mthca does not restore the following PCI-X/PCI Express registers after reset:
PCI-X device: PCI-X command register
PCI-X bridge: upstream and downstream split transaction registers
PCI Express : PCI Express device control and link control registers
This causes instability and/or bad performance on systems where one of
these registers is set to a non-default value by BIOS.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When ipoib_stop() is called it first calls netif_stop_queue() to stop
the kernel from passing more packets to the network driver. However,
the completion handler may call netif_wake_queue() re-enabling packet
transfer.
This might result in leaks (we see AH leaks which we think can be
attributed to this bug) as new packets get posted while the interface
is going down.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Michael Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If we post a list of length exactly a multiple of 256, nreq in
doorbell gets set to 256 which is wrong: it should be encoded by 0.
This is because we only zero it out on the next WR, which may not be
there. The solution is to ring the doorbell after posting a WQE, not
before posting the next one.
This is the same bug that we just fixed for QPs with non-shared RQ.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
At this point, the core QP structure hasn't been initialized, so what's
in there isn't valid. Get the same information elsewhere.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The problem was that node A's sending thread, which handles sending RDMA
read response data, would write the trigger word, the last packet would
be sent, node B would send a new RDMA read request, node A's interrupt
handler would initialize s_rdma_sge, then node A's sending thread would
update s_rdma_sge. This didn't happen very often naturally but was more
frequent with 1 byte RDMA reads. Rather than adding more locking or
increasing the QP structure size and copying sge data, I modified the
copy routine to update the pointers before writing the trigger word to
avoid the update race.
Signed-off-by: Ralph Campbell <ralphc@pathscale.com>
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fixed so it works on the PE-800. It had not previously been updated to
match PE-800 receive interrupt differences from HT-400.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This is required for even semi-decent performance on OpenIB.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix NULL deref due to pcidev being clobbered before dd->ipath_f_cleanup()
was called.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix the interface version that gets exported to userspace.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Make sure modify_qp won't modify the QP if any of the changes failed.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The local loopback path for RC can lock the rkey table lock without
blocking interrupts. The receive interrupt path can then call
ipath_rkey_ok() and deadlock. Remove the redundant lock.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If we post a list of length 256 exactly, nreq in doorbell gets set to
256 which is wrong: it should be encoded by 0. This is because we
only zero it out on the next WR, which may not be there. The solution
is to ring the doorbell after posting a WQE, not before posting the
next one.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
In ib_umem_release_on_close(), if the kmalloc() fails, then a
reference to current->mm will be leaked. Fix this by adding a mmput()
instead of just returning on kmalloc() failure.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When flushing out queued commands after a successful device reset,
make sure that SRP completes the right commands, instead of calling
scsi_done on the command passed into the device reset handler over and
over.
Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If a reconnection attempt fails, then SRP does two scsi_host_put()s.
This is a historical relic from an earlier version of the driver that
took a reference on the scsi_host before trying to reconnect, so get
rid of the extra scsi_host_put().
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Sending a DREQ may fail, for example because the remote target has
already broken the connection. If so, then SRP should not wait for
the disconnection to complete, because it never will.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Setting fw_cmd_doorbell allows FW command to be queued using posted
writes instead of requiring polling on a "go" bit, so it should be a
performance boost. However, the option causes problems with at least
some device/firmware combinations, so set the default to 0 until we
understand what's going on better.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix race condition during destruction calls to avoid possibility of
accessing object after it has been freed. Instead of waking up a wait
queue directly, which is susceptible to a race where the object is
freed between the reference count going to 0 and the wake_up(), use a
completion to wait in the function doing the freeing.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The ipath driver's table of PCI IDs needs a { 0, } entry at the end.
This makes all of the device aliases visible to userspace so hotplug
loads the module for all supported devices. Without the patch,
modinfo ipath_core only shows:
alias: pci:v00001FC1d0000000Dsv*sd*bc*sc*i*
instead of the correct:
alias: pci:v00001FC1d00000010sv*sd*bc*sc*i*
alias: pci:v00001FC1d0000000Dsv*sd*bc*sc*i*
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Addresses for ioremap must be calculated off of pci_resource_start;
we can't directly use the bus address as seen by the HCA. Fix the
code that remaps device memory for FMR access.
Based on patch by Klaus Smolin.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When deleting a child interface with a non-default P_Key via
/sys/class/net/ibX/delete_child, the interface must be freed with
free_netdev() (rather than kfree() on the private data).
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix races in in destroying various objects. If a destroy routine
waits for an object to become free by doing
wait_event(&obj->wait, !atomic_read(&obj->refcount));
/* now clean up and destroy the object */
and another place drops a reference to the object by doing
if (atomic_dec_and_test(&obj->refcount))
wake_up(&obj->wait);
then this is susceptible to a race where the wait_event() and final
freeing of the object occur between the atomic_dec_and_test() and the
wake_up(). And this is a use-after-free, since wake_up() will be
called on part of the already-freed object.
Fix this in mthca by replacing the atomic_t refcounts with plain old
integers protected by a spinlock. This makes it possible to do the
decrement of the reference count and the wake_up() so that it appears
as a single atomic operation to the code waiting on the wait queue.
While touching this code, also simplify mthca_cq_clean(): the CQ being
cleaned cannot go away, because it still has a QP attached to it. So
there's no reason to be paranoid and look up the CQ by number; it's
perfectly safe to use the pointer that the callers already have.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If a SCSI abort completes, or the command completes successfully, then
the driver must remove the command from its queue of pending
commands. Similarly, if a device reset succeeds, then all commands
queued for the given device must be removed from the queue.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The code to display local_link_integrity_errors and
excessive_buffer_overrun_errors in
/sys/class/infiniband/<hca>/ports/<n>/counters/
uses the wrong shift to extract the 4 bit values.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Names that are the opposite of their intended meanings are not so helpful.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The reset code now turns off the PRESENT flag during a reset, so that
other code won't attempt to access a device that's in mid-reset.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Remember when the verbs layer unregisters from the lower-level code.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Different ipath hardware types have different numbers of buffers
available, so we decide on the counts ourselves unless we are specifically
overridden with a module parameter.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Some systems do not set up 64-bit maps on systems with 2GB or less of
memory installed, so we have to fall back to trying a 32-bit setup.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
We were accidentally exposing the "reset" sysfs file more than once
per device.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
GuidInfo records have 8 byte GUIDs in them, so an index should be
multiplied by 8 to get an offset. mthca_query_gid() was incorrectly
multiplying by 16.
Noticed by Leonid Keller <leonid@mellanox.co.il>.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch makes the needlessly global mthca_update_rate() static.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Only check that RMPP version is not specified when MAD class does not
support RMPP. Just because a class is allowed to use RMPP doesn't
mean that rmpp_version needs to be set for the MAD agent to
register. Checking this was a recent change which was too pedantic.
Signed-off-by: Hal Rosenstock <halr@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If a SCSI abort succeeds, then the aborted request should to be
removed from the list of pending requests. This fixes list corruption
after an abort occurs.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The driver allocates SRQ WQEs size with a power of 2 size both for
Tavor and for memfree. For Tavor, however, the hardware only requires
the WQE size to be a multiple of 16, not a power of 2, and the max
number of scatter-gather allowed is reported accordingly by the
firmware (and this is the value currently returned by
ib_query_device() and ibv_query_device()).
If the max number of scatter/gather entries reported by the FW is used
when creating an SRQ, the creation will fail for Tavor, since the
required WQE size will be increased to the next power of 2, which
turns out to be larger than the device permitted max WQE size (which
is not a power of 2).
This patch reduces the reported SRQ max wqe size so that it can be used
successfully in creating an SRQ on Tavor HCAs.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When allocating gid_cache, use kmalloc(sizeof *gid_cache, ...) rather
than kmalloc(sizeof *pkey_cache, ...). It doesn't really matter which
one is used, since the size ends up the same either way, but it's much
better to say what we mean.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
We know ipoib_flush_paths() is called from plain process context with
interrupts enabled, since it does wait_for_completion(). So there's
no need to use spin_lock_irqsave() -- spin_lock_irq() is fine.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ib_sa_cancel_query() must be called with priv->lock held since
a completion might arrive and set path->query to NULL.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The PCI spec recommends against drivers playing with a device's PCI
read burst size, and says that systems software should configure it.
And we actually have users that report that changing it from the
default set by BIOS hurts performance and/or stability for them. On
the other hand, the Mellanox Programmer's Reference Manual recommends
turning it up all the way to the maximum value. Some tests conducted
here in the lab do not show performance improvement from this tuning,
but this might be just me.
As a work-around, make this tuning an option, off by default (safe
value), with an eye towards removing it completely one day if no one
complains.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Make IPoIB's send and receive queue sizes tunable via module
parameters ("send_queue_size" and "recv_queue_size"). This allows the
queue sizes to be enlarged to fix disastrously bad performance on some
platforms and workloads, without bloating memory usage when large
queues aren't needed.
Signed-off-by: Shirley Ma <xma@us.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipoib_mcast_restart_task() might free an mcast object while a join
request is still outstanding, leading to an oops when the query
completes. Fix this by waiting for query to complete, similar to what
ipoib_stop_thread() is doing. The wait for mcast completion code is
consolidated in wait_for_mcast_join().
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Push translation of static rate to HCA format into low-level drivers,
where it belongs. For static rate encoding, use encoding of rate
field from IB standard PathRecord, with addition of value 0, for
backwards compatibility with current usage. The changes are:
- Add enum ib_rate to midlayer includes.
- Get rid of static rate translation in IPoIB; just use static rate
directly from Path and MulticastGroup records.
- Update mthca driver to translate absolute static rate into the
format used by hardware. This also fixes mthca's static rate
handling for HCAs that are capable of 4X DDR.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Consolidate IPoIB's private neighbour data handling into
ipoib_neigh_alloc() and ipoib_neigh_free(). This will make it easier
to keep track of the neighbour structures that IPoIB is handling, and
is a nice cleanup of the code:
add/remove: 2/1 grow/shrink: 1/8 up/down: 100/-178 (-78)
function old new delta
ipoib_neigh_alloc - 61 +61
ipoib_neigh_free - 36 +36
ipoib_mcast_join_finish 1288 1291 +3
path_rec_completion 575 573 -2
ipoib_mcast_join_task 664 660 -4
ipoib_neigh_destructor 101 92 -9
ipoib_neigh_setup_dev 14 3 -11
ipoib_neigh_setup 17 - -17
path_free 238 215 -23
ipoib_mcast_free 329 306 -23
ipoib_mcast_send 718 684 -34
neigh_add_path 705 650 -55
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Change the mthca debugging trace output code so that it can enabled
and disabled at runtime with the debug_level module parameter in
sysfs. Also, don't allow CONFIG_INFINIBAND_MTHCA_DEBUG to be disabled
unless CONFIG_EMBEDDED is selected. We want users (and especially
distros) to have this turned on unless they really need to save space,
because by the time we want debugging output, it's usually too late to
rebuild a kernel.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Don't allow CONFIG_INFINIBAND_IPOIB_DEBUG to be disabled unless
CONFIG_EMBEDDED is selected. We want users (and especially distros)
to have this turned on unless they really need to save space, because
by the time we want debugging output, it's usually too late to rebuild
a kernel. The debugging output can be controlled at runtime via the
debug_level module parameter in sysfs.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
We have seen the following OOPs in cancel_mads, when restarting opensm
multiple times:
Call Trace:
[<c010549b>] show_stack+0x9b/0xb0
[<c01055ec>] show_registers+0x11c/0x190
[<c01057cd>] die+0xed/0x160
[<c031b966>] do_page_fault+0x3f6/0x5d0
[<c010511f>] error_code+0x4f/0x60
[<f8ac4e38>] cancel_mads+0x128/0x150 [ib_mad]
[<f8ac2811>] unregister_mad_agent+0x11/0x130 [ib_mad]
[<f8ac2a12>] ib_unregister_mad_agent+0x12/0x20 [ib_mad]
[<f8b10f23>] ib_umad_close+0xf3/0x130 [ib_umad]
[<c0162937>] __fput+0x187/0x1c0
[<c01627a9>] fput+0x19/0x20
[<c0160f7a>] filp_close+0x3a/0x60
[<c0121ca8>] put_files_struct+0x68/0xa0
[<c0103cf7>] do_signal+0x47/0x100
[<c0103ded>] do_notify_resume+0x3d/0x40
[<c0103f9e>] work_notifysig+0x13/0x25
We traced this back to local_completions unlocking mad_agent_priv->lock
while still keeping a pointer into local_list. A later call to
list_del(&local->completion_list) would then corrupt the list.
To fix this, remove the entry from local_list after looking it up but
before releasing mad_agent_priv->lock, to prevent cancel_mads from
finding and freeing it.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Integrate the ipath core and OpenIB drivers into the kernel build
infrastructure. Add entry to MAINTAINERS.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The ipath_verbs.c file implements the driver-specific components of the
kernel's Infiniband verbs layer.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Completion queues, local and remote memory keys, and memory region
support.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This is an implementation of the Infiniband RC ("reliable connection")
protocol.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
These files implement the Infiniband UC ("unreliable connection") and UD
("unreliable datagram") protocols.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
These header files are used by the layered Infiniband driver.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The layering interfaces are used to implement the Infiniband protocols
and the ethernet emulation driver.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
These files introduce a char device that userspace apps use to gain
direct memory-mapped access to the InfiniPath hardware, and routines for
pinning and unpinning user memory in cases where the hardware needs to
DMA into the user address space.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The ipathfs filesystem contains files that are not appropriate for
sysfs, because they contain binary data. The hierarchy is simple; the
top-level directory contains driver-wide attribute files, while numbered
subdirectories contain per-device attribute files.
Our userspace code currently expects this filesystem to be mounted on
/ipathfs, but a final location has not yet been chosen.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
EEPROM support, interrupt handling, statistics gathering, and write
combining management for x86_64.
A note regarding i2c: The Atmel EEPROM hardware we use looks like an
i2c device electrically, but is not i2c compliant at all from a
functional perspective. We tried using the kernel's i2c support to
talk to it, but failed.
Normal i2c devices have a single 7-bit or 10-bit i2c address that they
respond to. Valid 7-bit addresses range from 0x03 to 0x77. Addresses
0x00 to 0x02 and 0x78 to 0x7F are special reserved addresses
(e.g. 0x00 is the "general call" address.) The Atmel device, on the
other hand, responds to ALL addresses. It's designed to be the only
device on a given i2c bus. A given i2c device address corresponds to
the memory address within the i2c device itself.
At least one reason why the linux core i2c stuff won't work for this
is that it prohibits access to reserved addresses like 0x00, which are
really valid addresses on the Atmel devices.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipath_init_chip.c sets up an InfiniPath device for use.
ipath_diag.c permits userspace diagnostic tools to read and write a
chip's registers. It is different in purpose from the mmap interfaces
to the /sys/bus/pci resource files.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This file contains routines and definitions specific to InfiniPath
devices that have PCI Express interfaces.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The ipath_ht400.c file contains routines and definitions specific to
HyperTransport-based InfiniPath devices.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipath_common.h and ips_common.h contain definitions shared between
userspace and the kernel.
ipath_kernel.h is the core driver header file.
ipath_debug.h contains mask values used for controlling driver debugging.
ipath_registers.h contains bitmask definitions used in chip registers.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The ipath driver is a low-level driver for PathScale InfiniPath host
channel adapters (HCAs) based on the HT-400 and PE-800 chips, including
the InfiniPath HT-460, the small form factor InfiniPath HT-460, the
InfiniPath HT-470 and the Linux Networx LS/X.
The ipath_driver.c file contains much of the low-level device handling
code.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add RMPP support for additional management classes that support it.
Also, validate RMPP is consistent with management class specified.
Signed-off-by: Hal Rosenstock <halr@voltaire.com>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Received responses are currently matched against sent requests based
on TID only. According to the spec, responses should match based on
the combination of TID, management class, and requester LID/GID.
Without the additional qualification, an agent that is responding to
two requests, both of which have the same TID, can match RMPP ACKs
with the incorrect transaction. This problem can occur on the SM node
when responding to SA queries.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Quite a few cleanup functions in mthca were marked as __devexit.
However, they could also be called from error paths during
initialization, so they cannot be marked that way. Just delete all of
the incorrect annotations.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipoib_hard_header() needs to handle the case that daddr is NULL. This
can happen when packets are injected via a raw socket, and IPoIB
shouldn't oops in this case.
Reported by Anton Blanchard <anton@samba.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The previous patch for Tavor broke MemFree logic.
The driver should perform limit check only for Tavor. For MemFree,
the check is incorrect, since ds (WQE stride) is always a power-of-2
(although the max_desc_size may not be).
In Tavor, however, WQE stride and desc_size are the same, and are not
necessarily power-of-2. The check was really for the WQE stride (and
it Tavor, we use max_desc_size for the stride).
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The recently merged patch to create a fake scatterlist for non-SG SCSI
commands had a bug: the driver ended up doing dma_unmap_sg() on a
scatterlist scmnd->request_buffer rather than the fake scatter list it
created. Fix this so that the driver unmaps the same thing it maps.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch causes the network interface to respond to P_Key change
events correctly. As a result, you'll see a child interface in the
"RUNNING" state (netif_carrier_on()) only when the corresponding P_Key
is configured by the SM. When SM removes a P_Key, the "RUNNING" state
will be disabled for the corresponding network interface. To
implement this, I added IB_EVENT_PKEY_CHANGE event handling. To
prevent flushing the device before the device is open by the "delay
open" mechanism, I added an additional device flag called
IPOIB_FLAG_INITIALIZED.
This also prevents the child network interface from trying to join to
multicast groups until the PKEY is configured. We used to get error
messages like:
ib0.f2f2: couldn't attach QP to multicast group ff12:401b:f2f2:0:0:0:ffff:ffff
in this case. To fix this, I just check IPOIB_FLAG_OPER_UP flag in
ipoib_set_mcast_list().
Signed-off-by: Leonid Arsh <leonida@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If the call to mthca_MODIFY_QP() failed, then mthca_modify_qp() would
still do some things it shouldn't, such as store away attributes for
special QPs. Fix this, and simplify the code, by simply jumping to
the exit path if mthca_MODIFY_QP() fails.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
With the current IPoIB driver, the status of network interfaces stays
"RUNNING" even if the link goes down (for example because a cable is
unplugged). Fix this by flushing the IPoIB interface when the link
goes down.
Signed-off-by: Leonid Arsh <leonida@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
mthca_alloc_sqp() by mthca_set_qp_size() need to set qp->transport
before calling mthca_set_qp_size(), since the value is used there.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When setting the shared receive queue (SRQ) watermark in a modify SRQ
operation, make sure that the supplied value is not larger than the
full size of the SRQ.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Guarantee the calculated work queue entry size does not exceed the max
allowable WQE size when creating an SRQ. This is a problem with Arbel
in Tavor-compatibility mode because the current WQE size computation
method rounds up to next power of 2.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add a check that the modify QP parameters sgid_index and path_mtu are
valid, since they might come from userspace.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Since the SCSI midlayer is moving towards entirely getting rid of
commands with use_sg == 0, we should treat this case as an exception.
Therefore, change the IB SRP initiator to create a fake scatterlist
for these commands with sg_init_one(). This simplifies the flow of
DMA mapping and unmapping, since SRP can just use dma_map_sg() and
dma_unmap_sg() unconditionally, rather than having to choose between
the dma_{map,unmap}_sg() and dma_{map,unmap}_single() variants.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipoib_ib_dev_flush() should get passed cpriv->dev, not &cpriv->dev.
Signed-off-by: Leonid Arsh <leonida@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
struct neigh_ops currently has a destructor field, which no in-kernel
drivers outside of infiniband use. The infiniband/ulp/ipoib in-tree
driver stashes some info in the neighbour structure (the results of
the second-stage lookup from ARP results to real link-level path), and
it uses neigh->ops->destructor to get a callback so it can clean up
this extra info when a neighbour is freed. We've run into problems
with this: since the destructor is in an ops field that is shared
between neighbours that may belong to different net devices, there's
no way to set/clear it safely.
The following patch moves this field to neigh_parms where it can be
safely set, together with its twin neigh_setup. Two additional
patches in the patch series update ipoib to use this new interface.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix endianness handling of srq_limit: it is big-endian in the context
structure, so we need to swab it before returning it.
Also add support for srq_limit query for Tavor (non-MemFree) HCAs.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
In neigh_add_path(), the queue of delayed packets can never be full,
because the queue is always freshly created and cannot be found by any
other code path. In fact, the test of the queue length is worse than
useless: if somehow the test ever triggered and path_rec_start() also
failed, then dev_kfree_skb_any() will be called twice on the same skb.
Fix this by deleting the useless test. Pointed out by Michael
S. Tsirkin <mst@mellanox.co.il>.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
MemFree devices need to reserve one shared receive queue (SRQ) work
request for internal use, so the capacity returned from the create_srq
and query_srq methods should be srq->max - 1.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix an oopsable race debugged by Eli Cohen <eli@mellanox.co.il>:
After removing the port from port_list, ib_mad_port_close flushes
port_priv->wq before destroying the special QPs. This means that a
completion event could arrive, and queue a new work in this work queue
after flush.
This patch also removes an unnecessary flush_workqueue():
destroy_workqueue() already includes a flush.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix leak found by Coverity: in the SRP_OPT_DGID case,
srp_parse_options() didn't free the result of match_strdup().
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix bug found by coverity: the loop body never executed, because it
was doing for (i = 0; i < MTHCA_EQ_CMD; ++i), but MTHCA_EQ_CMD is 0.
The correct loop bound is MTHCA_NUM_EQ, to loop over all EQs.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix two bugs found by coverity:
- Memory leak in error path of alloc_group_attrs()
- Fencepost error in state_show(): the test should be < ARRAY_SIZE(),
not <= ARRAY_SIZE().
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Move ipoib_ib_dev_flush() to ipoib's workqueue. This keeps it ordered
with respect to other work scheduled by the ipoib driver. This fixes
problems with races, for example:
- ipoib_ib_dev_flush() has started running because of an IB event
- user does ifconfig ib0 down
- ipoib_mcast_stop_thread() gets called twice and waits for the same
completion twice
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix the IPoIB build (which is broken in net-2.6.17 because of my
screw-up, which left out this chunk in ipoib_multicast.c).
The neighbour destructor is now in neigh_params, so we don't
need to clear it in the ops structure.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The old code incorrectly used the primary P_Key index as the alternate
index too.
Signed-off-by: Ami Perlmutter <amip@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support for sending and receiving large RMPP transfers. The old
code supports transfers only as large as a single contiguous kernel
memory allocation. This patch uses linked list of memory buffers when
sending and receiving data to avoid needing contiguous pages for
larger transfers.
Receive side: copy the arriving MADs in chunks instead of coalescing
to one large buffer in kernel space.
Send side: split a multipacket MAD buffer to a list of segments,
(multipacket_list) and send these using a gather list of size 2.
Also, save pointer to last sent segment, and retrieve requested
segments by walking list starting at last sent segment. Finally,
save pointer to last-acked segment. When retrying, retrieve
segments for resending relative to this pointer. When updating last
ack, start at this pointer.
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add SCSI host attributes in sysfs that show the ID extension, IOC
GUID, service ID, P_Key and destination GID for each target port that
the SRP initiator connects to.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Move checking the state of a cm_id before modifying it when handling a
REP. This fixes a bug seen under MPI scale-up testing, where a NULL
timewait_info pointer is dereferenced if a request times out before a
REP is received.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Sinai (one-port PCI Express) HCAs get improved throughput for messages
bigger than 80 KB in DDR mode if memory keys are formatted in a
specific way. The enhancement only works if the memory key table is
smaller than 2^24 entries. For larger tables, the enhancement is off
and a warning is printed (to avoid silent performance loss).
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Michael Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The old code didn't convert from the kernel's enum correctly.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
According to the IB spec version 1.2, section 11.2.4.2, the current
table has a couple of mistakes where it allows the current QP state
(IB_QP_CUR_STATE) attribute. For the transitions:
RTS -> RTS: IB_QP_CUR_STATE should be allowed for all transports
SQD -> SQD: IB_QP_CUR_STATE should never be allowed
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipoib_mcast_stop_thread currently tests mcast->query and if it is
NULL, does not perform wait_for_completion on the mcast and frees the
mcast object directly.
However, since both operations are done without locking, it is
possible that ipoib_mcast_join_complete is in progress on this mcast
object and has set mcast->query to NULL already.
Solve this by:
- taking priv->lock before we change mcast->query in ipoib_mcast_join_complete,
and keeping it until we no longer need the mcast object
- taking priv->lock around mcast->query test in ipoib_mcast_stop_thread
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If posting receives in ipoib_ib_dev_open() fails, call
ipoib_ib_dev_stop() to move the device's QP back to the RESET state so
that we can try again later.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Use a named enum for the HCA's internal page size, rather than having
magic values of 4096 and shifts by 12 all over the code. Also, fix
one minor bug in EQ handling: only one HCA page is mapped to the HCA
during initialization, but a full kernel page is unmapped during
cleanup. This might cause problems when PAGE_SIZE != 4096.
Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Check that the alternate P_Key index is in range when setting the
alternate path for a QP. Also make a cosmetic touch up to the debug
message printed when the main P_Key index is out of range.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support for IB_SEND_FENCE flag in post_send methods.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipoib_mcast_send() tests mcast->ah twice. If this value is changed
between these two points, we leak an skb. However,
ipoib_mcast_join_finish() sets mcast->ah with no locking, so it could
race against ipoib_mcast_send().
As a solution, take priv->lock around assignment to mcast->ah thus
making sure ipoib_mcast_send() (which also takes priv->lock) is not in
flight.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Implement query_ah (except for AVs which are in HCA memory). This is
needed to implement RMPP duplicate session detection on sending side
(extraction of DGID/DLID and GRH flag from address handle).
Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch is checks whether the HCA supports posting FW commands
through a doorbell page (user access region 0, or "UAR0"). If this is
supported, the driver maps UAR0 and uses it for FW commands. This can
be controlled by the value of a writable module parameter
fw_cmd_doorbell. When the parameter is 0, the commands are posted
through HCR using the old method; otherwise if HCA is capable commands
go through UAR0.
This use of UAR0 to post commands eliminates the need for polling the
"go" bit prior to posting a new command. Since reading from a PCI
device is much more expensive then issuing a posted write, it is
expected that issuing FW commands this way will provide better CPU
utilization.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Pass actual capacity of created SRQ back to userspace, so that
userspace can report accurate capacities. This requires an ABI bump,
to change struct ib_uverbs_create_srq_resp.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Have mthca's create_srq method return the actual capacity of the SRQ
that gets created. Also update comments in <rdma/ib_verbs.h> to
clarify that this is what is expected from ib_create_srq().
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Cosmetic change: make alignment explicit in to_ipoib_neigh.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support to uverbs to handle querying userspace SRQs (shared
receive queues), including adding an ABI for marshalling requests and
responses. The kernel midlayer already has the underlying
ib_query_srq() function.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support to uverbs to handle querying userspace QPs (queue pairs),
including adding an ABI for marshalling requests and responses. The
kernel midlayer already has the underlying ib_query_qp() function.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Use ib_modify_qp_is_ok() in mthca, and delete the big table of
attributes for queue pair state transitions.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The in-kernel mthca driver contains a table of which attributes are
valid for each queue pair state transition. It turns out that both
other IB drivers -- ipath and ehca -- which are being prepared for
merging have copied this table, errors and all.
To forestall this code duplication, move this table and the code to
check parameters against it into a midlayer library function,
ib_modify_qp_is_ok().
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add low-level driver support to ib_mthca so that consumers can request
a "send queue drained" event be generated when a transiton to the SQD
state completes.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The call to ib_get_agent_port() shouldn't be possible to fail when
smi_check_local_dr_smp() is called from ib_mad_recv_done_handler().
When it is called from handle_outgoing_dr_smp(), the device and
port_num come from mad_agent_priv so I assume the call to
ib_get_agent_port() shouldn't fail either. In either case,
smi_check_local_smp() only uses the mad_agent pointer to check that
mad_agent->device->process_mad is not NULL. The device pointer would
have to be the same as the one passed to smi_check_local_dr_smp()
since that pointer is used later instead of the one checked in
smi_check_local_smp().
Signed-off-by: Hal Rosenstock <halr@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
smi_check_local_dr_smp() is called only from two places in core/mad.c
It returns 0 or 1. In smi_check_local_dr_smp(), it checks for
a directed route SMP but this function is only called when the SMP
is a directed route so this is a NOP.
Signed-off-by: Hal Rosenstock <halr@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch allows the consumer to set the page size of "pages" mapped
by the pool FMRs, which is a feature already existing in the base
verbs API. On the cosmetic side it changes ib_fmr_attr.page_size field
to be named page_shift.
Signed-off-by: Or Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add a modify_device method to mthca, which implements setting the node
description. This makes the writable "node_desc" sysfs attribute work
for Mellanox HCAs.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Expose a writable "node_desc" sysfs attribute for InfiniBand devices.
This allows userspace to update the node description with information
such as the node's hostname, so that IB network management software
can tie its view to the real world.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support to uverbs to handle resizing userspace CQs (completion
queues), including adding an ABI for marshalling requests and
responses. The kernel midlayer already has ib_resize_cq().
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The might_sleep() annotations in mthca are silly -- they all occur
shortly before calls that will end up in core functions like kmalloc()
that will print the same warning in an unsafe context anyway. In
fact, beyond cluttering the source, we're actually bloating text with
CONFIG_DEBUG_SPINLOCK_SLEEP and/or CONFIG_PREEMPT_VOLUNTARY set.
With both options set, getting rid of the might_sleep()s saves a lot:
add/remove: 0/0 grow/shrink: 0/7 up/down: 0/-171 (-171)
function old new delta
mthca_pd_alloc 132 109 -23
mthca_init_cq 969 946 -23
mthca_mr_alloc 592 568 -24
mthca_pd_free 67 42 -25
mthca_free_mr 219 194 -25
mthca_free_cq 570 545 -25
mthca_fmr_alloc 742 716 -26
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The function mthca_free_err_wqe() can never fail, so get rid of its
return value. That means handle_error_cqe() doesn't have to check
what mthca_free_err_wqe() returns, which means it can't fail either
and doesn't have to return anything either. All this results in
simpler source code and a slight object code improvement:
add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-10 (-10)
function old new delta
mthca_free_err_wqe 83 81 -2
mthca_poll_cq 1758 1750 -8
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Even after the last fix, it's still possible for a send-only join to
start before the join for the broadcast group has finished. This
could cause us to create a multicast group using attributes from the
broadcast group that haven't been initialized yet, so we would use
garbage for the Q_Key, etc. Fix this by waiting until the broadcast
group's attached flag is set before starting send-only joins.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When debugging is enabled, the mthca_QUERY_DEV_LIM() firmware command
function prints out some of the device limits that it queries.
However the debugging prints happen before all of the fields are
extracted from the firmware response, so some of the values that get
printed are uninitialized junk. Move the prints to the end of the
function to fix this.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Further, there's an additional issue that I saw in testing:
ipoib_mcast_send may get called when priv->broadcast is NULL (e.g. if
the device was downed and then upped internally because of a port
event).
If this happends and the send-only join request gets completed before
priv->broadcast is set, we get an oops.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix the following race scenario:
- Device is up.
- Port event or set mcast list triggers ipoib_mcast_stop_thread,
this cancels the query and waits on mcast "done" completion.
- Completion is called and "done" is set.
- Meanwhile, ipoib_mcast_send arrives and starts a new query,
re-initializing "done".
Fix this by adding a "multicast started" bit and checking it before
starting a send-only join.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Current IB code doesn't work with userspace programs that listen only to
the kernel event netlink socket as it is trying to create its own dev
interface. This small patch fixes this problem, and removes some
unneeded code as the driver core handles this logic for you
automatically.
Acked-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Fix handling of directed route SMPs with a beginning or ending LID
routed part.
Signed-off-by: Ralph Campbell <ralphc@pathscale.com>
Signed-off-by: Hal Rosenstock <halr@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Convert semaphores to mutexes in mthca. Leave firmware command
interface poll_sem and event_sem as semaphores.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
We have run into the following problem: if a task receives a signal
while in the process of e.g. destroying a resource (which could be
because the relevant file was closed) mthca could bail out from trying
to take a command interface semaphore without performing the
appropriate command to tell hardware that the resource is being
destroyed.
As a result we see messages like
ib_mthca 0000:04:00.0: HW2SW_CQ failed (-4)
In this case, hardware could access the resource after the memory has
been freed, possibly causing memory corruption.
A simple solution is to replace down_interruptible() by down() in
command interface activation.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
[ It's also not safe to bail out on multicast table operations, since
they may be invoked on the cleanup path too. So use down() for
mcg_table.sem too. ]
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Convert srp_host->target_mutex from a semaphore to a mutex.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
There are some cards around that have UAR (user access region) size
different from 8 MB. Relax our sanity check to make sure that the PCI
BAR is big enough to access the UAR size reported by the device
firmware instead.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
