Qi Zhang [Tue, 16 Oct 2018 00:16:29 +0000 (08:16 +0800)]
eal: support attach/detach shared device from secondary
This patch cover the multi-process hotplug case when a device
attach/detach request be issued from a secondary process
device attach on secondary:
a) secondary send sync request to the primary.
b) primary receive the request and attach the new device if
failed goto i).
c) primary forward attach sync request to all secondary.
d) secondary receive the request and attach the device and send a reply.
e) primary check the reply if all success goes to j).
f) primary send attach rollback sync request to all secondary.
g) secondary receive the request and detach the device and send a reply.
h) primary receive the reply and detach device as rollback action.
i) send attach fail to secondary as a reply of step a), goto k).
j) send attach success to secondary as a reply of step a).
k) secondary receive reply and return.
device detach on secondary:
a) secondary send sync request to the primary.
b) primary send detach sync request to all secondary.
c) secondary detach the device and send a reply.
d) primary check the reply if all success goes to g).
e) primary send detach rollback sync request to all secondary.
f) secondary receive the request and attach back device. goto h).
g) primary detach the device if success goto i), else goto e).
h) primary send detach fail to secondary as a reply of step a), goto j).
i) primary send detach success to secondary as a reply of step a).
j) secondary receive reply and return.
Qi Zhang [Tue, 16 Oct 2018 00:16:28 +0000 (08:16 +0800)]
eal: enable hotplug on multi-process
We are going to introduce the solution to handle hotplug in
multi-process, it includes the below scenario:
1. Attach a device from the primary
2. Detach a device from the primary
3. Attach a device from a secondary
4. Detach a device from a secondary
In the primary-secondary process model, we assume devices are shared
by default. that means attaches or detaches a device on any process
will broadcast to all other processes through mp channel then device
information will be synchronized on all processes.
Any failure during attaching/detaching process will cause inconsistent
status between processes, so proper rollback action should be considered.
This patch covers the implementation of case 1,2.
Case 3,4 will be implemented on a separate patch.
IPC scenario for Case 1, 2:
attach a device
a) primary attach the new device if failed goto h).
b) primary send attach sync request to all secondary.
c) secondary receive request and attach the device and send a reply.
d) primary check the reply if all success goes to i).
e) primary send attach rollback sync request to all secondary.
f) secondary receive the request and detach the device and send a reply.
g) primary receive the reply and detach device as rollback action.
h) attach fail
i) attach success
detach a device
a) primary send detach sync request to all secondary
b) secondary detach the device and send reply
c) primary check the reply if all success goes to f).
d) primary send detach rollback sync request to all secondary.
e) secondary receive the request and attach back device. goto g)
f) primary detach the device if success goto g), else goto d)
g) detach fail.
h) detach success.
Qi Zhang [Tue, 16 Oct 2018 00:16:27 +0000 (08:16 +0800)]
ethdev: add function to release port in secondary process
Add driver API rte_eth_release_port_secondary to support the
case when an ethdev need to be detached on a secondary process.
Local state is set to unused and shared data will not be reset
so the primary process can still use it.
However, Except the first file, the change missed to include
<rte_vfio.h> where HAVE_VFIO_DEV_REQ_INTERFACE defined.
This creates runtime following error on vfio-pci mode and
kernel >= 4.0.0 combination.
EAL: [rte_intr_enable] Unknown handle type of fd 95
EAL: [pci_vfio_enable_notifier]Fail to enable req notifier.
EAL: Fail to unregister req notifier handler.
EAL: Error setting up notifier!
EAL: Requested device 0000:07:00.1 cannot be used
Fixes: cda94419964f ("vfio: fix build with Linux < 4.0") Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com> Signed-off-by: Pavan Nikhilesh <pbhagavatula@caviumnetworks.com>
Hemant Agrawal [Fri, 12 Oct 2018 10:04:24 +0000 (15:34 +0530)]
net/dpaa2: enhance queue memory cleanup
Earlier the tx queue data was getting cleaned up in close
while rest of the functionality was in un-init.
Now a new func is created to free queue memory.
Shreyansh Jain [Fri, 12 Oct 2018 10:04:21 +0000 (15:34 +0530)]
net/dpaa2: support statistics per queue
For now, only the packet count stats per queue is available. This is
part of xstats output (though, per queue stats are actually part of
rte_eth_stats basic stats).
Shreyansh Jain [Fri, 12 Oct 2018 10:04:20 +0000 (15:34 +0530)]
net/dpaa2: read hardware provided MAC for DPNI devices
Firmware would contain pre-configured devices for each DPMAC backing
a DPNI. This patch reads those MAC address when the device is
initialized and sets it. THereafter, it can be changed through API or
commands from testpmd.
Shreyansh Jain [Mon, 15 Oct 2018 12:01:56 +0000 (17:31 +0530)]
fslmc: enable dpaax library
With this patch, fslmc bus and ethernet devices on this bus
would start using the physical-virtual library interfaces.
This patch impacts mempool/dpaa2, event/dpaa2, net/dpaa2,
raw/dpaa2_cmdif and raw/dpaa2_qdma as they are dependent
on the bus/fslmc and thus impact linkage of libraries.
Shreyansh Jain [Mon, 15 Oct 2018 12:01:54 +0000 (17:31 +0530)]
common/dpaax: add library for PA/VA translation table
A common library, valid for dpaaX drivers, which is used to maintain
a local copy of PA->VA translations.
In case of physical addressing mode (one of the option for FSLMC, and
only option for DPAA bus), the addresses of descriptors Rx'd are
physical. These need to be converted into equivalent VA for rte_mbuf
and other similar calls.
Using the rte_mem_virt2iova or rte_mem_virt2phy is expensive. This
library is an attempt to reduce the overall cost associated with
this translation.
A small table is maintained, containing continuous entries
representing a continguous physical range. Each of these entries
stores the equivalent VA, which is fed during mempool creation, or
memory allocation/deallocation callbacks.
Jeff Guo [Tue, 16 Oct 2018 11:42:33 +0000 (19:42 +0800)]
vfio: fix build with Linux < 4.0
Since the older kernel version do not implement the device request
interface for vfio, so when build on the kernel < v4.0.0, which is
the version begin to add the device request interface, it will
throw the error to show “VFIO_PCI_REQ_IRQ_INDEX” is undeclared.
This patch aim to fix this compile issue by add the macro
“HAVE_VFIO_DEV_REQ_INTERFACE” after checking the kernel version.
Jeff Guo [Thu, 4 Oct 2018 06:44:43 +0000 (14:44 +0800)]
vfio: handle hotplug request notifier
When device is be hot-unplugged, the vfio kernel module will sent req
notifier to request user space to release the allocated resources at
first. After that, vfio kernel module will detect the device disappear,
and then delete the device in kernel.
This patch aim to add req notifier processing to enable hotplug for vfio.
By enable the req notifier monitoring and register the notifier callback,
when device be hot-unplugged, the hot-unplug handler will be called to
process hotplug for vfio.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Jeff Guo [Thu, 4 Oct 2018 06:44:42 +0000 (14:44 +0800)]
bus/pci: add VFIO request interrupt handle to device
There are some extended interrupt types in vfio pci device except from the
existing interrupts, such as err and req notifier, they could be useful for
device error monitoring. And these corresponding interrupt handler is
different from the other interrupt handler that register in PMDs, so a new
interrupt handler should be added. This patch will add specific req handler
in generic pci device.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Jeff Guo [Thu, 4 Oct 2018 06:44:41 +0000 (14:44 +0800)]
eal: modify device event process function
This patch modify the device event callback process function name to be
more explicit, change the variable to be const. And more, because not only
eal device helper will use the callback, but also vfio bus will use the
callback to handle hot-unplug, so exposure the API out from private eal.
The bus drivers and eal device would directly use this API to process
device event callback.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Jeff Guo [Mon, 15 Oct 2018 11:27:27 +0000 (19:27 +0800)]
app/testpmd: use hotplug failure handler
This patch use testpmd for example, to show how an app smoothly handle
failure when device be hot-unplug. Except that app should enabled the
device event monitor and register the hotplug event’s callback, it also
need enable hotplug handle mechanism before running. Once app detect the
removal event, the hot-unplug callback would be called. It will first stop
the packet forwarding, then stop the port, close the port, and finally
detach the port to clean the device and release the resources.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Jeff Guo [Mon, 15 Oct 2018 11:27:26 +0000 (19:27 +0800)]
eal: add failure handling for hot-unplug
The mechanism can initially register the sigbus handler after the device
event monitor is enabled. When a sigbus event is captured, it will check
the failure address and accordingly handle the memory failure of the
corresponding device by invoke the hot-unplug handler. It could prevent
the application from crashing when a device is hot-unplugged.
By this patch, users could call below new added APIs to enable/disable
the device hotplug handle mechanism. Note that it just implement the
hot-unplug handler in these functions, the other handler of hotplug, such
as handler for hotplug binding, could be add in the future if need:
- rte_dev_hotplug_handle_enable
- rte_dev_hotplug_handle_disable
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Jeff Guo [Mon, 15 Oct 2018 11:27:24 +0000 (19:27 +0800)]
bus/pci: support sigbus handler
This patch implements the ops for the PCI bus sigbus handler. It finds the
PCI device that is being hot-unplugged and calls the relevant ops of the
hot-unplug handler to handle the hot-unplug failure of the device.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Shaopeng He <shaopeng.he@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Jeff Guo [Mon, 15 Oct 2018 11:27:23 +0000 (19:27 +0800)]
bus: add sigbus handler
When a device is hot-unplugged, a sigbus error will occur of the datapath
can still read/write to the device. A handler is required here to capture
the sigbus signal and handle it appropriately.
This patch introduces a bus ops to handle sigbus errors. Each bus can
implement its own case-dependent logic to handle the sigbus errors.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Shaopeng He <shaopeng.he@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Jeff Guo [Mon, 15 Oct 2018 11:27:22 +0000 (19:27 +0800)]
bus/pci: support hot-unplug handler
This patch implements the ops to handle hot-unplug on the PCI bus.
For UIO PCI, it could avoids BARs read/write errors by creating a
new dummy memory to remap the memory where the failure is. For VFIO
or other kernel driver, it could specific implement function to handle
hot-unplug case by case.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Shaopeng He <shaopeng.he@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Jeff Guo [Mon, 15 Oct 2018 11:27:21 +0000 (19:27 +0800)]
bus: add hot-unplug handler
A hot-unplug failure and app crash can be caused, when a device is
hot-unplugged but the application still try to access the device
by reading or writing from the BARs, which is already invalid but
still not timely be unmap or released.
This patch introduces bus ops to handle hot-unplug failures. Each
bus can implement its own case-dependent logic to handle the failures.
Signed-off-by: Jeff Guo <jia.guo@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
This patch introduces a new table action for packet decapsulation
which removes n bytes from the start of the input packet. The n
is read from the current table entry. The following mbuf fields
are updated by the action: data_off, data_len, pkt_len.
This patch introduces the packet tag table action which attaches
a 32-bit value (the tag) to the current input packet. The tag is
read from the current table entry. The tag is written into the
mbuf->hash.fdir.hi and the flags PKT_RX_FDIR and PKT_RX_FDIR_ID
are set into mbuf->ol_flags.
Fan Zhang [Fri, 28 Sep 2018 12:26:09 +0000 (13:26 +0100)]
pipeline: add symmetric crypto table action
This patch adds the symmetric crypto action support to pipeline
library. The symmetric crypto action works as the shim layer
between pipeline and DPDK cryptodev and is able to interact with
cryptodev with the control path requests such as session
creation/deletion and data path work to assemble the crypto
operations for received packets.
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Fan Zhang [Mon, 1 Oct 2018 10:02:23 +0000 (11:02 +0100)]
port: add symmetric crypto
This patch adds the symmetric crypto support to port library.
The crypto port acts as a shim layer to DPDK cryptodev library and
supports in-place crypto workload processing.
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Support for validating and mapping rte flow rule with
ACL table match is added.
As part of this support below utility functions
been added
flow_rule_match_get()
flow_rule_match_acl_get()
flow_item_skip_disabled_protos()
flow_item_proto_preprocess()
flow_item_is_proto()
flow_item_raw_preprocess()
Change dev_name, action_profile_name and key_mask
from char* type to arary type of structures
softnic_port_in_params, softnic_port_out_params
and softnic_table_hash_params.
Kevin Laatz [Tue, 25 Sep 2018 15:32:28 +0000 (16:32 +0100)]
lib/librte_table: add hash function headers
This commit adds rte_table_hash_func.h and rte_table_hash_func_arm64.h to
librte_table. This reduces code duplication by removing duplicate header
files within two folders and consolidating them into a single one. This
also adds a scalar implementation of the x86_64 intrinsic for crc32 as a
generic fallback.
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com> Signed-off-by: Kevin Laatz <kevin.laatz@intel.com> Acked-by: Gavin Hu <gavin.hu@arm.com> Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Krzysztof Kanas [Fri, 17 Aug 2018 11:39:19 +0000 (13:39 +0200)]
app/testpmd: add TM commands to mark packets
Add following testpmd run-time commands to support test of TM packet
marking:
set port tm mark ip_ecn <port_id> <green> <yellow> <red>
set port tm mark ip_dscp <port_id> <green> <yellow> <red>
set port tm mark vlan_dei <port_id> <green> <yellow> <red>
Signed-off-by: Krzysztof Kanas <krzysztof.kanas@caviumnetworks.com>
Rosen Xu [Thu, 16 Aug 2018 01:14:16 +0000 (09:14 +0800)]
ethdev: expand queue threshold size of RED parameters
There's very commonly that more than 4G DDR memory in NIC for HQoS,
so right now the queue threshold size of RED needs to expand to
uint64_t. This patch fixes it.
eal: use correct data type for bitmap slab operations
Currently, slab operations use unsigned long data type for 64-bit slab
related operations. On target 'i686-native-linuxapp-gcc', unsigned long
is 32-bit and thus, slab operations breaks on this target. Changing slab
operations to use unsigned long long for correct functioning on
all targets.
Ivan Malov [Thu, 11 Oct 2018 14:51:13 +0000 (15:51 +0100)]
net/sfc: allow to query RSS key and HF when RSS is disabled
If global RSS is not enabled in the multiqueue mode setting,
it will not be possible to change RSS configuration. However,
querying default RSS settings should be possible in any case since
it may be needed by RTE flow API users to find out what RSS settings
will be used by default for a flow rule with RSS action if custom
RSS key and hash function choice are not specified.
Fixes: 63ab5e0c8fda ("net/sfc: use zero RSS channels as disabled RSS indicator") Cc: stable@dpdk.org Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Ivan Malov [Thu, 11 Oct 2018 14:51:12 +0000 (15:51 +0100)]
net/sfc: allow to query RSS key and HF in isolated mode
Isolated mode prevents global RSS from being enabled and configured.
However, an application may need to query default RSS key and hash
functions when a flow rule with RSS action is added which does not
contain custom RSS key or hash function choice. In this case
global RSS key and hash functions will be used to handle the rule,
and there should be some way for the application to query these
global default settings to clarify expectations on the traffic
distribution.
Fixes: 84a9b48128c1 ("net/sfc: support flow API isolated mode") Cc: stable@dpdk.org Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Ivan Malov [Thu, 11 Oct 2018 14:49:30 +0000 (15:49 +0100)]
net/sfc: do not skip RSS configuration step on reconfigure
Earlier a patch was made to support change of Rx queue
number. That patch added goto label in wrong place
because reconfiguration with the same number of queues
results in skipping not only queue init but also RSS
settings. If a user configures device with RSS multiqueue
mode and then wants to stop it and reconfigure without RSS,
this change will be ignored and RSS will continue working.
Move the label in the right place and rename it to describe it.
Fixes: 55a539003f1a ("net/sfc: support changing the number of receive queues") Cc: stable@dpdk.org Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
net/e1000: enable MSI-x for linkup and other events in 82574
Linux supports 82574 MSI-x interrupt for linkup and other link
conditions. Enable the same feature in the e1000 PMD in order to
allow this card to work properly, as it requires interrupt
handling for link negotiations among other things.
net/e1000: do not error out if Rx drop enable is set
rx_drop_en is an optimization that does nothing on single-queue
devices like e1000. Do not force applications that do not care to
select per-devices optimizations flags by returning an error, just
log it and carry on.
Fixes: 805803445a02 ("e1000: support EM devices (also known as e1000/e1000e)") Cc: stable@dpdk.org Signed-off-by: Luca Boccassi <bluca@debian.org> Acked-by: Wei Zhao <wei.zhao1@intel.com>
flow create 0 transfer ingress
pattern eth / ipv4 / udp dst is 7000 / end
actions set_ipv4_src ipv4_addr 172.168.0.1 /
set_ipv4_dst ipv4_addr 172.168.10.1 /
set_tp_dst port 9000 /
set_tp_src port 700 /
port_id id 1 / end
Signed-off-by: Xiaoyu Min <jackmin@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Moti Haimovsky [Thu, 11 Oct 2018 10:48:39 +0000 (10:48 +0000)]
net/mlx5: support e-switch TCP-flags flow filter
This patch adds support for offloading flow rules with TCP-flags
filter to mlx5 eswitch Hardwrae.
With mlx5 it is possible to offload a limited set of flow rules to
the mlxsw (or e-switch) using the DPDK flow commands using the
"transfer" attribute. This set of flow rules also supports filtering
according to the values found in the TCP flags.
This patch implements this offload capability in the mlx5 PMD under
transfer attribute.
git.droids-corp.org / dpdk.git / log