diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 20 | ||||
| -rw-r--r-- | mm/hmm.c | 490 | ||||
| -rw-r--r-- | mm/madvise.c | 42 | ||||
| -rw-r--r-- | mm/memcontrol.c | 25 | ||||
| -rw-r--r-- | mm/mempolicy.c | 17 | ||||
| -rw-r--r-- | mm/memremap.c | 105 | ||||
| -rw-r--r-- | mm/migrate.c | 276 | ||||
| -rw-r--r-- | mm/mincore.c | 17 | ||||
| -rw-r--r-- | mm/mmu_notifier.c | 263 | ||||
| -rw-r--r-- | mm/mprotect.c | 26 | ||||
| -rw-r--r-- | mm/page_alloc.c | 2 | ||||
| -rw-r--r-- | mm/pagewalk.c | 126 |
12 files changed, 675 insertions, 734 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 56cec636a1fc..2fe4902ad755 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -669,23 +669,17 @@ config ZONE_DEVICE If FS_DAX is enabled, then say Y. -config MIGRATE_VMA_HELPER - bool - config DEV_PAGEMAP_OPS bool +# +# Helpers to mirror range of the CPU page tables of a process into device page +# tables. +# config HMM_MIRROR - bool "HMM mirror CPU page table into a device page table" - depends on (X86_64 || PPC64) - depends on MMU && 64BIT - select MMU_NOTIFIER - help - Select HMM_MIRROR if you want to mirror range of the CPU page table of a - process into a device page table. Here, mirror means "keep synchronized". - Prerequisites: the device must provide the ability to write-protect its - page tables (at PAGE_SIZE granularity), and must be able to recover from - the resulting potential page faults. + bool + depends on MMU + depends on MMU_NOTIFIER config DEVICE_PRIVATE bool "Unaddressable device memory (GPU memory, ...)" @@ -8,7 +8,7 @@ * Refer to include/linux/hmm.h for information about heterogeneous memory * management or HMM for short. */ -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/hmm.h> #include <linux/init.h> #include <linux/rmap.h> @@ -26,101 +26,37 @@ #include <linux/mmu_notifier.h> #include <linux/memory_hotplug.h> -static const struct mmu_notifier_ops hmm_mmu_notifier_ops; - -/** - * hmm_get_or_create - register HMM against an mm (HMM internal) - * - * @mm: mm struct to attach to - * Returns: returns an HMM object, either by referencing the existing - * (per-process) object, or by creating a new one. - * - * This is not intended to be used directly by device drivers. If mm already - * has an HMM struct then it get a reference on it and returns it. Otherwise - * it allocates an HMM struct, initializes it, associate it with the mm and - * returns it. - */ -static struct hmm *hmm_get_or_create(struct mm_struct *mm) +static struct mmu_notifier *hmm_alloc_notifier(struct mm_struct *mm) { struct hmm *hmm; - lockdep_assert_held_write(&mm->mmap_sem); - - /* Abuse the page_table_lock to also protect mm->hmm. */ - spin_lock(&mm->page_table_lock); - hmm = mm->hmm; - if (mm->hmm && kref_get_unless_zero(&mm->hmm->kref)) - goto out_unlock; - spin_unlock(&mm->page_table_lock); - - hmm = kmalloc(sizeof(*hmm), GFP_KERNEL); + hmm = kzalloc(sizeof(*hmm), GFP_KERNEL); if (!hmm) - return NULL; + return ERR_PTR(-ENOMEM); + init_waitqueue_head(&hmm->wq); INIT_LIST_HEAD(&hmm->mirrors); init_rwsem(&hmm->mirrors_sem); - hmm->mmu_notifier.ops = NULL; INIT_LIST_HEAD(&hmm->ranges); spin_lock_init(&hmm->ranges_lock); - kref_init(&hmm->kref); hmm->notifiers = 0; - hmm->mm = mm; - - hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops; - if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) { - kfree(hmm); - return NULL; - } - - mmgrab(hmm->mm); - - /* - * We hold the exclusive mmap_sem here so we know that mm->hmm is - * still NULL or 0 kref, and is safe to update. - */ - spin_lock(&mm->page_table_lock); - mm->hmm = hmm; - -out_unlock: - spin_unlock(&mm->page_table_lock); - return hmm; + return &hmm->mmu_notifier; } -static void hmm_free_rcu(struct rcu_head *rcu) +static void hmm_free_notifier(struct mmu_notifier *mn) { - struct hmm *hmm = container_of(rcu, struct hmm, rcu); + struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); - mmdrop(hmm->mm); + WARN_ON(!list_empty(&hmm->ranges)); + WARN_ON(!list_empty(&hmm->mirrors)); kfree(hmm); } -static void hmm_free(struct kref *kref) -{ - struct hmm *hmm = container_of(kref, struct hmm, kref); - - spin_lock(&hmm->mm->page_table_lock); - if (hmm->mm->hmm == hmm) - hmm->mm->hmm = NULL; - spin_unlock(&hmm->mm->page_table_lock); - - mmu_notifier_unregister_no_release(&hmm->mmu_notifier, hmm->mm); - mmu_notifier_call_srcu(&hmm->rcu, hmm_free_rcu); -} - -static inline void hmm_put(struct hmm *hmm) -{ - kref_put(&hmm->kref, hmm_free); -} - static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); struct hmm_mirror *mirror; - /* Bail out if hmm is in the process of being freed */ - if (!kref_get_unless_zero(&hmm->kref)) - return; - /* * Since hmm_range_register() holds the mmget() lock hmm_release() is * prevented as long as a range exists. @@ -137,8 +73,6 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) mirror->ops->release(mirror); } up_read(&hmm->mirrors_sem); - - hmm_put(hmm); } static void notifiers_decrement(struct hmm *hmm) @@ -165,23 +99,14 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn, { struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); struct hmm_mirror *mirror; - struct hmm_update update; struct hmm_range *range; unsigned long flags; int ret = 0; - if (!kref_get_unless_zero(&hmm->kref)) - return 0; - - update.start = nrange->start; - update.end = nrange->end; - update.event = HMM_UPDATE_INVALIDATE; - update.blockable = mmu_notifier_range_blockable(nrange); - spin_lock_irqsave(&hmm->ranges_lock, flags); hmm->notifiers++; list_for_each_entry(range, &hmm->ranges, list) { - if (update.end < range->start || update.start >= range->end) + if (nrange->end < range->start || nrange->start >= range->end) continue; range->valid = false; @@ -198,9 +123,10 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn, list_for_each_entry(mirror, &hmm->mirrors, list) { int rc; - rc = mirror->ops->sync_cpu_device_pagetables(mirror, &update); + rc = mirror->ops->sync_cpu_device_pagetables(mirror, nrange); if (rc) { - if (WARN_ON(update.blockable || rc != -EAGAIN)) + if (WARN_ON(mmu_notifier_range_blockable(nrange) || + rc != -EAGAIN)) continue; ret = -EAGAIN; break; @@ -211,7 +137,6 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn, out: if (ret) notifiers_decrement(hmm); - hmm_put(hmm); return ret; } @@ -220,17 +145,15 @@ static void hmm_invalidate_range_end(struct mmu_notifier *mn, { struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); - if (!kref_get_unless_zero(&hmm->kref)) - return; - notifiers_decrement(hmm); - hmm_put(hmm); } static const struct mmu_notifier_ops hmm_mmu_notifier_ops = { .release = hmm_release, .invalidate_range_start = hmm_invalidate_range_start, .invalidate_range_end = hmm_invalidate_range_end, + .alloc_notifier = hmm_alloc_notifier, + .free_notifier = hmm_free_notifier, }; /* @@ -242,18 +165,27 @@ static const struct mmu_notifier_ops hmm_mmu_notifier_ops = { * * To start mirroring a process address space, the device driver must register * an HMM mirror struct. + * + * The caller cannot unregister the hmm_mirror while any ranges are + * registered. + * + * Callers using this function must put a call to mmu_notifier_synchronize() + * in their module exit functions. */ int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm) { + struct mmu_notifier *mn; + lockdep_assert_held_write(&mm->mmap_sem); /* Sanity check */ if (!mm || !mirror || !mirror->ops) return -EINVAL; - mirror->hmm = hmm_get_or_create(mm); - if (!mirror->hmm) - return -ENOMEM; + mn = mmu_notifier_get_locked(&hmm_mmu_notifier_ops, mm); + if (IS_ERR(mn)) + return PTR_ERR(mn); + mirror->hmm = container_of(mn, struct hmm, mmu_notifier); down_write(&mirror->hmm->mirrors_sem); list_add(&mirror->list, &mirror->hmm->mirrors); @@ -277,7 +209,7 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror) down_write(&hmm->mirrors_sem); list_del(&mirror->list); up_write(&hmm->mirrors_sem); - hmm_put(hmm); + mmu_notifier_put(&hmm->mmu_notifier); } EXPORT_SYMBOL(hmm_mirror_unregister); @@ -285,8 +217,7 @@ struct hmm_vma_walk { struct hmm_range *range; struct dev_pagemap *pgmap; unsigned long last; - bool fault; - bool block; + unsigned int flags; }; static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr, @@ -298,17 +229,27 @@ static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr, struct vm_area_struct *vma = walk->vma; vm_fault_t ret; - flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY; - flags |= write_fault ? FAULT_FLAG_WRITE : 0; + if (!vma) + goto err; + + if (hmm_vma_walk->flags & HMM_FAULT_ALLOW_RETRY) + flags |= FAULT_FLAG_ALLOW_RETRY; + if (write_fault) + flags |= FAULT_FLAG_WRITE; + ret = handle_mm_fault(vma, addr, flags); - if (ret & VM_FAULT_RETRY) + if (ret & VM_FAULT_RETRY) { + /* Note, handle_mm_fault did up_read(&mm->mmap_sem)) */ return -EAGAIN; - if (ret & VM_FAULT_ERROR) { - *pfn = range->values[HMM_PFN_ERROR]; - return -EFAULT; } + if (ret & VM_FAULT_ERROR) + goto err; return -EBUSY; + +err: + *pfn = range->values[HMM_PFN_ERROR]; + return -EFAULT; } static int hmm_pfns_bad(unsigned long addr, @@ -328,8 +269,8 @@ static int hmm_pfns_bad(unsigned long addr, } /* - * hmm_vma_walk_hole() - handle a range lacking valid pmd or pte(s) - * @start: range virtual start address (inclusive) + * hmm_vma_walk_hole_() - handle a range lacking valid pmd or pte(s) + * @addr: range virtual start address (inclusive) * @end: range virtual end address (exclusive) * @fault: should we fault or not ? * @write_fault: write fault ? @@ -346,13 +287,15 @@ static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end, struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; uint64_t *pfns = range->pfns; - unsigned long i, page_size; + unsigned long i; hmm_vma_walk->last = addr; - page_size = hmm_range_page_size(range); - i = (addr - range->start) >> range->page_shift; + i = (addr - range->start) >> PAGE_SHIFT; + + if (write_fault && walk->vma && !(walk->vma->vm_flags & VM_WRITE)) + return -EPERM; - for (; addr < end; addr += page_size, i++) { + for (; addr < end; addr += PAGE_SIZE, i++) { pfns[i] = range->values[HMM_PFN_NONE]; if (fault || write_fault) { int ret; @@ -373,15 +316,15 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk, { struct hmm_range *range = hmm_vma_walk->range; - if (!hmm_vma_walk->fault) + if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) return; /* * So we not only consider the individual per page request we also * consider the default flags requested for the range. The API can - * be use in 2 fashions. The first one where the HMM user coalesce - * multiple page fault into one request and set flags per pfns for - * of those faults. The second one where the HMM user want to pre- + * be used 2 ways. The first one where the HMM user coalesces + * multiple page faults into one request and sets flags per pfn for + * those faults. The second one where the HMM user wants to pre- * fault a range with specific flags. For the latter one it is a * waste to have the user pre-fill the pfn arrays with a default * flags value. @@ -391,7 +334,7 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk, /* We aren't ask to do anything ... */ if (!(pfns & range->flags[HMM_PFN_VALID])) return; - /* If this is device memory than only fault if explicitly requested */ + /* If this is device memory then only fault if explicitly requested */ if ((cpu_flags & range->flags[HMM_PFN_DEVICE_PRIVATE])) { /* Do we fault on device memory ? */ if (pfns & range->flags[HMM_PFN_DEVICE_PRIVATE]) { @@ -418,7 +361,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, { unsigned long i; - if (!hmm_vma_walk->fault) { + if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) { *fault = *write_fault = false; return; } @@ -458,22 +401,10 @@ static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd) range->flags[HMM_PFN_VALID]; } -static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud) -{ - if (!pud_present(pud)) - return 0; - return pud_write(pud) ? range->flags[HMM_PFN_VALID] | - range->flags[HMM_PFN_WRITE] : - range->flags[HMM_PFN_VALID]; -} - -static int hmm_vma_handle_pmd(struct mm_walk *walk, - unsigned long addr, - unsigned long end, - uint64_t *pfns, - pmd_t pmd) -{ #ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, + unsigned long end, uint64_t *pfns, pmd_t pmd) +{ struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; unsigned long pfn, npages, i; @@ -488,7 +419,7 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, if (pmd_protnone(pmd) || fault || write_fault) return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk); - pfn = pmd_pfn(pmd) + pte_index(addr); + pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) { if (pmd_devmap(pmd)) { hmm_vma_walk->pgmap = get_dev_pagemap(pfn, @@ -504,11 +435,12 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, } hmm_vma_walk->last = end; return 0; -#else - /* If THP is not enabled then we should never reach that code ! */ - return -EINVAL; -#endif } +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +/* stub to allow the code below to compile */ +int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, + unsigned long end, uint64_t *pfns, pmd_t pmd); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte) { @@ -525,7 +457,6 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, { struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; - struct vm_area_struct *vma = walk->vma; bool fault, write_fault; uint64_t cpu_flags; pte_t pte = *ptep; @@ -546,6 +477,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, swp_entry_t entry = pte_to_swp_entry(pte); if (!non_swap_entry(entry)) { + cpu_flags = pte_to_hmm_pfn_flags(range, pte); + hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags, + &fault, &write_fault); if (fault || write_fault) goto fault; return 0; @@ -574,8 +508,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, if (fault || write_fault) { pte_unmap(ptep); hmm_vma_walk->last = addr; - migration_entry_wait(vma->vm_mm, - pmdp, addr); + migration_entry_wait(walk->mm, pmdp, addr); return -EBUSY; } return 0; @@ -623,21 +556,16 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp, { struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; - struct vm_area_struct *vma = walk->vma; uint64_t *pfns = range->pfns; unsigned long addr = start, i; pte_t *ptep; pmd_t pmd; - again: pmd = READ_ONCE(*pmdp); if (pmd_none(pmd)) return hmm_vma_walk_hole(start, end, walk); - if (pmd_huge(pmd) && (range->vma->vm_flags & VM_HUGETLB)) - return hmm_pfns_bad(start, end, walk); - if (thp_migration_supported() && is_pmd_migration_entry(pmd)) { bool fault, write_fault; unsigned long npages; @@ -651,7 +579,7 @@ again: 0, &fault, &write_fault); if (fault || write_fault) { hmm_vma_walk->last = addr; - pmd_migration_entry_wait(vma->vm_mm, pmdp); + pmd_migration_entry_wait(walk->mm, pmdp); return -EBUSY; } return 0; @@ -660,11 +588,11 @@ again: if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) { /* - * No need to take pmd_lock here, even if some other threads + * No need to take pmd_lock here, even if some other thread * is splitting the huge pmd we will get that event through * mmu_notifier callback. * - * So just read pmd value and check again its a transparent + * So just read pmd value and check again it's a transparent * huge or device mapping one and compute corresponding pfn * values. */ @@ -678,7 +606,7 @@ again: } /* - * We have handled all the valid case above ie either none, migration, + * We have handled all the valid cases above ie either none, migration, * huge or transparent huge. At this point either it is a valid pmd * entry pointing to pte directory or it is a bad pmd that will not * recover. @@ -714,10 +642,19 @@ again: return 0; } -static int hmm_vma_walk_pud(pud_t *pudp, - unsigned long start, - unsigned long end, - struct mm_walk *walk) +#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) +static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud) +{ + if (!pud_present(pud)) + return 0; + return pud_write(pud) ? range->flags[HMM_PFN_VALID] | + range->flags[HMM_PFN_WRITE] : + range->flags[HMM_PFN_VALID]; +} + +static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end, + struct mm_walk *walk) { struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; @@ -781,42 +718,29 @@ again: return 0; } +#else +#define hmm_vma_walk_pud NULL +#endif +#ifdef CONFIG_HUGETLB_PAGE static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, unsigned long start, unsigned long end, struct mm_walk *walk) { -#ifdef CONFIG_HUGETLB_PAGE - unsigned long addr = start, i, pfn, mask, size, pfn_inc; + unsigned long addr = start, i, pfn; struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; struct vm_area_struct *vma = walk->vma; - struct hstate *h = hstate_vma(vma); uint64_t orig_pfn, cpu_flags; bool fault, write_fault; spinlock_t *ptl; pte_t entry; int ret = 0; - size = 1UL << huge_page_shift(h); - mask = size - 1; - if (range->page_shift != PAGE_SHIFT) { - /* Make sure we are looking at full page. */ - if (start & mask) - return -EINVAL; - if (end < (start + size)) - return -EINVAL; - pfn_inc = size >> PAGE_SHIFT; - } else { - pfn_inc = 1; - size = PAGE_SIZE; - } - - - ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); entry = huge_ptep_get(pte); - i = (start - range->start) >> range->page_shift; + i = (start - range->start) >> PAGE_SHIFT; orig_pfn = range->pfns[i]; range->pfns[i] = range->values[HMM_PFN_NONE]; cpu_flags = pte_to_hmm_pfn_flags(range, entry); @@ -828,8 +752,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, goto unlock; } - pfn = pte_pfn(entry) + ((start & mask) >> range->page_shift); - for (; addr < end; addr += size, i++, pfn += pfn_inc) + pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT); + for (; addr < end; addr += PAGE_SIZE, i++, pfn++) range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags; hmm_vma_walk->last = end; @@ -841,10 +765,10 @@ unlock: return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk); return ret; -#else /* CONFIG_HUGETLB_PAGE */ - return -EINVAL; -#endif } +#else +#define hmm_vma_walk_hugetlb_entry NULL +#endif /* CONFIG_HUGETLB_PAGE */ static void hmm_pfns_clear(struct hmm_range *range, uint64_t *pfns, @@ -859,44 +783,32 @@ static void hmm_pfns_clear(struct hmm_range *range, * hmm_range_register() - start tracking change to CPU page table over a range * @range: range * @mm: the mm struct for the range of virtual address - * @start: start virtual address (inclusive) - * @end: end virtual address (exclusive) - * @page_shift: expect page shift for the range - * Returns 0 on success, -EFAULT if the address space is no longer valid + * + * Return: 0 on success, -EFAULT if the address space is no longer valid * * Track updates to the CPU page table see include/linux/hmm.h */ -int hmm_range_register(struct hmm_range *range, - struct hmm_mirror *mirror, - unsigned long start, - unsigned long end, - unsigned page_shift) +int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror) { - unsigned long mask = ((1UL << page_shift) - 1UL); struct hmm *hmm = mirror->hmm; unsigned long flags; range->valid = false; range->hmm = NULL; - if ((start & mask) || (end & mask)) + if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1))) return -EINVAL; - if (start >= end) + if (range->start >= range->end) return -EINVAL; - range->page_shift = page_shift; - range->start = start; - range->end = end; - /* Prevent hmm_release() from running while the range is valid */ - if (!mmget_not_zero(hmm->mm)) + if (!mmget_not_zero(hmm->mmu_notifier.mm)) return -EFAULT; /* Initialize range to track CPU page table updates. */ spin_lock_irqsave(&hmm->ranges_lock, flags); range->hmm = hmm; - kref_get(&hmm->kref); list_add(&range->list, &hmm->ranges); /* @@ -928,8 +840,7 @@ void hmm_range_unregister(struct hmm_range *range) spin_unlock_irqrestore(&hmm->ranges_lock, flags); /* Drop reference taken by hmm_range_register() */ - mmput(hmm->mm); - hmm_put(hmm); + mmput(hmm->mmu_notifier.mm); /* * The range is now invalid and the ref on the hmm is dropped, so @@ -941,105 +852,33 @@ void hmm_range_unregister(struct hmm_range *range) } EXPORT_SYMBOL(hmm_range_unregister); -/* - * hmm_range_snapshot() - snapshot CPU page table for a range - * @range: range - * Return: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid - * permission (for instance asking for write and range is read only), - * -EBUSY if you need to retry, -EFAULT invalid (ie either no valid - * vma or it is illegal to access that range), number of valid pages - * in range->pfns[] (from range start address). - * - * This snapshots the CPU page table for a range of virtual addresses. Snapshot - * validity is tracked by range struct. See in include/linux/hmm.h for example - * on how to use. - */ -long hmm_range_snapshot(struct hmm_range *range) -{ - const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP; - unsigned long start = range->start, end; - struct hmm_vma_walk hmm_vma_walk; - struct hmm *hmm = range->hmm; - struct vm_area_struct *vma; - struct mm_walk mm_walk; - - lockdep_assert_held(&hmm->mm->mmap_sem); - do { - /* If range is no longer valid force retry. */ - if (!range->valid) - return -EBUSY; - - vma = find_vma(hmm->mm, start); - if (vma == NULL || (vma->vm_flags & device_vma)) - return -EFAULT; - - if (is_vm_hugetlb_page(vma)) { - if (huge_page_shift(hstate_vma(vma)) != - range->page_shift && - range->page_shift != PAGE_SHIFT) - return -EINVAL; - } else { - if (range->page_shift != PAGE_SHIFT) - return -EINVAL; - } - - if (!(vma->vm_flags & VM_READ)) { - /* - * If vma do not allow read access, then assume that it - * does not allow write access, either. HMM does not - * support architecture that allow write without read. - */ - hmm_pfns_clear(range, range->pfns, - range->start, range->end); - return -EPERM; - } - - range->vma = vma; - hmm_vma_walk.pgmap = NULL; - hmm_vma_walk.last = start; - hmm_vma_walk.fault = false; - hmm_vma_walk.range = range; - mm_walk.private = &hmm_vma_walk; - end = min(range->end, vma->vm_end); - - mm_walk.vma = vma; - mm_walk.mm = vma->vm_mm; - mm_walk.pte_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.hugetlb_entry = NULL; - mm_walk.pud_entry = hmm_vma_walk_pud; - mm_walk.pmd_entry = hmm_vma_walk_pmd; - mm_walk.pte_hole = hmm_vma_walk_hole; - mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry; - - walk_page_range(start, end, &mm_walk); - start = end; - } while (start < range->end); - - return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; -} -EXPORT_SYMBOL(hmm_range_snapshot); +static const struct mm_walk_ops hmm_walk_ops = { + .pud_entry = hmm_vma_walk_pud, + .pmd_entry = hmm_vma_walk_pmd, + .pte_hole = hmm_vma_walk_hole, + .hugetlb_entry = hmm_vma_walk_hugetlb_entry, +}; -/* - * hmm_range_fault() - try to fault some address in a virtual address range - * @range: range being faulted - * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem) - * Return: number of valid pages in range->pfns[] (from range start - * address). This may be zero. If the return value is negative, - * then one of the following values may be returned: +/** + * hmm_range_fault - try to fault some address in a virtual address range + * @range: range being faulted + * @flags: HMM_FAULT_* flags * - * -EINVAL invalid arguments or mm or virtual address are in an - * invalid vma (for instance device file vma). - * -ENOMEM: Out of memory. - * -EPERM: Invalid permission (for instance asking for write and - * range is read only). - * -EAGAIN: If you need to retry and mmap_sem was drop. This can only - * happens if block argument is false. - * -EBUSY: If the the range is being invalidated and you should wait - * for invalidation to finish. - * -EFAULT: Invalid (ie either no valid vma or it is illegal to access - * that range), number of valid pages in range->pfns[] (from - * range start address). + * Return: the number of valid pages in range->pfns[] (from range start + * address), which may be zero. On error one of the following status codes + * can be returned: + * + * -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma + * (e.g., device file vma). + * -ENOMEM: Out of memory. + * -EPERM: Invalid permission (e.g., asking for write and range is read + * only). + * -EAGAIN: A page fault needs to be retried and mmap_sem was dropped. + * -EBUSY: The range has been invalidated and the caller needs to wait for + * the invalidation to finish. + * -EFAULT: Invalid (i.e., either no valid vma or it is illegal to access + * that range) number of valid pages in range->pfns[] (from + * range start address). * * This is similar to a regular CPU page fault except that it will not trigger * any memory migration if the memory being faulted is not accessible by CPUs @@ -1048,37 +887,26 @@ EXPORT_SYMBOL(hmm_range_snapshot); * On error, for one virtual address in the range, the function will mark the * corresponding HMM pfn entry with an error flag. */ -long hmm_range_fault(struct hmm_range *range, bool block) +long hmm_range_fault(struct hmm_range *range, unsigned int flags) { const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP; unsigned long start = range->start, end; struct hmm_vma_walk hmm_vma_walk; struct hmm *hmm = range->hmm; struct vm_area_struct *vma; - struct mm_walk mm_walk; int ret; - lockdep_assert_held(&hmm->mm->mmap_sem); + lockdep_assert_held(&hmm->mmu_notifier.mm->mmap_sem); do { /* If range is no longer valid force retry. */ if (!range->valid) return -EBUSY; - vma = find_vma(hmm->mm, start); + vma = find_vma(hmm->mmu_notifier.mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) return -EFAULT; - if (is_vm_hugetlb_page(vma)) { - if (huge_page_shift(hstate_vma(vma)) != - range->page_shift && - range->page_shift != PAGE_SHIFT) - return -EINVAL; - } else { - if (range->page_shift != PAGE_SHIFT) - return -EINVAL; - } - if (!(vma->vm_flags & VM_READ)) { /* * If vma do not allow read access, then assume that it @@ -1090,27 +918,18 @@ long hmm_range_fault(struct hmm_range *range, bool block) return -EPERM; } - range->vma = vma; hmm_vma_walk.pgmap = NULL; hmm_vma_walk.last = start; - hmm_vma_walk.fault = true; - hmm_vma_walk.block = block; + hmm_vma_walk.flags = flags; hmm_vma_walk.range = range; - mm_walk.private = &hmm_vma_walk; end = min(range->end, vma->vm_end); - mm_walk.vma = vma; - mm_walk.mm = vma->vm_mm; - mm_walk.pte_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.hugetlb_entry = NULL; - mm_walk.pud_entry = hmm_vma_walk_pud; - mm_walk.pmd_entry = hmm_vma_walk_pmd; - mm_walk.pte_hole = hmm_vma_walk_hole; - mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry; + walk_page_range(vma->vm_mm, start, end, &hmm_walk_ops, + &hmm_vma_walk); do { - ret = walk_page_range(start, end, &mm_walk); + ret = walk_page_range(vma->vm_mm, start, end, + &hmm_walk_ops, &hmm_vma_walk); start = hmm_vma_walk.last; /* Keep trying while the range is valid. */ @@ -1133,25 +952,22 @@ long hmm_range_fault(struct hmm_range *range, bool block) EXPORT_SYMBOL(hmm_range_fault); /** - * hmm_range_dma_map() - hmm_range_fault() and dma map page all in one. - * @range: range being faulted - * @device: device against to dma map page to - * @daddrs: dma address of mapped pages - * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem) - * Return: number of pages mapped on success, -EAGAIN if mmap_sem have been - * drop and you need to try again, some other error value otherwise + * hmm_range_dma_map - hmm_range_fault() and dma map page all in one. + * @range: range being faulted + * @device: device to map page to + * @daddrs: array of dma addresses for the mapped pages + * @flags: HMM_FAULT_* * - * Note same usage pattern as hmm_range_fault(). + * Return: the number of pages mapped on success (including zero), or any + * status return from hmm_range_fault() otherwise. */ -long hmm_range_dma_map(struct hmm_range *range, - struct device *device, - dma_addr_t *daddrs, - bool block) +long hmm_range_dma_map(struct hmm_range *range, struct device *device, + dma_addr_t *daddrs, unsigned int flags) { unsigned long i, npages, mapped; long ret; - ret = hmm_range_fault(range, block); + ret = hmm_range_fault(range, flags); if (ret <= 0) return ret ? ret : -EBUSY; @@ -1222,7 +1038,6 @@ EXPORT_SYMBOL(hmm_range_dma_map); /** * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map() * @range: range being unmapped - * @vma: the vma against which the range (optional) * @device: device against which dma map was done * @daddrs: dma address of mapped pages * @dirty: dirty page if it had the write flag set @@ -1234,7 +1049,6 @@ EXPORT_SYMBOL(hmm_range_dma_map); * concurrent mmu notifier or sync_cpu_device_pagetables() to make progress. */ long hmm_range_dma_unmap(struct hmm_range *range, - struct vm_area_struct *vma, struct device *device, dma_addr_t *daddrs, bool dirty) diff --git a/mm/madvise.c b/mm/madvise.c index bac973b9f2cc..88babcc384b9 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -21,6 +21,7 @@ #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> +#include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> @@ -226,19 +227,9 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, return 0; } -static void force_swapin_readahead(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - struct mm_walk walk = { - .mm = vma->vm_mm, - .pmd_entry = swapin_walk_pmd_entry, - .private = vma, - }; - - walk_page_range(start, end, &walk); - - lru_add_drain(); /* Push any new pages onto the LRU now */ -} +static const struct mm_walk_ops swapin_walk_ops = { + .pmd_entry = swapin_walk_pmd_entry, +}; static void force_shm_swapin_readahead(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -281,7 +272,8 @@ static long madvise_willneed(struct vm_area_struct *vma, *prev = vma; #ifdef CONFIG_SWAP if (!file) { - force_swapin_readahead(vma, start, end); + walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma); + lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } @@ -450,20 +442,9 @@ next: return 0; } -static void madvise_free_page_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, - unsigned long addr, unsigned long end) -{ - struct mm_walk free_walk = { - .pmd_entry = madvise_free_pte_range, - .mm = vma->vm_mm, - .private = tlb, - }; - - tlb_start_vma(tlb, vma); - walk_page_range(addr, end, &free_walk); - tlb_end_vma(tlb, vma); -} +static const struct mm_walk_ops madvise_free_walk_ops = { + .pmd_entry = madvise_free_pte_range, +}; static int madvise_free_single_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) @@ -490,7 +471,10 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); - madvise_free_page_range(&tlb, vma, range.start, range.end); + 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); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, range.start, range.end); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 597d58101872..f3c15bb07cce 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -25,7 +25,7 @@ #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/cgroup.h> -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <linux/hugetlb.h> @@ -5499,17 +5499,16 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, return 0; } +static const struct mm_walk_ops precharge_walk_ops = { + .pmd_entry = mem_cgroup_count_precharge_pte_range, +}; + static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) { unsigned long precharge; - struct mm_walk mem_cgroup_count_precharge_walk = { - .pmd_entry = mem_cgroup_count_precharge_pte_range, - .mm = mm, - }; down_read(&mm->mmap_sem); - walk_page_range(0, mm->highest_vm_end, - &mem_cgroup_count_precharge_walk); + walk_page_range(mm, 0, mm->highest_vm_end, &precharge_walk_ops, NULL); up_read(&mm->mmap_sem); precharge = mc.precharge; @@ -5778,13 +5777,12 @@ put: /* get_mctgt_type() gets the page */ return ret; } +static const struct mm_walk_ops charge_walk_ops = { + .pmd_entry = mem_cgroup_move_charge_pte_range, +}; + static void mem_cgroup_move_charge(void) { - struct mm_walk mem_cgroup_move_charge_walk = { - .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mc.mm, - }; - lru_add_drain_all(); /* * Signal lock_page_memcg() to take the memcg's move_lock @@ -5810,7 +5808,8 @@ retry: * When we have consumed all precharges and failed in doing * additional charge, the page walk just aborts. */ - walk_page_range(0, mc.mm->highest_vm_end, &mem_cgroup_move_charge_walk); + walk_page_range(mc.mm, 0, mc.mm->highest_vm_end, &charge_walk_ops, + NULL); up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 65e0874fce17..f000771558d8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -68,7 +68,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> @@ -655,6 +655,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, return 1; } +static const struct mm_walk_ops queue_pages_walk_ops = { + .hugetlb_entry = queue_pages_hugetlb, + .pmd_entry = queue_pages_pte_range, + .test_walk = queue_pages_test_walk, +}; + /* * Walk through page tables and collect pages to be migrated. * @@ -679,15 +685,8 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .nmask = nodes, .prev = NULL, }; - struct mm_walk queue_pages_walk = { - .hugetlb_entry = queue_pages_hugetlb, - .pmd_entry = queue_pages_pte_range, - .test_walk = queue_pages_test_walk, - .mm = mm, - .private = &qp, - }; - return walk_page_range(start, end, &queue_pages_walk); + return walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); } /* diff --git a/mm/memremap.c b/mm/memremap.c index ed70c4e8e52a..32c79b51af86 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -21,13 +21,13 @@ DEFINE_STATIC_KEY_FALSE(devmap_managed_key); EXPORT_SYMBOL(devmap_managed_key); static atomic_t devmap_managed_enable; -static void devmap_managed_enable_put(void *data) +static void devmap_managed_enable_put(void) { if (atomic_dec_and_test(&devmap_managed_enable)) static_branch_disable(&devmap_managed_key); } -static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +static int devmap_managed_enable_get(struct dev_pagemap *pgmap) { if (!pgmap->ops || !pgmap->ops->page_free) { WARN(1, "Missing page_free method\n"); @@ -36,13 +36,16 @@ static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgm if (atomic_inc_return(&devmap_managed_enable) == 1) static_branch_enable(&devmap_managed_key); - return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL); + return 0; } #else -static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +static int devmap_managed_enable_get(struct dev_pagemap *pgmap) { return -EINVAL; } +static void devmap_managed_enable_put(void) +{ +} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static void pgmap_array_delete(struct resource *res) @@ -99,10 +102,8 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) pgmap->ref = NULL; } -static void devm_memremap_pages_release(void *data) +void memunmap_pages(struct dev_pagemap *pgmap) { - struct dev_pagemap *pgmap = data; - struct device *dev = pgmap->dev; struct resource *res = &pgmap->res; unsigned long pfn; int nid; @@ -129,8 +130,14 @@ static void devm_memremap_pages_release(void *data) untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res)); pgmap_array_delete(res); - dev_WARN_ONCE(dev, pgmap->altmap.alloc, - "%s: failed to free all reserved pages\n", __func__); + WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n"); + devmap_managed_enable_put(); +} +EXPORT_SYMBOL_GPL(memunmap_pages); + +static void devm_memremap_pages_release(void *data) +{ + memunmap_pages(data); } static void dev_pagemap_percpu_release(struct percpu_ref *ref) @@ -141,27 +148,12 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref) complete(&pgmap->done); } -/** - * devm_memremap_pages - remap and provide memmap backing for the given resource - * @dev: hosting device for @res - * @pgmap: pointer to a struct dev_pagemap - * - * Notes: - * 1/ At a minimum the res and type members of @pgmap must be initialized - * by the caller before passing it to this function - * - * 2/ The altmap field may optionally be initialized, in which case - * PGMAP_ALTMAP_VALID must be set in pgmap->flags. - * - * 3/ The ref field may optionally be provided, in which pgmap->ref must be - * 'live' on entry and will be killed and reaped at - * devm_memremap_pages_release() time, or if this routine fails. - * - * 4/ res is expected to be a host memory range that could feasibly be - * treated as a "System RAM" range, i.e. not a device mmio range, but - * this is not enforced. +/* + * Not device managed version of dev_memremap_pages, undone by + * memunmap_pages(). Please use dev_memremap_pages if you have a struct + * device available. */ -void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) +void *memremap_pages(struct dev_pagemap *pgmap, int nid) { struct resource *res = &pgmap->res; struct dev_pagemap *conflict_pgmap; @@ -172,7 +164,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) .altmap = pgmap_altmap(pgmap), }; pgprot_t pgprot = PAGE_KERNEL; - int error, nid, is_ram; + int error, is_ram; bool need_devmap_managed = true; switch (pgmap->type) { @@ -220,14 +212,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) } if (need_devmap_managed) { - error = devmap_managed_enable_get(dev, pgmap); + error = devmap_managed_enable_get(pgmap); if (error) return ERR_PTR(error); } conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL); if (conflict_pgmap) { - dev_WARN(dev, "Conflicting mapping in same section\n"); + WARN(1, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); error = -ENOMEM; goto err_array; @@ -235,7 +227,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL); if (conflict_pgmap) { - dev_WARN(dev, "Conflicting