linux-sg2042/drivers/scsi/sd.c

3712 lines
97 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 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/sed-opal.h>
#include <linux/pm_runtime.h>
#include <linux/pr.h>
#include <linux/t10-pi.h>
#include <linux/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"
[SCSI] sd: limit the scope of the async probe domain sd injects and synchronizes probe work on the global kernel-wide domain. This runs into conflict with PM that wants to perform resume actions in async context: [ 494.237079] INFO: task kworker/u:3:554 blocked for more than 120 seconds. [ 494.294396] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 494.360809] kworker/u:3 D 0000000000000000 0 554 2 0x00000000 [ 494.420739] ffff88012e4d3af0 0000000000000046 ffff88013200c160 ffff88012e4d3fd8 [ 494.484392] ffff88012e4d3fd8 0000000000012500 ffff8801394ea0b0 ffff88013200c160 [ 494.548038] ffff88012e4d3ae0 00000000000001e3 ffffffff81a249e0 ffff8801321c5398 [ 494.611685] Call Trace: [ 494.632649] [<ffffffff8149dd25>] schedule+0x5a/0x5c [ 494.674687] [<ffffffff8104b968>] async_synchronize_cookie_domain+0xb6/0x112 [ 494.734177] [<ffffffff810461ff>] ? __init_waitqueue_head+0x50/0x50 [ 494.787134] [<ffffffff8131a224>] ? scsi_remove_target+0x48/0x48 [ 494.837900] [<ffffffff8104b9d9>] async_synchronize_cookie+0x15/0x17 [ 494.891567] [<ffffffff8104ba49>] async_synchronize_full+0x54/0x70 <-- here we wait for async contexts to complete [ 494.943783] [<ffffffff8104b9f5>] ? async_synchronize_full_domain+0x1a/0x1a [ 495.002547] [<ffffffffa00114b1>] sd_remove+0x2c/0xa2 [sd_mod] [ 495.051861] [<ffffffff812fe94f>] __device_release_driver+0x86/0xcf [ 495.104807] [<ffffffff812fe9bd>] device_release_driver+0x25/0x32 <-- here we take device_lock() [ 853.511341] INFO: task kworker/u:4:549 blocked for more than 120 seconds. [ 853.568693] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 853.635119] kworker/u:4 D ffff88013097b5d0 0 549 2 0x00000000 [ 853.695129] ffff880132773c40 0000000000000046 ffff880130790000 ffff880132773fd8 [ 853.758990] ffff880132773fd8 0000000000012500 ffff88013288a0b0 ffff880130790000 [ 853.822796] 0000000000000246 0000000000000040 ffff88013097b5c8 ffff880130790000 [ 853.886633] Call Trace: [ 853.907631] [<ffffffff8149dd25>] schedule+0x5a/0x5c [ 853.949670] [<ffffffff8149cc44>] __mutex_lock_common+0x220/0x351 [ 854.001225] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4 [ 854.049082] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4 [ 854.097011] [<ffffffff8149ce48>] mutex_lock_nested+0x2f/0x36 <-- here we wait for device_lock() [ 854.145591] [<ffffffff81304bd7>] device_resume+0x58/0x1c4 [ 854.192066] [<ffffffff81304d61>] async_resume+0x1e/0x45 [ 854.237019] [<ffffffff8104bc93>] async_run_entry_fn+0xc6/0x173 <-- ...while running in async context Provide a 'scsi_sd_probe_domain' so that async probe actions actions can be flushed without regard for the state of PM, and allow for the resume path to handle devices that have transitioned from SDEV_QUIESCE to SDEV_DEL prior to resume. Acked-by: Alan Stern <stern@rowland.harvard.edu> [alan: uplevel scsi_sd_probe_domain, clarify scsi_device_resume] Signed-off-by: Dan Williams <dan.j.williams@intel.com> [jejb: remove unneeded config guards in include file] Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2012-03-23 08:05:11 +08:00
#include "scsi_priv.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 20:02:37 +08:00
MODULE_ALIAS_SCSI_DEVICE(TYPE_DISK);
MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD);
MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC);
#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT)
#define SD_MINORS 16
#else
#define SD_MINORS 0
#endif
static void sd_config_discard(struct scsi_disk *, unsigned int);
static void sd_config_write_same(struct scsi_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>
2008-01-07 02:17:12 +08:00
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>
2008-01-07 02:17:12 +08:00
static int sd_probe(struct device *);
static int sd_remove(struct device *);
static void sd_shutdown(struct device *);
static int sd_suspend_system(struct device *);
static int sd_suspend_runtime(struct device *);
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
static int sd_resume(struct device *);
static void sd_rescan(struct device *);
static int sd_init_command(struct scsi_cmnd *SCpnt);
static void sd_uninit_command(struct scsi_cmnd *SCpnt);
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
static int sd_done(struct scsi_cmnd *);
static void sd_eh_reset(struct scsi_cmnd *);
static int sd_eh_action(struct scsi_cmnd *, int);
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
static 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>
2008-01-07 02:17:12 +08:00
static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *);
static void sd_print_result(const struct scsi_disk *, const char *, int);
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
static 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 void sd_set_flush_flag(struct scsi_disk *sdkp)
{
bool wc = false, fua = false;
if (sdkp->WCE) {
wc = true;
if (sdkp->DPOFUA)
fua = true;
}
blk_queue_write_cache(sdkp->disk->queue, wc, fua);
}
static ssize_t
cache_type_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
int ct, 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;
static const char temp[] = "temporary ";
int len;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
/* 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;
if (strncmp(buf, temp, sizeof(temp) - 1) == 0) {
buf += sizeof(temp) - 1;
sdkp->cache_override = 1;
} else {
sdkp->cache_override = 0;
}
ct = sysfs_match_string(sd_cache_types, buf);
if (ct < 0)
return -EINVAL;
rcd = ct & 0x01 ? 1 : 0;
wce = (ct & 0x02) && !sdkp->write_prot ? 1 : 0;
if (sdkp->cache_override) {
sdkp->WCE = wce;
sdkp->RCD = rcd;
sd_set_flush_flag(sdkp);
return count;
}
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;
buffer_data[0] &= ~0x80;
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
manage_start_stop_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
struct scsi_device *sdp = sdkp->device;
return sprintf(buf, "%u\n", sdp->manage_start_stop);
}
static ssize_t
manage_start_stop_store(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 DEVICE_ATTR_RW(manage_start_stop);
static ssize_t
allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%u\n", sdkp->device->allow_restart);
}
static ssize_t
allow_restart_store(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;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
return -EINVAL;
sdp->allow_restart = simple_strtoul(buf, NULL, 10);
return count;
}
static DEVICE_ATTR_RW(allow_restart);
static ssize_t
cache_type_show(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 sprintf(buf, "%s\n", sd_cache_types[ct]);
}
static DEVICE_ATTR_RW(cache_type);
static ssize_t
FUA_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%u\n", sdkp->DPOFUA);
}
static DEVICE_ATTR_RO(FUA);
static ssize_t
protection_type_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%u\n", sdkp->protection_type);
}
static ssize_t
protection_type_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
unsigned int val;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
err = kstrtouint(buf, 10, &val);
if (err)
return err;
if (val <= T10_PI_TYPE3_PROTECTION)
sdkp->protection_type = val;
return count;
}
static DEVICE_ATTR_RW(protection_type);
static ssize_t
protection_mode_show(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, T10_PI_TYPE0_PROTECTION)) {
dif = 0;
dix = 1;
}
if (!dif && !dix)
return sprintf(buf, "none\n");
return sprintf(buf, "%s%u\n", dix ? "dix" : "dif", dif);
}
static DEVICE_ATTR_RO(protection_mode);
static ssize_t
app_tag_own_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%u\n", sdkp->ATO);
}
static DEVICE_ATTR_RO(app_tag_own);
static ssize_t
thin_provisioning_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%u\n", sdkp->lbpme);
}
static DEVICE_ATTR_RO(thin_provisioning);
/* sysfs_match_string() requires dense arrays */
static const char *lbp_mode[] = {
[SD_LBP_FULL] = "full",
[SD_LBP_UNMAP] = "unmap",
[SD_LBP_WS16] = "writesame_16",
[SD_LBP_WS10] = "writesame_10",
[SD_LBP_ZERO] = "writesame_zero",
[SD_LBP_DISABLE] = "disabled",
};
static ssize_t
provisioning_mode_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%s\n", lbp_mode[sdkp->provisioning_mode]);
}
static ssize_t
provisioning_mode_store(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;
int mode;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sd_is_zoned(sdkp)) {
sd_config_discard(sdkp, SD_LBP_DISABLE);
return count;
}
if (sdp->type != TYPE_DISK)
return -EINVAL;
mode = sysfs_match_string(lbp_mode, buf);
if (mode < 0)
return -EINVAL;
sd_config_discard(sdkp, mode);
return count;
}
static DEVICE_ATTR_RW(provisioning_mode);
/* sysfs_match_string() requires dense arrays */
static const char *zeroing_mode[] = {
[SD_ZERO_WRITE] = "write",
[SD_ZERO_WS] = "writesame",
[SD_ZERO_WS16_UNMAP] = "writesame_16_unmap",
[SD_ZERO_WS10_UNMAP] = "writesame_10_unmap",
};
static ssize_t
zeroing_mode_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%s\n", zeroing_mode[sdkp->zeroing_mode]);
}
static ssize_t
zeroing_mode_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
int mode;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
mode = sysfs_match_string(zeroing_mode, buf);
if (mode < 0)
return -EINVAL;
sdkp->zeroing_mode = mode;
return count;
}
static DEVICE_ATTR_RW(zeroing_mode);
static ssize_t
max_medium_access_timeouts_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%u\n", sdkp->max_medium_access_timeouts);
}
static ssize_t
max_medium_access_timeouts_store(struct device *dev,
struct device_attribute *attr, const char *buf,
size_t count)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
int err;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
err = kstrtouint(buf, 10, &sdkp->max_medium_access_timeouts);
return err ? err : count;
}
static DEVICE_ATTR_RW(max_medium_access_timeouts);
static ssize_t
max_write_same_blocks_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return sprintf(buf, "%u\n", sdkp->max_ws_blocks);
}
static ssize_t
max_write_same_blocks_store(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;
unsigned long max;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
return -EINVAL;
err = kstrtoul(buf, 10, &max);
if (err)
return err;
if (max == 0)
sdp->no_write_same = 1;
else if (max <= SD_MAX_WS16_BLOCKS) {
sdp->no_write_same = 0;
sdkp->max_ws_blocks = max;
}
sd_config_write_same(sdkp);
return count;
}
static DEVICE_ATTR_RW(max_write_same_blocks);
static struct attribute *sd_disk_attrs[] = {
&dev_attr_cache_type.attr,
&dev_attr_FUA.attr,
&dev_attr_allow_restart.attr,
&dev_attr_manage_start_stop.attr,
&dev_attr_protection_type.attr,
&dev_attr_protection_mode.attr,
&dev_attr_app_tag_own.attr,
&dev_attr_thin_provisioning.attr,
&dev_attr_provisioning_mode.attr,
&dev_attr_zeroing_mode.attr,
&dev_attr_max_write_same_blocks.attr,
&dev_attr_max_medium_access_timeouts.attr,
NULL,
};
ATTRIBUTE_GROUPS(sd_disk);
static struct class sd_disk_class = {
.name = "scsi_disk",
.owner = THIS_MODULE,
.dev_release = scsi_disk_release,
.dev_groups = sd_disk_groups,
};
static const struct dev_pm_ops sd_pm_ops = {
.suspend = sd_suspend_system,
.resume = sd_resume,
.poweroff = sd_suspend_system,
.restore = sd_resume,
.runtime_suspend = sd_suspend_runtime,
.runtime_resume = sd_resume,
};
static struct scsi_driver sd_template = {
.gendrv = {
.name = "sd",
.owner = THIS_MODULE,
.probe = sd_probe,
.remove = sd_remove,
.shutdown = sd_shutdown,
.pm = &sd_pm_ops,
},
.rescan = sd_rescan,
.init_command = sd_init_command,
.uninit_command = sd_uninit_command,
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
.done = sd_done,
.eh_action = sd_eh_action,
.eh_reset = sd_eh_reset,
};
/*
* Dummy kobj_map->probe function.
