Merge tag 'powerpc-3.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc updates from Michael Ellerman:

 - Update of all defconfigs

 - Addition of a bunch of config options to modernise our defconfigs

 - Some PS3 updates from Geoff

 - Optimised memcmp for 64 bit from Anton

 - Fix for kprobes that allows 'perf probe' to work from Naveen

 - Several cxl updates from Ian & Ryan

 - Expanded support for the '24x7' PMU from Cody & Sukadev

 - Freescale updates from Scott:
    "Highlights include 8xx optimizations, some more work on datapath
     device tree content, e300 machine check support, t1040 corenet
     error reporting, and various cleanups and fixes"

* tag 'powerpc-3.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (102 commits)
  cxl: Add missing return statement after handling AFU errror
  cxl: Fail AFU initialisation if an invalid configuration record is found
  cxl: Export optional AFU configuration record in sysfs
  powerpc/mm: Warn on flushing tlb page in kernel context
  powerpc/powernv: Add OPAL soft-poweroff routine
  powerpc/perf/hv-24x7: Document sysfs event description entries
  powerpc/perf/hv-gpci: add the remaining gpci requests
  powerpc/perf/{hv-gpci, hv-common}: generate requests with counters annotated
  powerpc/perf/hv-24x7: parse catalog and populate sysfs with events
  perf: define EVENT_DEFINE_RANGE_FORMAT_LITE helper
  perf: add PMU_EVENT_ATTR_STRING() helper
  perf: provide sysfs_show for struct perf_pmu_events_attr
  powerpc/kernel: Avoid initializing device-tree pointer twice
  powerpc: Remove old compile time disabled syscall tracing code
  powerpc/kernel: Make syscall_exit a local label
  cxl: Fix device_node reference counting
  powerpc/mm: bail out early when flushing TLB page
  powerpc: defconfigs: add MTD_SPI_NOR (new dependency for M25P80)
  perf/powerpc: reset event hw state when adding it to the PMU
  powerpc/qe: Use strlcpy()
  ...

6 files changed, 161 insertions, 60 deletions

diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index f241accc053d..6f3c5d33c3af 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,7 +1,7 @@
 obj-y                   += setup.o opal-wrappers.o opal.o opal-async.o
 obj-y                   += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y                   += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
-obj-y                   += opal-msglog.o opal-hmi.o
+obj-y                   += opal-msglog.o opal-hmi.o opal-power.o
 
 obj-$(CONFIG_SMP)       += smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_PCI)       += pci.o pci-p5ioc2.o pci-ioda.o
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 1d19e7917d7f..e261869adc86 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -68,6 +68,17 @@ static int powernv_eeh_init(void)
 
                 if (phb->model == PNV_PHB_MODEL_P7IOC)
                         eeh_add_flag(EEH_ENABLE_IO_FOR_LOG);
+
+                /*
+                 * PE#0 should be regarded as valid by EEH core
+                 * if it's not the reserved one. Currently, we
+                 * have the reserved PE#0 and PE#127 for PHB3
+                 * and P7IOC separately. So we should regard
+                 * PE#0 as valid for P7IOC.
+                 */
+                if (phb->ioda.reserved_pe != 0)
+                        eeh_add_flag(EEH_VALID_PE_ZERO);
+
                 break;
         }
 
diff --git a/arch/powerpc/platforms/powernv/opal-power.c b/arch/powerpc/platforms/powernv/opal-power.c
new file mode 100644
index 000000000000..48bf5b080bcf
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-power.c
@@ -0,0 +1,65 @@
+/*
+ * PowerNV OPAL power control for graceful shutdown handling
+ *
+ * Copyright 2015 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/notifier.h>
+
+#include <asm/opal.h>
+#include <asm/machdep.h>
+
+#define SOFT_OFF 0x00
+#define SOFT_REBOOT 0x01
+
+static int opal_power_control_event(struct notifier_block *nb,
+                                    unsigned long msg_type, void *msg)
+{
+        struct opal_msg *power_msg = msg;
+        uint64_t type;
+
+        type = be64_to_cpu(power_msg->params[0]);
+
+        switch (type) {
+        case SOFT_REBOOT:
+                /* Fall through. The service processor is responsible for
+                 * bringing the machine back up */
+        case SOFT_OFF:
+                pr_info("OPAL: poweroff requested\n");
+                orderly_poweroff(true);
+                break;
+        default:
+                pr_err("OPAL: power control type unexpected %016llx\n", type);
+        }
+
+        return 0;
+}
+
+static struct notifier_block opal_power_control_nb = {
+        .notifier_call  = opal_power_control_event,
+        .next           = NULL,
+        .priority       = 0,
+};
+
+static int __init opal_power_control_init(void)
+{
+        int ret;
+
+        ret = opal_message_notifier_register(OPAL_MSG_SHUTDOWN,
+                                             &opal_power_control_nb);
+        if (ret) {
+                pr_err("%s: Can't register OPAL event notifier (%d)\n",
+                                __func__, ret);
+                return ret;
+        }
+
+        return 0;
+}
+machine_subsys_initcall(powernv, opal_power_control_init);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index f10b9ec8c1f5..18fd4e71c9c1 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -208,7 +208,7 @@ static int __init opal_register_exception_handlers(void)
          * start catching/handling HMI directly in Linux.
          */
         if (!opal_check_token(OPAL_HANDLE_HMI)) {
-                pr_info("opal: Old firmware detected, OPAL handles HMIs.\n");
+                pr_info("Old firmware detected, OPAL handles HMIs.\n");
                 opal_register_exception_handler(
                                 OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
                                 0, glue);
@@ -667,7 +667,13 @@ static void __init opal_dump_region_init(void)
 
         /* Register kernel log buffer */
         addr = log_buf_addr_get();
+        if (addr == NULL)
+                return;
+
         size = log_buf_len_get();
+        if (size == 0)
+                return;
+
         rc = opal_register_dump_region(OPAL_DUMP_REGION_LOG_BUF,
                                        __pa(addr), size);
         /* Don't warn if this is just an older OPAL that doesn't
@@ -695,15 +701,54 @@ static void opal_i2c_create_devs(void)
                 of_platform_device_create(np, NULL, NULL);
 }
 
+static void __init opal_irq_init(struct device_node *dn)
+{
+        const __be32 *irqs;
+        int i, irqlen;
+
+        /* Get interrupt property */
+        irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
+        opal_irq_count = irqs ? (irqlen / 4) : 0;
+        pr_debug("Found %d interrupts reserved for OPAL\n", opal_irq_count);
+        if (!opal_irq_count)
+                return;
+
+        /* Install interrupt handlers */
+        opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
+        for (i = 0; irqs && i < opal_irq_count; i++, irqs++) {
+                unsigned int irq, virq;
+                int rc;
+
+                /* Get hardware and virtual IRQ */
+                irq = be32_to_cpup(irqs);
+                virq = irq_create_mapping(NULL, irq);
+                if (virq == NO_IRQ) {
+                        pr_warn("Failed to map irq 0x%x\n", irq);
+                        continue;
+                }
+
+                /* Install interrupt handler */
+                rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
+                if (rc) {
+                        irq_dispose_mapping(virq);
+                        pr_warn("Error %d requesting irq %d (0x%x)\n",
+                                 rc, virq, irq);
+                        continue;
+                }
+
+                /* Cache IRQ */
+                opal_irqs[i] = virq;
+        }
+}
+
 static int __init opal_init(void)
 {
         struct device_node *np, *consoles;
-        const __be32 *irqs;
-        int rc, i, irqlen;
+        int rc;
 
         opal_node = of_find_node_by_path("/ibm,opal");
         if (!opal_node) {
-                pr_warn("opal: Node not found\n");
+                pr_warn("Device node not found\n");
                 return -ENODEV;
         }
 
@@ -725,24 +770,7 @@ static int __init opal_init(void)
         opal_i2c_create_devs();
 
         /* Find all OPAL interrupts and request them */
-        irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
-        pr_debug("opal: Found %d interrupts reserved for OPAL\n",
-                 irqs ? (irqlen / 4) : 0);
-        opal_irq_count = irqlen / 4;
-        opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
-        for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
-                unsigned int hwirq = be32_to_cpup(irqs);
-                unsigned int irq = irq_create_mapping(NULL, hwirq);
-                if (irq == NO_IRQ) {
-                        pr_warning("opal: Failed to map irq 0x%x\n", hwirq);
-                        continue;
-                }
-                rc = request_irq(irq, opal_interrupt, 0, "opal", NULL);
-                if (rc)
-                        pr_warning("opal: Error %d requesting irq %d"
-                                   " (0x%x)\n", rc, irq, hwirq);
-                opal_irqs[i] = irq;
-        }
+        opal_irq_init(opal_node);
 
         /* Create "opal" kobject under /sys/firmware */
         rc = opal_sysfs_init();
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index fac88ed8a915..6c9ff2b95119 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -75,6 +75,28 @@ static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 #define pe_info(pe, fmt, ...)                                   \
         pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
 
+static bool pnv_iommu_bypass_disabled __read_mostly;
+
+static int __init iommu_setup(char *str)
+{
+        if (!str)
+                return -EINVAL;
+
+        while (*str) {
+                if (!strncmp(str, "nobypass", 8)) {
+                        pnv_iommu_bypass_disabled = true;
+                        pr_info("PowerNV: IOMMU bypass window disabled.\n");
+                        break;
+                }
+                str += strcspn(str, ",");
+                if (*str == ',')
+                        str++;
+        }
+
+        return 0;
+}
+early_param("iommu", iommu_setup);
+
 /*
  * stdcix is only supposed to be used in hypervisor real mode as per
  * the architecture spec
@@ -357,6 +379,9 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
         phb->ioda.m64_segsize = phb->ioda.m64_size / phb->ioda.total_pe;
         phb->ioda.m64_base = pci_addr;
 
+        pr_info(" MEM64 0x%016llx..0x%016llx -> 0x%016llx\n",
+                        res->start, res->end, pci_addr);
+
         /* Use last M64 BAR to cover M64 window */
         phb->ioda.m64_bar_idx = 15;
         phb->init_m64 = pnv_ioda2_init_m64;
@@ -1348,7 +1373,9 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
                 pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 
         /* Also create a bypass window */
-        pnv_pci_ioda2_setup_bypass_pe(phb, pe);
+        if (!pnv_iommu_bypass_disabled)
+                pnv_pci_ioda2_setup_bypass_pe(phb, pe);
+
         return;
 fail:
         if (pe->tce32_seg >= 0)
@@ -1460,15 +1487,15 @@ static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 
 #ifdef CONFIG_CXL_BASE
 
-struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev)
+struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
 {
         struct pci_controller *hose = pci_bus_to_host(dev->bus);
 
-        return hose->dn;
+        return of_node_get(hose->dn);
 }
-EXPORT_SYMBOL(pnv_pci_to_phb_node);
+EXPORT_SYMBOL(pnv_pci_get_phb_node);
 
-int pnv_phb_to_cxl(struct pci_dev *dev)
+int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode)
 {
         struct pci_controller *hose = pci_bus_to_host(dev->bus);
         struct pnv_phb *phb = hose->private_data;
@@ -1481,13 +1508,13 @@ int pnv_phb_to_cxl(struct pci_dev *dev)
 
         pe_info(pe, "Switching PHB to CXL\n");
 
-        rc = opal_pci_set_phb_cxl_mode(phb->opal_id, 1, pe->pe_number);
+        rc = opal_pci_set_phb_cxl_mode(phb->opal_id, mode, pe->pe_number);
         if (rc)
                 dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
 
         return rc;
 }
-EXPORT_SYMBOL(pnv_phb_to_cxl);
+EXPORT_SYMBOL(pnv_phb_to_cxl_mode);
 
 /* Find PHB for cxl dev and allocate MSI hwirqs?
  * Returns the absolute hardware IRQ number
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 4945e87f12dc..e69142f4af08 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -781,35 +781,6 @@ static void pnv_p7ioc_rc_quirk(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk);
 
-static int pnv_pci_probe_mode(struct pci_bus *bus)
-{
-        struct pci_controller *hose = pci_bus_to_host(bus);
-        const __be64 *tstamp;
-        u64 now, target;
-
-
-        /* We hijack this as a way to ensure we have waited long
-         * enough since the reset was lifted on the PCI bus
-         */
-        if (bus != hose->bus)
-                return PCI_PROBE_NORMAL;
-        tstamp = of_get_property(hose->dn, "reset-clear-timestamp", NULL);
-        if (!tstamp || !*tstamp)
-                return PCI_PROBE_NORMAL;
-
-        now = mftb() / tb_ticks_per_usec;
-        target = (be64_to_cpup(tstamp) / tb_ticks_per_usec)
-                + PCI_RESET_DELAY_US;
-
-        pr_devel("pci %04d: Reset target: 0x%llx now: 0x%llx\n",
-                 hose->global_number, target, now);
-
-        if (now < target)
-                msleep((target - now + 999) / 1000);
-
-        return PCI_PROBE_NORMAL;
-}
-
 void __init pnv_pci_init(void)
 {
         struct device_node *np;
@@ -856,7 +827,6 @@ void __init pnv_pci_init(void)
         ppc_md.tce_build_rm = pnv_tce_build_rm;
         ppc_md.tce_free_rm = pnv_tce_free_rm;
         ppc_md.tce_get = pnv_tce_get;
-        ppc_md.pci_probe_mode = pnv_pci_probe_mode;
         set_pci_dma_ops(&dma_iommu_ops);
 
         /* Configure MSIs */