Commit Graph

165 Commits

Author SHA1 Message Date
Vipul Pandya 9919d5bd01 RDMA/cxgb4: Fix onchip queue support for T5
T5 adapter does not support onchip queue memory. Present logic fails to
allocate QP for T5 and returns an error. Also, if module parameter ocqp_support
is zero then we are unable to allocate QP which should not be the case. Ideally
if ocqp_support parameter is 0 or onchip queue support is disable then host QP
should be allocated before returning an error.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-14 11:35:59 -04:00
Vipul Pandya 3b174d942c RDMA/cxgb4: Bump tcam_full stat and WR reply timeout
Always bump the tcam_full stat. Also, bump wr reply timeout to 30 seconds.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-14 11:35:59 -04:00
Vipul Pandya 0e5eca791c RDMA/cxgb4: Map pbl buffers for dma if using DSGL.
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-14 11:35:59 -04:00
Vipul Pandya 42b6a94990 RDMA/cxgb4: Use DSGLs for fastreg and adapter memory writes for T5.
It enables direct DMA by HW to memory region PBL arrays and fast register PBL
arrays from host memory, vs the T4 way of passing these arrays in the WR itself.
The result is lower latency for memory registration, and larger PBL array
support for fast register operations.

This patch also updates ULP_TX_MEM_WRITE command fields for T5. Ordering bit of
ULP_TX_MEM_WRITE is at bit position 22 in T5 and at 23 in T4.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-14 11:35:59 -04:00
Vipul Pandya 80ccdd6051 RDMA/cxgb4: Add module_params to enable DB FC & Coalescing on T5
Both DB Flow-Control and DB Coalescing are disabled by default on T5

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-14 11:35:58 -04:00
Vipul Pandya 3cbdb928e2 RDMA/cxgb4: Turn off db coalescing when RDMA QPs are in use.
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-14 11:35:58 -04:00
Vipul Pandya f079af7a11 RDMA/cxgb4: Add Support for Chelsio T5 adapter
Adds support for Chelsio T5 adapter.
Enables T5's Write Combining feature.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-14 11:35:58 -04:00
Tejun Heo e8d4dd606b IB/cxgb4: convert to idr_alloc()
Convert to the much saner new idr interface.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-27 19:10:16 -08:00
Roland Dreier ef4e359d9b Merge branches 'core', 'cxgb4', 'ipoib', 'iser', 'misc', 'mlx4', 'qib' and 'srp' into for-next 2013-02-26 09:17:56 -08:00
Shani Michaeli 7083e42ee2 IB/core: Add "type 2" memory windows support
This patch enhances the IB core support for Memory Windows (MWs).

MWs allow an application to have better/flexible control over remote
access to memory.

Two types of MWs are supported, with the second type having two flavors:

    Type 1  - associated with PD only
    Type 2A - associated with QPN only
    Type 2B - associated with PD and QPN

Applications can allocate a MW once, and then repeatedly bind the MW
to different ranges in MRs that are associated to the same PD. Type 1
windows are bound through a verb, while type 2 windows are bound by
posting a work request.

The 32-bit memory key is composed of a 24-bit index and an 8-bit
key. The key is changed with each bind, thus allowing more control
over the peer's use of the memory key.

The changes introduced are the following:

* add memory window type enum and a corresponding parameter to ib_alloc_mw.
* type 2 memory window bind work request support.
* create a struct that contains the common part of the bind verb struct
  ibv_mw_bind and the bind work request into a single struct.
* add the ib_inc_rkey helper function to advance the tag part of an rkey.

Consumer interface details:

* new device capability flags IB_DEVICE_MEM_WINDOW_TYPE_2A and
  IB_DEVICE_MEM_WINDOW_TYPE_2B are added to indicate device support
  for these features.

  Devices can set either IB_DEVICE_MEM_WINDOW_TYPE_2A or
  IB_DEVICE_MEM_WINDOW_TYPE_2B if it supports type 2A or type 2B
  memory windows. It can set neither to indicate it doesn't support
  type 2 windows at all.

* modify existing provides and consumers code to the new param of
  ib_alloc_mw and the ib_mw_bind_info structure

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Shani Michaeli <shanim@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-21 11:51:45 -08:00
Stefan Hasko b23523d858 RDMA/cxgb4: Fix cast warning
Fix compile warning about cast to pointer from integer of different size.

Signed-off-by: Stefan Hasko <hasko.stevo@gmail.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-15 15:13:43 -08:00
Paul Bolle 710a31102b RDMA/cxgb4: "cookie" can stay in host endianness
Work requests are passed between the host and the firmware with a
"cookie".  This cookie is swapped to big-endian when passed to the
firmware and back to host endianness on return.  This swapping seems
to be implemented incorrectly.  Moreover, the byte swapping triggers
GCC warnings on 32 bit:

    drivers/infiniband/hw/cxgb4/cm.c: In function ‘passive_ofld_conn_reply’:
    drivers/infiniband/hw/cxgb4/cm.c:2803:12: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
    drivers/infiniband/hw/cxgb4/cm.c: In function ‘send_fw_pass_open_req’:
    drivers/infiniband/hw/cxgb4/cm.c:2941:16: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
    [...]

But byte swapping isn't needed as the firmware doesn't actually touch
the cookie.  Dropping byte swapping makes the warnings go away too.

Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:55:05 -08:00
Vipul Pandya ef5d6355ed RDMA/cxgb4: Address sparse warnings
Fixe the following types of sparse warnings
- cast to pointer from integer of different size
- cast from pointer to integer of different size
- incorrect type in assignment (different base types)
- incorrect type in argument 1 (different base types)
- cast from restricted __be64
- cast from restricted __be32

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:58 -08:00
Vipul Pandya b3de6cfebc RDMA/cxgb4: Insert hwtid in pass_accept_req instead in pass_establish
CPL_ABORT_REQ_RSS can come before TCP connection is established.  In
such case peer_abort was trying to remove the hwtid, which was not
inserted.  To avoid this we insert the hwtid when we are sure that we
are surely going to send passive accept request.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:58 -08:00
Vipul Pandya 7c0a33d611 RDMA/cxgb4: Don't wakeup threads for MPAv2
Don't wakeup threads blocked in rdma_init/rdma_fini if we are on
MPAv2, and want to retry connection with MPAv1.

Stop ep-timer on getting MPA version mismatch, before doing the
abort_connection - in process_mpa_request.

Take care to stop ep-timer in error paths for process_mpa_request.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:57 -08:00
Vipul Pandya fe7e0a4dd0 RDMA/cxgb4: Don't reconnect on abort for mpa_rev 1
Only reconnect if the endpoint wasn't freed.

peer_abort() should only attempt to reconnect if the endpoint wasn't
freed.  Also remove hwtid from the debugfs idr.

Add missing check for peer2peer in MPAv2 code

Use correct mpa version on reject.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:57 -08:00
Vipul Pandya 1ec779cc29 RDMA/cxgb4: Fix endpoint timeout race condition
The endpoint timeout logic had a race that could cause an endpoint
object to be freed while it was still on the timedout list.  This
can happen if the timer is stopped after it had fired, but before
the timedout thread processed the endpoint timeout.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:57 -08:00
Vipul Pandya e8e5b9278b RDMA/cxgb4: Only log rx_data warnings if cpl status is non-zero
With newer firmware, we can get streaming data due to connection
errors before the driver moves the QP out of RTS.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:56 -08:00
Vipul Pandya 04236df2a5 RDMA/cxgb4: Always log async errors
Log AEs even if the QP isn't in RTS.  It is useful information.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:56 -08:00
Vipul Pandya 325abead6c RDMA/cxgb4: Keep QP referenced until TID released
The driver is currently releasing the last ref on the QP too early.
This can cause bus errors due to HW still fetching WRs from the HW
queue.  The fix is to keep a qp ref until we release the HW TID.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:56 -08:00
Vipul Pandya 1557967bf9 RDMA/cxgb4: Display streaming mode error only if detected in RTS
With later firmware, the chances of getting streaming mode data after
we exit RTS is likely, so we don't need to warn for it.  The only real
case where we don't expect it is when the QP is in RTS.

Move QP to ERROR when streaming mode data received.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:55 -08:00
Vipul Pandya 91e9c07195 RDMA/cxgb4: Abort connections when moving to ERROR state
If a FINI operation fails, then we need to ABORT instead of CLOSE.
Also, if we ABORT due to unexpected STREAMING data, then wake up
anybody blocked in FINI...

