Commit Graph

931 Commits

Author SHA1 Message Date
Sagi Grimberg
2371e5da8c iser-target: Parallelize CM connection establishment
There is no point in accepting a new CM request only
when we are completely done with the last iscsi login.
Instead we accept immediately, this will also cause the
CM connection to reach connected state and the initiator
is allowed to send the first login. We mark that we got
the initial login and let iscsi layer pick it up when it
gets there.

This reduces the parallel login sequence by a factor of
more then 4 (and more for multi-login) and also prevents
the initiator (who does all logins in parallel) from
giving up on login timeout expiration.

In order to support multiple login requests sequence (CHAP)
we call isert_rx_login_req from isert_rx_completion insead
of letting isert_get_login_rx call it.

Squashed:

iser-target: Use kref_get_unless_zero in connected_handler
iser-target: Acquire conn_mutex when changing connection state
iser-target: Reject connect request in failure path

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # v3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-12-12 22:58:52 -08:00
Sagi Grimberg
128e9cc845 iser-target: Fix flush + disconnect completion handling
ISER_CONN_UP state is not sufficient to know if
we should wait for completion of flush errors and
disconnected_handler event.

Instead, split it to 2 states:
- ISER_CONN_UP: Got to CM connected phase, This state
indicates that we need to wait for a CM disconnect
event before going to teardown.

- ISER_CONN_FULL_FEATURE: Got to full feature phase
after we posted login response, This state indicates
that we posted recv buffers and we need to wait for
flush completions before going to teardown.

Also avoid deffering disconnected handler to a work,
and handle it within disconnected handler.
More work here is needed to handle DEVICE_REMOVAL event
correctly (cleanup all resources).

Squashed:

iser-target: Don't deffer disconnected handler to a work

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # v3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-12-12 22:57:28 -08:00
Sagi Grimberg
954f23722b iscsi,iser-target: Initiate termination only once
Since commit 0fc4ea701f ("Target/iser: Don't put isert_conn inside
disconnected handler") we put the conn kref in isert_wait_conn, so we
need .wait_conn to be invoked also in the error path.

Introduce call to isert_conn_terminate (called under lock)
which transitions the connection state to TERMINATING and calls
rdma_disconnect. If the state is already teminating, just bail
out back (temination started).

Also, make sure to destroy the connection when getting a connect
error event if didn't get to connected (state UP). Same for the
handling of REJECTED and UNREACHABLE cma events.

Squashed:

iscsi-target: Add call to wait_conn in establishment error flow

Reported-by: Slava Shwartsman <valyushash@gmail.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # v3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-12-12 22:55:22 -08:00
Chris Moore
b1a5ad006b IB/isert: Adjust CQ size to HW limits
isert has an issue of trying to create a CQ with more CQEs than are
supported by the hardware, that currently results in failures during
isert_device creation during first session login.

This is the isert version of the patch that Minh Tran submitted for
iser, and is simple a workaround required to function with existing
ocrdma hardware.

Signed-off-by: Chris Moore <chris.moore@emulex.com>
Reviewied-by: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-11-19 22:28:42 -08:00
Sagi Grimberg
3b726ae2de iser-target: Handle DEVICE_REMOVAL event on network portal listener correctly
In this case the cm_id->context is the isert_np, and the cm_id->qp
is NULL, so use that to distinct the cases.

Since we don't expect any other events on this cm_id we can
just return -1 for explicit termination of the cm_id by the
cma layer.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-11-02 22:04:48 -08:00
Or Gerlitz
f57915cfa5 ib_isert: Add max_send_sge=2 minimum for control PDU responses
This patch adds a max_send_sge=2 minimum in isert_conn_setup_qp()
to ensure outgoing control PDU responses with tx_desc->num_sge=2
are able to function correctly.

This addresses a bug with RDMA hardware using dev_attr.max_sge=3,
that in the original code with the ConnectX-2 work-around would
result in isert_conn->max_sge=1 being negotiated.

Originally reported by Chris with ocrdma driver.

Reported-by: Chris Moore <Chris.Moore@emulex.com>
Tested-by: Chris Moore <Chris.Moore@emulex.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-11-02 22:04:29 -08:00
Bart Van Assche
ab477c1ff5 srp-target: Retry when QP creation fails with ENOMEM
It is not guaranteed to that srp_sq_size is supported
by the HCA. So if we failed to create the QP with ENOMEM,
try with a smaller srp_sq_size. Keep it up until we hit
MIN_SRPT_SQ_SIZE, then fail the connection.

Reported-by: Mark Lehrer <lehrer@gmail.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # 3.4+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-10-28 13:55:08 -07:00
Linus Torvalds
c3351dfabf Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending
Pull SCSI target updates from Nicholas Bellinger:
 "Here are the target updates for v3.18-rc2 code.  These where
  originally destined for -rc1, but due to the combination of travel
  last week for KVM Forum and my mistake of taking the three week merge
  window literally, the pull request slipped..  Apologies for that.

  Things where reasonably quiet this round.  The highlights include:

   - New userspace backend driver (target_core_user.ko) by Shaohua Li
     and Andy Grover
   - A number of cleanups in target, iscsi-taret and qla_target code
     from Joern Engel
   - Fix an OOPs related to queue full handling with CHECK_CONDITION
     status from Quinn Tran
   - Fix to disable TX completion interrupt coalescing in iser-target,
     that was causing problems on some hardware
   - Fix for PR APTPL metadata handling with demo-mode ACLs

  I'm most excited about the new backend driver that uses UIO + shared
  memory ring to dispatch I/O and control commands into user-space.
  This was probably the most requested feature by users over the last
  couple of years, and opens up a new area of development + porting of
  existing user-space storage applications to LIO.  Thanks to Shaohua +
  Andy for making this happen.

  Also another honorable mention, a new Xen PV SCSI driver was merged
  via the xen/tip.git tree recently, which puts us now at 10 target
  drivers in upstream! Thanks to David Vrabel + Juergen Gross for their
  work to get this code merged"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending: (40 commits)
  target/file: fix inclusive vfs_fsync_range() end
  iser-target: Disable TX completion interrupt coalescing
  target: Add force_pr_aptpl device attribute
  target: Fix APTPL metadata handling for dynamic MappedLUNs
  qla_target: don't delete changed nacls
  target/user: Recalculate pad size inside is_ring_space_avail()
  tcm_loop: Fixup tag handling
  iser-target: Fix smatch warning
  target/user: Fix up smatch warnings in tcmu_netlink_event
  target: Add a user-passthrough backstore
  target: Add documentation on the target userspace pass-through driver
  uio: Export definition of struct uio_device
  target: Remove unneeded check in sbc_parse_cdb
  target: Fix queue full status NULL pointer for SCF_TRANSPORT_TASK_SENSE
  qla_target: rearrange struct qla_tgt_prm
  qla_target: improve qlt_unmap_sg()
  qla_target: make some global functions static
  qla_target: remove unused parameter
  target: simplify core_tmr_abort_task
  target: encapsulate smp_mb__after_atomic()
  ...
2014-10-21 13:06:38 -07:00
Linus Torvalds
2eb7f910c1 Main set of InfiniBand/RDMA updates for 3.18 merge window:
- Large set of iSER initiator improvements
  - Hardware driver fixes for cxgb4, mlx5 and ocrdma
  - Small fixes to core midlayer
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABCAAGBQJUQEczAAoJEENa44ZhAt0h3n8P/RqklU+JJiF1eWRgvdf3fOPC
 WDzOzdKUHvv3Lm5qSv8V6q23oYzf2QC/vjuZJgyM5156vj/qSf3iw1ueZTwYSQ3v
 B6bV7/ptSpBlxRx/sI9/ks5yqT869jww7QAO+wtvzuq7JDxQr+t4Yw1j3WOM8DGd
 F/rBFWJgLCD3zFSeJVY+AgZwIeDpNvBO0/QVnchs9iPUY0jSBvhDLsWegGhs92Uv
 wfeiV36f8hPVnbYVMV+xA2t9NkBV21r1sUK1l+CfPDgL/unDoXXqriuqb401l4cj
 zR4/Xwro9WzOC0gey2a5KkyX9wQUW9+Y4TnHRLnJ5shO/yzqxmc+/FMksxnaoWtI
 koF5LqyfXxNhq0VZBpoy+astY4vv4h34WlyBC2lxDCJBEw8VYzO+Wg9QJAzWOxlq
 JXtY9l9zRxfgTLe78xjl2n9LEeOysbYJemp3YFpZVh7a4JvUK4L9Kh9mXKZu8tqt
 zd7YniNNJSdDfF5+Gx1kSK4kE1r/89f04ED6hg/eIf/IqhNYJ/vD5joQuJ4RqQNx
 5G0wdCfKMy9cCwbx1/eCRJOuP+dbGR73UskgXc41s5/VtXCdq8JHvBcWw5CgxQ5I
 AYGUrCuu/ZsQSMNM1i7Pocz8m4uLlnpXF7Qv62ULt/NQJQHj5Xfdvb9M3BK0urIf
 +aBpf+LiZahaUEfo5eYt
 =+ABw
 -----END PGP SIGNATURE-----

Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull infiniband/RDMA updates from Roland Dreier:
 - large set of iSER initiator improvements
 - hardware driver fixes for cxgb4, mlx5 and ocrdma
 - small fixes to core midlayer

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (47 commits)
  RDMA/cxgb4: Fix ntuple calculation for ipv6 and remove duplicate line
  RDMA/cxgb4: Add missing neigh_release in find_route
  RDMA/cxgb4: Take IPv6 into account for best_mtu and set_emss
  RDMA/cxgb4: Make c4iw_wr_log_size_order static
  IB/core: Fix XRC race condition in ib_uverbs_open_qp
  IB/core: Clear AH attr variable to prevent garbage data
  RDMA/ocrdma: Save the bit environment, spare unncessary parenthesis
  RDMA/ocrdma: The kernel has a perfectly good BIT() macro - use it
  RDMA/ocrdma: Don't memset() buffers we just allocated with kzalloc()
  RDMA/ocrdma: Remove a unused-label warning
  RDMA/ocrdma: Convert kernel VA to PA for mmap in user
  RDMA/ocrdma: Get vlan tag from ib_qp_attrs
  RDMA/ocrdma: Add default GID at index 0
  IB/mlx5, iser, isert: Add Signature API additions
  Target/iser: Centralize ib_sig_domain setting
  IB/iser: Centralize ib_sig_domain settings
  IB/mlx5: Use extended internal signature layout
  IB/iser: Set IP_CSUM as default guard type
  IB/iser: Remove redundant assignment
  IB/mlx5: Use enumerations for PI copy mask
  ...
2014-10-19 12:29:23 -07:00
Rasmus Villemoes
b60459f080 ib_srpt: replace strnicmp with strncasecmp
The kernel used to contain two functions for length-delimited,
case-insensitive string comparison, strnicmp with correct semantics and
a slightly buggy strncasecmp.  The latter is the POSIX name, so strnicmp
was renamed to strncasecmp, and strnicmp made into a wrapper for the new
strncasecmp to avoid breaking existing users.

To allow the compat wrapper strnicmp to be removed at some point in the
future, and to avoid the extra indirection cost, do
s/strnicmp/strncasecmp/g.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Roland Dreier <roland@kernel.org>
Cc: Nicholas Bellinger <nab@linux-iscsi.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 02:18:25 +02:00
Sagi Grimberg
78eda2bb65 IB/mlx5, iser, isert: Add Signature API additions
Expose more signature setting parameters. We modify the signature API
to allow usage of some new execution parameters relevant to data
integrity feature.

This patch modifies ib_sig_domain structure by:

- Deprecate DIF type in signature API (operation will
  be determined by the parameters alone, no DIF type awareness)
- Add APPTAG check bitmask (for input domain)
- Add REFTAG remap (increment) flag for each domain
- Add APPTAG/REFTAG escape options for each domain

The mlx5 driver is modified to follow the new parameters in HW
signature setup.

At the moment the callers (iser/isert) hard-code new parameters (by
DIF type). In the future, callers will retrieve them from the scsi
command structure.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:10:53 -07:00
Sagi Grimberg
3d73cf1a2a Target/iser: Centralize ib_sig_domain setting
Later there will be more parameters to set, so we want to do it in a
centralized place.

This patch does not change any functionality.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:10:53 -07:00
Sagi Grimberg
92792c0a19 IB/iser: Centralize ib_sig_domain settings
Later there will be more parameters to set, so we want to do it in a
centralized place.

This patch does not change any functionality.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:10:53 -07:00
Sagi Grimberg
f043032ef1 IB/iser: Set IP_CSUM as default guard type
In the future this will be a per-command parameter so we can lose it,
but in the mean time IP_CSUM is a lot lighter for SW layers to
compute, set it as default.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:10:53 -07:00
Sagi Grimberg
6f5f8a016e IB/iser: Remove redundant assignment
We clear the struct before - no need to do 0 assignment.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:10:53 -07:00
Or Gerlitz
b261aeafe1 IB/iser: Bump version, add maintainer
Update the driver version and add Sagi Grimberg as maintainer

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:46 -07:00
Sagi Grimberg
dc05ac36f7 IB/iser: Fix/add kernel-doc style description in iscsi_iser.c
This patch does not change any functionality.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:46 -07:00
Sagi Grimberg
cd88621a9e IB/iser: Add/Fix kernel doc style descriptions in iscsi_iser.h
- iser_hdr
- iser_data_buf
- iser_mem_reg
- iser_regd_buf
- iser_tx_desc
- iser_rx_desc
- iser_device
- iser_pi_context
- iser_conn
- ib_conn
- iser_comp
- iscsi_iser_task
- iser_global

While we're at it, change nit alignments in this file

This patch does not change any functionality.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:46 -07:00
Sagi Grimberg
e9d49b82f1 IB/iser: Nit - add space after __func__ in iser logging
Change logging: "iser:XXXX" to "iser: XXXX"

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:46 -07:00
Ariel Nahum
bba0a3c9d7 IB/iser: Change iscsi_conn_stop log level to info
Match to the debug level of all functions in connect/disconnect flows.

Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:42 -07:00
Sagi Grimberg
6df5a128f0 IB/iser: Suppress scsi command send completions
Singal completion of every 32 scsi commands and suppress all the rest.
We don't do anything upon getting the completion so no need to "just
consume" it.  Cleanup of scsi command is done in cleanup_task callback.

Still keep dataout and control send completions as we may need to
cleanup there. This helps reducing the amount of interrupts/completions
in the IO path.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:07 -07:00
Sagi Grimberg
6e6fe2fb1d IB/iser: Optimize completion polling
Poll in batch of 16. Since we don't want it on the stack, keep under
iser completion context (iser_comp).

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:07 -07:00
Sagi Grimberg
ff3dd52d26 IB/iser: Use beacon to indicate all completions were consumed
Avoid post_send counting (atomic) in the IO path just to keep track of
how many completions we need to consume.  Use a beacon post to indicate
that all prior posts completed.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:07 -07:00
Sagi Grimberg
6aabfa76f5 IB/iser: Use single CQ for RX and TX
This will solve a possible condition where we might miss TX completion
(flush error) during session teardown.  Since we are using a single
CQ, we don't need to actively drain the TX CQ, instead just wait for
flush_completion (when counters reach zero) and remove iser_poll_for_flush_errors().

This patch might introduce a minor performance regression on its own,
but the next patches will enhance performance using a single CQ for RX
and TX.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:07 -07:00
Sagi Grimberg
183cfa434e IB/iser: Use internal polling budget to avoid possible live-lock
We need a way to guarentee that we don't stay in soft-IRQ context for
too long.  We might starve other pending CQ tasklets or worse lock
against application trying to issue IO on the running CPU.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
bf17554035 IB/iser: Centralize iser completion contexts
Introduce iser_comp which centralizes all iser completion related
items and is referenced by iser_device and each ib_conn.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Ariel Nahum
aea8f4df6d IB/iser: Use iser_warn instead of BUG_ON in iser_conn_release
In case iscsid was violently killed (SIGKILL) during its error
recovery stage, we may never get a connection teardown sequence for
some of the old connections.  No harm done, but when we try to unload
the module we will need to cleanup all these connections.  So we
actually may end-up here - so it's not a BUG_ON(), just give a relaxed
warning that this happened and continue with normal unload.  BUG_ON()
will cause segfault on module_exit and we don't want that.

Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
8c204e69ce IB/iser: Signal iSCSI layer that transport is broken in error completions
Previously we notified iscsi layer about the connection layer when
we consumed all of our flush errors. This was racy as there
was no guarentee that iscsi_conn wasn't terminated by then (which ends
up in an invalid memory access). In case we got a non FLUSH error
completion, we are guarenteed that iscsi_conn is still alive. We should
notify iSCSI layer with iscsi_conn_failure to initiate error handling.

While we are at it, add a nice kernel-doc style documentation.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
3a940daf6f IB/iser: Protect tasks cleanup in case IB device was already released
Bailout in case a task cleanup (iscsi_iser_cleanup_task) is called
after the IB device was removed (DEVICE_REMOVAL CM event).  We also
call iscsi_conn_stop with a lock taken to prevent DEVICE_REMOVAL and
tasks cleanup from racing.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Ariel Nahum
ec370e2b63 IB/iser: Unbind at conn_stop stage
Previously we didn't need to unbind the iser_conn and iscsi_conn since
we always relied on iscsi daemon to teardown the connection and never
let it finish before we cleanup all that is needed in iser.  This is
not the case anymore (for DEVICE_REMOVAL event).  So avoid any possible
chance we cause iscsi_conn dereference after iscsi_conn was freed.

We also call iser_conn_terminate (safe to call multiple times) just
for the corner case of iscsi daemon stopping an old connection before
invoking endpoint removal (might happen if it was violently killed).

Notice we are unbinding under a lock - which is required.

Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
c107a6c0cf IB/iser: Don't bound release_work completions timeouts
We no longer rely on iscsi connection teardown sequence, so no need to
give a grace period and continue cleanup if it expired. Have
iser_conn_release wait for full completion before freeing iser_conn.

ib_completion:
	Guaranteed to come when:
	    - Got DISCONNECTED/ADDR_CHANGE event or
	    - iSCSI called ep_disconnect/conn_stop
	Guaranteed to finish when:
	    - Got TIMEWAIT_EXIT/DEVICE_REMOVAL event
	    - All Flush errors are consumed
	    - IB related resources are destroyed

stop_completion:
	Guaranteed to come when:
	    - iSCSI calls conn_stop
	Guaranteed to finish when:
	    - All inflight tasks were cleaned up

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
c47a3c9ed5 IB/iser: Fix DEVICE REMOVAL handling in the absence of iscsi daemon
iscsi daemon is in user-space, thus we can't rely on it to be invoked
at connection teardown (if not running or does not receive CPU time).

This patch addresses the issue by re-structuring iSER connection
teardown logic and CM events handling.

The CM events will dictate the RDMA resources destruction (ib_conn)
and iser_conn is kept around as long as iscsi_conn is left around
allowing iscsi/iser callbacks to continue after RDMA transport was
destroyed.

This patch introduces a separation in logic when handling CM events:

- DISCONNECTED_HANDLER, ADDR_CHANGED
  This events indicate the start of teardown process.
  Actions:
  1. Terminate the connection: rdma_disconnect (send DREQ/DREP)
  2. Notify iSCSI of connection failure
  3. Change state to TERMINATING
  4. Poll for all flush errors to be consumed

- TIMEWAIT_EXIT, DEVICE_REMOVAL
  These events indicate the final stage of termination process and
  we can free RDMA related resources.
  Actions:
  1. Call disconnected handler (we are not guaranteed that DISCONNECTED
     event was invoked in the past)
  2. Cleanup RDMA related resources
  3. For DEVICE_REMOVAL return non-zero rc from cma_handler to
     implicitly destroy the cm_id (Can't rely on user-space, make sure
     we have forward progress)

We replace flush_completion (indicate all flushes were consumed) with
ib_completion (rdma resources were cleaned up).

The iser_conn_release_work will wait for teardown completions:

- conn_stop was completed (tasks were cleaned-up) - stop_completion
- RDMA resources were destroyed - ib_completion

And then will continue to free iser connection representation (iser_conn).

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
96f15198c1 IB/iser: Extend iser_free_ib_conn_res()
Put all connection IB related resources release in this routine.  One
exception is the cm_id which cannot be destroyed as the routine is
protected by the state mutex.  Also move its position to avoid forward
declaration.  While at it fix qp NULL assignment.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Roi Dayan
6bb0279f95 IB/iser: Remove unused variables and dead code
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
a4ee3539f6 IB/iser: Re-introduce ib_conn
Structure that describes the RDMA relates connection objects.  Static
member of iser_conn.

This patch does not change any functionality

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Sagi Grimberg
5716af6e52 IB/iser: Rename ib_conn -> iser_conn
Two reasons why we choose to do this:

1. No point today calling struct iser_conn by another name ib_conn
2. In the next patches we will restructure iser control plane representation
   - struct iser_conn: connection logical representation
   - struct ib_conn: connection RDMA layout representation

This patch does not change any functionality.

Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-10-09 00:06:06 -07:00
Eric Dumazet
0287587884 net: better IFF_XMIT_DST_RELEASE support
Testing xmit_more support with netperf and connected UDP sockets,
I found strange dst refcount false sharing.

Current handling of IFF_XMIT_DST_RELEASE is not optimal.

Dropping dst in validate_xmit_skb() is certainly too late in case
packet was queued by cpu X but dequeued by cpu Y

The logical point to take care of drop/force is in __dev_queue_xmit()
before even taking qdisc lock.

As Julian Anastasov pointed out, need for skb_dst() might come from some
packet schedulers or classifiers.

This patch adds new helper to cleanly express needs of various drivers
or qdiscs/classifiers.

Drivers that need skb_dst() in their ndo_start_xmit() should call
following helper in their setup instead of the prior :

	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
->
	netif_keep_dst(dev);

Instead of using a single bit, we use two bits, one being
eventually rebuilt in bonding/team drivers.

The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being
rebuilt in bonding/team. Eventually, we could add something
smarter later.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-07 13:22:11 -04:00
Nicholas Bellinger
0d0f660d88 iser-target: Disable TX completion interrupt coalescing
This patch explicitly disables TX completion interrupt coalescing logic
in isert_put_response() and isert_put_datain() that was originally added
as an efficiency optimization in commit 95b60f07.

It has been reported that this change can trigger ABORT_TASK timeouts
under certain small block workloads, where disabling coalescing was
required for stability.  According to Sagi, this doesn't impact
overall performance, so go ahead and disable it for now.

Reported-by: Moussa Ba <moussaba@micron.com>
Reported-by: Sagi Grimberg <sagig@dev.mellanox.co.il>
Cc: <stable@vger.kernel.org> # 3.13+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-10-05 02:27:05 -07:00
Sagi Grimberg
1acff63f6e iser-target: Fix smatch warning
Unused return value from down_interruptible

Reported-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-10-03 11:16:11 -07:00
Linus Torvalds
452b6361c4 Last late set of InfiniBand/RDMA fixes for 3.17:
- Fixes for the new memory region re-registration support
  - iSER initiator error path fixes
  - Grab bag of small fixes for the qib and ocrdma hardware drivers
  - Larger set of fixes for mlx4, especially in RoCE mode
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABCAAGBQJUIexdAAoJEENa44ZhAt0hP10QAJztxlS2a8U3JCJzthwSYxlI
 ohT9487iLk1uEcj4Z3i7w2ERRUzXaHbRTktNHFjwfRb8x2qMUgT2PfD6/30sQ250
 nJAk3FRFNipxKkJSfmcc3+O4r91i4F+CaN8DGypaBDHcupeD2drKocl/Iu5MIvkG
 e5CzLlS7i/xrWKmgYP4bIqqFZsqQ+2rJrYBDybuLZSaZNd0PTDE3yCDihfOcsxjn
 TeOCVbm5895fPRtxzeCGHy8bXbYYN9vItuhtHC+sntYtbhNJhjpmP+1yD6M2SoZR
 34sGd7AA1j1H6ATmanzeW2aALkFYPIuGihDbbnRQlDG1v09lEPfP2GtfLxoQ9Ibo
 nfe2rsthzV6Qh2xcXjn6KicgV7bb6aSUXEK24zKx7O3MkOvHkOC/JIIrd9dFe+uj
 R7pUd3XlAk8SBhTQ4gLub06Dl7ynzSRArwcdMTHp30LvtnjJZoQR67WGGrsdwlIW
 MV43105i7iLCcdaSd0ihKnR6OFlSh13Z0wpu+B386bwxkHxjFJXkVHxOJir/iAk9
 cW4RXbA/ic7nwIjes4GbMNDOvdJO2tDcg9KGSgiDY3kC5GksPqfxXYVDlMB2rFoE
 PhfQ8TOcbZYTmlcKLMpMIFXP484VPhWQJeYWPOf9KGS6aW5QRNPsPCmAvaoSXWLs
 GVSlvjbE6O7MgonqG1Jh
 =Kpm1
 -----END PGP SIGNATURE-----

Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull infiniband/rdma fixes from Roland Dreier:
 "Last late set of InfiniBand/RDMA fixes for 3.17:

   - fixes for the new memory region re-registration support
   - iSER initiator error path fixes
   - grab bag of small fixes for the qib and ocrdma hardware drivers
   - larger set of fixes for mlx4, especially in RoCE mode"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (26 commits)
  IB/mlx4: Fix VF mac handling in RoCE
  IB/mlx4: Do not allow APM under RoCE
  IB/mlx4: Don't update QP1 in native mode
  IB/mlx4: Avoid accessing netdevice when building RoCE qp1 header
  mlx4: Fix mlx4 reg/unreg mac to work properly with 0-mac addresses
  IB/core: When marshaling uverbs path, clear unused fields
  IB/mlx4: Avoid executing gid task when device is being removed
  IB/mlx4: Fix lockdep splat for the iboe lock
  IB/mlx4: Get upper dev addresses as RoCE GIDs when port comes up
  IB/mlx4: Reorder steps in RoCE GID table initialization
  IB/mlx4: Don't duplicate the default RoCE GID
  IB/mlx4: Avoid null pointer dereference in mlx4_ib_scan_netdevs()
  IB/iser: Bump version to 1.4.1
  IB/iser: Allow bind only when connection state is UP
  IB/iser: Fix RX/TX CQ resource leak on error flow
  RDMA/ocrdma: Use right macro in query AH
  RDMA/ocrdma: Resolve L2 address when creating user AH
  mlx4: Correct error flows in rereg_mr
  IB/qib: Correct reference counting in debugfs qp_stats
  IPoIB: Remove unnecessary port query
  ...
2014-09-23 16:47:34 -07:00
Linus Torvalds
98f75b8291 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:

 1) If the user gives us a msg_namelen of 0, don't try to interpret
    anything pointed to by msg_name.  From Ani Sinha.

 2) Fix some bnx2i/bnx2fc randconfig compilation errors.

    The gist of the issue is that we firstly have drivers that span both
    SCSI and networking.  And at the top of that chain of dependencies
    we have things like SCSI_FC_ATTRS and SCSI_NETLINK which are
    selected.

    But since select is a sledgehammer and ignores dependencies,
    everything to select's SCSI_FC_ATTRS and/or SCSI_NETLINK has to also
    explicitly select their dependencies and so on and so forth.

    Generally speaking 'select' is supposed to only be used for child
    nodes, those which have no dependencies of their own.  And this
    whole chain of dependencies in the scsi layer violates that rather
    strongly.

    So just make SCSI_NETLINK depend upon it's dependencies, and so on
    and so forth for the things selecting it (either directly or
    indirectly).

    From Anish Bhatt and Randy Dunlap.

 3) Fix generation of blackhole routes in IPSEC, from Steffen Klassert.

 4) Actually notice netdev feature changes in rtl_open() code, from
    Hayes Wang.

 5) Fix divide by zero in bond enslaving, from Nikolay Aleksandrov.

 6) Missing memory barrier in sunvnet driver, from David Stevens.

 7) Don't leave anycast addresses around when ipv6 interface is
    destroyed, from Sabrina Dubroca.

 8) Don't call efx_{arch}_filter_sync_rx_mode before addr_list_lock is
    initialized in SFC driver, from Edward Cree.

 9) Fix missing DMA error checking in 3c59x, from Neal Horman.

10) Openvswitch doesn't emit OVS_FLOW_CMD_NEW notifications accidently,
    fix from Samuel Gauthier.

11) pch_gbe needs to select NET_PTP_CLASSIFY otherwise we can get a
    build error.

12) Fix macvlan regression wherein we stopped emitting
    broadcast/multicast frames over software devices.  From Nicolas
    Dichtel.

13) Fix infiniband bug due to unintended overflow of skb->cb[], from
    Eric Dumazet.  And add an assertion so this doesn't happen again.

14) dm9000_parse_dt() should return error pointers, not NULL.  From
    Tobias Klauser.

15) IP tunneling code uses this_cpu_ptr() in preemptible contexts, fix
    from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  net: bcmgenet: call bcmgenet_dma_teardown in bcmgenet_fini_dma
  net: bcmgenet: fix TX reclaim accounting for fragments
  ipv4: do not use this_cpu_ptr() in preemptible context
  dm9000: Return an ERR_PTR() in all error conditions of dm9000_parse_dt()
  r8169: fix an if condition
  r8152: disable ALDPS
  ipoib: validate struct ipoib_cb size
  net: sched: shrink struct qdisc_skb_cb to 28 bytes
  tg3: Work around HW/FW limitations with vlan encapsulated frames
  macvlan: allow to enqueue broadcast pkt on virtual device
  pch_gbe: 'select' NET_PTP_CLASSIFY.
  scsi: Use 'depends' with LIBFC instead of 'select'.
  openvswitch: restore OVS_FLOW_CMD_NEW notifications
  genetlink: add function genl_has_listeners()
  lib: rhashtable: remove second linux/log2.h inclusion
  net: allow macvlans to move to net namespace
  3c59x: Fix bad offset spec in skb_frag_dma_map
  3c59x: Add dma error checking and recovery
  sparc: bpf_jit: fix support for ldx/stx mem and SKF_AD_VLAN_TAG
  can: at91_can: add missing prepare and unprepare of the clock
  ...
2014-09-22 18:23:33 -07:00
Eric Dumazet
b49fe36208 ipoib: validate struct ipoib_cb size
To catch future errors sooner.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-22 14:29:55 -04:00
Roland Dreier
3bdad2d13f Merge branches 'core', 'ipoib', 'iser', 'mlx4', 'ocrdma' and 'qib' into for-next 2014-09-22 10:05:40 -07:00
Or Gerlitz
61aabb3c91 IB/iser: Bump version to 1.4.1
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-09-22 09:46:42 -07:00
Sagi Grimberg
91eb1df39a IB/iser: Allow bind only when connection state is UP
We need to fail the bind operation if the iser connection state != UP
(started teardown) and this should be done under the state lock.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-09-22 09:46:42 -07:00
Roi Dayan
c33b15f00b IB/iser: Fix RX/TX CQ resource leak on error flow
When failing to allocate TX CQ we already allocated RX CQ, so we need to make
sure we release it. Also, when failing to register notification to the RX CQ
we currently leak both RX and TX CQs of the current index, fix that too.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-09-22 09:46:42 -07:00
Alex Estrin
68f9d83c77 IPoIB: Remove unnecessary port query
There are two queries for port attributes one after another. A second
call is not needed since port_attr structure already holds the data.

Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Alex Estrin <alex.estrin@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-09-19 10:17:40 -07:00
Sagi Grimberg
1a92e17e39 Target/iser: Fix initiator_depth and responder_resources
The iser target is the RDMA requester and the iser initiator is the
RDMA responder. In order to determine the max inflight RDMA READ requests
to set on the QP (initiator_depth), it should take the min between the
initiator published initiator_depth and the max inflight rdma read
requests its local HCA support (max_qp_init_rd_atom).

The target will never handle incoming RDMA READ requests so no need to
set responder_resources.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-09-15 14:02:55 -07:00
Sagi Grimberg
38a8316b5d Target/iser: Avoid calling rdma_disconnect twice
rdma_disconnect may be called in 2 code flows:
- isert_wait_conn: disconnect initiated be the target
- disconnected_handler: disconnect invoked by the initiator

In case isert_conn->disconnect is true then rdma_disconnect
was called in disconnected handler, no need to call it again
from isert_wait_conn.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-09-15 14:02:30 -07:00
Sagi Grimberg
0fc4ea701f Target/iser: Don't put isert_conn inside disconnected handler
disconnected_handler is invoked on several CM events (such
as DISCONNECTED, DEVICE_REMOVAL, TIMEWAIT_EXIT...). Since
multiple  events can occur while before isert_free_conn is
invoked, we might put all isert_conn references and free
the connection too early.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Cc: <stable@vger.kernel.org> # v3.10+
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
2014-09-15 14:02:16 -07:00