Add support for O_ASYNC notifications on userspace verbs
completion and asynchronous event file descriptors.
Signed-off-by: Gleb Natapov <glebn@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix handling of error CQ entries on mem-free HCAs: the doorbell count
is never valid so we shouldn't look at it. This fixes problems exposed
by new HCA firmware.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support for userspace queue pairs (QPs) to mthca.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for userspace completion queues (CQs) to mthca.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for userspace memory regions (MRs) to mthca.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for userspace protection domains (PDs) to mthca.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for mmap() method to mthca, so that userspace can get access to
doorbell registers. This allows userspace to get direct access to the HCA for
data path operations.
Each userspace context gets its own copy of the doorbell registers and is only
allowed to use resources that the kernel has given it access to. In other
words, this is safe.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for managing userspace contexts to mthca.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for userspace doorbell records to mthca.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add the mthca_user.h header file, which defines the device-specific ABI used
by the mthca low-level driver for kernel/user communication.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Hook up InfiniBand userspace verbs to Kconfig and the make system.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for pinning userspace memory regions and returning a list of pages
in the region. This includes tracking pinned memory against vm_locked and
preventing unprivileged users from exceeding RLIMIT_MEMLOCK.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add the core of the InfiniBand userspace verbs implementation, including
creating character device nodes, dispatching requests from userspace, and
passing event notifications back up to userspace.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add the ib_user_verbs.h header file, which defines the ABI used by InfiniBand
userspace verbs for kernel/user communication.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Update mthca to compile against the updated API for low-level drivers.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Update kernel InfiniBand midlayer to compile against the updated API for
low-level drivers. This just amounts to passing NULL for all
userspace-related parameters, and setting userspace-related structure members
to NULL.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
First of a series of patches which add support for direct userspace access to
InfiniBand hardware -- so-called "userspace verbs." I believe these patches
are ready to merge, but a final review would be useful.
These patches should incorporate all of the feedback from the discussion when
I posted an earlier version back in April (see
http://lkml.org/lkml/2005/4/4/267 for the start of the thread). In
particular, memory pinned for use by userspace is accounted for in
current->mm->vm_locked and requests to pin memory are checked against
RLIMIT_MEMLOCK.
This patch:
Modify the ib_verbs.h header file with changes required for InfiniBand
userspace verbs support. We add a few structures to keep track of userspace
context, and extend the driver API so that low-level drivers know when they're
creating resources that will be used from userspace.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix handling of fields with size_bits == 64. Pointed out by Hal Rosenstock.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Use a copy of the id we'll return to the consumer so that we don't
dereference query->sa_query after calling send_mad(). A completion may
occur very quickly and end up freeing the query before we get to do
anything after send_mad().
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
It's about time for a version bump.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Future versions of Mellanox HCA firmware will require command mailboxes to be
aligned to 4K. Support this by using a pci_pool to allocate all mailboxes.
This has the added benefit of shrinking the source and text of mthca.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Free page_list buffer on error path of mthca_reg_phys_mr().
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Split allocation of MTT range from creation of MR. This will be useful for
implementing shared memory regions and userspace verbs.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Make mthca_table_put() and mthca_table_put_range() NOPs if the device is not
mem-free, so that we don't have to have "if (mthca_is_memfree())" tests in the
callers of these functions. This makes our code more readable and
maintainable, and saves a couple dozen bytes of text in ib_mthca.ko as well.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix memset to use sizeof *props instead of just sizeof props.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add support for unreliable connected (UC) transport to mthca driver:
- Add attributes for UC to modify QP table.
- Add support for posting UC work requests.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
mthca apparently had the meanings of the max_rd_atomic and max_dest_rd_atomic
QP attributes backwards. max_rd_atomic limits the maximum number of
outstanding RDMA/atomic requests as an initiator (on a send queue), and
max_dest_rd_atomic specifies the resources allocated to handle RMDA/atomic
requests from the remote end of the connection. We were programming our QP
context with these values swapped.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix offset of static_rate in QP context. Pointed out by Dror Goldenberg.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Switch all allocations of coherent memory from pci_alloc_consistent() to
dma_alloc_coherent(), so that we can pass GFP_KERNEL. This should help when
the system is low on memory.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Clean up CQ debugging code: make dump_cqe print on one line, and only dump
error CQ entries for local operation errors.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
- Fix incorrect cut-n-paste in error messages.
- Add missing newlines in error messages.
- Use DRV_NAME instead of "ib_mthca" in a couple of places.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add Sun copyright to files modified by Tom Duffy.
Signed-off-by: Tom Duffy <tduffy@sun.com>
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
sysfs: fix the rest of the kernel so if an attribute doesn't
implement show or store method read/write will return
-EIO instead of 0 or -EINVAL or -EPERM.
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Make MTU field in SA PathRecord and MCMemberRecord a u8 rather than an enum
to avoid complications with endianness.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Free all unclaimed MAD receive buffers when userspace closes our file so we
don't leak memory.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Check if a client passes a NULL callback into an SA query, and if so, never
call back. This fixes an oops if someone unloads ib_ipoib and ib_sa in
rapid succession. ib_ipoib does an MCMember delete with a NULL callback
and 0 timeout on unload, which is usually fine since the delete completes
successfully. However, if ib_sa is unloaded immediately afterwards, the
delete will be canceled and ib_sa will try to call the (now already
unloaded) ib_ipoib module back with the cancel completion, which triggers
the oops.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix order of #include lines in mthca_memfree.c
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Correct unwinding in error path of mthca_init_icm().
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Decouple table of HCA features from exact HCA device type. Add a current FW
version field so we can warn when someone is using old FW. Add support for
new MT25204 HCA.
Remove the warning about mem-free support, since it should be pretty solid at
this point.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix RDMA in mem-free mode: we need to make sure that the RDMA context memory
is mapped for the HCA.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Update initialization of receive queue to match new documentation. This
change is required to support new MT25204 HCA.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Clean up mem-free mode support by introducing mthca_is_memfree() function,
which encapsulates the logic of deciding if a device is mem-free.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Minor tweaks to firmware command handling: kill off an unused get of a value,
and add a little more info to debug output.
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Implement fast memory regions (FMRs), where the driver writes directly into
the HCA's translation tables rather than requiring a firmware command. For
Tavor, MTTs for FMR are separate from regular MTTs, and are reserved at driver
initialization. This is done to limit the amount of virtual memory needed to
map the MTTs. For Arbel, there's no such limitation, and all MTTs and MPTs
may be used for FMR or for regular MR.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Split Tavor and Arbel/mem-free index<->hw key munging routines, so that FMR
implementation can call correct implementation without testing HCA type (which
it already knows).
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add mthca_table_find() function, which returns the lowmem address of an entry
in a mem-free HCA's context tables. This will be used by the FMR
implementation.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <roland@topspin.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
