1
0
Fork 0
alistair23-linux/drivers/acpi/numa.c

490 lines
12 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157 Based on 3 normalized pattern(s): this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [graeme] [gregory] [gg]@[slimlogic] [co] [uk] [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] [based] [on] [twl6030]_[usb] [c] [author] [hema] [hk] [hemahk]@[ti] [com] this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details extracted by the scancode license scanner the SPDX license identifier GPL-2.0-or-later has been chosen to replace the boilerplate/reference in 1105 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Allison Randal <allison@lohutok.net> Reviewed-by: Richard Fontana <rfontana@redhat.com> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190527070033.202006027@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-27 00:55:06 -06:00
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* acpi_numa.c - ACPI NUMA support
*
* Copyright (C) 2002 Takayoshi Kochi <t-kochi@bq.jp.nec.com>
*/
#define pr_fmt(fmt) "ACPI: " fmt
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/acpi.h>
#include <linux/memblock.h>
#include <linux/numa.h>
#include <linux/nodemask.h>
#include <linux/topology.h>
static nodemask_t nodes_found_map = NODE_MASK_NONE;
/* maps to convert between proximity domain and logical node ID */
static int pxm_to_node_map[MAX_PXM_DOMAINS]
= { [0 ... MAX_PXM_DOMAINS - 1] = NUMA_NO_NODE };
static int node_to_pxm_map[MAX_NUMNODES]
= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
unsigned char acpi_srat_revision __initdata;
int acpi_numa __initdata;
int pxm_to_node(int pxm)
{
if (pxm < 0)
return NUMA_NO_NODE;
return pxm_to_node_map[pxm];
}
int node_to_pxm(int node)
{
if (node < 0)
return PXM_INVAL;
return node_to_pxm_map[node];
}
static void __acpi_map_pxm_to_node(int pxm, int node)
{
if (pxm_to_node_map[pxm] == NUMA_NO_NODE || node < pxm_to_node_map[pxm])
pxm_to_node_map[pxm] = node;
if (node_to_pxm_map[node] == PXM_INVAL || pxm < node_to_pxm_map[node])
node_to_pxm_map[node] = pxm;
}
int acpi_map_pxm_to_node(int pxm)
{
int node;
if (pxm < 0 || pxm >= MAX_PXM_DOMAINS || numa_off)
return NUMA_NO_NODE;
node = pxm_to_node_map[pxm];
if (node == NUMA_NO_NODE) {
if (nodes_weight(nodes_found_map) >= MAX_NUMNODES)
return NUMA_NO_NODE;
node = first_unset_node(nodes_found_map);
__acpi_map_pxm_to_node(pxm, node);
node_set(node, nodes_found_map);
}
return node;
}
acpi/nfit, device-dax: Identify differentiated memory with a unique numa-node Persistent memory, as described by the ACPI NFIT (NVDIMM Firmware Interface Table), is the first known instance of a memory range described by a unique "target" proximity domain. Where "initiator" and "target" proximity domains is an approach that the ACPI HMAT (Heterogeneous Memory Attributes Table) uses to described the unique performance properties of a memory range relative to a given initiator (e.g. CPU or DMA device). Currently the numa-node for a /dev/pmemX block-device or /dev/daxX.Y char-device follows the traditional notion of 'numa-node' where the attribute conveys the closest online numa-node. That numa-node attribute is useful for cpu-binding and memory-binding processes *near* the device. However, when the memory range backing a 'pmem', or 'dax' device is onlined (memory hot-add) the memory-only-numa-node representing that address needs to be differentiated from the set of online nodes. In other words, the numa-node association of the device depends on whether you can bind processes *near* the cpu-numa-node in the offline device-case, or bind process *on* the memory-range directly after the backing address range is onlined. Allow for the case that platform firmware describes persistent memory with a unique proximity domain, i.e. when it is distinct from the proximity of DRAM and CPUs that are on the same socket. Plumb the Linux numa-node translation of that proximity through the libnvdimm region device to namespaces that are in device-dax mode. With this in place the proposed kmem driver [1] can optionally discover a unique numa-node number for the address range as it transitions the memory from an offline state managed by a device-driver to an online memory range managed by the core-mm. [1]: https://lore.kernel.org/lkml/20181022201317.8558C1D8@viggo.jf.intel.com Reported-by: Fan Du <fan.du@intel.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Oliver O'Halloran" <oohall@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2018-11-09 13:43:07 -07:00
EXPORT_SYMBOL(acpi_map_pxm_to_node);
/**
* acpi_map_pxm_to_online_node - Map proximity ID to online node
* @pxm: ACPI proximity ID
*
* This is similar to acpi_map_pxm_to_node(), but always returns an online
* node. When the mapped node from a given proximity ID is offline, it
* looks up the node distance table and returns the nearest online node.
*
* ACPI device drivers, which are called after the NUMA initialization has
* completed in the kernel, can call this interface to obtain their device
* NUMA topology from ACPI tables. Such drivers do not have to deal with
* offline nodes. A node may be offline when a device proximity ID is
* unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
* "numa=off" on x86.
*/
int acpi_map_pxm_to_online_node(int pxm)
{
int node, min_node;
node = acpi_map_pxm_to_node(pxm);
if (node == NUMA_NO_NODE)
node = 0;
min_node = node;
if (!node_online(node)) {
int min_dist = INT_MAX, dist, n;
for_each_online_node(n) {
dist = node_distance(node, n);
if (dist < min_dist) {
min_dist = dist;
min_node = n;
}
}
}
return min_node;
}
EXPORT_SYMBOL(acpi_map_pxm_to_online_node);
static void __init
acpi_table_print_srat_entry(struct acpi_subtable_header *header)
{
switch (header->type) {
case ACPI_SRAT_TYPE_CPU_AFFINITY:
{
struct acpi_srat_cpu_affinity *p =
(struct acpi_srat_cpu_affinity *)header;
pr_debug("SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
p->apic_id, p->local_sapic_eid,
p->proximity_domain_lo,
(p->flags & ACPI_SRAT_CPU_ENABLED) ?
"enabled" : "disabled");
}
break;
case ACPI_SRAT_TYPE_MEMORY_AFFINITY:
{
struct acpi_srat_mem_affinity *p =
(struct acpi_srat_mem_affinity *)header;
ACPI: NUMA: Use correct type for printing addresses on i386-PAE The addresses of NUMA nodes are not printed correctly on i386-PAE which is misleading. Here is a debian9-32bit with PAE in a QEMU guest having more than 4G of memory: qemu-system-i386 \ -hda /var/lib/libvirt/images/debian32.qcow2 \ -m 5G \ -enable-kvm \ -smp 10 \ -numa node,mem=512M,nodeid=0,cpus=0 \ -numa node,mem=512M,nodeid=1,cpus=1 \ -numa node,mem=512M,nodeid=2,cpus=2 \ -numa node,mem=512M,nodeid=3,cpus=3 \ -numa node,mem=512M,nodeid=4,cpus=4 \ -numa node,mem=512M,nodeid=5,cpus=5 \ -numa node,mem=512M,nodeid=6,cpus=6 \ -numa node,mem=512M,nodeid=7,cpus=7 \ -numa node,mem=512M,nodeid=8,cpus=8 \ -numa node,mem=512M,nodeid=9,cpus=9 \ -serial stdio Because of the wrong value type, it prints as below: [ 0.021049] ACPI: SRAT Memory (0x0 length 0xa0000) in proximity domain 0 enabled [ 0.021740] ACPI: SRAT Memory (0x100000 length 0x1ff00000) in proximity domain 0 enabled [ 0.022425] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 1 enabled [ 0.023092] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 2 enabled [ 0.023764] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 3 enabled [ 0.024431] ACPI: SRAT Memory (0x80000000 length 0x20000000) in proximity domain 4 enabled [ 0.025104] ACPI: SRAT Memory (0xa0000000 length 0x20000000) in proximity domain 5 enabled [ 0.025791] ACPI: SRAT Memory (0x0 length 0x20000000) in proximity domain 6 enabled [ 0.026412] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 7 enabled [ 0.027118] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 8 enabled [ 0.027802] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 9 enabled The upper half of the start address of the NUMA domains between 6 and 9 inclusive was cut, so the printed values are incorrect. Fix the value type, to get the correct values in the log as follows: [ 0.023698] ACPI: SRAT Memory (0x0 length 0xa0000) in proximity domain 0 enabled [ 0.024325] ACPI: SRAT Memory (0x100000 length 0x1ff00000) in proximity domain 0 enabled [ 0.024981] ACPI: SRAT Memory (0x20000000 length 0x20000000) in proximity domain 1 enabled [ 0.025659] ACPI: SRAT Memory (0x40000000 length 0x20000000) in proximity domain 2 enabled [ 0.026317] ACPI: SRAT Memory (0x60000000 length 0x20000000) in proximity domain 3 enabled [ 0.026980] ACPI: SRAT Memory (0x80000000 length 0x20000000) in proximity domain 4 enabled [ 0.027635] ACPI: SRAT Memory (0xa0000000 length 0x20000000) in proximity domain 5 enabled [ 0.028311] ACPI: SRAT Memory (0x100000000 length 0x20000000) in proximity domain 6 enabled [ 0.028985] ACPI: SRAT Memory (0x120000000 length 0x20000000) in proximity domain 7 enabled [ 0.029667] ACPI: SRAT Memory (0x140000000 length 0x20000000) in proximity domain 8 enabled [ 0.030334] ACPI: SRAT Memory (0x160000000 length 0x20000000) in proximity domain 9 enabled Signed-off-by: Chao Fan <fanc.fnst@cn.fujitsu.com> [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2018-12-25 20:34:50 -07:00
pr_debug("SRAT Memory (0x%llx length 0x%llx) in proximity domain %d %s%s%s\n",
(unsigned long long)p->base_address,
(unsigned long long)p->length,
p->proximity_domain,
(p->flags & ACPI_SRAT_MEM_ENABLED) ?
"enabled" : "disabled",
(p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
" hot-pluggable" : "",
(p->flags & ACPI_SRAT_MEM_NON_VOLATILE) ?
" non-volatile" : "");
}
break;
case ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY:
{
struct acpi_srat_x2apic_cpu_affinity *p =
(struct acpi_srat_x2apic_cpu_affinity *)header;
pr_debug("SRAT Processor (x2apicid[0x%08x]) in proximity domain %d %s\n",
p->apic_id,
p->proximity_domain,
(p->flags & ACPI_SRAT_CPU_ENABLED) ?
"enabled" : "disabled");
}
break;
case ACPI_SRAT_TYPE_GICC_AFFINITY:
{
struct acpi_srat_gicc_affinity *p =
(struct acpi_srat_gicc_affinity *)header;
pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
p->acpi_processor_uid,
p->proximity_domain,
(p->flags & ACPI_SRAT_GICC_ENABLED) ?
"enabled" : "disabled");
}
break;
default:
pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
header->type);
break;
}
}
/*
* A lot of BIOS fill in 10 (= no distance) everywhere. This messes
* up the NUMA heuristics which wants the local node to have a smaller
* distance than the others.
* Do some quick checks here and only use the SLIT if it passes.
*/
static int __init slit_valid(struct acpi_table_slit *slit)
{
int i, j;
int d = slit->locality_count;
for (i = 0; i < d; i++) {
for (j = 0; j < d; j++) {
u8 val = slit->entry[d*i + j];
if (i == j) {
if (val != LOCAL_DISTANCE)
return 0;
} else if (val <= LOCAL_DISTANCE)
return 0;
}
}
return 1;
}
void __init bad_srat(void)
{
pr_err("SRAT: SRAT not used.\n");
acpi_numa = -1;
}
int __init srat_disabled(void)
{
return acpi_numa < 0;
}
#if defined(CONFIG_X86) || defined(CONFIG_ARM64)
/*
* Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for
* I/O localities since SRAT does not list them. I/O localities are
* not supported at this point.
*/
void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
{
int i, j;
for (i = 0; i < slit->locality_count; i++) {
const int from_node = pxm_to_node(i);
if (from_node == NUMA_NO_NODE)
continue;
for (j = 0; j < slit->locality_count; j++) {
const int to_node = pxm_to_node(j);
if (to_node == NUMA_NO_NODE)
continue;
numa_set_distance(from_node, to_node,
slit->entry[slit->locality_count * i + j]);
}
}
}
/*
* Default 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)) {
pr_err("SRAT: Unexpected header length: %d\n",
ma->header.length);
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 && !IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
goto out_err;
start = ma->base_address;
end = start + ma->length;
pxm = ma->proximity_domain;
if (acpi_srat_revision <= 1)
pxm &= 0xff;
node = acpi_map_pxm_to_node(pxm);
if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
pr_err("SRAT: Too many proximity domains.\n");
goto out_err_bad_srat;
}
if (numa_add_memblk(node, start, end) < 0) {
pr_err("SRAT: Failed to add memblk to node %u [mem %#010Lx-%#010Lx]\n",
node, (unsigned long long) start,
(unsigned long long) end - 1);
goto out_err_bad_srat;
}
node_set(node, numa_nodes_parsed);
pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n",
node, pxm,
(unsigned long long) start, (unsigned long long) end - 1,
hotpluggable ? " hotplug" : "",
ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : "");
/* 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);
max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
return 0;
out_err_bad_srat:
bad_srat();
out_err:
return -EINVAL;
}
#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
static int __init acpi_parse_slit(struct acpi_table_header *table)
{
struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
if (!slit_valid(slit)) {
pr_info("SLIT table looks invalid. Not used.\n");
return -EINVAL;
}
acpi_numa_slit_init(slit);
return 0;
}
void __init __weak
acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
{
pr_warn("Found unsupported x2apic [0x%08x] SRAT entry\n", pa->apic_id);
}
static int __init
acpi_parse_x2apic_affinity(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_srat_x2apic_cpu_affinity *processor_affinity;
processor_affinity = (struct acpi_srat_x2apic_cpu_affinity *)header;
if (!processor_affinity)
return -EINVAL;
acpi_table_print_srat_entry(&header->common);
/* let architecture-dependent part to do it */
acpi_numa_x2apic_affinity_init(processor_affinity);
return 0;
}
static int __init
acpi_parse_processor_affinity(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_srat_cpu_affinity *processor_affinity;
processor_affinity = (struct acpi_srat_cpu_affinity *)header;
if (!processor_affinity)
return -EINVAL;
acpi_table_print_srat_entry(&header->common);
/* let architecture-dependent part to do it */
acpi_numa_processor_affinity_init(processor_affinity);
return 0;
}
static int __init
acpi_parse_gicc_affinity(union acpi_subtable_headers *header,
const unsigned long end)
{
struct acpi_srat_gicc_affinity *processor_affinity;
processor_affinity = (struct acpi_srat_gicc_affinity *)header;
if (!processor_affinity)
return -EINVAL;
acpi_table_print_srat_entry(&header->common);
/* let architecture-dependent part to do it */
acpi_numa_gicc_affinity_init(processor_affinity);
return 0;
}
static int __initdata parsed_numa_memblks;
static int __init
acpi_parse_memory_affinity(union acpi_subtable_headers * header,
const unsigned long end)
{
struct acpi_srat_mem_affinity *memory_affinity;
memory_affinity = (struct acpi_srat_mem_affinity *)header;
if (!memory_affinity)
return -EINVAL;
acpi_table_print_srat_entry(&header->common);
/* let architecture-dependent part to do it */
if (!acpi_numa_memory_affinity_init(memory_affinity))
parsed_numa_memblks++;
return 0;
}
static int __init acpi_parse_srat(struct acpi_table_header *table)
{
struct acpi_table_srat *srat = (struct acpi_table_srat *)table;
acpi_srat_revision = srat->header.revision;
/* Real work done in acpi_table_parse_srat below. */
return 0;
}
static int __init
acpi_table_parse_srat(enum acpi_srat_type id,
acpi_tbl_entry_handler handler, unsigned int max_entries)
{
return acpi_table_parse_entries(ACPI_SIG_SRAT,
sizeof(struct acpi_table_srat), id,
handler, max_entries);
}
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>
2013-03-01 15:51:27 -07:00
int __init acpi_numa_init(void)
acpi, memory-hotplug: parse SRAT before memblock is ready On linux, the pages used by kernel could not be migrated. As a result, if a memory range is used by kernel, it cannot be hot-removed. So if we want to hot-remove memory, we should prevent kernel from using it. The way now used to prevent this is specify a memory range by movablemem_map boot option and set it as ZONE_MOVABLE. But when the system is booting, memblock will allocate memory, and reserve the memory for kernel. And before we parse SRAT, and know the node memory ranges, memblock is working. And it may allocate memory in ranges to be set as ZONE_MOVABLE. This memory can be used by kernel, and never be freed. So, let's parse SRAT before memblock is called first. And it is early enough. The first call of memblock_find_in_range_node() is in: setup_arch() |-->setup_real_mode() so, this patch add a function early_parse_srat() to parse SRAT, and call it before setup_real_mode() is called. NOTE: 1) early_parse_srat() is called before numa_init(), and has initialized numa_meminfo. So DO NOT clear numa_nodes_parsed in numa_init() and DO NOT zero numa_meminfo in numa_init(), otherwise we will lose memory numa info. 2) I don't know why using count of memory affinities parsed from SRAT as a return value in original acpi_numa_init(). So I add a static variable srat_mem_cnt to remember this count and use it as the return value of the new acpi_numa_init() [mhocko@suse.cz: parse SRAT before memblock is ready fix] Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Wen Congyang <wency@cn.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Wu Jianguo <wujianguo@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Len Brown <lenb@kernel.org> Cc: "Brown, Len" <len.brown@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-22 17:33:44 -07:00
{
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>
2013-03-01 15:51:27 -07:00
int cnt = 0;
if (acpi_disabled)
return -EINVAL;
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>
2010-12-16 20:09:58 -07:00
/*
* Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
* SRAT cpu entries could have different order with that in MADT.
* So go over all cpu entries in SRAT to get apicid to node mapping.
*/
/* SRAT: System Resource Affinity Table */
if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
struct acpi_subtable_proc srat_proc[3];
memset(srat_proc, 0, sizeof(srat_proc));
srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
srat_proc[0].handler = acpi_parse_processor_affinity;
srat_proc[1].id = ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY;
srat_proc[1].handler = acpi_parse_x2apic_affinity;
srat_proc[2].id = ACPI_SRAT_TYPE_GICC_AFFINITY;
srat_proc[2].handler = acpi_parse_gicc_affinity;
acpi_table_parse_entries_array(ACPI_SIG_SRAT,
sizeof(struct acpi_table_srat),
srat_proc, ARRAY_SIZE(srat_proc), 0);
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>
2013-03-01 15:51:27 -07:00
cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
acpi_parse_memory_affinity, 0);
}
/* SLIT: System Locality Information Table */
acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
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>
2013-03-01 15:51:27 -07:00
if (cnt < 0)
return cnt;
else if (!parsed_numa_memblks)
return -ENOENT;
return 0;
}
static int acpi_get_pxm(acpi_handle h)
{
unsigned long long pxm;
acpi_status status;
acpi_handle handle;
acpi_handle phandle = h;
do {
handle = phandle;
status = acpi_evaluate_integer(handle, "_PXM", NULL, &pxm);
if (ACPI_SUCCESS(status))
return pxm;
status = acpi_get_parent(handle, &phandle);
} while (ACPI_SUCCESS(status));
return -1;
}
int acpi_get_node(acpi_handle handle)
{
int pxm;
pxm = acpi_get_pxm(handle);
return acpi_map_pxm_to_node(pxm);
}
EXPORT_SYMBOL(acpi_get_node);