There are three timing problems in the kthread usages of iscsi_target_mod:
- np_thread of struct iscsi_np
- rx_thread and tx_thread of struct iscsi_conn
In iscsit_close_connection(), it calls
send_sig(SIGINT, conn->tx_thread, 1);
kthread_stop(conn->tx_thread);
In conn->tx_thread, which is iscsi_target_tx_thread(), when it receive
SIGINT the kthread will exit without checking the return value of
kthread_should_stop().
So if iscsi_target_tx_thread() exit right between send_sig(SIGINT...)
and kthread_stop(...), the kthread_stop() will try to stop an already
stopped kthread.
This is invalid according to the documentation of kthread_stop().
(Fix -ECONNRESET logout handling in iscsi_target_tx_thread and
early iscsi_target_rx_thread failure case - nab)
Signed-off-by: Jiang Yi <jiangyilism@gmail.com>
Cc: <stable@vger.kernel.org> # v3.12+
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>
We currently do
tcmu_free_device ->tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE) ->
uio_unregister_device -> kfree(tcmu_dev).
The problem is that the kernel does not wait for userspace to
do the close() on the uio device before freeing the tcmu_dev.
We can then hit a race where the kernel frees the tcmu_dev before
userspace does close() and so when close() -> release -> tcmu_release
is done, we try to access a freed tcmu_dev.
This patch made over the target-pending master branch moves the freeing
of the tcmu_dev to when the last reference has been dropped.
This also fixes a leak where if tcmu_configure_device was not called on a
device we did not free udev->name which was allocated at tcmu_alloc_device time.
Signed-off-by: Mike Christie <mchristi@redhat.com>
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>
Pull SCSI target updates from Nicholas Bellinger:
"Things were a lot more calm than previously expected. It's primarily
fixes in various areas, with most of the new functionality centering
around TCMU backend driver work that Xiubo Li has been driving.
Here's the summary on the feature side:
- Make T10-PI verify configurable for emulated (FILEIO + RD) backends
(Dmitry Monakhov)
- Allow target-core/TCMU pass-through to use in-kernel SPC-PR logic
(Bryant Ly + MNC)
- Add TCMU support for growing ring buffer size (Xiubo Li + MNC)
- Add TCMU support for global block data pool (Xiubo Li + MNC)
and on the bug-fix side:
- Fix COMPARE_AND_WRITE non GOOD status handling for READ phase
failures (Gary Guo + nab)
- Fix iscsi-target hang with explicitly changing per NodeACL
CmdSN number depth with concurrent login driven session
reinstatement. (Gary Guo + nab)
- Fix ibmvscsis fabric driver ABORT task handling (Bryant Ly)
- Fix target-core/FILEIO zero length handling (Bart Van Assche)
Also, there was an OOPs introduced with the WRITE_VERIFY changes that
I ended up reverting at the last minute, because as not unusual Bart
and I could not agree on the fix in time for -rc1. Since it's specific
to a conformance test, it's been reverted for now.
There is a separate patch in the queue to address the underlying
control CDB write overflow regression in >= v4.3 separate from the
WRITE_VERIFY revert here, that will be pushed post -rc1"
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (30 commits)
Revert "target: Fix VERIFY and WRITE VERIFY command parsing"
IB/srpt: Avoid that aborting a command triggers a kernel warning
IB/srpt: Fix abort handling
target/fileio: Fix zero-length READ and WRITE handling
ibmvscsis: Do not send aborted task response
tcmu: fix module removal due to stuck thread
target: Don't force session reset if queue_depth does not change
iscsi-target: Set session_fall_back_to_erl0 when forcing reinstatement
target: Fix compare_and_write_callback handling for non GOOD status
tcmu: Recalculate the tcmu_cmd size to save cmd area memories
tcmu: Add global data block pool support
tcmu: Add dynamic growing data area feature support
target: fixup error message in target_tg_pt_gp_tg_pt_gp_id_store()
target: fixup error message in target_tg_pt_gp_alua_access_type_store()
target/user: PGR Support
target: Add WRITE_VERIFY_16
Documentation/target: add an example script to configure an iSCSI target
target: Use kmalloc_array() in transport_kmap_data_sg()
target: Use kmalloc_array() in compare_and_write_callback()
target: Improve size determinations in two functions
...
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>
This patch fixes zero-length READ and WRITE handling in target/FILEIO,
which was broken a long time back by:
Since:
commit d81cb44726
Author: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon Sep 17 16:36:11 2012 -0700
target: go through normal processing for all zero-length commands
which moved zero-length READ and WRITE completion out of target-core,
to doing submission into backend driver code.
To address this, go ahead and invoke target_complete_cmd() for any
non negative return value in fd_do_rw().
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: David Disseldorp <ddiss@suse.de>
Cc: <stable@vger.kernel.org> # v3.7+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
We need to do a kthread_should_stop to check when kthread_stop has been
called.
This was a regression added in
b6df4b79a5
tcmu: Add global data block pool support
so not sure if you wanted to merge it in with that patch or what.
Signed-off-by: Mike Christie <mchristi@redhat.com>
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>
For the "struct tcmu_cmd_entry" in cmd area, the minimum size
will be sizeof(struct tcmu_cmd_entry) == 112 Bytes. And it could
fill about (sizeof(struct rsp) - sizeof(struct req)) /
sizeof(struct iovec) == 68 / 16 ~= 4 data regions(iov[4]) by
default.
For most tcmu_cmds, the data block indexes allocated from the
data area will be continuous. And for the continuous blocks they
will be merged into the same region using only one iovec. For
the current code, it will always allocates the same number of
iovecs with blocks for each tcmu_cmd, and it will wastes much
memories.
For example, when the block size is 4K and the DATA_OUT buffer
size is 64K, and the regions needed is less than 5(on my
environment is almost 99.7%). The current code will allocate
about 16 iovecs, and there will be (16 - 4) * sizeof(struct
iovec) = 192 Bytes cmd area memories wasted.
Here adds two helpers to calculate the base size and full size
of the tcmu_cmd. And will recalculate them again when it make sure
how many iovs is needed before insert it to cmd area.
Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
Acked-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
For each target there will be one ring, when the target number
grows larger and larger, it could eventually runs out of the
system memories.
In this patch for each target ring, currently for the cmd area
the size will be fixed to 8MB and for the data area the size
will grow from 0 to max 256K * PAGE_SIZE(1G for 4K page size).
For all the targets' data areas, they will get empty blocks
from the "global data block pool", which has limited to 512K *
PAGE_SIZE(2G for 4K page size) for now.
When the "global data block pool" has been used up, then any
target could wake up the unmap thread routine to shrink other
targets' data area memories. And the unmap thread routine will
always try to truncate the ring vma from the last using block
offset.
When user space has touched the data blocks out of tcmu_cmd
iov[], the tcmu_page_fault() will try to return one zeroed blocks.
Here we move the timeout's tcmu_handle_completions() into unmap
thread routine, that's to say when the timeout fired, it will
only do the tcmu_check_expired_cmd() and then wake up the unmap
thread to do the completions() and then try to shrink its idle
memories. Then the cmdr_lock could be a mutex and could simplify
this patch because the unmap_mapping_range() or zap_* may go to
sleep.
Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
Signed-off-by: Jianfei Hu <hujianfei@cmss.chinamobile.com>
Acked-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Currently for the TCMU, the ring buffer size is fixed to 64K cmd
area + 1M data area, and this will be bottlenecks for high iops.
The struct tcmu_cmd_entry {} size is fixed about 112 bytes with
iovec[N] & N <= 4, and the size of struct iovec is about 16 bytes.
If N == 0, the ratio will be sizeof(cmd entry) : sizeof(datas) ==
112Bytes : (N * 4096)Bytes = 28 : 0, no data area is need.
If 0 < N <=4, the ratio will be sizeof(cmd entry) : sizeof(datas)
== 112Bytes : (N * 4096)Bytes = 28 : (N * 1024), so the max will
be 28 : 1024.
If N > 4, the sizeof(cmd entry) will be [(N - 4) *16 + 112] bytes,
and its corresponding data size will be [N * 4096], so the ratio
of sizeof(cmd entry) : sizeof(datas) == [(N - 4) * 16 + 112)Bytes
: (N * 4096)Bytes == 4/1024 - 12/(N * 1024), so the max is about
4 : 1024.
When N is bigger, the ratio will be smaller.
As the initial patch, we will set the cmd area size to 2M, and
the cmd area size to 32M. The TCMU will dynamically grows the data
area from 0 to max 32M size as needed.
The cmd area memory will be allocated through vmalloc(), and the
data area's blocks will be allocated individually later when needed.
The allocated data area block memory will be managed via radix tree.
For now the bitmap still be the most efficient way to search and
manage the block index, this could be update later.
Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
Signed-off-by: Jianfei Hu <hujianfei@cmss.chinamobile.com>
Acked-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
When setting up an ALUA target port group with an invalid ID the
error message
kstrtoul() returned -22 for tg_pt_gp_id
is displayed, which is not really helpful.
Convert it to something sane.
And while we're at it, join the messages onto a single line.
Signed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Bart van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
When setting up a target the error message:
Unable to do set ##_name ALUA state on non valid tg_pt_gp ID: 0
is displayed.
Apparently concatenation doesn't work in a string; one should be using
implicit string concatenation here.
Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Bart van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This adds initial PGR support for just TCMU, since tcmu doesn't
have the necessary IT_NEXUS info to process PGR in userspace,
so have those commands be processed in kernel.
HA support is not available yet, we will work on it if this patch
is acceptable.
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch addresses clients who needs write_verify_16 for
large volume groups such as AIX.
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Signed-off-by: Nicholas 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: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Nicholas 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.
* Replace the specification of a data structure by a pointer dereference
to make the corresponding size determination a bit safer according to
the Linux coding style convention.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Replace the specification of two data structures by pointer dereferences
as the parameter for the operator "sizeof" to make the corresponding size
determinations a bit safer according to the Linux coding style convention.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* Multiplications for the size determination of memory allocations
indicated that array data structures should be processed.
Thus use the corresponding function "kcalloc".
This issue was detected by using the Coccinelle software.
* Replace the specification of data structures by pointer dereferences
to make the corresponding size determination a bit safer according to
the Linux coding style convention.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Replace the specification of four data structures by pointer dereferences
as the parameter for the operator "sizeof" to make the corresponding size
determinations a bit safer according to the Linux coding style convention.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
