diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 8d45fabc5f3baf556b1da2558a42df183ab09e80..ce3251ce5504e478ff65f936608245be3df7312e 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM tristate "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM select PREEMPT_NOTIFIERS + select MMU_NOTIFIER select ANON_INODES ---help--- Support hosting fully virtualized guest machines using hardware diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 746f975b58ef3a4843b00622dbfa1958f1000074..386edbe2cb4e98b1a01767e15978b02df896d895 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -253,6 +254,9 @@ struct mm_struct { struct file *exe_file; unsigned long num_exe_file_vmas; #endif +#ifdef CONFIG_MMU_NOTIFIER + struct mmu_notifier_mm *mmu_notifier_mm; +#endif }; #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h new file mode 100644 index 0000000000000000000000000000000000000000..b77486d152cd307228dae87523b884b80f300111 --- /dev/null +++ b/include/linux/mmu_notifier.h @@ -0,0 +1,279 @@ +#ifndef _LINUX_MMU_NOTIFIER_H +#define _LINUX_MMU_NOTIFIER_H + +#include +#include +#include + +struct mmu_notifier; +struct mmu_notifier_ops; + +#ifdef CONFIG_MMU_NOTIFIER + +/* + * The mmu notifier_mm structure is allocated and installed in + * mm->mmu_notifier_mm inside the mm_take_all_locks() protected + * critical section and it's released only when mm_count reaches zero + * in mmdrop(). + */ +struct mmu_notifier_mm { + /* all mmu notifiers registerd in this mm are queued in this list */ + struct hlist_head list; + /* to serialize the list modifications and hlist_unhashed */ + spinlock_t lock; +}; + +struct mmu_notifier_ops { + /* + * Called either by mmu_notifier_unregister or when the mm is + * being destroyed by exit_mmap, always before all pages are + * freed. This can run concurrently with other mmu notifier + * methods (the ones invoked outside the mm context) and it + * should tear down all secondary mmu mappings and freeze the + * secondary mmu. If this method isn't implemented you've to + * be sure that nothing could possibly write to the pages + * through the secondary mmu by the time the last thread with + * tsk->mm == mm exits. + * + * As side note: the pages freed after ->release returns could + * be immediately reallocated by the gart at an alias physical + * address with a different cache model, so if ->release isn't + * implemented because all _software_ driven memory accesses + * through the secondary mmu are terminated by the time the + * last thread of this mm quits, you've also to be sure that + * speculative _hardware_ operations can't allocate dirty + * cachelines in the cpu that could not be snooped and made + * coherent with the other read and write operations happening + * through the gart alias address, so leading to memory + * corruption. + */ + void (*release)(struct mmu_notifier *mn, + struct mm_struct *mm); + + /* + * clear_flush_young is called after the VM is + * test-and-clearing the young/accessed bitflag in the + * pte. This way the VM will provide proper aging to the + * accesses to the page through the secondary MMUs and not + * only to the ones through the Linux pte. + */ + int (*clear_flush_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * Before this is invoked any secondary MMU is still ok to + * read/write to the page previously pointed to by the Linux + * pte because the page hasn't been freed yet and it won't be + * freed until this returns. If required set_page_dirty has to + * be called internally to this method. + */ + void (*invalidate_page)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* + * invalidate_range_start() and invalidate_range_end() must be + * paired and are called only when the mmap_sem and/or the + * locks protecting the reverse maps are held. The subsystem + * must guarantee that no additional references are taken to + * the pages in the range established between the call to + * invalidate_range_start() and the matching call to + * invalidate_range_end(). + * + * Invalidation of multiple concurrent ranges may be + * optionally permitted by the driver. Either way the + * establishment of sptes is forbidden in the range passed to + * invalidate_range_begin/end for the whole duration of the + * invalidate_range_begin/end critical section. + * + * invalidate_range_start() is called when all pages in the + * range are still mapped and have at least a refcount of one. + * + * invalidate_range_end() is called when all pages in the + * range have been unmapped and the pages have been freed by + * the VM. + * + * The VM will remove the page table entries and potentially + * the page between invalidate_range_start() and + * invalidate_range_end(). If the page must not be freed + * because of pending I/O or other circumstances then the + * invalidate_range_start() callback (or the initial mapping + * by the driver) must make sure that the refcount is kept + * elevated. + * + * If the driver increases the refcount when the pages are + * initially mapped into an address space then either + * invalidate_range_start() or invalidate_range_end() may + * decrease the refcount. If the refcount is decreased on + * invalidate_range_start() then the VM can free pages as page + * table entries are removed. If the refcount is only + * droppped on invalidate_range_end() then the driver itself + * will drop the last refcount but it must take care to flush + * any secondary tlb before doing the final free on the + * page. Pages will no longer be referenced by the linux + * address space but may still be referenced by sptes until + * the last refcount is dropped. + */ + void (*invalidate_range_start)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); + void (*invalidate_range_end)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, unsigned long end); +}; + +/* + * The notifier chains are protected by mmap_sem and/or the reverse map + * semaphores. Notifier chains are only changed when all reverse maps and + * the mmap_sem locks are taken. + * + * Therefore notifier chains can only be traversed when either + * + * 1. mmap_sem is held. + * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock). + * 3. No other concurrent thread can access the list (release) + */ +struct mmu_notifier { + struct hlist_node hlist; + const struct mmu_notifier_ops *ops; +}; + +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return unlikely(mm->mmu_notifier_mm); +} + +extern int mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern int __mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void mmu_notifier_unregister(struct mmu_notifier *mn, + struct mm_struct *mm); +extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); +extern void __mmu_notifier_release(struct mm_struct *mm); +extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address); +extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end); +extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end); + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_release(mm); +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_clear_flush_young(mm, address); + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_page(mm, address); +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_start(mm, start, end); +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_invalidate_range_end(mm, start, end); +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ + mm->mmu_notifier_mm = NULL; +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ + if (mm_has_notifiers(mm)) + __mmu_notifier_mm_destroy(mm); +} + +/* + * These two macros will sometime replace ptep_clear_flush. + * ptep_clear_flush is impleemnted as macro itself, so this also is + * implemented as a macro until ptep_clear_flush will converted to an + * inline function, to diminish the risk of compilation failure. The + * invalidate_page method over time can be moved outside the PT lock + * and these two macros can be later removed. + */ +#define ptep_clear_flush_notify(__vma, __address, __ptep) \ +({ \ + pte_t __pte; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __pte = ptep_clear_flush(___vma, ___address, __ptep); \ + mmu_notifier_invalidate_page(___vma->vm_mm, ___address); \ + __pte; \ +}) + +#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ + __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ + ___address); \ + __young; \ +}) + +#else /* CONFIG_MMU_NOTIFIER */ + +static inline void mmu_notifier_release(struct mm_struct *mm) +{ +} + +static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + return 0; +} + +static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ +} + +static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline void mmu_notifier_mm_init(struct mm_struct *mm) +{ +} + +static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) +{ +} + +#define ptep_clear_flush_young_notify ptep_clear_flush_young +#define ptep_clear_flush_notify ptep_clear_flush + +#endif /* CONFIG_MMU_NOTIFIER */ + +#endif /* _LINUX_MMU_NOTIFIER_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 8214ba7c8bb1ad78e110687ade3459bff8b40073..7ce2ebe847964ecd0701c3c74c18994e3eebcf26 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -414,6 +415,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; + mmu_notifier_mm_init(mm); return mm; } @@ -446,6 +448,7 @@ void __mmdrop(struct mm_struct *mm) BUG_ON(mm == &init_mm); mm_free_pgd(mm); destroy_context(mm); + mmu_notifier_mm_destroy(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); diff --git a/mm/Kconfig b/mm/Kconfig index efee5d379df4adb74afba4bbc83118a64f0a9767..446c6588c75398ab91e9413c20363dcd076432da 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -208,3 +208,6 @@ config NR_QUICK config VIRT_TO_BUS def_bool y depends on !ARCH_NO_VIRT_TO_BUS + +config MMU_NOTIFIER + bool diff --git a/mm/Makefile b/mm/Makefile index 06ca2381fef1bc561eceb16fa91751ca7c7ae79a..da4ccf015aea72ba4d18dc69cf47e7ac97481129 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_SHMEM) += shmem.o obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o obj-$(CONFIG_SLOB) += slob.o +obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 98a3f31ccd6ab2070aed454351c22279efa338f5..380ab402d71160a05d82a00598e5e35efeb5f116 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -188,7 +189,7 @@ __xip_unmap (struct address_space * mapping, if (pte) { /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); page_remove_rmap(page, vma); dec_mm_counter(mm, file_rss); BUG_ON(pte_dirty(pteval)); diff --git a/mm/fremap.c b/mm/fremap.c index 07a9c82ce1a3fa0e24da2f2da23e9416e3f1819c..7881638e4a12bd8c5489c8d08b5779b5ae5a0080 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -214,7 +215,9 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, spin_unlock(&mapping->i_mmap_lock); } + mmu_notifier_invalidate_range_start(mm, start, start + size); err = populate_range(mm, vma, start, size, pgoff); + mmu_notifier_invalidate_range_end(mm, start, start + size); if (!err && !(flags & MAP_NONBLOCK)) { if (unlikely(has_write_lock)) { downgrade_write(&mm->mmap_sem); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3be79dc18c5c65a0c3b251d4849e3c895eadefd3..80eb0d31d0d3b88d89f5eb489201356d45b8a166 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -1672,6 +1673,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); + mmu_notifier_invalidate_range_start(mm, start, end); spin_lock(&mm->page_table_lock); for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); @@ -1713,6 +1715,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range_end(mm, start, end); list_for_each_entry_safe(page, tmp, &page_list, lru) { list_del(&page->lru); put_page(page); diff --git a/mm/memory.c b/mm/memory.c index a8ca04faaea62c6d28e9dc908a0615e927d73ddb..67f0ab9077d9472f99387aa66013bd2665d58887 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -652,6 +653,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long next; unsigned long addr = vma->vm_start; unsigned long end = vma->vm_end; + int ret; /* * Don't copy ptes where a page fault will fill them correctly. @@ -667,17 +669,33 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); + /* + * We need to invalidate the secondary MMU mappings only when + * there could be a permission downgrade on the ptes of the + * parent mm. And a permission downgrade will only happen if + * is_cow_mapping() returns true. + */ + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_start(src_mm, addr, end); + + ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next)) - return -ENOMEM; + if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + vma, addr, next))) { + ret = -ENOMEM; + break; + } } while (dst_pgd++, src_pgd++, addr = next, addr != end); - return 0; + + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_end(src_mm, + vma->vm_start, end); + return ret; } static unsigned long zap_pte_range(struct mmu_gather *tlb, @@ -881,7 +899,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, unsigned long start = start_addr; spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; int fullmm = (*tlbp)->fullmm; + struct mm_struct *mm = vma->vm_mm; + mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { unsigned long end; @@ -946,6 +966,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, } } out: + mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); return start; /* which is now the end (or restart) address */ } @@ -1616,10 +1637,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, { pgd_t *pgd; unsigned long next; - unsigned long end = addr + size; + unsigned long start = addr, end = addr + size; int err; BUG_ON(addr >= end); + mmu_notifier_invalidate_range_start(mm, start, end); pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); @@ -1627,6 +1649,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, if (err) break; } while (pgd++, addr = next, addr != end); + mmu_notifier_invalidate_range_end(mm, start, end); return err; } EXPORT_SYMBOL_GPL(apply_to_page_range); @@ -1839,7 +1862,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * seen in the presence of one thread doing SMC and another * thread doing COW. */ - ptep_clear_flush(vma, address, page_table); + ptep_clear_flush_notify(vma, address, page_table); set_pte_at(mm, address, page_table, entry); update_mmu_cache(vma, address, entry); lru_cache_add_active(new_page); diff --git a/mm/mmap.c b/mm/mmap.c index e5f9cb83d6d4fad10631872759170c5611fabf67..245c3d69067b7bc4c0b83ba2fa6a08df28bc7f9b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -2061,6 +2062,7 @@ void exit_mmap(struct mm_struct *mm) /* mm's last user has gone, and its about to be pulled down */ arch_exit_mmap(mm); + mmu_notifier_release(mm); lru_add_drain(); flush_cache_mm(mm); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c new file mode 100644 index 0000000000000000000000000000000000000000..5f4ef0250beea45533c0f8a316960b1f94b67825 --- /dev/null +++ b/mm/mmu_notifier.c @@ -0,0 +1,277 @@ +/* + * linux/mm/mmu_notifier.c + * + * Copyright (C) 2008 Qumranet, Inc. + * Copyright (C) 2008 SGI + * Christoph Lameter + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include +#include +#include +#include +#include +#include +#include + +/* + * This function can't run concurrently against mmu_notifier_register + * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap + * runs with mm_users == 0. Other tasks may still invoke mmu notifiers + * in parallel despite there being no task using this mm any more, + * through the vmas outside of the exit_mmap context, such as with + * vmtruncate. This serializes against mmu_notifier_unregister with + * the mmu_notifier_mm->lock in addition to RCU and it serializes + * against the other mmu notifiers with RCU. struct mmu_notifier_mm + * can't go away from under us as exit_mmap holds an mm_count pin + * itself. + */ +void __mmu_notifier_release(struct mm_struct *mm) +{ + struct mmu_notifier *mn; + + spin_lock(&mm->mmu_notifier_mm->lock); + while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { + mn = hlist_entry(mm->mmu_notifier_mm->list.first, + struct mmu_notifier, + hlist); + /* + * We arrived before mmu_notifier_unregister so + * mmu_notifier_unregister will do nothing other than + * to wait ->release to finish and + * mmu_notifier_unregister to return. + */ + hlist_del_init_rcu(&mn->hlist); + /* + * RCU here will block mmu_notifier_unregister until + * ->release returns. + */ + rcu_read_lock(); + spin_unlock(&mm->mmu_notifier_mm->lock); + /* + * if ->release runs before mmu_notifier_unregister it + * must be handled as it's the only way for the driver + * to flush all existing sptes and stop the driver + * from establishing any more sptes before all the + * pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); + spin_lock(&mm->mmu_notifier_mm->lock); + } + spin_unlock(&mm->mmu_notifier_mm->lock); + + /* + * synchronize_rcu here prevents mmu_notifier_release to + * return to exit_mmap (which would proceed freeing all pages + * in the mm) until the ->release method returns, if it was + * invoked by mmu_notifier_unregister. + * + * The mmu_notifier_mm can't go away from under us because one + * mm_count is hold by exit_mmap. + */ + synchronize_rcu(); +} + +/* + * If