Add support for SVM atomics in Nouveau

index 18205f851c24..eec3a9d7176e 100644
@@ -691,7 +691,7 @@ static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
 	if (!non_swap_entry(entry))
 		dec_mm_counter(mm, MM_SWAPENTS);
 	else if (is_migration_entry(entry)) {
-		struct page *page = migration_entry_to_page(entry);
+		struct page *page = pfn_swap_entry_to_page(entry);
 
 		dec_mm_counter(mm, mm_counter(page));
 	}

index 3cec6fbef725..08ee59d945c0 100644
@@ -514,10 +514,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 			} else {
 				mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
 			}
-		} else if (is_migration_entry(swpent))
-			page = migration_entry_to_page(swpent);
-		else if (is_device_private_entry(swpent))
-			page = device_private_entry_to_page(swpent);
+		} else if (is_pfn_swap_entry(swpent))
+			page = pfn_swap_entry_to_page(swpent);
 	} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
 							&& pte_none(*pte))) {
 		page = xa_load(&vma->vm_file->f_mapping->i_pages,

@@ -549,7 +547,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 
 		if (is_migration_entry(entry))
-			page = migration_entry_to_page(entry);
+			page = pfn_swap_entry_to_page(entry);
 	}
 	if (IS_ERR_OR_NULL(page))
 		return;

@@ -691,10 +689,8 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
-		if (is_migration_entry(swpent))
-			page = migration_entry_to_page(swpent);
-		else if (is_device_private_entry(swpent))
-			page = device_private_entry_to_page(swpent);
+		if (is_pfn_swap_entry(swpent))
+			page = pfn_swap_entry_to_page(swpent);
 	}
 	if (page) {
 		int mapcount = page_mapcount(page);

@@ -1383,11 +1379,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 			frame = swp_type(entry) |
 				(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
 		flags |= PM_SWAP;
-		if (is_migration_entry(entry))
-			page = migration_entry_to_page(entry);
-
-		if (is_device_private_entry(entry))
-			page = device_private_entry_to_page(entry);
+		if (is_pfn_swap_entry(entry))
+			page = pfn_swap_entry_to_page(entry);
 	}
 
 	if (page && !PageAnon(page))

@@ -1444,7 +1437,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			if (pmd_swp_soft_dirty(pmd))
 				flags |= PM_SOFT_DIRTY;
 			VM_BUG_ON(!is_pmd_migration_entry(pmd));
-			page = migration_entry_to_page(entry);
+			page = pfn_swap_entry_to_page(entry);
 		}
 #endif
 

index 4cc6ec3bf0ab..516104b9334b 100644
@@ -523,8 +523,8 @@ static inline void show_swap_cache_info(void)
 {
 }
 
-#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));})
-#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));})
+/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */
+#define free_swap_and_cache(e) is_pfn_swap_entry(e)
 
 static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
 {

99 lines not on this page · raw message

index 943cb2ba4442..3b2dda71d0ed 100644
@@ -214,7 +214,7 @@ static inline bool hmm_is_device_private_entry(struct hmm_range *range,
 		swp_entry_t entry)
 {
 	return is_device_private_entry(entry) &&
-		device_private_entry_to_page(entry)->pgmap->owner =
+		pfn_swap_entry_to_page(entry)->pgmap->owner =
 		range->dev_private_owner;
 }
 

@@ -257,8 +257,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 			cpu_flags = HMM_PFN_VALID;
 			if (is_write_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
-			*hmm_pfn = device_private_entry_to_pfn(entry) |
-					cpu_flags;
+			*hmm_pfn = swp_offset(entry) | cpu_flags;
 			return 0;
 		}
 

index 395c75111d33..a4cda8564bcf 100644
@@ -1700,7 +1700,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 			VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
 			entry = pmd_to_swp_entry(orig_pmd);
-			page = pfn_to_page(swp_offset(entry));
+			page = pfn_swap_entry_to_page(entry);
 			flush_needed = 0;
 		} else
 			WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");

@@ -2108,7 +2108,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		swp_entry_t entry;
 
 		entry = pmd_to_swp_entry(old_pmd);
-		page = pfn_to_page(swp_offset(entry));
+		page = pfn_swap_entry_to_page(entry);
 		write = is_write_migration_entry(entry);
 		young = false;
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);

index 845eec01ef9d..043840dbe48a 100644
@@ -5523,7 +5523,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 	 * as special swap entry in the CPU page table.
 	 */
 	if (is_device_private_entry(ent)) {
-		page = device_private_entry_to_page(ent);
+		page = pfn_swap_entry_to_page(ent);
 		/*
 		 * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have
 		 * a refcount of 1 when free (unlike normal page)

index c8e357627318..1c98e3c1c2de 100644
@@ -730,7 +730,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		}
 		rss[MM_SWAPENTS]++;
 	} else if (is_migration_entry(entry)) {
-		page = migration_entry_to_page(entry);
+		page = pfn_swap_entry_to_page(entry);
 
 		rss[mm_counter(page)]++;
 

@@ -749,7 +749,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			set_pte_at(src_mm, addr, src_pte, pte);
 		}
 	} else if (is_device_private_entry(entry)) {
-		page = device_private_entry_to_page(entry);
+		page = pfn_swap_entry_to_page(entry);
 
 		/*
 		 * Update rss count even for unaddressable pages, as

@@ -1286,7 +1286,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 
 		entry = pte_to_swp_entry(ptent);
 		if (is_device_private_entry(entry)) {
-			struct page *page = device_private_entry_to_page(entry);
+			struct page *page = pfn_swap_entry_to_page(entry);
 
 			if (unlikely(details && details->check_mapping)) {
 				/*

@@ -1315,7 +1315,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		else if (is_migration_entry(entry)) {
 			struct page *page;
 
-			page = migration_entry_to_page(entry);
+			page = pfn_swap_entry_to_page(entry);
 			rss[mm_counter(page)]--;
 		}
 		if (unlikely(!free_swap_and_cache(entry)))

@@ -3282,7 +3282,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			migration_entry_wait(vma->vm_mm, vmf->pmd,
 					     vmf->address);
 		} else if (is_device_private_entry(entry)) {
-			vmf->page = device_private_entry_to_page(entry);
+			vmf->page = pfn_swap_entry_to_page(entry);
 			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;

index 62b81d5257aa..600978d18750 100644
@@ -321,7 +321,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 	if (!is_migration_entry(entry))
 		goto out;
 
-	page = migration_entry_to_page(entry);
+	page = pfn_swap_entry_to_page(entry);
 
 	/*
 	 * Once page cache replacement of page migration started, page_count

@@ -361,7 +361,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
 	ptl = pmd_lock(mm, pmd);
 	if (!is_pmd_migration_entry(*pmd))
 		goto unlock;
-	page = migration_entry_to_page(pmd_to_swp_entry(*pmd));
+	page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd));
 	if (!get_page_unless_zero(page))
 		goto unlock;
 	spin_unlock(ptl);

@@ -2443,7 +2443,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 			if (!is_device_private_entry(entry))
 				goto next;
 
-			page = device_private_entry_to_page(entry);
+			page = pfn_swap_entry_to_page(entry);
 			if (!(migrate->flags &
 				MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
 			    page->pgmap->owner != migrate->pgmap_owner)

index 86e3a3688d59..eed988ab2e81 100644
@@ -96,7 +96,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 		if (!is_migration_entry(entry))
 			return false;
 
-		pfn = migration_entry_to_pfn(entry);
+		pfn = swp_offset(entry);
 	} else if (is_swap_pte(*pvmw->pte)) {
 		swp_entry_t entry;
 

@@ -105,7 +105,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 		if (!is_device_private_entry(entry))
 			return false;
 
-		pfn = device_private_entry_to_pfn(entry);
+		pfn = swp_offset(entry);
 	} else {
 		if (!pte_present(*pvmw->pte))
 			return false;

@@ -200,7 +200,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 				if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
 					swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
 
-					if (migration_entry_to_page(entry) != page)
+					if (pfn_swap_entry_to_page(entry) != page)
 						return not_found(pvmw);
 					return true;
 				}

index 139be8235ad2..4dfd807ae52a 100644
@@ -100,35 +100,35 @@ static inline void *swp_to_radix_entry(swp_entry_t entry)
 }
 
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
-static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
+static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
 {
-	return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ,
-			 page_to_pfn(page));
+	return swp_entry(SWP_DEVICE_READ, offset);
 }
 
-static inline bool is_device_private_entry(swp_entry_t entry)
+static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset)
 {
-	int type = swp_type(entry);
-	return type = SWP_DEVICE_READ || type = SWP_DEVICE_WRITE;
+	return swp_entry(SWP_DEVICE_WRITE, offset);
 }
 
-static inline void make_device_private_entry_read(swp_entry_t *entry)
+static inline bool is_device_private_entry(swp_entry_t entry)
 {
-	*entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry));
+	int type = swp_type(entry);
+	return type = SWP_DEVICE_READ || type = SWP_DEVICE_WRITE;
 }
 
-static inline bool is_write_device_private_entry(swp_entry_t entry)
+static inline bool is_writable_device_private_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) = SWP_DEVICE_WRITE);
 }
 #else /* CONFIG_DEVICE_PRIVATE */
-static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
+static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
 {
 	return swp_entry(0, 0);
 }
 
-static inline void make_device_private_entry_read(swp_entry_t *entry)
+static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset)
 {
+	return swp_entry(0, 0);
 }
 
 static inline bool is_device_private_entry(swp_entry_t entry)

@@ -136,35 +136,32 @@ static inline bool is_device_private_entry(swp_entry_t entry)
 	return false;
 }
 
-static inline bool is_write_device_private_entry(swp_entry_t entry)
+static inline bool is_writable_device_private_entry(swp_entry_t entry)
 {
 	return false;
 }
 #endif /* CONFIG_DEVICE_PRIVATE */
 
 #ifdef CONFIG_MIGRATION
-static inline swp_entry_t make_migration_entry(struct page *page, int write)
-{
-	BUG_ON(!PageLocked(compound_head(page)));
-
-	return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ,
-			page_to_pfn(page));
-}
-
 static inline int is_migration_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) = SWP_MIGRATION_READ ||
 			swp_type(entry) = SWP_MIGRATION_WRITE);
 }
 
-static inline int is_write_migration_entry(swp_entry_t entry)
+static inline int is_writable_migration_entry(swp_entry_t entry)
 {
 	return unlikely(swp_type(entry) = SWP_MIGRATION_WRITE);
 }
 
-static inline void make_migration_entry_read(swp_entry_t *entry)
+static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
 {
-	*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
+	return swp_entry(SWP_MIGRATION_READ, offset);
+}
+
+static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
+{
+	return swp_entry(SWP_MIGRATION_WRITE, offset);
 }
 
 extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,

@@ -174,21 +171,28 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 extern void migration_entry_wait_huge(struct vm_area_struct *vma,
 		struct mm_struct *mm, pte_t *pte);
 #else
+static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
+{
+	return swp_entry(0, 0);
+}
+
+static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
+{
+	return swp_entry(0, 0);
+}
 
-#define make_migration_entry(page, write) swp_entry(0, 0)
 static inline int is_migration_entry(swp_entry_t swp)
 {
 	return 0;
 }
 
-static inline void make_migration_entry_read(swp_entry_t *entryp) { }
 static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 					spinlock_t *ptl) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
 static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
 		struct mm_struct *mm, pte_t *pte) { }
-static inline int is_write_migration_entry(swp_entry_t entry)
+static inline int is_writable_migration_entry(swp_entry_t entry)
 {
 	return 0;
 }

index a9bd6ce1ba02..3697a80b32f8 100644
@@ -817,17 +817,17 @@ static void __init swap_migration_tests(void)
 	 * locked, otherwise it stumbles upon a BUG_ON().
 	 */
 	__SetPageLocked(page);
-	swp = make_migration_entry(page, 1);
+	swp = make_writable_migration_entry(page_to_pfn(page));
 	WARN_ON(!is_migration_entry(swp));
-	WARN_ON(!is_write_migration_entry(swp));
+	WARN_ON(!is_writable_migration_entry(swp));
 
-	make_migration_entry_read(&swp);
+	swp = make_readable_migration_entry(swp_offset(swp));
 	WARN_ON(!is_migration_entry(swp));
-	WARN_ON(is_write_migration_entry(swp));
+	WARN_ON(is_writable_migration_entry(swp));
 
-	swp = make_migration_entry(page, 0);
+	swp = make_readable_migration_entry(page_to_pfn(page));
 	WARN_ON(!is_migration_entry(swp));
-	WARN_ON(is_write_migration_entry(swp));
+	WARN_ON(is_writable_migration_entry(swp));
 	__ClearPageLocked(page);
 	__free_page(page);
 }

index 3b2dda71d0ed..11df3ca30b82 100644
@@ -255,7 +255,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		 */
 		if (hmm_is_device_private_entry(range, entry)) {
 			cpu_flags = HMM_PFN_VALID;
-			if (is_write_device_private_entry(entry))
+			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
 			*hmm_pfn = swp_offset(entry) | cpu_flags;
 			return 0;

index a4cda8564bcf..89af065cea5b 100644
@@ -1051,8 +1051,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		swp_entry_t entry = pmd_to_swp_entry(pmd);
 
 		VM_BUG_ON(!is_pmd_migration_entry(pmd));
-		if (is_write_migration_entry(entry)) {
-			make_migration_entry_read(&entry);
+		if (is_writable_migration_entry(entry)) {
+			entry = make_readable_migration_entry(
+							swp_offset(entry));
 			pmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*src_pmd))
 				pmd = pmd_swp_mksoft_dirty(pmd);

@@ -1825,13 +1826,14 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 
 		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
-		if (is_write_migration_entry(entry)) {
+		if (is_writable_migration_entry(entry)) {
 			pmd_t newpmd;
 			/*
 			 * A protection check is difficult so
 			 * just be safe and disable write
 			 */
-			make_migration_entry_read(&entry);
+			entry = make_readable_migration_entry(
+							swp_offset(entry));
 			newpmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*pmd))
 				newpmd = pmd_swp_mksoft_dirty(newpmd);

@@ -2109,7 +2111,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
 		entry = pmd_to_swp_entry(old_pmd);
 		page = pfn_swap_entry_to_page(entry);
-		write = is_write_migration_entry(entry);
+		write = is_writable_migration_entry(entry);
 		young = false;
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);
 		uffd_wp = pmd_swp_uffd_wp(old_pmd);

@@ -2141,7 +2143,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		 */
 		if (freeze || pmd_migration) {
 			swp_entry_t swp_entry;
-			swp_entry = make_migration_entry(page + i, write);
+			if (write)
+				swp_entry = make_writable_migration_entry(
+							page_to_pfn(page + i));
+			else
+				swp_entry = make_readable_migration_entry(
+							page_to_pfn(page + i));
 			entry = swp_entry_to_pte(swp_entry);
 			if (soft_dirty)
 				entry = pte_swp_mksoft_dirty(entry);

@@ -2998,7 +3005,10 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
 	if (pmd_dirty(pmdval))
 		set_page_dirty(page);
-	entry = make_migration_entry(page, pmd_write(pmdval));
+	if (pmd_write(pmdval))
+		entry = make_writable_migration_entry(page_to_pfn(page));
+	else
+		entry = make_readable_migration_entry(page_to_pfn(page));
 	pmdswp = swp_entry_to_pmd(entry);
 	if (pmd_soft_dirty(pmdval))
 		pmdswp = pmd_swp_mksoft_dirty(pmdswp);

@@ -3024,7 +3034,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot));
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
-	if (is_write_migration_entry(entry))
+	if (is_writable_migration_entry(entry))
 		pmde = maybe_pmd_mkwrite(pmde, vma);
 
 	flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);

index 8fb42c6dd74b..59645169839b 100644
@@ -3795,12 +3795,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 				    is_hugetlb_entry_hwpoisoned(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
 
-			if (is_write_migration_entry(swp_entry) && cow) {
+			if (is_writable_migration_entry(swp_entry) && cow) {
 				/*
 				 * COW mappings require pages in both
 				 * parent and child to be set to read.
 				 */
-				make_migration_entry_read(&swp_entry);
+				swp_entry = make_readable_migration_entry(
+							swp_offset(swp_entry));
 				entry = swp_entry_to_pte(swp_entry);
 				set_huge_swap_pte_at(src, addr, src_pte,
 						     entry, sz);

@@ -4970,10 +4971,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		if (unlikely(is_hugetlb_entry_migration(pte))) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
-			if (is_write_migration_entry(entry)) {
+			if (is_writable_migration_entry(entry)) {
 				pte_t newpte;
 
-				make_migration_entry_read(&entry);
+				entry = make_readable_migration_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				set_huge_swap_pte_at(mm, address, ptep,
 						     newpte, huge_page_size(h));

index 1c98e3c1c2de..3a5705cfc891 100644
@@ -734,13 +734,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 		rss[mm_counter(page)]++;
 
-		if (is_write_migration_entry(entry) &&
+		if (is_writable_migration_entry(entry) &&
 				is_cow_mapping(vm_flags)) {
 			/*
 			 * COW mappings require pages in both
 			 * parent and child to be set to read.
 			 */
-			make_migration_entry_read(&entry);
+			entry = make_readable_migration_entry(
+							swp_offset(entry));
 			pte = swp_entry_to_pte(entry);
 			if (pte_swp_soft_dirty(*src_pte))
 				pte = pte_swp_mksoft_dirty(pte);

@@ -771,9 +772,10 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 * when a device driver is involved (you cannot easily
 		 * save and restore device driver state).
 		 */
-		if (is_write_device_private_entry(entry) &&
+		if (is_writable_device_private_entry(entry) &&
 		    is_cow_mapping(vm_flags)) {
-			make_device_private_entry_read(&entry);
+			entry = make_readable_device_private_entry(
+							swp_offset(entry));
 			pte = swp_entry_to_pte(entry);
 			if (pte_swp_uffd_wp(*src_pte))
 				pte = pte_swp_mkuffd_wp(pte);

index 600978d18750..b752543adb64 100644
@@ -237,13 +237,18 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		 * Recheck VMA as permissions can change since migration started
 		 */
 		entry = pte_to_swp_entry(*pvmw.pte);
-		if (is_write_migration_entry(entry))
+		if (is_writable_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
 		if (unlikely(is_device_private_page(new))) {
-			entry = make_device_private_entry(new, pte_write(pte));
+			if (pte_write(pte))
+				entry = make_writable_device_private_entry(
+							page_to_pfn(new));
+			else
+				entry = make_readable_device_private_entry(
+							page_to_pfn(new));
 			pte = swp_entry_to_pte(entry);
 			if (pte_swp_soft_dirty(*pvmw.pte))
 				pte = pte_swp_mksoft_dirty(pte);

@@ -2451,7 +2456,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 
 			mpfn = migrate_pfn(page_to_pfn(page)) |
 					MIGRATE_PFN_MIGRATE;
-			if (is_write_device_private_entry(entry))
+			if (is_writable_device_private_entry(entry))
 				mpfn |= MIGRATE_PFN_WRITE;
 		} else {
 			if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM))

@@ -2497,8 +2502,12 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 			ptep_get_and_clear(mm, addr, ptep);
 
 			/* Setup special migration page table entry */
-			entry = make_migration_entry(page, mpfn &
-						     MIGRATE_PFN_WRITE);
+			if (mpfn & MIGRATE_PFN_WRITE)
+				entry = make_writable_migration_entry(
+							page_to_pfn(page));
+			else
+				entry = make_readable_migration_entry(
+							page_to_pfn(page));
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_present(pte)) {
 				if (pte_soft_dirty(pte))

@@ -2971,7 +2980,12 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 		if (is_device_private_page(page)) {
 			swp_entry_t swp_entry;
 
-			swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
+			if (vma->vm_flags & VM_WRITE)
+				swp_entry = make_writable_device_private_entry(
+							page_to_pfn(page));
+			else
+				swp_entry = make_readable_device_private_entry(
+							page_to_pfn(page));
 			entry = swp_entry_to_pte(swp_entry);
 		}
 	} else {

index 94188df1ee55..f21b760ec809 100644
@@ -143,23 +143,25 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 			pte_t newpte;
 
-			if (is_write_migration_entry(entry)) {
+			if (is_writable_migration_entry(entry)) {
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
 				 */
-				make_migration_entry_read(&entry);
+				entry = make_readable_migration_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_soft_dirty(oldpte))
 					newpte = pte_swp_mksoft_dirty(newpte);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);
-			} else if (is_write_device_private_entry(entry)) {
+			} else if (is_writable_device_private_entry(entry)) {
 				/*
 				 * We do not preserve soft-dirtiness. See
 				 * copy_one_pte() for explanation.
 				 */
-				make_device_private_entry_read(&entry);
+				entry = make_readable_device_private_entry(
+							swp_offset(entry));
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);

index b0fc27e77d6d..977e70803ed8 100644
@@ -1526,7 +1526,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * pte. do_swap_page() will wait until the migration
 			 * pte is removed and then restart fault handling.
 			 */
-			entry = make_migration_entry(page, 0);
+			entry = make_readable_migration_entry(page_to_pfn(page));
 			swp_pte = swp_entry_to_pte(entry);
 
 			/*

@@ -1622,8 +1622,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * pte. do_swap_page() will wait until the migration
 			 * pte is removed and then restart fault handling.
 			 */
-			entry = make_migration_entry(subpage,
-					pte_write(pteval));
+			if (pte_write(pteval))
+				entry = make_writable_migration_entry(
+							page_to_pfn(subpage));
+			else
+				entry = make_readable_migration_entry(
+							page_to_pfn(subpage));
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);

index def5c62c93b3..e26ac2d71346 100644
@@ -87,7 +87,6 @@ struct anon_vma_chain {
 
 enum ttu_flags {
 	TTU_MIGRATION		= 0x1,	/* migration mode */
-	TTU_MUNLOCK		= 0x2,	/* munlock mode */
 
 	TTU_SPLIT_HUGE_PMD	= 0x4,	/* split huge PMD if any */
 	TTU_IGNORE_MLOCK	= 0x8,	/* ignore mlock */

index 977e70803ed8..d02bade5245b 100644
@@ -1405,10 +1405,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 
-	/* munlock has nothing to gain from examining un-locked vmas */
-	if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
-		return true;
-
 	if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) &&
 	    is_zone_device_page(page) && !is_device_private_page(page))
 		return true;

@@ -1469,8 +1465,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
-			if (flags & TTU_MUNLOCK)
-				continue;
 		}
 
 		/* Unexpected PMD-mapped THP? */

@@ -1784,6 +1778,37 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
 	return !page_mapcount(page) ? true : false;
 }
 
+static bool try_to_munlock_one(struct page *page, struct vm_area_struct *vma,
+		     unsigned long address, void *arg)
+{
+	struct page_vma_mapped_walk pvmw = {
+		.page = page,
+		.vma = vma,
+		.address = address,
+	};
+
+	/* munlock has nothing to gain from examining un-locked vmas */
+	if (!(vma->vm_flags & VM_LOCKED))
+		return true;
+
+	while (page_vma_mapped_walk(&pvmw)) {
+		/* PTE-mapped THP are never mlocked */
+		if (!PageTransCompound(page)) {
+			/*
+			 * Holding pte lock, we do *not* need
+			 * mmap_lock here
+			 */
+			mlock_vma_page(page);
+		}
+		page_vma_mapped_walk_done(&pvmw);
+
+		/* found a mlocked page, no point continuing munlock check */
+		return false;
+	}
+
+	return true;
+}
+
 /**
  * try_to_munlock - try to munlock a page
  * @page: the page to be munlocked

@@ -1796,8 +1821,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
 void try_to_munlock(struct page *page)
 {
 	struct rmap_walk_control rwc = {
-		.rmap_one = try_to_unmap_one,
-		.arg = (void *)TTU_MUNLOCK,
+		.rmap_one = try_to_munlock_one,
 		.done = page_not_mapped,
 		.anon_lock = page_lock_anon_vma_read,
 

index e26ac2d71346..6062e0cfca2d 100644
@@ -86,8 +86,6 @@ struct anon_vma_chain {
 };
 
 enum ttu_flags {
-	TTU_MIGRATION		= 0x1,	/* migration mode */
-
 	TTU_SPLIT_HUGE_PMD	= 0x4,	/* split huge PMD if any */
 	TTU_IGNORE_MLOCK	= 0x8,	/* ignore mlock */
 	TTU_IGNORE_HWPOISON	= 0x20,	/* corrupted page is recoverable */

@@ -96,7 +94,6 @@ enum ttu_flags {
 					 * do a final flush if necessary */
 	TTU_RMAP_LOCKED		= 0x80,	/* do not grab rmap lock:
 					 * caller holds it */
-	TTU_SPLIT_FREEZE	= 0x100,		/* freeze pte under splitting thp */
 };
 
 #ifdef CONFIG_MMU

@@ -193,6 +190,7 @@ static inline void page_dup_rmap(struct page *page, bool compound)
 int page_referenced(struct page *, int is_locked,
 			struct mem_cgroup *memcg, unsigned long *vm_flags);
 
+bool try_to_migrate(struct page *page, enum ttu_flags flags);
 bool try_to_unmap(struct page *, enum ttu_flags flags);
 
 /* Avoid racy checks */

index 89af065cea5b..eab004331b97 100644
@@ -2357,16 +2357,21 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 
 static void unmap_page(struct page *page)
 {
-	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
-		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
+	enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
 	bool unmap_success;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
-		ttu_flags |= TTU_SPLIT_FREEZE;
-
-	unmap_success = try_to_unmap(page, ttu_flags);
+		unmap_success = try_to_migrate(page, ttu_flags);
+	else
+		/*
+		 * Don't install migration entries for file backed pages. This
+		 * helps handle cases when i_size is in the middle of the page
+		 * as there is no need to unmap pages beyond i_size manually.
+		 */
+		unmap_success = try_to_unmap(page, ttu_flags |
+						TTU_IGNORE_MLOCK);
 	VM_BUG_ON_PAGE(!unmap_success, page);
 }
 

index b752543adb64..cc4612e2a246 100644
@@ -1130,7 +1130,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		/* Establish migration ptes */
 		VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
 				page);
-		try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK);
+		try_to_migrate(page, 0);
 		page_was_mapped = 1;
 	}
 

@@ -1332,7 +1332,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 
 	if (page_mapped(hpage)) {
 		bool mapping_locked = false;
-		enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK;
+		enum ttu_flags ttu = 0;
 
 		if (!PageAnon(hpage)) {
 			/*

@@ -1349,7 +1349,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 			ttu |= TTU_RMAP_LOCKED;
 		}
 
-		try_to_unmap(hpage, ttu);
+		try_to_migrate(hpage, ttu);
 		page_was_mapped = 1;
 
 		if (mapping_locked)

@@ -2756,7 +2756,6 @@ static void migrate_vma_prepare(struct migrate_vma *migrate)
  */
 static void migrate_vma_unmap(struct migrate_vma *migrate)
 {
-	int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK;
 	const unsigned long npages = migrate->npages;
 	const unsigned long start = migrate->start;
 	unsigned long addr, i, restore = 0;

@@ -2768,7 +2767,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate)
 			continue;
 
 		if (page_mapped(page)) {
-			try_to_unmap(page, flags);
+			try_to_migrate(page, 0);
 			if (page_mapped(page))
 				goto restore;
 		}

394 lines not on this page · raw message

index f18bd53da052..94f841026c3b 100644
@@ -265,7 +265,7 @@ nouveau_svmm_invalidate_range_start(struct mmu_notifier *mn,
 	 * the invalidation is handled as part of the migration process.
 	 */
 	if (update->event = MMU_NOTIFY_MIGRATE &&
-	    update->migrate_pgmap_owner = svmm->vmm->cli->drm->dev)
+	    update->owner = svmm->vmm->cli->drm->dev)
 		goto out;
 
 	if (limit > svmm->unmanaged.start && start < svmm->unmanaged.limit) {

index b8200782dede..2e6068d3fb9f 100644
@@ -41,7 +41,12 @@ struct mmu_interval_notifier;
  *
  * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal
  * a device driver to possibly ignore the invalidation if the
- * migrate_pgmap_owner field matches the driver's device private pgmap owner.
+ * owner field matches the driver's device private pgmap owner.
+ *
+ * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no
+ * longer have exclusive access to the page. May ignore the invalidation that's
+ * part of make_device_exclusive_range() if the owner field
+ * matches the value passed to make_device_exclusive_range().
  */
 enum mmu_notifier_event {
 	MMU_NOTIFY_UNMAP = 0,

@@ -51,6 +56,7 @@ enum mmu_notifier_event {
 	MMU_NOTIFY_SOFT_DIRTY,
 	MMU_NOTIFY_RELEASE,
 	MMU_NOTIFY_MIGRATE,
+	MMU_NOTIFY_EXCLUSIVE,
 };
 
 #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)

@@ -269,7 +275,7 @@ struct mmu_notifier_range {
 	unsigned long end;
 	unsigned flags;
 	enum mmu_notifier_event event;
-	void *migrate_pgmap_owner;
+	void *owner;
 };
 
 static inline int mm_has_notifiers(struct mm_struct *mm)

@@ -521,14 +527,14 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range,
 	range->flags = flags;
 }
 
-static inline void mmu_notifier_range_init_migrate(
-			struct mmu_notifier_range *range, unsigned int flags,
+static inline void mmu_notifier_range_init_owner(
+			struct mmu_notifier_range *range,
+			enum mmu_notifier_event event, unsigned int flags,
 			struct vm_area_struct *vma, struct mm_struct *mm,
-			unsigned long start, unsigned long end, void *pgmap)
+			unsigned long start, unsigned long end, void *owner)
 {
-	mmu_notifier_range_init(range, MMU_NOTIFY_MIGRATE, flags, vma, mm,
-				start, end);
-	range->migrate_pgmap_owner = pgmap;
+	mmu_notifier_range_init(range, event, flags, vma, mm, start, end);
+	range->owner = owner;
 }
 
 #define ptep_clear_flush_young_notify(__vma, __address, __ptep)		\

@@ -655,8 +661,8 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range,
 
 #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end)  \
 	_mmu_notifier_range_init(range, start, end)
-#define mmu_notifier_range_init_migrate(range, flags, vma, mm, start, end, \
-					pgmap) \
+#define mmu_notifier_range_init_owner(range, event, flags, vma, mm, start, \
+					end, owner) \
 	_mmu_notifier_range_init(range, start, end)
 
 static inline bool

index 6062e0cfca2d..b207c138cbff 100644
@@ -193,6 +193,10 @@ int page_referenced(struct page *, int is_locked,
 bool try_to_migrate(struct page *page, enum ttu_flags flags);
 bool try_to_unmap(struct page *, enum ttu_flags flags);
 
+int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, struct page **pages,
+				void *arg);
+
 /* Avoid racy checks */
 #define PVMW_SYNC		(1 << 0)
 /* Look for migarion entries rather than present PTEs */

index 516104b9334b..7a3c260146df 100644
@@ -63,9 +63,11 @@ static inline int current_is_kswapd(void)
  * to a special SWP_DEVICE_* entry.
  */
 #ifdef CONFIG_DEVICE_PRIVATE
-#define SWP_DEVICE_NUM 2
+#define SWP_DEVICE_NUM 4
 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM)
 #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1)
+#define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2)
+#define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3)
 #else
 #define SWP_DEVICE_NUM 0
 #endif

62 lines not on this page · raw message

index 80a78877bd93..5c9f5a020c1d 100644
@@ -218,7 +218,7 @@ static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
 	 * the invalidation is handled as part of the migration process.
 	 */
 	if (range->event = MMU_NOTIFY_MIGRATE &&
-	    range->migrate_pgmap_owner = dmirror->mdevice)
+	    range->owner = dmirror->mdevice)
 		return true;
 
 	if (mmu_notifier_range_blockable(range))

index 11df3ca30b82..fad6be2bf072 100644
@@ -26,6 +26,8 @@
 #include <linux/mmu_notifier.h>
 #include <linux/memory_hotplug.h>
 
+#include "internal.h"
+
 struct hmm_vma_walk {
 	struct hmm_range	*range;
 	unsigned long		last;

@@ -271,6 +273,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		if (!non_swap_entry(entry))
 			goto fault;
 
+		if (is_device_exclusive_entry(entry))
+			goto fault;
+
 		if (is_migration_entry(entry)) {
 			pte_unmap(ptep);
 			hmm_vma_walk->last = addr;

138 lines not on this page · raw message

index cc4612e2a246..9cc9251d4802 100644
@@ -2570,8 +2570,8 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
 	 * that the registered device driver can skip invalidating device
 	 * private page mappings that won't be migrated.
 	 */
-	mmu_notifier_range_init_migrate(&range, 0, migrate->vma,
-		migrate->vma->vm_mm, migrate->start, migrate->end,
+	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0,
+		migrate->vma, migrate->vma->vm_mm, migrate->start, migrate->end,
 		migrate->pgmap_owner);
 	mmu_notifier_invalidate_range_start(&range);
 

@@ -3074,9 +3074,9 @@ void migrate_vma_pages(struct migrate_vma *migrate)
 			if (!notified) {
 				notified = true;
 
-				mmu_notifier_range_init_migrate(&range, 0,
-					migrate->vma, migrate->vma->vm_mm,
-					addr, migrate->end,
+				mmu_notifier_range_init_owner(&range,
+					MMU_NOTIFY_MIGRATE, 0, migrate->vma,
+					migrate->vma->vm_mm, addr, migrate->end,
 					migrate->pgmap_owner);
 				mmu_notifier_invalidate_range_start(&range);
 			}

index f21b760ec809..c6018541ea3d 100644
@@ -165,6 +165,14 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				newpte = swp_entry_to_pte(entry);
 				if (pte_swp_uffd_wp(oldpte))
 					newpte = pte_swp_mkuffd_wp(newpte);
+			} else if (is_writable_device_exclusive_entry(entry)) {
+				entry = make_readable_device_exclusive_entry(
+							swp_offset(entry));
+				newpte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(oldpte))
+					newpte = pte_swp_mksoft_dirty(newpte);
+				if (pte_swp_uffd_wp(oldpte))
+					newpte = pte_swp_mkuffd_wp(newpte);
 			} else {
 				newpte = oldpte;
 			}

index eed988ab2e81..29842f169219 100644
@@ -41,7 +41,8 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
 
 				/* Handle un-addressable ZONE_DEVICE memory */
 				entry = pte_to_swp_entry(*pvmw->pte);
-				if (!is_device_private_entry(entry))
+				if (!is_device_private_entry(entry) &&
+				    !is_device_exclusive_entry(entry))
 					return false;
 			} else if (!pte_present(*pvmw->pte))
 				return false;

@@ -93,7 +94,8 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 			return false;
 		entry = pte_to_swp_entry(*pvmw->pte);
 
-		if (!is_migration_entry(entry))
+		if (!is_migration_entry(entry) &&
+		    !is_device_exclusive_entry(entry))
 			return false;
 
 		pfn = swp_offset(entry);

@@ -102,7 +104,8 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 
 		/* Handle un-addressable ZONE_DEVICE memory */
 		entry = pte_to_swp_entry(*pvmw->pte);
-		if (!is_device_private_entry(entry))
+		if (!is_device_private_entry(entry) &&
+		    !is_device_exclusive_entry(entry))
 			return false;
 
 		pfn = swp_offset(entry);

216 lines not on this page · raw message

index 5c9f5a020c1d..305a9d9e2b4c 100644
@@ -25,6 +25,7 @@
 #include <linux/swapops.h>
 #include <linux/sched/mm.h>
 #include <linux/platform_device.h>
+#include <linux/rmap.h>
 
 #include "test_hmm_uapi.h"
 

@@ -46,6 +47,7 @@ struct dmirror_bounce {
 	unsigned long		cpages;
 };
 
+#define DPT_XA_TAG_ATOMIC 1UL
 #define DPT_XA_TAG_WRITE 3UL
 
 /*

@@ -619,6 +621,54 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,
 	}
 }
 
+static int dmirror_check_atomic(struct dmirror *dmirror, unsigned long start,
+			     unsigned long end)
+{
+	unsigned long pfn;
+
+	for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
+		void *entry;
+		struct page *page;
+
+		entry = xa_load(&dmirror->pt, pfn);
+		page = xa_untag_pointer(entry);
+		if (xa_pointer_tag(entry) = DPT_XA_TAG_ATOMIC)
+			return -EPERM;
+	}
+
+	return 0;
+}
+
+static int dmirror_atomic_map(unsigned long start, unsigned long end,
+			      struct page **pages, struct dmirror *dmirror)
+{
+	unsigned long pfn, mapped = 0;
+	int i;
+
+	/* Map the migrated pages into the device's page tables. */
+	mutex_lock(&dmirror->mutex);
+
+	for (i = 0, pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++, i++) {
+		void *entry;
+
+		if (!pages[i])
+			continue;
+
+		entry = pages[i];
+		entry = xa_tag_pointer(entry, DPT_XA_TAG_ATOMIC);
+		entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC);
+		if (xa_is_err(entry)) {
+			mutex_unlock(&dmirror->mutex);
+			return xa_err(entry);
+		}
+
+		mapped++;
+	}
+
+	mutex_unlock(&dmirror->mutex);
+	return mapped;
+}
+
 static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 					    struct dmirror *dmirror)
 {

@@ -661,6 +711,71 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args,
 	return 0;
 }
 
+static int dmirror_exclusive(struct dmirror *dmirror,
+			     struct hmm_dmirror_cmd *cmd)
+{
+	unsigned long start, end, addr;
+	unsigned long size = cmd->npages << PAGE_SHIFT;
+	struct mm_struct *mm = dmirror->notifier.mm;
+	struct page *pages[64];
+	struct dmirror_bounce bounce;
+	unsigned long next;
+	int ret;
+
+	start = cmd->addr;
+	end = start + size;
+	if (end < start)
+		return -EINVAL;
+
+	/* Since the mm is for the mirrored process, get a reference first. */
+	if (!mmget_not_zero(mm))
+		return -EINVAL;
+
+	mmap_read_lock(mm);
+	for (addr = start; addr < end; addr = next) {
+		int i, mapped;
+
+		if (end < addr + (ARRAY_SIZE(pages) << PAGE_SHIFT))
+			next = end;
+		else
+			next = addr + (ARRAY_SIZE(pages) << PAGE_SHIFT);
+
+		ret = make_device_exclusive_range(mm, addr, next, pages, NULL);
+		mapped = dmirror_atomic_map(addr, next, pages, dmirror);
+		for (i = 0; i < ret; i++) {
+			if (pages[i]) {
+				unlock_page(pages[i]);
+				put_page(pages[i]);
+			}
+		}
+
+		if (addr + (mapped << PAGE_SHIFT) < next) {
+			mmap_read_unlock(mm);
+			mmput(mm);
+			return -EBUSY;
+		}
+	}
+	mmap_read_unlock(mm);
+	mmput(mm);
+
+	/* Return the migrated data for verification. */
+	ret = dmirror_bounce_init(&bounce, start, size);
+	if (ret)
+		return ret;
+	mutex_lock(&dmirror->mutex);
+	ret = dmirror_do_read(dmirror, start, end, &bounce);
+	mutex_unlock(&dmirror->mutex);
+	if (ret = 0) {
+		if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr,
+				 bounce.size))
+			ret = -EFAULT;
+	}
+
+	cmd->cpages = bounce.cpages;
+	dmirror_bounce_fini(&bounce);
+	return ret;
+}
+
 static int dmirror_migrate(struct dmirror *dmirror,
 			   struct hmm_dmirror_cmd *cmd)
 {

@@ -949,6 +1064,15 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp,
 		ret = dmirror_migrate(dmirror, &cmd);
 		break;
 
+	case HMM_DMIRROR_EXCLUSIVE:
+		ret = dmirror_exclusive(dmirror, &cmd);
+		break;
+
+	case HMM_DMIRROR_CHECK_EXCLUSIVE:
+		ret = dmirror_check_atomic(dmirror, cmd.addr,
+					cmd.addr + (cmd.npages << PAGE_SHIFT));
+		break;
+
 	case HMM_DMIRROR_SNAPSHOT:
 		ret = dmirror_snapshot(dmirror, &cmd);
 		break;

index 670b4ef2a5b6..f14dea5dcd06 100644
@@ -33,6 +33,8 @@ struct hmm_dmirror_cmd {
 #define HMM_DMIRROR_WRITE		_IOWR('H', 0x01, struct hmm_dmirror_cmd)
 #define HMM_DMIRROR_MIGRATE		_IOWR('H', 0x02, struct hmm_dmirror_cmd)
 #define HMM_DMIRROR_SNAPSHOT		_IOWR('H', 0x03, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_EXCLUSIVE		_IOWR('H', 0x04, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_CHECK_EXCLUSIVE	_IOWR('H', 0x05, struct hmm_dmirror_cmd)
 
 /*
  * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.

162 lines not on this page · raw message

index 94f841026c3b..a195e48c9aee 100644
@@ -567,18 +567,27 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 	unsigned long hmm_pfns[1];
 	struct hmm_range range = {
 		.notifier = &notifier->notifier,
-		.start = notifier->notifier.interval_tree.start,
-		.end = notifier->notifier.interval_tree.last + 1,
 		.default_flags = hmm_flags,
 		.hmm_pfns = hmm_pfns,
 		.dev_private_owner = drm->dev,
 	};
-	struct mm_struct *mm = notifier->notifier.mm;
+	struct mm_struct *mm = svmm->notifier.mm;
 	int ret;
 
+	ret = mmu_interval_notifier_insert(&notifier->notifier, mm,
+					args->p.addr, args->p.size,
+					&nouveau_svm_mni_ops);
+	if (ret)
+		return ret;
+
+	range.start = notifier->notifier.interval_tree.start;
+	range.end = notifier->notifier.interval_tree.last + 1;
+
 	while (true) {
-		if (time_after(jiffies, timeout))
-			return -EBUSY;
+		if (time_after(jiffies, timeout)) {
+			ret = -EBUSY;
+			goto out;
+		}
 
 		range.notifier_seq = mmu_interval_read_begin(range.notifier);
 		mmap_read_lock(mm);

@@ -587,7 +596,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 		if (ret) {
 			if (ret = -EBUSY)
 				continue;
-			return ret;
+			goto out;
 		}
 
 		mutex_lock(&svmm->mutex);

@@ -606,6 +615,9 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 	svmm->vmm->vmm.object.client->super = false;
 	mutex_unlock(&svmm->mutex);
 
+out:
+	mmu_interval_notifier_remove(&notifier->notifier);
+
 	return ret;
 }
 

@@ -727,14 +739,8 @@ nouveau_svm_fault(struct nvif_notify *notify)
 		}
 
 		notifier.svmm = svmm;
-		ret = mmu_interval_notifier_insert(&notifier.notifier, mm,
-						   args.i.p.addr, args.i.p.size,
-						   &nouveau_svm_mni_ops);
-		if (!ret) {
-			ret = nouveau_range_fault(svmm, svm->drm, &args.i,
-				sizeof(args), hmm_flags, &notifier);
-			mmu_interval_notifier_remove(&notifier.notifier);
-		}
+		ret = nouveau_range_fault(svmm, svm->drm, &args.i,
+					sizeof(args), hmm_flags, &notifier);
 		mmput(mm);
 
 		limit = args.i.p.addr + args.i.p.size;

index d6dd40f21eed..9c7ff56831c5 100644
@@ -77,6 +77,7 @@ struct nvif_vmm_pfnmap_v0 {
 #define NVIF_VMM_PFNMAP_V0_APER                           0x00000000000000f0ULL
 #define NVIF_VMM_PFNMAP_V0_HOST                           0x0000000000000000ULL
 #define NVIF_VMM_PFNMAP_V0_VRAM                           0x0000000000000010ULL
+#define NVIF_VMM_PFNMAP_V0_A				  0x0000000000000004ULL
 #define NVIF_VMM_PFNMAP_V0_W                              0x0000000000000002ULL
 #define NVIF_VMM_PFNMAP_V0_V                              0x0000000000000001ULL
 #define NVIF_VMM_PFNMAP_V0_NONE                           0x0000000000000000ULL

190 lines not on this page · raw message

index a2b179568970..f6188aa9171c 100644
@@ -178,6 +178,7 @@ void nvkm_vmm_unmap_region(struct nvkm_vmm *, struct nvkm_vma *);
 #define NVKM_VMM_PFN_APER                                 0x00000000000000f0ULL
 #define NVKM_VMM_PFN_HOST                                 0x0000000000000000ULL
 #define NVKM_VMM_PFN_VRAM                                 0x0000000000000010ULL
+#define NVKM_VMM_PFN_A					  0x0000000000000004ULL
 #define NVKM_VMM_PFN_W                                    0x0000000000000002ULL
 #define NVKM_VMM_PFN_V                                    0x0000000000000001ULL
 #define NVKM_VMM_PFN_NONE                                 0x0000000000000000ULL

index 236db5570771..f02abd9cb4dd 100644
@@ -88,6 +88,9 @@ gp100_vmm_pgt_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
 		if (!(*map->pfn & NVKM_VMM_PFN_W))
 			data |= BIT_ULL(6); /* RO. */
 
+		if (!(*map->pfn & NVKM_VMM_PFN_A))
+			data |= BIT_ULL(7); /* Atomic disable. */
+
 		if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) {
 			addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT;
 			addr = dma_map_page(dev, pfn_to_page(addr), 0,

@@ -322,6 +325,9 @@ gp100_vmm_pd0_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt,
 		if (!(*map->pfn & NVKM_VMM_PFN_W))
 			data |= BIT_ULL(6); /* RO. */
 
+		if (!(*map->pfn & NVKM_VMM_PFN_A))
+			data |= BIT_ULL(7); /* Atomic disable. */
+
 		if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) {
 			addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT;
 			addr = dma_map_page(dev, pfn_to_page(addr), 0,