With the addition of commit 00d909a107 ("scsi: target: Make the session
shutdown code also wait for commands that are being aborted") in v4.19-rc, it
incorrectly assumes no signals will be pending for task_struct executing the
normal session shutdown and I/O quiesce code-path.
For example, iscsi-target and iser-target issue SIGINT to all kthreads as part
of session shutdown. This has been the behaviour since day one.
As-is when signals are pending with se_cmds active in se_sess->sess_cmd_list,
wait_event_interruptible_lock_irq_timeout() returns a negative number and
immediately kills the machine because of the do while (ret <= 0) loop that was
added in commit 00d909a107 to spin while backend I/O is taking any amount of
extended time (say 30 seconds) to complete.
Here's what it looks like in action with debug plus delayed backend I/O
completion:
[ 4951.909951] se_sess: 000000003e7e08fa before target_wait_for_sess_cmds
[ 4951.914600] target_wait_for_sess_cmds: signal_pending: 1
[ 4951.918015] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 0
[ 4951.921639] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 1
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 2
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 3
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 4
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 5
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 6
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 7
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 8
[ 4951.921944] wait_event_interruptible_lock_irq_timeout ret: -512 signal_pending: 1 loop count: 9
... followed by the usual RCU CPU stalls and deadlock.
There was never a case pre commit 00d909a107 where
wait_for_complete(&se_cmd->cmd_wait_comp) was able to be interrupted, so to
address this for v4.19+ moving forward go ahead and use
wait_event_lock_irq_timeout() instead so new code works with all fabric
drivers.
Also for commit 00d909a107, fix a minor regression in
target_release_cmd_kref() to only wake_up the new se_sess->cmd_list_wq only
when shutdown has actually been triggered via se_sess->sess_tearing_down.
Fixes: 00d909a107 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted")
Cc: <stable@vger.kernel.org> # v4.19+
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Reviewed-by: Bryant G. Ly <bly@catalogicsoftware.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Short of reverting commit 00d909a107 ("scsi: target: Make the session
shutdown code also wait for commands that are being aborted") for v4.19,
target-core needs a wait_event_t macro can be executed using
TASK_UNINTERRUPTIBLE to function correctly with existing fabric drivers that
expect to run with signals pending during session shutdown and active se_cmd
I/O quiesce.
The most notable is iscsi-target/iser-target, while ibmvscsi_tgt invokes
session shutdown logic from userspace via configfs attribute that could also
potentially have signals pending.
So go ahead and introduce wait_event_lock_irq_timeout() to achieve this, and
update + rename __wait_event_lock_irq_timeout() to make it accept 'state' as a
parameter.
Fixes: 00d909a107 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted")
Cc: <stable@vger.kernel.org> # v4.19+
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Reviewed-by: Bryant G. Ly <bly@catalogicsoftware.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This patch fixes a se_cmd->cmd_kref reference leak that can
occur when a non immediate TMR is proceeded our of command
sequence number order, and CMDSN_LOWER_THAN_EXP is returned
by iscsit_sequence_cmd().
To address this bug, call target_put_sess_cmd() during this
special case following what iscsit_process_scsi_cmd() does
upon CMDSN_LOWER_THAN_EXP.
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Since commit 59b6986dbf fixed a potential NULL pointer dereference
by allocating a se_tmr_req for ISCSI_TM_FUNC_TASK_REASSIGN, the
se_tmr_req is currently leaked by iscsit_free_cmd() because no
iscsi_cmd->se_cmd.se_tfo was associated.
To address this, treat ISCSI_TM_FUNC_TASK_REASSIGN like any other
TMR and call transport_init_se_cmd() + target_get_sess_cmd() to
setup iscsi_cmd->se_cmd.se_tfo with se_cmd->cmd_kref of 2.
This will ensure normal release operation once se_cmd->cmd_kref
reaches zero and target_release_cmd_kref() is invoked, se_tmr_req
will be released via existing target_free_cmd_mem() and
core_tmr_release_req() code.
Reported-by: Donald White <dew@datera.io>
Cc: Donald White <dew@datera.io>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes bug where early se_cmd exceptions that occur
before backend execution can result in use-after-free if/when
a subsequent ABORT_TASK occurs for the same tag.
Since an early se_cmd exception will have had se_cmd added to
se_session->sess_cmd_list via target_get_sess_cmd(), it will
not have CMD_T_COMPLETE set by the usual target_complete_cmd()
backend completion path.
This causes a subsequent ABORT_TASK + __target_check_io_state()
to signal ABORT_TASK should proceed. As core_tmr_abort_task()
executes, it will bring the outstanding se_cmd->cmd_kref count
down to zero releasing se_cmd, after se_cmd has already been
queued with error status into fabric driver response path code.
To address this bug, introduce a CMD_T_PRE_EXECUTE bit that is
set at target_get_sess_cmd() time, and cleared immediately before
backend driver dispatch in target_execute_cmd() once CMD_T_ACTIVE
is set.
Then, check CMD_T_PRE_EXECUTE within __target_check_io_state() to
determine when an early exception has occured, and avoid aborting
this se_cmd since it will have already been queued into fabric
driver response path code.
Reported-by: Donald White <dew@datera.io>
Cc: Donald White <dew@datera.io>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a potential end-less loop during QUEUE_FULL,
where cmd->se_tfo->write_pending() callback fails repeatedly
but __transport_wait_for_tasks() has already been invoked to
quiese the outstanding se_cmd descriptor.
To address this bug, this patch adds a CMD_T_STOP|CMD_T_ABORTED
check within transport_write_pending_qf() and invokes the
existing se_cmd->t_transport_stop_comp to signal quiese
completion back to __transport_wait_for_tasks().
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: Potnuri Bharat Teja <bharat@chelsio.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: stable@vger.kernel.org # 4.11+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
With the recent addition of transport_check_aborted_status() within
transport_generic_request_failure() to avoid sending a SCSI status
exception after CMD_T_ABORTED w/ TAS=1 has occured, it introduced
a COMPARE_AND_WRITE early failure regression.
Namely when COMPARE_AND_WRITE fails and se_device->caw_sem has
been taken by sbc_compare_and_write(), if the new check for
transport_check_aborted_status() returns true and exits,
cmd->transport_complete_callback() -> compare_and_write_post()
is skipped never releasing se_device->caw_sem.
This regression was originally introduced by:
commit e3b88ee95b
Author: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Tue Feb 14 16:25:45 2017 -0800
target: Fix handling of aborted failed commands
To address this bug, move the transport_check_aborted_status()
call after transport_complete_task_attr() and
cmd->transport_complete_callback().
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: stable@vger.kernel.org # 4.11+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a bug during QUEUE_FULL where transport_complete_qf()
calls transport_complete_task_attr() after it's already been invoked
by target_complete_ok_work() or transport_generic_request_failure()
during initial completion, preceeding QUEUE_FULL.
This will result in se_device->simple_cmds, se_device->dev_cur_ordered_id
and/or se_device->dev_ordered_sync being updated multiple times for
a single se_cmd.
To address this bug, clear SCF_TASK_ATTR_SET after the first call
to transport_complete_task_attr(), and avoid updating SCSI task
attribute related counters for any subsequent calls.
Also, when a se_cmd is deferred due to ordered tags and executed
via target_restart_delayed_cmds(), set CMD_T_SENT before execution
matching what target_execute_cmd() does.
Cc: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: stable@vger.kernel.org # 4.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a bug associated with iscsit_reset_np_thread()
that can occur during parallel configfs rmdir of a single iscsi_np
used across multiple iscsi-target instances, that would result in
hung task(s) similar to below where configfs rmdir process context
was blocked indefinately waiting for iscsi_np->np_restart_comp
to finish:
[ 6726.112076] INFO: task dcp_proxy_node_:15550 blocked for more than 120 seconds.
[ 6726.119440] Tainted: G W O 4.1.26-3321 #2
[ 6726.125045] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 6726.132927] dcp_proxy_node_ D ffff8803f202bc88 0 15550 1 0x00000000
[ 6726.140058] ffff8803f202bc88 ffff88085c64d960 ffff88083b3b1ad0 ffff88087fffeb08
[ 6726.147593] ffff8803f202c000 7fffffffffffffff ffff88083f459c28 ffff88083b3b1ad0
[ 6726.155132] ffff88035373c100 ffff8803f202bca8 ffffffff8168ced2 ffff8803f202bcb8
[ 6726.162667] Call Trace:
[ 6726.165150] [<ffffffff8168ced2>] schedule+0x32/0x80
[ 6726.170156] [<ffffffff8168f5b4>] schedule_timeout+0x214/0x290
[ 6726.176030] [<ffffffff810caef2>] ? __send_signal+0x52/0x4a0
[ 6726.181728] [<ffffffff8168d7d6>] wait_for_completion+0x96/0x100
[ 6726.187774] [<ffffffff810e7c80>] ? wake_up_state+0x10/0x10
[ 6726.193395] [<ffffffffa035d6e2>] iscsit_reset_np_thread+0x62/0xe0 [iscsi_target_mod]
[ 6726.201278] [<ffffffffa0355d86>] iscsit_tpg_disable_portal_group+0x96/0x190 [iscsi_target_mod]
[ 6726.210033] [<ffffffffa0363f7f>] lio_target_tpg_store_enable+0x4f/0xc0 [iscsi_target_mod]
[ 6726.218351] [<ffffffff81260c5a>] configfs_write_file+0xaa/0x110
[ 6726.224392] [<ffffffff811ea364>] vfs_write+0xa4/0x1b0
[ 6726.229576] [<ffffffff811eb111>] SyS_write+0x41/0xb0
[ 6726.234659] [<ffffffff8169042e>] system_call_fastpath+0x12/0x71
It would happen because each iscsit_reset_np_thread() sets state
to ISCSI_NP_THREAD_RESET, sends SIGINT, and then blocks waiting
for completion on iscsi_np->np_restart_comp.
However, if iscsi_np was active processing a login request and
more than a single iscsit_reset_np_thread() caller to the same
iscsi_np was blocked on iscsi_np->np_restart_comp, iscsi_np
kthread process context in __iscsi_target_login_thread() would
flush pending signals and only perform a single completion of
np->np_restart_comp before going back to sleep within transport
specific iscsit_transport->iscsi_accept_np code.
To address this bug, add a iscsi_np->np_reset_count and update
__iscsi_target_login_thread() to keep completing np->np_restart_comp
until ->np_reset_count has reached zero.
Reported-by: Gary Guo <ghg@datera.io>
Tested-by: Gary Guo <ghg@datera.io>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch drops two incorrect usages of tcm_qla2xxx_free_cmd()
during TMR ABORT within tcm_qla2xxx_handle_data_work() and
tcm_qla2xxx_aborted_task(), which where attempting to dispatch
into workqueue context to do tcm_qla2xxx_complete_free() and
subsequently invoke transport_generic_free_cmd().
This is incorrect because during TMR ABORT target-core will
drop the outstanding se_cmd->cmd_kref references once it has
quiesced the se_cmd via transport_wait_for_tasks(), and in
the case of qla2xxx it should not attempt to do it's own
transport_generic_free_cmd() once the abort has occured.
As reported by Pascal, this was originally manifesting as a
BUG_ON(cmd->cmd_in_wq) in qlt_free_cmd() during TMR ABORT,
with a LIO backend that had sufficently high enough WRITE
latency to trigger a host side TMR ABORT_TASK.
(v2: Drop the qla_tgt_cmd->write_pending_abort_comp changes,
as they will be addressed in a seperate series)
Reported-by: Pascal de Bruijn <p.debruijn@unilogic.nl>
Tested-by: Pascal de Bruijn <p.debruijn@unilogic.nl>
Cc: Pascal de Bruijn <p.debruijn@unilogic.nl>
Reported-by: Lukasz Engel <lukasz.engel@softax.pl>
Cc: Lukasz Engel <lukasz.engel@softax.pl>
Acked-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Cc: Quinn Tran <quinn.tran@cavium.com>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch re-introduces part of a long standing login workaround that
was recently dropped by:
commit 1c99de981f
Author: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Sun Apr 2 13:36:44 2017 -0700
iscsi-target: Drop work-around for legacy GlobalSAN initiator
Namely, the workaround for FirstBurstLength ended up being required by
Mellanox Flexboot PXE boot ROMs as reported by Robert.
So this patch re-adds the work-around for FirstBurstLength within
iscsi_check_proposer_for_optional_reply(), and makes the key optional
to respond when the initiator does not propose, nor respond to it.
Also as requested by Arun, this patch introduces a new TPG attribute
named 'login_keys_workaround' that controls the use of both the
FirstBurstLength workaround, as well as the two other existing
workarounds for gPXE iSCSI boot client.
By default, the workaround is enabled with login_keys_workaround=1,
since Mellanox FlexBoot requires it, and Arun has verified the Qlogic
MSFT initiator already proposes FirstBurstLength, so it's uneffected
by this re-adding this part of the original work-around.
Reported-by: Robert LeBlanc <robert@leblancnet.us>
Cc: Robert LeBlanc <robert@leblancnet.us>
Reviewed-by: Arun Easi <arun.easi@cavium.com>
Cc: <stable@vger.kernel.org> # 3.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch drops two incorrect usages of tcm_qla2xxx_free_cmd()
during TMR ABORT within tcm_qla2xxx_handle_data_work() and
tcm_qla2xxx_aborted_task(), which where attempting to dispatch
into workqueue context to do tcm_qla2xxx_complete_free() and
subsequently invoke transport_generic_free_cmd().
This is incorrect because during TMR ABORT target-core will
drop the outstanding se_cmd->cmd_kref references once it has
quiesced the se_cmd via transport_wait_for_tasks(), and in
the case of qla2xxx it should not attempt to do it's own
transport_generic_free_cmd() once the abort has occured.
As reported by Pascal, this was originally manifesting as a
BUG_ON(cmd->cmd_in_wq) in qlt_free_cmd() during TMR ABORT,
with a LIO backend that had sufficently high enough WRITE
latency to trigger a host side TMR ABORT_TASK.
In addition, for the case in tcm_qla2xxx_write_pending_status()
and tcm_qla2xxx_handle_data_work() that waits for outstanding
FCP WRITE data transfer to complete before preceeding with a
TMR ABORT, avoid se_cmd->t_transport_stop_comp that is already
used by transport_wait_for_tasks() and use a qla2xxx internal
struct completion instead.
Reported-by: Pascal de Bruijn <p.debruijn@unilogic.nl>
Tested-by: Pascal de Bruijn <p.debruijn@unilogic.nl>
Acked-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Cc: Quinn Tran <quinn.tran@cavium.com>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a NULL pointer dereference in isert_login_recv_done()
of isert_conn->cm_id due to isert_cma_handler() -> isert_connect_error()
resetting isert_conn->cm_id = NULL during a failed login attempt.
As per Sagi, we will always see the completion of all recv wrs posted
on the qp (given that we assigned a ->done handler), this is a FLUSH
error completion, we just don't get to verify that because we deref
NULL before.
The issue here, was the assumption that dereferencing the connection
cm_id is always safe, which is not true since:
commit 4a579da258
Author: Sagi Grimberg <sagig@mellanox.com>
Date: Sun Mar 29 15:52:04 2015 +0300
iser-target: Fix possible deadlock in RDMA_CM connection error
As I see it, we have a direct reference to the isert_device from
isert_conn which is the one-liner fix that we actually need like
we do in isert_rdma_read_done() and isert_rdma_write_done().
Reported-by: Andrea Righi <righi.andrea@gmail.com>
Tested-by: Andrea Righi <righi.andrea@gmail.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
With commit 25cdda95fd in place to address the initial login
PDU asynchronous socket close OOPs, go ahead and kill off the
left-over iscsi_target_do_cleanup() and ->login_cleanup_work.
Reported-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Following Himanshu's earlier patch to drop the redundant tag
lookup within __qlt_24xx_handle_abts(), go ahead and drop this
now QLA_TGT_ABTS can use TARGET_SCF_LOOKUP_LUN_FROM_TAG and
have target_submit_tmr() do this from common code.
Reviewed-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Acked-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Quinn Tran <quinn.tran@cavium.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch introduces support in target_submit_tmr() for locating a
unpacked_lun from an existing se_cmd->tag during ABORT_TASK.
When TARGET_SCF_LOOKUP_LUN_FROM_TAG is set, target_submit_tmr()
will do the extra lookup via target_lookup_lun_from_tag() and
subsequently invoke transport_lookup_tmr_lun() so a proper
percpu se_lun->lun_ref is taken before workqueue dispatch into
se_device->tmr_wq happens.
Aside from the extra target_lookup_lun_from_tag(), the existing
code-path remains unchanged.
Reviewed-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Quinn Tran <quinn.tran@cavium.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch introduces TMR percpu reference counting using
se_lun->lun_ref in transport_lookup_tmr_lun(), following
how existing non TMR per se_lun reference counting works
within transport_lookup_cmd_lun().
It also adds explicit transport_lun_remove_cmd() calls to
drop the reference in the three tmr related locations that
invoke transport_cmd_check_stop_to_fabric();
- target_tmr_work() during normal ->queue_tm_rsp()
- target_complete_tmr_failure() during error ->queue_tm_rsp()
- transport_generic_handle_tmr() during early failure
Also, note the exception paths in transport_generic_free_cmd()
and transport_cmd_finish_abort() already check SCF_SE_LUN_CMD,
and will invoke transport_lun_remove_cmd() when necessary.
Reviewed-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Quinn Tran <quinn.tran@cavium.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
As originally reported by Jia-Ju, iscsit_tpg_enable_portal_group()
holds iscsi_portal_group->tpg_state_lock while updating AUTHMETHOD
via iscsi_update_param_value(), which performs a GFP_KERNEL
allocation.
However, since iscsit_tpg_enable_portal_group() is already protected
by iscsit_get_tpg() -> iscsi_portal_group->tpg_access_lock in it's
parent caller, ->tpg_state_lock only needs to be held when setting
TPG_STATE_ACTIVE.
Reported-by: Jia-Ju Bai <baijiaju1990@163.com>
Reviewed-by: Jia-Ju Bai <baijiaju1990@163.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Instead of using a hardcoded magic value in se_lun when verifying
a target config_item symlink source during target_fabric_mappedlun_link(),
go ahead and use target_fabric_port_item_ops directly instead.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Instead of using a hardcoded magic value in se_device when verifying
a target config_item symlink source during target_fabric_port_link(),
go ahead and use target_core_dev_item_ops directly instead.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The people who are actively using iblock_execute_write_same_direct() are
doing so in the context of ESX VAAI BlockZero, together with
EXTENDED_COPY and COMPARE_AND_WRITE primitives.
In practice though I've not seen any users of IBLOCK WRITE_SAME for
anything other than VAAI BlockZero, so just using blkdev_issue_zeroout()
when available, and falling back to iblock_execute_write_same() if the
WRITE_SAME buffer contains anything other than zeros should be OK.
(Hook up max_write_zeroes_sectors to signal LBPRZ feature bit in
target_configure_unmap_from_queue - nab)
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
When iscsi WRITE underflow occurs there are two different scenarios
that can happen.
Normally in practice, when an EDTL vs. SCSI CDB TRANSFER LENGTH
underflow is detected, the iscsi immediate data payload is the
smaller SCSI CDB TRANSFER LENGTH.
That is, when a host fabric LLD is using a fixed size EDTL for
a specific control CDB, the SCSI CDB TRANSFER LENGTH and actual
SCSI payload ends up being smaller than EDTL. In iscsi, this
means the received iscsi immediate data payload matches the
smaller SCSI CDB TRANSFER LENGTH, because there is no more
SCSI payload to accept beyond SCSI CDB TRANSFER LENGTH.
However, it's possible for a malicous host to send a WRITE
underflow where EDTL is larger than SCSI CDB TRANSFER LENGTH,
but incoming iscsi immediate data actually matches EDTL.
In the wild, we've never had a iscsi host environment actually
try to do this.
For this special case, it's wrong to truncate part of the
control CDB payload and continue to process the command during
underflow when immediate data payload received was larger than
SCSI CDB TRANSFER LENGTH, so go ahead and reject and drop the
bogus payload as a defensive action.
Note this potential bug was originally relaxed by the following
for allowing WRITE underflow in MSFT FCP host environments:
commit c72c525022
Author: Roland Dreier <roland@purestorage.com>
Date: Wed Jul 22 15:08:18 2015 -0700
target: allow underflow/overflow for PR OUT etc. commands
Cc: Roland Dreier <roland@purestorage.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: <stable@vger.kernel.org> # v4.3+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a BUG() in iscsit_close_session() that could be
triggered when iscsit_logout_post_handler() execution from within
tx thread context was not run for more than SECONDS_FOR_LOGOUT_COMP
(15 seconds), and the TCP connection didn't already close before
then forcing tx thread context to automatically exit.
This would manifest itself during explicit logout as:
[33206.974254] 1 connection(s) still exist for iSCSI session to iqn.1993-08.org.debian:01:3f5523242179
[33206.980184] INFO: NMI handler (kgdb_nmi_handler) took too long to run: 2100.772 msecs
[33209.078643] ------------[ cut here ]------------
[33209.078646] kernel BUG at drivers/target/iscsi/iscsi_target.c:4346!
Normally when explicit logout attempt fails, the tx thread context
exits and iscsit_close_connection() from rx thread context does the
extra cleanup once it detects conn->conn_logout_remove has not been
cleared by the logout type specific post handlers.
To address this special case, if the logout post handler in tx thread
context detects conn->tx_thread_active has already been cleared, simply
return and exit in order for existing iscsit_close_connection()
logic from rx thread context do failed logout cleanup.
Reported-by: Bart Van Assche <bart.vanassche@sandisk.com>
Tested-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: stable@vger.kernel.org # 3.14+
Tested-by: Gary Guo <ghg@datera.io>
Tested-by: Chu Yuan Lin <cyl@datera.io>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a se_cmd->cmd_kref underflow during CMD_T_ABORTED
when a fabric driver drops it's second reference from below the
target_core_tmr.c based callers of transport_cmd_finish_abort().
Recently with the conversion of kref to refcount_t, this bug was
manifesting itself as:
[705519.601034] refcount_t: underflow; use-after-free.
[705519.604034] INFO: NMI handler (kgdb_nmi_handler) took too long to run: 20116.512 msecs
[705539.719111] ------------[ cut here ]------------
[705539.719117] WARNING: CPU: 3 PID: 26510 at lib/refcount.c:184 refcount_sub_and_test+0x33/0x51
Since the original kref atomic_t based kref_put() didn't check for
underflow and only invoked the final callback when zero was reached,
this bug did not manifest in practice since all se_cmd memory is
using preallocated tags.
To address this, go ahead and propigate the existing return from
transport_put_cmd() up via transport_cmd_finish_abort(), and
change transport_cmd_finish_abort() + core_tmr_handle_tas_abort()
callers to only do their local target_put_sess_cmd() if necessary.
Reported-by: Bart Van Assche <bart.vanassche@sandisk.com>
Tested-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: stable@vger.kernel.org # 3.14+
Tested-by: Gary Guo <ghg@datera.io>
Tested-by: Chu Yuan Lin <cyl@datera.io>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a OOPs originally introduced by:
commit bb048357da
Author: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Thu Sep 5 14:54:04 2013 -0700
iscsi-target: Add sk->sk_state_change to cleanup after TCP failure
which would trigger a NULL pointer dereference when a TCP connection
was closed asynchronously via iscsi_target_sk_state_change(), but only
when the initial PDU processing in iscsi_target_do_login() from iscsi_np
process context was blocked waiting for backend I/O to complete.
To address this issue, this patch makes the following changes.
First, it introduces some common helper functions used for checking
socket closing state, checking login_flags, and atomically checking
socket closing state + setting login_flags.
Second, it introduces a LOGIN_FLAGS_INITIAL_PDU bit to know when a TCP
connection has dropped via iscsi_target_sk_state_change(), but the
initial PDU processing within iscsi_target_do_login() in iscsi_np
context is still running. For this case, it sets LOGIN_FLAGS_CLOSED,
but doesn't invoke schedule_delayed_work().
The original NULL pointer dereference case reported by MNC is now handled
by iscsi_target_do_login() doing a iscsi_target_sk_check_close() before
transitioning to FFP to determine when the socket has already closed,
or iscsi_target_start_negotiation() if the login needs to exchange
more PDUs (eg: iscsi_target_do_login returned 0) but the socket has
closed. For both of these cases, the cleanup up of remaining connection
resources will occur in iscsi_target_start_negotiation() from iscsi_np
process context once the failure is detected.
Finally, to handle to case where iscsi_target_sk_state_change() is
called after the initial PDU procesing is complete, it now invokes
conn->login_work -> iscsi_target_do_login_rx() to perform cleanup once
existing iscsi_target_sk_check_close() checks detect connection failure.
For this case, the cleanup of remaining connection resources will occur
in iscsi_target_do_login_rx() from delayed workqueue process context
once the failure is detected.
Reported-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Tested-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Reported-by: Hannes Reinecke <hare@suse.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Varun Prakash <varun@chelsio.com>
Cc: <stable@vger.kernel.org> # v3.12+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
During v4.3 when the overflow/underflow check was relaxed by
commit c72c525022:
commit c72c525022
Author: Roland Dreier <roland@purestorage.com>
Date: Wed Jul 22 15:08:18 2015 -0700
target: allow underflow/overflow for PR OUT etc. commands
to allow underflow/overflow for Windows compliance + FCP, a
consequence was to allow control CDBs to process overflow
data for iscsi-target with immediate data as well.
As per Roland's original change, continue to allow underflow
cases for control CDBs to make Windows compliance + FCP happy,
but until overflow for control CDBs is supported tree-wide,
explicitly reject all control WRITEs with overflow following
pre v4.3.y logic.
Reported-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Roland Dreier <roland@purestorage.com>
Cc: <stable@vger.kernel.org> # v4.3+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This reverts commit 0e2eb7d12e
Author: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Thu Mar 30 10:12:39 2017 -0700
target: Fix VERIFY and WRITE VERIFY command parsing
This patch broke existing behaviour for WRITE_VERIFY because
it dropped the original SCF_SCSI_DATA_CDB assignment for
bytchk = 0 so target_cmd_size_check() no longer rejected
this case, allowing an overflow case to trigger an OOPs
in iscsi-target.
Since the short term and long term fixes are still being
discussed, revert it for now since it's late in the merge
window and try again in v4.13-rc1.
Conflicts:
drivers/target/target_core_sbc.c
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Keeping in the idempotent nature of target_core_fabric_configfs.c,
if a queue_depth value is set and it's the same as the existing
value, don't attempt to force session reinstatement.