* The default ->probe function will call modprobe, which is
* pointless as this module is already loaded.
*/
static struct kobject *sd_default_probe(dev_t devt, int *partno, void *data)
{
return NULL;
}
/*
* 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;
mutex_lock(&sd_ref_mutex);
if (disk->private_data) {
sdkp = scsi_disk(disk);
if (scsi_device_get(sdkp->device) == 0)
get_device(&sdkp->dev);
else
sdkp = NULL;
}
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);
}
#ifdef CONFIG_BLK_SED_OPAL
static int sd_sec_submit(void *data, u16 spsp, u8 secp, void *buffer,
size_t len, bool send)
{
struct scsi_device *sdev = data;
u8 cdb[12] = { 0, };
int ret;
cdb[0] = send ? SECURITY_PROTOCOL_OUT : SECURITY_PROTOCOL_IN;
cdb[1] = secp;
put_unaligned_be16(spsp, &cdb[2]);
put_unaligned_be32(len, &cdb[6]);
ret = scsi_execute_req(sdev, cdb,
send ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
buffer, len, NULL, SD_TIMEOUT, SD_MAX_RETRIES, NULL);
return ret <= 0 ? ret : -EIO;
}
#endif /* CONFIG_BLK_SED_OPAL */
static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd,
unsigned int dix, unsigned int dif)
{
struct bio *bio = scmd->request->bio;
unsigned int prot_op = sd_prot_op(rq_data_dir(scmd->request), dix, dif);
unsigned int protect = 0;
if (dix) { /* DIX Type 0, 1, 2, 3 */
if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM))
scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM;
if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
scmd->prot_flags |= SCSI_PROT_GUARD_CHECK;
}
if (dif != T10_PI_TYPE3_PROTECTION) { /* DIX/DIF Type 0, 1, 2 */
scmd->prot_flags |= SCSI_PROT_REF_INCREMENT;
if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
scmd->prot_flags |= SCSI_PROT_REF_CHECK;
}
if (dif) { /* DIX/DIF Type 1, 2, 3 */
scmd->prot_flags |= SCSI_PROT_TRANSFER_PI;
if (bio_integrity_flagged(bio, BIP_DISK_NOCHECK))
protect = 3 << 5; /* Disable target PI checking */
else
protect = 1 << 5; /* Enable target PI checking */
}
scsi_set_prot_op(scmd, prot_op);
scsi_set_prot_type(scmd, dif);
scmd->prot_flags &= sd_prot_flag_mask(prot_op);
return protect;
}
static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
{
struct request_queue *q = sdkp->disk->queue;
unsigned int logical_block_size = sdkp->device->sector_size;
unsigned int max_blocks = 0;
q->limits.discard_alignment =
sdkp->unmap_alignment * logical_block_size;
q->limits.discard_granularity =
max(sdkp->physical_block_size,
sdkp->unmap_granularity * logical_block_size);
sdkp->provisioning_mode = mode;
switch (mode) {
case SD_LBP_FULL:
case SD_LBP_DISABLE:
blk_queue_max_discard_sectors(q, 0);
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
return;
case SD_LBP_UNMAP:
max_blocks = min_not_zero(sdkp->max_unmap_blocks,
(u32)SD_MAX_WS16_BLOCKS);
break;
case SD_LBP_WS16:
if (sdkp->device->unmap_limit_for_ws)
max_blocks = sdkp->max_unmap_blocks;
else
max_blocks = sdkp->max_ws_blocks;
max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS);
break;
case SD_LBP_WS10:
if (sdkp->device->unmap_limit_for_ws)
max_blocks = sdkp->max_unmap_blocks;
else
max_blocks = sdkp->max_ws_blocks;
max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS);
break;
case SD_LBP_ZERO:
max_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS10_BLOCKS);
break;
}
blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9));
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
static int sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
{
struct scsi_device *sdp = cmd->device;
struct request *rq = cmd->request;
u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
unsigned int data_len = 24;
char *buf;
rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
if (!rq->special_vec.bv_page)
return BLKPREP_DEFER;
rq->special_vec.bv_offset = 0;
rq->special_vec.bv_len = data_len;
rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
cmd->cmd_len = 10;
cmd->cmnd[0] = UNMAP;
cmd->cmnd[8] = 24;
buf = page_address(rq->special_vec.bv_page);
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]);
cmd->allowed = SD_MAX_RETRIES;
cmd->transfersize = data_len;
rq->timeout = SD_TIMEOUT;
scsi_req(rq)->resid_len = data_len;
return scsi_init_io(cmd);
}
static int sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap)
{
struct scsi_device *sdp = cmd->device;
struct request *rq = cmd->request;
u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
u32 data_len = sdp->sector_size;
rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
if (!rq->special_vec.bv_page)
return BLKPREP_DEFER;
rq->special_vec.bv_offset = 0;
rq->special_vec.bv_len = data_len;
rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
cmd->cmd_len = 16;
cmd->cmnd[0] = WRITE_SAME_16;
if (unmap)
cmd->cmnd[1] = 0x8; /* UNMAP */
put_unaligned_be64(sector, &cmd->cmnd[2]);
put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
cmd->allowed = SD_MAX_RETRIES;
cmd->transfersize = data_len;
rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
scsi_req(rq)->resid_len = data_len;
return scsi_init_io(cmd);
}
static int sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, bool unmap)
{
struct scsi_device *sdp = cmd->device;
struct request *rq = cmd->request;
u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
u32 data_len = sdp->sector_size;
rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
if (!rq->special_vec.bv_page)
return BLKPREP_DEFER;
rq->special_vec.bv_offset = 0;
rq->special_vec.bv_len = data_len;
rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
cmd->cmd_len = 10;
cmd->cmnd[0] = WRITE_SAME;
if (unmap)
cmd->cmnd[1] = 0x8; /* UNMAP */
put_unaligned_be32(sector, &cmd->cmnd[2]);
put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
cmd->allowed = SD_MAX_RETRIES;
cmd->transfersize = data_len;
rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
scsi_req(rq)->resid_len = data_len;
return scsi_init_io(cmd);
}
static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
{
struct request *rq = cmd->request;
struct scsi_device *sdp = cmd->device;
struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
int ret;
if (!(rq->cmd_flags & REQ_NOUNMAP)) {
switch (sdkp->zeroing_mode) {
case SD_ZERO_WS16_UNMAP:
ret = sd_setup_write_same16_cmnd(cmd, true);
goto out;
case SD_ZERO_WS10_UNMAP:
ret = sd_setup_write_same10_cmnd(cmd, true);
goto out;
}
}
if (sdp->no_write_same)
return BLKPREP_INVALID;
if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
ret = sd_setup_write_same16_cmnd(cmd, false);
else
ret = sd_setup_write_same10_cmnd(cmd, false);
out:
if (sd_is_zoned(sdkp) && ret == BLKPREP_OK)
return sd_zbc_write_lock_zone(cmd);
return ret;
}
static void sd_config_write_same(struct scsi_disk *sdkp)
{
struct request_queue *q = sdkp->disk->queue;
unsigned int logical_block_size = sdkp->device->sector_size;
if (sdkp->device->no_write_same) {
sdkp->max_ws_blocks = 0;
goto out;
}
/* Some devices can not handle block counts above 0xffff despite
* supporting WRITE SAME(16). Consequently we default to 64k
* blocks per I/O unless the device explicitly advertises a
* bigger limit.
*/
if (sdkp->max_ws_blocks > SD_MAX_WS10_BLOCKS)
sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS16_BLOCKS);
else if (sdkp->ws16 || sdkp->ws10 || sdkp->device->no_report_opcodes)
sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS10_BLOCKS);
else {
sdkp->device->no_write_same = 1;
sdkp->max_ws_blocks = 0;
}
if (sdkp->lbprz && sdkp->lbpws)
sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
else if (sdkp->lbprz && sdkp->lbpws10)
sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
else if (sdkp->max_ws_blocks)
sdkp->zeroing_mode = SD_ZERO_WS;
else
sdkp->zeroing_mode = SD_ZERO_WRITE;
out:
blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
(logical_block_size >> 9));
blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks *
(logical_block_size >> 9));
}
/**
* sd_setup_write_same_cmnd - write the same data to multiple blocks
* @cmd: command to prepare
*
* Will set up either WRITE SAME(10) or WRITE SAME(16) depending on
* the preference indicated by the target device.
