* [PATCH net-next 0/2] net/mlx5: Declare no DMA segment boundary restriction
@ 2026-11-20 8:18 Tariq Toukan
2026-11-20 8:18 ` [PATCH net-next 1/2] " Tariq Toukan
2026-11-20 8:18 ` [PATCH net-next 2/2] net/mlx5: Declare no DMA segment boundary for data direct device Tariq Toukan
0 siblings, 2 replies; 3+ messages in thread
From: Tariq Toukan @ 2026-11-20 8:18 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
netdev, Paolo Abeni
Cc: Gal Pressman, Leon Romanovsky, linux-rdma, Mark Bloch,
Moshe Shemesh, Saeed Mahameed, Tariq Toukan, Yishai Hadas
Hi,
This series by Yishai declares that the mlx5 devices have no DMA segment
boundary restriction.
Regards,
Tariq
Yishai Hadas (2):
net/mlx5: Declare no DMA segment boundary restriction
net/mlx5: Declare no DMA segment boundary for data direct device
drivers/net/ethernet/mellanox/mlx5/core/data_direct.c | 1 +
drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
2 files changed, 2 insertions(+)
base-commit: 2208ab00f4f213ade91ab775e7f8c4dacdcc856e
--
2.44.0
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH net-next 1/2] net/mlx5: Declare no DMA segment boundary restriction
2026-11-20 8:18 [PATCH net-next 0/2] net/mlx5: Declare no DMA segment boundary restriction Tariq Toukan
@ 2026-11-20 8:18 ` Tariq Toukan
2026-11-20 8:18 ` [PATCH net-next 2/2] net/mlx5: Declare no DMA segment boundary for data direct device Tariq Toukan
1 sibling, 0 replies; 3+ messages in thread
From: Tariq Toukan @ 2026-11-20 8:18 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
netdev, Paolo Abeni
Cc: Gal Pressman, Leon Romanovsky, linux-rdma, Mark Bloch,
Moshe Shemesh, Saeed Mahameed, Tariq Toukan, Yishai Hadas
From: Yishai Hadas <yishaih@nvidia.com>
The PCI core initialises every PCI device with a DMA segment boundary
mask of 0xffffffff in pci_device_add(), which forbids any segment from
crossing a 4GB-aligned address regardless of its length. mlx5_core
raises the default maximum segment size to 2GB but never overrides the
boundary, although the device has no such limitation.
Consumers such as ib_umem_get() coalesce physically contiguous pages up
to the maximum segment size without consulting the boundary mask.
Registering a large MR can therefore produce a segment that crosses a
4GB-aligned address, which the DMA API debug checker reports:
DMA-API: mlx5_core 0000:08:00.0: mapping sg segment across boundary
[start=0x00000002ffe27000] [end=0x000000030020efff]
[boundary=0x00000000ffffffff]
The segment is about 4MB long, well below the 2GB maximum, but it spans
the 12GB (0x300000000) boundary: the upper halves of start and end are
0x2 and 0x3.
Set the segment boundary mask to ULONG_MAX so the DMA constraints
declared for the device match what the hardware supports.
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 079e91c98041..b3f4d319d29e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -190,6 +190,7 @@ static int set_dma_caps(struct pci_dev *pdev)
}
dma_set_max_seg_size(&pdev->dev, 2u * 1024 * 1024 * 1024);
+ dma_set_seg_boundary(&pdev->dev, ULONG_MAX);
return err;
}
--
2.44.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
* [PATCH net-next 2/2] net/mlx5: Declare no DMA segment boundary for data direct device
2026-11-20 8:18 [PATCH net-next 0/2] net/mlx5: Declare no DMA segment boundary restriction Tariq Toukan
2026-11-20 8:18 ` [PATCH net-next 1/2] " Tariq Toukan
@ 2026-11-20 8:18 ` Tariq Toukan
1 sibling, 0 replies; 3+ messages in thread
From: Tariq Toukan @ 2026-11-20 8:18 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
netdev, Paolo Abeni
Cc: Gal Pressman, Leon Romanovsky, linux-rdma, Mark Bloch,
Moshe Shemesh, Saeed Mahameed, Tariq Toukan, Yishai Hadas
From: Yishai Hadas <yishaih@nvidia.com>
The PCI core initialises every PCI device with a DMA segment boundary
mask of 0xffffffff in pci_device_add(), which forbids any segment from
crossing a 4GB-aligned address regardless of its length. The data direct
device raises the default maximum segment size to 2GB but keeps that
boundary, although it has no such limitation.
Declare that explicitly, in line with mlx5_core, to avoid a mismatch
between the declared constraints and the hardware capabilities.
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/data_direct.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c b/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c
index 5afb11a2a9f0..73eef8bbc327 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/data_direct.c
@@ -103,6 +103,7 @@ static int mlx5_data_direct_set_dma_caps(struct pci_dev *pdev)
}
dma_set_max_seg_size(&pdev->dev, SZ_2G);
+ dma_set_seg_boundary(&pdev->dev, ULONG_MAX);
return 0;
}
--
2.44.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-11-20 8:19 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-20 8:18 [PATCH net-next 0/2] net/mlx5: Declare no DMA segment boundary restriction Tariq Toukan
2026-11-20 8:18 ` [PATCH net-next 1/2] " Tariq Toukan
2026-11-20 8:18 ` [PATCH net-next 2/2] net/mlx5: Declare no DMA segment boundary for data direct device Tariq Toukan
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox