This patch bumps the default number of tags allocated per session by
iscsi-target via transport_alloc_session_tags() -> percpu_ida_init()
by another (tag_num / 2).
This is done to take into account the tags waiting to be acknowledged
and released in iscsit_ack_from_expstatsn(), but who's number are not
directly limited by the CmdSN Window queue_depth being enforced by
the target.
Using a larger value here is also useful to prevent percpu_ida_alloc()
from having to steal tags from other CPUs when no tags are available
on the local CPU, while waiting for unacknowledged tags to be released.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts iscsit_ack_from_expstatsn() to populate a local
ack_list of commands, and call iscsit_free_cmd() directly from RX
thread context, instead of using iscsit_add_cmd_to_immediate_queue()
to queue the acknowledged commands to be released from TX thread
context.
It is helpful to release the acknowledge commands as quickly as
possible, along with the associated percpu_ida tags, in order to
prevent percpu_ida_alloc() from having to steal tags from other
CPUs while waiting for iscsit_free_cmd() to happen from TX thread
context.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch changes transport_generic_free_cmd() to only wait_for_tasks
when shutdown=true is passed to iscsit_free_cmd().
With the advent of >= v3.10 iscsi-target code using se_cmd->cmd_kref,
the extra wait_for_tasks with shutdown=false is unnecessary, and may
end up causing an extra context switch when releasing WRITEs.
Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a bug for backends such as IBLOCK that perform
asynchronous completion via transport_complete_cmd(), that will call
target_complete_failure_work() -> transport_generic_request_failure(),
upon exception status and invoke cmd->transport_complete_callback()
-> compare_and_write_callback() incorrectly during the failure case.
It adds a check for a non zero se_cmd->scsi_status within the first
invocation of compare_and_write_callback(), and will jump to out plus
up se_device->caw_sem before exiting the callback.
Reported-by: Thomas Glanzmann <thomas@glanzmann.de>
Tested-by: Thomas Glanzmann <thomas@glanzmann.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses a bug when compare_and_write_callback() invoked from
target_complete_ok_work() hits an failure from __target_execute_cmd() ->
cmd->execute_cmd(), that ends up calling transport_generic_request_failure()
-> compare_and_write_post(), thus causing SCF_COMPARE_AND_WRITE_POST to
incorrectly be set.
The result of this bug is that target_complete_ok_work() no longer hits
the if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST) check
that forces an immediate return, and instead double completes the se_cmd
in question, triggering an OOPs in the process.
This patch changes compare_and_write_post() to only set this bit when a
failure has not already occured to ensure the immediate return from within
target_complete_ok_work(), and thus allow transport_generic_request_failure()
to handle the sending of the CHECK_CONDITION exception status.
Reported-by: Thomas Glanzmann <thomas@glanzmann.de>
Tested-by: Thomas Glanzmann <thomas@glanzmann.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch resets se_cmd->data_length for COMPARE_AND_WRITE emulation
within sbc_compare_and_write() to NoLB * block_size in order to address
a bug with FILEIO backends where a I/O failure will occur when data_length
does not match the I/O size being actually dispatched for the individual
per block READs + WRITEs.
This is done late enough in sbc_compare_and_write() after the memory
allocations have occured in transport_generic_new_cmd() to not cause
any unwanted side-effects.
Reported-by: Thomas Glanzmann <thomas@glanzmann.de>
Tested-by: Thomas Glanzmann <thomas@glanzmann.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch changes transport_alloc_session_tags() to fall back to
use vzalloc when kzalloc fails for big tag_num that end up generating
larger order allocations.
Also use is_vmalloc_addr() in transport_alloc_session_tags() failure
path, and normal transport_free_session() path to determine when
vfree() needs to be called instead of kfree().
v2 changes:
- Use __GFP_NOWARN | __GFP_REPEAT for sess_cmd_map kzalloc (mst)
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Asias He <asias@redhat.com>
Cc: Kent Overstreet <kmo@daterainc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Pull SCSI target updates from Nicholas Bellinger:
"Lots of activity again this round for I/O performance optimizations
(per-cpu IDA pre-allocation for vhost + iscsi/target), and the
addition of new fabric independent features to target-core
(COMPARE_AND_WRITE + EXTENDED_COPY).
The main highlights include:
- Support for iscsi-target login multiplexing across individual
network portals
- Generic Per-cpu IDA logic (kent + akpm + clameter)
- Conversion of vhost to use per-cpu IDA pre-allocation for
descriptors, SGLs and userspace page pointer list
- Conversion of iscsi-target + iser-target to use per-cpu IDA
pre-allocation for descriptors
- Add support for generic COMPARE_AND_WRITE (AtomicTestandSet)
emulation for virtual backend drivers
- Add support for generic EXTENDED_COPY (CopyOffload) emulation for
virtual backend drivers.
- Add support for fast memory registration mode to iser-target (Vu)
The patches to add COMPARE_AND_WRITE and EXTENDED_COPY support are of
particular significance, which make us the first and only open source
target to support the full set of VAAI primitives.
Currently Linux clients are lacking upstream support to actually
utilize these primitives. However, with server side support now in
place for folks like MKP + ZAB working on the client, this logic once
reserved for the highest end of storage arrays, can now be run in VMs
on their laptops"
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (50 commits)
target/iscsi: Bump versions to v4.1.0
target: Update copyright ownership/year information to 2013
iscsi-target: Bump default TCP listen backlog to 256
target: Fix >= v3.9+ regression in PR APTPL + ALUA metadata write-out
iscsi-target; Bump default CmdSN Depth to 64
iscsi-target: Remove unnecessary wait_for_completion in iscsi_get_thread_set
iscsi-target: Add thread_set->ts_activate_sem + use common deallocate
iscsi-target: Fix race with thread_pre_handler flush_signals + ISCSI_THREAD_SET_DIE
target: remove unused including <linux/version.h>
iser-target: introduce fast memory registration mode (FRWR)
iser-target: generalize rdma memory registration and cleanup
iser-target: move rdma wr processing to a shared function
target: Enable global EXTENDED_COPY setup/release
target: Add Third Party Copy (3PC) bit in INQUIRY response
target: Enable EXTENDED_COPY setup in spc_parse_cdb
target: Add support for EXTENDED_COPY copy offload emulation
target: Avoid non-existent tg_pt_gp_mem in target_alua_state_check
target: Add global device list for EXTENDED_COPY
target: Make helpers non static for EXTENDED_COPY command setup
target: Make spc_parse_naa_6h_vendor_specific non static
...
Update copyright ownership/year information for target-core,
loopback, iscsi-target, tcm_qla2xx, vhost and iser-target.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch bumps the default TCP listen backlog within iscsit_setup_np()
from 5 to 256, in order to reduce the overall latency caused by a small
backlog with 100's of simultaneous login attempts directed to the same
single network portal.
Also add a ISCSIT_TCP_BACKLOG macro in iscsi_target_core.h.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes a >= v3.9+ regression in __core_scsi3_write_aptpl_to_file()
+ core_alua_write_tpg_metadata() write-out, where a return value of -EIO was
incorrectly being returned upon success.
This bug was originally introduced in:
commit 0e9b10a90f
Author: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat Feb 23 15:22:43 2013 -0500
target: writev() on single-element vector is pointless
However, given that the return of core_scsi3_update_and_write_aptpl()
was not used to determine if a command should be returned with non GOOD
status, this bug was not being triggered in PR logic until v3.11-rc1 by
commit:
commit 459f213ba1
Author: Andy Grover <agrover@redhat.com>
Date: Thu May 16 10:41:02 2013 -0700
target: Allocate aptpl_buf inside update_and_write_aptpl()
So, go ahead and only return -EIO if kernel_write() returned a
negative value.
Reported-by: Gera Kazakov <gkazakov@msn.com>
Signed-off-by: Gera Kazakov <gkazakov@msn.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Grover <agrover@redhat.com>
Cc: stable@vger.kernel.org # 3.9+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch bumps the default TA_DEFAULT_CMDSN_DEPTH from 16 -> 64,
which is closer to a sane default for larger pipes @ 10 Gb/sec
with traditional iSCSI, or @ 40/56 Gb/sec Ethernet/Infiniband with
iSCSI Extentions for RDMA.
There is really no downside to increasing this default value for
1 Gb/sec.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch removes an unnecessary wait_for_completion within
iscsi_get_thread_set(), that would wait for 1 second before
trying to obtain an inactive struct iscsi_thread_set from
iscsi_get_ts_from_inactive_list().
Since iscsi_allocate_thread_sets() will already be adding the
newly allocated iscsi_thread_set to the inactive list directly,
there is no need to wait here.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch removes the iscsi_thread_set->[rx,tx]_post_start_comp that
was originally used synchronize startup between rx and tx threads within
a single thread_set.
Instead, use a single ->ts_activate_sem in iscsi_activate_thread_set()
to wait for both processes to awake in the RX/TX pre handlers.
Also, go ahead and refactor thread_set deallocate code into a common
iscsi_deallocate_thread_one(), and update iscsi_deallocate_thread_sets()
and iscsi_deallocate_extra_thread_sets() use this code
v3 changes:
- Make iscsi_deallocate_thread_one defined as static (Fengguang)
v2 changes:
- Set ISCSI_THREAD_SET_ACTIVE before calling complete in
iscsi_activate_thread_set
- Protect ts->conn sanity checks with ->ts_state_lock in
RX/TX pre handlers
- Add ->ts_activate_sem to save extra context switches per
iscsi_activate_thread_set() call.
- Refactor thread_set shutdown into iscsi_deallocate_thread_one()
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses an long standing race in iscsi_[rx,tx]_thread_pre_handler()
use of flush_signals(), and between iscsi_deallocate_extra_thread_sets() setting
ISCSI_THREAD_SET_DIE before calling kthread_stop().
It addresses the issue by both holding ts_state_lock before calling send_sig()
in iscsi_deallocate_extra_thread_sets(), as well as only calling flush_signals()
when ts->status != ISCSI_THREAD_SET_DIE within iscsi_[rx,tx]_thread_pre_handler()
code.
v2 changes:
- Add explicit complete(&ts->[rx,tx]_start_comp); before kthread_stop() in
iscsi_deallocate_extra_thread_sets()
- Drop left-over send_sig() calls in iscsi_deallocate_extra_thread_sets()
- Add kthread_should_stop() check in iscsi_signal_thread_pre_handler()
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch adds support for EXTENDED_COPY emulation from SPC-3, that
enables full copy offload target support within both a single virtual
backend device, and across multiple virtual backend devices. It also
functions independent of target fabric, and supports copy offload
across multiple target fabric ports.
This implemenation supports both EXTENDED_COPY PUSH and PULL models
of operation, so the actual CDB may be received on either source or
desination logical unit.
For Target Descriptors, it currently supports the NAA IEEE Registered
Extended designator (type 0xe4), which allows the reference of target
ports to occur independent of fabric type using EVPD 0x83 WWNs.
For Segment Descriptors, it currently supports copy from block to
block (0x02) mode.
It also honors any present SCSI reservations of the destination target
port. Note that only Supports No List Identifier (SNLID=1) mode is
supported.
Also included is basic RECEIVE_COPY_RESULTS with service action type
OPERATING PARAMETERS (0x03) required for SNLID=1 operation.
v3 changes:
- Fix incorrect return type in target_do_receive_copy_results()
(Fengguang)
v2 changes:
- Use target_alloc_sgl() instead of transport_generic_get_mem()
- Convert debug output to use pr_debug()
- Convert target_xcopy_parse_target_descriptors() NAA IEEN WWN
dump to use 0x%16phN format specification
- Drop unnecessary xcopy_pt_cmd->xpt_passthrough_wsem, and
associated usage in xcopy_pt_write_pending() and
target_xcopy_issue_pt_cmd()
- Add check for unsupported EXTENDED_COPY(LID4) service action
bits in target_do_xcopy()
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Martin Petersen <martin.petersen@oracle.com>
Cc: Chris Mason <chris.mason@fusionio.com>
Cc: Roland Dreier <roland@purestorage.com>
Cc: Zach Brown <zab@redhat.com>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Nicholas Bellinger <nab@daterainc.com>
