From 53fee04f318222a3179ca5933d8bda82c1eef17a Mon Sep 17 00:00:00 2001 From: Rohit Seth Date: Tue, 13 Feb 2007 13:26:22 +0100 Subject: [PATCH] x86-64: Fix fake numa for x86_64 machines with big IO hole This patch resolves the issue of running with numa=fake=X on kernel command line on x86_64 machines that have big IO hole. While calculating the size of each node now we look at the total hole size in that range. Previously there were nodes that only had IO holes in them causing kernel boot problems. We now use the NODE_MIN_SIZE (64MB) as the minimum size of memory that any node must have. We reduce the number of allocated nodes if the number of nodes specified on kernel command line results in any node getting memory smaller than NODE_MIN_SIZE. This change allows the extra memory to be incremented in NODE_MIN_SIZE granule and uniformly distribute among as many nodes (called big nodes) as possible. [akpm@osdl.org: build fix] Signed-off-by: David Rientjes Signed-off-by: Paul Menage Signed-off-by: Rohit Seth Signed-off-by: Andi Kleen Cc: Andi Kleen Signed-off-by: Andrew Morton --- arch/x86_64/mm/numa.c | 110 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 96 insertions(+), 14 deletions(-) (limited to 'arch/x86_64/mm') diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 1ec16ea97519..d3f747dd61d3 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -272,31 +272,113 @@ void __init numa_init_array(void) } #ifdef CONFIG_NUMA_EMU +/* Numa emulation */ int numa_fake __initdata = 0; -/* Numa emulation */ +/* + * This function is used to find out if the start and end correspond to + * different zones. + */ +int zone_cross_over(unsigned long start, unsigned long end) +{ + if ((start < (MAX_DMA32_PFN << PAGE_SHIFT)) && + (end >= (MAX_DMA32_PFN << PAGE_SHIFT))) + return 1; + return 0; +} + static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn) { - int i; + int i, big; struct bootnode nodes[MAX_NUMNODES]; - unsigned long sz = ((end_pfn - start_pfn)< 1) { - unsigned long x = 1; - while ((x << 1) < sz) - x <<= 1; - if (x < sz/2) - printk(KERN_ERR "Numa emulation unbalanced. Complain to maintainer\n"); - sz = x; - } + old_sz = sz; + /* + * Round down to the nearest FAKE_NODE_MIN_SIZE. + */ + sz &= FAKE_NODE_MIN_HASH_MASK; + + /* + * We ensure that each node is at least 64MB big. Smaller than this + * size can cause VM hiccups. + */ + if (sz == 0) { + printk(KERN_INFO "Not enough memory for %d nodes. Reducing " + "the number of nodes\n", numa_fake); + numa_fake = (max_addr - start - hole_size) / FAKE_NODE_MIN_SIZE; + printk(KERN_INFO "Number of fake nodes will be = %d\n", + numa_fake); + sz = FAKE_NODE_MIN_SIZE; + } + /* + * Find out how many nodes can get an extra NODE_MIN_SIZE granule. + * This logic ensures the extra memory gets distributed among as many + * nodes as possible (as compared to one single node getting all that + * extra memory. + */ + big = ((old_sz - sz) * numa_fake) / FAKE_NODE_MIN_SIZE; + printk(KERN_INFO "Fake node Size: %luMB hole_size: %luMB big nodes: " + "%d\n", + (sz >> 20), (hole_size >> 20), big); memset(&nodes,0,sizeof(nodes)); + end = start; for (i = 0; i < numa_fake; i++) { - nodes[i].start = (start_pfn<= max_addr) { + numa_fake = i - 1; + break; + } + start = nodes[i].start = end; + /* + * Final node can have all the remaining memory. + */ if (i == numa_fake-1) - sz = (end_pfn<= max_addr) + break; + } + /* + * Look at the next node to make sure there is some real memory + * to map. Bad things happen when the only memory present + * in a zone on a fake node is IO hole. + */ + while (e820_hole_size(end, end + FAKE_NODE_MIN_SIZE) > 0) { + if (zone_cross_over(start, end + sz)) { + end = (MAX_DMA32_PFN << PAGE_SHIFT); + break; + } + if (end >= max_addr) + break; + end += FAKE_NODE_MIN_SIZE; + } + if (end > max_addr) + end = max_addr; + nodes[i].end = end; printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", i, nodes[i].start, nodes[i].end, -- cgit v1.2.2