powerpc/powernv: Implement NMI IPI with OPAL_SIGNAL_SYSTEM_RESET

This allows MSR[EE]=0 lockups to be detected on an OPAL (bare metal)
system similarly to the hcall NMI IPI on pseries guests, when the
platform/firmware supports it.

This is an example of CPU10 spinning with interrupts hard disabled:

  Watchdog CPU:32 detected Hard LOCKUP other CPUS:10
  Watchdog CPU:10 Hard LOCKUP
  CPU: 10 PID: 4410 Comm: bash Not tainted 4.13.0-rc7-00074-ge89ce1f89f62-dirty #34
  task: c0000003a82b4400 task.stack: c0000003af55c000
  NIP: c0000000000a7b38 LR: c000000000659044 CTR: c0000000000a7b00
  REGS: c00000000fd23d80 TRAP: 0100   Not tainted  (4.13.0-rc7-00074-ge89ce1f89f62-dirty)
  MSR: 90000000000c1033 <SF,HV,ME,IR,DR,RI,LE>
  CR: 28422222  XER: 20000000
  CFAR: c0000000000a7b38 SOFTE: 0
  GPR00: c000000000659044 c0000003af55fbb0 c000000001072a00 0000000000000078
  GPR04: c0000003c81b5c80 c0000003c81cc7e8 9000000000009033 0000000000000000
  GPR08: 0000000000000000 c0000000000a7b00 0000000000000001 9000000000001003
  GPR12: c0000000000a7b00 c00000000fd83200 0000000010180df8 0000000010189e60
  GPR16: 0000000010189ed8 0000000010151270 000000001018bd88 000000001018de78
  GPR20: 00000000370a0668 0000000000000001 00000000101645e0 0000000010163c10
  GPR24: 00007fffd14d6294 00007fffd14d6290 c000000000fba6f0 0000000000000004
  GPR28: c000000000f351d8 0000000000000078 c000000000f4095c 0000000000000000
  NIP [c0000000000a7b38] sysrq_handle_xmon+0x38/0x40
  LR [c000000000659044] __handle_sysrq+0xe4/0x270
  Call Trace:
  [c0000003af55fbd0] [c000000000659044] __handle_sysrq+0xe4/0x270
  [c0000003af55fc70] [c000000000659810] write_sysrq_trigger+0x70/0xa0
  [c0000003af55fca0] [c0000000003da650] proc_reg_write+0xb0/0x110
  [c0000003af55fcf0] [c0000000003423bc] __vfs_write+0x6c/0x1b0
  [c0000003af55fd90] [c000000000344398] vfs_write+0xd8/0x240
  [c0000003af55fde0] [c00000000034632c] SyS_write+0x6c/0x110
  [c0000003af55fe30] [c00000000000b220] system_call+0x58/0x6c

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Use kernel types for opal_signal_system_reset()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This commit is contained in:
Nicholas Piggin 2017-09-29 13:29:42 +10:00 committed by Michael Ellerman
parent 78adf6c214
commit e36d0a2ed5
5 changed files with 57 additions and 0 deletions

View File

@ -188,6 +188,7 @@
#define OPAL_XIVE_DUMP 142
#define OPAL_XIVE_RESERVED3 143
#define OPAL_XIVE_RESERVED4 144
#define OPAL_SIGNAL_SYSTEM_RESET 145
#define OPAL_NPU_INIT_CONTEXT 146
#define OPAL_NPU_DESTROY_CONTEXT 147
#define OPAL_NPU_MAP_LPAR 148

View File

@ -281,6 +281,8 @@ int opal_get_power_shift_ratio(u32 handle, int token, u32 *psr);
int opal_set_power_shift_ratio(u32 handle, int token, u32 psr);
int opal_sensor_group_clear(u32 group_hndl, int token);
s64 opal_signal_system_reset(s32 cpu);
/* Internal functions */
extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
int depth, void *data);

View File

@ -307,6 +307,7 @@ OPAL_CALL(opal_xive_get_vp_info, OPAL_XIVE_GET_VP_INFO);
OPAL_CALL(opal_xive_set_vp_info, OPAL_XIVE_SET_VP_INFO);
OPAL_CALL(opal_xive_sync, OPAL_XIVE_SYNC);
OPAL_CALL(opal_xive_dump, OPAL_XIVE_DUMP);
OPAL_CALL(opal_signal_system_reset, OPAL_SIGNAL_SYSTEM_RESET);
OPAL_CALL(opal_npu_init_context, OPAL_NPU_INIT_CONTEXT);
OPAL_CALL(opal_npu_destroy_context, OPAL_NPU_DESTROY_CONTEXT);
OPAL_CALL(opal_npu_map_lpar, OPAL_NPU_MAP_LPAR);

View File

@ -282,6 +282,7 @@ static void __init pnv_setup_machdep_opal(void)
ppc_md.restart = pnv_restart;
pm_power_off = pnv_power_off;
ppc_md.halt = pnv_halt;
/* ppc_md.system_reset_exception gets filled in by pnv_smp_init() */
ppc_md.machine_check_exception = opal_machine_check;
ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery;
ppc_md.hmi_exception_early = opal_hmi_exception_early;

View File

@ -297,6 +297,54 @@ static void __init pnv_smp_probe(void)
}
}
static int pnv_system_reset_exception(struct pt_regs *regs)
{
if (smp_handle_nmi_ipi(regs))
return 1;
return 0;
}
static int pnv_cause_nmi_ipi(int cpu)
{
int64_t rc;
if (cpu >= 0) {
rc = opal_signal_system_reset(get_hard_smp_processor_id(cpu));
if (rc != OPAL_SUCCESS)
return 0;
return 1;
} else if (cpu == NMI_IPI_ALL_OTHERS) {
bool success = true;
int c;
/*
* We do not use broadcasts (yet), because it's not clear
* exactly what semantics Linux wants or the firmware should
* provide.
*/
for_each_online_cpu(c) {
if (c == smp_processor_id())
continue;
rc = opal_signal_system_reset(
get_hard_smp_processor_id(c));
if (rc != OPAL_SUCCESS)
success = false;
}
if (success)
return 1;
/*
* Caller will fall back to doorbells, which may pick
* up the remainders.
*/
}
return 0;
}
static struct smp_ops_t pnv_smp_ops = {
.message_pass = NULL, /* Use smp_muxed_ipi_message_pass */
.cause_ipi = NULL, /* Filled at runtime by pnv_smp_probe() */
@ -315,6 +363,10 @@ static struct smp_ops_t pnv_smp_ops = {
/* This is called very early during platform setup_arch */
void __init pnv_smp_init(void)
{
if (opal_check_token(OPAL_SIGNAL_SYSTEM_RESET)) {
ppc_md.system_reset_exception = pnv_system_reset_exception;
pnv_smp_ops.cause_nmi_ipi = pnv_cause_nmi_ipi;
}
smp_ops = &pnv_smp_ops;
#ifdef CONFIG_HOTPLUG_CPU