mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS

In preparation for fixing dax-dma-vs-unmap issues, filesystems need to
be able to rely on the fact that they will get wakeups on dev_pagemap
page-idle events. Introduce MEMORY_DEVICE_FS_DAX and
generic_dax_page_free() as common indicator / infrastructure for dax
filesytems to require. With this change there are no users of the
MEMORY_DEVICE_HOST designation, so remove it.

The HMM sub-system extended dev_pagemap to arrange a callback when a
dev_pagemap managed page is freed. Since a dev_pagemap page is free /
idle when its reference count is 1 it requires an additional branch to
check the page-type at put_page() time. Given put_page() is a hot-path
we do not want to incur that check if HMM is not in use, so a static
branch is used to avoid that overhead when not necessary.

Now, the FS_DAX implementation wants to reuse this mechanism for
receiving dev_pagemap ->page_free() callbacks. Rework the HMM-specific
static-key into a generic mechanism that either HMM or FS_DAX code paths
can enable.

For ARCH=um builds, and any other arch that lacks ZONE_DEVICE support,
care must be taken to compile out the DEV_PAGEMAP_OPS infrastructure.
However, we still need to support FS_DAX in the FS_DAX_LIMITED case
implemented by the s390/dcssblk driver.

Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Thomas Meyer <thomas@m3y3r.de>
Reported-by: Dave Jiang <dave.jiang@intel.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

2 files changed, 63 insertions, 44 deletions

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 7b4899c06f49..5ebfff65da4d 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_MEMREMAP_H_
 #define _LINUX_MEMREMAP_H_
-#include <linux/mm.h>
 #include <linux/ioport.h>
 #include <linux/percpu-refcount.h>
 
@@ -30,13 +29,6 @@ struct vmem_altmap {
  * Specialize ZONE_DEVICE memory into multiple types each having differents
  * usage.
  *
- * MEMORY_DEVICE_HOST:
- * Persistent device memory (pmem): struct page might be allocated in different
- * memory and architecture might want to perform special actions. It is similar
- * to regular memory, in that the CPU can access it transparently. However,
- * it is likely to have different bandwidth and latency than regular memory.
- * See Documentation/nvdimm/nvdimm.txt for more information.
- *
  * MEMORY_DEVICE_PRIVATE:
  * Device memory that is not directly addressable by the CPU: CPU can neither
  * read nor write private memory. In this case, we do still have struct pages
@@ -53,11 +45,19 @@ struct vmem_altmap {
  * 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
+ * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
+ * wakeup event whenever a page is unpinned and becomes idle. This
+ * wakeup is used to coordinate physical address space management (ex:
+ * fs truncate/hole punch) vs pinned pages (ex: device dma).
  */
 enum memory_type {
-	MEMORY_DEVICE_HOST = 0,
-	MEMORY_DEVICE_PRIVATE,
+	MEMORY_DEVICE_PRIVATE = 1,
 	MEMORY_DEVICE_PUBLIC,
+	MEMORY_DEVICE_FS_DAX,
 };
 
 /*
@@ -129,8 +129,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
-
-static inline bool is_zone_device_page(const struct page *page);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct dev_pagemap *pgmap)
@@ -161,20 +159,6 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap,
 }
 #endif /* CONFIG_ZONE_DEVICE */
 
-#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
-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;
-}
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
 {
 	if (pgmap)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1ac1f06a4be6..6e19265ee8f8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -821,27 +821,65 @@ static inline bool is_zone_device_page(const struct page *page)
 }
 #endif
 
-#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
-void put_zone_device_private_or_public_page(struct page *page);
-DECLARE_STATIC_KEY_FALSE(device_private_key);
-#define IS_HMM_ENABLED static_branch_unlikely(&device_private_key)
-static inline bool is_device_private_page(const struct page *page);
-static inline bool is_device_public_page(const struct page *page);
-#else /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-static inline void put_zone_device_private_or_public_page(struct page *page)
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void dev_pagemap_get_ops(void);
+void dev_pagemap_put_ops(void);
+void __put_devmap_managed_page(struct page *page);
+DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
+static inline bool put_devmap_managed_page(struct page *page)
+{
+	if (!static_branch_unlikely(&devmap_managed_key))
+		return false;
+	if (!is_zone_device_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;
+	default:
+		break;
+	}
+	return false;
+}
+
+static inline bool is_device_private_page(const struct page *page)
 {
+	return is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
 }
-#define IS_HMM_ENABLED 0
+
+static inline bool is_device_public_page(const struct page *page)
+{
+	return is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PUBLIC;
+}
+
+#else /* CONFIG_DEV_PAGEMAP_OPS */
+static inline void dev_pagemap_get_ops(void)
+{
+}
+
+static inline void dev_pagemap_put_ops(void)
+{
+}
+
+static inline bool put_devmap_managed_page(struct page *page)
+{
+	return false;
+}
+
 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 /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 static inline void get_page(struct page *page)
 {
@@ -859,16 +897,13 @@ static inline void put_page(struct page *page)
 	page = compound_head(page);
 
 	/*
-	 * For private device pages we need to catch refcount transition from
-	 * 2 to 1, when refcount reach one it means the private device page is
-	 * free and we need to inform the device driver through callback. See
+	 * For devmap managed pages we need to catch refcount transition from
+	 * 2 to 1, when refcount reach one it means the page is free and we
+	 * need to inform the device driver through callback. See
 	 * include/linux/memremap.h and HMM for details.
 	 */
-	if (IS_HMM_ENABLED && unlikely(is_device_private_page(page) ||
-	    unlikely(is_device_public_page(page)))) {
-		put_zone_device_private_or_public_page(page);
+	if (put_devmap_managed_page(page))
 		return;
-	}
 
 	if (put_page_testzero(page))
 		__put_page(page);