diff options
| author | Moshe Shemesh <moshe@nvidia.com> | 2025-06-10 18:15:06 +0300 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2025-06-27 11:07:23 +0100 |
| commit | 3c20dd215825f32508967439f06d7b474e28ef88 (patch) | |
| tree | 4ced9410a4d973c39dd338ded6e0e29885c4e920 | |
| parent | 649c6299462a3cbdad93f654218c95c5832a58db (diff) | |
net/mlx5: Ensure fw pages are always allocated on same NUMA
[ Upstream commit f37258133c1e95e61db532e14067e28b4881bf24 ]
When firmware asks the driver to allocate more pages, using event of
give_pages, the driver should always allocate it from same NUMA, the
original device NUMA. Current code uses dev_to_node() which can result
in different NUMA as it is changed by other driver flows, such as
mlx5_dma_zalloc_coherent_node(). Instead, use saved numa node for
allocating firmware pages.
Fixes: 311c7c71c9bb ("net/mlx5e: Allocate DMA coherent memory on reader NUMA node")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-2-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 95dc67fb3001..99909c74a214 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -285,7 +285,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function) static int alloc_system_page(struct mlx5_core_dev *dev, u32 function) { struct device *device = mlx5_core_dma_dev(dev); - int nid = dev_to_node(device); + int nid = dev->priv.numa_node; struct page *page; u64 zero_addr = 1; u64 addr; |