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

1 files changed, 42 insertions, 7 deletions

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e16ec7b3b427..9ca7148b5881 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -566,10 +566,35 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 #endif
 
 #ifdef CONFIG_NMI_IPI
-static void stop_this_cpu(struct pt_regs *regs)
-#else
+static void nmi_stop_this_cpu(struct pt_regs *regs)
+{
+	/*
+	 * This is a special case because it never returns, so the NMI IPI
+	 * handling would never mark it as done, which makes any later
+	 * smp_send_nmi_ipi() call spin forever. Mark it done now.
+	 *
+	 * IRQs are already hard disabled by the smp_handle_nmi_ipi.
+	 */
+	nmi_ipi_lock();
+	nmi_ipi_busy_count--;
+	nmi_ipi_unlock();
+
+	/* Remove this CPU */
+	set_cpu_online(smp_processor_id(), false);
+
+	spin_begin();
+	while (1)
+		spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
+}
+
+#else /* CONFIG_NMI_IPI */
+
 static void stop_this_cpu(void *dummy)
-#endif
 {
 	/* Remove this CPU */
 	set_cpu_online(smp_processor_id(), false);
@@ -582,12 +607,22 @@ static void stop_this_cpu(void *dummy)
 
 void smp_send_stop(void)
 {
-#ifdef CONFIG_NMI_IPI
-	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000);
-#else
+	static bool stopped = false;
+
+	/*
+	 * Prevent waiting on csd lock from a previous smp_send_stop.
+	 * This is racy, but in general callers try to do the right
+	 * thing and only fire off one smp_send_stop (e.g., see
+	 * kernel/panic.c)
+	 */
+	if (stopped)
+		return;
+
+	stopped = true;
+
 	smp_call_function(stop_this_cpu, NULL, 0);
-#endif
 }
+#endif /* CONFIG_NMI_IPI */
 
 struct thread_info *current_set[NR_CPUS];