From bac4894dfa9c75c297b905e2ea88caaa5768f1e2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 30 Jan 2008 13:32:54 +0100 Subject: x86: make NUMA work on 32-bit again On 32-bit NUMA, the memmap representing struct pages on each node is allocated from node-local memory if possible. As only node-0 has memory from ZONE_NORMAL, the memmap must be mapped into low memory. This is done by reserving space in the Kernel Virtual Area (KVA) for the memmap belonging to other nodes by taking pages from the end of ZONE_NORMAL and remapping the other nodes memmap into those virtual addresses. The node boundaries are then adjusted so that the region of pages is not used and it is marked as reserved in the bootmem allocator. This reserved portion of the KVA is PMD aligned althought strictly speaking that requirement could be lifted (see thread at http://lkml.org/lkml/2007/8/24/220). The problem is that when aligned, there may be a portion of ZONE_NORMAL at the end that is not used for memmap and does not have an initialised memmap nor is it marked reserved in the bootmem allocator. Later in the boot process, these pages are freed and a storm of Bad page state messages result. This patch marks these pages reserved that are wasted due to alignment in the bootmem allocator so they are not accidently freed. It is worth noting that memory from node-0 is wasted where it could have been put into ZONE_HIGHMEM on NUMA machines. Worse, the KVA is always reserved from the location of real memory even when there is plenty of spare virtual address space. This patch also makes sure that reserve_bootmem() is not called with a 0-length size in numa_kva_reserve(). When this happens, it usually means that a kernel built for Summit is being booted on a normal machine. The resulting BUG_ON() is misleading so it is caught here. Signed-off-by: Mel Gorman Signed-off-by: Andy Whitcroft Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/mm/discontig_32.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index 88a7499e8e4..9f1d02cfde3 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -268,6 +268,7 @@ unsigned long __init setup_memory(void) { int nid; unsigned long system_start_pfn, system_max_low_pfn; + unsigned long wasted_pages; /* * When mapping a NUMA machine we allocate the node_mem_map arrays @@ -292,7 +293,14 @@ unsigned long __init setup_memory(void) kva_start_pfn = PFN_DOWN(initrd_start - PAGE_OFFSET) - kva_pages; #endif - kva_start_pfn -= kva_start_pfn & (PTRS_PER_PTE-1); + + /* + * We waste pages past at the end of the KVA for no good reason other + * than how it is located. This is bad. + */ + wasted_pages = kva_start_pfn & (PTRS_PER_PTE-1); + kva_start_pfn -= wasted_pages; + kva_pages += wasted_pages; system_max_low_pfn = max_low_pfn = find_max_low_pfn(); printk("kva_start_pfn ~ %ld find_max_low_pfn() ~ %ld\n", @@ -345,7 +353,8 @@ unsigned long __init setup_memory(void) void __init numa_kva_reserve(void) { - reserve_bootmem(PFN_PHYS(kva_start_pfn),PFN_PHYS(kva_pages)); + if (kva_pages) + reserve_bootmem(PFN_PHYS(kva_start_pfn), PFN_PHYS(kva_pages)); } void __init zone_sizes_init(void) -- cgit v1.2.3