]> git.ipfire.org Git - thirdparty/kernel/stable.git/commit
iommu/amd: Fix race in increase_address_space()
authorJoerg Roedel <jroedel@suse.de>
Fri, 6 Sep 2019 08:39:54 +0000 (10:39 +0200)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Sat, 21 Sep 2019 05:15:45 +0000 (07:15 +0200)
commitb15bf74405faa1a65025eb8a6eb337e140e5250a
tree8fc2cdcc8dadad5ea40aa327e6f97890be143192
parentd6a4eedb0088b1a6755e7caff77c681d3b8be101
iommu/amd: Fix race in increase_address_space()

[ Upstream commit 754265bcab78a9014f0f99cd35e0d610fcd7dfa7 ]

After the conversion to lock-less dma-api call the
increase_address_space() function can be called without any
locking. Multiple CPUs could potentially race for increasing
the address space, leading to invalid domain->mode settings
and invalid page-tables. This has been happening in the wild
under high IO load and memory pressure.

Fix the race by locking this operation. The function is
called infrequently so that this does not introduce
a performance regression in the dma-api path again.

Reported-by: Qian Cai <cai@lca.pw>
Fixes: 256e4621c21a ('iommu/amd: Make use of the generic IOVA allocator')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drivers/iommu/amd_iommu.c