cpu: Cleanup AMR and IAMR when re-initializing CPUs

There's a bug in current Linux kernels leaving crap in those registers
accross kexec and not sanitizing them on boot. This breaks kexec under
some circumstances (such as booting a hash kernel from a radix one
on P9 DD2.0).

The long term fix is in Linux, but this workaround is a reasonable
way of "sanitizing" those SPRs when Linux calls opal_reinit_cpus()
and shouldn't have adverse effects.

We could also use that same mechanism to cleanup other things as
well such as restoring some other SPRs to their default value in
the future.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>

1 files changed, 29 insertions, 0 deletions

diff --git a/core/cpu.c b/core/cpu.c
index 75c7008..a0c395f 100644
--- a/core/cpu.c
+++ b/core/cpu.c
@@ -1077,6 +1077,27 @@ void cpu_set_radix_mode(void)
 	cpu_change_all_hid0(&req);
 }
 
+static void cpu_cleanup_one(void *param __unused)
+{
+	mtspr(SPR_AMR, 0);
+	mtspr(SPR_IAMR, 0);
+}
+
+static int64_t cpu_cleanup_all(void)
+{
+	struct cpu_thread *cpu;
+
+	for_each_available_cpu(cpu) {
+		if (cpu == this_cpu()) {
+			cpu_cleanup_one(NULL);
+			continue;
+		}
+		cpu_wait_job(cpu_queue_job(cpu, "cpu_cleanup",
+					   cpu_cleanup_one, NULL), true);
+	}
+	return OPAL_SUCCESS;
+}
+
 void cpu_fast_reboot_complete(void)
 {
 	/* Fast reboot will have cleared HID0:HILE */
@@ -1132,6 +1153,14 @@ static int64_t opal_reinit_cpus(uint64_t flags)
 	this_cpu()->in_reinit = true;
 	unlock(&reinit_lock);
 
+	/*
+	 * This cleans up a few things left over by Linux
+	 * that can cause problems in cases such as radix->hash
+	 * transitions. Ideally Linux should do it but doing it
+	 * here works around existing broken kernels.
+	 */
+	cpu_cleanup_all();
+
 	/* If HILE change via HID0 is supported ... */
 	if (hile_supported &&
 	    (flags & (OPAL_REINIT_CPUS_HILE_BE |