Merge tag 'powerpc-5.12-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "Fix a bug on pseries where spurious wakeups from H_PROD would prevent
  partition migration from succeeding.

  Fix oopses seen in pcpu_alloc(), caused by parallel faults of the
  percpu mapping causing us to corrupt the protection key used for the
  mapping, and cause a fatal key fault.

  Thanks to Aneesh Kumar K.V, Murilo Opsfelder Araujo, and Nathan Lynch"

* tag 'powerpc-5.12-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/mm/book3s64: Use the correct storage key value when calling H_PROTECT
  powerpc/pseries/mobility: handle premature return from H_JOIN
  powerpc/pseries/mobility: use struct for shared state

2 files changed, 46 insertions, 5 deletions

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 764170fdb0f7..3805519a6469 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -887,7 +887,8 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 
 	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
-	flags = (newpp & 7) | H_AVPN;
+	flags = (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO)) | H_AVPN;
+	flags |= (newpp & HPTE_R_KEY_HI) >> 48;
 	if (mmu_has_feature(MMU_FTR_KERNEL_RO))
 		/* Move pp0 into bit 8 (IBM 55) */
 		flags |= (newpp & HPTE_R_PP0) >> 55;
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index ea4d6a660e0d..e83e0891272d 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -452,12 +452,28 @@ static int do_suspend(void)
 	return ret;
 }
 
+/**
+ * struct pseries_suspend_info - State shared between CPUs for join/suspend.
+ * @counter: Threads are to increment this upon resuming from suspend
+ *           or if an error is received from H_JOIN. The thread which performs
+ *           the first increment (i.e. sets it to 1) is responsible for
+ *           waking the other threads.
+ * @done: False if join/suspend is in progress. True if the operation is
+ *        complete (successful or not).
+ */
+struct pseries_suspend_info {
+	atomic_t counter;
+	bool done;
+};
+
 static int do_join(void *arg)
 {
-	atomic_t *counter = arg;
+	struct pseries_suspend_info *info = arg;
+	atomic_t *counter = &info->counter;
 	long hvrc;
 	int ret;
 
+retry:
 	/* Must ensure MSR.EE off for H_JOIN. */
 	hard_irq_disable();
 	hvrc = plpar_hcall_norets(H_JOIN);
@@ -473,8 +489,20 @@ static int do_join(void *arg)
 	case H_SUCCESS:
 		/*
 		 * The suspend is complete and this cpu has received a
-		 * prod.
+		 * prod, or we've received a stray prod from unrelated
+		 * code (e.g. paravirt spinlocks) and we need to join
+		 * again.
+		 *
+		 * This barrier orders the return from H_JOIN above vs
+		 * the load of info->done. It pairs with the barrier
+		 * in the wakeup/prod path below.
 		 */
+		smp_mb();
+		if (READ_ONCE(info->done) == false) {
+			pr_info_ratelimited("premature return from H_JOIN on CPU %i, retrying",
+					    smp_processor_id());
+			goto retry;
+		}
 		ret = 0;
 		break;
 	case H_BAD_MODE:
@@ -488,6 +516,13 @@ static int do_join(void *arg)
 
 	if (atomic_inc_return(counter) == 1) {
 		pr_info("CPU %u waking all threads\n", smp_processor_id());
+		WRITE_ONCE(info->done, true);
+		/*
+		 * This barrier orders the store to info->done vs subsequent
+		 * H_PRODs to wake the other CPUs. It pairs with the barrier
+		 * in the H_SUCCESS case above.
+		 */
+		smp_mb();
 		prod_others();
 	}
 	/*
@@ -535,11 +570,16 @@ static int pseries_suspend(u64 handle)
 	int ret;
 
 	while (true) {
-		atomic_t counter = ATOMIC_INIT(0);
+		struct pseries_suspend_info info;
 		unsigned long vasi_state;
 		int vasi_err;
 
-		ret = stop_machine(do_join, &counter, cpu_online_mask);
+		info = (struct pseries_suspend_info) {
+			.counter = ATOMIC_INIT(0),
+			.done = false,
+		};
+
+		ret = stop_machine(do_join, &info, cpu_online_mask);
 		if (ret == 0)
 			break;
 		/*