linux/drivers/scsi/sd.c

2754 lines
72 KiB
C
Raw Normal View History

/*
* sd.c Copyright (C) 1992 Drew Eckhardt
* Copyright (C) 1993, 1994, 1995, 1999 Eric Youngdale
*
* Linux scsi disk driver
* Initial versions: Drew Eckhardt
* Subsequent revisions: Eric Youngdale
* Modification history:
* - Drew Eckhardt <drew@colorado.edu> original
* - Eric Youngdale <eric@andante.org> add scatter-gather, multiple
* outstanding request, and other enhancements.
* Support loadable low-level scsi drivers.
* - Jirka Hanika <geo@ff.cuni.cz> support more scsi disks using
* eight major numbers.
* - Richard Gooch <rgooch@atnf.csiro.au> support devfs.
* - Torben Mathiasen <tmm@image.dk> Resource allocation fixes in
* sd_init and cleanups.
* - Alex Davis <letmein@erols.com> Fix problem where partition info
* not being read in sd_open. Fix problem where removable media
* could be ejected after sd_open.
* - Douglas Gilbert <dgilbert@interlog.com> cleanup for lk 2.5.x
* - Badari Pulavarty <pbadari@us.ibm.com>, Matthew Wilcox
* <willy@debian.org>, Kurt Garloff <garloff@suse.de>:
* Support 32k/1M disks.
*
* Logging policy (needs CONFIG_SCSI_LOGGING defined):
* - setting up transfer: SCSI_LOG_HLQUEUE levels 1 and 2
* - end of transfer (bh + scsi_lib): SCSI_LOG_HLCOMPLETE level 1
* - entering sd_ioctl: SCSI_LOG_IOCTL level 1
* - entering other commands: SCSI_LOG_HLQUEUE level 3
* Note: when the logging level is set by the user, it must be greater
* than the level indicated above to trigger output.
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bio.h>
#include <linux/genhd.h>
#include <linux/hdreg.h>
#include <linux/errno.h>
#include <linux/idr.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/delay.h>
#include <linux/mutex.h>
#include <linux/string_helpers.h>
#include <linux/async.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 08:04:11 +00:00
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/unaligned.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/scsicam.h>
#include "sd.h"
#include "scsi_logging.h"
MODULE_AUTHOR("Eric Youngdale");
MODULE_DESCRIPTION("SCSI disk (sd) driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK0_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK1_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK2_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK3_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK4_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK5_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK6_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK7_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK8_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK9_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK10_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK11_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK12_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK13_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK14_MAJOR);
MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK15_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 12:02:37 +00:00
MODULE_ALIAS_SCSI_DEVICE(TYPE_DISK);
MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD);
MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);
#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT)
#define SD_MINORS 16
#else
#define SD_MINORS 0
#endif
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>
2008-01-06 18:17:12 +00:00
static int sd_revalidate_disk(struct gendisk *);
static void sd_unlock_native_capacity(struct gendisk *disk);
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>
2008-01-06 18:17:12 +00:00
static int sd_probe(struct device *);
static int sd_remove(struct device *);
static void sd_shutdown(struct device *);
static int sd_suspend(struct device *, pm_message_t state);
static int sd_resume(struct device *);
static void sd_rescan(struct device *);
static int sd_done(struct scsi_cmnd *);
static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer);
static void scsi_disk_release(struct device *cdev);
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>
2008-01-06 18:17:12 +00:00
static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *);
static void sd_print_result(struct scsi_disk *, int);
static DEFINE_SPINLOCK(sd_index_lock);
static DEFINE_IDA(sd_index_ida);
/* 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(sd_ref_mutex);
static struct kmem_cache *sd_cdb_cache;
static mempool_t *sd_cdb_pool;
static const char *sd_cache_types[] = {
"write through", "none", "write back",
"write back, no read (daft)"
};
static ssize_t
sd_store_cache_type(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
int i, ct = -1, rcd, wce, sp;
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
char buffer[64];
char *buffer_data;
struct scsi_mode_data data;
struct scsi_sense_hdr sshdr;
int len;
if (sdp->type != TYPE_DISK)
/* no cache control on RBC devices; theoretically they
* can do it, but there's probably so many exceptions
* it's not worth the risk */
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(sd_cache_types); i++) {
len = strlen(sd_cache_types[i]);
if (strncmp(sd_cache_types[i], buf, len) == 0 &&
buf[len] == '\n') {
ct = i;
break;
}
}
if (ct < 0)
return -EINVAL;
rcd = ct & 0x01 ? 1 : 0;
wce = ct & 0x02 ? 1 : 0;
if (scsi_mode_sense(sdp, 0x08, 8, buffer, sizeof(buffer), SD_TIMEOUT,
SD_MAX_RETRIES, &data, NULL))
return -EINVAL;
len = min_t(size_t, sizeof(buffer), data.length - data.header_length -
data.block_descriptor_length);
buffer_data = buffer + data.header_length +
data.block_descriptor_length;
buffer_data[2] &= ~0x05;
buffer_data[2] |= wce << 2 | rcd;
sp = buffer_data[0] & 0x80 ? 1 : 0;
if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT,
SD_MAX_RETRIES, &data, &sshdr)) {
if (scsi_sense_valid(&sshdr))
sd_print_sense_hdr(sdkp, &sshdr);
return -EINVAL;
}
revalidate_disk(sdkp->disk);
return count;
}
static ssize_t
sd_store_manage_start_stop(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
sdp->manage_start_stop = simple_strtoul(buf, NULL, 10);
return count;
}
static ssize_t
sd_store_allow_restart(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (sdp->type != TYPE_DISK)
return -EINVAL;
sdp->allow_restart = simple_strtoul(buf, NULL, 10);
return count;
}
static ssize_t
sd_show_cache_type(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
int ct = sdkp->RCD + 2*sdkp->WCE;
return snprintf(buf, 40, "%s\n", sd_cache_types[ct]);
}
static ssize_t
sd_show_fua(struct device *dev, struct device_attribute *attr, char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return snprintf(buf, 20, "%u\n", sdkp->DPOFUA);
}
static ssize_t
sd_show_manage_start_stop(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
return snprintf(buf, 20, "%u\n", sdp->manage_start_stop);
}
static ssize_t
sd_show_allow_restart(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return snprintf(buf, 40, "%d\n", sdkp->device->allow_restart);
}
static ssize_t
sd_show_protection_type(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return snprintf(buf, 20, "%u\n", sdkp->protection_type);
}
static ssize_t
sd_show_protection_mode(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
unsigned int dif, dix;
dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type);
dix = scsi_host_dix_capable(sdp->host, sdkp->protection_type);
if (!dix && scsi_host_dix_capable(sdp->host, SD_DIF_TYPE0_PROTECTION)) {
dif = 0;
dix = 1;
}
if (!dif && !dix)
return snprintf(buf, 20, "none\n");
return snprintf(buf, 20, "%s%u\n", dix ? "dix" : "dif", dif);
}
static ssize_t
sd_show_app_tag_own(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return snprintf(buf, 20, "%u\n", sdkp->ATO);
}
static ssize_t
sd_show_thin_provisioning(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return snprintf(buf, 20, "%u\n", sdkp->thin_provisioning);
}
static struct device_attribute sd_disk_attrs[] = {
__ATTR(cache_type, S_IRUGO|S_IWUSR, sd_show_cache_type,
sd_store_cache_type),
__ATTR(FUA, S_IRUGO, sd_show_fua, NULL),
__ATTR(allow_restart, S_IRUGO|S_IWUSR, sd_show_allow_restart,
sd_store_allow_restart),
__ATTR(manage_start_stop, S_IRUGO|S_IWUSR, sd_show_manage_start_stop,
sd_store_manage_start_stop),
__ATTR(protection_type, S_IRUGO, sd_show_protection_type, NULL),
__ATTR(protection_mode, S_IRUGO, sd_show_protection_mode, NULL),
__ATTR(app_tag_own, S_IRUGO, sd_show_app_tag_own, NULL),
__ATTR(thin_provisioning, S_IRUGO, sd_show_thin_provisioning, NULL),
__ATTR_NULL,
};
static struct class sd_disk_class = {
.name = "scsi_disk",
.owner = THIS_MODULE,
.dev_release = scsi_disk_release,
.dev_attrs = sd_disk_attrs,
};
static struct scsi_driver sd_template = {
.owner = THIS_MODULE,
.gendrv = {
.name = "sd",
.probe = sd_probe,
.remove = sd_remove,
.suspend = sd_suspend,
.resume = sd_resume,
.shutdown = sd_shutdown,
},
.rescan = sd_rescan,
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>
2008-01-06 18:17:12 +00:00
.done = sd_done,
};
/*
* Device no to disk mapping:
*
* major disc2 disc p1
* |............|.............|....|....| <- dev_t
* 31 20 19 8 7 4 3 0
*
* Inside a major, we have 16k disks, however mapped non-
* contiguously. The first 16 disks are for major0, the next
* ones with major1, ... Disk 256 is for major0 again, disk 272
* for major1, ...
* As we stay compatible with our numbering scheme, we can reuse
* the well-know SCSI majors 8, 65--71, 136--143.
*/
static int sd_major(int major_idx)
{
switch (major_idx) {
case 0:
return SCSI_DISK0_MAJOR;
case 1 ... 7:
return SCSI_DISK1_MAJOR + major_idx - 1;
case 8 ... 15:
return SCSI_DISK8_MAJOR + major_idx - 8;
default:
BUG();
return 0; /* shut up gcc */
}
}
static struct scsi_disk *__scsi_disk_get(struct gendisk *disk)
{
struct scsi_disk *sdkp = NULL;
if (disk->private_data) {
sdkp = scsi_disk(disk);
if (scsi_device_get(sdkp->device) == 0)
get_device(&sdkp->dev);
else
sdkp = NULL;
}
return sdkp;
}
static struct scsi_disk *scsi_disk_get(struct gendisk *disk)
{
struct scsi_disk *sdkp;
mutex_lock(&sd_ref_mutex);
sdkp = __scsi_disk_get(disk);
mutex_unlock(&sd_ref_mutex);
return sdkp;
}
static struct scsi_disk *scsi_disk_get_from_dev(struct device *dev)
{
struct scsi_disk *sdkp;
mutex_lock(&sd_ref_mutex);
sdkp = dev_get_drvdata(dev);
if (sdkp)
sdkp = __scsi_disk_get(sdkp->disk);
mutex_unlock(&sd_ref_mutex);
return sdkp;
}
static void scsi_disk_put(struct scsi_disk *sdkp)
{
struct scsi_device *sdev = sdkp->device;
mutex_lock(&sd_ref_mutex);
put_device(&sdkp->dev);
scsi_device_put(sdev);
mutex_unlock(&sd_ref_mutex);
}
static void sd_prot_op(struct scsi_cmnd *scmd, unsigned int dif)
{
unsigned int prot_op = SCSI_PROT_NORMAL;
unsigned int dix = scsi_prot_sg_count(scmd);
if (scmd->sc_data_direction == DMA_FROM_DEVICE) {
if (dif && dix)
prot_op = SCSI_PROT_READ_PASS;
else if (dif && !dix)
prot_op = SCSI_PROT_READ_STRIP;
else if (!dif && dix)
prot_op = SCSI_PROT_READ_INSERT;
} else {
if (dif && dix)
prot_op = SCSI_PROT_WRITE_PASS;
else if (dif && !dix)
prot_op = SCSI_PROT_WRITE_INSERT;
else if (!dif && dix)
prot_op = SCSI_PROT_WRITE_STRIP;
}
scsi_set_prot_op(scmd, prot_op);
scsi_set_prot_type(scmd, dif);
}
/**
* scsi_setup_discard_cmnd - unmap blocks on thinly provisioned device
* @sdp: scsi device to operate one
* @rq: Request to prepare
*
* Will issue either UNMAP or WRITE SAME(16) depending on preference
* indicated by target device.
**/
static int scsi_setup_discard_cmnd(struct scsi_device *sdp, struct request *rq)
{
struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
struct bio *bio = rq->bio;
sector_t sector = bio->bi_sector;
unsigned int nr_sectors = bio_sectors(bio);
unsigned int len;
int ret;
struct page *page;
if (sdkp->device->sector_size == 4096) {
sector >>= 3;
nr_sectors >>= 3;
}
rq->timeout = SD_TIMEOUT;
memset(rq->cmd, 0, rq->cmd_len);
page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
if (!page)
return BLKPREP_DEFER;
if (sdkp->unmap) {
char *buf = page_address(page);
rq->cmd_len = 10;
rq->cmd[0] = UNMAP;
rq->cmd[8] = 24;
put_unaligned_be16(6 + 16, &buf[0]);
put_unaligned_be16(16, &buf[2]);
put_unaligned_be64(sector, &buf[8]);
put_unaligned_be32(nr_sectors, &buf[16]);
len = 24;
} else {
rq->cmd_len = 16;
rq->cmd[0] = WRITE_SAME_16;
rq->cmd[1] = 0x8; /* UNMAP */
put_unaligned_be64(sector, &rq->cmd[2]);
put_unaligned_be32(nr_sectors, &rq->cmd[10]);
len = sdkp->device->sector_size;
}
blk_add_request_payload(rq, page, len);
ret = scsi_setup_blk_pc_cmnd(sdp, rq);
rq->buffer = page_address(page);
if (ret != BLKPREP_OK) {
__free_page(page);
rq->buffer = NULL;
}
return ret;
}
static int scsi_setup_flush_cmnd(struct scsi_device *sdp, struct request *rq)
{
rq->timeout = SD_FLUSH_TIMEOUT;
rq->retries = SD_MAX_RETRIES;
rq->cmd[0] = SYNCHRONIZE_CACHE;
rq->cmd_len = 10;
return scsi_setup_blk_pc_cmnd(sdp, rq);
}
static void sd_unprep_fn(struct request_queue *q, struct request *rq)
{
if (rq->cmd_flags & REQ_DISCARD) {
free_page((unsigned long)rq->buffer);
rq->buffer = NULL;
}
}
/**
* sd_init_command - build a scsi (read or write) command from
* information in the request structure.
