From a1dbf20e8e1381f70d4a834db35371969db89edf Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Tue, 17 Apr 2018 16:33:22 +0200 Subject: [PATCH] FROMLIST: mm: introduce __page_add_new_anon_rmap() When dealing with speculative page fault handler, we may race with VMA being split or merged. In this case the vma->vm_start and vm->vm_end fields may not match the address the page fault is occurring. This can only happens when the VMA is split but in that case, the anon_vma pointer of the new VMA will be the same as the original one, because in __split_vma the new->anon_vma is set to src->anon_vma when *new = *vma. So even if the VMA boundaries are not correct, the anon_vma pointer is still valid. If the VMA has been merged, then the VMA in which it has been merged must have the same anon_vma pointer otherwise the merge can't be done. So in all the case we know that the anon_vma is valid, since we have checked before starting the speculative page fault that the anon_vma pointer is valid for this VMA and since there is an anon_vma this means that at one time a page has been backed and that before the VMA is cleaned, the page table lock would have to be grab to clean the PTE, and the anon_vma field is checked once the PTE is locked. This patch introduce a new __page_add_new_anon_rmap() service which doesn't check for the VMA boundaries, and create a new inline one which do the check. When called from a page fault handler, if this is not a speculative one, there is a guarantee that vm_start and vm_end match the faulting address, so this check is useless. In the context of the speculative page fault handler, this check may be wrong but anon_vma is still valid as explained above. Change-Id: I72c47830181579f8c9618df879077d321653b5f1 Signed-off-by: Laurent Dufour Link: https://lore.kernel.org/lkml/1523975611-15978-17-git-send-email-ldufour@linux.vnet.ibm.com/ Bug: 161210518 Signed-off-by: Vinayak Menon --- include/linux/rmap.h | 12 ++++++++++-- mm/memory.c | 8 ++++---- mm/rmap.c | 5 ++--- 3 files changed, 16 insertions(+), 9 deletions(-) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 70085ca1a3fc..96f68e7b510e 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -173,8 +173,16 @@ void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, int); -void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); +void __page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, + unsigned long address, bool compound); +static inline void page_add_new_anon_rmap(struct page *page, + struct vm_area_struct *vma, + unsigned long address, bool compound) +{ + VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); + __page_add_new_anon_rmap(page, vma, address, compound); +} + void page_add_file_rmap(struct page *, bool); void page_remove_rmap(struct page *, bool); diff --git a/mm/memory.c b/mm/memory.c index adde8624e7fe..019563c5d513 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2951,7 +2951,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); + __page_add_new_anon_rmap(new_page, vma, vmf->address, false); __lru_cache_add_inactive_or_unevictable(new_page, vmf->vma_flags); /* * We call the notify macro here because, when using secondary @@ -3494,7 +3494,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); + __page_add_new_anon_rmap(page, vma, vmf->address, false); __lru_cache_add_inactive_or_unevictable(page, vmf->vma_flags); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); @@ -3644,7 +3644,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); + __page_add_new_anon_rmap(page, vma, vmf->address, false); __lru_cache_add_inactive_or_unevictable(page, vmf->vma_flags); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3906,7 +3906,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) /* copy-on-write page */ if (write && !(vmf->vma_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); + __page_add_new_anon_rmap(page, vma, vmf->address, false); __lru_cache_add_inactive_or_unevictable(page, vmf->vma_flags); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); diff --git a/mm/rmap.c b/mm/rmap.c index 6657000b18d4..faeed19c8a89 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1156,7 +1156,7 @@ void do_page_add_anon_rmap(struct page *page, } /** - * page_add_new_anon_rmap - add pte mapping to a new anonymous page + * __page_add_new_anon_rmap - add pte mapping to a new anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped @@ -1166,12 +1166,11 @@ void do_page_add_anon_rmap(struct page *page, * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ -void page_add_new_anon_rmap(struct page *page, +void __page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { int nr = compound ? thp_nr_pages(page) : 1; - VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); __SetPageSwapBacked(page); if (compound) { VM_BUG_ON_PAGE(!PageTransHuge(page), page);