powerpc/book3s64/radix/tlb: Determine hugepage flush correctly
PATCH 1/1 powerpc/book3s64/radix/tlb: Determine hugepage flush correctly
With a 64K page size flush with start and end value as below (start, end) = (721f680d0000, 721f680e0000) results in (hstart, hend) = (721f68200000, 721f68000000)
Avoid doing a __tlbie_va_range with the wrong hstart and hend value in this case.
__tlbie_va_range will skip the actual tlbie operation for start > end. But we still end up doing the tlbie fixup.
--- arch/powerpc/mm/book3s64/radix_tlb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
arch/powerpc/mm/book3s64/radix_tlb.c +3 -3
@@ -884,10 +884,10 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,if (IS_ENABLED (CONFIG_TRANSPARENT_HUGEPAGE )) { hstart = (start +PMD_SIZE -1 ) &PMD_MASK ; hend = end &PMD_MASK ; -if (hstart == hend) - hflush = false; -else +if (hstart < hend) hflush = true; +else + hflush = false; }if (local) {
Signature · 1 line
2.26.2
Excerpts from Aneesh Kumar K.V's message of May 13, 2020 1:06 pm:
Quoted 9 lines
With a 64K page size flush with start and end value as below (start, end) = (
721f680d0000,721f680e0000) results in (hstart, hend) = (721f68200000,721f68000000)Avoid doing a
__tlbie_va_rangewith the wrong hstart and hend value in this case.
__tlbie_va_rangewill skip the actual tlbie operation for start > end. But we still end up doing the tlbie fixup.
Hm, good catch.
Quoted 11 lines
Reported-by Bharata B Rao <[email protected]>Signed-off-by Aneesh Kumar K.V <[email protected]>--- arch/powerpc/mm/book3s64/radix_tlb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)arch/powerpc/mm/book3s64/radix_tlb.c +0
-0
arch/powerpc/mm/book3s64/radix_tlb.c static inline void __radix__flush_tlb_range(struct mm_struct *mm, · line 890
Quoted 10 lines
arch/powerpc/mm/book3s64/radix_tlb.c +3
-3@@ -884,10 +884,10 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,if (IS_ENABLED (CONFIG_TRANSPARENT_HUGEPAGE )) { hstart = (start +PMD_SIZE -1 ) &PMD_MASK ; hend = end &PMD_MASK ; -if (hstart == hend) - hflush = false; -else +if (hstart < hend) hflush = true; +else + hflush = false;
We can probably get rid of the else part since it is already false.
Otherwise
Michael Ellerman
reviewerQuoted 28 lines · Nicholas Piggin
Excerpts from Aneesh Kumar K.V's message of May 13, 2020 1:06 pm:
Quoted 9 lines
With a 64K page size flush with start and end value as below (start, end) = (
721f680d0000,721f680e0000) results in (hstart, hend) = (721f68200000,721f68000000)Avoid doing a
__tlbie_va_rangewith the wrong hstart and hend value in this case.
__tlbie_va_rangewill skip the actual tlbie operation for start > end. But we still end up doing the tlbie fixup.Hm, good catch.
Quoted 15 lines
Reported-by Bharata B Rao <[email protected]>Signed-off-by Aneesh Kumar K.V <[email protected]>--- arch/powerpc/mm/book3s64/radix_tlb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)arch/powerpc/mm/book3s64/radix_tlb.c +0
-1@@ -884,10 +884,10 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,if (IS_ENABLED (CONFIG_TRANSPARENT_HUGEPAGE )) { hstart = (start +PMD_SIZE -1 ) &PMD_MASK ; hend = end &PMD_MASK ; -if (hstart == hend)
Quoted 8 lines
arch/powerpc/mm/book3s64/radix_tlb.c static inline void __radix__flush_tlb_range(struct mm_struct *mm, · line 890
Quoted 6 lines
arch/powerpc/mm/book3s64/radix_tlb.c +3
-2- hflush = false; - else +if (hstart < hend) hflush = true; +else + hflush = false;We can probably get rid of the else part since it is already false.
Yeah I can do that when applying.
cheers
Michael Ellerman
AppliedQuoted 8 lines · Aneesh Kumar K.V
With a 64K page size flush with start and end value as below (start, end) = (
721f680d0000,721f680e0000) results in (hstart, hend) = (721f68200000,721f68000000)Avoid doing a
__tlbie_va_rangewith the wrong hstart and hend value in this case.[...]
Applied to powerpc/next.
[1/1] powerpc/book3s64/radix/tlb: Determine hugepage flush correctly
https://git.kernel.org/powerpc/c/8f53f9c0f68ab2168f637494b9e24034899c1310
cheers