tmakin/tegra-linux-noble
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

iommu/amd/pgtbl_v2: Take protection domain lock before invalidating TLB

Browse Source 
BugLink: https://bugs.launchpad.net/bugs/2101915

[ Upstream commit 016991606aa01c4d92e6941be636c0c897aa05c7 ]

Commit c7fc12354b ("iommu/amd/pgtbl_v2: Invalidate updated page ranges
only") missed to take domain lock before calling
amd_iommu_domain_flush_pages(). Fix this by taking protection domain
lock before calling TLB invalidation function.

Fixes: c7fc12354b ("iommu/amd/pgtbl_v2: Invalidate updated page ranges only")
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20241030063556.6104-2-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[koichiroden: adjusted context without backporting the following commits
(which have been applied in linux-6.11.y) to avoid multiple conflicts
and reduce regression risk:
- 9ac0b3380acd ("iommu/amd: Narrow the use of struct protection_domain to invalidation")
- 47f218d10895 ("iommu/amd: Store the nid in io_pgtable_cfg instead of the domain")
- 670b57796c5d ("iommu/amd: Rename struct amd_io_pgtable iopt to pgtbl")
- 1ed2d21d471c ("iommu/amd: Remove the amd_iommu_domain_set_pt_root() and related")]
Signed-off-by: Koichiro Den <koichiro.den@canonical.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
This commit is contained in:
Vasant Hegde
2025-03-11 08:51:19 +09:00
committed by Stefan Bader
parent 258f582713
commit c0471c0ffd
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
drivers/iommu/amd/io_pgtable_v2.c
+6 -1
View File
@@ -270,8 +270,13 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
}
out:
if (updated)
if (updated) {
unsigned long flags;
spin_lock_irqsave(&pdom->lock, flags);
amd_iommu_domain_flush_pages(pdom, o_iova, size);
spin_unlock_irqrestore(&pdom->lock, flags);
}
if (mapped)
*mapped += mapped_size;