From b37ab91907e9002925f4217e3bbd496aa12c2fa3 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 8 May 2009 00:36:44 -0700 Subject: x86: Sanity check the e820 against the SRAT table using e820 map only node_cover_memory() sanity checks the SRAT table by ensuring that all PXMs cover the memory reported in the e820. However, when calculating the size of the holes in the e820, it uses the early_node_map[] which contains information taken from both SRAT and e820. If the SRAT is missing an entry, then it is not detected that the SRAT table is incorrect and missing entries. This patch uses the e820 map to calculate the holes instead of early_node_map[]. comment is from Mel. [ Impact: reject incorrect SRAT tables ] Signed-off-by: Yinghai Lu Acked-by: Mel Gorman Cc: Andrew Morton LKML-Reference: <4A03E10C.60906@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/mm/srat_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/mm/srat_64.c') diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 01765955baaf..c7a18aaccf8d 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -345,7 +345,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes) pxmram = 0; } - e820ram = max_pfn - absent_pages_in_range(0, max_pfn); + e820ram = max_pfn - (e820_hole_size(0, max_pfn<>PAGE_SHIFT); /* We seem to lose 3 pages somewhere. Allow a bit of slack. */ if ((long)(e820ram - pxmram) >= 1*1024*1024) { printk(KERN_ERR -- cgit v1.2.1 From 0964b0562bb9c93194e852b47bab2397b9e11c18 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 8 May 2009 00:37:34 -0700 Subject: x86: Allow 1MB of slack between the e820 map and SRAT, not 4GB It is expected that there might be slight differences between the e820 map and the SRAT table and the intention was that 1MB of slack be allowed. The calculation comparing e820ram and pxmram assumes the units are bytes, when they are in fact pages. This means 4GB of slack is being allowed, not 1MB. This patch makes the correct comparison. comment is from Mel. [ Impact: don't accept buggy SRATs that could dump up to 4G of RAM ] Signed-off-by: Yinghai Lu Acked-by: Mel Gorman Cc: Andrew Morton LKML-Reference: <4A03E13E.6050107@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/mm/srat_64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm/srat_64.c') diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index c7a18aaccf8d..87b45bff250d 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -346,8 +346,8 @@ static int __init nodes_cover_memory(const struct bootnode *nodes) } e820ram = max_pfn - (e820_hole_size(0, max_pfn<>PAGE_SHIFT); - /* We seem to lose 3 pages somewhere. Allow a bit of slack. */ - if ((long)(e820ram - pxmram) >= 1*1024*1024) { + /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ + if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) { printk(KERN_ERR "SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n", (pxmram << PAGE_SHIFT) >> 20, -- cgit v1.2.1 From 888a589f6be07d624e21e2174d98375e9f95911b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 15 May 2009 13:59:37 -0700 Subject: mm, x86: remove MEMORY_HOTPLUG_RESERVE related code after: | commit b263295dbffd33b0fbff670720fa178c30e3392a | Author: Christoph Lameter | Date: Wed Jan 30 13:30:47 2008 +0100 | | x86: 64-bit, make sparsemem vmemmap the only memory model we don't have MEMORY_HOTPLUG_RESERVE anymore. Historically, x86-64 had an architecture-specific method for memory hotplug whereby it scanned the SRAT for physical memory ranges that could be potentially used for memory hot-add later. By reserving those ranges without physical memory, the memmap would be allocated and left dormant until needed. This depended on the DISCONTIG memory model which has been removed so the code implementing HOTPLUG_RESERVE is now dead. This patch removes the dead code used by MEMORY_HOTPLUG_RESERVE. (Changelog authored by Mel.) v2: updated changelog, and remove hotadd= in doc [ Impact: remove dead code ] Signed-off-by: Yinghai Lu Reviewed-by: Christoph Lameter Reviewed-by: Mel Gorman Workflow-found-OK-by: Andrew Morton LKML-Reference: <4A0C4910.7090508@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/mm/srat_64.c | 63 ++++++++++----------------------------------------- 1 file changed, 12 insertions(+), 51 deletions(-) (limited to 'arch/x86/mm/srat_64.c') diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 87b45bff250d..b0dbbd48e58a 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -31,8 +31,6 @@ static nodemask_t nodes_parsed __initdata; static nodemask_t cpu_nodes_parsed __initdata; static struct bootnode nodes[MAX_NUMNODES] __initdata; static struct bootnode nodes_add[MAX_NUMNODES]; -static int found_add_area __initdata; -int hotadd_percent __initdata = 0; static int num_node_memblks __initdata; static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata; @@ -66,9 +64,6 @@ static __init void cutoff_node(int i, unsigned long start, unsigned long end) { struct bootnode *nd = &nodes[i]; - if (found_add_area) - return; - if (nd->start < start) { nd->start = start; if (nd->end < nd->start) @@ -86,7 +81,6 @@ static __init void bad_srat(void) int i; printk(KERN_ERR "SRAT: SRAT not used.\n"); acpi_numa = -1; - found_add_area = 0; for (i = 0; i < MAX_LOCAL_APIC; i++) apicid_to_node[i] = NUMA_NO_NODE; for (i = 0; i < MAX_NUMNODES; i++) @@ -182,24 +176,21 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) pxm, apic_id, node); } -static int update_end_of_memory(unsigned long end) {return -1;} -static int hotadd_enough_memory(struct bootnode *nd) {return 1;} #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static inline int save_add_info(void) {return 1;} #else static inline int save_add_info(void) {return 0;} #endif /* - * Update nodes_add and decide if to include add are in the zone. - * Both SPARSE and RESERVE need nodes_add information. - * This code supports one contiguous hot add area per node. + * Update nodes_add[] + * This code supports one contiguous hot add area per node */ -static int __init -reserve_hotadd(int node, unsigned long start, unsigned long end) +static void __init +update_nodes_add(int node, unsigned long start, unsigned long end) { unsigned long s_pfn = start >> PAGE_SHIFT; unsigned long e_pfn = end >> PAGE_SHIFT; - int ret = 0, changed = 0; + int changed = 0; struct bootnode *nd = &nodes_add[node]; /* I had some trouble with strange memory hotadd regions breaking @@ -210,7 +201,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end) mistakes */ if ((signed long)(end - start) < NODE_MIN_SIZE) { printk(KERN_ERR "SRAT: Hotplug area too small\n"); - return -1; + return; } /* This check might be a bit too strict, but I'm keeping it for now. */ @@ -218,12 +209,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end) printk(KERN_ERR "SRAT: Hotplug area %lu -> %lu has existing memory\n", s_pfn, e_pfn); - return -1; - } - - if (!hotadd_enough_memory(&nodes_add[node])) { - printk(KERN_ERR "SRAT: Hotplug area too large\n"); - return -1; + return; } /* Looks good */ @@ -245,11 +231,9 @@ reserve_hotadd(int node, unsigned long start, unsigned long end) printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n"); } - ret = update_end_of_memory(nd->end); - if (changed) - printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end); - return ret; + printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", + nd->start, nd->end); } /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ @@ -310,13 +294,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) start, end); e820_register_active_regions(node, start >> PAGE_SHIFT, end >> PAGE_SHIFT); - push_node_boundaries(node, nd->start >> PAGE_SHIFT, - nd->end >> PAGE_SHIFT); - if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && - (reserve_hotadd(node, start, end) < 0)) { - /* Ignore hotadd region. Undo damage */ - printk(KERN_NOTICE "SRAT: Hotplug region ignored\n"); + if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) { + update_nodes_add(node, start, end); + /* restore nodes[node] */ *nd = oldnode; if ((nd->start | nd->end) == 0) node_clear(node, nodes_parsed); @@ -510,26 +491,6 @@ static int null_slit_node_compare(int a, int b) } #endif /* CONFIG_NUMA_EMU */ -void __init srat_reserve_add_area(int nodeid) -{ - if (found_add_area && nodes_add[nodeid].end) { - u64 total_mb; - - printk(KERN_INFO "SRAT: Reserving hot-add memory space " - "for node %d at %Lx-%Lx\n", - nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end); - total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start) - >> PAGE_SHIFT; - total_mb *= sizeof(struct page); - total_mb >>= 20; - printk(KERN_INFO "SRAT: This will cost you %Lu MB of " - "pre-allocated memory.\n", (unsigned long long)total_mb); - reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start, - nodes_add[nodeid].end - nodes_add[nodeid].start, - BOOTMEM_DEFAULT); - } -} - int __node_distance(int a, int b) { int index; -- cgit v1.2.1 From 7c43769a9776141ec23ca81a1bdd5a9c0512f165 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 15 May 2009 13:59:37 -0700 Subject: x86, mm: Fix node_possible_map logic Recently there were some changes to the meaning of node_possible_map, and it is quite strange: - the node without memory would be set in node_possible_map - but some node with less NODE_MIN_SIZE will be kicked out of node_possible_map. fix it by adding strict_setup_node_bootmem(). Also, remove unparse_node(). so result will be: 1. cpu_to_node() will return online node only (nearest one) 2. apicid_to_node() still returns the node that could be not online but is set in node_possible_map. 3. node_possible_map will include nodes that mem on it are less NODE_MIN_SIZE v2: after move_cpus_to_node change. [ Impact: get node_possible_map right ] Signed-off-by: Yinghai Lu Tested-by: Jack Steiner LKML-Reference: <4A0C49BE.6080800@kernel.org> [ v3: various small cleanups and comment clarifications ] Signed-off-by: Ingo Molnar --- arch/x86/mm/srat_64.c | 29 ++--------------------------- 1 file changed, 2 insertions(+), 27 deletions(-) (limited to 'arch/x86/mm/srat_64.c') diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index b0dbbd48e58a..2dfcbf9df2ae 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -36,10 +36,6 @@ static int num_node_memblks __initdata; static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata; static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata; -/* Too small nodes confuse the VM badly. Usually they result - from BIOS bugs. */ -#define NODE_MIN_SIZE (4*1024*1024) - static __init int setup_node(int pxm) { return acpi_map_pxm_to_node(pxm); @@ -338,17 +334,6 @@ static int __init nodes_cover_memory(const struct bootnode *nodes) return 1; } -static void __init unparse_node(int node) -{ - int i; - node_clear(node, nodes_parsed); - node_clear(node, cpu_nodes_parsed); - for (i = 0; i < MAX_LOCAL_APIC; i++) { - if (apicid_to_node[i] == node) - apicid_to_node[i] = NUMA_NO_NODE; - } -} - void __init acpi_numa_arch_fixup(void) {} /* Use the information discovered above to actually set up the nodes. */ @@ -360,18 +345,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) return -1; /* First clean up the node list */ - for (i = 0; i < MAX_NUMNODES; i++) { + for (i = 0; i < MAX_NUMNODES; i++) cutoff_node(i, start, end); - /* - * don't confuse VM with a node that doesn't have the - * minimum memory. - */ - if (nodes[i].end && - (nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) { - unparse_node(i); - node_set_offline(i); - } - } if (!nodes_cover_memory(nodes)) { bad_srat(); @@ -404,7 +379,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) if (node == NUMA_NO_NODE) continue; - if (!node_isset(node, node_possible_map)) + if (!node_online(node)) numa_clear_node(i); } numa_init_array(); -- cgit v1.2.1