diff options
Diffstat (limited to 'mm/hmm.c')
| -rw-r--r-- | mm/hmm.c | 1086 |
1 files changed, 737 insertions, 349 deletions
@@ -30,6 +30,7 @@ #include <linux/hugetlb.h> #include <linux/memremap.h> #include <linux/jump_label.h> +#include <linux/dma-mapping.h> #include <linux/mmu_notifier.h> #include <linux/memory_hotplug.h> @@ -38,54 +39,48 @@ #if IS_ENABLED(CONFIG_HMM_MIRROR) static const struct mmu_notifier_ops hmm_mmu_notifier_ops; -/* - * struct hmm - HMM per mm struct - * - * @mm: mm struct this HMM struct is bound to - * @lock: lock protecting ranges list - * @ranges: list of range being snapshotted - * @mirrors: list of mirrors for this mm - * @mmu_notifier: mmu notifier to track updates to CPU page table - * @mirrors_sem: read/write semaphore protecting the mirrors list - */ -struct hmm { - struct mm_struct *mm; - spinlock_t lock; - struct list_head ranges; - struct list_head mirrors; - struct mmu_notifier mmu_notifier; - struct rw_semaphore mirrors_sem; -}; +static inline struct hmm *mm_get_hmm(struct mm_struct *mm) +{ + struct hmm *hmm = READ_ONCE(mm->hmm); -/* - * hmm_register - register HMM against an mm (HMM internal) + if (hmm && kref_get_unless_zero(&hmm->kref)) + return hmm; + + return NULL; +} + +/** + * 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. It allocates an - * HMM struct if mm does not have one, and initializes it. + * 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_register(struct mm_struct *mm) +static struct hmm *hmm_get_or_create(struct mm_struct *mm) { - struct hmm *hmm = READ_ONCE(mm->hmm); + struct hmm *hmm = mm_get_hmm(mm); bool cleanup = false; - /* - * The hmm struct can only be freed once the mm_struct goes away, - * hence we should always have pre-allocated an new hmm struct - * above. - */ if (hmm) return hmm; hmm = kmalloc(sizeof(*hmm), GFP_KERNEL); if (!hmm) return NULL; + 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->lock); + mutex_init(&hmm->lock); + kref_init(&hmm->kref); + hmm->notifiers = 0; + hmm->dead = false; hmm->mm = mm; spin_lock(&mm->page_table_lock); @@ -106,7 +101,7 @@ static struct hmm *hmm_register(struct mm_struct *mm) if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) goto error_mm; - return mm->hmm; + return hmm; error_mm: spin_lock(&mm->page_table_lock); @@ -118,54 +113,60 @@ error: return NULL; } -void hmm_mm_destroy(struct mm_struct *mm) +static void hmm_free(struct kref *kref) { - kfree(mm->hmm); -} + struct hmm *hmm = container_of(kref, struct hmm, kref); + struct mm_struct *mm = hmm->mm; -static int hmm_invalidate_range(struct hmm *hmm, bool device, - const struct hmm_update *update) -{ - struct hmm_mirror *mirror; - struct hmm_range *range; - - spin_lock(&hmm->lock); - list_for_each_entry(range, &hmm->ranges, list) { - unsigned long addr, idx, npages; + mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm); - if (update->end < range->start || update->start >= range->end) - continue; + spin_lock(&mm->page_table_lock); + if (mm->hmm == hmm) + mm->hmm = NULL; + spin_unlock(&mm->page_table_lock); - range->valid = false; - addr = max(update->start, range->start); - idx = (addr - range->start) >> PAGE_SHIFT; - npages = (min(range->end, update->end) - addr) >> PAGE_SHIFT; - memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages); - } - spin_unlock(&hmm->lock); + kfree(hmm); +} - if (!device) - return 0; +static inline void hmm_put(struct hmm *hmm) +{ + kref_put(&hmm->kref, hmm_free); +} - down_read(&hmm->mirrors_sem); - list_for_each_entry(mirror, &hmm->mirrors, list) { - int ret; +void hmm_mm_destroy(struct mm_struct *mm) +{ + struct hmm *hmm; - ret = mirror->ops->sync_cpu_device_pagetables(mirror, update); - if (!update->blockable && ret == -EAGAIN) { - up_read(&hmm->mirrors_sem); - return -EAGAIN; - } + spin_lock(&mm->page_table_lock); + hmm = mm_get_hmm(mm); + mm->hmm = NULL; + if (hmm) { + hmm->mm = NULL; + hmm->dead = true; + spin_unlock(&mm->page_table_lock); + hmm_put(hmm); + return; } - up_read(&hmm->mirrors_sem); - return 0; + spin_unlock(&mm->page_table_lock); } static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) { + struct hmm *hmm = mm_get_hmm(mm); struct hmm_mirror *mirror; - struct hmm *hmm = mm->hmm; + struct hmm_range *range; + + /* Report this HMM as dying. */ + hmm->dead = true; + + /* Wake-up everyone waiting on any range. */ + mutex_lock(&hmm->lock); + list_for_each_entry(range, &hmm->ranges, list) { + range->valid = false; + } + wake_up_all(&hmm->wq); + mutex_unlock(&hmm->lock); down_write(&hmm->mirrors_sem); mirror = list_first_entry_or_null(&hmm->mirrors, struct hmm_mirror, @@ -186,36 +187,86 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) struct hmm_mirror, list); } up_write(&hmm->mirrors_sem); + + hmm_put(hmm); } static int hmm_invalidate_range_start(struct mmu_notifier *mn, - const struct mmu_notifier_range *range) + const struct mmu_notifier_range *nrange) { + struct hmm *hmm = mm_get_hmm(nrange->mm); + struct hmm_mirror *mirror; struct hmm_update update; - struct hmm *hmm = range->mm->hmm; + struct hmm_range *range; + int ret = 0; VM_BUG_ON(!hmm); - update.start = range->start; - update.end = range->end; + update.start = nrange->start; + update.end = nrange->end; update.event = HMM_UPDATE_INVALIDATE; - update.blockable = range->blockable; - return hmm_invalidate_range(hmm, true, &update); + update.blockable = mmu_notifier_range_blockable(nrange); + + if (mmu_notifier_range_blockable(nrange)) + mutex_lock(&hmm->lock); + else if (!mutex_trylock(&hmm->lock)) { + ret = -EAGAIN; + goto out; + } + hmm->notifiers++; + list_for_each_entry(range, &hmm->ranges, list) { + if (update.end < range->start || update.start >= range->end) + continue; + + range->valid = false; + } + mutex_unlock(&hmm->lock); + + if (mmu_notifier_range_blockable(nrange)) + down_read(&hmm->mirrors_sem); + else if (!down_read_trylock(&hmm->mirrors_sem)) { + ret = -EAGAIN; + goto out; + } + list_for_each_entry(mirror, &hmm->mirrors, list) { + int ret; + + ret = mirror->ops->sync_cpu_device_pagetables(mirror, &update); + if (!update.blockable && ret == -EAGAIN) { + up_read(&hmm->mirrors_sem); + ret = -EAGAIN; + goto out; + } + } + up_read(&hmm->mirrors_sem); + +out: + hmm_put(hmm); + return ret; } static void hmm_invalidate_range_end(struct mmu_notifier *mn, - const struct mmu_notifier_range *range) + const struct mmu_notifier_range *nrange) { - struct hmm_update update; - struct hmm *hmm = range->mm->hmm; + struct hmm *hmm = mm_get_hmm(nrange->mm); VM_BUG_ON(!hmm); - update.start = range->start; - update.end = range->end; - update.event = HMM_UPDATE_INVALIDATE; - update.blockable = true; - hmm_invalidate_range(hmm, false, &update); + mutex_lock(&hmm->lock); + hmm->notifiers--; + if (!hmm->notifiers) { + struct hmm_range *range; + + list_for_each_entry(range, &hmm->ranges, list) { + if (range->valid) + continue; + range->valid = true; + } + wake_up_all(&hmm->wq); + } + mutex_unlock(&hmm->lock); + + hmm_put(hmm); } static const struct mmu_notifier_ops hmm_mmu_notifier_ops = { @@ -241,24 +292,13 @@ int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm) if (!mm || !mirror || !mirror->ops) return -EINVAL; -again: - mirror->hmm = hmm_register(mm); + mirror->hmm = hmm_get_or_create(mm); if (!mirror->hmm) return -ENOMEM; down_write(&mirror->hmm->mirrors_sem); - if (mirror->hmm->mm == NULL) { - /* - * A racing hmm_mirror_unregister() is about to destroy the hmm - * struct. Try again to allocate a new one. - */ - up_write(&mirror->hmm->mirrors_sem); - mirror->hmm = NULL; - goto again; - } else { - list_add(&mirror->list, &mirror->hmm->mirrors); - up_write(&mirror->hmm->mirrors_sem); - } + list_add(&mirror->list, &mirror->hmm->mirrors); + up_write(&mirror->hmm->mirrors_sem); return 0; } @@ -273,38 +313,24 @@ EXPORT_SYMBOL(hmm_mirror_register); */ void hmm_mirror_unregister(struct hmm_mirror *mirror) { - bool should_unregister = false; - struct mm_struct *mm; - struct hmm *hmm; + struct hmm *hmm = READ_ONCE(mirror->hmm); - if (mirror->hmm == NULL) + if (hmm == NULL) return; - hmm = mirror->hmm; down_write(&hmm->mirrors_sem); list_del_init(&mirror->list); - should_unregister = list_empty(&hmm->mirrors); + /* To protect us against double unregister ... */ mirror->hmm = NULL; - mm = hmm->mm; - hmm->mm = NULL; up_write(&hmm->mirrors_sem); - if (!should_unregister || mm == NULL) - return; - - mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm); - - spin_lock(&mm->page_table_lock); - if (mm->hmm == hmm) - mm->hmm = NULL; - spin_unlock(&mm->page_table_lock); - - kfree(hmm); + hmm_put(hmm); } EXPORT_SYMBOL(hmm_mirror_unregister); struct hmm_vma_walk { struct hmm_range *range; + struct dev_pagemap *pgmap; unsigned long last; bool fault; bool block; @@ -323,13 +349,13 @@ static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr, flags |= write_fault ? FAULT_FLAG_WRITE : 0; ret = handle_mm_fault(vma, addr, flags); if (ret & VM_FAULT_RETRY) - return -EBUSY; + return -EAGAIN; if (ret & VM_FAULT_ERROR) { *pfn = range->values[HMM_PFN_ERROR]; return -EFAULT; } - return -EAGAIN; + return -EBUSY; } static int hmm_pfns_bad(unsigned long addr, @@ -355,7 +381,7 @@ static int hmm_pfns_bad(unsigned long addr, * @fault: should we fault or not ? * @write_fault: write fault ? * @walk: mm_walk structure - * Returns: 0 on success, -EAGAIN after page fault, or page fault error + * Returns: 0 on success, -EBUSY after page fault, or page fault error * * This function will be called whenever pmd_none() or pte_none() returns true, * or whenever there is no page directory covering the virtual address range. @@ -367,23 +393,25 @@ 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; + unsigned long i, page_size; hmm_vma_walk->last = addr; - i = (addr - range->start) >> PAGE_SHIFT; - for (; addr < end; addr += PAGE_SIZE, i++) { + page_size = hmm_range_page_size(range); + i = (addr - range->start) >> range->page_shift; + + for (; addr < end; addr += page_size, i++) { pfns[i] = range->values[HMM_PFN_NONE]; if (fault || write_fault) { int ret; ret = hmm_vma_do_fault(walk, addr, write_fault, &pfns[i]); - if (ret != -EAGAIN) + if (ret != -EBUSY) return ret; } } - return (fault || write_fault) ? -EAGAIN : 0; + return (fault || write_fault) ? -EBUSY : 0; } static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk, @@ -392,10 +420,21 @@ static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk, { struct hmm_range *range = hmm_vma_walk->range; - *fault = *write_fault = false; if (!hmm_vma_walk->fault) 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- + * 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. + */ + pfns = (pfns & range->pfn_flags_mask) | range->default_flags; + /* We aren't ask to do anything ... */ if (!(pfns & range->flags[HMM_PFN_VALID])) return; @@ -431,10 +470,11 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, return; } + *fault = *write_fault = false; for (i = 0; i < npages; ++i) { hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags, fault, write_fault); - if ((*fault) || (*write_fault)) + if ((*write_fault)) return; } } @@ -465,12 +505,22 @@ 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 struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; unsigned long pfn, npages, i; @@ -486,10 +536,25 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk); pfn = pmd_pfn(pmd) + pte_index(addr); - for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) - pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags; + for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) { + if (pmd_devmap(pmd)) { + hmm_vma_walk->pgmap = get_dev_pagemap(pfn, + hmm_vma_walk->pgmap); + if (unlikely(!hmm_vma_walk->pgmap)) + return -EBUSY; + } + pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags; + } + if (hmm_vma_walk->pgmap) { + put_dev_pagemap(hmm_vma_walk->pgmap); + hmm_vma_walk->pgmap = NULL; + } hmm_vma_walk->last = end; return 0; +#else + /* If THP is not enabled then we should never reach that code ! */ + return -EINVAL; +#endif } static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte) @@ -514,11 +579,11 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, uint64_t orig_pfn = *pfn; *pfn = range->values[HMM_PFN_NONE]; - cpu_flags = pte_to_hmm_pfn_flags(range, pte); - hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags, - &fault, &write_fault); + fault = write_fault = false; if (pte_none(pte)) { + hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0, + &fault, &write_fault); if (fault || write_fault) goto fault; return 0; @@ -546,7 +611,8 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, &fault, &write_fault); if (fault || write_fault) goto fault; - *pfn = hmm_pfn_from_pfn(range, swp_offset(entry)); + *pfn = hmm_device_entry_from_pfn(range, + swp_offset(entry)); *pfn |= cpu_flags; return 0; } @@ -557,7 +623,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, hmm_vma_walk->last = addr; migration_entry_wait(vma->vm_mm, pmdp, addr); - return -EAGAIN; + return -EBUSY; } return 0; } @@ -565,15 +631,33 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, /* Report error for everything else */ *pfn = range->values[HMM_PFN_ERROR]; return -EFAULT; + } else { + 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; - *pfn = hmm_pfn_from_pfn(range, pte_pfn(pte)) | cpu_flags; + if (pte_devmap(pte)) { + hmm_vma_walk->pgmap = get_dev_pagemap(pte_pfn(pte), + hmm_vma_walk->pgmap); + if (unlikely(!hmm_vma_walk->pgmap)) + return -EBUSY; + } else if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pte_special(pte)) { + *pfn = range->values[HMM_PFN_SPECIAL]; + return -EFAULT; + } + + *pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags; return 0; fault: + if (hmm_vma_walk->pgmap) { + put_dev_pagemap(hmm_vma_walk->pgmap); + hmm_vma_walk->pgmap = NULL; + } pte_unmap(ptep); /* Fault any virtual address we were asked to fault */ return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk); @@ -615,7 +699,7 @@ again: if (fault || write_fault) { hmm_vma_walk->last = addr; pmd_migration_entry_wait(vma->vm_mm, pmdp); - return -EAGAIN; + return -EBUSY; } return 0; } else if (!pmd_present(pmd)) @@ -661,12 +745,158 @@ again: return r; } } + if (hmm_vma_walk->pgmap) { + /* + * We do put_dev_pagemap() here and not in hmm_vma_handle_pte() + * so that we can leverage get_dev_pagemap() optimization which + * will not re-take a reference on a pgmap if we already have + * one. + */ + put_dev_pagemap(hmm_vma_walk->pgmap); + hmm_vma_walk->pgmap = NULL; + } pte_unmap(ptep - 1); hmm_vma_walk->last = addr; return 0; } +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; + unsigned long addr = start, next; + pmd_t *pmdp; + pud_t pud; + int ret; + +again: + pud = READ_ONCE(*pudp); + if (pud_none(pud)) + return hmm_vma_walk_hole(start, end, walk); + + if (pud_huge(pud) && pud_devmap(pud)) { + unsigned long i, npages, pfn; + uint64_t *pfns, cpu_flags; + bool fault, write_fault; + + if (!pud_present(pud)) + return hmm_vma_walk_hole(start, end, walk); + + i = (addr - range->start) >> PAGE_SHIFT; + npages = (end - addr) >> PAGE_SHIFT; + pfns = &range->pfns[i]; + + cpu_flags = pud_to_hmm_pfn_flags(range, pud); + hmm_range_need_fault(hmm_vma_walk, pfns, npages, + cpu_flags, &fault, &write_fault); + if (fault || write_fault) + return hmm_vma_walk_hole_(addr, end, fault, + write_fault, walk); + +#ifdef CONFIG_HUGETLB_PAGE + pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + for (i = 0; i < npages; ++i, ++pfn) { + hmm_vma_walk->pgmap = get_dev_pagemap(pfn, + hmm_vma_walk->pgmap); + if (unlikely(!hmm_vma_walk->pgmap)) + return -EBUSY; + pfns[i] = hmm_device_entry_from_pfn(range, pfn) | + cpu_flags; + } + if (hmm_vma_walk->pgmap) { + put_dev_pagemap(hmm_vma_walk->pgmap); + hmm_vma_walk->pgmap = NULL; + } + hmm_vma_walk->last = end; + return 0; +#else + return -EINVAL; +#endif + } + + split_huge_pud(walk->vma, pudp, addr); + if (pud_none(*pudp)) + goto again; + + pmdp = pmd_offset(pudp, addr); + do { + next = pmd_addr_end(addr, end); + ret = hmm_vma_walk_pmd(pmdp, addr, next, walk); + if (ret) + return ret; + } while (pmdp++, addr = next, addr != end); + + return 0; +} + +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; + 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); + entry = huge_ptep_get(pte); + + i = (start - range->start) >> range->page_shift; + orig_pfn = range->pfns[i]; + range->pfns[i] = range->values[HMM_PFN_NONE]; + cpu_flags = pte_to_hmm_pfn_flags(range, entry); + fault = write_fault = false; + hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags, + &fault, &write_fault); + if (fault || write_fault) { + ret = -ENOENT; + goto unlock; + } + + pfn = pte_pfn(entry) + ((start & mask) >> range->page_shift); + for (; addr < end; addr += size, i++, pfn += pfn_inc) + range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) | + cpu_flags; + hmm_vma_walk->last = end; + +unlock: + spin_unlock(ptl); + + if (ret == -ENOENT) + return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk); + + return ret; +#else /* CONFIG_HUGETLB_PAGE */ + return -EINVAL; +#endif +} + static void hmm_pfns_clear(struct hmm_range *range, uint64_t *pfns, unsigned long addr, @@ -676,279 +906,437 @@ static void hmm_pfns_clear(struct hmm_range *range, *pfns = range->values[HMM_PFN_NONE]; } -static void hmm_pfns_special(struct hmm_range *range) -{ - unsigned long addr = range->start, i = 0; - - for (; addr < range->end; addr += PAGE_SIZE, i++) - range->pfns[i] = range->values[HMM_PFN_SPECIAL]; -} - /* - * hmm_vma_get_pfns() - snapshot CPU page table for a range of virtual addresses - * @range: range being snapshotted - * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid - * vma permission, 0 success - * - * This snapshots the CPU page table for a range of virtual addresses. Snapshot - * validity is tracked by range struct. See hmm_vma_range_done() for further - * information. - * - * The range struct is initialized here. It tracks the CPU page table, but only - * if the function returns success (0), in which case the caller must then call - * hmm_vma_range_done() to stop CPU page table update tracking on this 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 * - * NOT CALLING hmm_vma_range_done() IF FUNCTION RETURNS 0 WILL LEAD TO SERIOUS - * MEMORY CORRUPTION ! YOU HAVE BEEN WARNED ! + * Track updates to the CPU page table see include/linux/hmm.h */ -int hmm_vma_get_pfns(struct hmm_range *range) +int hmm_range_register(struct hmm_range *range, + struct mm_struct *mm, + unsigned long start, + unsigned long end, + unsigned page_shift) { - struct vm_area_struct *vma = range->vma; - struct hmm_vma_walk hmm_vma_walk; - struct mm_walk mm_walk; - struct hmm *hmm; + unsigned long mask = ((1UL << page_shift) - 1UL); + + range->valid = false; + range->hmm = NULL; - /* Sanity check, this really should not happen ! */ - if (range->start < vma->vm_start || range->start >= vma->vm_end) + if ((start & mask) || (end & mask)) return -EINVAL; - if (range->end < vma->vm_start || range->end > vma->vm_end) + if (start >= end) return -EINVAL; - hmm = hmm_register(vma->vm_mm); - if (!hmm) - return -ENOMEM; - /* Caller must have registered a mirror, via hmm_mirror_register() ! */ - if (!hmm->mmu_notifier.ops) - return -EINVAL; + range->page_shift = page_shift; + range->start = start; + range->end = end; - /* FIXME support hugetlb fs */ - if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) || - vma_is_dax(vma)) { - hmm_pfns_special(range); - return -EINVAL; - } + range->hmm = hmm_get_or_create(mm); + if (!range->hmm) + return -EFAULT; - if (!(vma->vm_flags & VM_READ)) { - /* - * If vma do not allow read access, then assume that it does - * not allow write access, either. Architecture that allow - * write without read access are not supported by HMM, because - * operations such has atomic access would not work. - */ - hmm_pfns_clear(range, range->pfns, range->start, range->end); - return -EPERM; + /* Check if hmm_mm_destroy() was call. */ + if (range->hmm->mm == NULL || range->hmm->dead) { + hmm_put(range->hmm); + return -EFAULT; } /* Initialize range to track CPU page table update */ - spin_lock(&hmm->lock); - range->valid = true; - list_add_rcu(&range->list, &hmm->ranges); - spin_unlock(&hmm->lock); - - hmm_vma_walk.fault = false; - hmm_vma_walk.range = range; - mm_walk.private = &hmm_vma_walk; - - 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.pmd_entry = hmm_vma_walk_pmd; - mm_walk.pte_hole = hmm_vma_walk_hole; - - walk_page_range(range->start, range->end, &mm_walk); + mutex_lock(&range->hmm->lock); + + list_add_rcu(&range->list, &range->hmm->ranges); + + /* + * If there are any concurrent notifiers we have to wait for them for + * the range to be valid (see hmm_range_wait_until_valid()). + */ + if (!range->hmm->notifiers) + range->valid = true; + mutex_unlock(&range->hmm->lock); + return 0; } -EXPORT_SYMBOL(hmm_vma_get_pfns); +EXPORT_SYMBOL(hmm_range_register); /* - * hmm_vma_range_done() - stop tracking change to CPU page table over a range - * @range: range being tracked - * Returns: false if range data has been invalidated, true otherwise + * hmm_range_unregister() - stop tracking change to CPU page table over a range + * @range: range * * Range struct is used to track updates to the CPU page table after a call to - * either hmm_vma_get_pfns() or hmm_vma_fault(). Once the device driver is done - * using the data, or wants to lock updates to the data it got from those - * functions, it must call the hmm_vma_range_done() function, which will then - * stop tracking CPU page table updates. - * - * Note that device driver must still implement general CPU page table update - * tracking either by using hmm_mirror (see hmm_mirror_register()) or by using - * the mmu_notifier API directly. - * - * CPU page table update tracking done through hmm_range is only temporary and - * to be used while trying to duplicate CPU page table contents for a range of - * virtual addresses. - * - * There are two ways to use this : - * again: - * hmm_vma_get_pfns(range); or hmm_vma_fault(...); - * trans = device_build_page_table_update_transaction(pfns); - * device_page_table_lock(); - * if (!hmm_vma_range_done(range)) { - * device_page_table_unlock(); - * goto again; - * } - * device_commit_transaction(trans); - * device_page_table_unlock(); + * hmm_range_register(). See include/linux/hmm.h for how to use it. + */ +void hmm_range_unregister(struct hmm_range *range) +{ + /* Sanity check this really should not happen. */ + if (range->hmm == NULL || range->end <= range->start) + return; + + mutex_lock(&range->hmm->lock); + list_del_rcu(&range->list); + mutex_unlock(&range->hmm->lock); + + /* Drop reference taken by hmm_range_register() */ + range->valid = false; + hmm_put(range->hmm); + range->hmm = NULL; +} +EXPORT_SYMBOL(hmm_range_unregister); + +/* + * hmm_range_snapshot() - snapshot CPU page table for a range + * @range: range + * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid + * permission (for instance asking for write and range is read only), + * -EAGAIN 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). * - * Or: - * hmm_vma_get_pfns(range); or hmm_vma_fault(...); - * device_page_table_lock(); - * hmm_vma_range_done(range); - * device_update_page_table(range->pfns); - * device_page_table_unlock(); + * 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. */ -bool hmm_vma_range_done(struct hmm_range *range) +long hmm_range_snapshot(struct hmm_range *range) { - unsigned long npages = (range->end - range->start) >> PAGE_SHIFT; - struct hmm *hmm; + 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; - if (range->end <= range->start) { - BUG(); - return false; - } + /* Check if hmm_mm_destroy() was call. */ + if (hmm->mm == NULL || hmm->dead) + return -EFAULT; - hmm = hmm_register(range->vma->vm_mm); - if (!hmm) { - memset(range->pfns, 0, sizeof(*range->pfns) * npages); - return false; - } + do { + /* If range is no longer valid force retry. */ + if (!range->valid) + return -EAGAIN; - spin_lock(&hmm->lock); - list_del_rcu(&range->list); - spin_unlock(&hmm->lock); + vma = find_vma(hmm->mm, start); + if (vma == NULL || (vma->vm_flags & device_vma)) + return -EFAULT; + + if (is_vm_hugetlb_page(vma)) { + struct hstate *h = hstate_vma(vma); - return range->valid; + if (huge_page_shift(h) != 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_vma_range_done); +EXPORT_SYMBOL(hmm_range_snapshot); /* - * hmm_vma_fault() - try to fault some address in a virtual address range + * 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) - * Returns: 0 success, error otherwise (-EAGAIN means mmap_sem have been drop) + * Returns: 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: + * + * -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). * * 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. + * any memory migration if the memory being faulted is not accessible by CPUs + * and caller does not ask for migration. * * On error, for one virtual address in the range, the function will mark the * corresponding HMM pfn entry with an error flag. - * - * Expected use pattern: - * retry: - * down_read(&mm->mmap_sem); - * // Find vma and address device wants to fault, initialize hmm_pfn_t - * // array accordingly - * ret = hmm_vma_fault(range, write, block); - * switch (ret) { - * case -EAGAIN: - * hmm_vma_range_done(range); - * // You might want to rate limit or yield to play nicely, you may - * // also commit any valid pfn in the array assuming that you are - * // getting true from hmm_vma_range_monitor_end() - * goto retry; - * case 0: - * break; - * case -ENOMEM: - * case -EINVAL: - * case -EPERM: - * default: - * // Handle error ! - * up_read(&mm->mmap_sem) - * return; - * } - * // Take device driver lock that serialize device page table update - * driver_lock_device_page_table_update(); - * hmm_vma_range_done(range); - * // Commit pfns we got from hmm_vma_fault() - * driver_unlock_device_page_table_update(); - * up_read(&mm->mmap_sem) - * - * YOU MUST CALL hmm_vma_range_done() AFTER THIS FUNCTION RETURN SUCCESS (0) - * BEFORE FREEING THE range struct OR YOU WILL HAVE SERIOUS MEMORY CORRUPTION ! - * - * YOU HAVE BEEN WARNED ! */ -int hmm_vma_fault(struct hmm_range *range, bool block) +long hmm_range_fault(struct hmm_range *range, bool block) { - struct vm_area_struct *vma = range->vma; - unsigned long start = range->start; + 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; - struct hmm *hmm; int ret; - /* Sanity check, this really should not happen ! */ - if (range->start < vma->vm_start || range->start >= vma->vm_end) - return -EINVAL; - if (range->end < vma->vm_start || range->end > vma->vm_end) - return -EINVAL; + /* Check if hmm_mm_destroy() was call. */ + if (hmm->mm == NULL || hmm->dead) + return -EFAULT; - hmm = hmm_register(vma->vm_mm); - if (!hmm) { - hmm_pfns_clear(range, range->pfns, range->start, range->end); - return -ENOMEM; - } - /* Caller must have registered a mirror using hmm_mirror_register() */ - if (!hmm->mmu_notifier.ops) - return -EINVAL; + do { + /* If range is no longer valid force retry. */ + if (!range->valid) { + up_read(&hmm->mm->mmap_sem); + return -EAGAIN; + } - /* FIXME support hugetlb fs */ - if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) || - vma_is_dax(vma)) { - hmm_pfns_special(range); - return -EINVAL; - } + 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 = true; + hmm_vma_walk.block = block; + 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; + + do { + ret = walk_page_range(start, end, &mm_walk); + start = hmm_vma_walk.last; + + /* Keep trying while the range is valid. */ + } while (ret == -EBUSY && range->valid); + + if (ret) { + unsigned long i; + + i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; + hmm_pfns_clear(range, &range->pfns[i], + hmm_vma_walk.last, range->end); + return ret; + } + start = end; + + } while (start < range->end); + + return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; +} +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) + * Returns: number of pages mapped on success, -EAGAIN if mmap_sem have been + * drop and you need to try again, some other error value otherwise + * + * Note same usage pattern as hmm_range_fault(). + */ +long hmm_range_dma_map(struct hmm_range *range, + struct device *device, + dma_addr_t *daddrs, + bool block) +{ + unsigned long i, npages, mapped; + long ret; + + ret = hmm_range_fault(range, block); + if (ret <= 0) + return ret ? ret : -EBUSY; + + npages = (range->end - range->start) >> PAGE_SHIFT; + for (i = 0, mapped = 0; i < npages; ++i) { + enum dma_data_direction dir = DMA_TO_DEVICE; + struct page *page; - if (!(vma->vm_flags & VM_READ)) { /* - * If vma do not allow read access, then assume that it does - * not allow write access, either. Architecture that allow - * write without read access are not supported by HMM, because - * operations such has atomic access would not work. + * FIXME need to update DMA API to provide invalid DMA address + * value instead of a function to test dma address value. This + * would remove lot of dumb code duplicated accross many arch. + * + * For now setting it to 0 here is good enough as the pfns[] + * value is what is use to check what is valid and what isn't. */ - hmm_pfns_clear(range, range->pfns, range->start, range->end); - return -EPERM; + daddrs[i] = 0; + + page = hmm_device_entry_to_page(range, range->pfns[i]); + if (page == NULL) + continue; + + /* Check if range is being invalidated */ + if (!range->valid) { + ret = -EBUSY; + goto unmap; + } + + /* If it is read and write than map bi-directional. */ + if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) + dir = DMA_BIDIRECTIONAL; + + daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir); + if (dma_mapping_error(device, daddrs[i])) { + ret = -EFAULT; + goto unmap; + } + + mapped++; } - /* Initialize range to track CPU page table update */ - spin_lock(&hmm->lock); - range->valid = true; - list_add_rcu(&range->list, &hmm->ranges); - spin_unlock(&hmm->lock); - - hmm_vma_walk.fault = true; - hmm_vma_walk.block = block; - hmm_vma_walk.range = range; - mm_walk.private = &hmm_vma_walk; - hmm_vma_walk.last = range->start; - - 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.pmd_entry = hmm_vma_walk_pmd; - mm_walk.pte_hole = hmm_vma_walk_hole; + return mapped; - do { - ret = walk_page_range(start, range->end, &mm_walk); - start = hmm_vma_walk.last; - } while (ret == -EAGAIN); +unmap: + for (npages = i, i = 0; (i < npages) && mapped; ++i) { + enum dma_data_direction dir = DMA_TO_DEVICE; + struct page *page; - if (ret) { - unsigned long i; + page = hmm_device_entry_to_page(range, range->pfns[i]); + if (page == NULL) + continue; + + if (dma_mapping_error(device, daddrs[i])) + continue; - i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; - hmm_pfns_clear(range, &range->pfns[i], hmm_vma_walk.last, - range->end); - hmm_vma_range_done(range); + /* If it is read and write than map bi-directional. */ + if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) + dir = DMA_BIDIRECTIONAL; + + dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir); + mapped--; } + return ret; } -EXPORT_SYMBOL(hmm_vma_fault); +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 + * Returns: number of page unmapped on success, -EINVAL otherwise + * + * Note that caller MUST abide by mmu notifier or use HMM mirror and abide + * to the sync_cpu_device_pagetables() callback so that it is safe here to + * call set_page_dirty(). Caller must also take appropriate locks to avoid + * 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) +{ + unsigned long i, npages; + long cpages = 0; + + /* Sanity check. */ + if (range->end <= range->start) + return -EINVAL; + if (!daddrs) + return -EINVAL; + if (!range->pfns) + return -EINVAL; + + npages = (range->end - range->start) >> PAGE_SHIFT; + for (i = 0; i < npages; ++i) { + enum dma_data_direction dir = DMA_TO_DEVICE; + struct page *page; + + page = hmm_device_entry_to_page(range, range->pfns[i]); + if (page == NULL) + continue; + + /* If it is read and write than map bi-directional. */ + if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) { + dir = DMA_BIDIRECTIONAL; + + /* + * See comments in function description on why it is + * safe here to call set_page_dirty() + */ + if (dirty) + set_page_dirty(page); + } + + /* Unmap and clear pfns/dma address */ + dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir); + range->pfns[i] = range->values[HMM_PFN_NONE]; + /* FIXME see comments in hmm_vma_dma_map() */ + daddrs[i] = 0; + cpages++; + } + + return cpages; +} +EXPORT_SYMBOL(hmm_range_dma_unmap); #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ |