From 5835d87162afa8424c692a73a10ef5723dcc183b Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Tue, 17 Apr 2018 16:33:12 +0200 Subject: [PATCH] FROMLIST: mm: make pte_unmap_same compatible with SPF pte_unmap_same() is making the assumption that the page table are still around because the mmap_sem is held. This is no more the case when running a speculative page fault and additional check must be made to ensure that the final page table are still there. This is now done by calling pte_spinlock() to check for the VMA's consistency while locking for the page tables. This is requiring passing a vm_fault structure to pte_unmap_same() which is containing all the needed parameters. As pte_spinlock() may fail in the case of a speculative page fault, if the VMA has been touched in our back, pte_unmap_same() should now return 3 cases : 1. pte are the same (0) 2. pte are different (VM_FAULT_PTNOTSAME) 3. a VMA's changes has been detected (VM_FAULT_RETRY) The case 2 is handled by the introduction of a new VM_FAULT flag named VM_FAULT_PTNOTSAME which is then trapped in cow_user_page(). If VM_FAULT_RETRY is returned, it is passed up to the callers to retry the page fault while holding the mmap_sem. Change-Id: Iaccfa0d877334f4343f8b0ec3400af5070ff5864 Acked-by: David Rientjes Signed-off-by: Laurent Dufour Link: https://lore.kernel.org/lkml/1523975611-15978-7-git-send-email-ldufour@linux.vnet.ibm.com/ Bug: 161210518 Signed-off-by: Vinayak Menon Signed-off-by: Charan Teja Reddy --- include/linux/mm_types.h | 1 + mm/memory.c | 41 ++++++++++++++++++++++++++++------------ 2 files changed, 30 insertions(+), 12 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index dd00d12530c5..e092160e9361 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -735,6 +735,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_PTNOTSAME = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/mm/memory.c b/mm/memory.c index 501129e89f88..6044e52c63fd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2595,21 +2595,29 @@ EXPORT_SYMBOL_GPL(apply_to_existing_page_range); * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). + * + * pte_unmap_same() returns: + * 0 if the PTE are the same + * VM_FAULT_PTNOTSAME if the PTE are different + * VM_FAULT_RETRY if the VMA has changed in our back during + * a speculative page fault handling. */ -static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, - pte_t *page_table, pte_t orig_pte) +static inline int pte_unmap_same(struct vm_fault *vmf) { - int same = 1; -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) + int ret = 0; + +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) if (sizeof(pte_t) > sizeof(unsigned long)) { - spinlock_t *ptl = pte_lockptr(mm, pmd); - spin_lock(ptl); - same = pte_same(*page_table, orig_pte); - spin_unlock(ptl); + if (pte_spinlock(vmf)) { + if (!pte_same(*vmf->pte, vmf->orig_pte)) + ret = VM_FAULT_PTNOTSAME; + spin_unlock(vmf->ptl); + } else + ret = VM_FAULT_RETRY; } #endif - pte_unmap(page_table); - return same; + pte_unmap(vmf->pte); + return ret; } static inline bool cow_user_page(struct page *dst, struct page *src, @@ -3289,11 +3297,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) pte_t pte; int locked; int exclusive = 0; - vm_fault_t ret = 0; + vm_fault_t ret; void *shadow = NULL; - if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) + ret = pte_unmap_same(vmf); + if (ret) { + /* + * If pte != orig_pte, this means another thread did the + * swap operation in our back. + * So nothing else to do. + */ + if (ret == VM_FAULT_PTNOTSAME) + ret = 0; goto out; + } entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) {