.h"
#include "ibm.h"
#include "ultrix.h"
#include "efi.h"
#include "karma.h"
#include "sysv68.h"
#ifdef CONFIG_BLK_DEV_MD
extern void md_autodetect_dev(dev_t dev);
#endif
int warn_no_part = 1; /*This is ugly: should make genhd removable media aware*/
static int (*check_part[])(struct parsed_partitions *) = {
/*
* Probe partition formats with tables at disk address 0
* that also have an ADFS boot block at 0xdc0.
*/
#ifdef CONFIG_ACORN_PARTITION_ICS
adfspart_check_ICS,
#endif
#ifdef CONFIG_ACORN_PARTITION_POWERTEC
adfspart_check_POWERTEC,
#endif
#ifdef CONFIG_ACORN_PARTITION_EESOX
adfspart_check_EESOX,
#endif
/*
* Now move on to formats that only have partition info at
* disk address 0xdc0. Since these may also have stale
* PC/BIOS partition tables, they need to come before
* the msdos entry.
*/
#ifdef CONFIG_ACORN_PARTITION_CUMANA
adfspart_check_CUMANA,
#endif
#ifdef CONFIG_ACORN_PARTITION_ADFS
adfspart_check_ADFS,
#endif
#ifdef CONFIG_EFI_PARTITION
efi_partition, /* this must come before msdos */
#endif
#ifdef CONFIG_SGI_PARTITION
sgi_partition,
#endif
#ifdef CONFIG_LDM_PARTITION
ldm_partition, /* this must come before msdos */
#endif
#ifdef CONFIG_MSDOS_PARTITION
msdos_partition,
#endif
#ifdef CONFIG_OSF_PARTITION
osf_partition,
#endif
#ifdef CONFIG_SUN_PARTITION
sun_partition,
#endif
#ifdef CONFIG_AMIGA_PARTITION
amiga_partition,
#endif
#ifdef CONFIG_ATARI_PARTITION
atari_partition,
#endif
#ifdef CONFIG_MAC_PARTITION
mac_partition,
#endif
#ifdef CONFIG_ULTRIX_PARTITION
ultrix_partition,
#endif
#ifdef CONFIG_IBM_PARTITION
ibm_partition,
#endif
#ifdef CONFIG_KARMA_PARTITION
karma_partition,
#endif
#ifdef CONFIG_SYSV68_PARTITION
sysv68_partition,
#endif
NULL
};
/*
* disk_name() is used by partition check code and the genhd driver.
* It formats the devicename of the indicated disk into
* the supplied buffer (of size at least 32), and returns
* a pointer to that same buffer (for convenience).
*/
char *disk_name(struct gendisk *hd, int partno, char *buf)
{
if (!partno)
snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
else
snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
return buf;
}
const char *bdevname(struct block_device *bdev, char *buf)
{
return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
}
EXPORT_SYMBOL(bdevname);
/*
* There's very little reason to use this, you should really
* have a struct block_device just about everywhere and use
* bdevname() instead.
*/
const char *__bdevname(dev_t dev, char *buffer)
{
scnprintf(buffer, BDEVNAME_SIZE, "unknown-block(%u,%u)",
MAJOR(dev), MINOR(dev));
return buffer;
}
EXPORT_SYMBOL(__bdevname);
static struct parsed_partitions *
check_partition(struct gendisk *hd, struct block_device *bdev)
{
struct parsed_partitions *state;
int i, res, err;
state = kzalloc(sizeof(struct parsed_partitions), GFP_KERNEL);
if (!state)
return NULL;
state->pp_buf = (char *)__get_free_page(GFP_KERNEL);
if (!state->pp_buf) {
kfree(state);
return NULL;
}
state->pp_buf[0] = '\0';
state->bdev = bdev;
disk_name(hd, 0, state->name);
snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name);
if (isdigit(state->name[strlen(state->name)-1]))
sprintf(state->name, "p");
state->limit = disk_max_parts(hd);
i = res = err = 0;
while (!res && check_part[i]) {
memset(&state->parts, 0, sizeof(state->parts));
res = check_part[i++](state);
if (res < 0) {
/* We have hit an I/O error which we don't report now.
* But record it, and let the others do their job.
*/
err = res;
res = 0;
}
}
if (res > 0) {
printk(KERN_INFO "%s", state->pp_buf);
free_page((unsigned long)state->pp_buf);
return state;
}
if (state->access_beyond_eod)
err = -ENOSPC;
if (err)
/* The partition is unrecognized. So report I/O errors if there were any */
res = err;
if (!res)
strlcat(state->pp_buf, " unknown partition table\n", PAGE_SIZE);
else if (warn_no_part)
strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE);
printk(KERN_INFO "%s", state->pp_buf);
free_page((unsigned long)state->pp_buf);
kfree(state);
return ERR_PTR(res);
}
static ssize_t part_partition_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%d\n", p->partno);
}
static ssize_t part_start_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect);
}
ssize_t part_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
}
ssize_t part_alignment_offset_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
}
ssize_t part_discard_alignment_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%u\n", p->discard_alignment);
}
ssize_t part_stat_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
int cpu;
cpu = part_stat_lock();
part_round_stats(cpu, p);
part_stat_unlock();
return sprintf(buf,
"%8lu %8lu %8llu %8u "
"%8lu %8lu %8llu %8u "
"%8u %8u %8u"
"\n",
part_stat_read(p, ios[READ]),
part_stat_read(p, merges[READ]),
(unsigned long long)part_stat_read(p, sectors[READ]),
jiffies_to_msecs(part_stat_read(p, ticks[READ])),
part_stat_read(p, ios[WRITE]),
part_stat_read(p, merges[WRITE]),
(unsigned long long)part_stat_read(p, sectors[WRITE]),
jiffies_to_msecs(part_stat_read(p, ticks[WRITE])),
part_in_flight(p),
jiffies_to_msecs(part_stat_read(p, io_ticks)),
jiffies_to_msecs(part_stat_read(p, time_in_queue)));
}
ssize_t part_inflight_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]);
}
#ifdef CONFIG_FAIL_MAKE_REQUEST
ssize_t part_fail_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%d\n", p->make_it_fail);
}
ssize_t part_fail_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct hd_struct *p = dev_to_part(dev);
int i;
if (count > 0 && sscanf(buf, "%d", &i) > 0)
p->make_it_fail = (i == 0) ? 0 : 1;
return count;
}
#endif
static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
NULL);
static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static struct device_attribute dev_attr_fail =
__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
#endif
static struct attribute *part_attrs[] = {
&dev_attr_partition.attr,
&dev_attr_start.attr,
&dev_attr_size.attr,
&dev_attr_alignment_offset.attr,
&dev_attr_discard_alignment.attr,
&dev_attr_stat.attr,
&dev_attr_inflight.attr,
#ifdef CONFIG_FAIL_MAKE_REQUEST
&dev_attr_fail.attr,
#endif
NULL
};
static struct attribute_group part_attr_group = {
.attrs = part_attrs,
};
static const struct attribute_group *part_attr_groups[] = {
&part_attr_group,
blktrace: add ftrace plugin Impact: New way of using the blktrace infrastructure This drops the requirement of userspace utilities to use the blktrace facility. Configuration is done thru sysfs, adding a "trace" directory to the partition directory where blktrace can be enabled for the associated request_queue. The same filters present in the IOCTL interface are present as sysfs device attributes. The /sys/block/sdX/sdXN/trace/enable file allows tracing without any filters. The other files in this directory: pid, act_mask, start_lba and end_lba can be used with the same meaning as with the IOCTL interface. Using the sysfs interface will only setup the request_queue->blk_trace fields, tracing will only take place when the "blk" tracer is selected via the ftrace interface, as in the following example: To see the trace, one can use the /d/tracing/trace file or the /d/tracign/trace_pipe file, with semantics defined in the ftrace documentation in Documentation/ftrace.txt. [root@f10-1 ~]# cat /t/trace kjournald-305 [000] 3046.491224: 8,1 A WBS 6367 + 8 <- (8,1) 6304 kjournald-305 [000] 3046.491227: 8,1 Q R 6367 + 8 [kjournald] kjournald-305 [000] 3046.491236: 8,1 G RB 6367 + 8 [kjournald] kjournald-305 [000] 3046.491239: 8,1 P NS [kjournald] kjournald-305 [000] 3046.491242: 8,1 I RBS 6367 + 8 [kjournald] kjournald-305 [000] 3046.491251: 8,1 D WB 6367 + 8 [kjournald] kjournald-305 [000] 3046.491610: 8,1 U WS [kjournald] 1 <idle>-0 [000] 3046.511914: 8,1 C RS 6367 + 8 [6367] [root@f10-1 ~]# The default line context (prefix) format is the one described in the ftrace documentation, with the blktrace specific bits using its existing format, described in blkparse(8). If one wants to have the classic blktrace formatting, this is possible by using: [root@f10-1 ~]# echo blk_classic > /t/trace_options [root@f10-1 ~]# cat /t/trace 8,1 0 3046.491224 305 A WBS 6367 + 8 <- (8,1) 6304 8,1 0 3046.491227 305 Q R 6367 + 8 [kjournald] 8,1 0 3046.491236 305 G RB 6367 + 8 [kjournald] 8,1 0 3046.491239 305 P NS [kjournald] 8,1 0 3046.491242 305 I RBS 6367 + 8 [kjournald] 8,1 0 3046.491251 305 D WB 6367 + 8 [kjournald] 8,1 0 3046.491610 305 U WS [kjournald] 1 8,1 0 3046.511914 0 C RS 6367 + 8 [6367] [root@f10-1 ~]# Using the ftrace standard format allows more flexibility, such as the ability of asking for backtraces via trace_options: [root@f10-1 ~]# echo noblk_classic > /t/trace_options [root@f10-1 ~]# echo stacktrace > /t/trace_options [root@f10-1 ~]# cat /t/trace kjournald-305 [000] 3318.826779: 8,1 A WBS 6375 + 8 <- (8,1) 6312 kjournald-305 [000] 3318.826782: <= submit_bio <= submit_bh <= sync_dirty_buffer <= journal_commit_transaction <= kjournald <= kthread <= child_rip kjournald-305 [000] 3318.826836: 8,1 Q R 6375 + 8 [kjournald] kjournald-305 [000] 3318.826837: <= generic_make_request <= submit_bio <= submit_bh <= sync_dirty_buffer <= journal_commit_transaction <= kjournald <= kthread Please read the ftrace documentation to use aditional, standardized tracing filters such as /d/tracing/trace_cpumask, etc. See also /d/tracing/trace_mark to add comments in the trace stream, that is equivalent to the /d/block/sdaN/msg interface. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 07:06:27 -07:00
#ifdef CONFIG_BLK_DEV_IO_TRACE
&blk_trace_attr_group,
#endif
NULL
};
static void part_release(struct device *dev)
{
struct hd_struct *p = dev_to_part(dev);
free_part_stats(p);
free_part_info(p);
kfree(p);
}
struct device_type part_type = {
.name = "partition",
.groups = part_attr_groups,
.release = part_release,
};
static void delete_partition_rcu_cb(struct rcu_head *head)
{
struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. When reloading partition tables, quiesce IO to ensure that no request references to the partition struct exists. When it is safe to free the partition table, the IO for that device is restarted again. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-10-19 01:05:00 -06:00
struct gendisk *disk = part_to_disk(part);
struct request_queue *q = disk->queue;
unsigned long flags;
part->start_sect = 0;
part->nr_sects = 0;
part_stat_set_all(part, 0);
put_device(part_to_dev(part));
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. When reloading partition tables, quiesce IO to ensure that no request references to the partition struct exists. When it is safe to free the partition table, the IO for that device is restarted again. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-10-19 01:05:00 -06:00
