powerpc/numa: Update cpu_cpu_map on CPU online/offline

cpu_cpu_map holds all the CPUs in the DIE. However in PowerPC, when
onlining/offlining of CPUs, this mask doesn't get updated.  This mask
is however updated when CPUs are added/removed. So when both
operations like online/offline of CPUs and adding/removing of CPUs are
done simultaneously, then cpumaps end up broken.

WARNING: CPU: 13 PID: 1142 at kernel/sched/topology.c:898
build_sched_domains+0xd48/0x1720
Modules linked in: rpadlpar_io rpaphp mptcp_diag xsk_diag tcp_diag
udp_diag raw_diag inet_diag unix_diag af_packet_diag netlink_diag
bonding tls nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib
nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct
nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set
rfkill nf_tables nfnetlink pseries_rng xts vmx_crypto uio_pdrv_genirq
uio binfmt_misc ip_tables xfs libcrc32c dm_service_time sd_mod t10_pi sg
ibmvfc scsi_transport_fc ibmveth dm_multipath dm_mirror dm_region_hash
dm_log dm_mod fuse
CPU: 13 PID: 1142 Comm: kworker/13:2 Not tainted 5.13.0-rc6+ #28
Workqueue: events cpuset_hotplug_workfn
NIP:  c0000000001caac8 LR: c0000000001caac4 CTR: 00000000007088ec
REGS: c00000005596f220 TRAP: 0700   Not tainted  (5.13.0-rc6+)
MSR:  8000000000029033 <SF,EE,ME,IR,DR,RI,LE>  CR: 48828222  XER:
00000009
CFAR: c0000000001ea698 IRQMASK: 0
GPR00: c0000000001caac4 c00000005596f4c0 c000000001c4a400 0000000000000036
GPR04: 00000000fffdffff c00000005596f1d0 0000000000000027 c0000018cfd07f90
GPR08: 0000000000000023 0000000000000001 0000000000000027 c0000018fe68ffe8
GPR12: 0000000000008000 c00000001e9d1880 c00000013a047200 0000000000000800
GPR16: c000000001d3c7d0 0000000000000240 0000000000000048 c000000010aacd18
GPR20: 0000000000000001 c000000010aacc18 c00000013a047c00 c000000139ec2400
GPR24: 0000000000000280 c000000139ec2520 c000000136c1b400 c000000001c93060
GPR28: c00000013a047c20 c000000001d3c6c0 c000000001c978a0 000000000000000d
NIP [c0000000001caac8] build_sched_domains+0xd48/0x1720
LR [c0000000001caac4] build_sched_domains+0xd44/0x1720
Call Trace:
[c00000005596f4c0] [c0000000001caac4] build_sched_domains+0xd44/0x1720 (unreliable)
[c00000005596f670] [c0000000001cc5ec] partition_sched_domains_locked+0x3ac/0x4b0
[c00000005596f710] [c0000000002804e4] rebuild_sched_domains_locked+0x404/0x9e0
[c00000005596f810] [c000000000283e60] rebuild_sched_domains+0x40/0x70
[c00000005596f840] [c000000000284124] cpuset_hotplug_workfn+0x294/0xf10
[c00000005596fc60] [c000000000175040] process_one_work+0x290/0x590
[c00000005596fd00] [c0000000001753c8] worker_thread+0x88/0x620
[c00000005596fda0] [c000000000181704] kthread+0x194/0x1a0
[c00000005596fe10] [c00000000000ccec] ret_from_kernel_thread+0x5c/0x70
Instruction dump:
485af049 60000000 2fa30800 409e0028 80fe0000 e89a00f8 e86100e8 38da0120
7f88e378 7ce53b78 4801fb91 60000000 <0fe00000> 39000000 38e00000 38c00000

Fix this by updating cpu_cpu_map aka cpumask_of_node() on every CPU
online/offline.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210826100521.412639-5-srikar@linux.vnet.ibm.com
This commit is contained in:
Srikar Dronamraju 2021-08-26 15:35:20 +05:30 committed by Michael Ellerman
parent 544a09ee74
commit 9a245d0e1f
3 changed files with 18 additions and 5 deletions

View file

@ -66,6 +66,11 @@ static inline int early_cpu_to_node(int cpu)
int of_drconf_to_nid_single(struct drmem_lmb *lmb);
void update_numa_distance(struct device_node *node);
extern void map_cpu_to_node(int cpu, int node);
#ifdef CONFIG_HOTPLUG_CPU
extern void unmap_cpu_from_node(unsigned long cpu);
#endif /* CONFIG_HOTPLUG_CPU */
#else
static inline int early_cpu_to_node(int cpu) { return 0; }
@ -95,6 +100,14 @@ static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
}
static inline void update_numa_distance(struct device_node *node) {}
#ifdef CONFIG_SMP
static inline void map_cpu_to_node(int cpu, int node) {}
#ifdef CONFIG_HOTPLUG_CPU
static inline void unmap_cpu_from_node(unsigned long cpu) {}
#endif /* CONFIG_HOTPLUG_CPU */
#endif /* CONFIG_SMP */
#endif /* CONFIG_NUMA */
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)

View file

@ -1442,6 +1442,8 @@ static void remove_cpu_from_masks(int cpu)
struct cpumask *(*mask_fn)(int) = cpu_sibling_mask;
int i;
unmap_cpu_from_node(cpu);
if (shared_caches)
mask_fn = cpu_l2_cache_mask;
@ -1526,6 +1528,7 @@ static void add_cpu_to_masks(int cpu)
* This CPU will not be in the online mask yet so we need to manually
* add it to it's own thread sibling mask.
*/
map_cpu_to_node(cpu, cpu_to_node(cpu));
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
cpumask_set_cpu(cpu, cpu_core_mask(cpu));

View file

@ -142,7 +142,7 @@ static void reset_numa_cpu_lookup_table(void)
numa_cpu_lookup_table[cpu] = -1;
}
static void map_cpu_to_node(int cpu, int node)
void map_cpu_to_node(int cpu, int node)
{
update_numa_cpu_lookup_table(cpu, node);
@ -153,7 +153,7 @@ static void map_cpu_to_node(int cpu, int node)
}
#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
static void unmap_cpu_from_node(unsigned long cpu)
void unmap_cpu_from_node(unsigned long cpu)
{
int node = numa_cpu_lookup_table[cpu];
@ -800,9 +800,6 @@ static int ppc_numa_cpu_prepare(unsigned int cpu)
static int ppc_numa_cpu_dead(unsigned int cpu)
{
#ifdef CONFIG_HOTPLUG_CPU
unmap_cpu_from_node(cpu);
#endif
return 0;
}