diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2019-08-07 16:03:55 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2019-08-07 16:03:55 +1000 |
commit | 22426e9febca626336de02577692c2471fa79502 (patch) | |
tree | 65b15f68327c0255bf3ee8414f57f29edfbe6098 | |
parent | c2642150b8e6b27f084c412b75152137cca2111f (diff) | |
parent | cc374377a19d2a49d693997b62dc3a6f5fac6d61 (diff) | |
download | linux-next-22426e9febca626336de02577692c2471fa79502.tar.gz |
Merge remote-tracking branch 'hmm/hmm'
-rw-r--r-- | Documentation/vm/hmm.rst | 17 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 14 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/nouveau/nouveau_svm.c | 15 | ||||
-rw-r--r-- | include/linux/hmm.h | 84 | ||||
-rw-r--r-- | mm/hmm.c | 217 |
7 files changed, 105 insertions, 246 deletions
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index 710ce1c701bf..ddcb5ca8b296 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -192,15 +192,14 @@ read only, or fully unmap, etc.). The device must complete the update before the driver callback returns. When the device driver wants to populate a range of virtual addresses, it can -use either:: +use:: - long hmm_range_snapshot(struct hmm_range *range); - long hmm_range_fault(struct hmm_range *range, bool block); + long hmm_range_fault(struct hmm_range *range, unsigned int flags); -The first one (hmm_range_snapshot()) will only fetch present CPU page table +With the HMM_RANGE_SNAPSHOT flag, it will only fetch present CPU page table entries and will not trigger a page fault on missing or non-present entries. -The second one does trigger a page fault on missing or read-only entries if -write access is requested (see below). Page faults use the generic mm page +Without that flag, it does trigger a page fault on missing or read-only entries +if write access is requested (see below). Page faults use the generic mm page fault code path just like a CPU page fault. Both functions copy CPU page table entries into their pfns array argument. Each @@ -227,20 +226,20 @@ The usage pattern is:: /* * Just wait for range to be valid, safe to ignore return value as we - * will use the return value of hmm_range_snapshot() below under the + * will use the return value of hmm_range_fault() below under the * mmap_sem to ascertain the validity of the range. */ hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC); again: down_read(&mm->mmap_sem); - ret = hmm_range_snapshot(&range); + ret = hmm_range_fault(&range, HMM_RANGE_SNAPSHOT); if (ret) { up_read(&mm->mmap_sem); if (ret == -EBUSY) { /* * No need to check hmm_range_wait_until_valid() return value - * on retry we will get proper error with hmm_range_snapshot() + * on retry we will get proper error with hmm_range_fault() */ hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC); goto again; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 50022acc8a81..ec4f36970d22 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -195,13 +195,14 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node, * Block for operations on BOs to finish and mark pages as accessed and * potentially dirty. */ -static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, - const struct hmm_update *update) +static int +amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, + const struct mmu_notifier_range *update) { struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror); unsigned long start = update->start; unsigned long end = update->end; - bool blockable = update->blockable; + bool blockable = mmu_notifier_range_blockable(update); struct interval_tree_node *it; /* notification is exclusive, but interval is inclusive */ @@ -243,13 +244,14 @@ static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror, * necessitates evicting all user-mode queues of the process. The BOs * are restorted in amdgpu_mn_invalidate_range_end_hsa. */ -static int amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror, - const struct hmm_update *update) +static int +amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror, + const struct mmu_notifier_range *update) { struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror); unsigned long start = update->start; unsigned long end = update->end; - bool blockable = update->blockable; + bool blockable = mmu_notifier_range_blockable(update); struct interval_tree_node *it; /* notification is exclusive, but interval is inclusive */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8f8b7a350b8b..bb41a2ee9cb3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -848,7 +848,7 @@ retry: down_read(&mm->mmap_sem); - r = hmm_range_fault(range, true); + r = hmm_range_fault(range, 0); if (unlikely(r < 0)) { if (likely(r == -EAGAIN)) { /* diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 1333220787a1..345c63cb752a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -845,7 +845,7 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, struct page *page; uint64_t addr; - page = hmm_pfn_to_page(range, range->pfns[i]); + page = hmm_device_entry_to_page(range, range->pfns[i]); if (page == NULL) continue; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index a835cebb6d90..a74530b5a523 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -252,13 +252,13 @@ nouveau_svmm_invalidate(struct nouveau_svmm *svmm, u64 start, u64 limit) static int nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror, - const struct hmm_update *update) + const struct mmu_notifier_range *update) { struct nouveau_svmm *svmm = container_of(mirror, typeof(*svmm), mirror); unsigned long start = update->start; unsigned long limit = update->end; - if (!update->blockable) + if (!mmu_notifier_range_blockable(update)) return -EAGAIN; SVMM_DBG(svmm, "invalidate %016lx-%016lx", start, limit); @@ -496,20 +496,20 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) range->start, range->end, PAGE_SHIFT); if (ret) { - up_read(&range->vma->vm_mm->mmap_sem); + up_read(&range->hmm->mm->mmap_sem); return (int)ret; } if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { - up_read(&range->vma->vm_mm->mmap_sem); - return -EAGAIN; + up_read(&range->hmm->mm->mmap_sem); + return -EBUSY; } - ret = hmm_range_fault(range, true); + ret = hmm_range_fault(range, 0); if (ret <= 0) { if (ret == 0) ret = -EBUSY; - up_read(&range->vma->vm_mm->mmap_sem); + up_read(&range->hmm->mm->mmap_sem); hmm_range_unregister(range); return ret; } @@ -682,7 +682,6 @@ nouveau_svm_fault(struct nvif_notify *notify) args.i.p.addr + args.i.p.size, fn - fi); /* Have HMM fault pages within the fault window to the GPU. */ - range.vma = vma; range.start = args.i.p.addr; range.end = args.i.p.addr + args.i.p.size; range.pfns = args.phys; diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 7ef56dc18050..82265118d94a 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -164,7 +164,6 @@ enum hmm_pfn_value_e { */ struct hmm_range { struct hmm *hmm; - struct vm_area_struct *vma; struct list_head list; unsigned long start; unsigned long end; @@ -291,40 +290,6 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, } /* - * Old API: - * hmm_pfn_to_page() - * hmm_pfn_to_pfn() - * hmm_pfn_from_page() - * hmm_pfn_from_pfn() - * - * This are the OLD API please use new API, it is here to avoid cross-tree - * merge painfullness ie we convert things to new API in stages. - */ -static inline struct page *hmm_pfn_to_page(const struct hmm_range *range, - uint64_t pfn) -{ - return hmm_device_entry_to_page(range, pfn); -} - -static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range, - uint64_t pfn) -{ - return hmm_device_entry_to_pfn(range, pfn); -} - -static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range, - struct page *page) -{ - return hmm_device_entry_from_page(range, page); -} - -static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, - unsigned long pfn) -{ - return hmm_device_entry_from_pfn(range, pfn); -} - -/* * Mirroring: how to synchronize device page table with CPU page table. * * A device driver that is participating in HMM mirroring must always @@ -375,29 +340,6 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, struct hmm_mirror; /* - * enum hmm_update_event - type of update - * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) - */ -enum hmm_update_event { - HMM_UPDATE_INVALIDATE, -}; - -/* - * struct hmm_update - HMM update information for callback - * - * @start: virtual start address of the range to update - * @end: virtual end address of the range to update - * @event: event triggering the update (what is happening) - * @blockable: can the callback block/sleep ? - */ -struct hmm_update { - unsigned long start; - unsigned long end; - enum hmm_update_event event; - bool blockable; -}; - -/* * struct hmm_mirror_ops - HMM mirror device operations callback * * @update: callback to update range on a device @@ -417,9 +359,9 @@ struct hmm_mirror_ops { /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror - * @update: update information (see struct hmm_update) - * Return: -EAGAIN if update.blockable false and callback need to - * block, 0 otherwise. + * @update: update information (see struct mmu_notifier_range) + * Return: -EAGAIN if mmu_notifier_range_blockable(update) is false + * and callback needs to block, 0 otherwise. * * This callback ultimately originates from mmu_notifiers when the CPU * page table is updated. The device driver must update its page table @@ -430,8 +372,9 @@ struct hmm_mirror_ops { * page tables are completely updated (TLBs flushed, etc); this is a * synchronous call. */ - int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - const struct hmm_update *update); + int (*sync_cpu_device_pagetables)( + struct hmm_mirror *mirror, + const struct mmu_notifier_range *update); }; /* @@ -463,12 +406,21 @@ int hmm_range_register(struct hmm_range *range, unsigned long end, unsigned page_shift); void hmm_range_unregister(struct hmm_range *range); -long hmm_range_snapshot(struct hmm_range *range); -long hmm_range_fault(struct hmm_range *range, bool block); + +/* + * Retry fault if non-blocking, drop mmap_sem and return -EAGAIN in that case. + */ +#define HMM_FAULT_ALLOW_RETRY (1 << 0) + +/* Don't fault in missing PTEs, just snapshot the current state. */ +#define HMM_FAULT_SNAPSHOT (1 << 1) + +long hmm_range_fault(struct hmm_range *range, unsigned int flags); + long hmm_range_dma_map(struct hmm_range *range, struct device *device, dma_addr_t *daddrs, - bool block); + unsigned int flags); long hmm_range_dma_unmap(struct hmm_range *range, struct vm_area_struct *vma, struct device *device, @@ -32,7 +32,7 @@ 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 + * Return: 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 @@ -165,7 +165,6 @@ 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; @@ -173,15 +172,10 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn, 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 +192,10 @@ 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; @@ -285,8 +280,7 @@ 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, @@ -298,11 +292,16 @@ 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 (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; @@ -328,8 +327,8 @@ 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 ? @@ -373,15 +372,15 @@ 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 +390,7 @@ 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 +417,7 @@ 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; } @@ -505,7 +504,7 @@ 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 ! */ + /* If THP is not enabled then we should never reach this code ! */ return -EINVAL; #endif } @@ -525,7 +524,6 @@ 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; @@ -574,8 +572,7 @@ 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 +620,16 @@ 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 +643,7 @@ 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 +652,11 @@ 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 +670,7 @@ 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. @@ -798,10 +790,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, pte_t entry; int ret = 0; - size = 1UL << huge_page_shift(h); + size = huge_page_size(h); mask = size - 1; if (range->page_shift != PAGE_SHIFT) { - /* Make sure we are looking at full page. */ + /* Make sure we are looking at a full page. */ if (start & mask) return -EINVAL; if (end < (start + size)) @@ -812,8 +804,7 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, 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; @@ -862,7 +853,7 @@ static void hmm_pfns_clear(struct hmm_range *range, * @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 */ @@ -941,105 +932,26 @@ 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). +/** + * hmm_range_fault - try to fault some address in a virtual address range + * @range: range being faulted + * @flags: HMM_FAULT_* flags * - * 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); - -/* - * 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: + * 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 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). + * -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 @@ -1048,7 +960,7 @@ 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; @@ -1090,11 +1002,9 @@ 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); @@ -1133,25 +1043,22 @@ 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; |