spin_lock_irqsave(q->queue_lock, flags);
elv_quiesce_end(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
void delete_partition(struct gendisk *disk, int partno)
{
struct disk_part_tbl *ptbl = disk->part_tbl;
struct hd_struct *part;
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. When reloading partition tables, quiesce IO to ensure that no request references to the partition struct exists. When it is safe to free the partition table, the IO for that device is restarted again. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-10-19 01:05:00 -06:00
struct request_queue *q = disk->queue;
if (partno >= ptbl->len)
return;
part = ptbl->part[partno];
if (!part)
return;
blk_free_devt(part_devt(part));
rcu_assign_pointer(ptbl->part[partno], NULL);
rcu_assign_pointer(ptbl->last_lookup, NULL);
kobject_put(part->holder_dir);
device_del(part_to_dev(part));
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. When reloading partition tables, quiesce IO to ensure that no request references to the partition struct exists. When it is safe to free the partition table, the IO for that device is restarted again. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-10-19 01:05:00 -06:00
spin_lock_irq(q->queue_lock);
elv_quiesce_start(q);
spin_unlock_irq(q->queue_lock);
call_rcu(&part->rcu_head, delete_partition_rcu_cb);
}
static ssize_t whole_disk_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return 0;
}
static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
whole_disk_show, NULL);
struct hd_struct *add_partition(struct gendisk *disk, int partno,
sector_t start, sector_t len, int flags,
struct partition_meta_info *info)
{
struct hd_struct *p;
dev_t devt = MKDEV(0, 0);
struct device *ddev = disk_to_dev(disk);
struct device *pdev;
struct disk_part_tbl *ptbl;
const char *dname;
int err;
err = disk_expand_part_tbl(disk, partno);
if (err)
return ERR_PTR(err);
ptbl = disk->part_tbl;
if (ptbl->part[partno])
return ERR_PTR(-EBUSY);
2007-07-19 02:49:03 -06:00
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return ERR_PTR(-EBUSY);
if (!init_part_stats(p)) {
err = -ENOMEM;
goto out_free;
}
pdev = part_to_dev(p);
p->start_sect = start;
p->alignment_offset =
queue_limit_alignment_offset(&disk->queue->limits, start);
p->discard_alignment =
queue_limit_discard_alignment(&disk->queue->limits, start);
p->nr_sects = len;
p->partno = partno;
p->policy = get_disk_ro(disk);
if (info) {
struct partition_meta_info *pinfo = alloc_part_info(disk);
if (!pinfo)
goto out_free_stats;
memcpy(pinfo, info, sizeof(*info));
p->info = pinfo;
}
dname = dev_name(ddev);
if (isdigit(dname[strlen(dname) - 1]))
dev_set_name(pdev, "%sp%d", dname, partno);
else
dev_set_name(pdev, "%s%d", dname, partno);
device_initialize(pdev);
pdev->class = &block_class;
pdev->type = &part_type;
pdev->parent = ddev;
err = blk_alloc_devt(p, &devt);
if (err)
goto out_free_info;
pdev->devt = devt;
/* delay uevent until 'holders' subdir is created */
dev_set_uevent_suppress(pdev, 1);
err = device_add(pdev);
if (err)
goto out_put;
err = -ENOMEM;
p->holder_dir = kobject_create_and_add("holders", &pdev->kobj);
if (!p->holder_dir)
goto out_del;
dev_set_uevent_suppress(pdev, 0);
if (flags & ADDPART_FLAG_WHOLEDISK) {
err = device_create_file(pdev, &dev_attr_whole_disk);
if (err)
goto out_del;
}
/* everything is up and running, commence */
rcu_assign_pointer(ptbl->part[partno], p);
/* suppress uevent if the disk supresses it */
if (!dev_get_uevent_suppress(ddev))
