__GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to
the page allocator.  This has been true but only for allocations
requests larger than PAGE_ALLOC_COSTLY_ORDER.  It has been always
ignored for smaller sizes.  This is a bit unfortunate because there is
no way to express the same semantic for those requests and they are
considered too important to fail so they might end up looping in the
page allocator for ever, similarly to GFP_NOFAIL requests.

Now that the whole tree has been cleaned up and accidental or misled
usage of __GFP_REPEAT flag has been removed for !costly requests we can
give the original flag a better name and more importantly a more useful
semantic.  Let's rename it to __GFP_RETRY_MAYFAIL which tells the user
that the allocator would try really hard but there is no promise of a
success.  This will work independent of the order and overrides the
default allocator behavior.  Page allocator users have several levels of
guarantee vs.  cost options (take GFP_KERNEL as an example)

 - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_
   attempt to free memory at all. The most light weight mode which even
   doesn't kick the background reclaim. Should be used carefully because
   it might deplete the memory and the next user might hit the more
   aggressive reclaim

 - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic
   allocation without any attempt to free memory from the current
   context but can wake kswapd to reclaim memory if the zone is below
   the low watermark. Can be used from either atomic contexts or when
   the request is a performance optimization and there is another
   fallback for a slow path.

 - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) -
   non sleeping allocation with an expensive fallback so it can access
   some portion of memory reserves. Usually used from interrupt/bh
   context with an expensive slow path fallback.

 - GFP_KERNEL - both background and direct reclaim are allowed and the
   _default_ page allocator behavior is used. That means that !costly
   allocation requests are basically nofail but there is no guarantee of
   that behavior so failures have to be checked properly by callers
   (e.g. OOM killer victim is allowed to fail currently).

 - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior
   and all allocation requests fail early rather than cause disruptive
   reclaim (one round of reclaim in this implementation). The OOM killer
   is not invoked.

 - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator
   behavior and all allocation requests try really hard. The request
   will fail if the reclaim cannot make any progress. The OOM killer
   won't be triggered.

 - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior
   and all allocation requests will loop endlessly until they succeed.
   This might be really dangerous especially for larger orders.

Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL
because they already had their semantic.  No new users are added.
__alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if
there is no progress and we have already passed the OOM point.

This means that all the reclaim opportunities have been exhausted except
the most disruptive one (the OOM killer) and a user defined fallback
behavior is more sensible than keep retrying in the page allocator.

[akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c]
[mhocko@suse.com: semantic fix]
  Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz
[mhocko@kernel.org: address other thing spotted by Vlastimil]
  Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Cc: Alex Belits <alex.belits@cavium.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: NeilBrown <neilb@suse.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.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: NBart Van Assche <bart.vanassche@sandisk.com>
Tested-by: NBart 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: NGary Guo <ghg@datera.io>
Tested-by: NChu Yuan Lin <cyl@datera.io>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

During v4.3 when the overflow/underflow check was relaxed by
commit c72c5250:

  commit c72c5250
  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: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Roland Dreier <roland@purestorage.com>
Cc: <stable@vger.kernel.org> # v4.3+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

A multiplication for the size determination of a memory allocation
indicated that an array data structure should be processed.
Thus use the corresponding function "kmalloc_array".

This issue was detected by using the Coccinelle software.
Signed-off-by: NMarkus Elfring <elfring@users.sourceforge.net>
Signed-off-by: NNicholas 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: NPotnuri Bharat Teja <bharat@chelsio.com>
Reviewed-by: NPotnuri Bharat Teja <bharat@chelsio.com>
Tested-by: NPotnuri Bharat Teja <bharat@chelsio.com>
Cc: Potnuri Bharat Teja <bharat@chelsio.com>
Reported-by: NSteve Wise <swise@opengridcomputing.com>
Cc: Steve Wise <swise@opengridcomputing.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: NNicholas 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: NNicholas 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: NRob Millner <rlm@daterainc.com>
Tested-by: NRob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Tested-by: NVaibhav Tandon <vst@datera.io>
Cc: Vaibhav Tandon <vst@datera.io>
Tested-by: NBryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

If a target driver (e.g. tcm_qla2xxx) calls
transport_generic_request_failure() to report that receiving data
has failed and that SCSI command has already been aborted by the
initiator, ensure that the SCSI status ABORTED is sent back to the
initiator instead of the sense code provided by the target driver.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The code that tests the CMD_T_DEV_ACTIVE flag has been removed. Hence
also remove the flag itself.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The patch that reworks task management function handling guarantees
that target_remove_from_state_list() is always called with CMD_T_BUSY
cleared. Since that function is the only function that tests that flag
this means that that flag is now superfluous. Hence remove that flag.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This patch does not change any functionality.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The function transport_cmd_check_stop() has two callers. These callers
invoke this function as follows:
* transport_cmd_check_stop(cmd, true, false)
* transport_cmd_check_stop(cmd, false, true)
Hence inline this function into its callers.

This patch does not change any functionality but improves source
code readability.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NBryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Enabling dynamic debug for the target_core_mod kernel module
causes the system log to be spammed with the "Incremented ..."
message. Hence remove it.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Stop execution if CMD_T_STOP has been set for a command just after
the command has been added to the device command list and before
.write_pending() is called. The following sequence can trigger this:
- transport_handle_cdb_direct() gets called. This function namely
  sets CMD_T_ACTIVE before it calls transport_generic_new_cmd().
- __transport_wait_for_tasks() is called concurrently. This function
  sets CMD_T_STOP for all active commands that have not been aborted.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

transport_wait_for_tasks() not only waits for command completion
but also sets CMD_T_STOP. Additionally, this function is not only
called by frontend drivers but also by the target core. Update
the transport_wait_for_tasks() documentation to reflect this.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Signed-off-by: NNicholas 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: NRob Millner <rlm@daterainc.com>
Tested-by: NRob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Cc: stable@vger.kernel.org # 4.1+
Signed-off-by: NNicholas 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: NRob Millner <rlm@daterainc.com>
Tested-by: NRob Millner <rlm@daterainc.com>
Cc: Rob Millner <rlm@daterainc.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

As defined in http://www.t10.org/lists/asc-num.htm. To be used during
validation of XCOPY target and segment descriptor lists.
Signed-off-by: NDavid Disseldorp <ddiss@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>

target_sess_cmd_list_waiting() might hit on a condition where
the kref for the command is already 0, but the destructor has
not been called yet (or is stuck in waiting for a spin lock).
Rather than leaving the command on the list we should explicitly
remove it to avoid race issues later on.
Signed-off-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This reverts commit c1ccbfe0.

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: NNicholas 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: NNixon Vincent <nixon.vincent@calsoftinc.com>
Tested-by: NNixon Vincent <nixon.vincent@calsoftinc.com>
Cc: Nixon Vincent <nixon.vincent@calsoftinc.com>
Tested-by: NDinesh Israni <ddi@datera.io>
Signed-off-by: NDinesh Israni <ddi@datera.io>
Cc: Dinesh Israni <ddi@datera.io>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: NNicholas 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 febe562c 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: NVaibhav Tandon <vst@datera.io>
Tested-by: NVaibhav Tandon <vst@datera.io>
Cc: Vaibhav Tandon <vst@datera.io>
Cc: stable@vger.kernel.org # 4.1+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This patch fixes residual overflow handling to correctly set the
residual_count using SPDTL, instead of SCSI Allocation Length.

Allocation Length is the maximum value of the SPDTL and not substitute
for it, hence it shouldn’t be used to calculate ResidualCount except for
cases where SPDTL > Allocation Length and Data is truncated (in that
case both Alloc Len and SPDTL are same). (SPC 5r01 Section 4.2.5.6).

Thanks to Ajay Nair in assisting with this patch.
Signed-off-by: NSumit Rai <sumitrai96@gmail.com>
Signed-off-by: NNicholas 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: NBryant G. Ly <bryantly@linux.vnet.ibm.com>
Signed-off-by: NBryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: NMichael Cyr <mikecyr@linux.vnet.ibm.com>
Signed-off-by: NMichael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org # 4.4+
Signed-off-by: NNicholas 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: NMichael Cyr <mikecyr@linux.vnet.ibm.com>
Tested-by: NMichael Cyr <mikecyr@linux.vnet.ibm.com>
Reported-by: NBryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: NBryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org # 4.4+
Signed-off-by: NNicholas 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: NNicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: NNicholas 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: NNicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The SRP target driver will need to allocate and chain it's own SGLs soon.
For this export target_alloc_sgl, and add a new argument to it so that it
can allocate an additional chain entry that doesn't point to a page.  Also
export transport_free_sgl after renaming it to target_free_sgl to free
these SGLs again.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NBart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Both of them are unused now that drivers handle any delayed session
shutdown internally.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Ensure we can use list_empty on the sess_acl_list to remove the need for
this flag.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This patch fixes an active I/O shutdown bug for fabric
drivers using target_wait_for_sess_cmds(), where se_cmd
descriptor shutdown would result in hung tasks waiting
indefinitely for se_cmd->cmd_wait_comp to complete().

To address this bug, drop the incorrect list_del_init()
usage in target_wait_for_sess_cmds() and always complete()
during se_cmd target_release_cmd_kref() put, in order to
let caller invoke the final fabric release callback
into se_cmd->se_tfo->release_cmd() code.
Reported-by: NHimanshu Madhani <himanshu.madhani@qlogic.com>
Tested-by: NHimanshu Madhani <himanshu.madhani@qlogic.com>
Signed-off-by: NHimanshu Madhani <himanshu.madhani@qlogic.com>
Cc: stable@vger.kernel.org
Signed-off-by: NNicholas 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: NChristoph 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: NNicholas 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: NChristoph 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: NNicholas Bellinger <nab@linux-iscsi.org>

Signed-off-by: NQuinn Tran <quinn.tran@qlogic.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NBart Van Assche <bart.vanassche@sandisk.com>
Fixes: fb3269ba ("qla2xxx: Add selective command queuing")
Signed-off-by: NHimanshu Madhani <himanshu.madhani@qlogic.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

With CMD_T_FABRIC_STOP + se_cmd->cmd_wait_set usage in place,
go ahead and drop left-over CMD_T_REQUEST_STOP checks in
target_complete_cmd() and unused target_stop_cmd().
Reviewed-by: NChristoph 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>
Signed-off-by: NNicholas 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: NNicholas 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: NNicholas Bellinger <nab@daterainc.com>

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: NQuinn 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: NNicholas 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: NQuinn 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: NNicholas Bellinger <nab@linux-iscsi.org>