OpenCloudOS-Kernel/arch/x86/mm/numa.c

885 lines
22 KiB
C
Raw Normal View History

/* Common code for 32 and 64-bit NUMA */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/nodemask.h>
#include <linux/sched.h>
#include <linux/topology.h>
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/dma.h>
#include <asm/acpi.h>
#include <asm/amd_nb.h>
#include "numa_internal.h"
int __initdata numa_off;
nodemask_t numa_nodes_parsed __initdata;
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
static struct numa_meminfo numa_meminfo
#ifndef CONFIG_MEMORY_HOTPLUG
__initdata
#endif
;
static int numa_distance_cnt;
static u8 *numa_distance;
static __init int numa_setup(char *opt)
{
if (!opt)
return -EINVAL;
if (!strncmp(opt, "off", 3))
numa_off = 1;
#ifdef CONFIG_NUMA_EMU
if (!strncmp(opt, "fake=", 5))
numa_emu_cmdline(opt + 5);
#endif
#ifdef CONFIG_ACPI_NUMA
if (!strncmp(opt, "noacpi", 6))
acpi_numa = -1;
#endif
return 0;
}
early_param("numa", numa_setup);
/*
* apicid, cpu, node mappings
*/
cpu_hotplug: clear apicid to node when the cpu is hotremoved When a cpu is hotpluged, we call acpi_map_cpu2node() in _acpi_map_lsapic() to store the cpu's node and apicid's node. But we don't clear the cpu's node in acpi_unmap_lsapic() when this cpu is hotremoved. If the node is also hotremoved, we will get the following messages: kernel BUG at include/linux/gfp.h:329! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat xt_CHECKSUM iptable_mangle bridge stp llc sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel microcode pcspkr i2c_i801 i2c_core lpc_ich mfd_core ioatdma e1000e i7core_edac edac_core sg acpi_memhotplug igb dca sd_mod crc_t10dif megaraid_sas mptsas mptscsih mptbase scsi_transport_sas scsi_mod Pid: 3126, comm: init Not tainted 3.6.0-rc3-tangchen-hostbridge+ #13 FUJITSU-SV PRIMEQUEST 1800E/SB RIP: 0010:[<ffffffff811bc3fd>] [<ffffffff811bc3fd>] allocate_slab+0x28d/0x300 RSP: 0018:ffff88078a049cf8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000001 RDI: 0000000000000246 RBP: ffff88078a049d38 R08: 00000000000040d0 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000b5f R12: 00000000000052d0 R13: ffff8807c1417300 R14: 0000000000030038 R15: 0000000000000003 FS: 00007fa9b1b44700(0000) GS:ffff8807c3800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007fa9b09acca0 CR3: 000000078b855000 CR4: 00000000000007e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process init (pid: 3126, threadinfo ffff88078a048000, task ffff8807bb6f2650) Call Trace: new_slab+0x30/0x1b0 __slab_alloc+0x358/0x4c0 kmem_cache_alloc_node_trace+0xb4/0x1e0 alloc_fair_sched_group+0xd0/0x1b0 sched_create_group+0x3e/0x110 sched_autogroup_create_attach+0x4d/0x180 sys_setsid+0xd4/0xf0 system_call_fastpath+0x16/0x1b Code: 89 c4 e9 73 fe ff ff 31 c0 89 de 48 c7 c7 45 de 9e 81 44 89 45 c8 e8 22 05 4b 00 85 db 44 8b 45 c8 0f 89 4f ff ff ff 0f 0b eb fe <0f> 0b 90 eb fd 0f 0b eb fe 89 de 48 c7 c7 45 de 9e 81 31 c0 44 RIP [<ffffffff811bc3fd>] allocate_slab+0x28d/0x300 RSP <ffff88078a049cf8> ---[ end trace adf84c90f3fea3e5 ]--- The reason is that the cpu's node is not NUMA_NO_NODE, we will call alloc_pages_exact_node() to alloc memory on the node, but the node is offlined. If the node is onlined, we still need cpu's node. For example: a task on the cpu is sleeped when the cpu is hotremoved. We will choose another cpu to run this task when it is waked up. If we know the cpu's node, we will choose the cpu on the same node first. So we should clear cpu-to-node mapping when the node is offlined. This patch only clears apicid-to-node mapping when the cpu is hotremoved. [akpm@linux-foundation.org: fix section error] Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Jiang Liu <liuj97@gmail.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 08:33:24 +08:00
s16 __apicid_to_node[MAX_LOCAL_APIC] = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 06:23:59 +08:00
int numa_cpu_node(int cpu)
{
int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
if (apicid != BAD_APICID)
return __apicid_to_node[apicid];
return NUMA_NO_NODE;
}
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
EXPORT_SYMBOL(node_to_cpumask_map);
/*
* Map cpu index to node index
*/
DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
void numa_set_node(int cpu, int node)
{
int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
/* early setting, no percpu area yet */
if (cpu_to_node_map) {
cpu_to_node_map[cpu] = node;
return;
}
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
dump_stack();
return;
}
#endif
per_cpu(x86_cpu_to_node_map, cpu) = node;
set_cpu_numa_node(cpu, node);
}
void numa_clear_node(int cpu)
{
numa_set_node(cpu, NUMA_NO_NODE);
}
/*
* Allocate node_to_cpumask_map based on number of available nodes
* Requires node_possible_map to be valid.
*
* Note: cpumask_of_node() is not valid until after this is done.
* (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
*/
void __init setup_node_to_cpumask_map(void)
{
unsigned int node;
/* setup nr_node_ids if not done yet */
if (nr_node_ids == MAX_NUMNODES)
setup_nr_node_ids();
/* allocate the map */
for (node = 0; node < nr_node_ids; node++)
alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
/* cpumask_of_node() will now work */
pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
}
static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
struct numa_meminfo *mi)
{
/* ignore zero length blks */
if (start == end)
return 0;
/* whine about and ignore invalid blks */
if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
pr_warning("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
nid, start, end - 1);
return 0;
}
if (mi->nr_blks >= NR_NODE_MEMBLKS) {
pr_err("NUMA: too many memblk ranges\n");
return -EINVAL;
}
mi->blk[mi->nr_blks].start = start;
mi->blk[mi->nr_blks].end = end;
mi->blk[mi->nr_blks].nid = nid;
mi->nr_blks++;
return 0;
}
/**
* numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo
* @idx: Index of memblk to remove
* @mi: numa_meminfo to remove memblk from
*
* Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and
* decrementing @mi->nr_blks.
*/
void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
{
mi->nr_blks--;
memmove(&mi->blk[idx], &mi->blk[idx + 1],
(mi->nr_blks - idx) * sizeof(mi->blk[0]));
}
/**
* numa_add_memblk - Add one numa_memblk to numa_meminfo
* @nid: NUMA node ID of the new memblk
* @start: Start address of the new memblk
* @end: End address of the new memblk
*
* Add a new memblk to the default numa_meminfo.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int __init numa_add_memblk(int nid, u64 start, u64 end)
{
return numa_add_memblk_to(nid, start, end, &numa_meminfo);
}
x86/mm/numa: Drop dead code and rename setup_node_data() to setup_alloc_data() The setup_node_data() function allocates a pg_data_t object, inserts it into the node_data[] array and initializes the following fields: node_id, node_start_pfn and node_spanned_pages. However, a few function calls later during the kernel boot, free_area_init_node() re-initializes those fields, possibly with setup_node_data() is not used. This causes a small glitch when running Linux as a hyperv numa guest: SRAT: PXM 0 -> APIC 0x00 -> Node 0 SRAT: PXM 0 -> APIC 0x01 -> Node 0 SRAT: PXM 1 -> APIC 0x02 -> Node 1 SRAT: PXM 1 -> APIC 0x03 -> Node 1 SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff] SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff] SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff] NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff] Initmem setup node 0 [mem 0x00000000-0x7fffffff] NODE_DATA [mem 0x7ffdc000-0x7ffeffff] Initmem setup node 1 [mem 0x80800000-0x1081fffff] NODE_DATA [mem 0x1081ea000-0x1081fdfff] crashkernel: memory value expected [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0 [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1 Zone ranges: DMA [mem 0x00001000-0x00ffffff] DMA32 [mem 0x01000000-0xffffffff] Normal [mem 0x100000000-0x1081fffff] Movable zone start for each node Early memory node ranges node 0: [mem 0x00001000-0x0009efff] node 0: [mem 0x00100000-0x7ffeffff] node 1: [mem 0x80200000-0xf7ffffff] node 1: [mem 0x100000000-0x1081fffff] On node 0 totalpages: 524174 DMA zone: 64 pages used for memmap DMA zone: 21 pages reserved DMA zone: 3998 pages, LIFO batch:0 DMA32 zone: 8128 pages used for memmap DMA32 zone: 520176 pages, LIFO batch:31 On node 1 totalpages: 524288 DMA32 zone: 7672 pages used for memmap DMA32 zone: 491008 pages, LIFO batch:31 Normal zone: 520 pages used for memmap Normal zone: 33280 pages, LIFO batch:7 In this dmesg, the SRAT table reports that the memory range for node 1 starts at 0x80200000. However, the line starting with "Initmem" reports that node 1 memory range starts at 0x80800000. The "Initmem" line is reported by setup_node_data() and is wrong, because the kernel ends up using the range as reported in the SRAT table. This commit drops all that dead code from setup_node_data(), renames it to alloc_node_data() and adds a printk() to free_area_init_node() so that we report a node's memory range accurately. Here's the same dmesg section with this patch applied: SRAT: PXM 0 -> APIC 0x00 -> Node 0 SRAT: PXM 0 -> APIC 0x01 -> Node 0 SRAT: PXM 1 -> APIC 0x02 -> Node 1 SRAT: PXM 1 -> APIC 0x03 -> Node 1 SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff] SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff] SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff] NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff] NODE_DATA(0) allocated [mem 0x7ffdc000-0x7ffeffff] NODE_DATA(1) allocated [mem 0x1081ea000-0x1081fdfff] crashkernel: memory value expected [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0 [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1 Zone ranges: DMA [mem 0x00001000-0x00ffffff] DMA32 [mem 0x01000000-0xffffffff] Normal [mem 0x100000000-0x1081fffff] Movable zone start for each node Early memory node ranges node 0: [mem 0x00001000-0x0009efff] node 0: [mem 0x00100000-0x7ffeffff] node 1: [mem 0x80200000-0xf7ffffff] node 1: [mem 0x100000000-0x1081fffff] Initmem setup node 0 [mem 0x00001000-0x7ffeffff] On node 0 totalpages: 524174 DMA zone: 64 pages used for memmap DMA zone: 21 pages reserved DMA zone: 3998 pages, LIFO batch:0 DMA32 zone: 8128 pages used for memmap DMA32 zone: 520176 pages, LIFO batch:31 Initmem setup node 1 [mem 0x80200000-0x1081fffff] On node 1 totalpages: 524288 DMA32 zone: 7672 pages used for memmap DMA32 zone: 491008 pages, LIFO batch:31 Normal zone: 520 pages used for memmap Normal zone: 33280 pages, LIFO batch:7 This commit was tested on a two node bare-metal NUMA machine and Linux as a numa guest on hyperv and qemu/kvm. PS: The wrong memory range reported by setup_node_data() seems to be harmless in the current kernel because it's just not used. However, that bad range is used in kernel 2.6.32 to initialize the old boot memory allocator, which causes a crash during boot. Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Rientjes <rientjes@google.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-23 04:27:36 +08:00
/* Allocate NODE_DATA for a node on the local memory */
static void __init alloc_node_data(int nid)
{
const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
u64 nd_pa;
void *nd;
int tnid;
/*
* Allocate node data. Try node-local memory and then any node.
* Never allocate in DMA zone.
*/
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 <tim.gardner@canonical.com> Reported-by: Don Morris <don.morris@hp.com> Bisected-by: Don Morris <don.morris@hp.com> Tested-by: Don Morris <don.morris@hp.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Tejun Heo <tj@kernel.org> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-03-02 06:51:27 +08:00
nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
if (!nd_pa) {
nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES,
MEMBLOCK_ALLOC_ACCESSIBLE);
if (!nd_pa) {
pr_err("Cannot find %zu bytes in node %d\n",
nd_size, nid);
return;
}
}
nd = __va(nd_pa);
/* report and initialize */
x86/mm/numa: Drop dead code and rename setup_node_data() to setup_alloc_data() The setup_node_data() function allocates a pg_data_t object, inserts it into the node_data[] array and initializes the following fields: node_id, node_start_pfn and node_spanned_pages. However, a few function calls later during the kernel boot, free_area_init_node() re-initializes those fields, possibly with setup_node_data() is not used. This causes a small glitch when running Linux as a hyperv numa guest: SRAT: PXM 0 -> APIC 0x00 -> Node 0 SRAT: PXM 0 -> APIC 0x01 -> Node 0 SRAT: PXM 1 -> APIC 0x02 -> Node 1 SRAT: PXM 1 -> APIC 0x03 -> Node 1 SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff] SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff] SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff] NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff] Initmem setup node 0 [mem 0x00000000-0x7fffffff] NODE_DATA [mem 0x7ffdc000-0x7ffeffff] Initmem setup node 1 [mem 0x80800000-0x1081fffff] NODE_DATA [mem 0x1081ea000-0x1081fdfff] crashkernel: memory value expected [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0 [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1 Zone ranges: DMA [mem 0x00001000-0x00ffffff] DMA32 [mem 0x01000000-0xffffffff] Normal [mem 0x100000000-0x1081fffff] Movable zone start for each node Early memory node ranges node 0: [mem 0x00001000-0x0009efff] node 0: [mem 0x00100000-0x7ffeffff] node 1: [mem 0x80200000-0xf7ffffff] node 1: [mem 0x100000000-0x1081fffff] On node 0 totalpages: 524174 DMA zone: 64 pages used for memmap DMA zone: 21 pages reserved DMA zone: 3998 pages, LIFO batch:0 DMA32 zone: 8128 pages used for memmap DMA32 zone: 520176 pages, LIFO batch:31 On node 1 totalpages: 524288 DMA32 zone: 7672 pages used for memmap DMA32 zone: 491008 pages, LIFO batch:31 Normal zone: 520 pages used for memmap Normal zone: 33280 pages, LIFO batch:7 In this dmesg, the SRAT table reports that the memory range for node 1 starts at 0x80200000. However, the line starting with "Initmem" reports that node 1 memory range starts at 0x80800000. The "Initmem" line is reported by setup_node_data() and is wrong, because the kernel ends up using the range as reported in the SRAT table. This commit drops all that dead code from setup_node_data(), renames it to alloc_node_data() and adds a printk() to free_area_init_node() so that we report a node's memory range accurately. Here's the same dmesg section with this patch applied: SRAT: PXM 0 -> APIC 0x00 -> Node 0 SRAT: PXM 0 -> APIC 0x01 -> Node 0 SRAT: PXM 1 -> APIC 0x02 -> Node 1 SRAT: PXM 1 -> APIC 0x03 -> Node 1 SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff] SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff] SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff] NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff] NODE_DATA(0) allocated [mem 0x7ffdc000-0x7ffeffff] NODE_DATA(1) allocated [mem 0x1081ea000-0x1081fdfff] crashkernel: memory value expected [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0 [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1 Zone ranges: DMA [mem 0x00001000-0x00ffffff] DMA32 [mem 0x01000000-0xffffffff] Normal [mem 0x100000000-0x1081fffff] Movable zone start for each node Early memory node ranges node 0: [mem 0x00001000-0x0009efff] node 0: [mem 0x00100000-0x7ffeffff] node 1: [mem 0x80200000-0xf7ffffff] node 1: [mem 0x100000000-0x1081fffff] Initmem setup node 0 [mem 0x00001000-0x7ffeffff] On node 0 totalpages: 524174 DMA zone: 64 pages used for memmap DMA zone: 21 pages reserved DMA zone: 3998 pages, LIFO batch:0 DMA32 zone: 8128 pages used for memmap DMA32 zone: 520176 pages, LIFO batch:31 Initmem setup node 1 [mem 0x80200000-0x1081fffff] On node 1 totalpages: 524288 DMA32 zone: 7672 pages used for memmap DMA32 zone: 491008 pages, LIFO batch:31 Normal zone: 520 pages used for memmap Normal zone: 33280 pages, LIFO batch:7 This commit was tested on a two node bare-metal NUMA machine and Linux as a numa guest on hyperv and qemu/kvm. PS: The wrong memory range reported by setup_node_data() seems to be harmless in the current kernel because it's just not used. However, that bad range is used in kernel 2.6.32 to initialize the old boot memory allocator, which causes a crash during boot. Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Rientjes <rientjes@google.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-23 04:27:36 +08:00
printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid,
nd_pa, nd_pa + nd_size - 1);
tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
if (tnid != nid)
printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid);
node_data[nid] = nd;
memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
node_set_online(nid);
}
/**
* numa_cleanup_meminfo - Cleanup a numa_meminfo
* @mi: numa_meminfo to clean up
*
* Sanitize @mi by merging and removing unncessary memblks. Also check for
* conflicts and clear unused memblks.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
{
const u64 low = 0;
const u64 high = PFN_PHYS(max_pfn);
int i, j, k;
/* first, trim all entries */
for (i = 0; i < mi->nr_blks; i++) {
struct numa_memblk *bi = &mi->blk[i];
/* make sure all blocks are inside the limits */
bi->start = max(bi->start, low);
bi->end = min(bi->end, high);
mem-hotplug: handle node hole when initializing numa_meminfo. When parsing SRAT, all memory ranges are added into numa_meminfo. In numa_init(), before entering numa_cleanup_meminfo(), all possible memory ranges are in numa_meminfo. And numa_cleanup_meminfo() removes all ranges over max_pfn or empty. But, this only works if the nodes are continuous. Let's have a look at the following example: We have an SRAT like this: SRAT: Node 0 PXM 0 [mem 0x00000000-0x5fffffff] SRAT: Node 0 PXM 0 [mem 0x100000000-0x1ffffffffff] SRAT: Node 1 PXM 1 [mem 0x20000000000-0x3ffffffffff] SRAT: Node 4 PXM 2 [mem 0x40000000000-0x5ffffffffff] hotplug SRAT: Node 5 PXM 3 [mem 0x60000000000-0x7ffffffffff] hotplug SRAT: Node 2 PXM 4 [mem 0x80000000000-0x9ffffffffff] hotplug SRAT: Node 3 PXM 5 [mem 0xa0000000000-0xbffffffffff] hotplug SRAT: Node 6 PXM 6 [mem 0xc0000000000-0xdffffffffff] hotplug SRAT: Node 7 PXM 7 [mem 0xe0000000000-0xfffffffffff] hotplug On boot, only node 0,1,2,3 exist. And the numa_meminfo will look like this: numa_meminfo.nr_blks = 9 1. on node 0: [0, 60000000] 2. on node 0: [100000000, 20000000000] 3. on node 1: [20000000000, 40000000000] 4. on node 4: [40000000000, 60000000000] 5. on node 5: [60000000000, 80000000000] 6. on node 2: [80000000000, a0000000000] 7. on node 3: [a0000000000, a0800000000] 8. on node 6: [c0000000000, a0800000000] 9. on node 7: [e0000000000, a0800000000] And numa_cleanup_meminfo() will merge 1 and 2, and remove 8,9 because the end address is over max_pfn, which is a0800000000. But 4 and 5 are not removed because their end addresses are less then max_pfn. But in fact, node 4 and 5 don't exist. In a word, numa_cleanup_meminfo() is not able to handle holes between nodes. Since memory ranges in node 4 and 5 are in numa_meminfo, in numa_register_memblks(), node 4 and 5 will be mistakenly set to online. If you run lscpu, it will show: NUMA node0 CPU(s): 0-14,128-142 NUMA node1 CPU(s): 15-29,143-157 NUMA node2 CPU(s): NUMA node3 CPU(s): NUMA node4 CPU(s): 62-76,190-204 NUMA node5 CPU(s): 78-92,206-220 In this patch, we use memblock_overlaps_region() to check if ranges in numa_meminfo overlap with ranges in memory_block. Since memory_block contains all available memory at boot time, if they overlap, it means the ranges exist. If not, then remove them from numa_meminfo. After this patch, lscpu will show: NUMA node0 CPU(s): 0-14,128-142 NUMA node1 CPU(s): 15-29,143-157 NUMA node4 CPU(s): 62-76,190-204 NUMA node5 CPU(s): 78-92,206-220 Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tejun Heo <tj@kernel.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Vladimir Murzin <vladimir.murzin@arm.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Alexander Kuleshov <kuleshovmail@gmail.com> Cc: Baoquan He <bhe@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 06:02:03 +08:00
/* and there's no empty or non-exist block */
if (bi->start >= bi->end ||
!memblock_overlaps_region(&memblock.memory,
bi->start, bi->end - bi->start))
numa_remove_memblk_from(i--, mi);
}
/* merge neighboring / overlapping entries */
for (i = 0; i < mi->nr_blks; i++) {
struct numa_memblk *bi = &mi->blk[i];
for (j = i + 1; j < mi->nr_blks; j++) {
struct numa_memblk *bj = &mi->blk[j];
u64 start, end;
/*
* See whether there are overlapping blocks. Whine
* about but allow overlaps of the same nid. They
* will be merged below.
*/
if (bi->end > bj->start && bi->start < bj->end) {
if (bi->nid != bj->nid) {
pr_err("NUMA: node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
bi->nid, bi->start, bi->end - 1,
bj->nid, bj->start, bj->end - 1);
return -EINVAL;
}
pr_warning("NUMA: Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
bi->nid, bi->start, bi->end - 1,
bj->start, bj->end - 1);
}
/*
* Join together blocks on the same node, holes
* between which don't overlap with memory on other
* nodes.
*/
if (bi->nid != bj->nid)
continue;
start = min(bi->start, bj->start);
end = max(bi->end, bj->end);
for (k = 0; k < mi->nr_blks; k++) {
struct numa_memblk *bk = &mi->blk[k];
if (bi->nid == bk->nid)
continue;
if (start < bk->end && end > bk->start)
break;
}
if (k < mi->nr_blks)
continue;
printk(KERN_INFO "NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n",
bi->nid, bi->start, bi->end - 1, bj->start,
bj->end - 1, start, end - 1);
bi->start = start;
bi->end = end;
numa_remove_memblk_from(j--, mi);
}
}
/* clear unused ones */
for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
mi->blk[i].start = mi->blk[i].end = 0;
mi->blk[i].nid = NUMA_NO_NODE;
}
return 0;
}
/*
* Set nodes, which have memory in @mi, in *@nodemask.
*/
static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
const struct numa_meminfo *mi)
{
int i;
for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
if (mi->blk[i].start != mi->blk[i].end &&
mi->blk[i].nid != NUMA_NO_NODE)
node_set(mi->blk[i].nid, *nodemask);
}
/**
* numa_reset_distance - Reset NUMA distance table
*
* The current table is freed. The next numa_set_distance() call will
* create a new one.
*/
void __init numa_reset_distance(void)
{
size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
/* numa_distance could be 1LU marking allocation failure, test cnt */
if (numa_distance_cnt)
memblock_free(__pa(numa_distance), size);
numa_distance_cnt = 0;
numa_distance = NULL; /* enable table creation */
}
static int __init numa_alloc_distance(void)
{
nodemask_t nodes_parsed;
size_t size;
int i, j, cnt = 0;
u64 phys;
/* size the new table and allocate it */
nodes_parsed = numa_nodes_parsed;
numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);
for_each_node_mask(i, nodes_parsed)
cnt = i;
cnt++;
size = cnt * cnt * sizeof(numa_distance[0]);
phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
size, PAGE_SIZE);
if (!phys) {
pr_warning("NUMA: Warning: can't allocate distance table!\n");
/* don't retry until explicitly reset */
numa_distance = (void *)1LU;
return -ENOMEM;
}
memblock_reserve(phys, size);
numa_distance = __va(phys);
numa_distance_cnt = cnt;
/* fill with the default distances */
for (i = 0; i < cnt; i++)
for (j = 0; j < cnt; j++)
numa_distance[i * cnt + j] = i == j ?
LOCAL_DISTANCE : REMOTE_DISTANCE;
printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
return 0;
}
/**
* numa_set_distance - Set NUMA distance from one NUMA to another
* @from: the 'from' node to set distance
* @to: the 'to' node to set distance
* @distance: NUMA distance
*
* Set the distance from node @from to @to to @distance. If distance table
* doesn't exist, one which is large enough to accommodate all the currently
* known nodes will be created.
*
* If such table cannot be allocated, a warning is printed and further
* calls are ignored until the distance table is reset with
* numa_reset_distance().
*
* If @from or @to is higher than the highest known node or lower than zero
* at the time of table creation or @distance doesn't make sense, the call
* is ignored.
* This is to allow simplification of specific NUMA config implementations.
*/
void __init numa_set_distance(int from, int to, int distance)
{
if (!numa_distance && numa_alloc_distance() < 0)
return;
if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
from < 0 || to < 0) {
pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
if ((u8)distance != distance ||
(from == to && distance != LOCAL_DISTANCE)) {
pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
numa_distance[from * numa_distance_cnt + to] = distance;
}
int __node_distance(int from, int to)
{
if (from >= numa_distance_cnt || to >= numa_distance_cnt)
return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
return numa_distance[from * numa_distance_cnt + to];
}
EXPORT_SYMBOL(__node_distance);
/*
* Sanity check to catch more bad NUMA configurations (they are amazingly
* common). Make sure the nodes cover all memory.
*/
static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
{
u64 numaram, e820ram;
int i;
numaram = 0;
for (i = 0; i < mi->nr_blks; i++) {
u64 s = mi->blk[i].start >> PAGE_SHIFT;
u64 e = mi->blk[i].end >> PAGE_SHIFT;
numaram += e - s;
numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
if ((s64)numaram < 0)
numaram = 0;
}
e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
(numaram << PAGE_SHIFT) >> 20,
(e820ram << PAGE_SHIFT) >> 20);
return false;
}
return true;
}
static void __init numa_clear_kernel_node_hotplug(void)
{
int i, nid;
nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
unsigned long start, end;
struct memblock_region *r;
/*
* At this time, all memory regions reserved by memblock are
* used by the kernel. Set the nid in memblock.reserved will
* mark out all the nodes the kernel resides in.
*/
for (i = 0; i < numa_meminfo.nr_blks; i++) {
struct numa_memblk *mb = &numa_meminfo.blk[i];
memblock_set_node(mb->start, mb->end - mb->start,
&memblock.reserved, mb->nid);
}
x86/mm/numa: Fix kernel stack corruption in numa_init()->numa_clear_kernel_node_hotplug() I got below kernel panic during kdump test on Thinkpad T420 laptop: [ 0.000000] No NUMA configuration found [ 0.000000] Faking a node at [mem 0x0000000000000000-0x0000000037ba4fff] [ 0.000000] Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: ffffffff81d21910 ... [ 0.000000] Call Trace: [ 0.000000] [<ffffffff817c2a26>] dump_stack+0x45/0x57 [ 0.000000] [<ffffffff817bc8d2>] panic+0xd0/0x204 [ 0.000000] [<ffffffff81d21910>] ? numa_clear_kernel_node_hotplug+0xe6/0xf2 [ 0.000000] [<ffffffff8107741b>] __stack_chk_fail+0x1b/0x20 [ 0.000000] [<ffffffff81d21910>] numa_clear_kernel_node_hotplug+0xe6/0xf2 [ 0.000000] [<ffffffff81d21e5d>] numa_init+0x1a5/0x520 [ 0.000000] [<ffffffff81d222b1>] x86_numa_init+0x19/0x3d [ 0.000000] [<ffffffff81d22460>] initmem_init+0x9/0xb [ 0.000000] [<ffffffff81d0d00c>] setup_arch+0x94f/0xc82 [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff817bd0bb>] ? printk+0x55/0x6b [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff81d05d9b>] start_kernel+0xe8/0x4d6 [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff81d055ee>] x86_64_start_reservations+0x2a/0x2c [ 0.000000] [<ffffffff81d05751>] x86_64_start_kernel+0x161/0x184 [ 0.000000] ---[ end Kernel panic - not syncing: stack-protector: Kernel sta This is caused by writing over the end of numa mask bitmap in numa_clear_kernel_node(). numa_clear_kernel_node() tries to set the node id in a mask bitmap, by iterating all reserved regions and assuming that every region has a valid nid. This assumption is not true because there's an exception for some graphic memory quirks. See trim_snb_memory() in arch/x86/kernel/setup.c It is easily to reproduce the bug in the kdump kernel because kdump kernel use pre-reserved memory instead of the whole memory, but kexec pass other reserved memory ranges to 2nd kernel as well. like below in my test: kdump kernel ram 0x2d000000 - 0x37bfffff One of the reserved regions: 0x40000000 - 0x40100000 which includes 0x40004000, a page excluded in trim_snb_memory(). For this memblock reserved region the nid is not set, it is still default value MAX_NUMNODES. later node_set will set bit MAX_NUMNODES thus stack corruption happen. This also happens when booting with mem= kernel commandline during my test. Fixing it by adding a check, do not call node_set in case nid is MAX_NUMNODES. Signed-off-by: Dave Young <dyoung@redhat.com> Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: bhe@redhat.com Cc: qiuxishi@huawei.com Link: http://lkml.kernel.org/r/20150407134132.GA23522@dhcp-16-198.nay.redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-07 21:41:32 +08:00
/*
* Mark all kernel nodes.
*
* When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo
* may not include all the memblock.reserved memory ranges because
* trim_snb_memory() reserves specific pages for Sandy Bridge graphics.
*/
for_each_memblock(reserved, r)
x86/mm/numa: Fix kernel stack corruption in numa_init()->numa_clear_kernel_node_hotplug() I got below kernel panic during kdump test on Thinkpad T420 laptop: [ 0.000000] No NUMA configuration found [ 0.000000] Faking a node at [mem 0x0000000000000000-0x0000000037ba4fff] [ 0.000000] Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: ffffffff81d21910 ... [ 0.000000] Call Trace: [ 0.000000] [<ffffffff817c2a26>] dump_stack+0x45/0x57 [ 0.000000] [<ffffffff817bc8d2>] panic+0xd0/0x204 [ 0.000000] [<ffffffff81d21910>] ? numa_clear_kernel_node_hotplug+0xe6/0xf2 [ 0.000000] [<ffffffff8107741b>] __stack_chk_fail+0x1b/0x20 [ 0.000000] [<ffffffff81d21910>] numa_clear_kernel_node_hotplug+0xe6/0xf2 [ 0.000000] [<ffffffff81d21e5d>] numa_init+0x1a5/0x520 [ 0.000000] [<ffffffff81d222b1>] x86_numa_init+0x19/0x3d [ 0.000000] [<ffffffff81d22460>] initmem_init+0x9/0xb [ 0.000000] [<ffffffff81d0d00c>] setup_arch+0x94f/0xc82 [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff817bd0bb>] ? printk+0x55/0x6b [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff81d05d9b>] start_kernel+0xe8/0x4d6 [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff81d05120>] ? early_idt_handlers+0x120/0x120 [ 0.000000] [<ffffffff81d055ee>] x86_64_start_reservations+0x2a/0x2c [ 0.000000] [<ffffffff81d05751>] x86_64_start_kernel+0x161/0x184 [ 0.000000] ---[ end Kernel panic - not syncing: stack-protector: Kernel sta This is caused by writing over the end of numa mask bitmap in numa_clear_kernel_node(). numa_clear_kernel_node() tries to set the node id in a mask bitmap, by iterating all reserved regions and assuming that every region has a valid nid. This assumption is not true because there's an exception for some graphic memory quirks. See trim_snb_memory() in arch/x86/kernel/setup.c It is easily to reproduce the bug in the kdump kernel because kdump kernel use pre-reserved memory instead of the whole memory, but kexec pass other reserved memory ranges to 2nd kernel as well. like below in my test: kdump kernel ram 0x2d000000 - 0x37bfffff One of the reserved regions: 0x40000000 - 0x40100000 which includes 0x40004000, a page excluded in trim_snb_memory(). For this memblock reserved region the nid is not set, it is still default value MAX_NUMNODES. later node_set will set bit MAX_NUMNODES thus stack corruption happen. This also happens when booting with mem= kernel commandline during my test. Fixing it by adding a check, do not call node_set in case nid is MAX_NUMNODES. Signed-off-by: Dave Young <dyoung@redhat.com> Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: bhe@redhat.com Cc: qiuxishi@huawei.com Link: http://lkml.kernel.org/r/20150407134132.GA23522@dhcp-16-198.nay.redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-07 21:41:32 +08:00
if (r->nid != MAX_NUMNODES)
node_set(r->nid, numa_kernel_nodes);
/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
for (i = 0; i < numa_meminfo.nr_blks; i++) {
nid = numa_meminfo.blk[i].nid;
if (!node_isset(nid, numa_kernel_nodes))
continue;
start = numa_meminfo.blk[i].start;
end = numa_meminfo.blk[i].end;
memblock_clear_hotplug(start, end - start);
}
}
static int __init numa_register_memblks(struct numa_meminfo *mi)
{
x86, numa: Implement pfn -> nid mapping granularity check SPARSEMEM w/o VMEMMAP and DISCONTIGMEM, both used only on 32bit, use sections array to map pfn to nid which is limited in granularity. If NUMA nodes are laid out such that the mapping cannot be accurate, boot will fail triggering BUG_ON() in mminit_verify_page_links(). On 32bit, it's 512MiB w/ PAE and SPARSEMEM. This seems to have been granular enough until commit 2706a0bf7b (x86, NUMA: Enable CONFIG_AMD_NUMA on 32bit too). Apparently, there is a machine which aligns NUMA nodes to 128MiB and has only AMD NUMA but not SRAT. This led to the following BUG_ON(). On node 0 totalpages: 2096615 DMA zone: 32 pages used for memmap DMA zone: 0 pages reserved DMA zone: 3927 pages, LIFO batch:0 Normal zone: 1740 pages used for memmap Normal zone: 220978 pages, LIFO batch:31 HighMem zone: 16405 pages used for memmap HighMem zone: 1853533 pages, LIFO batch:31 BUG: Int 6: CR2 (null) EDI (null) ESI 00000002 EBP 00000002 ESP c1543ecc EBX f2400000 EDX 00000006 ECX (null) EAX 00000001 err (null) EIP c16209aa CS 00000060 flg 00010002 Stack: f2400000 00220000 f7200800 c1620613 00220000 01000000 04400000 00238000 (null) f7200000 00000002 f7200b58 f7200800 c1620929 000375fe (null) f7200b80 c16395f0 00200a02 f7200a80 (null) 000375fe 00000002 (null) Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00181-g2706a0b #17 Call Trace: [<c136b1e5>] ? early_fault+0x2e/0x2e [<c16209aa>] ? mminit_verify_page_links+0x12/0x42 [<c1620613>] ? memmap_init_zone+0xaf/0x10c [<c1620929>] ? free_area_init_node+0x2b9/0x2e3 [<c1607e99>] ? free_area_init_nodes+0x3f2/0x451 [<c1601d80>] ? paging_init+0x112/0x118 [<c15f578d>] ? setup_arch+0x791/0x82f [<c15f43d9>] ? start_kernel+0x6a/0x257 This patch implements node_map_pfn_alignment() which determines maximum internode alignment and update numa_register_memblks() to reject NUMA configuration if alignment exceeds the pfn -> nid mapping granularity of the memory model as determined by PAGES_PER_SECTION. This makes the problematic machine boot w/ flatmem by rejecting the NUMA config and provides protection against crazy NUMA configurations. Signed-off-by: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/20110712074534.GB2872@htj.dyndns.org LKML-Reference: <20110628174613.GP478@escobedo.osrc.amd.com> Reported-and-Tested-by: Hans Rosenfeld <hans.rosenfeld@amd.com> Cc: Conny Seidel <conny.seidel@amd.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2011-07-12 15:45:34 +08:00
unsigned long uninitialized_var(pfn_align);
int i, nid;
/* Account for nodes with cpus and no memory */
node_possible_map = numa_nodes_parsed;
numa_nodemask_from_meminfo(&node_possible_map, mi);
if (WARN_ON(nodes_empty(node_possible_map)))
return -EINVAL;
for (i = 0; i < mi->nr_blks; i++) {
struct numa_memblk *mb = &mi->blk[i];
memblock_set_node(mb->start, mb->end - mb->start,
&memblock.memory, mb->nid);
}
x86, numa: Implement pfn -> nid mapping granularity check SPARSEMEM w/o VMEMMAP and DISCONTIGMEM, both used only on 32bit, use sections array to map pfn to nid which is limited in granularity. If NUMA nodes are laid out such that the mapping cannot be accurate, boot will fail triggering BUG_ON() in mminit_verify_page_links(). On 32bit, it's 512MiB w/ PAE and SPARSEMEM. This seems to have been granular enough until commit 2706a0bf7b (x86, NUMA: Enable CONFIG_AMD_NUMA on 32bit too). Apparently, there is a machine which aligns NUMA nodes to 128MiB and has only AMD NUMA but not SRAT. This led to the following BUG_ON(). On node 0 totalpages: 2096615 DMA zone: 32 pages used for memmap DMA zone: 0 pages reserved DMA zone: 3927 pages, LIFO batch:0 Normal zone: 1740 pages used for memmap Normal zone: 220978 pages, LIFO batch:31 HighMem zone: 16405 pages used for memmap HighMem zone: 1853533 pages, LIFO batch:31 BUG: Int 6: CR2 (null) EDI (null) ESI 00000002 EBP 00000002 ESP c1543ecc EBX f2400000 EDX 00000006 ECX (null) EAX 00000001 err (null) EIP c16209aa CS 00000060 flg 00010002 Stack: f2400000 00220000 f7200800 c1620613 00220000 01000000 04400000 00238000 (null) f7200000 00000002 f7200b58 f7200800 c1620929 000375fe (null) f7200b80 c16395f0 00200a02 f7200a80 (null) 000375fe 00000002 (null) Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00181-g2706a0b #17 Call Trace: [<c136b1e5>] ? early_fault+0x2e/0x2e [<c16209aa>] ? mminit_verify_page_links+0x12/0x42 [<c1620613>] ? memmap_init_zone+0xaf/0x10c [<c1620929>] ? free_area_init_node+0x2b9/0x2e3 [<c1607e99>] ? free_area_init_nodes+0x3f2/0x451 [<c1601d80>] ? paging_init+0x112/0x118 [<c15f578d>] ? setup_arch+0x791/0x82f [<c15f43d9>] ? start_kernel+0x6a/0x257 This patch implements node_map_pfn_alignment() which determines maximum internode alignment and update numa_register_memblks() to reject NUMA configuration if alignment exceeds the pfn -> nid mapping granularity of the memory model as determined by PAGES_PER_SECTION. This makes the problematic machine boot w/ flatmem by rejecting the NUMA config and provides protection against crazy NUMA configurations. Signed-off-by: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/20110712074534.GB2872@htj.dyndns.org LKML-Reference: <20110628174613.GP478@escobedo.osrc.amd.com> Reported-and-Tested-by: Hans Rosenfeld <hans.rosenfeld@amd.com> Cc: Conny Seidel <conny.seidel@amd.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2011-07-12 15:45:34 +08:00
/*
* At very early time, the kernel have to use some memory such as
* loading the kernel image. We cannot prevent this anyway. So any
* node the kernel resides in should be un-hotpluggable.
*
* And when we come here, alloc node data won't fail.
*/
numa_clear_kernel_node_hotplug();
x86, numa: Implement pfn -> nid mapping granularity check SPARSEMEM w/o VMEMMAP and DISCONTIGMEM, both used only on 32bit, use sections array to map pfn to nid which is limited in granularity. If NUMA nodes are laid out such that the mapping cannot be accurate, boot will fail triggering BUG_ON() in mminit_verify_page_links(). On 32bit, it's 512MiB w/ PAE and SPARSEMEM. This seems to have been granular enough until commit 2706a0bf7b (x86, NUMA: Enable CONFIG_AMD_NUMA on 32bit too). Apparently, there is a machine which aligns NUMA nodes to 128MiB and has only AMD NUMA but not SRAT. This led to the following BUG_ON(). On node 0 totalpages: 2096615 DMA zone: 32 pages used for memmap DMA zone: 0 pages reserved DMA zone: 3927 pages, LIFO batch:0 Normal zone: 1740 pages used for memmap Normal zone: 220978 pages, LIFO batch:31 HighMem zone: 16405 pages used for memmap HighMem zone: 1853533 pages, LIFO batch:31 BUG: Int 6: CR2 (null) EDI (null) ESI 00000002 EBP 00000002 ESP c1543ecc EBX f2400000 EDX 00000006 ECX (null) EAX 00000001 err (null) EIP c16209aa CS 00000060 flg 00010002 Stack: f2400000 00220000 f7200800 c1620613 00220000 01000000 04400000 00238000 (null) f7200000 00000002 f7200b58 f7200800 c1620929 000375fe (null) f7200b80 c16395f0 00200a02 f7200a80 (null) 000375fe 00000002 (null) Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00181-g2706a0b #17 Call Trace: [<c136b1e5>] ? early_fault+0x2e/0x2e [<c16209aa>] ? mminit_verify_page_links+0x12/0x42 [<c1620613>] ? memmap_init_zone+0xaf/0x10c [<c1620929>] ? free_area_init_node+0x2b9/0x2e3 [<c1607e99>] ? free_area_init_nodes+0x3f2/0x451 [<c1601d80>] ? paging_init+0x112/0x118 [<c15f578d>] ? setup_arch+0x791/0x82f [<c15f43d9>] ? start_kernel+0x6a/0x257 This patch implements node_map_pfn_alignment() which determines maximum internode alignment and update numa_register_memblks() to reject NUMA configuration if alignment exceeds the pfn -> nid mapping granularity of the memory model as determined by PAGES_PER_SECTION. This makes the problematic machine boot w/ flatmem by rejecting the NUMA config and provides protection against crazy NUMA configurations. Signed-off-by: Tejun Heo <tj@kernel.org> Link: http://lkml.kernel.org/r/20110712074534.GB2872@htj.dyndns.org LKML-Reference: <20110628174613.GP478@escobedo.osrc.amd.com> Reported-and-Tested-by: Hans Rosenfeld <hans.rosenfeld@amd.com> Cc: Conny Seidel <conny.seidel@amd.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2011-07-12 15:45:34 +08:00
/*
* If sections array is gonna be used for pfn -> nid mapping, check
* whether its granularity is fine enough.
*/
#ifdef NODE_NOT_IN_PAGE_FLAGS
pfn_align = node_map_pfn_alignment();
if (pfn_align && pfn_align < PAGES_PER_SECTION) {
printk(KERN_WARNING "Node alignment %LuMB < min %LuMB, rejecting NUMA config\n",
PFN_PHYS(pfn_align) >> 20,
PFN_PHYS(PAGES_PER_SECTION) >> 20);
return -EINVAL;
}
#endif
if (!numa_meminfo_cover_memory(mi))
return -EINVAL;
/* Finally register nodes. */
for_each_node_mask(nid, node_possible_map) {
u64 start = PFN_PHYS(max_pfn);
u64 end = 0;
for (i = 0; i < mi->nr_blks; i++) {
if (nid != mi->blk[i].nid)
continue;
start = min(mi->blk[i].start, start);
end = max(mi->blk[i].end, end);
}
x86/mm/numa: Drop dead code and rename setup_node_data() to setup_alloc_data() The setup_node_data() function allocates a pg_data_t object, inserts it into the node_data[] array and initializes the following fields: node_id, node_start_pfn and node_spanned_pages. However, a few function calls later during the kernel boot, free_area_init_node() re-initializes those fields, possibly with setup_node_data() is not used. This causes a small glitch when running Linux as a hyperv numa guest: SRAT: PXM 0 -> APIC 0x00 -> Node 0 SRAT: PXM 0 -> APIC 0x01 -> Node 0 SRAT: PXM 1 -> APIC 0x02 -> Node 1 SRAT: PXM 1 -> APIC 0x03 -> Node 1 SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff] SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff] SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff] NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff] Initmem setup node 0 [mem 0x00000000-0x7fffffff] NODE_DATA [mem 0x7ffdc000-0x7ffeffff] Initmem setup node 1 [mem 0x80800000-0x1081fffff] NODE_DATA [mem 0x1081ea000-0x1081fdfff] crashkernel: memory value expected [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0 [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1 Zone ranges: DMA [mem 0x00001000-0x00ffffff] DMA32 [mem 0x01000000-0xffffffff] Normal [mem 0x100000000-0x1081fffff] Movable zone start for each node Early memory node ranges node 0: [mem 0x00001000-0x0009efff] node 0: [mem 0x00100000-0x7ffeffff] node 1: [mem 0x80200000-0xf7ffffff] node 1: [mem 0x100000000-0x1081fffff] On node 0 totalpages: 524174 DMA zone: 64 pages used for memmap DMA zone: 21 pages reserved DMA zone: 3998 pages, LIFO batch:0 DMA32 zone: 8128 pages used for memmap DMA32 zone: 520176 pages, LIFO batch:31 On node 1 totalpages: 524288 DMA32 zone: 7672 pages used for memmap DMA32 zone: 491008 pages, LIFO batch:31 Normal zone: 520 pages used for memmap Normal zone: 33280 pages, LIFO batch:7 In this dmesg, the SRAT table reports that the memory range for node 1 starts at 0x80200000. However, the line starting with "Initmem" reports that node 1 memory range starts at 0x80800000. The "Initmem" line is reported by setup_node_data() and is wrong, because the kernel ends up using the range as reported in the SRAT table. This commit drops all that dead code from setup_node_data(), renames it to alloc_node_data() and adds a printk() to free_area_init_node() so that we report a node's memory range accurately. Here's the same dmesg section with this patch applied: SRAT: PXM 0 -> APIC 0x00 -> Node 0 SRAT: PXM 0 -> APIC 0x01 -> Node 0 SRAT: PXM 1 -> APIC 0x02 -> Node 1 SRAT: PXM 1 -> APIC 0x03 -> Node 1 SRAT: Node 0 PXM 0 [mem 0x00000000-0x7fffffff] SRAT: Node 1 PXM 1 [mem 0x80200000-0xf7ffffff] SRAT: Node 1 PXM 1 [mem 0x100000000-0x1081fffff] NUMA: Node 1 [mem 0x80200000-0xf7ffffff] + [mem 0x100000000-0x1081fffff] -> [mem 0x80200000-0x1081fffff] NODE_DATA(0) allocated [mem 0x7ffdc000-0x7ffeffff] NODE_DATA(1) allocated [mem 0x1081ea000-0x1081fdfff] crashkernel: memory value expected [ffffea0000000000-ffffea0001ffffff] PMD -> [ffff88007de00000-ffff88007fdfffff] on node 0 [ffffea0002000000-ffffea00043fffff] PMD -> [ffff880105600000-ffff8801077fffff] on node 1 Zone ranges: DMA [mem 0x00001000-0x00ffffff] DMA32 [mem 0x01000000-0xffffffff] Normal [mem 0x100000000-0x1081fffff] Movable zone start for each node Early memory node ranges node 0: [mem 0x00001000-0x0009efff] node 0: [mem 0x00100000-0x7ffeffff] node 1: [mem 0x80200000-0xf7ffffff] node 1: [mem 0x100000000-0x1081fffff] Initmem setup node 0 [mem 0x00001000-0x7ffeffff] On node 0 totalpages: 524174 DMA zone: 64 pages used for memmap DMA zone: 21 pages reserved DMA zone: 3998 pages, LIFO batch:0 DMA32 zone: 8128 pages used for memmap DMA32 zone: 520176 pages, LIFO batch:31 Initmem setup node 1 [mem 0x80200000-0x1081fffff] On node 1 totalpages: 524288 DMA32 zone: 7672 pages used for memmap DMA32 zone: 491008 pages, LIFO batch:31 Normal zone: 520 pages used for memmap Normal zone: 33280 pages, LIFO batch:7 This commit was tested on a two node bare-metal NUMA machine and Linux as a numa guest on hyperv and qemu/kvm. PS: The wrong memory range reported by setup_node_data() seems to be harmless in the current kernel because it's just not used. However, that bad range is used in kernel 2.6.32 to initialize the old boot memory allocator, which causes a crash during boot. Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Rientjes <rientjes@google.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-23 04:27:36 +08:00
if (start >= end)
continue;
/*
* Don't confuse VM with a node that doesn't have the
* minimum amount of memory:
*/
if (end && (end - start) < NODE_MIN_SIZE)
continue;
alloc_node_data(nid);
}
/* Dump memblock with node info and return. */
memblock_dump_all();
return 0;
}
/*
* There are unfortunately some poorly designed mainboards around that
* only connect memory to a single CPU. This breaks the 1:1 cpu->node
* mapping. To avoid this fill in the mapping for all possible CPUs,
* as the number of CPUs is not known yet. We round robin the existing
* nodes.
*/
static void __init numa_init_array(void)
{
int rr, i;
rr = first_node(node_online_map);
for (i = 0; i < nr_cpu_ids; i++) {
if (early_cpu_to_node(i) != NUMA_NO_NODE)
continue;
numa_set_node(i, rr);
rr = next_node(rr, node_online_map);
if (rr == MAX_NUMNODES)
rr = first_node(node_online_map);
}
}
static int __init numa_init(int (*init_func)(void))
{
int i;
int ret;
for (i = 0; i < MAX_LOCAL_APIC; i++)
set_apicid_to_node(i, NUMA_NO_NODE);
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 <tim.gardner@canonical.com> Reported-by: Don Morris <don.morris@hp.com> Bisected-by: Don Morris <don.morris@hp.com> Tested-by: Don Morris <don.morris@hp.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Tejun Heo <tj@kernel.org> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-03-02 06:51:27 +08:00
nodes_clear(numa_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
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 <tim.gardner@canonical.com> Reported-by: Don Morris <don.morris@hp.com> Bisected-by: Don Morris <don.morris@hp.com> Tested-by: Don Morris <don.morris@hp.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Tejun Heo <tj@kernel.org> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-03-02 06:51:27 +08:00
memset(&numa_meminfo, 0, sizeof(numa_meminfo));
WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
MAX_NUMNODES));
acpi, numa, mem_hotplug: mark all nodes the kernel resides un-hotpluggable At very early time, the kernel have to use some memory such as loading the kernel image. We cannot prevent this anyway. So any node the kernel resides in should be un-hotpluggable. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Liu Jiang <jiang.liu@huawei.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:32 +08:00
WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
MAX_NUMNODES));
acpi, numa, mem_hotplug: mark hotpluggable memory in memblock When parsing SRAT, we know that which memory area is hotpluggable. So we invoke function memblock_mark_hotplug() introduced by previous patch to mark hotpluggable memory in memblock. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Liu Jiang <jiang.liu@huawei.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:29 +08:00
/* In case that parsing SRAT failed. */
WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
numa_reset_distance();
ret = init_func();
if (ret < 0)
return ret;
mem-hotplug: introduce movable_node boot option The hot-Pluggable field in SRAT specifies which memory is hotpluggable. As we mentioned before, if hotpluggable memory is used by the kernel, it cannot be hot-removed. So memory hotplug users may want to set all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use it. Memory hotplug users may also set a node as movable node, which has ZONE_MOVABLE only, so that the whole node can be hot-removed. But the kernel cannot use memory in ZONE_MOVABLE. By doing this, the kernel cannot use memory in movable nodes. This will cause NUMA performance down. And other users may be unhappy. So we need a way to allow users to enable and disable this functionality. In this patch, we introduce movable_node boot option to allow users to choose to not to consume hotpluggable memory at early boot time and later we can set it as ZONE_MOVABLE. To achieve this, the movable_node boot option will control the memblock allocation direction. That said, after memblock is ready, before SRAT is parsed, we should allocate memory near the kernel image as we explained in the previous patches. So if movable_node boot option is set, the kernel does the following: 1. After memblock is ready, make memblock allocate memory bottom up. 2. After SRAT is parsed, make memblock behave as default, allocate memory top down. Users can specify "movable_node" in kernel commandline to enable this functionality. For those who don't use memory hotplug or who don't want to lose their NUMA performance, just don't specify anything. The kernel will work as before. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Suggested-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:08:10 +08:00
/*
* We reset memblock back to the top-down direction
* here because if we configured ACPI_NUMA, we have
* parsed SRAT in init_func(). It is ok to have the
* reset here even if we did't configure ACPI_NUMA
* or acpi numa init fails and fallbacks to dummy
* numa init.
*/
memblock_set_bottom_up(false);
ret = numa_cleanup_meminfo(&numa_meminfo);
if (ret < 0)
return ret;
numa_emulation(&numa_meminfo, numa_distance_cnt);
ret = numa_register_memblks(&numa_meminfo);
if (ret < 0)
return ret;
for (i = 0; i < nr_cpu_ids; i++) {
int nid = early_cpu_to_node(i);
if (nid == NUMA_NO_NODE)
continue;
if (!node_online(nid))
numa_clear_node(i);
}
numa_init_array();
acpi, numa, mem_hotplug: mark all nodes the kernel resides un-hotpluggable At very early time, the kernel have to use some memory such as loading the kernel image. We cannot prevent this anyway. So any node the kernel resides in should be un-hotpluggable. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Liu Jiang <jiang.liu@huawei.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:32 +08:00
return 0;
}
/**
* dummy_numa_init - Fallback dummy NUMA init
*
* Used if there's no underlying NUMA architecture, NUMA initialization
* fails, or NUMA is disabled on the command line.
*
* Must online at least one node and add memory blocks that cover all
* allowed memory. This function must not fail.
*/
static int __init dummy_numa_init(void)
{
printk(KERN_INFO "%s\n",
numa_off ? "NUMA turned off" : "No NUMA configuration found");
printk(KERN_INFO "Faking a node at [mem %#018Lx-%#018Lx]\n",
0LLU, PFN_PHYS(max_pfn) - 1);
node_set(0, numa_nodes_parsed);
numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
return 0;
}
/**
* x86_numa_init - Initialize NUMA
*
* Try each configured NUMA initialization method until one succeeds. The
* last fallback is dummy single node config encomapssing whole memory and
* never fails.
*/
void __init x86_numa_init(void)
{
if (!numa_off) {
#ifdef CONFIG_ACPI_NUMA
if (!numa_init(x86_acpi_numa_init))
return;
#endif
#ifdef CONFIG_AMD_NUMA
if (!numa_init(amd_numa_init))
return;
#endif
}
numa_init(dummy_numa_init);
}
static __init int find_near_online_node(int node)
{
int n, val;
int min_val = INT_MAX;
int best_node = -1;
for_each_online_node(n) {
val = node_distance(node, n);
if (val < min_val) {
min_val = val;
best_node = n;
}
}
return best_node;
}
/*
* Setup early cpu_to_node.
*
* Populate cpu_to_node[] only if x86_cpu_to_apicid[],
* and apicid_to_node[] tables have valid entries for a CPU.
* This means we skip cpu_to_node[] initialisation for NUMA
* emulation and faking node case (when running a kernel compiled
* for NUMA on a non NUMA box), which is OK as cpu_to_node[]
* is already initialized in a round robin manner at numa_init_array,
* prior to this call, and this initialization is good enough
* for the fake NUMA cases.
*
* Called before the per_cpu areas are setup.
*/
void __init init_cpu_to_node(void)
{
int cpu;
u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
BUG_ON(cpu_to_apicid == NULL);
for_each_possible_cpu(cpu) {
int node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
continue;
if (!node_online(node))
node = find_near_online_node(node);
numa_set_node(cpu, node);
}
}
#ifndef CONFIG_DEBUG_PER_CPU_MAPS
# ifndef CONFIG_NUMA_EMU
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 06:23:59 +08:00
void numa_add_cpu(int cpu)
{
cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 06:23:59 +08:00
void numa_remove_cpu(int cpu)
{
cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
# endif /* !CONFIG_NUMA_EMU */
#else /* !CONFIG_DEBUG_PER_CPU_MAPS */
int __cpu_to_node(int cpu)
{
if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
printk(KERN_WARNING
"cpu_to_node(%d): usage too early!\n", cpu);
dump_stack();
return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
}
return per_cpu(x86_cpu_to_node_map, cpu);
}
EXPORT_SYMBOL(__cpu_to_node);
/*
* Same function as cpu_to_node() but used if called before the
* per_cpu areas are setup.
*/
int early_cpu_to_node(int cpu)
{
if (early_per_cpu_ptr(x86_cpu_to_node_map))
return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
if (!cpu_possible(cpu)) {
printk(KERN_WARNING
"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
dump_stack();
return NUMA_NO_NODE;
}
return per_cpu(x86_cpu_to_node_map, cpu);
}
void debug_cpumask_set_cpu(int cpu, int node, bool enable)
{
struct cpumask *mask;
if (node == NUMA_NO_NODE) {
/* early_cpu_to_node() already emits a warning and trace */
return;
}
mask = node_to_cpumask_map[node];
if (!mask) {
pr_err("node_to_cpumask_map[%i] NULL\n", node);
dump_stack();
return;
}
if (enable)
cpumask_set_cpu(cpu, mask);
else
cpumask_clear_cpu(cpu, mask);
printk(KERN_DEBUG "%s cpu %d node %d: mask now %*pbl\n",
enable ? "numa_add_cpu" : "numa_remove_cpu",
cpu, node, cpumask_pr_args(mask));
return;
}
# ifndef CONFIG_NUMA_EMU
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 06:23:59 +08:00
static void numa_set_cpumask(int cpu, bool enable)
{
debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 06:23:59 +08:00
void numa_add_cpu(int cpu)
{
numa_set_cpumask(cpu, true);
}
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 06:23:59 +08:00
void numa_remove_cpu(int cpu)
{
numa_set_cpumask(cpu, false);
}
# endif /* !CONFIG_NUMA_EMU */
/*
* Returns a pointer to the bitmask of CPUs on Node 'node'.
*/
const struct cpumask *cpumask_of_node(int node)
{
if (node >= nr_node_ids) {
printk(KERN_WARNING
"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
node, nr_node_ids);
dump_stack();
return cpu_none_mask;
}
if (node_to_cpumask_map[node] == NULL) {
printk(KERN_WARNING
"cpumask_of_node(%d): no node_to_cpumask_map!\n",
node);
dump_stack();
return cpu_online_mask;
}
return node_to_cpumask_map[node];
}
EXPORT_SYMBOL(cpumask_of_node);
#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
#ifdef CONFIG_MEMORY_HOTPLUG
int memory_add_physaddr_to_nid(u64 start)
{
struct numa_meminfo *mi = &numa_meminfo;
int nid = mi->blk[0].nid;
int i;
for (i = 0; i < mi->nr_blks; i++)
if (mi->blk[i].start <= start && mi->blk[i].end > start)
nid = mi->blk[i].nid;
return nid;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif