From: Leon Romanovsky <leonro@nvidia.com>

The eRDMA device interface requires explicit byte ordering, but several
DMA-visible values that should be little-endian remain native-endian.
Command request payloads are copied verbatim, data-path SQE headers are
written without cpu_to_le64(), and kernel doorbell records are assigned
plain u64 values. The command completion path also reads a little-endian
SQE header without conversion.

These paths are byte-swapped on big-endian kernels and can break command
processing during probe. Since complete big-endian support requires
converting every device-visible structure, depend on !CPU_BIG_ENDIAN.

Fixes: ca7fd6cff3b8 ("RDMA/erdma: Add driver to kernel build environment")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
RDMA/erdma: restrict the driver to little-endian systems
---
 drivers/infiniband/hw/erdma/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/erdma/Kconfig b/drivers/infiniband/hw/erdma/Kconfig
index 267fc1f3c42a..745e5551773f 100644
--- a/drivers/infiniband/hw/erdma/Kconfig
+++ b/drivers/infiniband/hw/erdma/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config INFINIBAND_ERDMA
 	tristate "Alibaba Elastic RDMA Adapter (ERDMA) support"
-	depends on PCI_MSI && 64BIT
+	depends on PCI_MSI && 64BIT && !CPU_BIG_ENDIAN
 	depends on INFINIBAND_ADDR_TRANS
 	depends on INFINIBAND_USER_ACCESS
 	help

---
base-commit: 961ac0f0c5e414abdd6b33fae84b311d9fde0bd0
change-id: 20260806-missing-endianness-conversion-for-64-f0af69246071

Best regards,
--  
Leon Romanovsky <leonro@nvidia.com>

On Thu, 06 Aug 2026 11:48:56 +0300, Leon Romanovsky wrote:
> The eRDMA device interface requires explicit byte ordering, but several
> DMA-visible values that should be little-endian remain native-endian.
> Command request payloads are copied verbatim, data-path SQE headers are
> written without cpu_to_le64(), and kernel doorbell records are assigned
> plain u64 values. The command completion path also reads a little-endian
> SQE header without conversion.
> 
> [...]

Applied, thanks!

[1/1] RDMA/erdma: restrict the driver to little-endian systems
      https://git.kernel.org/rdma/rdma/c/a12d9145145b21

Best regards,
-- 
Leon Romanovsky <leonro@nvidia.com>

On 8/6/26 4:48 PM, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@nvidia.com>
> 
> The eRDMA device interface requires explicit byte ordering, but several
> DMA-visible values that should be little-endian remain native-endian.
> Command request payloads are copied verbatim, data-path SQE headers are
> written without cpu_to_le64(), and kernel doorbell records are assigned
> plain u64 values. The command completion path also reads a little-endian
> SQE header without conversion.
> 
> These paths are byte-swapped on big-endian kernels and can break command
> processing during probe. Since complete big-endian support requires
> converting every device-visible structure, depend on !CPU_BIG_ENDIAN.
> 
> Fixes: ca7fd6cff3b8 ("RDMA/erdma: Add driver to kernel build environment")
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> ---
> RDMA/erdma: restrict the driver to little-endian systems
> ---
>  drivers/infiniband/hw/erdma/Kconfig | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 

Acked-by: Cheng Xu <chengyou@linux.alibaba.com>

> diff --git a/drivers/infiniband/hw/erdma/Kconfig b/drivers/infiniband/hw/erdma/Kconfig
> index 267fc1f3c42a..745e5551773f 100644
> --- a/drivers/infiniband/hw/erdma/Kconfig
> +++ b/drivers/infiniband/hw/erdma/Kconfig
> @@ -1,7 +1,7 @@
>  # SPDX-License-Identifier: GPL-2.0-only
>  config INFINIBAND_ERDMA
>  	tristate "Alibaba Elastic RDMA Adapter (ERDMA) support"
> -	depends on PCI_MSI && 64BIT
> +	depends on PCI_MSI && 64BIT && !CPU_BIG_ENDIAN
>  	depends on INFINIBAND_ADDR_TRANS
>  	depends on INFINIBAND_USER_ACCESS
>  	help
> 
> ---
> base-commit: 961ac0f0c5e414abdd6b33fae84b311d9fde0bd0
> change-id: 20260806-missing-endianness-conversion-for-64-f0af69246071
> 
> Best regards,
> --  
> Leon Romanovsky <leonro@nvidia.com>