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>

7 files changed, 13 insertions, 12 deletions

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 97e48b0eefc7..1841ef69183d 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -645,7 +645,7 @@ mem_init (void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	pg_data_t *pgdat;
 	struct zone *zone;
@@ -656,7 +656,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	pgdat = NODE_DATA(nid);
 
 	zone = pgdat->node_zones +
-		zone_for_memory(nid, start, size, ZONE_NORMAL);
+		zone_for_memory(nid, start, size, ZONE_NORMAL, for_device);
 	ret = __add_pages(nid, zone, start_pfn, nr_pages);
 
 	if (ret)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 0f11819d8f1d..6571cfb05668 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -113,7 +113,7 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 #endif
 
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdata;
 	struct zone *zone;
@@ -128,7 +128,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	/* this should work for most non-highmem platforms */
 	zone = pgdata->node_zones +
-		zone_for_memory(nid, start, size, 0);
+		zone_for_memory(nid, start, size, 0, for_device);
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 76e873748b56..48ee78be88ba 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -168,7 +168,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
 	unsigned long start_pfn = PFN_DOWN(start);
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 2790b6a64157..c1490096b863 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -485,7 +485,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	pg_data_t *pgdat;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
@@ -496,7 +496,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	/* We only have ZONE_NORMAL, so this is easy.. */
 	ret = __add_pages(nid, pgdat->node_zones +
-			zone_for_memory(nid, start, size, ZONE_NORMAL),
+			zone_for_memory(nid, start, size, ZONE_NORMAL,
+			for_device),
 			start_pfn, nr_pages);
 	if (unlikely(ret))
 		printk("%s: Failed, __add_pages() == %d\n", __func__, ret);
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index 5bd252e3fdc5..d4e1fc41d06d 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -863,7 +863,7 @@ void __init mem_init(void)
  * memory to the highmem for now.
  */
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-int arch_add_memory(u64 start, u64 size)
+int arch_add_memory(u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdata = &contig_page_data;
 	struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8340e45c891a..2a9237d20a70 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -822,11 +822,11 @@ void __init mem_init(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdata = NODE_DATA(nid);
 	struct zone *zone = pgdata->node_zones +
-		zone_for_memory(nid, start, size, ZONE_HIGHMEM);
+		zone_for_memory(nid, start, size, ZONE_HIGHMEM, for_device);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3fba623e3ba5..30564e2752d3 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -687,11 +687,11 @@ static void  update_end_of_memory_vars(u64 start, u64 size)
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdat = NODE_DATA(nid);
 	struct zone *zone = pgdat->node_zones +
-		zone_for_memory(nid, start, size, ZONE_NORMAL);
+		zone_for_memory(nid, start, size, ZONE_NORMAL, for_device);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;