In failsafe device start can be called for ports/devices that
had been plugged out.
The mlx4 PMD detects device removal by listening to the device RMV
events, when the mlx4 port is being stopped, the PMD no longer
listens to these events causing the PMD to stop detecting device
removals.
This patch fixes this issue by moving installation of the interrupt
handler to device configuration, and toggle only the Rx-queue
interrupts on start/stop.
Fixes: a6e8b01c3c26 ("net/mlx4: compact interrupt functions")
Cc: stable@dpdk.org
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
Create a rte_ethdev_driver.h file and move PMD specific APIs here.
Drivers updated to include this new header file.
There is no update in header content and since ethdev.h included by
ethdev_driver.h, nothing changed from driver point of view, only
logically grouping of APIs. From applications point of view they can't
access to driver specific APIs anymore and they shouldn't.
More PMD specific data structures still remain in ethdev.h because of
inline functions in header use them. Those will be handled separately.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Inner VXLAN RSS was supported and performed by default prior to the entire
mlx4 refactoring that occurred in DPDK 17.11, however so far the new Verbs
RSS API did not provide means to enable it. This will be addressed in
Linux 4.15 and in RDMA core.
Thanks to RSS capabilities, the PMD can now probe for its support and
enable it again by default.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Until now, UDP RSS support could not be relied on due to a problem in the
Linux kernel implementation and mlx4 RSS capabilities were not reported at
all, hence the PMD had to make assumptions.
Since both issues will be addressed simultaneously in Linux 4.15 (related
patches already upstream) and likely backported afterward, UDP RSS support
can be enabled by probing RSS capabilities.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
A couple of structure fields are not Doxygen-friendly.
Fixes: 5db1d364086e ("net/mlx4: restore Tx checksum offloads")
Cc: stable@dpdk.org
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
This patch enhances the Rx packet type offload to also report the L4
protocol information in the hw ptype filled by the PMD for each received
packet.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Memory regions assigned to hardware and used during Tx/Rx are mapped to
mbuf pools. Each Rx queue creates its own MR based on the mempool
provided during queue setup, while each Tx queue looks up and registers
MRs for all existing mbuf pools instead.
Since most applications use few large mbuf pools (usually only a single
one per NUMA node) common to all Tx/Rx queues, the above approach wastes
hardware resources due to redundant MRs. This negatively affects
performance, particularly with large numbers of queues.
This patch therefore makes the entire MR registration common to all
queues using a reference count. A spinlock is added to protect against
asynchronous registration that may occur from the Tx side where new
mempools are discovered based on mbuf data.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Associate memory region to mempool (on data path) in a short function.
Handle the less common case of adding a new memory region to mempool
in a separate function.
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This patch adds hardware offloading support for IPv4, UDP and TCP checksum
calculation, including inner/outer checksums on supported tunnel types.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This patch dissociates single-queue indirection tables and hash QP objects
from Rx queue structures to relinquish their control to users through the
RSS flow rule action, while simultaneously allowing multiple queues to be
associated with RSS contexts.
Flow rules share identical RSS contexts (hashed fields, hash key, target
queues) to save on memory and other resources. The trade-off is some added
complexity due to reference counters management on RSS contexts.
The QUEUE action is re-implemented on top of an automatically-generated
single-queue RSS context.
The following hardware limitations apply to RSS contexts:
- The number of queues in a group must be a power of two.
- Queue indices must be consecutive, for instance the [0 1 2 3] set is
allowed, however [3 2 1 0], [0 2 1 3] and [0 0 1 1 2 3 3 3] are not.
- The first queue of a group must be aligned to a multiple of the context
size, e.g. if queues [0 1 2 3 4] are defined globally, allowed group
combinations are [0 1] and [2 3]; groups [1 2] and [3 4] are not
supported.
- RSS hash key, while configurable per context, must be exactly 40 bytes
long.
- The only supported hash algorithm is Toeplitz.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Work queues (WQs) are lower-level than standard queue pairs (QPs). They are
dedicated to one traffic direction and have to be used in conjunction with
indirection tables and special "hash" QPs to get the same level of
functionality.
These extra objects however are the building blocks for RSS support brought
by subsequent commits, as a single "hash" QP can manage several WQs through
an indirection table according to a hash algorithm and other parameters.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Implement promiscuous and all multicast through internal flow rules
automatically generated according to the configured mode.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
This commit brings back VLAN filter configuration support without any
artificial limitation on the number of simultaneous VLANs that can be
configured (previously 127).
Also thanks to the fact it does not rely on fixed per-queue arrays for
potential Verbs flow handle storage anymore, this version wastes a lot less
memory (previously 128 * 127 * pointer size, i.e. 130 kiB per Rx queue,
only one of which actually had any use for this room: the RSS parent
queue).
The number of internal flow rules generated still depends on the number of
configured MAC addresses times that of configured VLAN filters though.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
This commit brings back support for configuring up to 128 MAC addresses on
a port through internal flow rules automatically generated on demand.
Unlike its previous incarnation, the necessary extra flow rule for
broadcast traffic does not consume an entry from the MAC array anymore.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
When not in isolated mode, a flow rule is automatically configured by the
PMD to receive traffic addressed to the MAC address of the device. This
somewhat duplicates flow API functionality.
Remove legacy support for internal flow rules to instead handle them
through the flow API implementation.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Verbs QP and CQ resources for drop flow rules do not need to be permanently
allocated, only when at least one rule needs them.
Besides, struct rte_flow_drop is outside the mlx4 PMD name space and should
never have been defined there. struct rte_flow is currently the only
exception to this rule.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Add missing comments and fix those not Doxygen-friendly.
Since the private structure definition is modified, use this opportunity to
add one remaining missing include required by one of its fields
(sys/queue.h for LIST_HEAD()).
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
The stats_get dev op API doesn't include return value, so PMD cannot
return an error in case of failure at stats getting process time.
Since PCI devices can be removed and there is a time between the
physical removal to the RMV interrupt, the user may get invalid stats
without any indication.
This patch changes the stats_get API return value to be int instead of
void.
All the net PMDs stats_get dev ops are adjusted by this patch.
Signed-off-by: Matan Azrad <matan@mellanox.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Allocation and management of Tx/Rx queue arrays is done by wrappers at the
ethdev level. The resulting information is copied to the private structure
while configuring the device, where it is managed separately by the PMD.
This is redundant and consumes space in the private structure.
Relying more on ethdev also means there is no need to protect the PMD
against burst function calls while closing the device anymore.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Add missing includes and sort them, then update/remove comments around them
for consistency.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Private functions are now prefixed with "mlx4_" to prevent them from
conflicting with their mlx5 PMD counterparts at link time.
No impact on functionality.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This commit groups all data plane functions (Rx/Tx) into a separate file
and adjusts header files accordingly.
Private functions are now prefixed with "mlx4_" to prevent them from
conflicting with their mlx5 PMD counterparts at link time.
No impact on functionality.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Except for a minor documentation update on internal structure definitions
to make them more Doxygen-friendly, there is no impact on functionality.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Private functions are now prefixed with "mlx4_" to prevent them from
conflicting with their mlx5 PMD counterparts at link time.
No impact on functionality.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Link status (LSC) and removal (RMV) interrupts share a common handler and
are toggled simultaneously from common install/uninstall functions.
Four additional wrapper functions (two for each interrupt type) are
currently necessary because the PMD maintains an internal configuration
state for interrupts (priv->intr_conf).
This complexity can be avoided entirely since the PMD does not disable
interrupts configuration parameters in case of error anymore.
With this commit, only two functions are necessary to toggle interrupts
(including Rx) during start/stop cycles.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
File descriptors used for interrupts processing must be made non-blocking.
Doing so as soon as they are opened instead of waiting until they are
needed is more efficient as it avoids performing redundant system calls and
run through their associated error-handling code later on.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The reason one interrupt handle is currently used for RMV/LSC events and
another one for Rx traffic is because these come from distinct file
descriptors.
This can be simplified however as Rx interrupt file descriptors are stored
elsewhere and are registered separately.
Modifying the interrupt handle type to RTE_INTR_HANDLE_UNKNOWN has never
been necessary as disabling interrupts is actually done by unregistering
the associated callback (RMV/LSC) or emptying the EFD array (Rx). Instead,
make clear that the base handle file descriptor is invalid by setting it to
-1 when disabled.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The new definitions also rely on the existing DPDK logging subsystem
instead of using fprintf() directly.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Concurrent use of various control path functions (e.g. configuring a queue
and destroying it simultaneously) may lead to undefined behavior.
PMD are not supposed to protect themselves from misbehaving applications,
and mlx4 is one of the few with internal locks on most control path
operations. This adds unnecessary complexity.
Leave this role to wrapper functions in ethdev.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Thanks to the fact the PMD temporarily uses a slower interface for Rx,
removing the WR ID hack to instead store mbuf pointers directly makes the
code simpler at no extra cost.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This reverts commit acac55f164128fc76da8d93cae1e8c1e560e99f6.
"Fast Verbs" is a nonstandard experimental interface that must be reverted
for compatibility reasons. Its replacement is slower but temporary,
performance will be restored by a subsequent commit through an enhanced
data path implementation. This one focuses on maintaining basic
functionality in the meantime.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This reverts commit 9980f81dc2623291b89cf1c281a6a9f116fd2394.
"Fast Verbs" is a nonstandard experimental interface that must be reverted
for compatibility reasons. Its replacement is slower but temporary,
performance will be restored by a subsequent commit through an enhanced
data path implementation. This one focuses on maintaining basic
functionality in the meantime.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This reverts commit 3e49c148b715c3c0a12c1200295bb9b312f7028e.
Resource domains are not part of the standard Verbs interface. The
performance improvement they bring will be restored later through a
different data path implementation.
This commit makes the PMD not rely on the non-standard QP allocation
interface.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The Verbs API used to implement inline receive is deprecated.
Support will be added back after refactoring the PMD.
Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The Verbs API used to implement Tx and Rx burst functions is deprecated.
Drop scatter/gather support to ease refactoring while maintaining basic
single-segment Rx/Tx functionality in the meantime.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The Verbs API used to implement Tx and Rx checksum offloads is deprecated.
Support for these will be added back after refactoring the PMD.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The Verbs RSS API used in this PMD is now obsolete. It is superseded by an
enhanced API with fewer constraints already used in the mlx5 PMD.
Drop RSS support in preparation for a major refactoring. The ability to
configure several Rx queues is retained, these can be targeted directly by
creating specific flow rules.
There is no need for "ignored" Rx queues anymore since their number is no
longer limited to powers of two.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This reverts commit ff00a0dc5600dbb0a29e4aa7fa4b078f98c7a360.
Support for several RSS parent queues was necessary to implement the RSS
flow rule action, dropped in a prior commit.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This reverts commit d7769c7c08cc08a9d1bc4e40b95524d9697707d9.
Existing RSS features rely on experimental Verbs provided by Mellanox OFED.
In order to replace this dependency with standard distribution packages,
RSS support must be temporarily removed to be re-implemented using a
different API.
Removing support for the RSS flow rule action is the first step toward this
goal.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Configuring several Rx queues enables RSS, which causes an additional
special parent queue to be created to manage them.
MAC flows are associated with the queue supposed to receive packets; either
the parent one in case of RSS or the single orphan otherwise.
For historical reasons the current implementation supports another scenario
with multiple orphans, in which case MAC flows are configured on all of
them. This is harmless but useless since it cannot happen.
Removing this feature allows dissociating the remaining MAC flow from Rx
queues and store it inside the private structure where it belongs.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Only the default port MAC address remains and is not configurable.
This is done in preparation for a major refactoring.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This option both sets the maximum number of segments for Rx/Tx packets and
whether scattered mode is supported at all. This commit removes the latter
as well as configuration file exposure since the most appropriate value
should be decided at run-time.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