* @SCpnt: pointer to mid-level's per scsi command structure that
* contains request and into which the scsi command is written
*
* Returns 1 if successful and 0 if error (or cannot be done now).
**/
static int sd_prep_fn(struct request_queue *q, struct request *rq)
{
struct scsi_cmnd *SCpnt;
struct scsi_device *sdp = q->queuedata;
struct gendisk *disk = rq->rq_disk;
struct scsi_disk *sdkp;
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 13:24:39 +00:00
sector_t block = blk_rq_pos(rq);
sector_t threshold;
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 13:24:39 +00:00
unsigned int this_count = blk_rq_sectors(rq);
int ret, host_dif;
unsigned char protect;
/*
* Discard request come in as REQ_TYPE_FS but we turn them into
* block PC requests to make life easier.
*/
if (rq->cmd_flags & REQ_DISCARD) {
ret = scsi_setup_discard_cmnd(sdp, rq);
goto out;
} else if (rq->cmd_flags & REQ_FLUSH) {
ret = scsi_setup_flush_cmnd(sdp, rq);
goto out;
} else if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
ret = scsi_setup_blk_pc_cmnd(sdp, rq);
goto out;
} else if (rq->cmd_type != REQ_TYPE_FS) {
ret = BLKPREP_KILL;
goto out;
}
ret = scsi_setup_fs_cmnd(sdp, rq);
if (ret != BLKPREP_OK)
goto out;
SCpnt = rq->special;
sdkp = scsi_disk(disk);
/* from here on until we're complete, any goto out
* is used for a killable error condition */
ret = BLKPREP_KILL;
SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt,
"sd_init_command: block=%llu, "
"count=%d\n",
(unsigned long long)block,
this_count));
if (!sdp || !scsi_device_online(sdp) ||
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 13:24:39 +00:00
block + blk_rq_sectors(rq) > get_capacity(disk)) {
SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
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 13:24:39 +00:00
"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 (sdp->changed) {
/*
* quietly refuse to do anything to a changed disc until
* the changed bit has been reset
*/
/* printk("SCSI disk has been changed or is not present. Prohibiting further I/O.\n"); */
goto out;
}
/*
* Some SD card readers can't handle multi-sector accesses which touch
* the last one or two hardware sectors. Split accesses as needed.
*/
threshold = get_capacity(disk) - SD_LAST_BUGGY_SECTORS *
(sdp->sector_size / 512);
if (unlikely(sdp->last_sector_bug && block + this_count > threshold)) {
if (block < threshold) {
/* Access up to the threshold but not beyond */
this_count = threshold - block;
} else {
/* Access only a single hardware sector */
this_count = sdp->sector_size / 512;
}
}
SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, "block=%llu\n",
(unsigned long long)block));
/*
* If we have a 1K hardware sectorsize, prevent access to single
* 512 byte sectors. In theory we could handle this - in fact
* the scsi cdrom driver must be able to handle this because
* we typically use 1K blocksizes, and cdroms typically have
* 2K hardware sectorsizes. Of course, things are simpler
* with the cdrom, since it is read-only. For performance
* reasons, the filesystems should be able to handle this
* and not force the scsi disk driver to use bounce buffers
* for this.
*/
if (sdp->sector_size == 1024) {
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 13:24:39 +00:00
if ((block & 1) || (blk_rq_sectors(rq) & 1)) {
scmd_printk(KERN_ERR, SCpnt,
"Bad block number requested\n");
goto out;
} else {
block = block >> 1;
this_count = this_count >> 1;
}
}
if (sdp->sector_size == 2048) {
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 13:24:39 +00:00
if ((block & 3) || (blk_rq_sectors(rq) & 3)) {
scmd_printk(KERN_ERR, SCpnt,
"Bad block number requested\n");
goto out;
} else {
block = block >> 2;
this_count = this_count >> 2;
}
}
if (sdp->sector_size == 4096) {
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 13:24:39 +00:00
if ((block & 7) || (blk_rq_sectors(rq) & 7)) {
scmd_printk(KERN_ERR, SCpnt,
"Bad block number requested\n");
goto out;
} else {
block = block >> 3;
this_count = this_count >> 3;
}
}
if (rq_data_dir(rq) == WRITE) {
if (!sdp->writeable) {
goto out;
}
SCpnt->cmnd[0] = WRITE_6;
SCpnt->sc_data_direction = DMA_TO_DEVICE;
if (blk_integrity_rq(rq) &&
sd_dif_prepare(rq, block, sdp->sector_size) == -EIO)
goto out;
} else if (rq_data_dir(rq) == READ) {
SCpnt->cmnd[0] = READ_6;
SCpnt->sc_data_direction = DMA_FROM_DEVICE;
} else {
scmd_printk(KERN_ERR, SCpnt, "Unknown command %x\n", rq->cmd_flags);
goto out;
}
SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt,
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 13:24:39 +00:00
"%s %d/%u 512 byte blocks.\n",
(rq_data_dir(rq) == WRITE) ?
"writing" : "reading", this_count,
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 13:24:39 +00:00
blk_rq_sectors(rq)));
/* Set RDPROTECT/WRPROTECT if disk is formatted with DIF */
host_dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type);
if (host_dif)
protect = 1 << 5;
else
protect = 0;
if (host_dif == SD_DIF_TYPE2_PROTECTION) {
SCpnt->cmnd = mempool_alloc(sd_cdb_pool, GFP_ATOMIC);
if (unlikely(SCpnt->cmnd == NULL)) {
ret = BLKPREP_DEFER;
goto out;
}
SCpnt->cmd_len = SD_EXT_CDB_SIZE;
memset(SCpnt->cmnd, 0, SCpnt->cmd_len);
SCpnt->cmnd[0] = VARIABLE_LENGTH_CMD;
SCpnt->cmnd[7] = 0x18;
SCpnt->cmnd[9] = (rq_data_dir(rq) == READ) ? READ_32 : WRITE_32;
SCpnt->cmnd[10] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0);
/* LBA */
SCpnt->cmnd[12] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0;
SCpnt->cmnd[13] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0;
SCpnt->cmnd[14] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0;
SCpnt->cmnd[15] = sizeof(block) > 4 ? (unsigned char) (block >> 32) & 0xff : 0;
SCpnt->cmnd[16] = (unsigned char) (block >> 24) & 0xff;
SCpnt->cmnd[17] = (unsigned char) (block >> 16) & 0xff;
SCpnt->cmnd[18] = (unsigned char) (block >> 8) & 0xff;
SCpnt->cmnd[19] = (unsigned char) block & 0xff;
/* Expected Indirect LBA */
SCpnt->cmnd[20] = (unsigned char) (block >> 24) & 0xff;
SCpnt->cmnd[21] = (unsigned char) (block >> 16) & 0xff;
SCpnt->cmnd[22] = (unsigned char) (block >> 8) & 0xff;
SCpnt->cmnd[23] = (unsigned char) block & 0xff;
/* Transfer length */
SCpnt->cmnd[28] = (unsigned char) (this_count >> 24) & 0xff;
SCpnt->cmnd[29] = (unsigned char) (this_count >> 16) & 0xff;
SCpnt->cmnd[30] = (unsigned char) (this_count >> 8) & 0xff;
SCpnt->cmnd[31] = (unsigned char) this_count & 0xff;
} else if (block > 0xffffffff) {
SCpnt->cmnd[0] += READ_16 - READ_6;
SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0);
SCpnt->cmnd[2] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0;
SCpnt->cmnd[3] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0;
SCpnt->cmnd[4] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0;
SCpnt->cmnd[5] = sizeof(block) > 4 ? (unsigned char) (block >> 32) & 0xff : 0;
SCpnt->cmnd[6] = (unsigned char) (block >> 24) & 0xff;
SCpnt->cmnd[7] = (unsigned char) (block >> 16) & 0xff;
SCpnt->cmnd[8] = (unsigned char) (block >> 8) & 0xff;
SCpnt->cmnd[9] = (unsigned char) block & 0xff;
SCpnt->cmnd[10] = (unsigned char) (this_count >> 24) & 0xff;
SCpnt->cmnd[11] = (unsigned char) (this_count >> 16) & 0xff;
SCpnt->cmnd[12] = (unsigned char) (this_count >> 8) & 0xff;
SCpnt->cmnd[13] = (unsigned char) this_count & 0xff;
SCpnt->cmnd[14] = SCpnt->cmnd[15] = 0;
} else if ((this_count > 0xff) || (block > 0x1fffff) ||
scsi_device_protection(SCpnt->device) ||
SCpnt->device->use_10_for_rw) {
if (this_count > 0xffff)
this_count = 0xffff;
SCpnt->cmnd[0] += READ_10 - READ_6;
SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0);
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;
} else {
if (unlikely(rq->cmd_flags & REQ_FUA)) {
/*
* This happens only if this drive failed
* 10byte rw command with ILLEGAL_REQUEST
* during operation and thus turned off
* use_10_for_rw.
*/
scmd_printk(KERN_ERR, SCpnt,
"FUA write on READ/WRITE(6) drive\n");
goto out;
}
SCpnt->cmnd[1] |= (unsigned char) ((block >> 16) & 0x1f);
SCpnt->cmnd[2] = (unsigned char) ((block >> 8) & 0xff);
SCpnt->cmnd[3] = (unsigned char) block & 0xff;
SCpnt->cmnd[4] = (unsigned char) this_count;
SCpnt->cmnd[5] = 0;
}
SCpnt->sdb.length = this_count * sdp->sector_size;
/* If DIF or DIX is enabled, tell HBA how to handle request */
if (host_dif || scsi_prot_sg_count(SCpnt))
sd_prot_op(SCpnt, host_dif);
/*
* 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 = sdp->sector_size;
SCpnt->underflow = this_count << 9;
SCpnt->allowed = SD_MAX_RETRIES;
/*
* This indicates that the command is ready from our end to be
* queued.
*/
ret = BLKPREP_OK;
out:
return scsi_prep_return(q, rq, ret);
}
/**
* sd_open - open a scsi disk device
* @inode: only i_rdev member may be used
* @filp: only f_mode and f_flags may be used
*
* Returns 0 if successful. Returns a negated errno value in case
* of error.
*
* Note: This can be called from a user context (e.g. fsck(1) )
* or from within the kernel (e.g. as a result of a mount(1) ).
* In the latter case @inode and @filp carry an abridged amount
* of information as noted above.
*
* Locking: called with bdev->bd_mutex held.
**/
static int sd_open(struct block_device *bdev, fmode_t mode)
{
struct scsi_disk *sdkp = scsi_disk_get(bdev->bd_disk);
struct scsi_device *sdev;
int retval;
if (!sdkp)
return -ENXIO;
SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_open\n"));
sdev = sdkp->device;
retval = scsi_autopm_get_device(sdev);
if (retval)
goto error_autopm;
/*
* 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;
if (sdev->removable || sdkp->write_prot)
check_disk_change(bdev);
/*
* If the drive is empty, just let the open fail.
*/
retval = -ENOMEDIUM;
if (sdev->removable && !sdkp->media_present && !(mode & FMODE_NDELAY))
goto error_out;
/*
* If the device has the write protect tab set, have the open fail
* if the user expects to be able to write to the thing.
*/
retval = -EROFS;
if (sdkp->write_prot && (mode & FMODE_WRITE))
goto error_out;
/*
* It is possible that the disk changing stuff resulted in
* the device being taken offline. If this is the case,
* report this to the user, and don't pretend that the
* open actually succeeded.
*/
retval = -ENXIO;
if (!scsi_device_online(sdev))
goto error_out;
if ((atomic_inc_return(&sdkp->openers) == 1) && sdev->removable) {
if (scsi_block_when_processing_errors(sdev))
scsi_set_medium_removal(sdev, SCSI_REMOVAL_PREVENT);
}
return 0;
error_out:
scsi_autopm_put_device(sdev);
error_autopm:
scsi_disk_put(sdkp);
return retval;
}
/**
* sd_release - invoked when the (last) close(2) is called on this
* scsi disk.
* @inode: only i_rdev member may be used
* @filp: only f_mode and f_flags may be used
*
* Returns 0.
*
* Note: may block (uninterruptible) if error recovery is underway
* on this disk.
*
* Locking: called with bdev->bd_mutex held.
**/
static int sd_release(struct gendisk *disk, fmode_t mode)
{
struct scsi_disk *sdkp = scsi_disk(disk);
struct scsi_device *sdev = sdkp->device;
SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_release\n"));
if (atomic_dec_return(&sdkp->openers) == 0 && sdev->removable) {
if (scsi_block_when_processing_errors(sdev))
scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW);
}
/*
* XXX and what if there are packets in flight and this close()
* XXX is followed by a "rmmod sd_mod"?
*/
scsi_autopm_put_device(sdev);
scsi_disk_put(sdkp);
return 0;
}
static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
struct scsi_device *sdp = sdkp->device;
struct Scsi_Host *host = sdp->host;
int diskinfo[4];
/* default to most commonly used values */
diskinfo[0] = 0x40; /* 1 << 6 */
diskinfo[1] = 0x20; /* 1 << 5 */
diskinfo[2] = sdkp->capacity >> 11;
/* override with calculated, extended default, or driver values */
if (host->hostt->bios_param)
host->hostt->bios_param(sdp, bdev, sdkp->capacity, diskinfo);
else
scsicam_bios_param(bdev, sdkp->capacity, diskinfo);
geo->heads = diskinfo[0];
geo->sectors = diskinfo[1];
geo->cylinders = diskinfo[2];
return 0;
}
/**
* sd_ioctl - process an ioctl
* @inode: only i_rdev/i_bdev members may be used
* @filp: only f_mode and f_flags may be used
* @cmd: ioctl command number
* @arg: this is third argument given to ioctl(2) system call.
* Often contains a pointer.
*
* Returns 0 if successful (some ioctls return postive numbers on
* success as well). Returns a negated errno value in case of error.
*
* Note: most ioctls are forward onto the block subsystem or further
* down in the scsi subsystem.
**/
static int sd_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct gendisk *disk = bdev->bd_disk;
struct scsi_device *sdp = scsi_disk(disk)->device;
void __user *p = (void __user *)arg;
int error;
SCSI_LOG_IOCTL(1, printk("sd_ioctl: disk=%s, cmd=0x%x\n",
disk->disk_name, cmd));
/*
* If we are in the middle of error recovery, don't let anyone
* else try and use this device. Also, if error recovery fails, it
* may try and take the device offline, in which case all further
* access to the device is prohibited.
*/
error = scsi_nonblockable_ioctl(sdp, cmd, p,
(mode & FMODE_NDELAY) != 0);
if (!scsi_block_when_processing_errors(sdp) || !error)
goto out;
/*
* Send SCSI addressing ioctls directly to mid level, send other
* ioctls to block level and then onto mid level if they can't be
* resolved.
*/
switch (cmd) {
case SCSI_IOCTL_GET_IDLUN:
case SCSI_IOCTL_GET_BUS_NUMBER:
error = scsi_ioctl(sdp, cmd, p);
break;
default:
error = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, p);
if (error != -ENOTTY)
break;
error = scsi_ioctl(sdp, cmd, p);
break;
}
out:
return error;
}
static void set_media_not_present(struct scsi_disk *sdkp)
{
if (sdkp->media_present)
sdkp->device->changed = 1;
if (sdkp->device->removable) {
sdkp->media_present = 0;
sdkp->capacity = 0;
}
}
static int media_not_present(struct scsi_disk *sdkp,
struct scsi_sense_hdr *sshdr)
{
if (!scsi_sense_valid(sshdr))
return 0;
/* not invoked for commands that could return deferred errors */
switch (sshdr->sense_key) {
case UNIT_ATTENTION:
case NOT_READY:
/* medium not present */
if (sshdr->asc == 0x3A) {
set_media_not_present(sdkp);
return 1;
}
}
return 0;
}
/**
* sd_check_events - check media events
* @disk: kernel device descriptor
* @clearing: disk events currently being cleared
*
* Returns mask of DISK_EVENT_*.
*
* Note: this function is invoked from the block subsystem.
**/
static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing)
{
struct scsi_disk *sdkp = scsi_disk(disk);
struct scsi_device *sdp = sdkp->device;
struct scsi_sense_hdr *sshdr = NULL;
int retval;
SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n"));
/*
* If the device is offline, don't send any commands - just pretend as
* if the command failed. If the device ever comes back online, we
* can deal with it then. It is only because of unrecoverable errors
* that we would ever take a device offline in the first place.
*/
if (!scsi_device_online(sdp)) {
set_media_not_present(sdkp);
goto out;
}
/*
* Using TEST_UNIT_READY enables differentiation between drive with
* no cartridge loaded - NOT READY, drive with changed cartridge -
* UNIT ATTENTION, or with same cartridge - GOOD STATUS.
*
* Drives that auto spin down. eg iomega jaz 1G, will be started
* by sd_spinup_disk() from sd_revalidate_disk(), which happens whenever
* sd_revalidate() is called.
*/
retval = -ENODEV;
if (scsi_block_when_processing_errors(sdp)) {
sshdr = kzalloc(sizeof(*sshdr), GFP_KERNEL);
retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, SD_MAX_RETRIES,
sshdr);
}
/* failed to execute TUR, assume media not present */
if (host_byte(retval)) {
set_media_not_present(sdkp);
goto out;
}
if (media_not_present(sdkp, sshdr))
goto out;
/*
* For removable scsi disk we have to recognise the presence
* of a disk in the drive.
*/
if (!sdkp->media_present)
sdp->changed = 1;
sdkp->media_present = 1;
out:
/*
* sdp->changed is set under the following conditions:
*
* Medium present state has changed in either direction.
* Device has indicated UNIT_ATTENTION.
*/
kfree(sshdr);
retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0;
sdp->changed = 0;
return retval;
}
static int sd_sync_cache(struct scsi_disk *sdkp)
{
int retries, res;
struct scsi_device *sdp = sdkp->device;
struct scsi_sense_hdr sshdr;
if (!scsi_device_online(sdp))
return -ENODEV;
for (retries = 3; retries > 0; --retries) {
unsigned char cmd[10] = { 0 };
cmd[0] = SYNCHRONIZE_CACHE;
/*
* Leave the rest of the command zero to indicate
* flush everything.
*/
res = scsi_execute_req(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
SD_FLUSH_TIMEOUT, SD_MAX_RETRIES, NULL);
if (res == 0)
break;
}
if (res) {
sd_print_result(sdkp, res);
if (driver_byte(res) & DRIVER_SENSE)
sd_print_sense_hdr(sdkp, &sshdr);
}
if (res)
return -EIO;
return 0;
}
static void sd_rescan(struct device *dev)
{
struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev);
if (sdkp) {
revalidate_disk(sdkp->disk);
scsi_disk_put(sdkp);
}
}
#ifdef CONFIG_COMPAT
/*
* This gets directly called from VFS. When the ioctl
* is not recognized we go back to the other translation paths.
*/
static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
/*
* If we are in the middle of error recovery, don't let anyone
* else try and use this device. Also, if error recovery fails, it
* may try and take the device offline, in which case all further
* access to the device is prohibited.
*/
if (!scsi_block_when_processing_errors(sdev))
return -ENODEV;
if (sdev->host->hostt->compat_ioctl) {
int ret;
ret = sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg);
return ret;
}
/*
* Let the static ioctl translation table take care of it.
*/
return -ENOIOCTLCMD;
}
#endif
static const struct block_device_operations sd_fops = {
.owner = THIS_MODULE,
.open = sd_open,
.release = sd_release,
.ioctl = sd_ioctl,
.getgeo = sd_getgeo,
#ifdef CONFIG_COMPAT
.compat_ioctl = sd_compat_ioctl,
#endif
.check_events = sd_check_events,
.revalidate_disk = sd_revalidate_disk,
.unlock_native_capacity = sd_unlock_native_capacity,
};
static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd)
{
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 13:24:39 +00:00
u64 start_lba = blk_rq_pos(scmd->request);
u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512);
u64 bad_lba;
int info_valid;
/*
* resid is optional but mostly filled in. When it's unused,
* its value is zero, so we assume the whole buffer transferred
*/
unsigned int transferred = scsi_bufflen(scmd) - scsi_get_resid(scmd);
unsigned int good_bytes;
if (scmd->request->cmd_type != REQ_TYPE_FS)
return 0;
info_valid = scsi_get_sense_info_fld(scmd->sense_buffer,
SCSI_SENSE_BUFFERSIZE,
&bad_lba);
if (!info_valid)
return 0;
if (scsi_bufflen(scmd) <= scmd->device->sector_size)
return 0;
if (scmd->device->sector_size < 512) {
/* only legitimate sector_size here is 256 */
start_lba <<= 1;
end_lba <<= 1;
} else {
/* be careful ... don't want any overflows */
u64 factor = scmd->device->sector_size / 512;
do_div(start_lba, factor);
do_div(end_lba, factor);
}
/* The bad lba was reported incorrectly, we have no idea where
* the error is.
*/
if (bad_lba < start_lba || bad_lba >= end_lba)
return 0;
/* This computation should always be done in terms of
* the resolution of the device's medium.
*/
good_bytes = (bad_lba - start_lba) * scmd->device->sector_size;
return min(good_bytes, transferred);
}
/**
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>
2008-01-06 18:17:12 +00:00
* sd_done - bottom half handler: called when the lower level
* driver has completed (successfully or otherwise) a scsi command.
* @SCpnt: mid-level's per command structure.
*
* Note: potentially run from within an ISR. Must not block.
**/
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>
2008-01-06 18:17:12 +00:00
static int sd_done(struct scsi_cmnd *SCpnt)
{
int result = SCpnt->result;
unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt);
struct scsi_sense_hdr sshdr;
struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk);
int sense_valid = 0;
int sense_deferred = 0;
if (SCpnt->request->cmd_flags & REQ_DISCARD) {
if (!result)
scsi_set_resid(SCpnt, 0);
return good_bytes;
}
if (result) {
sense_valid = scsi_command_normalize_sense(SCpnt, &sshdr);
if (sense_valid)
sense_deferred = scsi_sense_is_deferred(&sshdr);
}
#ifdef CONFIG_SCSI_LOGGING
SCSI_LOG_HLCOMPLETE(1, scsi_print_result(SCpnt));
if (sense_valid) {
SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, 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>
2008-01-06 18:17:12 +00:00
"sd_done: sb[respc,sk,asc,"
"ascq]=%x,%x,%x,%x\n",
sshdr.response_code,
sshdr.sense_key, sshdr.asc,
sshdr.ascq));
}
#endif
if (driver_byte(result) != DRIVER_SENSE &&
(!sense_valid || sense_deferred))
goto out;
switch (sshdr.sense_key) {
case HARDWARE_ERROR:
case MEDIUM_ERROR:
good_bytes = sd_completed_bytes(SCpnt);
break;
case RECOVERED_ERROR:
good_bytes = scsi_bufflen(SCpnt);
break;
case NO_SENSE:
/* This indicates a false check condition, so ignore it. An
* unknown amount of data was transferred so treat it as an
* error.
*/
scsi_print_sense("sd", SCpnt);
SCpnt->result = 0;
memset(SCpnt->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
break;
case ABORTED_COMMAND: /* DIF: Target detected corruption */
case ILLEGAL_REQUEST: /* DIX: Host detected corruption */
if (sshdr.asc == 0x10)
good_bytes = sd_completed_bytes(SCpnt);
break;
default:
break;
}
out:
if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
sd_dif_complete(SCpnt, good_bytes);
if (scsi_host_dif_capable(sdkp->device->host, sdkp->protection_type)
== SD_DIF_TYPE2_PROTECTION && SCpnt->cmnd != SCpnt->request->cmd) {
/* We have to print a failed command here as the
* extended CDB gets freed before scsi_io_completion()
* is called.
*/
if (result)
scsi_print_command(SCpnt);
mempool_free(SCpnt->cmnd, sd_cdb_pool);
SCpnt->cmnd = NULL;
SCpnt->cmd_len = 0;
}
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>
2008-01-06 18:17:12 +00:00
return good_bytes;
}
/*
* spinup disk - called only in sd_revalidate_disk()
*/
static void
sd_spinup_disk(struct scsi_disk *sdkp)
{
unsigned char cmd[10];
unsigned long spintime_expire = 0;
int retries, spintime;
unsigned int the_result;
struct scsi_sense_hdr sshdr;
int sense_valid = 0;
spintime = 0;
/* Spin up drives, as required. Only do this at boot time */
/* Spinup needs to be done for module loads too. */
do {
retries = 0;
do {
cmd[0] = TEST_UNIT_READY;
memset((void *) &cmd[1], 0, 9);
the_result = scsi_execute_req(sdkp->device, cmd,
DMA_NONE, NULL, 0,
&sshdr, SD_TIMEOUT,
SD_MAX_RETRIES, NULL);
/*
* If the drive has indicated to us that it
* doesn't have any media in it, don't bother
* with any more polling.
*/
if (media_not_present(sdkp, &sshdr))
return;
if (the_result)
sense_valid = scsi_sense_valid(&sshdr);
retries++;
} while (retries < 3 &&
(!scsi_status_is_good(the_result) ||
((driver_byte(the_result) & DRIVER_SENSE) &&
sense_valid && sshdr.sense_key == UNIT_ATTENTION)));
if ((driver_byte(the_result) & DRIVER_SENSE) == 0) {
/* no sense, TUR either succeeded or failed
* with a status error */
if(!spintime && !scsi_status_is_good(the_result)) {
sd_printk(KERN_NOTICE, sdkp, "Unit Not Ready\n");
sd_print_result(sdkp, the_result);
}
break;
}
/*
* The device does not want the automatic start to be issued.
*/
if (sdkp->device->no_start_on_add)
break;
if (sense_valid && sshdr.sense_key == NOT_READY) {
if (sshdr.asc == 4 && sshdr.ascq == 3)
break; /* manual intervention required */
if (sshdr.asc == 4 && sshdr.ascq == 0xb)
break; /* standby */
if (sshdr.asc == 4 && sshdr.ascq == 0xc)
break; /* unavailable */
/*
* Issue command to spin up drive when not ready
*/
if (!spintime) {
sd_printk(KERN_NOTICE, sdkp, "Spinning up disk...");
cmd[0] = START_STOP;
cmd[1] = 1; /* Return immediately */
memset((void *) &cmd[2], 0, 8);
cmd[4] = 1; /* Start spin cycle */
if (sdkp->device->start_stop_pwr_cond)
cmd[4] |= 1 << 4;
scsi_execute_req(sdkp->device, cmd, DMA_NONE,
NULL, 0, &sshdr,
SD_TIMEOUT, SD_MAX_RETRIES,
NULL);
spintime_expire = jiffies + 100 * HZ;
spintime = 1;
}
/* Wait 1 second for next try */
msleep(1000);
printk(".");
/*
* Wait for USB flash devices with slow firmware.
* Yes, this sense key/ASC combination shouldn't
* occur here. It's characteristic of these devices.
*/
} else if (sense_valid &&
sshdr.sense_key == UNIT_ATTENTION &&
sshdr.asc == 0x28) {
if (!spintime) {
spintime_expire = jiffies + 5 * HZ;
spintime = 1;
}
/* Wait 1 second for next try */
msleep(1000);
} else {
/* we don't understand the sense code, so it's
* probably pointless to loop */
if(!spintime) {
sd_printk(KERN_NOTICE, sdkp, "Unit Not Ready\n");
sd_print_sense_hdr(sdkp, &sshdr);
}
break;
}
} while (spintime && time_before_eq(jiffies, spintime_expire));
if (spintime) {
if (scsi_status_is_good(the_result))
printk("ready\n");
else
printk("not responding...\n");
}
}
/*
* Determine whether disk supports Data Integrity Field.
*/
static void sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer)
{
struct scsi_device *sdp = sdkp->device;
u8 type;
if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0)
return;
type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */
if (type == sdkp->protection_type || !sdkp->first_scan)
return;
sdkp->protection_type = type;
if (type > SD_DIF_TYPE3_PROTECTION) {
sd_printk(KERN_ERR, sdkp, "formatted with unsupported " \
"protection type %u. Disabling disk!\n", type);
sdkp->capacity = 0;
return;
}
if (scsi_host_dif_capable(sdp->host, type))
sd_printk(KERN_NOTICE, sdkp,
"Enabling DIF Type %u protection\n", type);
else
sd_printk(KERN_NOTICE, sdkp,
"Disabling DIF Type %u protection\n", type);
}
static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
struct scsi_sense_hdr *sshdr, int sense_valid,
int the_result)
{
sd_print_result(sdkp, the_result);
if (driver_byte(the_result) & DRIVER_SENSE)
sd_print_sense_hdr(sdkp, sshdr);
else
sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n");
/*
* Set dirty bit for removable devices if not ready -
* sometimes drives will not report this properly.
*/
if (sdp->removable &&
sense_valid && sshdr->sense_key == NOT_READY)
set_media_not_present(sdkp);
/*
* We used to set media_present to 0 here to indicate no media
* in the drive, but some drives fail read capacity even with
* media present, so we can't do that.
*/
sdkp->capacity = 0; /* unknown mapped to zero - as usual */
}
#define RC16_LEN 32
#if RC16_LEN > SD_BUF_SIZE
#error RC16_LEN must not be more than SD_BUF_SIZE
#endif
#define READ_CAPACITY_RETRIES_ON_RESET 10
static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
unsigned char *buffer)
{
unsigned char cmd[16];
struct scsi_sense_hdr sshdr;
int sense_valid = 0;
int the_result;
int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET;
unsigned int alignment;
unsigned long long lba;
unsigned sector_size;
scsi/sd: add a no_read_capacity_16 scsi_device flag I seem to have a knack for digging up buggy usb devices which don't work with Linux, and I'm crazy enough to try to make them work. So this time a friend of mine asked me to get an mp4 player (an mp3 player which can play videos on a small screen) to work with Linux. It is based on the well known rockbox chipset for which we already have an unusual devs entries to work around some of its bugs. But this model comes with an additional twist. This model chokes on read_capacity_16 calls. Now normally we don't make those calls, but this model comes with an sdcard slot and when there is no card in there (and shipped from the factory there is none), it reports a size of 0. However this time the programmers actually got the read_capacity_10 response right! So they substract one from the size as stored internally in the mp3 player before reporting it back, resulting in an answer of ... 0xffffffff sectors, causing sd.c to try a read_capacity_16, on which the device crashes. This patch adds a flag to scsi_device to indicate that a a device cannot handle read_capacity_16, and when this flag is set if a device reports an lba of 0xffffffff as answer to a read_capacity_10, assumes it tries to report a size of 0. Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Matthew Dharm <mdharm-usb@one-eyed-alien.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-10-01 21:20:10 +00:00
if (sdp->no_read_capacity_16)
return -EINVAL;
do {
memset(cmd, 0, 16);
cmd[0] = SERVICE_ACTION_IN;
cmd[1] = SAI_READ_CAPACITY_16;
cmd[13] = RC16_LEN;
memset(buffer, 0, RC16_LEN);
the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
buffer, RC16_LEN, &sshdr,
SD_TIMEOUT, SD_MAX_RETRIES, NULL);
if (media_not_present(sdkp, &sshdr))
return -ENODEV;
if (the_result) {
sense_valid = scsi_sense_valid(&sshdr);
if (sense_valid &&
sshdr.sense_key == ILLEGAL_REQUEST &&
(sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
sshdr.ascq == 0x00)
/* Invalid Command Operation Code or
* Invalid Field in CDB, just retry
* silently with RC10 */
return -EINVAL;
if (sense_valid &&
sshdr.sense_key == UNIT_ATTENTION &&
sshdr.asc == 0x29 && sshdr.ascq == 0x00)
/* Device reset might occur several times,
* give it one more chance */
if (--reset_retries > 0)
continue;
}
retries--;
} while (the_result && retries);
if (the_result) {
sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY(16) failed\n");
read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result);
return -EINVAL;
}
sector_size = get_unaligned_be32(&buffer[8]);
lba = get_unaligned_be64(&buffer[0]);
sd_read_protection_type(sdkp, buffer);
if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) {
sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
"kernel compiled with support for large block "
"devices.\n");
sdkp->capacity = 0;
return -EOVERFLOW;
}
/* Logical blocks per physical block exponent */
sdkp->physical_block_size = (1 << (buffer[13] & 0xf)) * sector_size;
/* Lowest aligned logical block */
alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size;
blk_queue_alignment_offset(sdp->request_queue, alignment);
if (alignment && sdkp->first_scan)
sd_printk(KERN_NOTICE, sdkp,
"physical block alignment offset: %u\n", alignment);
if (buffer[14] & 0x80) { /* TPE */
struct request_queue *q = sdp->request_queue;
sdkp->thin_provisioning = 1;
q->limits.discard_granularity = sdkp->physical_block_size;
q->limits.max_discard_sectors = 0xffffffff;
if (buffer[14] & 0x40) /* TPRZ */
q->limits.discard_zeroes_data = 1;
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
sdkp->capacity = lba + 1;
return sector_size;
}
static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp,
unsigned char *buffer)
{
unsigned char cmd[16];
struct scsi_sense_hdr sshdr;
int sense_valid = 0;
int the_result;
int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET;
sector_t lba;
unsigned sector_size;
do {
cmd[0] = READ_CAPACITY;
memset(&cmd[1], 0, 9);
memset(buffer, 0, 8);
the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
buffer, 8, &sshdr,
SD_TIMEOUT, SD_MAX_RETRIES, NULL);
if (media_not_present(sdkp, &sshdr))
return -ENODEV;
if (the_result) {
sense_valid = scsi_sense_valid(&sshdr);
if (sense_valid &&
sshdr.sense_key == UNIT_ATTENTION &&
sshdr.asc == 0x29 && sshdr.ascq == 0x00)
/* Device reset might occur several times,
* give it one more chance */
if (--reset_retries > 0)
continue;
}
retries--;
} while (the_result && retries);
if (the_result) {
sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY failed\n");
read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result);
return -EINVAL;
}
sector_size = get_unaligned_be32(&buffer[4]);
lba = get_unaligned_be32(&buffer[0]);
scsi/sd: add a no_read_capacity_16 scsi_device flag I seem to have a knack for digging up buggy usb devices which don't work with Linux, and I'm crazy enough to try to make them work. So this time a friend of mine asked me to get an mp4 player (an mp3 player which can play videos on a small screen) to work with Linux. It is based on the well known rockbox chipset for which we already have an unusual devs entries to work around some of its bugs. But this model comes with an additional twist. This model chokes on read_capacity_16 calls. Now normally we don't make those calls, but this model comes with an sdcard slot and when there is no card in there (and shipped from the factory there is none), it reports a size of 0. However this time the programmers actually got the read_capacity_10 response right! So they substract one from the size as stored internally in the mp3 player before reporting it back, resulting in an answer of ... 0xffffffff sectors, causing sd.c to try a read_capacity_16, on which the device crashes. This patch adds a flag to scsi_device to indicate that a a device cannot handle read_capacity_16, and when this flag is set if a device reports an lba of 0xffffffff as answer to a read_capacity_10, assumes it tries to report a size of 0. Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Matthew Dharm <mdharm-usb@one-eyed-alien.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-10-01 21:20:10 +00:00
if (sdp->no_read_capacity_16 && (lba == 0xffffffff)) {
/* Some buggy (usb cardreader) devices return an lba of
0xffffffff when the want to report a size of 0 (with
which they really mean no media is present) */
sdkp->capacity = 0;
sdkp->physical_block_size = sector_size;
scsi/sd: add a no_read_capacity_16 scsi_device flag I seem to have a knack for digging up buggy usb devices which don't work with Linux, and I'm crazy enough to try to make them work. So this time a friend of mine asked me to get an mp4 player (an mp3 player which can play videos on a small screen) to work with Linux. It is based on the well known rockbox chipset for which we already have an unusual devs entries to work around some of its bugs. But this model comes with an additional twist. This model chokes on read_capacity_16 calls. Now normally we don't make those calls, but this model comes with an sdcard slot and when there is no card in there (and shipped from the factory there is none), it reports a size of 0. However this time the programmers actually got the read_capacity_10 response right! So they substract one from the size as stored internally in the mp3 player before reporting it back, resulting in an answer of ... 0xffffffff sectors, causing sd.c to try a read_capacity_16, on which the device crashes. This patch adds a flag to scsi_device to indicate that a a device cannot handle read_capacity_16, and when this flag is set if a device reports an lba of 0xffffffff as answer to a read_capacity_10, assumes it tries to report a size of 0. Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Matthew Dharm <mdharm-usb@one-eyed-alien.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-10-01 21:20:10 +00:00
return sector_size;
}
if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) {
sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
"kernel compiled with support for large block "
"devices.\n");
sdkp->capacity = 0;
return -EOVERFLOW;
}
sdkp->capacity = lba + 1;
sdkp->physical_block_size = sector_size;
return sector_size;
}
static int sd_try_rc16_first(struct scsi_device *sdp)
{
if (sdp->host->max_cmd_len < 16)
return 0;
if (sdp->scsi_level > SCSI_SPC_2)
return 1;
if (scsi_device_protection(sdp))
return 1;
return 0;
}
/*
* read disk capacity
*/
static void
sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer)
{
int sector_size;
struct scsi_device *sdp = sdkp->device;
sector_t old_capacity = sdkp->capacity;
if (sd_try_rc16_first(sdp)) {
sector_size = read_capacity_16(sdkp, sdp, buffer);
if (sector_size == -EOVERFLOW)
goto got_data;
if (sector_size == -ENODEV)
return;
if (sector_size < 0)
sector_size = read_capacity_10(sdkp, sdp, buffer);
if (sector_size < 0)
return;
} else {
sector_size = read_capacity_10(sdkp, sdp, buffer);
if (sector_size == -EOVERFLOW)
goto got_data;
if (sector_size < 0)
return;
if ((sizeof(sdkp->capacity) > 4) &&
(sdkp->capacity > 0xffffffffULL)) {
int old_sector_size = sector_size;
sd_printk(KERN_NOTICE, sdkp, "Very big device. "
"Trying to use READ CAPACITY(16).\n");
sector_size = read_capacity_16(sdkp, sdp, buffer);
if (sector_size < 0) {
sd_printk(KERN_NOTICE, sdkp,
"Using 0xffffffff as device size\n");
sdkp->capacity = 1 + (sector_t) 0xffffffff;
sector_size = old_sector_size;
goto got_data;
}
}
}
/* Some devices are known to return the total number of blocks,
* not the highest block number. Some devices have versions
* which do this and others which do not. Some devices we might
* suspect of doing this but we don't know for certain.
