| Age | Commit message (Collapse) | Author |
|---|
|
This reverts commit 95c337cce0e11d06a715da73e6796ade9216637f.
The revert is required due to the suspicion it cause some tests
fail and will be moved to further investigation.
Fixes: 95c337cce0e1 ("net/mlx5: DR, Supporting inline WQE when possible")
Signed-off-by: Itamar Gozlan <igozlan@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20231114215846.5902-2-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In WQE (Work Queue Entry), the two types of data segments memories are
pointers and inline data, where inline data is passed directly as
part of the WQE.
For software steering, the maximal inline size should be less than
2*MLX5_SEND_WQE_BB, i.e., the potential data must fit with the required
inline WQE headers.
Two consecutive blocks (MLX5_SEND_WQE_BB) are not guaranteed to reside
on the same memory page. Hence, writes to MLX5_SEND_WQE_BB should be
done separately, i.e., each MLX5_SEND_WQE_BB should be obtained using
the mlx5_wq_cyc_get_wqe macro.
Signed-off-by: Itamar Gozlan <igozlan@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
This commit enables the dynamic allocation of EQs at runtime, allowing
for more flexibility in managing completion EQs and reducing the memory
overhead of driver load. Whenever a CQ is created for a given vector
index, the driver will lookup to see if there is an already mapped
completion EQ for that vector, if so, utilize it. Otherwise, allocate a
new EQ on demand and then utilize it for the CQ completion events.
Add a protection lock to the EQ table to protect from concurrent EQ
creation attempts.
While at it, replace mlx5_vector2irqn()/mlx5_vector2eqn() with
mlx5_comp_eqn_get() and mlx5_comp_irqn_get() which will allocate an
EQ on demand if no EQ is found for the given vector.
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
To accurately represent its purpose, rename the function that retrieves
the value of maximum vectors from mlx5_comp_vectors_count() to
mlx5_comp_vectors_max().
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
When allocating a QP we allocate an RQ and an SQ, the RQ is stored first
in memory and followed by the SQ.
This allocation is not physically continiuos - it may span across different
physical pages. SW Steering code always writes in pairs: 1BB write + 1BB read,
or 2 continuous BBs of GTA WQE.
This lead to an issue where RQ allocation was 4x16 which is equal to 1 WQE BB,
causing 1 BB offset in the page and splitting the GTA WQE between different
physical pages.
The solution was to create the RQ with a even number of BBs and to have the
RQ aligned to a page.
Signed-off-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Instead of using the write buffer for reading we will use a dedicated
buffer only for reading ICM memory.
Due to the new support for args, we can have a case with pending_wc
being odd number, and with reading into the same write buffer, it is
possible to overwrite next write on the same slot.
For example:
pending_wc is 17 so the buffer for write is:
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
and we have requests as follows:
r wr wr wr wr wr wr wr wr
Now, the first read will be written into the last write because we use
the same buffer for read and write, before it was written to the HW and
we will have a wrong data in the ICM area.
Signed-off-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
The accelerated modify header arguments are written in the HW area
with special WQE and specific data format.
New function was added to support writing of new argument type.
Note that GTA WQE is larger than READ and WRITE, so the queue
management logic was updated to support this.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Starting with ConnectX-6 Dx, we use new design of modify_header FW object.
The current modify_header object allows for having only limited number
of FW objects, so the new design of pattern and argument allows pattern
reuse, saving memory, and having a large number of modify_header objects.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
The send engine should be ready to handle more opcodes
in addition to RDMA_WRITE/RDMA_READ.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Return value from mlx5dr_send_postsend_action() directly instead of taking
this in another redundant variable.
Signed-off-by: zhang songyi <zhang.songyi@zte.com.cn>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Instead of allocating/freeing send info objects dynamically, manage them
in pool. The number of send info objects doesn't depend on rules, so after
pre-populating the pool with an initial batch of send info objects, the
pool is not expected to grow.
This way we save alloc/free during writing STEs to ICM, which can
sometimes take up to 40msec.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Calling fast teardown as part of the normal unloading caused
a problem with SW steering - SW steering still needs to clear
its tables, write to ICM and poll for completions.
When teardown has been done, SW steering keeps polling the CQ
forever, because nobody flushes it.
This patch fixes the issue by checking the device state in
cases where no CQE was returned.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
It can be calculated via function mlx5dr_ste_get_hw_ste().
Very simple and lightweight, no need to use a dedicated member.
Reduce 8 bytes from struct mlx5dr_ste and its size is 48 bytes now.
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Shun Hao <shunh@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Remove chunk_size in struct mlx5dr_icm_chunk and use
chunk->size instead.
Remove ste_arr/hw_ste_arr/miss_list since they can be accessed
from htbl->chunk pointer, no need to keep a copy.
This commit reduces 28 bytes from struct mlx5dr_ste_htbl and its
size is 32 bytes now.
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Shun Hao <shunh@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Target to reduce the memory consumption in large scale of flow rules.
They can be calculated quickly from buddy memory pool.
1. num_of_entries calls dr_icm_pool_get_chunk_num_of_entries().
2. byte_size calls dr_icm_pool_get_chunk_byte_size().
Use chunk size in dr_icm_chunk to speed up and the one in dr_ste_htbl
will be removed in the upcoming commit.
This commit reduce 8 bytes from struct mlx5_dr_icm_chunk and its
current size is 56 bytes.
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Shun Hao <shunh@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Reduce memory footprint by removing mr_addr and rkey from
mlx5_dr_icm_chunk.
1. mr_addr is calculated by mlx5dr_icm_pool_get_chunk_mr_addr()
2. rkey is calculated by mlx5dr_icm_pool_get_chunk_rkey()
The two new functions are very lightweight and straightforward.
Reduce 8 bytes from struct mlx5_dr_icm_chunk, its current size is
72 bytes.
Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Shun Hao <shunh@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
In mlx5_core and vdpa there is no use of mlx5_core_mkey members except
for the key itself.
As preparation for moving mlx5_core_mkey to mlx5_ib, the occurrences of
struct mlx5_core_mkey in all modules except for mlx5_ib are replaced by
a u32 key.
Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
|
|
In the event of SW steering QP entering error state, SW steering
cannot insert more rules, and will silently ignore the insertion
after issuing a warning.
Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Under high stress, SW steering might get stuck on polling for completion
that never comes.
For such cases QP needs to have protocol retransmission mechanism enabled.
Currently the retransmission timeout is defined as 0 (unlimited). Fix this
by defining a real timeout.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Conflicts:
drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
9e26680733d5 ("bnxt_en: Update firmware call to retrieve TX PTP timestamp")
9e518f25802c ("bnxt_en: 1PPS functions to configure TSIO pins")
099fdeda659d ("bnxt_en: Event handler for PPS events")
kernel/bpf/helpers.c
include/linux/bpf-cgroup.h
a2baf4e8bb0f ("bpf: Fix potentially incorrect results with bpf_get_local_storage()")
c7603cfa04e7 ("bpf: Add ambient BPF runtime context stored in current")
drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
5957cc557dc5 ("net/mlx5: Set all field of mlx5_irq before inserting it to the xarray")
2d0b41a37679 ("net/mlx5: Refcount mlx5_irq with integer")
MAINTAINERS
7b637cd52f02 ("MAINTAINERS: fix Microchip CAN BUS Analyzer Tool entry typo")
7d901a1e878a ("net: phy: add Maxlinear GPY115/21x/24x driver")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The CQ destroy is performed based on the IRQ number that is stored in
cq->irqn. That number wasn't set explicitly during CQ creation and as
expected some of the API users of mlx5_core_create_cq() forgot to update
it.
This caused to wrong synchronization call of the wrong IRQ with a number
0 instead of the real one.
As a fix, set the IRQ number directly in the mlx5_core_create_cq() and
update all users accordingly.
Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Fixes: ef1659ade359 ("IB/mlx5: Add DEVX support for CQ events")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
is_apu_thread_cq() used to detect CQs which are attached to APU
threads. This was extended to support other elements as well,
so the function was renamed to is_apu_cq().
c_eqn_or_apu_element was extended from 8 bits to 32 bits, which wan't
reflected when the APU support was first introduced.
Acked-by: Michael S. Tsirkin <mst@redhat.com> # vdpa
Signed-off-by: Tal Gilboa <talgi@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
|
|
When using SW steering, rule insertion rate depends on the RDMA RC QP
performance used for writing to the ICM. During stress this QP is competing
on the HW resources with all the other QPs that are used to send data.
To protect SW steering QP's performance in such cases, we set this QP to
use isolated VL. The VL number is reserved by FW and is not exposed to the
driver.
Support for this QP on isolated VL exists only when both force-loopback and
isolate_vl_tc capabilities are set.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
When supported by the device, SW steering RoCE RC QP that is used to
write/read to/from ICM will be created with force-loopback attribute.
Such QP doesn't require GID index upon creation.
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
QP doorbell size is 16 bits.
Fixing sw steering's QP doorbel bitmask, which had 20 bits.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Rename the argument to better reflect that the meaning is
not number of records, but wheather or not we should
ring the dorbell.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
The cmd size is 8K so use kvzalloc().
Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
mlx5dr_action is a generally used data structure, and there is an
union for different types of actions in it. The size of mlx5dr_action
is about 72 bytes, but for those actions with fewer fields, most of
the allocated memory is wasted.
Remove this union, and mlx5dr_action becomes a generic action header.
Then actions are dynamically allocated with needed memory, the data
for each action is stored right after the header.
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
QPs which don't care from timestamp mode, should set the ts_format
to default, otherwise the QP creation could be failed if the timestamp
mode is not supported.
Fixes: 2fe8d4b87802 ("RDMA/mlx5: Fail QP creation if the device can not support the CQE TS")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
STEv0 format and STEv1 HW format are different, each has a
different order:
STEv0: CTRL 32B, TAG 16B, BITMASK 16B
STEv1: CTRL 32B, BITMASK 16B, TAG 16B
To make this transparent to upper layers we introduce a
new ste_ctx function to format the STE prior to writing it.
Signed-off-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Use the PCI device directly for dma accesses as non PCI device unlikely
support IOMMU and dma mappings.
Introduce and use helper routine to access DMA device.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Validity check is done by reading the next lu_type from the STE,
this check can be replaced by checking the refcount.
This will make the check independent on internal STE structure.
Signed-off-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
|
|
Variable "in" in dr_create_rc_qp() is allocated with kvzalloc() and
should be freed with kvfree().
Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Cc: stable@vger.kernel.org
Signed-off-by: Denis Efremov <efremov@linux.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Adding this lock will allow writing steering entries without
locking the dr_domain and allow parallel insertion.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Conflicts were all overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In polling mode, set arm_db member to a value that will avoid CQ
event recovery by the HW.
Otherwise we might get event without completion function.
In addition,empty completion function to was added to protect from
unexpected events.
Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
The FPGA, SW steering and IPoIB need to have only QPN from the
mlx5_core_qp struct, so reduce memory footprint by storing QPN
directly.
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
Remove dependency on qp.c from SW steering by open
coding modify QP interface.
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
The QP and CQ events functions do nothing except printing some debug
messages. There is nothing to do with this knowledge and such events,
so remove them.
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
FPGA, IPoIB and SW steering don't need anything from the
mlx5_core_create_qp() and mlx5_core_destroy_qp() except calls
to mlx5_cmd_exec().
Let's open-code it, so we will be able to move qp.c to mlx5_ib.
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
|
|
Overlapping header include additions in macsec.c
A bug fix in 'net' overlapping with the removal of 'version'
string in ena_netdev.c
Overlapping test additions in selftests Makefile
Overlapping PCI ID table adjustments in iwlwifi driver.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Fix the send info write length to be (actions x action) size in bytes.
Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Hamdan Igbaria <hamdani@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Few print messages are in debug level where they should be in error, and
few messages are missing.
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Use raw_smp_processor_id instead of smp_processor_id() otherwise we will
get the following trace in debug-kernel:
BUG: using smp_processor_id() in preemptible [00000000] code: devlink
caller is dr_create_cq.constprop.2+0x31d/0x970 [mlx5_core]
Call Trace:
dump_stack+0x9a/0xf0
debug_smp_processor_id+0x1f3/0x200
dr_create_cq.constprop.2+0x31d/0x970
genl_family_rcv_msg+0x5fd/0x1170
genl_rcv_msg+0xb8/0x160
netlink_rcv_skb+0x11e/0x340
Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
When creating a CQ, the CPU id is used for the vector value.
This would fail in-case the CPU id was higher than the maximum
vector value.
Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
The memory return by kzalloc() has already be set to zero, so
remove useless memset(0).
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
|
Inserting or deleting a rule is done by RDMA read/write operation to SW
ICM device memory. This file provides the support for executing these
operations. It includes allocating the needed resources and providing an
API for writing steering entries to the memory.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
|
