4 files changed, 72 insertions, 11 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;
 		/*
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index b3ac2455faad..637300330507 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -4,6 +4,7 @@
  * Copyright 2006-2007 Michael Ellerman, IBM Corp.
  */
 
+#include <linux/crash_dump.h>
 #include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
@@ -458,8 +459,28 @@ again:
 			return hwirq;
 		}
 
-		virq = irq_create_mapping_affinity(NULL, hwirq,
-						   entry->affinity);
+		/*
+		 * Depending on the number of online CPUs in the original
+		 * kernel, it is likely for CPU #0 to be offline in a kdump
+		 * kernel. The associated IRQs in the affinity mappings
+		 * provided by irq_create_affinity_masks() are thus not
+		 * started by irq_startup(), as per-design for managed IRQs.
+		 * This can be a problem with multi-queue block devices driven
+		 * by blk-mq : such a non-started IRQ is very likely paired
+		 * with the single queue enforced by blk-mq during kdump (see
+		 * blk_mq_alloc_tag_set()). This causes the device to remain
+		 * silent and likely hangs the guest at some point.
+		 *
+		 * We don't really care for fine-grained affinity when doing
+		 * kdump actually : simply ignore the pre-computed affinity
+		 * masks in this case and let the default mask with all CPUs
+		 * be used when creating the IRQ mappings.
+		 */
+		if (is_kdump_kernel())
+			virq = irq_create_mapping(NULL, hwirq);
+		else
+			virq = irq_create_mapping_affinity(NULL, hwirq,
+							   entry->affinity);
 
 		if (!virq) {
 			pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index b2797cfe4e2b..9cb4fc839fd5 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1261,7 +1261,6 @@ static int vio_bus_remove(struct device *dev)
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct vio_driver *viodrv = to_vio_driver(dev->driver);
 	struct device *devptr;
-	int ret = 1;
 
 	/*
 	 * Hold a reference to the device after the remove function is called
@@ -1270,13 +1269,13 @@ static int vio_bus_remove(struct device *dev)
 	devptr = get_device(dev);
 
 	if (viodrv->remove)
-		ret = viodrv->remove(viodev);
+		viodrv->remove(viodev);
 
-	if (!ret && firmware_has_feature(FW_FEATURE_CMO))
+	if (firmware_has_feature(FW_FEATURE_CMO))
 		vio_cmo_bus_remove(viodev);
 
 	put_device(devptr);
-	return ret;
+	return 0;
 }
 
 /**