kobject_uevent(&pdev->kobj, KOBJ_ADD);
return p;
out_free_info:
free_part_info(p);
out_free_stats:
free_part_stats(p);
out_free:
kfree(p);
return ERR_PTR(err);
out_del:
kobject_put(p->holder_dir);
device_del(pdev);
out_put:
put_device(pdev);
blk_free_devt(devt);
return ERR_PTR(err);
}
/* Not exported, helper to add_disk(). */
void register_disk(struct gendisk *disk)
{
struct device *ddev = disk_to_dev(disk);
struct block_device *bdev;
struct disk_part_iter piter;
struct hd_struct *part;
int err;
ddev->parent = disk->driverfs_dev;
dev_set_name(ddev, disk->disk_name);
/* delay uevents, until we scanned partition table */
dev_set_uevent_suppress(ddev, 1);
if (device_add(ddev))
return;
if (!sysfs_deprecated) {
err = sysfs_create_link(block_depr, &ddev->kobj,
kobject_name(&ddev->kobj));
if (err) {
device_del(ddev);
return;
}
}
disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
/* No minors to use for partitions */
if (!disk_partitionable(disk))
goto exit;
/* No such device (e.g., media were just removed) */
if (!get_capacity(disk))
goto exit;
bdev = bdget_disk(disk, 0);
if (!bdev)
goto exit;
bdev->bd_invalidated = 1;
err = blkdev_get(bdev, FMODE_READ);
if (err < 0)
goto exit;
blkdev_put(bdev, FMODE_READ);
exit:
/* announce disk after possible partitions are created */
dev_set_uevent_suppress(ddev, 0);
kobject_uevent(&ddev->kobj, KOBJ_ADD);
/* announce possible partitions */
disk_part_iter_init(&piter, disk, 0);
while ((part = disk_part_iter_next(&piter)))
kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
disk_part_iter_exit(&piter);
}
static bool disk_unlock_native_capacity(struct gendisk *disk)
{
const struct block_device_operations *bdops = disk->fops;
if (bdops->unlock_native_capacity &&
!(disk->flags & GENHD_FL_NATIVE_CAPACITY)) {
printk(KERN_CONT "enabling native capacity\n");
bdops->unlock_native_capacity(disk);
disk->flags |= GENHD_FL_NATIVE_CAPACITY;
return true;
} else {
printk(KERN_CONT "truncated\n");
return false;
}
}
int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
{
struct parsed_partitions *state = NULL;
struct disk_part_iter piter;
struct hd_struct *part;
int p, highest, res;
rescan:
if (state && !IS_ERR(state)) {
kfree(state);
state = NULL;
}
if (bdev->bd_part_count)
return -EBUSY;
res = invalidate_partition(disk, 0);
if (res)
return res;
disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
while ((part = disk_part_iter_next(&piter)))
delete_partition(disk, part->partno);
disk_part_iter_exit(&piter);
if (disk->fops->revalidate_disk)
disk->fops->revalidate_disk(disk);
check_disk_size_change(disk, bdev);
bdev->bd_invalidated = 0;
if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
return 0;
if (IS_ERR(state)) {
/*
* I/O error reading the partition table. If any
* partition code tried to read beyond EOD, retry
* after unlocking native capacity.
*/
if (PTR_ERR(state) == -ENOSPC) {
printk(KERN_WARNING "%s: partition table beyond EOD, ",
disk->disk_name);
if (disk_unlock_native_capacity(disk))
goto rescan;
}
return -EIO;
}
/*
* If any partition code tried to read beyond EOD, try
* unlocking native capacity even if partition table is
* sucessfully read as we could be missing some partitions.
*/
if (state->access_beyond_eod) {
printk(KERN_WARNING
"%s: partition table partially beyond EOD, ",
disk->disk_name);
if (disk_unlock_native_capacity(disk))
goto rescan;
}
/* tell userspace that the media / partition table may have changed */
kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
/* Detect the highest partition number and preallocate
* disk->part_tbl. This is an optimization and not strictly
* necessary.
*/
for (p = 1, highest = 0; p < state->limit; p++)
if (state->parts[p].size)
highest = p;
disk_expand_part_tbl(disk, highest);
/* add partitions */
for (p = 1; p < state->limit; p++) {
sector_t size, from;
struct partition_meta_info *info = NULL;
size = state->parts[p].size;
if (!size)
continue;
from = state->parts[p].from;
block: sanitize invalid partition table entries We currently follow blindly what the partition table lies about the disk, and let the kernel create block devices which can not be accessed. Trying to identify the device leads to kernel logs full of: sdb: rw=0, want=73392, limit=28800 attempt to access beyond end of device Here is an example of a broken partition table, where sda2 starts behind the end of the disk, and sdb3 is larger than the entire disk: Disk /dev/sdb: 14 MB, 14745600 bytes 1 heads, 29 sectors/track, 993 cylinders, total 28800 sectors Device Boot Start End Blocks Id System /dev/sdb1 29 7800 3886 83 Linux /dev/sdb2 37801 45601 3900+ 83 Linux /dev/sdb3 15602 73402 28900+ 83 Linux /dev/sdb4 23403 28796 2697 83 Linux The kernel creates these completely invalid devices, which can not be accessed, or may lead to other unpredictable failures: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb2/start:37801 /sys/class/block/sdb2/size:7801 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:57801 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 With this patch, we ignore partitions which start behind the end of the disk, and limit partitions to the end of the disk if they pretend to be larger: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:13198 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 These warnings are printed to the kernel log: sdb: p2 ignored, start 37801 is behind the end of the disk sdb: p3 size 57801 limited to end of disk Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Cc: Herton Ronaldo Krzesinski <herton@mandriva.com.br> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-15 23:04:21 -06:00
if (from >= get_capacity(disk)) {
printk(KERN_WARNING
"%s: p%d start %llu is beyond EOD, ",
block: sanitize invalid partition table entries We currently follow blindly what the partition table lies about the disk, and let the kernel create block devices which can not be accessed. Trying to identify the device leads to kernel logs full of: sdb: rw=0, want=73392, limit=28800 attempt to access beyond end of device Here is an example of a broken partition table, where sda2 starts behind the end of the disk, and sdb3 is larger than the entire disk: Disk /dev/sdb: 14 MB, 14745600 bytes 1 heads, 29 sectors/track, 993 cylinders, total 28800 sectors Device Boot Start End Blocks Id System /dev/sdb1 29 7800 3886 83 Linux /dev/sdb2 37801 45601 3900+ 83 Linux /dev/sdb3 15602 73402 28900+ 83 Linux /dev/sdb4 23403 28796 2697 83 Linux The kernel creates these completely invalid devices, which can not be accessed, or may lead to other unpredictable failures: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb2/start:37801 /sys/class/block/sdb2/size:7801 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:57801 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 With this patch, we ignore partitions which start behind the end of the disk, and limit partitions to the end of the disk if they pretend to be larger: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:13198 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 These warnings are printed to the kernel log: sdb: p2 ignored, start 37801 is behind the end of the disk sdb: p3 size 57801 limited to end of disk Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Cc: Herton Ronaldo Krzesinski <herton@mandriva.com.br> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-15 23:04:21 -06:00
disk->disk_name, p, (unsigned long long) from);
if (disk_unlock_native_capacity(disk))
goto rescan;
block: sanitize invalid partition table entries We currently follow blindly what the partition table lies about the disk, and let the kernel create block devices which can not be accessed. Trying to identify the device leads to kernel logs full of: sdb: rw=0, want=73392, limit=28800 attempt to access beyond end of device Here is an example of a broken partition table, where sda2 starts behind the end of the disk, and sdb3 is larger than the entire disk: Disk /dev/sdb: 14 MB, 14745600 bytes 1 heads, 29 sectors/track, 993 cylinders, total 28800 sectors Device Boot Start End Blocks Id System /dev/sdb1 29 7800 3886 83 Linux /dev/sdb2 37801 45601 3900+ 83 Linux /dev/sdb3 15602 73402 28900+ 83 Linux /dev/sdb4 23403 28796 2697 83 Linux The kernel creates these completely invalid devices, which can not be accessed, or may lead to other unpredictable failures: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb2/start:37801 /sys/class/block/sdb2/size:7801 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:57801 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 With this patch, we ignore partitions which start behind the end of the disk, and limit partitions to the end of the disk if they pretend to be larger: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:13198 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 These warnings are printed to the kernel log: sdb: p2 ignored, start 37801 is behind the end of the disk sdb: p3 size 57801 limited to end of disk Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Cc: Herton Ronaldo Krzesinski <herton@mandriva.com.br> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-15 23:04:21 -06:00
continue;
}
if (from + size > get_capacity(disk)) {
printk(KERN_WARNING
"%s: p%d size %llu extends beyond EOD, ",
block: sanitize invalid partition table entries We currently follow blindly what the partition table lies about the disk, and let the kernel create block devices which can not be accessed. Trying to identify the device leads to kernel logs full of: sdb: rw=0, want=73392, limit=28800 attempt to access beyond end of device Here is an example of a broken partition table, where sda2 starts behind the end of the disk, and sdb3 is larger than the entire disk: Disk /dev/sdb: 14 MB, 14745600 bytes 1 heads, 29 sectors/track, 993 cylinders, total 28800 sectors Device Boot Start End Blocks Id System /dev/sdb1 29 7800 3886 83 Linux /dev/sdb2 37801 45601 3900+ 83 Linux /dev/sdb3 15602 73402 28900+ 83 Linux /dev/sdb4 23403 28796 2697 83 Linux The kernel creates these completely invalid devices, which can not be accessed, or may lead to other unpredictable failures: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb2/start:37801 /sys/class/block/sdb2/size:7801 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:57801 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 With this patch, we ignore partitions which start behind the end of the disk, and limit partitions to the end of the disk if they pretend to be larger: grep . /sys/class/block/sdb*/{start,size} /sys/class/block/sdb/size:28800 /sys/class/block/sdb1/start:29 /sys/class/block/sdb1/size:7772 /sys/class/block/sdb3/start:15602 /sys/class/block/sdb3/size:13198 /sys/class/block/sdb4/start:23403 /sys/class/block/sdb4/size:5394 These warnings are printed to the kernel log: sdb: p2 ignored, start 37801 is behind the end of the disk sdb: p3 size 57801 limited to end of disk Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Cc: Herton Ronaldo Krzesinski <herton@mandriva.com.br> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-15 23:04:21 -06:00
disk->disk_name, p, (unsigned long long) size);
if (disk_unlock_native_capacity(disk)) {
/* free state and restart */
goto rescan;
} else {
/*
* we can not ignore partitions of broken tables
* created by for example camera firmware, but
* we limit them to the end of the disk to avoid
* creating invalid block devices
*/
size = get_capacity(disk) - from;
}
}
if (state->parts[p].has_info)
info = &state->parts[p].info;
part = add_partition(disk, p, from, size,
state->parts[p].flags,
&state->parts[p].info);
if (IS_ERR(part)) {
printk(KERN_ERR " %s: p%d could not be added: %ld\n",
disk->disk_name, p, -PTR_ERR(part));
continue;
}
#ifdef CONFIG_BLK_DEV_MD
if (state->parts[p].flags & ADDPART_FLAG_RAID)
md_autodetect_dev(part_to_dev(part)->devt);
#endif
}
kfree(state);
return 0;
}
unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
struct page *page;
page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)),
NULL);
if (!IS_ERR(page)) {
if (PageError(page))
goto fail;
p->v = page;
return (unsigned char *)page_address(page) + ((n & ((1 << (PAGE_CACHE_SHIFT - 9)) - 1)) << 9);
fail:
page_cache_release(page);
}
p->v = NULL;
return NULL;
}
EXPORT_SYMBOL(read_dev_sector);
void del_gendisk(struct gendisk *disk)
{
struct disk_part_iter piter;
struct hd_struct *part;
/* invalidate stuff */
disk_part_iter_init(&piter, disk,
DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
while ((part = disk_part_iter_next(&piter))) {
invalidate_partition(disk, part->partno);
delete_partition(disk, part->partno);
}
disk_part_iter_exit(&piter);
invalidate_partition(disk, 0);
blk_free_devt(disk_to_dev(disk)->devt);
set_capacity(disk, 0);
disk->flags &= ~GENHD_FL_UP;
unlink_gendisk(disk);
part_stat_set_all(&disk->part0, 0);
disk->part0.stamp = 0;
kobject_put(disk->part0.holder_dir);
kobject_put(disk->slave_dir);
disk->driverfs_dev = NULL;
if (!sysfs_deprecated)
sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
device_del(disk_to_dev(disk));
}