*
* If we know the reported capacity is wrong, decrement it. If
* we can only guess, then assume the number of blocks is even
* (usually true but not always) and err on the side of lowering
* the capacity.
*/
if (sdp->fix_capacity ||
(sdp->guess_capacity && (sdkp->capacity & 0x01))) {
sd_printk(KERN_INFO, sdkp, "Adjusting the sector count "
"from its reported value: %llu\n",
(unsigned long long) sdkp->capacity);
--sdkp->capacity;
}
got_data:
if (sector_size == 0) {
sector_size = 512;
sd_printk(KERN_NOTICE, sdkp, "Sector size 0 reported, "
"assuming 512.\n");
}
if (sector_size != 512 &&
sector_size != 1024 &&
sector_size != 2048 &&
sector_size != 4096 &&
sector_size != 256) {
sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n",
sector_size);
/*
* The user might want to re-format the drive with
* a supported sectorsize. Once this happens, it
* would be relatively trivial to set the thing up.
* For this reason, we leave the thing in the table.
*/
sdkp->capacity = 0;
/*
* set a bogus sector size so the normal read/write
* logic in the block layer will eventually refuse any
* request on this device without tripping over power
* of two sector size assumptions
*/
sector_size = 512;
}
blk_queue_logical_block_size(sdp->request_queue, sector_size);
{
char cap_str_2[10], cap_str_10[10];
u64 sz = (u64)sdkp->capacity << ilog2(sector_size);
string_get_size(sz, STRING_UNITS_2, cap_str_2,
sizeof(cap_str_2));
string_get_size(sz, STRING_UNITS_10, cap_str_10,
sizeof(cap_str_10));
if (sdkp->first_scan || old_capacity != sdkp->capacity) {
sd_printk(KERN_NOTICE, sdkp,
"%llu %d-byte logical blocks: (%s/%s)\n",
(unsigned long long)sdkp->capacity,
sector_size, cap_str_10, cap_str_2);
if (sdkp->physical_block_size != sector_size)
sd_printk(KERN_NOTICE, sdkp,
"%u-byte physical blocks\n",
sdkp->physical_block_size);
}
}
/* Rescale capacity to 512-byte units */
if (sector_size == 4096)
sdkp->capacity <<= 3;
else if (sector_size == 2048)
sdkp->capacity <<= 2;
else if (sector_size == 1024)
sdkp->capacity <<= 1;
else if (sector_size == 256)
sdkp->capacity >>= 1;
blk_queue_physical_block_size(sdp->request_queue,
sdkp->physical_block_size);
sdkp->device->sector_size = sector_size;
}
/* called with buffer of length 512 */
static inline int
sd_do_mode_sense(struct scsi_device *sdp, int dbd, int modepage,
unsigned char *buffer, int len, struct scsi_mode_data *data,
struct scsi_sense_hdr *sshdr)
{
return scsi_mode_sense(sdp, dbd, modepage, buffer, len,
SD_TIMEOUT, SD_MAX_RETRIES, data,
sshdr);
}
/*
* read write protect setting, if possible - called only in sd_revalidate_disk()
* called with buffer of length SD_BUF_SIZE
*/
static void
sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer)
{
int res;
struct scsi_device *sdp = sdkp->device;
struct scsi_mode_data data;
int old_wp = sdkp->write_prot;
set_disk_ro(sdkp->disk, 0);
if (sdp->skip_ms_page_3f) {
sd_printk(KERN_NOTICE, sdkp, "Assuming Write Enabled\n");
return;
}
if (sdp->use_192_bytes_for_3f) {
res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 192, &data, NULL);
} else {
/*
* First attempt: ask for all pages (0x3F), but only 4 bytes.
* We have to start carefully: some devices hang if we ask
* for more than is available.
*/
res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 4, &data, NULL);
/*
* Second attempt: ask for page 0 When only page 0 is
* implemented, a request for page 3F may return Sense Key
* 5: Illegal Request, Sense Code 24: Invalid field in
* CDB.
*/
if (!scsi_status_is_good(res))
res = sd_do_mode_sense(sdp, 0, 0, buffer, 4, &data, NULL);
/*
* Third attempt: ask 255 bytes, as we did earlier.
*/
if (!scsi_status_is_good(res))
res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 255,
&data, NULL);
}
if (!scsi_status_is_good(res)) {
sd_printk(KERN_WARNING, sdkp,
"Test WP failed, assume Write Enabled\n");
} else {
sdkp->write_prot = ((data.device_specific & 0x80) != 0);
set_disk_ro(sdkp->disk, sdkp->write_prot);
if (sdkp->first_scan || old_wp != sdkp->write_prot) {
sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n",
sdkp->write_prot ? "on" : "off");
sd_printk(KERN_DEBUG, sdkp,
"Mode Sense: %02x %02x %02x %02x\n",
buffer[0], buffer[1], buffer[2], buffer[3]);
}
}
}
/*
* sd_read_cache_type - called only from sd_revalidate_disk()
* called with buffer of length SD_BUF_SIZE
*/
static void
sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
{
int len = 0, res;
struct scsi_device *sdp = sdkp->device;
int dbd;
int modepage;
struct scsi_mode_data data;
struct scsi_sense_hdr sshdr;
int old_wce = sdkp->WCE;
int old_rcd = sdkp->RCD;
int old_dpofua = sdkp->DPOFUA;
[SCSI] Retrieve the Caching mode page Some kernel transport drivers unconditionally disable retrieval of the Caching mode page. One such for example is the BBB/CBI transport over USB.  Such a restraint is too harsh as some devices do support the Caching mode page. Unconditionally enabling the retrieval of this mode page over those transports at their transport code level may result in some devices failing and becoming unusable. This patch implements a method of retrieving the Caching mode page without unconditionally enabling it in the transports which unconditionally disable it. The idea is to ask for all supported pages, page code 0x3F, and then search for the Caching mode page in the mode parameter data returned. The sd driver already asks for all the mode pages supported by the attached device by setting the page code to 0x3F in order to find out if the media is write protected by reading the WP bit in the Device Specific Parameter field. It then attempts to retrieve only the Caching mode page by setting the page code to 8 and actually attempting to retrieve it if and only if the transport allows it. The method implemented here is that if the transport doesn't allow retrieval of the Caching mode page and the device is not RBC, then we ask for all pages supported by setting the page code to 0x3F (similarly to how the WP bit is retrieved above), and then we search for the Caching mode page in the mode parameter data returned. With this patch, devices over SATA, report this (no change): Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] 976773168 512-byte logical blocks: (500 GB/465 GiB) Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: Attached scsi generic sg0 type 0 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA Smart devices report their Caching mode page. This is a change where we'd previously see the kernel making assumption about the device's cache being write-through: Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: Attached scsi generic sg2 type 0 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] 610472646 4096-byte logical blocks: (2.50 TB/2.27 TiB) Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Mode Sense: 47 00 10 08 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write cache: enabled, read cache: enabled, supports DPO and FUA And "dumb" devices over BBB, are correctly shown not to support reporting the Caching mode page: Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] 15663104 512-byte logical blocks: (8.01 GB/7.46 GiB) Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Write Protect is off Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Mode Sense: 23 00 00 00 Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] No Caching mode page present Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Assuming drive cache: write through Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2010-10-23 04:24:36 +00:00
if (sdp->skip_ms_page_8) {
if (sdp->type == TYPE_RBC)
goto defaults;
else {
modepage = 0x3F;
dbd = 0;
}
} else if (sdp->type == TYPE_RBC) {
modepage = 6;
dbd = 8;
} else {
modepage = 8;
dbd = 0;
}
/* cautiously ask */
res = sd_do_mode_sense(sdp, dbd, modepage, buffer, 4, &data, &sshdr);
if (!scsi_status_is_good(res))
goto bad_sense;
if (!data.header_length) {
modepage = 6;
sd_printk(KERN_ERR, sdkp, "Missing header in MODE_SENSE response\n");
}
/* that went OK, now ask for the proper length */
len = data.length;
/*
* We're only interested in the first three bytes, actually.
* But the data cache page is defined for the first 20.
*/
if (len < 3)
goto bad_sense;
[SCSI] Retrieve the Caching mode page Some kernel transport drivers unconditionally disable retrieval of the Caching mode page. One such for example is the BBB/CBI transport over USB.  Such a restraint is too harsh as some devices do support the Caching mode page. Unconditionally enabling the retrieval of this mode page over those transports at their transport code level may result in some devices failing and becoming unusable. This patch implements a method of retrieving the Caching mode page without unconditionally enabling it in the transports which unconditionally disable it. The idea is to ask for all supported pages, page code 0x3F, and then search for the Caching mode page in the mode parameter data returned. The sd driver already asks for all the mode pages supported by the attached device by setting the page code to 0x3F in order to find out if the media is write protected by reading the WP bit in the Device Specific Parameter field. It then attempts to retrieve only the Caching mode page by setting the page code to 8 and actually attempting to retrieve it if and only if the transport allows it. The method implemented here is that if the transport doesn't allow retrieval of the Caching mode page and the device is not RBC, then we ask for all pages supported by setting the page code to 0x3F (similarly to how the WP bit is retrieved above), and then we search for the Caching mode page in the mode parameter data returned. With this patch, devices over SATA, report this (no change): Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] 976773168 512-byte logical blocks: (500 GB/465 GiB) Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: Attached scsi generic sg0 type 0 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA Smart devices report their Caching mode page. This is a change where we'd previously see the kernel making assumption about the device's cache being write-through: Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: Attached scsi generic sg2 type 0 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] 610472646 4096-byte logical blocks: (2.50 TB/2.27 TiB) Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Mode Sense: 47 00 10 08 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write cache: enabled, read cache: enabled, supports DPO and FUA And "dumb" devices over BBB, are correctly shown not to support reporting the Caching mode page: Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] 15663104 512-byte logical blocks: (8.01 GB/7.46 GiB) Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Write Protect is off Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Mode Sense: 23 00 00 00 Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] No Caching mode page present Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Assuming drive cache: write through Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2010-10-23 04:24:36 +00:00
else if (len > SD_BUF_SIZE) {
sd_printk(KERN_NOTICE, sdkp, "Truncating mode parameter "
"data from %d to %d bytes\n", len, SD_BUF_SIZE);
len = SD_BUF_SIZE;
}
/* Get the data */
res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len, &data, &sshdr);
if (scsi_status_is_good(res)) {
int offset = data.header_length + data.block_descriptor_length;
[SCSI] Retrieve the Caching mode page Some kernel transport drivers unconditionally disable retrieval of the Caching mode page. One such for example is the BBB/CBI transport over USB.  Such a restraint is too harsh as some devices do support the Caching mode page. Unconditionally enabling the retrieval of this mode page over those transports at their transport code level may result in some devices failing and becoming unusable. This patch implements a method of retrieving the Caching mode page without unconditionally enabling it in the transports which unconditionally disable it. The idea is to ask for all supported pages, page code 0x3F, and then search for the Caching mode page in the mode parameter data returned. The sd driver already asks for all the mode pages supported by the attached device by setting the page code to 0x3F in order to find out if the media is write protected by reading the WP bit in the Device Specific Parameter field. It then attempts to retrieve only the Caching mode page by setting the page code to 8 and actually attempting to retrieve it if and only if the transport allows it. The method implemented here is that if the transport doesn't allow retrieval of the Caching mode page and the device is not RBC, then we ask for all pages supported by setting the page code to 0x3F (similarly to how the WP bit is retrieved above), and then we search for the Caching mode page in the mode parameter data returned. With this patch, devices over SATA, report this (no change): Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] 976773168 512-byte logical blocks: (500 GB/465 GiB) Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: Attached scsi generic sg0 type 0 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA Smart devices report their Caching mode page. This is a change where we'd previously see the kernel making assumption about the device's cache being write-through: Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: Attached scsi generic sg2 type 0 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] 610472646 4096-byte logical blocks: (2.50 TB/2.27 TiB) Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Mode Sense: 47 00 10 08 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write cache: enabled, read cache: enabled, supports DPO and FUA And "dumb" devices over BBB, are correctly shown not to support reporting the Caching mode page: Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] 15663104 512-byte logical blocks: (8.01 GB/7.46 GiB) Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Write Protect is off Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Mode Sense: 23 00 00 00 Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] No Caching mode page present Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Assuming drive cache: write through Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2010-10-23 04:24:36 +00:00
while (offset < len) {
u8 page_code = buffer[offset] & 0x3F;
u8 spf = buffer[offset] & 0x40;
if (page_code == 8 || page_code == 6) {
/* We're interested only in the first 3 bytes.
*/
if (len - offset <= 2) {
sd_printk(KERN_ERR, sdkp, "Incomplete "
"mode parameter data\n");
goto defaults;
} else {
modepage = page_code;
goto Page_found;
}
} else {
/* Go to the next page */
if (spf && len - offset > 3)
offset += 4 + (buffer[offset+2] << 8) +
buffer[offset+3];
else if (!spf && len - offset > 1)
offset += 2 + buffer[offset+1];
else {
sd_printk(KERN_ERR, sdkp, "Incomplete "
"mode parameter data\n");
goto defaults;
}
}
}
[SCSI] Retrieve the Caching mode page Some kernel transport drivers unconditionally disable retrieval of the Caching mode page. One such for example is the BBB/CBI transport over USB.  Such a restraint is too harsh as some devices do support the Caching mode page. Unconditionally enabling the retrieval of this mode page over those transports at their transport code level may result in some devices failing and becoming unusable. This patch implements a method of retrieving the Caching mode page without unconditionally enabling it in the transports which unconditionally disable it. The idea is to ask for all supported pages, page code 0x3F, and then search for the Caching mode page in the mode parameter data returned. The sd driver already asks for all the mode pages supported by the attached device by setting the page code to 0x3F in order to find out if the media is write protected by reading the WP bit in the Device Specific Parameter field. It then attempts to retrieve only the Caching mode page by setting the page code to 8 and actually attempting to retrieve it if and only if the transport allows it. The method implemented here is that if the transport doesn't allow retrieval of the Caching mode page and the device is not RBC, then we ask for all pages supported by setting the page code to 0x3F (similarly to how the WP bit is retrieved above), and then we search for the Caching mode page in the mode parameter data returned. With this patch, devices over SATA, report this (no change): Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] 976773168 512-byte logical blocks: (500 GB/465 GiB) Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: Attached scsi generic sg0 type 0 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA Smart devices report their Caching mode page. This is a change where we'd previously see the kernel making assumption about the device's cache being write-through: Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: Attached scsi generic sg2 type 0 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] 610472646 4096-byte logical blocks: (2.50 TB/2.27 TiB) Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Mode Sense: 47 00 10 08 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write cache: enabled, read cache: enabled, supports DPO and FUA And "dumb" devices over BBB, are correctly shown not to support reporting the Caching mode page: Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] 15663104 512-byte logical blocks: (8.01 GB/7.46 GiB) Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Write Protect is off Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Mode Sense: 23 00 00 00 Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] No Caching mode page present Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Assuming drive cache: write through Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2010-10-23 04:24:36 +00:00
if (modepage == 0x3F) {
sd_printk(KERN_ERR, sdkp, "No Caching mode page "
"present\n");
goto defaults;
} else if ((buffer[offset] & 0x3f) != modepage) {
sd_printk(KERN_ERR, sdkp, "Got wrong page\n");
goto defaults;
}
[SCSI] Retrieve the Caching mode page Some kernel transport drivers unconditionally disable retrieval of the Caching mode page. One such for example is the BBB/CBI transport over USB.  Such a restraint is too harsh as some devices do support the Caching mode page. Unconditionally enabling the retrieval of this mode page over those transports at their transport code level may result in some devices failing and becoming unusable. This patch implements a method of retrieving the Caching mode page without unconditionally enabling it in the transports which unconditionally disable it. The idea is to ask for all supported pages, page code 0x3F, and then search for the Caching mode page in the mode parameter data returned. The sd driver already asks for all the mode pages supported by the attached device by setting the page code to 0x3F in order to find out if the media is write protected by reading the WP bit in the Device Specific Parameter field. It then attempts to retrieve only the Caching mode page by setting the page code to 8 and actually attempting to retrieve it if and only if the transport allows it. The method implemented here is that if the transport doesn't allow retrieval of the Caching mode page and the device is not RBC, then we ask for all pages supported by setting the page code to 0x3F (similarly to how the WP bit is retrieved above), and then we search for the Caching mode page in the mode parameter data returned. With this patch, devices over SATA, report this (no change): Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] 976773168 512-byte logical blocks: (500 GB/465 GiB) Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: Attached scsi generic sg0 type 0 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00 Oct 22 18:45:58 localhost kernel: sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA Smart devices report their Caching mode page. This is a change where we'd previously see the kernel making assumption about the device's cache being write-through: Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: Attached scsi generic sg2 type 0 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] 610472646 4096-byte logical blocks: (2.50 TB/2.27 TiB) Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write Protect is off Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Mode Sense: 47 00 10 08 Oct 22 18:45:58 localhost kernel: sd 6:0:0:0: [sdb] Write cache: enabled, read cache: enabled, supports DPO and FUA And "dumb" devices over BBB, are correctly shown not to support reporting the Caching mode page: Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] 15663104 512-byte logical blocks: (8.01 GB/7.46 GiB) Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Write Protect is off Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Mode Sense: 23 00 00 00 Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] No Caching mode page present Oct 22 18:49:06 localhost kernel: sd 7:0:0:0: [sdc] Assuming drive cache: write through Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2010-10-23 04:24:36 +00:00
Page_found:
if (modepage == 8) {
sdkp->WCE = ((buffer[offset + 2] & 0x04) != 0);
sdkp->RCD = ((buffer[offset + 2] & 0x01) != 0);
} else {
sdkp->WCE = ((buffer[offset + 2] & 0x01) == 0);
sdkp->RCD = 0;
}
sdkp->DPOFUA = (data.device_specific & 0x10) != 0;
if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
sd_printk(KERN_NOTICE, sdkp,
"Uses READ/WRITE(6), disabling FUA\n");
sdkp->DPOFUA = 0;
}
if (sdkp->first_scan || old_wce != sdkp->WCE ||
old_rcd != sdkp->RCD || old_dpofua != sdkp->DPOFUA)
sd_printk(KERN_NOTICE, sdkp,
"Write cache: %s, read cache: %s, %s\n",
sdkp->WCE ? "enabled" : "disabled",
sdkp->RCD ? "disabled" : "enabled",
sdkp->DPOFUA ? "supports DPO and FUA"
: "doesn't support DPO or FUA");
return;
}
bad_sense:
if (scsi_sense_valid(&sshdr) &&
sshdr.sense_key == ILLEGAL_REQUEST &&
sshdr.asc == 0x24 && sshdr.ascq == 0x0)
/* Invalid field in CDB */
sd_printk(KERN_NOTICE, sdkp, "Cache data unavailable\n");
else
sd_printk(KERN_ERR, sdkp, "Asking for cache data failed\n");
defaults:
sd_printk(KERN_ERR, sdkp, "Assuming drive cache: write through\n");
sdkp->WCE = 0;
sdkp->RCD = 0;
sdkp->DPOFUA = 0;
}
/*
* The ATO bit indicates whether the DIF application tag is available
* for use by the operating system.
*/
static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer)
{
int res, offset;
struct scsi_device *sdp = sdkp->device;
struct scsi_mode_data data;
struct scsi_sense_hdr sshdr;
if (sdp->type != TYPE_DISK)
return;
if (sdkp->protection_type == 0)
return;
res = scsi_mode_sense(sdp, 1, 0x0a, buffer, 36, SD_TIMEOUT,
SD_MAX_RETRIES, &data, &sshdr);
if (!scsi_status_is_good(res) || !data.header_length ||
data.length < 6) {
sd_printk(KERN_WARNING, sdkp,
"getting Control mode page failed, assume no ATO\n");
if (scsi_sense_valid(&sshdr))
sd_print_sense_hdr(sdkp, &sshdr);
return;
}
offset = data.header_length + data.block_descriptor_length;
if ((buffer[offset] & 0x3f) != 0x0a) {
sd_printk(KERN_ERR, sdkp, "ATO Got wrong page\n");
return;
}
if ((buffer[offset + 5] & 0x80) == 0)
return;
sdkp->ATO = 1;
return;
}
/**
* sd_read_block_limits - Query disk device for preferred I/O sizes.
* @disk: disk to query
*/
static void sd_read_block_limits(struct scsi_disk *sdkp)
{
struct request_queue *q = sdkp->disk->queue;
unsigned int sector_sz = sdkp->device->sector_size;
const int vpd_len = 64;
unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL);
if (!buffer ||
/* Block Limits VPD */
scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len))
goto out;
blk_queue_io_min(sdkp->disk->queue,
get_unaligned_be16(&buffer[6]) * sector_sz);
blk_queue_io_opt(sdkp->disk->queue,
get_unaligned_be32(&buffer[12]) * sector_sz);
/* Thin provisioning enabled and page length indicates TP support */
if (sdkp->thin_provisioning && buffer[3] == 0x3c) {
unsigned int lba_count, desc_count, granularity;
lba_count = get_unaligned_be32(&buffer[20]);
desc_count = get_unaligned_be32(&buffer[24]);
if (lba_count && desc_count) {
if (sdkp->tpvpd && !sdkp->tpu)
sdkp->unmap = 0;
else
sdkp->unmap = 1;
}
if (sdkp->tpvpd && !sdkp->tpu && !sdkp->tpws) {
sd_printk(KERN_ERR, sdkp, "Thin provisioning is " \
"enabled but neither TPU, nor TPWS are " \
"set. Disabling discard!\n");
goto out;
}
if (lba_count)
q->limits.max_discard_sectors =
lba_count * sector_sz >> 9;
granularity = get_unaligned_be32(&buffer[28]);
if (granularity)
q->limits.discard_granularity = granularity * sector_sz;
if (buffer[32] & 0x80)
q->limits.discard_alignment =
get_unaligned_be32(&buffer[32]) & ~(1 << 31);
}
out:
kfree(buffer);
}
/**
* sd_read_block_characteristics - Query block dev. characteristics
* @disk: disk to query
*/
static void sd_read_block_characteristics(struct scsi_disk *sdkp)
{
unsigned char *buffer;
u16 rot;
const int vpd_len = 64;
buffer = kmalloc(vpd_len, GFP_KERNEL);
if (!buffer ||
/* Block Device Characteristics VPD */
scsi_get_vpd_page(sdkp->device, 0xb1, buffer, vpd_len))
goto out;
rot = get_unaligned_be16(&buffer[4]);
if (rot == 1)
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, sdkp->disk->queue);
out:
kfree(buffer);
}
/**
* sd_read_thin_provisioning - Query thin provisioning VPD page
* @disk: disk to query
*/
static void sd_read_thin_provisioning(struct scsi_disk *sdkp)
{
unsigned char *buffer;
const int vpd_len = 8;
if (sdkp->thin_provisioning == 0)
return;
buffer = kmalloc(vpd_len, GFP_KERNEL);
if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb2, buffer, vpd_len))
goto out;
sdkp->tpvpd = 1;
sdkp->tpu = (buffer[5] >> 7) & 1; /* UNMAP */
sdkp->tpws = (buffer[5] >> 6) & 1; /* WRITE SAME(16) with UNMAP */
out:
kfree(buffer);
}
static int sd_try_extended_inquiry(struct scsi_device *sdp)
{
/*
* Although VPD inquiries can go to SCSI-2 type devices,
* some USB ones crash on receiving them, and the pages
* we currently ask for are for SPC-3 and beyond
*/
if (sdp->scsi_level > SCSI_SPC_2)
return 1;
return 0;
}
/**
* sd_revalidate_disk - called the first time a new disk is seen,
* performs disk spin up, read_capacity, etc.
* @disk: struct gendisk we care about
**/
static int sd_revalidate_disk(struct gendisk *disk)
{
struct scsi_disk *sdkp = scsi_disk(disk);
struct scsi_device *sdp = sdkp->device;
unsigned char *buffer;
unsigned flush = 0;
SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
"sd_revalidate_disk\n"));
/*
* If the device is offline, don't try and read capacity or any
* of the other niceties.
*/
if (!scsi_device_online(sdp))
goto out;
buffer = kmalloc(SD_BUF_SIZE, GFP_KERNEL);
if (!buffer) {
sd_printk(KERN_WARNING, sdkp, "sd_revalidate_disk: Memory "
"allocation failure.\n");
goto out;
}
sd_spinup_disk(sdkp);
/*
* Without media there is no reason to ask; moreover, some devices
* react badly if we do.
*/
if (sdkp->media_present) {
sd_read_capacity(sdkp, buffer);
if (sd_try_extended_inquiry(sdp)) {
sd_read_thin_provisioning(sdkp);
sd_read_block_limits(sdkp);
sd_read_block_characteristics(sdkp);
}
sd_read_write_protect_flag(sdkp, buffer);
sd_read_cache_type(sdkp, buffer);
sd_read_app_tag_own(sdkp, buffer);
}
sdkp->first_scan = 0;
/*
* We now have all cache related info, determine how we deal
* with flush requests.
*/
if (sdkp->WCE) {
flush |= REQ_FLUSH;
if (sdkp->DPOFUA)
flush |= REQ_FUA;
}
blk_queue_flush(sdkp->disk->queue, flush);
set_capacity(disk, sdkp->capacity);
kfree(buffer);
out:
return 0;
}
/**
* sd_unlock_native_capacity - unlock native capacity
* @disk: struct gendisk to set capacity for
*
* Block layer calls this function if it detects that partitions
* on @disk reach beyond the end of the device. If the SCSI host
* implements ->unlock_native_capacity() method, it's invoked to
* give it a chance to adjust the device capacity.
*
* CONTEXT:
* Defined by block layer. Might sleep.
*/
static void sd_unlock_native_capacity(struct gendisk *disk)
{
struct scsi_device *sdev = scsi_disk(disk)->device;
if (sdev->host->hostt->unlock_native_capacity)
sdev->host->hostt->unlock_native_capacity(sdev);
}
/**
* sd_format_disk_name - format disk name
* @prefix: name prefix - ie. "sd" for SCSI disks
* @index: index of the disk to format name for
* @buf: output buffer
* @buflen: length of the output buffer
*
* SCSI disk names starts at sda. The 26th device is sdz and the
* 27th is sdaa. The last one for two lettered suffix is sdzz
* which is followed by sdaaa.
*
* This is basically 26 base counting with one extra 'nil' entry
* at the beginning from the second digit on and can be
* determined using similar method as 26 base conversion with the
* index shifted -1 after each digit is computed.
*
* CONTEXT:
* Don't care.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
static int sd_format_disk_name(char *prefix, int index, char *buf, int buflen)
{
const int base = 'z' - 'a' + 1;
char *begin = buf + strlen(prefix);
char *end = buf + buflen;
char *p;
int unit;
p = end - 1;
*p = '\0';
unit = base;
do {
if (p == begin)
return -EINVAL;
*--p = 'a' + (index % unit);
index = (index / unit) - 1;
} while (index >= 0);
memmove(begin, p, end - p);
memcpy(buf, prefix, strlen(prefix));
return 0;
}
/*
* The asynchronous part of sd_probe
*/
static void sd_probe_async(void *data, async_cookie_t cookie)
{
struct scsi_disk *sdkp = data;
struct scsi_device *sdp;
struct gendisk *gd;
u32 index;
struct device *dev;
sdp = sdkp->device;
gd = sdkp->disk;
index = sdkp->index;
dev = &sdp->sdev_gendev;
gd->major = sd_major((index & 0xf0) >> 4);
gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00);
gd->minors = SD_MINORS;
gd->fops = &sd_fops;
gd->private_data = &sdkp->driver;
gd->queue = sdkp->device->request_queue;
/* defaults, until the device tells us otherwise */
sdp->sector_size = 512;
sdkp->capacity = 0;
sdkp->media_present = 1;
sdkp->write_prot = 0;
sdkp->WCE = 0;
sdkp->RCD = 0;
sdkp->ATO = 0;
sdkp->first_scan = 1;
sd_revalidate_disk(gd);
blk_queue_prep_rq(sdp->request_queue, sd_prep_fn);
blk_queue_unprep_rq(sdp->request_queue, sd_unprep_fn);
gd->driverfs_dev = &sdp->sdev_gendev;
gd->flags = GENHD_FL_EXT_DEVT;
if (sdp->removable) {
gd->flags |= GENHD_FL_REMOVABLE;
gd->events |= DISK_EVENT_MEDIA_CHANGE;
}
add_disk(gd);
sd_dif_config_host(sdkp);
sd_revalidate_disk(gd);
sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n",
sdp->removable ? "removable " : "");
scsi_autopm_put_device(sdp);
[SCSI] fix oops during scsi scanning Chris Webb reported: p0# uname -a Linux f7ea8425-d45b-490f-a738-d181d0df6963.host.elastichosts.com 2.6.30.4-elastic-lon-p #2 SMP PREEMPT Thu Aug 20 14:30:50 BST 2009 x86_64 Intel(R) Xeon(R) CPU E5420 @ 2.50GHz GenuineIntel GNU/Linux p0# zgrep SCAN_ASYNC /proc/config.gz # CONFIG_SCSI_SCAN_ASYNC is not set p0# cat /var/log/kern/2009-08-20 [...] 15:27:10.485 kernel: scsi9 : iSCSI Initiator over TCP/IP 15:27:11.493 kernel: scsi 9:0:0:0: RAID IET Controller 0001 PQ: 0 ANSI: 5 15:27:11.493 kernel: scsi 9:0:0:0: Attached scsi generic sg6 type 12 15:27:11.495 kernel: scsi 9:0:0:1: Direct-Access IET VIRTUAL-DISK 0001 PQ: 0 ANSI: 5 15:27:11.495 kernel: sd 9:0:0:1: Attached scsi generic sg7 type 0 15:27:11.495 kernel: sd 9:0:0:1: [sdg] 4194304 512-byte hardware sectors: (2.14 GB/2.00 GiB) 15:27:11.495 kernel: sd 9:0:0:1: [sdg] Write Protect is off 15:27:11.495 kernel: sd 9:0:0:1: [sdg] Write cache: disabled, read cache: enabled, doesn't support DPO or FUA 15:27:13.012 kernel: sdg:<6>scsi 9:0:0:1: [sdg] Unhandled error code 15:27:13.012 kernel: scsi 9:0:0:1: [sdg] Result: hostbyte=0x07 driverbyte=0x00 15:27:13.012 kernel: end_request: I/O error, dev sdg, sector 0 15:27:13.012 kernel: Buffer I/O error on device sdg, logical block 0 15:27:13.012 kernel: ldm_validate_partition_table(): Disk read failed. 15:27:13.012 kernel: unable to read partition table 15:27:13.014 kernel: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 15:27:13.014 kernel: IP: [<ffffffff803f0d77>] disk_part_iter_next+0x74/0xfd 15:27:13.014 kernel: PGD 82ad0b067 PUD 82cd7e067 PMD 0 15:27:13.014 kernel: Oops: 0000 [#1] PREEMPT SMP 15:27:13.014 kernel: last sysfs file: /sys/devices/platform/host9/session4/iscsi_session/session4/ifacename 15:27:13.014 kernel: CPU 5 15:27:13.014 kernel: Modules linked in: 15:27:13.014 kernel: Pid: 13999, comm: async/0 Not tainted 2.6.30.4-elastic-lon-p #2 X7DBN 15:27:13.014 kernel: RIP: 0010:[<ffffffff803f0d77>] [<ffffffff803f0d77>] disk_part_iter_next+0x74/0xfd 15:27:13.014 kernel: RSP: 0018:ffff88066afa3dd0 EFLAGS: 00010246 15:27:13.014 kernel: RAX: ffff88082b58a000 RBX: ffff88066afa3e00 RCX: 0000000000000000 15:27:13.014 kernel: RDX: 0000000000000000 RSI: ffff88082b58a000 RDI: 0000000000000000 15:27:13.014 kernel: RBP: ffff88066afa3df0 R08: ffff88066afa2000 R09: ffff8806a204f000 15:27:13.014 kernel: R10: 000000fb12c7d274 R11: ffff8806c2bf0628 R12: ffff88066afa3e00 15:27:13.014 kernel: R13: ffff88082c829a00 R14: 0000000000000000 R15: ffff8806bc50c920 15:27:13.014 kernel: FS: 0000000000000000(0000) GS:ffff88002818a000(0000) knlGS:0000000000000000 15:27:13.014 kernel: CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b 15:27:13.014 kernel: CR2: 0000000000000010 CR3: 000000082ade3000 CR4: 00000000000426e0 15:27:13.014 kernel: DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 15:27:13.014 kernel: DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 15:27:13.014 kernel: Process async/0 (pid: 13999, threadinfo ffff88066afa2000, task ffff8806c2bf05e0) 15:27:13.014 kernel: Stack: 15:27:13.014 kernel: 0000000000000000 ffff88066afa3e00 ffff88066afa3e00 ffff88082c829a00 15:27:13.014 kernel: ffff88066afa3e40 ffffffff80306feb ffff88082b58a000 0000000000000000 15:27:13.014 kernel: 0000000000000001 ffff8806bc50c920 ffff88066afa3e40 ffff88082b58a000 15:27:13.014 kernel: Call Trace: 15:27:13.014 kernel: [<ffffffff80306feb>] register_disk+0x122/0x13a 15:27:13.014 kernel: [<ffffffff803f0b0f>] add_disk+0xaa/0x106 15:27:13.014 kernel: [<ffffffff80493609>] sd_probe_async+0x198/0x25b 15:27:13.014 kernel: [<ffffffff80270482>] async_thread+0x10c/0x20d 15:27:13.014 kernel: [<ffffffff802545ff>] ? default_wake_function+0x0/0xf 15:27:13.014 kernel: [<ffffffff80270376>] ? async_thread+0x0/0x20d 15:27:13.014 kernel: [<ffffffff8026ad89>] kthread+0x55/0x80 15:27:13.014 kernel: [<ffffffff8022be6a>] child_rip+0xa/0x20 15:27:13.014 kernel: [<ffffffff8026ad34>] ? kthread+0x0/0x80 15:27:13.014 kernel: [<ffffffff8022be60>] ? child_rip+0x0/0x20 15:27:13.014 kernel: Code: c8 ff 80 e1 0c b9 00 00 00 00 0f 44 c1 41 83 cd ff 48 8d 7a 20 48 be ff ff ff ff 08 00 00 00 48 b9 00 00 00 00 08 00 00 00 eb 50 <8b> 42 10 41 bd 01 00 00 00 eb db 4c 63 c2 4e 8d 04 c7 4d 8b 20 15:27:13.015 kernel: RIP [<ffffffff803f0d77>] disk_part_iter_next+0x74/0xfd 15:27:13.015 kernel: RSP <ffff88066afa3dd0> 15:27:13.015 kernel: CR2: 0000000000000010 15:27:13.015 kernel: ---[ end trace 6104b56ef5590e25 ]--- The problem is caused because the async scanning split in sd.c doesn't hold any reference to the device when it kicks off the async piece. What's happening is that an iSCSI disconnect is destorying the device again *before* the async sd scanning thread even starts. Fix this by taking a reference before starting the thread and dropping it again when the thread completes. Reported-by: Chris Webb <chris@arachsys.com> Cc: Stable Tree <stable@kernel.org> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2009-08-21 15:47:54 +00:00
put_device(&sdkp->dev);
}
/**
* sd_probe - called during driver initialization and whenever a
* new scsi device is attached to the system. It is called once
* for each scsi device (not just disks) present.
* @dev: pointer to device object
*
* Returns 0 if successful (or not interested in this scsi device
* (e.g. scanner)); 1 when there is an error.
*
* Note: this function is invoked from the scsi mid-level.
* This function sets up the mapping between a given
* <host,channel,id,lun> (found in sdp) and new device name
* (e.g. /dev/sda). More precisely it is the block device major
* and minor number that is chosen here.
*
* Assume sd_attach is not re-entrant (for time being)
* Also think about sd_attach() and sd_remove() running coincidentally.
**/
static int sd_probe(struct device *dev)
{
struct scsi_device *sdp = to_scsi_device(dev);
struct scsi_disk *sdkp;
struct gendisk *gd;
int index;
int error;
error = -ENODEV;
if (sdp->type != TYPE_DISK && sdp->type != TYPE_MOD && sdp->type != TYPE_RBC)
goto out;
SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp,
"sd_attach\n"));
error = -ENOMEM;
sdkp = kzalloc(sizeof(*sdkp), GFP_KERNEL);
if (!sdkp)
goto out;
gd = alloc_disk(SD_MINORS);
if (!gd)
goto out_free;
do {
if (!ida_pre_get(&sd_index_ida, GFP_KERNEL))
goto out_put;
spin_lock(&sd_index_lock);
error = ida_get_new(&sd_index_ida, &index);
spin_unlock(&sd_index_lock);
} while (error == -EAGAIN);
if (error)
goto out_put;
if (index >= SD_MAX_DISKS) {
error = -ENODEV;
sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name space exhausted.\n");
goto out_free_index;
}
error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN);
if (error)
goto out_free_index;
sdkp->device = sdp;
sdkp->driver = &sd_template;
sdkp->disk = gd;
sdkp->index = index;
atomic_set(&sdkp->openers, 0);
if (!sdp->request_queue->rq_timeout) {
if (sdp->type != TYPE_MOD)
blk_queue_rq_timeout(sdp->request_queue, SD_TIMEOUT);
else
blk_queue_rq_timeout(sdp->request_queue,
SD_MOD_TIMEOUT);
}
device_initialize(&sdkp->dev);
sdkp->dev.parent = dev;
sdkp->dev.class = &sd_disk_class;
dev_set_name(&sdkp->dev, dev_name(dev));
if (device_add(&sdkp->dev))
goto out_free_index;
get_device(dev);
dev_set_drvdata(dev, sdkp);
[SCSI] fix oops during scsi scanning Chris Webb reported: p0# uname -a Linux f7ea8425-d45b-490f-a738-d181d0df6963.host.elastichosts.com 2.6.30.4-elastic-lon-p #2 SMP PREEMPT Thu Aug 20 14:30:50 BST 2009 x86_64 Intel(R) Xeon(R) CPU E5420 @ 2.50GHz GenuineIntel GNU/Linux p0# zgrep SCAN_ASYNC /proc/config.gz # CONFIG_SCSI_SCAN_ASYNC is not set p0# cat /var/log/kern/2009-08-20 [...] 15:27:10.485 kernel: scsi9 : iSCSI Initiator over TCP/IP 15:27:11.493 kernel: scsi 9:0:0:0: RAID IET Controller 0001 PQ: 0 ANSI: 5 15:27:11.493 kernel: scsi 9:0:0:0: Attached scsi generic sg6 type 12 15:27:11.495 kernel: scsi 9:0:0:1: Direct-Access IET VIRTUAL-DISK 0001 PQ: 0 ANSI: 5 15:27:11.495 kernel: sd 9:0:0:1: Attached scsi generic sg7 type 0 15:27:11.495 kernel: sd 9:0:0:1: [sdg] 4194304 512-byte hardware sectors: (2.14 GB/2.00 GiB) 15:27:11.495 kernel: sd 9:0:0:1: [sdg] Write Protect is off 15:27:11.495 kernel: sd 9:0:0:1: [sdg] Write cache: disabled, read cache: enabled, doesn't support DPO or FUA 15:27:13.012 kernel: sdg:<6>scsi 9:0:0:1: [sdg] Unhandled error code 15:27:13.012 kernel: scsi 9:0:0:1: [sdg] Result: hostbyte=0x07 driverbyte=0x00 15:27:13.012 kernel: end_request: I/O error, dev sdg, sector 0 15:27:13.012 kernel: Buffer I/O error on device sdg, logical block 0 15:27:13.012 kernel: ldm_validate_partition_table(): Disk read failed. 15:27:13.012 kernel: unable to read partition table 15:27:13.014 kernel: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 15:27:13.014 kernel: IP: [<ffffffff803f0d77>] disk_part_iter_next+0x74/0xfd 15:27:13.014 kernel: PGD 82ad0b067 PUD 82cd7e067 PMD 0 15:27:13.014 kernel: Oops: 0000 [#1] PREEMPT SMP 15:27:13.014 kernel: last sysfs file: /sys/devices/platform/host9/session4/iscsi_session/session4/ifacename 15:27:13.014 kernel: CPU 5 15:27:13.014 kernel: Modules linked in: 15:27:13.014 kernel: Pid: 13999, comm: async/0 Not tainted 2.6.30.4-elastic-lon-p #2 X7DBN 15:27:13.014 kernel: RIP: 0010:[<ffffffff803f0d77>] [<ffffffff803f0d77>] disk_part_iter_next+0x74/0xfd 15:27:13.014 kernel: RSP: 0018:ffff88066afa3dd0 EFLAGS: 00010246 15:27:13.014 kernel: RAX: ffff88082b58a000 RBX: ffff88066afa3e00 RCX: 0000000000000000 15:27:13.014 kernel: RDX: 0000000000000000 RSI: ffff88082b58a000 RDI: 0000000000000000 15:27:13.014 kernel: RBP: ffff88066afa3df0 R08: ffff88066afa2000 R09: ffff8806a204f000 15:27:13.014 kernel: R10: 000000fb12c7d274 R11: ffff8806c2bf0628 R12: ffff88066afa3e00 15:27:13.014 kernel: R13: ffff88082c829a00 R14: 0000000000000000 R15: ffff8806bc50c920 15:27:13.014 kernel: FS: 0000000000000000(0000) GS:ffff88002818a000(0000) knlGS:0000000000000000 15:27:13.014 kernel: CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b 15:27:13.014 kernel: CR2: 0000000000000010 CR3: 000000082ade3000 CR4: 00000000000426e0 15:27:13.014 kernel: DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 15:27:13.014 kernel: DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 15:27:13.014 kernel: Process async/0 (pid: 13999, threadinfo ffff88066afa2000, task ffff8806c2bf05e0) 15:27:13.014 kernel: Stack: 15:27:13.014 kernel: 0000000000000000 ffff88066afa3e00 ffff88066afa3e00 ffff88082c829a00 15:27:13.014 kernel: ffff88066afa3e40 ffffffff80306feb ffff88082b58a000 0000000000000000 15:27:13.014 kernel: 0000000000000001 ffff8806bc50c920 ffff88066afa3e40 ffff88082b58a000 15:27:13.014 kernel: Call Trace: 15:27:13.014 kernel: [<ffffffff80306feb>] register_disk+0x122/0x13a 15:27:13.014 kernel: [<ffffffff803f0b0f>] add_disk+0xaa/0x106 15:27:13.014 kernel: [<ffffffff80493609>] sd_probe_async+0x198/0x25b 15:27:13.014 kernel: [<ffffffff80270482>] async_thread+0x10c/0x20d 15:27:13.014 kernel: [<ffffffff802545ff>] ? default_wake_function+0x0/0xf 15:27:13.014 kernel: [<ffffffff80270376>] ? async_thread+0x0/0x20d 15:27:13.014 kernel: [<ffffffff8026ad89>] kthread+0x55/0x80 15:27:13.014 kernel: [<ffffffff8022be6a>] child_rip+0xa/0x20 15:27:13.014 kernel: [<ffffffff8026ad34>] ? kthread+0x0/0x80 15:27:13.014 kernel: [<ffffffff8022be60>] ? child_rip+0x0/0x20 15:27:13.014 kernel: Code: c8 ff 80 e1 0c b9 00 00 00 00 0f 44 c1 41 83 cd ff 48 8d 7a 20 48 be ff ff ff ff 08 00 00 00 48 b9 00 00 00 00 08 00 00 00 eb 50 <8b> 42 10 41 bd 01 00 00 00 eb db 4c 63 c2 4e 8d 04 c7 4d 8b 20 15:27:13.015 kernel: RIP [<ffffffff803f0d77>] disk_part_iter_next+0x74/0xfd 15:27:13.015 kernel: RSP <ffff88066afa3dd0> 15:27:13.015 kernel: CR2: 0000000000000010 15:27:13.015 kernel: ---[ end trace 6104b56ef5590e25 ]--- The problem is caused because the async scanning split in sd.c doesn't hold any reference to the device when it kicks off the async piece. What's happening is that an iSCSI disconnect is destorying the device again *before* the async sd scanning thread even starts. Fix this by taking a reference before starting the thread and dropping it again when the thread completes. Reported-by: Chris Webb <chris@arachsys.com> Cc: Stable Tree <stable@kernel.org> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2009-08-21 15:47:54 +00:00
get_device(&sdkp->dev); /* prevent release before async_schedule */
async_schedule(sd_probe_async, sdkp);
return 0;
out_free_index:
spin_lock(&sd_index_lock);
ida_remove(&sd_index_ida, index);
spin_unlock(&sd_index_lock);
out_put:
put_disk(gd);
out_free:
kfree(sdkp);
out:
return error;
}
/**
* sd_remove - called whenever a scsi disk (previously recognized by
* sd_probe) is detached from the system. It is called (potentially
* multiple times) during sd module unload.
* @sdp: pointer to mid level scsi device object
*
* Note: this function is invoked from the scsi mid-level.
* This function potentially frees up a device name (e.g. /dev/sdc)
* that could be re-used by a subsequent sd_probe().
* This function is not called when the built-in sd driver is "exit-ed".
**/
static int sd_remove(struct device *dev)
{
struct scsi_disk *sdkp;
sdkp = dev_get_drvdata(dev);
scsi_autopm_get_device(sdkp->device);
async_synchronize_full();
blk_queue_prep_rq(sdkp->device->request_queue, scsi_prep_fn);
blk_queue_unprep_rq(sdkp->device->request_queue, NULL);
device_del(&sdkp->dev);
del_gendisk(sdkp->disk);
sd_shutdown(dev);
mutex_lock(&sd_ref_mutex);
dev_set_drvdata(dev, NULL);
put_device(&sdkp->dev);
mutex_unlock(&sd_ref_mutex);
return 0;
}
/**
* scsi_disk_release - Called to free the scsi_disk structure
* @dev: pointer to embedded class device
*
* sd_ref_mutex must be held entering this routine. Because it is
* called on last put, you should always use the scsi_disk_get()
* scsi_disk_put() helpers which manipulate the semaphore directly
* and never do a direct put_device.
**/
static void scsi_disk_release(struct device *dev)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct gendisk *disk = sdkp->disk;
spin_lock(&sd_index_lock);
ida_remove(&sd_index_ida, sdkp->index);
spin_unlock(&sd_index_lock);
disk->private_data = NULL;
put_disk(disk);
put_device(&sdkp->device->sdev_gendev);
kfree(sdkp);
}
static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
{
unsigned char cmd[6] = { START_STOP }; /* START_VALID */
struct scsi_sense_hdr sshdr;
struct scsi_device *sdp = sdkp->device;
int res;
if (start)
cmd[4] |= 1; /* START */
if (sdp->start_stop_pwr_cond)
cmd[4] |= start ? 1 << 4 : 3 << 4; /* Active or Standby */
if (!scsi_device_online(sdp))
return -ENODEV;
res = scsi_execute_req(sdp, cmd, DMA_NONE, NULL, 0, &sshdr,
SD_TIMEOUT, SD_MAX_RETRIES, NULL);
if (res) {
sd_printk(KERN_WARNING, sdkp, "START_STOP FAILED\n");
sd_print_result(sdkp, res);
if (driver_byte(res) & DRIVER_SENSE)
sd_print_sense_hdr(sdkp, &sshdr);
}
return res;
}
/*
* Send a SYNCHRONIZE CACHE instruction down to the device through
* the normal SCSI command structure. Wait for the command to
* complete.
*/
static void sd_shutdown(struct device *dev)
{
struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev);
if (!sdkp)
return; /* this can happen */
if (sdkp->WCE) {
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
sd_sync_cache(sdkp);
}
if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) {
sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
sd_start_stop_device(sdkp, 0);
}
scsi_disk_put(sdkp);
}
static int sd_suspend(struct device *dev, pm_message_t mesg)
{
struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev);
int ret = 0;
if (!sdkp)
return 0; /* this can happen */
if (sdkp->WCE) {
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
ret = sd_sync_cache(sdkp);
if (ret)
goto done;
}
if ((mesg.event & PM_EVENT_SLEEP) && sdkp->device->manage_start_stop) {
sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
ret = sd_start_stop_device(sdkp, 0);
}
done:
scsi_disk_put(sdkp);
return ret;
}
static int sd_resume(struct device *dev)
{
struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev);
int ret = 0;
if (!sdkp->device->manage_start_stop)
goto done;
sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
ret = sd_start_stop_device(sdkp, 1);
done:
scsi_disk_put(sdkp);
return ret;
}
/**
* init_sd - entry point for this driver (both when built in or when
* a module).
*
* Note: this function registers this driver with the scsi mid-level.
**/
static int __init init_sd(void)
{
int majors = 0, i, err;
SCSI_LOG_HLQUEUE(3, printk("init_sd: sd driver entry point\n"));
for (i = 0; i < SD_MAJORS; i++)
if (register_blkdev(sd_major(i), "sd") == 0)
majors++;
if (!majors)
return -ENODEV;
err = class_register(&sd_disk_class);
if (err)
goto err_out;
err = scsi_register_driver(&sd_template.gendrv);
if (err)
goto err_out_class;
sd_cdb_cache = kmem_cache_create("sd_ext_cdb", SD_EXT_CDB_SIZE,
0, 0, NULL);
if (!sd_cdb_cache) {
printk(KERN_ERR "sd: can't init extended cdb cache\n");
goto err_out_class;
}
sd_cdb_pool = mempool_create_slab_pool(SD_MEMPOOL_SIZE, sd_cdb_cache);
if (!sd_cdb_pool) {
printk(KERN_ERR "sd: can't init extended cdb pool\n");
goto err_out_cache;
}
return 0;
err_out_cache:
kmem_cache_destroy(sd_cdb_cache);
err_out_class:
class_unregister(&sd_disk_class);
err_out:
for (i = 0; i < SD_MAJORS; i++)
unregister_blkdev(sd_major(i), "sd");
return err;
}
/**
* exit_sd - exit point for this driver (when it is a module).
*
* Note: this function unregisters this driver from the scsi mid-level.
**/
static void __exit exit_sd(void)
{
int i;
SCSI_LOG_HLQUEUE(3, printk("exit_sd: exiting sd driver\n"));
mempool_destroy(sd_cdb_pool);
kmem_cache_destroy(sd_cdb_cache);
scsi_unregister_driver(&sd_template.gendrv);
class_unregister(&sd_disk_class);
for (i = 0; i < SD_MAJORS; i++)
unregister_blkdev(sd_major(i), "sd");
}
module_init(init_sd);
module_exit(exit_sd);
static void sd_print_sense_hdr(struct scsi_disk *sdkp,
struct scsi_sense_hdr *sshdr)
{
sd_printk(KERN_INFO, sdkp, " ");
scsi_show_sense_hdr(sshdr);
sd_printk(KERN_INFO, sdkp, " ");
scsi_show_extd_sense(sshdr->asc, sshdr->ascq);
}
static void sd_print_result(struct scsi_disk *sdkp, int result)
{
sd_printk(KERN_INFO, sdkp, " ");
scsi_show_result(result);
}