iommu/amd: Fix amd_iommu_detect() (does not fix any issues).
PATCH 1/1 iommu/amd: Fix amd_iommu_detect() (does not fix any issues).
From: Jérôme Glisse <[email protected]>
Fix amd_iommu_detect() to return positive value on success, like intended, and not zero. This will not change anything in the end as AMD IOMMU disable swiotlb and properly associate itself with devices even if detect() doesn't return a positive value.
--- drivers/iommu/amd_iommu_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/iommu/amd_iommu_init.c +1 -1
@@ -2198,7 +2198,7 @@ int __init amd_iommu_detect(void) iommu_detected =1 ; x86_init.iommu.iommu_init = amd_iommu_init; -return 0 ; +return 1 ; }/****************************************************************************
Signature · 6 lines
1.8.3.1 _______________________________________________ iommu mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/iommu
Joerg Roedel
AppliedQuoted 10 lines · On Mon, Aug 31, 2015 at 06:13:03PM -0400…
From: Jérôme Glisse <[email protected]>
Fix
amd_iommu_detect()to return positive value on success, like intended, and not zero. This will not change anything in the end as AMD IOMMU disable swiotlb and properly associate itself with devices even ifdetect()doesn't return a positive value.Signed-off-by Jérôme Glisse <[email protected]>Cc Joerg Roedel <[email protected]>Cc iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
Applied, thanks.
Quoted 5 lines · On Mon, Aug 31, 2015 at 06:13:03PM -0400…
From: Jérôme Glisse <[email protected]>
Fix
amd_iommu_detect()to return positive value on success, like intended, and not zero. This will not change anything in the end as AMD IOMMU disable swiotlb and properly associate itself with
Not sure how it disables SWIOTLB? The AMD Vi does not seem to change 'swiotlb'. While 'gart_iommu_init' does. Did you mean the AMD GART code?
Quoted 1 line
devices even if
detect()doesn't return a positive value.
Returning positive will mean that the pci_iommu_alloc will stop processing _all_ other IOMMUs.
While returning 0 will let it detect the other IOMMUs.
Granted on an AMD machine there can be two 'IOMMU's - the GART and the AMD Vi. The detection is always to call gart_iommu_hole_init first, then amd_iommu_detect.
I presume if there was one more type on AMD we would run into trouble.
Quoted 28 lines
Signed-off-by Jérôme Glisse <[email protected]>Cc Joerg Roedel <[email protected]>Cc iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org--- drivers/iommu/amd_iommu_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)drivers/iommu/amd_iommu_init.c +1
-1@@ -2198,7 +2198,7 @@ int __init amd_iommu_detect(void) iommu_detected =1 ; x86_init.iommu.iommu_init = amd_iommu_init; -return 0 ; +return 1 ; }/**************************************************************************** Signature · 6 lines
1.8.3.1 _______________________________________________ iommu mailing list iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Quoted 10 lines · Konrad Rzeszutek Wilk
Quoted 5 lines · On Mon, Aug 31, 2015 at 06:13:03PM -0400…
From: Jérôme Glisse <[email protected]>
Fix
amd_iommu_detect()to return positive value on success, like intended, and not zero. This will not change anything in the end as AMD IOMMU disable swiotlb and properly associate itself withNot sure how it disables SWIOTLB? The AMD Vi does not seem to change 'swiotlb'. While '
gart_iommu_init' does. Did you mean the AMD GART code?
So this is convoluted and painfull, each i look back at that it takes me time to figure out of thing happen. Basicly amd_iommu_init_dma_ops() will replace dma_ops to no_mmu unless passthrough, and when the AMD iommu associate itself with each device it will set the archdata.dma_ops again this unbind the default of swiotlb that is initialize before hw IOMMU.
Quoted 7 lines
Quoted 2 lines
devices even if
detect()doesn't return a positive value.Returning positive will mean that the
pci_iommu_allocwill stop processing _all_ other IOMMUs.While returning 0 will let it detect the other IOMMUs.
No see the IOMMU_FINISH_IF_DETECTED flags in pci_iommu_alloc(). Which is not set for AMD hence my patch should not change anything it (AFAICT and from testing but i do not have all AMD hw the ever existed).
So i am just making the detect function do what the API doc says it should do. See line 72 to 80 of : arch/x86/include/asm/iommu_table.h
Quoted 6 lines
Granted on an AMD machine there can be two 'IOMMU's - the GART and the AMD Vi. The detection is always to call
gart_iommu_hole_initfirst, thenamd_iommu_detect.I presume if there was one more type on AMD we would run into trouble.
No because of IOMMU_FINISH_IF_DETECTED flag.
