diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 34ea2002c4b8..c7ad4e0df464 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -189,6 +189,7 @@ config ARM64 select SWIOTLB select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK + select ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT help ARM 64-bit (AArch64) Linux support. diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index d26e6cd28953..cc221057a11c 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -406,10 +406,9 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re #define VM_FAULT_BADMAP 0x010000 #define VM_FAULT_BADACCESS 0x020000 -static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, +static int __do_page_fault(struct vm_area_struct *vma, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags) { - struct vm_area_struct *vma = find_vma(mm, addr); if (unlikely(!vma)) return VM_FAULT_BADMAP; @@ -456,6 +455,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, vm_fault_t fault, major = 0; unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + struct vm_area_struct *vma = NULL; if (kprobe_page_fault(regs, esr)) return 0; @@ -495,6 +495,14 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); + /* + * let's try a speculative page fault without grabbing the + * mmap_sem. + */ + fault = handle_speculative_fault(mm, addr, mm_flags, &vma); + if (fault != VM_FAULT_RETRY) + goto done; + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -519,7 +527,10 @@ retry: #endif } - fault = __do_page_fault(mm, addr, mm_flags, vm_flags); + if (!vma || !can_reuse_spf_vma(vma, addr)) + vma = find_vma(mm, addr); + + fault = __do_page_fault(vma, addr, mm_flags, vm_flags); major |= fault & VM_FAULT_MAJOR; if (fault & VM_FAULT_RETRY) { @@ -542,11 +553,20 @@ retry: if (mm_flags & FAULT_FLAG_ALLOW_RETRY) { mm_flags &= ~FAULT_FLAG_ALLOW_RETRY; mm_flags |= FAULT_FLAG_TRIED; + + /* + * Do not try to reuse this vma and fetch it + * again since we will release the mmap_sem. + */ + vma = NULL; + goto retry; } } up_read(&mm->mmap_sem); +done: + /* * Handle the "normal" (no error) case first. */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 32573b365d5d..350a1488ef13 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1277,8 +1277,11 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, goto out_mm; } for (vma = mm->mmap; vma; vma = vma->vm_next) { - vma->vm_flags &= ~VM_SOFTDIRTY; + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, + vma->vm_flags & ~VM_SOFTDIRTY); vma_set_page_prot(vma); + vm_write_end(vma); } downgrade_write(&mm->mmap_sem); break; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index ebf17d7e1093..ab846136c05c 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -675,8 +675,11 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) octx = vma->vm_userfaultfd_ctx.ctx; if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { + vm_write_begin(vma); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + WRITE_ONCE(vma->vm_flags, + vma->vm_flags & ~(VM_UFFD_WP | VM_UFFD_MISSING)); + vm_write_end(vma); return 0; } @@ -919,8 +922,10 @@ static int userfaultfd_release(struct inode *inode, struct file *file) else prev = vma; } - vma->vm_flags = new_flags; + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vm_write_end(vma); } up_write(&mm->mmap_sem); mmput(mm); @@ -1487,8 +1492,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, * the next vma was merged into the current one and * the current one has not been updated yet. */ - vma->vm_flags = new_flags; + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, new_flags); vma->vm_userfaultfd_ctx.ctx = ctx; + vm_write_end(vma); skip: prev = vma; @@ -1650,8 +1657,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, * the next vma was merged into the current one and * the current one has not been updated yet. */ - vma->vm_flags = new_flags; + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vm_write_end(vma); skip: prev = vma; diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h index 0660a03d37d9..9e25283d6fc9 100644 --- a/include/linux/hugetlb_inline.h +++ b/include/linux/hugetlb_inline.h @@ -8,7 +8,7 @@ static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma) { - return !!(vma->vm_flags & VM_HUGETLB); + return !!(READ_ONCE(vma->vm_flags) & VM_HUGETLB); } #else diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 72120061b7d4..8a7b150c2270 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -124,14 +124,14 @@ static inline void __ClearPageMovable(struct page *page) #ifdef CONFIG_NUMA_BALANCING extern bool pmd_trans_migrating(pmd_t pmd); extern int migrate_misplaced_page(struct page *page, - struct vm_area_struct *vma, int node); + struct vm_fault *vmf, int node); #else static inline bool pmd_trans_migrating(pmd_t pmd) { return false; } static inline int migrate_misplaced_page(struct page *page, - struct vm_area_struct *vma, int node) + struct vm_fault *vmf, int node) { return -EAGAIN; /* can't migrate now */ } diff --git a/include/linux/mm.h b/include/linux/mm.h index 1280985ae058..ef6de62a42a8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -393,6 +393,8 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */ #define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */ #define FAULT_FLAG_PREFAULT_OLD 0x400 /* Make faultaround ptes old */ +/* Speculative fault, not holding mmap_sem */ +#define FAULT_FLAG_SPECULATIVE 0x200 #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ @@ -421,6 +423,10 @@ struct vm_fault { gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + unsigned int sequence; + pmd_t orig_pmd; /* value of PMD at the time of fault */ +#endif pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching @@ -529,6 +535,15 @@ struct vm_operations_struct { unsigned long addr); }; +static inline void INIT_VMA(struct vm_area_struct *vma) +{ + INIT_LIST_HEAD(&vma->anon_vma_chain); +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + seqcount_init(&vma->vm_sequence); + atomic_set(&vma->vm_ref_count, 1); +#endif +} + static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; @@ -536,7 +551,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; - INIT_LIST_HEAD(&vma->anon_vma_chain); + INIT_VMA(vma); } static inline void vma_set_anonymous(struct vm_area_struct *vma) @@ -830,9 +845,9 @@ void free_compound_page(struct page *page); * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ -static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) +static inline pte_t maybe_mkwrite(pte_t pte, unsigned long vma_flags) { - if (likely(vma->vm_flags & VM_WRITE)) + if (likely(vma_flags & VM_WRITE)) pte = pte_mkwrite(pte); return pte; } @@ -1439,8 +1454,14 @@ struct zap_details { pgoff_t last_index; /* Highest page->index to unmap */ }; -struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte); +struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte, unsigned long vma_flags); +static inline struct page *vm_normal_page(struct vm_area_struct *vma, + unsigned long addr, pte_t pte) +{ + return _vm_normal_page(vma, addr, pte, vma->vm_flags); +} + struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); @@ -1467,6 +1488,47 @@ int follow_phys(struct vm_area_struct *vma, unsigned long address, int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT +static inline void vm_write_begin(struct vm_area_struct *vma) +{ + write_seqcount_begin(&vma->vm_sequence); +} +static inline void vm_write_begin_nested(struct vm_area_struct *vma, + int subclass) +{ + write_seqcount_begin_nested(&vma->vm_sequence, subclass); +} +static inline void vm_write_end(struct vm_area_struct *vma) +{ + write_seqcount_end(&vma->vm_sequence); +} +static inline void vm_raw_write_begin(struct vm_area_struct *vma) +{ + raw_write_seqcount_begin(&vma->vm_sequence); +} +static inline void vm_raw_write_end(struct vm_area_struct *vma) +{ + raw_write_seqcount_end(&vma->vm_sequence); +} +#else +static inline void vm_write_begin(struct vm_area_struct *vma) +{ +} +static inline void vm_write_begin_nested(struct vm_area_struct *vma, + int subclass) +{ +} +static inline void vm_write_end(struct vm_area_struct *vma) +{ +} +static inline void vm_raw_write_begin(struct vm_area_struct *vma) +{ +} +static inline void vm_raw_write_end(struct vm_area_struct *vma) +{ +} +#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */ + extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); @@ -1478,6 +1540,43 @@ int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags); + +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT +extern int __handle_speculative_fault(struct mm_struct *mm, + unsigned long address, + unsigned int flags, + struct vm_area_struct **vma); +static inline int handle_speculative_fault(struct mm_struct *mm, + unsigned long address, + unsigned int flags, + struct vm_area_struct **vma) +{ + /* + * Try speculative page fault for multithreaded user space task only. + */ + if (!