linux.git/include/scsi, branch v4.4.215

scsi: Revert "target: iscsi: Wait for all commands to finish before freeing a session"

2020-02-28T14:39:17+00:00

commit 807b9515b7d044cf77df31f1af9d842a76ecd5cb upstream.

Since commit e9d3009cb936 introduced a regression and since the fix for
that regression was not perfect, revert this commit.

Link: https://marc.info/?l=target-devel&m=158157054906195
Cc: Rahul Kundu 
Cc: Mike Marciniszyn 
Cc: Sagi Grimberg 
Reported-by: Dakshaja Uppalapati 
Fixes: e9d3009cb936 ("scsi: target: iscsi: Wait for all commands to finish before freeing a session")
Signed-off-by: Bart Van Assche 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Greg Kroah-Hartman

scsi: target: iscsi: Wait for all commands to finish before freeing a session

2020-01-04T12:34:36+00:00

[ Upstream commit e9d3009cb936bd0faf0719f68d98ad8afb1e613b ]

The iSCSI target driver is the only target driver that does not wait for
ongoing commands to finish before freeing a session. Make the iSCSI target
driver wait for ongoing commands to finish before freeing a session. This
patch fixes the following KASAN complaint:

BUG: KASAN: use-after-free in __lock_acquire+0xb1a/0x2710
Read of size 8 at addr ffff8881154eca70 by task kworker/0:2/247

CPU: 0 PID: 247 Comm: kworker/0:2 Not tainted 5.4.0-rc1-dbg+ #6
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
Workqueue: target_completion target_complete_ok_work [target_core_mod]
Call Trace:
 dump_stack+0x8a/0xd6
 print_address_description.constprop.0+0x40/0x60
 __kasan_report.cold+0x1b/0x33
 kasan_report+0x16/0x20
 __asan_load8+0x58/0x90
 __lock_acquire+0xb1a/0x2710
 lock_acquire+0xd3/0x200
 _raw_spin_lock_irqsave+0x43/0x60
 target_release_cmd_kref+0x162/0x7f0 [target_core_mod]
 target_put_sess_cmd+0x2e/0x40 [target_core_mod]
 lio_check_stop_free+0x12/0x20 [iscsi_target_mod]
 transport_cmd_check_stop_to_fabric+0xd8/0xe0 [target_core_mod]
 target_complete_ok_work+0x1b0/0x790 [target_core_mod]
 process_one_work+0x549/0xa40
 worker_thread+0x7a/0x5d0
 kthread+0x1bc/0x210
 ret_from_fork+0x24/0x30

Allocated by task 889:
 save_stack+0x23/0x90
 __kasan_kmalloc.constprop.0+0xcf/0xe0
 kasan_slab_alloc+0x12/0x20
 kmem_cache_alloc+0xf6/0x360
 transport_alloc_session+0x29/0x80 [target_core_mod]
 iscsi_target_login_thread+0xcd6/0x18f0 [iscsi_target_mod]
 kthread+0x1bc/0x210
 ret_from_fork+0x24/0x30

Freed by task 1025:
 save_stack+0x23/0x90
 __kasan_slab_free+0x13a/0x190
 kasan_slab_free+0x12/0x20
 kmem_cache_free+0x146/0x400
 transport_free_session+0x179/0x2f0 [target_core_mod]
 transport_deregister_session+0x130/0x180 [target_core_mod]
 iscsit_close_session+0x12c/0x350 [iscsi_target_mod]
 iscsit_logout_post_handler+0x136/0x380 [iscsi_target_mod]
 iscsit_response_queue+0x8de/0xbe0 [iscsi_target_mod]
 iscsi_target_tx_thread+0x27f/0x370 [iscsi_target_mod]
 kthread+0x1bc/0x210
 ret_from_fork+0x24/0x30

The buggy address belongs to the object at ffff8881154ec9c0
 which belongs to the cache se_sess_cache of size 352
The buggy address is located 176 bytes inside of
 352-byte region [ffff8881154ec9c0, ffff8881154ecb20)
The buggy address belongs to the page:
page:ffffea0004553b00 refcount:1 mapcount:0 mapping:ffff888101755400 index:0x0 compound_mapcount: 0
flags: 0x2fff000000010200(slab|head)
raw: 2fff000000010200 dead000000000100 dead000000000122 ffff888101755400
raw: 0000000000000000 0000000080130013 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8881154ec900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8881154ec980: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
>ffff8881154eca00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                             ^
 ffff8881154eca80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8881154ecb00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc

Cc: Mike Christie 
Link: https://lore.kernel.org/r/20191113220508.198257-3-bvanassche@acm.org
Reviewed-by: Roman Bolshakov 
Signed-off-by: Bart Van Assche 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Sasha Levin

scsi: core: Reduce memory required for SCSI logging

2019-10-07T19:01:01+00:00

[ Upstream commit dccc96abfb21dc19d69e707c38c8ba439bba7160 ]

The data structure used for log messages is so large that it can cause a
boot failure. Since allocations from that data structure can fail anyway,
use kmalloc() / kfree() instead of that data structure.

See also https://bugzilla.kernel.org/show_bug.cgi?id=204119.
See also commit ded85c193a39 ("scsi: Implement per-cpu logging buffer") # v4.0.

Reported-by: Jan Palus 
Cc: Christoph Hellwig 
Cc: Hannes Reinecke 
Cc: Johannes Thumshirn 
Cc: Ming Lei 
Cc: Jan Palus 
Signed-off-by: Bart Van Assche 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Sasha Levin

scsi: fcoe: Embed fc_rport_priv in fcoe_rport structure

2019-08-25T08:53:04+00:00

commit 023358b136d490ca91735ac6490db3741af5a8bd upstream.

Gcc-9 complains for a memset across pointer boundaries, which happens as
the code tries to allocate a flexible array on the stack.  Turns out we
cannot do this without relying on gcc-isms, so with this patch we'll embed
the fc_rport_priv structure into fcoe_rport, can use the normal
'container_of' outcast, and will only have to do a memset over one
structure.

Signed-off-by: Hannes Reinecke 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Greg Kroah-Hartman

scsi: Add STARGET_CREATED_REMOVE state to scsi_target_state

2018-11-10T15:41:37+00:00

[ Upstream commit f9279c968c257ee39b0d7bd2571a4d231a67bcc1 ]

The addition of the STARGET_REMOVE state had the side effect of
introducing a race condition that can cause a crash.

scsi_target_reap_ref_release() checks the starget->state to
see if it still in STARGET_CREATED, and if so, skips calling
transport_remove_device() and device_del(), because the starget->state
is only set to STARGET_RUNNING after scsi_target_add() has called
device_add() and transport_add_device().

However, if an rport loss occurs while a target is being scanned,
it can happen that scsi_remove_target() will be called while the
starget is still in the STARGET_CREATED state.  In this case, the
starget->state will be set to STARGET_REMOVE, and as a result,
scsi_target_reap_ref_release() will take the wrong path.  The end
result is a panic:

[ 1255.356653] Oops: 0000 [#1] SMP
[ 1255.360154] Modules linked in: x86_pkg_temp_thermal kvm_intel kvm irqbypass crc32c_intel ghash_clmulni_i
[ 1255.393234] CPU: 5 PID: 149 Comm: kworker/u96:4 Tainted: G        W       4.11.0+ #8
[ 1255.401879] Hardware name: Dell Inc. PowerEdge R320/08VT7V, BIOS 2.0.22 11/19/2013
[ 1255.410327] Workqueue: scsi_wq_6 fc_scsi_scan_rport [scsi_transport_fc]
[ 1255.417720] task: ffff88060ca8c8c0 task.stack: ffffc900048a8000
[ 1255.424331] RIP: 0010:kernfs_find_ns+0x13/0xc0
[ 1255.429287] RSP: 0018:ffffc900048abbf0 EFLAGS: 00010246
[ 1255.435123] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[ 1255.443083] RDX: 0000000000000000 RSI: ffffffff8188d659 RDI: 0000000000000000
[ 1255.451043] RBP: ffffc900048abc10 R08: 0000000000000000 R09: 0000012433fe0025
[ 1255.459005] R10: 0000000025e5a4b5 R11: 0000000025e5a4b5 R12: ffffffff8188d659
[ 1255.466972] R13: 0000000000000000 R14: ffff8805f55e5088 R15: 0000000000000000
[ 1255.474931] FS:  0000000000000000(0000) GS:ffff880616b40000(0000) knlGS:0000000000000000
[ 1255.483959] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1255.490370] CR2: 0000000000000068 CR3: 0000000001c09000 CR4: 00000000000406e0
[ 1255.498332] Call Trace:
[ 1255.501058]  kernfs_find_and_get_ns+0x31/0x60
[ 1255.505916]  sysfs_unmerge_group+0x1d/0x60
[ 1255.510498]  dpm_sysfs_remove+0x22/0x60
[ 1255.514783]  device_del+0xf4/0x2e0
[ 1255.518577]  ? device_remove_file+0x19/0x20
[ 1255.523241]  attribute_container_class_device_del+0x1a/0x20
[ 1255.529457]  transport_remove_classdev+0x4e/0x60
[ 1255.534607]  ? transport_add_class_device+0x40/0x40
[ 1255.540046]  attribute_container_device_trigger+0xb0/0xc0
[ 1255.546069]  transport_remove_device+0x15/0x20
[ 1255.551025]  scsi_target_reap_ref_release+0x25/0x40
[ 1255.556467]  scsi_target_reap+0x2e/0x40
[ 1255.560744]  __scsi_scan_target+0xaa/0x5b0
[ 1255.565312]  scsi_scan_target+0xec/0x100
[ 1255.569689]  fc_scsi_scan_rport+0xb1/0xc0 [scsi_transport_fc]
[ 1255.576099]  process_one_work+0x14b/0x390
[ 1255.580569]  worker_thread+0x4b/0x390
[ 1255.584651]  kthread+0x109/0x140
[ 1255.588251]  ? rescuer_thread+0x330/0x330
[ 1255.592730]  ? kthread_park+0x60/0x60
[ 1255.596815]  ret_from_fork+0x29/0x40
[ 1255.600801] Code: 24 08 48 83 42 40 01 5b 41 5c 5d c3 66 66 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66 90
[ 1255.621876] RIP: kernfs_find_ns+0x13/0xc0 RSP: ffffc900048abbf0
[ 1255.628479] CR2: 0000000000000068
[ 1255.632756] ---[ end trace 34a69ba0477d036f ]---

Fix this by adding another scsi_target state STARGET_CREATED_REMOVE
to distinguish this case.

Fixes: f05795d3d771 ("scsi: Add intermediate STARGET_REMOVE state to scsi_target_state")
Reported-by: David Jeffery 
Signed-off-by: Ewan D. Milne 
Cc: 
Reviewed-by: Laurence Oberman 
Tested-by: Laurence Oberman 
Reviewed-by: Johannes Thumshirn 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Sasha Levin

scsi: sg: disable SET_FORCE_LOW_DMA

2018-01-23T18:50:14+00:00

commit 745dfa0d8ec26b24f3304459ff6e9eacc5c8351b upstream.

The ioctl SET_FORCE_LOW_DMA has never worked since the initial git
check-in, and the respective setting is nowadays handled correctly. So
disable it entirely.

Signed-off-by: Hannes Reinecke 
Reviewed-by: Johannes Thumshirn 
Tested-by: Johannes Thumshirn 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Greg Kroah-Hartman

scsi: libsas: align sata_device's rps_resp on a cacheline

2017-12-16T09:33:48+00:00

commit c2e8fbf908afd81ad502b567a6639598f92c9b9d upstream.

The rps_resp buffer in ata_device is a DMA target, but it isn't
explicitly cacheline aligned. Due to this, adjacent fields can be
overwritten with stale data from memory on non-coherent architectures.
As a result, the kernel is sometimes unable to communicate with an SATA
device behind a SAS expander.

Fix this by ensuring that the rps_resp buffer is cacheline aligned.

This issue is similar to that fixed by Commit 84bda12af31f93 ("libata:
align ap->sector_buf") and Commit 4ee34ea3a12396f35b26 ("libata: Align
ata_device's id on a cacheline").

Signed-off-by: Huacai Chen 
Signed-off-by: Christoph Hellwig 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Greg Kroah-Hartman

scsi: libiscsi: add lock around task lists to fix list corruption regression

2017-03-26T10:13:19+00:00

commit 6f8830f5bbab16e54f261de187f3df4644a5b977 upstream.

There's a rather long standing regression from the commit "libiscsi:
Reduce locking contention in fast path"

Depending on iSCSI target behavior, it's possible to hit the case in
iscsi_complete_task where the task is still on a pending list
(!list_empty(&task->running)).  When that happens the task is removed
from the list while holding the session back_lock, but other task list
modification occur under the frwd_lock.  That leads to linked list
corruption and eventually a panicked system.

Rather than back out the session lock split entirely, in order to try
and keep some of the performance gains this patch adds another lock to
maintain the task lists integrity.

Major enterprise supported kernels have been backing out the lock split
for while now, thanks to the efforts at IBM where a lab setup has the
most reliable reproducer I've seen on this issue.  This patch has been
tested there successfully.

Signed-off-by: Chris Leech 
Fixes: 659743b02c41 ("[SCSI] libiscsi: Reduce locking contention in fast path")
Reported-by: Prashantha Subbarao 
Reviewed-by: Guilherme G. Piccoli 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Greg Kroah-Hartman

scsi: use 'scsi_device_from_queue()' for scsi_dh

2017-03-12T05:37:26+00:00

commit 857de6e00778738dc3d61f75acbac35bdc48e533 upstream.

The device handler needs to check if a given queue belongs to a scsi
device; only then does it make sense to attach a device handler.

[mkp: dropped flags]

Signed-off-by: Hannes Reinecke 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Greg Kroah-Hartman

scsi: Add intermediate STARGET_REMOVE state to scsi_target_state

2016-06-01T19:15:54+00:00

commit f05795d3d771f30a7bdc3a138bf714b06d42aa95 upstream.

Add intermediate STARGET_REMOVE state to scsi_target_state to avoid
running into the BUG_ON() in scsi_target_reap(). The STARGET_REMOVE
state is only valid in the path from scsi_remove_target() to
scsi_target_destroy() indicating this target is going to be removed.

This re-fixes the problem introduced in commits bc3f02a795d3 ("[SCSI]
scsi_remove_target: fix softlockup regression on hot remove") and
40998193560d ("scsi: restart list search after unlock in
scsi_remove_target") in a more comprehensive way.

[mkp: Included James' fix for scsi_target_destroy()]

Signed-off-by: Johannes Thumshirn 
Fixes: 40998193560dab6c3ce8d25f4fa58a23e252ef38
Reported-by: Sergey Senozhatsky 
Tested-by: Sergey Senozhatsky 
Reviewed-by: Ewan D. Milne 
Reviewed-by: Hannes Reinecke 
Reviewed-by: James Bottomley 
Signed-off-by: Martin K. Petersen 
Signed-off-by: Greg Kroah-Hartman