From f85086f95fa36194eb0db5cd5c12e56801b98523 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Fri, 25 Sep 2020 21:19:31 -0700 Subject: 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: 4fbce633910e ("mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range()") Signed-off-by: Laurent Dufour Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Fenghua Yu Cc: Nathan Lynch Cc: Scott Cheloha Cc: Tony Luck Cc: Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds --- include/linux/node.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux/node.h') diff --git a/include/linux/node.h b/include/linux/node.h index 4866f32a02d8..014ba3ab2efd 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -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; -- cgit v1.2.3-71-gd317 From 90c7eaeb14a325a760d732184ff1fbed47e5fa98 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Thu, 15 Oct 2020 20:09:15 -0700 Subject: mm: don't panic when links can't be created in sysfs At boot time, or when doing memory hot-add operations, if the links in sysfs can't be created, the system is still able to run, so just report the error in the kernel log rather than BUG_ON and potentially make system unusable because the callpath can be called with locks held. Since the number of memory blocks managed could be high, the messages are rate limited. As a consequence, link_mem_sections() has no status to report anymore. Signed-off-by: Laurent Dufour Signed-off-by: Andrew Morton Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Acked-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Fenghua Yu Cc: Nathan Lynch Cc: "Rafael J . Wysocki" Cc: Scott Cheloha Cc: Tony Luck Link: https://lkml.kernel.org/r/20200915094143.79181-4-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds --- drivers/base/node.c | 33 +++++++++++++++++++++------------ include/linux/node.h | 16 +++++++--------- mm/memory_hotplug.c | 5 ++--- 3 files changed, 30 insertions(+), 24 deletions(-) (limited to 'include/linux/node.h') diff --git a/drivers/base/node.c b/drivers/base/node.c index 43d21f9e88b1..6ffa470e2984 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -772,8 +772,8 @@ 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) +static void do_register_memory_block_under_node(int nid, + struct memory_block *mem_blk) { int ret; @@ -786,12 +786,19 @@ static int do_register_memory_block_under_node(int 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; + if (ret && ret != -EEXIST) + dev_err_ratelimited(&node_devices[nid]->dev, + "can't create link to %s in sysfs (%d)\n", + kobject_name(&mem_blk->dev.kobj), ret); - return sysfs_create_link_nowarn(&mem_blk->dev.kobj, + ret = sysfs_create_link_nowarn(&mem_blk->dev.kobj, &node_devices[nid]->dev.kobj, kobject_name(&node_devices[nid]->dev.kobj)); + if (ret && ret != -EEXIST) + dev_err_ratelimited(&mem_blk->dev, + "can't create link to %s in sysfs (%d)\n", + kobject_name(&node_devices[nid]->dev.kobj), + ret); } /* register memory section under specified node if it spans that node */ @@ -827,7 +834,8 @@ static int register_mem_block_under_node_early(struct memory_block *mem_blk, if (page_nid != nid) continue; - return do_register_memory_block_under_node(nid, mem_blk); + do_register_memory_block_under_node(nid, mem_blk); + return 0; } /* mem section does not span the specified node */ return 0; @@ -842,7 +850,8 @@ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk, { int nid = *(int *)arg; - return do_register_memory_block_under_node(nid, mem_blk); + do_register_memory_block_under_node(nid, mem_blk); + return 0; } /* @@ -860,8 +869,8 @@ 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, - enum meminit_context context) +void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, + enum meminit_context context) { walk_memory_blocks_func_t func; @@ -870,9 +879,9 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, else func = register_mem_block_under_node_early; - return walk_memory_blocks(PFN_PHYS(start_pfn), - PFN_PHYS(end_pfn - start_pfn), (void *)&nid, - func); + walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), + (void *)&nid, func); + return; } #ifdef CONFIG_HUGETLBFS diff --git a/include/linux/node.h b/include/linux/node.h index 014ba3ab2efd..8e5a29897936 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,15 +99,14 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context); +void 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, - enum meminit_context context) +static inline void link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context) { - return 0; } #endif @@ -130,8 +129,7 @@ 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, - MEMINIT_EARLY); + link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY); } return error; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1efc92f66b9d..d397af38f9ce 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1092,9 +1092,8 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) } /* link memory sections under this node.*/ - ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1), - MEMINIT_HOTPLUG); - BUG_ON(ret); + link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1), + MEMINIT_HOTPLUG); /* create new memmap entry */ if (!strcmp(res->name, "System RAM")) -- cgit v1.2.3-71-gd317