Right now if we push the NTB really hard, we start dropping packets due
to not able to process the packets fast enough. We need to st:qop the
upper layer from flooding us when that happens.

A timer is necessary in order to restart the queue once the resource has
been processed on the receive side. Due to the way NTB is setup, the
resources on the tx side are tied to the processing of the rx side and
there's no async way to know when the rx side has released those
resources.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Remove early dereference of a pointer that is checked later in the code.
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

A plain 32 bit integer will overflow for values over 4GiB.

Change the plain integer size to the appropriate size type in
ntb_set_mw.  Change the type of the size parameter and two local
variables used for size.

Even if there is no overflow, a size of zero is invalid here.
Reported-by: NJuyoung Jung <jjung@micron.com>
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Schedule to receive on QP link up, to make sure that the doorbell is
properly cleared for interrupts.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

When the remote side is not up, we do not have all the context for the
transport, and that causes NULL ptr access. Have the debugfs reads check
to see if transport is up before we make access.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Currently the debugfs does not have files for all NTB transport queue
pairs.  When there are multiple NTBs present in a system, the QP names
of the last transport clobber the names of previously added transport
QPs.  Only the last added QPs can be observed via debugfs.

Create a directory per NTB transport to associate the QPs with that
transport.  Name the directory the same as the PCI device.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

It was possible for a synchronous update of the RX index in the error
case to get ahead of the asynchronous RX index update in the normal
case.  Change the RX processing to preserve an RX completion order.

There were two error cases.  First, if a buffer is not present to
receive data, there would be no queue entry to preserve the RX
completion order.  Instead of dropping the RX frame, leave the RX frame
in the ring.  Schedule RX processing when RX entries are enqueued, in
case there are RX frames waiting in the ring to be received.

Second, if a buffer is too small to receive data, drop the frame in the
ring, mark the RX entry as done, and indicate the error in the RX entry
length.  Check for a negative length in the receive callback in
ntb_netdev, and count occurrences as rx_length_errors.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Printouts driver name and version to indicate what is being loaded.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Benchmarking showed a significant performance increase with the MTU size
to 64k instead of 16k.  Change the driver default to 64k.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Disable DMA usage by default, since the CPU provides much better
performance with write combining.  Provide a module parameter to enable
DMA usage when offloading the memcpy is preferred.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Changing the memory window BAR mappings to write combining significantly
boosts the performance.  We will also use memcpy that uses non-temporal
store, which showed performance improvement when doing non-cached
memcpys.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Allocate memory and request the DMA channel for the same NUMA node as
the NTB device.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

When the ntb transport is connecting and waiting for the peer, the debug
console receives lots of debug level messages about the remote qp link
status being down.  Rate limit those messages.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Reset the link stats when the link goes down.  In particular, the TX and
RX index and count must be reset, or else the TX side will be sending
packets to the RX side where the RX side is not expecting them.  Reset
all the stats, to be consistent.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

On link down, don't advance RX index to the next entry.  The next entry
should never be valid after receiving the link down flag.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

The same message "qp %d: Link Down\n" was printed at two locations in
ntb_transport.  Change the messages so they are distinct.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

The transport was writing and then reading the peer scratch pad,
essentially reading what it just wrote instead of exchanging any
information with the peer.  The transport expects the peer values to be
the same as the local values, so this issue was not obvious.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

Change ntb_hw_intel to use the new NTB hardware abstraction layer.

Split ntb_transport into its own driver.  Change it to use the new NTB
hardware abstraction layer.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

This patch only moves files to their new locations, before applying the
next two patches adding the NTB Abstraction layer.  Splitting this patch
from the next is intended make distinct which code is changed only due
to moving the files, versus which are substantial code changes in adding
the NTB Abstraction layer.
Signed-off-by: NAllen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

The NTB translate register must have the value to be BAR size aligned.
This alignment check make sure that the DMA memory allocated has the
proper alignment. Another requirement for NTB to function properly with
memory window BAR size greater or equal to 4M is to use the CMA feature
in 3.16 kernel with the appropriate CONFIG_CMA_ALIGNMENT and
CONFIG_CMA_SIZE_MBYTES set.
Signed-off-by: NDave Jiang <dave.jiang@intel.com>
Signed-off-by: NJon Mason <jdmason@kudzu.us>

The detection of an uneven number of queues on the given memory windows
was not correct.  The mw_num is zero based and the mod should be
division to spread them evenly over the mw's.
Signed-off-by: NJon Mason <jon.mason@intel.com>

Some white space and 80 char overruns corrected.
Signed-off-by: NJon Mason <jon.mason@intel.com>

Provide a better event interface between the client and transport
Signed-off-by: NJon Mason <jon.mason@intel.com>

Disable interrupts and poll under high load
Signed-off-by: NJon Mason <jon.mason@intel.com>

dmaengine_get() causes the initialization of the per-cpu channel tables.
It needs to be called prior to dma_find_channel().

Initial version by Dan Williams <dan.j.williams@intel.com>
Signed-off-by: NJon Mason <jon.mason@intel.com>

A WARN_ON is being hit in ntb_qp_link_work due to the NTB transport link
being down while the ntb qp link is still active.  This is caused by the
transport link being brought down prior to the qp link worker thread
being terminated.  To correct this, shutdown the qp's prior to bringing
the transport link down.  Also, only call the qp worker thread if it is
in interrupt context, otherwise call the function directly.
Signed-off-by: NJon Mason <jon.mason@intel.com>

Remove no longer needed DMA unmap flags:
- DMA_COMPL_SKIP_SRC_UNMAP
- DMA_COMPL_SKIP_DEST_UNMAP
- DMA_COMPL_SRC_UNMAP_SINGLE
- DMA_COMPL_DEST_UNMAP_SINGLE

Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Tomasz Figa <t.figa@samsung.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Acked-by: NJon Mason <jon.mason@intel.com>
Acked-by: NMark Brown <broonie@linaro.org>
[djbw: clean up straggling skip unmap flags in ntb]
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Use the generic unmap object to unmap dma buffers.

Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Tomasz Figa <t.figa@samsung.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: NBartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Acked-by: NJon Mason <jon.mason@intel.com>
[djbw: fix up unmap len, and GFP flags]
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Add "data" ntb_register_db_callback parameter description comment and
correct poor spelling.
Signed-off-by: NJon Mason <jon.mason@intel.com>

Remove unused pci_dev variable from ntb_transport_free()
Signed-off-by: NJon Mason <jon.mason@intel.com>

Many variable names in the NTB driver refer to the primary or secondary
side.  However, these variables will be used to access the reverse case
when in NTB-RP mode.  Make these names more generic in anticipation of
NTB-RP support.
Signed-off-by: NJon Mason <jon.mason@intel.com>

Allocate and use a DMA engine channel to transmit and receive data over
NTB.  If none is allocated, fall back to using the CPU to transfer data.
Signed-off-by: NJon Mason <jon.mason@intel.com>
Reviewed-by: NDan Williams <dan.j.williams@intel.com>
Reviewed-by: NDave Jiang <dave.jiang@intel.com>

There is a Xeon hardware errata related to writes to SDOORBELL or
B2BDOORBELL in conjunction with inbound access to NTB MMIO Space, which
may hang the system.  To workaround this issue, use one of the memory
windows to access the interrupt and scratch pad registers on the remote
system.  This bypasses the issue, but removes one of the memory windows
from use by the transport.  This reduction of MWs necessitates adding
some logic to determine the number of available MWs.

Since some NTB usage methodologies may have unidirectional traffic, the
ability to disable the workaround via modparm has been added.

See BF113 in
http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/xeon-c5500-c3500-spec-update.pdf
See BT119 in
http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/xeon-e5-family-spec-update.pdfSigned-off-by: NJon Mason <jon.mason@intel.com>

Debugfs was setup in NTB to only have a single debugfs directory.  This
resulted in the leaking of debugfs directories and files when multiple
NTB devices were present, due to each device stomping on the variables
containing the previous device's values (thus preventing them from being
freed on cleanup).  Correct this by creating a secondary directory of
the PCI BDF for each device present, and nesting the previously existing
information in those directories.
Signed-off-by: NJon Mason <jon.mason@intel.com>

Fix issue with adding multiple ntb client devices to the ntb virtual
bus.  Previously, multiple devices would be added with the same name,
resulting in crashes.  To get around this issue, add a unique number to
the device when it is added.
Signed-off-by: NJon Mason <jon.mason@intel.com>

The system will appear to lockup for long periods of time due to the NTB
driver spending too much time in memcpy.  Avoid this by reducing the
number of packets that can be serviced on a given interrupt.
Signed-off-by: NJon Mason <jon.mason@intel.com>

The ring logic of the NTB receive buffer/transmit memory window requires
there to be at least 2 payload sized allotments.  For the minimal size
case, split the buffer into two and set the transport_mtu to the
appropriate size.
Signed-off-by: NJon Mason <jon.mason@intel.com>

If the NTB link toggles, the driver could stop receiving due to the
tx_index not being set to 0 on the transmitting size on a link-up event.
This is due to the driver expecting the incoming data to start at the
beginning of the receive buffer and not at a random place.
Signed-off-by: NJon Mason <jon.mason@intel.com>

Each link-up will allocate a new NTB receive buffer when the NTB
properties are negotiated with the remote system.  These allocations did
not check for existing buffers and thus did not free them.  Now, the
driver will check for an existing buffer and free it if not of the
correct size, before trying to alloc a new one.
Signed-off-by: NJon Mason <jon.mason@intel.com>

64bit BAR sizes are permissible with an NTB device.  To support them
various modifications and clean-ups were required, most significantly
using 2 32bit scratch pad registers for each BAR.

Also, modify the driver to allow more than 2 Memory Windows.
Signed-off-by: NJon Mason <jon.mason@intel.com>