[PATCH 15/27] mm: add zone device coherent type memory support

[Christoph Hellwig <hch@lst.de>]

From: Alex Sierra <alex.sierra@amd.com>

Device memory that is cache coherent from device and CPU point of view.
This is used on platforms that have an advanced system bus (like CAPI
or CXL). Any page of a process can be migrated to such memory. However,
no one should be allowed to pin such memory so that it can always be
evicted.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
[hch: rebased ontop of the refcount changes,
      removed is_dev_private_or_coherent_page]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/memremap.h | 14 ++++++++++++++
 mm/memcontrol.c          |  7 ++++---
 mm/memory-failure.c      |  8 ++++++--
 mm/memremap.c            | 10 ++++++++++
 mm/migrate_device.c      | 16 +++++++---------
 mm/rmap.c                |  5 +++--
 6 files changed, 44 insertions(+), 16 deletions(-)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index d6a114dd5ea8b7..eb73630a49da39 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -41,6 +41,13 @@ 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_COHERENT:
+ * Device memory that is cache coherent from device and CPU point of view. This
+ * is used on platforms that have an advanced system bus (like CAPI or CXL). 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 allowed 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
@@ -61,6 +68,7 @@ struct vmem_altmap {
 enum memory_type {
 	/* 0 is reserved to catch uninitialized type fields */
 	MEMORY_DEVICE_PRIVATE = 1,
+	MEMORY_DEVICE_COHERENT,
 	MEMORY_DEVICE_FS_DAX,
 	MEMORY_DEVICE_GENERIC,
 	MEMORY_DEVICE_PCI_P2PDMA,
@@ -138,6 +146,12 @@ static inline bool is_device_private_page(const struct page *page)
 		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
 }
 
+static inline bool is_device_coherent_page(const struct page *page)
+{
+	return is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_COHERENT;
+}
+
 static inline bool is_pci_p2pdma_page(const struct page *page)
 {
 	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 510cbfb82bb62a..10259c35fde20d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5687,8 +5687,8 @@ 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_PRIVATE
- *     (so ZONE_DEVICE page and thus not on the lru).
+ *   3(MC_TARGET_DEVICE): like MC_TARGET_PAGE  but page is device memory 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.
@@ -5722,7 +5722,8 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		 */
 		if (page_memcg(page) == mc.from) {
 			ret = MC_TARGET_PAGE;
-			if (is_device_private_page(page))
+			if (is_device_private_page(page) ||
+			    is_device_coherent_page(page))
 				ret = MC_TARGET_DEVICE;
 			if (target)
 				target->page = page;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 97a9ed8f87a96a..f498ed3ece79ae 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1617,12 +1617,16 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		goto unlock;
 	}
 
-	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+	switch (pgmap->type) {
+	case MEMORY_DEVICE_PRIVATE:
+	case MEMORY_DEVICE_COHERENT:
 		/*
-		 * TODO: Handle HMM pages which may need coordination
+		 * TODO: Handle device pages which may need coordination
 		 * with device-side memory.
 		 */
 		goto unlock;
+	default:
+		break;
 	}
 
 	/*
diff --git a/mm/memremap.c b/mm/memremap.c
index e00ffcdba7b632..d00bb21a0630cd 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -313,6 +313,16 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			return ERR_PTR(-EINVAL);
 		}
 		break;
+	case MEMORY_DEVICE_COHERENT:
+		if (!pgmap->ops->page_free) {
+			WARN(1, "Missing page_free method\n");
+			return ERR_PTR(-EINVAL);
+		}
+		if (!pgmap->owner) {
+			WARN(1, "Missing owner\n");
+			return ERR_PTR(-EINVAL);
+		}
+		break;
 	case MEMORY_DEVICE_FS_DAX:
 		if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
 			WARN(1, "File system DAX not supported\n");
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 749e0bab8e4779..bfd66e7d830b02 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -494,7 +494,7 @@ EXPORT_SYMBOL(migrate_vma_setup);
  *     handle_pte_fault()
  *       do_anonymous_page()
  * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
+ * private or coherent page.
  */
 static void migrate_vma_insert_page(struct migrate_vma *migrate,
 				    unsigned long addr,
@@ -570,11 +570,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 						page_to_pfn(page));
 		entry = swp_entry_to_pte(swp_entry);
 	} else {
-		/*
-		 * For now we only support migrating to un-addressable device
-		 * memory.
-		 */
-		if (is_zone_device_page(page)) {
+		if (is_zone_device_page(page) &&
+		    !is_device_coherent_page(page)) {
 			pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
 			goto abort;
 		}
@@ -677,10 +674,11 @@ void migrate_vma_pages(struct migrate_vma *migrate)
 
 		mapping = page_mapping(page);
 
-		if (is_device_private_page(newpage)) {
+		if (is_device_private_page(newpage) ||
+		    is_device_coherent_page(newpage)) {
 			/*
-			 * For now only support private anonymous when migrating
-			 * to un-addressable device memory.
+			 * For now only support anonymous memory migrating to
+			 * device private or coherent memory.
 			 */
 			if (mapping) {
 				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
diff --git a/mm/rmap.c b/mm/rmap.c
index 6a1e8c7f621361..c34de7bd22393e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1835,7 +1835,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
 		/* Update high watermark before we lower rss */
 		update_hiwater_rss(mm);
 
-		if (is_zone_device_page(page)) {
+		if (is_device_private_page(page)) {
 			unsigned long pfn = page_to_pfn(page);
 			swp_entry_t entry;
 			pte_t swp_pte;
@@ -1976,7 +1976,8 @@ void try_to_migrate(struct page *page, enum ttu_flags flags)
 					TTU_SYNC)))
 		return;
 
-	if (is_zone_device_page(page) && !is_device_private_page(page))
+	if (is_zone_device_page(page) &&
+	    (!is_device_private_page(page) && !is_device_coherent_page(page)))
 		return;
 
 	/*
-- 
2.30.2