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 <npig...@gmail.com>
---
arch/powerpc/include/asm/opal-api.h | 1 +
arch/powerpc/include/asm/opal.h | 2 ++
arch/powerpc/kernel/irq.c | 43 +++++++++++++++++++---
arch/powerpc/platforms/powernv/opal-wrappers.S | 1 +
arch/powerpc/platforms/powernv/powernv.h | 1 +
arch/powerpc/platforms/powernv/setup.c | 3 ++
arch/powerpc/platforms/powernv/smp.c | 50 ++++++++++++++++++++++++++
7 files changed, 97 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/opal-api.h
b/arch/powerpc/include/asm/opal-api.h
index 450a60b81d2a..9d191ebea706 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -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
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 726c23304a57..7d7613c49f2b 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -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);
+int64_t opal_signal_system_reset(int32_t cpu);
+
/* Internal functions */
extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
int depth, void *data);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4e65bf82f5e0..472d294d0df5 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -394,11 +394,21 @@ bool prep_irq_for_idle_irqsoff(void)
/*
* Take the SRR1 wakeup reason, index into this table to find the
* appropriate irq_happened bit.
+ *
+ * Sytem reset exceptions taken in idle state also come through here,
+ * but they are NMI interrupts so do not need to wait for IRQs to be
+ * restored, and should be taken as early as practical. These are marked
+ * with 0xff in the table. The Power ISA specifies 0100b as the system
+ * reset interrupt reason, but POWER9 DD1 can set 0010b.
*/
+#define IRQ_SYSTEM_RESET 0xff
+
static const u8 srr1_to_lazyirq[0x10] = {
- 0, 0, 0,
- PACA_IRQ_DBELL,
0,
+ 0,
+ IRQ_SYSTEM_RESET,
+ PACA_IRQ_DBELL,
+ IRQ_SYSTEM_RESET,
PACA_IRQ_DBELL,
PACA_IRQ_DEC,
0,
@@ -407,15 +417,40 @@ static const u8 srr1_to_lazyirq[0x10] = {
PACA_IRQ_HMI,
0, 0, 0, 0, 0 };
+static noinline void replay_system_reset(void)
+{
+ struct pt_regs regs;
+
+ ppc_save_regs(®s);
+ regs.trap = 0x100;
+ get_paca()->in_nmi = 1;
+ system_reset_exception(®s);
+ get_paca()->in_nmi = 0;
+}
+
void irq_set_pending_from_srr1(unsigned long srr1)
{
unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18;
+ u8 reason = srr1_to_lazyirq[idx];
+
+ /*
+ * Take the system reset now, which is immediately after registers
+ * are restored from idle. It's an NMI, so interrupts need not be
+ * re-enabled when it's taken.
+ */
+ if (unlikely(reason == IRQ_SYSTEM_RESET)) {
+ replay_system_reset();
+ return;
+ }
/*
* The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
- * so this can be called unconditionally with srr1 wake reason.
+ * so this can be called unconditionally with the SRR1 wake
+ * reason as returned by the idle code. If a future CPU was to
+ * designate this as an interrupt reason, then a new index for
+ * no interrupt must be assigned.
*/
- local_paca->irq_happened |= srr1_to_lazyirq[idx];
+ local_paca->irq_happened |= reason;
}
#endif /* CONFIG_PPC_BOOK3S */
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S
b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 8c1ede2d3f7e..37cd170201a2 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -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);
diff --git a/arch/powerpc/platforms/powernv/powernv.h
b/arch/powerpc/platforms/powernv/powernv.h
index a159d48573d7..49add2037e0d 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -3,6 +3,7 @@
#ifdef CONFIG_SMP
extern void pnv_smp_init(void);
+extern int pnv_system_reset_exception(struct pt_regs *regs);
#else
static inline void pnv_smp_init(void) { }
#endif
diff --git a/arch/powerpc/platforms/powernv/setup.c
b/arch/powerpc/platforms/powernv/setup.c
index 897aa1400eb8..4fdaa1d7c4cd 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -282,6 +282,9 @@ static void __init pnv_setup_machdep_opal(void)
ppc_md.restart = pnv_restart;
pm_power_off = pnv_power_off;
ppc_md.halt = pnv_halt;
+#ifdef CONFIG_SMP
+ ppc_md.system_reset_exception = pnv_system_reset_exception;
+#endif
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;
diff --git a/arch/powerpc/platforms/powernv/smp.c
b/arch/powerpc/platforms/powernv/smp.c
index c17f81e433f7..23da03eda954 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -290,6 +290,54 @@ static void __init pnv_smp_probe(void)
}
}
+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() */
@@ -308,6 +356,8 @@ 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))
+ pnv_smp_ops.cause_nmi_ipi = pnv_cause_nmi_ipi;
smp_ops = &pnv_smp_ops;
#ifdef CONFIG_HOTPLUG_CPU
--
2.13.3
