Commit Graph

72 Commits

Author SHA1 Message Date
Oren Duer c5057ddccb mlx4_core: Support creation of FMRs with pages smaller than 4K
Don't hard code a test against a minimum page shift of 12, since the
device may support smaller pages.  Test against the actual smallest
page size from the device capabilities.

Signed-off-by: Oren Duer <oren@mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-05-05 15:56:52 -07:00
Olaf Kirch bbdc2821db mlx4_core: Avoid recycling old FMR R_Keys too soon
When a FMR is unmapped, mlx4 resets the map count to 0, and clears the
upper part of the R_Key which is used as the sequence counter.

This poses a problem for RDS, which uses ib_fmr_unmap as a fence
operation.  RDS assumes that after issuing an unmap, the old R_Keys
will be invalid for a "reasonable" period of time. For instance,
Oracle processes uses shared memory buffers allocated from a pool of
buffers.  When a process dies, we want to reclaim these buffers -- but
we must make sure there are no pending RDMA operations to/from those
buffers.  The only way to achieve that is by using unmap and sync the
TPT.

However, when the sequence count is reset on unmap, there is a high
likelihood that a new mapping will be given the same R_Key that was
issued a few milliseconds ago.

To prevent this, don't reset the sequence count when unmapping a FMR.

Signed-off-by: Olaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:53 -07:00
Yevgeny Petrilin e463c7b197 mlx4_core: Add a way to set the "collapsed" CQ flag
Extend the mlx4_cq_resize() API with a way to set the "collapsed" flag
for the CQ being created.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-29 13:46:50 -07:00
Yevgeny Petrilin ed4d3c1061 mlx4_core: Add helper to move QP to ready-to-send
Avoid duplicating code in ethernet and FC modules.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-25 14:52:32 -07:00
Yevgeny Petrilin 38ae6a5354 mlx4_core: Add HW queues allocation helpers
Wrap doorbell, buffer and MTT allocation in helper functions for
ethernet and FC modules to use.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-25 14:27:08 -07:00
Vladimir Sokolovsky f5b3a096b1 mlx4_core: CQ resizing should pass a 0 opcode modifier to MODIFY_CQ
The call to mlx4_MODIFY_CQ() had a typo so that mlx4_cq_resize() was
actually asking the FW to modify a CQ's interrupt moderation rather than
asking it to resize a CQ.

Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Yevgeny Petrilin 6296883ca4 mlx4_core: Move kernel doorbell management into core
In addition to mlx4_ib, there will be ethernet and FC consumers of
mlx4_core, so move the code for managing kernel doorbells into the
core module to avoid having to duplicate this multiple times.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-23 11:55:45 -07:00
Eli Cohen 4ff08a76bc IB/mlx4: Fix incorrect comment
mlx4 hardware does not support external DDR memory.  Moreover, UAR
area (BAR 2) can change depending on FW version.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:35 -07:00
Eli Cohen 4dc51b3258 IB/mlx4: Fix race when detaching a QP from a multicast group
When detaching the last QP from an MCG entry, we need to make
sure that at any time, there will be no entry with zero number of
QPs which is linked to the list of the MCGs of the corresponding
hash index.  So don't write back the MCG entry if we are removing the
last QP; just unlink the entry.

Also, remove an unnecessary MCG read when attaching a QP requires
allocation of a new entry in the AMGM.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:35 -07:00
Vladimir Sokolovsky bbf8eed1a0 IB/mlx4: Add support for resizing CQs
Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:33 -07:00
Eli Cohen 3fdcb97f0b IB/mlx4: Add support for modifying CQ moderation parameters
Signed-off-by: Eli Cohen <eli@mellnaox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:33 -07:00
Jack Morgenstein 9b1f38515c mlx4_core: Increase max number of QPs to 128K
With the advent large clusters which utilize multicore hosts, 64K QPs
is not enough.  We should increase the default maximum for QPs to 128K.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:32 -07:00
Eli Cohen b832be1e40 IB/mlx4: Add IPoIB LSO support
Add TSO support to the mlx4_ib driver.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:09:27 -07:00
Eli Cohen 8ff095ec4b IB/mlx4: Add IPoIB checksum offload support
ConnectX devices support checksum generation and verification of TCP
and UDP packets for UD IPoIB messages.  This patch checks if the HCA
supports this and sets the IB_DEVICE_UD_IP_CSUM capability flag if it
does.  It implements support for handling the IB_SEND_IP_CSUM send
flag and setting the csum_ok field in receive work completions.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Ali Ayub <ali@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:10 -07:00
Roland Dreier 37608eea86 mlx4_core: Fix confusion between mlx4_event and mlx4_dev_event enums
The struct mlx4_interface.event() method was supposed to get an enum
mlx4_dev_event, but the driver code was actually passing in the
hardware enum mlx4_event values.  Fix up the callers of
mlx4_dispatch_event() so that they pass in the right type of value,
and fix up the event method in mlx4_ib so that it can handle the enum
mlx4_dev_event values.

This eliminates the need for the subtype parameter to the event
method, so remove it.

This also fixes the sparse warning

    drivers/net/mlx4/intf.c:127:48: warning: mixing different enum types
    drivers/net/mlx4/intf.c:127:48:     int enum mlx4_event  versus
    drivers/net/mlx4/intf.c:127:48:     int enum mlx4_dev_event

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:08 -07:00
Roland Dreier ca28121114 mlx4_core: Move opening brace of function onto a new line
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-04-16 21:01:04 -07:00
Jack Morgenstein 11e75a7455 mlx4_core: Move table_find from fmr_alloc to fmr_enable
mlx4_table_find (for FMR MPTs) requires that ICM memory already be
mapped.  Before this fix, FMR allocation depended on ICM memory
already being mapped for the MPT entry.  If all currently mapped
entries are taken, the find operation fails (even if the MPT ICM table
still had more entries, which were just not mapped yet).

This fix moves the mpt find operation to fmr_enable, to guarantee that
any required ICM memory mapping has already occurred.

Found by Oren Duer of Mellanox.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-14 10:43:48 -08:00
Olof Johansson 29c271123d mlx4_core: Fix build break (missing include)
Commit 313abe55 ("mlx4_core: For 64-bit systems, vmap() kernel queue
buffers") caused this to pop up on powerpc allyesconfig, looks like a
missing include file:

    drivers/net/mlx4/alloc.c: In function 'mlx4_buf_alloc':
    drivers/net/mlx4/alloc.c:162: error: implicit declaration of function 'vmap'
    drivers/net/mlx4/alloc.c:162: error: 'VM_MAP' undeclared (first use in this function)
    drivers/net/mlx4/alloc.c:162: error: (Each undeclared identifier is reported only once
    drivers/net/mlx4/alloc.c:162: error: for each function it appears in.)
    drivers/net/mlx4/alloc.c:162: warning: assignment makes pointer from integer without a cast
    drivers/net/mlx4/alloc.c: In function 'mlx4_buf_free':
    drivers/net/mlx4/alloc.c:187: error: implicit declaration of function 'vunmap'

Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-11 14:19:42 -08:00
Roland Dreier b57aacfa7a mlx4_core: Clean up struct mlx4_buf
Now that struct mlx4_buf.u is a struct instead of a union because of
the vmap() changes, there's no point in having a struct at all.  So
move .direct and .page_list directly into struct mlx4_buf and get rid
of a bunch of unnecessary ".u"s.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-06 21:17:59 -08:00
Jack Morgenstein 313abe55a8 mlx4_core: For 64-bit systems, vmap() kernel queue buffers
Since kernel virtual memory is not a problem on 64-bit systems, there
is no reason to use our own 2-layer page mapping scheme for large
kernel queue buffers on such systems.  Instead, map the page list to a
single virtually contiguous buffer with vmap(), so that can we access
buffer memory via direct indexing.

Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-06 21:17:45 -08:00
Roland Dreier f33afc26dc IB: Avoid marking __devinitdata as const
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:44 -08:00
Jack Morgenstein 893da75956 mlx4_core: Don't read reserved fields in mlx4_QUERY_ADAPTER()
The firmware QUERY_ADAPTER command does not return vendor_id,
device_id, and revision_id; eliminate these fields from the query.

Initialize the rev_id field of the mlx4 device via init_node_data (MAD
IFC query), as is done in the query_device verb implementation.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:43 -08:00
Roland Dreier e8f9b2ed98 mlx4_core: Fix more section mismatches
Commit 3d73c288 ("mlx4_core: Fix section mismatches") fixed some of
the section mismatches introduced when error recovery was added, but
there were still more cases of errory recovery code calling into
__devinit code from regular .text.  Fix this by getting rid of the
now-incorrect __devinit annotations.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-02-04 20:20:41 -08:00
Jack Morgenstein 5920869f1e mlx4_core: Fix max_eqs masking in QUERY_DEV_CAP
log_max_eqs is a 4-bit field, not a 3-bit field in the response to the
QUERY_DEV_CAP FW command, so we should mask with 0xf instead of 0x7
when reading it.

Found by Yossi Leybovitch of Mellanox.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25 14:15:29 -08:00
Jack Morgenstein 9ed87fd34c mlx4_core: Fix state check in mlx4_qp_modify()
When checking the states passed in, mlx4_qp_modify() accidentally checks
cur_state twice rather than checking cur_state and new_state.  Fix this
to make sure that both values are in-bounds.

Since these values may be passed in from userspace, this bug results in
userspace being able to trigger an oops.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Cc: stable <stable@kernel.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-11-20 13:01:28 -08:00
Jack Morgenstein e383d19e90 mlx4_core: Fix thinko in QP destroy (incorrect bitmap_free)
Fix thinko in commit eaf559bf ("mlx4_core: Don't free special QPs in
QP number bitmap").  The old commit had the logic exactly backwards
and ended up freeing *only* special QPs, which not only left the
original bug in place but also introduced the problem that the QP
number bitmap would get full after a while.

Found by Dotan Barak of Mellanox.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-11-14 08:20:03 -08:00
Ali Ayoub 3bba11e5c4 mlx4_core: Fix possible bad free in mlx4_buf_free()
When mlx4_buf_free() is called from the error path of
mlx4_buf_alloc(), it may be passed a buffer structure that does not
have all pages filled in.  Add a check for NULL to mlx4_buf_free() so
we avoid passing NULL to dma_free_coherent() (which will crash).

Signed-off-by: Ali Ayoub <ali@mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-11-13 15:26:57 -08:00
Jens Axboe 642f149031 SG: Change sg_set_page() to take length and offset argument
Most drivers need to set length and offset as well, so may as well fold
those three lines into one.

Add sg_assign_page() for those two locations that only needed to set
the page, where the offset/length is set outside of the function context.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-10-24 11:20:47 +02:00
Linus Torvalds 0b776eb542 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  mlx4_core: Increase command timeout for INIT_HCA to 10 seconds
  IPoIB/cm: Use common CQ for CM send completions
  IB/uverbs: Fix checking of userspace object ownership
  IB/mlx4: Sanity check userspace send queue sizes
  IPoIB: Rewrite "if (!likely(...))" as "if (unlikely(!(...)))"
  IB/ehca: Enable large page MRs by default
  IB/ehca: Change meaning of hca_cap_mr_pgsize
  IB/ehca: Fix ehca_encode_hwpage_size() and alloc_fmr()
  IB/ehca: Fix masking error in {,re}reg_phys_mr()
  IB/ehca: Supply QP token for SRQ base QPs
  IPoIB: Use round_jiffies() for ah_reap_task
  RDMA/cma: Fix deadlock destroying listen requests
  RDMA/cma: Add locking around QP accesses
  IB/mthca: Avoid alignment traps when writing doorbells
  mlx4_core: Kill mlx4_write64_raw()
2007-10-23 09:56:11 -07:00
Jens Axboe 45711f1af6 [SG] Update drivers to use sg helpers
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-10-22 21:19:53 +02:00
Jack Morgenstein 77109cc282 mlx4_core: Increase command timeout for INIT_HCA to 10 seconds
The current INIT_HCA firmware command timeout is sufficient for the
default number of resources (QPs, CQs, etc) being allocated, but if
the HCA profile is modified to increase the amount of resources, then
a spurious timeout is detected and HCA initialization fails.

Increase the timeout for the INIT_HCA command to 10 seconds, which
also brings it into line with all the other command timeouts.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-21 15:06:04 -07:00
Roland Dreier b027cacdab mlx4_core: Fix infinite loop on device initialization
Commit 3d73c288 ("mlx4_core: Fix section mismatches") introduced a
stupid bug in device init: when some of mlx4_init_one() was split off
into __mlx4_init_one(), the call from the main mlx4_init_one()
function was back to mlx4_init_one() rather than to __mlx4_init_one(),
which leads to an obvious infinite loop if the function is every
called.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-13 14:10:50 -07:00
Roland Dreier 3d73c2884f mlx4_core: Fix section mismatches
Commit ee49bd93 ("mlx4_core: Reset device when internal error is
detected") introduced some section mismatch problems when
CONFIG_HOTPLUG=n, because the error recovery code tears down and
reinitializes the device after everything is loaded, which ends up
calling into lots of code marked __devinit and __devexit from regular
.text.  Fix this by getting rid of these now-incorrect section
markers.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-10 15:43:54 -07:00
Roland Dreier 2e61c646ed mlx4_core: Use mmiowb() to avoid firmware commands getting jumbled up
Firmware commands are sent to the HCA by writing multiple words to a
command register block.  Access to this block of registers is
serialized with a mutex.  However, on large SGI systems writes to the
register block may be reordered within the system interconnect and
reach the HCA in a different order than they were issued (even with
the mutex).  Fix this by adding an mmiowb() before dropping the mutex.

This bug was observed with real workloads with the similar FW command
code in the mthca driver, and adding the mmiowb() as in commit
66547550 ("IB/mthca: Use mmiowb() to avoid firmware commands getting
jumbled up") was confirmed to fix the problems, so we should add the
same fix to mlx4.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:18 -07:00
Jack Morgenstein e57ac0c297 mlx4_core: Increase max number of QPs per multicast group to 56
Increase the number of QPs allowed per multicast group from 8 to 56.
This allows for one QP per core on 16-core systems, which are now
quite common, and allows some space for future growth.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:16 -07:00
Jack Morgenstein 8ad11fb6b0 IB/mlx4: Implement FMRs
Implement FMRs for mlx4.  This is an adaptation of code from mthca.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:16 -07:00
Jack Morgenstein d7bb58fb1c mlx4_core: Write MTTs from CPU instead with of WRITE_MTT FW command
Write MTT entries directly to ICM from the driver (eliminating use of
WRITE_MTT command).  This reduces the number of FW commands needed to
register an MR by at least a factor of 2 and speeds up memory
registration significantly.  This code will also be used to implement
FMRs.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:16 -07:00
Roland Dreier 121964ec38 mlx4_core: Fix meaning of dev->caps.reserved_mtts
Everything that uses caps.reserved_mtts expects it to be a count of MTT
segments, not MTT entries.  So convert the value that the FW gives us to
a count of segments.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:16 -07:00
Roland Dreier cf78237d7b mlx4_core: Reserve the correct number of MTT segments
Taking ilog2(dev->caps.reserved_mtts) to find out the order to pass to
the MTT buddy allocator will do the wrong thing if reserved_mtts is ever
not a power of 2.  Be safe and use fls(dev->caps.reserved_mtts - 1).

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:16 -07:00
Jack Morgenstein 5b0bf5e25e mlx4_core: Support ICM tables in coherent memory
Enable having ICM tables in coherent memory, and use coherent memory
for the dMPT table.  This will allow writing MPT entries for MRs both
via the SW2HW_MPT command and also directly by the driver for FMR
remapping without needing to flush or worry about cacheline boundaries.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:15 -07:00
Jack Morgenstein cd9281d873 IB/mlx4: Display misc device information under /sys/class/infiniband/
display the following device information under /sys/class/infiniband/mlx4_X:
board_id, fw_ver, hw_rev, hca_type.

This patch makes this information available to userspace utilities
such as ibstat and ibv_devinfo.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:14 -07:00
Roland Dreier ea98054fef mlx4_core: Change capability decoding: SRC->XRC
The SRC ("scalable RC") transport has been renamed to XRC ("extended 
RC"), to avoid having an abbreviation that is so easily confused with an 
abbreviation for "source."  Update the HCA capability decoding output to 
use the new name.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:13 -07:00
Roland Dreier d7dc3ccbe4 IB/mlx4: Fix up SRQ limit_watermark endianness
mlx4_srq_query() returns a big-endian 16-bit value through an int *,
which screws up sparse checking.  Fix this so that a CPU-endian value
is returned.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:06 -07:00
Michael S. Tsirkin 08fb105540 mlx4_core: Enable MSI-X by default
Recover from MSI-X errors by automatically falling back on regular
interrupt, instead of asking the user to do this manually.  This makes
it possible to enable MSI-X by default, and will make it possible to
get rid of the msi_x module option in the future.

Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:05 -07:00
Roland Dreier eaf559bf56 mlx4_core: Don't free special QPs in QP number bitmap
Special QPs are not allocated using the regular QP number bitmap, so
when they are destroyed, their QP number should not be freed in the
bitmap.

Found by Dotan Barak of Mellanox.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:05 -07:00
Dotan Barak 36ce10d3e8 mlx4_core: Use enum value GO_BIT_TIMEOUT_MSECS
Rename GO_BIT_TIMEOUT to GO_BIT_TIMEOUT_MSECS for clarity, and
actually use it as the go bit timeout (instead of having the define
but then ignoring it and using a hard-coded 10 * HZ for the actual
timeout).

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-10-09 19:59:04 -07:00
Eli Cohen 947b2a8083 mlx4_core: Wait 1 second after reset before accessing device
Put a 1000 msec delay after resetting the device before attempting to
do config cycles on it.  Not waiting causes system hangs on some
chipsets, e.g. Intel E7520, when the driver is loaded.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-08-13 08:47:44 -07:00
Jack Morgenstein 0172e2e14c mlx4_core: Remove kfree() in mlx4_mr_alloc() error flow
mlx4_mr_alloc() doesn't actually allocate mr (it just initializes the
pointer that the caller passes in), so it shouldn't free it if an
error occurs.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-28 08:30:45 -07:00
Roland Dreier 0981582dbf mlx4_core: Change command token on timeout
The FW command token is currently only updated on a command completion
event. This means that on command timeout, the same token will be
reused for new command, which results in a mess if the timed out
command *does* eventually complete.

This is the same change as the patch for mthca from Michael
S. Tsirkin <mst@dev.mellanox.co.il> that was just merged.  It seems
sensible to avoid gratuitous differences in FW command processing
between mthca and mlx4.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-20 21:19:43 -07:00
Jack Morgenstein c9f2ba5ed2 IB/mlx4: Increase max outstanding RDMA reads as target
Change the maximum number of outstanding RDMA reads allowed as a
target from 4 to 16 to per QP.  This allows RDMA read operations to
pipeline better.

Pointed out by Dotan Barak and Sagi Rotem.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17 20:50:50 -07:00