From: keith mannthey Address a long standing issue of booting with an initrd on an i386 numa system. Currently (and always) the numa kva area is mapped into low memory by finding the end of low memory and moving that mark down (thus creating space for the kva). The issue with this is that Grub loads initrds into this similar space so when the kernel check the initrd it finds it outside max_low_pfn and disables it (it thinks the initrd is not mapped into usable memory) thus initrd enabled kernels can't boot i386 numa :( My solution to the problem just converts the numa kva area to use the bootmem allocator to save it's area (instead of moving the end of low memory). Using bootmem allows the kva area to be mapped into more diverse addresses (not just the end of low memory) and enables the kva area to be mapped below the initrd if present. I have tested this patch on numaq(no initrd) and summit(initrd) i386 numa based systems. Signed-off-by: Keith Mannthey Signed-off-by: Andrew Morton --- arch/i386/kernel/setup.c | 7 ++++++- arch/i386/mm/discontig.c | 30 ++++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 9 deletions(-) diff -puN arch/i386/kernel/setup.c~convert-i386-numa-kva-space-to-bootmem arch/i386/kernel/setup.c --- a/arch/i386/kernel/setup.c~convert-i386-numa-kva-space-to-bootmem +++ a/arch/i386/kernel/setup.c @@ -1202,6 +1202,9 @@ extern unsigned long __init setup_memory extern void zone_sizes_init(void); #endif /* !CONFIG_NEED_MULTIPLE_NODES */ +#ifdef CONFIG_NUMA +extern void numa_kva_reserve(void); +#endif void __init setup_bootmem_allocator(void) { unsigned long bootmap_size; @@ -1257,7 +1260,9 @@ void __init setup_bootmem_allocator(void */ find_smp_config(); #endif - +#ifdef CONFIG_NUMA + numa_kva_reserve(); +#endif #ifdef CONFIG_BLK_DEV_INITRD if (LOADER_TYPE && INITRD_START) { if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) { diff -puN arch/i386/mm/discontig.c~convert-i386-numa-kva-space-to-bootmem arch/i386/mm/discontig.c --- a/arch/i386/mm/discontig.c~convert-i386-numa-kva-space-to-bootmem +++ a/arch/i386/mm/discontig.c @@ -117,7 +117,8 @@ void set_pmd_pfn(unsigned long vaddr, un void *node_remap_end_vaddr[MAX_NUMNODES]; void *node_remap_alloc_vaddr[MAX_NUMNODES]; - +static unsigned long kva_start_pfn; +static unsigned long kva_pages; /* * FLAT - support for basic PC memory model with discontig enabled, essentially * a single node with all available processors in it with a flat @@ -286,7 +287,6 @@ unsigned long __init setup_memory(void) { int nid; unsigned long system_start_pfn, system_max_low_pfn; - unsigned long reserve_pages; /* * When mapping a NUMA machine we allocate the node_mem_map arrays @@ -298,14 +298,23 @@ unsigned long __init setup_memory(void) find_max_pfn(); get_memcfg_numa(); - reserve_pages = calculate_numa_remap_pages(); + kva_pages = calculate_numa_remap_pages(); /* partially used pages are not usable - thus round upwards */ system_start_pfn = min_low_pfn = PFN_UP(init_pg_tables_end); - system_max_low_pfn = max_low_pfn = find_max_low_pfn() - reserve_pages; - printk("reserve_pages = %ld find_max_low_pfn() ~ %ld\n", - reserve_pages, max_low_pfn + reserve_pages); + kva_start_pfn = find_max_low_pfn() - kva_pages; + +#ifdef CONFIG_BLK_DEV_INITRD + /* Numa kva area is below the initrd */ + if (LOADER_TYPE && INITRD_START) + kva_start_pfn = PFN_DOWN(INITRD_START) - kva_pages; +#endif + kva_start_pfn -= kva_start_pfn & (PTRS_PER_PTE-1); + + system_max_low_pfn = max_low_pfn = find_max_low_pfn(); + printk("kva_start_pfn ~ %ld find_max_low_pfn() ~ %ld\n", + kva_start_pfn, max_low_pfn); printk("max_pfn = %ld\n", max_pfn); #ifdef CONFIG_HIGHMEM highstart_pfn = highend_pfn = max_pfn; @@ -323,7 +332,7 @@ unsigned long __init setup_memory(void) (ulong) pfn_to_kaddr(max_low_pfn)); for_each_online_node(nid) { node_remap_start_vaddr[nid] = pfn_to_kaddr( - highstart_pfn + node_remap_offset[nid]); + kva_start_pfn + node_remap_offset[nid]); /* Init the node remap allocator */ node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] + (node_remap_size[nid] * PAGE_SIZE); @@ -338,7 +347,6 @@ unsigned long __init setup_memory(void) } printk("High memory starts at vaddr %08lx\n", (ulong) pfn_to_kaddr(highstart_pfn)); - vmalloc_earlyreserve = reserve_pages * PAGE_SIZE; for_each_online_node(nid) find_max_pfn_node(nid); @@ -348,6 +356,12 @@ unsigned long __init setup_memory(void) return max_low_pfn; } +void __init numa_kva_reserve (void) +{ + reserve_bootmem(PFN_PHYS(kva_start_pfn),PFN_PHYS(kva_pages)); + +} + void __init zone_sizes_init(void) { int nid; _