Provide common handling for marshalling data between userspace clients
and kernel InfiniBand drivers.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Memfree firmware is in rare cases reporting WQE index == base - 1 in
receive completion with error, instead of (rq size - 1); base is 0 in
mthca. Here is a patch to avoid kernel crash and report a correct WR
id in this case.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
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>