**/
static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
{
struct request *rq = cmd->request;
struct scsi_device *sdp = cmd->device;
struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
struct bio *bio = rq->bio;
sector_t sector = blk_rq_pos(rq);
unsigned int nr_sectors = blk_rq_sectors(rq);
Revert "sd: remove __data_len hack for WRITE SAME" This patch reverts commit f80de881d8df and avoids that sending a WRITE SAME command to the iSCSI initiator triggers the following: BUG: unable to handle kernel NULL pointer dereference at 0000000000000014 TARGET_CORE[iSCSI]: Expected Transfer Length: 260096 does not match SCSI CDB Length: 512 for SAM Opcode: 0x41 IP: iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp] Oops: 0000 [#1] SMP Modules linked in: target_core_user uio target_core_iblock target_core_file iscsi_target_mod target_core_mod netconsole configfs crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 crypto_simd cryptd glue_helper virtio_console virtio_rng virtio_balloon serio_raw i2c_piix4 acpi_cpufreq button iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ext4 jbd2 mbcache virtio_blk virtio_net psmouse floppy drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_pci CPU: 2 PID: 5 Comm: kworker/u8:0 Not tainted 4.10.0-rc5-debug+ #3 Workqueue: iscsi_q_0 iscsi_xmitworker [libiscsi] RIP: 0010:iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp] Call Trace: iscsi_sw_tcp_xmit_segment+0x84/0x120 [iscsi_tcp] iscsi_sw_tcp_pdu_xmit+0x51/0x180 [iscsi_tcp] iscsi_tcp_task_xmit+0xb3/0x290 [libiscsi_tcp] iscsi_xmit_task+0x4e/0xc0 [libiscsi] iscsi_xmitworker+0x243/0x330 [libiscsi] process_one_work+0x1d8/0x4b0 worker_thread+0x49/0x4a0 kthread+0x102/0x140 Fixes: f80de881d8df ("sd: remove __data_len hack for WRITE SAME") Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Hannes Reinecke <hare@suse.com> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: Jens Axboe <axboe@fb.com> Cc: Lee Duncan <lduncan@suse.com> Cc: Chris Leech <cleech@redhat.com> Acked-by: Christoph Hellwig <hch@lst.de> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-01-26 05:43:56 +08:00
unsigned int nr_bytes = blk_rq_bytes(rq);
int ret;
if (sdkp->device->no_write_same)
return BLKPREP_INVALID;
BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sd_is_zoned(sdkp)) {
ret = sd_zbc_write_lock_zone(cmd);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (ret != BLKPREP_OK)
return ret;
}
sector >>= ilog2(sdp->sector_size) - 9;
nr_sectors >>= ilog2(sdp->sector_size) - 9;
rq->timeout = SD_WRITE_SAME_TIMEOUT;
if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff) {
cmd->cmd_len = 16;
cmd->cmnd[0] = WRITE_SAME_16;
put_unaligned_be64(sector, &cmd->cmnd[2]);
put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
} else {
cmd->cmd_len = 10;
cmd->cmnd[0] = WRITE_SAME;
put_unaligned_be32(sector, &cmd->cmnd[2]);
put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
}
cmd->transfersize = sdp->sector_size;
cmd->allowed = SD_MAX_RETRIES;
Revert "sd: remove __data_len hack for WRITE SAME" This patch reverts commit f80de881d8df and avoids that sending a WRITE SAME command to the iSCSI initiator triggers the following: BUG: unable to handle kernel NULL pointer dereference at 0000000000000014 TARGET_CORE[iSCSI]: Expected Transfer Length: 260096 does not match SCSI CDB Length: 512 for SAM Opcode: 0x41 IP: iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp] Oops: 0000 [#1] SMP Modules linked in: target_core_user uio target_core_iblock target_core_file iscsi_target_mod target_core_mod netconsole configfs crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 crypto_simd cryptd glue_helper virtio_console virtio_rng virtio_balloon serio_raw i2c_piix4 acpi_cpufreq button iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ext4 jbd2 mbcache virtio_blk virtio_net psmouse floppy drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_pci CPU: 2 PID: 5 Comm: kworker/u8:0 Not tainted 4.10.0-rc5-debug+ #3 Workqueue: iscsi_q_0 iscsi_xmitworker [libiscsi] RIP: 0010:iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp] Call Trace: iscsi_sw_tcp_xmit_segment+0x84/0x120 [iscsi_tcp] iscsi_sw_tcp_pdu_xmit+0x51/0x180 [iscsi_tcp] iscsi_tcp_task_xmit+0xb3/0x290 [libiscsi_tcp] iscsi_xmit_task+0x4e/0xc0 [libiscsi] iscsi_xmitworker+0x243/0x330 [libiscsi] process_one_work+0x1d8/0x4b0 worker_thread+0x49/0x4a0 kthread+0x102/0x140 Fixes: f80de881d8df ("sd: remove __data_len hack for WRITE SAME") Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Hannes Reinecke <hare@suse.com> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: Jens Axboe <axboe@fb.com> Cc: Lee Duncan <lduncan@suse.com> Cc: Chris Leech <cleech@redhat.com> Acked-by: Christoph Hellwig <hch@lst.de> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-01-26 05:43:56 +08:00
/*
* For WRITE SAME the data transferred via the DATA OUT buffer is
* different from the amount of data actually written to the target.
*
* We set up __data_len to the amount of data transferred via the
* DATA OUT buffer so that blk_rq_map_sg sets up the proper S/G list
* to transfer a single sector of data first, but then reset it to
* the amount of data to be written right after so that the I/O path
* knows how much to actually write.
*/
rq->__data_len = sdp->sector_size;
ret = scsi_init_io(cmd);
rq->__data_len = nr_bytes;
if (sd_is_zoned(sdkp) && ret != BLKPREP_OK)
sd_zbc_write_unlock_zone(cmd);
Revert "sd: remove __data_len hack for WRITE SAME" This patch reverts commit f80de881d8df and avoids that sending a WRITE SAME command to the iSCSI initiator triggers the following: BUG: unable to handle kernel NULL pointer dereference at 0000000000000014 TARGET_CORE[iSCSI]: Expected Transfer Length: 260096 does not match SCSI CDB Length: 512 for SAM Opcode: 0x41 IP: iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp] Oops: 0000 [#1] SMP Modules linked in: target_core_user uio target_core_iblock target_core_file iscsi_target_mod target_core_mod netconsole configfs crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 crypto_simd cryptd glue_helper virtio_console virtio_rng virtio_balloon serio_raw i2c_piix4 acpi_cpufreq button iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ext4 jbd2 mbcache virtio_blk virtio_net psmouse floppy drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_pci CPU: 2 PID: 5 Comm: kworker/u8:0 Not tainted 4.10.0-rc5-debug+ #3 Workqueue: iscsi_q_0 iscsi_xmitworker [libiscsi] RIP: 0010:iscsi_tcp_segment_done+0x20b/0x310 [libiscsi_tcp] Call Trace: iscsi_sw_tcp_xmit_segment+0x84/0x120 [iscsi_tcp] iscsi_sw_tcp_pdu_xmit+0x51/0x180 [iscsi_tcp] iscsi_tcp_task_xmit+0xb3/0x290 [libiscsi_tcp] iscsi_xmit_task+0x4e/0xc0 [libiscsi] iscsi_xmitworker+0x243/0x330 [libiscsi] process_one_work+0x1d8/0x4b0 worker_thread+0x49/0x4a0 kthread+0x102/0x140 Fixes: f80de881d8df ("sd: remove __data_len hack for WRITE SAME") Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Hannes Reinecke <hare@suse.com> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: Jens Axboe <axboe@fb.com> Cc: Lee Duncan <lduncan@suse.com> Cc: Chris Leech <cleech@redhat.com> Acked-by: Christoph Hellwig <hch@lst.de> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-01-26 05:43:56 +08:00
return ret;
}
static int sd_setup_flush_cmnd(struct scsi_cmnd *cmd)
{
struct request *rq = cmd->request;
/* flush requests don't perform I/O, zero the S/G table */
memset(&cmd->sdb, 0, sizeof(cmd->sdb));
cmd->cmnd[0] = SYNCHRONIZE_CACHE;
cmd->cmd_len = 10;
cmd->transfersize = 0;
cmd->allowed = SD_MAX_RETRIES;
rq->timeout = rq->q->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER;
return BLKPREP_OK;
}
static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
{
struct request *rq = SCpnt->request;
struct scsi_device *sdp = SCpnt->device;
struct gendisk *disk = rq->rq_disk;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
struct scsi_disk *sdkp = scsi_disk(disk);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:39 +08:00
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 21:24:39 +08:00
unsigned int this_count = blk_rq_sectors(rq);
unsigned int dif, dix;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
bool zoned_write = sd_is_zoned(sdkp) && rq_data_dir(rq) == WRITE;
int ret;
unsigned char protect;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (zoned_write) {
ret = sd_zbc_write_lock_zone(SCpnt);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (ret != BLKPREP_OK)
return ret;
}
ret = scsi_init_io(SCpnt);
if (ret != BLKPREP_OK)
goto out;
WARN_ON_ONCE(SCpnt != rq->special);
/* 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,
"%s: block=%llu, count=%d\n",
__func__, (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 21:24:39 +08:00
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 21:24:39 +08:00
"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 21:24:39 +08:00
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 21:24:39 +08:00
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 21:24:39 +08:00
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) {
SCpnt->cmnd[0] = WRITE_6;
if (blk_integrity_rq(rq))
sd_dif_prepare(SCpnt);
} else if (rq_data_dir(rq) == READ) {
SCpnt->cmnd[0] = READ_6;
} else {
scmd_printk(KERN_ERR, SCpnt, "Unknown command %d\n", req_op(rq));
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 21:24:39 +08:00
"%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 21:24:39 +08:00
blk_rq_sectors(rq)));
dix = scsi_prot_sg_count(SCpnt);
dif = scsi_host_dif_capable(SCpnt->device->host, sdkp->protection_type);
if (dif || dix)
protect = sd_setup_protect_cmnd(SCpnt, dix, dif);
else
protect = 0;
if (protect && sdkp->protection_type == T10_PI_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 (sdp->use_16_for_rw || (this_count > 0xffff)) {
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) {
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;
/*
* 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:
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (zoned_write && ret != BLKPREP_OK)
sd_zbc_write_unlock_zone(SCpnt);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
return ret;
}
static int sd_init_command(struct scsi_cmnd *cmd)
{
struct request *rq = cmd->request;
switch (req_op(rq)) {
case REQ_OP_DISCARD:
switch (scsi_disk(rq->rq_disk)->provisioning_mode) {
case SD_LBP_UNMAP:
return sd_setup_unmap_cmnd(cmd);
case SD_LBP_WS16:
return sd_setup_write_same16_cmnd(cmd, true);
case SD_LBP_WS10:
return sd_setup_write_same10_cmnd(cmd, true);
case SD_LBP_ZERO:
return sd_setup_write_same10_cmnd(cmd, false);
default:
return BLKPREP_INVALID;
}
case REQ_OP_WRITE_ZEROES:
return sd_setup_write_zeroes_cmnd(cmd);
case REQ_OP_WRITE_SAME:
return sd_setup_write_same_cmnd(cmd);
case REQ_OP_FLUSH:
return sd_setup_flush_cmnd(cmd);
case REQ_OP_READ:
case REQ_OP_WRITE:
return sd_setup_read_write_cmnd(cmd);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
case REQ_OP_ZONE_REPORT:
return sd_zbc_setup_report_cmnd(cmd);
case REQ_OP_ZONE_RESET:
return sd_zbc_setup_reset_cmnd(cmd);
default:
BUG();
}
}
static void sd_uninit_command(struct scsi_cmnd *SCpnt)
{
struct request *rq = SCpnt->request;
if (SCpnt->flags & SCMD_ZONE_WRITE_LOCK)
sd_zbc_write_unlock_zone(SCpnt);
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
__free_page(rq->special_vec.bv_page);
if (SCpnt->cmnd != scsi_req(rq)->cmd) {
mempool_free(SCpnt->cmnd, sd_cdb_pool);
SCpnt->cmnd = NULL;
SCpnt->cmd_len = 0;
}
}
/**
* sd_open - open a scsi disk device
* @bdev: Block device of the scsi disk to open
* @mode: FMODE_* mask
*
* 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;
/*
* 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_disk_put(sdkp);
return retval;
}
/**
* sd_release - invoked when the (last) close(2) is called on this
* scsi disk.
* @disk: disk to release
* @mode: FMODE_* mask
*
* Returns 0.
*
* Note: may block (uninterruptible) if error recovery is underway
* on this disk.
*
* Locking: called with bdev->bd_mutex held.
**/
static void 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_disk_put(sdkp);
}
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;
sector_t capacity = logical_to_sectors(sdp, sdkp->capacity);
int diskinfo[4];
/* default to most commonly used values */
diskinfo[0] = 0x40; /* 1 << 6 */
diskinfo[1] = 0x20; /* 1 << 5 */
diskinfo[2] = capacity >> 11;
/* override with calculated, extended default, or driver values */
if (host->hostt->bios_param)
host->hostt->bios_param(sdp, bdev, capacity, diskinfo);
else
scsicam_bios_param(bdev, capacity, diskinfo);
geo->heads = diskinfo[0];
geo->sectors = diskinfo[1];
geo->cylinders = diskinfo[2];
return 0;
}
/**
* sd_ioctl - process an ioctl
* @bdev: target block device
* @mode: FMODE_* mask
* @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 positive 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_disk *sdkp = scsi_disk(disk);
struct scsi_device *sdp = sdkp->device;
void __user *p = (void __user *)arg;
int error;
SCSI_LOG_IOCTL(1, sd_printk(KERN_INFO, sdkp, "sd_ioctl: disk=%s, "
"cmd=0x%x\n", disk->disk_name, cmd));
block: fail SCSI passthrough ioctls on partition devices Linux allows executing the SG_IO ioctl on a partition or LVM volume, and will pass the command to the underlying block device. This is well-known, but it is also a large security problem when (via Unix permissions, ACLs, SELinux or a combination thereof) a program or user needs to be granted access only to part of the disk. This patch lets partitions forward a small set of harmless ioctls; others are logged with printk so that we can see which ioctls are actually sent. In my tests only CDROM_GET_CAPABILITY actually occurred. Of course it was being sent to a (partition on a) hard disk, so it would have failed with ENOTTY and the patch isn't changing anything in practice. Still, I'm treating it specially to avoid spamming the logs. In principle, this restriction should include programs running with CAP_SYS_RAWIO. If for example I let a program access /dev/sda2 and /dev/sdb, it still should not be able to read/write outside the boundaries of /dev/sda2 independent of the capabilities. However, for now programs with CAP_SYS_RAWIO will still be allowed to send the ioctls. Their actions will still be logged. This patch does not affect the non-libata IDE driver. That driver however already tests for bd != bd->bd_contains before issuing some ioctl; it could be restricted further to forbid these ioctls even for programs running with CAP_SYS_ADMIN/CAP_SYS_RAWIO. Cc: linux-scsi@vger.kernel.org Cc: Jens Axboe <axboe@kernel.dk> Cc: James Bottomley <JBottomley@parallels.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> [ Make it also print the command name when warning - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 23:01:28 +08:00
error = scsi_verify_blk_ioctl(bdev, cmd);
if (error < 0)
return error;
/*
* 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_ioctl_block_when_processing_errors(sdp, cmd,
(mode & FMODE_NDELAY) != 0);
if (error)
goto out;
if (is_sed_ioctl(cmd))
return sed_ioctl(sdkp->opal_dev, cmd, p);
/*
* 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_blk_ioctl(bdev, 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_get(disk);
struct scsi_device *sdp;
int retval;
if (!sdkp)
return 0;
sdp = sdkp->device;
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.
*/
if (scsi_block_when_processing_errors(sdp)) {
struct scsi_sense_hdr sshdr = { 0, };
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.
*/
retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0;
sdp->changed = 0;
scsi_disk_put(sdkp);
return retval;
}
static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
{
int retries, res;
struct scsi_device *sdp = sdkp->device;
const int timeout = sdp->request_queue->rq_timeout
* SD_FLUSH_TIMEOUT_MULTIPLIER;
struct scsi_sense_hdr my_sshdr;
if (!scsi_device_online(sdp))
return -ENODEV;
/* caller might not be interested in sense, but we need it */
if (!sshdr)
sshdr = &my_sshdr;
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(sdp, cmd, DMA_NONE, NULL, 0, NULL, sshdr,
timeout, SD_MAX_RETRIES, 0, RQF_PM, NULL);
if (res == 0)
break;
}
if (res) {
sd_print_result(sdkp, "Synchronize Cache(10) failed", res);
if (driver_byte(res) & DRIVER_SENSE)
sd_print_sense_hdr(sdkp, sshdr);
/* we need to evaluate the error return */
if (scsi_sense_valid(sshdr) &&
(sshdr->asc == 0x3a || /* medium not present */
sshdr->asc == 0x20)) /* invalid command */
/* this is no error here */
return 0;
switch (host_byte(res)) {
/* ignore errors due to racing a disconnection */
case DID_BAD_TARGET:
case DID_NO_CONNECT:
return 0;
/* signal the upper layer it might try again */
case DID_BUS_BUSY:
case DID_IMM_RETRY:
case DID_REQUEUE:
case DID_SOFT_ERROR:
return -EBUSY;
default:
return -EIO;
}
}
return 0;
}
static void sd_rescan(struct device *dev)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
revalidate_disk(sdkp->disk);
}
#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;
int error;
error = scsi_ioctl_block_when_processing_errors(sdev, cmd,
(mode & FMODE_NDELAY) != 0);
if (error)
return error;
/*
* Let the static ioctl translation table take care of it.
*/
if (!sdev->host->hostt->compat_ioctl)
return -ENOIOCTLCMD;
return sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg);
}
#endif
static char sd_pr_type(enum pr_type type)
{
switch (type) {
case PR_WRITE_EXCLUSIVE:
return 0x01;
case PR_EXCLUSIVE_ACCESS:
return 0x03;
case PR_WRITE_EXCLUSIVE_REG_ONLY:
return 0x05;
case PR_EXCLUSIVE_ACCESS_REG_ONLY:
return 0x06;
case PR_WRITE_EXCLUSIVE_ALL_REGS:
return 0x07;
case PR_EXCLUSIVE_ACCESS_ALL_REGS:
return 0x08;
default:
return 0;
}
};
static int sd_pr_command(struct block_device *bdev, u8 sa,
u64 key, u64 sa_key, u8 type, u8 flags)
{
struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
struct scsi_sense_hdr sshdr;
int result;
u8 cmd[16] = { 0, };
u8 data[24] = { 0, };
cmd[0] = PERSISTENT_RESERVE_OUT;
cmd[1] = sa;
cmd[2] = type;
put_unaligned_be32(sizeof(data), &cmd[5]);
put_unaligned_be64(key, &data[0]);
put_unaligned_be64(sa_key, &data[8]);
data[20] = flags;
result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data),
&sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL);
if ((driver_byte(result) & DRIVER_SENSE) &&
(scsi_sense_valid(&sshdr))) {
sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
scsi_print_sense_hdr(sdev, NULL, &sshdr);
}
return result;
}
static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
u32 flags)
{
if (flags & ~PR_FL_IGNORE_KEY)
return -EOPNOTSUPP;
return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
old_key, new_key, 0,
(1 << 0) /* APTPL */);
}
static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
u32 flags)
{
if (flags)
return -EOPNOTSUPP;
return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0);
}
static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0);
}
static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
enum pr_type type, bool abort)
{
return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key,
sd_pr_type(type), 0);
}
static int sd_pr_clear(struct block_device *bdev, u64 key)
{
return sd_pr_command(bdev, 0x03, key, 0, 0, 0);
}
static const struct pr_ops sd_pr_ops = {
.pr_register = sd_pr_register,
.pr_reserve = sd_pr_reserve,
.pr_release = sd_pr_release,
.pr_preempt = sd_pr_preempt,
.pr_clear = sd_pr_clear,
};
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,
.pr_ops = &sd_pr_ops,
};
/**
* sd_eh_reset - reset error handling callback
* @scmd: sd-issued command that has failed
*
* This function is called by the SCSI midlayer before starting
* SCSI EH. When counting medium access failures we have to be
* careful to register it only only once per device and SCSI EH run;
* there might be several timed out commands which will cause the
* 'max_medium_access_timeouts' counter to trigger after the first
* SCSI EH run already and set the device to offline.
* So this function resets the internal counter before starting SCSI EH.
**/
static void sd_eh_reset(struct scsi_cmnd *scmd)
{
struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk);
/* New SCSI EH run, reset gate variable */
sdkp->ignore_medium_access_errors = false;
}
/**
* sd_eh_action - error handling callback
* @scmd: sd-issued command that has failed
* @eh_disp: The recovery disposition suggested by the midlayer
*
* This function is called by the SCSI midlayer upon completion of an
* error test command (currently TEST UNIT READY). The result of sending
* the eh command is passed in eh_disp. We're looking for devices that
* fail medium access commands but are OK with non access commands like
* test unit ready (so wrongly see the device as having a successful
* recovery)
**/
static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp)
{
struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk);
struct scsi_device *sdev = scmd->device;
if (!scsi_device_online(sdev) ||
!scsi_medium_access_command(scmd) ||
host_byte(scmd->result) != DID_TIME_OUT ||
eh_disp != SUCCESS)
return eh_disp;
/*
* The device has timed out executing a medium access command.
* However, the TEST UNIT READY command sent during error
* handling completed successfully. Either the device is in the
* process of recovering or has it suffered an internal failure
* that prevents access to the storage medium.
*/
if (!sdkp->ignore_medium_access_errors) {
sdkp->medium_access_timed_out++;
sdkp->ignore_medium_access_errors = true;
}
/*
* If the device keeps failing read/write commands but TEST UNIT
* READY always completes successfully we assume that medium
* access is no longer possible and take the device offline.
*/
if (sdkp->medium_access_timed_out >= sdkp->max_medium_access_timeouts) {
scmd_printk(KERN_ERR, scmd,
"Medium access timeout failure. Offlining disk!\n");
mutex_lock(&sdev->state_mutex);
scsi_device_set_state(sdev, SDEV_OFFLINE);
mutex_unlock(&sdev->state_mutex);
return SUCCESS;
}
return eh_disp;
}
static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd)
{
struct request *req = scmd->request;
struct scsi_device *sdev = scmd->device;
unsigned int transferred, good_bytes;
u64 start_lba, end_lba, bad_lba;
/*
* Some commands have a payload smaller than the device logical
* block size (e.g. INQUIRY on a 4K disk).
*/
if (scsi_bufflen(scmd) <= sdev->sector_size)
return 0;
/* Check if we have a 'bad_lba' information */
if (!scsi_get_sense_info_fld(scmd->sense_buffer,
SCSI_SENSE_BUFFERSIZE,
&bad_lba))
return 0;
/*
* If the bad lba was reported incorrectly, we have no idea where
* the error is.
*/
start_lba = sectors_to_logical(sdev, blk_rq_pos(req));
end_lba = start_lba + bytes_to_logical(sdev, scsi_bufflen(scmd));
if (bad_lba < start_lba || bad_lba >= end_lba)
return 0;
/*
* resid is optional but mostly filled in. When it's unused,
* its value is zero, so we assume the whole buffer transferred
*/
transferred = scsi_bufflen(scmd) - scsi_get_resid(scmd);
/* This computation should always be done in terms of the
* resolution of the device's medium.
*/
good_bytes = logical_to_bytes(sdev, bad_lba - start_lba);
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>
2008-01-07 02:17:12 +08:00
* 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>
2008-01-07 02:17:12 +08:00
static int sd_done(struct scsi_cmnd *SCpnt)
{
int result = SCpnt->result;
unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt);
unsigned int sector_size = SCpnt->device->sector_size;
unsigned int resid;
struct scsi_sense_hdr sshdr;
struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk);
struct request *req = SCpnt->request;
int sense_valid = 0;
int sense_deferred = 0;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
switch (req_op(req)) {
case REQ_OP_DISCARD:
case REQ_OP_WRITE_ZEROES:
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
case REQ_OP_WRITE_SAME:
case REQ_OP_ZONE_RESET:
if (!result) {
good_bytes = blk_rq_bytes(req);
scsi_set_resid(SCpnt, 0);
} else {
good_bytes = 0;
scsi_set_resid(SCpnt, blk_rq_bytes(req));
}
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
break;
case REQ_OP_ZONE_REPORT:
if (!result) {
good_bytes = scsi_bufflen(SCpnt)
- scsi_get_resid(SCpnt);
scsi_set_resid(SCpnt, 0);
} else {
good_bytes = 0;
scsi_set_resid(SCpnt, blk_rq_bytes(req));
}
break;
default:
/*
* In case of bogus fw or device, we could end up having
* an unaligned partial completion. Check this here and force
* alignment.
*/
resid = scsi_get_resid(SCpnt);
if (resid & (sector_size - 1)) {
sd_printk(KERN_INFO, sdkp,
"Unaligned partial completion (resid=%u, sector_sz=%u)\n",
resid, sector_size);
resid = min(scsi_bufflen(SCpnt),
round_up(resid, sector_size));
scsi_set_resid(SCpnt, resid);
}
}
if (result) {
sense_valid = scsi_command_normalize_sense(SCpnt, &sshdr);
if (sense_valid)
sense_deferred = scsi_sense_is_deferred(&sshdr);
}
sdkp->medium_access_timed_out = 0;
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.
*/
SCpnt->result = 0;
memset(SCpnt->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE);
break;
case ABORTED_COMMAND:
if (sshdr.asc == 0x10) /* DIF: Target detected corruption */
good_bytes = sd_completed_bytes(SCpnt);
break;
case ILLEGAL_REQUEST:
switch (sshdr.asc) {
case 0x10: /* DIX: Host detected corruption */
good_bytes = sd_completed_bytes(SCpnt);
break;
case 0x20: /* INVALID COMMAND OPCODE */
case 0x24: /* INVALID FIELD IN CDB */
switch (SCpnt->cmnd[0]) {
case UNMAP:
sd_config_discard(sdkp, SD_LBP_DISABLE);
break;
case WRITE_SAME_16:
case WRITE_SAME:
if (SCpnt->cmnd[1] & 8) { /* UNMAP */
sd_config_discard(sdkp, SD_LBP_DISABLE);
} else {
sdkp->device->no_write_same = 1;
sd_config_write_same(sdkp);
req->__data_len = blk_rq_bytes(req);
req->rq_flags |= RQF_QUIET;
}
break;
}
}
break;
default:
break;
}
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
out:
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sd_is_zoned(sdkp))
sd_zbc_complete(SCpnt, good_bytes, &sshdr);
SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
"sd_done: completed %d of %d bytes\n",
good_bytes, scsi_bufflen(SCpnt)));
if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
sd_dif_complete(SCpnt, good_bytes);
Revert "scsi: revert "[SCSI] Get rid of scsi_cmnd->done"" This reverts commit ac40532ef0b8649e6f7f83859ea0de1c4ed08a19, which gets us back the original cleanup of 6f5391c283d7fdcf24bf40786ea79061919d1e1d. It turns out that the bug that was triggered by that commit was apparently not actually triggered by that commit at all, and just the testing conditions had changed enough to make it appear to be due to it. The real problem seems to have been found by Peter Osterlund: "pktcdvd sets it [block device size] when opening the /dev/pktcdvd device, but when the drive is later opened as /dev/scd0, there is nothing that sets it back. (Btw, 40944 is possible if the disk is a CDRW that was formatted with "cdrwtool -m 10236".) The problem is that pktcdvd opens the cd device in non-blocking mode when pktsetup is run, and doesn't close it again until pktsetup -d is run. The effect is that if you meanwhile open the cd device, blkdev.c:do_open() doesn't call bd_set_size() because bdev->bd_openers is non-zero." In particular, to repeat the bug (regardless of whether commit 6f5391c283d7fdcf24bf40786ea79061919d1e1d is applied or not): " 1. Start with an empty drive. 2. pktsetup 0 /dev/scd0 3. Insert a CD containing an isofs filesystem. 4. mount /dev/pktcdvd/0 /mnt/tmp 5. umount /mnt/tmp 6. Press the eject button. 7. Insert a DVD containing a non-writable filesystem. 8. mount /dev/scd0 /mnt/tmp 9. find /mnt/tmp -type f -print0 | xargs -0 sha1sum >/dev/null 10. If the DVD contains data beyond the physical size of a CD, you get I/O errors in the terminal, and dmesg reports lots of "attempt to access beyond end of device" errors." which in turn is because the nested open after the media change won't cause the size to be set properly (because the original open still holds the block device, and we only do the bd_set_size() when we don't have other people holding the device open). The proper fix for that is probably to just do something like bdev->bd_inode->i_size = (loff_t)get_capacity(disk)<<9; in fs/block_dev.c:do_open() even for the cases where we're not the original opener (but *not* call bd_set_size(), since that will also change the block size of the device). Cc: Peter Osterlund <petero2@telia.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Ingo Molnar <mingo@elte.hu> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-07 02:17:12 +08:00
return good_bytes;
}
/*
* 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_print_result(sdkp, "Test Unit Ready failed",
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 int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer)
{
struct scsi_device *sdp = sdkp->device;
u8 type;
int ret = 0;
if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0)
return ret;
type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */
if (type > T10_PI_TYPE3_PROTECTION)
ret = -ENODEV;
else if (scsi_host_dif_capable(sdp->host, type))
ret = 1;
if (sdkp->first_scan || type != sdkp->protection_type)
switch (ret) {
case -ENODEV:
sd_printk(KERN_ERR, sdkp, "formatted with unsupported" \
" protection type %u. Disabling disk!\n",
type);
break;
case 1:
sd_printk(KERN_NOTICE, sdkp,
"Enabling DIF Type %u protection\n", type);
break;
case 0:
sd_printk(KERN_NOTICE, sdkp,
"Disabling DIF Type %u protection\n", type);
break;
}
sdkp->protection_type = type;
return ret;
}
static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
struct scsi_sense_hdr *sshdr, int sense_valid,
int 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
/*
* Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set
* and the reported logical block size is bigger than 512 bytes. Note
* that last_sector is a u64 and therefore logical_to_sectors() is not
* applicable.
*/
static bool sd_addressable_capacity(u64 lba, unsigned int sector_size)
{
u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9);
if (sizeof(sector_t) == 4 && last_sector > U32_MAX)
return false;
return true;
}
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>
2010-10-02 05:20:10 +08:00
if (sdp->no_read_capacity_16)
return -EINVAL;
do {
memset(cmd, 0, 16);
cmd[0] = SERVICE_ACTION_IN_16;
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_print_result(sdkp, "Read Capacity(16) failed", the_result);
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]);
if (sd_read_protection_type(sdkp, buffer) < 0) {
sdkp->capacity = 0;
return -ENODEV;
}
if (!sd_addressable_capacity(lba, sector_size)) {
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;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
/* RC basis */
sdkp->rc_basis = (buffer[12] >> 4) & 0x3;
/* 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) { /* LBPME */
sdkp->lbpme = 1;
if (buffer[14] & 0x40) /* LBPRZ */
sdkp->lbprz = 1;
sd_config_discard(sdkp, SD_LBP_WS16);
}
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_print_result(sdkp, "Read Capacity(10) failed", the_result);
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>
2010-10-02 05:20:10 +08:00
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>
2010-10-02 05:20:10 +08:00
return sector_size;
}
if (!sd_addressable_capacity(lba, sector_size)) {
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->try_rc_10_first)
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;
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) {
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);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
blk_queue_physical_block_size(sdp->request_queue,
sdkp->physical_block_size);
sdkp->device->sector_size = sector_size;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sdkp->capacity > 0xffffffff)
sdp->use_16_for_rw = 1;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
}
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
/*
* Print disk capacity
*/
static void
sd_print_capacity(struct scsi_disk *sdkp,
sector_t old_capacity)
{
int sector_size = sdkp->device->sector_size;
char cap_str_2[10], cap_str_10[10];
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
string_get_size(sdkp->capacity, sector_size,
STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
string_get_size(sdkp->capacity, sector_size,
STRING_UNITS_10, cap_str_10,
sizeof(cap_str_10));
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
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);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sdkp->physical_block_size != sector_size)
sd_printk(KERN_NOTICE, sdkp,
"%u-byte physical blocks\n",
sdkp->physical_block_size);
sd_zbc_print_zones(sdkp);
}
}
/* 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_first_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_first_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: %4ph\n", buffer);
}
}
}
/*
* 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;
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
int first_len;
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;
if (sdkp->cache_override)
return;
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
first_len = 4;
if (sdp->skip_ms_page_8) {
if (sdp->type == TYPE_RBC)
goto defaults;
else {
if (sdp->skip_ms_page_3f)
goto defaults;
modepage = 0x3F;
if (sdp->use_192_bytes_for_3f)
first_len = 192;
dbd = 0;
}
} else if (sdp->type == TYPE_RBC) {
modepage = 6;
dbd = 8;
} else {
modepage = 8;
dbd = 0;
}
/* cautiously ask */
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
res = sd_do_mode_sense(sdp, dbd, modepage, buffer, first_len,
&data, &sshdr);
if (!scsi_status_is_good(res))
goto bad_sense;
if (!data.header_length) {
modepage = 6;
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
first_len = 0;
sd_first_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 (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
else if (len > SD_BUF_SIZE) {
sd_first_printk(KERN_NOTICE, sdkp, "Truncating mode parameter "
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
"data from %d to %d bytes\n", len, SD_BUF_SIZE);
len = SD_BUF_SIZE;
}
if (modepage == 0x3F && sdp->use_192_bytes_for_3f)
len = 192;
/* Get the data */
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
if (len > first_len)
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 (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
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_first_printk(KERN_ERR, sdkp,
"Incomplete mode parameter "
"data\n");
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
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_first_printk(KERN_ERR, sdkp,
"Incomplete mode "
"parameter data\n");
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
goto defaults;
}
}
}
sd_first_printk(KERN_ERR, sdkp, "No Caching mode page found\n");
goto defaults;
[SCSI] Retrieve the Caching mode page (version 2) 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 Version 2 adds this: Some devices don't support page code 0x3F, and others require a fixed transfer length of 192 bytes. This single commit includes a patch by Alan Stern which fixes this. Reported-and-tested-by: Richard Senior <richard@r-senior.demon.co.uk> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Luben Tuikov <ltuikov@yahoo.com> Signed-off-by: James Bottomley <jbottomley@parallels.com>
2011-05-19 15:00:58 +08:00
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 (sdp->broken_fua) {
sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n");
sdkp->DPOFUA = 0;
} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw &&
!sdkp->device->use_16_for_rw) {
sd_first_printk(KERN_NOTICE, sdkp,
"Uses READ/WRITE(6), disabling FUA\n");
sdkp->DPOFUA = 0;
}
/* No cache flush allowed for write protected devices */
if (sdkp->WCE && sdkp->write_prot)
sdkp->WCE = 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_first_printk(KERN_NOTICE, sdkp, "Cache data unavailable\n");
else
sd_first_printk(KERN_ERR, sdkp,
"Asking for cache data failed\n");
defaults:
if (sdp->wce_default_on) {
sd_first_printk(KERN_NOTICE, sdkp,
"Assuming drive cache: write back\n");
sdkp->WCE = 1;
} else {
sd_first_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;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
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_first_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_first_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.
* @sdkp: disk to query
*/
static void sd_read_block_limits(struct scsi_disk *sdkp)
{
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);
block/sd: Fix device-imposed transfer length limits Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests") had the unfortunate side-effect of removing an implicit clamp to BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer code. This caused problems for some SMR drives. Debugging this issue revealed a few problems with the existing infrastructure since the block layer didn't know how to deal with device-imposed limits, only limits set by the I/O controller. - Introduce a new queue limit, max_dev_sectors, which is used by the ULD to signal the maximum sectors for a REQ_TYPE_FS request. - Ensure that max_dev_sectors is correctly stacked and taken into account when overriding max_sectors through sysfs. - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer values for later processing. - In sd_revalidate() set the queue's max_dev_sectors based on the MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value is not reported, fall back to a cap based on the CDB TRANSFER LENGTH field size. - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits VPD--if reported and sane--to signal the preferred device transfer size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS. - blk_limits_max_hw_sectors() is no longer used and can be removed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581 Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: sweeneygj@gmx.com Tested-by: Arzeets <anatol.pomozov@gmail.com> Tested-by: David Eisner <david.eisner@oriel.oxon.org> Tested-by: Mario Kicherer <dev@kicherer.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2015-11-14 05:46:48 +08:00
sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]);
sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]);
if (buffer[3] == 0x3c) {
unsigned int lba_count, desc_count;
sdkp->max_ws_blocks = (u32)get_unaligned_be64(&buffer[36]);
if (!sdkp->lbpme)
goto out;
lba_count = get_unaligned_be32(&buffer[20]);
desc_count = get_unaligned_be32(&buffer[24]);
if (lba_count && desc_count)
sdkp->max_unmap_blocks = lba_count;
sdkp->unmap_granularity = get_unaligned_be32(&buffer[28]);
if (buffer[32] & 0x80)
sdkp->unmap_alignment =
get_unaligned_be32(&buffer[32]) & ~(1 << 31);
if (!sdkp->lbpvpd) { /* LBP VPD page not provided */
if (sdkp->max_unmap_blocks)
sd_config_discard(sdkp, SD_LBP_UNMAP);
else
sd_config_discard(sdkp, SD_LBP_WS16);
} else { /* LBP VPD page tells us what to use */
if (sdkp->lbpu && sdkp->max_unmap_blocks)
sd_config_discard(sdkp, SD_LBP_UNMAP);
else if (sdkp->lbpws)
sd_config_discard(sdkp, SD_LBP_WS16);
else if (sdkp->lbpws10)
sd_config_discard(sdkp, SD_LBP_WS10);
else
sd_config_discard(sdkp, SD_LBP_DISABLE);
}
}
out:
kfree(buffer);
}
/**
* sd_read_block_characteristics - Query block dev. characteristics
* @sdkp: disk to query
*/
static void sd_read_block_characteristics(struct scsi_disk *sdkp)
{
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
struct request_queue *q = sdkp->disk->queue;
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) {
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
}
if (sdkp->device->type == TYPE_ZBC) {
/* Host-managed */
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
q->limits.zoned = BLK_ZONED_HM;
} else {
sdkp->zoned = (buffer[8] >> 4) & 3;
if (sdkp->zoned == 1)
/* Host-aware */
q->limits.zoned = BLK_ZONED_HA;
else
/*
* Treat drive-managed devices as
* regular block devices.
*/
q->limits.zoned = BLK_ZONED_NONE;
}
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (blk_queue_is_zoned(q) && sdkp->first_scan)
sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n",
q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware");
out:
kfree(buffer);
}
/**
* sd_read_block_provisioning - Query provisioning VPD page
* @sdkp: disk to query
*/
static void sd_read_block_provisioning(struct scsi_disk *sdkp)
{
unsigned char *buffer;
const int vpd_len = 8;
if (sdkp->lbpme == 0)
return;
buffer = kmalloc(vpd_len, GFP_KERNEL);
if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb2, buffer, vpd_len))
goto out;
sdkp->lbpvpd = 1;
sdkp->lbpu = (buffer[5] >> 7) & 1; /* UNMAP */
sdkp->lbpws = (buffer[5] >> 6) & 1; /* WRITE SAME(16) with UNMAP */
sdkp->lbpws10 = (buffer[5] >> 5) & 1; /* WRITE SAME(10) with UNMAP */
out:
kfree(buffer);
}
static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer)
{
struct scsi_device *sdev = sdkp->device;
if (sdev->host->no_write_same) {
sdev->no_write_same = 1;
return;
}
if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) {
/* too large values might cause issues with arcmsr */
int vpd_buf_len = 64;
sdev->no_report_opcodes = 1;
/* Disable WRITE SAME if REPORT SUPPORTED OPERATION
* CODES is unsupported and the device has an ATA
* Information VPD page (SAT).
*/
if (!scsi_get_vpd_page(sdev, 0x89, buffer, vpd_buf_len))
sdev->no_write_same = 1;
}
if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16) == 1)
sdkp->ws16 = 1;
if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME) == 1)
sdkp->ws10 = 1;
}
static void sd_read_security(struct scsi_disk *sdkp, unsigned char *buffer)
{
struct scsi_device *sdev = sdkp->device;
if (!sdev->security_supported)
return;
if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE,
SECURITY_PROTOCOL_IN) == 1 &&
scsi_report_opcode(sdev, buffer, SD_BUF_SIZE,
SECURITY_PROTOCOL_OUT) == 1)
sdkp->security = 1;
}
/**
* 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;
block/sd: Fix device-imposed transfer length limits Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests") had the unfortunate side-effect of removing an implicit clamp to BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer code. This caused problems for some SMR drives. Debugging this issue revealed a few problems with the existing infrastructure since the block layer didn't know how to deal with device-imposed limits, only limits set by the I/O controller. - Introduce a new queue limit, max_dev_sectors, which is used by the ULD to signal the maximum sectors for a REQ_TYPE_FS request. - Ensure that max_dev_sectors is correctly stacked and taken into account when overriding max_sectors through sysfs. - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer values for later processing. - In sd_revalidate() set the queue's max_dev_sectors based on the MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value is not reported, fall back to a cap based on the CDB TRANSFER LENGTH field size. - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits VPD--if reported and sane--to signal the preferred device transfer size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS. - blk_limits_max_hw_sectors() is no longer used and can be removed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581 Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: sweeneygj@gmx.com Tested-by: Arzeets <anatol.pomozov@gmail.com> Tested-by: David Eisner <david.eisner@oriel.oxon.org> Tested-by: Mario Kicherer <dev@kicherer.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2015-11-14 05:46:48 +08:00
struct request_queue *q = sdkp->disk->queue;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
sector_t old_capacity = sdkp->capacity;
unsigned char *buffer;
block/sd: Fix device-imposed transfer length limits Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests") had the unfortunate side-effect of removing an implicit clamp to BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer code. This caused problems for some SMR drives. Debugging this issue revealed a few problems with the existing infrastructure since the block layer didn't know how to deal with device-imposed limits, only limits set by the I/O controller. - Introduce a new queue limit, max_dev_sectors, which is used by the ULD to signal the maximum sectors for a REQ_TYPE_FS request. - Ensure that max_dev_sectors is correctly stacked and taken into account when overriding max_sectors through sysfs. - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer values for later processing. - In sd_revalidate() set the queue's max_dev_sectors based on the MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value is not reported, fall back to a cap based on the CDB TRANSFER LENGTH field size. - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits VPD--if reported and sane--to signal the preferred device transfer size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS. - blk_limits_max_hw_sectors() is no longer used and can be removed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581 Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: sweeneygj@gmx.com Tested-by: Arzeets <anatol.pomozov@gmail.com> Tested-by: David Eisner <david.eisner@oriel.oxon.org> Tested-by: Mario Kicherer <dev@kicherer.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2015-11-14 05:46:48 +08:00
unsigned int dev_max, rw_max;
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 (scsi_device_supports_vpd(sdp)) {
sd_read_block_provisioning(sdkp);
sd_read_block_limits(sdkp);
sd_read_block_characteristics(sdkp);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
sd_zbc_read_zones(sdkp, buffer);
}
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
sd_print_capacity(sdkp, old_capacity);
sd_read_write_protect_flag(sdkp, buffer);
sd_read_cache_type(sdkp, buffer);
sd_read_app_tag_own(sdkp, buffer);
sd_read_write_same(sdkp, buffer);
sd_read_security(sdkp, buffer);
}
/*
* We now have all cache related info, determine how we deal
* with flush requests.
*/
sd_set_flush_flag(sdkp);
block/sd: Fix device-imposed transfer length limits Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests") had the unfortunate side-effect of removing an implicit clamp to BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer code. This caused problems for some SMR drives. Debugging this issue revealed a few problems with the existing infrastructure since the block layer didn't know how to deal with device-imposed limits, only limits set by the I/O controller. - Introduce a new queue limit, max_dev_sectors, which is used by the ULD to signal the maximum sectors for a REQ_TYPE_FS request. - Ensure that max_dev_sectors is correctly stacked and taken into account when overriding max_sectors through sysfs. - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer values for later processing. - In sd_revalidate() set the queue's max_dev_sectors based on the MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value is not reported, fall back to a cap based on the CDB TRANSFER LENGTH field size. - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits VPD--if reported and sane--to signal the preferred device transfer size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS. - blk_limits_max_hw_sectors() is no longer used and can be removed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581 Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: sweeneygj@gmx.com Tested-by: Arzeets <anatol.pomozov@gmail.com> Tested-by: David Eisner <david.eisner@oriel.oxon.org> Tested-by: Mario Kicherer <dev@kicherer.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2015-11-14 05:46:48 +08:00
/* Initial block count limit based on CDB TRANSFER LENGTH field size. */
dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS;
/* Some devices report a maximum block count for READ/WRITE requests. */
dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks);
q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
/*
* Determine the device's preferred I/O size for reads and writes
* unless the reported value is unreasonably small, large, or
* garbage.
block/sd: Fix device-imposed transfer length limits Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests") had the unfortunate side-effect of removing an implicit clamp to BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer code. This caused problems for some SMR drives. Debugging this issue revealed a few problems with the existing infrastructure since the block layer didn't know how to deal with device-imposed limits, only limits set by the I/O controller. - Introduce a new queue limit, max_dev_sectors, which is used by the ULD to signal the maximum sectors for a REQ_TYPE_FS request. - Ensure that max_dev_sectors is correctly stacked and taken into account when overriding max_sectors through sysfs. - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer values for later processing. - In sd_revalidate() set the queue's max_dev_sectors based on the MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value is not reported, fall back to a cap based on the CDB TRANSFER LENGTH field size. - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits VPD--if reported and sane--to signal the preferred device transfer size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS. - blk_limits_max_hw_sectors() is no longer used and can be removed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581 Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: sweeneygj@gmx.com Tested-by: Arzeets <anatol.pomozov@gmail.com> Tested-by: David Eisner <david.eisner@oriel.oxon.org> Tested-by: Mario Kicherer <dev@kicherer.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2015-11-14 05:46:48 +08:00
*/
if (sdkp->opt_xfer_blocks &&
sdkp->opt_xfer_blocks <= dev_max &&
sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_SIZE) {
q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
} else
rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
(sector_t)BLK_DEF_MAX_SECTORS);
/* Do not exceed controller limit */
rw_max = min(rw_max, queue_max_hw_sectors(q));
/*
* Only update max_sectors if previously unset or if the current value
* exceeds the capabilities of the hardware.
*/
if (sdkp->first_scan ||
q->limits.max_sectors > q->limits.max_dev_sectors ||
q->limits.max_sectors > q->limits.max_hw_sectors)
q->limits.max_sectors = rw_max;
sdkp->first_scan = 0;
set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity));
sd_config_write_same(sdkp);
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->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->cache_override = 0;
sdkp->WCE = 0;
sdkp->RCD = 0;
sdkp->ATO = 0;
sdkp->first_scan = 1;
sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS;
sd_revalidate_disk(gd);
gd->flags = GENHD_FL_EXT_DEVT;
if (sdp->removable) {
gd->flags |= GENHD_FL_REMOVABLE;
gd->events |= DISK_EVENT_MEDIA_CHANGE;
}
blk_pm_runtime_init(sdp->request_queue, dev);
device_add_disk(dev, gd);
if (sdkp->capacity)
sd_dif_config_host(sdkp);
sd_revalidate_disk(gd);
if (sdkp->security) {
sdkp->opal_dev = init_opal_dev(sdp, &sd_sec_submit);
if (sdkp->opal_dev)
sd_printk(KERN_NOTICE, sdkp, "supports TCG Opal\n");
}
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 23:47:54 +08:00
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_probe is not re-entrant (for time being)
* Also think about sd_probe() 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;
scsi_autopm_get_device(sdp);
error = -ENODEV;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
if (sdp->type != TYPE_DISK &&
sdp->type != TYPE_ZBC &&
sdp->type != TYPE_MOD &&
sdp->type != TYPE_RBC)
goto out;
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
#ifndef CONFIG_BLK_DEV_ZONED
if (sdp->type == TYPE_ZBC)
goto out;
#endif
SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp,
"sd_probe\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) {
sdev_printk(KERN_WARNING, sdp, "sd_probe: memory exhausted.\n");
goto out_put;
}
error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN);
if (error) {
sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n");
goto out_free_index;
}
sdkp->device = sdp;
sdkp->driver = &sd_template;
sdkp->disk = gd;
sdkp->index = index;
atomic_set(&sdkp->openers, 0);
atomic_set(&sdkp->device->ioerr_cnt, 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, "%s", dev_name(dev));
error = device_add(&sdkp->dev);
if (error)
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 23:47:54 +08:00
get_device(&sdkp->dev); /* prevent release before async_schedule */
[SCSI] sd: limit the scope of the async probe domain sd injects and synchronizes probe work on the global kernel-wide domain. This runs into conflict with PM that wants to perform resume actions in async context: [ 494.237079] INFO: task kworker/u:3:554 blocked for more than 120 seconds. [ 494.294396] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 494.360809] kworker/u:3 D 0000000000000000 0 554 2 0x00000000 [ 494.420739] ffff88012e4d3af0 0000000000000046 ffff88013200c160 ffff88012e4d3fd8 [ 494.484392] ffff88012e4d3fd8 0000000000012500 ffff8801394ea0b0 ffff88013200c160 [ 494.548038] ffff88012e4d3ae0 00000000000001e3 ffffffff81a249e0 ffff8801321c5398 [ 494.611685] Call Trace: [ 494.632649] [<ffffffff8149dd25>] schedule+0x5a/0x5c [ 494.674687] [<ffffffff8104b968>] async_synchronize_cookie_domain+0xb6/0x112 [ 494.734177] [<ffffffff810461ff>] ? __init_waitqueue_head+0x50/0x50 [ 494.787134] [<ffffffff8131a224>] ? scsi_remove_target+0x48/0x48 [ 494.837900] [<ffffffff8104b9d9>] async_synchronize_cookie+0x15/0x17 [ 494.891567] [<ffffffff8104ba49>] async_synchronize_full+0x54/0x70 <-- here we wait for async contexts to complete [ 494.943783] [<ffffffff8104b9f5>] ? async_synchronize_full_domain+0x1a/0x1a [ 495.002547] [<ffffffffa00114b1>] sd_remove+0x2c/0xa2 [sd_mod] [ 495.051861] [<ffffffff812fe94f>] __device_release_driver+0x86/0xcf [ 495.104807] [<ffffffff812fe9bd>] device_release_driver+0x25/0x32 <-- here we take device_lock() [ 853.511341] INFO: task kworker/u:4:549 blocked for more than 120 seconds. [ 853.568693] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 853.635119] kworker/u:4 D ffff88013097b5d0 0 549 2 0x00000000 [ 853.695129] ffff880132773c40 0000000000000046 ffff880130790000 ffff880132773fd8 [ 853.758990] ffff880132773fd8 0000000000012500 ffff88013288a0b0 ffff880130790000 [ 853.822796] 0000000000000246 0000000000000040 ffff88013097b5c8 ffff880130790000 [ 853.886633] Call Trace: [ 853.907631] [<ffffffff8149dd25>] schedule+0x5a/0x5c [ 853.949670] [<ffffffff8149cc44>] __mutex_lock_common+0x220/0x351 [ 854.001225] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4 [ 854.049082] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4 [ 854.097011] [<ffffffff8149ce48>] mutex_lock_nested+0x2f/0x36 <-- here we wait for device_lock() [ 854.145591] [<ffffffff81304bd7>] device_resume+0x58/0x1c4 [ 854.192066] [<ffffffff81304d61>] async_resume+0x1e/0x45 [ 854.237019] [<ffffffff8104bc93>] async_run_entry_fn+0xc6/0x173 <-- ...while running in async context Provide a 'scsi_sd_probe_domain' so that async probe actions actions can be flushed without regard for the state of PM, and allow for the resume path to handle devices that have transitioned from SDEV_QUIESCE to SDEV_DEL prior to resume. Acked-by: Alan Stern <stern@rowland.harvard.edu> [alan: uplevel scsi_sd_probe_domain, clarify scsi_device_resume] Signed-off-by: Dan Williams <dan.j.williams@intel.com> [jejb: remove unneeded config guards in include file] Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2012-03-23 08:05:11 +08:00
async_schedule_domain(sd_probe_async, sdkp, &scsi_sd_probe_domain);
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:
scsi_autopm_put_device(sdp);
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.
* @dev: pointer to 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;
dev_t devt;
sdkp = dev_get_drvdata(dev);
devt = disk_devt(sdkp->disk);
scsi_autopm_get_device(sdkp->device);
scsi: async sd resume async_schedule() sd resume work to allow disks and other devices to resume in parallel. This moves the entirety of scsi_device resume to an async context to ensure that scsi_device_resume() remains ordered with respect to the completion of the start/stop command. For the duration of the resume, new command submissions (that do not originate from the scsi-core) will be deferred (BLKPREP_DEFER). It adds a new ASYNC_DOMAIN_EXCLUSIVE(scsi_sd_pm_domain) as a container of these operations. Like scsi_sd_probe_domain it is flushed at sd_remove() time to ensure async ops do not continue past the end-of-life of the sdev. The implementation explicitly refrains from reusing scsi_sd_probe_domain directly for this purpose as it is flushed at the end of dpm_resume(), potentially defeating some of the benefit. Given sdevs are quiesced it is permissible for these resume operations to bleed past the async_synchronize_full() calls made by the driver core. We defer the resolution of which pm callback to call until scsi_dev_type_{suspend|resume} time and guarantee that the callback parameter is never NULL. With this in place the type of resume operation is encoded in the async function identifier. There is a concern that async resume could trigger PSU overload. In the enterprise, storage enclosures enforce staggered spin-up regardless of what the kernel does making async scanning safe by default. Outside of that context a user can disable asynchronous scanning via a kernel command line or CONFIG_SCSI_SCAN_ASYNC. Honor that setting when deciding whether to do resume asynchronously. Inspired by Todd's analysis and initial proposal [2]: https://01.org/suspendresume/blogs/tebrandt/2013/hard-disk-resume-optimization-simpler-approach Cc: Len Brown <len.brown@intel.com> Cc: Phillip Susi <psusi@ubuntu.com> [alan: bug fix and clean up suggestion] Acked-by: Alan Stern <stern@rowland.harvard.edu> Suggested-by: Todd Brandt <todd.e.brandt@linux.intel.com> [djbw: kick all resume work to the async queue] Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2014-04-11 06:30:35 +08:00
async_synchronize_full_domain(&scsi_sd_pm_domain);
[SCSI] sd: limit the scope of the async probe domain sd injects and synchronizes probe work on the global kernel-wide domain. This runs into conflict with PM that wants to perform resume actions in async context: [ 494.237079] INFO: task kworker/u:3:554 blocked for more than 120 seconds. [ 494.294396] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 494.360809] kworker/u:3 D 0000000000000000 0 554 2 0x00000000 [ 494.420739] ffff88012e4d3af0 0000000000000046 ffff88013200c160 ffff88012e4d3fd8 [ 494.484392] ffff88012e4d3fd8 0000000000012500 ffff8801394ea0b0 ffff88013200c160 [ 494.548038] ffff88012e4d3ae0 00000000000001e3 ffffffff81a249e0 ffff8801321c5398 [ 494.611685] Call Trace: [ 494.632649] [<ffffffff8149dd25>] schedule+0x5a/0x5c [ 494.674687] [<ffffffff8104b968>] async_synchronize_cookie_domain+0xb6/0x112 [ 494.734177] [<ffffffff810461ff>] ? __init_waitqueue_head+0x50/0x50 [ 494.787134] [<ffffffff8131a224>] ? scsi_remove_target+0x48/0x48 [ 494.837900] [<ffffffff8104b9d9>] async_synchronize_cookie+0x15/0x17 [ 494.891567] [<ffffffff8104ba49>] async_synchronize_full+0x54/0x70 <-- here we wait for async contexts to complete [ 494.943783] [<ffffffff8104b9f5>] ? async_synchronize_full_domain+0x1a/0x1a [ 495.002547] [<ffffffffa00114b1>] sd_remove+0x2c/0xa2 [sd_mod] [ 495.051861] [<ffffffff812fe94f>] __device_release_driver+0x86/0xcf [ 495.104807] [<ffffffff812fe9bd>] device_release_driver+0x25/0x32 <-- here we take device_lock() [ 853.511341] INFO: task kworker/u:4:549 blocked for more than 120 seconds. [ 853.568693] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 853.635119] kworker/u:4 D ffff88013097b5d0 0 549 2 0x00000000 [ 853.695129] ffff880132773c40 0000000000000046 ffff880130790000 ffff880132773fd8 [ 853.758990] ffff880132773fd8 0000000000012500 ffff88013288a0b0 ffff880130790000 [ 853.822796] 0000000000000246 0000000000000040 ffff88013097b5c8 ffff880130790000 [ 853.886633] Call Trace: [ 853.907631] [<ffffffff8149dd25>] schedule+0x5a/0x5c [ 853.949670] [<ffffffff8149cc44>] __mutex_lock_common+0x220/0x351 [ 854.001225] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4 [ 854.049082] [<ffffffff81304bd7>] ? device_resume+0x58/0x1c4 [ 854.097011] [<ffffffff8149ce48>] mutex_lock_nested+0x2f/0x36 <-- here we wait for device_lock() [ 854.145591] [<ffffffff81304bd7>] device_resume+0x58/0x1c4 [ 854.192066] [<ffffffff81304d61>] async_resume+0x1e/0x45 [ 854.237019] [<ffffffff8104bc93>] async_run_entry_fn+0xc6/0x173 <-- ...while running in async context Provide a 'scsi_sd_probe_domain' so that async probe actions actions can be flushed without regard for the state of PM, and allow for the resume path to handle devices that have transitioned from SDEV_QUIESCE to SDEV_DEL prior to resume. Acked-by: Alan Stern <stern@rowland.harvard.edu> [alan: uplevel scsi_sd_probe_domain, clarify scsi_device_resume] Signed-off-by: Dan Williams <dan.j.williams@intel.com> [jejb: remove unneeded config guards in include file] Signed-off-by: James Bottomley <JBottomley@Parallels.com>
2012-03-23 08:05:11 +08:00
async_synchronize_full_domain(&scsi_sd_probe_domain);
device_del(&sdkp->dev);
del_gendisk(sdkp->disk);
sd_shutdown(dev);
sd: Implement support for ZBC devices Implement ZBC support functions to setup zoned disks, both host-managed and host-aware models. Only zoned disks that satisfy the following conditions are supported: 1) All zones are the same size, with the exception of an eventual last smaller runt zone. 2) For host-managed disks, reads are unrestricted (reads are not failed due to zone or write pointer alignement constraints). Zoned disks that do not satisfy these 2 conditions are setup with a capacity of 0 to prevent their use. The function sd_zbc_read_zones, called from sd_revalidate_disk, checks that the device satisfies the above two constraints. This function may also change the disk capacity previously set by sd_read_capacity for devices reporting only the capacity of conventional zones at the beginning of the LBA range (i.e. devices reporting rc_basis set to 0). The capacity message output was moved out of sd_read_capacity into a new function sd_print_capacity to include this eventual capacity change by sd_zbc_read_zones. This new function also includes a call to sd_zbc_print_zones to display the number of zones and zone size of the device. Signed-off-by: Hannes Reinecke <hare@suse.de> [Damien: * Removed zone cache support * Removed mapping of discard to reset write pointer command * Modified sd_zbc_read_zones to include checks that the device satisfies the kernel constraints * Implemeted REPORT ZONES setup and post-processing based on code from Shaun Tancheff <shaun.tancheff@seagate.com> * Removed confusing use of 512B sector units in functions interface] Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Shaun Tancheff <shaun.tancheff@seagate.com> Tested-by: Shaun Tancheff <shaun.tancheff@seagate.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-10-18 14:40:34 +08:00
sd_zbc_remove(sdkp);
free_opal_dev(sdkp->opal_dev);
blk_register_region(devt, SD_MINORS, NULL,
sd_default_probe, NULL, NULL);
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(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
SD_TIMEOUT, SD_MAX_RETRIES, 0, RQF_PM, NULL);
if (res) {
sd_print_result(sdkp, "Start/Stop Unit failed", res);
if (driver_byte(res) & DRIVER_SENSE)
sd_print_sense_hdr(sdkp, &sshdr);
if (scsi_sense_valid(&sshdr) &&
/* 0x3a is medium not present */
sshdr.asc == 0x3a)
res = 0;
}
/* SCSI error codes must not go to the generic layer */
if (res)
return -EIO;
return 0;
}
/*
* 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 = dev_get_drvdata(dev);
if (!sdkp)
return; /* this can happen */
if (pm_runtime_suspended(dev))
return;
if (sdkp->WCE && sdkp->media_present) {
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
sd_sync_cache(sdkp, NULL);
}
if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) {
sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
sd_start_stop_device(sdkp, 0);
}
}
static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
struct scsi_sense_hdr sshdr;
int ret = 0;
if (!sdkp) /* E.g.: runtime suspend following sd_remove() */
return 0;
if (sdkp->WCE && sdkp->media_present) {
sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
ret = sd_sync_cache(sdkp, &sshdr);
if (ret) {
/* ignore OFFLINE device */
if (ret == -ENODEV)
return 0;
if (!scsi_sense_valid(&sshdr) ||
sshdr.sense_key != ILLEGAL_REQUEST)
return ret;
/*
* sshdr.sense_key == ILLEGAL_REQUEST means this drive
* doesn't support sync. There's not much to do and
* suspend shouldn't fail.
*/
ret = 0;
}
}
if (sdkp->device->manage_start_stop) {
sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
/* an error is not worth aborting a system sleep */
ret = sd_start_stop_device(sdkp, 0);
if (ignore_stop_errors)
ret = 0;
}
return ret;
}
static int sd_suspend_system(struct device *dev)
{
return sd_suspend_common(dev, true);
}
static int sd_suspend_runtime(struct device *dev)
{
return sd_suspend_common(dev, false);
}
static int sd_resume(struct device *dev)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
int ret;
if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */
return 0;
if (!sdkp->device->manage_start_stop)
return 0;
sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
ret = sd_start_stop_device(sdkp, 1);
if (!ret)
opal_unlock_from_suspend(sdkp->opal_dev);
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)
continue;
majors++;
blk_register_region(sd_major(i), SD_MINORS, NULL,
sd_default_probe, NULL, NULL);
}
if (!majors)
return -ENODEV;
err = class_register(&sd_disk_class);
if (err)
goto err_out;
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");
err = -ENOMEM;
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");
err = -ENOMEM;
goto err_out_cache;
}
err = scsi_register_driver(&sd_template.gendrv);
if (err)
goto err_out_driver;
return 0;
err_out_driver:
mempool_destroy(sd_cdb_pool);
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"));
scsi_unregister_driver(&sd_template.gendrv);
mempool_destroy(sd_cdb_pool);
kmem_cache_destroy(sd_cdb_cache);
class_unregister(&sd_disk_class);
for (i = 0; i < SD_MAJORS; i++) {
blk_unregister_region(sd_major(i), SD_MINORS);
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)
{
scsi_print_sense_hdr(sdkp->device,
sdkp->disk ? sdkp->disk->disk_name : NULL, sshdr);
}
static void sd_print_result(const struct scsi_disk *sdkp, const char *msg,
int result)
{
const char *hb_string = scsi_hostbyte_string(result);
const char *db_string = scsi_driverbyte_string(result);
if (hb_string || db_string)
sd_printk(KERN_INFO, sdkp,
"%s: Result: hostbyte=%s driverbyte=%s\n", msg,
hb_string ? hb_string : "invalid",
db_string ? db_string : "invalid");
else
sd_printk(KERN_INFO, sdkp,
"%s: Result: hostbyte=0x%02x driverbyte=0x%02x\n",
msg, host_byte(result), driver_byte(result));
}