8 files changed, 142 insertions, 25 deletions

diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index d3e840d643af..c24684c818ab 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -6,6 +6,7 @@ config PPC_POWERNV
         select PPC_ICP_NATIVE
         select PPC_P7_NAP
         select PPC_PCI_CHOICE if EMBEDDED
+        select EPAPR_BOOT
         default y
 
 config POWERNV_MSI
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index ade4463226c6..628c564ceadb 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
+#include <linux/slab.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 
@@ -28,6 +29,8 @@ struct opal {
 static struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
 extern u64 opal_mc_secondary_handler[];
+static unsigned int *opal_irqs;
+static unsigned int opal_irq_count;
 
 int __init early_init_dt_scan_opal(unsigned long node,
                                    const char *uname, int depth, void *data)
@@ -53,7 +56,11 @@ int __init early_init_dt_scan_opal(unsigned long node,
                  opal.entry, entryp, entrysz);
 
         powerpc_firmware_features |= FW_FEATURE_OPAL;
-        if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
+        if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
+                powerpc_firmware_features |= FW_FEATURE_OPALv2;
+                powerpc_firmware_features |= FW_FEATURE_OPALv3;
+                printk("OPAL V3 detected !\n");
+        } else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
                 powerpc_firmware_features |= FW_FEATURE_OPALv2;
                 printk("OPAL V2 detected !\n");
         } else {
@@ -144,6 +151,13 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
                                 rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
                 len = total_len;
                 rc = opal_console_write(vtermno, &len, data);
+
+                /* Closed or other error drop */
+                if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
+                    rc != OPAL_BUSY_EVENT) {
+                        written = total_len;
+                        break;
+                }
                 if (rc == OPAL_SUCCESS) {
                         total_len -= len;
                         data += len;
@@ -316,6 +330,8 @@ static int __init opal_init(void)
         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);
@@ -327,7 +343,19 @@ static int __init opal_init(void)
                 if (rc)
                         pr_warning("opal: Error %d requesting irq %d"
                                    " (0x%x)\n", rc, irq, hwirq);
+                opal_irqs[i] = irq;
         }
         return 0;
 }
 subsys_initcall(opal_init);
+
+void opal_shutdown(void)
+{
+        unsigned int i;
+
+        for (i = 0; i < opal_irq_count; i++) {
+                if (opal_irqs[i])
+                        free_irq(opal_irqs[i], 0);
+                opal_irqs[i] = 0;
+        }
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 1da578b7c1bf..9c9d15e4cdf2 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -68,16 +68,6 @@ define_pe_printk_level(pe_err, KERN_ERR);
 define_pe_printk_level(pe_warn, KERN_WARNING);
 define_pe_printk_level(pe_info, KERN_INFO);
 
-static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev)
-{
-        struct device_node *np;
-
-        np = pci_device_to_OF_node(dev);
-        if (!np)
-                return NULL;
-        return PCI_DN(np);
-}
-
 static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
         unsigned long pe;
@@ -110,7 +100,7 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
 {
         struct pci_controller *hose = pci_bus_to_host(dev->bus);
         struct pnv_phb *phb = hose->private_data;
-        struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
+        struct pci_dn *pdn = pci_get_pdn(dev);
 
         if (!pdn)
                 return NULL;
@@ -173,7 +163,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 
         /* Add to all parents PELT-V */
         while (parent) {
-                struct pci_dn *pdn = pnv_ioda_get_pdn(parent);
+                struct pci_dn *pdn = pci_get_pdn(parent);
                 if (pdn && pdn->pe_number != IODA_INVALID_PE) {
                         rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
                                                 pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
@@ -252,7 +242,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 {
         struct pci_controller *hose = pci_bus_to_host(dev->bus);
         struct pnv_phb *phb = hose->private_data;
-        struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
+        struct pci_dn *pdn = pci_get_pdn(dev);
         struct pnv_ioda_pe *pe;
         int pe_num;
 
@@ -323,7 +313,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
         struct pci_dev *dev;
 
         list_for_each_entry(dev, &bus->devices, bus_list) {
-                struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
+                struct pci_dn *pdn = pci_get_pdn(dev);
 
                 if (pdn == NULL) {
                         pr_warn("%s: No device node associated with device !\n",
@@ -436,7 +426,7 @@ static void pnv_pci_ioda_setup_PEs(void)
 
 static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
 {
-        struct pci_dn *pdn = pnv_ioda_get_pdn(pdev);
+        struct pci_dn *pdn = pci_get_pdn(pdev);
         struct pnv_ioda_pe *pe;
 
         /*
@@ -768,6 +758,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
                                   unsigned int is_64, struct msi_msg *msg)
 {
         struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
+        struct pci_dn *pdn = pci_get_pdn(dev);
         struct irq_data *idata;
         struct irq_chip *ichip;
         unsigned int xive_num = hwirq - phb->msi_base;
@@ -783,6 +774,10 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
         if (pe->mve_number < 0)
                 return -ENXIO;
 
+        /* Force 32-bit MSI on some broken devices */
+        if (pdn && pdn->force_32bit_msi)
+                is_64 = 0;
+
         /* Assign XIVE to PE */
         rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
         if (rc) {
@@ -1035,7 +1030,7 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev)
         if (!phb->initialized)
                 return 0;
 
-        pdn = pnv_ioda_get_pdn(dev);
+        pdn = pci_get_pdn(dev);
         if (!pdn || pdn->pe_number == IODA_INVALID_PE)
                 return -EINVAL;
 
@@ -1048,6 +1043,12 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
         return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
 }
 
+static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
+{
+        opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+                       OPAL_ASSERT_RESET);
+}
+
 void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 {
         struct pci_controller *hose;
@@ -1178,6 +1179,9 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
         /* Setup TCEs */
         phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 
+        /* Setup shutdown function for kexec */
+        phb->shutdown = pnv_pci_ioda_shutdown;
+
         /* Setup MSI support */
         pnv_pci_init_ioda_msis(phb);
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 55dfca844ddf..277343cc6a3d 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -47,6 +47,10 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
 {
         struct pci_controller *hose = pci_bus_to_host(pdev->bus);
         struct pnv_phb *phb = hose->private_data;
+        struct pci_dn *pdn = pci_get_pdn(pdev);
+
+        if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
+                return -ENODEV;
 
         return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
 }
@@ -367,7 +371,7 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
         while (npages--)
                 *(tcep++) = 0;
 
-        if (tbl->it_type & TCE_PCI_SWINV_CREATE)
+        if (tbl->it_type & TCE_PCI_SWINV_FREE)
                 pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
 }
 
@@ -450,6 +454,18 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
                 pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+void pnv_pci_shutdown(void)
+{
+        struct pci_controller *hose;
+
+        list_for_each_entry(hose, &hose_list, list_node) {
+                struct pnv_phb *phb = hose->private_data;
+
+                if (phb && phb->shutdown)
+                        phb->shutdown(phb);
+        }
+}
+
 /* Fixup wrong class code in p7ioc and p8 root complex */
 static void pnv_p7ioc_rc_quirk(struct pci_dev *dev)
 {
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 48dc4bb856a1..25d76c4df50b 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -86,6 +86,7 @@ struct pnv_phb {
         void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
         void (*fixup_phb)(struct pci_controller *hose);
         u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
+        void (*shutdown)(struct pnv_phb *phb);
 
         union {
                 struct {
@@ -158,4 +159,5 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
                                         u64 *startp, u64 *endp);
+
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 8a9df7f9667e..a1c6f83fc391 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -9,8 +9,10 @@ static inline void pnv_smp_init(void) { }
 
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
+extern void pnv_pci_shutdown(void);
 #else
 static inline void pnv_pci_init(void) { }
+static inline void pnv_pci_shutdown(void) { }
 #endif
 
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index db1ad1c8f68f..d4459bfc92f7 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -78,7 +78,9 @@ static void pnv_show_cpuinfo(struct seq_file *m)
         if (root)
                 model = of_get_property(root, "model", NULL);
         seq_printf(m, "machine\t\t: PowerNV %s\n", model);
-        if (firmware_has_feature(FW_FEATURE_OPALv2))
+        if (firmware_has_feature(FW_FEATURE_OPALv3))
+                seq_printf(m, "firmware\t: OPAL v3\n");
+        else if (firmware_has_feature(FW_FEATURE_OPALv2))
                 seq_printf(m, "firmware\t: OPAL v2\n");
         else if (firmware_has_feature(FW_FEATURE_OPAL))
                 seq_printf(m, "firmware\t: OPAL v1\n");
@@ -126,6 +128,17 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
+static void pnv_shutdown(void)
+{
+        /* Let the PCI code clear up IODA tables */
+        pnv_pci_shutdown();
+
+        /* And unregister all OPAL interrupts so they don't fire
+         * up while we kexec
+         */
+        opal_shutdown();
+}
+
 #ifdef CONFIG_KEXEC
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
@@ -187,6 +200,7 @@ define_machine(powernv) {
         .init_IRQ               = pnv_init_IRQ,
         .show_cpuinfo           = pnv_show_cpuinfo,
         .progress               = pnv_progress,
+        .machine_shutdown       = pnv_shutdown,
         .power_save             = power7_idle,
         .calibrate_decr         = generic_calibrate_decr,
 #ifdef CONFIG_KEXEC
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 6a3ecca5b725..88c9459c3e07 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -71,18 +71,68 @@ int pnv_smp_kick_cpu(int nr)
 
         BUG_ON(nr < 0 || nr >= NR_CPUS);
 
-        /* On OPAL v2 the CPU are still spinning inside OPAL itself,
-         * get them back now
+        /*
+         * If we already started or OPALv2 is not supported, we just
+         * kick the CPU via the PACA
          */
-        if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) {
-                pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu);
-                rc = opal_start_cpu(pcpu, start_here);
+        if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2))
+                goto kick;
+
+        /*
+         * At this point, the CPU can either be spinning on the way in
+         * from kexec or be inside OPAL waiting to be started for the
+         * first time. OPAL v3 allows us to query OPAL to know if it
+         * has the CPUs, so we do that
+         */
+        if (firmware_has_feature(FW_FEATURE_OPALv3)) {
+                uint8_t status;
+
+                rc = opal_query_cpu_status(pcpu, &status);
                 if (rc != OPAL_SUCCESS) {
-                        pr_warn("OPAL Error %ld starting CPU %d\n",
+                        pr_warn("OPAL Error %ld querying CPU %d state\n",
                                 rc, nr);
                         return -ENODEV;
                 }
+
+                /*
+                 * Already started, just kick it, probably coming from
+                 * kexec and spinning
+                 */
+                if (status == OPAL_THREAD_STARTED)
+                        goto kick;
+
+                /*
+                 * Available/inactive, let's kick it
+                 */
+                if (status == OPAL_THREAD_INACTIVE) {
+                        pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n",
+                                 nr, pcpu);
+                        rc = opal_start_cpu(pcpu, start_here);
+                        if (rc != OPAL_SUCCESS) {
+                                pr_warn("OPAL Error %ld starting CPU %d\n",
+                                        rc, nr);
+                                return -ENODEV;
+                        }
+                } else {
+                        /*
+                         * An unavailable CPU (or any other unknown status)
+                         * shouldn't be started. It should also
+                         * not be in the possible map but currently it can
+                         * happen
+                         */
+                        pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable"
+                                 " (status %d)...\n", nr, pcpu, status);
+                        return -ENODEV;
+                }
+        } else {
+                /*
+                 * On OPAL v2, we just kick it and hope for the best,
+                 * we must not test the error from opal_start_cpu() or
+                 * we would fail to get CPUs from kexec.
+                 */
+                opal_start_cpu(pcpu, start_here);
         }
+ kick:
         return smp_generic_kick_cpu(nr);
 }