10 files changed, 169 insertions, 442 deletions

diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 930898635c9f..e5e0ff466904 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -1,8 +1,11 @@
+ifeq ($(CONFIG_PPC64),y)
+EXTRA_CFLAGS            += -mno-minimal-toc
+endif
+
 obj-y                   := pci.o lpar.o hvCall.o nvram.o reconfig.o \
                            setup.o iommu.o ras.o rtasd.o pci_dlpar.o \
                            firmware.o
 obj-$(CONFIG_SMP)       += smp.o
-obj-$(CONFIG_IBMVIO)    += vio.o
 obj-$(CONFIG_XICS)      += xics.o
 obj-$(CONFIG_SCANLOG)   += scanlog.o
 obj-$(CONFIG_EEH)       += eeh.o eeh_cache.o eeh_driver.o eeh_event.o
diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c
index d4a402c5866c..98c23aec85be 100644
--- a/arch/powerpc/platforms/pseries/eeh_cache.c
+++ b/arch/powerpc/platforms/pseries/eeh_cache.c
@@ -304,6 +304,8 @@ void __init pci_addr_cache_build(void)
                 pci_addr_cache_insert_device(dev);
 
                 dn = pci_device_to_OF_node(dev);
+                if (!dn)
+                        continue;
                 pci_dev_get (dev);  /* matching put is in eeh_remove_device() */
                 PCI_DN(dn)->pcidev = dev;
         }
diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index 1fba695e32e8..0ec9a5445b95 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -23,9 +23,8 @@
  *
  */
 #include <linux/delay.h>
-#include <linux/irq.h>
 #include <linux/interrupt.h>
-#include <linux/notifier.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <asm/eeh.h>
 #include <asm/eeh_event.h>
@@ -202,7 +201,11 @@ static void eeh_report_failure(struct pci_dev *dev, void *userdata)
 
 static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
 {
-        int rc;
+        int cnt, rc;
+
+        /* pcibios will clear the counter; save the value */
+        cnt = pe_dn->eeh_freeze_count;
+
         if (bus)
                 pcibios_remove_pci_devices(bus);
 
@@ -241,6 +244,7 @@ static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
                 ssleep (5);
                 pcibios_add_pci_devices(bus);
         }
+        pe_dn->eeh_freeze_count = cnt;
 
         return 0;
 }
@@ -250,23 +254,29 @@ static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
  */
 #define MAX_WAIT_FOR_RECOVERY 15
 
-void handle_eeh_events (struct eeh_event *event)
+struct pci_dn * handle_eeh_events (struct eeh_event *event)
 {
         struct device_node *frozen_dn;
         struct pci_dn *frozen_pdn;
         struct pci_bus *frozen_bus;
         int rc = 0;
         enum pci_ers_result result = PCI_ERS_RESULT_NONE;
-        const char *pci_str, *drv_str;
+        const char *location, *pci_str, *drv_str;
 
         frozen_dn = find_device_pe(event->dn);
         frozen_bus = pcibios_find_pci_bus(frozen_dn);
 
         if (!frozen_dn) {
-                printk(KERN_ERR "EEH: Error: Cannot find partition endpoint for %s\n",
-                        pci_name(event->dev));
-                return;
+
+                location = (char *) get_property(event->dn, "ibm,loc-code", NULL);
+                location = location ? location : "unknown";
+                printk(KERN_ERR "EEH: Error: Cannot find partition endpoint "
+                                "for location=%s pci addr=%s\n",
+                        location, pci_name(event->dev));
+                return NULL;
         }
+        location = (char *) get_property(frozen_dn, "ibm,loc-code", NULL);
+        location = location ? location : "unknown";
 
         /* There are two different styles for coming up with the PE.
          * In the old style, it was the highest EEH-capable device
@@ -278,9 +288,10 @@ void handle_eeh_events (struct eeh_event *event)
                 frozen_bus = pcibios_find_pci_bus (frozen_dn->parent);
 
         if (!frozen_bus) {
-                printk(KERN_ERR "EEH: Cannot find PCI bus for %s\n",
-                        frozen_dn->full_name);
-                return;
+                printk(KERN_ERR "EEH: Cannot find PCI bus "
+                        "for location=%s dn=%s\n",
+                        location, frozen_dn->full_name);
+                return NULL;
         }
 
 #if 0
@@ -314,8 +325,9 @@ void handle_eeh_events (struct eeh_event *event)
 
         eeh_slot_error_detail(frozen_pdn, 1 /* Temporary Error */);
         printk(KERN_WARNING
-           "EEH: This PCI device has failed %d times since last reboot: %s - %s\n",
-                frozen_pdn->eeh_freeze_count, drv_str, pci_str);
+           "EEH: This PCI device has failed %d times since last reboot: "
+                "location=%s driver=%s pci addr=%s\n",
+                frozen_pdn->eeh_freeze_count, location, drv_str, pci_str);
 