mapping in same section\n"); + WARN(1, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); error = -ENOMEM; goto err_array; @@ -251,14 +243,11 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) goto err_array; } - pgmap->dev = dev; - error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end), pgmap, GFP_KERNEL)); if (error) goto err_array; - nid = dev_to_node(dev); if (nid < 0) nid = numa_mem_id(); @@ -314,12 +303,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) PHYS_PFN(res->start), PHYS_PFN(resource_size(res)), pgmap); percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); - - error = devm_add_action_or_reset(dev, devm_memremap_pages_release, - pgmap); - if (error) - return ERR_PTR(error); - return __va(res->start); err_add_memory: @@ -331,8 +314,46 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) err_array: dev_pagemap_kill(pgmap); dev_pagemap_cleanup(pgmap); + devmap_managed_enable_put(); return ERR_PTR(error); } +EXPORT_SYMBOL_GPL(memremap_pages); + +/** + * devm_memremap_pages - remap and provide memmap backing for the given resource + * @dev: hosting device for @res + * @pgmap: pointer to a struct dev_pagemap + * + * Notes: + * 1/ At a minimum the res and type members of @pgmap must be initialized + * by the caller before passing it to this function + * + * 2/ The altmap field may optionally be initialized, in which case + * PGMAP_ALTMAP_VALID must be set in pgmap->flags. + * + * 3/ The ref field may optionally be provided, in which pgmap->ref must be + * 'live' on entry and will be killed and reaped at + * devm_memremap_pages_release() time, or if this routine fails. + * + * 4/ res is expected to be a host memory range that could feasibly be + * treated as a "System RAM" range, i.e. not a device mmio range, but + * this is not enforced. + */ +void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) +{ + int error; + void *ret; + + ret = memremap_pages(pgmap, dev_to_node(dev)); + if (IS_ERR(ret)) + return ret; + + error = devm_add_action_or_reset(dev, devm_memremap_pages_release, + pgmap); + if (error) + return ERR_PTR(error); + return ret; +} EXPORT_SYMBOL_GPL(devm_memremap_pages); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) diff --git a/mm/migrate.c b/mm/migrate.c index a42858d8e00b..9f4ed4e985c1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -38,6 +38,7 @@ #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/gfp.h> +#include <linux/pagewalk.h> #include <linux/pfn_t.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> @@ -2119,17 +2120,7 @@ out_unlock: #endif /* CONFIG_NUMA */ -#if defined(CONFIG_MIGRATE_VMA_HELPER) -struct migrate_vma { - struct vm_area_struct *vma; - unsigned long *dst; - unsigned long *src; - unsigned long cpages; - unsigned long npages; - unsigned long start; - unsigned long end; -}; - +#ifdef CONFIG_DEVICE_PRIVATE static int migrate_vma_collect_hole(unsigned long start, unsigned long end, struct mm_walk *walk) @@ -2249,8 +2240,8 @@ again: goto next; page = device_private_entry_to_page(entry); - mpfn = migrate_pfn(page_to_pfn(page))| - MIGRATE_PFN_DEVICE | MIGRATE_PFN_MIGRATE; + mpfn = migrate_pfn(page_to_pfn(page)) | + MIGRATE_PFN_MIGRATE; if (is_write_device_private_entry(entry)) mpfn |= MIGRATE_PFN_WRITE; } else { @@ -2329,6 +2320,11 @@ next: return 0; } +static const struct mm_walk_ops migrate_vma_walk_ops = { + .pmd_entry = migrate_vma_collect_pmd, + .pte_hole = migrate_vma_collect_hole, +}; + /* * migrate_vma_collect() - collect pages over a range of virtual addresses * @migrate: migrate struct containing all migration information @@ -2340,21 +2336,15 @@ next: static void migrate_vma_collect(struct migrate_vma *migrate) { struct mmu_notifier_range range; - struct mm_walk mm_walk = { - .pmd_entry = migrate_vma_collect_pmd, - .pte_hole = migrate_vma_collect_hole, - .vma = migrate->vma, - .mm = migrate->vma->vm_mm, - .private = migrate, - }; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm, - migrate->start, - migrate->end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, + migrate->vma->vm_mm, migrate->start, migrate->end); mmu_notifier_invalidate_range_start(&range); - walk_page_range(migrate->start, migrate->end, &mm_walk); - mmu_notifier_invalidate_range_end(&range); + walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end, + &migrate_vma_walk_ops, migrate); + + mmu_notifier_invalidate_range_end(&range); migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT); } @@ -2577,6 +2567,110 @@ restore: } } +/** + * migrate_vma_setup() - prepare to migrate a range of memory + * @args: contains the vma, start, and and pfns arrays for the migration + * + * Returns: negative errno on failures, 0 when 0 or more pages were migrated + * without an error. + * + * Prepare to migrate a range of memory virtual address range by collecting all + * the pages backing each virtual address in the range, saving them inside the + * src array. Then lock those pages and unmap them. Once the pages are locked + * and unmapped, check whether each page is pinned or not. Pages that aren't + * pinned have the MIGRATE_PFN_MIGRATE flag set (by this function) in the + * corresponding src array entry. Then restores any pages that are pinned, by + * remapping and unlocking those pages. + * + * The caller should then allocate destination memory and copy source memory to + * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE + * flag set). Once these are allocated and copied, the caller must update each + * corresponding entry in the dst array with the pfn value of the destination + * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_LOCKED flags set + * (destination pages must have their struct pages locked, via lock_page()). + * + * Note that the caller does not have to migrate all the pages that are marked + * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from + * device memory to system memory. If the caller cannot migrate a device page + * back to system memory, then it must return VM_FAULT_SIGBUS, which has severe + * consequences for the userspace process, so it must be avoided if at all + * possible. + * + * For empty entries inside CPU page table (pte_none() or pmd_none() is true) we + * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus + * allowing the caller to allocate device memory for those unback virtual + * address. For this the caller simply has to allocate device memory and + * properly set the destination entry like for regular migration. Note that + * this can still fails and thus inside the device driver must check if the + * migration was successful for those entries after calling migrate_vma_pages() + * just like for regular migration. + * + * After that, the callers must call migrate_vma_pages() to go over each entry + * in the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag + * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set, + * then migrate_vma_pages() to migrate struct page information from the source + * struct page to the destination struct page. If it fails to migrate the + * struct page information, then it clears the MIGRATE_PFN_MIGRATE flag in the + * src array. + * + * At this point all successfully migrated pages have an entry in the src + * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst + * array entry with MIGRATE_PFN_VALID flag set. + * + * Once migrate_vma_pages() returns the caller may inspect which pages were + * successfully migrated, and which were not. Successfully migrated pages will + * have the MIGRATE_PFN_MIGRATE flag set for their src array entry. + * + * It is safe to update device page table after migrate_vma_pages() because + * both destination and source page are still locked, and the mmap_sem is held + * in read mode (hence no one can unmap the range being migrated). + * + * Once the caller is done cleaning up things and updating its page table (if it + * chose to do so, this is not an obligation) it finally calls + * migrate_vma_finalize() to update the CPU page table to point to new pages + * for successfully migrated pages or otherwise restore the CPU page table to + * point to the original source pages. + */ +int migrate_vma_setup(struct migrate_vma *args) +{ + long nr_pages = (args->end - args->start) >> PAGE_SHIFT; + + args->start &= PAGE_MASK; + args->end &= PAGE_MASK; + if (!args->vma || is_vm_hugetlb_page(args->vma) || + (args->vma->vm_flags & VM_SPECIAL) || vma_is_dax(args->vma)) + return -EINVAL; + if (nr_pages <= 0) + return -EINVAL; + if (args->start < args->vma->vm_start || + args->start >= args->vma->vm_end) + return -EINVAL; + if (args->end <= args->vma->vm_start || args->end > args->vma->vm_end) + return -EINVAL; + if (!args->src || !args->dst) + return -EINVAL; + + memset(args->src, 0, sizeof(*args->src) * nr_pages); + args->cpages = 0; + args->npages = 0; + + migrate_vma_collect(args); + + if (args->cpages) + migrate_vma_prepare(args); + if (args->cpages) + migrate_vma_unmap(args); + + /* + * At this point pages are locked and unmapped, and thus they have + * stable content and can safely be copied to destination memory that + * is allocated by the drivers. + */ + return 0; + +} +EXPORT_SYMBOL(migrate_vma_setup); + static void migrate_vma_insert_page(struct migrate_vma *migrate, unsigned long addr, struct page *page, @@ -2708,7 +2802,7 @@ abort: *src &= ~MIGRATE_PFN_MIGRATE; } -/* +/** * migrate_vma_pages() - migrate meta-data from src page to dst page * @migrate: migrate struct containing all migration information * @@ -2716,7 +2810,7 @@ abort: * struct page. This effectively finishes the migration from source page to the * destination page. */ -static void migrate_vma_pages(struct migrate_vma *migrate) +void migrate_vma_pages(struct migrate_vma *migrate) { const unsigned long npages = migrate->npages; const unsigned long start = migrate->start; @@ -2790,8 +2884,9 @@ static void migrate_vma_pages(struct migrate_vma *migrate) if (notified) mmu_notifier_invalidate_range_only_end(&range); } +EXPORT_SYMBOL(migrate_vma_pages); -/* +/** * migrate_vma_finalize() - restore CPU page table entry * @migrate: migrate struct containing all migration information * @@ -2802,7 +2897,7 @@ static void migrate_vma_pages(struct migrate_vma *migrate) * This also unlocks the pages and puts them back on the lru, or drops the extra * refcount, for device pages. */ -static void migrate_vma_finalize(struct migrate_vma *migrate) +void migrate_vma_finalize(struct migrate_vma *migrate) { const unsigned long npages = migrate->npages; unsigned long i; @@ -2845,124 +2940,5 @@ static void migrate_vma_finalize(struct migrate_vma *migrate) } } } - -/* - * migrate_vma() - migrate a range of memory inside vma - * - * @ops: migration callback for allocating destination memory and copying - * @vma: virtual memory area containing the range to be migrated - * @start: start address of the range to migrate (inclusive) - * @end: end address of the range to migrate (exclusive) - * @src: array of hmm_pfn_t containing source pfns - * @dst: array of hmm_pfn_t containing destination pfns - * @private: pointer passed back to each of the callback - * Returns: 0 on success, error code otherwise - * - * This function tries to migrate a range of memory virtual address range, using - * callbacks to allocate and copy memory from source to destination. First it - * collects all the pages backing each virtual address in the range, saving this - * inside the src array. Then it locks those pages and unmaps them. Once the pages - * are locked and unmapped, it checks whether each page is pinned or not. Pages - * that aren't pinned have the MIGRATE_PFN_MIGRATE flag set (by this function) - * in the corresponding src array entry. It then restores any pages that are - * pinned, by remapping and unlocking those pages. - * - * At this point it calls the alloc_and_copy() callback. For documentation on - * what is expected from that callback, see struct migrate_vma_ops comments in - * include/linux/migrate.h - * - * After the alloc_and_copy() callback, this function goes over each entry in - * the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag - * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set, - * then the function tries to migrate struct page information from the source - * struct page to the destination struct page. If it fails to migrate the struct - * page information, then it clears the MIGRATE_PFN_MIGRATE flag in the src - * array. - * - * At this point all successfully migrated pages have an entry in the src - * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst - * array entry with MIGRATE_PFN_VALID flag set. - * - * It then calls the finalize_and_map() callback. See comments for "struct - * migrate_vma_ops", in include/linux/migrate.h for details about - * finalize_and_map() behavior. - * - * After the finalize_and_map() callback, for successfully migrated pages, this - * function updates the CPU page table to point to new pages, otherwise it - * restores the CPU page table to point to the original source pages. - * - * Function returns 0 after the above steps, even if no pages were migrated - * (The function only returns an error if any of the arguments are invalid.) - * - * Both src and dst array must be big enough for (end - start) >> PAGE_SHIFT - * unsigned long entries. - */ -int migrate_vma(const struct migrate_vma_ops *ops, - struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - unsigned long *src, - unsigned long *dst, - void *private) -{ - struct migrate_vma migrate; - - /* Sanity check the arguments */ - start &= PAGE_MASK; - end &= PAGE_MASK; - if (!vma || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) || - vma_is_dax(vma)) - return -EINVAL; - if (start < vma->vm_start || start >= vma->vm_end) - return -EINVAL; - if (end <= vma->vm_start || end > vma->vm_end) - return -EINVAL; - if (!ops || !src || !dst || start >= end) - return -EINVAL; - - memset(src, 0, sizeof(*src) * ((end - start) >> PAGE_SHIFT)); - migrate.src = src; - migrate.dst = dst; - migrate.start = start; - migrate.npages = 0; - migrate.cpages = 0; - migrate.end = end; - migrate.vma = vma; - - /* Collect, and try to unmap source pages */ - migrate_vma_collect(&migrate); - if (!migrate.cpages) - return 0; - - /* Lock and isolate page */ - migrate_vma_prepare(&migrate); - if (!migrate.cpages) - return 0; - - /* Unmap pages */ - migrate_vma_unmap(&migrate); - if (!migrate.cpages) - return 0; - - /* - * At this point pages are locked and unmapped, and thus they have - * stable content and can safely be copied to destination memory that - * is allocated by the callback. - * - * Note that migration can fail in migrate_vma_struct_page() for each - * individual page. - */ - ops->alloc_and_copy(vma, src, dst, start, end, private); - - /* This does the real migration of struct page */ - migrate_vma_pages(&migrate); - - ops->finalize_and_map(vma, src, dst, start, end, private); - - /* Unlock and remap pages */ - migrate_vma_finalize(&migrate); - - return 0; -} -EXPORT_SYMBOL(migrate_vma); -#endif /* defined(MIGRATE_VMA_HELPER) */ +EXPORT_SYMBOL(migrate_vma_finalize); +#endif /* CONFIG_DEVICE_PRIVATE */ diff --git a/mm/mincore.c b/mm/mincore.c index 4fe91d497436..f9a9dbe8cd33 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -10,7 +10,7 @@ */ #include <linux/pagemap.h> #include <linux/gfp.h> -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/mman.h> #include <linux/syscalls.h> #include <linux/swap.h> @@ -193,6 +193,12 @@ static inline bool can_do_mincore(struct vm_area_struct *vma) inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0; } +static const struct mm_walk_ops mincore_walk_ops = { + .pmd_entry = mincore_pte_range, + .pte_hole = mincore_unmapped_range, + .hugetlb_entry = mincore_hugetlb, +}; + /* * Do a chunk of "sys_mincore()". We've already checked * all the arguments, we hold the mmap semaphore: we should @@ -203,12 +209,6 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v struct vm_area_struct *vma; unsigned long end; int err; - struct mm_walk mincore_walk = { - .pmd_entry = mincore_pte_range, - .pte_hole = mincore_unmapped_range, - .hugetlb_entry = mincore_hugetlb, - .private = vec, - }; vma = find_vma(current->mm, addr); if (!vma || addr < vma->vm_start) @@ -219,8 +219,7 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v memset(vec, 1, pages); return pages; } - mincore_walk.mm = vma->vm_mm; - err = walk_page_range(addr, end, &mincore_walk); + err = walk_page_range(vma->vm_mm, addr, end, &mincore_walk_ops, vec); if (err < 0) return err; return (end - addr) >> PAGE_SHIFT; diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index b5670620aea0..7fde88695f35 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -21,17 +21,11 @@ /* global SRCU for all MMs */ DEFINE_STATIC_SRCU(srcu); -/* - * This function allows mmu_notifier::release callback to delay a call to - * a function that will free appropriate resources. The function must be - * quick and must not block. - */ -void mmu_notifier_call_srcu(struct rcu_head *rcu, - void (*func)(struct rcu_head *rcu)) -{ - call_srcu(&srcu, rcu, func); -} -EXPORT_SYMBOL_GPL(mmu_notifier_call_srcu); +#ifdef CONFIG_LOCKDEP +struct lockdep_map __mmu_notifier_invalidate_range_start_map = { + .name = "mmu_notifier_invalidate_range_start" +}; +#endif /* * This function can't run concurrently against mmu_notifier_register @@ -174,11 +168,19 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(mn, &range->mm->mmu_notifier_mm->list, hlist) { if (mn->ops->invalidate_range_start) { - int _ret = mn->ops->invalidate_range_start(mn, range); + int _ret; + + if (!mmu_notifier_range_blockable(range)) + non_block_start(); + _ret = mn->ops->invalidate_range_start(mn, range); + if (!mmu_notifier_range_blockable(range)) + non_block_end(); if (_ret) { pr_info("%pS callback failed with %d in %sblockable context.\n", mn->ops->invalidate_range_start, _ret, !mmu_notifier_range_blockable(range) ? "non-" : ""); + WARN_ON(mmu_notifier_range_blockable(range) || + ret != -EAGAIN); ret = _ret; } } @@ -187,7 +189,6 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) return ret; } -EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_start); void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range, bool only_end) @@ -195,6 +196,7 @@ void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range, struct mmu_notifier *mn; int id; + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(mn, &range->mm->mmu_notifier_mm->list, hlist) { /* @@ -214,12 +216,17 @@ void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range, mn->ops->invalidate_range(mn, range->mm, range->start, range->end); - if (mn->ops->invalidate_range_end) + if (mn->ops->invalidate_range_end) { + if (!mmu_notifier_range_blockable(range)) + non_block_start(); mn->ops->invalidate_range_end(mn, range); + if (!mmu_notifier_range_blockable(range)) + non_block_end(); + } } srcu_read_unlock(&srcu, id); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); } -EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end); void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) @@ -234,35 +241,49 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm, } srcu_read_unlock(&srcu, id); } -EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range); -static int do_mmu_notifier_register(struct mmu_notifier *mn, - struct mm_struct *mm, - int take_mmap_sem) +/* + * 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) { - struct mmu_notifier_mm *mmu_notifier_mm; + struct mmu_notifier_mm *mmu_notifier_mm = NULL; int ret; + lockdep_assert_held_write(&mm->mmap_sem); 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 (IS_ENABLED(CONFIG_LOCKDEP)) { + fs_reclaim_acquire(GFP_KERNEL); + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); + fs_reclaim_release(GFP_KERNEL); + } - if (take_mmap_sem) - down_write(&mm->mmap_sem); - ret = mm_take_all_locks(mm); - if (unlikely(ret)) - goto out_clean; + mn->mm = mm; + mn->users = 1; + + if (!mm->mmu_notifier_mm) { + /* + * kmalloc cannot be called under mm_take_all_locks(), but we + * know that mm->mmu_notifier_mm can't change while we hold + * the write side of the mmap_sem. + */ + mmu_notifier_mm = + kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL); + if (!mmu_notifier_mm) + return -ENOMEM; - 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; } + + ret = mm_take_all_locks(mm); + if (unlikely(ret)) + goto out_clean; + + /* Pairs with the mmdrop in mmu_notifier_unregister_* */ mmgrab(mm); /* @@ -273,48 +294,118 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn, * We can't race against any other mmu notifier method either * thanks to mm_take_all_locks(). */ + if (mmu_notifier_mm) + mm->mmu_notifier_mm = mmu_notifier_mm; + spin_lock(&mm->mmu_notifier_mm->lock); hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list); spin_unlock(&mm->mmu_notifier_mm->lock); mm_drop_all_locks(mm); + BUG_ON(atomic_read(&mm->mm_users) <= 0); + return 0; + out_clean: - if (take_mmap_sem) - up_write(&mm->mmap_sem); kfree(mmu_notifier_mm); -out: - BUG_ON(atomic_read(&mm->mm_users) <= 0); return ret; } +EXPORT_SYMBOL_GPL(__mmu_notifier_register); -/* +/** + * mmu_notifier_register - Register a notifier on a mm + * @mn: The notifier to attach + * @mm: The mm to attach the notifier to + * * 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. + * returns. + * + * mmu_notifier_unregister() or mmu_notifier_put() must be always called to + * unregister the notifier. + * + * While the caller has a mmu_notifier get the mn->mm pointer will remain + * valid, and can be converted to an active mm pointer via mmget_not_zero(). */ int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) { - return do_mmu_notifier_register(mn, mm, 1); + int ret; + + down_write(&mm->mmap_sem); + ret = __mmu_notifier_register(mn, mm); + up_write(&mm->mmap_sem); + return ret; } EXPORT_SYMBOL_GPL(mmu_notifier_register); -/* - * Same as mmu_notifier_register but here the caller must hold the - * mmap_sem in write mode. +static struct mmu_notifier * +find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops) +{ + struct mmu_notifier *mn; + + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_for_each_entry_rcu (mn, &mm->mmu_notifier_mm->list, hlist) { + if (mn->ops != ops) + continue; + + if (likely(mn->users != UINT_MAX)) + mn->users++; + else + mn = ERR_PTR(-EOVERFLOW); + spin_unlock(&mm->mmu_notifier_mm->lock); + return mn; + } + spin_unlock(&mm->mmu_notifier_mm->lock); + return NULL; +} + +/** + * mmu_notifier_get_locked - Return the single struct mmu_notifier for + * the mm & ops + * @ops: The operations struct being subscribe with + * @mm : The mm to attach notifiers too + * + * This function either allocates a new mmu_notifier via + * ops->alloc_notifier(), or returns an already existing notifier on the + * list. The value of the ops pointer is used to determine when two notifiers + * are the same. + * + * Each call to mmu_notifier_get() must be paired with a call to + * mmu_notifier_put(). The caller must hold the write side of mm->mmap_sem. + * + * While the caller has a mmu_notifier get the mm pointer will remain valid, + * and can be converted to an active mm pointer via mmget_not_zero(). */ -int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) +struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, + struct mm_struct *mm) { - return do_mmu_notifier_register(mn, mm, 0); + struct mmu_notifier *mn; + int ret; + + lockdep_assert_held_write(&mm->mmap_sem); + + if (mm->mmu_notifier_mm) { + mn = find_get_mmu_notifier(mm, ops); + if (mn) + return mn; + } + + mn = ops->alloc_notifier(mm); + if (IS_ERR(mn)) + return mn; + mn->ops = ops; + ret = __mmu_notifier_register(mn, mm); + if (ret) + goto out_free; + return mn; +out_free: + mn->ops->free_notifier(mn); + return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(__mmu_notifier_register); +EXPORT_SYMBOL_GPL(mmu_notifier_get_locked); /* this is called after the last mmu_notifier_unregister() returned */ void __mmu_notifier_mm_destroy(struct mm_struct *mm) @@ -375,24 +466,74 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmu_notifier_unregister); -/* - * Same as mmu_notifier_unregister but no callback and no srcu synchronization. +static void mmu_notifier_free_rcu(struct rcu_head *rcu) +{ + struct mmu_notifier *mn = container_of(rcu, struct mmu_notifier, rcu); + struct mm_struct *mm = mn->mm; + + mn->ops->free_notifier(mn); + /* Pairs with the get in __mmu_notifier_register() */ + mmdrop(mm); +} + +/** + * mmu_notifier_put - Release the reference on the notifier + * @mn: The notifier to act on + * + * This function must be paired with each mmu_notifier_get(), it releases the + * reference obtained by the get. If this is the last reference then process + * to free the notifier will be run asynchronously. + * + * Unlike mmu_notifier_unregister() the get/put flow only calls ops->release + * when the mm_struct is destroyed. Instead free_notifier is always called to + * release any resources held by the user. + * + * As ops->release is not guaranteed to be called, the user must ensure that + * all sptes are dropped, and no new sptes can be established before + * mmu_notifier_put() is called. + * + * This function can be called from the ops->release callback, however the + * caller must still ensure it is called pairwise with mmu_notifier_get(). + * + * Modules calling this function must call mmu_notifier_synchronize() in + * their __exit functions to ensure the async work is completed. */ -void mmu_notifier_unregister_no_release(struct mmu_notifier *mn, - struct mm_struct *mm) +void mmu_notifier_put(struct mmu_notifier *mn) { + struct mm_struct *mm = mn->mm; + spin_lock(&mm->mmu_notifier_mm->lock); - /* - * Can not use list_del_rcu() since __mmu_notifier_release - * can delete it before we hold the lock. - */ + if (WARN_ON(!mn->users) || --mn->users) + goto out_unlock; hlist_del_init_rcu(&mn->hlist); spin_unlock(&mm->mmu_notifier_mm->lock); - BUG_ON(atomic_read(&mm->mm_count) <= 0); - mmdrop(mm); + call_srcu(&srcu, &mn->rcu, mmu_notifier_free_rcu); + return; + +out_unlock: + spin_unlock(&mm->mmu_notifier_mm->lock); +} +EXPORT_SYMBOL_GPL(mmu_notifier_put); + +/** + * mmu_notifier_synchronize - Ensure all mmu_notifiers are freed + * + * This function ensures that all outstanding async SRU work from + * mmu_notifier_put() is completed. After it returns any mmu_notifier_ops + * associated with an unused mmu_notifier will no longer be called. + * + * Before using the caller must ensure that all of its mmu_notifiers have been + * fully released via mmu_notifier_put(). + * + * Modules using the mmu_notifier_put() API should call this in their __exit + * function to avoid module unloading races. + */ +void mmu_notifier_synchronize(void) +{ + synchronize_srcu(&srcu); } -EXPORT_SYMBOL_GPL(mmu_notifier_unregister_no_release); +EXPORT_SYMBOL_GPL(mmu_notifier_synchronize); bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range) diff --git a/mm/mprotect.c b/mm/mprotect.c index bf38dfbbb4b4..675e5d34a507 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -9,7 +9,7 @@ * (C) Copyright 2002 Red Hat Inc, All Rights Reserved */ -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/hugetlb.h> #include <linux/shm.h> #include <linux/mman.h> @@ -329,20 +329,11 @@ static int prot_none_test(unsigned long addr, unsigned long next, return 0; } -static int prot_none_walk(struct vm_area_struct *vma, unsigned long start, - unsigned long end, unsigned long newflags) -{ - pgprot_t new_pgprot = vm_get_page_prot(newflags); - struct mm_walk prot_none_walk = { - .pte_entry = prot_none_pte_entry, - .hugetlb_entry = prot_none_hugetlb_entry, - .test_walk = prot_none_test, - .mm = current->mm, - .private = &new_pgprot, - }; - - return walk_page_range(start, end, &prot_none_walk); -} +static const struct mm_walk_ops prot_none_walk_ops = { + .pte_entry = prot_none_pte_entry, + .hugetlb_entry = prot_none_hugetlb_entry, + .test_walk = prot_none_test, +}; int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, @@ -369,7 +360,10 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, if (arch_has_pfn_modify_check() && (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) { - error = prot_none_walk(vma, start, end, newflags); + pgprot_t new_pgprot = vm_get_page_prot(newflags); + + error = walk_page_range(current->mm, start, end, + &prot_none_walk_ops, &new_pgprot); if (error) return error; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6991ccec9c32..ff5484fdbdf9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5971,7 +5971,7 @@ void __ref memmap_init_zone_device(struct zone *zone, } } - pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev), + pr_info("%s initialised %lu pages in %ums\n", __func__, size, jiffies_to_msecs(jiffies - start)); } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index c3084ff2569d..d48c2a986ea3 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/mm.h> +#include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/sched.h> #include <linux/hugetlb.h> @@ -9,10 +9,11 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, { pte_t *pte; int err = 0; + const struct mm_walk_ops *ops = walk->ops; pte = pte_offset_map(pmd, addr); for (;;) { - err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk); + err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; addr += PAGE_SIZE; @@ -30,6 +31,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, { pmd_t *pmd; unsigned long next; + const struct mm_walk_ops *ops = walk->ops; int err = 0; pmd = pmd_offset(pud, addr); @@ -37,8 +39,8 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, again: next = pmd_addr_end(addr, end); if (pmd_none(*pmd) || !walk->vma) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; @@ -47,8 +49,8 @@ again: * This implies that each ->pmd_entry() handler * needs to know about pmd_trans_huge() pmds */ - if (walk->pmd_entry) - err = walk->pmd_entry(pmd, addr, next, walk); + if (ops->pmd_entry) + err = ops->pmd_entry(pmd, addr, next, walk); if (err) break; @@ -56,7 +58,7 @@ again: * Check this here so we only break down trans_huge * pages when we _need_ to */ - if (!walk->pte_entry) + if (!ops->pte_entry) continue; split_huge_pmd(walk->vma, pmd, addr); @@ -75,6 +77,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, { pud_t *pud; unsigned long next; + const struct mm_walk_ops *ops = walk->ops; int err = 0; pud = pud_offset(p4d, addr); @@ -82,18 +85,18 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, again: next = pud_addr_end(addr, end); if (pud_none(*pud) || !walk->vma) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; } - if (walk->pud_entry) { + if (ops->pud_entry) { spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma); if (ptl) { - err = walk->pud_entry(pud, addr, next, walk); + err = ops->pud_entry(pud, addr, next, walk); spin_unlock(ptl); if (err) break; @@ -105,7 +108,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pud)) goto again; - if (walk->pmd_entry || walk->pte_entry) + if (ops->pmd_entry || ops->pte_entry) err = walk_pmd_range(pud, addr, next, walk); if (err) break; @@ -119,19 +122,20 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, { p4d_t *p4d; unsigned long next; + const struct mm_walk_ops *ops = walk->ops; int err = 0; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; } - if (walk->pmd_entry || walk->pte_entry) + if (ops->pmd_entry || ops->pte_entry) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -145,19 +149,20 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, { pgd_t *pgd; unsigned long next; + const struct mm_walk_ops *ops = walk->ops; int err = 0; pgd = pgd_offset(walk->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; continue; } - if (walk->pmd_entry || walk->pte_entry) + if (ops->pmd_entry || ops->pte_entry) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; @@ -183,6 +188,7 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, unsigned long hmask = huge_page_mask(h); unsigned long sz = huge_page_size(h); pte_t *pte; + const struct mm_walk_ops *ops = walk->ops; int err = 0; do { @@ -190,9 +196,9 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, pte = huge_pte_offset(walk->mm, addr & hmask, sz); if (pte) - err = walk->hugetlb_entry(pte, hmask, addr, next, walk); - else if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); + err = ops->hugetlb_entry(pte, hmask, addr, next, walk); + else if (ops->pte_hole) + err = ops->pte_hole(addr, next, walk); if (err) break; @@ -220,9 +226,10 @@ static int walk_page_test(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; + const struct mm_walk_ops *ops = walk->ops; - if (walk->test_walk) - return walk->test_walk(start, end, walk); + if (ops->test_walk) + return ops->test_walk(start, end, walk); /* * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP @@ -234,8 +241,8 @@ static int walk_page_test(unsigned long start, unsigned long end, */ if (vma->vm_flags & VM_PFNMAP) { int err = 1; - if (walk->pte_hole) - err = walk->pte_hole(start, end, walk); + if (ops->pte_hole) + err = ops->pte_hole(start, end, walk); return err ? err : 1; } return 0; @@ -248,7 +255,7 @@ static int __walk_page_range(unsigned long start, unsigned long end, struct vm_area_struct *vma = walk->vma; if (vma && is_vm_hugetlb_page(vma)) { - if (walk->hugetlb_entry) + if (walk->ops->hugetlb_entry) err = walk_hugetlb_range(start, end, walk); } else err = walk_pgd_range(start, end, walk); @@ -258,11 +265,13 @@ static int __walk_page_range(unsigned long start, unsigned long end, /** * walk_page_range - walk page table with caller specific callbacks - * @start: start address of the virtual address range - * @end: end address of the virtual address range - * @walk: mm_walk structure defining the callbacks and the target address space + * @mm: mm_struct representing the target process of page table walk + * @start: start address of the virtual address range + * @end: end address of the virtual address range + * @ops: operation to call during the walk + * @private: private data for callbacks' usage * - * Recursively walk the page table tree of the process represented by @walk->mm + * Recursively walk the page table tree of the process represented by @mm * within the virtual address range [@start, @end). During walking, we can do * some caller-specific works for each entry, by setting up pmd_entry(), * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these @@ -278,47 +287,52 @@ static int __walk_page_range(unsigned long start, unsigned long end, * * Before starting to walk page table, some callers want to check whether * they really want to walk over the current vma, typically by checking - * its vm_flags. walk_page_test() and @walk->test_walk() are used for this + * its vm_flags. walk_page_test() and @ops->test_walk() are used for this * purpose. * * struct mm_walk keeps current values of some common data like vma and pmd, * which are useful for the access from callbacks. If you want to pass some - * caller-specific data to callbacks, @walk->private should be helpful. + * caller-specific data to callbacks, @private should be helpful. * * Locking: - * Callers of walk_page_range() and walk_page_vma() should hold - * @walk->mm->mmap_sem, because these function traverse vma list and/or - * access to vma's data. + * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_sem, + * because these function traverse vma list and/or access to vma's data. */ -int walk_page_range(unsigned long start, unsigned long end, - struct mm_walk *walk) +int walk_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private) { int err = 0; unsigned long next; struct vm_area_struct *vma; + struct mm_walk walk = { + .ops = ops, + .mm = mm, + .private = private, + }; if (start >= end) return -EINVAL; - if (!walk->mm) + if (!walk.mm) return -EINVAL; - VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm); + lockdep_assert_held(&walk.mm->mmap_sem); - vma = find_vma(walk->mm, start); + vma = find_vma(walk.mm, start); do { if (!vma) { /* after the last vma */ - walk->vma = NULL; + walk.vma = NULL; next = end; } else if (start < vma->vm_start) { /* outside vma */ - walk->vma = NULL; + walk.vma = NULL; next = min(end, vma->vm_start); } else { /* inside vma */ - walk->vma = vma; + walk.vma = vma; next = min(end, vma->vm_end); vma = vma->vm_next; - err = walk_page_test(start, next, walk); + err = walk_page_test(start, next, &walk); if (err > 0) { /* * positive return values are purely for @@ -331,28 +345,34 @@ int walk_page_range(unsigned long start, unsigned long end, if (err < 0) break; } - if (walk->vma || walk->pte_hole) - err = __walk_page_range(start, next, walk); + if (walk.vma || walk.ops->pte_hole) + err = __walk_page_range(start, next, &walk); if (err) break; } while (start = next, start < end); return err; } -int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk) +int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, + void *private) { + struct mm_walk walk = { + .ops = ops, + .mm = vma->vm_mm, + .vma = vma, + .private = private, + }; int err; - if (!walk->mm) + if (!walk.mm) return -EINVAL; - VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); - VM_BUG_ON(!vma); - walk->vma = vma; - err = walk_page_test(vma->vm_start, vma->vm_end, walk); + lockdep_assert_held(&walk.mm->mmap_sem); + + err = walk_page_test(vma->vm_start, vma->vm_end, &walk); if (err > 0) return 0; if (err < 0) return err; - return __walk_page_range(vma->vm_start, vma->vm_end, walk); + return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } |