From 033fbae988fcb67e5077203512181890848b8e90 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 9 Aug 2015 15:29:06 -0400 Subject: 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 Cc: Ingo Molnar Cc: Dave Hansen Cc: Rik van Riel Cc: Mel Gorman Cc: Jerome Glisse [hch: various simplifications in the arch interface] Signed-off-by: Christoph Hellwig Signed-off-by: Dan Williams --- mm/Kconfig | 17 +++++++++++++++++ mm/memory_hotplug.c | 14 +++++++++++--- mm/page_alloc.c | 3 +++ 3 files changed, 31 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/Kconfig b/mm/Kconfig index e79de2bd12cd..a0cd086df16b 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -654,3 +654,20 @@ config DEFERRED_STRUCT_PAGE_INIT when kswapd starts. This has a potential performance impact on processes running early in the lifetime of the systemm until kswapd finishes the initialisation. + +config ZONE_DEVICE + bool "Device memory (pmem, etc...) hotplug support" if EXPERT + default !ZONE_DMA + depends on !ZONE_DMA + depends on MEMORY_HOTPLUG + depends on MEMORY_HOTREMOVE + depends on X86_64 #arch_add_memory() comprehends device memory + + help + Device memory hotplug support allows for establishing pmem, + or other device driver discovered memory regions, in the + memmap. This allows pfn_to_page() lookups of otherwise + "device-physical" addresses which is needed for using a DAX + mapping in an O_DIRECT operation, among other things. + + If FS_DAX is enabled, then say Y. diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 26fbba7d888f..24e4c76c951b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -770,7 +770,10 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, start = phys_start_pfn << PAGE_SHIFT; size = nr_pages * PAGE_SIZE; - ret = release_mem_region_adjustable(&iomem_resource, start, size); + + /* in the ZONE_DEVICE case device driver owns the memory region */ + if (!is_dev_zone(zone)) + ret = release_mem_region_adjustable(&iomem_resource, start, size); if (ret) { resource_size_t endres = start + size - 1; @@ -1207,8 +1210,13 @@ static int should_add_memory_movable(int nid, u64 start, u64 size) return 0; } -int zone_for_memory(int nid, u64 start, u64 size, int zone_default) +int zone_for_memory(int nid, u64 start, u64 size, int zone_default, + bool for_device) { +#ifdef CONFIG_ZONE_DEVICE + if (for_device) + return ZONE_DEVICE; +#endif if (should_add_memory_movable(nid, start, size)) return ZONE_MOVABLE; @@ -1249,7 +1257,7 @@ int __ref add_memory(int nid, u64 start, u64 size) } /* call arch's memory hotadd */ - ret = arch_add_memory(nid, start, size); + ret = arch_add_memory(nid, start, size, false); if (ret < 0) goto error; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ef19f22b2b7d..0f19b4e18233 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -207,6 +207,9 @@ static char * const zone_names[MAX_NR_ZONES] = { "HighMem", #endif "Movable", +#ifdef CONFIG_ZONE_DEVICE + "Device", +#endif }; int min_free_kbytes = 1024; -- cgit v1.2.3