mm: ZONE_DEVICE for "device memory"

While pmem is usable as a block device or via DAX mappings to userspace
there are several usage scenarios that can not target pmem due to its
lack of struct page coverage. In preparation for "hot plugging" pmem
into the vmemmap add ZONE_DEVICE as a new zone to tag these pages
separately from the ones that are subject to standard page allocations.
Importantly "device memory" can be removed at will by userspace
unbinding the driver of the device.

Having a separate zone prevents allocation and otherwise marks these
pages that are distinct from typical uniform memory.  Device memory has
different lifetime and performance characteristics than RAM.  However,
since we have run out of ZONES_SHIFT bits this functionality currently
depends on sacrificing ZONE_DMA.

Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Jerome Glisse <j.glisse@gmail.com>
[hch: various simplifications in the arch interface]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

2 files changed, 26 insertions, 2 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 6ffa0ac7f7d6..8f60e899b33c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -266,8 +266,9 @@ static inline void remove_memory(int nid, u64 start, u64 size) {}
 extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 		void *arg, int (*func)(struct memory_block *, void *));
 extern int add_memory(int nid, u64 start, u64 size);
-extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default);
-extern int arch_add_memory(int nid, u64 start, u64 size);
+extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
+		bool for_device);
+extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern void remove_memory(int nid, u64 start, u64 size);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 754c25966a0a..9217fd93c25b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -319,7 +319,11 @@ enum zone_type {
 	ZONE_HIGHMEM,
 #endif
 	ZONE_MOVABLE,
+#ifdef CONFIG_ZONE_DEVICE
+	ZONE_DEVICE,
+#endif
 	__MAX_NR_ZONES
+
 };
 
 #ifndef __GENERATING_BOUNDS_H
@@ -794,6 +798,25 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat)
 	return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
 }
 
+static inline int zone_id(const struct zone *zone)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+
+	return zone - pgdat->node_zones;
+}
+
+#ifdef CONFIG_ZONE_DEVICE
+static inline bool is_dev_zone(const struct zone *zone)
+{
+	return zone_id(zone) == ZONE_DEVICE;
+}
+#else
+static inline bool is_dev_zone(const struct zone *zone)
+{
+	return false;
+}
+#endif
+
 #include <linux/memory_hotplug.h>
 
 extern struct mutex zonelists_mutex;