nvme-pci: fix parameter order in nvme_free_sgls() call
Subsystems (2)
PATCH 1/1 nvme-pci: fix parameter order in nvme_free_sgls() call
The call to nvme_free_sgls() in nvme_unmap_data() has the sg_list and sge parameters swapped. This wasn't noticed by the compiler because both share the same type. On a Xen PV hardware domain, and possibly any other architectures that takes that path, this leads to corruption of the NVMe contents.
---
If possible it would be good for this to go in 6.19.0-rc8, as corruption of the root device as part of a kernel update is unexpected. Sadly 6.18 already contained this issue, and no-one noticed, so its impact is limited?
--- drivers/nvme/host/pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/nvme/host/pci.c +2 -2
@@ -806,8 +806,8 @@ static void nvme_unmap_data(struct request *req)if (!blk_rq_dma_unmap (req, dma_dev, &iod->dma_state, iod->total_len, map)) {if (nvme_pci_cmd_use_sgl (&iod->cmd)) -nvme_free_sgls (req, iod->descriptors[0 ], - &iod->cmd.common.dptr.sgl, attrs); +nvme_free_sgls (req, &iod->cmd.common.dptr.sgl, + iod->descriptors[0 ], attrs);else nvme_free_prps (req, attrs); }
Signature · 1 line
2.51.0
Quoted 6 lines · Roger Pau Monne
The call to
nvme_free_sgls()innvme_unmap_data()has thesg_listand sge parameters swapped. This wasn't noticed by the compiler because both share the same type. On a Xen PV hardware domain, and possibly any other architectures that takes that path, this leads to corruption of the NVMe contents.
Quoted 6 lines
Fixes f0887e2a52d4 ("nvme-pci: create common sgl unmapping helper")Signed-off-by Roger Pau Monné <[email protected]>---
If possible it would be good for this to go in 6.19.0-rc8, as corruption of the root device as part of a kernel update is unexpected. Sadly 6.18 already contained this issue, and no-one noticed, so its impact is limited?
This only affects non-IOMMU paths with a non-noop dma_unmap_phys. So it is a very common setup, but very severe for those. Because of that we should get into 6.19-rc and -stable ASAP.
The fix looks good:
but maybe we can reword the subject to sound less harmless, e.g.:
nvme-pci: DMA unmap the correct regions in nvme_free_sgls
?
Quoted 14 lines · Christoph Hellwig
Quoted 6 lines · Roger Pau Monne
The call to
nvme_free_sgls()innvme_unmap_data()has thesg_listand sge parameters swapped. This wasn't noticed by the compiler because both share the same type. On a Xen PV hardware domain, and possibly any other architectures that takes that path, this leads to corruption of the NVMe contents.Quoted 6 lines
Fixes f0887e2a52d4 ("nvme-pci: create common sgl unmapping helper")Signed-off-by Roger Pau Monné <[email protected]>---
If possible it would be good for this to go in 6.19.0-rc8, as corruption of the root device as part of a kernel update is unexpected. Sadly 6.18 already contained this issue, and no-one noticed, so its impact is limited?
Quoted 2 lines
This only affects non-IOMMU paths with a non-noop
dma_unmap_phys. So it is a very common setup, but very severe for those. Because of
Do you mean a "not very common setup"? Otherwise I can't parse the sentence.
Quoted 5 lines
that we should get into 6.19-rc and -stable ASAP.
The fix looks good:
Reviewed-by Christoph Hellwig <[email protected]>
Thanks.
Quoted 3 lines
but maybe we can reword the subject to sound less harmless, e.g.:
nvme-pci: DMA unmap the correct regions in
nvme_free_sgls
Fine with me. I think I was more focused on describing the logical change rather that the actual effect of it. Can you adjust it when picking up?
Regards, Roger.
Christoph Hellwig
maintainerQuoted 8 lines · Roger Pau Monné
Quoted 5 lines
Quoted 2 lines
the root device as part of a kernel update is unexpected. Sadly 6.18 already contained this issue, and no-one noticed, so its impact is limited?
This only affects non-IOMMU paths with a non-noop
dma_unmap_phys. So it is a very common setup, but very severe for those. Because ofDo you mean a "not very common setup"? Otherwise I can't parse the sentence.
Yes, sorry.
Quoted 5 lines · Roger Pau Monne
The call to
nvme_free_sgls()innvme_unmap_data()has thesg_listand sge parameters swapped. This wasn't noticed by the compiler because both share the same type. On a Xen PV hardware domain, and possibly any other architectures that takes that path, this leads to corruption of the NVMe contents.
Thanks, applied to nvme-6.19 with updated subject.
Quoted 6 lines · Keith Busch
Quoted 5 lines · Roger Pau Monne
The call to
nvme_free_sgls()innvme_unmap_data()has thesg_listand sge parameters swapped. This wasn't noticed by the compiler because both share the same type. On a Xen PV hardware domain, and possibly any other architectures that takes that path, this leads to corruption of the NVMe contents.
Quoted 5 lines · Christoph Hellwig
Reviewed-by Christoph Hellwig <[email protected]>but maybe we can reword the subject to sound less harmless, e.g.:
nvme-pci: DMA unmap the correct regions in
nvme_free_sgls
Quoted 1 line · Keith Busch
Thanks, applied to nvme-6.19 with updated subject.
Hi,
I think this wants to be included in v6.18 too, as it also has the faulty commit. And indeed, I do hit this issue when running 6.18.38.
Signature · 3 lines
Best Regards, Marek Marczykowski-Górecki Invisible Things Lab
Sasha Levin
maintainerQuoted 2 lines · Marek Marczykowski-Górecki
I think this wants to be included in v6.18 too, as it also has the faulty commit. And indeed, I do hit this issue when running 6.18.38.
Nicolai Buchwitz sent a 6.18.y backport of this, which is now queued for 6.18, thanks.
Signature · 2 lines
Thanks, Sasha