Commit f85086f9 authored by Laurent Dufour's avatar Laurent Dufour Committed by Linus Torvalds

mm: don't rely on system state to detect hot-plug operations

In register_mem_sect_under_node() the system_state's value is checked to
detect whether the call is made during boot time or during an hot-plug
operation.  Unfortunately, that check against SYSTEM_BOOTING is wrong
because regular memory is registered at SYSTEM_SCHEDULING state.  In
addition, memory hot-plug operation can be triggered at this system
state by the ACPI [1].  So checking against the system state is not
enough.

The consequence is that on system with interleaved node's ranges like this:

 Early memory node ranges
   node   1: [mem 0x0000000000000000-0x000000011fffffff]
   node   2: [mem 0x0000000120000000-0x000000014fffffff]
   node   1: [mem 0x0000000150000000-0x00000001ffffffff]
   node   0: [mem 0x0000000200000000-0x000000048fffffff]
   node   2: [mem 0x0000000490000000-0x00000007ffffffff]

This can be seen on PowerPC LPAR after multiple memory hot-plug and
hot-unplug operations are done.  At the next reboot the node's memory
ranges can be interleaved and since the call to link_mem_sections() is
made in topology_init() while the system is in the SYSTEM_SCHEDULING
state, the node's id is not checked, and the sections registered to
multiple nodes:

  $ ls -l /sys/devices/system/memory/memory21/node*
  total 0
  lrwxrwxrwx 1 root root     0 Aug 24 05:27 node1 -> ../../node/node1
  lrwxrwxrwx 1 root root     0 Aug 24 05:27 node2 -> ../../node/node2

In that case, the system is able to boot but if later one of theses
memory blocks is hot-unplugged and then hot-plugged, the sysfs
inconsistency is detected and this is triggering a BUG_ON():

  kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084!
  Oops: Exception in kernel mode, sig: 5 [#1]
  LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
  Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4
  CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25
  Call Trace:
    add_memory_resource+0x23c/0x340 (unreliable)
    __add_memory+0x5c/0xf0
    dlpar_add_lmb+0x1b4/0x500
    dlpar_memory+0x1f8/0xb80
    handle_dlpar_errorlog+0xc0/0x190
    dlpar_store+0x198/0x4a0
    kobj_attr_store+0x30/0x50
    sysfs_kf_write+0x64/0x90
    kernfs_fop_write+0x1b0/0x290
    vfs_write+0xe8/0x290
    ksys_write+0xdc/0x130
    system_call_exception+0x160/0x270
    system_call_common+0xf0/0x27c

This patch addresses the root cause by not relying on the system_state
value to detect whether the call is due to a hot-plug operation.  An
extra parameter is added to link_mem_sections() detailing whether the
operation is due to a hot-plug operation.

[1] According to Oscar Salvador, using this qemu command line, ACPI
memory hotplug operations are raised at SYSTEM_SCHEDULING state:

  $QEMU -enable-kvm -machine pc -smp 4,sockets=4,cores=1,threads=1 -cpu host -monitor pty \
        -m size=$MEM,slots=255,maxmem=4294967296k  \
        -numa node,nodeid=0,cpus=0-3,mem=512 -numa node,nodeid=1,mem=512 \
        -object memory-backend-ram,id=memdimm0,size=134217728 -device pc-dimm,node=0,memdev=memdimm0,id=dimm0,slot=0 \
        -object memory-backend-ram,id=memdimm1,size=134217728 -device pc-dimm,node=0,memdev=memdimm1,id=dimm1,slot=1 \
        -object memory-backend-ram,id=memdimm2,size=134217728 -device pc-dimm,node=0,memdev=memdimm2,id=dimm2,slot=2 \
        -object memory-backend-ram,id=memdimm3,size=134217728 -device pc-dimm,node=0,memdev=memdimm3,id=dimm3,slot=3 \
        -object memory-backend-ram,id=memdimm4,size=134217728 -device pc-dimm,node=1,memdev=memdimm4,id=dimm4,slot=4 \
        -object memory-backend-ram,id=memdimm5,size=134217728 -device pc-dimm,node=1,memdev=memdimm5,id=dimm5,slot=5 \
        -object memory-backend-ram,id=memdimm6,size=134217728 -device pc-dimm,node=1,memdev=memdimm6,id=dimm6,slot=6 \

Fixes: 4fbce633 ("mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range()")
Signed-off-by: default avatarLaurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Reviewed-by: default avatarDavid Hildenbrand <david@redhat.com>
Reviewed-by: default avatarOscar Salvador <osalvador@suse.de>
Acked-by: default avatarMichal Hocko <mhocko@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@linux.ibm.comSigned-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent c1d0da83
......@@ -761,14 +761,36 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
return pfn_to_nid(pfn);
}
static int do_register_memory_block_under_node(int nid,
struct memory_block *mem_blk)
{
int ret;
/*
* If this memory block spans multiple nodes, we only indicate
* the last processed node.
*/
mem_blk->nid = nid;
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
if (ret)
return ret;
return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
&node_devices[nid]->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
}
/* register memory section under specified node if it spans that node */
static int register_mem_sect_under_node(struct memory_block *mem_blk,
void *arg)
static int register_mem_block_under_node_early(struct memory_block *mem_blk,
void *arg)
{
unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
int ret, nid = *(int *)arg;
int nid = *(int *)arg;
unsigned long pfn;
for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
......@@ -785,38 +807,33 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
}
/*
* We need to check if page belongs to nid only for the boot
* case, during hotplug we know that all pages in the memory
* block belong to the same node.
*/
if (system_state == SYSTEM_BOOTING) {
page_nid = get_nid_for_pfn(pfn);
if (page_nid < 0)
continue;
if (page_nid != nid)
continue;
}
/*
* If this memory block spans multiple nodes, we only indicate
* the last processed node.
* We need to check if page belongs to nid only at the boot
* case because node's ranges can be interleaved.
*/
mem_blk->nid = nid;
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
if (ret)
return ret;
page_nid = get_nid_for_pfn(pfn);
if (page_nid < 0)
continue;
if (page_nid != nid)
continue;
return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
&node_devices[nid]->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
return do_register_memory_block_under_node(nid, mem_blk);
}
/* mem section does not span the specified node */
return 0;
}
/*
* During hotplug we know that all pages in the memory block belong to the same
* node.
*/
static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
void *arg)
{
int nid = *(int *)arg;
return do_register_memory_block_under_node(nid, mem_blk);
}
/*
* Unregister a memory block device under the node it spans. Memory blocks
* with multiple nodes cannot be offlined and therefore also never be removed.
......@@ -832,11 +849,19 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
enum meminit_context context)
{
walk_memory_blocks_func_t func;
if (context == MEMINIT_HOTPLUG)
func = register_mem_block_under_node_hotplug;
else
func = register_mem_block_under_node_early;
return walk_memory_blocks(PFN_PHYS(start_pfn),
PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
register_mem_sect_under_node);
func);
}
#ifdef CONFIG_HUGETLBFS
......
......@@ -99,11 +99,13 @@ extern struct node *node_devices[];
typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
extern int link_mem_sections(int nid, unsigned long start_pfn,
unsigned long end_pfn);
int link_mem_sections(int nid, unsigned long start_pfn,
unsigned long end_pfn,
enum meminit_context context);
#else
static inline int link_mem_sections(int nid, unsigned long start_pfn,
unsigned long end_pfn)
unsigned long end_pfn,
enum meminit_context context)
{
return 0;
}
......@@ -128,7 +130,8 @@ static inline int register_one_node(int nid)
if (error)
return error;
/* link memory sections under this node */
error = link_mem_sections(nid, start_pfn, end_pfn);
error = link_mem_sections(nid, start_pfn, end_pfn,
MEMINIT_EARLY);
}
return error;
......
......@@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res)
}
/* link memory sections under this node.*/
ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1));
ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
MEMINIT_HOTPLUG);
BUG_ON(ret);
/* create new memmap entry */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment