| Age | Commit message (Collapse) | Author |
|---|
|
Generate a traffic type bitmap that will define which
steering objects we need to create for the steering
based LAG.
Bits in this bitmap are set according to the LAG hash type.
In addition, have a field that indicate if the lag is in encap
mode or not.
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Downstream patches add another lag related file so it makes
sense to have all the lag files in a dedicated directory.
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
The uplink destination type should be used in rules to steer the
packet to the uplink when the device is in steering based LAG mode.
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Introduce new APIs to create and destroy flow matcher
for given format id.
Flow match definer object is used for defining the fields and
mask used for the hash calculation. User should mask the desired
fields like done in the match criteria.
This object is assigned to flow group of type hash. In this flow
group type, packets lookup is done based on the hash result.
This patch also adds the required bits to create such flow group.
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Add new port selection flow steering namespace. Flow steering rules in
this namespaceare are used to determine the physical port for egress
packets.
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Add bitmasks to ttc_params to indicate if rule is valid or not.
It will allow to create TTC table with support only in part of the
traffic types.
In later patches which introduce the steering based LAG port selection,
TTC will be created with only part of the rules according to the hash
type.
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Change the TCP common variable - "iscsi_ooo" to "ooo_opq".
This variable is common between all the TCP L5 protocols and not
specific to iSCSI.
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Shai Malin <smalin@marvell.com>
Link: https://lore.kernel.org/r/20211015124118.29041-2-smalin@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Optimize the ll2 TCP out-of-order likely flows:
- Optimize the non-error flows of the ll2 ooo data path.
- Optimize "QED_OOO_RIGHT_BUF" over "QED_OOO_LEFT_BUF".
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Shai Malin <smalin@marvell.com>
Link: https://lore.kernel.org/r/20211015124118.29041-1-smalin@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
A new warning in clang points out two places in this driver where
boolean expressions are being used with a bitwise OR instead of a
logical one:
drivers/net/ethernet/netronome/nfp/nfp_asm.c:199:20: error: use of bitwise '|' with boolean operands [-Werror,-Wbitwise-instead-of-logical]
reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
||
drivers/net/ethernet/netronome/nfp/nfp_asm.c:199:20: note: cast one or both operands to int to silence this warning
drivers/net/ethernet/netronome/nfp/nfp_asm.c:280:20: error: use of bitwise '|' with boolean operands [-Werror,-Wbitwise-instead-of-logical]
reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
||
drivers/net/ethernet/netronome/nfp/nfp_asm.c:280:20: note: cast one or both operands to int to silence this warning
2 errors generated.
The motivation for the warning is that logical operations short circuit
while bitwise operations do not. In this case, it does not seem like
short circuiting is harmful so implement the suggested fix of changing
to a logical operation to fix the warning.
Link: https://github.com/ClangBuiltLinux/linux/issues/1479
Reported-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20211018193101.2340261-1-nathan@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Use single state machine for driver initialization and for service
initialized driver. The init state machine implemented in init_task()
is merged into the watchdog_task(). The init_task() function is
removed.
Signed-off-by: Jakub Pawlak <jakub.pawlak@intel.com>
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
This commit adds a new state, __IAVF_INIT_FAILED to the state machine.
From now on initialization functions report errors not by returning an
error value, but by changing the state to indicate that something went
wrong.
Signed-off-by: Jakub Pawlak <jakub.pawlak@intel.com>
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Replace state changes of iavf state machine
with a method that also tracks the previous
state the machine was on.
This change is required for further work with
refactoring init and watchdog state machines.
Tracking of previous state would help us
recover iavf after failure has occurred.
Signed-off-by: Jakub Pawlak <jakub.pawlak@intel.com>
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
mlx5_tout_ms() returns a u64, we can't directly divide it.
This is not a problem here, @timeout which is the value
that actually matters here is already a ulong, so this
implies storing return value of mlx5_tout_ms() on a ulong
should be fine.
This fixes:
ERROR: modpost: "__udivdi3" [drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko] undefined!
Fixes: 32def4120e48 ("net/mlx5: Read timeout values from DTOR")
Link: https://lore.kernel.org/r/20211018172608.1069754-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Everything except the first 32 bits was lost when the pause flags were
added. This makes the 50000baseCR2 mode flag (bit 34) not appear.
I have tested this with a 10G card (SFN5122F-R7) by modifying it to
return a non-legacy link mode (10000baseCR).
Signed-off-by: Erik Ekman <erik@kryo.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
During the process of driver probing, the probe function should return < 0
for failure, otherwise, the kernel will treat value > 0 as success.
Signed-off-by: Zheyu Ma <zheyuma97@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Fix following coccicheck warning:
./drivers/net/ethernet/mscc/ocelot_vsc7514.c:946:1-33: WARNING: Function
for_each_available_child_of_node should have of_node_put() before goto.
Early exits from for_each_available_child_of_node should decrement the
node reference counter.
Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Fix following coccicheck warning:
./drivers/net/ethernet/microchip/sparx5/s4parx5_main.c:723:1-33: WARNING: Function
for_each_available_child_of_node should have of_node_put() before goto
Early exits from for_each_available_child_of_node should decrement the
node reference counter.
Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Building the VF and PF side of this driver differently, with one being
a loadable module and the other one built-in results in a link failure
for the common PTP driver:
ld.lld: error: undefined symbol: __this_module
>>> referenced by otx2_ptp.c
>>> net/ethernet/marvell/octeontx2/nic/otx2_ptp.o:(otx2_ptp_init) in archive drivers/built-in.a
>>> referenced by otx2_ptp.c
>>> net/ethernet/marvell/octeontx2/nic/otx2_ptp.o:(otx2_ptp_init) in archive drivers/built-in.a
Move the otx2_ptp.c code into a separate module that gets built for
both configurations, making it built-in if at least one of the other
two is built-in.
Fixes: 43510ef4ddad ("octeontx2-nicvf: Add PTP hardware clock support to NIX VF")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add basic support for UniPhier NX1 SoC. This includes a compatible string
and SoC-dependent data.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Up to now w5100_remove() returns zero unconditionally. Make it return
void instead which makes it easier to see in the callers that there is
no error to handle.
Also the return value of platform and spi remove callbacks is ignored
anyway.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Up to now ks8851_remove_common() returns zero unconditionally. Make it
return void instead which makes it easier to see in the callers that
there is no error to handle.
Also the return value of platform and spi remove callbacks is ignored
anyway.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The only factor differentiating per-CPU bstats data type (struct
gnet_stats_basic_cpu) from the packed non-per-CPU one (struct
gnet_stats_basic_packed) was a u64_stats sync point inside the former.
The two data types are now equivalent: earlier commits added a u64_stats
sync point to the latter.
Combine both data types into "struct gnet_stats_basic_sync". This
eliminates redundancy and simplifies the bstats read/write APIs.
Use u64_stats_t for bstats "packets" and "bytes" data types. On 64-bit
architectures, u64_stats sync points do not use sequence counter
protection.
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Read the address into an array on the stack, then call
eth_hw_addr_set(). ixgb_get_ee_mac_addr() is used with
a non-nevdev->dev_addr pointer so we can't deal with the problem
inside it.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
We'll want to make netdev->dev_addr const, remove the local
helper which is missing a const qualifier on the argument
and use ether_addr_to_u64().
Similar story to mlx4.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Pass a netdev into the helper instead of just the address,
read the address into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Copy the address into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Use a zero'ed array on the stack, then call eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Read the address into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Read the address into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Use an array on the stack, then call eth_hw_addr_set().
eth_hw_addr_set() is after error checking, this should
be fine, error propagates all the way to failing probe.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Read the address into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Break the address apart into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
macaddr[] is a module param, and int, so copy the address into
an array of u8 on the stack, then call eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit 406f42fa0d3c ("net-next: When a bond have a massive amount
of VLANs...") introduced a rbtree for faster Ethernet address look
up. To maintain netdev->dev_addr in this tree we need to make all
the writes to it got through appropriate helpers.
Read the address into an array on the stack, then call
eth_hw_addr_set().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2021-10-15
1) From Rongwei Liu:
Use system_image_guid and native_port_num when bonding.
Don't relay on PCIe ids anymore.
With some specific NIC, the physical devices may have PCIe IDs like
0001:01:00.0/1 and 0002:02:00.0/1. All of these devices should have
the same system_image_guid and device index can be queried from
native_port_num.
For matching sibling devices/port of the same HCA, compare the HCA
GUID reported on each device rather than just assuming PCIe ids have
similar attributes.
2) From Amir Tzin: Use HCA defined Timouts
Replace hard coded timeouts with values stored by firmware in default
timeouts register (DTOR). Timeouts are read during driver load. If DTOR
is not supported by firmware then fallback to hard coded defaults
instead.
3) From Shay Drory: Disable roce at HCA level
Disable RoCE in Firmware when devlink roce parameter is set to off.
4) A small set of trivial cleanups
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
With specific NICs, the PFs may have different PCIe ids like
0001:01:00.0/1 and 0002:02:00:00/1.
For PFs with the same system_image_guid, driver should consider
them under the same physical NIC and they are legal to bond together.
If firmware doesn't support system_image_guid, set it to zero and
fallback to use PCIe ids.
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Downstream patches.
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
When querying system_image_guid from firmware, we should check return
value first. The buffer content is valid only if query succeed.
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
As noted in the "Deprecated Interfaces, Language Features, Attributes,
and Conventions" documentation [1], size calculations (especially
multiplication) should not be performed in memory allocator (or similar)
function arguments due to the risk of them overflowing. This could lead
to values wrapping around and a smaller allocation being made than the
caller was expecting. Using those allocations could lead to linear
overflows of heap memory and other misbehaviors.
So, refactor the code a bit to use the purpose specific kcalloc()
function instead of the argument size * count in the kzalloc() function.
[1] https://www.kernel.org/doc/html/v5.14/process/deprecated.html#open-coded-arithmetic-in-allocator-arguments
Signed-off-by: Len Baker <len.baker@gmx.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
As multiple places EOPNOTSUPP and EINVAL is returned from driver
it becomes difficult to understand the reason only with error code.
With the netlink extack message exact reason will be known and will
aid in debugging.
Signed-off-by: Abhiram R N <abhiramrn@gmail.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
If CT fails to initialize it's rhashtables, it doesn't destroy
the ct nat global table.
Destroy the ct nat global table on ct init failure.
Fixes: d7cade513752 ("net/mlx5e: check return value of rhashtable_init")
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Currently, when a user disables roce via the devlink param, this change
isn't passed down to the device.
If device allows disabling RoCE at device level, make use of it. This
instructs the device to skip memory allocations related to RoCE
functionality which otherwise is done by the device.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Enable steering IPoIB packets via ethtool, the same way it is done today
for Ethernet packets.
Signed-off-by: Moosa Baransi <moosab@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Currently, SMFS mode doesn't support rx-loopback flows which causes bridge
egress rules to be rejected because without hint rules for both rx and tx
destinations are created by default. Provide explicit flow source hints for
compatibility with SMFS.
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Replace hard coded timeouts with values stored by firmware in default
timeouts register (DTOR). Timeouts are read during driver load. If DTOR
is not supported by firmware then fallback to hard coded defaults
instead.
Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Replace hard coded timeouts with values stored in firmware's init
segment. Timeouts are read from init segment during driver load. If init
segment timeouts are not supported then fallback to hard coded defaults
instead. Also move pre initialization timeouts which cannot be read from
firmware to the new mechanism.
Signed-off-by: Amir Tzin <amirtz@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Go through the code base and use ice_for_each_* macros. While at it,
introduce ice_for_each_xdp_txq() macro that can be used for looping over
xdp_rings array.
Commit is not introducing any new functionality.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Under rare circumstances there might be a situation where a requirement
of having XDP Tx queue per CPU could not be fulfilled and some of the Tx
resources have to be shared between CPUs. This yields a need for placing
accesses to xdp_ring inside a critical section protected by spinlock.
These accesses happen to be in the hot path, so let's introduce the
static branch that will be triggered from the control plane when driver
could not provide Tx queue dedicated for XDP on each CPU.
Currently, the design that has been picked is to allow any number of XDP
Tx queues that is at least half of a count of CPUs that platform has.
For lower number driver will bail out with a response to user that there
were not enough Tx resources that would allow configuring XDP. The
sharing of rings is signalled via static branch enablement which in turn
indicates that lock for xdp_ring accesses needs to be taken in hot path.
Approach based on static branch has no impact on performance of a
non-fallback path. One thing that is needed to be mentioned is a fact
that the static branch will act as a global driver switch, meaning that
if one PF got out of Tx resources, then other PFs that ice driver is
servicing will suffer. However, given the fact that HW that ice driver
is handling has 1024 Tx queues per each PF, this is currently an
unlikely scenario.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Optimize Tx descriptor cleaning for XDP. Current approach doesn't
really scale and chokes when multiple flows are handled.
Introduce two ring fields, @next_dd and @next_rs that will keep track of
descriptor that should be looked at when the need for cleaning arise and
the descriptor that should have the RS bit set, respectively.
Note that at this point the threshold is a constant (32), but it is
something that we could make configurable.
First thing is to get away from setting RS bit on each descriptor. Let's
do this only once NTU is higher than the currently @next_rs value. In
such case, grab the tx_desc[next_rs], set the RS bit in descriptor and
advance the @next_rs by a 32.
Second thing is to clean the Tx ring only when there are less than 32
free entries. For that case, look up the tx_desc[next_dd] for a DD bit.
This bit is written back by HW to let the driver know that xmit was
successful. It will happen only for those descriptors that had RS bit
set. Clean only 32 descriptors and advance the DD bit.
Actual cleaning routine is moved from ice_napi_poll() down to the
ice_xmit_xdp_ring(). It is safe to do so as XDP ring will not get any
SKBs in there that would rely on interrupts for the cleaning. Nice side
effect is that for rare case of Tx fallback path (that next patch is
going to introduce) we don't have to trigger the SW irq to clean the
ring.
With those two concepts, ring is kept at being almost full, but it is
guaranteed that driver will be able to produce Tx descriptors.
This approach seems to work out well even though the Tx descriptors are
produced in one-by-one manner. Test was conducted with the ice HW
bombarded with packets from HW generator, configured to generate 30
flows.
Xdp2 sample yields the following results:
<snip>
proto 17: 79973066 pkt/s
proto 17: 80018911 pkt/s
proto 17: 80004654 pkt/s
proto 17: 79992395 pkt/s
proto 17: 79975162 pkt/s
proto 17: 79955054 pkt/s
proto 17: 79869168 pkt/s
proto 17: 79823947 pkt/s
proto 17: 79636971 pkt/s
</snip>
As that sample reports the Rx'ed frames, let's look at sar output.
It says that what we Rx'ed we do actually Tx, no noticeable drops.
Average: IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
Average: ens4f1 79842324.00 79842310.40 4678261.17 4678260.38 0.00 0.00 0.00 38.32
with tx_busy staying calm.
When compared to a state before:
Average: IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
Average: ens4f1 90919711.60 42233822.60 5327326.85 2474638.04 0.00 0.00 0.00 43.64
it can be observed that the amount of txpck/s is almost doubled, meaning
that the performance is improved by around 90%. All of this due to the
drops in the driver, previously the tx_busy stat was bumped at a 7mpps
rate.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