         /* Walk the various device drivers attached to this slot through
          * a reset sequence, giving each an opportunity to do what it needs
@@ -355,7 +367,7 @@ void handle_eeh_events (struct eeh_event *event)
         /* Tell all device drivers that they can resume operations */
         pci_walk_bus(frozen_bus, eeh_report_resume, NULL);
 
-        return;
+        return frozen_pdn;
         
 excess_failures:
         /*
@@ -364,17 +376,18 @@ excess_failures:
          * due to actual, failed cards.
          */
         printk(KERN_ERR
-           "EEH: PCI device %s - %s has failed %d times \n"
-           "and has been permanently disabled.  Please try reseating\n"
-           "this device or replacing it.\n",
-                drv_str, pci_str, frozen_pdn->eeh_freeze_count);
+           "EEH: PCI device at location=%s driver=%s pci addr=%s \n"
+                "has failed %d times and has been permanently disabled. \n"
+                "Please try reseating this device or replacing it.\n",
+                location, drv_str, pci_str, frozen_pdn->eeh_freeze_count);
         goto perm_error;
 
 hard_fail:
         printk(KERN_ERR
-           "EEH: Unable to recover from failure of PCI device %s - %s\n"
+           "EEH: Unable to recover from failure of PCI device "
+           "at location=%s driver=%s pci addr=%s \n"
            "Please try reseating this device or replacing it.\n",
-                drv_str, pci_str);
+                location, drv_str, pci_str);
 
 perm_error:
         eeh_slot_error_detail(frozen_pdn, 2 /* Permanent Error */);
@@ -384,6 +397,8 @@ perm_error:
 
         /* Shut down the device drivers for good. */
         pcibios_remove_pci_devices(frozen_bus);
+
+        return NULL;
 }
 
 /* ---------- end of file ---------- */
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 40020c65c89e..8f2d12935b99 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -18,6 +18,7 @@
  * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
  */
 
+#include <linux/delay.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
@@ -56,38 +57,43 @@ static int eeh_event_handler(void * dummy)
 {
         unsigned long flags;
         struct eeh_event        *event;
+        struct pci_dn *pdn;
 
         daemonize ("eehd");
+        set_current_state(TASK_INTERRUPTIBLE);
 
-        while (1) {
-                set_current_state(TASK_INTERRUPTIBLE);
+        spin_lock_irqsave(&eeh_eventlist_lock, flags);
+        event = NULL;
 
-                spin_lock_irqsave(&eeh_eventlist_lock, flags);
-                event = NULL;
+        /* Unqueue the event, get ready to process. */
+        if (!list_empty(&eeh_eventlist)) {
+                event = list_entry(eeh_eventlist.next, struct eeh_event, list);
+                list_del(&event->list);
+        }
+        spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
 
-                /* Unqueue the event, get ready to process. */
-                if (!list_empty(&eeh_eventlist)) {
-                        event = list_entry(eeh_eventlist.next, struct eeh_event, list);
-                        list_del(&event->list);
-                }
-                spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+        if (event == NULL)
+                return 0;
 
-                if (event == NULL)
-                        break;
+        /* Serialize processing of EEH events */
+        mutex_lock(&eeh_event_mutex);
+        eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
 
-                /* Serialize processing of EEH events */
-                mutex_lock(&eeh_event_mutex);
-                eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
+        printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
+               pci_name(event->dev));
 
-                printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
-                       pci_name(event->dev));
+        pdn = handle_eeh_events(event);
 
-                handle_eeh_events(event);
+        eeh_clear_slot(event->dn, EEH_MODE_RECOVERING);
+        pci_dev_put(event->dev);
+        kfree(event);
+        mutex_unlock(&eeh_event_mutex);
 
-                eeh_clear_slot(event->dn, EEH_MODE_RECOVERING);
-                pci_dev_put(event->dev);
-                kfree(event);
-                mutex_unlock(&eeh_event_mutex);
+        /* If there are no new errors after an hour, clear the counter. */
+        if (pdn && pdn->eeh_freeze_count>0) {
+                msleep_interruptible (3600*1000);
+                if (pdn->eeh_freeze_count>0)
+                        pdn->eeh_freeze_count--;
         }
 
         return 0;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 2643078433f0..d03a8b078f9d 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1,23 +1,24 @@
 /*
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  *
- * Rewrite, cleanup: 
+ * Rewrite, cleanup:
  *
  * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
+ * Copyright (C) 2006 Olof Johansson <olof@lixom.net>
  *
  * Dynamic DMA mapping support, pSeries-specific parts, both SMP and LPAR.
  *
- * 
+ *
  * 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.
- * 
+ *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- * 
+ *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
@@ -49,52 +50,46 @@
 
 #define DBG(fmt...)
 
-static void tce_build_pSeries(struct iommu_table *tbl, long index, 
-                              long npages, unsigned long uaddr, 
+static void tce_build_pSeries(struct iommu_table *tbl, long index,
+                              long npages, unsigned long uaddr,
                               enum dma_data_direction direction)
 {
-        union tce_entry t;
-        union tce_entry *tp;
+        u64 proto_tce;
+        u64 *tcep;
+        u64 rpn;
 
         index <<= TCE_PAGE_FACTOR;
         npages <<= TCE_PAGE_FACTOR;
 
-        t.te_word = 0;
-        t.te_rdwr = 1; // Read allowed 
+        proto_tce = TCE_PCI_READ; // Read allowed
 
         if (direction != DMA_TO_DEVICE)
-                t.te_pciwr = 1;
+                proto_tce |= TCE_PCI_WRITE;
 
-        tp = ((union tce_entry *)tbl->it_base) + index;
+        tcep = ((u64 *)tbl->it_base) + index;
 
         while (npages--) {
                 /* can't move this out since we might cross LMB boundary */
-                t.te_rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
-        
-                tp->te_word = t.te_word;
+                rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+                *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
 
                 uaddr += TCE_PAGE_SIZE;
-                tp++;
+                tcep++;
         }
 }
 
 
 static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
 {
-        union tce_entry t;
-        union tce_entry *tp;
+        u64 *tcep;
 
         npages <<= TCE_PAGE_FACTOR;
         index <<= TCE_PAGE_FACTOR;
 
-        t.te_word = 0;
-        tp  = ((union tce_entry *)tbl->it_base) + index;
-                
-        while (npages--) {
-                tp->te_word = t.te_word;
-                
-                tp++;
-        }
+        tcep = ((u64 *)tbl->it_base) + index;
+
+        while (npages--)
+                *(tcep++) = 0;
 }
 
 
@@ -103,43 +98,44 @@ static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
                                 enum dma_data_direction direction)
 {
         u64 rc;
-        union tce_entry tce;
+        u64 proto_tce, tce;
+        u64 rpn;
 
         tcenum <<= TCE_PAGE_FACTOR;
         npages <<= TCE_PAGE_FACTOR;
 
-        tce.te_word = 0;
-        tce.te_rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
-        tce.te_rdwr = 1;
+        rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+        proto_tce = TCE_PCI_READ;
         if (direction != DMA_TO_DEVICE)
-                tce.te_pciwr = 1;
+                proto_tce |= TCE_PCI_WRITE;
 
         while (npages--) {
-                rc = plpar_tce_put((u64)tbl->it_index, 
-                                   (u64)tcenum << 12, 
-                                   tce.te_word );
-                
+                tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+                rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce);
+
                 if (rc && printk_ratelimit()) {
                         printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc);
                         printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
                         printk("\ttcenum  = 0x%lx\n", (u64)tcenum);
-                        printk("\ttce val = 0x%lx\n", tce.te_word );
+                        printk("\ttce val = 0x%lx\n", tce );
                         show_stack(current, (unsigned long *)__get_SP());
                 }
-                        
+
                 tcenum++;
-                tce.te_rpn++;
+                rpn++;
         }
 }
 
-static DEFINE_PER_CPU(void *, tce_page) = NULL;
+static DEFINE_PER_CPU(u64 *, tce_page) = NULL;
 
 static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
                                      long npages, unsigned long uaddr,
                                      enum dma_data_direction direction)
 {
         u64 rc;
-        union tce_entry tce, *tcep;
+        u64 proto_tce;
+        u64 *tcep;
+        u64 rpn;
         long l, limit;
 
         if (TCE_PAGE_FACTOR == 0 && npages == 1)
@@ -152,7 +148,7 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
          * from iommu_alloc{,_sg}()
          */
         if (!tcep) {
-                tcep = (void *)__get_free_page(GFP_ATOMIC);
+                tcep = (u64 *)__get_free_page(GFP_ATOMIC);
                 /* If allocation fails, fall back to the loop implementation */
                 if (!tcep)
                         return tce_build_pSeriesLP(tbl, tcenum, npages,
@@ -163,11 +159,10 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
         tcenum <<= TCE_PAGE_FACTOR;
         npages <<= TCE_PAGE_FACTOR;
 
-        tce.te_word = 0;
-        tce.te_rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
-        tce.te_rdwr = 1;
+        rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+        proto_tce = TCE_PCI_READ;
         if (direction != DMA_TO_DEVICE)
-                tce.te_pciwr = 1;
+                proto_tce |= TCE_PCI_WRITE;
 
