Use existing function ntb_transport_tx_free_entry() instead of open coding
the check to see if there are outstanding tx descriptors.
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
ntb_transport_tx_free_entry() never returns 0 with the current
calculation. If head == tail, then it would return qp->tx_max_entry.
Change compare to tail >= head and when they are equal, a 0 would be
returned.
Fixes: e74bfeedad ("NTB: Add flow control to the ntb_netdev")
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: renlonglong <ren.longlong@h3c.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Currently when the transport receive packets after netdev has closed the
transport returns error and triggers tx errors to be incremented and
carrier to be stopped. There is no reason to return error if the device is
already closed. Drop the packet and return 0.
Fixes: e26a5843f7 ("NTB: Split ntb_hw_intel and ntb_transport drivers")
Reported-by: Yuan Y Lu <yuan.y.lu@intel.com>
Tested-by: Yuan Y Lu <yuan.y.lu@intel.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The tx tail index is not reset when the link goes down. This causes the
tail index to go out of sync when the link goes down and comes back up.
Refactor the ntb_qp_link_down_reset() and reset the tail index as well.
Fixes: 2849b5d706 ("NTB: Reset transport QP link stats on down")
Reported-by: Yuan Y Lu <yuan.y.lu@intel.com>
Tested-by: Yuan Y Lu <yuan.y.lu@intel.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
If device_register() returns error, the name allocated by
dev_set_name() need be freed. As comment of device_register()
says, it should use put_device() to give up the reference in
the error path. So fix this by calling put_device(), then the
name can be freed in kobject_cleanup(), and client_dev is freed
in ntb_transport_client_release().
Fixes: fce8a7bb5b ("PCI-Express Non-Transparent Bridge Support")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The driver core ignores the return value of this callback because there
is only little it can do when a device disappears.
This is the final bit of a long lasting cleanup quest where several
buses were converted to also return void from their remove callback.
Additionally some resource leaks were fixed that were caused by drivers
returning an error code in the expectation that the driver won't go
away.
With struct bus_type::remove returning void it's prevented that newly
implemented buses return an ignored error code and so don't anticipate
wrong expectations for driver authors.
Reviewed-by: Tom Rix <trix@redhat.com> (For fpga)
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Cornelia Huck <cohuck@redhat.com> (For drivers/s390 and drivers/vfio)
Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> (For ARM, Amba and related parts)
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Chen-Yu Tsai <wens@csie.org> (for sunxi-rsb)
Acked-by: Pali Rohár <pali@kernel.org>
Acked-by: Mauro Carvalho Chehab <mchehab@kernel.org> (for media)
Acked-by: Hans de Goede <hdegoede@redhat.com> (For drivers/platform)
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-By: Vinod Koul <vkoul@kernel.org>
Acked-by: Juergen Gross <jgross@suse.com> (For xen)
Acked-by: Lee Jones <lee.jones@linaro.org> (For mfd)
Acked-by: Johannes Thumshirn <jth@kernel.org> (For mcb)
Acked-by: Johan Hovold <johan@kernel.org>
Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> (For slimbus)
Acked-by: Kirti Wankhede <kwankhede@nvidia.com> (For vfio)
Acked-by: Maximilian Luz <luzmaximilian@gmail.com>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com> (For ulpi and typec)
Acked-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com> (For ipack)
Acked-by: Geoff Levand <geoff@infradead.org> (For ps3)
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com> (For thunderbolt)
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> (For intel_th)
Acked-by: Dominik Brodowski <linux@dominikbrodowski.net> (For pcmcia)
Acked-by: Rafael J. Wysocki <rafael@kernel.org> (For ACPI)
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org> (rpmsg and apr)
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> (For intel-ish-hid)
Acked-by: Dan Williams <dan.j.williams@intel.com> (For CXL, DAX, and NVDIMM)
Acked-by: William Breathitt Gray <vilhelm.gray@gmail.com> (For isa)
Acked-by: Stefan Richter <stefanr@s5r6.in-berlin.de> (For firewire)
Acked-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> (For hid)
Acked-by: Thorsten Scherer <t.scherer@eckelmann.de> (For siox)
Acked-by: Sven Van Asbroeck <TheSven73@gmail.com> (For anybuss)
Acked-by: Ulf Hansson <ulf.hansson@linaro.org> (For MMC)
Acked-by: Wolfram Sang <wsa@kernel.org> # for I2C
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Acked-by: Finn Thain <fthain@linux-m68k.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20210713193522.1770306-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Since snprintf() returns the would-be-output size instead of the
actual output size, the succeeding calls may go beyond the given
buffer limit. Fix it by replacing with scnprintf().
Fixes: fce8a7bb5b (PCI-Express Non-Transparent Bridge Support)
Fixes: 282a2feeb9 (NTB: Use DMA Engine to Transmit and Receive)
Fixes: a754a8fcaf (NTB: allocate number transport entries depending on size of ring size)
Fixes: d98ef99e37 (NTB: Clean up QP stats info)
Fixes: e74bfeedad (NTB: Add flow control to the ntb_netdev)
Fixes: 569410ca75 (NTB: Use unique DMA channels for TX and RX)
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Variable rc is initialized to a value that is never read and it
is re-assigned later. The initialization is redundant and can be
removed.
Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Introduce the module parameter 'use_msi' which, when set, uses
MSI interrupts instead of doorbells for each queue pair (QP). The
parameter is only available if NTB MSI support is configured into
the kernel. We also require there to be more than one memory window
(MW) so that an extra one is available to forward the APIC region.
To use MSIs, we request one interrupt per QP and forward the MSI address
and data to the peer using scratch pad registers (SPADS) above the MW
SPADS. (If there are not enough SPADS the MSI interrupt will not be used.)
Once registered, we simply use ntb_msi_peer_trigger and the receiving
ISR simply queues up the rxc_db_work for the queue.
This addition can significantly improve performance of ntb_transport.
In a simple, untuned, apples-to-apples comparision using ntb_netdev
and iperf with switchtec hardware, I see 3.88Gb/s without MSI
interrupts and 14.1Gb/s wit MSI, which is a more than 3x improvement.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Allen Hubbe <allenbh@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Dan Carpenter's static checker reported:
drivers/ntb/ntb_transport.c:1926 ntb_transport_create_queue()
error: we previously assumed 'qp->tx_dma_chan' could be null (see line 1872)
This is because the tx_mw_dma_addr is uninitialized in this function and
may be incorrectly released using a NULL DMA channel.
In practice this bug will not likely be seen. I'd guess you could hit
this if you loaded ntb_netdev with use_dma=True, then unloaded it and
loaded it again after setting the module parameter to use_dma=False.
To fix this, we simply ensure that tx_mw_dma_addr is always
initialized to zero. This is the safest in case any other part of the
code operates on it if it is non-zero.
Fixes: c59666bb32 ("NTB: ntb_transport: Ensure the destination buffer is mapped for TX DMA")
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Presently, when ntb_transport is used with DMA and the IOMMU turned on,
it fails with errors from the IOMMU such as:
DMAR: DRHD: handling fault status reg 202
DMAR: [DMA Write] Request device [00:04.0] fault addr
381fc0340000 [fault reason 05] PTE Write access is not set
This is because ntb_transport does not map the BAR space with the IOMMU.
To fix this, we map the entire MW region for each QP after we assign
the DMA channel. This prevents needing an extra DMA map in the fast
path.
Link: https://lore.kernel.org/linux-pci/499934e7-3734-1aee-37dd-b42a5d2a2608@intel.com/
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
If NTB peer host crashes or reboots, the NTB transport link will be
down and the MWs of NTB transport will be invalid. But the
ntb_transport_link_cleanup() does not free these invalid MWs. When
the NTB peer host is recovered later, NTB transport link will be
up and the ntb_set_mw() will not reset up MWs. Because the MWs of
NTB transport are invalid, the NTB transport will not work.
We can fix it by freeing MWs when NTB transport link is down, then
the ntb_set_mw() will reset up MWs when NTB transport link is up.
Signed-off-by: Joey Zhang <joey.zhang@microchip.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Be a little wasteful if the (likely CMA) message window buffer is not
suitably aligned after our first attempt; allocate a buffer twice as big
as we need and manually align our MW buffer within it.
This was needed on Intel Broadwell DE platforms with intel_iommu=off
Signed-off-by: Aaron Sierra <asierra@xes-inc.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Addresses-Coverity-ID: 1373888 ("Missing break in switch")
Addresses-Coverity-ID: 1373889 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Allen Hubbe <allenbh@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
- Additional struct_size() conversions (Matthew, Kees)
- Explicitly reported overflow fixes (Silvio, Kees)
- Add missing kvcalloc() function (Kees)
- Treewide conversions of allocators to use either 2-factor argument
variant when available, or array_size() and array3_size() as needed (Kees)
-----BEGIN PGP SIGNATURE-----
Comment: Kees Cook <kees@outflux.net>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=zUUp
-----END PGP SIGNATURE-----
Merge tag 'overflow-v4.18-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
Pull more overflow updates from Kees Cook:
"The rest of the overflow changes for v4.18-rc1.
This includes the explicit overflow fixes from Silvio, further
struct_size() conversions from Matthew, and a bug fix from Dan.
But the bulk of it is the treewide conversions to use either the
2-factor argument allocators (e.g. kmalloc(a * b, ...) into
kmalloc_array(a, b, ...) or the array_size() macros (e.g. vmalloc(a *
b) into vmalloc(array_size(a, b)).
Coccinelle was fighting me on several fronts, so I've done a bunch of
manual whitespace updates in the patches as well.
Summary:
- Error path bug fix for overflow tests (Dan)
- Additional struct_size() conversions (Matthew, Kees)
- Explicitly reported overflow fixes (Silvio, Kees)
- Add missing kvcalloc() function (Kees)
- Treewide conversions of allocators to use either 2-factor argument
variant when available, or array_size() and array3_size() as needed
(Kees)"
* tag 'overflow-v4.18-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: (26 commits)
treewide: Use array_size in f2fs_kvzalloc()
treewide: Use array_size() in f2fs_kzalloc()
treewide: Use array_size() in f2fs_kmalloc()
treewide: Use array_size() in sock_kmalloc()
treewide: Use array_size() in kvzalloc_node()
treewide: Use array_size() in vzalloc_node()
treewide: Use array_size() in vzalloc()
treewide: Use array_size() in vmalloc()
treewide: devm_kzalloc() -> devm_kcalloc()
treewide: devm_kmalloc() -> devm_kmalloc_array()
treewide: kvzalloc() -> kvcalloc()
treewide: kvmalloc() -> kvmalloc_array()
treewide: kzalloc_node() -> kcalloc_node()
treewide: kzalloc() -> kcalloc()
treewide: kmalloc() -> kmalloc_array()
mm: Introduce kvcalloc()
video: uvesafb: Fix integer overflow in allocation
UBIFS: Fix potential integer overflow in allocation
leds: Use struct_size() in allocation
Convert intel uncore to struct_size
...
ntb_transport_create_queue() is never called in atomic context.
ntb_transport_create_queue() is only called by ntb_netdev_probe(),
which is set as ".probe" in struct ntb_transport_client.
Despite never getting called from atomic context,
ntb_transport_create_queue() calls kzalloc_node() with GFP_ATOMIC,
which does not sleep for allocation.
GFP_ATOMIC is not necessary and can be replaced with GFP_KERNEL,
which can sleep and improve the possibility of sucessful allocation.
This is found by a static analysis tool named DCNS written by myself.
And I also manually check it
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
ntb_transport_setup_qp_mw() is never called in atomic context.
ntb_transport_setup_qp_mw() is only called by ntb_transport_link_work(),
which is set as a parameter of INIT_DELAYED_WORK()
in ntb_transport_probe().
Despite never getting called from atomic context,
ntb_transport_setup_qp_mw() calls kzalloc_node() with GFP_ATOMIC,
which does not sleep for allocation.
GFP_ATOMIC is not necessary and can be replaced with GFP_KERNEL,
which can sleep and improve the possibility of sucessful allocation.
This is found by a static analysis tool named DCNS written by myself.
And I also manually check it.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
When using the max_mw_size parameter of ntb_transport to limit the size of
the Memory windows, communication cannot be established and the queues
freeze.
This is because the mw_size that's reported to the peer is correctly
limited but the size used locally is not. So the MW is initialized
with a buffer smaller than the window but the TX side is using the
full window. This means the TX side will be writing to a region of the
window that points nowhere.
This is easily fixed by applying the same limit to tx_size in
ntb_transport_init_queue().
Fixes: e26a5843f7 ("NTB: Split ntb_hw_intel and ntb_transport drivers")
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
With Switchtec hardware it's impossible to get the alignment parameters
for a peer's memory window until the peer's driver has configured its
windows. Strictly speaking, the link doesn't have to be up for this,
but the link being up is the only way the client can tell that
the other side has been configured.
This patch converts ntb_transport and ntb_perf to use this function after
the link goes up. This simplifies these clients slightly because they
no longer have to store the alignment parameters. It also tweaks
ntb_tool so that peer_mw_trans will print zero if it is run before
the link goes up.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
It seems that under certain scenarios the SPAD can have bogus values caused
by an agent (i.e. BIOS or other software) that is not the kernel driver, and
that causes memory window setup failure. This should not cause the link to
be disabled because if we do that, the driver will never recover again. We
have verified in testing that this issue happens and prevents proper link
recovery.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Fixes: 84f766855f ("ntb: stop link work when we do not have memory")
After converting to the new API, both ntb_tool and ntb_transport are
using ntb_mw_count to iterate through ntb_peer_get_addr when they
should be using ntb_peer_mw_count.
This probably isn't an issue with the Intel and AMD drivers but
this will matter for any future driver with asymetric memory window
counts.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Allen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Fixes: 443b9a14ec ("NTB: Alter MW API to support multi-ports devices")
Even though there is no any real NTB hardware, which would have both more
than two ports and Scratchpad registers, it is logically correct to have
Scratchpad API accepting a peer port index as well. Intel/AMD drivers utilize
Primary and Secondary topology to split Scratchpad between connected root
devices. Since port-index API introduced, Intel/AMD NTB hardware drivers can
use device port to determine which Scratchpad registers actually belong to
local and peer devices. The same approach can be used if some potential
hardware in future will be multi-port and have some set of Scratchpads.
Here are the brief of changes in the API:
ntb_spad_count() - return number of Scratchpads per each port
ntb_peer_spad_addr(pidx, sidx) - address of Scratchpad register of the
peer device with pidx-index
ntb_peer_spad_read(pidx, sidx) - read specified Scratchpad register of the
peer with pidx-index
ntb_peer_spad_write(pidx, sidx) - write data to Scratchpad register of the
peer with pidx-index
Since there is hardware which doesn't support Scratchpad registers, the
corresponding API methods are now made optional.
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Multi-port NTB devices permit to share a memory between all accessible peers.
Memory Windows API is altered to correspondingly initialize and map memory
windows for such devices:
ntb_mw_count(pidx); - number of inbound memory windows, which can be allocated
for shared buffer with specified peer device.
ntb_mw_get_align(pidx, widx); - get alignment and size restriction parameters
to properly allocate inbound memory region.
ntb_peer_mw_count(); - get number of outbound memory windows.
ntb_peer_mw_get_addr(widx); - get mapping address of an outbound memory window
If hardware supports inbound translation configured on the local ntb port:
ntb_mw_set_trans(pidx, widx); - set translation address of allocated inbound
memory window so a peer device could access it.
ntb_mw_clear_trans(pidx, widx); - clear the translation address of an inbound
memory window.
If hardware supports outbound translation configured on the peer ntb port:
ntb_peer_mw_set_trans(pidx, widx); - set translation address of a memory
window retrieved from a peer device
ntb_peer_mw_clear_trans(pidx, widx); - clear the translation address of an
outbound memory window
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
There is some NTB hardware, which can combine more than just two domains
over NTB. For instance, some IDT PCIe-switches can have NTB-functions
activated on more than two-ports. The different domains are distinguished
by ports they are connected to. So the new port-related methods are added to
the NTB API:
ntb_port_number() - return local port
ntb_peer_port_count() - return number of peers local port can connect to
ntb_peer_port_number(pdix) - return port number by it index
ntb_peer_port_idx(port) - return port index by it number
Current test-drivers aren't changed much. They still support two-ports devices
for the time being while multi-ports hardware drivers aren't added.
By default port-related API is declared for two-ports hardware.
So corresponding hardware drivers won't need to implement it.
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Do not sleep in ntb_async_tx_submit, which could deadlock.
This reverts commit "8c874cc140d667f84ae4642bb5b5e0d6396d2ca4"
Fixes: 8c874cc140 ("NTB: Address out of DMA descriptor issue with NTB")
Reported-by: Jia-Ju Bai <baijiaju1990@163.com>
Signed-off-by: Allen Hubbe <Allen.Hubbe@dell.com>
Acked-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
A divide by zero error occurs if qp_count is less than mw_count because
num_qps_mw is calculated to be zero. The calculation appears to be
incorrect.
The requirement is for num_qps_mw to be set to qp_count / mw_count
with any remainder divided among the earlier mws.
For example, if mw_count is 5 and qp_count is 12 then mws 0 and 1
will have 3 qps per window and mws 2 through 4 will have 2 qps per window.
Thus, when mw_num < qp_count % mw_count, num_qps_mw is 1 higher
than when mw_num >= qp_count.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Fixes: e26a5843f7 ("NTB: Split ntb_hw_intel and ntb_transport drivers")
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
In cases where there are more mw's than spads/2-2, the mw count gets
reduced to match the limitation. ntb_transport also tries to ensure that
there are fewer qps than mws but uses the full mw count instead of
the reduced one. When this happens, the math in
'ntb_transport_setup_qp_mw' will get confused and result in a kernel
paging request bug.
This patch fixes the bug by reducing qp_count to the reduced mw count
instead of the full mw count.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Fixes: e26a5843f7 ("NTB: Split ntb_hw_intel and ntb_transport drivers")
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Fix typo causing ntb_transport_create_queue to select the first
queue every time, instead of using the next free queue.
Signed-off-by: Thomas VanSelus <tvanselus@xes-inc.com>
Signed-off-by: Aaron Sierra <asierra@xes-inc.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Fixes: fce8a7bb5 ("PCI-Express Non-Transparent Bridge Support")
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The call to debugfs_remove_recursive(qp->debugfs_dir) of the sub-level
directory must not be later than
debugfs_remove_recursive(nt_debugfs_dir) of the top-level directory.
Otherwise, the sub-level directory will not exist, and it would be
invalid (panic) to attempt to remove it. This removes the top-level
directory last, after sub-level directories have been cleaned up.
Signed-off-by: Allen Hubbe <Allen.Hubbe@dell.com>
Fixes: e26a5843f ("NTB: Split ntb_hw_intel and ntb_transport drivers")
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The results were previously ignored, anyway.
Signed-off-by: Steve Wahl <Steve.Wahl@dell.com>
Fixes: e26a5843f7
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
When the underlying NTB H/W driver advertises more memory windows
than the number of scratchpads available to setup MW's, it is likely
that we may end up filling the remaining memory windows with garbage.
So to avoid that, lets limit the memory windows that transport driver
can setup based on the available scratchpads.
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Acked-by: Allen Hubbe <Allen.Hubbe@dell.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
schedule_timeout_* takes a timeout in jiffies but the code currently is
passing in a constant which makes this timeout HZ dependent, so pass it
through msecs_to_jiffies() to fix this up.
Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Adding support on the rx DMA path to allow recovery of errors when
DMA responds with error status and abort all the subsequent ops.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Allen Hubbe <Allen.Hubbe@emc.com>
Cc: Jon Mason <jdmason@kudzu.us>
Cc: linux-ntb@googlegroups.com
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Adding support on the tx DMA path to allow recovery of errors when
DMA responds with error status and abort all the subsequent ops.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Allen Hubbe <Allen.Hubbe@emc.com>
Cc: Jon Mason <jdmason@kudzu.us>
Cc: linux-ntb@googlegroups.com
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
I'm working on hardware that currently has a limited number of
scratchpad registers and ntb_ndev fails with no clue as to why. I
feel it is better to fail early and provide a reasonable error message
then to fail later on.
The same is done to ntb_perf, but it doesn't currently require enough
spads to actually fail. I've also removed the unused SPAD_MSG and
SPAD_ACK enums so that MAX_SPAD accurately reflects the number of
spads used.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Currently we only allocate a fixed default number of descriptors for the tx
and rx side. We should dynamically resize it to the number of descriptors
resides in the transport rings. We should know the number of transmit
descriptors at initializaiton. We will allocate the default number of
descriptors for receive side and allocate additional ones when we know the
actual max entries for receive.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Allen Hubbe <allen.hubbe@emc.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Instead of keep trying to go through the init routine when we aren't able
to allocate memory, we should just stop and go down.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
We can leave tasklet spinning forever if we disable the tasklet during
qp shutdown and the tasklets are still being kicked off. This hopefully
should avoid that race condition.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reported-by: Alex Depoutovitch <alex@pernixdata.com>
Tested-by: Alex Depoutovitch <alex@pernixdata.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The transport right now does not handle the case where we run out of DMA
descriptors. We just fail when we do not succeed. Adding code to retry for
a bit attempting to use the DMA engine instead of instantly fail to CPU
copy.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Allen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The transmit overrun avoidance error path in ntb_process_tx accidentally
swapped the first two values being passed to the tx_handler client.
This could result in crashes in the ntb_netdev (or other out-of-tree NTB
clients).
Reported-by: Alex Depoutovitch <alex@pernixdata.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
resource_size_t may be 32-bit wide on some architectures, which causes
this warning when building the NTB code:
drivers/ntb/ntb_transport.c: In function 'ntb_transport_link_work':
drivers/ntb/ntb_transport.c:828:46: warning: right shift count >= width of type [-Wshift-count-overflow]
The warning is harmless but can be avoided by using the upper_32_bits()
macro.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: e26a5843f7 ("NTB: Split ntb_hw_intel and ntb_transport drivers")
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Order of operations issue with the QP Num and MW count, which would
result in the receive buffer pointer being invalid if there are more
than 1 MW. Corrected with parenthesis to enforce the proper order of
operations.
Reported-by: John I. Kading <John.Kading@gd-ms.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
These variables were not used anywhere. So remove them.
Signed-off-by: Sudip Mukherjee <sudip@vectorindia.org>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
We were accessing nt->mw_vec after freeing it. Fix the error path so
that we free nt->mw_vec after we have finished using it.
Signed-off-by: Sudip Mukherjee <sudip@vectorindia.org>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
smatch detected an issue in the function ntb_transport_max_size() where
we could be dereferencing a dma channel pointer when it is NULL.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Allocate two DMA channels, one for TX operation and one for RX
operation, instead of having one DMA channel for everything. This
provides slightly better performance, and also will make error handling
cleaner later on.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
The dma_sync_wait can hurt the performance of workloads mixed with both
large and small frames. Large frames will be copied using the dma
engine. Small frames will be copied by the cpu. The dma_sync_wait
prevents the cpu and dma engine copying in parallel.
In the period where the cpu is copying, the dma engine is stopped. The
dma engine is not doing any useful work to copy large frames during that
time, and the additional time to restart the dma engine for the next
large frame. This will decrease the throughput for the portion of a
workload with large frames.
In the period where the dma engine is copying, the cpu is held up
waiting for dma to complete. The small frames processing will be
delayed until the dma is complete. The RX frames are completed
in-order, and the processing of small frames takes very little time, so
dma_sync_wait may have an insignificant impact on the respose time of
frames. The more significant impact is to the system, because the delay
in dma_sync_wait is implemented as busy non-blocking wait. This can
prevent the delayed core from doing any useful work, even if it could be
processing work for other drivers, unrelated to transport RX processing.
After applying the earlier patch to fix out-of-order RX acknoledgement,
the dma_sync_wait is no longer necessary. Remove it, so that cpu memcpy
will proceed immediately for small frames, in parallel with ongoing dma
for large frames. Do not hold up the cpu from doing work while dma is
in progress. The prior fix will continue to ensure in-order completion
of the RX frames to the upper layer, and in-order delivery of the RX
acknoledgement.
Signed-off-by: Allen Hubbe <Allen.Hubbe@emc.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Make QP stats info more readable for debugging purposes. Also add an
entry to indicate whether DMA is being used.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Dave Jiang