Hope this clarify thing this spagethi mix :)
Cheers,
Jérôme
Quoted 40 lines · Jerome Glisse
Quoted 10 lines · Konrad Rzeszutek Wilk
Quoted 5 lines · On Mon, Aug 31, 2015 at 06:13:03PM -0400…
From: Jérôme Glisse <[email protected]>
Fix
amd_iommu_detect()to return positive value on success, like intended, and not zero. This will not change anything in the end as AMD IOMMU disable swiotlb and properly associate itself withNot sure how it disables SWIOTLB? The AMD Vi does not seem to change 'swiotlb'. While '
gart_iommu_init' does. Did you mean the AMD GART code?So this is convoluted and painfull, each i look back at that it takes me time to figure out of thing happen. Basicly
amd_iommu_init_dma_ops()will replacedma_opstono_mmuunless passthrough, and when the AMD iommu associate itself with each device it will set the archdata.dma_ops again this unbind the default of swiotlb that is initialize before hw IOMMU.Quoted 7 lines
Quoted 2 lines
devices even if
detect()doesn't return a positive value.Returning positive will mean that the
pci_iommu_allocwill stop processing _all_ other IOMMUs.While returning 0 will let it detect the other IOMMUs.
No see the
IOMMU_FINISH_IF_DETECTEDflags inpci_iommu_alloc(). Which is not set for AMD hence my patch should not change anything it (AFAICT and from testing but i do not have all AMD hw the ever existed).So i am just making the detect function do what the API doc says it should do. See line 72 to 80 of :
arch/x86/include/asm/iommu_table.hQuoted 5 lines
Granted on an AMD machine there can be two 'IOMMU's - the GART and the AMD Vi. The detection is always to call
gart_iommu_hole_initfirst, thenamd_iommu_detect.
Quoted 5 lines
Quoted 1 line
I presume if there was one more type on AMD we would run into trouble.
No because of
IOMMU_FINISH_IF_DETECTEDflag.Hope this clarify thing this spagethi mix :)
Ok my bad amd actualy is using IOMMU_INIT_FINISH() so it finish before trying other. Which make sense for AMD as AMD driver will call the gart init gart_iommu_init() if it fails to initialize. If we ever end up with a platform with multiple IOMMU beside AMD then we need to switch to the IOMMU_INIT() instead of the finish one.
Cheers,
Jérôme
Quoted 13 lines · Jerome Glisse
Quoted 12 lines · Jerome Glisse
Quoted 10 lines · Konrad Rzeszutek Wilk
Quoted 5 lines · On Mon, Aug 31, 2015 at 06:13:03PM -0400…
From: Jérôme Glisse <[email protected]>
Fix
amd_iommu_detect()to return positive value on success, like intended, and not zero. This will not change anything in the end as AMD IOMMU disable swiotlb and properly associate itself withNot sure how it disables SWIOTLB? The AMD Vi does not seem to change 'swiotlb'. While '
gart_iommu_init' does. Did you mean the AMD GART code?
Quoted 6 lines
Quoted 6 lines
So this is convoluted and painfull, each i look back at that it takes me time to figure out of thing happen. Basicly
amd_iommu_init_dma_ops()will replacedma_opstono_mmuunless passthrough, and when the AMD iommu associate itself with each device it will set the archdata.dma_ops again this unbind the default of swiotlb that is initialize before hw IOMMU.
Oh my. That is not exactly clear.
Quoted 26 lines
Quoted 26 lines
Quoted 8 lines
Quoted 3 lines
devices even if
detect()doesn't return a positive value.Returning positive will mean that the
pci_iommu_allocwill stop processing _all_ other IOMMUs.While returning 0 will let it detect the other IOMMUs.
No see the
IOMMU_FINISH_IF_DETECTEDflags inpci_iommu_alloc(). Which is not set for AMD hence my patch should not change anything it (AFAICT and from testing but i do not have all AMD hw the ever existed).So i am just making the detect function do what the API doc says it should do. See line 72 to 80 of :
arch/x86/include/asm/iommu_table.hQuoted 6 lines
Granted on an AMD machine there can be two 'IOMMU's - the GART and the AMD Vi. The detection is always to call
gart_iommu_hole_initfirst, thenamd_iommu_detect.I presume if there was one more type on AMD we would run into trouble.
No because of
IOMMU_FINISH_IF_DETECTEDflag.
Quoted 7 lines
Quoted 1 line
Hope this clarify thing this spagethi mix :)
Ok my bad amd actualy is using
IOMMU_INIT_FINISH()so it finish before trying other. Which make sense for AMD as AMD driver will call the gart initgart_iommu_init()if it fails to initialize. If we ever end up with a platform with multiple IOMMU beside AMD then we need to switch to theIOMMU_INIT()instead of the finish one.
Right :-)
Does it make sense then to push this patch out considering that it will make it harder in the future (aka, somebody will have to track why their IOMMUs are not initializing)?
Or perhaps just make a patch that puts a comment around the 'return ' and says why it has the value it has now?
Quoted 3 lines
Cheers,
Jérôme