mm/device-public-memory: device memory cache coherent with CPU

Platform with advance system bus (like CAPI or CCIX) allow device memory
to be accessible from CPU in a cache coherent fashion.  Add a new type of
ZONE_DEVICE to represent such memory.  The use case are the same as for
the un-addressable device memory but without all the corners cases.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Jérôme Glisse <[email protected]>
Cc: Aneesh Kumar <[email protected]>
Cc: Paul E. McKenney <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Ross Zwisler <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: David Nellans <[email protected]>
Cc: Evgeny Baskakov <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: John Hubbard <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Mark Hairgrove <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Sherry Cheung <[email protected]>
Cc: Subhash Gutti <[email protected]>
Cc: Vladimir Davydov <[email protected]>
Cc: Bob Liu <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Jérôme Glisse

fs/proc/task_mmu.c

@@ -1267,7 +1267,7 @@ 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);
+		page = _vm_normal_page(vma, addr, pte, true);
 		if (pte_soft_dirty(pte))
 			flags |= PM_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {

include/linux/hmm.h

@@ -327,7 +327,7 @@ int hmm_vma_fault(struct vm_area_struct *vma,
 #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
 
 
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
 struct hmm_devmem;
 
 struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
@@ -494,7 +494,7 @@ struct hmm_device {
  */
 struct hmm_device *hmm_device_new(void *drvdata);
 void hmm_device_put(struct hmm_device *hmm_device);
-#endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
 
 
 /* Below are for HMM internal use only! Not to be used by device driver! */

include/linux/ioport.h

@@ -131,6 +131,7 @@ 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

@@ -57,10 +57,18 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
  *
  * A more complete discussion of unaddressable memory may be found in
  * include/linux/hmm.h and Documentation/vm/hmm.txt.
+ *
+ * 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.
  */
 enum memory_type {
 	MEMORY_DEVICE_HOST = 0,
 	MEMORY_DEVICE_PRIVATE,
+	MEMORY_DEVICE_PUBLIC,
 };
 
 /*
@@ -92,6 +100,8 @@ enum memory_type {
  * The page_free() callback is called once the page refcount reaches 1
  * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug.
  * This allows the device driver to implement its own memory management.)
+ *
+ * For MEMORY_DEVICE_PUBLIC only the page_free() callback matter.
  */
 typedef int (*dev_page_fault_t)(struct vm_area_struct *vma,
 				unsigned long addr,
@@ -134,6 +144,12 @@ static inline bool is_device_private_page(const struct page *page)
 	return is_zone_device_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;
+}
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct resource *res, struct percpu_ref *ref,
@@ -157,6 +173,11 @@ 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;
+}
 #endif
 
 /**

include/linux/mm.h

@@ -800,15 +800,16 @@ static inline bool is_zone_device_page(const struct page *page)
 }
 #endif
 
-#ifdef CONFIG_DEVICE_PRIVATE
-void put_zone_device_private_page(struct page *page);
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
+void put_zone_device_private_or_public_page(struct page *page);
 #else
-static inline void put_zone_device_private_page(struct page *page)
+static inline void put_zone_device_private_or_public_page(struct page *page)
 {
 }
-#endif
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
 
 static inline bool is_device_private_page(const struct page *page);
+static inline bool is_device_public_page(const struct page *page);
 
 DECLARE_STATIC_KEY_FALSE(device_private_key);
 
@@ -834,8 +835,9 @@ static inline void put_page(struct page *page)
 	 * include/linux/memremap.h and HMM for details.
 	 */
 	if (static_branch_unlikely(&device_private_key) &&
-	    unlikely(is_device_private_page(page))) {
-		put_zone_device_private_page(page);
+	    unlikely(is_device_private_page(page) ||
+		     is_device_public_page(page))) {
+		put_zone_device_private_or_public_page(page);
 		return;
 	}
 
@@ -1224,8 +1226,10 @@ 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);
+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_pmd(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t pmd);
 

kernel/memremap.c

@@ -501,8 +501,8 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
 #endif /* CONFIG_ZONE_DEVICE */
 
 
-#ifdef CONFIG_DEVICE_PRIVATE
-void put_zone_device_private_page(struct page *page)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
+void put_zone_device_private_or_public_page(struct page *page)
 {
 	int count = page_ref_dec_return(page);
 
@@ -522,5 +522,5 @@ void put_zone_device_private_page(struct page *page)
 	} else if (!count)
 		__put_page(page);
 }
-EXPORT_SYMBOL(put_zone_device_private_page);
-#endif /* CONFIG_DEVICE_PRIVATE */
+EXPORT_SYMBOL(put_zone_device_private_or_public_page);
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */

mm/Kconfig

@@ -720,12 +720,23 @@ config HMM_MIRROR
 config DEVICE_PRIVATE
 	bool "Unaddressable device memory (GPU memory, ...)"
 	depends on ARCH_HAS_HMM
+	select HMM
 
 	help
 	  Allows creation of struct pages to represent unaddressable device
 	  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
+
+	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

@@ -456,6 +456,13 @@ 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;
 	}
 	get_page(*page);
 out:

mm/hmm.c

@@ -737,7 +737,7 @@ EXPORT_SYMBOL(hmm_vma_fault);
 #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
 
 
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
+#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
 struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma,
 				       unsigned long addr)
 {
@@ -1177,4 +1177,4 @@ static int __init hmm_init(void)
 }
 
 device_initcall(hmm_init);
-#endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */
+#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */

mm/madvise.c

@@ -355,7 +355,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 			continue;
 		}
 
-		page = vm_normal_page(vma, addr, ptent);
+		page = _vm_normal_page(vma, addr, ptent, true);
 		if (!page)
 			continue;
 

mm/memcontrol.c

@@ -4623,10 +4623,11 @@ 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_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.
+ *   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).
+ *     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.
  *
  *     See Documentations/vm/hmm.txt and include/linux/hmm.h
  *
@@ -4657,7 +4658,8 @@ 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))
+			if (is_device_private_page(page) ||
+			    is_device_public_page(page))
 				ret = MC_TARGET_DEVICE;
 			if (target)
 				target->page = page;

mm/memory.c

@@ -818,8 +818,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 #else
 # define HAVE_PTE_SPECIAL 0
 #endif
-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
-				pte_t pte)
+struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t pte, bool with_public_device)
 {
 	unsigned long pfn = pte_pfn(pte);
 
@@ -830,8 +830,31 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 			return vma->vm_ops->find_special_page(vma, addr);
 		if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
 			return NULL;
-		if (!is_zero_pfn(pfn))
-			print_bad_pte(vma, addr, pte, 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;
+			}
+		}
+		print_bad_pte(vma, addr, pte, NULL);
 		return NULL;
 	}
 
@@ -1012,6 +1035,19 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		get_page(page);
 		page_dup_rmap(page, false);
 		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:
@@ -1267,7 +1303,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		if (pte_present(ptent)) {
 			struct page *page;
 
-			page = vm_normal_page(vma, addr, ptent);
+			page = _vm_normal_page(vma, addr, ptent, true);
 			if (unlikely(details) && page) {
 				/*
 				 * unmap_shared_mapping_pages() wants to