no young bitflag is supported by the hardware, ->clear_flush_young can + * unmap the address and return 1 or 0 depending if the mapping previously + * existed or not. + */ +int __mmu_notifier_clear_flush_young(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + int young = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->clear_flush_young) + young |= mn->ops->clear_flush_young(mn, mm, address); + } + rcu_read_unlock(); + + return young; +} + +void __mmu_notifier_invalidate_page(struct mm_struct *mm, + unsigned long address) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_page) + mn->ops->invalidate_page(mn, mm, address); + } + rcu_read_unlock(); +} + +void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_range_start) + mn->ops->invalidate_range_start(mn, mm, start, end); + } + rcu_read_unlock(); +} + +void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + struct mmu_notifier *mn; + struct hlist_node *n; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops->invalidate_range_end) + mn->ops->invalidate_range_end(mn, mm, start, end); + } + rcu_read_unlock(); +} + +static int do_mmu_notifier_register(struct mmu_notifier *mn, + struct mm_struct *mm, + int take_mmap_sem) +{ + struct mmu_notifier_mm *mmu_notifier_mm; + int ret; + + BUG_ON(atomic_read(&mm->mm_users) <= 0); + + ret = -ENOMEM; + mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL); + if (unlikely(!mmu_notifier_mm)) + goto out; + + if (take_mmap_sem) + down_write(&mm->mmap_sem); + ret = mm_take_all_locks(mm); + if (unlikely(ret)) + goto out_cleanup; + + if (!mm_has_notifiers(mm)) { + INIT_HLIST_HEAD(&mmu_notifier_mm->list); + spin_lock_init(&mmu_notifier_mm->lock); + mm->mmu_notifier_mm = mmu_notifier_mm; + mmu_notifier_mm = NULL; + } + atomic_inc(&mm->mm_count); + + /* + * Serialize the update against mmu_notifier_unregister. A + * side note: mmu_notifier_release can't run concurrently with + * us because we hold the mm_users pin (either implicitly as + * current->mm or explicitly with get_task_mm() or similar). + * We can't race against any other mmu notifier method either + * thanks to mm_take_all_locks(). + */ + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list); + spin_unlock(&mm->mmu_notifier_mm->lock); + + mm_drop_all_locks(mm); +out_cleanup: + if (take_mmap_sem) + up_write(&mm->mmap_sem); + /* kfree() does nothing if mmu_notifier_mm is NULL */ + kfree(mmu_notifier_mm); +out: + BUG_ON(atomic_read(&mm->mm_users) <= 0); + return ret; +} + +/* + * Must not hold mmap_sem nor any other VM related lock when calling + * this registration function. Must also ensure mm_users can't go down + * to zero while this runs to avoid races with mmu_notifier_release, + * so mm has to be current->mm or the mm should be pinned safely such + * as with get_task_mm(). If the mm is not current->mm, the mm_users + * pin should be released by calling mmput after mmu_notifier_register + * returns. mmu_notifier_unregister must be always called to + * unregister the notifier. mm_count is automatically pinned to allow + * mmu_notifier_unregister to safely run at any time later, before or + * after exit_mmap. ->release will always be called before exit_mmap + * frees the pages. + */ +int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) +{ + return do_mmu_notifier_register(mn, mm, 1); +} +EXPORT_SYMBOL_GPL(mmu_notifier_register); + +/* + * Same as mmu_notifier_register but here the caller must hold the + * mmap_sem in write mode. + */ +int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) +{ + return do_mmu_notifier_register(mn, mm, 0); +} +EXPORT_SYMBOL_GPL(__mmu_notifier_register); + +/* this is called after the last mmu_notifier_unregister() returned */ +void __mmu_notifier_mm_destroy(struct mm_struct *mm) +{ + BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list)); + kfree(mm->mmu_notifier_mm); + mm->mmu_notifier_mm = LIST_POISON1; /* debug */ +} + +/* + * This releases the mm_count pin automatically and frees the mm + * structure if it was the last user of it. It serializes against + * running mmu notifiers with RCU and against mmu_notifier_unregister + * with the unregister lock + RCU. All sptes must be dropped before + * calling mmu_notifier_unregister. ->release or any other notifier + * method may be invoked concurrently with mmu_notifier_unregister, + * and only after mmu_notifier_unregister returned we're guaranteed + * that ->release or any other method can't run anymore. + */ +void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) +{ + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + spin_lock(&mm->mmu_notifier_mm->lock); + if (!hlist_unhashed(&mn->hlist)) { + hlist_del_rcu(&mn->hlist); + + /* + * RCU here will force exit_mmap to wait ->release to finish + * before freeing the pages. + */ + rcu_read_lock(); + spin_unlock(&mm->mmu_notifier_mm->lock); + /* + * exit_mmap will block in mmu_notifier_release to + * guarantee ->release is called before freeing the + * pages. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); + } else + spin_unlock(&mm->mmu_notifier_mm->lock); + + /* + * Wait any running method to finish, of course including + * ->release if it was run by mmu_notifier_relase instead of us. + */ + synchronize_rcu(); + + BUG_ON(atomic_read(&mm->mm_count) <= 0); + + mmdrop(mm); +} +EXPORT_SYMBOL_GPL(mmu_notifier_unregister); diff --git a/mm/mprotect.c b/mm/mprotect.c index abd645a3b0a021bb34d5de49cff94efae109966c..fded06f923f4b939d75f745225b38b8e41e8ee08 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -203,10 +204,12 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, dirty_accountable = 1; } + mmu_notifier_invalidate_range_start(mm, start, end); if (is_vm_hugetlb_page(vma)) hugetlb_change_protection(vma, start, end, vma->vm_page_prot); else change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable); + mmu_notifier_invalidate_range_end(mm, start, end); vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); vm_stat_account(mm, newflags, vma->vm_file, nrpages); return 0; diff --git a/mm/mremap.c b/mm/mremap.c index 08e3c7f2bd15a1b2e502aeb3e9f509148cb5dfa8..1a7743923c8c42c536d79ecb64f45457b2a3f994 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -74,7 +75,11 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; + unsigned long old_start; + old_start = old_addr; + mmu_notifier_invalidate_range_start(vma->vm_mm, + old_start, old_end); if (vma->vm_file) { /* * Subtle point from Rajesh Venkatasubramanian: before @@ -116,6 +121,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) spin_unlock(&mapping->i_mmap_lock); + mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end); } #define LATENCY_LIMIT (64 * PAGE_SIZE) diff --git a/mm/rmap.c b/mm/rmap.c index 39ae5a9bf382615120e14e3fbe4efd3bc7cda153..99bc3f9cd796f34a58ec1d61798c27c583a0eaf3 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -49,6 +49,7 @@ #include #include #include +#include #include @@ -287,7 +288,7 @@ static int page_referenced_one(struct page *page, if (vma->vm_flags & VM_LOCKED) { referenced++; *mapcount = 1; /* break early from loop */ - } else if (ptep_clear_flush_young(vma, address, pte)) + } else if (ptep_clear_flush_young_notify(vma, address, pte)) referenced++; /* Pretend the page is referenced if the task has the @@ -457,7 +458,7 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma) pte_t entry; flush_cache_page(vma, address, pte_pfn(*pte)); - entry = ptep_clear_flush(vma, address, pte); + entry = ptep_clear_flush_notify(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(mm, address, pte, entry); @@ -705,14 +706,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * skipped over this mm) then we should reactivate it. */ if (!migration && ((vma->vm_flags & VM_LOCKED) || - (ptep_clear_flush_young(vma, address, pte)))) { + (ptep_clear_flush_young_notify(vma, address, pte)))) { ret = SWAP_FAIL; goto out_unmap; } /* Nuke the page table entry. */ flush_cache_page(vma, address, page_to_pfn(page)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); /* Move the dirty bit to the physical page now the pte is gone. */ if (pte_dirty(pteval)) @@ -837,12 +838,12 @@ static void try_to_unmap_cluster(unsigned long cursor, page = vm_normal_page(vma, address, *pte); BUG_ON(!page || PageAnon(page)); - if (ptep_clear_flush_young(vma, address, pte)) + if (ptep_clear_flush_young_notify(vma, address, pte)) continue; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); + pteval = ptep_clear_flush_notify(vma, address, pte); /* If nonlinear, store the file page offset in the pte. */ if (page->index != linear_page_index(vma, address))