It does not need much, just skip populating kernel linear mapping for range of un-addressable device memory (it is pick so that there is no physical memory resource overlapping it). All the logic is in share mm code.
Only support x86-64 as this feature doesn't make much sense with constrained virtual address space of 32bits architecture. Signed-off-by: Jérôme Glisse <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: "H. Peter Anvin" <[email protected]> --- arch/x86/mm/init_64.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 6c0b24e..b635636 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -658,6 +658,7 @@ int arch_add_memory(int nid, u64 start, u64 size, enum memory_type type) case MEMORY_NORMAL: break; case MEMORY_DEVICE_PERSISTENT: + case MEMORY_DEVICE_UNADDRESSABLE: for_device = true; break; default: @@ -668,7 +669,17 @@ int arch_add_memory(int nid, u64 start, u64 size, enum memory_type type) zone = pgdat->node_zones + zone_for_memory(nid, start, size, ZONE_NORMAL, for_device); - init_memory_mapping(start, start + size); + /* + * We get un-addressable memory when some one is adding a ZONE_DEVICE + * to have struct page for a device memory which is not accessible by + * the CPU so it is pointless to have a linear kernel mapping of such + * memory. + * + * Core mm should make sure it never set a pte pointing to such fake + * physical range. + */ + if (type != MEMORY_DEVICE_UNADDRESSABLE) + init_memory_mapping(start, start + size); ret = __add_pages(nid, zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); @@ -980,6 +991,7 @@ int __ref arch_remove_memory(u64 start, u64 size, enum memory_type type) switch (type) { case MEMORY_NORMAL: case MEMORY_DEVICE_PERSISTENT: + case MEMORY_DEVICE_UNADDRESSABLE: break; default: pr_err("hotplug unsupported memory type %d\n", type); @@ -993,7 +1005,9 @@ int __ref arch_remove_memory(u64 start, u64 size, enum memory_type type) zone = page_zone(page); ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); - kernel_physical_mapping_remove(start, start + size); + + if (type != MEMORY_DEVICE_UNADDRESSABLE) + kernel_physical_mapping_remove(start, start + size); return ret; } -- 2.9.3
