diff options
| author | Tariq Toukan <tariqt@nvidia.com> | 2021-03-10 23:09:15 -0800 |
|---|---|---|
| committer | Saeed Mahameed <saeedm@nvidia.com> | 2021-03-12 13:07:46 -0800 |
| commit | 26bf30902c10473ba38f220d3401a61c56d8db3b (patch) | |
| tree | 4a7d3e53dc4b5bb96aec8670e21011b9b0b700e0 /include | |
| parent | c3e666f1ada9cbfbe5465f122f9a2d63ddfd25ed (diff) | |
| download | linux-26bf30902c10473ba38f220d3401a61c56d8db3b.tar.bz2 | |
net/mlx5: Use order-0 allocations for EQs
Currently we are allocating high-order page for EQs. In case of
fragmented system, VF hot remove/add in VMs for example, there isn't
enough contiguous memory for EQs allocation, which results in crashing
of the VM.
Therefore, use order-0 fragments for the EQ allocations instead.
Performance tests:
ConnectX-5 100Gbps, CPU: Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz
Performance tests show no sensible degradation.
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/mlx5/driver.h | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8fe51b4a781e..5c0422930b01 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -873,6 +873,11 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } +static inline u32 wq_get_byte_sz(u8 log_sz, u8 log_stride) +{ + return ((u32)1 << log_sz) << log_stride; +} + static inline void mlx5_init_fbc_offset(struct mlx5_buf_list *frags, u8 log_stride, u8 log_sz, u16 strides_offset, |