The sleeping code in iscsi_target_tx_thread() is susceptible to the classic
missed wakeup race:
- TX thread finishes handle_immediate_queue() and handle_response_queue(),
thinks both queues are empty.
- Another thread adds a queue entry and does wake_up_process(), which does
nothing because the TX thread is still awake.
- TX thread does schedule_timeout() and sleeps forever.
In practice this can kill an iSCSI connection if for example an initiator
does single-threaded writes and the target misses the wakeup window when
queueing an R2T; in this case the connection will be stuck until the
initiator loses patience and does some task management operation (or kills
the connection entirely).
Fix this by converting to wait_event_interruptible(), which does not
suffer from this sort of race.
Signed-off-by: Roland Dreier <roland@purestorage.com>
Cc: Andy Grover <agrover@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Pull scsi target updates from Nicholas Bellinger:
"Things have been calm for the most part with no new fabric drivers in
flight for v3.7 (we're up to eight now !), so this update is primarily
focused on addressing a few long-standing items within target-core and
iscsi-target fabric code.
The highlights include:
- target: Simplify fabric sense data length handling (roland)
- qla2xxx: Fix endianness of task management response code (roland)
- target: fix truncation of mode data, support zero allocation length
(paolo)
- target: Properly support zero-length commands in normal processing
path (paolo)
- iscsi-target: Correctly set 0xffffffff field within ISCSI_OP_REJECT
PDU (ronnie + nab)
- iscsi-target: Add explicit set of cache_dynamic_acls=1 for TPG
demo-mode (ronnie + nab)
- target/file: Re-enable optional fd_buffered_io=1 operation (nab +
hch)
- iscsi-target: Add MaxXmitDataSegmenthLength forr target ->
initiator MDRSL declaration (nab)
- target: Add target_submit_cmd_map_sgls for SGL fabric memory
passthrough (nab + hch)
- tcm_loop: Convert I/O path to use target_submit_cmd_map_sgls (hch +
nab)
- tcm_vhost: Convert I/O path to use target_submit_cmd_map_sgls (nab
+ hch)
The last series for adding a new target_submit_cmd_map_sgls() fabric
caller (as requested by hch) that accepts pre-allocated SGL memory
(using existing logic), along with converting tcm_loop + tcm_vhost has
only been in -next for the last days, but has gotten enough review
+testing and is clear enough a mechanical change that I think it's
reasonable to merge for -rc1 code.
Thanks again to everyone who contributed this round! Extra special
thanks to Roland (PureStorage) for tracking down the qla2xxx target
TMR response code endian issue, and to Paolo (Redhat) for resolving
the long standing zero-length CDB issues within target-core between
virtual and pSCSI backends."
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (44 commits)
iscsi-target: Bump defaults for nopin_timeout + nopin_response_timeout values
iscsit: proper endianess conversions
iscsit: use the itt_t abstract type
iscsit: add missing endianess conversion in iscsit_check_inaddr_any
iscsit: remove incorrect unlock in iscsit_build_sendtargets_resp
iscsit: mark various functions static
target/iscsi: precedence bug in iscsit_set_dataout_sequence_values()
target/usb-gadget: strlen() doesn't count the terminator
target/usb-gadget: remove duplicate initialization
tcm_vhost: Convert I/O path to use target_submit_cmd_map_sgls
target: Add control CDB READ payload zero work-around
tcm_loop: Convert I/O path to use target_submit_cmd_map_sgls
target: Add target_submit_cmd_map_sgls for SGL fabric memory passthrough
iscsi-target: Add explicit set of cache_dynamic_acls=1 for TPG demo-mode
iscsi-target: Change iscsi_target_seq_pdu_list.c to honor MaxXmitDataSegmentLength
iscsi-target: Add MaxXmitDataSegmentLength connection recovery check
iscsi-target: Convert incoming PDU payload checks to MaxXmitDataSegmentLength
iscsi-target: Enable MaxXmitDataSegmentLength operation in login path
iscsi-target: Add base MaxXmitDataSegmentLength code
target/file: Re-enable optional fd_buffered_io=1 operation
...
This patch increases the default for nopin_timeout to 15 seconds (wait
between sending a new NopIN ping) and nopin_response_timeout to 30 seconds
(wait for NopOUT response before failing the connection) in order to avoid
false positives by iSCSI Initiators who are not always able (under load) to
respond to NopIN echo PING requests within the current 5 second window.
False positives have been observed recently using Open-iSCSI code on v3.3.x
with heavy large-block READ workloads over small MTU 1 Gb/sec ports, and
increasing these values to more reasonable defaults significantly reduces
the possibility of false positive NopIN response timeout events under
this specific workload.
Historically these have been set low to initiate connection recovery as
soon as possible if we don't hear a ping back, but for modern v3.x code
on 1 -> 10 Gb/sec ports these new defaults make alot more sense.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Make sure all on the wire types are use as big endian and big endian only so
that sparse can verify all the conversions are done right.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Use the special itt_t type defined by the iscsi headers and the initiator
to make sure it's an opaque value.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Sparse noticed that INADDR_ANY needs to be converted to big endian before
it can be stored in struct sockaddr_in.s_addr.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Fix a potential multiple spin-unlock -> deadlock scenario during the
overflow check within iscsit_build_sendtargets_resp() as found by
sparse static checking.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch marks a number of functions static to appease sparse static
checking.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Clang warns about this bug:
drivers/target/iscsi/iscsi_target_erl0.c:52:45: warning: operator '?:'
has lower precedence than '+'; '+' will be evaluated first
[-Wparentheses]
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
We've had reports in the past about this specific case, so it's time to
go ahead and explicitly set cache_dynamic_acls=1 for generate_node_acls=1
(TPG demo-mode) operation.
During normal generate_node_acls=0 operation with explicit NodeACLs ->
se_node_acl memory is persistent to the configfs group located at
/sys/kernel/config/target/$TARGETNAME/$TPGT/acls/$INITIATORNAME, so in
the generate_node_acls=1 case we want the reservation logic to reference
existing per initiator IQN se_node_acl memory (not to generate a new
se_node_acl), so go ahead and always set cache_dynamic_acls=1 when
TPG demo-mode is enabled.
Reported-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts iscsi_target_seq_pdu_list.c code for DataSequenceInOrder=No +
DataPDUInOrder=No operation to honor the MaxXmitDataSegmentLength value
for iscsi_cmd->se_cmd.data_direction == DMA_TO_DEVICE cases.
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Andy Grover <agrover@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The iSCSI TMR TASK_REASSIGN completion logic in iscsi_tmr_task_reassign()
does an explict check for MRDSL across task reassignment, so go ahead and
add an explict MaxXmitDataSegmentLength check here as well to be safe.
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Andy Grover <agrover@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Now that iscsi-target supports a local configurable MaxXmitDataSegmentLength,
go ahead and make ISCSI_OP_SCSI_CMD, ISCSI_OP_SCSI_DATA_OUT, ISCSI_OP_NOOP_OUT
and ISCSI_OP_TEXT PDU payload checks honor conn_ops->MaxXmitDataSegmentLength.
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Andy Grover <agrover@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch activates MaxXmitDataSegmentLength usage that performs the
following sequence of events:
- Once the incoming initiator's MAXRECVDATASEGMENTLENGTH key is detected
within iscsi_check_acceptor_state(), save the requested MRDSL into
conn->conn_ops->MaxRecvDataSegmentLength
- Next change the outgoing target's MaxRecvDataSegmenthLength key=value
based upon the local TPG's MaxXmitDataSegmentLength attribute value.
- Change iscsi_set_connection_parameters() to skip the assignment of
conn->conn_ops->MaxRecvDataSegmentLength, now setup within
iscsi_check_acceptor_state()
Also update iscsi_decode_text_input() -> iscsi_check_acceptor_state()
code-path to accept struct iscsi_conn *.
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Andy Grover <agrover@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch introduces a new per connection MaxXmitDataSegmentLength
parameter value used to represent the outgoing MaxRecvDataSegmentLength
that is actually sent over the wire during iSCSI login response back
to the initiator side.
It also adds a new MaxXmitDataSegmentLength configfs attribute to
represent this value within the existing TPG parameter group under
/sys/kernel/config/target/iscsi/$TARGETNAME/$TPGT/param/
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Andy Grover <agrover@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Pull the trivial tree from Jiri Kosina:
"Tiny usual fixes all over the place"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (34 commits)
doc: fix old config name of kprobetrace
fs/fs-writeback.c: cleanup riteback_sb_inodes kerneldoc
btrfs: fix the commment for the action flags in delayed-ref.h
btrfs: fix trivial typo for the comment of BTRFS_FREE_INO_OBJECTID
vfs: fix kerneldoc for generic_fh_to_parent()
treewide: fix comment/printk/variable typos
ipr: fix small coding style issues
doc: fix broken utf8 encoding
nfs: comment fix
platform/x86: fix asus_laptop.wled_type module parameter
mfd: printk/comment fixes
doc: getdelays.c: remember to close() socket on error in create_nl_socket()
doc: aliasing-test: close fd on write error
mmc: fix comment typos
dma: fix comments
spi: fix comment/printk typos in spi
Coccinelle: fix typo in memdup_user.cocci
tmiofb: missing NULL pointer checks
tools: perf: Fix typo in tools/perf
tools/testing: fix comment / output typos
...
This patch adds a missing iscsi_reject->ffffffff assignment within
iscsit_send_reject() code to properly follow RFC-3720 Section 10.17
Bytes 16 -> 19 for the PDU format definition of ISCSI_OP_REJECT.
We've not seen any initiators care about this bytes in practice, but
as Ronnie reported this was causing trouble with wireshark packet
decoding lets go ahead and fix this up now.
Reported-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
There's no need for iscsi_target_init_negotiation() to print
iSCSI Login negotiation failed.
on failure, since its only caller (__iscsi_target_login_thread())
prints exactly the same message if it gets an error return back.
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Every fabric driver has to supply a se_tfo->set_fabric_sense_len()
method, just so iSCSI can return an offset of 2. However, every fabric
driver is already allocating a sense buffer and passing it into the
target core, either via transport_init_se_cmd() or target_submit_cmd().
So instead of having iSCSI pass the start of its sense buffer into the
core and then later tell the core to skip the first 2 bytes, it seems
easier for iSCSI just to do the offset of 2 when it passes the sense
buffer into the core. Then we can drop the se_tfo->set_fabric_sense_len()
everywhere, and just add a couple of lines of code to iSCSI to set the
sense data length to the beginning of the buffer right before it sends
it over the network.
(nab: Remove .set_fabric_sense_len usage from tcm_qla2xxx_npiv_ops +
change transport_get_sense_buffer to follow v3.6-rc6 code w/o
->set_fabric_sense_len usage)
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
There are no callers of se_tfo->get_fabric_sense_len(), so we should
stop having every fabric driver implement it.
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch updates iscsi_login_zero_tsih_s1() usage for generating
iscsi_session->session_index to properly check the return value from
idr_get_new(), and reject the iSCSI login attempt with exception
status ISCSI_LOGIN_STATUS_NO_RESOURCES in the event of a failure.
Signed-off-by: Benjamin Wang <cpwang2009@gmail.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
From Al Viro:
BTW, speaking of struct file treatment related to sockets -
there's this piece of code in iscsi:
/*
* The SCTP stack needs struct socket->file.
*/
if ((np->np_network_transport == ISCSI_SCTP_TCP) ||
(np->np_network_transport == ISCSI_SCTP_UDP)) {
if (!new_sock->file) {
new_sock->file = kzalloc(
sizeof(struct file), GFP_KERNEL);
For one thing, as far as I can see it'not true - sctp does *not* depend on
socket->file being non-NULL; it does, in one place, check socket->file->f_flags
for O_NONBLOCK, but there it treats NULL socket->file as "flag not set".
Which is the case here anyway - the fake struct file created in
__iscsi_target_login_thread() (and in iscsi_target_setup_login_socket(), with
the same excuse) do *not* get that flag set.
Moreover, it's a bloody serious violation of a bunch of asserts in VFS;
all struct file instances should come from filp_cachep, via get_empty_filp()
(or alloc_file(), which is a wrapper for it). FWIW, I'm very tempted to
do this and be done with the entire mess:
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Grover <agrover@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Bubble-up retval from iscsi_update_param_value() and
iscsit_ta_authentication().
Other very small retval cleanups.
Signed-off-by: Andy Grover <agrover@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Roland Dreier
Linus Torvalds
Nicholas Bellinger
Christoph Hellwig
Dan Carpenter
Masanari Iida
Benjamin Wang
Al Viro
Andy Grover