Re: [PATCH v2 0/5] Convert riscv to use the generic iommu page table

From: Jason Gunthorpe <jgg@nvidia.com>
To: Robin Murphy <robin.murphy@arm.com>
Cc: Vincent Chen <vincent.chen@sifive.com>,
	Alexandre Ghiti <alex@ghiti.fr>,
	Albert Ou <aou@eecs.berkeley.edu>,
	iommu@lists.linux.dev, Joerg Roedel <joro@8bytes.org>,
	linux-riscv@lists.infradead.org,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <pjw@kernel.org>,
	Tomasz Jeznach <tjeznach@rivosinc.com>,
	Will Deacon <will@kernel.org>,
	lihangjing@bytedance.com, Xu Lu <luxu.kernel@bytedance.com>,
	patches@lists.linux.dev, xieyongji@bytedance.com
Subject: Re: [PATCH v2 0/5] Convert riscv to use the generic iommu page table
Date: Fri, 30 Jan 2026 20:27:28 -0400	[thread overview]
Message-ID: <20260131002728.GM2223369@nvidia.com> (raw)
In-Reply-To: <b1b220be-fd5e-4f83-8f5e-7d5282be39f9@arm.com>

On Thu, Jan 29, 2026 at 11:21:53AM +0000, Robin Murphy wrote:

> The driver does not advertise IOMMU_CAP_DEFERRED_FLUSH, as the existing
> pagetable code has never implemented the conditional TLB maintenance
> optimisation that makes it meaningful. Mind you, I don't see any reference
> to iommu_iotlb_gather_queued() in generic_pt either, so I have no idea how
> that's trying to do it :/

Well, correct me if I've got it wrong..

DMA-FQ always does flush all, so the goal is to eliminate redundant
flushes from within the page table logic itself.

DMA-FQ requires two functionalites from the page table:
1) use gather->freelist to avoid a HW UAF (iommupt always does this)
2) avoid internal calls to iommu_iotlb_sync()

When the gather reaches __iommu_dma_unmap() it discards any iova range
inside it, queues the freelist, and queues a flush all. So any flush
implied by the gather is removed by the core code.

iommu_iotlb_gather_queued() should be used in the page table to
supress any internal flushes.

iommupt doesn't have any calls because it doesn't have any internal
flushes. It calls iommu_iotlb_gather_add_range() which blindly updates
the iova and never flushes.

The one call to iommu_iotlb_sync() is only for the para-virtualization
optimization of narrowing invalidations. It would be nonsensical for a
driver to enable this optimization and offer IOMMU_CAP_DEFERRED_FLUSH.

But it is a good point that riscv pagetable may not have supported it
before, but it does now, so we should probably add
IOMMU_CAP_DEFERRED_FLUSH. I'll send a patch next cycle.

Jason

_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv