Merge tag 'powerpc-4.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - An implementation for the newly added hv_ops->flush() for the OPAL
   hvc console driver backends, I forgot to apply this after merging the
   hvc driver changes before the merge window.

 - Enable all PCI bridges at boot on powernv, to avoid races when
   multiple children of a bridge try to enable it simultaneously. This
   is a workaround until the PCI core can be enhanced to fix the races.

 - A fix to query PowerVM for the correct system topology at boot before
   initialising sched domains, seen in some configurations to cause
   broken scheduling etc.

 - A fix for pte_access_permitted() on "nohash" platforms.

 - Two commits to fix SIGBUS when using remap_pfn_range() seen on Power9
   due to a workaround when using the nest MMU (GPUs, accelerators).

 - Another fix to the VFIO code used by KVM, the previous fix had some
   bugs which caused guests to not start in some configurations.

 - A handful of other minor fixes.

Thanks to: Aneesh Kumar K.V, Benjamin Herrenschmidt, Christophe Leroy,
Hari Bathini, Luke Dashjr, Mahesh Salgaonkar, Nicholas Piggin, Paul
Mackerras, Srikar Dronamraju.

* tag 'powerpc-4.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/mce: Fix SLB rebolting during MCE recovery path.
  KVM: PPC: Book3S: Fix guest DMA when guest partially backed by THP pages
  powerpc/mm/radix: Only need the Nest MMU workaround for R -> RW transition
  powerpc/mm/books3s: Add new pte bit to mark pte temporarily invalid.
  powerpc/nohash: fix pte_access_permitted()
  powerpc/topology: Get topology for shared processors at boot
  powerpc64/ftrace: Include ftrace.h needed for enable/disable calls
  powerpc/powernv/pci: Work around races in PCI bridge enabling
  powerpc/fadump: cleanup crash memory ranges support
  powerpc/powernv: provide a console flush operation for opal hvc driver
  powerpc/traps: Avoid rate limit messages from show unhandled signals
  powerpc/64s: Fix PACA_IRQ_HARD_DIS accounting in idle_power4()

2 files changed, 89 insertions, 31 deletions

diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 404c379db168..38fe4087484a 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -370,12 +370,8 @@ static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, b
 	olen = cpu_to_be64(total_len);
 	rc = opal_console_write(vtermno, &olen, data);
 	if (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		if (rc == OPAL_BUSY_EVENT) {
-			mdelay(OPAL_BUSY_DELAY_MS);
+		if (rc == OPAL_BUSY_EVENT)
 			opal_poll_events(NULL);
-		} else if (rc == OPAL_BUSY_EVENT) {
-			mdelay(OPAL_BUSY_DELAY_MS);
-		}
 		written = -EAGAIN;
 		goto out;
 	}
@@ -401,15 +397,6 @@ out:
 	if (atomic)
 		spin_unlock_irqrestore(&opal_write_lock, flags);
 
-	/* In the -EAGAIN case, callers loop, so we have to flush the console
-	 * here in case they have interrupts off (and we don't want to wait
-	 * for async flushing if we can make immediate progress here). If
-	 * necessary the API could be made entirely non-flushing if the
-	 * callers had a ->flush API to use.
-	 */
-	if (written == -EAGAIN)
-		opal_flush_console(vtermno);
-
 	return written;
 }
 
@@ -429,40 +416,74 @@ int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len)
 	return __opal_put_chars(vtermno, data, total_len, true);
 }
 
-int opal_flush_console(uint32_t vtermno)
+static s64 __opal_flush_console(uint32_t vtermno)
 {
 	s64 rc;
 
 	if (!opal_check_token(OPAL_CONSOLE_FLUSH)) {
 		__be64 evt;
 
-		WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n");
 		/*
 		 * If OPAL_CONSOLE_FLUSH is not implemented in the firmware,
 		 * the console can still be flushed by calling the polling
 		 * function while it has OPAL_EVENT_CONSOLE_OUTPUT events.
 		 */
-		do {
-			opal_poll_events(&evt);
-		} while (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT);
+		WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n");
+
+		opal_poll_events(&evt);
+		if (!(be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT))
+			return OPAL_SUCCESS;
+		return OPAL_BUSY;
 
-		return OPAL_SUCCESS;
+	} else {
+		rc = opal_console_flush(vtermno);
+		if (rc == OPAL_BUSY_EVENT) {
+			opal_poll_events(NULL);
+			rc = OPAL_BUSY;
+		}
+		return rc;
 	}
 
-	do  {
-		rc = OPAL_BUSY;
-		while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-			rc = opal_console_flush(vtermno);
-			if (rc == OPAL_BUSY_EVENT) {
-				mdelay(OPAL_BUSY_DELAY_MS);
-				opal_poll_events(NULL);
-			} else if (rc == OPAL_BUSY) {
-				mdelay(OPAL_BUSY_DELAY_MS);
+}
+
+/*
+ * opal_flush_console spins until the console is flushed
+ */
+int opal_flush_console(uint32_t vtermno)
+{
+	for (;;) {
+		s64 rc = __opal_flush_console(vtermno);
+
+		if (rc == OPAL_BUSY || rc == OPAL_PARTIAL) {
+			mdelay(1);
+			continue;
+		}
+
+		return opal_error_code(rc);
+	}
+}
+
+/*
+ * opal_flush_chars is an hvc interface that sleeps until the console is
+ * flushed if wait, otherwise it will return -EBUSY if the console has data,
+ * -EAGAIN if it has data and some of it was flushed.
+ */
+int opal_flush_chars(uint32_t vtermno, bool wait)
+{
+	for (;;) {
+		s64 rc = __opal_flush_console(vtermno);
+
+		if (rc == OPAL_BUSY || rc == OPAL_PARTIAL) {
+			if (wait) {
+				msleep(OPAL_BUSY_DELAY_MS);
+				continue;
 			}
+			if (rc == OPAL_PARTIAL)
+				return -EAGAIN;
 		}
-	} while (rc == OPAL_PARTIAL); /* More to flush */
 
-	return opal_error_code(rc);
+		return opal_error_code(rc);
+	}
 }
 
 static int opal_recover_mce(struct pt_regs *regs,
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 4e6302bf4073..cde710297a4e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3228,12 +3228,49 @@ static void pnv_pci_ioda_create_dbgfs(void)
 #endif /* CONFIG_DEBUG_FS */
 }
 
+static void pnv_pci_enable_bridge(struct pci_bus *bus)
+{
+	struct pci_dev *dev = bus->self;
+	struct pci_bus *child;
+
+	/* Empty bus ? bail */
+	if (list_empty(&bus->devices))
+		return;
+
+	/*
+	 * If there's a bridge associated with that bus enable it. This works
+	 * around races in the generic code if the enabling is done during
+	 * parallel probing. This can be removed once those races have been
+	 * fixed.
+	 */
+	if (dev) {
+		int rc = pci_enable_device(dev);
+		if (rc)
+			pci_err(dev, "Error enabling bridge (%d)\n", rc);
+		pci_set_master(dev);
+	}
+
+	/* Perform the same to child busses */
+	list_for_each_entry(child, &bus->children, node)
+		pnv_pci_enable_bridge(child);
+}
+
+static void pnv_pci_enable_bridges(void)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node)
+		pnv_pci_enable_bridge(hose->bus);
+}
+
 static void pnv_pci_ioda_fixup(void)
 {
 	pnv_pci_ioda_setup_PEs();
 	pnv_pci_ioda_setup_iommu_api();
 	pnv_pci_ioda_create_dbgfs();
 
+	pnv_pci_enable_bridges();
+
 #ifdef CONFIG_EEH
 	pnv_eeh_post_init();
 #endif