Re: [PATCH v7 14/15] dt-bindings: of: Add restricted DMA pool
From: Will Deacon <will@kernel.org>
Date: 2021-05-26 12:13:38
Also in:
dri-devel, intel-gfx, linux-devicetree, linux-iommu, linux-pci, lkml, xen-devel
Hi Claire, On Tue, May 18, 2021 at 02:42:14PM +0800, Claire Chang wrote:
quoted hunk ↗ jump to hunk
Introduce the new compatible string, restricted-dma-pool, for restricted DMA. One can specify the address and length of the restricted DMA memory region by restricted-dma-pool in the reserved-memory node. Signed-off-by: Claire Chang <redacted> --- .../reserved-memory/reserved-memory.txt | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+)diff --git a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt index e8d3096d922c..284aea659015 100644 --- a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt +++ b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt@@ -51,6 +51,23 @@ compatible (optional) - standard definition used as a shared pool of DMA buffers for a set of devices. It can be used by an operating system to instantiate the necessary pool management subsystem if necessary. + - restricted-dma-pool: This indicates a region of memory meant to be + used as a pool of restricted DMA buffers for a set of devices. The + memory region would be the only region accessible to those devices. + When using this, the no-map and reusable properties must not be set, + so the operating system can create a virtual mapping that will be used + for synchronization. The main purpose for restricted DMA is to + mitigate the lack of DMA access control on systems without an IOMMU, + which could result in the DMA accessing the system memory at + unexpected times and/or unexpected addresses, possibly leading to data + leakage or corruption. The feature on its own provides a basic level + of protection against the DMA overwriting buffer contents at + unexpected times. However, to protect against general data leakage and + system memory corruption, the system needs to provide way to lock down + the memory access, e.g., MPU. Note that since coherent allocation + needs remapping, one must set up another device coherent pool by + shared-dma-pool and use dma_alloc_from_dev_coherent instead for atomic + coherent allocation. - vendor specific string in the form <vendor>,[<device>-]<usage> no-map (optional) - empty property - Indicates the operating system must not create a virtual mapping@@ -120,6 +137,11 @@ one for multimedia processing (named multimedia-memory@77000000, 64MiB). compatible = "acme,multimedia-memory"; reg = <0x77000000 0x4000000>; }; + + restricted_dma_mem_reserved: restricted_dma_mem_reserved { + compatible = "restricted-dma-pool"; + reg = <0x50000000 0x400000>; + };
nit: You need to update the old text that states "This example defines 3 contiguous regions ...".
quoted hunk ↗ jump to hunk
}; /* ... */@@ -138,4 +160,9 @@ one for multimedia processing (named multimedia-memory@77000000, 64MiB). memory-region = <&multimedia_reserved>; /* ... */ }; + + pcie_device: pcie_device@0,0 { + memory-region = <&restricted_dma_mem_reserved>; + /* ... */ + };
I still don't understand how this works for individual PCIe devices -- how is dev->of_node set to point at the node you have above? I tried adding the memory-region to the host controller instead, and then I see it crop up in dmesg: | pci-host-generic 40000000.pci: assigned reserved memory node restricted_dma_mem_reserved but none of the actual PCI devices end up with 'dma_io_tlb_mem' set, and so the restricted DMA area is not used. In fact, swiotlb isn't used at all. What am I missing to make this work with PCIe devices? Thanks, Will