powernv/kdump: Fix cases where the kdump kernel can get HMI's

Certain HMI's such as malfunction error propagate through
all threads/core on the system. If a thread was offline
prior to us crashing the system and jumping to the kdump
kernel, bad things happen when it wakes up due to an HMI
in the kdump kernel.

There are several possible ways to solve this problem

1. Put the offline cores in a state such that they are
not woken up for machine check and HMI errors. This
does not work, since we might need to wake up offline
threads to handle TB errors
2. Ignore HMI errors, setup HMEER to mask HMI errors,
but this still leads the window open for any MCEs
and masking them for the duration of the dump might
be a concern
3. Wake up offline CPUs, as in send them to
crash_ipi_callback (not wake them up as in mark them
online as seen by the hotplug). kexec does a
wake_online_cpus() call, this patch does something
similar, but instead sends an IPI and forces them to
crash_ipi_callback()

This patch takes approach #3.

Care is taken to enable this only for powenv platforms
via crash_wake_offline (a global value set at setup
time). The crash code sends out IPI's to all CPU's
which then move to crash_ipi_callback and kexec_smp_wait().

Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 28 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index ba030669eca1..9664c8461f03 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -37,6 +37,8 @@
 #include <asm/kvm_ppc.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cpuidle.h>
+#include <asm/kexec.h>
+#include <asm/reg.h>
 
 #include "powernv.h"
 
@@ -209,9 +211,32 @@ static void pnv_smp_cpu_kill_self(void)
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
+		} else if ((srr1 & wmask) == SRR1_WAKERESET) {
+			irq_set_pending_from_srr1(srr1);
+			/* Does not return */
 		}
+
 		smp_mb();
 
+		/*
+		 * For kdump kernels, we process the ipi and jump to
+		 * crash_ipi_callback
+		 */
+		if (kdump_in_progress()) {
+			/*
+			 * If we got to this point, we've not used
+			 * NMI's, otherwise we would have gone
+			 * via the SRR1_WAKERESET path. We are
+			 * using regular IPI's for waking up offline
+			 * threads.
+			 */
+			struct pt_regs regs;
+
+			ppc_save_regs(&regs);
+			crash_ipi_callback(&regs);
+			/* Does not return */
+		}
+
 		if (cpu_core_split_required())
 			continue;
 
@@ -371,5 +396,8 @@ void __init pnv_smp_init(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	ppc_md.cpu_die	= pnv_smp_cpu_kill_self;
+#ifdef CONFIG_KEXEC_CORE
+	crash_wake_offline = 1;
+#endif
 #endif
 }