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

207 lines
5.0 KiB
C
Raw Normal View History

/*
* ACPI 3.0 based NUMA setup
* Copyright 2004 Andi Kleen, SuSE Labs.
*
* Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
*
* Called from acpi_numa_init while reading the SRAT and SLIT tables.
* Assumes all memory regions belonging to a single proximity domain
* are in one chunk. Holes between them will be included in the node.
*/
#include <linux/kernel.h>
#include <linux/acpi.h>
#include <linux/mmzone.h>
#include <linux/bitmap.h>
#include <linux/module.h>
#include <linux/topology.h>
[PATCH] x86_64: Reserve SRAT hotadd memory on x86-64 From: Keith Mannthey, Andi Kleen Implement memory hotadd without sparsemem. The memory in the SRAT hotadd area is just preserved instead and can be activated later. There are a few restrictions: - Only one continuous hotadd area allowed per node The main problem is dealing with the many buggy SRAT tables that are out there. The strategy here is to reject anything suspicious. Originally from Keith Mannthey, with several hacks and changes by AK and also contributions from Andrew Morton [ TBD: Problems pointed out by KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>: 1) Goto's rebuild_zonelist patch will not work if CONFIG_MEMORY_HOTPLUG=n. Rebuilding zonelist is necessary when the system has just memory < 4G at boot, and hot add memory > 4G. because x86_64 has DMA32, ZONE_NORAML is not included into zonelist at boot time if system doesn't have memory >4G at boot. [AK: should just force the higher zones at boot time when SRAT tells us] 2) zone and node's spanned_pages and present_pages are not incremented. They should be. For example, our server (ia64/Fujitsu PrimeQuest) can equip memory from 4G to 1T(maybe 2T in future), and SRAT will *always* say we have possible 1T +memory. (Microsoft requires "write all possible memory in SRAT") When we reserve memmap for possible 1T memory, Linux will not work well in +minimum 4G configuraion ;) [AK: needs limiting to 5-10% of max memory] ] Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-08 01:49:18 +08:00
#include <linux/bootmem.h>
#include <linux/memblock.h>
[PATCH] x86_64: Reserve SRAT hotadd memory on x86-64 From: Keith Mannthey, Andi Kleen Implement memory hotadd without sparsemem. The memory in the SRAT hotadd area is just preserved instead and can be activated later. There are a few restrictions: - Only one continuous hotadd area allowed per node The main problem is dealing with the many buggy SRAT tables that are out there. The strategy here is to reject anything suspicious. Originally from Keith Mannthey, with several hacks and changes by AK and also contributions from Andrew Morton [ TBD: Problems pointed out by KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>: 1) Goto's rebuild_zonelist patch will not work if CONFIG_MEMORY_HOTPLUG=n. Rebuilding zonelist is necessary when the system has just memory < 4G at boot, and hot add memory > 4G. because x86_64 has DMA32, ZONE_NORAML is not included into zonelist at boot time if system doesn't have memory >4G at boot. [AK: should just force the higher zones at boot time when SRAT tells us] 2) zone and node's spanned_pages and present_pages are not incremented. They should be. For example, our server (ia64/Fujitsu PrimeQuest) can equip memory from 4G to 1T(maybe 2T in future), and SRAT will *always* say we have possible 1T +memory. (Microsoft requires "write all possible memory in SRAT") When we reserve memmap for possible 1T memory, Linux will not work well in +minimum 4G configuraion ;) [AK: needs limiting to 5-10% of max memory] ] Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-08 01:49:18 +08:00
#include <linux/mm.h>
#include <asm/proto.h>
#include <asm/numa.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/uv/uv.h>
int acpi_numa __initdata;
static __init int setup_node(int pxm)
{
return acpi_map_pxm_to_node(pxm);
}
static __init void bad_srat(void)
{
printk(KERN_ERR "SRAT: SRAT not used.\n");
acpi_numa = -1;
}
static __init inline int srat_disabled(void)
{
return acpi_numa < 0;
}
/* Callback for SLIT parsing */
void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
{
int i, j;
for (i = 0; i < slit->locality_count; i++)
for (j = 0; j < slit->locality_count; j++)
numa_set_distance(pxm_to_node(i), pxm_to_node(j),
slit->entry[slit->locality_count * i + j]);
}
/* Callback for Proximity Domain -> x2APIC mapping */
void __init
acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
{
int pxm, node;
int apic_id;
if (srat_disabled())
return;
if (pa->header.length < sizeof(struct acpi_srat_x2apic_cpu_affinity)) {
bad_srat();
return;
}
if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
return;
pxm = pa->proximity_domain;
apic_id = pa->apic_id;
if (!apic->apic_id_valid(apic_id)) {
printk(KERN_INFO "SRAT: PXM %u -> X2APIC 0x%04x ignored\n",
pxm, apic_id);
return;
}
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
bad_srat();
return;
}
x86, acpi: Parse all SRAT cpu entries even above the cpu number limitation Recent Intel new system have different order in MADT, aka will list all thread0 at first, then all thread1. But SRAT table still old order, it will list cpus in one socket all together. If the user have compiled limited NR_CPUS or boot with nr_cpus=, could have missed to put some cpus apic id to node mapping into apicid_to_node[]. for example for 4 sockets system with 64 cpus with nr_cpus=32 will get crash... [ 9.106288] Total of 32 processors activated (136190.88 BogoMIPS). [ 9.235021] divide error: 0000 [#1] SMP [ 9.235315] last sysfs file: [ 9.235481] CPU 1 [ 9.235592] Modules linked in: [ 9.245398] [ 9.245478] Pid: 2, comm: kthreadd Not tainted 2.6.37-rc1-tip-yh-01782-ge92ef79-dirty #274 /Sun Fire x4800 [ 9.265415] RIP: 0010:[<ffffffff81075a8f>] [<ffffffff81075a8f>] select_task_rq_fair+0x4f0/0x623 ... [ 9.645938] RIP [<ffffffff81075a8f>] select_task_rq_fair+0x4f0/0x623 [ 9.665356] RSP <ffff88103f8d1c40> [ 9.665568] ---[ end trace 2296156d35fdfc87 ]--- So let just parse all cpu entries in SRAT. Also add apicid checking with MAX_LOCAL_APIC, in case We could out of boundaries of apicid_to_node[]. it fixes following bug too. https://bugzilla.kernel.org/show_bug.cgi?id=22662 -v2: expand to 32bit according to hpa need to add MAX_LOCAL_APIC for 32bit Reported-and-Tested-by: Wu Fengguang <fengguang.wu@intel.com> Reported-by: Bjorn Helgaas <bjorn.helgaas@hp.com> Tested-by: Myron Stowe <myron.stowe@hp.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0AD486.9020704@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-17 11:09:58 +08:00
if (apic_id >= MAX_LOCAL_APIC) {
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
return;
}
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
acpi_numa = 1;
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
pxm, apic_id, node);
}
/* Callback for Proximity Domain -> LAPIC mapping */
void __init
acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
{
int pxm, node;
int apic_id;
if (srat_disabled())
return;
if (pa->header.length != sizeof(struct acpi_srat_cpu_affinity)) {
bad_srat();
return;
}
if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
return;
pxm = pa->proximity_domain_lo;
if (acpi_srat_revision >= 2)
pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
bad_srat();
return;
}
if (get_uv_system_type() >= UV_X2APIC)
apic_id = (pa->apic_id << 8) | pa->local_sapic_eid;
else
apic_id = pa->apic_id;
x86, acpi: Parse all SRAT cpu entries even above the cpu number limitation Recent Intel new system have different order in MADT, aka will list all thread0 at first, then all thread1. But SRAT table still old order, it will list cpus in one socket all together. If the user have compiled limited NR_CPUS or boot with nr_cpus=, could have missed to put some cpus apic id to node mapping into apicid_to_node[]. for example for 4 sockets system with 64 cpus with nr_cpus=32 will get crash... [ 9.106288] Total of 32 processors activated (136190.88 BogoMIPS). [ 9.235021] divide error: 0000 [#1] SMP [ 9.235315] last sysfs file: [ 9.235481] CPU 1 [ 9.235592] Modules linked in: [ 9.245398] [ 9.245478] Pid: 2, comm: kthreadd Not tainted 2.6.37-rc1-tip-yh-01782-ge92ef79-dirty #274 /Sun Fire x4800 [ 9.265415] RIP: 0010:[<ffffffff81075a8f>] [<ffffffff81075a8f>] select_task_rq_fair+0x4f0/0x623 ... [ 9.645938] RIP [<ffffffff81075a8f>] select_task_rq_fair+0x4f0/0x623 [ 9.665356] RSP <ffff88103f8d1c40> [ 9.665568] ---[ end trace 2296156d35fdfc87 ]--- So let just parse all cpu entries in SRAT. Also add apicid checking with MAX_LOCAL_APIC, in case We could out of boundaries of apicid_to_node[]. it fixes following bug too. https://bugzilla.kernel.org/show_bug.cgi?id=22662 -v2: expand to 32bit according to hpa need to add MAX_LOCAL_APIC for 32bit Reported-and-Tested-by: Wu Fengguang <fengguang.wu@intel.com> Reported-by: Bjorn Helgaas <bjorn.helgaas@hp.com> Tested-by: Myron Stowe <myron.stowe@hp.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4D0AD486.9020704@kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-12-17 11:09:58 +08:00
if (apic_id >= MAX_LOCAL_APIC) {
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
return;
}
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
acpi_numa = 1;
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
pxm, apic_id, node);
}
#ifdef CONFIG_MEMORY_HOTPLUG
static inline int save_add_info(void) {return 1;}
#else
static inline int save_add_info(void) {return 0;}
#endif
[PATCH] x86_64: Reserve SRAT hotadd memory on x86-64 From: Keith Mannthey, Andi Kleen Implement memory hotadd without sparsemem. The memory in the SRAT hotadd area is just preserved instead and can be activated later. There are a few restrictions: - Only one continuous hotadd area allowed per node The main problem is dealing with the many buggy SRAT tables that are out there. The strategy here is to reject anything suspicious. Originally from Keith Mannthey, with several hacks and changes by AK and also contributions from Andrew Morton [ TBD: Problems pointed out by KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>: 1) Goto's rebuild_zonelist patch will not work if CONFIG_MEMORY_HOTPLUG=n. Rebuilding zonelist is necessary when the system has just memory < 4G at boot, and hot add memory > 4G. because x86_64 has DMA32, ZONE_NORAML is not included into zonelist at boot time if system doesn't have memory >4G at boot. [AK: should just force the higher zones at boot time when SRAT tells us] 2) zone and node's spanned_pages and present_pages are not incremented. They should be. For example, our server (ia64/Fujitsu PrimeQuest) can equip memory from 4G to 1T(maybe 2T in future), and SRAT will *always* say we have possible 1T +memory. (Microsoft requires "write all possible memory in SRAT") When we reserve memmap for possible 1T memory, Linux will not work well in +minimum 4G configuraion ;) [AK: needs limiting to 5-10% of max memory] ] Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-08 01:49:18 +08:00
/* 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())
goto out_err;
if (ma->header.length != sizeof(struct acpi_srat_mem_affinity))
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())
goto out_err;
start = ma->base_address;
end = start + ma->length;
pxm = ma->proximity_domain;
if (acpi_srat_revision <= 1)
pxm &= 0xff;
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains.\n");
goto out_err_bad_srat;
}
if (numa_add_memblk(node, start, end) < 0)
goto out_err_bad_srat;
[PATCH] x86_64: Reserve SRAT hotadd memory on x86-64 From: Keith Mannthey, Andi Kleen Implement memory hotadd without sparsemem. The memory in the SRAT hotadd area is just preserved instead and can be activated later. There are a few restrictions: - Only one continuous hotadd area allowed per node The main problem is dealing with the many buggy SRAT tables that are out there. The strategy here is to reject anything suspicious. Originally from Keith Mannthey, with several hacks and changes by AK and also contributions from Andrew Morton [ TBD: Problems pointed out by KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>: 1) Goto's rebuild_zonelist patch will not work if CONFIG_MEMORY_HOTPLUG=n. Rebuilding zonelist is necessary when the system has just memory < 4G at boot, and hot add memory > 4G. because x86_64 has DMA32, ZONE_NORAML is not included into zonelist at boot time if system doesn't have memory >4G at boot. [AK: should just force the higher zones at boot time when SRAT tells us] 2) zone and node's spanned_pages and present_pages are not incremented. They should be. For example, our server (ia64/Fujitsu PrimeQuest) can equip memory from 4G to 1T(maybe 2T in future), and SRAT will *always* say we have possible 1T +memory. (Microsoft requires "write all possible memory in SRAT") When we reserve memmap for possible 1T memory, Linux will not work well in +minimum 4G configuraion ;) [AK: needs limiting to 5-10% of max memory] ] Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-08 01:49:18 +08:00
x86/numa: Set numa_nodes_parsed at acpi_numa_memory_affinity_init() When hot-adding a CPU, the system outputs following messages since node_to_cpumask_map[2] was not allocated memory. Booting Node 2 Processor 32 APIC 0xc0 node_to_cpumask_map[2] NULL Pid: 0, comm: swapper/32 Tainted: G A 3.3.5-acd #21 Call Trace: [<ffffffff81048845>] debug_cpumask_set_cpu+0x155/0x160 [<ffffffff8105e28a>] ? add_timer_on+0xaa/0x120 [<ffffffff8150665f>] numa_add_cpu+0x1e/0x22 [<ffffffff815020bb>] identify_cpu+0x1df/0x1e4 [<ffffffff815020d6>] identify_econdary_cpu+0x16/0x1d [<ffffffff81504614>] smp_store_cpu_info+0x3c/0x3e [<ffffffff81505263>] smp_callin+0x139/0x1be [<ffffffff815052fb>] start_secondary+0x13/0xeb The reason is that the bit of node 2 was not set at numa_nodes_parsed. numa_nodes_parsed is set by only acpi_numa_processor_affinity_init / acpi_numa_x2apic_affinity_init. Thus even if hot-added memory which is same PXM as hot-added CPU is written in ACPI SRAT Table, if the hot-added CPU is not written in ACPI SRAT table, numa_nodes_parsed is not set. But according to ACPI Spec Rev 5.0, it says about ACPI SRAT table as follows: This optional table provides information that allows OSPM to associate processors and memory ranges, including ranges of memory provided by hot-added memory devices, with system localities / proximity domains and clock domains. It means that ACPI SRAT table only provides information for CPUs present at boot time and for memory including hot-added memory. So hot-added memory is written in ACPI SRAT table, but hot-added CPU is not written in it. Thus numa_nodes_parsed should be set by not only acpi_numa_processor_affinity_init / acpi_numa_x2apic_affinity_init but also acpi_numa_memory_affinity_init for the case. Additionally, if system has cpuless memory node, acpi_numa_processor_affinity_init / acpi_numa_x2apic_affinity_init cannot set numa_nodes_parseds since these functions cannot find cpu description for the node. In this case, numa_nodes_parsed needs to be set by acpi_numa_memory_affinity_init. Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: liuj97@gmail.com Cc: kosaki.motohiro@gmail.com Link: http://lkml.kernel.org/r/4FCC2098.4030007@jp.fujitsu.com [ merged it ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-04 10:42:32 +08:00
node_set(node, numa_nodes_parsed);
pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n",
node, pxm,
(unsigned long long) start, (unsigned long long) end - 1,
hotpluggable ? " hotplug" : "");
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
/* Mark hotplug range in memblock. */
if (hotpluggable && memblock_mark_hotplug(start, ma->length))
pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
(unsigned long long)start, (unsigned long long)end - 1);
return 0;
out_err_bad_srat:
bad_srat();
out_err:
return -1;
}
void __init acpi_numa_arch_fixup(void) {}
int __init x86_acpi_numa_init(void)
{
int ret;
ret = acpi_numa_init();
if (ret < 0)
return ret;
return srat_disabled() ? -EINVAL : 0;
}