Nicholas Piggin [off-list ref] writes:
When the mm is being torn down there will be a full PID flush so
there is no need to flush the TLB on page size changes.
and that tlb flush is PID flush since tlb->fulmm is set? So this avoids
multiple PID tlb flush.
Reviewed-by: Aneesh Kumar K.V <redacted>
quoted hunk ↗ jump to hunk
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/tlb.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 5d3107f2b014..d1b3dc4a6a0a 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -84,6 +84,9 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
unsigned int page_size)
{
+ if (tlb->fullmm)
+ return;
+
if (!tlb->page_size)
tlb->page_size = page_size;
else if (tlb->page_size != page_size) {--
2.17.0