Reported-by: Raghu Krishnamurthy <rk@datera.io>
Cc: Raghu Krishnamurthy <rk@datera.io>
Tested-by: Gary Guo <ghg@datera.io>
Cc: Gary Guo <ghg@datera.io>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
While testing modification of per se_node_acl queue_depth forcing
session reinstatement via lio_target_nacl_cmdsn_depth_store() ->
core_tpg_set_initiator_node_queue_depth(), a hung task bug triggered
when changing cmdsn_depth invoked session reinstatement while an iscsi
login was already waiting for session reinstatement to complete.
This can happen when an outstanding se_cmd descriptor is taking a
long time to complete, and session reinstatement from iscsi login
or cmdsn_depth change occurs concurrently.
To address this bug, explicitly set session_fall_back_to_erl0 = 1
when forcing session reinstatement, so session reinstatement is
not attempted if an active session is already being shutdown.
This patch has been tested with two scenarios. The first when
iscsi login is blocked waiting for iscsi session reinstatement
to complete followed by queue_depth change via configfs, and
second when queue_depth change via configfs us blocked followed
by a iscsi login driven session reinstatement.
Note this patch depends on commit d36ad77f70 to handle multiple
sessions per se_node_acl when changing cmdsn_depth, and for
pre v4.5 kernels will need to be included for stable as well.
Reported-by: Gary Guo <ghg@datera.io>
Tested-by: Gary Guo <ghg@datera.io>
Cc: Gary Guo <ghg@datera.io>
Cc: <stable@vger.kernel.org> # v4.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Following the bugfix for handling non SAM_STAT_GOOD COMPARE_AND_WRITE
status during COMMIT phase in commit 9b2792c3da, the same bug exists
for the READ phase as well.
This would manifest first as a lost SCSI response, and eventual
hung task during fabric driver logout or re-login, as existing
shutdown logic waited for the COMPARE_AND_WRITE se_cmd->cmd_kref
to reach zero.
To address this bug, compare_and_write_callback() has been changed
to set post_ret = 1 and return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE
as necessary to signal failure status.
Reported-by: Bill Borsari <wgb@datera.io>
Cc: Bill Borsari <wgb@datera.io>
Tested-by: Gary Guo <ghg@datera.io>
Cc: Gary Guo <ghg@datera.io>
Cc: <stable@vger.kernel.org> # v4.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Once upon a time back in 2009, a work-around was added to support
the GlobalSAN iSCSI initiator v3.3 for MacOSX, which during login
did not propose nor respond to MaxBurstLength, FirstBurstLength,
DefaultTime2Wait and DefaultTime2Retain keys.
The work-around in iscsi_check_proposer_for_optional_reply()
allowed the missing keys to be proposed, but did not require
waiting for a response before moving to full feature phase
operation. This allowed GlobalSAN v3.3 to work out-of-the
box, and for many years we didn't run into login interopt
issues with any other initiators..
Until recently, when Martin tried a QLogic 57840S iSCSI Offload
HBA on Windows 2016 which completed login, but subsequently
failed with:
Got unknown iSCSI OpCode: 0x43
The issue was QLogic MSFT side did not propose DefaultTime2Wait +
DefaultTime2Retain, so LIO proposes them itself, and immediately
transitions to full feature phase because of the GlobalSAN hack.
However, the QLogic MSFT side still attempts to respond to
DefaultTime2Retain + DefaultTime2Wait, even though LIO has set
ISCSI_FLAG_LOGIN_NEXT_STAGE3 + ISCSI_FLAG_LOGIN_TRANSIT
in last login response.
So while the QLogic MSFT side should have been proposing these
two keys to start, it was doing the correct thing per RFC-3720
attempting to respond to proposed keys before transitioning to
full feature phase.
All that said, recent versions of GlobalSAN iSCSI (v5.3.0.541)
does correctly propose the four keys during login, making the
original work-around moot.
So in order to allow QLogic MSFT to run unmodified as-is, go
ahead and drop this long standing work-around.
Reported-by: Martin Svec <martin.svec@zoner.cz>
Cc: Martin Svec <martin.svec@zoner.cz>
Cc: Himanshu Madhani <Himanshu.Madhani@cavium.com>
Cc: Arun Easi <arun.easi@cavium.com>
Cc: stable@vger.kernel.org # 3.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses two queue-full handling bugs in iser-target.
The first is propagating isert_rdma_rw_ctx_post() return back
to target-core via isert_put_datain() + isert_get_dataout()
callbacks, in order to trigger queue-full logic in target-core.
Note target-core expects -EAGAIN or -ENOMEM error to signal
RDMA WRITE/READ data-transfer callbacks should be retried,
after queue-full logic been invoked.
Other types of errors propagated up from RDMA RW API will result
in target-core generating internal CHECK_CONDITION status,
avoiding subsequent isert_put_datain() and isert_get_dataout()
iscsit_transport callback retry attempts.
The second is to use transport_generic_request_failure()
during T10-PI hw-offload errors in isert_rdma_write_done()
and isert_rdma_read_done(), so CHECK_CONDITION queue-full
is handled internally by target-core.
Also add isert_put_response() T10-PI failure case fixme in
isert_rdma_write_done(), which is currently not internally
retried or released until session reinstatement.
Reported-by: Potnuri Bharat Teja <bharat@chelsio.com>
Reviewed-by: Potnuri Bharat Teja <bharat@chelsio.com>
Tested-by: Potnuri Bharat Teja <bharat@chelsio.com>
Cc: Potnuri Bharat Teja <bharat@chelsio.com>
Reported-by: Steve Wise <swise@opengridcomputing.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a set of queue-full response handling
bugs, where outgoing responses are leaked when a fabric
driver is propagating non -EAGAIN or -ENOMEM errors
to target-core.
It introduces TRANSPORT_COMPLETE_QF_ERR state used to
signal when CHECK_CONDITION status should be generated,
when fabric driver ->write_pending(), ->queue_data_in(),
or ->queue_status() callbacks fail with non -EAGAIN or
-ENOMEM errors, and data-transfer should not be retried.
Note all fabric driver -EAGAIN and -ENOMEM errors are
still retried indefinately with associated data-transfer
callbacks, following existing queue-full logic.
Also fix two missing ->queue_status() queue-full cases
related to CMD_T_ABORTED w/ TAS status handling.
Reported-by: Potnuri Bharat Teja <bharat@chelsio.com>
Reviewed-by: Potnuri Bharat Teja <bharat@chelsio.com>
Tested-by: Potnuri Bharat Teja <bharat@chelsio.com>
Cc: Potnuri Bharat Teja <bharat@chelsio.com>
Reported-by: Steve Wise <swise@opengridcomputing.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch closes a race between se_lun deletion during configfs
unlink in target_fabric_port_unlink() -> core_dev_del_lun()
-> core_tpg_remove_lun(), when transport_clear_lun_ref() blocks
waiting for percpu_ref RCU grace period to finish, but a new
NodeACL mappedlun is added before the RCU grace period has
completed.
This can happen in target_fabric_mappedlun_link() because it
only checks for se_lun->lun_se_dev, which is not cleared until
after transport_clear_lun_ref() percpu_ref RCU grace period
finishes.
This bug originally manifested as NULL pointer dereference
OOPsen in target_stat_scsi_att_intr_port_show_attr_dev() on
v4.1.y code, because it dereferences lun->lun_se_dev without
a explicit NULL pointer check.
In post v4.1 code with target-core RCU conversion, the code
in target_stat_scsi_att_intr_port_show_attr_dev() no longer
uses se_lun->lun_se_dev, but the same race still exists.
To address the bug, go ahead and set se_lun>lun_shutdown as
early as possible in core_tpg_remove_lun(), and ensure new
NodeACL mappedlun creation in target_fabric_mappedlun_link()
fails during se_lun shutdown.
Reported-by: James Shen <jcs@datera.io>
Cc: James Shen <jcs@datera.io>
Tested-by: James Shen <jcs@datera.io>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a iscsi-target specific TMR reference leak
during session shutdown, that could occur when a TMR was
quiesced before the hand-off back to iscsi-target code
via transport_cmd_check_stop_to_fabric().
The reference leak happens because iscsit_free_cmd() was
incorrectly skipping the final target_put_sess_cmd() for
TMRs when transport_generic_free_cmd() returned zero because
the se_cmd->cmd_kref did not reach zero, due to the missing
se_cmd assignment in original code.
The result was iscsi_cmd and it's associated se_cmd memory
would be freed once se_sess->sess_cmd_map where released,
but the associated se_tmr_req was leaked and remained part
of se_device->dev_tmr_list.
This bug would manfiest itself as kernel paging request
OOPsen in core_tmr_lun_reset(), when a left-over se_tmr_req
attempted to dereference it's se_cmd pointer that had
already been released during normal session shutdown.
To address this bug, go ahead and treat ISCSI_OP_SCSI_CMD
and ISCSI_OP_SCSI_TMFUNC the same when there is an extra
se_cmd->cmd_kref to drop in iscsit_free_cmd(), and use
op_scsi to signal __iscsit_free_cmd() when the former
needs to clear any further iscsi related I/O state.
Reported-by: Rob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Reported-by: Chu Yuan Lin <cyl@datera.io>
Cc: Chu Yuan Lin <cyl@datera.io>
Tested-by: Chu Yuan Lin <cyl@datera.io>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The new cmd_time_out configfs attribute for TCMU is allowed to
be disabled, so go ahead and drop the tcmu_cmd_time_out_store()
check.
Reported-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Instead of putting cmd_time_out under ../target/core/user_0/foo/control,
which has historically been used by parameters needed for initial
backend device configuration, go ahead and move cmd_time_out into
a backend device attribute.
In order to do this, tcmu_module_init() has been updated to create
a local struct configfs_attribute **tcmu_attrs, that is based upon
the existing passthrough_attrib_attrs along with the new cmd_time_out
attribute. Once **tcm_attrs has been setup, go ahead and point
it at tcmu_ops->tb_dev_attrib_attrs so it's picked up by target-core.
Also following MNC's previous change, ->cmd_time_out is stored in
milliseconds but exposed via configfs in seconds. Also, note this
patch restricts the modification of ->cmd_time_out to before +
after the TCMU device has been configured, but not while it has
active fabric exports.
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
All in-tree fabric drivers provide a tfo->check_stop_free(),
so there is no need to do the extra check within existing
transport_cmd_check_stop_to_fabric() code.
Just to be sure, add a check in target_fabric_tf_ops_check()
to notify any out-of-tree drivers that might be missing it.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The following fixes a divide by zero OOPs with TYPE_TAPE
due to pscsi_tape_read_blocksize() failing causing a zero
sd->sector_size being propigated up via dev_attrib.hw_block_size.
It also fixes another long-standing bug where TYPE_TAPE and
TYPE_MEDIMUM_CHANGER where using pscsi_create_type_other(),
which does not call scsi_device_get() to take the device
reference. Instead, rename pscsi_create_type_rom() to
pscsi_create_type_nondisk() and use it for all cases.
Finally, also drop a dump_stack() in pscsi_get_blocks() for
non TYPE_DISK, which in modern target-core can get invoked
via target_sense_desc_format() during CHECK_CONDITION.
Reported-by: Malcolm Haak <insanemal@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Due to the long standing checks in iscsit_snmp_get_tiqn()
that assume conn->sess->tpg dereference of tpg->tpg_tiqn
for iscsit_collect_login_stats() usage, some of the early
login failure cases like ISCSI_LOGIN_STATUS_TGT_FORBIDDEN
where not getting incremented, due to sess->tpg assignment
happening later in iscsi_login_zero_tsih_s2().
Instead, use the earlier conn->tpg assignment done by
iscsi_target_locate_portal() -> iscsit_get_tpg_from_np()
so the existing counters are incremented correctly for
the various early login failure cases.
Also, go ahead and drop the old rate limiting check in
iscsit_collect_login_stats(), so we get the true number
of failed login attempts in the existing statistics.
Reported-by: Ryan Stiles <ras@datera.io>
Cc: Ryan Stiles <ras@datera.io>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
When transport_clear_lun_ref() is shutting down a se_lun via
configfs with new I/O in-flight, it's possible to trigger a
NULL pointer dereference in transport_lookup_cmd_lun() due
to the fact percpu_ref_get() doesn't do any __PERCPU_REF_DEAD
checking before incrementing lun->lun_ref.count after
lun->lun_ref has switched to atomic_t mode.
This results in a NULL pointer dereference as LUN shutdown
code in core_tpg_remove_lun() continues running after the
existing ->release() -> core_tpg_lun_ref_release() callback
completes, and clears the RCU protected se_lun->lun_se_dev
pointer.
During the OOPs, the state of lun->lun_ref in the process
which triggered the NULL pointer dereference looks like
the following on v4.1.y stable code:
struct se_lun {
lun_link_magic = 4294932337,
lun_status = TRANSPORT_LUN_STATUS_FREE,
.....
lun_se_dev = 0x0,
lun_sep = 0x0,
.....
lun_ref = {
count = {
counter = 1
},
percpu_count_ptr = 3,
release = 0xffffffffa02fa1e0 <core_tpg_lun_ref_release>,
confirm_switch = 0x0,
force_atomic = false,
rcu = {
next = 0xffff88154fa1a5d0,
func = 0xffffffff8137c4c0 <percpu_ref_switch_to_atomic_rcu>
}
}
}
To address this bug, use percpu_ref_tryget_live() to ensure
once __PERCPU_REF_DEAD is visable on all CPUs and ->lun_ref
has switched to atomic_t, all new I/Os will fail to obtain
a new lun->lun_ref reference.
Also use an explicit percpu_ref_kill_and_confirm() callback
to block on ->lun_ref_comp to allow the first stage and
associated RCU grace period to complete, and then block on
->lun_ref_shutdown waiting for the final percpu_ref_put()
to drop the last reference via transport_lun_remove_cmd()
before continuing with core_tpg_remove_lun() shutdown.
Reported-by: Rob Millner <rlm@daterainc.com>
Tested-by: Rob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Tested-by: Vaibhav Tandon <vst@datera.io>
Cc: Vaibhav Tandon <vst@datera.io>
Tested-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a long standing bug where the commit phase
of COMPARE_AND_WRITE would result in a se_cmd->cmd_kref reference
leak if se_cmd->scsi_status returned non SAM_STAT_GOOD.
This would manifest first as a lost SCSI response, and eventual
hung task during fabric driver logout or re-login, as existing
shutdown logic waited for the COMPARE_AND_WRITE se_cmd->cmd_kref
to reach zero.
To address this bug, compare_and_write_post() has been changed
to drop the incorrect !cmd->scsi_status conditional that was
preventing *post_ret = 1 for being set during non SAM_STAT_GOOD
status.
This patch has been tested with SAM_STAT_CHECK_CONDITION status
from normal target_complete_cmd() callback path, as well as the
incoming __target_execute_cmd() submission failure path when
se_cmd->execute_cmd() returns non zero status.
Reported-by: Donald White <dew@datera.io>
Cc: Donald White <dew@datera.io>
Tested-by: Gary Guo <ghg@datera.io>
Cc: Gary Guo <ghg@datera.io>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: <stable@vger.kernel.org> # v3.12+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a long-standing bug with multi-session
(eg: iscsi-target + iser-target) se_node_acl dynamic free
withini transport_deregister_session().
This bug is caused when a storage endpoint is configured with
demo-mode (generate_node_acls = 1 + cache_dynamic_acls = 1)
initiators, and initiator login creates a new dynamic node acl
and attaches two sessions to it.
After that, demo-mode for the storage instance is disabled via
configfs (generate_node_acls = 0 + cache_dynamic_acls = 0) and
the existing dynamic acl is never converted to an explicit ACL.
The end result is dynamic acl resources are released twice when
the sessions are shutdown in transport_deregister_session().
If the storage instance is not changed to disable demo-mode,
or the dynamic acl is converted to an explict ACL, or there
is only a single session associated with the dynamic ACL,
the bug is not triggered.
To address this big, move the release of dynamic se_node_acl
memory into target_complete_nacl() so it's only freed once
when se_node_acl->acl_kref reaches zero.
(Drop unnecessary list_del_init usage - HCH)
Reported-by: Rob Millner <rlm@daterainc.com>
Tested-by: Rob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Cc: stable@vger.kernel.org # 4.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a bug where incoming task management requests
can be explicitly aborted during an active LUN_RESET, but who's
struct work_struct are canceled in-flight before execution.
This occurs when core_tmr_drain_tmr_list() invokes cancel_work_sync()
for the incoming se_tmr_req->task_cmd->work, resulting in cmd->work
for target_tmr_work() never getting invoked and the aborted TMR
waiting indefinately within transport_wait_for_tasks().
To address this case, perform a CMD_T_ABORTED check early in
transport_generic_handle_tmr(), and invoke the normal path via
transport_cmd_check_stop_to_fabric() to complete any TMR kthreads
blocked waiting for CMD_T_STOP in transport_wait_for_tasks().
Also, move the TRANSPORT_ISTATE_PROCESSING assignment earlier
into transport_generic_handle_tmr() so the existing check in
core_tmr_drain_tmr_list() avoids attempting abort the incoming
se_tmr_req->task_cmd->work if it has already been queued into
se_device->tmr_wq.
Reported-by: Rob Millner <rlm@daterainc.com>
Tested-by: Rob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch adds the missing target_complete_cmd() SCSI status
parameter change in target_xcopy_do_work(), that was originally
missing in commit 926317de33.
It correctly propigates up the correct SCSI status during
EXTENDED_COPY exception cases, instead of always using the
hardcoded SAM_STAT_CHECK_CONDITION from original code.
This is required for ESX host environments that expect to
hit SAM_STAT_RESERVATION_CONFLICT for certain scenarios,
and SAM_STAT_CHECK_CONDITION results in non-retriable
status for these cases.
Reported-by: Nixon Vincent <nixon.vincent@calsoftinc.com>
Tested-by: Nixon Vincent <nixon.vincent@calsoftinc.com>
Cc: Nixon Vincent <nixon.vincent@calsoftinc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
After the v4.2+ RCU conversion to se_node_acl->lun_entry_hlist,
a BUG_ON() was added in core_enable_device_list_for_node() to
detect when the located orig->se_lun_acl contains an existing
se_lun_acl pointer reference.
However, this scenario can happen when a dynamically generated
NodeACL is being converted to an explicit NodeACL, when the
explicit NodeACL contains a different LUN mapping than the
default provided by the WWN endpoint.
So instead of triggering BUG_ON(), go ahead and fail instead
following the original pre RCU conversion logic.
Reported-by: Benjamin ESTRABAUD <ben.estrabaud@mpstor.com>
Cc: Benjamin ESTRABAUD <ben.estrabaud@mpstor.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org # 4.2+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This reverts commit c1ccbfe031.
Reverting this patch, as it incorrectly assumes the additional length
for INQUIRY in target_complete_cmd_with_length() is SCSI allocation
length, which breaks existing user-space code when SCSI allocation
length is smaller than additional length.
root@scsi-mq:~# sg_inq --len=4 -vvvv /dev/sdb
found bsg_major=253
open /dev/sdb with flags=0x800
inquiry cdb: 12 00 00 00 04 00
duration=0 ms
inquiry: pass-through requested 4 bytes (data-in) but got -28 bytes
inquiry: pass-through can't get negative bytes, say it got none
inquiry: got too few bytes (0)
INQUIRY resid (32) should never exceed requested len=4
inquiry: failed requesting 4 byte response: Malformed response to
SCSI command [resid=32]
AFAICT the original change was not to address a specific host issue,
so go ahead and revert to original logic for now.
Cc: Douglas Gilbert <dgilbert@interlog.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Sumit Rai <sumitrai96@gmail.com>
Cc: stable@vger.kernel.org # 4.8+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a bug where EXTENDED_COPY across multiple LUNs
results in a CHECK_CONDITION when the source + destination are not
located on the same physical node.
ESX Host environments expect sense COPY_ABORTED w/ COPY TARGET DEVICE
NOT REACHABLE to be returned when this occurs, in order to signal
fallback to local copy method.
As described in section 6.3.3 of spc4r22:
"If it is not possible to complete processing of a segment because the
copy manager is unable to establish communications with a copy target
device, because the copy target device does not respond to INQUIRY,
or because the data returned in response to INQUIRY indicates
an unsupported logical unit, then the EXTENDED COPY command shall be
terminated with CHECK CONDITION status, with the sense key set to
COPY ABORTED, and the additional sense code set to COPY TARGET DEVICE
NOT REACHABLE."
Tested on v4.1.y with ESX v5.5u2+ with BlockCopy across multiple nodes.
Reported-by: Nixon Vincent <nixon.vincent@calsoftinc.com>
Tested-by: Nixon Vincent <nixon.vincent@calsoftinc.com>
Cc: Nixon Vincent <nixon.vincent@calsoftinc.com>
Tested-by: Dinesh Israni <ddi@datera.io>
Signed-off-by: Dinesh Israni <ddi@datera.io>
Cc: Dinesh Israni <ddi@datera.io>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a regression in >= v4.1.y code where the original
SCF_ACK_KREF assignment in target_get_sess_cmd() was dropped upstream
in commit 054922bb, but the series for addressing TMR ABORT_TASK +
LUN_RESET with fabric session reinstatement in commit febe562c20 still
depends on this code in transport_cmd_finish_abort().
The regression manifests itself as a se_cmd->cmd_kref +1 leak, where
ABORT_TASK + LUN_RESET can hang indefinately for a specific I_T session
for drivers using SCF_ACK_KREF, resulting in hung kthreads.
This patch has been verified with v4.1.y code.
Reported-by: Vaibhav Tandon <vst@datera.io>
Tested-by: Vaibhav Tandon <vst@datera.io>
Cc: Vaibhav Tandon <vst@datera.io>
Cc: stable@vger.kernel.org # 4.1+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
If a Simple command is sent with a failure, target_setup_cmd_from_cdb
returns with TCM_UNSUPPORTED_SCSI_OPCODE or TCM_INVALID_CDB_FIELD.
So in the cases where target_setup_cmd_from_cdb returns an error, we
never get far enough to call target_execute_cmd to increment simple_cmds.
Since simple_cmds isn't incremented, the result of the failure from
target_setup_cmd_from_cdb causes transport_generic_request_failure to
decrement simple_cmds, due to call to transport_complete_task_attr.
With this dev->simple_cmds or dev->dev_ordered_sync is now -1, not 0.
So when a subsequent command with an Ordered Task is sent, it causes
a hang, since dev->simple_cmds is at -1.
Tested-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Signed-off-by: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org # 4.4+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
If a command with a Simple task attribute is failed due to a Unit
Attention, then a subsequent command with an Ordered task attribute
will hang forever. The reason for this is that the Unit Attention
status is checked for in target_setup_cmd_from_cdb, before the call
to target_execute_cmd, which calls target_handle_task_attr, which
in turn increments dev->simple_cmds.
However, transport_generic_request_failure still calls
transport_complete_task_attr, which will decrement dev->simple_cmds.
In this case, simple_cmds is now -1. So when a command with the
Ordered task attribute is sent, target_handle_task_attr sees that
dev->simple_cmds is not 0, so it decides it can't execute the
command until all the (nonexistent) Simple commands have completed.
Reported-by: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Tested-by: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Reported-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org # 4.4+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a race in iscsit_release_commands_from_conn() ->
iscsit_free_cmd() -> transport_generic_free_cmd() + wait_for_tasks=1,
where CMD_T_FABRIC_STOP could end up being set after the final
kref_put() is called from core_tmr_abort_task() context.
This results in transport_generic_free_cmd() blocking indefinately
on se_cmd->cmd_wait_comp, because the target_release_cmd_kref()
check for CMD_T_FABRIC_STOP returns false.
To address this bug, make iscsit_release_commands_from_conn()
do list_splice and set CMD_T_FABRIC_STOP early while holding
iscsi_conn->cmd_lock. Also make iscsit_aborted_task() only
remove iscsi_cmd_t if CMD_T_FABRIC_STOP has not already been
set.
Finally in target_release_cmd_kref(), only honor fabric_stop
if CMD_T_ABORTED has been set.
Cc: Mike Christie <mchristi@redhat.com>
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org # 3.14+
Tested-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
During transport_generic_free_cmd() with a concurrent TMR
ABORT_TASK and shutdown CMD_T_FABRIC_STOP bit set, the
caller will be blocked on se_cmd->cmd_wait_stop completion
until the final kref_put() -> target_release_cmd_kref()
has been invoked to call complete().
However, when ABORT_TASK is completed with FUNCTION_COMPLETE
in core_tmr_abort_task(), the aborted se_cmd will have already
been removed from se_sess->sess_cmd_list via list_del_init().
This results in target_release_cmd_kref() hitting the
legacy list_empty() == true check, invoking ->release_cmd()
but skipping complete() to wakeup se_cmd->cmd_wait_stop
blocked earlier in transport_generic_free_cmd() code.
To address this bug, it's safe to go ahead and drop the
original list_empty() check so that fabric_stop invokes
the complete() as expected, since list_del_init() can
safely be used on a empty list.
Cc: Mike Christie <mchristi@redhat.com>
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org # 3.14+
Tested-by: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
While doing recent bring-up of nvme/host with target-core T10-PI,
I noticed /sys/block/nvme*/integrity/device_is_integrity_capable
was false, and /sys/block/nvme*/integrity/tag_size contained
a bogus value.
AFAICT outside of blk_integrity_compare() for DM + MD these
are informational values, but go ahead and add the missing
assignments for nvme/host to match what SCSI does within
sd_dif_config_host() for consistency's sake.
Cc: Keith Busch <keith.busch@intel.com>
Cc: Jay Freyensee <james.p.freyensee@intel.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Sagi Grimberg <sagig@grimberg.me>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Reviewed-by: Sagi Grimberg <sagi at grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
There is a iscsi-target/tcp login race in LOGIN_FLAGS_READY
state assignment that can result in frequent errors during
iscsi discovery:
"iSCSI Login negotiation failed."
To address this bug, move the initial LOGIN_FLAGS_READY
assignment ahead of iscsi_target_do_login() when handling
the initial iscsi_target_start_negotiation() request PDU
during connection login.
As iscsi_target_do_login_rx() work_struct callback is
clearing LOGIN_FLAGS_READ_ACTIVE after subsequent calls
to iscsi_target_do_login(), the early sk_data_ready
ahead of the first iscsi_target_do_login() expects
LOGIN_FLAGS_READY to also be set for the initial
login request PDU.
As reported by Maged, this was first obsered using an
MSFT initiator running across multiple VMWare host
virtual machines with iscsi-target/tcp.
Reported-by: Maged Mokhtar <mmokhtar@binarykinetics.com>
Tested-by: Maged Mokhtar <mmokhtar@binarykinetics.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Instead of having cxgbit use type ISCSI_HW_OFFLOAD + 'hw_offload'
tpg_np attribute, it should be using it's own driver specific
type + attribute
Cc: Varun Prakash <varun@chelsio.com>
Cc: Hariprasad Shenai <hariprasad@chelsio.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Instead of special casing the handful of callers that check for
iser-target rdma verbs specific shutdown, use a simple flag at
iscsit_transport->rdma_shutdown so each driver can signal this.
Also, update iscsi-target/tcp + cxgbit to rdma_shutdown = false.
Cc: Varun Prakash <varun@chelsio.com>
Cc: Hariprasad Shenai <hariprasad@chelsio.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Go ahead and fold the duplicate iscsi_tpg_np driver attribute
show/store functions into generic callers, invoked by current
driver specific functions.
This allows for future v4.8+ changes to have iscsi_target_mod
use tpg_np driver attributes at runtime, instead of having
the defaults hardcoded in iscsi_target_configfs.c.
Also, drop the unused/legacy 'sctp' attribute for non standard
RFC-3720 operation with IPPROTO_SCTP.
Cc: Varun Prakash <varun@chelsio.com>
Cc: Hariprasad Shenai <hariprasad@chelsio.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch modifies existing transport_complete_*() code
to avoid invoking target_core_fabric_ops->queue_data_in()
driver callbacks for I/O READs with non-GOOD SAM status.
Some initiators expect GOOD status when a DATA-IN payload
transfer is involved, so to be safe go ahead and always
invoke target_core_fabric_ops->queue_status() to generate
fabric responses instead.
Note this is a prerequisite for IBLOCK supporting retriable
status, so SAM_STAT_BUSY + SAM_STAT_TASK_SET_FULL always
generates fabric driver responses instead of initiating
DataIN payload transfer when non-GOOD status is present
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Fix the following printk size_t warning as per 0-day build:
All warnings (new ones prefixed by >>):
drivers/target/target_core_user.c: In function 'is_ring_space_avail':
>> drivers/target/target_core_user.c:385:12: warning: format '%lu'
>> expects argument of type 'long unsigned int', but argument 3 has type
>> 'size_t {aka unsigned int}' [-Wformat=]
pr_debug("no data space: only %lu available, but ask for %lu\n",
^
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts ib_srpt to use existing percpu_ida tag
pre-allocation for struct srpt_send_ioctx.
This allows ib_srpt to drop it's internal pre-allocation
mechanisms with the extra spin_lock_irqsave, and use
percpu_ida common code for doing this.
Cc: Vu Pham <vu@mellanox.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts tcm_fc to modern TARGET_SCF_ACK_KREF
usage for ft_queue_status(), and fixes ft_check_stop_free()
to return transport_generic_free_cmd() for ->cmd_kref.
It also converts TM request -> ft_send_tm() to use ACK_KREF,
and update ft_queue_tm_resp() to drop the outstanding kref
after queueing TM response into fabric code.
Cc: Vasu Dev <vasu.dev@linux.intel.com>
Cc: Mark Rustad <mark.d.rustad@intel.com>
Cc: Robert Love <robert.w.love@intel.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts xen-scsiback to modern TARGET_SCF_ACK_KREF
usage for scsiback_cmd_done() callback path.
It also also converts TMR -> scsiback_device_action() to use
modern target_submit_tmr() code.
Acked-by: Juergen Gross <jgross@suse.com>
Tested-by: Juergen Gross <jgross@suse.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts xen-scsiback to use percpu_ida tag
pre-allocation for struct vscsibk_pend descriptor, in
order to avoid fast-path struct vscsibk_pend memory
allocations.
Note by default this is currently hardcoded to 128.
(Add wrapper for handling pending_req tag failure - Juergen)
(Drop left-over se_cmd memset in scsiback_cmd_exec - Juergen)
Acked-by: Juergen Gross <jgross@suse.com>
Tested-by: Juergen Gross <jgross@suse.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts usb-gadget target to use percpu_ida tag
pre-allocation for struct usbg_cmd descriptor, in order to
avoid fast-path struct usbg_cmd memory allocations.
Note by default this is currently hardcoded to 128.
Tested-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts sbp-target to modern TARGET_SCF_ACK_KREF
usage for sbp_send_status() callback path, and drops the now
obsolete sbp_free_request() failure path calls.
Acked-by: Chris Boot <bootc@bootc.net>
Tested-by: Chris Boot <bootc@bootc.net>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts sbp-target to use struct sbp_target_request
descriptor tag pre-allocation using percpu_ida.
(Fix sbp_mgt_get_req() IS_ERR failure checking - Dan Carpenter)
(Add missing sbp_target_request tag memset - Chris Boot)
Acked-by: Chris Boot <bootc@bootc.net>
Tested-by: Chris Boot <bootc@bootc.net>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts vhost/scsi pre-allocation of vhost_scsi_cmd
descriptors to use the new alloc_session callback().
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a recent ABORT_TASK regression associated
with commit febe562c, where a left-over target_put_sess_cmd()
would still be called when __target_check_io_state() detected
a command has already been completed, and explicit ABORT must
be avoided.
Note commit febe562c dropped the local kref_get_unless_zero()
check in core_tmr_abort_task(), but did not drop this extra
corresponding target_put_sess_cmd() in the failure path.
So go ahead and drop this now bogus target_put_sess_cmd(),
and avoid this potential use-after-free.
Reported-by: Dan Lane <dracodan@gmail.com>
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Based on HCH's original patch, this adds a full version to
support percpu-ida tag pre-allocation and callback function
pointer into fabric driver code to complete session setup.
Reported-by: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes an incorrect return of zero from the new
unmap_zeroes_data_store() configfs store attribute handler
introduced in v4.5-rc1, to use the correct 'count' bytes
return value.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a race between setting of SCF_SEND_DELAYED_TAS
in transport_send_task_abort(), and check of the same bit in
transport_check_aborted_status().
It adds a __transport_check_aborted_status() version that is
used by target_execute_cmd() when se_cmd->t_state_lock is
held, and a transport_check_aborted_status() wrapper for
all other existing callers.
Also, it handles the case where the check happens before
transport_send_task_abort() gets called. For this, go
ahead and set SCF_SEND_DELAYED_TAS early when necessary,
and have transport_send_task_abort() send the abort.
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
To address the bug where fabric driver level shutdown
of se_cmd occurs at the same time when TMR CMD_T_ABORTED
is happening resulting in a -1 ->cmd_kref, this patch
adds a CMD_T_FABRIC_STOP bit that is used to determine
when TMR + driver I_T nexus shutdown is happening
concurrently.
It changes target_sess_cmd_list_set_waiting() to obtain
se_cmd->cmd_kref + set CMD_T_FABRIC_STOP, and drop local
reference in target_wait_for_sess_cmds() and invoke extra
target_put_sess_cmd() during Task Aborted Status (TAS)
when necessary.
Also, it adds a new target_wait_free_cmd() wrapper around
transport_wait_for_tasks() for the special case within
transport_generic_free_cmd() to set CMD_T_FABRIC_STOP,
and is now aware of CMD_T_ABORTED + CMD_T_TAS status
bits to know when an extra transport_put_cmd() during
TAS is required.
Note transport_generic_free_cmd() is expected to block on
cmd->cmd_wait_comp in order to follow what iscsi-target
expects during iscsi_conn context se_cmd shutdown.
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@daterainc.com>
This patch fixes a bug in TMR task aborted status (TAS)
handling when multiple sessions are connected to the
same target WWPN endpoint and se_node_acl descriptor,
resulting in TASK_ABORTED status to not be generated
for aborted se_cmds on the remote port.
This is due to core_tmr_handle_tas_abort() incorrectly
comparing se_node_acl instead of se_session, for which
the multi-session case is expected to be sharing the
same se_node_acl.
Instead, go ahead and update core_tmr_handle_tas_abort()
to compare tmr_sess + cmd->se_sess in order to determine
if the LUN_RESET was received on a different I_T nexus,
and TASK_ABORTED status response needs to be generated.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a NULL pointer se_cmd->cmd_kref < 0
refcount bug during TMR LUN_RESET with active TMRs,
triggered during se_cmd + se_tmr_req descriptor
shutdown + release via core_tmr_drain_tmr_list().
To address this bug, go ahead and obtain a local
kref_get_unless_zero(&se_cmd->cmd_kref) for active I/O
to set CMD_T_ABORTED, and transport_wait_for_tasks()
followed by the final target_put_sess_cmd() to drop
the local ->cmd_kref.
Also add two new checks within target_tmr_work() to
avoid CMD_T_ABORTED -> TFO->queue_tm_rsp() callbacks
ahead of invoking the backend -> fabric put in
transport_cmd_check_stop_to_fabric().
For good measure, also change core_tmr_release_req()
to use list_del_init() ahead of se_tmr_req memory
free.
Reviewed-by: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a NULL pointer se_cmd->cmd_kref < 0
refcount bug during TMR LUN_RESET with active se_cmd
I/O, that can be triggered during se_cmd descriptor
shutdown + release via core_tmr_drain_state_list() code.
To address this bug, add common __target_check_io_state()
helper for ABORT_TASK + LUN_RESET w/ CMD_T_COMPLETE
checking, and set CMD_T_ABORTED + obtain ->cmd_kref for
both cases ahead of last target_put_sess_cmd() after
TFO->aborted_task() -> transport_cmd_finish_abort()
callback has completed.
It also introduces SCF_ACK_KREF to determine when
transport_cmd_finish_abort() needs to drop the second
extra reference, ahead of calling target_put_sess_cmd()
for the final kref_put(&se_cmd->cmd_kref).
It also updates transport_cmd_check_stop() to avoid
holding se_cmd->t_state_lock while dropping se_cmd
device state via target_remove_from_state_list(), now
that core_tmr_drain_state_list() is holding the
se_device lock while checking se_cmd state from
within TMR logic.
Finally, move transport_put_cmd() release of SGL +
TMR + extended CDB memory into target_free_cmd_mem()
in order to avoid potential resource leaks in TMR
ABORT_TASK + LUN_RESET code-paths. Also update
target_release_cmd_kref() accordingly.
Reviewed-by: Quinn Tran <quinn.tran@qlogic.com>
Cc: Himanshu Madhani <himanshu.madhani@qlogic.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a long standing race where obtaining
se_node_acl->acl_kref in __transport_register_session()
happens a bit too late, and leaves open the potential
for core_tpg_del_initiator_node_acl() to hit a NULL
pointer dereference.
Instead, take ->acl_kref in core_tpg_get_initiator_node_acl()
while se_portal_group->acl_node_mutex is held, and move the
final target_put_nacl() from transport_deregister_session()
into transport_free_session() so that fabric driver login
failure handling using the modern method to still work
as expected.
Also, update core_tpg_get_initiator_node_acl() to take
an extra reference for dynamically generated acls for
demo-mode, before returning to fabric caller. Also
update iscsi-target sendtargets special case handling
to use target_tpg_has_node_acl() when checking if
demo_mode_discovery == true during discovery lookup.
Note the existing wait_for_completion(&acl->acl_free_comp)
in core_tpg_del_initiator_node_acl() does not change.
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts core_tpg_set_initiator_node_queue_depth()
to use struct se_node_acl->acl_sess_list when performing
explicit se_tpg_tfo->shutdown_session() for active sessions,
in order for new se_node_acl->queue_depth to take effect.
This follows how core_tpg_del_initiator_node_acl() currently
works when invoking se_tpg_tfo->shutdown-session(), and ahead
of the next patch to take se_node_acl->acl_kref during lookup,
the extra get_initiator_node_acl() can go away. In order to
achieve this, go ahead and change target_get_session() to use
kref_get_unless_zero() and propigate up the return value
to know when a session is already being released.
This is because se_node_acl->acl_group is already protecting
se_node_acl->acl_group reference via configfs, and shutdown
within core_tpg_del_initiator_node_acl() won't occur until
sys_write() to core_tpg_set_initiator_node_queue_depth()
attribute returns back to user-space.
Also, drop the left-over iscsi-target hack, and obtain
se_portal_group->session_lock in lio_tpg_shutdown_session()
internally. Remove iscsi-target wrapper and unused se_tpg +
force parameters and associated code.
Reported-by: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch is a iscsi-target specific bug-fix for a dead-lock
that can occur during explicit struct se_node_acl->acl_group
se_session deletion via configfs rmdir(2), when iscsi-target
time2retain timer is still active.
It changes iscsi-target to obtain se_portal_group->session_lock
internally using spin_in_locked() to check for the specific
se_node_acl configfs shutdown rmdir(2) case.
Note this patch is intended for stable, and the subsequent
v4.5-rc patch converts target_core_tpg.c to use proper
se_sess->sess_kref reference counting for both se_node_acl
deletion + se_node_acl->queue_depth se_session restart.
Reported-by:: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch does a simple conversion of ib_srpt code to use
proper modern core_tpg_get_initiator_node_acl() lookup using
se_node_acl->acl_kref, and drops the legacy internal list
usage from srpt_lookup_acl().
This involves doing transport_init_session() earlier, and
making sure transport_free_session() is called during
a se_node_acl lookup failure to drop the last ->acl_kref.
Also, it adds a minor backwards-compat hack to avoid the
potential for user-space wrt node-acl WWPN formatting by
simply stripping off '0x' prefix from ch->sess_name, and
retrying once if core_tpg_get_initiator_node_acl() fails.
Finally, go ahead and drop port_acl_list port_acl_lock
since they are no longer used.
Cc: Vu Pham <vu@mellanox.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch does a simple conversion of tcm_fc code to use
proper modern core_tpg_get_initiator_node_acl() lookup using
se_node_acl->acl_kref, and drops the legacy list walk from
ft_acl_get().
Note the original lookup also took node_name into account,
but since ft_init_nodeacl() only ever sets port_name for
se_node_acl->acl_group within configfs, this is purely
a mechanical change.
As per HCH, go ahead and fold ft_acl_get() into original
caller.
Cc: Vasu Dev <vasu.dev@linux.intel.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Andy Grover <agrover@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
As reported by Dan, isert_create_device_ib_res() failure within
isert_device_get() can potentially return a postive value,
resulting in ERR_PTR() triggering a NULL pointer dereference.
Caught by the static checker:
drivers/infiniband/ulp/isert/ib_isert.c:423 isert_device_get()
error: passing non negative 1 to ERR_PTR
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Fix up tcm_usbg_tpg_store_enable() return value to propagate
usbg_attach() failure up to user-space if no HDC is found.
Reported-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch adds the missing tcm_usbg_drop_nexus() to properly
release tcm_usbg_nexus memory during typical ->fabric_drop_tpg()
callback shutdown.
Reported-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Avoid stripping off the 'naa.' I_T nexus prefix from configfs
attribute store input, so that user-space will get back what
it originaly wrote into ../usb_gadget/$WWPN/$TPGT/nexus.
Note the SCSI initiator WWPN is purely symbolic for UAS + BOT,
so it will not effect host side code.
Reported-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Signed-off-by: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a race + use after free where the first
stage of COMPARE_AND_WRITE in compare_and_write_callback()
is rescheduled after the backend sends the secondary WRITE,
resulting in second stage compare_and_write_post() callback
completing in target_complete_ok_work() before the first
can return.
Because current code depends on checking se_cmd->se_cmd_flags
after return from se_cmd->transport_complete_callback(),
this results in first stage having SCF_COMPARE_AND_WRITE_POST
set, which incorrectly falls through into second stage CAW
processing code, eventually triggering a NULL pointer
dereference due to use after free.
To address this bug, pass in a new *post_ret parameter into
se_cmd->transport_complete_callback(), and depend upon this
value instead of ->se_cmd_flags to determine when to return
or fall through into ->queue_status() code for CAW.
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # v3.12+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a case where iscsi_target_do_tx_login_io()
fails sending the last login response PDU, after the RX/TX
threads have already been started.
The case centers around iscsi_target_rx_thread() not invoking
allow_signal(SIGINT) before the send_sig(SIGINT, ...) occurs
from the failure path, resulting in RX thread hanging
indefinately on iscsi_conn->rx_login_comp.
Note this bug is a regression introduced by:
commit e54198657b
Author: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Wed Jul 22 23:14:19 2015 -0700
iscsi-target: Fix iscsit_start_kthreads failure OOPs
To address this bug, complete ->rx_login_complete for good
measure in the failure path, and immediately return from
RX thread context if connection state did not actually reach
full feature phase (TARG_CONN_STATE_LOGGED_IN).
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # v3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a v4.2+ regression introduced by commit c04a6091
that removed support for obsolete sync-and-steering markers usage
as originally defined in RFC-3720.
The regression would involve attempting to send OFMarker=No +
IFMarker=No keys during opertional negotiation login phase,
including when initiators did not actually propose these keys.
The result for MSFT iSCSI initiators would be random junk in
TCP stream after the last successful login request was been sent
signaling the move to full feature phase (FFP) operation.
To address this bug, go ahead and avoid negotiating these keys
by default unless the initiator explicitly proposes them, but
still respond to them with 'No' if they are proposed.
Reported-by: Dragan Milivojević <galileo@pkm-inc.com>
Bisected-by: Christophe Vu-Brugier <cvubrugier@fastmail.fm>
Tested-by: Christophe Vu-Brugier <cvubrugier@fastmail.fm>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch changes transport_lookup_cmd_lun() to obtain
se_lun->lun_ref + se_cmd->se_device rcu_dereference during
TCM_WRITE_PROTECT -> CHECK_CONDITION failure status.
Do this to ensure the active control D_SENSE mode page bit
is being honored.
Reported-by: Sagi Grimberg <sagig@mellanox.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch allows target_sense_desc_format() to be called without a
valid se_device pointer, which can occur during an early exception
ahead of transport_lookup_cmd_lun() setting up se_cmd->se_device.
This addresses a v4.3-rc1 specific NULL pointer dereference
regression introduced by commit 4e4937e8.
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch adds a DF_READ_ONLY flag that is used by IBLOCK to
signal when a backend has been set to read-only mode, in order
to propigate read-only status up to core_tpg_add_lun() for all
future LUN fabric exports.
With this is place, existing emulation for reporting read-only
in spc_emulate_modesense() and normal transport_lookup_cmd_lun()
TCM_WRITE_PROTECTED status checking just works as expected.
Reported-by: Joeue Deng <joeue404@gmail.com>
Reported-by: Andy Grover <agrover@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Nicholas Bellinger