From 20e6926dcbafa1b361f1c29d967688be14b6ca4b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 1 Mar 2013 14:51:27 -0800 Subject: x86, ACPI, mm: Revert movablemem_map support Tim found: WARNING: at arch/x86/kernel/smpboot.c:324 topology_sane.isra.2+0x6f/0x80() Hardware name: S2600CP sched: CPU #1's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency. smpboot: Booting Node 1, Processors #1 Modules linked in: Pid: 0, comm: swapper/1 Not tainted 3.9.0-0-generic #1 Call Trace: set_cpu_sibling_map+0x279/0x449 start_secondary+0x11d/0x1e5 Don Morris reproduced on a HP z620 workstation, and bisected it to commit e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") It turns out movable_map has some problems, and it breaks several things 1. numa_init is called several times, NOT just for srat. so those nodes_clear(numa_nodes_parsed) memset(&numa_meminfo, 0, sizeof(numa_meminfo)) can not be just removed. Need to consider sequence is: numaq, srat, amd, dummy. and make fall back path working. 2. simply split acpi_numa_init to early_parse_srat. a. that early_parse_srat is NOT called for ia64, so you break ia64. b. for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE) still left in numa_init. So it will just clear result from early_parse_srat. it should be moved before that.... c. it breaks ACPI_TABLE_OVERIDE...as the acpi table scan is moved early before override from INITRD is settled. 3. that patch TITLE is total misleading, there is NO x86 in the title, but it changes critical x86 code. It caused x86 guys did not pay attention to find the problem early. Those patches really should be routed via tip/x86/mm. 4. after that commit, following range can not use movable ram: a. real_mode code.... well..funny, legacy Node0 [0,1M) could be hot-removed? b. initrd... it will be freed after booting, so it could be on movable... c. crashkernel for kdump...: looks like we can not put kdump kernel above 4G anymore. d. init_mem_mapping: can not put page table high anymore. e. initmem_init: vmemmap can not be high local node anymore. That is not good. If node is hotplugable, the mem related range like page table and vmemmap could be on the that node without problem and should be on that node. We have workaround patch that could fix some problems, but some can not be fixed. So just remove that offending commit and related ones including: f7210e6c4ac7 ("mm/memblock.c: use CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect movablecore_map in memblock_overlaps_region().") 01a178a94e8e ("acpi, memory-hotplug: support getting hotplug info from SRAT") 27168d38fa20 ("acpi, memory-hotplug: extend movablemem_map ranges to the end of node") e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") fb06bc8e5f42 ("page_alloc: bootmem limit with movablecore_map") 42f47e27e761 ("page_alloc: make movablemem_map have higher priority") 6981ec31146c ("page_alloc: introduce zone_movable_limit[] to keep movable limit for nodes") 34b71f1e04fc ("page_alloc: add movable_memmap kernel parameter") 4d59a75125d5 ("x86: get pg_data_t's memory from other node") Later we should have patches that will make sure kernel put page table and vmemmap on local node ram instead of push them down to node0. Also need to find way to put other kernel used ram to local node ram. Reported-by: Tim Gardner Reported-by: Don Morris Bisected-by: Don Morris Tested-by: Don Morris Signed-off-by: Yinghai Lu Cc: Tony Luck Cc: Thomas Renninger Cc: Tejun Heo Cc: Tang Chen Cc: Yasuaki Ishimatsu Signed-off-by: Linus Torvalds --- arch/x86/kernel/setup.c | 13 ++--- arch/x86/mm/numa.c | 11 ++--- arch/x86/mm/srat.c | 125 ++---------------------------------------------- 3 files changed, 12 insertions(+), 137 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e89acdf6b77b..84d32855f65c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1056,15 +1056,6 @@ void __init setup_arch(char **cmdline_p) setup_bios_corruption_check(); #endif - /* - * In the memory hotplug case, the kernel needs info from SRAT to - * determine which memory is hotpluggable before allocating memory - * using memblock. - */ - acpi_boot_table_init(); - early_acpi_boot_init(); - early_parse_srat(); - #ifdef CONFIG_X86_32 printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n", (max_pfn_mapped<cnt; i++) { - if (end <= rgn->regions[i].base || - start >= rgn->regions[i].base + - rgn->regions[i].size) - continue; - - /* - * If the memory range overlaps the memory reserved by - * memblock, then the kernel resides in this node. - */ - node_set(node, movablemem_map.numa_nodes_kernel); - - goto out; - } - - /* - * If the kernel resides in this node, then the whole node - * should not be hotpluggable. - */ - if (node_isset(node, movablemem_map.numa_nodes_kernel)) - goto out; - - insert_movablemem_map(start_pfn, end_pfn); - - /* - * numa_nodes_hotplug nodemask represents which nodes are put - * into movablemem_map.map[]. - */ - node_set(node, movablemem_map.numa_nodes_hotplug); - goto out; - } - - /* - * For movablemem_map=nn[KMG]@ss[KMG]: - * - * SRAT: |_____| |_____| |_________| |_________| ...... - * node id: 0 1 1 2 - * user specified: |__| |___| - * movablemem_map: |___| |_________| |______| ...... - * - * Using movablemem_map, we can prevent memblock from allocating memory - * on ZONE_MOVABLE at boot time. - * - * NOTE: In this case, SRAT info will be ingored. - */ - overlap = movablemem_map_overlap(start_pfn, end_pfn); - if (overlap >= 0) { - /* - * If part of this range is in movablemem_map, we need to - * add the range after it to extend the range to the end - * of the node, because from the min address specified to - * the end of the node will be ZONE_MOVABLE. - */ - start_pfn = max(start_pfn, - movablemem_map.map[overlap].start_pfn); - insert_movablemem_map(start_pfn, end_pfn); - - /* - * Set the nodemask, so that if the address range on one node - * is not continuse, we can add the subsequent ranges on the - * same node into movablemem_map. - */ - node_set(node, movablemem_map.numa_nodes_hotplug); - } else { - if (node_isset(node, movablemem_map.numa_nodes_hotplug)) - /* - * Insert the range if we already have movable ranges - * on the same node. - */ - insert_movablemem_map(start_pfn, end_pfn); - } -out: - return; -} -#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -static inline void -handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable) -{ -} -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ - /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { u64 start, end; - u32 hotpluggable; int node, pxm; if (srat_disabled()) @@ -269,8 +154,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) goto out_err_bad_srat; if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) goto out_err; - hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE; - if (hotpluggable && !save_add_info()) + if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) goto out_err; start = ma->base_address; @@ -290,12 +174,9 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx] %s\n", + printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", node, pxm, - (unsigned long long) start, (unsigned long long) end - 1, - hotpluggable ? "Hot Pluggable": ""); - - handle_movablemem(node, start, end, hotpluggable); + (unsigned long long) start, (unsigned long long) end - 1); return 0; out_err_bad_srat: -- cgit v1.2.3