Remove the sizeable cache of the chip sizing CSRs and replace with CSR
reads as needed.
Reviewed-by: NMichael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

Move some s_flags defines out of rdmavt and into hfi1 because they are
hfi1 specific and therefore should remain in the driver instead of
bubbling up to rdmavt.

Document device specific ranges in rdmavt and remap
those in hfi1.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NKaike Wan <kaike.wan@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

User send context integrity bits are cleared before the context is
disabled.  If the send context is still processing data, any packets
that need those integrity bits will cause an error and halt the send
context.

During the disable handling, the driver waits for the context to drain.
If the context is halted, the driver will eventually timeout because
the context won't drain and then incorrectly bounce the link.

Reorder the bit clearing and the context disable.

Examine the software state and send context status as well as the
egress status to determine if a send context is in the halted state.

Promote the check macros to static functions for consistency with the
new check and to follow kernel style.

Remove an unused define that refers to the egress timeout.

Cc: <stable@vger.kernel.org> # 4.9.x
Reviewed-by: NMitko Haralanov <mitko.haralanov@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NMichael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Kzalloc_node API doesn't check for overflows in size multiplication.
While kcalloc API check for overflows in size multiplication
but these implementations are not NUMA-aware.

This conversion allowed for correcting an allocation used in the hot
path to be on the local NUMA and ensure us overflow free multiplication
for the size of a memory allocation.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NKamenee Arumugam <kamenee.arumugam@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

OPA VNIC does not use PIO contexts and instead only uses SDMA
engines. Do not allocate PIO contexts for VNIC ports.
Reviewed-by: NMichael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: NNiranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE()

Please do not apply this to mainline directly, instead please re-run the
coccinelle script shown below and apply its output.

For several reasons, it is desirable to use {READ,WRITE}_ONCE() in
preference to ACCESS_ONCE(), and new code is expected to use one of the
former. So far, there's been no reason to change most existing uses of
ACCESS_ONCE(), as these aren't harmful, and changing them results in
churn.

However, for some features, the read/write distinction is critical to
correct operation. To distinguish these cases, separate read/write
accessors must be used. This patch migrates (most) remaining
ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following
coccinelle script:

----
// Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and
// WRITE_ONCE()

// $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch

virtual patch

@ depends on patch @
expression E1, E2;
@@

- ACCESS_ONCE(E1) = E2
+ WRITE_ONCE(E1, E2)

@ depends on patch @
expression E;
@@

- ACCESS_ONCE(E)
+ READ_ONCE(E)
----
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: linux-arch@vger.kernel.org
Cc: mpe@ellerman.id.au
Cc: shuah@kernel.org
Cc: snitzer@redhat.com
Cc: thor.thayer@linux.intel.com
Cc: tj@kernel.org
Cc: viro@zeniv.linux.org.uk
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Currently, link down interrupts queue link entries
on a workqueue intended for sending events only.
Create a workqueue for queuing link events.
Reviewed-by: NDean Luick <dean.luick@intel.com>
Signed-off-by: NSebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

When an egress resource(SDMA descriptors, pio credits) is not available,
a sending thread will be put on the resource's wait queue. When the
resource becomes available again, up to a fixed number of sending threads
can be awakened sequentially and removed from the wait queue, depending
on the number of waiting threads and the number of free resources. Since
each awakened sending thread will send as many packets as possible, it
is highly likely that the first sending thread will consume all the
egress resources. Subsequently, it will be put back to the end of the wait
queue. Depending on the timing when the later sending threads wake up,
they may not be able to send any packet and be again put back to the end
of the wait queue sequentially, right behind the first sending thread.
This starvation cycle continues until some sending threads exceed their
retry limit and consequently fail.

This patch fixes the issue by two simple approaches:
(1) Any starved sending thread will be put to the head of the wait queue
while a served sending thread will be put to the tail;
(2) The most starved sending thread will be served first.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NKaike Wan <kaike.wan@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

HFI1 HW specific support for VNIC functionality.
Dynamically allocate a set of contexts for VNIC when the first vnic
port is instantiated. Allocate VNIC contexts from user contexts pool
and return them back to the same pool while freeing up. Set aside
enough MSI-X interrupts for VNIC contexts and assign them when the
contexts are allocated. On the receive side, use an RSM rule to
spread TCP/UDP streams among VNIC contexts.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Signed-off-by: NNiranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: NAndrzej Kacprowski <andrzej.kacprowski@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Do not allocate credit return base and DMA memory for
NUMA nodes without CPUs.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NHarish Chegondi <harish.chegondi@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In sc_buffer_alloc(), the sc->alloc_lock is released
before calling sc_release_update(), and it is reacquired
after the function call. This causes CPU lock trading.
Fix it by not dropping the lock before calling
sc_release_update().
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NSebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The prints after [k|v][m|z|c]alloc() functions are not needed,
because in case of failure, allocator will print their internal
error prints anyway.
Signed-off-by: NLeon Romanovsky <leon@kernel.org>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Both pio_buf and send_context structs have oversized
fields and have cachelines that can be optimized.

Reduce oversized fields for both structs.
Make sure pio_buf struct fits within a cacheline.
Move read-only fields to their own cacheline in
send_context struct.

All of this will avoid cacheline trading as the ring
progresses and pio buffers/send contexts are used.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NSebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The div instruction shows costly in profiles.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NSebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Profiling suggests that the read_seqbegin() in
the txreq put logic is colliding with other uses
of the iowait lock.

The packet at a time use of this lock dictates a unique
lock to avoid reader/writer collisions when the number
of vTxWait events is low.

In order to support a unique lock the iowait struct embedded
in the QP is extended to remember the lock that protects the queue
head.

The QP destroy removes that QP from any wait list.  It doesn't
need to know the head because of the linked list API, but it does
need to know the lock required to protect the head.

This also opens up the wait logic to have unique per resources locks
which needs to be in future refinement.
Reviewed-by: NSebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Prevent setting up integrity check flags when module is loaded
with NO_INTEGRITY capability.
Reviewed-by: NDean Luick <dean.luick@intel.com>
Signed-off-by: NJakub Pawlak <jakub.pawlak@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The dma_XXX API functions return bus addresses which are
physical addresses when IOMMU is disabled. Buffer
mapping to user-space is done via remap_pfn_range() with PFN
based on bus address instead of physical. This results in
wrong pages being mapped to user-space when IOMMU is enabled.
Reviewed-by: NMitko Haralanov <mitko.haralanov@intel.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NTymoteusz Kielan <tymoteusz.kielan@intel.com>
Signed-off-by: NAndrzej Kacprowski <andrzej.kacprowski@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Checking the return value of the memory allocation call in
init_pervl_scs() was missed.  Recently the kmalloc() was changed to
kzalloc() which identified the problem.

While fixing this issue 2 other bugs were noticed.  First, the array
being allocated is accessed in the nomem path which can be reached before
it is allocated.  Second, kernel_send_context was not released on error.
Fix both of these by creating a more common memory unwind label structure.

Fixes: 35f6befc ("staging/rdma/hfi1: Add qp to send context mapping for PIO")
Reported-by: NLeon Romanovsky <leon@kernel.org>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NIra Weiny <ira.weiny@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

While handling buffer control MAD, partially initialized
dd->kernel_send_context area may cause potential dereference
of uninitialized pointers. Fix by using kzalloc_node()
instead of kmalloc_node().
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NAndrzej Kacprowski <andrzej.kacprowski@intel.com>
Signed-off-by: NTymoteusz Kielan <tymoteusz.kielan@intel.com>
Signed-off-by: NAndrzej Kacprowski <andrzej.kacprowski@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The current value of 500us for the packet egress timeout is too small
which causes the host to declare failure on draining packets too early
and unnecessarily bounces the link. Increase this to 50ms taking into
account the switch packet discard timer default and the worst case
per-VL package drainage rate.
Reviewed-by: NDean Luick <dean.luick@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The credit return threshold adjustment on mtu change algorithm does not
take into account all the kernel send contexts that are assigned per VL.
Use the pio send context map to adjust the credit return thresholds for
all the allocated and assigned kernel send contexts based on the MTU
adjustment per VL.

The pio send context map can be changed dynamically based on the actual
number of operational vls which is set by the fabric manager. When this
happens update the credit return threshold values for all the remapped
kernel send contexts.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: NJianxin Xiong <jianxin.xiong@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The pio map initialization function is off by 1 causing the last
kernel send context that is allocated to not get mapped into the
pio map which leads to the last kernel send context not being used
by any of the qps.

The send context reserved for VL15 is taken care of by setting the
scontext variable that is used as the index into the kernel send
context array to 1 and does not need to be accounted for in the
kernel send context counting loop as it is currently done.

Fix the kernel send context counting loop to account for all the
allocated send contexts and map all of them to the different VLs.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: NJianxin Xiong <jianxin.xiong@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The TODO list for the hfi1 driver was completed during 4.6. In addition
other objections raised (which are far beyond what was in the TODO list)
have been addressed as well. It is now time to remove the driver from
staging and into the drivers/infiniband sub-tree.
Reviewed-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The pio buffers were pooled evenly among all kernel contexts and
user contexts. However, the demand from kernel contexts is much
lower than user contexts. This patch reduces the allocation for
kernel contexts and thus makes more credits available for PSM,
helping performance. This is especially useful on high core-count
systems where large numbers of contexts are used.

A new context type SC_VL15 is added to distinguish the context used
for VL15 from other kernel contexts. The reason is that VL15 needs
to support 2KB sized packet while other kernel contexts need only
support packets up to the size determined by "piothreshold", which
has a default value of 256.

The new allocation method allows triple buffering of largest pio
packets configured for these contexts. This is sufficient to maintain
verbs performance. The largest pio packet size is 2048B for VL15
and "piothreshold" for other kernel contexts. A cap is applied to
"piothreshold" to avoid excessive buffer allocation.

The special case that SDMA is disable is handled differently. In
that case, the original pooling allocation is used to better
support the much higher pio traffic.

Notice that if adaptive pio is disabled (piothreshold==0), the pio
buffer size doesn't matter for non-VL15 kernel send contexts when
SDMA is enabled because pio is not used at all on these contexts
and thus the new allocation is still valid. If SDMA is disabled then
pooling allocation is used as mentioned in previous paragraph.

Adjustment is also made to the calculation of the credit return
threshold for the kernel contexts. Instead of purely based on
the MTU size, a percentage based threshold is also considered and
the smaller one of the two is chosen. This is necessary to ensure
that with the reduced buffer allocation credits are returned in
time to avoid unnecessary stall in the send path.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: NDean Luick <dean.luick@intel.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NMark Debbage <mark.debbage@intel.com>
Reviewed-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NJianxin Xiong <jianxin.xiong@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

There is a timing hole if there had been greater than
PIO_WAIT_BATCH_SIZE waiters.  This code will dispatch the first
batch but leave the others in the queue.   If the restarted waiters
don't in turn wait on a buffer, there is a hang.

Fix by forcing a return when the QP queue is non-empty.
Reviewed-by: NVennila Megavannan <vennila.megavannan@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Implement changes recommended by the Coccinelle tool to move constant to
the right in bitwise operations

-bash-4.2$ make coccicheck MODE=report M=drivers/infiniband/hw/hfi1/

drivers/infiniband/hw/hfi1/pio.c:765:4-16: Move constant to right.
drivers/infiniband/hw/hfi1/rc.c:2503:19-29: Move constant to right.
drivers/infiniband/hw/hfi1/chip.c:9813:11-22: Move constant to right.
drivers/infiniband/hw/hfi1/chip.c:14468:29-40: Move constant to right.
Reviewed-by: NJubin John <jubin.john@intel.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NHarish Chegondi <harish.chegondi@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Fix 3 memory leaks reported by the LeakCheck tool in the KEDR framework.

The following resources were allocated memory during their respective
initializations but not freed during cleanup:
1. SDMA map elements
2. PIO map elements
3. HW send context to SW index map

This patch fixes the memory leaks by freeing the allocated memory in the
cleanup path.
Reviewed-by: NDean Luick <dean.luick@intel.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Fix the header by moving the copyright notice out of the license text
and to the top of the header. Also, update the copyright date.
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Fix code alignment to fix checkpatch check:
CHECK: Alignment should match open parenthesis
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Fix block comments with proper formatting to fix checkpatch warnings:
WARNING: Block comments use * on subsequent lines
WARNING: Block comments use a trailing */ on a separate line
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Use sizeof(*p) instead of sizeof(struct foo) to fix checkpatch check:
CHECK: Prefer alloc(sizeof(*p)...) over alloc(sizeof(struct foo)...)
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Convert pointer comparisons to NULL to !pointer
to fix checkpatch check:
CHECK: Comparison to NULL could be written "!pointer"
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Remove the space after a cast to fix checkpatch check:
CHECK: No space is necessary after a cast
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Remove multiple blank lines to fix checkpatch check:
CHECK: Please don't use multiple blank lines
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add spaces around binary operators.

Fixes checkpatch check:
CHECK: spaces preferred around that 'x'
where x is a binary operator
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

PIO send context mapping is changed from per-VL to QPN based.

qp to send context mapping is done using a mapping infrastructure
similar to the current vl to sdma engine mapping.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NJubin John <jubin.john@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The change requires a new pio_busy field in the iowait structure to
track the number of outstanding pios.  The new counter together
with the sdma counter serve as the basis for a packet by packet decision
as to which egress mechanism to use.  Since packets given to different
egress mechanisms are not ordered, this scheme will preserve the order.

The iowait drain/wait mechanisms are extended for a pio case.  An
additional qp wait flag is added for the PIO drain wait case.

Currently the only pio wait is for buffers, so the no_bufs_available()
routine name is changed to pio_wait() and a third argument is passed
with one of the two pio wait flags to generalize the routine.  A module
parameter is added to hold a configurable threshold. For now, the
module parameter is zero.

A heuristic routine is added to return the func pointer of the proper
egress routine to use.

The heuristic is as follows:
- SMI always uses pio
- GSI,UD qps <= threshold use pio
- UD qps > threadhold use sdma
  o No coordination with sdma is required because order is not required
    and this qp pio count is not maintained for UD
- RC/UC ONLY packets <= threshold chose as follows:
  o If sdmas pending, use SDMA
  o Otherwise use pio and enable the pio tracking count at
    the time the pio buffer is allocated
- RC/UC ONLY packets > threshold use SDMA
  o If pio's are pending the pio_wait with the new wait flag is
    called to delay for pios to drain

The threshold is potentially reduced by the QP's mtu.

The sc_buffer_alloc() has two additional args (a callback, a void *)
which are exploited by the RC/UC cases to pass a new complete routine
and a qp *.

When the shadow ring completes the credit associated with a packet,
the new complete routine is called.  The verbs_pio_complete() will then
decrement the busy count and trigger any drain waiters in qp destroy
or reset.
Reviewed-by: NJubin John <jubin.john@intel.com>
Reviewed-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Use the definitions of the s_flags and r_flags which are now in rdmavt.
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NHarish Chegondi <harish.chegondi@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch does the actual removal of the queue pair from the hfi1 driver
along with a number of dependent data structures. These were moved to rvt.

It also removes the MR functions to use those in rdmavt.

These two pieces can not reasonably be split apart becuase they depend on
each other.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

In preparation for moving the queue pair data structure to rdmavt the
members of the driver specific queue pairs which are not common need to be
pushed off to a private driver structure. This structure will be available
in the queue pair once moved to rdmavt as a void pointer. This patch while
not adding a lot of value in and of itself is a prerequisite to move the
queue pair out of the drivers and into rdmavt.

The driver specific, private queue pair data structure should condense as
more of the send side code moves to rdmavt.
Reviewed-by: NMike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: NDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>