Commit 80c78428 authored by Nathan Lynch's avatar Nathan Lynch Committed by Michael Ellerman

powerpc/pseries: safely roll back failed DLPAR cpu add

dlpar_online_cpu() attempts to online all threads of a core that has
been added to an LPAR. If onlining a non-primary thread
fails (e.g. due to an allocation failure), the core is left with at
least one thread online. dlpar_cpu_add() attempts to roll back the
whole operation, releasing the core back to the platform. However,
since some threads of the core being removed are still online, the
BUG_ON(cpu_online(cpu)) in pseries_remove_processor() strikes:

LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 3 PID: 8587 Comm: drmgr Not tainted 5.3.0-rc2-00190-g9b123d1e-dirty #46
NIP:  c0000000000eeb2c LR: c0000000000eeac4 CTR: c0000000000ee9e0
REGS: c0000001f745b6c0 TRAP: 0700   Not tainted  (5.3.0-rc2-00190-g9b123d1e-dirty)
MSR:  800000010282b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE,TM[E]>  CR: 44002448  XER: 00000000
CFAR: c00000000195d718 IRQMASK: 0
GPR00: c0000000000eeac4 c0000001f745b950 c0000000032f6200 0000000000000008
GPR04: 0000000000000008 c000000003349c78 0000000000000040 00000000000001ff
GPR08: 0000000000000008 0000000000000000 0000000000000001 0007ffffffffffff
GPR12: 0000000084002844 c00000001ecacb80 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000008
GPR24: c000000003349ee0 c00000000334a2e4 c0000000fca4d7a8 c000000001d20048
GPR28: 0000000000000001 ffffffffffffffff ffffffffffffffff c0000000fca4d7c4
NIP [c0000000000eeb2c] pseries_smp_notifier+0x14c/0x2e0
LR [c0000000000eeac4] pseries_smp_notifier+0xe4/0x2e0
Call Trace:
[c0000001f745b950] [c0000000000eeac4] pseries_smp_notifier+0xe4/0x2e0 (unreliable)
[c0000001f745ba10] [c0000000001ac774] notifier_call_chain+0xb4/0x190
[c0000001f745bab0] [c0000000001ad62c] blocking_notifier_call_chain+0x7c/0xb0
[c0000001f745baf0] [c00000000167bda0] of_detach_node+0xc0/0x110
[c0000001f745bb50] [c0000000000e7ae4] dlpar_detach_node+0x64/0xa0
[c0000001f745bb80] [c0000000000edefc] dlpar_cpu_add+0x31c/0x360
[c0000001f745bc10] [c0000000000ee980] dlpar_cpu_probe+0x50/0xb0
[c0000001f745bc50] [c00000000002cf70] arch_cpu_probe+0x40/0x70
[c0000001f745bc70] [c000000000ccd808] cpu_probe_store+0x48/0x80
[c0000001f745bcb0] [c000000000cbcef8] dev_attr_store+0x38/0x60
[c0000001f745bcd0] [c00000000059c980] sysfs_kf_write+0x70/0xb0
[c0000001f745bd10] [c00000000059afb8] kernfs_fop_write+0xf8/0x280
[c0000001f745bd60] [c0000000004b437c] __vfs_write+0x3c/0x70
[c0000001f745bd80] [c0000000004b8710] vfs_write+0xd0/0x220
[c0000001f745bdd0] [c0000000004b8acc] ksys_write+0x7c/0x140
[c0000001f745be20] [c00000000000bbd8] system_call+0x5c/0x68

Move dlpar_offline_cpu() up in the file so that dlpar_online_cpu() can
use it to re-offline any threads that have been onlined when an error
is encountered.
Signed-off-by: default avatarNathan Lynch <nathanl@linux.ibm.com>
Fixes: e666ae0b ("powerpc/pseries: Update CPU hotplug error recovery")
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191016183611.10867-3-nathanl@linux.ibm.com
parent 3366ebe9
......@@ -338,6 +338,62 @@ static void pseries_remove_processor(struct device_node *np)
cpu_maps_update_done();
}
static int dlpar_offline_cpu(struct device_node *dn)
{
int rc = 0;
unsigned int cpu;
int len, nthreads, i;
const __be32 *intserv;
u32 thread;
intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
if (!intserv)
return -EINVAL;
nthreads = len / sizeof(u32);
cpu_maps_update_begin();
for (i = 0; i < nthreads; i++) {
thread = be32_to_cpu(intserv[i]);
for_each_present_cpu(cpu) {
if (get_hard_smp_processor_id(cpu) != thread)
continue;
if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
break;
if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
set_preferred_offline_state(cpu,
CPU_STATE_OFFLINE);
cpu_maps_update_done();
timed_topology_update(1);
rc = device_offline(get_cpu_device(cpu));
if (rc)
goto out;
cpu_maps_update_begin();
break;
}
/*
* The cpu is in CPU_STATE_INACTIVE.
* Upgrade it's state to CPU_STATE_OFFLINE.
*/
set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
WARN_ON(plpar_hcall_norets(H_PROD, thread) != H_SUCCESS);
__cpu_die(cpu);
break;
}
if (cpu == num_possible_cpus()) {
pr_warn("Could not find cpu to offline with physical id 0x%x\n",
thread);
}
}
cpu_maps_update_done();
out:
return rc;
}
static int dlpar_online_cpu(struct device_node *dn)
{
int rc = 0;
......@@ -364,8 +420,10 @@ static int dlpar_online_cpu(struct device_node *dn)
timed_topology_update(1);
find_and_online_cpu_nid(cpu);
rc = device_online(get_cpu_device(cpu));
if (rc)
if (rc) {
dlpar_offline_cpu(dn);
goto out;
}
cpu_maps_update_begin();
break;
......@@ -505,62 +563,6 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
return rc;
}
static int dlpar_offline_cpu(struct device_node *dn)
{
int rc = 0;
unsigned int cpu;
int len, nthreads, i;
const __be32 *intserv;
u32 thread;
intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
if (!intserv)
return -EINVAL;
nthreads = len / sizeof(u32);
cpu_maps_update_begin();
for (i = 0; i < nthreads; i++) {
thread = be32_to_cpu(intserv[i]);
for_each_present_cpu(cpu) {
if (get_hard_smp_processor_id(cpu) != thread)
continue;
if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
break;
if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
set_preferred_offline_state(cpu,
CPU_STATE_OFFLINE);
cpu_maps_update_done();
timed_topology_update(1);
rc = device_offline(get_cpu_device(cpu));
if (rc)
goto out;
cpu_maps_update_begin();
break;
}
/*
* The cpu is in CPU_STATE_INACTIVE.
* Upgrade it's state to CPU_STATE_OFFLINE.
*/
set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
WARN_ON(plpar_hcall_norets(H_PROD, thread) != H_SUCCESS);
__cpu_die(cpu);
break;
}
if (cpu == num_possible_cpus()) {
pr_warn("Could not find cpu to offline with physical id 0x%x\n",
thread);
}
}
cpu_maps_update_done();
out:
return rc;
}
static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index)
{
int rc;
......
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