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:55 -08:00
Vipul Pandya 55abf8df0a RDMA/cxgb4: Abort connections that receive unexpected streaming mode data
This error means the RDMA connection was knocked out of RDMA mode,
probably due to an error on the connection.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2013-02-14 15:51:55 -08:00
Vipul Pandya 793dad94e7 RDMA/cxgb4: Fix bug for active and passive LE hash collision path
Retries active opens for INUSE errors.

Logs any active ofld_connect_wr error replies.

Sends ofld_connect_wr on same ctrlq. It needs to go  on the same control txq as
regular CPL active/passive messages.

Retries on active open replies with EADDRINUSE.

Uses active open fw wr only if active filter region is set.

Adds stat for ofld_connect_wr failures.

This patch also adds debugfs file to show endpoints.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-12-19 23:03:12 -08:00
Vipul Pandya 1cab775c3e RDMA/cxgb4: Fix LE hash collision bug for passive open connection
It establishes passive open connection through firmware work request. Passive
open connection will go through this path as now instead of listening server we
create a server filter which will redirect the incoming SYN packet to the
offload queue. After this driver tries to establish the connection using
firmware work request.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-12-19 23:03:11 -08:00
Vipul Pandya 5be78ee924 RDMA/cxgb4: Fix LE hash collision bug for active open connection
It enables establishing active open connection using fw_ofld_connection work
request when cpl_act_open_rpl says TCAM full error which may be because
of LE hash collision. Current support is only for IPv4 active open connections.

Sets ntuple bits in active open requests. For T4 firmware greater than 1.4.10.0
ntuple bits are required to be set.

Adds nocong and enable_ecn module parameter options.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>

[ Move all FW return values to t4fw_api.h.  - Roland ]

Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-12-19 23:02:43 -08:00
Julia Lawall 76f267b7ad RDMA/cxgb4: use WARN
Use WARN rather than printk followed by WARN_ON(1), for conciseness.

A simplified version of the semantic patch that makes this transformation
is as follows: (http://coccinelle.lip6.fr/)

// <smpl>
@@
expression list es;
@@

-printk(
+WARN(1,
  es);
-WARN_ON(1);
// </smpl>

Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-11-26 11:07:18 -08:00
Thadeu Lima de Souza Cascardo 32c631f9f2 RDMA/cxgb4: Don't free chunk that we have failed to allocate
In the error path of registering memory when there's a failure to
allocate a chunk from the memory pool, we try to free the same chunk
we just failed to allocate, which will BUG().

Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-10-22 11:05:00 -07:00
Linus Torvalds 7a9a2970b5 First batch of InfiniBand/RDMA changes for the 3.7 merge window:
- mlx4 IB support for SR-IOV
  - A couple of SRP initiator fixes
  - Batch of nes hardware driver fixes
  - Fix for long-standing use-after-free crash in IPoIB
  - Other miscellaneous fixes
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.11 (GNU/Linux)
 
 iQIcBAABCAAGBQJQav4jAAoJEENa44ZhAt0hmL0QAJTuMdSOzYFd/NB38owJCNM2
 kz/N1GlBm3z98fIlGo8u+lzgV2qxqZSAzsJsouMeK38KiAX3CL8HKe44A1QvTM6v
 dXTNL4JFX24/YF+nlmMY8Av518I9Mkte3BZCnpYkBjVFBWe0ePwoRC/btfBXPDIV
 0snq4OtjoBAn00dOOyuZ5PoyY9xf0z4UB0Gple9sM4mzEb8wVWdNDDPOiuPJc6fA
 L+gk6HLkZDg54+QswafdKYwpeTq45wIKLmCdS3oUNmppMLVhZY8rECOwzSa+KiTr
 /Yo19n+zl+IBlvjQHhmUqGHvdD17PaGlr+TckAsQqmVfXUH5qqpEnkF8FoEK59c5
 YA3lVU8Sj4BPhJ7qX54CuN3767mZizakkxCr9iPRzABFTgzWVgcSgCrE8jjx4i0h
 Pam+L5bmANFStgmGR8PmXiNgcrCUcEqYHsOWDDAnHa5ekb2nyv1JL1c18hlY9hC3
 Xb1YTMZFwvofGza89hBu7oHrMbLOUc5kW2lBpvUn2nlyf3i0F8ISlVbVbNjFA54p
 60/jHa2VOQ2CcJUJKnJOk4ajOOEfHnPtMn2q96XJ69Dp8+eSYEO/G+0i1OlChq4h
 ClnG0Yp+NkT1o8WXMd7guDR+RsXt+DXIij5TiUWRIqnIlopIsMTRhNH28tMu4jQL
 fgN5n987wru91ewdX4gW
 =PAcy
 -----END PGP SIGNATURE-----

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

Pull infiniband updates from Roland Dreier:
 "First batch of InfiniBand/RDMA changes for the 3.7 merge window:
   - mlx4 IB support for SR-IOV
   - A couple of SRP initiator fixes
   - Batch of nes hardware driver fixes
   - Fix for long-standing use-after-free crash in IPoIB
   - Other miscellaneous fixes"

This merge also removes a new use of __cancel_delayed_work(), and
replaces it with the regular cancel_delayed_work() that is now irq-safe
thanks to the workqueue updates.

That said, I suspect the sequence in question should probably use
"mod_delayed_work()".  I just did the minimal "don't use deprecated
functions" fixup, though.

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (45 commits)
  IB/qib: Fix local access validation for user MRs
  mlx4_core: Disable SENSE_PORT for multifunction devices
  mlx4_core: Clean up enabling of SENSE_PORT for older (ConnectX-1/-2) HCAs
  mlx4_core: Stash PCI ID driver_data in mlx4_priv structure
  IB/srp: Avoid having aborted requests hang
  IB/srp: Fix use-after-free in srp_reset_req()
  IB/qib: Add a qib driver version
  RDMA/nes: Fix compilation error when nes_debug is enabled
  RDMA/nes: Print hardware resource type
  RDMA/nes: Fix for crash when TX checksum offload is off
  RDMA/nes: Cosmetic changes
  RDMA/nes: Fix for incorrect MSS when TSO is on
  RDMA/nes: Fix incorrect resolving of the loopback MAC address
  mlx4_core: Fix crash on uninitialized priv->cmd.slave_sem
  mlx4_core: Trivial cleanups to driver log messages
  mlx4_core: Trivial readability fix: "0X30" -> "0x30"
  IB/mlx4: Create paravirt contexts for VFs when master IB driver initializes
  mlx4: Modify proxy/tunnel QP mechanism so that guests do no calculations
  mlx4: Paravirtualize Node Guids for slaves
  mlx4: Activate SR-IOV mode for IB
  ...
2012-10-02 17:20:40 -07:00
Emil Goode c079c28714 RDMA/cxgb4: Fix error handling in create_qp()
The variable ret is assigned return values in a couple of places, but
its value is never returned.  This patch makes use of the ret variable
so that the caller get correct error codes returned.

The following changes are also introduced:

- The alloc_oc_sq function can return -ENOSYS or -ENOMEM so we want to
  get the return value from it.

- Change the label names to improve readability.

Signed-off-by: Emil Goode <emilgoode@gmail.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-09-30 20:32:14 -07:00
David S. Miller 6a06e5e1bb Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
	drivers/net/team/team.c
	drivers/net/usb/qmi_wwan.c
	net/batman-adv/bat_iv_ogm.c
	net/ipv4/fib_frontend.c
	net/ipv4/route.c
	net/l2tp/l2tp_netlink.c

The team, fib_frontend, route, and l2tp_netlink conflicts were simply
overlapping changes.

qmi_wwan and bat_iv_ogm were of the "use HEAD" variety.

With help from Antonio Quartulli.

Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-28 14:40:49 -04:00
Wei Yongjun 92dd6c3d4d RDMA/cxgb4: Move dereference below NULL test
spatch with a semantic match is used to found this.
(http://coccinelle.lip6.fr/)

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-09-07 16:19:03 -07:00
Vipul Pandya e5619c120d RDMA/cxgb4: Update RDMA/cxgb4 due to macro definition removal in cxgb4 driver
cxgb4 driver has duplicate definitions of registers which will be removed. This
patch updates the RDMA/cxgb4 driver accordingly.

Signed-off-by: Santosh Rastapur <santosh@chelsio.com>
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Reviewed-by: Sivakumar Subramani <sivasu@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-05 17:41:40 -04:00
Roland Dreier f747c34af4 RDMA/cxgb4: Fix endianness of addition to mpa->private_data_size
sparse correctly warns that if mpa->private_data_size is __be16, then
doing += on it is wrong, even if we do += htons(<something>) -- on a
little endian system, carries will go the wrong way.  Fix this up by
doing the addition in native byte order.

Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-07-08 18:02:33 -07:00
Thadeu Lima de Souza Cascardo 71b43fd573 RDMA/cxgb4: Fix crash when peer address is 0.0.0.0
When using rping -c -a 0.0.0.0 with iw_cxgb4, the system crashes when
rdma_connect() is called.  ip_dev_find() will return NULL, but pdev is
accessed anyway.

Checking that pdev is NULL and returning -ENODEV prevents the system
from crashing.

Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-06-03 22:59:15 -07:00
Vipul Pandya e572568fbc RDMA/cxgb4: Include vmalloc.h for vmalloc and vfree
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-21 09:00:34 -07:00
Vipul Pandya 67bbc05512 RDMA/cxgb4: Add query_qp support
This allows querying the QP state before flushing.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-18 13:22:37 -07:00
Vipul Pandya ec3eead217 RDMA/cxgb4: Remove kfifo usage
Using kfifos for ID management was limiting the number of QPs and
preventing NP384 MPI jobs.  So replace it with a simple bitmap
allocator.

Remove IDs from the IDR tables before deallocating them.  This bug was
causing the BUG_ON() in insert_handle() to fire because the ID was
getting reused before being removed from the IDR table.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-18 13:22:36 -07:00
Vipul Pandya d716a2a014 RDMA/cxgb4: Use vmalloc() for debugfs QP dump
This allows dumping thousands of QPs.  Log active open failures of
interest.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-18 13:22:35 -07:00
Vipul Pandya 422eea0a8c RDMA/cxgb4: DB Drop Recovery for RDMA and LLD queues
Add module option db_fc_threshold which is the count of active QPs
that trigger automatic db flow control mode.  Automatically transition
to/from flow control mode when the active qp count crosses
db_fc_theshold.

Add more db debugfs stats

On DB DROP event from the LLD, recover all the iwarp queues.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-18 13:22:33 -07:00
Vipul Pandya 4984037bef RDMA/cxgb4: Disable interrupts in c4iw_ev_dispatch()
Use GFP_ATOMIC in _insert_handle() if ints are disabled.

Don't panic if we get an abort with no endpoint found.  Just log a
warning.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-18 13:22:32 -07:00
Vipul Pandya 2c97478106 RDMA/cxgb4: Add DB Overflow Avoidance
Get FULL/EMPTY/DROP events from LLD.  On FULL event, disable normal
user mode DB rings.

Add modify_qp semantics to allow user processes to call into the
kernel to ring doobells without overflowing.

Add DB Full/Empty/Drop stats.

Mark queues when created indicating the doorbell state.

If we're in the middle of db overflow avoidance, then newly created
queues should start out in this mode.

Bump the C4IW_UVERBS_ABI_VERSION to 2 so the user mode library can
know if the driver supports the kernel mode db ringing.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-18 13:22:31 -07:00
Vipul Pandya 8d81ef34b2 RDMA/cxgb4: Add debugfs RDMA memory stats
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-18 13:22:29 -07:00
Steve Wise 14b9222808 RDMA/cxgb4: Drop peer_abort when no endpoint found
Log a warning and drop the abort message.  Otherwise we will do a
bogus wake_up() and crash.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-15 09:46:09 -07:00
Steve Wise 0f1dcfae6b RDMA/cxgb4: Always wake up waiters in c4iw_peer_abort_intr()
This fixes a race where an ingress abort fails to wake up the thread
blocked in rdma_init() causing the app to hang.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-15 09:46:04 -07:00
Steve Wise bd61baaf59 RDMA/cxgb4: Use dst parameter in import_ep()
Function import_ep() is incorrectly using ep->dst instead of the dst
ptr passed in.  This causes a crash when accepting new rdma connections
becase ep->dst is not initialized yet.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-05-08 11:17:04 -07:00
Linus Torvalds 0c2fe82a9b InfiniBand/RDMA changes for the 3.4 merge window. Nothing big really
stands out; by patch count lots of fixes to the mlx4 driver plus some
 cleanups and fixes to the core and other drivers.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.11 (GNU/Linux)
 