(flags & FAULT_FLAG_USER) || atomic_read(&mm->mm_users) == 1) { + *vma = NULL; + return VM_FAULT_RETRY; + } + return __handle_speculative_fault(mm, address, flags, vma); +} +extern bool can_reuse_spf_vma(struct vm_area_struct *vma, + unsigned long address); +#else +static inline int handle_speculative_fault(struct mm_struct *mm, + unsigned long address, + unsigned int flags, + struct vm_area_struct **vma) +{ + return VM_FAULT_RETRY; +} +static inline bool can_reuse_spf_vma(struct vm_area_struct *vma, + unsigned long address) +{ + return false; +} +#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */ + extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); @@ -2276,16 +2375,29 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, - struct vm_area_struct *expand); + struct vm_area_struct *expand, bool keep_locked); static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { - return __vma_adjust(vma, start, end, pgoff, insert, NULL); + return __vma_adjust(vma, start, end, pgoff, insert, NULL, false); } -extern struct vm_area_struct *vma_merge(struct mm_struct *, + +extern struct vm_area_struct *__vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, - unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx, const char __user *); + unsigned long vm_flags, struct anon_vma *anon, struct file *file, + pgoff_t pgoff, struct mempolicy *mpol, struct vm_userfaultfd_ctx uff, + const char __user *user, bool keep_locked); + +static inline struct vm_area_struct *vma_merge(struct mm_struct *mm, + struct vm_area_struct *prev, unsigned long addr, unsigned long end, + unsigned long vm_flags, struct anon_vma *anon, struct file *file, + pgoff_t off, struct mempolicy *pol, struct vm_userfaultfd_ctx uff, + const char __user *user) +{ + return __vma_merge(mm, prev, addr, end, vm_flags, anon, file, off, + pol, uff, user, false); +} + extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 533d73c47c0f..e1c2d68bccd9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -361,7 +361,10 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; - +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + seqcount_t vm_sequence; + atomic_t vm_ref_count; /* see vma_get(), vma_put() */ +#endif ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); @@ -385,6 +388,9 @@ struct mm_struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; u64 vmacache_seqnum; /* per-thread vmacache */ +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + rwlock_t mm_rb_lock; +#endif #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, @@ -701,6 +707,7 @@ 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/include/linux/pagemap.h b/include/linux/pagemap.h index 60136487b584..63dd45eb1b9c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -456,8 +456,8 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, pgoff_t pgoff; if (unlikely(is_vm_hugetlb_page(vma))) return linear_hugepage_index(vma, address); - pgoff = (address - vma->vm_start) >> PAGE_SHIFT; - pgoff += vma->vm_pgoff; + pgoff = (address - READ_ONCE(vma->vm_start)) >> PAGE_SHIFT; + pgoff += READ_ONCE(vma->vm_pgoff); return pgoff; } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 4e5bf0925534..7268a54b8956 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -179,8 +179,16 @@ 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/include/linux/swap.h b/include/linux/swap.h index 063c0c1e112b..e5288634c38b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -344,8 +344,14 @@ extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); -extern void lru_cache_add_active_or_unevictable(struct page *page, - struct vm_area_struct *vma); +extern void __lru_cache_add_active_or_unevictable(struct page *page, + unsigned long vma_flags); + +static inline void lru_cache_add_active_or_unevictable(struct page *page, + struct vm_area_struct *vma) +{ + return __lru_cache_add_active_or_unevictable(page, vma->vm_flags); +} /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index d29dd5fef8d2..e92926552bba 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -113,6 +113,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, +#endif +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + SPECULATIVE_PGFAULT, #endif NR_VM_EVENT_ITEMS }; diff --git a/include/trace/events/pagefault.h b/include/trace/events/pagefault.h new file mode 100644 index 000000000000..a9643b3759f2 --- /dev/null +++ b/include/trace/events/pagefault.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM pagefault + +#if !defined(_TRACE_PAGEFAULT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGEFAULT_H + +#include +#include + +DECLARE_EVENT_CLASS(spf, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address), + + TP_STRUCT__entry( + __field(unsigned long, caller) + __field(unsigned long, vm_start) + __field(unsigned long, vm_end) + __field(unsigned long, address) + ), + + TP_fast_assign( + __entry->caller = caller; + __entry->vm_start = vma->vm_start; + __entry->vm_end = vma->vm_end; + __entry->address = address; + ), + + TP_printk("ip:%lx vma:%lx-%lx address:%lx", + __entry->caller, __entry->vm_start, __entry->vm_end, + __entry->address) +); + +DEFINE_EVENT(spf, spf_pte_lock, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_changed, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_noanon, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_notsup, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_vma_access, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +DEFINE_EVENT(spf, spf_pmd_changed, + + TP_PROTO(unsigned long caller, + struct vm_area_struct *vma, unsigned long address), + + TP_ARGS(caller, vma, address) +); + +#endif /* _TRACE_PAGEFAULT_H */ + +/* This part must be outside protection */ +#include diff --git a/kernel/fork.c b/kernel/fork.c index 5139510abbb0..21a50e7d55ec 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -362,7 +362,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) if (new) { *new = *orig; - INIT_LIST_HEAD(&new->anon_vma_chain); + INIT_VMA(new); } return new; } @@ -486,7 +486,7 @@ EXPORT_SYMBOL(free_task); static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { - struct vm_area_struct *mpnt, *tmp, *prev, **pprev; + struct vm_area_struct *mpnt, *tmp, *prev, **pprev, *last = NULL; struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; @@ -605,8 +605,18 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, rb_parent = &tmp->vm_rb; mm->map_count++; - if (!(tmp->vm_flags & VM_WIPEONFORK)) + if (!(tmp->vm_flags & VM_WIPEONFORK)) { + if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT)) { + /* + * Mark this VMA as changing to prevent the + * speculative page fault hanlder to process + * it until the TLB are flushed below. + */ + last = mpnt; + vm_write_begin(mpnt); + } retval = copy_page_range(mm, oldmm, mpnt); + } if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); @@ -619,6 +629,22 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); + + if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT)) { + /* + * Since the TLB has been flush, we can safely unmark the + * copied VMAs and allows the speculative page fault handler to + * process them again. + * Walk back the VMA list from the last marked VMA. + */ + for (; last; last = last->vm_prev) { + if (last->vm_flags & VM_DONTCOPY) + continue; + if (!(last->vm_flags & VM_WIPEONFORK)) + vm_write_end(last); + } + } + up_write(&oldmm->mmap_sem); dup_userfaultfd_complete(&uf); fail_uprobe_end: @@ -1028,6 +1054,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->mmap = NULL; mm->mm_rb = RB_ROOT; mm->vmacache_seqnum = 0; +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + rwlock_init(&mm->mm_rb_lock); +#endif atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c4ebfcd93721..4683d83123ec 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1268,8 +1268,8 @@ static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { pte_t entry; - entry = mk_pte(pages[i], vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + entry = mk_pte(pages[i], vmf->vma_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags); memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); page_add_new_anon_rmap(pages[i], vmf->vma, haddr, false); @@ -2252,7 +2252,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_swp_mksoft_dirty(entry); } else { entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); - entry = maybe_mkwrite(entry, vma); + entry = maybe_mkwrite(entry, vma->vm_flags); if (!write) entry = pte_wrprotect(entry); if (!young) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 66ee1a894546..1a7f0890cf58 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3950,6 +3950,8 @@ retry: .vma = vma, .address = haddr, .flags = flags, + .vma_flags = vma->vm_flags, + .vma_page_prot = vma->vm_page_prot, /* * Hard to debug if it ends up being * used by a callee that assumes diff --git a/mm/init-mm.c b/mm/init-mm.c index 19603302a77f..0a4abdcf8886 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -28,6 +28,9 @@ */ struct mm_struct init_mm = { .mm_rb = RB_ROOT, +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + .mm_rb_lock = __RW_LOCK_UNLOCKED(init_mm.mm_rb_lock), +#endif .pgd = swapper_pg_dir, .mm_users = ATOMIC_INIT(2), .mm_count = ATOMIC_INIT(1), diff --git a/mm/internal.h b/mm/internal.h index 7dd7fbb577a9..d5dd3549559d 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -36,6 +36,26 @@ void page_writeback_init(void); vm_fault_t do_swap_page(struct vm_fault *vmf); +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT +extern struct vm_area_struct *get_vma(struct mm_struct *mm, + unsigned long addr); +extern void put_vma(struct vm_area_struct *vma); + +static inline bool vma_has_changed(struct vm_fault *vmf) +{ + int ret = RB_EMPTY_NODE(&vmf->vma->vm_rb); + unsigned int seq = READ_ONCE(vmf->vma->vm_sequence.sequence); + + /* + * Matches both the wmb in write_seqlock_{begin,end}() and + * the wmb in vma_rb_erase(). + */ + smp_rmb(); + + return ret || seq != vmf->sequence; +} +#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */ + void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a8a57bebb5fa..8e5007f724ec 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -900,6 +900,8 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm, .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, .pgoff = linear_page_index(vma, address), + .vma_flags = vma->vm_flags, + .vma_page_prot = vma->vm_page_prot, }; /* we only decide to swapin, if there is enough young ptes */ @@ -1026,6 +1028,7 @@ static void collapse_huge_page(struct mm_struct *mm, if (mm_find_pmd(mm, address) != pmd) goto out; + vm_write_begin(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, @@ -1062,6 +1065,7 @@ static void collapse_huge_page(struct mm_struct *mm, pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); + vm_write_end(vma); result = SCAN_FAIL; goto out; } @@ -1097,6 +1101,7 @@ static void collapse_huge_page(struct mm_struct *mm, set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); spin_unlock(pmd_ptl); + vm_write_end(vma); *hpage = NULL; diff --git a/mm/madvise.c b/mm/madvise.c index 637ae9183e82..b85bfe989984 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -171,7 +171,9 @@ success: /* * vm_flags is protected by the mmap_sem held in write mode. */ - vma->vm_flags = new_flags; + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, new_flags); + vm_write_end(vma); out_convert_errno: /* @@ -495,9 +497,11 @@ static void madvise_cold_page_range(struct mmu_gather *tlb, .target_task = task, }; + vm_write_begin(vma); tlb_start_vma(tlb, vma); walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); + vm_write_end(vma); } static long madvise_cold(struct task_struct *task, @@ -531,9 +535,11 @@ static void madvise_pageout_page_range(struct mmu_gather *tlb, .target_task = task, }; + vm_write_begin(vma); tlb_start_vma(tlb, vma); walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); + vm_write_end(vma); } static inline bool can_do_pageout(struct vm_area_struct *vma) @@ -736,10 +742,12 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); + vm_write_begin(vma); tlb_start_vma(&tlb, vma); walk_page_range(vma->vm_mm, range.start, range.end, &madvise_free_walk_ops, &tlb); tlb_end_vma(&tlb, vma); + vm_write_end(vma); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, range.start, range.end); diff --git a/mm/memory.c b/mm/memory.c index 65a527f11b36..b68c3e2356d6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -84,6 +84,9 @@ #include "internal.h" +#define CREATE_TRACE_POINTS +#include + #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif @@ -397,7 +400,9 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ + vm_write_begin(vma); unlink_anon_vmas(vma); + vm_write_end(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { @@ -411,7 +416,9 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; + vm_write_begin(vma); unlink_anon_vmas(vma); + vm_write_end(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, @@ -538,7 +545,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", - (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); + (void *)addr, READ_ONCE(vma->vm_flags), vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, @@ -549,7 +556,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, } /* - * vm_normal_page -- This function gets the "struct page" associated with a pte. + * __vm_normal_page -- This function gets the "struct page" associated with + * a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this @@ -590,8 +598,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, * PFNMAP mappings in order to support COWable mappings. * */ -struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte) +struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte, unsigned long vma_flags) { unsigned long pfn = pte_pfn(pte); @@ -600,7 +608,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); - if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + if (vma_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; @@ -612,9 +620,13 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ + /* + * This part should never get called when CONFIG_SPECULATIVE_PAGE_FAULT + * is set. This is mainly because we can't rely on vm_start. + */ - if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { - if (vma->vm_flags & VM_MIXEDMAP) { + if (unlikely(vma_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; @@ -623,7 +635,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; - if (!is_cow_mapping(vma->vm_flags)) + if (!is_cow_mapping(vma_flags)) return NULL; } } @@ -1247,6 +1259,7 @@ void unmap_page_range(struct mmu_gather *tlb, unsigned long next; BUG_ON(addr >= end); + vm_write_begin(vma); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { @@ -1256,6 +1269,7 @@ void unmap_page_range(struct mmu_gather *tlb, next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); + vm_write_end(vma); } @@ -1624,7 +1638,8 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, goto out_unlock; } entry = pte_mkyoung(*pte); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + entry = maybe_mkwrite(pte_mkdirty(entry), + vma->vm_flags); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } @@ -1639,7 +1654,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (mkwrite) { entry = pte_mkyoung(entry); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + entry = maybe_mkwrite(pte_mkdirty(entry), vma->vm_flags); } set_pte_at(mm, addr, pte, entry); @@ -2140,6 +2155,141 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL_GPL(apply_to_page_range); +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT +static bool pte_spinlock(struct vm_fault *vmf) +{ + bool ret = false; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + pmd_t pmdval; +#endif + + /* Check if vma is still valid */ + if (!(vmf->flags & FAULT_FLAG_SPECULATIVE)) { + vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); + spin_lock(vmf->ptl); + return true; + } + + local_irq_disable(); + if (vma_has_changed(vmf)) { + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); + goto out; + } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* + * We check if the pmd value is still the same to ensure that there + * is not a huge collapse operation in progress in our back. + */ + pmdval = READ_ONCE(*vmf->pmd); + if (!pmd_same(pmdval, vmf->orig_pmd)) { + trace_spf_pmd_changed(_RET_IP_, vmf->vma, vmf->address); + goto out; + } +#endif + + vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); + if (unlikely(!spin_trylock(vmf->ptl))) { + trace_spf_pte_lock(_RET_IP_, vmf->vma, vmf->address); + goto out; + } + + if (vma_has_changed(vmf)) { + spin_unlock(vmf->ptl); + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); + goto out; + } + + ret = true; +out: + local_irq_enable(); + return ret; +} + +static bool pte_map_lock(struct vm_fault *vmf) +{ + bool ret = false; + pte_t *pte; + spinlock_t *ptl; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + pmd_t pmdval; +#endif + + if (!(vmf->flags & FAULT_FLAG_SPECULATIVE)) { + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + return true; + } + + /* + * The first vma_has_changed() guarantees the page-tables are still + * valid, having IRQs disabled ensures they stay around, hence the + * second vma_has_changed() to make sure they are still valid once + * we've got the lock. After that a concurrent zap_pte_range() will + * block on the PTL and thus we're safe. + */ + local_irq_disable(); + if (vma_has_changed(vmf)) { + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); + goto out; + } + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* + * We check if the pmd value is still the same to ensure that there + * is not a huge collapse operation in progress in our back. + */ + pmdval = READ_ONCE(*vmf->pmd); + if (!pmd_same(pmdval, vmf->orig_pmd)) { + trace_spf_pmd_changed(_RET_IP_, vmf->vma, vmf->address); + goto out; + } +#endif + + /* + * Same as pte_offset_map_lock() except that we call + * spin_trylock() in place of spin_lock() to avoid race with + * unmap path which may have the lock and wait for this CPU + * to invalidate TLB but this CPU has irq disabled. + * Since we are in a speculative patch, accept it could fail + */ + ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); + pte = pte_offset_map(vmf->pmd, vmf->address); + if (unlikely(!spin_trylock(ptl))) { + pte_unmap(pte); + trace_spf_pte_lock(_RET_IP_, vmf->vma, vmf->address); + goto out; + } + + if (vma_has_changed(vmf)) { + pte_unmap_unlock(pte, ptl); + trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); + goto out; + } + + vmf->pte = pte; + vmf->ptl = ptl; + ret = true; +out: + local_irq_enable(); + return ret; +} +#else +static inline bool pte_spinlock(struct vm_fault *vmf) +{ + vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); + spin_lock(vmf->ptl); + return true; +} + +static inline bool pte_map_lock(struct vm_fault *vmf) +{ + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + return true; +} +#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */ + /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures @@ -2147,21 +2297,29 @@ EXPORT_SYMBOL_GPL(apply_to_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; + 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 void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) @@ -2315,7 +2473,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf) flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -2347,25 +2505,26 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) int page_copied = 0; struct mem_cgroup *memcg; struct mmu_notifier_range range; + int ret = VM_FAULT_OOM; if (unlikely(anon_vma_prepare(vma))) - goto oom; + goto out; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!new_page) - goto oom; + goto out; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!new_page) - goto oom; + goto out; cow_user_page(new_page, old_page, vmf->address, vma); } if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) - goto oom_free_new; + goto out_free_new; __SetPageUptodate(new_page); @@ -2377,7 +2536,10 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) /* * Re-check the pte - we dropped the lock */ - vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); + if (!pte_map_lock(vmf)) { + ret = VM_FAULT_RETRY; + goto out_uncharge; + } if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { @@ -2389,8 +2551,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); - entry = mk_pte(new_page, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + entry = mk_pte(new_page, vmf->vma_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags); /* * Clear the pte entry and flush it first, before updating the * pte with the new entry. This will avoid a race condition @@ -2398,9 +2560,9 @@ 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); mem_cgroup_commit_charge(new_page, memcg, false, false); - lru_cache_add_active_or_unevictable(new_page, vma); + __lru_cache_add_active_or_unevictable(new_page, vmf->vma_flags); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the @@ -2455,7 +2617,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ - if (page_copied && (vma->vm_flags & VM_LOCKED)) { + if (page_copied && (vmf->vma_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ if (PageMlocked(old_page)) munlock_vma_page(old_page); @@ -2464,12 +2626,14 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; -oom_free_new: +out_uncharge: + mem_cgroup_cancel_charge(new_page, memcg, false); +out_free_new: put_page(new_page); -oom: +out: if (old_page) put_page(old_page); - return VM_FAULT_OOM; + return ret; } /** @@ -2490,9 +2654,9 @@ oom: */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) { - WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); - vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + WARN_ON_ONCE(!(vmf->vma_flags & VM_SHARED)); + if (!pte_map_lock(vmf)) + return VM_FAULT_RETRY; /* * We might have raced with another page fault while we released the * pte_offset_map_lock. @@ -2584,7 +2748,8 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); + vmf->page = _vm_normal_page(vma, vmf->address, vmf->orig_pte, + vmf->vma_flags); if (!vmf->page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a @@ -2593,7 +2758,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ - if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + if ((vmf->vma_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) return wp_pfn_shared(vmf); @@ -2614,8 +2779,11 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); lock_page(vmf->page); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + if (!pte_map_lock(vmf)) { + unlock_page(vmf->page); + put_page(vmf->page); + return VM_FAULT_RETRY; + } if (!pte_same(*vmf->pte, vmf->orig_pte)) { unlock_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -2649,7 +2817,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) return VM_FAULT_WRITE; } unlock_page(vmf->page); - } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + } else if (unlikely((vmf->vma_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } @@ -2776,10 +2944,19 @@ 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; - 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))) { @@ -2818,6 +2995,17 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) lru_cache_add_anon(page); swap_readpage(page, true); } + } else if (vmf->flags & FAULT_FLAG_SPECULATIVE) { + /* + * Don't try readahead during a speculative page fault + * as the VMA's boundaries may change in our back. + * If the page is not in the swap cache and synchronous + * read is disabled, fall back to the regular page fault + * mechanism. + */ + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + ret = VM_FAULT_RETRY; + goto out; } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); @@ -2826,11 +3014,16 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!page) { /* - * Back out if somebody else faulted in this pte - * while we released the pte lock. + * Back out if the VMA has changed in our back during + * a speculative page fault or if somebody else + * faulted in this pte while we released the pte lock. */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + if (!pte_map_lock(vmf)) { + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + ret = VM_FAULT_RETRY; + goto out; + } + if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); @@ -2883,10 +3076,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) } /* - * Back out if somebody else already faulted in this pte. + * Back out if the VMA has changed in our back during a speculative + * page fault or if somebody else already faulted in this pte. */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + if (!pte_map_lock(vmf)) { + ret = VM_FAULT_RETRY; + goto out_cancel_cgroup; + } if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; @@ -2907,9 +3103,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); - pte = mk_pte(page, vma->vm_page_prot); + pte = mk_pte(page, vmf->vma_page_prot); if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { - pte = maybe_mkwrite(pte_mkdirty(pte), vma); + pte = maybe_mkwrite(pte_mkdirty(pte), vmf->vma_flags); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; @@ -2923,9 +3119,9 @@ 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); mem_cgroup_commit_charge(page, memcg, false, false); - lru_cache_add_active_or_unevictable(page, vma); + __lru_cache_add_active_or_unevictable(page, vmf->vma_flags); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); mem_cgroup_commit_charge(page, memcg, true, false); @@ -2934,7 +3130,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) swap_free(entry); if (mem_cgroup_swap_full(page) || - (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) + (vmf->vma_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache && swapcache) { @@ -2964,8 +3160,9 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg, false); pte_unmap_unlock(vmf->pte, vmf->ptl); +out_cancel_cgroup: + mem_cgroup_cancel_charge(page, memcg, false); out_page: unlock_page(page); out_release: @@ -2991,7 +3188,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) pte_t entry; /* File mapping without ->vm_ops ? */ - if (vma->vm_flags & VM_SHARED) + if (vmf->vma_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* @@ -3015,14 +3212,22 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), - vma->vm_page_prot)); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + vmf->vma_page_prot)); + if (!pte_map_lock(vmf)) + return VM_FAULT_RETRY; if (!pte_none(*vmf->pte)) goto unlock; ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; + /* + * Don't call the userfaultfd during the speculative path. + * We already checked for the VMA to not be managed through + * userfaultfd, but it may be set in our back once we have lock + * the pte. In such a case we can ignore it this time. + */ + if (vmf->flags & FAULT_FLAG_SPECULATIVE) + goto setpte; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -3049,21 +3254,24 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) */ __SetPageUptodate(page); - entry = mk_pte(page, vma->vm_page_prot); - if (vma->vm_flags & VM_WRITE) + entry = mk_pte(page, vmf->vma_page_prot); + if (vmf->vma_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); - if (!pte_none(*vmf->pte)) + if (!pte_map_lock(vmf)) { + ret = VM_FAULT_RETRY; goto release; + } + if (!pte_none(*vmf->pte)) + goto unlock_and_release; ret = check_stable_address_space(vma->vm_mm); if (ret) - goto release; + goto unlock_and_release; /* Deliver the page fault to userland, check inside PT lock */ - if (userfaultfd_missing(vma)) { + if (!(vmf->flags & FAULT_FLAG_SPECULATIVE) && + userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); mem_cgroup_cancel_charge(page, memcg, false); put_page(page); @@ -3071,9 +3279,9 @@ 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); mem_cgroup_commit_charge(page, memcg, false, false); - lru_cache_add_active_or_unevictable(page, vma); + __lru_cache_add_active_or_unevictable(page, vmf->vma_flags); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3082,10 +3290,12 @@ setpte: unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; +unlock_and_release: + pte_unmap_unlock(vmf->pte, vmf->ptl); release: mem_cgroup_cancel_charge(page, memcg, false); put_page(page); - goto unlock; + return ret; oom_free_page: put_page(page); oom: @@ -3160,7 +3370,7 @@ static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - if (!pmd_none(*vmf->pmd)) + if (!pmd_none(*vmf->pmd) || (vmf->flags & FAULT_FLAG_SPECULATIVE)) goto map_pte; if (vmf->prealloc_pte) { vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); @@ -3200,8 +3410,9 @@ map_pte: * pte_none() under vmf->ptl protection when we return to * alloc_set_pte(). */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + if (!pte_map_lock(vmf)) + return VM_FAULT_RETRY; + return 0; } @@ -3252,7 +3463,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) for (i = 0; i < HPAGE_PMD_NR; i++) flush_icache_page(vma, page + i); - entry = mk_huge_pmd(page, vma->vm_page_prot); + entry = mk_huge_pmd(page, vmf->vma_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); @@ -3328,19 +3539,19 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, return VM_FAULT_NOPAGE; flush_icache_page(vma, page); - entry = mk_pte(page, vma->vm_page_prot); + entry = mk_pte(page, vmf->vma_page_prot); if (write) - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + entry = maybe_mkwrite(pte_mkdirty(entry), vmf->vma_flags); if (vmf->flags & FAULT_FLAG_PREFAULT_OLD) entry = pte_mkold(entry); /* copy-on-write page */ - if (write && !(vma->vm_flags & VM_SHARED)) { + 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); mem_cgroup_commit_charge(page, memcg, false, false); - lru_cache_add_active_or_unevictable(page, vma); + __lru_cache_add_active_or_unevictable(page, vmf->vma_flags); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); @@ -3376,7 +3587,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf) /* Did we COW the page? */ if ((vmf->flags & FAULT_FLAG_WRITE) && - !(vmf->vma->vm_flags & VM_SHARED)) + !(vmf->vma_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; @@ -3655,7 +3866,7 @@ static vm_fault_t do_fault(struct vm_fault *vmf) } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); - else if (!(vma->vm_flags & VM_SHARED)) + else if (!(vmf->vma_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); @@ -3700,8 +3911,8 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * validation through pte_unmap_same(). It's of NUMA type but * the pfn may be screwed if the read is non atomic. */ - vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); - spin_lock(vmf->ptl); + if (!pte_spinlock(vmf)) + return VM_FAULT_RETRY; if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); goto out; @@ -3712,14 +3923,14 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * accessible ptes, some can allow access by kernel mode. */ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); - pte = pte_modify(old_pte, vma->vm_page_prot); + pte = pte_modify(old_pte, vmf->vma_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); - page = vm_normal_page(vma, vmf->address, pte); + page = _vm_normal_page(vma, vmf->address, pte, vmf->vma_flags); if (!page) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; @@ -3746,7 +3957,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * Flag if the page is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ - if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) + if (page_mapcount(page) > 1 && (vmf->vma_flags & VM_SHARED)) flags |= TNF_SHARED; last_cpupid = page_cpupid_last(page); @@ -3760,7 +3971,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) } /* Migrate to the requested node */ - migrated = migrate_misplaced_page(page, vma, target_nid); + migrated = migrate_misplaced_page(page, vmf, target_nid); if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; @@ -3791,7 +4002,7 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); /* COW handled on pte level: split pmd */ - VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma); + VM_BUG_ON_VMA(vmf->vma_flags & VM_SHARED, vmf->vma); __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; @@ -3846,6 +4057,15 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { + /* + * In the case of the speculative page fault handler we abort + * the speculative path immediately as the pmd is probably + * in the way to be converted in a huge one. We will try + * again holding the mmap_sem (which implies that the collapse + * operation is done). + */ + if (vmf->flags & FAULT_FLAG_SPECULATIVE) + return VM_FAULT_RETRY; /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table @@ -3853,7 +4073,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) * concurrent faults and from rmap lookups. */ vmf->pte = NULL; - } else { + } else if (!(vmf->flags & FAULT_FLAG_SPECULATIVE)) { /* See comment in pte_alloc_one_map() */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; @@ -3862,6 +4082,9 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) * pmd from under us anymore at this point because we hold the * mmap_sem read mode and khugepaged takes it in write mode. * So now it's safe to run pte_offset_map(). + * This is not applicable to the speculative page fault handler + * but in that case, the pte is fetched earlier in + * handle_speculative_fault(). */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; @@ -3884,6 +4107,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) if (!vmf->pte) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); + else if (vmf->flags & FAULT_FLAG_SPECULATIVE) + return VM_FAULT_RETRY; else return do_fault(vmf); } @@ -3894,8 +4119,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); - vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); - spin_lock(vmf->ptl); + if (!pte_spinlock(vmf)) + return VM_FAULT_RETRY; entry = vmf->orig_pte; if (unlikely(!pte_same(*vmf->pte, entry))) goto unlock; @@ -3938,6 +4163,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), + .vma_flags = vma->vm_flags, + .vma_page_prot = vma->vm_page_prot, }; unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; @@ -3979,6 +4206,10 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; + +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + vmf.sequence = raw_read_seqcount(&vma->vm_sequence); +#endif if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) @@ -4012,6 +4243,260 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, return handle_pte_fault(&vmf); } +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + +#ifndef CONFIG_ARCH_HAS_PTE_SPECIAL +/* This is required by vm_normal_page() */ +#error "Speculative page fault handler requires CONFIG_ARCH_HAS_PTE_SPECIAL" +#endif +/* + * vm_normal_page() adds some processing which should be done while + * hodling the mmap_sem. + */ + +/* + * Tries to handle the page fault in a speculative way, without grabbing the + * mmap_sem. + * When VM_FAULT_RETRY is returned, the vma pointer is valid and this vma must + * be checked later when the mmap_sem has been grabbed by calling + * can_reuse_spf_vma(). + * This is needed as the returned vma is kept in memory until the call to + * can_reuse_spf_vma() is made. + */ +int __handle_speculative_fault(struct mm_struct *mm, unsigned long address, + unsigned int flags, struct vm_area_struct **vma) +{ + struct vm_fault vmf = { + .address = address, + }; + pgd_t *pgd, pgdval; + p4d_t *p4d, p4dval; + pud_t pudval; + int seq, ret; + + /* Clear flags that may lead to release the mmap_sem to retry */ + flags &= ~(FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_KILLABLE); + flags |= FAULT_FLAG_SPECULATIVE; + + *vma = get_vma(mm, address); + if (!*vma) + return VM_FAULT_RETRY; + vmf.vma = *vma; + + /* rmb <-> seqlock,vma_rb_erase() */ + seq = raw_read_seqcount(&vmf.vma->vm_sequence); + if (seq & 1) { + trace_spf_vma_changed(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } + + /* + * Can't call vm_ops service has we don't know what they would do + * with the VMA. + * This include huge page from hugetlbfs. + */ + if (vmf.vma->vm_ops) { + trace_spf_vma_notsup(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } + + /* + * __anon_vma_prepare() requires the mmap_sem to be held + * because vm_next and vm_prev must be safe. This can't be guaranteed + * in the speculative path. + */ + if (unlikely(!vmf.vma->anon_vma)) { + trace_spf_vma_notsup(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } + + vmf.vma_flags = READ_ONCE(vmf.vma->vm_flags); + vmf.vma_page_prot = READ_ONCE(vmf.vma->vm_page_prot); + + /* Can't call userland page fault handler in the speculative path */ + if (unlikely(vmf.vma_flags & VM_UFFD_MISSING)) { + trace_spf_vma_notsup(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } + + if (vmf.vma_flags & VM_GROWSDOWN || vmf.vma_flags & VM_GROWSUP) { + /* + * This could be detected by the check address against VMA's + * boundaries but we want to trace it as not supported instead + * of changed. + */ + trace_spf_vma_notsup(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } + + if (address < READ_ONCE(vmf.vma->vm_start) + || READ_ONCE(vmf.vma->vm_end) <= address) { + trace_spf_vma_changed(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } + + if (!arch_vma_access_permitted(vmf.vma, flags & FAULT_FLAG_WRITE, + flags & FAULT_FLAG_INSTRUCTION, + flags & FAULT_FLAG_REMOTE)) + goto out_segv; + + /* This is one is required to check that the VMA has write access set */ + if (flags & FAULT_FLAG_WRITE) { + if (unlikely(!(vmf.vma_flags & VM_WRITE))) + goto out_segv; + } else if (unlikely(!(vmf.vma_flags & (VM_READ|VM_EXEC|VM_WRITE)))) + goto out_segv; + +#ifdef CONFIG_NUMA + struct mempolicy *pol; + + /* + * MPOL_INTERLEAVE implies additional checks in + * mpol_misplaced() which are not compatible with the + *speculative page fault processing. + */ + pol = __get_vma_policy(vmf.vma, address); + if (!pol) + pol = get_task_policy(current); + if (!pol) + if (pol && pol->mode == MPOL_INTERLEAVE) { + trace_spf_vma_notsup(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } +#endif + + /* + * Do a speculative lookup of the PTE entry. + */ + local_irq_disable(); + pgd = pgd_offset(mm, address); + pgdval = READ_ONCE(*pgd); + if (pgd_none(pgdval) || unlikely(pgd_bad(pgdval))) + goto out_walk; + + p4d = p4d_offset(pgd, address); + p4dval = READ_ONCE(*p4d); + if (p4d_none(p4dval) || unlikely(p4d_bad(p4dval))) + goto out_walk; + + vmf.pud = pud_offset(p4d, address); + pudval = READ_ONCE(*vmf.pud); + if (pud_none(pudval) || unlikely(pud_bad(pudval))) + goto out_walk; + + /* Huge pages at PUD level are not supported. */ + if (unlikely(pud_trans_huge(pudval))) + goto out_walk; + + vmf.pmd = pmd_offset(vmf.pud, address); + vmf.orig_pmd = READ_ONCE(*vmf.pmd); + /* + * pmd_none could mean that a hugepage collapse is in progress + * in our back as collapse_huge_page() mark it before + * invalidating the pte (which is done once the IPI is catched + * by all CPU and we have interrupt disabled). + * For this reason we cannot handle THP in a speculative way since we + * can't safely indentify an in progress collapse operation done in our + * back on that PMD. + * Regarding the order of the following checks, see comment in + * pmd_devmap_trans_unstable() + */ + if (unlikely(pmd_devmap(vmf.orig_pmd) || + pmd_none(vmf.orig_pmd) || pmd_trans_huge(vmf.orig_pmd) || + is_swap_pmd(vmf.orig_pmd))) + goto out_walk; + + /* + * The above does not allocate/instantiate page-tables because doing so + * would lead to the possibility of instantiating page-tables after + * free_pgtables() -- and consequently leaking them. + * + * The result is that we take at least one !speculative fault per PMD + * in order to instantiate it. + */ + + vmf.pte = pte_offset_map(vmf.pmd, address); + vmf.orig_pte = READ_ONCE(*vmf.pte); + barrier(); /* See comment in handle_pte_fault() */ + if (pte_none(vmf.orig_pte)) { + pte_unmap(vmf.pte); + vmf.pte = NULL; + } + + vmf.pgoff = linear_page_index(vmf.vma, address); + vmf.gfp_mask = __get_fault_gfp_mask(vmf.vma); + vmf.sequence = seq; + vmf.flags = flags; + + local_irq_enable(); + + /* + * We need to re-validate the VMA after checking the bounds, otherwise + * we might have a false positive on the bounds. + */ + if (read_seqcount_retry(&vmf.vma->vm_sequence, seq)) { + trace_spf_vma_changed(_RET_IP_, vmf.vma, address); + return VM_FAULT_RETRY; + } + + mem_cgroup_enter_user_fault(); + ret = handle_pte_fault(&vmf); + mem_cgroup_exit_user_fault(); + + /* + * If there is no need to retry, don't return the vma to the caller. + */ + if (ret != VM_FAULT_RETRY) { + count_vm_event(SPECULATIVE_PGFAULT); + put_vma(vmf.vma); + *vma = NULL; + } + + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); + return ret; + +out_walk: + trace_spf_vma_notsup(_RET_IP_, vmf.vma, address); + local_irq_enable(); + return VM_FAULT_RETRY; + +out_segv: + trace_spf_vma_access(_RET_IP_, vmf.vma, address); + /* + * We don't return VM_FAULT_RETRY so the caller is not expected to + * retrieve the fetched VMA. + */ + put_vma(vmf.vma); + *vma = NULL; + return VM_FAULT_SIGSEGV; +} + +/* + * This is used to know if the vma fetch in the speculative page fault handler + * is still valid when trying the regular fault path while holding the + * mmap_sem. + * The call to put_vma(vma) must be made after checking the vma's fields, as + * the vma may be freed by put_vma(). In such a case it is expected that false + * is returned. + */ +bool can_reuse_spf_vma(struct vm_area_struct *vma, unsigned long address) +{ + bool ret; + + ret = !RB_EMPTY_NODE(&vma->vm_rb) && + vma->vm_start <= address && address < vma->vm_end; + put_vma(vma); + return ret; +} +#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */ + /* * By the time we get here, we already hold the mm semaphore * diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4c60ba571c8e..1e0e7279da77 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -380,8 +380,11 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) struct vm_area_struct *vma; down_write(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) + for (vma = mm->mmap; vma; vma = vma->vm_next) { + vm_write_begin(vma); mpol_rebind_policy(vma->vm_policy, new); + vm_write_end(vma); + } up_write(&mm->mmap_sem); } @@ -596,9 +599,11 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, { int nr_updated; + vm_write_begin(vma); nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1); if (nr_updated) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); + vm_write_end(vma); return nr_updated; } @@ -711,6 +716,7 @@ static int vma_replace_policy(struct vm_area_struct *vma, if (IS_ERR(new)) return PTR_ERR(new); + vm_write_begin(vma); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) @@ -718,11 +724,17 @@ static int vma_replace_policy(struct vm_area_struct *vma, } old = vma->vm_policy; - vma->vm_policy = new; /* protected by mmap_sem */ + /* + * The speculative page fault handler accesses this field without + * hodling the mmap_sem. + */ + WRITE_ONCE(vma->vm_policy, new); + vm_write_end(vma); mpol_put(old); return 0; err_out: + vm_write_end(vma); mpol_put(new); return err; } @@ -1703,23 +1715,28 @@ COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { - struct mempolicy *pol = NULL; + struct mempolicy *pol; - if (vma) { - if (vma->vm_ops && vma->vm_ops->get_policy) { - pol = vma->vm_ops->get_policy(vma, addr); - } else if (vma->vm_policy) { - pol = vma->vm_policy; + if (!vma) + return NULL; - /* - * shmem_alloc_page() passes MPOL_F_SHARED policy with - * a pseudo vma whose vma->vm_ops=NULL. Take a reference - * count on these policies which will be dropped by - * mpol_cond_put() later - */ - if (mpol_needs_cond_ref(pol)) - mpol_get(pol); - } + if (vma->vm_ops && vma->vm_ops->get_policy) + return vma->vm_ops->get_policy(vma, addr); + + /* + * This could be called without holding the mmap_sem in the + * speculative page fault handler's path. + */ + pol = READ_ONCE(vma->vm_policy); + if (pol) { + /* + * shmem_alloc_page() passes MPOL_F_SHARED policy with + * a pseudo vma whose vma->vm_ops=NULL. Take a reference + * count on these policies which will be dropped by + * mpol_cond_put() later + */ + if (mpol_needs_cond_ref(pol)) + mpol_get(pol); } return pol; diff --git a/mm/migrate.c b/mm/migrate.c index 6bb39c65c9cc..f5b5376b6624 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -241,7 +241,7 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, */ entry = pte_to_swp_entry(*pvmw.pte); if (is_write_migration_entry(entry)) - pte = maybe_mkwrite(pte, vma); + pte = maybe_mkwrite(pte, vma->vm_flags); if (unlikely(is_zone_device_page(new))) { if (is_device_private_page(new)) { @@ -1968,7 +1968,7 @@ bool pmd_trans_migrating(pmd_t pmd) * node. Caller is expected to have an elevated reference count on * the page that will be dropped by this function before returning. */ -int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, +int migrate_misplaced_page(struct page *page, struct vm_fault *vmf, int node) { pg_data_t *pgdat = NODE_DATA(node); @@ -1981,7 +1981,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, * with execute permissions as they are probably shared libraries. */ if (page_mapcount(page) != 1 && page_is_file_cache(page) && - (vma->vm_flags & VM_EXEC)) + (vmf->vma_flags & VM_EXEC)) goto out; /* diff --git a/mm/mlock.c b/mm/mlock.c index 646acba3045b..395bf08f86d8 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -445,7 +445,9 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, vma->vm_flags & VM_LOCKED_CLEAR_MASK); + vm_write_end(vma); while (start < end) { struct page *page; @@ -569,10 +571,11 @@ success: * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ - - if (lock) - vma->vm_flags = newflags; - else + if (lock) { + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, newflags); + vm_write_end(vma); + } else munlock_vma_pages_range(vma, start, end); out: diff --git a/mm/mmap.c b/mm/mmap.c index f4ee016a017f..0fcbe5a72e64 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -165,6 +165,27 @@ void unlink_file_vma(struct vm_area_struct *vma) } } +static void __free_vma(struct vm_area_struct *vma) +{ + if (vma->vm_file) + fput(vma->vm_file); + mpol_put(vma_policy(vma)); + vm_area_free(vma); +} + +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT +void put_vma(struct vm_area_struct *vma) +{ + if (atomic_dec_and_test(&vma->vm_ref_count)) + __free_vma(vma); +} +#else +static inline void put_vma(struct vm_area_struct *vma) +{ + __free_vma(vma); +} +#endif + /* * Close a vm structure and free it, returning the next. */ @@ -175,10 +196,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) might_sleep(); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); - if (vma->vm_file) - fput(vma->vm_file); - mpol_put(vma_policy(vma)); - vm_area_free(vma); + put_vma(vma); return next; } @@ -431,6 +449,13 @@ static void validate_mm(struct mm_struct *mm) RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, unsigned long, rb_subtree_gap, vma_compute_gap) +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT +#define mm_rb_write_lock(mm) write_lock(&(mm)->mm_rb_lock) +#define mm_rb_write_unlock(mm) write_unlock(&(mm)->mm_rb_lock) +#else +#define mm_rb_write_lock(mm) do { } while (0) +#define mm_rb_write_unlock(mm) do { } while (0) +#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */ /* * Update augmented rbtree rb_subtree_gap values after vma->vm_start or @@ -447,26 +472,37 @@ static void vma_gap_update(struct vm_area_struct *vma) } static inline void vma_rb_insert(struct vm_area_struct *vma, - struct rb_root *root) + struct mm_struct *mm) { + struct rb_root *root = &mm->mm_rb; + /* All rb_subtree_gap values must be consistent prior to insertion */ validate_mm_rb(root, NULL); rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } -static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) +static void __vma_rb_erase(struct vm_area_struct *vma, struct mm_struct *mm) { + struct rb_root *root = &mm->mm_rb; /* * Note rb_erase_augmented is a fairly large inline function, * so make sure we instantiate it only once with our desired * augmented rbtree callbacks. */ + mm_rb_write_lock(mm); rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); + mm_rb_write_unlock(mm); /* wmb */ + + /* + * Ensure the removal is complete before clearing the node. + * Matched by vma_has_changed()/handle_speculative_fault(). + */ + RB_CLEAR_NODE(&vma->vm_rb); } static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma, - struct rb_root *root, + struct mm_struct *mm, struct vm_area_struct *ignore) { /* @@ -474,21 +510,21 @@ static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma, * with the possible exception of the "next" vma being erased if * next->vm_start was reduced. */ - validate_mm_rb(root, ignore); + validate_mm_rb(&mm->mm_rb, ignore); - __vma_rb_erase(vma, root); + __vma_rb_erase(vma, mm); } static __always_inline void vma_rb_erase(struct vm_area_struct *vma, - struct rb_root *root) + struct mm_struct *mm) { /* * All rb_subtree_gap values must be consistent prior to erase, * with the possible exception of the vma being erased. */ - validate_mm_rb(root, vma); + validate_mm_rb(&mm->mm_rb, vma); - __vma_rb_erase(vma, root); + __vma_rb_erase(vma, mm); } /* @@ -603,10 +639,12 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, * immediately update the gap to the correct value. Finally we * rebalance the rbtree after all augmented values have been set. */ + mm_rb_write_lock(mm); rb_link_node(&vma->vm_rb, rb_parent, rb_link); vma->rb_subtree_gap = 0; vma_gap_update(vma); - vma_rb_insert(vma, &mm->mm_rb); + vma_rb_insert(vma, mm); + mm_rb_write_unlock(mm); } static void __vma_link_file(struct vm_area_struct *vma) @@ -682,7 +720,7 @@ static __always_inline void __vma_unlink_common(struct mm_struct *mm, { struct vm_area_struct *next; - vma_rb_erase_ignore(vma, &mm->mm_rb, ignore); + vma_rb_erase_ignore(vma, mm, ignore); next = vma->vm_next; if (has_prev) prev->vm_next = next; @@ -716,7 +754,7 @@ static inline void __vma_unlink_prev(struct mm_struct *mm, */ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, - struct vm_area_struct *expand) + struct vm_area_struct *expand, bool keep_locked) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next, *orig_vma = vma; @@ -728,6 +766,30 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, long adjust_next = 0; int remove_next = 0; + /* + * Why using vm_raw_write*() functions here to avoid lockdep's warning ? + * + * Locked is complaining about a theoretical lock dependency, involving + * 3 locks: + * mapping->i_mmap_rwsem --> vma->vm_sequence --> fs_reclaim + * + * Here are the major path leading to this dependency : + * 1. __vma_adjust() mmap_sem -> vm_sequence -> i_mmap_rwsem + * 2. move_vmap() mmap_sem -> vm_sequence -> fs_reclaim + * 3. __alloc_pages_nodemask() fs_reclaim -> i_mmap_rwsem + * 4. unmap_mapping_range() i_mmap_rwsem -> vm_sequence + * + * So there is no way to solve this easily, especially because in + * unmap_mapping_range() the i_mmap_rwsem is grab while the impacted + * VMAs are not yet known. + * However, the way the vm_seq is used is guarantying that we will + * never block on it since we just check for its value and never wait + * for it to move, see vma_has_changed() and handle_speculative_fault(). + */ + vm_raw_write_begin(vma); + if (next) + vm_raw_write_begin(next); + if (next && !insert) { struct vm_area_struct *exporter = NULL, *importer = NULL; @@ -808,8 +870,12 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); - if (error) + if (error) { + if (next && next != vma) + vm_raw_write_end(next); + vm_raw_write_end(vma); return error; + } } } again: @@ -855,17 +921,18 @@ again: } if (start != vma->vm_start) { - vma->vm_start = start; + WRITE_ONCE(vma->vm_start, start); start_changed = true; } if (end != vma->vm_end) { - vma->vm_end = end; + WRITE_ONCE(vma->vm_end, end); end_changed = true; } - vma->vm_pgoff = pgoff; + WRITE_ONCE(vma->vm_pgoff, pgoff); if (adjust_next) { - next->vm_start += adjust_next << PAGE_SHIFT; - next->vm_pgoff += adjust_next; + WRITE_ONCE(next->vm_start, + next->vm_start + (adjust_next << PAGE_SHIFT)); + WRITE_ONCE(next->vm_pgoff, next->vm_pgoff + adjust_next); } if (root) { @@ -930,15 +997,13 @@ again: } if (remove_next) { - if (file) { + if (file) uprobe_munmap(next, next->vm_start, next->vm_end); - fput(file); - } if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; - mpol_put(vma_policy(next)); - vm_area_free(next); + vm_raw_write_end(next); + put_vma(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter @@ -952,6 +1017,8 @@ again: * "vma->vm_next" gap must be updated. */ next = vma->vm_next; + if (next) + vm_raw_write_begin(next); } else { /* * For the scope of the comment "next" and @@ -998,6 +1065,11 @@ again: if (insert && file) uprobe_mmap(insert); + if (next && next != vma) + vm_raw_write_end(next); + if (!keep_locked) + vm_raw_write_end(vma); + validate_mm(mm); return 0; @@ -1137,13 +1209,13 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * parameter) may establish ptes with the wrong permissions of NNNN * instead of the right permissions of XXXX. */ -struct vm_area_struct *vma_merge(struct mm_struct *mm, +struct vm_area_struct *__vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char __user *anon_name) + const char __user *anon_name, bool keep_locked) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -1193,10 +1265,11 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, /* cases 1, 6 */ err = __vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL, - prev); + prev, keep_locked); } else /* cases 2, 5, 7 */ err = __vma_adjust(prev, prev->vm_start, - end, prev->vm_pgoff, NULL, prev); + end, prev->vm_pgoff, NULL, prev, + keep_locked); if (err) return NULL; khugepaged_enter_vma_merge(prev, vm_flags); @@ -1214,10 +1287,12 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, anon_name)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, - addr, prev->vm_pgoff, NULL, next); + addr, prev->vm_pgoff, NULL, next, + keep_locked); else { /* cases 3, 8 */ err = __vma_adjust(area, addr, next->vm_end, - next->vm_pgoff - pglen, NULL, next); + next->vm_pgoff - pglen, NULL, next, + keep_locked); /* * In case 3 area is already equal to next and * this is a noop, but in case 8 "area" has @@ -1837,12 +1912,14 @@ unsigned long mmap_region(struct file *file, unsigned long addr, out: perf_event_mmap(vma); + vm_write_begin(vma); vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) - vma->vm_flags &= VM_LOCKED_CLEAR_MASK; + WRITE_ONCE(vma->vm_flags, + vma->vm_flags & VM_LOCKED_CLEAR_MASK); else mm->locked_vm += (len >> PAGE_SHIFT); } @@ -1857,9 +1934,10 @@ out: * then new mapped in-place (which must be aimed as * a completely new data area). */ - vma->vm_flags |= VM_SOFTDIRTY; + WRITE_ONCE(vma->vm_flags, vma->vm_flags | VM_SOFTDIRTY); vma_set_page_prot(vma); + vm_write_end(vma); return addr; @@ -2241,15 +2319,11 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ -struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +static struct vm_area_struct *__find_vma(struct mm_struct *mm, + unsigned long addr) { struct rb_node *rb_node; - struct vm_area_struct *vma; - - /* Check the cache first. */ - vma = vmacache_find(mm, addr); - if (likely(vma)) - return vma; + struct vm_area_struct *vma = NULL; rb_node = mm->mm_rb.rb_node; @@ -2267,13 +2341,40 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) rb_node = rb_node->rb_right; } + return vma; +} + +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + + /* Check the cache first. */ + vma = vmacache_find(mm, addr); + if (likely(vma)) + return vma; + + vma = __find_vma(mm, addr); if (vma) vmacache_update(addr, vma); return vma; } - EXPORT_SYMBOL(find_vma); +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT +struct vm_area_struct *get_vma(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma = NULL; + + read_lock(&mm->mm_rb_lock); + vma = __find_vma(mm, addr); + if (vma) + atomic_inc(&vma->vm_ref_count); + read_unlock(&mm->mm_rb_lock); + + return vma; +} +#endif + /* * Same as find_vma, but also return a pointer to the previous VMA in *pprev. */ @@ -2494,8 +2595,8 @@ int expand_downwards(struct vm_area_struct *vma, mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); - vma->vm_start = address; - vma->vm_pgoff -= grow; + WRITE_ONCE(vma->vm_start, address); + WRITE_ONCE(vma->vm_pgoff, vma->vm_pgoff - grow); anon_vma_interval_tree_post_update_vma(vma); vma_gap_update(vma); spin_unlock(&mm->page_table_lock); @@ -2641,7 +2742,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, insertion_point = (prev ? &prev->vm_next : &mm->mmap); vma->vm_prev = NULL; do { - vma_rb_erase(vma, &mm->mm_rb); + vma_rb_erase(vma, mm); mm->map_count--; tail_vma = vma; vma = vma->vm_next; @@ -3236,9 +3337,21 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) return NULL; /* should never get here */ - new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, vma_get_anon_name(vma)); + + /* There is 3 cases to manage here in + * AAAA AAAA AAAA AAAA + * PPPP.... PPPP......NNNN PPPP....NNNN PP........NN + * PPPPPPPP(A) PPPP..NNNNNNNN(B) PPPPPPPPPPPP(1) NULL + * PPPPPPPPNNNN(2) + * PPPPNNNNNNNN(3) + * + * new_vma == prev in case A,1,2 + * new_vma == next in case B,3 + */ + new_vma = __vma_merge(mm, prev, addr, addr + len, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, + vma_policy(vma), vma->vm_userfaultfd_ctx, + vma_get_anon_name(vma), true); if (new_vma) { /* * Source vma may have been merged into new_vma @@ -3276,6 +3389,15 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); + /* + * As the VMA is linked right now, it may be hit by the + * speculative page fault handler. But we don't want it to + * to start mapping page in this area until the caller has + * potentially move the pte from the moved VMA. To prevent + * that we protect it right now, and let the caller unprotect + * it once the move is done. + */ + vm_raw_write_begin(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); *need_rmap_locks = false; } diff --git a/mm/mprotect.c b/mm/mprotect.c index 65d317058e9e..5c1a70a80f8f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -454,12 +454,14 @@ success: * vm_flags and vm_page_prot are protected by the mmap_sem * held in write mode. */ - vma->vm_flags = newflags; + vm_write_begin(vma); + WRITE_ONCE(vma->vm_flags, newflags); dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot); vma_set_page_prot(vma); change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable, 0); + vm_write_end(vma); /* * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major diff --git a/mm/mremap.c b/mm/mremap.c index 1d98281f7204..7b841ad88982 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -357,6 +357,14 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (!new_vma) return -ENOMEM; + /* new_vma is returned protected by copy_vma, to prevent speculative + * page fault to be done in the destination area before we move the pte. + * Now, we must also protect the source VMA since we don't want pages + * to be mapped in our back while we are copying the PTEs. + */ + if (vma != new_vma) + vm_raw_write_begin(vma); + moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len, need_rmap_locks); if (moved_len < old_len) { @@ -373,6 +381,8 @@ static unsigned long move_vma(struct vm_area_struct *vma, */ move_page_tables(new_vma, new_addr, vma, old_addr, moved_len, true); + if (vma != new_vma) + vm_raw_write_end(vma); vma = new_vma; old_len = new_len; old_addr = new_addr; @@ -381,7 +391,10 @@ static unsigned long move_vma(struct vm_area_struct *vma, mremap_userfaultfd_prep(new_vma, uf); arch_remap(mm, old_addr, old_addr + old_len, new_addr, new_addr + new_len); + if (vma != new_vma) + vm_raw_write_end(vma); } + vm_raw_write_end(new_vma); /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT) { diff --git a/mm/rmap.c b/mm/rmap.c index c1cca1fd6706..fe4a3b2af774 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1138,7 +1138,7 @@ 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 @@ -1148,12 +1148,11 @@ 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 ? hpage_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); diff --git a/mm/swap.c b/mm/swap.c index 38c3fa4308e2..7da393f516e7 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -452,12 +452,12 @@ void lru_cache_add(struct page *page) * directly back onto it's zone's unevictable list, it does NOT use a * per cpu pagevec. */ -void lru_cache_add_active_or_unevictable(struct page *page, - struct vm_area_struct *vma) +void __lru_cache_add_active_or_unevictable(struct page *page, + unsigned long vma_flags) { VM_BUG_ON_PAGE(PageLRU(page), page); - if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) + if (likely((vma_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) SetPageActive(page); else if (!TestSetPageMlocked(page)) { /* diff --git a/mm/swap_state.c b/mm/swap_state.c index 8e7ce9a9bc5e..13b751a9d6a2 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -534,7 +534,11 @@ static unsigned long swapin_nr_pages(unsigned long offset) * This has been extended to use the NUMA policies from the mm triggering * the readahead. * - * Caller must hold read mmap_sem if vmf->vma is not NULL. + * Caller must hold down_read on the vma->vm_mm if vmf->vma is not NULL. + * This is needed to ensure the VMA will not be freed in our back. In the case + * of the speculative page fault handler, this cannot happen, even if we don't + * hold the mmap_sem. Callees are assumed to take care of reading VMA's fields + * using READ_ONCE() to read consistent values. */ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) @@ -631,9 +635,9 @@ static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { - *start = max3(lpfn, PFN_DOWN(vma->vm_start), + *start = max3(lpfn, PFN_DOWN(READ_ONCE(vma->vm_start)), PFN_DOWN(faddr & PMD_MASK)); - *end = min3(rpfn, PFN_DOWN(vma->vm_end), + *end = min3(rpfn, PFN_DOWN(READ_ONCE(vma->vm_end)), PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE)); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 61026e1289fe..661319e0a0cf 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1300,7 +1300,10 @@ const char * const vmstat_text[] = { "swap_ra", "swap_ra_hit", #endif -#endif /* CONFIG_VM_EVENTS_COUNTERS */ +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + "speculative_pgfault" +#endif +#endif /* CONFIG_VM_EVENT_COUNTERS */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */