RDMA/umem: Fix truncation for block sizes >= 4G
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
≥ a808273a495c657e33281b181fd7fcc2bb28f662 · < afd35fec9297195b759078745549c2671223f24f| No fix yet |
| Linux Linux |
|
|
In the Linux kernel, the following vulnerability has been resolved:
RDMA/umem: Fix truncation for block sizes >= 4G
When the iommu is used the linearization of the mapping can give a single block that is very large split across multiple SG entries.
When __rdma_block_iter_next() reassembles the split SG entries it is overflowing the 32 bit stack values and computed the wrong DMA addresses for blocks after the truncation.
Use the right types to hold DMA addresses.
From the CVE record · Linux
The Linux kernel's RDMA/umem block iterator can truncate values when an IOMMU mapping produces a block of 4 GB or more split across multiple scatter-gather entries. This can cause it to compute incorrect DMA addresses for later blocks. The input does not specify an attacker path, authentication requirements, or user interaction.
Engineers running Linux kernels that use RDMA/umem with IOMMU mappings should check their versions; affected versions are not specified.