This patch also contains ice_remove_adv_rule function to remove existing
advanced rules. It also handles the case when we have multiple VSI using
the same rule using the following helper functions:
ice_adv_rem_update_vsi_list - function to remove VS from VSI list for
advanced rules.
Signed-off-by: Shivanshu Shukla <shivanshu.shukla@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Code added to replay the advanced rule per VSI basis and remove the
advanced rule information from shared code recipe list.
Signed-off-by: Victor Raj <victor.raj@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
1. Added an interface to support adding advanced switch rules.
2. Advanced rules are provided in a form of protocol headers and values
to match in addition to actions (limited actions are current supported).
3. Retrieve field vectors for ICE configuration package to determine
extracted fields and extracted locations for recipe creation.
4. Chain multiple recipes together to match multiple protocol headers.
5. Add structure to manage the dynamic recipes.
Signed-off-by: Grishma Kotecha <grishma.kotecha@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Add functions to support following admin queue commands:
1. 0x0208: allocate resource to hold a switch recipe. This is needed
when a new switch recipe needs to be created.
2. 0x0290: create a recipe with protocol header information and
other details that determine how this recipe filter work.
3. 0x0292: get details of an existing recipe.
4. 0x0291: associate a switch recipe to a profile.
Signed-off-by: Grishma Kotecha <grishma.kotecha@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Add the Add Recipe (0x0290), Recipe to Profile (0x0291), Get Recipe
(0x0292) and Get Recipe to Profile (0x0293) Commands.
Signed-off-by: Lev Faerman <lev.faerman@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
When a port is not cabled, but DCBx is enabled in the firmware, the
status of DCBx will be NOT_STARTED. This is a valid state for FW
enabled and should not be treated as a is_fw_lldp true automatically.
Add the code to treat NOT_STARTED as another valid state.
Fixes: 1082f78654 ("net/ice/base: support DCB")
Cc: stable@dpdk.org
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Decouple ice_cfg_lldp_mib_change from the ice_init_dcb function call.
Signed-off-by: Chinh T Cao <chinh.t.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Once upon a time, the ice_flow_create_xtrct_seq() function in ice_flow.c
extracted only protocol fields explicitly specified by the caller of the
ice_flow_add_prof() function via its struct ice_flow_seg_info instances.
However, to support different ingress and egress flow profiles with the
same matching criteria, it would be necessary to also match on the
packet Direction metadata. The primary reason was because there could
not be more than one HW profile with the same CDID, PTG, and VSIG. The
Direction metadata was not a parameter used to select HW profile IDs.
Thus, for ACL, the direction flag would need to be added to the
extraction sequence. This information will be use later as one criteria
for ACL scenario entry matching.
Signed-off-by: Chinh T Cao <chinh.t.cao@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
According to API, 'rte_dev_probe()' and 'rte_dev_remove()' must
return 0 or negative error code. Bus code returns positive values
if device wasn't recognized by any driver, so the result of
'bus->plug/unplug()' must be converted. 'local_dev_probe()' and
'local_dev_remove()' also has their internal API, so the conversion
should be done there.
Positive on remove means that device not found by driver.
Positive on probe means that there are no suitable buses/drivers,
i.e. device is not supported.
Users of these API fixed to provide a good example by respecting
DPDK API. This also will allow to catch such issues in the future.
Fixes: a3ee360f44 ("eal: add hotplug add/remove device")
Fixes: 244d513071 ("eal: enable hotplug on multi-process")
Cc: stable@dpdk.org
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Putting a '__attribute__((deprecated))' in the middle of a function
prototype does not result in the expected result with gcc (while clang
is fine with this syntax).
$ cat deprecated.c
void * __attribute__((deprecated)) incorrect() { return 0; }
__attribute__((deprecated)) void *correct(void) { return 0; }
int main(int argc, char *argv[]) { incorrect(); correct(); return 0; }
$ gcc -o deprecated.o -c deprecated.c
deprecated.c: In function ‘main’:
deprecated.c:3:1: warning: ‘correct’ is deprecated (declared at
deprecated.c:2) [-Wdeprecated-declarations]
int main(int argc, char *argv[]) { incorrect(); correct(); return 0; }
^
Move the tag on a separate line and make it the first thing of function
prototypes.
This is not perfect but we will trust reviewers to catch the other not
so easy to detect patterns.
sed -i \
-e '/^\([^#].*\)\?__rte_experimental */{' \
-e 's//\1/; s/ *$//; i\' \
-e __rte_experimental \
-e '/^$/d}' \
$(git grep -l __rte_experimental -- '*.h')
Special mention for rte_mbuf_data_addr_default():
There is either a bug or a (not yet understood) issue with gcc.
gcc won't drop this inline when unused and rte_mbuf_data_addr_default()
calls rte_mbuf_buf_addr() which itself is experimental.
This results in a build warning when not accepting experimental apis
from sources just including rte_mbuf.h.
For this specific case, we hide the call to rte_mbuf_buf_addr() under
the ALLOW_EXPERIMENTAL_API flag.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
We had some inconsistencies between functions prototypes and actual
definitions.
Let's avoid this by only adding the experimental tag to the prototypes.
Tests with gcc and clang show it is enough.
git grep -l __rte_experimental |grep \.c$ |while read file; do
sed -i -e '/^__rte_experimental$/d' $file;
sed -i -e 's/ *__rte_experimental//' $file;
sed -i -e 's/__rte_experimental *//' $file;
done
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Those symbols are declared in the library map but the prototypes are
missing the experimental tag.
Without it, existing users won't notice it is experimental.
Fixes: ec0dec44ec ("net/atlantic: enable MACsec configuration")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
The incriminated commit promoted this symbol as stable but the
prototype still has the tag.
Fixes: fb1a20331d ("raw/dpaa2_qdma: remove experimental tag from APIs")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
The vmbus scan code can just skip non-network devices.
More importantly, this fixes the bug where some vmbus devices
don't have all the attributes (like monitor_id) and a single
failure would cause the scan to break the loop.
Fixes: 831dba47bd ("bus/vmbus: add Hyper-V virtual bus support")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
The Intel compiler is pickier about casts and generates:
otx2_mempool_ops.c(344):
error #191: type qualifier is meaningless on cast type
int64_t * const addr = (int64_t * const)
^
This is because of the nature of const.
In this example, the expression is being cast into a pointer
that can not be modified. This is meaningless because the
expression is already a lvalue.
See https://en.wikipedia.org/wiki/Const_(computer_programming)
Fixes: d7a0da3c00 ("mempool/octeontx2: add fast path mempool ops")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
When a component uses either XOPEN_SOURCE or POSIX_C_SOURCE macro
explicitly in its build recipe, it restricts visibility of a non POSIX
features subset, such as IANA protocol numbers (IPPROTO_* macros).
Non standard features are enabled by default for DPDK both for Linux
thanks to _GNU_SOURCE and for FreeBSD thanks to __BSD_VISIBLE. However
using XOPEN_SOURCE or POSIX_(C_)SOURCE in a component causes
__BSD_VISIBLE to be defined to 0 for FreeBSD, causing different feature
sets visibility for Linux and FreeBSD. It restricts from using IPPROTO
macros in public headers, such as rte_ip.h, despite the fact they are
already widely used in sources.
Add __BSD_VISIBLE macro specified unconditionally for FreeBSD targets
which enforces feature sets visibility unification between Linux and
FreeBSD.
Add single -D_GNU_SOURCE to config/meson.build as a project argument
instead of adding separate directive for each project subtree.
This patch solves the problem of build breaks for [1] on FreeBSD [2]
following the discussion [3].
[1] https://mails.dpdk.org/archives/dev/2019-May/131885.html
[2] http://mails.dpdk.org/archives/test-report/2019-May/082263.html
[3] https://mails.dpdk.org/archives/dev/2019-May/132110.html
Signed-off-by: Marcin Smoczynski <marcinx.smoczynski@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
The maximum number of mempools per application needs to be configured
on HW during mempool driver initialization. HW can support up to 1M
mempools, Since each mempool costs set of HW resources, the max_pools
devargs parameter is being introduced to configure the number of
mempools required for the application.
For example:
-w 0002:02:00.0,max_pools=512
With the above configuration, the driver will set up only 512 mempools
for the given application to save HW resources.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Harman Kalra <hkalra@marvell.com>
This patch adds an optimized arm64 instruction based routine to leverage
CPU pipeline characteristics of octeontx2. The theme is to fill the
pipeline with CASP operations as much HW can do so that HW can do alloc()
HW ops in full throttle.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
The DPDK mempool free operation frees HW AURA
and POOL reserved in alloc operation. In addition to that it free all
the memory resources allocated in mempool alloc operations.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
The DPDK mempool allocation reserves a single HW AURA
and POOL in 1:1 map mode. Upon reservation, SW programs the slow path
operations such as allocate stack memory for DMA and
bunch HW configurations to respective HW blocks.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Add a helper function to dump aura and pool context for NPA debugging.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Vivek Sharma <viveksharma@marvell.com>
Register and implement NPA IRQ handler for RAS and all type of
error interrupts to get the fatal errors from HW.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Implement the low-level NPA HW operations such as
alloc, free memory, etc.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
NPA object needs to initialize memory for queue interrupts context,
pool resource management, etc. This patch adds support for initializing
and finalizing the NPA object.
This patch also updates the otx2_npa_lf definition to meet the init/fini
requirements.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Add the make and meson based build infrastructure along
with the mempool(NPA) device probe.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Upon receiving FLR request from VF, It is PF responsibly
forward to AF and enable FLR for VFs.
This patch adds support for VF FLR support in PF.
This patch also add otx2_dev_active_vfs() API to find
the number of active VF for given PF.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Harman Kalra <hkalra@marvell.com>
The events like PHY link status change by AF or PHY configuration
change by PF would call for the uplink message.
The AF initiated uplink would land it in PF and PF would further
forward to VF(if it is intended for that specific VF)
The PF initiated uplink would be distributed to all active VFs.
This patch adds support for the same.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Harman Kalra <hkalra@marvell.com>
PF has additional responsibility being server for VF messages
and forward to AF and once AF process it then forward
the response back to VF.
otx2_vf_pf_mbox_irq() will process the VF mailbox request and
af_pf_wait_msg() will until getting a response back from AF.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
This patch adds support for AF to PF mailbox interrupt and message
handling. PF writes the message on mapped mailbox region
followed by writing the mailbox doorbell register. Upon receiving,
the mailbox request in AF(In Linux kernel), It processes the messages
and update the counter memory and update the AF mbox doorbell
register. That would trigger a VFIO interrupt to userspace and
otx2_process_msgs() will handle it.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
The mempool device(NPA) may be provisioned as a standalone device or
it can be part of ethdev/eventdev device. In order to address
mempool as standalone or integrated with ethdev/eventdev device,
An intra device structure being introduced.
When the _first_ ethdev/eventdev PCIe device or standalone mempool(NPA)
devices get probed by the eal PCI subsystem,
The NPA object(struct otx2_npa_lf) stored in otx2_dev base class.
Once it is accomplished, the other consumer drivers like
ethdev driver or eventdev driver use otx2_npa_* API to operate on
shared NPA object.
The similar concept followed for SSO object, Which needs to share between
PCIe devices.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
All PCIe drivers(ethdev, mempool, cryptodev and eventdev) in octeontx2,
needs to handle interrupt for mailbox and error handling.
Create a helper function over rte interrupt API to register,
unregister, disable interrupts.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Introduce otx2_dev class to hold octeontx2 PCIe device specific
information and operations.
All PCIe drivers(ethdev, mempool, cryptodev and eventdev) in octeontx2,
inherits this base object to avail the common functionalities such
as mailbox creation, interrupt registration, etc of the PCIe device.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Each RVU device has a dedicated 64KB mailbox region
shared with its peer for communication. RVU AF has
a separate mailbox region shared with each of RVU PFs
and an RVU PF has a separate region shared with each of
it's VF.
This patch add use 64KB memory and implemented mailbox
send and receive support.
These set of APIs are used by this driver (RVU AF) and
other RVU PF/VF drivers eg ethdev, cryptodev e.t.c.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
This patch adds mailbox init and fini support.
Each RVU device has a dedicated 64KB mailbox region
shared with its peer for communication. RVU AF has
a separate mailbox region shared with each of RVU PFs
and an RVU PF has a separate region shared with
each of it's VF.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
The admin function driver sits in Linux kernel as mailbox
server. The DPDK AF mailbox client, send the message to mailbox
server to complete the administrative task such as get mac
address.
This patch adds mailbox request and response definition of
existing mailbox defined between AF driver and DPDK driver.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Vivek Sharma <viveksharma@marvell.com>
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Signed-off-by: Zyta Szpak <zyta@marvell.com>
Various octeontx2 drivers use IO handling API, added octeontx2
specific IO handling routines in the common code.
Since some of those implementations are based on arm64 instructions
added the stub to compile the code on non arm64 ISA.
The non arm64 ISA stub is possible due to the fact that
it is an integrated controller i.e runs only on Marvell HW.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Add the make and meson based build infrastructure along with
HW definition header file.
This patch adds skeleton otx2_mbox.c file to make sure
all header files are intact, subsequent patches add content
to otx2_mbox.c
This patch also updates CONFIG_RTE_MAX_VFIO_GROUPS
value to 128 as the system can have up to 128 PFs/VFs.
For octeontx2 meson build target, CONFIG_RTE_MAX_VFIO_GROUPS
defined as 128 so no additional changes required.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
This driver had a bogus assert which could never happen.
This triggers "expression is always false warnings" with some
compilers which causes build failure.
Just remove it.
Fixes: 2af14ca79c ("net/qede: support 100G")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Rasesh Mody <rmody@marvell.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
This driver had a bogus assert which could never happen.
This triggers "expression is always false warnings" with some
compilers which causes build failure.
Just remove it.
Fixes: 6041aa619f ("net/bnx2x: fix poll link status")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Rasesh Mody <rmody@marvell.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
We should check the descriptor state instead of vq's internal
free count (i.e. the number of descriptors that we haven't made
available) for the remaining mergeable packets.
Fixes: a76290c8f1 ("net/virtio: implement Rx path for packed queues")
Cc: stable@dpdk.org
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
When there is no enough segments for a packet in mergeable
packed Rx path, we should free the whole mbuf chain instead
of just recycling the last segment.
Fixes: a76290c8f1 ("net/virtio: implement Rx path for packed queues")
Cc: stable@dpdk.org
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
When there is no enough segments for a packet in mergeable
Rx path, we should free the whole mbuf chain instead of just
recycling the last segment.
Fixes: bcac5aa207 ("net/virtio: improve batching in mergeable path")
Cc: stable@dpdk.org
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
When there is no enough segments for a packet in in-order
mergeable Rx path, we should free the whole mbuf chain instead
of just recycling the last segment.
Fixes: e5f456a98d ("net/virtio: support in-order Rx and Tx")
Cc: stable@dpdk.org
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
VLAN tag insertion should be in Tx prepare, not in Tx burst functions.
One of Tx prepare goals is to be able to do preparations in advance
(possibly on different CPU core) and then transmit it fast.
Also Tx prepare can report that a packet does not pass Tx offloads
check. E.g. has no enough headroom to insert VLAN header.
Fixes: 4fb7e803eb ("ethdev: add Tx preparation")
Cc: stable@dpdk.org
Signed-off-by: Dilshod Urazov <dilshod.urazov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Virtio requires pseudo-header checksum in TCP/UDP checksum to do
offload, but it was lost when Tx prepare is introduced. Also
rte_validate_tx_offload() should be used to validate Tx offloads.
Also it is incorrect to do virtio_tso_fix_cksum() after prepend
to mbuf without taking prepended size into account, since layer 2/3/4
lengths provide incorrect offsets after prepend.
Fixes: 4fb7e803eb ("ethdev: add Tx preparation")
Cc: stable@dpdk.org
Signed-off-by: Dilshod Urazov <dilshod.urazov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so all the private
resources for the port can be freed by rte_eth_dev_close().
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
We should unmap the device when we failed to initialize the device.
Fixes: 6ba1f63b5a ("virtio: support specification 1.0")
Cc: stable@dpdk.org
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
For legacy devices, we should also unmap the port IO
resource on device removal.
Fixes: b8f04520ad ("virtio: use PCI ioport API")
Cc: stable@dpdk.org
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
We should free queues when we failed to initialize the virtio device.
Fixes: 26b683b4f7 ("net/virtio: setup Rx queue interrupts")
Cc: stable@dpdk.org
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
DEBUG_DUMP_DESC flag is commented out in IAVF Makefile and to enable
it user needs to edit the Makefile. It is felt that this method is not
good. Hence removing this flag from IAVF makefile and adding a flag
CONFIG_RTE_LIBRTE_IAVF_DEBUG_DUMP_DESC to config/common_base.
Signed-off-by: Lavanya Govindarajan <lavanyax.govindarajan@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
This driver was inserting its own stub for queue_stats_mapping which
did nothing but cause this device to return a different errno
than every other device driver. All devices that don't implement
queue stats mapping should return the same error.
Maybe the plan originally was to implement something, if that
ever happens, just put in the right code.
Fixes: 4861cde461 ("i40e: new poll mode driver")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Copy/paste from i40e, let's align with the fix on i40e.
Fixes: a37bde5631 ("net/ice: support statistics")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
i40e and i40evf currently use two different names for the statistic on
dropped packets on the rx and tx sides.
Let's prefer i40evf so that all statistics are suffixed with _packets.
This also avoids a statistic name conflict in OVS.
Fixes: f4a91c38b4 ("i40e: add extended stats")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
In 'ipn3ke_hw_tm_node_wr()', elements of 'n->parent_node' are accessed
but 'n->parent_node' can be NULL.
After applying this patch, this null pointer dereference is avoided.
Coverity issue: 337921
Fixes: c820468ac9 ("net/ipn3ke: support TM")
Cc: stable@dpdk.org
Signed-off-by: Andy Pei <andy.pei@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
Check input argument "rte_eth_dev *ethdev", to be sure variable is not
NULL before operating on it.
Coverity issue: 337922
Fixes: 70d6b7f550 ("net/ipn3ke: add representor")
Cc: stable@dpdk.org
Signed-off-by: Andy Pei <andy.pei@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
Whether the if statement is true or not, the operation is identical.
It is unnecessary to check the if statement, so just delete the if
statement.
Coverity issue: 337928
Fixes: c820468ac9 ("net/ipn3ke: support TM")
Cc: stable@dpdk.org
Signed-off-by: Andy Pei <andy.pei@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
The VF spinlock was never initialized. It works because it is
in zmalloc'd memory and an unlocked lock on x86 is 0.
But for good practice, all spinlock's should be initialized.
Fixes: dc7680e859 ("net/netvsc: support integrated VF")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Implement the efx_proxy_auth_privilege_mask_get() to get a function's
privilege mask and efx_proxy_auth_privilege_modify() to add/remove
privileges for a function specified by PF and VF index.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Hypervisor should be able to track VF statistics.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Implement functions to set vPort VLAN and MAC address and reset the vPort.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Implement the APIs for PROXY_CMD, PROXY_COMPLETE and PRIVILEGE_MASK
messages to allow client drivers authorize VF operations like set MAC,
set MTU etc. with firmware.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Add the capability to receive MCDI proxy event from firmware and
invoke the client driver registered function to handle it.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
VMware expects that certain kind of configurations made on the VFs are
authorized by the ESXi before these are applied e.g. assigning a MAC
address to the VF, setting MTU etc. Firmware supports a feature called
MCDI proxy which will be used to implement this authorization check.
The proxy auth module is governed by EFSYS_OPT_MCDI_PROXY_AUTH switch.
This patch adds the framework for proxy auth module along with the APIs
required for SR-IOV initialization.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
ef10_nic_init() allocates a vAdaptor for the physical port in current
flow. In case of SR-IOV, this vAdaptor must be created for the PF as the
vSwitch is allocated on the physical port. So, the call to
efx_mcdi_vadaptor_alloc() should be avoided in ef10_nic_init() in SR-IOV
flow. To achieve this, for SR-IOV use case, the vSwitch is created
before NIC initialization and its handle is used to prevent vAdaptor
allocation in ef10_nic_init(). This approach has been taken to minimize
the changes in NIC initialization flow.
This is also the case with Linux driver where vSwitch creation happens
before NIC initialization.
Also, when DMA queues need to be allocated for Tx/Rx functionality
(MC_CMD_INIT_RXQ / MC_CMD_INIT_TXQ), the correct vPort is selected
based on efx_vswitch_t property of efx_nic_t structure - vport
corresponding to PF in case of SR-IOV use case and EVB_PORT_ID_ASSIGNED
for physical port.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Separate out vAdaptor allocation from ef10_nic_init() as it is not
required for SR-IOV use case. In case of SR-IOV, vAdaptor is allocated
early along with vSwitch creation and vPort configuration.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
The vSwitch create API takes an array of num_vports client driver
allocated vPort config entries where entry at index 0 contains the PF
configuration and rest num_vports-1 entries refer to vPort configuration
for VFs 0 to (num_vports-2). The required hierarchy
(vswitch/vport/vadaptor) is created within this API. The destroy API
tears down this hierarchy and releases memory for the vSwitch object.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Implement functions to allocate and free vSwitch, vPort and vAdaptor.
Also, implement functions to add and delete vPort MAC address and EVB
port assign.
Most of the efx_evb_ops_t functions take vSwitch ID as a parameter for
future enhancements. Currently, firmware doesn't implement vSwitch
identifier and hence this parameter is unused for EF10 architecture
implementation.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Add the functions to implement the vPort and vSwitch MCDI calls.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Implement the framework for Enterprise Virtual Briding (EVB) module.
SR-IOV augments the software virtual switch with NIC capabilities
supported from EVB module.
Further patches will add APIs to create and destroy EVB switching
hierarchy required for SR-IOV and APIs to set vPort properties like MAC,
VLAN etc.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Proxy authorization module for SR-IOV requires one instance of proxy
data structures per card. In order to achieve this, proxy data
structures will be allocated only for primary port (port id 0) and other
secondary ports in the card will access those data structures through
reference to primary port. Accordingly, the port number obtained from
efx_mcdi_get_port_assignment is stored in NIC configuration as
enc_mcdi_port.
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Allows to enable additional functionality related to this OEM
(e.g. vendor extensions to VPD, NC-SI etc.)
Signed-off-by: Kevin Lampis <klampis@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Request firmware updates be performed in background mode.
In this mode MCDI to the function processing the update
remains accessible and the client polls for completion.
This is supported for lengthy partition updates such as
MCFW and bundles. The MC ignores the flags used for this
mode for other partition updates.
Signed-off-by: Richard Houldsworth <rhouldsworth@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Old NVRAM info API required function prototype too often.
Signed-off-by: Richard Houldsworth <rhouldsworth@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
All signed images other than for the MCFW partition should
be written fully to the partition with no rearrangement.
Signed-off-by: Richard Houldsworth <rhouldsworth@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Add definitions header for reflash header IDs. This is required to
support different handling modes for signed firmware images.
Signed-off-by: Richard Houldsworth <rhouldsworth@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Add function to query partition characteristics.
Refactor efx_nvram_size to share implementation.
Signed-off-by: Richard Houldsworth <rhouldsworth@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Includes the partition read-only flag, to allow for
checks before opening the partition.
Signed-off-by: Richard Houldsworth <rhouldsworth@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Support the registration of a version string by the libefx
client. The string is passed on to the MC in efx_nic_probe
only to allow the MC to advertise the OS driver version in
NC-SI, and the content is considered opaque for libefx.
Signed-off-by: Richard Houldsworth <rhouldsworth@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Types defined in efx_types.h are used in efx.h and it is better do
not rely on the header inclusion from somewhere else (typically from
efsys.h).
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Add more comments to simplify code reading and understanding.
Signed-off-by: Mark Spender <mspender@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
This was probably an oversight when support for multiple sensor pages
was added.
Despite being undefined behaviour in C, it probably worked on Intel
x32/x64 as on them bit shift operations wrap round.
Fixes: dfb3b1ce15 ("net/sfc/base: import monitors access via MCDI")
Cc: stable@dpdk.org
Signed-off-by: Mark Spender <mspender@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Use UINT32_MAX instead of assigning -1 to a uint32_t variable to
resolve "conversion from 'int' to 'uint32_t', signed/unsigned mismatch"
errors produced by the Visual Studio 2017 toolchain [with the default
/W4 /WX C compiler options which set warning level 4 and treat warnings
as errors].
Fixes: 107cf1d792 ("net/sfc/base: move limits config to ef10 NIC board config")
Cc: stable@dpdk.org
Signed-off-by: Andrew Lee <alee@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Set WORKAROUND_BUG26807 which does the job.
Fix the misunderstanding in the Medford code: i.e. the workaround is
always supported by firmware, but the driver still needs to enable it.
Also, as it now applies to all EF10 controllers, the implementation is
moved to EF10 common place.
Fixes: 94190e3543 ("net/sfc/base: import SFN8xxx family support")
Fixes: 2b38e7b7b7 ("net/sfc/base: add Medford2 support to NIC module")
Cc: stable@dpdk.org
Signed-off-by: Gautam Dawar <gdawar@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Using access followed by open causes a static analysis warning
about Time of check versus Time of use. Also, access() and
open() have different UID permission checks.
This is not a serious problem; but easy to fix by using errno instead.
Coverity issue: 300870
Fixes: 4a928ef9f6 ("bus/pci: enable write combining during mapping")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: David Marchand <david.marchand@redhat.com>
The driver was defining its own version of roundup which was
conflicting with another version defined elsewhere.
Change the local definition of roundup to avoid compilation errors.
Fixes: f8168ca0e6 ("net/bnxt: support thor controller")
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
There is the patch [1] that uses master device Netlink socket
to retrieve master device link settings. This is not thread safe
because this resource may be in use by other call to the master
device itself. Using the same Netlink socket concurrently from
the multiple threads causes Netlink requests malfunction and
must be eliminated. The patch replaces master Netlink socket
with the socket from representor device.
[1] http://patches.dpdk.org/patch/53120/
Fixes: 0333b2f584 ("net/mlx5: inherit master link settings for representors")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
The SQ errors recovery mechanism in the PMD invokes a Verbs
functions to modify the RQ states in order to reset the SQ and to
reactivate it.
These Verbs functions are not allowed to be invoked from a secondary
process, hence the PMD skips the recovery when the error is captured
by secondary processes queues.
Using the DPDK IPC mechanism the secondary process can request Verbs
queues state modifications to be done synchronically by the primary
process.
Add support for secondary process Tx errors recovery.
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
The RQ errors recovery mechanism in the PMD invokes a Verbs functions to
modify the RQ states in order to reset the RQ and to reactivate it.
These Verbs functions are not allowed to be invoked from a secondary
process, hence the PMD skips the recovery when the error is captured by
secondary processes queues.
Using the DPDK IPC mechanism the secondary process can request Verbs
queues state modifications to be done synchronically by the primary
process.
Add support for secondary process Rx errors recovery.
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
When WQEs are posted to the HW to send packets, the PMD may get a
completion report with error from the HW, aka error CQE which is
associated to a bad WQE.
The error reason may be bad address, wrong lkey, bad sizes, etc.
that can wrongly be configured by the PMD or by the user.
Checking all the optional mistakes to prevent error CQEs doesn't make
sense due to performance impacts and huge complexity.
The error CQEs change the SQ state to error state what causes all the
next posted WQEs to be completed with CQE flush error forever.
Currently, the PMD doesn't handle Tx error CQEs and even may crashed
when one of them appears.
Extend the Tx data-path to detect these error CQEs, to report them by
the statistics error counters, to recover the SQ by moving the state
to ready again and adjusting the management variables appropriately.
Sometimes the error CQE root cause is very hard to debug and even may
be related to some corner cases which are not reproducible easily, hence
a dump file with debug information will be created for the first number
of error CQEs, this number can be configured by the PMD probe
parameters.
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
When WQEs are posted to the HW to receive packets, the PMD may receive
a completion report with error from the HW, aka error CQE which is
associated to a bad WQE.
The error reason may be bad address, wrong lkey, small buffer size,
etc. that can wrongly be configured by the PMD or by the user.
Checking all the optional mistakes to prevent error CQEs doesn't make
sense due to performance impacts, moreover, some error CQEs can be
triggered because of the packets coming from the wire when the DPDK
application has no any control.
Most of the error CQE types change the RQ state to error state what
causes all the next received packets to be dropped by the HW and to be
completed with CQE flush error forever.
The current solution detects these error CQEs and even reports the
errors to the user by the statistics error counters but without
recovery, so if the RQ inserted to the error state it never moves to
ready state again and all the next packets ever will be dropped.
Extend the error CQEs handling for recovery by moving the state to
ready again, and rearranging all the RQ WQEs and the management
variables appropriately.
Sometimes the error CQE root cause is very hard to debug and even may
be related to some corner cases which are not reproducible easily,
hence a dump file with debug information will be created for the first
number of error CQEs, this number can be configured by the PMD probe
parameters.
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