 iQIcBAABCAAGBQJPZ2THAAoJEENa44ZhAt0hMgkP/AwXjwzz6lYlIizytQ5KOH11
 CT/VoHLIGIwY31aRhZRHggWLEbJi8akgfh04K9PiSh/muFRPYk5KJDoQEoJV5Odv
 12krqtpZeL41YcAPq0wiyP3Ki5AZDCDumzWbOtmxE9m93mVfi3yFTTWDHFo/7SOx
 A2kUITdKuZhgBpCFYS23Gs8QTWcMPUlwNlM76edG90BjSySHsK15tbqTUaEOC6Ux
 SPG0p0c2YjlZCPmRObrCL65o5LFRVajinZ4rXN7rre4LEU+IuXgW+mQU2Kwy8z6a
 oMPE2l4OMSqj270r2PlVK087gGH69nKfLgLQLJiP0Id+KwdYUk7vQcA+Fu0jwjP3
 Ci/ahllvB76IiaNbax0vTy2ohCJmilLLotAP46NW0vPR2/KnmVy0Mqk8pXQQddw4
 tnAFNnafn/MjTty8GwqyXR/enJZs29ePcSxcYnKjXYRIgG4ldejL2wktgSra8+gb
 3/qFag1HRgZzcICkXGpHj7uWJ2KDe++1m6KTb0THUmrjuiel6ATFZpYoeRed3GfS
 ZMqpjZvuXM8nA9CrKMkzm5vIiUFF8Qq0hUTLR38F8FiNEhmC08JqH5PqjJ3Z18if
 R1yG4W4xmp/0ICHg4zyg6LWV3YsweDD+jSCJpW+KNBvu3HtYb41HIlK+i2TTmtPD
 3etEZZRwROAyYKcwN01p
 =DbLx
 -----END PGP SIGNATURE-----

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

Pull InfiniBand/RDMA changes for the 3.4 merge window from Roland Dreier:
 "Nothing big really stands out; by patch count lots of fixes to the
  mlx4 driver plus some cleanups and fixes to the core and other
  drivers."

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (28 commits)
  mlx4_core: Scale size of MTT table with system RAM
  mlx4_core: Allow dynamic MTU configuration for IB ports
  IB/mlx4: Fix info returned when querying IBoE ports
  IB/mlx4: Fix possible missed completion event
  mlx4_core: Report thermal error events
  mlx4_core: Fix one more static exported function
  IB: Change CQE "csum_ok" field to a bit flag
  RDMA/iwcm: Reject connect requests if cmid is not in LISTEN state
  RDMA/cxgb3: Don't pass irq flags to flush_qp()
  mlx4_core: Get rid of redundant ext_port_cap flags
  RDMA/ucma: Fix AB-BA deadlock
  IB/ehca: Fix ilog2() compile failure
  IB: Use central enum for speed instead of hard-coded values
  IB/iser: Post initial receive buffers before sending the final login request
  IB/iser: Free IB connection resources in the proper place
  IB/srp: Consolidate repetitive sysfs code
  IB/srp: Use pr_fmt() and pr_err()/pr_warn()
  IB/core: Fix SDR rates in sysfs
  mlx4: Enforce device max FMR maps in FMR alloc
  IB/mlx4: Set bad_wr for invalid send opcode
  ...
2012-03-21 10:33:42 -07:00
Roland Dreier f0e88aeb19 Merge branches 'cma', 'cxgb3', 'cxgb4', 'ehca', 'iser', 'mad', 'nes', 'qib', 'srp' and 'srpt' into for-next 2012-03-19 09:50:33 -07:00
Or Gerlitz 2e96691c31 IB: Use central enum for speed instead of hard-coded values
The kernel IB stack uses one enumeration for IB speed, which wasn't
explicitly specified in the verbs header file.  Add that enum, and use
it all over the code.

The IB speed/width notation is also used by iWARP and IBoE HW drivers,
which use the convention of rate = speed * width to advertise their
port link rate.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-03-05 09:25:16 -08:00
Kumar Sanghvi 91018f8632 RDMA/cxgb4: Add missing peer2peer check in MPAv2 code
Don't worry about p2p_type if peer2peer itself is not requested in the
first place.

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-02-25 17:45:02 -08:00