11 files changed, 628 insertions, 158 deletions

diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 992ba6753cf2..bdae04bb7a01 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug-cpu.o
 obj-$(CONFIG_HVC_CONSOLE)       += hvconsole.o
 obj-$(CONFIG_HVCS)              += hvcserver.o
 obj-$(CONFIG_HCALL_STATS)       += hvCall_inst.o
+obj-$(CONFIG_PHYP_DUMP) += phyp_dump.o
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 9eb539ee5f9a..550b2f7d2cc1 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -945,7 +945,6 @@ static void *early_enable_eeh(struct device_node *dn, void *data)
         unsigned int rets[3];
         struct eeh_early_enable_info *info = data;
         int ret;
-        const char *status = of_get_property(dn, "status", NULL);
         const u32 *class_code = of_get_property(dn, "class-code", NULL);
         const u32 *vendor_id = of_get_property(dn, "vendor-id", NULL);
         const u32 *device_id = of_get_property(dn, "device-id", NULL);
@@ -959,8 +958,8 @@ static void *early_enable_eeh(struct device_node *dn, void *data)
         pdn->eeh_freeze_count = 0;
         pdn->eeh_false_positives = 0;
 
-        if (status && strncmp(status, "ok", 2) != 0)
-                return NULL;    /* ignore devices with bad status */
+        if (!of_device_is_available(dn))
+                return NULL;
 
         /* Ignore bad nodes. */
         if (!class_code || !vendor_id || !device_id)
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 9a455d46379d..9235c469449e 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -40,6 +40,7 @@
 #include <asm/smp.h>
 
 #include "plpar_wrappers.h"
+#include "pseries.h"
 
 #ifdef DEBUG_LOW
 #define DBG_LOW(fmt...) do { udbg_printf(fmt); } while(0)
@@ -203,7 +204,6 @@ void __init find_udbg_vterm(void)
         struct device_node *stdout_node;
         const u32 *termno;
         const char *name;
-        int add_console;
 
         /* find the boot console from /chosen/stdout */
         if (!of_chosen)
@@ -219,8 +219,6 @@ void __init find_udbg_vterm(void)
                 printk(KERN_WARNING "stdout node missing 'name' property!\n");
                 goto out;
         }
-        /* The user has requested a console so this is already set up. */
-        add_console = !strstr(cmd_line, "console=");
 
         /* Check if it's a virtual terminal */
         if (strncmp(name, "vty", 3) != 0)
@@ -234,15 +232,13 @@ void __init find_udbg_vterm(void)
                 udbg_putc = udbg_putcLP;
                 udbg_getc = udbg_getcLP;
                 udbg_getc_poll = udbg_getc_pollLP;
-                if (add_console)
-                        add_preferred_console("hvc", termno[0] & 0xff, NULL);
+                add_preferred_console("hvc", termno[0] & 0xff, NULL);
         } else if (of_device_is_compatible(stdout_node, "hvterm-protocol")) {
                 vtermno = termno[0];
                 udbg_putc = udbg_hvsi_putc;
                 udbg_getc = udbg_hvsi_getc;
                 udbg_getc_poll = udbg_hvsi_getc_poll;
-                if (add_console)
-                        add_preferred_console("hvsi", termno[0] & 0xff, NULL);
+                add_preferred_console("hvsi", termno[0] & 0xff, NULL);
         }
 out:
         of_node_put(stdout_node);
@@ -520,6 +516,20 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
         BUG_ON(lpar_rc != H_SUCCESS);
 }
 
+static void pSeries_lpar_hpte_removebolted(unsigned long ea,
+                                           int psize, int ssize)
+{
+        unsigned long slot, vsid, va;
+
+        vsid = get_kernel_vsid(ea, ssize);
+        va = hpt_va(ea, vsid, ssize);
+
+        slot = pSeries_lpar_hpte_find(va, psize, ssize);
+        BUG_ON(slot == -1);
+
+        pSeries_lpar_hpte_invalidate(slot, va, psize, ssize, 0);
+}
+
 /* Flag bits for H_BULK_REMOVE */
 #define HBR_REQUEST     0x4000000000000000UL
 #define HBR_RESPONSE    0x8000000000000000UL
@@ -597,6 +607,7 @@ void __init hpte_init_lpar(void)
         ppc_md.hpte_updateboltedpp = pSeries_lpar_hpte_updateboltedpp;
         ppc_md.hpte_insert      = pSeries_lpar_hpte_insert;
         ppc_md.hpte_remove      = pSeries_lpar_hpte_remove;
+        ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
         ppc_md.flush_hash_range = pSeries_lpar_flush_hash_range;
         ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
 }
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 5a5a19e40bb4..0d7229cde0e9 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -123,7 +123,7 @@ pcibios_pci_config_bridge(struct pci_dev *dev)
         /* Add to children of PCI bridge dev->bus */
         child_bus = pci_add_new_bus(dev->bus, dev, sec_busno);
         if (!child_bus) {
-                printk (KERN_ERR "%s: could not add second bus\n", __FUNCTION__);
+                printk (KERN_ERR "%s: could not add second bus\n", __func__);
                 return -EIO;
         }
         sprintf(child_bus->name, "PCI Bus #%02x", child_bus->number);
diff --git a/arch/powerpc/platforms/pseries/phyp_dump.c b/arch/powerpc/platforms/pseries/phyp_dump.c
new file mode 100644
index 000000000000..edbc012c2ebc
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/phyp_dump.c
@@ -0,0 +1,507 @@
+/*
+ * Hypervisor-assisted dump
+ *
+ * Linas Vepstas, Manish Ahuja 2008
+ * Copyright 2008 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/init.h>
+#include <linux/kobject.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/pfn.h>
+#include <linux/swap.h>
+#include <linux/sysfs.h>
+
+#include <asm/page.h>
+#include <asm/phyp_dump.h>
+#include <asm/machdep.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+
+/* Variables, used to communicate data between early boot and late boot */
+static struct phyp_dump phyp_dump_vars;
+struct phyp_dump *phyp_dump_info = &phyp_dump_vars;
+
+static int ibm_configure_kernel_dump;
+/* ------------------------------------------------- */
+/* RTAS interfaces to declare the dump regions */
+
+struct dump_section {
+        u32 dump_flags;
+        u16 source_type;
+        u16 error_flags;
+        u64 source_address;
+        u64 source_length;
+        u64 length_copied;
+        u64 destination_address;
+};
+
+struct phyp_dump_header {
+        u32 version;
+        u16 num_of_sections;
+        u16 status;
+
+        u32 first_offset_section;
+        u32 dump_disk_section;
+        u64 block_num_dd;
+        u64 num_of_blocks_dd;
+        u32 offset_dd;
+        u32 maxtime_to_auto;
+        /* No dump disk path string used */
+
+        struct dump_section cpu_data;
+        struct dump_section hpte_data;
+        struct dump_section kernel_data;
+};
+
+/* The dump header *must be* in low memory, so .bss it */
+static struct phyp_dump_header phdr;
+
+#define NUM_DUMP_SECTIONS       3
+#define DUMP_HEADER_VERSION     0x1
+#define DUMP_REQUEST_FLAG       0x1
+#define DUMP_SOURCE_CPU         0x0001
+#define DUMP_SOURCE_HPTE        0x0002
+#define DUMP_SOURCE_RMO         0x0011
+#define DUMP_ERROR_FLAG         0x2000
+#define DUMP_TRIGGERED          0x4000
+#define DUMP_PERFORMED          0x8000
+
+
+/**
+ * init_dump_header() - initialize the header declaring a dump
+ * Returns: length of dump save area.
+ *
+ * When the hypervisor saves crashed state, it needs to put
+ * it somewhere. The dump header tells the hypervisor where
+ * the data can be saved.
+ */
+static unsigned long init_dump_header(struct phyp_dump_header *ph)
+{
+        unsigned long addr_offset = 0;
+
+        /* Set up the dump header */
+        ph->version = DUMP_HEADER_VERSION;
+        ph->num_of_sections = NUM_DUMP_SECTIONS;
+        ph->status = 0;
+
+        ph->first_offset_section =
+                (u32)offsetof(struct phyp_dump_header, cpu_data);
+        ph->dump_disk_section = 0;
+        ph->block_num_dd = 0;
+        ph->num_of_blocks_dd = 0;
+        ph->offset_dd = 0;
+
+        ph->maxtime_to_auto = 0; /* disabled */
+
+        /* The first two sections are mandatory */
+        ph->cpu_data.dump_flags = DUMP_REQUEST_FLAG;
+        ph->cpu_data.source_type = DUMP_SOURCE_CPU;
+        ph->cpu_data.source_address = 0;
+        ph->cpu_data.source_length = phyp_dump_info->cpu_state_size;
+        ph->cpu_data.destination_address = addr_offset;
+        addr_offset += phyp_dump_info->cpu_state_size;
+
+        ph->hpte_data.dump_flags = DUMP_REQUEST_FLAG;
+        ph->hpte_data.source_type = DUMP_SOURCE_HPTE;
+        ph->hpte_data.source_address = 0;
+        ph->hpte_data.source_length = phyp_dump_info->hpte_region_size;
+        ph->hpte_data.destination_address = addr_offset;
+        addr_offset += phyp_dump_info->hpte_region_size;
+
+        /* This section describes the low kernel region */
+        ph->kernel_data.dump_flags = DUMP_REQUEST_FLAG;
+        ph->kernel_data.source_type = DUMP_SOURCE_RMO;
+        ph->kernel_data.source_address = PHYP_DUMP_RMR_START;
+        ph->kernel_data.source_length = PHYP_DUMP_RMR_END;
+        ph->kernel_data.destination_address = addr_offset;
+        addr_offset += ph->kernel_data.source_length;
+
+        return addr_offset;
+}
+
+static void print_dump_header(const struct phyp_dump_header *ph)
+{
+#ifdef DEBUG
+        printk(KERN_INFO "dump header:\n");
+        /* setup some ph->sections required */
+        printk(KERN_INFO "version = %d\n", ph->version);
+        printk(KERN_INFO "Sections = %d\n", ph->num_of_sections);
+        printk(KERN_INFO "Status = 0x%x\n", ph->status);
+
+        /* No ph->disk, so all should be set to 0 */
+        printk(KERN_INFO "Offset to first section 0x%x\n",
+                ph->first_offset_section);
+        printk(KERN_INFO "dump disk sections should be zero\n");
+        printk(KERN_INFO "dump disk section = %d\n", ph->dump_disk_section);
+        printk(KERN_INFO "block num = %ld\n", ph->block_num_dd);
+        printk(KERN_INFO "number of blocks = %ld\n", ph->num_of_blocks_dd);
+        printk(KERN_INFO "dump disk offset = %d\n", ph->offset_dd);
+        printk(KERN_INFO "Max auto time= %d\n", ph->maxtime_to_auto);
+
+        /*set cpu state and hpte states as well scratch pad area */
+        printk(KERN_INFO " CPU AREA \n");
+        printk(KERN_INFO "cpu dump_flags =%d\n", ph->cpu_data.dump_flags);
+        printk(KERN_INFO "cpu source_type =%d\n", ph->cpu_data.source_type);
+        printk(KERN_INFO "cpu error_flags =%d\n", ph->cpu_data.error_flags);
+        printk(KERN_INFO "cpu source_address =%lx\n",
+                ph->cpu_data.source_address);
+        printk(KERN_INFO "cpu source_length =%lx\n",
+                ph->cpu_data.source_length);
+        printk(KERN_INFO "cpu length_copied =%lx\n",
+                ph->cpu_data.length_copied);
+
+        printk(KERN_INFO " HPTE AREA \n");
+        printk(KERN_INFO "HPTE dump_flags =%d\n", ph->hpte_data.dump_flags);
+        printk(KERN_INFO "HPTE source_type =%d\n", ph->hpte_data.source_type);
+        printk(KERN_INFO "HPTE error_flags =%d\n", ph->hpte_data.error_flags);
+        printk(KERN_INFO "HPTE source_address =%lx\n",
+                ph->hpte_data.source_address);
+        printk(KERN_INFO "HPTE source_length =%lx\n",
+                ph->hpte_data.source_length);
+        printk(KERN_INFO "HPTE length_copied =%lx\n",
+                ph->hpte_data.length_copied);
+
+        printk(KERN_INFO " SRSD AREA \n");
+        printk(KERN_INFO "SRSD dump_flags =%d\n", ph->kernel_data.dump_flags);
+        printk(KERN_INFO "SRSD source_type =%d\n", ph->kernel_data.source_type);
+        printk(KERN_INFO "SRSD error_flags =%d\n", ph->kernel_data.error_flags);
+        printk(KERN_INFO "SRSD source_address =%lx\n",
+                ph->kernel_data.source_address);
+        printk(KERN_INFO "SRSD source_length =%lx\n",
+                ph->kernel_data.source_length);
+        printk(KERN_INFO "SRSD length_copied =%lx\n",
+                ph->kernel_data.length_copied);
+#endif
+}
+
+static ssize_t show_phyp_dump_active(struct kobject *kobj,
+                        struct kobj_attribute *attr, char *buf)
+{
+
+        /* create filesystem entry so kdump is phyp-dump aware */
+        return sprintf(buf, "%lx\n", phyp_dump_info->phyp_dump_at_boot);
+}
+
+static struct kobj_attribute pdl = __ATTR(phyp_dump_active, 0600,
+                                        show_phyp_dump_active,
+                                        NULL);
+
+static void register_dump_area(struct phyp_dump_header *ph, unsigned long addr)
+{
+        int rc;
+
+        /* Add addr value if not initialized before */
+        if (ph->cpu_data.destination_address == 0) {
+                ph->cpu_data.destination_address += addr;
+                ph->hpte_data.destination_address += addr;
+                ph->kernel_data.destination_address += addr;
+        }
+
+        /* ToDo Invalidate kdump and free memory range. */
+
+        do {
+                rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
+                                1, ph, sizeof(struct phyp_dump_header));
+        } while (rtas_busy_delay(rc));
+
+        if (rc) {
+                printk(KERN_ERR "phyp-dump: unexpected error (%d) on "
+                                                "register\n", rc);
+                print_dump_header(ph);
+                return;
+        }
+
+        rc = sysfs_create_file(kernel_kobj, &pdl.attr);
+        if (rc)
+                printk(KERN_ERR "phyp-dump: unable to create sysfs"
+                                " file (%d)\n", rc);
+}
+
+static
+void invalidate_last_dump(struct phyp_dump_header *ph, unsigned long addr)
+{
+        int rc;
+
+        /* Add addr value if not initialized before */
+        if (ph->cpu_data.destination_address == 0) {
+                ph->cpu_data.destination_address += addr;
+                ph->hpte_data.destination_address += addr;
+                ph->kernel_data.destination_address += addr;
+        }
+
+        do {
+                rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
+                                2, ph, sizeof(struct phyp_dump_header));
+        } while (rtas_busy_delay(rc));
+
+        if (rc) {
+                printk(KERN_ERR "phyp-dump: unexpected error (%d) "
+                                                "on invalidate\n", rc);
+                print_dump_header(ph);
+        }
+}
+
+/* ------------------------------------------------- */
+/**
+ * release_memory_range -- release memory previously lmb_reserved
+ * @start_pfn: starting physical frame number
+ * @nr_pages: number of pages to free.
+ *
+ * This routine will release memory that had been previously
+ * lmb_reserved in early boot. The released memory becomes
+ * available for genreal use.
+ */
+static void release_memory_range(unsigned long start_pfn,
+                        unsigned long nr_pages)
+{
+        struct page *rpage;
+        unsigned long end_pfn;
+        long i;
+
+        end_pfn = start_pfn + nr_pages;
+
+        for (i = start_pfn; i <= end_pfn; i++) {
+                rpage = pfn_to_page(i);
+                if (PageReserved(rpage)) {
+                        ClearPageReserved(rpage);
+                        init_page_count(rpage);
+                        __free_page(rpage);
+                        totalram_pages++;
+                }
+        }
+}
+
+/**
+ * track_freed_range -- Counts the range being freed.
+ * Once the counter goes to zero, it re-registers dump for
+ * future use.
+ */
+static void
+track_freed_range(unsigned long addr, unsigned long length)
+{
+        static unsigned long scratch_area_size, reserved_area_size;
+
+        if (addr < phyp_dump_info->init_reserve_start)
+                return;
+
+        if ((addr >= phyp_dump_info->init_reserve_start) &&
+            (addr <= phyp_dump_info->init_reserve_start +
+             phyp_dump_info->init_reserve_size))
+                reserved_area_size += length;
+
+        if ((addr >= phyp_dump_info->reserved_scratch_addr) &&
+            (addr <= phyp_dump_info->reserved_scratch_addr +
+             phyp_dump_info->reserved_scratch_size))
+                scratch_area_size += length;
+
+        if ((reserved_area_size == phyp_dump_info->init_reserve_size) &&
+            (scratch_area_size == phyp_dump_info->reserved_scratch_size)) {
+
+                invalidate_last_dump(&phdr,
+                                phyp_dump_info->reserved_scratch_addr);
+                register_dump_area(&phdr,
+                                phyp_dump_info->reserved_scratch_addr);
+        }
+}
+
+/* ------------------------------------------------- */
+/**
+ * sysfs_release_region -- sysfs interface to release memory range.
+ *
+ * Usage:
+ *   "echo <start addr> <length> > /sys/kernel/release_region"
+ *
+ * Example:
+ *   "echo 0x40000000 0x10000000 > /sys/kernel/release_region"
+ *
+ * will release 256MB starting at 1GB.
+ */
+static ssize_t store_release_region(struct kobject *kobj,
+                                struct kobj_attribute *attr,
+                                const char *buf, size_t count)
+{
+        unsigned long start_addr, length, end_addr;
+        unsigned long start_pfn, nr_pages;
+        ssize_t ret;
+
+        ret = sscanf(buf, "%lx %lx", &start_addr, &length);
+        if (ret != 2)
+                return -EINVAL;
+
+        track_freed_range(start_addr, length);
+
+        /* Range-check - don't free any reserved memory that
+         * wasn't reserved for phyp-dump */
+        if (start_addr < phyp_dump_info->init_reserve_start)
+                start_addr = phyp_dump_info->init_reserve_start;
+
+        end_addr = phyp_dump_info->init_reserve_start +
+                        phyp_dump_info->init_reserve_size;
+        if (start_addr+length > end_addr)
+                length = end_addr - start_addr;
+
+        /* Release the region of memory assed in by user */
+        start_pfn = PFN_DOWN(start_addr);
+        nr_pages = PFN_DOWN(length);
+        release_memory_range(start_pfn, nr_pages);
+
+        return count;
+}
+
+static ssize_t show_release_region(struct kobject *kobj,
+                        struct kobj_attribute *attr, char *buf)
+{
+        u64 second_addr_range;
+
+        /* total reserved size - start of scratch area */
+        second_addr_range = phyp_dump_info->init_reserve_size -
+                                phyp_dump_info->reserved_scratch_size;
+        return sprintf(buf, "CPU:0x%lx-0x%lx: HPTE:0x%lx-0x%lx:"
+                            " DUMP:0x%lx-0x%lx, 0x%lx-0x%lx:\n",
+                phdr.cpu_data.destination_address,
+                phdr.cpu_data.length_copied,
+                phdr.hpte_data.destination_address,
+                phdr.hpte_data.length_copied,
+                phdr.kernel_data.destination_address,
+                phdr.kernel_data.length_copied,
+                phyp_dump_info->init_reserve_start,
+                second_addr_range);
+}
+
+static struct kobj_attribute rr = __ATTR(release_region, 0600,
+                                        show_release_region,
+                                        store_release_region);
+
+static int __init phyp_dump_setup(void)
+{
+        struct device_node *rtas;
+        const struct phyp_dump_header *dump_header = NULL;
+        unsigned long dump_area_start;
+        unsigned long dump_area_length;
+        int header_len = 0;
+        int rc;
+
+        /* If no memory was reserved in early boot, there is nothing to do */
+        if (phyp_dump_info->init_reserve_size == 0)
+                return 0;
+
+        /* Return if phyp dump not supported */
+        if (!phyp_dump_info->phyp_dump_configured)
+                return -ENOSYS;
+
+        /* Is there dump data waiting for us? If there isn't,
+         * then register a new dump area, and release all of
+         * the rest of the reserved ram.
+         *
+         * The /rtas/ibm,kernel-dump rtas node is present only
+         * if there is dump data waiting for us.
+         */
+        rtas = of_find_node_by_path("/rtas");
+        if (rtas) {
+                dump_header = of_get_property(rtas, "ibm,kernel-dump",
+                                                &header_len);
+                of_node_put(rtas);
+        }
+
+        print_dump_header(dump_header);
+        dump_area_length = init_dump_header(&phdr);
+        /* align down */
+        dump_area_start = phyp_dump_info->init_reserve_start & PAGE_MASK;
+
+        if (dump_header == NULL) {
+                register_dump_area(&phdr, dump_area_start);
+                return 0;
+        }
+
+        /* re-register the dump area, if old dump was invalid */
+        if ((dump_header) && (dump_header->status & DUMP_ERROR_FLAG)) {
+                invalidate_last_dump(&phdr, dump_area_start);
+                register_dump_area(&phdr, dump_area_start);
+                return 0;
+        }
+
+        if (dump_header) {
+                phyp_dump_info->reserved_scratch_addr =
+                                dump_header->cpu_data.destination_address;
+                phyp_dump_info->reserved_scratch_size =
+                                dump_header->cpu_data.source_length +
+                                dump_header->hpte_data.source_length +
+                                dump_header->kernel_data.source_length;
+        }
+
+        /* Should we create a dump_subsys, analogous to s390/ipl.c ? */
+        rc = sysfs_create_file(kernel_kobj, &rr.attr);
+        if (rc)
+                printk(KERN_ERR "phyp-dump: unable to create sysfs file (%d)\n",
+                                                                        rc);
+
+        /* ToDo: re-register the dump area, for next time. */
+        return 0;
+}
+machine_subsys_initcall(pseries, phyp_dump_setup);
+
+int __init early_init_dt_scan_phyp_dump(unsigned long node,
+                const char *uname, int depth, void *data)
+{
+        const unsigned int *sizes;
+
+        phyp_dump_info->phyp_dump_configured = 0;
+        phyp_dump_info->phyp_dump_is_active = 0;
+
+        if (depth != 1 || strcmp(uname, "rtas") != 0)
+                return 0;
+
+        if (of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL))
+                phyp_dump_info->phyp_dump_configured++;
+
+        if (of_get_flat_dt_prop(node, "ibm,dump-kernel", NULL))
+                phyp_dump_info->phyp_dump_is_active++;
+
+        sizes = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+                                    NULL);
+        if (!sizes)
+                return 0;
+
+        if (sizes[0] == 1)
+                phyp_dump_info->cpu_state_size = *((unsigned long *)&sizes[1]);
+
+        if (sizes[3] == 2)
+                phyp_dump_info->hpte_region_size =
+                                                *((unsigned long *)&sizes[4]);
+        return 1;
+}
+
+/* Look for phyp_dump= cmdline option */
+static int __init early_phyp_dump_enabled(char *p)
+{
+        phyp_dump_info->phyp_dump_at_boot = 1;
+
+        if (!p)
+                return 0;
+
+        if (strncmp(p, "1", 1) == 0)
+                phyp_dump_info->phyp_dump_at_boot = 1;
+        else if (strncmp(p, "0", 1) == 0)
+                phyp_dump_info->phyp_dump_at_boot = 0;
+
+        return 0;
+}
+early_param("phyp_dump", early_phyp_dump_enabled);
+
+/* Look for phyp_dump_reserve_size= cmdline option */
+static int __init early_phyp_dump_reserve_size(char *p)
+{
+        if (p)
+                phyp_dump_info->reserve_bootvar = memparse(p, &p);
+
+        return 0;
+}
+early_param("phyp_dump_reserve_size", early_phyp_dump_reserve_size);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 61136d019554..9e17c0d2a0c8 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -38,4 +38,6 @@ extern void pSeries_final_fixup(void);
 /* Poweron flag used for enabling auto ups restart */
 extern unsigned long rtas_poweron_auto;
 
+extern void find_udbg_vterm(void);
+
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 2800fced8c7c..ac75c10de278 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -222,14 +222,14 @@ static char * parse_next_property(char *buf, char *end, char **name, int *length
         tmp = strchr(buf, ' ');
         if (!tmp) {
                 printk(KERN_ERR "property parse failed in %s at line %d\n",
-                       __FUNCTION__, __LINE__);
+                       __func__, __LINE__);
                 return NULL;
         }
         *tmp = '\0';
 
         if (++tmp >= end) {
                 printk(KERN_ERR "property parse failed in %s at line %d\n",
-                       __FUNCTION__, __LINE__);
+                       __func__, __LINE__);
                 return NULL;
         }
 
@@ -238,12 +238,12 @@ static char * parse_next_property(char *buf, char *end, char **name, int *length
         *length = simple_strtoul(tmp, &tmp, 10);
         if (*length == -1) {
                 printk(KERN_ERR "property parse failed in %s at line %d\n",
-                       __FUNCTION__, __LINE__);
+                       __func__, __LINE__);
                 return NULL;
         }
         if (*tmp != ' ' || ++tmp >= end) {
                 printk(KERN_ERR "property parse failed in %s at line %d\n",
-                       __FUNCTION__, __LINE__);
+                       __func__, __LINE__);
                 return NULL;
         }
 
@@ -252,12 +252,12 @@ static char * parse_next_property(char *buf, char *end, char **name, int *length
         tmp += *length;
         if (tmp > end) {
                 printk(KERN_ERR "property parse failed in %s at line %d\n",
-                       __FUNCTION__, __LINE__);
+                       __func__, __LINE__);
                 return NULL;
         }
         else if (tmp < end && *tmp != ' ' && *tmp != '\0') {
                 printk(KERN_ERR "property parse failed in %s at line %d\n",
-                       __FUNCTION__, __LINE__);
+                       __func__, __LINE__);
                 return NULL;
         }
         tmp++;
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index 8e1ef168e2dd..e5b0ea870164 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -195,31 +195,30 @@ const struct file_operations scanlog_fops = {
 static int __init scanlog_init(void)
 {
         struct proc_dir_entry *ent;
+        void *data;
+        int err = -ENOMEM;
 
         ibm_scan_log_dump = rtas_token("ibm,scan-log-dump");
-        if (ibm_scan_log_dump == RTAS_UNKNOWN_SERVICE) {
-                printk(KERN_ERR "scan-log-dump not implemented on this system\n");
-                return -EIO;
-        }
+        if (ibm_scan_log_dump == RTAS_UNKNOWN_SERVICE)
+                return -ENODEV;
 
-        ent = create_proc_entry("ppc64/rtas/scan-log-dump",  S_IRUSR, NULL);
-        if (ent) {
-                ent->proc_fops = &scanlog_fops;
-                /* Ideally we could allocate a buffer < 4G */
-                ent->data = kmalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
-                if (!ent->data) {
-                        printk(KERN_ERR "Failed to allocate a buffer\n");
-                        remove_proc_entry("scan-log-dump", ent->parent);
-                        return -ENOMEM;
-                }
-                ((unsigned int *)ent->data)[0] = 0;
-        } else {
-                printk(KERN_ERR "Failed to create ppc64/scan-log-dump proc entry\n");
-                return -EIO;
-        }
+        /* Ideally we could allocate a buffer < 4G */
+        data = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
+        if (!data)
+                goto err;
+
+        ent = proc_create("ppc64/rtas/scan-log-dump", S_IRUSR, NULL,
+                          &scanlog_fops);
+        if (!ent)
+                goto err;
+
+        ent->data = data;
         proc_ppc64_scan_log_dump = ent;
 
         return 0;
+err:
+        kfree(data);
+        return err;
 }
 
 static void __exit scanlog_cleanup(void)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index fdb9b1c8f977..f66aa9c3b135 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -76,9 +76,6 @@
 #define DBG(fmt...)
 #endif
 
-/* move those away to a .h */
-extern void find_udbg_vterm(void);
-
 int fwnmi_active;  /* TRUE if an FWNMI handler is present */
 
 static void pseries_shared_idle_sleep(void);
@@ -127,14 +124,60 @@ void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc)
         desc->chip->eoi(irq);
 }
 
-static void __init pseries_mpic_init_IRQ(void)
+static void __init pseries_setup_i8259_cascade(void)
 {
-        struct device_node *np, *old, *cascade = NULL;
-        const unsigned int *addrp;
+        struct device_node *np, *old, *found = NULL;
+        unsigned int cascade;
+        const u32 *addrp;
         unsigned long intack = 0;
+        int naddr;
+
+        for_each_node_by_type(np, "interrupt-controller") {
+                if (of_device_is_compatible(np, "chrp,iic")) {
+                        found = np;
+                        break;
+                }
+        }
+
+        if (found == NULL) {
+                printk(KERN_DEBUG "pic: no ISA interrupt controller\n");
+                return;
+        }
+
+        cascade = irq_of_parse_and_map(found, 0);
+        if (cascade == NO_IRQ) {
+                printk(KERN_ERR "pic: failed to map cascade interrupt");
+                return;
+        }
+        pr_debug("pic: cascade mapped to irq %d\n", cascade);
+
+        for (old = of_node_get(found); old != NULL ; old = np) {
+                np = of_get_parent(old);
+                of_node_put(old);
+                if (np == NULL)
+                        break;
+                if (strcmp(np->name, "pci") != 0)
+                        continue;
+                addrp = of_get_property(np, "8259-interrupt-acknowledge", NULL);
+                if (addrp == NULL)
+                        continue;
+                naddr = of_n_addr_cells(np);
+                intack = addrp[naddr-1];
+                if (naddr > 1)
+                        intack |= ((unsigned long)addrp[naddr-2]) << 32;
+        }
+        if (intack)
+                printk(KERN_DEBUG "pic: PCI 8259 intack at 0x%016lx\n", intack);
+        i8259_init(found, intack);
+        of_node_put(found);
+        set_irq_chained_handler(cascade, pseries_8259_cascade);
+}
+
+static void __init pseries_mpic_init_IRQ(void)
+{
+        struct device_node *np;
         const unsigned int *opprop;
         unsigned long openpic_addr = 0;
-        unsigned int cascade_irq;
         int naddr, n, i, opplen;
         struct mpic *mpic;
 
@@ -167,43 +210,13 @@ static void __init pseries_mpic_init_IRQ(void)
         mpic_init(mpic);
 
         /* Look for cascade */
-        for_each_node_by_type(np, "interrupt-controller")
-                if (of_device_is_compatible(np, "chrp,iic")) {
-                        cascade = np;
-                        break;
-                }
-        if (cascade == NULL)
-                return;
-
-        cascade_irq = irq_of_parse_and_map(cascade, 0);
-        if (cascade_irq == NO_IRQ) {
-                printk(KERN_ERR "mpic: failed to map cascade interrupt");
-                return;
-        }
+        pseries_setup_i8259_cascade();
+}
 
-        /* Check ACK type */
-        for (old = of_node_get(cascade); old != NULL ; old = np) {
-                np = of_get_parent(old);
-                of_node_put(old);
-                if (np == NULL)
-                        break;
-                if (strcmp(np->name, "pci") != 0)
-                        continue;
-                addrp = of_get_property(np, "8259-interrupt-acknowledge",
-                                            NULL);
-                if (addrp == NULL)
-                        continue;
-                naddr = of_n_addr_cells(np);
-                intack = addrp[naddr-1];
-                if (naddr > 1)
-                        intack |= ((unsigned long)addrp[naddr-2]) << 32;
-        }
-        if (intack)
-                printk(KERN_DEBUG "mpic: PCI 8259 intack at 0x%016lx\n",
-                       intack);
-        i8259_init(cascade, intack);
-        of_node_put(cascade);
-        set_irq_chained_handler(cascade_irq, pseries_8259_cascade);
+static void __init pseries_xics_init_IRQ(void)
+{
+        xics_init_IRQ();
+        pseries_setup_i8259_cascade();
 }
 
 static void pseries_lpar_enable_pmcs(void)
@@ -235,7 +248,7 @@ static void __init pseries_discover_pic(void)
                         smp_init_pseries_mpic();
                         return;
                 } else if (strstr(typep, "ppc-xicp")) {
-                        ppc_md.init_IRQ       = xics_init_IRQ;
+                        ppc_md.init_IRQ       = pseries_xics_init_IRQ;
                         setup_kexec_cpu_down_xics();
                         smp_init_pseries_xics();
                         return;
@@ -393,6 +406,7 @@ static void pseries_dedicated_idle_sleep(void)
 { 
         unsigned int cpu = smp_processor_id();
         unsigned long start_snooze;
+        unsigned long in_purr, out_purr;
 
         /*
          * Indicate to the HV that we are idle. Now would be
@@ -400,6 +414,7 @@ static void pseries_dedicated_idle_sleep(void)
          */
         get_lppaca()->idle = 1;
         get_lppaca()->donate_dedicated_cpu = 1;
+        in_purr = mfspr(SPRN_PURR);
 
         /*
          * We come in with interrupts disabled, and need_resched()
@@ -432,6 +447,8 @@ static void pseries_dedicated_idle_sleep(void)
 
 out:
         HMT_medium();
+        out_purr = mfspr(SPRN_PURR);
+        get_lppaca()->wait_state_cycles += out_purr - in_purr;
         get_lppaca()->donate_dedicated_cpu = 0;
         get_lppaca()->idle = 0;
 }
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index a977f200db89..43df53c30aa0 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -516,6 +516,8 @@ static struct irq_chip xics_pic_lpar = {
         .set_affinity = xics_set_affinity
 };
 
+/* Points to the irq_chip we're actually using */
+static struct irq_chip *xics_irq_chip;
 
 static int xics_host_match(struct irq_host *h, struct device_node *node)
 {
@@ -526,23 +528,13 @@ static int xics_host_match(struct irq_host *h, struct device_node *node)
         return !of_device_is_compatible(node, "chrp,iic");
 }
 
-static int xics_host_map_direct(struct irq_host *h, unsigned int virq,
-                                irq_hw_number_t hw)
+static int xics_host_map(struct irq_host *h, unsigned int virq,
+                         irq_hw_number_t hw)
 {
-        pr_debug("xics: map_direct virq %d, hwirq 0x%lx\n", virq, hw);
+        pr_debug("xics: map virq %d, hwirq 0x%lx\n", virq, hw);
 
         get_irq_desc(virq)->status |= IRQ_LEVEL;
-        set_irq_chip_and_handler(virq, &xics_pic_direct, handle_fasteoi_irq);
-        return 0;
-}
-
-static int xics_host_map_lpar(struct irq_host *h, unsigned int virq,
-                              irq_hw_number_t hw)
-{
-        pr_debug("xics: map_direct virq %d, hwirq 0x%lx\n", virq, hw);
-
-        get_irq_desc(virq)->status |= IRQ_LEVEL;
-        set_irq_chip_and_handler(virq, &xics_pic_lpar, handle_fasteoi_irq);
+        set_irq_chip_and_handler(virq, xics_irq_chip, handle_fasteoi_irq);
         return 0;
 }
 
@@ -561,27 +553,20 @@ static int xics_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops xics_host_direct_ops = {
+static struct irq_host_ops xics_host_ops = {
         .match = xics_host_match,
-        .map = xics_host_map_direct,
-        .xlate = xics_host_xlate,
-};
-
-static struct irq_host_ops xics_host_lpar_ops = {
-        .match = xics_host_match,
-        .map = xics_host_map_lpar,
+        .map = xics_host_map,
         .xlate = xics_host_xlate,
 };
 
 static void __init xics_init_host(void)
 {
-        struct irq_host_ops *ops;
-
         if (firmware_has_feature(FW_FEATURE_LPAR))
-                ops = &xics_host_lpar_ops;
+                xics_irq_chip = &xics_pic_lpar;
         else
-                ops = &xics_host_direct_ops;
-        xics_host = irq_alloc_host(NULL, IRQ_HOST_MAP_TREE, 0, ops,
+                xics_irq_chip = &xics_pic_direct;
+
+        xics_host = irq_alloc_host(NULL, IRQ_HOST_MAP_TREE, 0, &xics_host_ops,
                                    XICS_IRQ_SPURIOUS);
         BUG_ON(xics_host == NULL);
         irq_set_default_host(xics_host);
@@ -655,52 +640,6 @@ static void __init xics_init_one_node(struct device_node *np,
         }
 }
 
-
-static void __init xics_setup_8259_cascade(void)
-{
-        struct device_node *np, *old, *found = NULL;
-        int cascade, naddr;
-        const u32 *addrp;
-        unsigned long intack = 0;
-
-        for_each_node_by_type(np, "interrupt-controller")
-                if (of_device_is_compatible(np, "chrp,iic")) {
-                        found = np;
-                        break;
-                }
-        if (found == NULL) {
-                printk(KERN_DEBUG "xics: no ISA interrupt controller\n");
-                return;
-        }
-        cascade = irq_of_parse_and_map(found, 0);
-        if (cascade == NO_IRQ) {
-                printk(KERN_ERR "xics: failed to map cascade interrupt");
-                return;
-        }
-        pr_debug("xics: cascade mapped to irq %d\n", cascade);
-
-        for (old = of_node_get(found); old != NULL ; old = np) {
-                np = of_get_parent(old);
-                of_node_put(old);
-                if (np == NULL)
-                        break;
-                if (strcmp(np->name, "pci") != 0)
-                        continue;
-                addrp = of_get_property(np, "8259-interrupt-acknowledge", NULL);
-                if (addrp == NULL)
-                        continue;
-                naddr = of_n_addr_cells(np);
-                intack = addrp[naddr-1];
-                if (naddr > 1)
-                        intack |= ((unsigned long)addrp[naddr-2]) << 32;
-        }
-        if (intack)
-                printk(KERN_DEBUG "xics: PCI 8259 intack at 0x%016lx\n", intack);
-        i8259_init(found, intack);
-        of_node_put(found);
-        set_irq_chained_handler(cascade, pseries_8259_cascade);
-}
-
 void __init xics_init_IRQ(void)
 {
         struct device_node *np;
@@ -733,8 +672,6 @@ void __init xics_init_IRQ(void)
 
         xics_setup_cpu();
 
-        xics_setup_8259_cascade();
-
         ppc64_boot_msg(0x21, "XICS Done");
 }
 
diff --git a/arch/powerpc/platforms/pseries/xics.h b/arch/powerpc/platforms/pseries/xics.h
index c26bcff47b6d..1c5321ae8f2f 100644
--- a/arch/powerpc/platforms/pseries/xics.h
+++ b/arch/powerpc/platforms/pseries/xics.h
@@ -28,7 +28,4 @@ struct xics_ipi_struct {
 
 extern struct xics_ipi_struct xics_ipi_message[NR_CPUS] __cacheline_aligned;
 
-struct irq_desc;
-extern void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc);
-
 #endif /* _POWERPC_KERNEL_XICS_H */