Merge tag 'powerpc-3.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc updates from Michael Ellerman:
 "Some nice cleanups like removing bootmem, and removal of
  __get_cpu_var().

  There is one patch to mm/gup.c.  This is the generic GUP
  implementation, but is only used by us and arm(64).  We have an ack
  from Steve Capper, and although we didn't get an ack from Andrew he
  told us to take the patch through the powerpc tree.

  There's one cxl patch.  This is in drivers/misc, but Greg said he was
  happy for us to manage fixes for it.

  There is an infrastructure patch to support an IPMI driver for OPAL.

  There is also an RTC driver for OPAL.  We weren't able to get any
  response from the RTC maintainer, Alessandro Zummo, so in the end we
  just merged the driver.

  The usual batch of Freescale updates from Scott"

* tag 'powerpc-3.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (101 commits)
  powerpc/powernv: Return to cpu offline loop when finished in KVM guest
  powerpc/book3s: Fix partial invalidation of TLBs in MCE code.
  powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault
  powerpc/xmon: Cleanup the breakpoint flags
  powerpc/xmon: Enable HW instruction breakpoint on POWER8
  powerpc/mm/thp: Use tlbiel if possible
  powerpc/mm/thp: Remove code duplication
  powerpc/mm/hugetlb: Sanity check gigantic hugepage count
  powerpc/oprofile: Disable pagefaults during user stack read
  powerpc/mm: Check for matching hpte without taking hpte lock
  powerpc: Drop useless warning in eeh_init()
  powerpc/powernv: Cleanup unused MCE definitions/declarations.
  powerpc/eeh: Dump PHB diag-data early
  powerpc/eeh: Recover EEH error on ownership change for BCM5719
  powerpc/eeh: Set EEH_PE_RESET on PE reset
  powerpc/eeh: Refactor eeh_reset_pe()
  powerpc: Remove more traces of bootmem
  powerpc/pseries: Initialise nvram_pstore_info's buf_lock
  cxl: Name interrupts in /proc/interrupt
  cxl: Return error to PSL if IRQ demultiplexing fails & print clearer warning
  ...

12 files changed, 261 insertions, 147 deletions

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index eba9cb10619..2809c989528 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -11,7 +11,6 @@
  * (at your option) any later version.
  */
 
-#include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -354,6 +353,9 @@ static int ioda_eeh_get_phb_state(struct eeh_pe *pe)
 	} else if (!(pe->state & EEH_PE_ISOLATED)) {
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
@@ -373,7 +375,7 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 	 * moving forward, we have to return operational
 	 * state during PE reset.
 	 */
-	if (pe->state & EEH_PE_CFG_BLOCKED) {
+	if (pe->state & EEH_PE_RESET) {
 		result = (EEH_STATE_MMIO_ACTIVE  |
 			  EEH_STATE_DMA_ACTIVE   |
 			  EEH_STATE_MMIO_ENABLED |
@@ -452,6 +454,9 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
@@ -731,7 +736,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
 			    char *drv_log, unsigned long len)
 {
-	pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+	if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
+		pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
 	return 0;
 }
@@ -1087,6 +1093,10 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		    !((*pe)->state & EEH_PE_ISOLATED)) {
 			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
 			ioda_eeh_phb_diag(*pe);
+
+			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+				pnv_pci_dump_phb_diag_data((*pe)->phb,
+							   (*pe)->data);
 		}
 
 		/*
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index e462ab947d1..693b6cdac69 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -71,6 +71,7 @@ int opal_async_get_token_interruptible(void)
 
 	return token;
 }
+EXPORT_SYMBOL_GPL(opal_async_get_token_interruptible);
 
 int __opal_async_release_token(int token)
 {
@@ -102,6 +103,7 @@ int opal_async_release_token(int token)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opal_async_release_token);
 
 int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
 {
@@ -120,6 +122,7 @@ int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opal_async_wait_response);
 
 static int opal_async_comp_event(struct notifier_block *nb,
 		unsigned long msg_type, void *msg)
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index 499707ddaa9..37dbee15769 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -15,6 +15,8 @@
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 #include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/of_platform.h>
 
 #include <asm/opal.h>
 #include <asm/firmware.h>
@@ -43,7 +45,7 @@ unsigned long __init opal_get_boot_time(void)
 	long rc = OPAL_BUSY;
 
 	if (!opal_check_token(OPAL_RTC_READ))
-		goto out;
+		return 0;
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
@@ -53,62 +55,33 @@ unsigned long __init opal_get_boot_time(void)
 			mdelay(10);
 	}
 	if (rc != OPAL_SUCCESS)
-		goto out;
+		return 0;
 
 	y_m_d = be32_to_cpu(__y_m_d);
 	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, &tm);
 	return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
 		      tm.tm_hour, tm.tm_min, tm.tm_sec);
-out:
-	ppc_md.get_rtc_time = NULL;
-	ppc_md.set_rtc_time = NULL;
-	return 0;
 }
 
-void opal_get_rtc_time(struct rtc_time *tm)
+static __init int opal_time_init(void)
 {
-	long rc = OPAL_BUSY;
-	u32 y_m_d;
-	u64 h_m_s_ms;
-	__be32 __y_m_d;
-	__be64 __h_m_s_ms;
+	struct platform_device *pdev;
+	struct device_node *rtc;
 
-	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
-			opal_poll_events(NULL);
+	rtc = of_find_node_by_path("/ibm,opal/rtc");
+	if (rtc) {
+		pdev = of_platform_device_create(rtc, "opal-rtc", NULL);
+		of_node_put(rtc);
+	} else {
+		if (opal_check_token(OPAL_RTC_READ) ||
+		    opal_check_token(OPAL_READ_TPO))
+			pdev = platform_device_register_simple("opal-rtc", -1,
+							       NULL, 0);
 		else
-			mdelay(10);
+			return -ENODEV;
 	}
-	if (rc != OPAL_SUCCESS)
-		return;
-	y_m_d = be32_to_cpu(__y_m_d);
-	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
-	opal_to_tm(y_m_d, h_m_s_ms, tm);
-}
-
-int opal_set_rtc_time(struct rtc_time *tm)
-{
-	long rc = OPAL_BUSY;
-	u32 y_m_d = 0;
-	u64 h_m_s_ms = 0;
-
-	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
-	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
-	y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
-	y_m_d |= ((u32)bin2bcd(tm->tm_mday));
-
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
 
-	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_rtc_write(y_m_d, h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
-			opal_poll_events(NULL);
-		else
-			mdelay(10);
-	}
-	return rc == OPAL_SUCCESS ? 0 : -EIO;
+	return PTR_ERR_OR_ZERO(pdev);
 }
+machine_subsys_initcall(powernv, opal_time_init);
diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c
index ae14c40b4b1..e11273b2386 100644
--- a/arch/powerpc/platforms/powernv/opal-tracepoints.c
+++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c
@@ -48,7 +48,7 @@ void __trace_opal_entry(unsigned long opcode, unsigned long *args)
 
 	local_irq_save(flags);
 
-	depth = &__get_cpu_var(opal_trace_depth);
+	depth = this_cpu_ptr(&opal_trace_depth);
 
 	if (*depth)
 		goto out;
@@ -69,7 +69,7 @@ void __trace_opal_exit(long opcode, unsigned long retval)
 
 	local_irq_save(flags);
 
-	depth = &__get_cpu_var(opal_trace_depth);
+	depth = this_cpu_ptr(&opal_trace_depth);
 
 	if (*depth)
 		goto out;
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index feb549aa3ee..0a299be588a 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -18,7 +18,7 @@
 	.section	".text"
 
 #ifdef CONFIG_TRACEPOINTS
-#ifdef CONFIG_JUMP_LABEL
+#ifdef HAVE_JUMP_LABEL
 #define OPAL_BRANCH(LABEL)					\
 	ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key)
 #else
@@ -250,3 +250,7 @@ OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
 OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
+OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
+OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
+OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
+OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index d019b081df9..cb0b6de79cd 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -50,7 +50,6 @@ static int mc_recoverable_range_len;
 
 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;
 static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
@@ -644,6 +643,16 @@ static void __init opal_dump_region_init(void)
 		pr_warn("DUMP: Failed to register kernel log buffer. "
 			"rc = %d\n", rc);
 }
+
+static void opal_ipmi_init(struct device_node *opal_node)
+{
+	struct device_node *np;
+
+	for_each_child_of_node(opal_node, np)
+		if (of_device_is_compatible(np, "ibm,opal-ipmi"))
+			of_platform_device_create(np, NULL, NULL);
+}
+
 static int __init opal_init(void)
 {
 	struct device_node *np, *consoles;
@@ -707,6 +716,8 @@ static int __init opal_init(void)
 		opal_msglog_init();
 	}
 
