mm: remove MEMORY_DEVICE_PUBLIC support

The code hasn't been used since it was added to the tree, and doesn't
appear to actually be usable.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

fs/proc/task_mmu.c

@@ -1279,7 +1279,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 		if (pm->show_pfn)
 			frame = pte_pfn(pte);
 		flags |= PM_PRESENT;
-		page = _vm_normal_page(vma, addr, pte, true);
+		page = vm_normal_page(vma, addr, pte);
 		if (pte_soft_dirty(pte))
 			flags |= PM_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {

include/linux/hmm.h

@@ -584,7 +584,7 @@ static inline void hmm_mm_destroy(struct mm_struct *mm) {}
 static inline void hmm_mm_init(struct mm_struct *mm) {}
 #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
 
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
 struct hmm_devmem;
 
 struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
@@ -722,9 +722,6 @@ struct hmm_devmem {
 struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 				  struct device *device,
 				  unsigned long size);
-struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
-					   struct device *device,
-					   struct resource *res);
 
 /*
  * hmm_devmem_page_set_drvdata - set per-page driver data field
@@ -751,7 +748,7 @@ static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page)
 {
 	return page->hmm_data;
 }
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
+#endif /* CONFIG_DEVICE_PRIVATE */
 #else /* IS_ENABLED(CONFIG_HMM) */
 static inline void hmm_mm_destroy(struct mm_struct *mm) {}
 static inline void hmm_mm_init(struct mm_struct *mm) {}

include/linux/ioport.h

@@ -132,7 +132,6 @@ enum {
 	IORES_DESC_PERSISTENT_MEMORY		= 4,
 	IORES_DESC_PERSISTENT_MEMORY_LEGACY	= 5,
 	IORES_DESC_DEVICE_PRIVATE_MEMORY	= 6,
-	IORES_DESC_DEVICE_PUBLIC_MEMORY		= 7,
 };
 
 /* helpers to define resources */

include/linux/memremap.h

@@ -37,13 +37,6 @@ struct vmem_altmap {
  * A more complete discussion of unaddressable memory may be found in
  * include/linux/hmm.h and Documentation/vm/hmm.rst.
  *
- * MEMORY_DEVICE_PUBLIC:
- * Device memory that is cache coherent from device and CPU point of view. This
- * is use on platform that have an advance system bus (like CAPI or CCIX). A
- * driver can hotplug the device memory using ZONE_DEVICE and with that memory
- * type. Any page of a process can be migrated to such memory. However no one
- * should be allow to pin such memory so that it can always be evicted.
- *
  * MEMORY_DEVICE_FS_DAX:
  * Host memory that has similar access semantics as System RAM i.e. DMA
  * coherent and supports page pinning. In support of coordinating page
@@ -58,7 +51,6 @@ struct vmem_altmap {
  */
 enum memory_type {
 	MEMORY_DEVICE_PRIVATE = 1,
-	MEMORY_DEVICE_PUBLIC,
 	MEMORY_DEVICE_FS_DAX,
 	MEMORY_DEVICE_PCI_P2PDMA,
 };

include/linux/mm.h

@@ -944,7 +944,6 @@ static inline bool put_devmap_managed_page(struct page *page)
 		return false;
 	switch (page->pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
-	case MEMORY_DEVICE_PUBLIC:
 	case MEMORY_DEVICE_FS_DAX:
 		__put_devmap_managed_page(page);
 		return true;
@@ -960,12 +959,6 @@ static inline bool is_device_private_page(const struct page *page)
 		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
 }
 
-static inline bool is_device_public_page(const struct page *page)
-{
-	return is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_PUBLIC;
-}
-
 #ifdef CONFIG_PCI_P2PDMA
 static inline bool is_pci_p2pdma_page(const struct page *page)
 {
@@ -998,11 +991,6 @@ static inline bool is_device_private_page(const struct page *page)
 	return false;
 }
 
-static inline bool is_device_public_page(const struct page *page)
-{
-	return false;
-}
-
 static inline bool is_pci_p2pdma_page(const struct page *page)
 {
 	return false;
@@ -1431,10 +1419,8 @@ struct zap_details {
 	pgoff_t last_index;			/* Highest page->index to unmap */
 };
 
-struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
-			     pte_t pte, bool with_public_device);
-#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false)
-
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t pte);
 struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t pmd);
 

mm/Kconfig

@@ -718,17 +718,6 @@ config DEVICE_PRIVATE
 	  memory; i.e., memory that is only accessible from the device (or
 	  group of devices). You likely also want to select HMM_MIRROR.
 
-config DEVICE_PUBLIC
-	bool "Addressable device memory (like GPU memory)"
-	depends on ARCH_HAS_HMM
-	select HMM
-	select DEV_PAGEMAP_OPS
-
-	help
-	  Allows creation of struct pages to represent addressable device
-	  memory; i.e., memory that is accessible from both the device and
-	  the CPU
-
 config FRAME_VECTOR
 	bool
 

mm/gup.c

@@ -605,13 +605,6 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 		if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
 			goto unmap;
 		*page = pte_page(*pte);
-
-		/*
-		 * This should never happen (a device public page in the gate
-		 * area).
-		 */
-		if (is_device_public_page(*page))
-			goto unmap;
 	}
 	if (unlikely(!try_get_page(*page))) {
 		ret = -ENOMEM;

mm/hmm.c

@@ -1331,7 +1331,7 @@ EXPORT_SYMBOL(hmm_range_dma_unmap);
 #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
 
 
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
 struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
 				       unsigned long addr)
 {
@@ -1478,54 +1478,4 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 	return devmem;
 }
 EXPORT_SYMBOL_GPL(hmm_devmem_add);
-
-struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
-					   struct device *device,
-					   struct resource *res)
-{
-	struct hmm_devmem *devmem;
-	void *result;
-	int ret;
-
-	if (res->desc != IORES_DESC_DEVICE_PUBLIC_MEMORY)
-		return ERR_PTR(-EINVAL);
-
-	dev_pagemap_get_ops();
-
-	devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL);
-	if (!devmem)
-		return ERR_PTR(-ENOMEM);
-
-	init_completion(&devmem->completion);
-	devmem->pfn_first = -1UL;
-	devmem->pfn_last = -1UL;
-	devmem->resource = res;
-	devmem->device = device;
-	devmem->ops = ops;
-
-	ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release,
-			      0, GFP_KERNEL);
-	if (ret)
-		return ERR_PTR(ret);
-
-	devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
-	devmem->pfn_last = devmem->pfn_first +
-			   (resource_size(devmem->resource) >> PAGE_SHIFT);
-	devmem->page_fault = hmm_devmem_fault;
-
-	devmem->pagemap.type = MEMORY_DEVICE_PUBLIC;
-	devmem->pagemap.res = *devmem->resource;
-	devmem->pagemap.page_free = hmm_devmem_free;
-	devmem->pagemap.altmap_valid = false;
-	devmem->pagemap.ref = &devmem->ref;
-	devmem->pagemap.data = devmem;
-	devmem->pagemap.kill = hmm_devmem_ref_kill;
-	devmem->pagemap.cleanup = hmm_devmem_ref_exit;
-
-	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
-	if (IS_ERR(result))
-		return result;
-	return devmem;
-}
-EXPORT_SYMBOL_GPL(hmm_devmem_add_resource);
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
+#endif /* CONFIG_DEVICE_PRIVATE  */

mm/madvise.c

@@ -354,7 +354,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 			continue;
 		}
 
-		page = _vm_normal_page(vma, addr, ptent, true);
+		page = vm_normal_page(vma, addr, ptent);
 		if (!page)
 			continue;
 

mm/memcontrol.c

@@ -4793,7 +4793,7 @@ enum mc_target_type {
 static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
 						unsigned long addr, pte_t ptent)
 {
-	struct page *page = _vm_normal_page(vma, addr, ptent, true);
+	struct page *page = vm_normal_page(vma, addr, ptent);
 
 	if (!page || !page_mapped(page))
 		return NULL;
@@ -4994,8 +4994,8 @@ static int mem_cgroup_move_account(struct page *page,
  *   2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
  *     target for charge migration. if @target is not NULL, the entry is stored
  *     in target->ent.
- *   3(MC_TARGET_DEVICE): like MC_TARGET_PAGE  but page is MEMORY_DEVICE_PUBLIC
- *     or MEMORY_DEVICE_PRIVATE (so ZONE_DEVICE page and thus not on the lru).
+ *   3(MC_TARGET_DEVICE): like MC_TARGET_PAGE  but page is MEMORY_DEVICE_PRIVATE
+ *     (so ZONE_DEVICE page and thus not on the lru).
  *     For now we such page is charge like a regular page would be as for all
  *     intent and purposes it is just special memory taking the place of a
  *     regular page.
@@ -5029,8 +5029,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		 */
 		if (page->mem_cgroup == mc.from) {
 			ret = MC_TARGET_PAGE;
-			if (is_device_private_page(page) ||
-			    is_device_public_page(page))
+			if (is_device_private_page(page))
 				ret = MC_TARGET_DEVICE;
 			if (target)
 				target->page = page;
@@ -5101,8 +5100,8 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	if (ptl) {
 		/*
 		 * Note their can not be MC_TARGET_DEVICE for now as we do not
-		 * support transparent huge page with MEMORY_DEVICE_PUBLIC or
-		 * MEMORY_DEVICE_PRIVATE but this might change.
+		 * support transparent huge page with MEMORY_DEVICE_PRIVATE but
+		 * this might change.
 		 */
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;

mm/memory-failure.c

@@ -1177,16 +1177,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		goto unlock;
 	}
 
-	switch (pgmap->type) {
-	case MEMORY_DEVICE_PRIVATE:
-	case MEMORY_DEVICE_PUBLIC:
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		/*
 		 * TODO: Handle HMM pages which may need coordination
 		 * with device-side memory.
 		 */
 		goto unlock;
-	default:
-		break;
 	}
 
 	/*

mm/memory.c

@@ -571,8 +571,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
  * PFNMAP mappings in order to support COWable mappings.
  *
  */
-struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
-			     pte_t pte, bool with_public_device)
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+			    pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
 
@@ -585,29 +585,6 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 			return NULL;
 		if (is_zero_pfn(pfn))
 			return NULL;
-
-		/*
-		 * Device public pages are special pages (they are ZONE_DEVICE
-		 * pages but different from persistent memory). They behave
-		 * allmost like normal pages. The difference is that they are
-		 * not on the lru and thus should never be involve with any-
-		 * thing that involve lru manipulation (mlock, numa balancing,
-		 * ...).
-		 *
-		 * This is why we still want to return NULL for such page from
-		 * vm_normal_page() so that we do not have to special case all
-		 * call site of vm_normal_page().
-		 */
-		if (likely(pfn <= highest_memmap_pfn)) {
-			struct page *page = pfn_to_page(pfn);
-
-			if (is_device_public_page(page)) {
-				if (with_public_device)
-					return page;
-				return NULL;
-			}
-		}
-
 		if (pte_devmap(pte))
 			return NULL;
 
@@ -797,17 +774,6 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		rss[mm_counter(page)]++;
 	} else if (pte_devmap(pte)) {
 		page = pte_page(pte);
-
-		/*
-		 * Cache coherent device memory behave like regular page and
-		 * not like persistent memory page. For more informations see
-		 * MEMORY_DEVICE_CACHE_COHERENT in memory_hotplug.h
-		 */
-		if (is_device_public_page(page)) {
-			get_page(page);
-			page_dup_rmap(page, false);
-			rss[mm_counter(page)]++;
-		}
 	}
 
 out_set_pte:
@@ -1063,7 +1029,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		if (pte_present(ptent)) {
 			struct page *page;
 
-			page = _vm_normal_page(vma, addr, ptent, true);
+			page = vm_normal_page(vma, addr, ptent);
 			if (unlikely(details) && page) {
 				/*
 				 * unmap_shared_mapping_pages() wants to

mm/migrate.c

@@ -246,8 +246,6 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 			if (is_device_private_page(new)) {
 				entry = make_device_private_entry(new, pte_write(pte));
 				pte = swp_entry_to_pte(entry);
-			} else if (is_device_public_page(new)) {
-				pte = pte_mkdevmap(pte);
 			}
 		}
 
@@ -381,7 +379,6 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
 	 * ZONE_DEVICE pages.
 	 */
 	expected_count += is_device_private_page(page);
-	expected_count += is_device_public_page(page);
 	if (mapping)
 		expected_count += hpage_nr_pages(page) + page_has_private(page);
 
@@ -994,10 +991,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		if (!PageMappingFlags(page))
 			page->mapping = NULL;
 
-		if (unlikely(is_zone_device_page(newpage))) {
-			if (is_device_public_page(newpage))
-				flush_dcache_page(newpage);
-		} else
+		if (likely(!is_zone_device_page(newpage)))
 			flush_dcache_page(newpage);
 
 	}
@@ -2265,7 +2259,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 				pfn = 0;
 				goto next;
 			}
-			page = _vm_normal_page(migrate->vma, addr, pte, true);
+			page = vm_normal_page(migrate->vma, addr, pte);
 			mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
 			mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
 		}
@@ -2406,16 +2400,7 @@ static bool migrate_vma_check_page(struct page *page)
 		 * FIXME proper solution is to rework migration_entry_wait() so
 		 * it does not need to take a reference on page.
 		 */
-		if (is_device_private_page(page))
-			return true;
-
-		/*
-		 * Only allow device public page to be migrated and account for
-		 * the extra reference count imply by ZONE_DEVICE pages.
-		 */
-		if (!is_device_public_page(page))
-			return false;
-		extra++;
+		return is_device_private_page(page);
 	}
 
 	/* For file back page */
@@ -2665,11 +2650,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 
 			swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
 			entry = swp_entry_to_pte(swp_entry);
-		} else if (is_device_public_page(page)) {
-			entry = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
-			if (vma->vm_flags & VM_WRITE)
-				entry = pte_mkwrite(pte_mkdirty(entry));
-			entry = pte_mkdevmap(entry);
 		}
 	} else {
 		entry = mk_pte(page, vma->vm_page_prot);
@@ -2789,7 +2769,7 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
 					migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
 					continue;
 				}
-			} else if (!is_device_public_page(newpage)) {
+			} else {
 				/*
 				 * Other types of ZONE_DEVICE page are not
 				 * supported.

mm/swap.c

@@ -740,17 +740,6 @@ void release_pages(struct page **pages, int nr)
 		if (is_huge_zero_page(page))
 			continue;
 
-		/* Device public page can not be huge page */
-		if (is_device_public_page(page)) {
-			if (locked_pgdat) {
-				spin_unlock_irqrestore(&locked_pgdat->lru_lock,
-						       flags);
-				locked_pgdat = NULL;
-			}
-			put_devmap_managed_page(page);
-			continue;
-		}
-
 		page = compound_head(page);
 		if (!put_page_testzero(page))
 			continue;