Merge tag 'powerpc-4.17-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "A bunch of fixes, mostly for existing code and going to stable.

  Our memory hot-unplug path wasn't flushing the cache before removing
  memory. That is a problem now that we are doing memory hotplug on bare
  metal.

  Three fixes for the NPU code that supports devices connected via
  NVLink (ie. GPUs). The main one tweaks the TLB flush algorithm to
  avoid soft lockups for large flushes.

  A fix for our memory error handling where we would loop infinitely,
  returning back to the bad access and hard lockup the CPU.

  Fixes for the OPAL RTC driver, which wasn't handling some error cases
  correctly.

  A fix for a hardlockup in the powernv cpufreq driver.

  And finally two fixes to our smp_send_stop(), required due to a recent
  change to use it on shutdown.

  Thanks to: Alistair Popple, Balbir Singh, Laurentiu Tudor, Mahesh
  Salgaonkar, Mark Hairgrove, Nicholas Piggin, Rashmica Gupta, Shilpasri
  G Bhat"

* tag 'powerpc-4.17-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/kvm/booke: Fix altivec related build break
  powerpc: Fix deadlock with multiple calls to smp_send_stop
  cpufreq: powernv: Fix hardlockup due to synchronous smp_call in timer interrupt
  powerpc: Fix smp_send_stop NMI IPI handling
  rtc: opal: Fix OPAL RTC driver OPAL_BUSY loops
  powerpc/mce: Fix a bug where mce loops on memory UE.
  powerpc/powernv/npu: Do a PID GPU TLB flush when invalidating a large address range
  powerpc/powernv/npu: Prevent overwriting of pnv_npu2_init_contex() callback parameters
  powerpc/powernv/npu: Add lock to prevent race in concurrent context init/destroy
  powerpc/powernv/memtrace: Let the arch hotunplug code flush cache
  powerpc/mm: Flush cache on memory hot(un)plug

2 files changed, 34 insertions, 17 deletions

diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 0591874856d3..54edaec1e608 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -679,6 +679,16 @@ void gpstate_timer_handler(struct timer_list *t)
 
 	if (!spin_trylock(&gpstates->gpstate_lock))
 		return;
+	/*
+	 * If the timer has migrated to the different cpu then bring
+	 * it back to one of the policy->cpus
+	 */
+	if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) {
+		gpstates->timer.expires = jiffies + msecs_to_jiffies(1);
+		add_timer_on(&gpstates->timer, cpumask_first(policy->cpus));
+		spin_unlock(&gpstates->gpstate_lock);
+		return;
+	}
 
 	/*
 	 * If PMCR was last updated was using fast_swtich then
@@ -718,10 +728,8 @@ void gpstate_timer_handler(struct timer_list *t)
 	if (gpstate_idx != gpstates->last_lpstate_idx)
 		queue_gpstate_timer(gpstates);
 
+	set_pstate(&freq_data);
 	spin_unlock(&gpstates->gpstate_lock);
-
-	/* Timer may get migrated to a different cpu on cpu hot unplug */
-	smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
 }
 
 /*
diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c
index 304e891e35fc..60f2250fd96b 100644
--- a/drivers/rtc/rtc-opal.c
+++ b/drivers/rtc/rtc-opal.c
@@ -57,7 +57,7 @@ static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms)
 
 static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
 {
-	long rc = OPAL_BUSY;
+	s64 rc = OPAL_BUSY;
 	int retries = 10;
 	u32 y_m_d;
 	u64 h_m_s_ms;
@@ -66,13 +66,17 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
+		if (rc == OPAL_BUSY_EVENT) {
+			msleep(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
-		else if (retries-- && (rc == OPAL_HARDWARE
-				       || rc == OPAL_INTERNAL_ERROR))
-			msleep(10);
-		else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
-			break;
+		} else if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+		} else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+			if (retries--) {
+				msleep(10); /* Wait 10ms before retry */
+				rc = OPAL_BUSY; /* go around again */
+			}
+		}
 	}
 
 	if (rc != OPAL_SUCCESS)
@@ -87,21 +91,26 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
 
 static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
 {
-	long rc = OPAL_BUSY;
+	s64 rc = OPAL_BUSY;
 	int retries = 10;
 	u32 y_m_d = 0;
 	u64 h_m_s_ms = 0;
 
 	tm_to_opal(tm, &y_m_d, &h_m_s_ms);
+
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_write(y_m_d, h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
+		if (rc == OPAL_BUSY_EVENT) {
+			msleep(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
-		else if (retries-- && (rc == OPAL_HARDWARE
-				       || rc == OPAL_INTERNAL_ERROR))
-			msleep(10);
-		else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
-			break;
+		} else if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+		} else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+			if (retries--) {
+				msleep(10); /* Wait 10ms before retry */
+				rc = OPAL_BUSY; /* go around again */
+			}
+		}
 	}
 
 	return rc == OPAL_SUCCESS ? 0 : -EIO;