mm: add zone device coherent type memory support

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.

[hch@lst.de: rebased ontop of the refcount changes, remove is_dev_private_or_coherent_page]
Link: https://lkml.kernel.org/r/20220715150521.18165-4-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

7 files changed, 53 insertions, 17 deletions

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 732dde5988fb..09320b7f706c 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/mm/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,
@@ -150,6 +158,17 @@ static inline bool is_pci_p2pdma_page(const struct page *page)
 		page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
 }
 
+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 folio_is_device_coherent(const struct folio *folio)
+{
+	return is_device_coherent_page(&folio->page);
+}
+
 #ifdef CONFIG_ZONE_DEVICE
 void *memremap_pages(struct dev_pagemap *pgmap, int nid);
 void memunmap_pages(struct dev_pagemap *pgmap);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a2d01e49253b..64393ed3330a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/pgtable.h>
 #include <linux/kasan.h>
+#include <linux/memremap.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -1537,7 +1538,9 @@ static inline bool is_longterm_pinnable_page(struct page *page)
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
-	return !is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page));
+	return !(is_device_coherent_page(page) ||
+		 is_zone_movable_page(page) ||
+		 is_zero_pfn(page_to_pfn(page)));
 }
 #else
 static inline bool is_longterm_pinnable_page(struct page *page)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1497affe08c4..b1868784f895 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5716,8 +5716,8 @@ 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).
+ *   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.
@@ -5755,7 +5755,8 @@ 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 f7612ccdb299..b7ca5db7e60e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1686,12 +1686,16 @@ 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 8b5c8fd4ea8e..f0955785150f 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -315,6 +315,16 @@ 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 5052093d0262..a4847ad65da3 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -518,7 +518,7 @@ 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,
@@ -594,11 +594,8 @@ 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;
 		}
@@ -701,10 +698,11 @@ 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 83172ee0ea35..0532fd92ecb3 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1953,7 +1953,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		/* Update high watermark before we lower rss */
 		update_hiwater_rss(mm);
 
-		if (folio_is_zone_device(folio)) {
+		if (folio_is_device_private(folio)) {
 			unsigned long pfn = folio_pfn(folio);
 			swp_entry_t entry;
 			pte_t swp_pte;
@@ -2124,7 +2124,8 @@ void try_to_migrate(struct folio *folio, enum ttu_flags flags)
 					TTU_SYNC)))
 		return;
 
-	if (folio_is_zone_device(folio) && !folio_is_device_private(folio))
+	if (folio_is_zone_device(folio) &&
+	    (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
 		return;
 
 	/*