diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index f890f7ce1593..5f3a33784259 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -592,6 +592,10 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, extern void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#define pmdp_collapse_flush pmdp_collapse_flush + #define __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 6bfadf1aa5cb..049d961802aa 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -560,41 +560,47 @@ pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - if (pmd_trans_huge(*pmdp)) { - pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp); - } else { - /* - * khugepaged calls this for normal pmd - */ - pmd = *pmdp; - pmd_clear(pmdp); - /* - * Wait for all pending hash_page to finish. This is needed - * in case of subpage collapse. When we collapse normal pages - * to hugepage, we first clear the pmd, then invalidate all - * the PTE entries. The assumption here is that any low level - * page fault will see a none pmd and take the slow path that - * will wait on mmap_sem. But we could very well be in a - * hash_page with local ptep pointer value. Such a hash page - * can result in adding new HPTE entries for normal subpages. - * That means we could be modifying the page content as we - * copy them to a huge page. So wait for parallel hash_page - * to finish before invalidating HPTE entries. We can do this - * by sending an IPI to all the cpus and executing a dummy - * function there. - */ - kick_all_cpus_sync(); - /* - * Now invalidate the hpte entries in the range - * covered by pmd. This make sure we take a - * fault and will find the pmd as none, which will - * result in a major fault which takes mmap_sem and - * hence wait for collapse to complete. Without this - * the __collapse_huge_page_copy can result in copying - * the old content. - */ - flush_tlb_pmd_range(vma->vm_mm, &pmd, address); - } + VM_BUG_ON(!pmd_trans_huge(*pmdp)); + pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp); + return pmd; +} + +pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + VM_BUG_ON(pmd_trans_huge(*pmdp)); + + pmd = *pmdp; + pmd_clear(pmdp); + /* + * Wait for all pending hash_page to finish. This is needed + * in case of subpage collapse. When we collapse normal pages + * to hugepage, we first clear the pmd, then invalidate all + * the PTE entries. The assumption here is that any low level + * page fault will see a none pmd and take the slow path that + * will wait on mmap_sem. But we could very well be in a + * hash_page with local ptep pointer value. Such a hash page + * can result in adding new HPTE entries for normal subpages. + * That means we could be modifying the page content as we + * copy them to a huge page. So wait for parallel hash_page + * to finish before invalidating HPTE entries. We can do this + * by sending an IPI to all the cpus and executing a dummy + * function there. + */ + kick_all_cpus_sync(); + /* + * Now invalidate the hpte entries in the range + * covered by pmd. This make sure we take a + * fault and will find the pmd as none, which will + * result in a major fault which takes mmap_sem and + * hence wait for collapse to complete. Without this + * the __collapse_huge_page_copy can result in copying + * the old content. + */ + flush_tlb_pmd_range(vma->vm_mm, &pmd, address); return pmd; } diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index bd910ceaccfa..d2c2171d1c32 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -189,6 +189,27 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif +#ifndef pmdp_collapse_flush +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + return pmdp_clear_flush(vma, address, pmdp); +} +#define pmdp_collapse_flush pmdp_collapse_flush +#else +static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUILD_BUG(); + return *pmdp; +} +#define pmdp_collapse_flush pmdp_collapse_flush +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b3d8cd8d6968..65dd8d67287b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2499,7 +2499,7 @@ static void collapse_huge_page(struct mm_struct *mm, * huge and small TLB entries for the same virtual address * to avoid the risk of CPU bugs in that area. */ - _pmd = pmdp_clear_flush(vma, address, pmd); + _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);