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 <jgli...@redhat.com> Cc: Thomas Gleixner <t...@linutronix.de> Cc: Ingo Molnar <mi...@redhat.com> Cc: "H. Peter Anvin" <h...@zytor.com> --- arch/x86/mm/init_64.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 442ac86..6e7f613 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -654,7 +654,8 @@ static void update_end_of_memory_vars(u64 start, u64 size) int arch_add_memory(int nid, u64 start, u64 size, int flags) { const int supported_flags = MEMORY_DEVICE | - MEMORY_DEVICE_ALLOW_MIGRATE; + MEMORY_DEVICE_ALLOW_MIGRATE | + MEMORY_DEVICE_UNADDRESSABLE; struct pglist_data *pgdat = NODE_DATA(nid); struct zone *zone = pgdat->node_zones + zone_for_memory(nid, start, size, ZONE_NORMAL, @@ -669,7 +670,17 @@ int arch_add_memory(int nid, u64 start, u64 size, int flags) return -EINVAL; } - 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 (!(flags & MEMORY_DEVICE_UNADDRESSABLE)) + init_memory_mapping(start, start + size); ret = __add_pages(nid, zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); @@ -968,7 +979,8 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end) int __ref arch_remove_memory(u64 start, u64 size, int flags) { const int supported_flags = MEMORY_DEVICE | - MEMORY_DEVICE_ALLOW_MIGRATE; + MEMORY_DEVICE_ALLOW_MIGRATE | + MEMORY_DEVICE_UNADDRESSABLE; unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; struct page *page = pfn_to_page(start_pfn); @@ -989,7 +1001,9 @@ int __ref arch_remove_memory(u64 start, u64 size, int flags) zone = page_zone(page); ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); - kernel_physical_mapping_remove(start, start + size); + + if (!(flags & MEMORY_DEVICE_UNADDRESSABLE)) + kernel_physical_mapping_remove(start, start + size); return ret; } -- 2.4.3