OpenCloudOS-Kernel/drivers/scsi/sr.c

1053 lines
26 KiB
C
Raw Normal View History

/*
* sr.c Copyright (C) 1992 David Giller
* Copyright (C) 1993, 1994, 1995, 1999 Eric Youngdale
*
* adapted from:
* sd.c Copyright (C) 1992 Drew Eckhardt
* Linux scsi disk driver by
* Drew Eckhardt <drew@colorado.edu>
*
* Modified by Eric Youngdale ericy@andante.org to
* add scatter-gather, multiple outstanding request, and other
* enhancements.
*
* Modified by Eric Youngdale eric@andante.org to support loadable
* low-level scsi drivers.
*
* Modified by Thomas Quinot thomas@melchior.cuivre.fdn.fr to
* provide auto-eject.
*
* Modified by Gerd Knorr <kraxel@cs.tu-berlin.de> to support the
* generic cdrom interface
*
* Modified by Jens Axboe <axboe@suse.de> - Uniform sr_packet()
* interface, capabilities probe additions, ioctl cleanups, etc.
*
* Modified by Richard Gooch <rgooch@atnf.csiro.au> to support devfs
*
* Modified by Jens Axboe <axboe@suse.de> - support DVD-RAM
* transparently and lose the GHOST hack
*
* Modified by Arnaldo Carvalho de Melo <acme@conectiva.com.br>
* check resource allocation in sr_init and some cleanups
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bio.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/cdrom.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/blk-pm.h>
#include <linux/mutex.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 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/pm_runtime.h>
#include <linux/uaccess.h>
#include <scsi/scsi.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_ioctl.h> /* For the door lock/unlock commands */
#include "scsi_logging.h"
#include "sr.h"
MODULE_DESCRIPTION("SCSI cdrom (sr) driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_CDROM_MAJOR);
[SCSI] modalias for scsi devices The following patch adds support for sysfs/uevent modalias attribute for scsi devices (like disks, tapes, cdroms etc), based on whatever current sd.c, sr.c, st.c and osst.c drivers supports. The modalias format is like this: scsi:type-0x04 (for TYPE_WORM, handled by sr.c now). Several comments. o This hexadecimal type value is because all TYPE_XXX constants in include/scsi/scsi.h are given in hex, but __stringify() will not convert them to decimal (so it will NOT be scsi:type-4). Since it does not really matter in which format it is, while both modalias in module and modalias attribute match each other, I descided to go for that 0x%02x format (and added a comment in include/scsi/scsi.h to keep them that way), instead of changing them all to decimal. o There was no .uevent routine for SCSI bus. It might be a good idea to add some more ueven environment variables in there. o osst.c driver handles tapes too, like st.c, but only SOME tapes. With this setup, hotplug scripts (or whatever is used by the user) will try to load both st and osst modules for all SCSI tapes found, because both modules have scsi:type-0x01 alias). It is not harmful, but one extra module is no good either. It is possible to solve this, by exporting more info in modalias attribute, including vendor and device identification strings, so that modalias becomes something like scsi:type-0x12:vendor-Adaptec LTD:device-OnStream Tape Drive and having that, match for all 3 attributes, not only device type. But oh well, vendor and device strings may be large, and they do contain spaces and whatnot. So I left them for now, awaiting for comments first. Signed-off-by: Michael Tokarev <mjt@tls.msk.ru> Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
2006-10-27 20:02:37 +08:00
MODULE_ALIAS_SCSI_DEVICE(TYPE_ROM);
MODULE_ALIAS_SCSI_DEVICE(TYPE_WORM);
#define SR_DISKS 256
#define SR_CAPABILITIES \
(CDC_CLOSE_TRAY|CDC_OPEN_TRAY|CDC_LOCK|CDC_SELECT_SPEED| \
CDC_SELECT_DISC|CDC_MULTI_SESSION|CDC_MCN|CDC_MEDIA_CHANGED| \
CDC_PLAY_AUDIO|CDC_RESET|CDC_DRIVE_STATUS| \
CDC_CD_R|CDC_CD_RW|CDC_DVD|CDC_DVD_R|CDC_DVD_RAM|CDC_GENERIC_PACKET| \
CDC_MRW|CDC_MRW_W|CDC_RAM)
static DEFINE_MUTEX(sr_mutex);
static int sr_probe(struct device *);
static int sr_remove(struct device *);
static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt);
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
static int sr_done(struct scsi_cmnd *);
static int sr_runtime_suspend(struct device *dev);
static const struct dev_pm_ops sr_pm_ops = {
.runtime_suspend = sr_runtime_suspend,
};
static struct scsi_driver sr_template = {
.gendrv = {
.name = "sr",
.owner = THIS_MODULE,
.probe = sr_probe,
.remove = sr_remove,
.pm = &sr_pm_ops,
},
.init_command = sr_init_command,
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
.done = sr_done,
};
static unsigned long sr_index_bits[SR_DISKS / BITS_PER_LONG];
static DEFINE_SPINLOCK(sr_index_lock);
/* This semaphore is used to mediate the 0->1 reference get in the
* face of object destruction (i.e. we can't allow a get on an
* object after last put) */
static DEFINE_MUTEX(sr_ref_mutex);
static int sr_open(struct cdrom_device_info *, int);
static void sr_release(struct cdrom_device_info *);
static void get_sectorsize(struct scsi_cd *);
static void get_capabilities(struct scsi_cd *);
static unsigned int sr_check_events(struct cdrom_device_info *cdi,
unsigned int clearing, int slot);
static int sr_packet(struct cdrom_device_info *, struct packet_command *);
static const struct cdrom_device_ops sr_dops = {
.open = sr_open,
.release = sr_release,
.drive_status = sr_drive_status,
.check_events = sr_check_events,
.tray_move = sr_tray_move,
.lock_door = sr_lock_door,
.select_speed = sr_select_speed,
.get_last_session = sr_get_last_session,
.get_mcn = sr_get_mcn,
.reset = sr_reset,
.audio_ioctl = sr_audio_ioctl,
.capability = SR_CAPABILITIES,
.generic_packet = sr_packet,
};
static void sr_kref_release(struct kref *kref);
static inline struct scsi_cd *scsi_cd(struct gendisk *disk)
{
return container_of(disk->private_data, struct scsi_cd, driver);
}
static int sr_runtime_suspend(struct device *dev)
{
struct scsi_cd *cd = dev_get_drvdata(dev);
if (!cd) /* E.g.: runtime suspend following sr_remove() */
return 0;
if (cd->media_present)
return -EBUSY;
else
return 0;
}
/*
* The get and put routines for the struct scsi_cd. Note this entity
* has a scsi_device pointer and owns a reference to this.
*/
static inline struct scsi_cd *scsi_cd_get(struct gendisk *disk)
{
struct scsi_cd *cd = NULL;
mutex_lock(&sr_ref_mutex);
if (disk->private_data == NULL)
goto out;
cd = scsi_cd(disk);
kref_get(&cd->kref);
if (scsi_device_get(cd->device)) {
kref_put(&cd->kref, sr_kref_release);
cd = NULL;
}
out:
mutex_unlock(&sr_ref_mutex);
return cd;
}
static void scsi_cd_put(struct scsi_cd *cd)
{
struct scsi_device *sdev = cd->device;
mutex_lock(&sr_ref_mutex);
kref_put(&cd->kref, sr_kref_release);
scsi_device_put(sdev);
mutex_unlock(&sr_ref_mutex);
}
static unsigned int sr_get_events(struct scsi_device *sdev)
{
u8 buf[8];
u8 cmd[] = { GET_EVENT_STATUS_NOTIFICATION,
1, /* polled */
0, 0, /* reserved */
1 << 4, /* notification class: media */
0, 0, /* reserved */
0, sizeof(buf), /* allocation length */
0, /* control */
};
struct event_header *eh = (void *)buf;
struct media_event_desc *med = (void *)(buf + 4);
struct scsi_sense_hdr sshdr;
int result;
result = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, sizeof(buf),
&sshdr, SR_TIMEOUT, MAX_RETRIES, NULL);
if (scsi_sense_valid(&sshdr) && sshdr.sense_key == UNIT_ATTENTION)
return DISK_EVENT_MEDIA_CHANGE;
if (result || be16_to_cpu(eh->data_len) < sizeof(*med))
return 0;
if (eh->nea || eh->notification_class != 0x4)
return 0;
if (med->media_event_code == 1)
return DISK_EVENT_EJECT_REQUEST;
else if (med->media_event_code == 2)
return DISK_EVENT_MEDIA_CHANGE;
return 0;
}
/*
* This function checks to see if the media has been changed or eject
* button has been pressed. It is possible that we have already
* sensed a change, or the drive may have sensed one and not yet
* reported it. The past events are accumulated in sdev->changed and
* returned together with the current state.
*/
static unsigned int sr_check_events(struct cdrom_device_info *cdi,
unsigned int clearing, int slot)
{
struct scsi_cd *cd = cdi->handle;
bool last_present;
struct scsi_sense_hdr sshdr;
unsigned int events;
int ret;
/* no changer support */
if (CDSL_CURRENT != slot)
return 0;
events = sr_get_events(cd->device);
[SCSI] sr: check_events() ignore GET_EVENT when TUR says otherwise Some broken devices indicates that media has changed on every GET_EVENT_STATUS_NOTIFICATION. This translates into MEDIA_CHANGE uevent on every open() which lets udev run into a loop. Verify GET_EVENT result against TUR and if it generates spurious events for several times in a row, ignore the GET_EVENT events, and trust only the TUR status. This is the log of a USB stick with a (broken) fake CDROM drive: scsi 5:0:0:0: Direct-Access SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 CCS sd 5:0:0:0: Attached scsi generic sg3 type 0 scsi 5:0:0:1: CD-ROM SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 sd 5:0:0:0: [sdb] Attached SCSI removable disk sr2: scsi3-mmc drive: 48x/48x tray sr 5:0:0:1: Attached scsi CD-ROM sr2 sr 5:0:0:1: Attached scsi generic sg4 type 5 sr2: GET_EVENT and TUR disagree continuously, suppress GET_EVENT events sd 5:0:0:0: [sdb] 31777279 512-byte logical blocks: (16.2 GB/15.1 GiB) sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sdb: sdb1 -tj: Updated to consider only spurious GET_EVENT events among different types of disagreement and allow using TUR for kernel event polling after GET_EVENT is ignored. Reported-By: Markus Rathgeb maggu2810@googlemail.com Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@kernel.org # >= v2.6.38, fixes udev busy looping w/ certain devices Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2011-06-30 21:03:48 +08:00
cd->get_event_changed |= events & DISK_EVENT_MEDIA_CHANGE;
/*
* If earlier GET_EVENT_STATUS_NOTIFICATION and TUR did not agree
* for several times in a row. We rely on TUR only for this likely
* broken device, to prevent generating incorrect media changed
* events for every open().
*/
if (cd->ignore_get_event) {
events &= ~DISK_EVENT_MEDIA_CHANGE;
goto do_tur;
}
/*
* GET_EVENT_STATUS_NOTIFICATION is enough unless MEDIA_CHANGE
* is being cleared. Note that there are devices which hang
* if asked to execute TUR repeatedly.
*/
[SCSI] sr: check_events() ignore GET_EVENT when TUR says otherwise Some broken devices indicates that media has changed on every GET_EVENT_STATUS_NOTIFICATION. This translates into MEDIA_CHANGE uevent on every open() which lets udev run into a loop. Verify GET_EVENT result against TUR and if it generates spurious events for several times in a row, ignore the GET_EVENT events, and trust only the TUR status. This is the log of a USB stick with a (broken) fake CDROM drive: scsi 5:0:0:0: Direct-Access SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 CCS sd 5:0:0:0: Attached scsi generic sg3 type 0 scsi 5:0:0:1: CD-ROM SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 sd 5:0:0:0: [sdb] Attached SCSI removable disk sr2: scsi3-mmc drive: 48x/48x tray sr 5:0:0:1: Attached scsi CD-ROM sr2 sr 5:0:0:1: Attached scsi generic sg4 type 5 sr2: GET_EVENT and TUR disagree continuously, suppress GET_EVENT events sd 5:0:0:0: [sdb] 31777279 512-byte logical blocks: (16.2 GB/15.1 GiB) sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sdb: sdb1 -tj: Updated to consider only spurious GET_EVENT events among different types of disagreement and allow using TUR for kernel event polling after GET_EVENT is ignored. Reported-By: Markus Rathgeb maggu2810@googlemail.com Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@kernel.org # >= v2.6.38, fixes udev busy looping w/ certain devices Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2011-06-30 21:03:48 +08:00
if (cd->device->changed) {
events |= DISK_EVENT_MEDIA_CHANGE;
cd->device->changed = 0;
cd->tur_changed = true;
}
[SCSI] sr: check_events() ignore GET_EVENT when TUR says otherwise Some broken devices indicates that media has changed on every GET_EVENT_STATUS_NOTIFICATION. This translates into MEDIA_CHANGE uevent on every open() which lets udev run into a loop. Verify GET_EVENT result against TUR and if it generates spurious events for several times in a row, ignore the GET_EVENT events, and trust only the TUR status. This is the log of a USB stick with a (broken) fake CDROM drive: scsi 5:0:0:0: Direct-Access SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 CCS sd 5:0:0:0: Attached scsi generic sg3 type 0 scsi 5:0:0:1: CD-ROM SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 sd 5:0:0:0: [sdb] Attached SCSI removable disk sr2: scsi3-mmc drive: 48x/48x tray sr 5:0:0:1: Attached scsi CD-ROM sr2 sr 5:0:0:1: Attached scsi generic sg4 type 5 sr2: GET_EVENT and TUR disagree continuously, suppress GET_EVENT events sd 5:0:0:0: [sdb] 31777279 512-byte logical blocks: (16.2 GB/15.1 GiB) sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sdb: sdb1 -tj: Updated to consider only spurious GET_EVENT events among different types of disagreement and allow using TUR for kernel event polling after GET_EVENT is ignored. Reported-By: Markus Rathgeb maggu2810@googlemail.com Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@kernel.org # >= v2.6.38, fixes udev busy looping w/ certain devices Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2011-06-30 21:03:48 +08:00
if (!(clearing & DISK_EVENT_MEDIA_CHANGE))
return events;
do_tur:
/* let's see whether the media is there with TUR */
last_present = cd->media_present;
ret = scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr);
/*
* Media is considered to be present if TUR succeeds or fails with
* sense data indicating something other than media-not-present
* (ASC 0x3a).
*/
cd->media_present = scsi_status_is_good(ret) ||
(scsi_sense_valid(&sshdr) && sshdr.asc != 0x3a);
if (last_present != cd->media_present)
[SCSI] sr: check_events() ignore GET_EVENT when TUR says otherwise Some broken devices indicates that media has changed on every GET_EVENT_STATUS_NOTIFICATION. This translates into MEDIA_CHANGE uevent on every open() which lets udev run into a loop. Verify GET_EVENT result against TUR and if it generates spurious events for several times in a row, ignore the GET_EVENT events, and trust only the TUR status. This is the log of a USB stick with a (broken) fake CDROM drive: scsi 5:0:0:0: Direct-Access SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 CCS sd 5:0:0:0: Attached scsi generic sg3 type 0 scsi 5:0:0:1: CD-ROM SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 sd 5:0:0:0: [sdb] Attached SCSI removable disk sr2: scsi3-mmc drive: 48x/48x tray sr 5:0:0:1: Attached scsi CD-ROM sr2 sr 5:0:0:1: Attached scsi generic sg4 type 5 sr2: GET_EVENT and TUR disagree continuously, suppress GET_EVENT events sd 5:0:0:0: [sdb] 31777279 512-byte logical blocks: (16.2 GB/15.1 GiB) sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sdb: sdb1 -tj: Updated to consider only spurious GET_EVENT events among different types of disagreement and allow using TUR for kernel event polling after GET_EVENT is ignored. Reported-By: Markus Rathgeb maggu2810@googlemail.com Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@kernel.org # >= v2.6.38, fixes udev busy looping w/ certain devices Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2011-06-30 21:03:48 +08:00
cd->device->changed = 1;
if (cd->device->changed) {
events |= DISK_EVENT_MEDIA_CHANGE;
cd->device->changed = 0;
[SCSI] sr: check_events() ignore GET_EVENT when TUR says otherwise Some broken devices indicates that media has changed on every GET_EVENT_STATUS_NOTIFICATION. This translates into MEDIA_CHANGE uevent on every open() which lets udev run into a loop. Verify GET_EVENT result against TUR and if it generates spurious events for several times in a row, ignore the GET_EVENT events, and trust only the TUR status. This is the log of a USB stick with a (broken) fake CDROM drive: scsi 5:0:0:0: Direct-Access SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 CCS sd 5:0:0:0: Attached scsi generic sg3 type 0 scsi 5:0:0:1: CD-ROM SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 sd 5:0:0:0: [sdb] Attached SCSI removable disk sr2: scsi3-mmc drive: 48x/48x tray sr 5:0:0:1: Attached scsi CD-ROM sr2 sr 5:0:0:1: Attached scsi generic sg4 type 5 sr2: GET_EVENT and TUR disagree continuously, suppress GET_EVENT events sd 5:0:0:0: [sdb] 31777279 512-byte logical blocks: (16.2 GB/15.1 GiB) sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sdb: sdb1 -tj: Updated to consider only spurious GET_EVENT events among different types of disagreement and allow using TUR for kernel event polling after GET_EVENT is ignored. Reported-By: Markus Rathgeb maggu2810@googlemail.com Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@kernel.org # >= v2.6.38, fixes udev busy looping w/ certain devices Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2011-06-30 21:03:48 +08:00
cd->tur_changed = true;
}
if (cd->ignore_get_event)
return events;
/* check whether GET_EVENT is reporting spurious MEDIA_CHANGE */
if (!cd->tur_changed) {
if (cd->get_event_changed) {
if (cd->tur_mismatch++ > 8) {
sr_printk(KERN_WARNING, cd,
"GET_EVENT and TUR disagree continuously, suppress GET_EVENT events\n");
[SCSI] sr: check_events() ignore GET_EVENT when TUR says otherwise Some broken devices indicates that media has changed on every GET_EVENT_STATUS_NOTIFICATION. This translates into MEDIA_CHANGE uevent on every open() which lets udev run into a loop. Verify GET_EVENT result against TUR and if it generates spurious events for several times in a row, ignore the GET_EVENT events, and trust only the TUR status. This is the log of a USB stick with a (broken) fake CDROM drive: scsi 5:0:0:0: Direct-Access SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 CCS sd 5:0:0:0: Attached scsi generic sg3 type 0 scsi 5:0:0:1: CD-ROM SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 sd 5:0:0:0: [sdb] Attached SCSI removable disk sr2: scsi3-mmc drive: 48x/48x tray sr 5:0:0:1: Attached scsi CD-ROM sr2 sr 5:0:0:1: Attached scsi generic sg4 type 5 sr2: GET_EVENT and TUR disagree continuously, suppress GET_EVENT events sd 5:0:0:0: [sdb] 31777279 512-byte logical blocks: (16.2 GB/15.1 GiB) sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sdb: sdb1 -tj: Updated to consider only spurious GET_EVENT events among different types of disagreement and allow using TUR for kernel event polling after GET_EVENT is ignored. Reported-By: Markus Rathgeb maggu2810@googlemail.com Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@kernel.org # >= v2.6.38, fixes udev busy looping w/ certain devices Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2011-06-30 21:03:48 +08:00
cd->ignore_get_event = true;
}
} else {
cd->tur_mismatch = 0;
}
}
[SCSI] sr: check_events() ignore GET_EVENT when TUR says otherwise Some broken devices indicates that media has changed on every GET_EVENT_STATUS_NOTIFICATION. This translates into MEDIA_CHANGE uevent on every open() which lets udev run into a loop. Verify GET_EVENT result against TUR and if it generates spurious events for several times in a row, ignore the GET_EVENT events, and trust only the TUR status. This is the log of a USB stick with a (broken) fake CDROM drive: scsi 5:0:0:0: Direct-Access SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 CCS sd 5:0:0:0: Attached scsi generic sg3 type 0 scsi 5:0:0:1: CD-ROM SanDisk U3 Cruzer Micro 8.02 PQ: 0 ANSI: 0 sd 5:0:0:0: [sdb] Attached SCSI removable disk sr2: scsi3-mmc drive: 48x/48x tray sr 5:0:0:1: Attached scsi CD-ROM sr2 sr 5:0:0:1: Attached scsi generic sg4 type 5 sr2: GET_EVENT and TUR disagree continuously, suppress GET_EVENT events sd 5:0:0:0: [sdb] 31777279 512-byte logical blocks: (16.2 GB/15.1 GiB) sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sd 5:0:0:0: [sdb] No Caching mode page present sd 5:0:0:0: [sdb] Assuming drive cache: write through sdb: sdb1 -tj: Updated to consider only spurious GET_EVENT events among different types of disagreement and allow using TUR for kernel event polling after GET_EVENT is ignored. Reported-By: Markus Rathgeb maggu2810@googlemail.com Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@kernel.org # >= v2.6.38, fixes udev busy looping w/ certain devices Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2011-06-30 21:03:48 +08:00
cd->tur_changed = false;
cd->get_event_changed = false;
return events;
}
/*
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
* sr_done is the interrupt routine for the device driver.
*
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
* It will be notified on the end of a SCSI read / write, and will take one
* of several actions based on success or failure.
*/
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
static int sr_done(struct scsi_cmnd *SCpnt)
{
int result = SCpnt->result;
int this_count = scsi_bufflen(SCpnt);
int good_bytes = (result == 0 ? this_count : 0);
int block_sectors = 0;
long error_sector;
struct scsi_cd *cd = scsi_cd(SCpnt->request->rq_disk);
#ifdef DEBUG
scmd_printk(KERN_INFO, SCpnt, "done: %x\n", result);
#endif
/*
* Handle MEDIUM ERRORs or VOLUME OVERFLOWs that indicate partial
* success. Since this is a relatively rare error condition, no
* care is taken to avoid unnecessary additional work such as
* memcpy's that could be avoided.
*/
if (driver_byte(result) != 0 && /* An error occurred */
(SCpnt->sense_buffer[0] & 0x7f) == 0x70) { /* Sense current */
switch (SCpnt->sense_buffer[2]) {
case MEDIUM_ERROR:
case VOLUME_OVERFLOW:
case ILLEGAL_REQUEST:
if (!(SCpnt->sense_buffer[0] & 0x90))
break;
error_sector = (SCpnt->sense_buffer[3] << 24) |
(SCpnt->sense_buffer[4] << 16) |
(SCpnt->sense_buffer[5] << 8) |
SCpnt->sense_buffer[6];
if (SCpnt->request->bio != NULL)
block_sectors =
bio_sectors(SCpnt->request->bio);
if (block_sectors < 4)
block_sectors = 4;
if (cd->device->sector_size == 2048)
error_sector <<= 2;
error_sector &= ~(block_sectors - 1);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:39 +08:00
good_bytes = (error_sector -
blk_rq_pos(SCpnt->request)) << 9;
if (good_bytes < 0 || good_bytes >= this_count)
good_bytes = 0;
/*
* The SCSI specification allows for the value
* returned by READ CAPACITY to be up to 75 2K
* sectors past the last readable block.
* Therefore, if we hit a medium error within the
* last 75 2K sectors, we decrease the saved size
* value.
*/
if (error_sector < get_capacity(cd->disk) &&
cd->capacity - error_sector < 4 * 75)
set_capacity(cd->disk, error_sector);
break;
case RECOVERED_ERROR:
good_bytes = this_count;
break;
default:
break;
}
}
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
return good_bytes;
}
static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt)
{
int block = 0, this_count, s_size;
struct scsi_cd *cd;
struct request *rq = SCpnt->request;
blk_status_t ret;
ret = scsi_init_io(SCpnt);
if (ret != BLK_STS_OK)
goto out;
cd = scsi_cd(rq->rq_disk);
/* from here on until we're complete, any goto out
* is used for a killable error condition */
ret = BLK_STS_IOERR;
SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt,
"Doing sr request, block = %d\n", block));
if (!cd->device || !scsi_device_online(cd->device)) {
SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
"Finishing %u sectors\n", blk_rq_sectors(rq)));
SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
"Retry with 0x%p\n", SCpnt));
goto out;
}
if (cd->device->changed) {
/*
* quietly refuse to do anything to a changed disc until the
* changed bit has been reset
*/
goto out;
}
/*
* we do lazy blocksize switching (when reading XA sectors,
* see CDROMREADMODE2 ioctl)
*/
s_size = cd->device->sector_size;
if (s_size > 2048) {
if (!in_interrupt())
sr_set_blocklength(cd, 2048);
else
scmd_printk(KERN_INFO, SCpnt,
"can't switch blocksize: in interrupt\n");
}
if (s_size != 512 && s_size != 1024 && s_size != 2048) {
scmd_printk(KERN_ERR, SCpnt, "bad sector size %d\n", s_size);
goto out;
}
switch (req_op(rq)) {
case REQ_OP_WRITE:
if (!cd->writeable)
goto out;
SCpnt->cmnd[0] = WRITE_10;
cd->cdi.media_written = 1;
break;
case REQ_OP_READ:
SCpnt->cmnd[0] = READ_10;
break;
default:
blk_dump_rq_flags(rq, "Unknown sr command");
goto out;
}
{
struct scatterlist *sg;
int i, size = 0, sg_count = scsi_sg_count(SCpnt);
scsi_for_each_sg(SCpnt, sg, sg_count, i)
size += sg->length;
if (size != scsi_bufflen(SCpnt)) {
scmd_printk(KERN_ERR, SCpnt,
"mismatch count %d, bytes %d\n",
size, scsi_bufflen(SCpnt));
if (scsi_bufflen(SCpnt) > size)
SCpnt->sdb.length = size;
}
}
/*
* request doesn't start on hw block boundary, add scatter pads
*/
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:39 +08:00
if (((unsigned int)blk_rq_pos(rq) % (s_size >> 9)) ||
(scsi_bufflen(SCpnt) % s_size)) {
scmd_printk(KERN_NOTICE, SCpnt, "unaligned transfer\n");
goto out;
}
this_count = (scsi_bufflen(SCpnt) >> 9) / (s_size >> 9);
SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
"%s %d/%u 512 byte blocks.\n",
(rq_data_dir(rq) == WRITE) ?
"writing" : "reading",
this_count, blk_rq_sectors(rq)));
SCpnt->cmnd[1] = 0;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:39 +08:00
block = (unsigned int)blk_rq_pos(rq) / (s_size >> 9);
if (this_count > 0xffff) {
this_count = 0xffff;
SCpnt->sdb.length = this_count * s_size;
}
SCpnt->cmnd[2] = (unsigned char) (block >> 24) & 0xff;
SCpnt->cmnd[3] = (unsigned char) (block >> 16) & 0xff;
SCpnt->cmnd[4] = (unsigned char) (block >> 8) & 0xff;
SCpnt->cmnd[5] = (unsigned char) block & 0xff;
SCpnt->cmnd[6] = SCpnt->cmnd[9] = 0;
SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff;
SCpnt->cmnd[8] = (unsigned char) this_count & 0xff;
/*
* We shouldn't disconnect in the middle of a sector, so with a dumb
* host adapter, it's safe to assume that we can at least transfer
* this many bytes between each connect / disconnect.
*/
SCpnt->transfersize = cd->device->sector_size;
SCpnt->underflow = this_count << 9;
SCpnt->allowed = MAX_RETRIES;
/*
* This indicates that the command is ready from our end to be
* queued.
*/
ret = BLK_STS_OK;
out:
return ret;
}
static int sr_block_open(struct block_device *bdev, fmode_t mode)
{
struct scsi_cd *cd;
2018-08-03 01:44:42 +08:00
struct scsi_device *sdev;
int ret = -ENXIO;
2018-08-03 01:44:42 +08:00
cd = scsi_cd_get(bdev->bd_disk);
if (!cd)
goto out;
sdev = cd->device;
scsi_autopm_get_device(sdev);
cdrom: do not call check_disk_change() inside cdrom_open() when mounting an ISO filesystem sometimes (very rarely) the system hangs because of a race condition between two tasks. PID: 6766 TASK: ffff88007b2a6dd0 CPU: 0 COMMAND: "mount" #0 [ffff880078447ae0] __schedule at ffffffff8168d605 #1 [ffff880078447b48] schedule_preempt_disabled at ffffffff8168ed49 #2 [ffff880078447b58] __mutex_lock_slowpath at ffffffff8168c995 #3 [ffff880078447bb8] mutex_lock at ffffffff8168bdef #4 [ffff880078447bd0] sr_block_ioctl at ffffffffa00b6818 [sr_mod] #5 [ffff880078447c10] blkdev_ioctl at ffffffff812fea50 #6 [ffff880078447c70] ioctl_by_bdev at ffffffff8123a8b3 #7 [ffff880078447c90] isofs_fill_super at ffffffffa04fb1e1 [isofs] #8 [ffff880078447da8] mount_bdev at ffffffff81202570 #9 [ffff880078447e18] isofs_mount at ffffffffa04f9828 [isofs] #10 [ffff880078447e28] mount_fs at ffffffff81202d09 #11 [ffff880078447e70] vfs_kern_mount at ffffffff8121ea8f #12 [ffff880078447ea8] do_mount at ffffffff81220fee #13 [ffff880078447f28] sys_mount at ffffffff812218d6 #14 [ffff880078447f80] system_call_fastpath at ffffffff81698c49 RIP: 00007fd9ea914e9a RSP: 00007ffd5d9bf648 RFLAGS: 00010246 RAX: 00000000000000a5 RBX: ffffffff81698c49 RCX: 0000000000000010 RDX: 00007fd9ec2bc210 RSI: 00007fd9ec2bc290 RDI: 00007fd9ec2bcf30 RBP: 0000000000000000 R8: 0000000000000000 R9: 0000000000000010 R10: 00000000c0ed0001 R11: 0000000000000206 R12: 00007fd9ec2bc040 R13: 00007fd9eb6b2380 R14: 00007fd9ec2bc210 R15: 00007fd9ec2bcf30 ORIG_RAX: 00000000000000a5 CS: 0033 SS: 002b This task was trying to mount the cdrom. It allocated and configured a super_block struct and owned the write-lock for the super_block->s_umount rwsem. While exclusively owning the s_umount lock, it called sr_block_ioctl and waited to acquire the global sr_mutex lock. PID: 6785 TASK: ffff880078720fb0 CPU: 0 COMMAND: "systemd-udevd" #0 [ffff880078417898] __schedule at ffffffff8168d605 #1 [ffff880078417900] schedule at ffffffff8168dc59 #2 [ffff880078417910] rwsem_down_read_failed at ffffffff8168f605 #3 [ffff880078417980] call_rwsem_down_read_failed at ffffffff81328838 #4 [ffff8800784179d0] down_read at ffffffff8168cde0 #5 [ffff8800784179e8] get_super at ffffffff81201cc7 #6 [ffff880078417a10] __invalidate_device at ffffffff8123a8de #7 [ffff880078417a40] flush_disk at ffffffff8123a94b #8 [ffff880078417a88] check_disk_change at ffffffff8123ab50 #9 [ffff880078417ab0] cdrom_open at ffffffffa00a29e1 [cdrom] #10 [ffff880078417b68] sr_block_open at ffffffffa00b6f9b [sr_mod] #11 [ffff880078417b98] __blkdev_get at ffffffff8123ba86 #12 [ffff880078417bf0] blkdev_get at ffffffff8123bd65 #13 [ffff880078417c78] blkdev_open at ffffffff8123bf9b #14 [ffff880078417c90] do_dentry_open at ffffffff811fc7f7 #15 [ffff880078417cd8] vfs_open at ffffffff811fc9cf #16 [ffff880078417d00] do_last at ffffffff8120d53d #17 [ffff880078417db0] path_openat at ffffffff8120e6b2 #18 [ffff880078417e48] do_filp_open at ffffffff8121082b #19 [ffff880078417f18] do_sys_open at ffffffff811fdd33 #20 [ffff880078417f70] sys_open at ffffffff811fde4e #21 [ffff880078417f80] system_call_fastpath at ffffffff81698c49 RIP: 00007f29438b0c20 RSP: 00007ffc76624b78 RFLAGS: 00010246 RAX: 0000000000000002 RBX: ffffffff81698c49 RCX: 0000000000000000 RDX: 00007f2944a5fa70 RSI: 00000000000a0800 RDI: 00007f2944a5fa70 RBP: 00007f2944a5f540 R8: 0000000000000000 R9: 0000000000000020 R10: 00007f2943614c40 R11: 0000000000000246 R12: ffffffff811fde4e R13: ffff880078417f78 R14: 000000000000000c R15: 00007f2944a4b010 ORIG_RAX: 0000000000000002 CS: 0033 SS: 002b This task tried to open the cdrom device, the sr_block_open function acquired the global sr_mutex lock. The call to check_disk_change() then saw an event flag indicating a possible media change and tried to flush any cached data for the device. As part of the flush, it tried to acquire the super_block->s_umount lock associated with the cdrom device. This was the same super_block as created and locked by the previous task. The first task acquires the s_umount lock and then the sr_mutex_lock; the second task acquires the sr_mutex_lock and then the s_umount lock. This patch fixes the issue by moving check_disk_change() out of cdrom_open() and let the caller take care of it. Signed-off-by: Maurizio Lombardi <mlombard@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-03-09 20:59:06 +08:00
check_disk_change(bdev);
mutex_lock(&sr_mutex);
2018-08-03 01:44:42 +08:00
ret = cdrom_open(&cd->cdi, bdev, mode);
mutex_unlock(&sr_mutex);
2018-08-03 01:44:42 +08:00
scsi_autopm_put_device(sdev);
if (ret)
scsi_cd_put(cd);
out:
return ret;
}
static void sr_block_release(struct gendisk *disk, fmode_t mode)
{
struct scsi_cd *cd = scsi_cd(disk);
mutex_lock(&sr_mutex);
cdrom_release(&cd->cdi, mode);
scsi_cd_put(cd);
mutex_unlock(&sr_mutex);
}
static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
unsigned long arg)
{
struct scsi_cd *cd = scsi_cd(bdev->bd_disk);
struct scsi_device *sdev = cd->device;
void __user *argp = (void __user *)arg;
int ret;
mutex_lock(&sr_mutex);
ret = scsi_ioctl_block_when_processing_errors(sdev, cmd,
(mode & FMODE_NDELAY) != 0);
if (ret)
goto out;
2018-08-03 01:44:42 +08:00
scsi_autopm_get_device(sdev);
/*
* Send SCSI addressing ioctls directly to mid level, send other
* ioctls to cdrom/block level.
*/
switch (cmd) {
case SCSI_IOCTL_GET_IDLUN:
case SCSI_IOCTL_GET_BUS_NUMBER:
ret = scsi_ioctl(sdev, cmd, argp);
2018-08-03 01:44:42 +08:00
goto put;
}
ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg);
if (ret != -ENOSYS)
2018-08-03 01:44:42 +08:00
goto put;
ret = scsi_ioctl(sdev, cmd, argp);
2018-08-03 01:44:42 +08:00
put:
scsi_autopm_put_device(sdev);
out:
mutex_unlock(&sr_mutex);
return ret;
}
static unsigned int sr_block_check_events(struct gendisk *disk,
unsigned int clearing)
{
sr: get/drop reference to device in revalidate and check_events We can't just use scsi_cd() to get the scsi_cd structure, we have to grab a live reference to the device. For both callbacks, we're not inside an open where we already hold a reference to the device. This fixes device removal/addition under concurrent device access, which otherwise could result in the below oops. NULL pointer dereference at 0000000000000010 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: sr 12:0:0:0: [sr2] scsi-1 drive scsi_debug crc_t10dif crct10dif_generic crct10dif_common nvme nvme_core sb_edac xl sr 12:0:0:0: Attached scsi CD-ROM sr2 sr_mod cdrom btrfs xor zstd_decompress zstd_compress xxhash lzo_compress zlib_defc sr 12:0:0:0: Attached scsi generic sg7 type 5 igb ahci libahci i2c_algo_bit libata dca [last unloaded: crc_t10dif] CPU: 43 PID: 4629 Comm: systemd-udevd Not tainted 4.16.0+ #650 Hardware name: Dell Inc. PowerEdge T630/0NT78X, BIOS 2.3.4 11/09/2016 RIP: 0010:sr_block_revalidate_disk+0x23/0x190 [sr_mod] RSP: 0018:ffff883ff357bb58 EFLAGS: 00010292 RAX: ffffffffa00b07d0 RBX: ffff883ff3058000 RCX: ffff883ff357bb66 RDX: 0000000000000003 RSI: 0000000000007530 RDI: ffff881fea631000 RBP: 0000000000000000 R08: ffff881fe4d38400 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000001b6 R12: 000000000800005d R13: 000000000800005d R14: ffff883ffd9b3790 R15: 0000000000000000 FS: 00007f7dc8e6d8c0(0000) GS:ffff883fff340000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000003ffda98005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __invalidate_device+0x48/0x60 check_disk_change+0x4c/0x60 sr_block_open+0x16/0xd0 [sr_mod] __blkdev_get+0xb9/0x450 ? iget5_locked+0x1c0/0x1e0 blkdev_get+0x11e/0x320 ? bdget+0x11d/0x150 ? _raw_spin_unlock+0xa/0x20 ? bd_acquire+0xc0/0xc0 do_dentry_open+0x1b0/0x320 ? inode_permission+0x24/0xc0 path_openat+0x4e6/0x1420 ? cpumask_any_but+0x1f/0x40 ? flush_tlb_mm_range+0xa0/0x120 do_filp_open+0x8c/0xf0 ? __seccomp_filter+0x28/0x230 ? _raw_spin_unlock+0xa/0x20 ? __handle_mm_fault+0x7d6/0x9b0 ? list_lru_add+0xa8/0xc0 ? _raw_spin_unlock+0xa/0x20 ? __alloc_fd+0xaf/0x160 ? do_sys_open+0x1a6/0x230 do_sys_open+0x1a6/0x230 do_syscall_64+0x5a/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Reviewed-by: Lee Duncan <lduncan@suse.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-04-12 01:26:09 +08:00
unsigned int ret = 0;
struct scsi_cd *cd;
sr: get/drop reference to device in revalidate and check_events We can't just use scsi_cd() to get the scsi_cd structure, we have to grab a live reference to the device. For both callbacks, we're not inside an open where we already hold a reference to the device. This fixes device removal/addition under concurrent device access, which otherwise could result in the below oops. NULL pointer dereference at 0000000000000010 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: sr 12:0:0:0: [sr2] scsi-1 drive scsi_debug crc_t10dif crct10dif_generic crct10dif_common nvme nvme_core sb_edac xl sr 12:0:0:0: Attached scsi CD-ROM sr2 sr_mod cdrom btrfs xor zstd_decompress zstd_compress xxhash lzo_compress zlib_defc sr 12:0:0:0: Attached scsi generic sg7 type 5 igb ahci libahci i2c_algo_bit libata dca [last unloaded: crc_t10dif] CPU: 43 PID: 4629 Comm: systemd-udevd Not tainted 4.16.0+ #650 Hardware name: Dell Inc. PowerEdge T630/0NT78X, BIOS 2.3.4 11/09/2016 RIP: 0010:sr_block_revalidate_disk+0x23/0x190 [sr_mod] RSP: 0018:ffff883ff357bb58 EFLAGS: 00010292 RAX: ffffffffa00b07d0 RBX: ffff883ff3058000 RCX: ffff883ff357bb66 RDX: 0000000000000003 RSI: 0000000000007530 RDI: ffff881fea631000 RBP: 0000000000000000 R08: ffff881fe4d38400 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000001b6 R12: 000000000800005d R13: 000000000800005d R14: ffff883ffd9b3790 R15: 0000000000000000 FS: 00007f7dc8e6d8c0(0000) GS:ffff883fff340000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000003ffda98005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __invalidate_device+0x48/0x60 check_disk_change+0x4c/0x60 sr_block_open+0x16/0xd0 [sr_mod] __blkdev_get+0xb9/0x450 ? iget5_locked+0x1c0/0x1e0 blkdev_get+0x11e/0x320 ? bdget+0x11d/0x150 ? _raw_spin_unlock+0xa/0x20 ? bd_acquire+0xc0/0xc0 do_dentry_open+0x1b0/0x320 ? inode_permission+0x24/0xc0 path_openat+0x4e6/0x1420 ? cpumask_any_but+0x1f/0x40 ? flush_tlb_mm_range+0xa0/0x120 do_filp_open+0x8c/0xf0 ? __seccomp_filter+0x28/0x230 ? _raw_spin_unlock+0xa/0x20 ? __handle_mm_fault+0x7d6/0x9b0 ? list_lru_add+0xa8/0xc0 ? _raw_spin_unlock+0xa/0x20 ? __alloc_fd+0xaf/0x160 ? do_sys_open+0x1a6/0x230 do_sys_open+0x1a6/0x230 do_syscall_64+0x5a/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Reviewed-by: Lee Duncan <lduncan@suse.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-04-12 01:26:09 +08:00
cd = scsi_cd_get(disk);
if (!cd)
return 0;
sr: get/drop reference to device in revalidate and check_events We can't just use scsi_cd() to get the scsi_cd structure, we have to grab a live reference to the device. For both callbacks, we're not inside an open where we already hold a reference to the device. This fixes device removal/addition under concurrent device access, which otherwise could result in the below oops. NULL pointer dereference at 0000000000000010 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: sr 12:0:0:0: [sr2] scsi-1 drive scsi_debug crc_t10dif crct10dif_generic crct10dif_common nvme nvme_core sb_edac xl sr 12:0:0:0: Attached scsi CD-ROM sr2 sr_mod cdrom btrfs xor zstd_decompress zstd_compress xxhash lzo_compress zlib_defc sr 12:0:0:0: Attached scsi generic sg7 type 5 igb ahci libahci i2c_algo_bit libata dca [last unloaded: crc_t10dif] CPU: 43 PID: 4629 Comm: systemd-udevd Not tainted 4.16.0+ #650 Hardware name: Dell Inc. PowerEdge T630/0NT78X, BIOS 2.3.4 11/09/2016 RIP: 0010:sr_block_revalidate_disk+0x23/0x190 [sr_mod] RSP: 0018:ffff883ff357bb58 EFLAGS: 00010292 RAX: ffffffffa00b07d0 RBX: ffff883ff3058000 RCX: ffff883ff357bb66 RDX: 0000000000000003 RSI: 0000000000007530 RDI: ffff881fea631000 RBP: 0000000000000000 R08: ffff881fe4d38400 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000001b6 R12: 000000000800005d R13: 000000000800005d R14: ffff883ffd9b3790 R15: 0000000000000000 FS: 00007f7dc8e6d8c0(0000) GS:ffff883fff340000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000003ffda98005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __invalidate_device+0x48/0x60 check_disk_change+0x4c/0x60 sr_block_open+0x16/0xd0 [sr_mod] __blkdev_get+0xb9/0x450 ? iget5_locked+0x1c0/0x1e0 blkdev_get+0x11e/0x320 ? bdget+0x11d/0x150 ? _raw_spin_unlock+0xa/0x20 ? bd_acquire+0xc0/0xc0 do_dentry_open+0x1b0/0x320 ? inode_permission+0x24/0xc0 path_openat+0x4e6/0x1420 ? cpumask_any_but+0x1f/0x40 ? flush_tlb_mm_range+0xa0/0x120 do_filp_open+0x8c/0xf0 ? __seccomp_filter+0x28/0x230 ? _raw_spin_unlock+0xa/0x20 ? __handle_mm_fault+0x7d6/0x9b0 ? list_lru_add+0xa8/0xc0 ? _raw_spin_unlock+0xa/0x20 ? __alloc_fd+0xaf/0x160 ? do_sys_open+0x1a6/0x230 do_sys_open+0x1a6/0x230 do_syscall_64+0x5a/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Reviewed-by: Lee Duncan <lduncan@suse.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-04-12 01:26:09 +08:00
if (!atomic_read(&cd->device->disk_events_disable_depth))
ret = cdrom_check_events(&cd->cdi, clearing);
scsi_cd_put(cd);
return ret;
}
static int sr_block_revalidate_disk(struct gendisk *disk)
{
struct scsi_sense_hdr sshdr;
sr: get/drop reference to device in revalidate and check_events We can't just use scsi_cd() to get the scsi_cd structure, we have to grab a live reference to the device. For both callbacks, we're not inside an open where we already hold a reference to the device. This fixes device removal/addition under concurrent device access, which otherwise could result in the below oops. NULL pointer dereference at 0000000000000010 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: sr 12:0:0:0: [sr2] scsi-1 drive scsi_debug crc_t10dif crct10dif_generic crct10dif_common nvme nvme_core sb_edac xl sr 12:0:0:0: Attached scsi CD-ROM sr2 sr_mod cdrom btrfs xor zstd_decompress zstd_compress xxhash lzo_compress zlib_defc sr 12:0:0:0: Attached scsi generic sg7 type 5 igb ahci libahci i2c_algo_bit libata dca [last unloaded: crc_t10dif] CPU: 43 PID: 4629 Comm: systemd-udevd Not tainted 4.16.0+ #650 Hardware name: Dell Inc. PowerEdge T630/0NT78X, BIOS 2.3.4 11/09/2016 RIP: 0010:sr_block_revalidate_disk+0x23/0x190 [sr_mod] RSP: 0018:ffff883ff357bb58 EFLAGS: 00010292 RAX: ffffffffa00b07d0 RBX: ffff883ff3058000 RCX: ffff883ff357bb66 RDX: 0000000000000003 RSI: 0000000000007530 RDI: ffff881fea631000 RBP: 0000000000000000 R08: ffff881fe4d38400 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000001b6 R12: 000000000800005d R13: 000000000800005d R14: ffff883ffd9b3790 R15: 0000000000000000 FS: 00007f7dc8e6d8c0(0000) GS:ffff883fff340000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000003ffda98005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __invalidate_device+0x48/0x60 check_disk_change+0x4c/0x60 sr_block_open+0x16/0xd0 [sr_mod] __blkdev_get+0xb9/0x450 ? iget5_locked+0x1c0/0x1e0 blkdev_get+0x11e/0x320 ? bdget+0x11d/0x150 ? _raw_spin_unlock+0xa/0x20 ? bd_acquire+0xc0/0xc0 do_dentry_open+0x1b0/0x320 ? inode_permission+0x24/0xc0 path_openat+0x4e6/0x1420 ? cpumask_any_but+0x1f/0x40 ? flush_tlb_mm_range+0xa0/0x120 do_filp_open+0x8c/0xf0 ? __seccomp_filter+0x28/0x230 ? _raw_spin_unlock+0xa/0x20 ? __handle_mm_fault+0x7d6/0x9b0 ? list_lru_add+0xa8/0xc0 ? _raw_spin_unlock+0xa/0x20 ? __alloc_fd+0xaf/0x160 ? do_sys_open+0x1a6/0x230 do_sys_open+0x1a6/0x230 do_syscall_64+0x5a/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Reviewed-by: Lee Duncan <lduncan@suse.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-04-12 01:26:09 +08:00
struct scsi_cd *cd;
cd = scsi_cd_get(disk);
if (!cd)
return -ENXIO;
/* if the unit is not ready, nothing more to do */
if (scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr))
goto out;
sr_cd_check(&cd->cdi);
get_sectorsize(cd);
out:
sr: get/drop reference to device in revalidate and check_events We can't just use scsi_cd() to get the scsi_cd structure, we have to grab a live reference to the device. For both callbacks, we're not inside an open where we already hold a reference to the device. This fixes device removal/addition under concurrent device access, which otherwise could result in the below oops. NULL pointer dereference at 0000000000000010 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: sr 12:0:0:0: [sr2] scsi-1 drive scsi_debug crc_t10dif crct10dif_generic crct10dif_common nvme nvme_core sb_edac xl sr 12:0:0:0: Attached scsi CD-ROM sr2 sr_mod cdrom btrfs xor zstd_decompress zstd_compress xxhash lzo_compress zlib_defc sr 12:0:0:0: Attached scsi generic sg7 type 5 igb ahci libahci i2c_algo_bit libata dca [last unloaded: crc_t10dif] CPU: 43 PID: 4629 Comm: systemd-udevd Not tainted 4.16.0+ #650 Hardware name: Dell Inc. PowerEdge T630/0NT78X, BIOS 2.3.4 11/09/2016 RIP: 0010:sr_block_revalidate_disk+0x23/0x190 [sr_mod] RSP: 0018:ffff883ff357bb58 EFLAGS: 00010292 RAX: ffffffffa00b07d0 RBX: ffff883ff3058000 RCX: ffff883ff357bb66 RDX: 0000000000000003 RSI: 0000000000007530 RDI: ffff881fea631000 RBP: 0000000000000000 R08: ffff881fe4d38400 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000000001b6 R12: 000000000800005d R13: 000000000800005d R14: ffff883ffd9b3790 R15: 0000000000000000 FS: 00007f7dc8e6d8c0(0000) GS:ffff883fff340000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000003ffda98005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? __invalidate_device+0x48/0x60 check_disk_change+0x4c/0x60 sr_block_open+0x16/0xd0 [sr_mod] __blkdev_get+0xb9/0x450 ? iget5_locked+0x1c0/0x1e0 blkdev_get+0x11e/0x320 ? bdget+0x11d/0x150 ? _raw_spin_unlock+0xa/0x20 ? bd_acquire+0xc0/0xc0 do_dentry_open+0x1b0/0x320 ? inode_permission+0x24/0xc0 path_openat+0x4e6/0x1420 ? cpumask_any_but+0x1f/0x40 ? flush_tlb_mm_range+0xa0/0x120 do_filp_open+0x8c/0xf0 ? __seccomp_filter+0x28/0x230 ? _raw_spin_unlock+0xa/0x20 ? __handle_mm_fault+0x7d6/0x9b0 ? list_lru_add+0xa8/0xc0 ? _raw_spin_unlock+0xa/0x20 ? __alloc_fd+0xaf/0x160 ? do_sys_open+0x1a6/0x230 do_sys_open+0x1a6/0x230 do_syscall_64+0x5a/0x100 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Reviewed-by: Lee Duncan <lduncan@suse.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-04-12 01:26:09 +08:00
scsi_cd_put(cd);
return 0;
}
static const struct block_device_operations sr_bdops =
{
.owner = THIS_MODULE,
.open = sr_block_open,
.release = sr_block_release,
.ioctl = sr_block_ioctl,
.check_events = sr_block_check_events,
.revalidate_disk = sr_block_revalidate_disk,
/*
* No compat_ioctl for now because sr_block_ioctl never
* seems to pass arbitrary ioctls down to host drivers.
*/
};
static int sr_open(struct cdrom_device_info *cdi, int purpose)
{
struct scsi_cd *cd = cdi->handle;
struct scsi_device *sdev = cd->device;
int retval;
/*
* If the device is in error recovery, wait until it is done.
* If the device is offline, then disallow any access to it.
*/
retval = -ENXIO;
if (!scsi_block_when_processing_errors(sdev))
goto error_out;
return 0;
error_out:
return retval;
}
static void sr_release(struct cdrom_device_info *cdi)
{
struct scsi_cd *cd = cdi->handle;
if (cd->device->sector_size > 2048)
sr_set_blocklength(cd, 2048);
}
static int sr_probe(struct device *dev)
{
struct scsi_device *sdev = to_scsi_device(dev);
struct gendisk *disk;
struct scsi_cd *cd;
int minor, error;
scsi_autopm_get_device(sdev);
error = -ENODEV;
if (sdev->type != TYPE_ROM && sdev->type != TYPE_WORM)
goto fail;
error = -ENOMEM;
cd = kzalloc(sizeof(*cd), GFP_KERNEL);
if (!cd)
goto fail;
kref_init(&cd->kref);
disk = alloc_disk(1);
if (!disk)
goto fail_free;
spin_lock(&sr_index_lock);
minor = find_first_zero_bit(sr_index_bits, SR_DISKS);
if (minor == SR_DISKS) {
spin_unlock(&sr_index_lock);
error = -EBUSY;
goto fail_put;
}
__set_bit(minor, sr_index_bits);
spin_unlock(&sr_index_lock);
disk->major = SCSI_CDROM_MAJOR;
disk->first_minor = minor;
sprintf(disk->disk_name, "sr%d", minor);
disk->fops = &sr_bdops;
disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT);
cd->device = sdev;
cd->disk = disk;
cd->driver = &sr_template;
cd->disk = disk;
cd->capacity = 0x1fffff;
cd->device->changed = 1; /* force recheck CD type */
cd->media_present = 1;
cd->use = 1;
cd->readcd_known = 0;
cd->readcd_cdda = 0;
cd->cdi.ops = &sr_dops;
cd->cdi.handle = cd;
cd->cdi.mask = 0;
cd->cdi.capacity = 1;
sprintf(cd->cdi.name, "sr%d", minor);
sdev->sector_size = 2048; /* A guess, just in case */
/* FIXME: need to handle a get_capabilities failure properly ?? */
get_capabilities(cd);
sr_vendor_init(cd);
set_capacity(disk, cd->capacity);
disk->private_data = &cd->driver;
disk->queue = sdev->request_queue;
cd->cdi.disk = disk;
if (register_cdrom(&cd->cdi))
goto fail_put;
/*
* Initialize block layer runtime PM stuffs before the
* periodic event checking request gets started in add_disk.
*/
blk_pm_runtime_init(sdev->request_queue, dev);
dev_set_drvdata(dev, cd);
disk->flags |= GENHD_FL_REMOVABLE;
device_add_disk(&sdev->sdev_gendev, disk, NULL);
sdev_printk(KERN_DEBUG, sdev,
"Attached scsi CD-ROM %s\n", cd->cdi.name);
scsi_autopm_put_device(cd->device);
return 0;
fail_put:
put_disk(disk);
fail_free:
kfree(cd);
fail:
scsi_autopm_put_device(sdev);
return error;
}
static void get_sectorsize(struct scsi_cd *cd)
{
unsigned char cmd[10];
unsigned char buffer[8];
int the_result, retries = 3;
int sector_size;
struct request_queue *queue;
do {
cmd[0] = READ_CAPACITY;
memset((void *) &cmd[1], 0, 9);
memset(buffer, 0, sizeof(buffer));
/* Do the command and wait.. */
the_result = scsi_execute_req(cd->device, cmd, DMA_FROM_DEVICE,
buffer, sizeof(buffer), NULL,
SR_TIMEOUT, MAX_RETRIES, NULL);
retries--;
} while (the_result && retries);
if (the_result) {
cd->capacity = 0x1fffff;
sector_size = 2048; /* A guess, just in case */
} else {
long last_written;
cd->capacity = 1 + ((buffer[0] << 24) | (buffer[1] << 16) |
(buffer[2] << 8) | buffer[3]);
/*
* READ_CAPACITY doesn't return the correct size on
* certain UDF media. If last_written is larger, use
* it instead.
*
* http://bugzilla.kernel.org/show_bug.cgi?id=9668
*/
if (!cdrom_get_last_written(&cd->cdi, &last_written))
cd->capacity = max_t(long, cd->capacity, last_written);
sector_size = (buffer[4] << 24) |
(buffer[5] << 16) | (buffer[6] << 8) | buffer[7];
switch (sector_size) {
/*
* HP 4020i CD-Recorder reports 2340 byte sectors
* Philips CD-Writers report 2352 byte sectors
*
* Use 2k sectors for them..
*/
case 0:
case 2340:
case 2352:
sector_size = 2048;
/* fall through */
case 2048:
cd->capacity *= 4;
/* fall through */
case 512:
break;
default:
sr_printk(KERN_INFO, cd,
"unsupported sector size %d.", sector_size);
cd->capacity = 0;
}
cd->device->sector_size = sector_size;
/*
* Add this so that we have the ability to correctly gauge
* what the device is capable of.
*/
set_capacity(cd->disk, cd->capacity);
}
queue = cd->device->request_queue;
blk_queue_logical_block_size(queue, sector_size);
return;
}
static void get_capabilities(struct scsi_cd *cd)
{
unsigned char *buffer;
struct scsi_mode_data data;
struct scsi_sense_hdr sshdr;
unsigned int ms_len = 128;
int rc, n;
static const char *loadmech[] =
{
"caddy",
"tray",
"pop-up",
"",
"changer",
"cartridge changer",
"",
""
};
/* allocate transfer buffer */
buffer = kmalloc(512, GFP_KERNEL | GFP_DMA);
if (!buffer) {
sr_printk(KERN_ERR, cd, "out of memory.\n");
return;
}
/* eat unit attentions */
scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr);
/* ask for mode page 0x2a */
rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, ms_len,
SR_TIMEOUT, 3, &data, NULL);
if (!scsi_status_is_good(rc) || data.length > ms_len ||
data.header_length + data.block_descriptor_length > data.length) {
/* failed, drive doesn't have capabilities mode page */
cd->cdi.speed = 1;
cd->cdi.mask |= (CDC_CD_R | CDC_CD_RW | CDC_DVD_R |
CDC_DVD | CDC_DVD_RAM |
CDC_SELECT_DISC | CDC_SELECT_SPEED |
CDC_MRW | CDC_MRW_W | CDC_RAM);
kfree(buffer);
sr_printk(KERN_INFO, cd, "scsi-1 drive");
return;
}
n = data.header_length + data.block_descriptor_length;
cd->cdi.speed = ((buffer[n + 8] << 8) + buffer[n + 9]) / 176;
cd->readcd_known = 1;
cd->readcd_cdda = buffer[n + 5] & 0x01;
/* print some capability bits */
sr_printk(KERN_INFO, cd,
"scsi3-mmc drive: %dx/%dx %s%s%s%s%s%s\n",
((buffer[n + 14] << 8) + buffer[n + 15]) / 176,
cd->cdi.speed,
buffer[n + 3] & 0x01 ? "writer " : "", /* CD Writer */
buffer[n + 3] & 0x20 ? "dvd-ram " : "",
buffer[n + 2] & 0x02 ? "cd/rw " : "", /* can read rewriteable */
buffer[n + 4] & 0x20 ? "xa/form2 " : "", /* can read xa/from2 */
buffer[n + 5] & 0x01 ? "cdda " : "", /* can read audio data */
loadmech[buffer[n + 6] >> 5]);
if ((buffer[n + 6] >> 5) == 0)
/* caddy drives can't close tray... */
cd->cdi.mask |= CDC_CLOSE_TRAY;
if ((buffer[n + 2] & 0x8) == 0)
/* not a DVD drive */
cd->cdi.mask |= CDC_DVD;
if ((buffer[n + 3] & 0x20) == 0)
/* can't write DVD-RAM media */
cd->cdi.mask |= CDC_DVD_RAM;
if ((buffer[n + 3] & 0x10) == 0)
/* can't write DVD-R media */
cd->cdi.mask |= CDC_DVD_R;
if ((buffer[n + 3] & 0x2) == 0)
/* can't write CD-RW media */
cd->cdi.mask |= CDC_CD_RW;
if ((buffer[n + 3] & 0x1) == 0)
/* can't write CD-R media */
cd->cdi.mask |= CDC_CD_R;
if ((buffer[n + 6] & 0x8) == 0)
/* can't eject */
cd->cdi.mask |= CDC_OPEN_TRAY;
if ((buffer[n + 6] >> 5) == mechtype_individual_changer ||
(buffer[n + 6] >> 5) == mechtype_cartridge_changer)
cd->cdi.capacity =
cdrom_number_of_slots(&cd->cdi);
if (cd->cdi.capacity <= 1)
/* not a changer */
cd->cdi.mask |= CDC_SELECT_DISC;
/*else I don't think it can close its tray
cd->cdi.mask |= CDC_CLOSE_TRAY; */
/*
* if DVD-RAM, MRW-W or CD-RW, we are randomly writable
*/
if ((cd->cdi.mask & (CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) !=
(CDC_DVD_RAM | CDC_MRW_W | CDC_RAM | CDC_CD_RW)) {
cd->writeable = 1;
}
kfree(buffer);
}
/*
* sr_packet() is the entry point for the generic commands generated
* by the Uniform CD-ROM layer.
*/
static int sr_packet(struct cdrom_device_info *cdi,
struct packet_command *cgc)
{
struct scsi_cd *cd = cdi->handle;
struct scsi_device *sdev = cd->device;
if (cgc->cmd[0] == GPCMD_READ_DISC_INFO && sdev->no_read_disc_info)
return -EDRIVE_CANT_DO_THIS;
if (cgc->timeout <= 0)
cgc->timeout = IOCTL_TIMEOUT;
sr_do_ioctl(cd, cgc);
return cgc->stat;
}
/**
* sr_kref_release - Called to free the scsi_cd structure
* @kref: pointer to embedded kref
*
* sr_ref_mutex must be held entering this routine. Because it is
* called on last put, you should always use the scsi_cd_get()
* scsi_cd_put() helpers which manipulate the semaphore directly
* and never do a direct kref_put().
**/
static void sr_kref_release(struct kref *kref)
{
struct scsi_cd *cd = container_of(kref, struct scsi_cd, kref);
struct gendisk *disk = cd->disk;
spin_lock(&sr_index_lock);
clear_bit(MINOR(disk_devt(disk)), sr_index_bits);
spin_unlock(&sr_index_lock);
unregister_cdrom(&cd->cdi);
disk->private_data = NULL;
put_disk(disk);
kfree(cd);
}
static int sr_remove(struct device *dev)
{
struct scsi_cd *cd = dev_get_drvdata(dev);
scsi_autopm_get_device(cd->device);
del_gendisk(cd->disk);
dev_set_drvdata(dev, NULL);
mutex_lock(&sr_ref_mutex);
kref_put(&cd->kref, sr_kref_release);
mutex_unlock(&sr_ref_mutex);
return 0;
}
static int __init init_sr(void)
{
int rc;
rc = register_blkdev(SCSI_CDROM_MAJOR, "sr");
if (rc)
return rc;
rc = scsi_register_driver(&sr_template.gendrv);
if (rc)
unregister_blkdev(SCSI_CDROM_MAJOR, "sr");
return rc;
}
static void __exit exit_sr(void)
{
scsi_unregister_driver(&sr_template.gendrv);
unregister_blkdev(SCSI_CDROM_MAJOR, "sr");
}
module_init(init_sr);
module_exit(exit_sr);
MODULE_LICENSE("GPL");