+	opal_ipmi_init(opal_node);
+
 	return 0;
 }
 machine_subsys_initcall(powernv, opal_init);
@@ -742,6 +753,8 @@ void opal_shutdown(void)
 
 /* Export this so that test modules can use it */
 EXPORT_SYMBOL_GPL(opal_invalid_call);
+EXPORT_SYMBOL_GPL(opal_ipmi_send);
+EXPORT_SYMBOL_GPL(opal_ipmi_recv);
 
 /* Convert a region of vmalloc memory to an opal sg list */
 struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
@@ -805,3 +818,9 @@ void opal_free_sg_list(struct opal_sg_list *sg)
 			sg = NULL;
 	}
 }
+
+EXPORT_SYMBOL_GPL(opal_poll_events);
+EXPORT_SYMBOL_GPL(opal_rtc_read);
+EXPORT_SYMBOL_GPL(opal_rtc_write);
+EXPORT_SYMBOL_GPL(opal_tpo_read);
+EXPORT_SYMBOL_GPL(opal_tpo_write);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3ba435ec3dc..fac88ed8a91 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -91,6 +91,24 @@ static inline bool pnv_pci_is_mem_pref_64(unsigned long flags)
 		(IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
 }
 
+static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
+{
+	if (!(pe_no >= 0 && pe_no < phb->ioda.total_pe)) {
+		pr_warn("%s: Invalid PE %d on PHB#%x\n",
+			__func__, pe_no, phb->hose->global_number);
+		return;
+	}
+
+	if (test_and_set_bit(pe_no, phb->ioda.pe_alloc)) {
+		pr_warn("%s: PE %d was assigned on PHB#%x\n",
+			__func__, pe_no, phb->hose->global_number);
+		return;
+	}
+
+	phb->ioda.pe_array[pe_no].phb = phb;
+	phb->ioda.pe_array[pe_no].pe_number = pe_no;
+}
+
 static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
 	unsigned long pe;
@@ -172,7 +190,7 @@ fail:
 	return -EIO;
 }
 
-static void pnv_ioda2_alloc_m64_pe(struct pnv_phb *phb)
+static void pnv_ioda2_reserve_m64_pe(struct pnv_phb *phb)
 {
 	resource_size_t sgsz = phb->ioda.m64_segsize;
 	struct pci_dev *pdev;
@@ -185,16 +203,15 @@ static void pnv_ioda2_alloc_m64_pe(struct pnv_phb *phb)
 	 * instead of root bus.
 	 */
 	list_for_each_entry(pdev, &phb->hose->bus->devices, bus_list) {
-		for (i = PCI_BRIDGE_RESOURCES;
-		     i <= PCI_BRIDGE_RESOURCE_END; i++) {
-			r = &pdev->resource[i];
+		for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) {
+			r = &pdev->resource[PCI_BRIDGE_RESOURCES + i];
 			if (!r->parent ||
 			    !pnv_pci_is_mem_pref_64(r->flags))
 				continue;
 
 			base = (r->start - phb->ioda.m64_base) / sgsz;
 			for (step = 0; step < resource_size(r) / sgsz; step++)
-				set_bit(base + step, phb->ioda.pe_alloc);
+				pnv_ioda_reserve_pe(phb, base + step);
 		}
 	}
 }
@@ -287,8 +304,6 @@ done:
 	while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe, i + 1)) <
 		phb->ioda.total_pe) {
 		pe = &phb->ioda.pe_array[i];
-		pe->phb = phb;
-		pe->pe_number = i;
 
 		if (!master_pe) {
 			pe->flags |= PNV_IODA_PE_MASTER;
@@ -313,6 +328,12 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	const u32 *r;
 	u64 pci_addr;
 
+	/* FIXME: Support M64 for P7IOC */
+	if (phb->type != PNV_PHB_IODA2) {
+		pr_info("  Not support M64 window\n");
+		return;
+	}
+
 	if (!firmware_has_feature(FW_FEATURE_OPALv3)) {
 		pr_info("  Firmware too old to support M64 window\n");
 		return;
@@ -325,12 +346,6 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 		return;
 	}
 
-	/* FIXME: Support M64 for P7IOC */
-	if (phb->type != PNV_PHB_IODA2) {
-		pr_info("  Not support M64 window\n");
-		return;
-	}
-
 	res = &hose->mem_resources[1];
 	res->start = of_translate_address(dn, r + 2);
 	res->end = res->start + of_read_number(r + 4, 2) - 1;
@@ -345,7 +360,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	/* Use last M64 BAR to cover M64 window */
 	phb->ioda.m64_bar_idx = 15;
 	phb->init_m64 = pnv_ioda2_init_m64;
-	phb->alloc_m64_pe = pnv_ioda2_alloc_m64_pe;
+	phb->reserve_m64_pe = pnv_ioda2_reserve_m64_pe;
 	phb->pick_m64_pe = pnv_ioda2_pick_m64_pe;
 }
 
@@ -358,7 +373,9 @@ static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)
 	/* Fetch master PE */
 	if (pe->flags & PNV_IODA_PE_SLAVE) {
 		pe = pe->master;
-		WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER));
+		if (WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER)))
+			return;
+
 		pe_no = pe->pe_number;
 	}
 
@@ -507,6 +524,106 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
 }
 #endif /* CONFIG_PCI_MSI */
 
+static int pnv_ioda_set_one_peltv(struct pnv_phb *phb,
+				  struct pnv_ioda_pe *parent,
+				  struct pnv_ioda_pe *child,
+				  bool is_add)
+{
+	const char *desc = is_add ? "adding" : "removing";
+	uint8_t op = is_add ? OPAL_ADD_PE_TO_DOMAIN :
+			      OPAL_REMOVE_PE_FROM_DOMAIN;
+	struct pnv_ioda_pe *slave;
+	long rc;
+
+	/* Parent PE affects child PE */
+	rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number,
+				child->pe_number, op);
+	if (rc != OPAL_SUCCESS) {
+		pe_warn(child, "OPAL error %ld %s to parent PELTV\n",
+			rc, desc);
+		return -ENXIO;
+	}
+
+	if (!(child->flags & PNV_IODA_PE_MASTER))
+		return 0;
+
+	/* Compound case: parent PE affects slave PEs */
+	list_for_each_entry(slave, &child->slaves, list) {
+		rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number,
+					slave->pe_number, op);
+		if (rc != OPAL_SUCCESS) {
+			pe_warn(slave, "OPAL error %ld %s to parent PELTV\n",
+				rc, desc);
+			return -ENXIO;
+		}
+	}
+
+	return 0;
+}
+
+static int pnv_ioda_set_peltv(struct pnv_phb *phb,
+			      struct pnv_ioda_pe *pe,
+			      bool is_add)
+{
+	struct pnv_ioda_pe *slave;
+	struct pci_dev *pdev;
+	int ret;
+
+	/*
+	 * Clear PE frozen state. If it's master PE, we need
+	 * clear slave PE frozen state as well.
+	 */
+	if (is_add) {
+		opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
+					  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+		if (pe->flags & PNV_IODA_PE_MASTER) {
+			list_for_each_entry(slave, &pe->slaves, list)
+				opal_pci_eeh_freeze_clear(phb->opal_id,
+							  slave->pe_number,
+							  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+		}
+	}
+
+	/*
+	 * Associate PE in PELT. We need add the PE into the
+	 * corresponding PELT-V as well. Otherwise, the error
+	 * originated from the PE might contribute to other
+	 * PEs.
+	 */
+	ret = pnv_ioda_set_one_peltv(phb, pe, pe, is_add);
+	if (ret)
+		return ret;
+
+	/* For compound PEs, any one affects all of them */
+	if (pe->flags & PNV_IODA_PE_MASTER) {
+		list_for_each_entry(slave, &pe->slaves, list) {
+			ret = pnv_ioda_set_one_peltv(phb, slave, pe, is_add);
+			if (ret)
+				return ret;
+		}
+	}
+
+	if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS))
+		pdev = pe->pbus->self;
+	else
+		pdev = pe->pdev->bus->self;
+	while (pdev) {
+		struct pci_dn *pdn = pci_get_pdn(pdev);
+		struct pnv_ioda_pe *parent;
+
+		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+			parent = &phb->ioda.pe_array[pdn->pe_number];
+			ret = pnv_ioda_set_one_peltv(phb, parent, pe, is_add);
+			if (ret)
+				return ret;
+		}
+
+		pdev = pdev->bus->self;
+	}
+
+	return 0;
+}
+
 static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
@@ -561,48 +678,36 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		return -ENXIO;
 	}
 
-	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
-				pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
-	if (rc)
-		pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
-	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
-				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+	/* Configure PELTV */
+	pnv_ioda_set_peltv(phb, pe, true);
 
-	/* Add to all parents PELT-V */
-	while (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);
-			/* XXX What to do in case of error ? */
-		}
-		parent = parent->bus->self;
-	}
 	/* Setup reverse map */
 	for (rid = pe->rid; rid < rid_end; rid++)
 		phb->ioda.pe_rmap[rid] = pe->pe_number;
 
 	/* Setup one MVTs on IODA1 */
-	if (phb->type == PNV_PHB_IODA1) {
-		pe->mve_number = pe->pe_number;
-		rc = opal_pci_set_mve(phb->opal_id, pe->mve_number,
-				      pe->pe_number);
+	if (phb->type != PNV_PHB_IODA1) {
+		pe->mve_number = 0;
+		goto out;
+	}
+
+	pe->mve_number = pe->pe_number;
+	rc = opal_pci_set_mve(phb->opal_id, pe->mve_number, pe->pe_number);
+	if (rc != OPAL_SUCCESS) {
+		pe_err(pe, "OPAL error %ld setting up MVE %d\n",
+		       rc, pe->mve_number);
+		pe->mve_number = -1;
+	} else {
+		rc = opal_pci_set_mve_enable(phb->opal_id,
+					     pe->mve_number, OPAL_ENABLE_MVE);
 		if (rc) {
-			pe_err(pe, "OPAL error %ld setting up MVE %d\n",
+			pe_err(pe, "OPAL error %ld enabling MVE %d\n",
 			       rc, pe->mve_number);
 			pe->mve_number = -1;
-		} else {
-			rc = opal_pci_set_mve_enable(phb->opal_id,
-						     pe->mve_number, OPAL_ENABLE_MVE);
-			if (rc) {
-				pe_err(pe, "OPAL error %ld enabling MVE %d\n",
-				       rc, pe->mve_number);
-				pe->mve_number = -1;
-			}
 		}
-	} else if (phb->type == PNV_PHB_IODA2)
-		pe->mve_number = 0;
+	}
 
+out:
 	return 0;
 }
 
@@ -837,8 +942,8 @@ static void pnv_pci_ioda_setup_PEs(void)
 		phb = hose->private_data;
 
 		/* M64 layout might affect PE allocation */
-		if (phb->alloc_m64_pe)
-			phb->alloc_m64_pe(phb);
+		if (phb->reserve_m64_pe)
+			phb->reserve_m64_pe(phb);
 
 		pnv_ioda_setup_PEs(hose->bus);
 	}
@@ -1834,19 +1939,14 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb_id = be64_to_cpup(prop64);
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
-	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (!phb) {
-		pr_err("  Out of memory !\n");
-		return;
-	}
+	phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0);
 
 	/* Allocate PCI controller */
-	memset(phb, 0, sizeof(struct pnv_phb));
 	phb->hose = hose = pcibios_alloc_controller(np);
 	if (!phb->hose) {
 		pr_err("  Can't allocate PCI controller for %s\n",
 		       np->full_name);
-		free_bootmem((unsigned long)phb, sizeof(struct pnv_phb));
+		memblock_free(__pa(phb), sizeof(struct pnv_phb));
 		return;
 	}
 
@@ -1913,8 +2013,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	}
 	pemap_off = size;
 	size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
-	aux = alloc_bootmem(size);
-	memset(aux, 0, size);
+	aux = memblock_virt_alloc(size, 0);
 	phb->ioda.pe_alloc = aux;
 	phb->ioda.m32_segmap = aux + m32map_off;
 	if (phb->type == PNV_PHB_IODA1)
@@ -1999,8 +2098,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		ioda_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
 	}
 
-	/* Configure M64 window */
-	if (phb->init_m64 && phb->init_m64(phb))
+	/* Remove M64 resource if we can't configure it successfully */
+	if (!phb->init_m64 || phb->init_m64(phb))
 		hose->mem_resources[1].flags = 0;
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 94ce3481490..6ef6d4d8e7e 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -122,12 +122,9 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 		return;
 	}
 
-	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (phb) {
-		memset(phb, 0, sizeof(struct pnv_phb));
-		phb->hose = pcibios_alloc_controller(np);
-	}
-	if (!phb || !phb->hose) {
+	phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0);
+	phb->hose = pcibios_alloc_controller(np);
+	if (!phb->hose) {
 		pr_err("  Failed to allocate PCI controller\n");
 		return;
 	}
@@ -196,16 +193,27 @@ void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
 	hub_id = be64_to_cpup(prop64);
 	pr_info(" HUB-ID : 0x%016llx\n", hub_id);
 
+	/* Count child PHBs and calculate TCE space per PHB */
+	for_each_child_of_node(np, phbn) {
+		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex"))
+			phb_count++;
+	}
+
+	if (phb_count <= 0) {
+		pr_info(" No PHBs for Hub %s\n", np->full_name);
+		return;
+	}
+
+	tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count);
+	pr_info(" Allocating %lld MB of TCE memory per PHB\n",
+		tce_per_phb >> 20);
+
 	/* Currently allocate 16M of TCE memory for every Hub
 	 *
 	 * XXX TODO: Make it chip local if possible
 	 */
-	tce_mem = __alloc_bootmem(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY,
-				  __pa(MAX_DMA_ADDRESS));
-	if (!tce_mem) {
-		pr_err(" Failed to allocate TCE Memory !\n");
-		return;
-	}
+	tce_mem = memblock_virt_alloc(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY);
 	pr_debug(" TCE    : 0x%016lx..0x%016lx\n",
 		__pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1);
 	rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem),
@@ -215,18 +223,6 @@ void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
 		return;
 	}
 
-	/* Count child PHBs */
-	for_each_child_of_node(np, phbn) {
-		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
-		    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex"))
-			phb_count++;
-	}
-
-	/* Calculate how much TCE space we can give per PHB */
-	tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count);
-	pr_info(" Allocating %lld MB of TCE memory per PHB\n",
-		tce_per_phb >> 20);
-
 	/* Initialize PHBs */
 	for_each_child_of_node(np, phbn) {
 		if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 540fc6dd56b..4945e87f12d 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 34d29eb2a4d..6c02ff8dd69 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -130,7 +130,7 @@ struct pnv_phb {
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	void (*shutdown)(struct pnv_phb *phb);
 	int (*init_m64)(struct pnv_phb *phb);
-	void (*alloc_m64_pe)(struct pnv_phb *phb);
+	void (*reserve_m64_pe)(struct pnv_phb *phb);
 	int (*pick_m64_pe)(struct pnv_phb *phb, struct pci_bus *bus, int all);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 3f9546d8a51..30b1c3e298a 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -265,10 +265,8 @@ static unsigned long pnv_memory_block_size(void)
 static void __init pnv_setup_machdep_opal(void)
 {
 	ppc_md.get_boot_time = opal_get_boot_time;
-	ppc_md.get_rtc_time = opal_get_rtc_time;
-	ppc_md.set_rtc_time = opal_set_rtc_time;
 	ppc_md.restart = pnv_restart;
-	ppc_md.power_off = pnv_power_off;
+	pm_power_off = pnv_power_off;
 	ppc_md.halt = pnv_halt;
 	ppc_md.machine_check_exception = opal_machine_check;
 	ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery;
@@ -285,7 +283,7 @@ static void __init pnv_setup_machdep_rtas(void)
 		ppc_md.set_rtc_time = rtas_set_rtc_time;
 	}
 	ppc_md.restart = rtas_restart;
-	ppc_md.power_off = rtas_power_off;
+	pm_power_off = rtas_power_off;
 	ppc_md.halt = rtas_halt;
 }
 #endif /* CONFIG_PPC_POWERNV_RTAS */
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 4753958cd50..b716f666e48 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -149,6 +149,7 @@ static int pnv_smp_cpu_disable(void)
 static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
+	unsigned long srr1;
 
 	/* Standard hot unplug procedure */
 	local_irq_disable();
@@ -165,13 +166,25 @@ static void pnv_smp_cpu_kill_self(void)
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
 		ppc64_runlatch_off();
-		power7_nap(1);
+		srr1 = power7_nap(1);
 		ppc64_runlatch_on();
 
-		/* Clear the IPI that woke us up */
-		icp_native_flush_interrupt();
-		local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
-		mb();
+		/*
+		 * If the SRR1 value indicates that we woke up due to
+		 * an external interrupt, then clear the interrupt.
+		 * We clear the interrupt before checking for the
+		 * reason, so as to avoid a race where we wake up for
+		 * some other reason, find nothing and clear the interrupt
+		 * just as some other cpu is sending us an interrupt.
+		 * If we returned from power7_nap as a result of
+		 * having finished executing in a KVM guest, then srr1
+		 * contains 0.
+		 */
+		if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) {
+			icp_native_flush_interrupt();
+			local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
+			smp_mb();
+		}
 
 		if (cpu_core_split_required())
 			continue;