From 75077afbec1ac89178c1542b23a70d0f960b0aaf Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 8 Oct 2012 16:30:15 -0700 Subject: thp, s390: thp splitting backend for s390 This patch is part of the architecture backend for thp on s390. It provides the functions related to thp splitting, including serialization against gup. Unlike other archs, pmdp_splitting_flush() cannot use a tlb flushing operation to serialize against gup on s390, because that wouldn't be stopped by the disabled IRQs. So instead, smp_call_function() is called with an empty function, which will have the expected effect. Signed-off-by: Gerald Schaefer Cc: Andrea Arcangeli Cc: Andi Kleen Cc: Hugh Dickins Cc: Hillf Danton Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/pgtable.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'arch/s390/mm/pgtable.c') diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index b402991e43d7..a6131d1fe6c0 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -866,3 +866,21 @@ bool kernel_page_present(struct page *page) return cc == 0; } #endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void pmdp_splitting_flush_sync(void *arg) +{ + /* Simply deliver the interrupt */ +} + +void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + if (!test_and_set_bit(_SEGMENT_ENTRY_SPLIT_BIT, + (unsigned long *) pmdp)) { + /* need to serialize against gup-fast (IRQ disabled) */ + smp_call_function(pmdp_splitting_flush_sync, NULL, 1); + } +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -- cgit v1.2.3 From 9501d09fa3c4ca18971083dfb0c9aa1afc85f19c Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 8 Oct 2012 16:30:18 -0700 Subject: thp, s390: thp pagetable pre-allocation for s390 This patch is part of the architecture backend for thp on s390. It provides the pagetable pre-allocation functions pgtable_trans_huge_deposit() and pgtable_trans_huge_withdraw(). Unlike other archs, s390 has no struct page * as pgtable_t, but rather a pointer to the page table. So instead of saving the pagetable pre- allocation list info inside the struct page, it is being saved within the pagetable itself. Signed-off-by: Gerald Schaefer Cc: Andrea Arcangeli Cc: Andi Kleen Cc: Hugh Dickins Cc: Hillf Danton Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/pgtable.c | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'arch/s390/mm/pgtable.c') diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a6131d1fe6c0..1ca371a06516 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -883,4 +883,42 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, smp_call_function(pmdp_splitting_flush_sync, NULL, 1); } } + +void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) +{ + struct list_head *lh = (struct list_head *) pgtable; + + assert_spin_locked(&mm->page_table_lock); + + /* FIFO */ + if (!mm->pmd_huge_pte) + INIT_LIST_HEAD(lh); + else + list_add(lh, (struct list_head *) mm->pmd_huge_pte); + mm->pmd_huge_pte = pgtable; +} + +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) +{ + struct list_head *lh; + pgtable_t pgtable; + pte_t *ptep; + + assert_spin_locked(&mm->page_table_lock); + + /* FIFO */ + pgtable = mm->pmd_huge_pte; + lh = (struct list_head *) pgtable; + if (list_empty(lh)) + mm->pmd_huge_pte = NULL; + else { + mm->pmd_huge_pte = (pgtable_t) lh->next; + list_del(lh); + } + ptep = (pte_t *) pgtable; + pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep++; + pte_val(*ptep) = _PAGE_TYPE_EMPTY; + return pgtable; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -- cgit v1.2.3 From 274023da1e8a49efa6fd9bf857f8557e5db44cdf Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 8 Oct 2012 16:30:21 -0700 Subject: thp, s390: disable thp for kvm host on s390 This patch is part of the architecture backend for thp on s390. It disables thp for kvm hosts, because there is no kvm host hugepage support so far. Existing thp mappings are split by follow_page() with FOLL_SPLIT, and future thp mappings are prevented by setting VM_NOHUGEPAGE in mm->def_flags. Signed-off-by: Gerald Schaefer Cc: Andrea Arcangeli Cc: Andi Kleen Cc: Hugh Dickins Cc: Hillf Danton Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/pgtable.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'arch/s390/mm/pgtable.c') diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 1ca371a06516..e86a523875eb 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -787,6 +787,30 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) tlb_table_flush(tlb); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +void thp_split_vma(struct vm_area_struct *vma) +{ + unsigned long addr; + struct page *page; + + for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) { + page = follow_page(vma, addr, FOLL_SPLIT); + } +} + +void thp_split_mm(struct mm_struct *mm) +{ + struct vm_area_struct *vma = mm->mmap; + + while (vma != NULL) { + thp_split_vma(vma); + vma->vm_flags &= ~VM_HUGEPAGE; + vma->vm_flags |= VM_NOHUGEPAGE; + vma = vma->vm_next; + } +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + /* * switch on pgstes for its userspace process (for kvm) */ @@ -824,6 +848,12 @@ int s390_enable_sie(void) if (!mm) return -ENOMEM; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* split thp mappings and disable thp for future mappings */ + thp_split_mm(mm); + mm->def_flags |= VM_NOHUGEPAGE; +#endif + /* Now lets check again if something happened */ task_lock(tsk); if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -- cgit v1.2.3 From 1ae1c1d09f220ded48ee9a7d91a65e94f95c4af1 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 8 Oct 2012 16:30:24 -0700 Subject: thp, s390: architecture backend for thp on s390 This implements the architecture backend for transparent hugepages on s390. Signed-off-by: Gerald Schaefer Cc: Andrea Arcangeli Cc: Andi Kleen Cc: Hugh Dickins Cc: Hillf Danton Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/pgtable.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'arch/s390/mm/pgtable.c') diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index e86a523875eb..c8188a18af05 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -898,6 +898,28 @@ bool kernel_page_present(struct page *page) #endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE +int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + /* No need to flush TLB + * On s390 reference bits are in storage key and never in TLB */ + return pmdp_test_and_clear_young(vma, address, pmdp); +} + +int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + + if (pmd_same(*pmdp, entry)) + return 0; + pmdp_invalidate(vma, address, pmdp); + set_pmd_at(vma->vm_mm, address, pmdp, entry); + return 1; +} + static void pmdp_splitting_flush_sync(void *arg) { /* Simply deliver the interrupt */ -- cgit v1.2.3