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/20170817000548.32038-19-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Evgeny Baskakov <ebaskakov@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Sherry Cheung <SCheung@nvidia.com>
Cc: Subhash Gutti <sgutti@nvidia.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

8 files changed, 118 insertions, 32 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index ec27855db133..7bea16697d87 100644
--- a/mm/Kconfig
+++ b/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
 
diff --git a/mm/gup.c b/mm/gup.c
index 76fd199aaae2..b2b4d4263768 100644
--- a/mm/gup.c
+++ b/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:
diff --git a/mm/hmm.c b/mm/hmm.c
index c9d23ef80552..b31d56662202 100644
--- a/mm/hmm.c
+++ b/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 */
diff --git a/mm/madvise.c b/mm/madvise.c
index eea1c733286f..21261ff0466f 100644
--- a/mm/madvise.c
+++ b/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;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8aa98f9bc723..126a939b600a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4623,10 +4623,11 @@ out:
  *   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;
diff --git a/mm/memory.c b/mm/memory.c
index 079eeac0b009..ad0ea1af1f44 100644
--- a/mm/memory.c
+++ b/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 @@ again:
 		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
diff --git a/mm/migrate.c b/mm/migrate.c
index e581253ef330..618aeb5e9cde 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,6 +36,7 @@
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
+#include <linux/pfn_t.h>
 #include <linux/memremap.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/balloon_compaction.h>
@@ -239,10 +240,14 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		if (is_write_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
 
-		if (unlikely(is_zone_device_page(new)) &&
-		    is_device_private_page(new)) {
-			entry = make_device_private_entry(new, pte_write(pte));
-			pte = swp_entry_to_pte(entry);
+		if (unlikely(is_zone_device_page(new))) {
+			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);
+				flush_dcache_page(new);
+			}
 		} else
 			flush_dcache_page(new);
 
@@ -437,12 +442,11 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	void **pslot;
 
 	/*
-	 * ZONE_DEVICE pages have 1 refcount always held by their device
-	 *
-	 * Note that DAX memory will never reach that point as it does not have
-	 * the MEMORY_DEVICE_ALLOW_MIGRATE flag set (see memory_hotplug.h).
+	 * Device public or private pages have an extra refcount as they are
+	 * ZONE_DEVICE pages.
 	 */
-	expected_count += is_zone_device_page(page);
+	expected_count += is_device_private_page(page);
+	expected_count += is_device_public_page(page);
 
 	if (!mapping) {
 		/* Anonymous page without mapping */
@@ -2123,7 +2127,6 @@ out_unlock:
 
 #endif /* CONFIG_NUMA */
 
-
 struct migrate_vma {
 	struct vm_area_struct	*vma;
 	unsigned long		*dst;
@@ -2263,7 +2266,7 @@ again:
 				pfn = 0;
 				goto next;
 			}
-			page = vm_normal_page(migrate->vma, addr, pte);
+			page = _vm_normal_page(migrate->vma, addr, pte, true);
 			mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
 			mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
 		}
@@ -2406,10 +2409,19 @@ static bool migrate_vma_check_page(struct page *page)
 		if (is_device_private_page(page))
 			return true;
 
-		/* Other ZONE_DEVICE memory type are not supported */
-		return false;
+		/*
+		 * 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++;
 	}
 
+	/* For file back page */
+	if (page_mapping(page))
+		extra += 1 + page_has_private(page);
+
 	if ((page_count(page) - extra) > page_mapcount(page))
 		return false;
 
@@ -2647,11 +2659,18 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	 */
 	__SetPageUptodate(page);
 
-	if (is_zone_device_page(page) && is_device_private_page(page)) {
-		swp_entry_t swp_entry;
-
-		swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
-		entry = swp_entry_to_pte(swp_entry);
+	if (is_zone_device_page(page)) {
+		if (is_device_private_page(page)) {
+			swp_entry_t swp_entry;
+
+			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);
 		if (vma->vm_flags & VM_WRITE)
@@ -2768,7 +2787,7 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
 					migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
 					continue;
 				}
-			} else {
+			} else if (!is_device_public_page(newpage)) {
 				/*
 				 * Other types of ZONE_DEVICE page are not
 				 * supported.
diff --git a/mm/swap.c b/mm/swap.c
index 62d96b8e5eb3..9295ae960d66 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -765,6 +765,17 @@ void release_pages(struct page **pages, int nr, bool cold)
 		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_zone_device_private_or_public_page(page);
+			continue;
+		}
+
 		page = compound_head(page);
 		if (!put_page_testzero(page))
 			continue;