         /* We can map max one pageful of TCEs at a time */
         do {
@@ -175,11 +170,11 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
                  * Set up the page with TCE data, looping through and setting
                  * the values.
                  */
-                limit = min_t(long, npages, 4096/sizeof(union tce_entry));
+                limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE);
 
                 for (l = 0; l < limit; l++) {
-                        tcep[l] = tce;
-                        tce.te_rpn++;
+                        tcep[l] = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+                        rpn++;
                 }
 
                 rc = plpar_tce_put_indirect((u64)tbl->it_index,
@@ -195,7 +190,7 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
                 printk("tce_buildmulti_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc);
                 printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
                 printk("\tnpages  = 0x%lx\n", (u64)npages);
-                printk("\ttce[0] val = 0x%lx\n", tcep[0].te_word);
+                printk("\ttce[0] val = 0x%lx\n", tcep[0]);
                 show_stack(current, (unsigned long *)__get_SP());
         }
 }
@@ -203,23 +198,17 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
 {
         u64 rc;
-        union tce_entry tce;
 
         tcenum <<= TCE_PAGE_FACTOR;
         npages <<= TCE_PAGE_FACTOR;
 
-        tce.te_word = 0;
-
         while (npages--) {
-                rc = plpar_tce_put((u64)tbl->it_index,
-                                   (u64)tcenum << 12,
-                                   tce.te_word);
+                rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, 0);
 
                 if (rc && printk_ratelimit()) {
                         printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc);
                         printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
                         printk("\ttcenum  = 0x%lx\n", (u64)tcenum);
-                        printk("\ttce val = 0x%lx\n", tce.te_word );
                         show_stack(current, (unsigned long *)__get_SP());
                 }
 
@@ -231,31 +220,24 @@ static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages
 static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
 {
         u64 rc;
-        union tce_entry tce;
 
         tcenum <<= TCE_PAGE_FACTOR;
         npages <<= TCE_PAGE_FACTOR;
 
-        tce.te_word = 0;
-
-        rc = plpar_tce_stuff((u64)tbl->it_index,
-                           (u64)tcenum << 12,
-                           tce.te_word,
-                           npages);
+        rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
 
         if (rc && printk_ratelimit()) {
                 printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n");
                 printk("\trc      = %ld\n", rc);
                 printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
                 printk("\tnpages  = 0x%lx\n", (u64)npages);
-                printk("\ttce val = 0x%lx\n", tce.te_word );
                 show_stack(current, (unsigned long *)__get_SP());
         }
 }
 
 static void iommu_table_setparms(struct pci_controller *phb,
                                  struct device_node *dn,
-                                 struct iommu_table *tbl) 
+                                 struct iommu_table *tbl)
 {
         struct device_node *node;
         unsigned long *basep;
@@ -275,16 +257,16 @@ static void iommu_table_setparms(struct pci_controller *phb,
         memset((void *)tbl->it_base, 0, *sizep);
 
         tbl->it_busno = phb->bus->number;
-        
+
         /* Units of tce entries */
         tbl->it_offset = phb->dma_window_base_cur >> PAGE_SHIFT;
-        
+
         /* Test if we are going over 2GB of DMA space */
         if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) {
                 udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
-                panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); 
+                panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n");
         }
-        
+
         phb->dma_window_base_cur += phb->dma_window_size;
 
         /* Set the tce table size - measured in entries */
@@ -299,30 +281,22 @@ static void iommu_table_setparms(struct pci_controller *phb,
  * iommu_table_setparms_lpar
  *
  * Function: On pSeries LPAR systems, return TCE table info, given a pci bus.
- *
- * ToDo: properly interpret the ibm,dma-window property.  The definition is:
- *      logical-bus-number      (1 word)
- *      phys-address            (#address-cells words)
- *      size                    (#cell-size words)
- *
- * Currently we hard code these sizes (more or less).
  */
 static void iommu_table_setparms_lpar(struct pci_controller *phb,
                                       struct device_node *dn,
                                       struct iommu_table *tbl,
-                                      unsigned int *dma_window)
+                                      unsigned char *dma_window)
 {
+        unsigned long offset, size;
+
         tbl->it_busno  = PCI_DN(dn)->bussubno;
+        of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size);
 
-        /* TODO: Parse field size properties properly. */
-        tbl->it_size   = (((unsigned long)dma_window[4] << 32) |
-                           (unsigned long)dma_window[5]) >> PAGE_SHIFT;
-        tbl->it_offset = (((unsigned long)dma_window[2] << 32) |
-                           (unsigned long)dma_window[3]) >> PAGE_SHIFT;
         tbl->it_base   = 0;
-        tbl->it_index  = dma_window[0];
         tbl->it_blocksize  = 16;
         tbl->it_type = TCE_PCI;
+        tbl->it_offset = offset >> PAGE_SHIFT;
+        tbl->it_size = size >> PAGE_SHIFT;
 }
 
 static void iommu_bus_setup_pSeries(struct pci_bus *bus)
@@ -357,13 +331,9 @@ static void iommu_bus_setup_pSeries(struct pci_bus *bus)
         if (isa_dn_orig)
                 of_node_put(isa_dn_orig);
 
-        /* Count number of direct PCI children of the PHB.
-         * All PCI device nodes have class-code property, so it's
-         * an easy way to find them.
-         */
+        /* Count number of direct PCI children of the PHB. */
         for (children = 0, tmp = dn->child; tmp; tmp = tmp->sibling)
-                if (get_property(tmp, "class-code", NULL))
-                        children++;
+                children++;
 
         DBG("Children: %d\n", children);
 
@@ -394,10 +364,11 @@ static void iommu_bus_setup_pSeries(struct pci_bus *bus)
         pci->phb->dma_window_size = 0x8000000ul;
         pci->phb->dma_window_base_cur = 0x8000000ul;
 
-        tbl = kmalloc(sizeof(struct iommu_table), GFP_KERNEL);
+        tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
+                           pci->phb->node);
 
         iommu_table_setparms(pci->phb, dn, tbl);
-        pci->iommu_table = iommu_init_table(tbl);
+        pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
 
         /* Divide the rest (1.75GB) among the children */
         pci->phb->dma_window_size = 0x80000000ul;
@@ -414,7 +385,7 @@ static void iommu_bus_setup_pSeriesLP(struct pci_bus *bus)
         struct iommu_table *tbl;
         struct device_node *dn, *pdn;
         struct pci_dn *ppci;
-        unsigned int *dma_window = NULL;
+        unsigned char *dma_window = NULL;
 
         DBG("iommu_bus_setup_pSeriesLP, bus %p, bus->self %p\n", bus, bus->self);
 
@@ -422,7 +393,7 @@ static void iommu_bus_setup_pSeriesLP(struct pci_bus *bus)
 
         /* Find nearest ibm,dma-window, walking up the device tree */
         for (pdn = dn; pdn != NULL; pdn = pdn->parent) {
-                dma_window = (unsigned int *)get_property(pdn, "ibm,dma-window", NULL);
+                dma_window = get_property(pdn, "ibm,dma-window", NULL);
                 if (dma_window != NULL)
                         break;
         }
@@ -440,12 +411,12 @@ static void iommu_bus_setup_pSeriesLP(struct pci_bus *bus)
 
                 ppci->bussubno = bus->number;
 
-                tbl = (struct iommu_table *)kmalloc(sizeof(struct iommu_table),
-                                                    GFP_KERNEL);
-        
+                tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
+                                   ppci->phb->node);
+
                 iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
 
-                ppci->iommu_table = iommu_init_table(tbl);
+                ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
         }
 
         if (pdn != dn)
@@ -468,9 +439,11 @@ static void iommu_dev_setup_pSeries(struct pci_dev *dev)
          */
         if (!dev->bus->self) {
                 DBG(" --> first child, no bridge. Allocating iommu table.\n");
-                tbl = kmalloc(sizeof(struct iommu_table), GFP_KERNEL);
+                tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
+                                   PCI_DN(dn)->phb->node);
                 iommu_table_setparms(PCI_DN(dn)->phb, dn, tbl);
-                PCI_DN(mydn)->iommu_table = iommu_init_table(tbl);
+                PCI_DN(dn)->iommu_table = iommu_init_table(tbl,
+                                                PCI_DN(dn)->phb->node);
 
                 return;
         }
@@ -516,7 +489,7 @@ static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
         struct device_node *pdn, *dn;
         struct iommu_table *tbl;
-        int *dma_window = NULL;
+        unsigned char *dma_window = NULL;
         struct pci_dn *pci;
 
         DBG("iommu_dev_setup_pSeriesLP, dev %p (%s)\n", dev, pci_name(dev));
@@ -531,8 +504,7 @@ static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
 
         for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
              pdn = pdn->parent) {
-                dma_window = (unsigned int *)
-                        get_property(pdn, "ibm,dma-window", NULL);
+                dma_window = get_property(pdn, "ibm,dma-window", NULL);
                 if (dma_window)
                         break;
         }
@@ -553,12 +525,12 @@ static void iommu_dev_setup_pSeriesLP(struct pci_dev *dev)
                 /* iommu_table_setparms_lpar needs bussubno. */
                 pci->bussubno = pci->phb->bus->number;
 
-                tbl = (struct iommu_table *)kmalloc(sizeof(struct iommu_table),
-                                                    GFP_KERNEL);
+                tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
+                                   pci->phb->node);
 
                 iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
 
-                pci->iommu_table = iommu_init_table(tbl);
+                pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
         }
 
         if (pdn != dn)
diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c
index e0000ce769e5..2e4e04042d85 100644
--- a/arch/powerpc/platforms/pseries/rtasd.c
+++ b/arch/powerpc/platforms/pseries/rtasd.c
@@ -348,7 +348,7 @@ static int enable_surveillance(int timeout)
                 return 0;
 
         if (error == -EINVAL) {
-                printk(KERN_INFO "rtasd: surveillance not supported\n");
+                printk(KERN_DEBUG "rtasd: surveillance not supported\n");
                 return 0;
         }
 
@@ -440,7 +440,7 @@ static int rtasd(void *unused)
                 goto error;
         }
 
-        printk(KERN_INFO "RTAS daemon started\n");
+        printk(KERN_DEBUG "RTAS daemon started\n");
 
         DEBUG("will sleep for %d milliseconds\n", (30000/rtas_event_scan_rate));
 
@@ -487,7 +487,7 @@ static int __init rtas_init(void)
 
         /* No RTAS */
         if (rtas_token("event-scan") == RTAS_UNKNOWN_SERVICE) {
-                printk(KERN_INFO "rtasd: no event-scan on system\n");
+                printk(KERN_DEBUG "rtasd: no event-scan on system\n");
                 return -ENODEV;
         }
 
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index 50643496eb63..77a5bb1d9c30 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -107,9 +107,9 @@ static ssize_t scanlog_read(struct file *file, char __user *buf,
                         /* Break to sleep default time */
                         break;
                     default:
-                        if (status > 9900 && status <= 9905) {
-                                wait_time = rtas_extended_busy_delay_time(status);
-                        } else {
+                        /* Assume extended busy */
+                        wait_time = rtas_busy_delay_time(status);
+                        if (!wait_time) {
                                 printk(KERN_ERR "scanlog: unknown error from rtas: %d\n", status);
                                 return -EIO;
                         }
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 3ba87835757e..1e28518c6121 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -235,14 +235,14 @@ static void __init pSeries_setup_arch(void)
         if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
                 vpa_init(boot_cpuid);
                 if (get_lppaca()->shared_proc) {
-                        printk(KERN_INFO "Using shared processor idle loop\n");
+                        printk(KERN_DEBUG "Using shared processor idle loop\n");
                         ppc_md.power_save = pseries_shared_idle_sleep;
                 } else {
-                        printk(KERN_INFO "Using dedicated idle loop\n");
+                        printk(KERN_DEBUG "Using dedicated idle loop\n");
                         ppc_md.power_save = pseries_dedicated_idle_sleep;
                 }
         } else {
-                printk(KERN_INFO "Using default idle loop\n");
+                printk(KERN_DEBUG "Using default idle loop\n");
         }
 
         if (firmware_has_feature(FW_FEATURE_LPAR))
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
deleted file mode 100644
index 8e53e04ada8b..000000000000
--- a/arch/powerpc/platforms/pseries/vio.c
+++ /dev/null
@@ -1,274 +0,0 @@
-/*
- * IBM PowerPC pSeries Virtual I/O Infrastructure Support.
- *
- *    Copyright (c) 2003-2005 IBM Corp.
- *     Dave Engebretsen engebret@us.ibm.com
- *     Santiago Leon santil@us.ibm.com
- *     Hollis Blanchard <hollisb@us.ibm.com>
- *     Stephen Rothwell
- *
- *      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/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/kobject.h>
-#include <asm/iommu.h>
-#include <asm/dma.h>
-#include <asm/prom.h>
-#include <asm/vio.h>
-#include <asm/hvcall.h>
-#include <asm/tce.h>
-
-extern struct subsystem devices_subsys; /* needed for vio_find_name() */
-
-static void probe_bus_pseries(void)
-{
-        struct device_node *node_vroot, *of_node;
-
-        node_vroot = find_devices("vdevice");
-        if ((node_vroot == NULL) || (node_vroot->child == NULL))
-                /* this machine doesn't do virtual IO, and that's ok */
-                return;
-
-        /*
-         * Create struct vio_devices for each virtual device in the device tree.
-         * Drivers will associate with them later.
-         */
-        for (of_node = node_vroot->child; of_node != NULL;
-                        of_node = of_node->sibling) {
-                printk(KERN_DEBUG "%s: processing %p\n", __FUNCTION__, of_node);
-                vio_register_device_node(of_node);
-        }
-}
-
-/**
- * vio_match_device_pseries: - Tell if a pSeries VIO device matches a
- *      vio_device_id
- */
-static int vio_match_device_pseries(const struct vio_device_id *id,
-                const struct vio_dev *dev)
-{
-        return (strncmp(dev->type, id->type, strlen(id->type)) == 0) &&
-                        device_is_compatible(dev->dev.platform_data, id->compat);
-}
-
-static void vio_release_device_pseries(struct device *dev)
-{
-        /* XXX free TCE table */
-        of_node_put(dev->platform_data);
-}
-
-static ssize_t viodev_show_devspec(struct device *dev,
-                struct device_attribute *attr, char *buf)
-{
-        struct device_node *of_node = dev->platform_data;
-
-        return sprintf(buf, "%s\n", of_node->full_name);
-}
-DEVICE_ATTR(devspec, S_IRUSR | S_IRGRP | S_IROTH, viodev_show_devspec, NULL);
-
-static void vio_unregister_device_pseries(struct vio_dev *viodev)
-{
-        device_remove_file(&viodev->dev, &dev_attr_devspec);
-}
-
-static struct vio_bus_ops vio_bus_ops_pseries = {
-        .match = vio_match_device_pseries,
-        .unregister_device = vio_unregister_device_pseries,
-        .release_device = vio_release_device_pseries,
-};
-
-/**
- * vio_bus_init_pseries: - Initialize the pSeries virtual IO bus
- */
-static int __init vio_bus_init_pseries(void)
-{
-        int err;
-
-        err = vio_bus_init(&vio_bus_ops_pseries);
-        if (err == 0)
-                probe_bus_pseries();
-        return err;
-}
-
-__initcall(vio_bus_init_pseries);
-
-/**
- * vio_build_iommu_table: - gets the dma information from OF and
- *      builds the TCE tree.
- * @dev: the virtual device.
- *
- * Returns a pointer to the built tce tree, or NULL if it can't
- * find property.
-*/
-static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
-{
-        unsigned int *dma_window;
-        struct iommu_table *newTceTable;
-        unsigned long offset;
-        int dma_window_property_size;
-
-        dma_window = (unsigned int *) get_property(dev->dev.platform_data, "ibm,my-dma-window", &dma_window_property_size);
-        if(!dma_window) {
-                return NULL;
-        }
-
-        newTceTable = (struct iommu_table *) kmalloc(sizeof(struct iommu_table), GFP_KERNEL);
-
-        /*  There should be some code to extract the phys-encoded offset
-                using prom_n_addr_cells(). However, according to a comment
-                on earlier versions, it's always zero, so we don't bother */
-        offset = dma_window[1] >>  PAGE_SHIFT;
-
-        /* TCE table size - measured in tce entries */
-        newTceTable->it_size            = dma_window[4] >> PAGE_SHIFT;
-        /* offset for VIO should always be 0 */
-        newTceTable->it_offset          = offset;
-        newTceTable->it_busno           = 0;
-        newTceTable->it_index           = (unsigned long)dma_window[0];
-        newTceTable->it_type            = TCE_VB;
-
-        return iommu_init_table(newTceTable);
-}
-
-/**
- * vio_register_device_node: - Register a new vio device.
- * @of_node:    The OF node for this device.
- *
- * Creates and initializes a vio_dev structure from the data in
- * of_node (dev.platform_data) and adds it to the list of virtual devices.
- * Returns a pointer to the created vio_dev or NULL if node has
- * NULL device_type or compatible fields.
- */
-struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node)
-{
-        struct vio_dev *viodev;
-        unsigned int *unit_address;
-        unsigned int *irq_p;
-
-        /* we need the 'device_type' property, in order to match with drivers */
-        if ((NULL == of_node->type)) {
-                printk(KERN_WARNING
-                        "%s: node %s missing 'device_type'\n", __FUNCTION__,
-                        of_node->name ? of_node->name : "<unknown>");
-                return NULL;
-        }
-
-        unit_address = (unsigned int *)get_property(of_node, "reg", NULL);
-        if (!unit_address) {
-                printk(KERN_WARNING "%s: node %s missing 'reg'\n", __FUNCTION__,
-                        of_node->name ? of_node->name : "<unknown>");
-                return NULL;
-        }
-
-        /* allocate a vio_dev for this node */
-        viodev = kmalloc(sizeof(struct vio_dev), GFP_KERNEL);
-        if (!viodev) {
-                return NULL;
-        }
-        memset(viodev, 0, sizeof(struct vio_dev));
-
-        viodev->dev.platform_data = of_node_get(of_node);
-
-        viodev->irq = NO_IRQ;
-        irq_p = (unsigned int *)get_property(of_node, "interrupts", NULL);
-        if (irq_p) {
-                int virq = virt_irq_create_mapping(*irq_p);
-                if (virq == NO_IRQ) {
-                        printk(KERN_ERR "Unable to allocate interrupt "
-                               "number for %s\n", of_node->full_name);
-                } else
-                        viodev->irq = irq_offset_up(virq);
-        }
-
-        snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address);
-        viodev->name = of_node->name;
-        viodev->type = of_node->type;
-        viodev->unit_address = *unit_address;
-        viodev->iommu_table = vio_build_iommu_table(viodev);
-
-        /* register with generic device framework */
-        if (vio_register_device(viodev) == NULL) {
-                /* XXX free TCE table */
-                kfree(viodev);
-                return NULL;
-        }
-        device_create_file(&viodev->dev, &dev_attr_devspec);
-
-        return viodev;
-}
-EXPORT_SYMBOL(vio_register_device_node);
-
-/**
- * vio_get_attribute: - get attribute for virtual device
- * @vdev:       The vio device to get property.
- * @which:      The property/attribute to be extracted.
- * @length:     Pointer to length of returned data size (unused if NULL).
- *
- * Calls prom.c's get_property() to return the value of the
- * attribute specified by the preprocessor constant @which
-*/
-const void * vio_get_attribute(struct vio_dev *vdev, void* which, int* length)
-{
-        return get_property(vdev->dev.platform_data, (char*)which, length);
-}
-EXPORT_SYMBOL(vio_get_attribute);
-
-/* vio_find_name() - internal because only vio.c knows how we formatted the
- * kobject name
- * XXX once vio_bus_type.devices is actually used as a kset in
- * drivers/base/bus.c, this function should be removed in favor of
- * "device_find(kobj_name, &vio_bus_type)"
- */
-static struct vio_dev *vio_find_name(const char *kobj_name)
-{
-        struct kobject *found;
-
-        found = kset_find_obj(&devices_subsys.kset, kobj_name);
-        if (!found)
-                return NULL;
-
-        return to_vio_dev(container_of(found, struct device, kobj));
-}
-
-/**
- * vio_find_node - find an already-registered vio_dev
- * @vnode: device_node of the virtual device we're looking for
- */
-struct vio_dev *vio_find_node(struct device_node *vnode)
-{
-        uint32_t *unit_address;
-        char kobj_name[BUS_ID_SIZE];
-
-        /* construct the kobject name from the device node */
-        unit_address = (uint32_t *)get_property(vnode, "reg", NULL);
-        if (!unit_address)
-                return NULL;
-        snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address);
-
-        return vio_find_name(kobj_name);
-}
-EXPORT_SYMBOL(vio_find_node);
-
-int vio_enable_interrupts(struct vio_dev *dev)
-{
-        int rc = h_vio_signal(dev->unit_address, VIO_IRQ_ENABLE);
-        if (rc != H_SUCCESS)
-                printk(KERN_ERR "vio: Error 0x%x enabling interrupts\n", rc);
-        return rc;
-}
-EXPORT_SYMBOL(vio_enable_interrupts);
-
-int vio_disable_interrupts(struct vio_dev *dev)
-{
-        int rc = h_vio_signal(dev->unit_address, VIO_IRQ_DISABLE);
-        if (rc != H_SUCCESS)
-                printk(KERN_ERR "vio: Error 0x%x disabling interrupts\n", rc);
-        return rc;
-}
-EXPORT_SYMBOL(vio_disable_interrupts);
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 2d60ea30fed6..b14f9b5c114e 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -522,7 +522,7 @@ nextnode:
 
         np = of_find_node_by_type(NULL, "interrupt-controller");
         if (!np) {
-                printk(KERN_WARNING "xics: no ISA interrupt controller\n");
+                printk(KERN_DEBUG "xics: no ISA interrupt controller\n");
                 xics_irq_8259_cascade_real = -1;
                 xics_irq_8259_cascade = -1;
         } else {
@@ -641,23 +641,26 @@ void xics_teardown_cpu(int secondary)
         ops->cppr_info(cpu, 0x00);
         iosync();
 
+        /* Clear IPI */
+        ops->qirr_info(cpu, 0xff);
+
+        /*
+         * we need to EOI the IPI if we got here from kexec down IPI
+         *
+         * probably need to check all the other interrupts too
+         * should we be flagging idle loop instead?
+         * or creating some task to be scheduled?
+         */
+        ops->xirr_info_set(cpu, XICS_IPI);
+
         /*
          * Some machines need to have at least one cpu in the GIQ,
          * so leave the master cpu in the group.
          */
-        if (secondary) {
-                /*
-                 * we need to EOI the IPI if we got here from kexec down IPI
-                 *
-                 * probably need to check all the other interrupts too
-                 * should we be flagging idle loop instead?
-                 * or creating some task to be scheduled?
-                 */
-                ops->xirr_info_set(cpu, XICS_IPI);
+        if (secondary)
                 rtas_set_indicator(GLOBAL_INTERRUPT_QUEUE,
                         (1UL << interrupt_server_size) - 1 -
                         default_distrib_server, 0);
-        }
 }
 
 #ifdef CONFIG_HOTPLUG_CPU