244 files changed, 7383 insertions, 6057 deletions

diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index bf1cf98d2a27..0256805b548f 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -10,7 +10,7 @@ standard for controlling intelligent devices that monitor a system.
 It provides for dynamic discovery of sensors in the system and the
 ability to monitor the sensors and be informed when the sensor's
 values change or go outside certain boundaries.  It also has a
-standardized database for field-replacable units (FRUs) and a watchdog
+standardized database for field-replaceable units (FRUs) and a watchdog
 timer.
 
 To use this, you need an interface to an IPMI controller in your
@@ -64,7 +64,7 @@ situation, you need to read the section below named 'The SI Driver' or
 IPMI defines a standard watchdog timer.  You can enable this with the
 'IPMI Watchdog Timer' config option.  If you compile the driver into
 the kernel, then via a kernel command-line option you can have the
-watchdog timer start as soon as it intitializes.  It also have a lot
+watchdog timer start as soon as it initializes.  It also have a lot
 of other options, see the 'Watchdog' section below for more details.
 Note that you can also have the watchdog continue to run if it is
 closed (by default it is disabled on close).  Go into the 'Watchdog
diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example.c
index 3d4713a6c207..2d6a14a463e0 100644
--- a/Documentation/filesystems/configfs/configfs_example.c
+++ b/Documentation/filesystems/configfs/configfs_example.c
@@ -264,6 +264,15 @@ static struct config_item_type simple_child_type = {
 };
 
 
+struct simple_children {
+        struct config_group group;
+};
+
+static inline struct simple_children *to_simple_children(struct config_item *item)
+{
+        return item ? container_of(to_config_group(item), struct simple_children, group) : NULL;
+}
+
 static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
 {
         struct simple_child *simple_child;
@@ -304,7 +313,13 @@ static ssize_t simple_children_attr_show(struct config_item *item,
 "items have only one attribute that is readable and writeable.\n");
 }
 
+static void simple_children_release(struct config_item *item)
+{
+        kfree(to_simple_children(item));
+}
+
 static struct configfs_item_operations simple_children_item_ops = {
+        .release        = simple_children_release,
         .show_attribute = simple_children_attr_show,
 };
 
@@ -345,10 +360,6 @@ static struct configfs_subsystem simple_children_subsys = {
  * children of its own.
  */
 
-struct simple_children {
-        struct config_group group;
-};
-
 static struct config_group *group_children_make_group(struct config_group *group, const char *name)
 {
         struct simple_children *simple_children;
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 2dc246af4885..86754eb390da 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -28,7 +28,6 @@ Currently, these files are in /proc/sys/vm:
 - block_dump
 - drop-caches
 - zone_reclaim_mode
-- zone_reclaim_interval
 - panic_on_oom
 
 ==============================================================
@@ -167,18 +166,6 @@ use of files and builds up large slab caches. However, the slab
 shrink operation is global, may take a long time and free slabs
 in all nodes of the system.
 
-================================================================
-
-zone_reclaim_interval:
-
-The time allowed for off node allocations after zone reclaim
-has failed to reclaim enough pages to allow a local allocation.
-
-Time is set in seconds and set by default to 30 seconds.
-
-Reduce the interval if undesired off node allocations occur. However, too
-frequent scans will have a negative impact onoff node allocation performance.
-
 =============================================================
 
 panic_on_oom
diff --git a/MAINTAINERS b/MAINTAINERS
index 31a13720f23c..7e5a7ff2a86c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -925,23 +925,21 @@ S:	Maintained
 
 EDAC-CORE
 P:      Doug Thompson
-M:      norsk5@xmission.com, dthompson@linuxnetworx.com
-P:      Dave Peterson
-M:      dsp@llnl.gov, dave_peterson@pobox.com
+M:      norsk5@xmission.com
 L:      bluesmoke-devel@lists.sourceforge.net
 W:      bluesmoke.sourceforge.net
-S:      Maintained
+S:      Supported
 
 EDAC-E752X
-P:      Dave Peterson
-M:      dsp@llnl.gov, dave_peterson@pobox.com
+P:      Mark Gross
+M:      mark.gross@intel.com
 L:      bluesmoke-devel@lists.sourceforge.net
 W:      bluesmoke.sourceforge.net
 S:      Maintained
 
 EDAC-E7XXX
-P:      Dave Peterson
-M:      dsp@llnl.gov, dave_peterson@pobox.com
+P:      Doug Thompson
+M:      norsk5@xmission.com
 L:      bluesmoke-devel@lists.sourceforge.net
 W:      bluesmoke.sourceforge.net
 S:      Maintained
diff --git a/arch/arm/mm/mm-armv.c b/arch/arm/mm/mm-armv.c
index 95273de4f772..931be1798122 100644
--- a/arch/arm/mm/mm-armv.c
+++ b/arch/arm/mm/mm-armv.c
@@ -227,7 +227,7 @@ void free_pgd_slow(pgd_t *pgd)
 
         pte = pmd_page(*pmd);
         pmd_clear(pmd);
-        dec_page_state(nr_page_table_pages);
+        dec_zone_page_state(virt_to_page((unsigned long *)pgd), NR_PAGETABLE);
         pte_lock_deinit(pte);
         pte_free(pte);
         pmd_free(pmd);
diff --git a/arch/i386/kernel/msr.c b/arch/i386/kernel/msr.c
index d022cb8fd725..5c29a9fb4a44 100644
--- a/arch/i386/kernel/msr.c
+++ b/arch/i386/kernel/msr.c
@@ -251,7 +251,9 @@ static int msr_class_device_create(int i)
         return err;
 }
 
-static int msr_class_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+#ifdef CONFIG_HOTPLUG_CPU
+static int msr_class_cpu_callback(struct notifier_block *nfb,
+                                unsigned long action, void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
 
@@ -270,6 +272,7 @@ static struct notifier_block __cpuinitdata msr_class_cpu_notifier =
 {
         .notifier_call = msr_class_cpu_callback,
 };
+#endif
 
 static int __init msr_init(void)
 {
@@ -292,7 +295,7 @@ static int __init msr_init(void)
                 if (err != 0)
                         goto out_class;
         }
-        register_cpu_notifier(&msr_class_cpu_notifier);
+        register_hotcpu_notifier(&msr_class_cpu_notifier);
 
         err = 0;
         goto out;
@@ -315,7 +318,7 @@ static void __exit msr_exit(void)
                 class_device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu));
         class_destroy(msr_class);
         unregister_chrdev(MSR_MAJOR, "cpu/msr");
-        unregister_cpu_notifier(&msr_class_cpu_notifier);
+        unregister_hotcpu_notifier(&msr_class_cpu_notifier);
 }
 
 module_init(msr_init);
diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c
index 5b8b579a079f..6e9e494c6c3d 100644
--- a/arch/i386/mach-voyager/voyager_smp.c
+++ b/arch/i386/mach-voyager/voyager_smp.c
@@ -1938,3 +1938,9 @@ smp_cpus_done(unsigned int max_cpus)
 {
         zap_low_mappings();
 }
+
+void __init
+smp_setup_processor_id(void)
+{
+        current_thread_info()->cpu = hard_smp_processor_id();
+}
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index 2889567e21a1..5e735ff90e8a 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -30,7 +30,6 @@ void show_mem(void)
         struct page *page;
         pg_data_t *pgdat;
         unsigned long i;
-        struct page_state ps;
         unsigned long flags;
 
         printk(KERN_INFO "Mem-info:\n");
@@ -58,12 +57,13 @@ void show_mem(void)
         printk(KERN_INFO "%d pages shared\n", shared);
         printk(KERN_INFO "%d pages swap cached\n", cached);
 
-        get_page_state(&ps);
-        printk(KERN_INFO "%lu pages dirty\n", ps.nr_dirty);
-        printk(KERN_INFO "%lu pages writeback\n", ps.nr_writeback);
-        printk(KERN_INFO "%lu pages mapped\n", ps.nr_mapped);
-        printk(KERN_INFO "%lu pages slab\n", ps.nr_slab);
-        printk(KERN_INFO "%lu pages pagetables\n", ps.nr_page_table_pages);
+        printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
+        printk(KERN_INFO "%lu pages writeback\n",
+                                        global_page_state(NR_WRITEBACK));
+        printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
+        printk(KERN_INFO "%lu pages slab\n", global_page_state(NR_SLAB));
+        printk(KERN_INFO "%lu pages pagetables\n",
+                                        global_page_state(NR_PAGETABLE));
 }
 
 /*
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index b487e227a1f7..47de9ee6bcd6 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -70,6 +70,11 @@ config DMA_IS_DMA32
         bool
         default y
 
+config DMA_IS_NORMAL
+        bool
+        depends on IA64_SGI_SN2
+        default y
+
 choice
         prompt "System type"
         default IA64_GENERIC
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 61bc44626c04..2476ca739c1e 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -766,7 +766,6 @@ unsigned long nr_iowait(void)
 #endif /* MODULE */
 EXPORT_SYMBOL_GPL(si_swapinfo);
 EXPORT_SYMBOL_GPL(nr_threads);
-EXPORT_SYMBOL_GPL(get_full_page_state);
 EXPORT_SYMBOL_GPL(nr_running);
 EXPORT_SYMBOL_GPL(nr_iowait);
 //EXPORT_SYMBOL_GPL(nr_context_switches);
diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c
index 7915a197d96d..4811e2dac864 100644
--- a/arch/s390/appldata/appldata_mem.c
+++ b/arch/s390/appldata/appldata_mem.c
@@ -107,21 +107,21 @@ static void appldata_get_mem_data(void *data)
          * serialized through the appldata_ops_lock and can use static
          */
         static struct sysinfo val;
-        static struct page_state ps;
+        unsigned long ev[NR_VM_EVENT_ITEMS];
         struct appldata_mem_data *mem_data;
 
         mem_data = data;
         mem_data->sync_count_1++;
 
-        get_full_page_state(&ps);
-        mem_data->pgpgin     = ps.pgpgin >> 1;
-        mem_data->pgpgout    = ps.pgpgout >> 1;
-        mem_data->pswpin     = ps.pswpin;
-        mem_data->pswpout    = ps.pswpout;
-        mem_data->pgalloc    = ps.pgalloc_high + ps.pgalloc_normal +
-                               ps.pgalloc_dma;
-        mem_data->pgfault    = ps.pgfault;
-        mem_data->pgmajfault = ps.pgmajfault;
+        all_vm_events(ev);
+        mem_data->pgpgin     = ev[PGPGIN] >> 1;
+        mem_data->pgpgout    = ev[PGPGOUT] >> 1;
+        mem_data->pswpin     = ev[PSWPIN];
+        mem_data->pswpout    = ev[PSWPOUT];
+        mem_data->pgalloc    = ev[PGALLOC_HIGH] + ev[PGALLOC_NORMAL] +
+                               ev[PGALLOC_DMA];
+        mem_data->pgfault    = ev[PGFAULT];
+        mem_data->pgmajfault = ev[PGMAJFAULT];
 
         si_meminfo(&val);
         mem_data->sharedram = val.sharedram;
@@ -130,7 +130,8 @@ static void appldata_get_mem_data(void *data)
         mem_data->totalhigh = P2K(val.totalhigh);
         mem_data->freehigh  = P2K(val.freehigh);
         mem_data->bufferram = P2K(val.bufferram);
-        mem_data->cached    = P2K(atomic_read(&nr_pagecache) - val.bufferram);
+        mem_data->cached    = P2K(global_page_state(NR_FILE_PAGES)
+                                - val.bufferram);
 
         si_swapinfo(&val);
         mem_data->totalswap = P2K(val.totalswap);
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 79d177149fdb..8654b446ac9e 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -26,6 +26,7 @@
  */
 
 #include <linux/config.h>
+#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -40,6 +41,7 @@
 #include <asm/vaddrs.h>
 #include <asm/oplib.h>
 #include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/sbus.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -143,6 +145,21 @@ void __iomem *sbus_ioremap(struct resource *phyres, unsigned long offset,
             phyres->start + offset, size, name);
 }
 
+void __iomem *of_ioremap(struct resource *res, unsigned long offset,
+                         unsigned long size, char *name)
+{
+        return _sparc_alloc_io(res->flags & 0xF,
+                               res->start + offset,
+                               size, name);
+}
+EXPORT_SYMBOL(of_ioremap);
+
+void of_iounmap(void __iomem *base, unsigned long size)
+{
+        iounmap(base);
+}
+EXPORT_SYMBOL(of_iounmap);
+
 /*
  */
 void sbus_iounmap(volatile void __iomem *addr, unsigned long size)
diff --git a/arch/sparc/kernel/of_device.c b/arch/sparc/kernel/of_device.c
index 80a809478781..bc956c530376 100644
--- a/arch/sparc/kernel/of_device.c
+++ b/arch/sparc/kernel/of_device.c
@@ -129,6 +129,26 @@ static int of_device_resume(struct device * dev)
         return error;
 }
 
+static int node_match(struct device *dev, void *data)
+{
+        struct of_device *op = to_of_device(dev);
+        struct device_node *dp = data;
+
+        return (op->node == dp);
+}
+
+struct of_device *of_find_device_by_node(struct device_node *dp)
+{
+        struct device *dev = bus_find_device(&of_bus_type, NULL,
+                                             dp, node_match);
+
+        if (dev)
+                return to_of_device(dev);
+
+        return NULL;
+}
+EXPORT_SYMBOL(of_find_device_by_node);
+
 #ifdef CONFIG_PCI
 struct bus_type ebus_bus_type = {
        .name    = "ebus",
@@ -153,10 +173,459 @@ struct bus_type sbus_bus_type = {
 EXPORT_SYMBOL(sbus_bus_type);
 #endif
 
+struct bus_type of_bus_type = {
+       .name    = "of",
+       .match   = of_platform_bus_match,
+       .probe   = of_device_probe,
+       .remove  = of_device_remove,
+       .suspend = of_device_suspend,
+       .resume  = of_device_resume,
+};
+EXPORT_SYMBOL(of_bus_type);
+
+static inline u64 of_read_addr(u32 *cell, int size)
+{
+        u64 r = 0;
+        while (size--)
+                r = (r << 32) | *(cell++);
+        return r;
+}
+
+static void __init get_cells(struct device_node *dp,
+                             int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = of_n_addr_cells(dp);
+        if (sizec)
+                *sizec = of_n_size_cells(dp);
+}
+
+/* Max address size we deal with */
+#define OF_MAX_ADDR_CELLS       4
+
+struct of_bus {
+        const char      *name;
+        const char      *addr_prop_name;
+        int             (*match)(struct device_node *parent);
+        void            (*count_cells)(struct device_node *child,
+                                       int *addrc, int *sizec);
+        u64             (*map)(u32 *addr, u32 *range, int na, int ns, int pna);
+        int             (*translate)(u32 *addr, u64 offset, int na);
+        unsigned int    (*get_flags)(u32 *addr);
+};
+
+/*
+ * Default translator (generic bus)
+ */
+
+static void of_bus_default_count_cells(struct device_node *dev,
+                                       int *addrc, int *sizec)
+{
+        get_cells(dev, addrc, sizec);
+}
+
+static u64 of_bus_default_map(u32 *addr, u32 *range, int na, int ns, int pna)
+{
+        u64 cp, s, da;
+
+        cp = of_read_addr(range, na);
+        s  = of_read_addr(range + na + pna, ns);
+        da = of_read_addr(addr, na);
+
+        if (da < cp || da >= (cp + s))
+                return OF_BAD_ADDR;
+        return da - cp;
+}
+
+static int of_bus_default_translate(u32 *addr, u64 offset, int na)
+{
+        u64 a = of_read_addr(addr, na);
+        memset(addr, 0, na * 4);
+        a += offset;
+        if (na > 1)
+                addr[na - 2] = a >> 32;
+        addr[na - 1] = a & 0xffffffffu;
+
+        return 0;
+}
+
+static unsigned int of_bus_default_get_flags(u32 *addr)
+{
+        return IORESOURCE_MEM;
+}
+
+
+/*
+ * PCI bus specific translator
+ */
+
+static int of_bus_pci_match(struct device_node *np)
+{
+        return !strcmp(np->type, "pci") || !strcmp(np->type, "pciex");
+}
+
+static void of_bus_pci_count_cells(struct device_node *np,
+                                   int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = 3;
+        if (sizec)
+                *sizec = 2;
+}
+
+static u64 of_bus_pci_map(u32 *addr, u32 *range, int na, int ns, int pna)
+{
+        u64 cp, s, da;
+
+        /* Check address type match */
+        if ((addr[0] ^ range[0]) & 0x03000000)
+                return OF_BAD_ADDR;
+
+        /* Read address values, skipping high cell */
+        cp = of_read_addr(range + 1, na - 1);
+        s  = of_read_addr(range + na + pna, ns);
+        da = of_read_addr(addr + 1, na - 1);
+
+        if (da < cp || da >= (cp + s))
+                return OF_BAD_ADDR;
+        return da - cp;
+}
+
+static int of_bus_pci_translate(u32 *addr, u64 offset, int na)
+{
+        return of_bus_default_translate(addr + 1, offset, na - 1);
+}
+
+static unsigned int of_bus_pci_get_flags(u32 *addr)
+{
+        unsigned int flags = 0;
+        u32 w = addr[0];
+
+        switch((w >> 24) & 0x03) {
+        case 0x01:
+                flags |= IORESOURCE_IO;
+        case 0x02: /* 32 bits */
+        case 0x03: /* 64 bits */
+                flags |= IORESOURCE_MEM;
+        }
+        if (w & 0x40000000)
+                flags |= IORESOURCE_PREFETCH;
+        return flags;
+}
+
+/*
+ * SBUS bus specific translator
+ */
+
+static int of_bus_sbus_match(struct device_node *np)
+{
+        return !strcmp(np->name, "sbus") ||
+                !strcmp(np->name, "sbi");
+}
+
+static void of_bus_sbus_count_cells(struct device_node *child,
+                                   int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = 2;
+        if (sizec)
+                *sizec = 1;
+}
+
+static u64 of_bus_sbus_map(u32 *addr, u32 *range, int na, int ns, int pna)
+{
+        return of_bus_default_map(addr, range, na, ns, pna);
+}
+
+static int of_bus_sbus_translate(u32 *addr, u64 offset, int na)
+{
+        return of_bus_default_translate(addr, offset, na);
+}
+
+static unsigned int of_bus_sbus_get_flags(u32 *addr)
+{
+        return IORESOURCE_MEM;
+}
+
+
+/*
+ * Array of bus specific translators
+ */
+
+static struct of_bus of_busses[] = {
+        /* PCI */
+        {
+                .name = "pci",
+                .addr_prop_name = "assigned-addresses",
+                .match = of_bus_pci_match,
+                .count_cells = of_bus_pci_count_cells,
+                .map = of_bus_pci_map,
+                .translate = of_bus_pci_translate,
+                .get_flags = of_bus_pci_get_flags,
+        },
+        /* SBUS */
+        {
+                .name = "sbus",
+                .addr_prop_name = "reg",
+                .match = of_bus_sbus_match,
+                .count_cells = of_bus_sbus_count_cells,
+                .map = of_bus_sbus_map,
+                .translate = of_bus_sbus_translate,
+                .get_flags = of_bus_sbus_get_flags,
+        },
+        /* Default */
+        {
+                .name = "default",
+                .addr_prop_name = "reg",
+                .match = NULL,
+                .count_cells = of_bus_default_count_cells,
+                .map = of_bus_default_map,
+                .translate = of_bus_default_translate,
+                .get_flags = of_bus_default_get_flags,
+        },
+};
+
+static struct of_bus *of_match_bus(struct device_node *np)
+{
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(of_busses); i ++)
+                if (!of_busses[i].match || of_busses[i].match(np))
+                        return &of_busses[i];
+        BUG();
+        return NULL;
+}
+
+static int __init build_one_resource(struct device_node *parent,
+                                     struct of_bus *bus,
+                                     struct of_bus *pbus,
+                                     u32 *addr,
+                                     int na, int ns, int pna)
+{
+        u32 *ranges;
+        unsigned int rlen;
+        int rone;
+        u64 offset = OF_BAD_ADDR;
+
+        ranges = of_get_property(parent, "ranges", &rlen);
+        if (ranges == NULL || rlen == 0) {
+                offset = of_read_addr(addr, na);
+                memset(addr, 0, pna * 4);
+                goto finish;
+        }
+
+        /* Now walk through the ranges */
+        rlen /= 4;
+        rone = na + pna + ns;
+        for (; rlen >= rone; rlen -= rone, ranges += rone) {
+                offset = bus->map(addr, ranges, na, ns, pna);
+                if (offset != OF_BAD_ADDR)
+                        break;
+        }
+        if (offset == OF_BAD_ADDR)
+                return 1;
+
+        memcpy(addr, ranges + na, 4 * pna);
+
+finish:
+        /* Translate it into parent bus space */
+        return pbus->translate(addr, offset, pna);
+}
+
+static void __init build_device_resources(struct of_device *op,
+                                          struct device *parent)
+{
+        struct of_device *p_op;
+        struct of_bus *bus;
+        int na, ns;
+        int index, num_reg;
+        void *preg;
+
+        if (!parent)
+                return;
+
+        p_op = to_of_device(parent);
+        bus = of_match_bus(p_op->node);
+        bus->count_cells(op->node, &na, &ns);
+
+        preg = of_get_property(op->node, bus->addr_prop_name, &num_reg);
+        if (!preg || num_reg == 0)
+                return;
+
+        /* Convert to num-cells.  */
+        num_reg /= 4;
+
+        /* Conver to num-entries.  */
+        num_reg /= na + ns;
+
+        for (index = 0; index < num_reg; index++) {
+                struct resource *r = &op->resource[index];
+                u32 addr[OF_MAX_ADDR_CELLS];
+                u32 *reg = (preg + (index * ((na + ns) * 4)));
+                struct device_node *dp = op->node;
+                struct device_node *pp = p_op->node;
+                struct of_bus *pbus;
+                u64 size, result = OF_BAD_ADDR;
+                unsigned long flags;
+                int dna, dns;
+                int pna, pns;
+
+                size = of_read_addr(reg + na, ns);
+                flags = bus->get_flags(reg);
+
+                memcpy(addr, reg, na * 4);
+
+                /* If the immediate parent has no ranges property to apply,
+                 * just use a 1<->1 mapping.
+                 */
+                if (of_find_property(pp, "ranges", NULL) == NULL) {
+                        result = of_read_addr(addr, na);
+                        goto build_res;
+                }
+
+                dna = na;
+                dns = ns;
+
+                while (1) {
+                        dp = pp;
+                        pp = dp->parent;
+                        if (!pp) {
+                                result = of_read_addr(addr, dna);
+                                break;
+                        }
+
+                        pbus = of_match_bus(pp);
+                        pbus->count_cells(dp, &pna, &pns);
+
+                        if (build_one_resource(dp, bus, pbus, addr, dna, dns, pna))
+                                break;
+
+                        dna = pna;
+                        dns = pns;
+                        bus = pbus;
+                }
+
+        build_res:
+                memset(r, 0, sizeof(*r));
+                if (result != OF_BAD_ADDR) {
+                        r->start = result & 0xffffffff;
+                        r->end = result + size - 1;
+                        r->flags = flags | ((result >> 32ULL) & 0xffUL);
+                } else {
+                        r->start = ~0UL;
+                        r->end = ~0UL;
+                }
+                r->name = op->node->name;
+        }
+}
+
+static struct of_device * __init scan_one_device(struct device_node *dp,
+                                                 struct device *parent)
+{
+        struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL);
+        struct linux_prom_irqs *intr;
+        int len, i;
+
+        if (!op)
+                return NULL;
+
+        op->node = dp;
+
+        op->clock_freq = of_getintprop_default(dp, "clock-frequency",
+                                               (25*1000*1000));
+        op->portid = of_getintprop_default(dp, "upa-portid", -1);
+        if (op->portid == -1)
+                op->portid = of_getintprop_default(dp, "portid", -1);
+
+        intr = of_get_property(dp, "intr", &len);
+        if (intr) {
+                op->num_irqs = len / sizeof(struct linux_prom_irqs);
+                for (i = 0; i < op->num_irqs; i++)
+                        op->irqs[i] = intr[i].pri;
+        } else {
+                unsigned int *irq = of_get_property(dp, "interrupts", &len);
+
+                if (irq) {
+                        op->num_irqs = len / sizeof(unsigned int);
+                        for (i = 0; i < op->num_irqs; i++)
+                                op->irqs[i] = irq[i];
+                } else {
+                        op->num_irqs = 0;
+                }
+        }
+        if (sparc_cpu_model == sun4d) {
+                static int pil_to_sbus[] = {
+                        0, 0, 1, 2, 0, 3, 0, 4, 0, 5, 0, 6, 0, 7, 0, 0,
+                };
+                struct device_node *busp = dp->parent;
+                struct linux_prom_registers *regs;
+                int board = of_getintprop_default(busp, "board#", 0);
+                int slot;
+
+                regs = of_get_property(dp, "reg", NULL);
+                slot = regs->which_io;
+
+                for (i = 0; i < op->num_irqs; i++) {
+                        int this_irq = op->irqs[i];
+                        int sbusl = pil_to_sbus[this_irq];
+
+                        if (sbusl)
+                                this_irq = (((board + 1) << 5) +
+                                            (sbusl << 2) +
+                                            slot);
+
+                        op->irqs[i] = this_irq;
+                }
+        }
+
+        build_device_resources(op, parent);
+
+        op->dev.parent = parent;
+        op->dev.bus = &of_bus_type;
+        if (!parent)
+                strcpy(op->dev.bus_id, "root");
+        else
+                strcpy(op->dev.bus_id, dp->path_component_name);
+
+        if (of_device_register(op)) {
+                printk("%s: Could not register of device.\n",
+                       dp->full_name);
+                kfree(op);
+                op = NULL;
+        }
+
+        return op;
+}
+
+static void __init scan_tree(struct device_node *dp, struct device *parent)
+{
+        while (dp) {
+                struct of_device *op = scan_one_device(dp, parent);
+
+                if (op)
+                        scan_tree(dp->child, &op->dev);
+
+                dp = dp->sibling;
+        }
+}
+
+static void __init scan_of_devices(void)
+{
+        struct device_node *root = of_find_node_by_path("/");
+        struct of_device *parent;
+
+        parent = scan_one_device(root, NULL);
+        if (!parent)
+                return;
+
+        scan_tree(root->child, &parent->dev);
+}
+
 static int __init of_bus_driver_init(void)
 {
-        int err = 0;
+        int err;
 
+        err = bus_register(&of_bus_type);
 #ifdef CONFIG_PCI
         if (!err)
                 err = bus_register(&ebus_bus_type);
@@ -165,7 +634,11 @@ static int __init of_bus_driver_init(void)
         if (!err)
                 err = bus_register(&sbus_bus_type);
 #endif
-        return 0;
+
+        if (!err)
+                scan_of_devices();
+
+        return err;
 }
 
 postcore_initcall(of_bus_driver_init);
diff --git a/arch/sparc/kernel/prom.c b/arch/sparc/kernel/prom.c
index 946ce6d15819..4b06dcb00ebd 100644
--- a/arch/sparc/kernel/prom.c
+++ b/arch/sparc/kernel/prom.c
@@ -190,6 +190,36 @@ int of_getintprop_default(struct device_node *np, const char *name, int def)
 }
 EXPORT_SYMBOL(of_getintprop_default);
 
+int of_n_addr_cells(struct device_node *np)
+{
+        int* ip;
+        do {
+                if (np->parent)
+                        np = np->parent;
+                ip = of_get_property(np, "#address-cells", NULL);
+                if (ip != NULL)
+                        return *ip;
+        } while (np->parent);
+        /* No #address-cells property for the root node, default to 2 */
+        return 2;
+}
+EXPORT_SYMBOL(of_n_addr_cells);
+
+int of_n_size_cells(struct device_node *np)
+{
+        int* ip;
+        do {
+                if (np->parent)
+                        np = np->parent;
+                ip = of_get_property(np, "#size-cells", NULL);
+                if (ip != NULL)
+                        return *ip;
+        } while (np->parent);
+        /* No #size-cells property for the root node, default to 1 */
+        return 1;
+}
+EXPORT_SYMBOL(of_n_size_cells);
+
 int of_set_property(struct device_node *dp, const char *name, void *val, int len)
 {
         struct property **prevp;
diff --git a/arch/sparc/kernel/sys_sunos.c b/arch/sparc/kernel/sys_sunos.c
index 288de276d9ff..aa0fb2efb615 100644
--- a/arch/sparc/kernel/sys_sunos.c
+++ b/arch/sparc/kernel/sys_sunos.c
@@ -196,7 +196,7 @@ asmlinkage int sunos_brk(unsigned long brk)
          * simple, it hopefully works in most obvious cases.. Easy to
          * fool it, but this should catch most mistakes.
          */
-        freepages = get_page_cache_size();
+        freepages = global_page_state(NR_FILE_PAGES);
         freepages >>= 1;
         freepages += nr_free_pages();
         freepages += nr_swap_pages;
diff --git a/arch/sparc/kernel/time.c b/arch/sparc/kernel/time.c
index 7dadcdb4ca42..9631e8f4ae60 100644
--- a/arch/sparc/kernel/time.c
+++ b/arch/sparc/kernel/time.c
@@ -42,6 +42,7 @@
 #include <asm/sun4paddr.h>
 #include <asm/page.h>
 #include <asm/pcic.h>
+#include <asm/of_device.h>
 
 extern unsigned long wall_jiffies;
 
@@ -273,83 +274,31 @@ static __inline__ void sun4_clock_probe(void)
 #endif
 }
 
-/* Probe for the mostek real time clock chip. */
-static __inline__ void clock_probe(void)
+static int __devinit clock_probe(struct of_device *op, const struct of_device_id *match)
 {
-        struct linux_prom_registers clk_reg[2];
-        char model[128];
-        register int node, cpuunit, bootbus;
-        struct resource r;
-
-        cpuunit = bootbus = 0;
-        memset(&r, 0, sizeof(r));
-
-        /* Determine the correct starting PROM node for the probe. */
-        node = prom_getchild(prom_root_node);
-        switch (sparc_cpu_model) {
-        case sun4c:
-                break;
-        case sun4m:
-                node = prom_getchild(prom_searchsiblings(node, "obio"));
-                break;
-        case sun4d:
-                node = prom_getchild(bootbus = prom_searchsiblings(prom_getchild(cpuunit = prom_searchsiblings(node, "cpu-unit")), "bootbus"));
-                break;
-        default:
-                prom_printf("CLOCK: Unsupported architecture!\n");
-                prom_halt();
-        }
+        struct device_node *dp = op->node;
+        char *model = of_get_property(dp, "model", NULL);
 
-        /* Find the PROM node describing the real time clock. */
-        sp_clock_typ = MSTK_INVALID;
-        node = prom_searchsiblings(node,"eeprom");
-        if (!node) {
-                prom_printf("CLOCK: No clock found!\n");
-                prom_halt();
-        }
+        if (!model)
+                return -ENODEV;
 
-        /* Get the model name and setup everything up. */
-        model[0] = '\0';
-        prom_getstring(node, "model", model, sizeof(model));
-        if (strcmp(model, "mk48t02") == 0) {
+        if (!strcmp(model, "mk48t02")) {
                 sp_clock_typ = MSTK48T02;
-                if (prom_getproperty(node, "reg", (char *) clk_reg, sizeof(clk_reg)) == -1) {
-                        prom_printf("clock_probe: FAILED!\n");
-                        prom_halt();
-                }
-                if (sparc_cpu_model == sun4d)
-                        prom_apply_generic_ranges (bootbus, cpuunit, clk_reg, 1);
-                else
-                        prom_apply_obio_ranges(clk_reg, 1);
+
                 /* Map the clock register io area read-only */
-                r.flags = clk_reg[0].which_io;
-                r.start = clk_reg[0].phys_addr;
-                mstk48t02_regs = sbus_ioremap(&r, 0,
-                    sizeof(struct mostek48t02), "mk48t02");
+                mstk48t02_regs = of_ioremap(&op->resource[0], 0,
+                                            sizeof(struct mostek48t02),
+                                            "mk48t02");
                 mstk48t08_regs = NULL;  /* To catch weirdness */
-        } else if (strcmp(model, "mk48t08") == 0) {
+        } else if (!strcmp(model, "mk48t08")) {
                 sp_clock_typ = MSTK48T08;
-                if(prom_getproperty(node, "reg", (char *) clk_reg,
-                                    sizeof(clk_reg)) == -1) {
-                        prom_printf("clock_probe: FAILED!\n");
-                        prom_halt();
-                }
-                if (sparc_cpu_model == sun4d)
-                        prom_apply_generic_ranges (bootbus, cpuunit, clk_reg, 1);
-                else
-                        prom_apply_obio_ranges(clk_reg, 1);
-                /* Map the clock register io area read-only */
-                /* XXX r/o attribute is somewhere in r.flags */
-                r.flags = clk_reg[0].which_io;
-                r.start = clk_reg[0].phys_addr;
-                mstk48t08_regs = sbus_ioremap(&r, 0,
-                    sizeof(struct mostek48t08), "mk48t08");
+                mstk48t08_regs = of_ioremap(&op->resource[0], 0,
+                                            sizeof(struct mostek48t08),
+                                            "mk48t08");
 
                 mstk48t02_regs = &mstk48t08_regs->regs;
-        } else {
-                prom_printf("CLOCK: Unknown model name '%s'\n",model);
-                prom_halt();
-        }
+        } else
+                return -ENODEV;
 
         /* Report a low battery voltage condition. */
         if (has_low_battery())
@@ -358,6 +307,28 @@ static __inline__ void clock_probe(void)
         /* Kick start the clock if it is completely stopped. */
         if (mostek_read(mstk48t02_regs + MOSTEK_SEC) & MSTK_STOP)
                 kick_start_clock();
+
+        return 0;
+}
+
+static struct of_device_id clock_match[] = {
+        {
+                .name = "eeprom",
+        },
+        {},
+};
+
+static struct of_platform_driver clock_driver = {
+        .name           = "clock",
+        .match_table    = clock_match,
+        .probe          = clock_probe,
+};
+
+
+/* Probe for the mostek real time clock chip. */
+static void clock_init(void)
+{
+        of_register_driver(&clock_driver, &of_bus_type);
 }
 
 void __init sbus_time_init(void)
@@ -376,7 +347,7 @@ void __init sbus_time_init(void)
         if (ARCH_SUN4)
                 sun4_clock_probe();
         else
-                clock_probe();
+                clock_init();
 
         sparc_init_timers(timer_interrupt);
         
diff --git a/arch/sparc64/kernel/auxio.c b/arch/sparc64/kernel/auxio.c
index c2c69c167d18..718350aba1ec 100644
--- a/arch/sparc64/kernel/auxio.c
+++ b/arch/sparc64/kernel/auxio.c
@@ -11,10 +11,9 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 
-#include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/io.h>
-#include <asm/sbus.h>
-#include <asm/ebus.h>
 #include <asm/auxio.h>
 
 void __iomem *auxio_register = NULL;
@@ -111,12 +110,6 @@ void auxio_set_lte(int on)
         }
 }
 
-static void __devinit auxio_report_dev(struct device_node *dp)
-{
-        printk(KERN_INFO "AUXIO: Found device at %s\n",
-               dp->full_name);
-}
-
 static struct of_device_id auxio_match[] = {
         {
                 .name = "auxio",
@@ -126,67 +119,48 @@ static struct of_device_id auxio_match[] = {
 
 MODULE_DEVICE_TABLE(of, auxio_match);
 
-#ifdef CONFIG_SBUS
-static int __devinit auxio_sbus_probe(struct of_device *dev, const struct of_device_id *match)
+static int __devinit auxio_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_dev *sdev = to_sbus_device(&dev->dev);
-
-        auxio_devtype  = AUXIO_TYPE_SBUS;
-        auxio_register = sbus_ioremap(&sdev->resource[0], 0,
-                                      sdev->reg_addrs[0].reg_size,
-                                      "auxiliaryIO");
-        if (!auxio_register)
+        struct device_node *dp = dev->node;
+        unsigned long size;
+
+        if (!strcmp(dp->parent->name, "ebus")) {
+                auxio_devtype = AUXIO_TYPE_EBUS;
+                size = sizeof(u32);
+        } else if (!strcmp(dp->parent->name, "sbus")) {
+                auxio_devtype = AUXIO_TYPE_SBUS;
+                size = 1;
+        } else {
+                printk("auxio: Unknown parent bus type [%s]\n",
+                       dp->parent->name);
                 return -ENODEV;
-
-        auxio_report_dev(dev->node);
-        return 0;
-}
-
-static struct of_platform_driver auxio_sbus_driver = {
-        .name           = "auxio",
-        .match_table    = auxio_match,
-        .probe          = auxio_sbus_probe,
-};
-#endif
-
-#ifdef CONFIG_PCI
-static int __devinit auxio_ebus_probe(struct of_device *dev, const struct of_device_id *match)
-{
-        struct linux_ebus_device *edev = to_ebus_device(&dev->dev);
-
-        auxio_devtype  = AUXIO_TYPE_EBUS;
-        auxio_register = ioremap(edev->resource[0].start, sizeof(u32));
+        }
+        auxio_register = of_ioremap(&dev->resource[0], 0, size, "auxio");
         if (!auxio_register)
                 return -ENODEV;
 
-        auxio_report_dev(dev->node);
+        printk(KERN_INFO "AUXIO: Found device at %s\n",
+               dp->full_name);
 
-        auxio_set_led(AUXIO_LED_ON);
+        if (auxio_devtype == AUXIO_TYPE_EBUS)
+                auxio_set_led(AUXIO_LED_ON);
 
         return 0;
 }
 
-static struct of_platform_driver auxio_ebus_driver = {
+static struct of_platform_driver auxio_driver = {
         .name           = "auxio",
         .match_table    = auxio_match,
-        .probe          = auxio_ebus_probe,
+        .probe          = auxio_probe,
 };
-#endif
 
-static int __init auxio_probe(void)
+static int __init auxio_init(void)
 {
-#ifdef CONFIG_SBUS
-        of_register_driver(&auxio_sbus_driver, &sbus_bus_type);
-#endif
-#ifdef CONFIG_PCI
-        of_register_driver(&auxio_ebus_driver, &ebus_bus_type);
-#endif
-
-        return 0;
+        return of_register_driver(&auxio_driver, &of_bus_type);
 }
 
 /* Must be after subsys_initcall() so that busses are probed.  Must
  * be before device_initcall() because things like the floppy driver
  * need to use the AUXIO register.
  */
-fs_initcall(auxio_probe);
+fs_initcall(auxio_init);
diff --git a/arch/sparc64/kernel/ebus.c b/arch/sparc64/kernel/ebus.c
index 98e0a8cbeecd..aac014d15ad3 100644
--- a/arch/sparc64/kernel/ebus.c
+++ b/arch/sparc64/kernel/ebus.c
@@ -20,6 +20,8 @@
 #include <asm/pbm.h>
 #include <asm/ebus.h>
 #include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/bpp.h>
 #include <asm/irq.h>
 
@@ -279,45 +281,12 @@ static inline void *ebus_alloc(size_t size)
         return mem;
 }
 
-int __init ebus_intmap_match(struct linux_ebus *ebus,
-                             struct linux_prom_registers *reg,
-                             int *interrupt)
-{
-        struct linux_prom_ebus_intmap *imap;
-        struct linux_prom_ebus_intmask *imask;
-        unsigned int hi, lo, irq;
-        int i, len, n_imap;
-
-        imap = of_get_property(ebus->prom_node, "interrupt-map", &len);
-        if (!imap)
-                return 0;
-        n_imap = len / sizeof(imap[0]);
-
-        imask = of_get_property(ebus->prom_node, "interrupt-map-mask", NULL);
-        if (!imask)
-                return 0;
-
-        hi = reg->which_io & imask->phys_hi;
-        lo = reg->phys_addr & imask->phys_lo;
-        irq = *interrupt & imask->interrupt;
-        for (i = 0; i < n_imap; i++) {
-                if ((imap[i].phys_hi == hi) &&
-                    (imap[i].phys_lo == lo) &&
-                    (imap[i].interrupt == irq)) {
-                        *interrupt = imap[i].cinterrupt;
-                        return 0;
-                }
-        }
-        return -1;
-}
-
-void __init fill_ebus_child(struct device_node *dp,
-                            struct linux_prom_registers *preg,
-                            struct linux_ebus_child *dev,
-                            int non_standard_regs)
+static void __init fill_ebus_child(struct device_node *dp,
+                                   struct linux_ebus_child *dev,
+                                   int non_standard_regs)
 {
+        struct of_device *op;
         int *regs;
-        int *irqs;
         int i, len;
 
         dev->prom_node = dp;
@@ -354,12 +323,16 @@ void __init fill_ebus_child(struct device_node *dp,
                 }
         }
 
-        for (i = 0; i < PROMINTR_MAX; i++)
-                dev->irqs[i] = PCI_IRQ_NONE;
-
-        irqs = of_get_property(dp, "interrupts", &len);
-        if (!irqs) {
+        op = of_find_device_by_node(dp);
+        if (!op) {
                 dev->num_irqs = 0;
+        } else {
+                dev->num_irqs = op->num_irqs;
+                for (i = 0; i < dev->num_irqs; i++)
+                        dev->irqs[i] = op->irqs[i];
+        }
+
+        if (!dev->num_irqs) {
                 /*
                  * Oh, well, some PROMs don't export interrupts
                  * property to children of EBus devices...
@@ -375,23 +348,6 @@ void __init fill_ebus_child(struct device_node *dp,
                                 dev->irqs[0] = dev->parent->irqs[1];
                         }
                 }
-        } else {
-                dev->num_irqs = len / sizeof(irqs[0]);
-                for (i = 0; i < dev->num_irqs; i++) {
-                        struct pci_pbm_info *pbm = dev->bus->parent;
-                        struct pci_controller_info *p = pbm->parent;
-
-                        if (ebus_intmap_match(dev->bus, preg, &irqs[i]) != -1) {
-                                dev->irqs[i] = p->irq_build(pbm,
-                                                            dev->bus->self,
-                                                            irqs[i]);
-                        } else {
-                                /* If we get a bogus interrupt property, just
-                                 * record the raw value instead of punting.
-                                 */
-                                dev->irqs[i] = irqs[i];
-                        }
-                }
         }
 }
 
@@ -403,72 +359,32 @@ static int __init child_regs_nonstandard(struct linux_ebus_device *dev)
         return 0;
 }
 
-void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_device *dev)
+static void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_device *dev)
 {
-        struct linux_prom_registers *regs;
         struct linux_ebus_child *child;
-        int *irqs;
-        int i, n, len;
+        struct of_device *op;
+        int i, len;
 
         dev->prom_node = dp;
 
         printk(" [%s", dp->name);
 
-        regs = of_get_property(dp, "reg", &len);
-        if (!regs) {
+        op = of_find_device_by_node(dp);
+        if (!op) {
                 dev->num_addrs = 0;
-                goto probe_interrupts;
-        }
-
-        if (len % sizeof(struct linux_prom_registers)) {
-                prom_printf("UGH: proplen for %s was %d, need multiple of %d\n",
-                            dev->prom_node->name, len,
-                            (int)sizeof(struct linux_prom_registers));
-                prom_halt();
-        }
-        dev->num_addrs = len / sizeof(struct linux_prom_registers);
-
-        for (i = 0; i < dev->num_addrs; i++) {
-                /* XXX Learn how to interpret ebus ranges... -DaveM */
-                if (regs[i].which_io >= 0x10)
-                        n = (regs[i].which_io - 0x10) >> 2;
-                else
-                        n = regs[i].which_io;
-
-                dev->resource[i].start  = dev->bus->self->resource[n].start;
-                dev->resource[i].start += (unsigned long)regs[i].phys_addr;
-                dev->resource[i].end    =
-                        (dev->resource[i].start + (unsigned long)regs[i].reg_size - 1UL);
-                dev->resource[i].flags  = IORESOURCE_MEM;
-                dev->resource[i].name   = dev->prom_node->name;
-                request_resource(&dev->bus->self->resource[n],
-                                 &dev->resource[i]);
-        }
-
-probe_interrupts:
-        for (i = 0; i < PROMINTR_MAX; i++)
-                dev->irqs[i] = PCI_IRQ_NONE;
-
-        irqs = of_get_property(dp, "interrupts", &len);
-        if (!irqs) {
                 dev->num_irqs = 0;
         } else {
-                dev->num_irqs = len / sizeof(irqs[0]);
-                for (i = 0; i < dev->num_irqs; i++) {
-                        struct pci_pbm_info *pbm = dev->bus->parent;
-                        struct pci_controller_info *p = pbm->parent;
-
-                        if (ebus_intmap_match(dev->bus, &regs[0], &irqs[i]) != -1) {
-                                dev->irqs[i] = p->irq_build(pbm,
-                                                            dev->bus->self,
-                                                            irqs[i]);
-                        } else {
-                                /* If we get a bogus interrupt property, just
-                                 * record the raw value instead of punting.
-                                 */
-                                dev->irqs[i] = irqs[i];
-                        }
-                }
+                (void) of_get_property(dp, "reg", &len);
+                dev->num_addrs = len / sizeof(struct linux_prom_registers);
+
+                for (i = 0; i < dev->num_addrs; i++)
+                        memcpy(&dev->resource[i],
+                               &op->resource[i],
+                               sizeof(struct resource));
+
+                dev->num_irqs = op->num_irqs;
+                for (i = 0; i < dev->num_irqs; i++)
+                        dev->irqs[i] = op->irqs[i];
         }
 
         dev->ofdev.node = dp;
@@ -490,7 +406,7 @@ probe_interrupts:
                 child->next = NULL;
                 child->parent = dev;
                 child->bus = dev->bus;
-                fill_ebus_child(dp, regs, child,
+                fill_ebus_child(dp, child,
                                 child_regs_nonstandard(dev));
 
                 while ((dp = dp->sibling) != NULL) {
@@ -500,7 +416,7 @@ probe_interrupts:
                         child->next = NULL;
                         child->parent = dev;
                         child->bus = dev->bus;
-                        fill_ebus_child(dp, regs, child,
+                        fill_ebus_child(dp, child,
                                         child_regs_nonstandard(dev));
                 }
         }
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc64/kernel/irq.c
index ab9e640df228..eebe02f3f4cb 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc64/kernel/irq.c
@@ -414,6 +414,10 @@ void irq_install_pre_handler(int virt_irq,
         data->pre_handler_arg1 = arg1;
         data->pre_handler_arg2 = arg2;
 
+        if (desc->chip == &sun4u_irq_ack ||
+            desc->chip == &sun4v_irq_ack)
+                return;
+
         desc->chip = (desc->chip == &sun4u_irq ?
                       &sun4u_irq_ack : &sun4v_irq_ack);
 }
diff --git a/arch/sparc64/kernel/isa.c b/arch/sparc64/kernel/isa.c
index 6f16dee280a8..0f3aec72ef5f 100644
--- a/arch/sparc64/kernel/isa.c
+++ b/arch/sparc64/kernel/isa.c
@@ -3,6 +3,8 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/isa.h>
 
 struct sparc_isa_bridge *isa_chain;
@@ -46,107 +48,16 @@ isa_dev_get_resource(struct sparc_isa_device *isa_dev)
         return pregs;
 }
 
-/* I can't believe they didn't put a real INO in the isa device
- * interrupts property.  The whole point of the OBP properties
- * is to shield the kernel from IRQ routing details.
- *
- * The P1275 standard for ISA devices seems to also have been
- * totally ignored.
- *
- * On later systems, an interrupt-map and interrupt-map-mask scheme
- * akin to EBUS is used.
- */
-static struct {
-        int     obp_irq;
-        int     pci_ino;
-} grover_irq_table[] = {
-        { 1, 0x00 },    /* dma, unknown ino at this point */
-        { 2, 0x27 },    /* floppy */
-        { 3, 0x22 },    /* parallel */
-        { 4, 0x2b },    /* serial */
-        { 5, 0x25 },    /* acpi power management */
-
-        { 0, 0x00 }     /* end of table */
-};
-
-static int __init isa_dev_get_irq_using_imap(struct sparc_isa_device *isa_dev,
-                                             struct sparc_isa_bridge *isa_br,
-                                             int *interrupt,
-                                             struct linux_prom_registers *reg)
-{
-        struct linux_prom_ebus_intmap *imap;
-        struct linux_prom_ebus_intmap *imask;
-        unsigned int hi, lo, irq;
-        int i, len, n_imap;
-
-        imap = of_get_property(isa_br->prom_node, "interrupt-map", &len);
-        if (!imap)
-                return 0;
-        n_imap = len / sizeof(imap[0]);
-
-        imask = of_get_property(isa_br->prom_node, "interrupt-map-mask", NULL);
-        if (!imask)
-                return 0;
-
-        hi = reg->which_io & imask->phys_hi;
-        lo = reg->phys_addr & imask->phys_lo;
-        irq = *interrupt & imask->interrupt;
-        for (i = 0; i < n_imap; i++) {
-                if ((imap[i].phys_hi == hi) &&
-                    (imap[i].phys_lo == lo) &&
-                    (imap[i].interrupt == irq)) {
-                        *interrupt = imap[i].cinterrupt;
-                        return 0;
-                }
-        }
-        return -1;
-}
-
 static void __init isa_dev_get_irq(struct sparc_isa_device *isa_dev,
                                    struct linux_prom_registers *pregs)
 {
-        int irq_prop;
+        struct of_device *op = of_find_device_by_node(isa_dev->prom_node);
 
-        irq_prop = of_getintprop_default(isa_dev->prom_node,
-                                         "interrupts", -1);
-        if (irq_prop <= 0) {
-                goto no_irq;
+        if (!op || !op->num_irqs) {
+                isa_dev->irq = PCI_IRQ_NONE;
         } else {
-                struct pci_controller_info *pcic;
-                struct pci_pbm_info *pbm;
-                int i;
-
-                if (of_find_property(isa_dev->bus->prom_node,
-                                     "interrupt-map", NULL)) {
-                        if (!isa_dev_get_irq_using_imap(isa_dev,
-                                                        isa_dev->bus,
-                                                        &irq_prop,
-                                                        pregs))
-                                goto route_irq;
-                }
-
-                for (i = 0; grover_irq_table[i].obp_irq != 0; i++) {
-                        if (grover_irq_table[i].obp_irq == irq_prop) {
-                                int ino = grover_irq_table[i].pci_ino;
-
-                                if (ino == 0)
-                                        goto no_irq;
- 
-                                irq_prop = ino;
-                                goto route_irq;
-                        }
-                }
-                goto no_irq;
-
-route_irq:
-                pbm = isa_dev->bus->parent;
-                pcic = pbm->parent;
-                isa_dev->irq = pcic->irq_build(pbm, NULL, irq_prop);
-                return;
+                isa_dev->irq = op->irqs[0];
         }
-
-no_irq:
-        isa_dev->irq = PCI_IRQ_NONE;
 }
 
 static void __init isa_fill_children(struct sparc_isa_device *parent_isa_dev)
diff --git a/arch/sparc64/kernel/of_device.c b/arch/sparc64/kernel/of_device.c
index 768475bbce82..3670dc8a7d5f 100644
--- a/arch/sparc64/kernel/of_device.c
+++ b/arch/sparc64/kernel/of_device.c
@@ -129,6 +129,43 @@ static int of_device_resume(struct device * dev)
         return error;
 }
 
+void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name)
+{
+        unsigned long ret = res->start + offset;
+
+        if (!request_region(ret, size, name))
+                ret = 0;
+
+        return (void __iomem *) ret;
+}
+EXPORT_SYMBOL(of_ioremap);
+
+void of_iounmap(void __iomem *base, unsigned long size)
+{
+        release_region((unsigned long) base, size);
+}
+EXPORT_SYMBOL(of_iounmap);
+
+static int node_match(struct device *dev, void *data)
+{
+        struct of_device *op = to_of_device(dev);
+        struct device_node *dp = data;
+
+        return (op->node == dp);
+}
+
+struct of_device *of_find_device_by_node(struct device_node *dp)
+{
+        struct device *dev = bus_find_device(&of_bus_type, NULL,
+                                             dp, node_match);
+
+        if (dev)
+                return to_of_device(dev);
+
+        return NULL;
+}
+EXPORT_SYMBOL(of_find_device_by_node);
+
 #ifdef CONFIG_PCI
 struct bus_type isa_bus_type = {
        .name    = "isa",
@@ -163,10 +200,654 @@ struct bus_type sbus_bus_type = {
 EXPORT_SYMBOL(sbus_bus_type);
 #endif
 
+struct bus_type of_bus_type = {
+       .name    = "of",
+       .match   = of_platform_bus_match,
+       .probe   = of_device_probe,
+       .remove  = of_device_remove,
+       .suspend = of_device_suspend,
+       .resume  = of_device_resume,
+};
+EXPORT_SYMBOL(of_bus_type);
+
+static inline u64 of_read_addr(u32 *cell, int size)
+{
+        u64 r = 0;
+        while (size--)
+                r = (r << 32) | *(cell++);
+        return r;
+}
+
+static void __init get_cells(struct device_node *dp,
+                             int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = of_n_addr_cells(dp);
+        if (sizec)
+                *sizec = of_n_size_cells(dp);
+}
+
+/* Max address size we deal with */
+#define OF_MAX_ADDR_CELLS       4
+
+struct of_bus {
+        const char      *name;
+        const char      *addr_prop_name;
+        int             (*match)(struct device_node *parent);
+        void            (*count_cells)(struct device_node *child,
+                                       int *addrc, int *sizec);
+        u64             (*map)(u32 *addr, u32 *range, int na, int ns, int pna);
+        int             (*translate)(u32 *addr, u64 offset, int na);
+        unsigned int    (*get_flags)(u32 *addr);
+};
+
+/*
+ * Default translator (generic bus)
+ */
+
+static void of_bus_default_count_cells(struct device_node *dev,
+                                       int *addrc, int *sizec)
+{
+        get_cells(dev, addrc, sizec);
+}
+
+static u64 of_bus_default_map(u32 *addr, u32 *range, int na, int ns, int pna)
+{
+        u64 cp, s, da;
+
+        cp = of_read_addr(range, na);
+        s  = of_read_addr(range + na + pna, ns);
+        da = of_read_addr(addr, na);
+
+        if (da < cp || da >= (cp + s))
+                return OF_BAD_ADDR;
+        return da - cp;
+}
+
+static int of_bus_default_translate(u32 *addr, u64 offset, int na)
+{
+        u64 a = of_read_addr(addr, na);
+        memset(addr, 0, na * 4);
+        a += offset;
+        if (na > 1)
+                addr[na - 2] = a >> 32;
+        addr[na - 1] = a & 0xffffffffu;
+
+        return 0;
+}
+
+static unsigned int of_bus_default_get_flags(u32 *addr)
+{
+        return IORESOURCE_MEM;
+}
+
+/*
+ * PCI bus specific translator
+ */
+
+static int of_bus_pci_match(struct device_node *np)
+{
+        return !strcmp(np->type, "pci") || !strcmp(np->type, "pciex");
+}
+
+static void of_bus_pci_count_cells(struct device_node *np,
+                                   int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = 3;
+        if (sizec)
+                *sizec = 2;
+}
+
+static u64 of_bus_pci_map(u32 *addr, u32 *range, int na, int ns, int pna)
+{
+        u64 cp, s, da;
+
+        /* Check address type match */
+        if ((addr[0] ^ range[0]) & 0x03000000)
+                return OF_BAD_ADDR;
+
+        /* Read address values, skipping high cell */
+        cp = of_read_addr(range + 1, na - 1);
+        s  = of_read_addr(range + na + pna, ns);
+        da = of_read_addr(addr + 1, na - 1);
+
+        if (da < cp || da >= (cp + s))
+                return OF_BAD_ADDR;
+        return da - cp;
+}
+
+static int of_bus_pci_translate(u32 *addr, u64 offset, int na)
+{
+        return of_bus_default_translate(addr + 1, offset, na - 1);
+}
+
+static unsigned int of_bus_pci_get_flags(u32 *addr)
+{
+        unsigned int flags = 0;
+        u32 w = addr[0];
+
+        switch((w >> 24) & 0x03) {
+        case 0x01:
+                flags |= IORESOURCE_IO;
+        case 0x02: /* 32 bits */
+        case 0x03: /* 64 bits */
+                flags |= IORESOURCE_MEM;
+        }
+        if (w & 0x40000000)
+                flags |= IORESOURCE_PREFETCH;
+        return flags;
+}
+
+/*
+ * ISA bus specific translator
+ */
+
+static int of_bus_isa_match(struct device_node *np)
+{
+        return !strcmp(np->name, "isa");
+}
+
+static void of_bus_isa_count_cells(struct device_node *child,
+                                   int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = 2;
+        if (sizec)
+                *sizec = 1;
+}
+
+static u64 of_bus_isa_map(u32 *addr, u32 *range, int na, int ns, int pna)
+{
+        u64 cp, s, da;
+
+        /* Check address type match */
+        if ((addr[0] ^ range[0]) & 0x00000001)
+                return OF_BAD_ADDR;
+
+        /* Read address values, skipping high cell */
+        cp = of_read_addr(range + 1, na - 1);
+        s  = of_read_addr(range + na + pna, ns);
+        da = of_read_addr(addr + 1, na - 1);
+
+        if (da < cp || da >= (cp + s))
+                return OF_BAD_ADDR;
+        return da - cp;
+}
+
+static int of_bus_isa_translate(u32 *addr, u64 offset, int na)
+{
+        return of_bus_default_translate(addr + 1, offset, na - 1);
+}
+
+static unsigned int of_bus_isa_get_flags(u32 *addr)
+{
+        unsigned int flags = 0;
+        u32 w = addr[0];
+
+        if (w & 1)
+                flags |= IORESOURCE_IO;
+        else
+                flags |= IORESOURCE_MEM;
+        return flags;
+}
+
+/*
+ * SBUS bus specific translator
+ */
+
+static int of_bus_sbus_match(struct device_node *np)
+{
+        return !strcmp(np->name, "sbus") ||
+                !strcmp(np->name, "sbi");
+}
+
+static void of_bus_sbus_count_cells(struct device_node *child,
+                                   int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = 2;
+        if (sizec)
+                *sizec = 1;
+}
+
+static u64 of_bus_sbus_map(u32 *addr, u32 *range, int na, int ns, int pna)
+{
+        return of_bus_default_map(addr, range, na, ns, pna);
+}
+
+static int of_bus_sbus_translate(u32 *addr, u64 offset, int na)
+{
+        return of_bus_default_translate(addr, offset, na);
+}
+
+static unsigned int of_bus_sbus_get_flags(u32 *addr)
+{
+        return IORESOURCE_MEM;
+}
+
+
+/*
+ * Array of bus specific translators
+ */
+
+static struct of_bus of_busses[] = {
+        /* PCI */
+        {
+                .name = "pci",
+                .addr_prop_name = "assigned-addresses",
+                .match = of_bus_pci_match,
+                .count_cells = of_bus_pci_count_cells,
+                .map = of_bus_pci_map,
+                .translate = of_bus_pci_translate,
+                .get_flags = of_bus_pci_get_flags,
+        },
+        /* ISA */
+        {
+                .name = "isa",
+                .addr_prop_name = "reg",
+                .match = of_bus_isa_match,
+                .count_cells = of_bus_isa_count_cells,
+                .map = of_bus_isa_map,
+                .translate = of_bus_isa_translate,
+                .get_flags = of_bus_isa_get_flags,
+        },
+        /* SBUS */
+        {
+                .name = "sbus",
+                .addr_prop_name = "reg",
+                .match = of_bus_sbus_match,
+                .count_cells = of_bus_sbus_count_cells,
+                .map = of_bus_sbus_map,
+                .translate = of_bus_sbus_translate,
+                .get_flags = of_bus_sbus_get_flags,
+        },
+        /* Default */
+        {
+                .name = "default",
+                .addr_prop_name = "reg",
+                .match = NULL,
+                .count_cells = of_bus_default_count_cells,
+                .map = of_bus_default_map,
+                .translate = of_bus_default_translate,
+                .get_flags = of_bus_default_get_flags,
+        },
+};
+
+static struct of_bus *of_match_bus(struct device_node *np)
+{
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(of_busses); i ++)
+                if (!of_busses[i].match || of_busses[i].match(np))
+                        return &of_busses[i];
+        BUG();
+        return NULL;
+}
+
+static int __init build_one_resource(struct device_node *parent,
+                                     struct of_bus *bus,
+                                     struct of_bus *pbus,
+                                     u32 *addr,
+                                     int na, int ns, int pna)
+{
+        u32 *ranges;
+        unsigned int rlen;
+        int rone;
+        u64 offset = OF_BAD_ADDR;
+
+        ranges = of_get_property(parent, "ranges", &rlen);
+        if (ranges == NULL || rlen == 0) {
+                offset = of_read_addr(addr, na);
+                memset(addr, 0, pna * 4);
+                goto finish;
+        }
+
+        /* Now walk through the ranges */
+        rlen /= 4;
+        rone = na + pna + ns;
+        for (; rlen >= rone; rlen -= rone, ranges += rone) {
+                offset = bus->map(addr, ranges, na, ns, pna);
+                if (offset != OF_BAD_ADDR)
+                        break;
+        }
+        if (offset == OF_BAD_ADDR)
+                return 1;
+
+        memcpy(addr, ranges + na, 4 * pna);
+
+finish:
+        /* Translate it into parent bus space */
+        return pbus->translate(addr, offset, pna);
+}
+
+static void __init build_device_resources(struct of_device *op,
+                                          struct device *parent)
+{
+        struct of_device *p_op;
+        struct of_bus *bus;
+        int na, ns;
+        int index, num_reg;
+        void *preg;
+
+        if (!parent)
+                return;
+
+        p_op = to_of_device(parent);
+        bus = of_match_bus(p_op->node);
+        bus->count_cells(op->node, &na, &ns);
+
+        preg = of_get_property(op->node, bus->addr_prop_name, &num_reg);
+        if (!preg || num_reg == 0)
+                return;
+
+        /* Convert to num-cells.  */
+        num_reg /= 4;
+
+        /* Conver to num-entries.  */
+        num_reg /= na + ns;
+
+        for (index = 0; index < num_reg; index++) {
+                struct resource *r = &op->resource[index];
+                u32 addr[OF_MAX_ADDR_CELLS];
+                u32 *reg = (preg + (index * ((na + ns) * 4)));
+                struct device_node *dp = op->node;
+                struct device_node *pp = p_op->node;
+                struct of_bus *pbus;
+                u64 size, result = OF_BAD_ADDR;
+                unsigned long flags;
+                int dna, dns;
+                int pna, pns;
+
+                size = of_read_addr(reg + na, ns);
+                flags = bus->get_flags(reg);
+
+                memcpy(addr, reg, na * 4);
+
+                /* If the immediate parent has no ranges property to apply,
+                 * just use a 1<->1 mapping.  Unless it is the 'dma' child
+                 * of an isa bus, which must be passed up towards the root.
+                 *
+                 * Also, don't try to translate PMU bus device registers.
+                 */
+                if ((of_find_property(pp, "ranges", NULL) == NULL &&
+                     strcmp(pp->name, "dma") != 0) ||
+                    !strcmp(pp->name, "pmu")) {
+                        result = of_read_addr(addr, na);
+                        goto build_res;
+                }
+
+                dna = na;
+                dns = ns;
+
+                while (1) {
+                        dp = pp;
+                        pp = dp->parent;
+                        if (!pp) {
+                                result = of_read_addr(addr, dna);
+                                break;
+                        }
+
+                        pbus = of_match_bus(pp);
+                        pbus->count_cells(dp, &pna, &pns);
+
+                        if (build_one_resource(dp, bus, pbus, addr, dna, dns, pna))
+                                break;
+
+                        dna = pna;
+                        dns = pns;
+                        bus = pbus;
+                }
+
+        build_res:
+                memset(r, 0, sizeof(*r));
+                if (result != OF_BAD_ADDR) {
+                        r->start = result;
+                        r->end = result + size - 1;
+                        r->flags = flags;
+                } else {
+                        r->start = ~0UL;
+                        r->end = ~0UL;
+                }
+                r->name = op->node->name;
+        }
+}
+
+static struct device_node * __init
+apply_interrupt_map(struct device_node *dp, struct device_node *pp,
+                    u32 *imap, int imlen, u32 *imask,
+                    unsigned int *irq_p)
+{
+        struct device_node *cp;
+        unsigned int irq = *irq_p;
+        struct of_bus *bus;
+        phandle handle;
+        u32 *reg;
+        int na, num_reg, i;
+
+        bus = of_match_bus(pp);
+        bus->count_cells(dp, &na, NULL);
+
+        reg = of_get_property(dp, "reg", &num_reg);
+        if (!reg || !num_reg)
+                return NULL;
+
+        imlen /= ((na + 3) * 4);
+        handle = 0;
+        for (i = 0; i < imlen; i++) {
+                int j;
+
+                for (j = 0; j < na; j++) {
+                        if ((reg[j] & imask[j]) != imap[j])
+                                goto next;
+                }
+                if (imap[na] == irq) {
+                        handle = imap[na + 1];
+                        irq = imap[na + 2];
+                        break;
+                }
+
+        next:
+                imap += (na + 3);
+        }
+        if (i == imlen)
+                return NULL;
+
+        *irq_p = irq;
+        cp = of_find_node_by_phandle(handle);
+
+        return cp;
+}
+
+static unsigned int __init pci_irq_swizzle(struct device_node *dp,
+                                           struct device_node *pp,
+                                           unsigned int irq)
+{
+        struct linux_prom_pci_registers *regs;
+        unsigned int devfn, slot, ret;
+
+        if (irq < 1 || irq > 4)
+                return irq;
+
+        regs = of_get_property(dp, "reg", NULL);
+        if (!regs)
+                return irq;
+
+        devfn = (regs->phys_hi >> 8) & 0xff;
+        slot = (devfn >> 3) & 0x1f;
+
+        ret = ((irq - 1 + (slot & 3)) & 3) + 1;
+
+        return ret;
+}
+
+static unsigned int __init build_one_device_irq(struct of_device *op,
+                                                struct device *parent,
+                                                unsigned int irq)
+{
+        struct device_node *dp = op->node;
+        struct device_node *pp, *ip;
+        unsigned int orig_irq = irq;
+
+        if (irq == 0xffffffff)
+                return irq;
+
+        if (dp->irq_trans) {
+                irq = dp->irq_trans->irq_build(dp, irq,
+                                               dp->irq_trans->data);
+#if 1
+                printk("%s: direct translate %x --> %x\n",
+                       dp->full_name, orig_irq, irq);
+#endif
+                return irq;
+        }
+
+        /* Something more complicated.  Walk up to the root, applying
+         * interrupt-map or bus specific translations, until we hit
+         * an IRQ translator.
+         *
+         * If we hit a bus type or situation we cannot handle, we
+         * stop and assume that the original IRQ number was in a
+         * format which has special meaning to it's immediate parent.
+         */
+        pp = dp->parent;
+        ip = NULL;
+        while (pp) {
+                void *imap, *imsk;
+                int imlen;
+
+                imap = of_get_property(pp, "interrupt-map", &imlen);
+                imsk = of_get_property(pp, "interrupt-map-mask", NULL);
+                if (imap && imsk) {
+                        struct device_node *iret;
+                        int this_orig_irq = irq;
+
+                        iret = apply_interrupt_map(dp, pp,
+                                                   imap, imlen, imsk,
+                                                   &irq);
+#if 1
+                        printk("%s: Apply [%s:%x] imap --> [%s:%x]\n",
+                               op->node->full_name,
+                               pp->full_name, this_orig_irq,
+                               (iret ? iret->full_name : "NULL"), irq);
+#endif
+                        if (!iret)
+                                break;
+
+                        if (iret->irq_trans) {
+                                ip = iret;
+                                break;
+                        }
+                } else {
+                        if (!strcmp(pp->type, "pci") ||
+                            !strcmp(pp->type, "pciex")) {
+                                unsigned int this_orig_irq = irq;
+
+                                irq = pci_irq_swizzle(dp, pp, irq);
+#if 1
+                                printk("%s: PCI swizzle [%s] %x --> %x\n",
+                                       op->node->full_name,
+                                       pp->full_name, this_orig_irq, irq);
+#endif
+                        }
+
+                        if (pp->irq_trans) {
+                                ip = pp;
+                                break;
+                        }
+                }
+                dp = pp;
+                pp = pp->parent;
+        }
+        if (!ip)
+                return orig_irq;
+
+        irq = ip->irq_trans->irq_build(op->node, irq,
+                                       ip->irq_trans->data);
+#if 1
+        printk("%s: Apply IRQ trans [%s] %x --> %x\n",
+               op->node->full_name, ip->full_name, orig_irq, irq);
+#endif
+
+        return irq;
+}
+
+static struct of_device * __init scan_one_device(struct device_node *dp,
+                                                 struct device *parent)
+{
+        struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL);
+        unsigned int *irq;
+        int len, i;
+
+        if (!op)
+                return NULL;
+
+        op->node = dp;
+
+        op->clock_freq = of_getintprop_default(dp, "clock-frequency",
+                                               (25*1000*1000));
+        op->portid = of_getintprop_default(dp, "upa-portid", -1);
+        if (op->portid == -1)
+                op->portid = of_getintprop_default(dp, "portid", -1);
+
+        irq = of_get_property(dp, "interrupts", &len);
+        if (irq) {
+                memcpy(op->irqs, irq, len);
+                op->num_irqs = len / 4;
+        } else {
+                op->num_irqs = 0;
+        }
+
+        build_device_resources(op, parent);
+        for (i = 0; i < op->num_irqs; i++)
+                op->irqs[i] = build_one_device_irq(op, parent, op->irqs[i]);
+
+        op->dev.parent = parent;
+        op->dev.bus = &of_bus_type;
+        if (!parent)
+                strcpy(op->dev.bus_id, "root");
+        else
+                strcpy(op->dev.bus_id, dp->path_component_name);
+
+        if (of_device_register(op)) {
+                printk("%s: Could not register of device.\n",
+                       dp->full_name);
+                kfree(op);
+                op = NULL;
+        }
+
+        return op;
+}
+
+static void __init scan_tree(struct device_node *dp, struct device *parent)
+{
+        while (dp) {
+                struct of_device *op = scan_one_device(dp, parent);
+
+                if (op)
+                        scan_tree(dp->child, &op->dev);
+
+                dp = dp->sibling;
+        }
+}
+
+static void __init scan_of_devices(void)
+{
+        struct device_node *root = of_find_node_by_path("/");
+        struct of_device *parent;
+
+        parent = scan_one_device(root, NULL);
+        if (!parent)
+                return;
+
+        scan_tree(root->child, &parent->dev);
+}
+
 static int __init of_bus_driver_init(void)
 {
-        int err = 0;
+        int err;
 
+        err = bus_register(&of_bus_type);
 #ifdef CONFIG_PCI
         if (!err)
                 err = bus_register(&isa_bus_type);
@@ -177,7 +858,11 @@ static int __init of_bus_driver_init(void)
         if (!err)
                 err = bus_register(&sbus_bus_type);
 #endif
-        return 0;
+
+        if (!err)
+                scan_of_devices();
+
+        return err;
 }
 
 postcore_initcall(of_bus_driver_init);
diff --git a/arch/sparc64/kernel/pci.c b/arch/sparc64/kernel/pci.c
index 20ca9ec8fd3b..04ea6c2eb7a1 100644
--- a/arch/sparc64/kernel/pci.c
+++ b/arch/sparc64/kernel/pci.c
@@ -307,7 +307,6 @@ static void __init pci_scan_each_controller_bus(void)
                 p->scan_bus(p);
 }
 
-extern void clock_probe(void);
 extern void power_init(void);
 
 static int __init pcibios_init(void)
@@ -320,7 +319,6 @@ static int __init pcibios_init(void)
 
         isa_init();
         ebus_init();
-        clock_probe();
         power_init();
 
         return 0;
@@ -406,14 +404,8 @@ void pcibios_bus_to_resource(struct pci_dev *pdev, struct resource *res,
 }
 EXPORT_SYMBOL(pcibios_bus_to_resource);
 
-extern int pci_irq_verbose;
-
 char * __init pcibios_setup(char *str)
 {
-        if (!strcmp(str, "irq_verbose")) {
-                pci_irq_verbose = 1;
-                return NULL;
-        }
         return str;
 }
 
diff --git a/arch/sparc64/kernel/pci_common.c b/arch/sparc64/kernel/pci_common.c
index b06a2955bf5f..7a59cc72c844 100644
--- a/arch/sparc64/kernel/pci_common.c
+++ b/arch/sparc64/kernel/pci_common.c
@@ -10,12 +10,10 @@
 
 #include <asm/pbm.h>
 #include <asm/prom.h>
+#include <asm/of_device.h>
 
 #include "pci_impl.h"
 
-/* Pass "pci=irq_verbose" on the kernel command line to enable this.  */
-int pci_irq_verbose;
-
 /* Fix self device of BUS and hook it into BUS->self.
  * The pci_scan_bus does not do this for the host bridge.
  */
@@ -169,6 +167,7 @@ static void __init pdev_cookie_fillin(struct pci_pbm_info *pbm,
         }
         pcp->pbm = pbm;
         pcp->prom_node = dp;
+        pcp->op = of_find_device_by_node(dp);
         memcpy(pcp->prom_regs, pregs,
                nregs * sizeof(struct linux_prom_pci_registers));
         pcp->num_prom_regs = nregs;
@@ -549,296 +548,18 @@ void __init pci_assign_unassigned(struct pci_pbm_info *pbm,
                 pci_assign_unassigned(pbm, bus);
 }
 
-static inline unsigned int pci_slot_swivel(struct pci_pbm_info *pbm,
-                                           struct pci_dev *toplevel_pdev,
-                                           struct pci_dev *pdev,
-                                           unsigned int interrupt)
-{
-        unsigned int ret;
-
-        if (unlikely(interrupt < 1 || interrupt > 4)) {
-                printk("%s: Device %s interrupt value of %u is strange.\n",
-                       pbm->name, pci_name(pdev), interrupt);
-                return interrupt;
-        }
-
-        ret = ((interrupt - 1 + (PCI_SLOT(pdev->devfn) & 3)) & 3) + 1;
-
-        if (pci_irq_verbose)
-                printk("%s: %s IRQ Swivel %s [%x:%x] -> [%x]\n",
-                       pbm->name, pci_name(toplevel_pdev), pci_name(pdev),
-                       interrupt, PCI_SLOT(pdev->devfn), ret);
-
-        return ret;
-}
-
-static inline unsigned int pci_apply_intmap(struct pci_pbm_info *pbm,
-                                            struct pci_dev *toplevel_pdev,
-                                            struct pci_dev *pbus,
-                                            struct pci_dev *pdev,
-                                            unsigned int interrupt,
-                                            struct device_node **cnode)
-{
-        struct linux_prom_pci_intmap *imap;
-        struct linux_prom_pci_intmask *imask;
-        struct pcidev_cookie *pbus_pcp = pbus->sysdata;
-        struct pcidev_cookie *pdev_pcp = pdev->sysdata;
-        struct linux_prom_pci_registers *pregs = pdev_pcp->prom_regs;
-        struct property *prop;
-        int plen, num_imap, i;
-        unsigned int hi, mid, lo, irq, orig_interrupt;
-
-        *cnode = pbus_pcp->prom_node;
-
-        prop = of_find_property(pbus_pcp->prom_node, "interrupt-map", &plen);
-        if (!prop ||
-            (plen % sizeof(struct linux_prom_pci_intmap)) != 0) {
-                printk("%s: Device %s interrupt-map has bad len %d\n",
-                       pbm->name, pci_name(pbus), plen);
-                goto no_intmap;
-        }
-        imap = prop->value;
-        num_imap = plen / sizeof(struct linux_prom_pci_intmap);
-
-        prop = of_find_property(pbus_pcp->prom_node, "interrupt-map-mask", &plen);
-        if (!prop ||
-            (plen % sizeof(struct linux_prom_pci_intmask)) != 0) {
-                printk("%s: Device %s interrupt-map-mask has bad len %d\n",
-                       pbm->name, pci_name(pbus), plen);
-                goto no_intmap;
-        }
-        imask = prop->value;
-
-        orig_interrupt = interrupt;
-
-        hi   = pregs->phys_hi & imask->phys_hi;
-        mid  = pregs->phys_mid & imask->phys_mid;
-        lo   = pregs->phys_lo & imask->phys_lo;
-        irq  = interrupt & imask->interrupt;
-
-        for (i = 0; i < num_imap; i++) {
-                if (imap[i].phys_hi  == hi   &&
-                    imap[i].phys_mid == mid  &&
-                    imap[i].phys_lo  == lo   &&
-                    imap[i].interrupt == irq) {
-                        *cnode = of_find_node_by_phandle(imap[i].cnode);
-                        interrupt = imap[i].cinterrupt;
-                }
-        }
-
-        if (pci_irq_verbose)
-                printk("%s: %s MAP BUS %s DEV %s [%x] -> [%x]\n",
-                       pbm->name, pci_name(toplevel_pdev),
-                       pci_name(pbus), pci_name(pdev),
-                       orig_interrupt, interrupt);
-
-no_intmap:
-        return interrupt;
-}
-
-/* For each PCI bus on the way to the root:
- * 1) If it has an interrupt-map property, apply it.
- * 2) Else, swivel the interrupt number based upon the PCI device number.
- *
- * Return the "IRQ controller" node.  If this is the PBM's device node,
- * all interrupt translations are complete, else we should use that node's
- * "reg" property to apply the PBM's "interrupt-{map,mask}" to the interrupt.
- */
-static struct device_node * __init
-pci_intmap_match_to_root(struct pci_pbm_info *pbm,
-                         struct pci_dev *pdev,
-                         unsigned int *interrupt)
-{
-        struct pci_dev *toplevel_pdev = pdev;
-        struct pcidev_cookie *toplevel_pcp = toplevel_pdev->sysdata;
-        struct device_node *cnode = toplevel_pcp->prom_node;
-
-        while (pdev->bus->number != pbm->pci_first_busno) {
-                struct pci_dev *pbus = pdev->bus->self;
-                struct pcidev_cookie *pcp = pbus->sysdata;
-                struct property *prop;
-
-                prop = of_find_property(pcp->prom_node, "interrupt-map", NULL);
-                if (!prop) {
-                        *interrupt = pci_slot_swivel(pbm, toplevel_pdev,
-                                                     pdev, *interrupt);
-                        cnode = pcp->prom_node;
-                } else {
-                        *interrupt = pci_apply_intmap(pbm, toplevel_pdev,
-                                                      pbus, pdev,
-                                                      *interrupt, &cnode);
-
-                        while (pcp->prom_node != cnode &&
-                               pbus->bus->number != pbm->pci_first_busno) {
-                                pbus = pbus->bus->self;
-                                pcp = pbus->sysdata;
-                        }
-                }
-                pdev = pbus;
-
-                if (cnode == pbm->prom_node)
-                        break;
-        }
-
-        return cnode;
-}
-
-static int __init pci_intmap_match(struct pci_dev *pdev, unsigned int *interrupt)
-{
-        struct pcidev_cookie *dev_pcp = pdev->sysdata;
-        struct pci_pbm_info *pbm = dev_pcp->pbm;
-        struct linux_prom_pci_registers *reg;
-        struct device_node *cnode;
-        struct property *prop;
-        unsigned int hi, mid, lo, irq;
-        int i, plen;
-
-        cnode = pci_intmap_match_to_root(pbm, pdev, interrupt);
-        if (cnode == pbm->prom_node)
-                goto success;
-
-        prop = of_find_property(cnode, "reg", &plen);
-        if (!prop ||
-            (plen % sizeof(struct linux_prom_pci_registers)) != 0) {
-                printk("%s: OBP node %s reg property has bad len %d\n",
-                       pbm->name, cnode->full_name, plen);
-                goto fail;
-        }
-        reg = prop->value;
-
-        hi   = reg[0].phys_hi & pbm->pbm_intmask->phys_hi;
-        mid  = reg[0].phys_mid & pbm->pbm_intmask->phys_mid;
-        lo   = reg[0].phys_lo & pbm->pbm_intmask->phys_lo;
-        irq  = *interrupt & pbm->pbm_intmask->interrupt;
-
-        for (i = 0; i < pbm->num_pbm_intmap; i++) {
-                struct linux_prom_pci_intmap *intmap;
-
-                intmap = &pbm->pbm_intmap[i];
-
-                if (intmap->phys_hi  == hi  &&
-                    intmap->phys_mid == mid &&
-                    intmap->phys_lo  == lo  &&
-                    intmap->interrupt == irq) {
-                        *interrupt = intmap->cinterrupt;
-                        goto success;
-                }
-        }
-
-fail:
-        return 0;
-
-success:
-        if (pci_irq_verbose)
-                printk("%s: Routing bus[%2x] slot[%2x] to INO[%02x]\n",
-                       pbm->name,
-                       pdev->bus->number, PCI_SLOT(pdev->devfn),
-                       *interrupt);
-        return 1;
-}
-
 static void __init pdev_fixup_irq(struct pci_dev *pdev)
 {
         struct pcidev_cookie *pcp = pdev->sysdata;
-        struct pci_pbm_info *pbm = pcp->pbm;
-        struct pci_controller_info *p = pbm->parent;
-        unsigned int portid = pbm->portid;
-        unsigned int prom_irq;
-        struct device_node *dp = pcp->prom_node;
-        struct property *prop;
-
-        /* If this is an empty EBUS device, sometimes OBP fails to
-         * give it a valid fully specified interrupts property.
-         * The EBUS hooked up to SunHME on PCI I/O boards of
-         * Ex000 systems is one such case.
-         *
-         * The interrupt is not important so just ignore it.
-         */
-        if (pdev->vendor == PCI_VENDOR_ID_SUN &&
-            pdev->device == PCI_DEVICE_ID_SUN_EBUS &&
-            !dp->child) {
-                pdev->irq = 0;
-                return;
-        }
+        struct of_device *op = pcp->op;
 
-        prop = of_find_property(dp, "interrupts", NULL);
-        if (!prop) {
-                pdev->irq = 0;
+        if (op->irqs[0] == 0xffffffff) {
+                pdev->irq = PCI_IRQ_NONE;
                 return;
         }
-        prom_irq = *(unsigned int *) prop->value;
-
-        if (tlb_type != hypervisor) {
-                /* Fully specified already? */
-                if (((prom_irq & PCI_IRQ_IGN) >> 6) == portid) {
-                        pdev->irq = p->irq_build(pbm, pdev, prom_irq);
-                        goto have_irq;
-                }
-
-                /* An onboard device? (bit 5 set) */
-                if ((prom_irq & PCI_IRQ_INO) & 0x20) {
-                        pdev->irq = p->irq_build(pbm, pdev, (portid << 6 | prom_irq));
-                        goto have_irq;
-                }
-        }
-
-        /* Can we find a matching entry in the interrupt-map? */
-        if (pci_intmap_match(pdev, &prom_irq)) {
-                pdev->irq = p->irq_build(pbm, pdev, (portid << 6) | prom_irq);
-                goto have_irq;
-        }
-
-        /* Ok, we have to do it the hard way. */
-        {
-                unsigned int bus, slot, line;
-
-                bus = (pbm == &pbm->parent->pbm_B) ? (1 << 4) : 0;
-
-                /* If we have a legal interrupt property, use it as
-                 * the IRQ line.
-                 */
-                if (prom_irq > 0 && prom_irq < 5) {
-                        line = ((prom_irq - 1) & 3);
-                } else {
-                        u8 pci_irq_line;
 
-                        /* Else just directly consult PCI config space. */
-                        pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pci_irq_line);
-                        line = ((pci_irq_line - 1) & 3);
-                }
-
-                /* Now figure out the slot.
-                 *
-                 * Basically, device number zero on the top-level bus is
-                 * always the PCI host controller.  Slot 0 is then device 1.
-                 * PBM A supports two external slots (0 and 1), and PBM B
-                 * supports 4 external slots (0, 1, 2, and 3).  On-board PCI
-                 * devices are wired to device numbers outside of these
-                 * ranges. -DaveM
-                 */
-                if (pdev->bus->number == pbm->pci_first_busno) {
-                        slot = PCI_SLOT(pdev->devfn) - pbm->pci_first_slot;
-                } else {
-                        struct pci_dev *bus_dev;
-
-                        /* Underneath a bridge, use slot number of parent
-                         * bridge which is closest to the PBM.
-                         */
-                        bus_dev = pdev->bus->self;
-                        while (bus_dev->bus &&
-                               bus_dev->bus->number != pbm->pci_first_busno)
-                                bus_dev = bus_dev->bus->self;
-
-                        slot = PCI_SLOT(bus_dev->devfn) - pbm->pci_first_slot;
-                }
-                slot = slot << 2;
-
-                pdev->irq = p->irq_build(pbm, pdev,
-                                         ((portid << 6) & PCI_IRQ_IGN) |
-                                         (bus | slot | line));
-        }
+        pdev->irq = op->irqs[0];
 
-have_irq:
         pci_write_config_byte(pdev, PCI_INTERRUPT_LINE,
                               pdev->irq & PCI_IRQ_INO);
 }
diff --git a/arch/sparc64/kernel/pci_psycho.c b/arch/sparc64/kernel/pci_psycho.c
index 5b2261ebda6f..bf7b32b36705 100644
--- a/arch/sparc64/kernel/pci_psycho.c
+++ b/arch/sparc64/kernel/pci_psycho.c
@@ -18,6 +18,7 @@
 #include <asm/irq.h>
 #include <asm/starfire.h>
 #include <asm/prom.h>
+#include <asm/of_device.h>
 
 #include "pci_impl.h"
 #include "iommu_common.h"
@@ -208,110 +209,6 @@ static struct pci_ops psycho_ops = {
         .write =        psycho_write_pci_cfg,
 };
 
-/* PSYCHO interrupt mapping support. */
-#define PSYCHO_IMAP_A_SLOT0     0x0c00UL
-#define PSYCHO_IMAP_B_SLOT0     0x0c20UL
-static unsigned long psycho_pcislot_imap_offset(unsigned long ino)
-{
-        unsigned int bus =  (ino & 0x10) >> 4;
-        unsigned int slot = (ino & 0x0c) >> 2;
-
-        if (bus == 0)
-                return PSYCHO_IMAP_A_SLOT0 + (slot * 8);
-        else
-                return PSYCHO_IMAP_B_SLOT0 + (slot * 8);
-}
-
-#define PSYCHO_IMAP_SCSI        0x1000UL
-#define PSYCHO_IMAP_ETH         0x1008UL
-#define PSYCHO_IMAP_BPP         0x1010UL
-#define PSYCHO_IMAP_AU_REC      0x1018UL
-#define PSYCHO_IMAP_AU_PLAY     0x1020UL
-#define PSYCHO_IMAP_PFAIL       0x1028UL
-#define PSYCHO_IMAP_KMS         0x1030UL
-#define PSYCHO_IMAP_FLPY        0x1038UL
-#define PSYCHO_IMAP_SHW         0x1040UL
-#define PSYCHO_IMAP_KBD         0x1048UL
-#define PSYCHO_IMAP_MS          0x1050UL
-#define PSYCHO_IMAP_SER         0x1058UL
-#define PSYCHO_IMAP_TIM0        0x1060UL
-#define PSYCHO_IMAP_TIM1        0x1068UL
-#define PSYCHO_IMAP_UE          0x1070UL
-#define PSYCHO_IMAP_CE          0x1078UL
-#define PSYCHO_IMAP_A_ERR       0x1080UL
-#define PSYCHO_IMAP_B_ERR       0x1088UL
-#define PSYCHO_IMAP_PMGMT       0x1090UL
-#define PSYCHO_IMAP_GFX         0x1098UL
-#define PSYCHO_IMAP_EUPA        0x10a0UL
-
-static unsigned long __onboard_imap_off[] = {
-/*0x20*/        PSYCHO_IMAP_SCSI,
-/*0x21*/        PSYCHO_IMAP_ETH,
-/*0x22*/        PSYCHO_IMAP_BPP,
-/*0x23*/        PSYCHO_IMAP_AU_REC,
-/*0x24*/        PSYCHO_IMAP_AU_PLAY,
-/*0x25*/        PSYCHO_IMAP_PFAIL,
-/*0x26*/        PSYCHO_IMAP_KMS,
-/*0x27*/        PSYCHO_IMAP_FLPY,
-/*0x28*/        PSYCHO_IMAP_SHW,
-/*0x29*/        PSYCHO_IMAP_KBD,
-/*0x2a*/        PSYCHO_IMAP_MS,
-/*0x2b*/        PSYCHO_IMAP_SER,
-/*0x2c*/        PSYCHO_IMAP_TIM0,
-/*0x2d*/        PSYCHO_IMAP_TIM1,
-/*0x2e*/        PSYCHO_IMAP_UE,
-/*0x2f*/        PSYCHO_IMAP_CE,
-/*0x30*/        PSYCHO_IMAP_A_ERR,
-/*0x31*/        PSYCHO_IMAP_B_ERR,
-/*0x32*/        PSYCHO_IMAP_PMGMT
-};
-#define PSYCHO_ONBOARD_IRQ_BASE         0x20
-#define PSYCHO_ONBOARD_IRQ_LAST         0x32
-#define psycho_onboard_imap_offset(__ino) \
-        __onboard_imap_off[(__ino) - PSYCHO_ONBOARD_IRQ_BASE]
-
-#define PSYCHO_ICLR_A_SLOT0     0x1400UL
-#define PSYCHO_ICLR_SCSI        0x1800UL
-
-#define psycho_iclr_offset(ino)                                       \
-        ((ino & 0x20) ? (PSYCHO_ICLR_SCSI + (((ino) & 0x1f) << 3)) :  \
-                        (PSYCHO_ICLR_A_SLOT0 + (((ino) & 0x1f)<<3)))
-
-static unsigned int psycho_irq_build(struct pci_pbm_info *pbm,
-                                     struct pci_dev *pdev,
-                                     unsigned int ino)
-{
-        unsigned long imap, iclr;
-        unsigned long imap_off, iclr_off;
-        int inofixup = 0;
-
-        ino &= PCI_IRQ_INO;
-        if (ino < PSYCHO_ONBOARD_IRQ_BASE) {
-                /* PCI slot */
-                imap_off = psycho_pcislot_imap_offset(ino);
-        } else {
-                /* Onboard device */
-                if (ino > PSYCHO_ONBOARD_IRQ_LAST) {
-                        prom_printf("psycho_irq_build: Wacky INO [%x]\n", ino);
-                        prom_halt();
-                }
-                imap_off = psycho_onboard_imap_offset(ino);
-        }
-
-        /* Now build the IRQ bucket. */
-        imap = pbm->controller_regs + imap_off;
-        imap += 4;
-
-        iclr_off = psycho_iclr_offset(ino);
-        iclr = pbm->controller_regs + iclr_off;
-        iclr += 4;
-
-        if ((ino & 0x20) == 0)
-                inofixup = ino & 0x03;
-
-        return build_irq(inofixup, iclr, imap);
-}
-
 /* PSYCHO error handling support. */
 enum psycho_error_type {
         UE_ERR, CE_ERR, PCI_ERR
@@ -944,51 +841,34 @@ static irqreturn_t psycho_pcierr_intr(int irq, void *dev_id, struct pt_regs *reg
 #define  PSYCHO_ECCCTRL_EE       0x8000000000000000UL /* Enable ECC Checking */
 #define  PSYCHO_ECCCTRL_UE       0x4000000000000000UL /* Enable UE Interrupts */
 #define  PSYCHO_ECCCTRL_CE       0x2000000000000000UL /* Enable CE INterrupts */
-#define PSYCHO_UE_INO           0x2e
-#define PSYCHO_CE_INO           0x2f
-#define PSYCHO_PCIERR_A_INO     0x30
-#define PSYCHO_PCIERR_B_INO     0x31
 static void psycho_register_error_handlers(struct pci_controller_info *p)
 {
         struct pci_pbm_info *pbm = &p->pbm_A; /* arbitrary */
+        struct of_device *op = of_find_device_by_node(pbm->prom_node);
         unsigned long base = p->pbm_A.controller_regs;
-        unsigned int irq, portid = pbm->portid;
         u64 tmp;
 
-        /* Build IRQs and register handlers. */
-        irq = psycho_irq_build(pbm, NULL, (portid << 6) | PSYCHO_UE_INO);
-        if (request_irq(irq, psycho_ue_intr,
-                        SA_SHIRQ, "PSYCHO UE", p) < 0) {
-                prom_printf("PSYCHO%d: Cannot register UE interrupt.\n",
-                            p->index);
-                prom_halt();
-        }
+        if (!op)
+                return;
 
-        irq = psycho_irq_build(pbm, NULL, (portid << 6) | PSYCHO_CE_INO);
-        if (request_irq(irq, psycho_ce_intr,
-                        SA_SHIRQ, "PSYCHO CE", p) < 0) {
-                prom_printf("PSYCHO%d: Cannot register CE interrupt.\n",
-                            p->index);
-                prom_halt();
-        }
+        /* Psycho interrupt property order is:
+         * 0: PCIERR PBM B INO
+         * 1: UE ERR
+         * 2: CE ERR
+         * 3: POWER FAIL
+         * 4: SPARE HARDWARE
+         * 5: PCIERR PBM A INO
+         */
 
-        pbm = &p->pbm_A;
-        irq = psycho_irq_build(pbm, NULL, (portid << 6) | PSYCHO_PCIERR_A_INO);
-        if (request_irq(irq, psycho_pcierr_intr,
-                        SA_SHIRQ, "PSYCHO PCIERR", &p->pbm_A) < 0) {
-                prom_printf("PSYCHO%d(PBMA): Cannot register PciERR interrupt.\n",
-                            p->index);
-                prom_halt();
-        }
+        if (op->num_irqs < 6)
+                return;
 
-        pbm = &p->pbm_B;
-        irq = psycho_irq_build(pbm, NULL, (portid << 6) | PSYCHO_PCIERR_B_INO);
-        if (request_irq(irq, psycho_pcierr_intr,
-                        SA_SHIRQ, "PSYCHO PCIERR", &p->pbm_B) < 0) {
-                prom_printf("PSYCHO%d(PBMB): Cannot register PciERR interrupt.\n",
-                            p->index);
-                prom_halt();
-        }
+        request_irq(op->irqs[1], psycho_ue_intr, SA_SHIRQ, "PSYCHO UE", p);
+        request_irq(op->irqs[2], psycho_ce_intr, SA_SHIRQ, "PSYCHO CE", p);
+        request_irq(op->irqs[5], psycho_pcierr_intr, SA_SHIRQ,
+                    "PSYCHO PCIERR-A", &p->pbm_A);
+        request_irq(op->irqs[0], psycho_pcierr_intr, SA_SHIRQ,
+                    "PSYCHO PCIERR-B", &p->pbm_B);
 
         /* Enable UE and CE interrupts for controller. */
         psycho_write(base + PSYCHO_ECC_CTRL,
@@ -1171,9 +1051,7 @@ static void psycho_iommu_init(struct pci_controller_info *p)
 
         /* If necessary, hook us up for starfire IRQ translations. */
         if (this_is_starfire)
-                p->starfire_cookie = starfire_hookup(p->pbm_A.portid);
-        else
-                p->starfire_cookie = NULL;
+                starfire_hookup(p->pbm_A.portid);
 }
 
 #define PSYCHO_IRQ_RETRY        0x1a00UL
@@ -1408,7 +1286,6 @@ void psycho_init(struct device_node *dp, char *model_name)
         p->index = pci_num_controllers++;
         p->pbms_same_domain = 0;
         p->scan_bus = psycho_scan_bus;
-        p->irq_build = psycho_irq_build;
         p->base_address_update = psycho_base_address_update;
         p->resource_adjust = psycho_resource_adjust;
         p->pci_ops = &psycho_ops;
diff --git a/arch/sparc64/kernel/pci_sabre.c b/arch/sparc64/kernel/pci_sabre.c
index 26f194ce4400..5e087b0fb4c9 100644
--- a/arch/sparc64/kernel/pci_sabre.c
+++ b/arch/sparc64/kernel/pci_sabre.c
@@ -485,114 +485,6 @@ static struct pci_ops sabre_ops = {
         .write =        sabre_write_pci_cfg,
 };
 
-static unsigned long sabre_pcislot_imap_offset(unsigned long ino)
-{
-        unsigned int bus =  (ino & 0x10) >> 4;
-        unsigned int slot = (ino & 0x0c) >> 2;
-
-        if (bus == 0)
-                return SABRE_IMAP_A_SLOT0 + (slot * 8);
-        else
-                return SABRE_IMAP_B_SLOT0 + (slot * 8);
-}
-
-static unsigned long __onboard_imap_off[] = {
-/*0x20*/        SABRE_IMAP_SCSI,
-/*0x21*/        SABRE_IMAP_ETH,
-/*0x22*/        SABRE_IMAP_BPP,
-/*0x23*/        SABRE_IMAP_AU_REC,
-/*0x24*/        SABRE_IMAP_AU_PLAY,
-/*0x25*/        SABRE_IMAP_PFAIL,
-/*0x26*/        SABRE_IMAP_KMS,
-/*0x27*/        SABRE_IMAP_FLPY,
-/*0x28*/        SABRE_IMAP_SHW,
-/*0x29*/        SABRE_IMAP_KBD,
-/*0x2a*/        SABRE_IMAP_MS,
-/*0x2b*/        SABRE_IMAP_SER,
-/*0x2c*/        0 /* reserved */,
-/*0x2d*/        0 /* reserved */,
-/*0x2e*/        SABRE_IMAP_UE,
-/*0x2f*/        SABRE_IMAP_CE,
-/*0x30*/        SABRE_IMAP_PCIERR,
-};
-#define SABRE_ONBOARD_IRQ_BASE          0x20
-#define SABRE_ONBOARD_IRQ_LAST          0x30
-#define sabre_onboard_imap_offset(__ino) \
-        __onboard_imap_off[(__ino) - SABRE_ONBOARD_IRQ_BASE]
-
-#define sabre_iclr_offset(ino)                                        \
-        ((ino & 0x20) ? (SABRE_ICLR_SCSI + (((ino) & 0x1f) << 3)) :  \
-                        (SABRE_ICLR_A_SLOT0 + (((ino) & 0x1f)<<3)))
-
-/* When a device lives behind a bridge deeper in the PCI bus topology
- * than APB, a special sequence must run to make sure all pending DMA
- * transfers at the time of IRQ delivery are visible in the coherency
- * domain by the cpu.  This sequence is to perform a read on the far
- * side of the non-APB bridge, then perform a read of Sabre's DMA
- * write-sync register.
- */
-static void sabre_wsync_handler(unsigned int ino, void *_arg1, void *_arg2)
-{
-        struct pci_dev *pdev = _arg1;
-        unsigned long sync_reg = (unsigned long) _arg2;
-        u16 _unused;
-
-        pci_read_config_word(pdev, PCI_VENDOR_ID, &_unused);
-        sabre_read(sync_reg);
-}
-
-static unsigned int sabre_irq_build(struct pci_pbm_info *pbm,
-                                    struct pci_dev *pdev,
-                                    unsigned int ino)
-{
-        unsigned long imap, iclr;
-        unsigned long imap_off, iclr_off;
-        int inofixup = 0;
-        int virt_irq;
-
-        ino &= PCI_IRQ_INO;
-        if (ino < SABRE_ONBOARD_IRQ_BASE) {
-                /* PCI slot */
-                imap_off = sabre_pcislot_imap_offset(ino);
-        } else {
-                /* onboard device */
-                if (ino > SABRE_ONBOARD_IRQ_LAST) {
-                        prom_printf("sabre_irq_build: Wacky INO [%x]\n", ino);
-                        prom_halt();
-                }
-                imap_off = sabre_onboard_imap_offset(ino);
-        }
-
-        /* Now build the IRQ bucket. */
-        imap = pbm->controller_regs + imap_off;
-        imap += 4;
-
-        iclr_off = sabre_iclr_offset(ino);
-        iclr = pbm->controller_regs + iclr_off;
-        iclr += 4;
-
-        if ((ino & 0x20) == 0)
-                inofixup = ino & 0x03;
-
-        virt_irq = build_irq(inofixup, iclr, imap);
-
-        if (pdev) {
-                struct pcidev_cookie *pcp = pdev->sysdata;
-
-                if (pdev->bus->number != pcp->pbm->pci_first_busno) {
-                        struct pci_controller_info *p = pcp->pbm->parent;
-
-                        irq_install_pre_handler(virt_irq,
-                                                sabre_wsync_handler,
-                                                pdev,
-                                                (void *)
-                                                p->pbm_A.controller_regs +
-                                                SABRE_WRSYNC);
-                }
-        }
-        return virt_irq;
-}
-
 /* SABRE error handling support. */
 static void sabre_check_iommu_error(struct pci_controller_info *p,
                                     unsigned long afsr,
@@ -929,17 +821,30 @@ static irqreturn_t sabre_pcierr_intr(int irq, void *dev_id, struct pt_regs *regs
         return IRQ_HANDLED;
 }
 
-/* XXX What about PowerFail/PowerManagement??? -DaveM */
-#define SABRE_UE_INO            0x2e
-#define SABRE_CE_INO            0x2f
-#define SABRE_PCIERR_INO        0x30
 static void sabre_register_error_handlers(struct pci_controller_info *p)
 {
         struct pci_pbm_info *pbm = &p->pbm_A; /* arbitrary */
+        struct device_node *dp = pbm->prom_node;
+        struct of_device *op;
         unsigned long base = pbm->controller_regs;
-        unsigned long irq, portid = pbm->portid;
         u64 tmp;
 
+        if (pbm->chip_type == PBM_CHIP_TYPE_SABRE)
+                dp = dp->parent;
+
+        op = of_find_device_by_node(dp);
+        if (!op)
+                return;
+
+        /* Sabre/Hummingbird IRQ property layout is:
+         * 0: PCI ERR
+         * 1: UE ERR
+         * 2: CE ERR
+         * 3: POWER FAIL
+         */
+        if (op->num_irqs < 4)
+                return;
+
         /* We clear the error bits in the appropriate AFSR before
          * registering the handler so that we don't get spurious
          * interrupts.
@@ -948,32 +853,16 @@ static void sabre_register_error_handlers(struct pci_controller_info *p)
                     (SABRE_UEAFSR_PDRD | SABRE_UEAFSR_PDWR |
                      SABRE_UEAFSR_SDRD | SABRE_UEAFSR_SDWR |
                      SABRE_UEAFSR_SDTE | SABRE_UEAFSR_PDTE));
-        irq = sabre_irq_build(pbm, NULL, (portid << 6) | SABRE_UE_INO);
-        if (request_irq(irq, sabre_ue_intr,
-                        SA_SHIRQ, "SABRE UE", p) < 0) {
-                prom_printf("SABRE%d: Cannot register UE interrupt.\n",
-                            p->index);
-                prom_halt();
-        }
+
+        request_irq(op->irqs[1], sabre_ue_intr, SA_SHIRQ, "SABRE UE", p);
 
         sabre_write(base + SABRE_CE_AFSR,
                     (SABRE_CEAFSR_PDRD | SABRE_CEAFSR_PDWR |
                      SABRE_CEAFSR_SDRD | SABRE_CEAFSR_SDWR));
-        irq = sabre_irq_build(pbm, NULL, (portid << 6) | SABRE_CE_INO);
-        if (request_irq(irq, sabre_ce_intr,
-                        SA_SHIRQ, "SABRE CE", p) < 0) {
-                prom_printf("SABRE%d: Cannot register CE interrupt.\n",
-                            p->index);
-                prom_halt();
-        }
 
-        irq = sabre_irq_build(pbm, NULL, (portid << 6) | SABRE_PCIERR_INO);
-        if (request_irq(irq, sabre_pcierr_intr,
-                        SA_SHIRQ, "SABRE PCIERR", p) < 0) {
-                prom_printf("SABRE%d: Cannot register PciERR interrupt.\n",
-                            p->index);
-                prom_halt();
-        }
+        request_irq(op->irqs[2], sabre_ce_intr, SA_SHIRQ, "SABRE CE", p);
+        request_irq(op->irqs[0], sabre_pcierr_intr, SA_SHIRQ,
+                    "SABRE PCIERR", p);
 
         tmp = sabre_read(base + SABRE_PCICTRL);
         tmp |= SABRE_PCICTRL_ERREN;
@@ -1492,7 +1381,6 @@ void sabre_init(struct device_node *dp, char *model_name)
         p->index = pci_num_controllers++;
         p->pbms_same_domain = 1;
         p->scan_bus = sabre_scan_bus;
-        p->irq_build = sabre_irq_build;
         p->base_address_update = sabre_base_address_update;
         p->resource_adjust = sabre_resource_adjust;
         p->pci_ops = &sabre_ops;
diff --git a/arch/sparc64/kernel/pci_schizo.c b/arch/sparc64/kernel/pci_schizo.c
index f16449ccd7bc..5c6e2a9b91f8 100644
--- a/arch/sparc64/kernel/pci_schizo.c
+++ b/arch/sparc64/kernel/pci_schizo.c
@@ -217,116 +217,6 @@ static struct pci_ops schizo_ops = {
         .write =        schizo_write_pci_cfg,
 };
 
-/* SCHIZO interrupt mapping support.  Unlike Psycho, for this controller the
- * imap/iclr registers are per-PBM.
- */
-#define SCHIZO_IMAP_BASE        0x1000UL
-#define SCHIZO_ICLR_BASE        0x1400UL
-
-static unsigned long schizo_imap_offset(unsigned long ino)
-{
-        return SCHIZO_IMAP_BASE + (ino * 8UL);
-}
-
-static unsigned long schizo_iclr_offset(unsigned long ino)
-{
-        return SCHIZO_ICLR_BASE + (ino * 8UL);
-}
-
-static void tomatillo_wsync_handler(unsigned int ino, void *_arg1, void *_arg2)
-{
-        unsigned long sync_reg = (unsigned long) _arg2;
-        u64 mask = 1UL << (ino & IMAP_INO);
-        u64 val;
-        int limit;
-
-        schizo_write(sync_reg, mask);
-
-        limit = 100000;
-        val = 0;
-        while (--limit) {
-                val = schizo_read(sync_reg);
-                if (!(val & mask))
-                        break;
-        }
-        if (limit <= 0) {
-                printk("tomatillo_wsync_handler: DMA won't sync [%lx:%lx]\n",
-                       val, mask);
-        }
-
-        if (_arg1) {
-                static unsigned char cacheline[64]
-                        __attribute__ ((aligned (64)));
-
-                __asm__ __volatile__("rd %%fprs, %0\n\t"
-                                     "or %0, %4, %1\n\t"
-                                     "wr %1, 0x0, %%fprs\n\t"
-                                     "stda %%f0, [%5] %6\n\t"
-                                     "wr %0, 0x0, %%fprs\n\t"
-                                     "membar #Sync"
-                                     : "=&r" (mask), "=&r" (val)
-                                     : "0" (mask), "1" (val),
-                                     "i" (FPRS_FEF), "r" (&cacheline[0]),
-                                     "i" (ASI_BLK_COMMIT_P));
-        }
-}
-
-static unsigned long schizo_ino_to_iclr(struct pci_pbm_info *pbm,
-                                        unsigned int ino)
-{
-        ino &= PCI_IRQ_INO;
-        return pbm->pbm_regs + schizo_iclr_offset(ino) + 4;
-}
-
-static unsigned long schizo_ino_to_imap(struct pci_pbm_info *pbm,
-                                        unsigned int ino)
-{
-        ino &= PCI_IRQ_INO;
-        return pbm->pbm_regs + schizo_imap_offset(ino) + 4;
-}
-
-static unsigned int schizo_irq_build(struct pci_pbm_info *pbm,
-                                     struct pci_dev *pdev,
-                                     unsigned int ino)
-{
-        unsigned long imap, iclr;
-        int ign_fixup;
-        int virt_irq;
-
-        ino &= PCI_IRQ_INO;
-
-        /* Now build the IRQ bucket. */
-        imap = schizo_ino_to_imap(pbm, ino);
-        iclr = schizo_ino_to_iclr(pbm, ino);
-
-        /* On Schizo, no inofixup occurs.  This is because each
-         * INO has it's own IMAP register.  On Psycho and Sabre
-         * there is only one IMAP register for each PCI slot even
-         * though four different INOs can be generated by each
-         * PCI slot.
-         *
-         * But, for JBUS variants (essentially, Tomatillo), we have
-         * to fixup the lowest bit of the interrupt group number.
-         */
-        ign_fixup = 0;
-        if (pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO) {
-                if (pbm->portid & 1)
-                        ign_fixup = (1 << 6);
-        }
-
-        virt_irq = build_irq(ign_fixup, iclr, imap);
-
-        if (pdev && pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO) {
-                irq_install_pre_handler(virt_irq,
-                                        tomatillo_wsync_handler,
-                                        ((pbm->chip_version <= 4) ?
-                                         (void *) 1 : (void *) 0),
-                                        (void *) pbm->sync_reg);
-        }
-
-        return virt_irq;
-}
-
 /* SCHIZO error handling support. */
 enum schizo_error_type {
         UE_ERR, CE_ERR, PCI_ERR, SAFARI_ERR
@@ -362,34 +252,6 @@ struct pci_pbm_info *pbm_for_ino(struct pci_controller_info *p, u32 ino)
         return &p->pbm_A;
 }
 
-static void schizo_clear_other_err_intr(struct pci_controller_info *p, int irq)
-{
-        struct pci_pbm_info *pbm;
-        unsigned long iclr;
-
-        /* Do not clear the interrupt for the other PCI bus.
-         *
-         * This "ACK both PBM IRQs" only needs to be performed
-         * for chip-wide error interrupts.
-         */
-        if ((irq & IMAP_INO) == SCHIZO_PCIERR_A_INO ||
-            (irq & IMAP_INO) == SCHIZO_PCIERR_B_INO)
-                return;
-
-        pbm = pbm_for_ino(p, irq);
-        if (pbm == &p->pbm_A)
-                pbm = &p->pbm_B;
-        else
-                pbm = &p->pbm_A;
-
-        schizo_irq_build(pbm, NULL,
-                         (pbm->portid << 6) | (irq & IMAP_INO));
-
-        iclr = schizo_ino_to_iclr(pbm,
-                                  (pbm->portid << 6) | (irq & IMAP_INO));
-        upa_writel(ICLR_IDLE, iclr);
-}
-
 #define SCHIZO_STC_ERR  0xb800UL /* --> 0xba00 */
 #define SCHIZO_STC_TAG  0xba00UL /* --> 0xba80 */
 #define SCHIZO_STC_LINE 0xbb00UL /* --> 0xbb80 */
@@ -720,8 +582,6 @@ static irqreturn_t schizo_ue_intr(int irq, void *dev_id, struct pt_regs *regs)
         /* Interrogate IOMMU for error status. */
         schizo_check_iommu_error(p, UE_ERR);
 
-        schizo_clear_other_err_intr(p, irq);
-
         return IRQ_HANDLED;
 }
 
@@ -811,8 +671,6 @@ static irqreturn_t schizo_ce_intr(int irq, void *dev_id, struct pt_regs *regs)
                 printk("(none)");
         printk("]\n");
 
-        schizo_clear_other_err_intr(p, irq);
-
         return IRQ_HANDLED;
 }
 
@@ -1033,8 +891,6 @@ static irqreturn_t schizo_pcierr_intr(int irq, void *dev_id, struct pt_regs *reg
         if (error_bits & (SCHIZO_PCIAFSR_PPERR | SCHIZO_PCIAFSR_SPERR))
                 pci_scan_for_parity_error(p, pbm, pbm->pci_bus);
 
-        schizo_clear_other_err_intr(p, irq);
-
         return IRQ_HANDLED;
 }
 
@@ -1090,7 +946,6 @@ static irqreturn_t schizo_safarierr_intr(int irq, void *dev_id, struct pt_regs *
                 printk("PCI%d: Unexpected Safari/JBUS error interrupt, errlog[%016lx]\n",
                        p->index, errlog);
 
-                schizo_clear_other_err_intr(p, irq);
                 return IRQ_HANDLED;
         }
 
@@ -1098,7 +953,6 @@ static irqreturn_t schizo_safarierr_intr(int irq, void *dev_id, struct pt_regs *
                p->index);
         schizo_check_iommu_error(p, SAFARI_ERR);
 
-        schizo_clear_other_err_intr(p, irq);
         return IRQ_HANDLED;
 }
 
@@ -1130,74 +984,47 @@ static irqreturn_t schizo_safarierr_intr(int irq, void *dev_id, struct pt_regs *
 static void tomatillo_register_error_handlers(struct pci_controller_info *p)
 {
         struct pci_pbm_info *pbm;
-        unsigned int irq;
+        struct of_device *op;
         u64 tmp, err_mask, err_no_mask;
 
-        /* Build IRQs and register handlers. */
+        /* Tomatillo IRQ property layout is:
+         * 0: PCIERR
+         * 1: UE ERR
+         * 2: CE ERR
+         * 3: SERR
+         * 4: POWER FAIL?
+         */
+
         pbm = pbm_for_ino(p, SCHIZO_UE_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_UE_INO);
-        if (request_irq(irq, schizo_ue_intr,
-                        SA_SHIRQ, "TOMATILLO UE", p) < 0) {
-                prom_printf("%s: Cannot register UE interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, (pbm->portid << 6) | SCHIZO_UE_INO));
-        upa_writel(tmp, (pbm->pbm_regs +
-                         schizo_imap_offset(SCHIZO_UE_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[1], schizo_ue_intr, SA_SHIRQ,
+                            "TOMATILLO_UE", p);
 
         pbm = pbm_for_ino(p, SCHIZO_CE_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_CE_INO);
-        if (request_irq(irq, schizo_ce_intr,
-                        SA_SHIRQ, "TOMATILLO CE", p) < 0) {
-                prom_printf("%s: Cannot register CE interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, (pbm->portid << 6) | SCHIZO_CE_INO));
-        upa_writel(tmp, (pbm->pbm_regs +
-                         schizo_imap_offset(SCHIZO_CE_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[2], schizo_ce_intr, SA_SHIRQ,
+                            "TOMATILLO CE", p);
 
         pbm = pbm_for_ino(p, SCHIZO_PCIERR_A_INO);
-        irq = schizo_irq_build(pbm, NULL, ((pbm->portid << 6) |
-                                           SCHIZO_PCIERR_A_INO));
-        if (request_irq(irq, schizo_pcierr_intr,
-                        SA_SHIRQ, "TOMATILLO PCIERR", pbm) < 0) {
-                prom_printf("%s: Cannot register PBM A PciERR interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, ((pbm->portid << 6) |
-                                                 SCHIZO_PCIERR_A_INO)));
-        upa_writel(tmp, (pbm->pbm_regs +
-                         schizo_imap_offset(SCHIZO_PCIERR_A_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[0], schizo_pcierr_intr, SA_SHIRQ,
+                            "TOMATILLO PCIERR-A", pbm);
+
 
         pbm = pbm_for_ino(p, SCHIZO_PCIERR_B_INO);
-        irq = schizo_irq_build(pbm, NULL, ((pbm->portid << 6) |
-                                            SCHIZO_PCIERR_B_INO));
-        if (request_irq(irq, schizo_pcierr_intr,
-                        SA_SHIRQ, "TOMATILLO PCIERR", pbm) < 0) {
-                prom_printf("%s: Cannot register PBM B PciERR interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, ((pbm->portid << 6) |
-                                                 SCHIZO_PCIERR_B_INO)));
-        upa_writel(tmp, (pbm->pbm_regs +
-                         schizo_imap_offset(SCHIZO_PCIERR_B_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[0], schizo_pcierr_intr, SA_SHIRQ,
+                            "TOMATILLO PCIERR-B", pbm);
 
         pbm = pbm_for_ino(p, SCHIZO_SERR_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_SERR_INO);
-        if (request_irq(irq, schizo_safarierr_intr,
-                        SA_SHIRQ, "TOMATILLO SERR", p) < 0) {
-                prom_printf("%s: Cannot register SafariERR interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, ((pbm->portid << 6) |
-                                                 SCHIZO_SERR_INO)));
-        upa_writel(tmp, (pbm->pbm_regs +
-                         schizo_imap_offset(SCHIZO_SERR_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[3], schizo_safarierr_intr, SA_SHIRQ,
+                            "TOMATILLO SERR", p);
 
         /* Enable UE and CE interrupts for controller. */
         schizo_write(p->pbm_A.controller_regs + SCHIZO_ECC_CTRL,
@@ -1265,64 +1092,47 @@ static void tomatillo_register_error_handlers(struct pci_controller_info *p)
 static void schizo_register_error_handlers(struct pci_controller_info *p)
 {
         struct pci_pbm_info *pbm;
-        unsigned int irq;
+        struct of_device *op;
         u64 tmp, err_mask, err_no_mask;
 
-        /* Build IRQs and register handlers. */
+        /* Schizo IRQ property layout is:
+         * 0: PCIERR
+         * 1: UE ERR
+         * 2: CE ERR
+         * 3: SERR
+         * 4: POWER FAIL?
+         */
+
         pbm = pbm_for_ino(p, SCHIZO_UE_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_UE_INO);
-        if (request_irq(irq, schizo_ue_intr,
-                        SA_SHIRQ, "SCHIZO UE", p) < 0) {
-                prom_printf("%s: Cannot register UE interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, (pbm->portid << 6) | SCHIZO_UE_INO));
-        upa_writel(tmp, (pbm->pbm_regs + schizo_imap_offset(SCHIZO_UE_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[1], schizo_ue_intr, SA_SHIRQ,
+                            "SCHIZO_UE", p);
 
         pbm = pbm_for_ino(p, SCHIZO_CE_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_CE_INO);
-        if (request_irq(irq, schizo_ce_intr,
-                        SA_SHIRQ, "SCHIZO CE", p) < 0) {
-                prom_printf("%s: Cannot register CE interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, (pbm->portid << 6) | SCHIZO_CE_INO));
-        upa_writel(tmp, (pbm->pbm_regs + schizo_imap_offset(SCHIZO_CE_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[2], schizo_ce_intr, SA_SHIRQ,
+                            "SCHIZO CE", p);
 
         pbm = pbm_for_ino(p, SCHIZO_PCIERR_A_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_PCIERR_A_INO);
-        if (request_irq(irq, schizo_pcierr_intr,
-                        SA_SHIRQ, "SCHIZO PCIERR", pbm) < 0) {
-                prom_printf("%s: Cannot register PBM A PciERR interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, (pbm->portid << 6) | SCHIZO_PCIERR_A_INO));
-        upa_writel(tmp, (pbm->pbm_regs + schizo_imap_offset(SCHIZO_PCIERR_A_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[0], schizo_pcierr_intr, SA_SHIRQ,
+                            "SCHIZO PCIERR-A", pbm);
+
 
         pbm = pbm_for_ino(p, SCHIZO_PCIERR_B_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_PCIERR_B_INO);
-        if (request_irq(irq, schizo_pcierr_intr,
-                        SA_SHIRQ, "SCHIZO PCIERR", &p->pbm_B) < 0) {
-                prom_printf("%s: Cannot register PBM B PciERR interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, (pbm->portid << 6) | SCHIZO_PCIERR_B_INO));
-        upa_writel(tmp, (pbm->pbm_regs + schizo_imap_offset(SCHIZO_PCIERR_B_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[0], schizo_pcierr_intr, SA_SHIRQ,
+                            "SCHIZO PCIERR-B", pbm);
 
         pbm = pbm_for_ino(p, SCHIZO_SERR_INO);
-        irq = schizo_irq_build(pbm, NULL, (pbm->portid << 6) | SCHIZO_SERR_INO);
-        if (request_irq(irq, schizo_safarierr_intr,
-                        SA_SHIRQ, "SCHIZO SERR", p) < 0) {
-                prom_printf("%s: Cannot register SafariERR interrupt.\n",
-                            pbm->name);
-                prom_halt();
-        }
-        tmp = upa_readl(schizo_ino_to_imap(pbm, (pbm->portid << 6) | SCHIZO_SERR_INO));
-        upa_writel(tmp, (pbm->pbm_regs + schizo_imap_offset(SCHIZO_SERR_INO) + 4));
+        op = of_find_device_by_node(pbm->prom_node);
+        if (op)
+                request_irq(op->irqs[3], schizo_safarierr_intr, SA_SHIRQ,
+                            "SCHIZO SERR", p);
 
         /* Enable UE and CE interrupts for controller. */
         schizo_write(p->pbm_A.controller_regs + SCHIZO_ECC_CTRL,
@@ -2022,7 +1832,6 @@ static void __schizo_init(struct device_node *dp, char *model_name, int chip_typ
         p->scan_bus = (chip_type == PBM_CHIP_TYPE_TOMATILLO ?
                        tomatillo_scan_bus :
                        schizo_scan_bus);
-        p->irq_build = schizo_irq_build;
         p->base_address_update = schizo_base_address_update;
         p->resource_adjust = schizo_resource_adjust;
         p->pci_ops = &schizo_ops;
diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc64/kernel/pci_sun4v.c
index b69e2270a721..03ad4c06758e 100644
--- a/arch/sparc64/kernel/pci_sun4v.c
+++ b/arch/sparc64/kernel/pci_sun4v.c
@@ -843,15 +843,6 @@ static void pci_sun4v_scan_bus(struct pci_controller_info *p)
         /* XXX register error interrupt handlers XXX */
 }
 
-static unsigned int pci_sun4v_irq_build(struct pci_pbm_info *pbm,
-                                        struct pci_dev *pdev,
-                                        unsigned int devino)
-{
-        u32 devhandle = pbm->devhandle;
-
-        return sun4v_build_irq(devhandle, devino);
-}
-
 static void pci_sun4v_base_address_update(struct pci_dev *pdev, int resource)
 {
         struct pcidev_cookie *pcp = pdev->sysdata;
@@ -1200,7 +1191,6 @@ void sun4v_pci_init(struct device_node *dp, char *model_name)
         p->pbms_same_domain = 0;
 
         p->scan_bus = pci_sun4v_scan_bus;
-        p->irq_build = pci_sun4v_irq_build;
         p->base_address_update = pci_sun4v_base_address_update;
         p->resource_adjust = pci_sun4v_resource_adjust;
         p->pci_ops = &pci_sun4v_ops;
diff --git a/arch/sparc64/kernel/power.c b/arch/sparc64/kernel/power.c
index 9496c7734014..4febeda958a3 100644
--- a/arch/sparc64/kernel/power.c
+++ b/arch/sparc64/kernel/power.c
@@ -17,9 +17,10 @@
 #include <linux/pm.h>
 
 #include <asm/system.h>
-#include <asm/ebus.h>
-#include <asm/isa.h>
 #include <asm/auxio.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
+#include <asm/io.h>
 
 #include <linux/unistd.h>
 
@@ -30,6 +31,7 @@
 int scons_pwroff = 1; 
 
 #ifdef CONFIG_PCI
+#include <linux/pci.h>
 static void __iomem *power_reg;
 
 static DECLARE_WAIT_QUEUE_HEAD(powerd_wait);
@@ -115,27 +117,33 @@ static int __init has_button_interrupt(unsigned int irq, struct device_node *dp)
         return 1;
 }
 
-static void __devinit power_probe_common(struct of_device *dev, struct resource *res, unsigned int irq)
+static int __devinit power_probe(struct of_device *op, const struct of_device_id *match)
 {
-        power_reg = ioremap(res->start, 0x4);
+        struct resource *res = &op->resource[0];
+        unsigned int irq= op->irqs[0];
 
-        printk("power: Control reg at %p ... ", power_reg);
+        power_reg = of_ioremap(res, 0, 0x4, "power");
+
+        printk("%s: Control reg at %lx ... ",
+               op->node->name, res->start);
 
         poweroff_method = machine_halt;  /* able to use the standard halt */
 
-        if (has_button_interrupt(irq, dev->node)) {
+        if (has_button_interrupt(irq, op->node)) {
                 if (kernel_thread(powerd, NULL, CLONE_FS) < 0) {
                         printk("Failed to start power daemon.\n");
-                        return;
+                        return 0;
                 }
                 printk("powerd running.\n");
 
                 if (request_irq(irq,
-                                power_handler, SA_SHIRQ, "power", NULL) < 0)
+                                power_handler, 0, "power", NULL) < 0)
                         printk("power: Error, cannot register IRQ handler.\n");
         } else {
                 printk("not using powerd.\n");
         }
+
+        return 0;
 }
 
 static struct of_device_id power_match[] = {
@@ -145,44 +153,15 @@ static struct of_device_id power_match[] = {
         {},
 };
 
-static int __devinit ebus_power_probe(struct of_device *dev, const struct of_device_id *match)
-{
-        struct linux_ebus_device *edev = to_ebus_device(&dev->dev);
-        struct resource *res = &edev->resource[0];
-        unsigned int irq = edev->irqs[0];
-
-        power_probe_common(dev, res,irq);
-
-        return 0;
-}
-
-static struct of_platform_driver ebus_power_driver = {
-        .name           = "power",
-        .match_table    = power_match,
-        .probe          = ebus_power_probe,
-};
-
-static int __devinit isa_power_probe(struct of_device *dev, const struct of_device_id *match)
-{
-        struct sparc_isa_device *idev = to_isa_device(&dev->dev);
-        struct resource *res = &idev->resource;
-        unsigned int irq = idev->irq;
-
-        power_probe_common(dev, res,irq);
-
-        return 0;
-}
-
-static struct of_platform_driver isa_power_driver = {
+static struct of_platform_driver power_driver = {
         .name           = "power",
         .match_table    = power_match,
-        .probe          = isa_power_probe,
+        .probe          = power_probe,
 };
 
 void __init power_init(void)
 {
-        of_register_driver(&ebus_power_driver, &ebus_bus_type);
-        of_register_driver(&isa_power_driver, &isa_bus_type);
+        of_register_driver(&power_driver, &of_bus_type);
         return;
 }
 #endif /* CONFIG_PCI */
diff --git a/arch/sparc64/kernel/prom.c b/arch/sparc64/kernel/prom.c
index 8e87e7ea0325..8a70c52c0447 100644
--- a/arch/sparc64/kernel/prom.c
+++ b/arch/sparc64/kernel/prom.c
@@ -15,6 +15,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 
+#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -23,7 +24,11 @@
 #include <linux/module.h>
 
 #include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/oplib.h>
+#include <asm/irq.h>
+#include <asm/asi.h>
+#include <asm/upa.h>
 
 static struct device_node *allnodes;
 
@@ -190,6 +195,36 @@ int of_getintprop_default(struct device_node *np, const char *name, int def)
 }
 EXPORT_SYMBOL(of_getintprop_default);
 
+int of_n_addr_cells(struct device_node *np)
+{
+        int* ip;
+        do {
+                if (np->parent)
+                        np = np->parent;
+                ip = of_get_property(np, "#address-cells", NULL);
+                if (ip != NULL)
+                        return *ip;
+        } while (np->parent);
+        /* No #address-cells property for the root node, default to 2 */
+        return 2;
+}
+EXPORT_SYMBOL(of_n_addr_cells);
+
+int of_n_size_cells(struct device_node *np)
+{
+        int* ip;
+        do {
+                if (np->parent)
+                        np = np->parent;
+                ip = of_get_property(np, "#size-cells", NULL);
+                if (ip != NULL)
+                        return *ip;
+        } while (np->parent);
+        /* No #size-cells property for the root node, default to 1 */
+        return 1;
+}
+EXPORT_SYMBOL(of_n_size_cells);
+
 int of_set_property(struct device_node *dp, const char *name, void *val, int len)
 {
         struct property **prevp;
@@ -253,6 +288,754 @@ static void * __init prom_early_alloc(unsigned long size)
         return ret;
 }
 
+#ifdef CONFIG_PCI
+/* PSYCHO interrupt mapping support. */
+#define PSYCHO_IMAP_A_SLOT0     0x0c00UL
+#define PSYCHO_IMAP_B_SLOT0     0x0c20UL
+static unsigned long psycho_pcislot_imap_offset(unsigned long ino)
+{
+        unsigned int bus =  (ino & 0x10) >> 4;
+        unsigned int slot = (ino & 0x0c) >> 2;
+
+        if (bus == 0)
+                return PSYCHO_IMAP_A_SLOT0 + (slot * 8);
+        else
+                return PSYCHO_IMAP_B_SLOT0 + (slot * 8);
+}
+
+#define PSYCHO_IMAP_SCSI        0x1000UL
+#define PSYCHO_IMAP_ETH         0x1008UL
+#define PSYCHO_IMAP_BPP         0x1010UL
+#define PSYCHO_IMAP_AU_REC      0x1018UL
+#define PSYCHO_IMAP_AU_PLAY     0x1020UL
+#define PSYCHO_IMAP_PFAIL       0x1028UL
+#define PSYCHO_IMAP_KMS         0x1030UL
+#define PSYCHO_IMAP_FLPY        0x1038UL
+#define PSYCHO_IMAP_SHW         0x1040UL
+#define PSYCHO_IMAP_KBD         0x1048UL
+#define PSYCHO_IMAP_MS          0x1050UL
+#define PSYCHO_IMAP_SER         0x1058UL
+#define PSYCHO_IMAP_TIM0        0x1060UL
+#define PSYCHO_IMAP_TIM1        0x1068UL
+#define PSYCHO_IMAP_UE          0x1070UL
+#define PSYCHO_IMAP_CE          0x1078UL
+#define PSYCHO_IMAP_A_ERR       0x1080UL
+#define PSYCHO_IMAP_B_ERR       0x1088UL
+#define PSYCHO_IMAP_PMGMT       0x1090UL
+#define PSYCHO_IMAP_GFX         0x1098UL
+#define PSYCHO_IMAP_EUPA        0x10a0UL
+
+static unsigned long __psycho_onboard_imap_off[] = {
+/*0x20*/        PSYCHO_IMAP_SCSI,
+/*0x21*/        PSYCHO_IMAP_ETH,
+/*0x22*/        PSYCHO_IMAP_BPP,
+/*0x23*/        PSYCHO_IMAP_AU_REC,
+/*0x24*/        PSYCHO_IMAP_AU_PLAY,
+/*0x25*/        PSYCHO_IMAP_PFAIL,
+/*0x26*/        PSYCHO_IMAP_KMS,
+/*0x27*/        PSYCHO_IMAP_FLPY,
+/*0x28*/        PSYCHO_IMAP_SHW,
+/*0x29*/        PSYCHO_IMAP_KBD,
+/*0x2a*/        PSYCHO_IMAP_MS,
+/*0x2b*/        PSYCHO_IMAP_SER,
+/*0x2c*/        PSYCHO_IMAP_TIM0,
+/*0x2d*/        PSYCHO_IMAP_TIM1,
+/*0x2e*/        PSYCHO_IMAP_UE,
+/*0x2f*/        PSYCHO_IMAP_CE,
+/*0x30*/        PSYCHO_IMAP_A_ERR,
+/*0x31*/        PSYCHO_IMAP_B_ERR,
+/*0x32*/        PSYCHO_IMAP_PMGMT
+};
+#define PSYCHO_ONBOARD_IRQ_BASE         0x20
+#define PSYCHO_ONBOARD_IRQ_LAST         0x32
+#define psycho_onboard_imap_offset(__ino) \
+        __psycho_onboard_imap_off[(__ino) - PSYCHO_ONBOARD_IRQ_BASE]
+
+#define PSYCHO_ICLR_A_SLOT0     0x1400UL
+#define PSYCHO_ICLR_SCSI        0x1800UL
+
+#define psycho_iclr_offset(ino)                                       \
+        ((ino & 0x20) ? (PSYCHO_ICLR_SCSI + (((ino) & 0x1f) << 3)) :  \
+                        (PSYCHO_ICLR_A_SLOT0 + (((ino) & 0x1f)<<3)))
+
+static unsigned int psycho_irq_build(struct device_node *dp,
+                                     unsigned int ino,
+                                     void *_data)
+{
+        unsigned long controller_regs = (unsigned long) _data;
+        unsigned long imap, iclr;
+        unsigned long imap_off, iclr_off;
+        int inofixup = 0;
+
+        ino &= 0x3f;
+        if (ino < PSYCHO_ONBOARD_IRQ_BASE) {
+                /* PCI slot */
+                imap_off = psycho_pcislot_imap_offset(ino);
+        } else {
+                /* Onboard device */
+                if (ino > PSYCHO_ONBOARD_IRQ_LAST) {
+                        prom_printf("psycho_irq_build: Wacky INO [%x]\n", ino);
+                        prom_halt();
+                }
+                imap_off = psycho_onboard_imap_offset(ino);
+        }
+
+        /* Now build the IRQ bucket. */
+        imap = controller_regs + imap_off;
+        imap += 4;
+
+        iclr_off = psycho_iclr_offset(ino);
+        iclr = controller_regs + iclr_off;
+        iclr += 4;
+
+        if ((ino & 0x20) == 0)
+                inofixup = ino & 0x03;
+
+        return build_irq(inofixup, iclr, imap);
+}
+
+static void psycho_irq_trans_init(struct device_node *dp)
+{
+        struct linux_prom64_registers *regs;
+
+        dp->irq_trans = prom_early_alloc(sizeof(struct of_irq_controller));
+        dp->irq_trans->irq_build = psycho_irq_build;
+
+        regs = of_get_property(dp, "reg", NULL);
+        dp->irq_trans->data = (void *) regs[2].phys_addr;
+}
+
+#define sabre_read(__reg) \
+({      u64 __ret; \
+        __asm__ __volatile__("ldxa [%1] %2, %0" \
+                             : "=r" (__ret) \
+                             : "r" (__reg), "i" (ASI_PHYS_BYPASS_EC_E) \
+                             : "memory"); \
+        __ret; \
+})
+
+struct sabre_irq_data {
+        unsigned long controller_regs;
+        unsigned int pci_first_busno;
+};
+#define SABRE_CONFIGSPACE       0x001000000UL
+#define SABRE_WRSYNC            0x1c20UL
+
+#define SABRE_CONFIG_BASE(CONFIG_SPACE) \
+        (CONFIG_SPACE | (1UL << 24))
+#define SABRE_CONFIG_ENCODE(BUS, DEVFN, REG)    \
+        (((unsigned long)(BUS)   << 16) |       \
+         ((unsigned long)(DEVFN) << 8)  |       \
+         ((unsigned long)(REG)))
+
+/* When a device lives behind a bridge deeper in the PCI bus topology
+ * than APB, a special sequence must run to make sure all pending DMA
+ * transfers at the time of IRQ delivery are visible in the coherency
+ * domain by the cpu.  This sequence is to perform a read on the far
+ * side of the non-APB bridge, then perform a read of Sabre's DMA
+ * write-sync register.
+ */
+static void sabre_wsync_handler(unsigned int ino, void *_arg1, void *_arg2)
+{
+        unsigned int phys_hi = (unsigned int) (unsigned long) _arg1;
+        struct sabre_irq_data *irq_data = _arg2;
+        unsigned long controller_regs = irq_data->controller_regs;
+        unsigned long sync_reg = controller_regs + SABRE_WRSYNC;
+        unsigned long config_space = controller_regs + SABRE_CONFIGSPACE;
+        unsigned int bus, devfn;
+        u16 _unused;
+
+        config_space = SABRE_CONFIG_BASE(config_space);
+
+        bus = (phys_hi >> 16) & 0xff;
+        devfn = (phys_hi >> 8) & 0xff;
+
+        config_space |= SABRE_CONFIG_ENCODE(bus, devfn, 0x00);
+
+        __asm__ __volatile__("membar #Sync\n\t"
+                             "lduha [%1] %2, %0\n\t"
+                             "membar #Sync"
+                             : "=r" (_unused)
+                             : "r" ((u16 *) config_space),
+                               "i" (ASI_PHYS_BYPASS_EC_E_L)
+                             : "memory");
+
+        sabre_read(sync_reg);
+}
+
+#define SABRE_IMAP_A_SLOT0      0x0c00UL
+#define SABRE_IMAP_B_SLOT0      0x0c20UL
+#define SABRE_IMAP_SCSI         0x1000UL
+#define SABRE_IMAP_ETH          0x1008UL
+#define SABRE_IMAP_BPP          0x1010UL
+#define SABRE_IMAP_AU_REC       0x1018UL
+#define SABRE_IMAP_AU_PLAY      0x1020UL
+#define SABRE_IMAP_PFAIL        0x1028UL
+#define SABRE_IMAP_KMS          0x1030UL
+#define SABRE_IMAP_FLPY         0x1038UL
+#define SABRE_IMAP_SHW          0x1040UL
+#define SABRE_IMAP_KBD          0x1048UL
+#define SABRE_IMAP_MS           0x1050UL
+#define SABRE_IMAP_SER          0x1058UL
+#define SABRE_IMAP_UE           0x1070UL
+#define SABRE_IMAP_CE           0x1078UL
+#define SABRE_IMAP_PCIERR       0x1080UL
+#define SABRE_IMAP_GFX          0x1098UL
+#define SABRE_IMAP_EUPA         0x10a0UL
+#define SABRE_ICLR_A_SLOT0      0x1400UL
+#define SABRE_ICLR_B_SLOT0      0x1480UL
+#define SABRE_ICLR_SCSI         0x1800UL
+#define SABRE_ICLR_ETH          0x1808UL
+#define SABRE_ICLR_BPP          0x1810UL
+#define SABRE_ICLR_AU_REC       0x1818UL
+#define SABRE_ICLR_AU_PLAY      0x1820UL
+#define SABRE_ICLR_PFAIL        0x1828UL
+#define SABRE_ICLR_KMS          0x1830UL
+#define SABRE_ICLR_FLPY         0x1838UL
+#define SABRE_ICLR_SHW          0x1840UL
+#define SABRE_ICLR_KBD          0x1848UL
+#define SABRE_ICLR_MS           0x1850UL
+#define SABRE_ICLR_SER          0x1858UL
+#define SABRE_ICLR_UE           0x1870UL
+#define SABRE_ICLR_CE           0x1878UL
+#define SABRE_ICLR_PCIERR       0x1880UL
+
+static unsigned long sabre_pcislot_imap_offset(unsigned long ino)
+{
+        unsigned int bus =  (ino & 0x10) >> 4;
+        unsigned int slot = (ino & 0x0c) >> 2;
+
+        if (bus == 0)
+                return SABRE_IMAP_A_SLOT0 + (slot * 8);
+        else
+                return SABRE_IMAP_B_SLOT0 + (slot * 8);
+}
+
+static unsigned long __sabre_onboard_imap_off[] = {
+/*0x20*/        SABRE_IMAP_SCSI,
+/*0x21*/        SABRE_IMAP_ETH,
+/*0x22*/        SABRE_IMAP_BPP,
+/*0x23*/        SABRE_IMAP_AU_REC,
+/*0x24*/        SABRE_IMAP_AU_PLAY,
+/*0x25*/        SABRE_IMAP_PFAIL,
+/*0x26*/        SABRE_IMAP_KMS,
+/*0x27*/        SABRE_IMAP_FLPY,
+/*0x28*/        SABRE_IMAP_SHW,
+/*0x29*/        SABRE_IMAP_KBD,
+/*0x2a*/        SABRE_IMAP_MS,
+/*0x2b*/        SABRE_IMAP_SER,
+/*0x2c*/        0 /* reserved */,
+/*0x2d*/        0 /* reserved */,
+/*0x2e*/        SABRE_IMAP_UE,
+/*0x2f*/        SABRE_IMAP_CE,
+/*0x30*/        SABRE_IMAP_PCIERR,
+};
+#define SABRE_ONBOARD_IRQ_BASE          0x20
+#define SABRE_ONBOARD_IRQ_LAST          0x30
+#define sabre_onboard_imap_offset(__ino) \
+        __sabre_onboard_imap_off[(__ino) - SABRE_ONBOARD_IRQ_BASE]
+
+#define sabre_iclr_offset(ino)                                        \
+        ((ino & 0x20) ? (SABRE_ICLR_SCSI + (((ino) & 0x1f) << 3)) :  \
+                        (SABRE_ICLR_A_SLOT0 + (((ino) & 0x1f)<<3)))
+
+static unsigned int sabre_irq_build(struct device_node *dp,
+                                    unsigned int ino,
+                                    void *_data)
+{
+        struct sabre_irq_data *irq_data = _data;
+        unsigned long controller_regs = irq_data->controller_regs;
+        struct linux_prom_pci_registers *regs;
+        unsigned long imap, iclr;
+        unsigned long imap_off, iclr_off;
+        int inofixup = 0;
+        int virt_irq;
+
+        ino &= 0x3f;
+        if (ino < SABRE_ONBOARD_IRQ_BASE) {
+                /* PCI slot */
+                imap_off = sabre_pcislot_imap_offset(ino);
+        } else {
+                /* onboard device */
+                if (ino > SABRE_ONBOARD_IRQ_LAST) {
+                        prom_printf("sabre_irq_build: Wacky INO [%x]\n", ino);
+                        prom_halt();
+                }
+                imap_off = sabre_onboard_imap_offset(ino);
+        }
+
+        /* Now build the IRQ bucket. */
+        imap = controller_regs + imap_off;
+        imap += 4;
+
+        iclr_off = sabre_iclr_offset(ino);
+        iclr = controller_regs + iclr_off;
+        iclr += 4;
+
+        if ((ino & 0x20) == 0)
+                inofixup = ino & 0x03;
+
+        virt_irq = build_irq(inofixup, iclr, imap);
+
+        regs = of_get_property(dp, "reg", NULL);
+        if (regs &&
+            ((regs->phys_hi >> 16) & 0xff) != irq_data->pci_first_busno) {
+                irq_install_pre_handler(virt_irq,
+                                        sabre_wsync_handler,
+                                        (void *) (long) regs->phys_hi,
+                                        (void *)
+                                        controller_regs +
+                                        SABRE_WRSYNC);
+        }
+
+        return virt_irq;
+}
+
+static void sabre_irq_trans_init(struct device_node *dp)
+{
+        struct linux_prom64_registers *regs;
+        struct sabre_irq_data *irq_data;
+        u32 *busrange;
+
+        dp->irq_trans = prom_early_alloc(sizeof(struct of_irq_controller));
+        dp->irq_trans->irq_build = sabre_irq_build;
+
+        irq_data = prom_early_alloc(sizeof(struct sabre_irq_data));
+
+        regs = of_get_property(dp, "reg", NULL);
+        irq_data->controller_regs = regs[0].phys_addr;
+
+        busrange = of_get_property(dp, "bus-range", NULL);
+        irq_data->pci_first_busno = busrange[0];
+
+        dp->irq_trans->data = irq_data;
+}
+
+/* SCHIZO interrupt mapping support.  Unlike Psycho, for this controller the
+ * imap/iclr registers are per-PBM.
+ */
+#define SCHIZO_IMAP_BASE        0x1000UL
+#define SCHIZO_ICLR_BASE        0x1400UL
+
+static unsigned long schizo_imap_offset(unsigned long ino)
+{
+        return SCHIZO_IMAP_BASE + (ino * 8UL);
+}
+
+static unsigned long schizo_iclr_offset(unsigned long ino)
+{
+        return SCHIZO_ICLR_BASE + (ino * 8UL);
+}
+
+static unsigned long schizo_ino_to_iclr(unsigned long pbm_regs,
+                                        unsigned int ino)
+{
+        return pbm_regs + schizo_iclr_offset(ino) + 4;
+}
+
+static unsigned long schizo_ino_to_imap(unsigned long pbm_regs,
+                                        unsigned int ino)
+{
+        return pbm_regs + schizo_imap_offset(ino) + 4;
+}
+
+#define schizo_read(__reg) \
+({      u64 __ret; \
+        __asm__ __volatile__("ldxa [%1] %2, %0" \
+                             : "=r" (__ret) \
+                             : "r" (__reg), "i" (ASI_PHYS_BYPASS_EC_E) \
+                             : "memory"); \
+        __ret; \
+})
+#define schizo_write(__reg, __val) \
+        __asm__ __volatile__("stxa %0, [%1] %2" \
+                             : /* no outputs */ \
+                             : "r" (__val), "r" (__reg), \
+                               "i" (ASI_PHYS_BYPASS_EC_E) \
+                             : "memory")
+
+static void tomatillo_wsync_handler(unsigned int ino, void *_arg1, void *_arg2)
+{
+        unsigned long sync_reg = (unsigned long) _arg2;
+        u64 mask = 1UL << (ino & IMAP_INO);
+        u64 val;
+        int limit;
+
+        schizo_write(sync_reg, mask);
+
+        limit = 100000;
+        val = 0;
+        while (--limit) {
+                val = schizo_read(sync_reg);
+                if (!(val & mask))
+                        break;
+        }
+        if (limit <= 0) {
+                printk("tomatillo_wsync_handler: DMA won't sync [%lx:%lx]\n",
+                       val, mask);
+        }
+
+        if (_arg1) {
+                static unsigned char cacheline[64]
+                        __attribute__ ((aligned (64)));
+
+                __asm__ __volatile__("rd %%fprs, %0\n\t"
+                                     "or %0, %4, %1\n\t"
+                                     "wr %1, 0x0, %%fprs\n\t"
+                                     "stda %%f0, [%5] %6\n\t"
+                                     "wr %0, 0x0, %%fprs\n\t"
+                                     "membar #Sync"
+                                     : "=&r" (mask), "=&r" (val)
+                                     : "0" (mask), "1" (val),
+                                     "i" (FPRS_FEF), "r" (&cacheline[0]),
+                                     "i" (ASI_BLK_COMMIT_P));
+        }
+}
+
+struct schizo_irq_data {
+        unsigned long pbm_regs;
+        unsigned long sync_reg;
+        u32 portid;
+        int chip_version;
+};
+
+static unsigned int schizo_irq_build(struct device_node *dp,
+                                     unsigned int ino,
+                                     void *_data)
+{
+        struct schizo_irq_data *irq_data = _data;
+        unsigned long pbm_regs = irq_data->pbm_regs;
+        unsigned long imap, iclr;
+        int ign_fixup;
+        int virt_irq;
+        int is_tomatillo;
+
+        ino &= 0x3f;
+
+        /* Now build the IRQ bucket. */
+        imap = schizo_ino_to_imap(pbm_regs, ino);
+        iclr = schizo_ino_to_iclr(pbm_regs, ino);
+
+        /* On Schizo, no inofixup occurs.  This is because each
+         * INO has it's own IMAP register.  On Psycho and Sabre
+         * there is only one IMAP register for each PCI slot even
+         * though four different INOs can be generated by each
+         * PCI slot.
+         *
+         * But, for JBUS variants (essentially, Tomatillo), we have
+         * to fixup the lowest bit of the interrupt group number.
+         */
+        ign_fixup = 0;
+
+        is_tomatillo = (irq_data->sync_reg != 0UL);
+
+        if (is_tomatillo) {
+                if (irq_data->portid & 1)
+                        ign_fixup = (1 << 6);
+        }
+
+        virt_irq = build_irq(ign_fixup, iclr, imap);
+
+        if (is_tomatillo) {
+                irq_install_pre_handler(virt_irq,
+                                        tomatillo_wsync_handler,
+                                        ((irq_data->chip_version <= 4) ?
+                                         (void *) 1 : (void *) 0),
+                                        (void *) irq_data->sync_reg);
+        }
+
+        return virt_irq;
+}
+
+static void schizo_irq_trans_init(struct device_node *dp)
+{
+        struct linux_prom64_registers *regs;
+        struct schizo_irq_data *irq_data;
+
+        dp->irq_trans = prom_early_alloc(sizeof(struct of_irq_controller));
+        dp->irq_trans->irq_build = schizo_irq_build;
+
+        irq_data = prom_early_alloc(sizeof(struct schizo_irq_data));
+
+        regs = of_get_property(dp, "reg", NULL);
+        dp->irq_trans->data = irq_data;
+
+        irq_data->pbm_regs = regs[0].phys_addr;
+        irq_data->sync_reg = regs[3].phys_addr + 0x1a18UL;
+        irq_data->portid = of_getintprop_default(dp, "portid", 0);
+        irq_data->chip_version = of_getintprop_default(dp, "version#", 0);
+}
+
+static unsigned int pci_sun4v_irq_build(struct device_node *dp,
+                                        unsigned int devino,
+                                        void *_data)
+{
+        u32 devhandle = (u32) (unsigned long) _data;
+
+        return sun4v_build_irq(devhandle, devino);
+}
+
+static void pci_sun4v_irq_trans_init(struct device_node *dp)
+{
+        struct linux_prom64_registers *regs;
+
+        dp->irq_trans = prom_early_alloc(sizeof(struct of_irq_controller));
+        dp->irq_trans->irq_build = pci_sun4v_irq_build;
+
+        regs = of_get_property(dp, "reg", NULL);
+        dp->irq_trans->data = (void *) (unsigned long)
+                ((regs->phys_addr >> 32UL) & 0x0fffffff);
+}
+#endif /* CONFIG_PCI */
+
+#ifdef CONFIG_SBUS
+/* INO number to IMAP register offset for SYSIO external IRQ's.
+ * This should conform to both Sunfire/Wildfire server and Fusion
+ * desktop designs.
+ */
+#define SYSIO_IMAP_SLOT0        0x2c04UL
+#define SYSIO_IMAP_SLOT1        0x2c0cUL
+#define SYSIO_IMAP_SLOT2        0x2c14UL
+#define SYSIO_IMAP_SLOT3        0x2c1cUL
+#define SYSIO_IMAP_SCSI         0x3004UL
+#define SYSIO_IMAP_ETH          0x300cUL
+#define SYSIO_IMAP_BPP          0x3014UL
+#define SYSIO_IMAP_AUDIO        0x301cUL
+#define SYSIO_IMAP_PFAIL        0x3024UL
+#define SYSIO_IMAP_KMS          0x302cUL
+#define SYSIO_IMAP_FLPY         0x3034UL
+#define SYSIO_IMAP_SHW          0x303cUL
+#define SYSIO_IMAP_KBD          0x3044UL
+#define SYSIO_IMAP_MS           0x304cUL
+#define SYSIO_IMAP_SER          0x3054UL
+#define SYSIO_IMAP_TIM0         0x3064UL
+#define SYSIO_IMAP_TIM1         0x306cUL
+#define SYSIO_IMAP_UE           0x3074UL
+#define SYSIO_IMAP_CE           0x307cUL
+#define SYSIO_IMAP_SBERR        0x3084UL
+#define SYSIO_IMAP_PMGMT        0x308cUL
+#define SYSIO_IMAP_GFX          0x3094UL
+#define SYSIO_IMAP_EUPA         0x309cUL
+
+#define bogon     ((unsigned long) -1)
+static unsigned long sysio_irq_offsets[] = {
+        /* SBUS Slot 0 --> 3, level 1 --> 7 */
+        SYSIO_IMAP_SLOT0, SYSIO_IMAP_SLOT0, SYSIO_IMAP_SLOT0, SYSIO_IMAP_SLOT0,
+        SYSIO_IMAP_SLOT0, SYSIO_IMAP_SLOT0, SYSIO_IMAP_SLOT0, SYSIO_IMAP_SLOT0,
+        SYSIO_IMAP_SLOT1, SYSIO_IMAP_SLOT1, SYSIO_IMAP_SLOT1, SYSIO_IMAP_SLOT1,
+        SYSIO_IMAP_SLOT1, SYSIO_IMAP_SLOT1, SYSIO_IMAP_SLOT1, SYSIO_IMAP_SLOT1,
+        SYSIO_IMAP_SLOT2, SYSIO_IMAP_SLOT2, SYSIO_IMAP_SLOT2, SYSIO_IMAP_SLOT2,
+        SYSIO_IMAP_SLOT2, SYSIO_IMAP_SLOT2, SYSIO_IMAP_SLOT2, SYSIO_IMAP_SLOT2,
+        SYSIO_IMAP_SLOT3, SYSIO_IMAP_SLOT3, SYSIO_IMAP_SLOT3, SYSIO_IMAP_SLOT3,
+        SYSIO_IMAP_SLOT3, SYSIO_IMAP_SLOT3, SYSIO_IMAP_SLOT3, SYSIO_IMAP_SLOT3,
+
+        /* Onboard devices (not relevant/used on SunFire). */
+        SYSIO_IMAP_SCSI,
+        SYSIO_IMAP_ETH,
+        SYSIO_IMAP_BPP,
+        bogon,
+        SYSIO_IMAP_AUDIO,
+        SYSIO_IMAP_PFAIL,
+        bogon,
+        bogon,
+        SYSIO_IMAP_KMS,
+        SYSIO_IMAP_FLPY,
+        SYSIO_IMAP_SHW,
+        SYSIO_IMAP_KBD,
+        SYSIO_IMAP_MS,
+        SYSIO_IMAP_SER,
+        bogon,
+        bogon,
+        SYSIO_IMAP_TIM0,
+        SYSIO_IMAP_TIM1,
+        bogon,
+        bogon,
+        SYSIO_IMAP_UE,
+        SYSIO_IMAP_CE,
+        SYSIO_IMAP_SBERR,
+        SYSIO_IMAP_PMGMT,
+};
+
+#undef bogon
+
+#define NUM_SYSIO_OFFSETS ARRAY_SIZE(sysio_irq_offsets)
+
+/* Convert Interrupt Mapping register pointer to associated
+ * Interrupt Clear register pointer, SYSIO specific version.
+ */
+#define SYSIO_ICLR_UNUSED0      0x3400UL
+#define SYSIO_ICLR_SLOT0        0x340cUL
+#define SYSIO_ICLR_SLOT1        0x344cUL
+#define SYSIO_ICLR_SLOT2        0x348cUL
+#define SYSIO_ICLR_SLOT3        0x34ccUL
+static unsigned long sysio_imap_to_iclr(unsigned long imap)
+{
+        unsigned long diff = SYSIO_ICLR_UNUSED0 - SYSIO_IMAP_SLOT0;
+        return imap + diff;
+}
+
+static unsigned int sbus_of_build_irq(struct device_node *dp,
+                                      unsigned int ino,
+                                      void *_data)
+{
+        unsigned long reg_base = (unsigned long) _data;
+        struct linux_prom_registers *regs;
+        unsigned long imap, iclr;
+        int sbus_slot = 0;
+        int sbus_level = 0;
+
+        ino &= 0x3f;
+
+        regs = of_get_property(dp, "reg", NULL);
+        if (regs)
+                sbus_slot = regs->which_io;
+
+        if (ino < 0x20)
+                ino += (sbus_slot * 8);
+
+        imap = sysio_irq_offsets[ino];
+        if (imap == ((unsigned long)-1)) {
+                prom_printf("get_irq_translations: Bad SYSIO INO[%x]\n",
+                            ino);
+                prom_halt();
+        }
+        imap += reg_base;
+
+        /* SYSIO inconsistency.  For external SLOTS, we have to select
+         * the right ICLR register based upon the lower SBUS irq level
+         * bits.
+         */
+        if (ino >= 0x20) {
+                iclr = sysio_imap_to_iclr(imap);
+        } else {
+                sbus_level = ino & 0x7;
+
+                switch(sbus_slot) {
+                case 0:
+                        iclr = reg_base + SYSIO_ICLR_SLOT0;
+                        break;
+                case 1:
+                        iclr = reg_base + SYSIO_ICLR_SLOT1;
+                        break;
+                case 2:
+                        iclr = reg_base + SYSIO_ICLR_SLOT2;
+                        break;
+                default:
+                case 3:
+                        iclr = reg_base + SYSIO_ICLR_SLOT3;
+                        break;
+                };
+
+                iclr += ((unsigned long)sbus_level - 1UL) * 8UL;
+        }
+        return build_irq(sbus_level, iclr, imap);
+}
+
+static void sbus_irq_trans_init(struct device_node *dp)
+{
+        struct linux_prom64_registers *regs;
+
+        dp->irq_trans = prom_early_alloc(sizeof(struct of_irq_controller));
+        dp->irq_trans->irq_build = sbus_of_build_irq;
+
+        regs = of_get_property(dp, "reg", NULL);
+        dp->irq_trans->data = (void *) (unsigned long) regs->phys_addr;
+}
+#endif /* CONFIG_SBUS */
+
+
+static unsigned int central_build_irq(struct device_node *dp,
+                                      unsigned int ino,
+                                      void *_data)
+{
+        struct device_node *central_dp = _data;
+        struct of_device *central_op = of_find_device_by_node(central_dp);
+        struct resource *res;
+        unsigned long imap, iclr;
+        u32 tmp;
+
+        if (!strcmp(dp->name, "eeprom")) {
+                res = &central_op->resource[5];
+        } else if (!strcmp(dp->name, "zs")) {
+                res = &central_op->resource[4];
+        } else if (!strcmp(dp->name, "clock-board")) {
+                res = &central_op->resource[3];
+        } else {
+                return ino;
+        }
+
+        imap = res->start + 0x00UL;
+        iclr = res->start + 0x10UL;
+
+        /* Set the INO state to idle, and disable.  */
+        upa_writel(0, iclr);
+        upa_readl(iclr);
+
+        tmp = upa_readl(imap);
+        tmp &= ~0x80000000;
+        upa_writel(tmp, imap);
+
+        return build_irq(0, iclr, imap);
+}
+
+static void central_irq_trans_init(struct device_node *dp)
+{
+        dp->irq_trans = prom_early_alloc(sizeof(struct of_irq_controller));
+        dp->irq_trans->irq_build = central_build_irq;
+
+        dp->irq_trans->data = dp;
+}
+
+struct irq_trans {
+        const char *name;
+        void (*init)(struct device_node *);
+};
+
+#ifdef CONFIG_PCI
+static struct irq_trans pci_irq_trans_table[] = {
+        { "SUNW,sabre", sabre_irq_trans_init },
+        { "pci108e,a000", sabre_irq_trans_init },
+        { "pci108e,a001", sabre_irq_trans_init },
+        { "SUNW,psycho", psycho_irq_trans_init },
+        { "pci108e,8000", psycho_irq_trans_init },
+        { "SUNW,schizo", schizo_irq_trans_init },
+        { "pci108e,8001", schizo_irq_trans_init },
+        { "SUNW,schizo+", schizo_irq_trans_init },
+        { "pci108e,8002", schizo_irq_trans_init },
+        { "SUNW,tomatillo", schizo_irq_trans_init },
+        { "pci108e,a801", schizo_irq_trans_init },
+        { "SUNW,sun4v-pci", pci_sun4v_irq_trans_init },
+};
+#endif
+
+static void irq_trans_init(struct device_node *dp)
+{
+        const char *model;
+        int i;
+
+        model = of_get_property(dp, "model", NULL);
+        if (!model)
+                model = of_get_property(dp, "compatible", NULL);
+        if (!model)
+                return;
+
+#ifdef CONFIG_PCI
+        for (i = 0; i < ARRAY_SIZE(pci_irq_trans_table); i++) {
+                struct irq_trans *t = &pci_irq_trans_table[i];
+
+                if (!strcmp(model, t->name))
+                        return t->init(dp);
+        }
+#endif
+#ifdef CONFIG_SBUS
+        if (!strcmp(dp->name, "sbus") ||
+            !strcmp(dp->name, "sbi"))
+                return sbus_irq_trans_init(dp);
+#endif
+        if (!strcmp(dp->name, "central"))
+                return central_irq_trans_init(dp->child);
+}
+
 static int is_root_node(const struct device_node *dp)
 {
         if (!dp)
@@ -676,10 +1459,10 @@ static struct device_node * __init create_node(phandle node)
         dp->type = get_one_property(node, "device_type");
         dp->node = node;
 
-        /* Build interrupts later... */
-
         dp->properties = build_prop_list(node);
 
+        irq_trans_init(dp);
+
         return dp;
 }
 
diff --git a/arch/sparc64/kernel/sbus.c b/arch/sparc64/kernel/sbus.c
index ac05e0f692ef..ef68aa4fec65 100644
--- a/arch/sparc64/kernel/sbus.c
+++ b/arch/sparc64/kernel/sbus.c
@@ -1221,9 +1221,7 @@ static void __init sbus_iommu_init(int __node, struct sbus_bus *sbus)
 
         /* Now some Xfire specific grot... */
         if (this_is_starfire)
-                sbus->starfire_cookie = starfire_hookup(sbus->portid);
-        else
-                sbus->starfire_cookie = NULL;
+                starfire_hookup(sbus->portid);
 
         sysio_register_error_handlers(sbus);
 }
@@ -1269,8 +1267,6 @@ int __init sbus_arch_preinit(void)
 void __init sbus_arch_postinit(void)
 {
         extern void firetruck_init(void);
-        extern void clock_probe(void);
 
         firetruck_init();
-        clock_probe();
 }
diff --git a/arch/sparc64/kernel/starfire.c b/arch/sparc64/kernel/starfire.c
index ae859d40771e..b930fee7708a 100644
--- a/arch/sparc64/kernel/starfire.c
+++ b/arch/sparc64/kernel/starfire.c
@@ -54,7 +54,7 @@ struct starfire_irqinfo {
 static struct starfire_irqinfo *sflist = NULL;
 
 /* Beam me up Scott(McNeil)y... */
-void *starfire_hookup(int upaid)
+void starfire_hookup(int upaid)
 {
         struct starfire_irqinfo *p;
         unsigned long treg_base, hwmid, i;
@@ -81,8 +81,6 @@ void *starfire_hookup(int upaid)
         p->upaid = upaid;
         p->next = sflist;
         sflist = p;
-
-        return (void *) p;
 }
 
 unsigned int starfire_translate(unsigned long imap,
diff --git a/arch/sparc64/kernel/sys_sunos32.c b/arch/sparc64/kernel/sys_sunos32.c
index ae5b32f817f0..87ebdf858a3a 100644
--- a/arch/sparc64/kernel/sys_sunos32.c
+++ b/arch/sparc64/kernel/sys_sunos32.c
@@ -155,7 +155,7 @@ asmlinkage int sunos_brk(u32 baddr)
          * simple, it hopefully works in most obvious cases.. Easy to
          * fool it, but this should catch most mistakes.
          */
-        freepages = get_page_cache_size();
+        freepages = global_page_state(NR_FILE_PAGES);
         freepages >>= 1;
         freepages += nr_free_pages();
         freepages += nr_swap_pages;
diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c
index 348b82035561..5f3dd4d800cd 100644
--- a/arch/sparc64/kernel/time.c
+++ b/arch/sparc64/kernel/time.c
@@ -38,11 +38,8 @@
 #include <asm/timer.h>
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/sbus.h>
-#include <asm/fhc.h>
-#include <asm/pbm.h>
-#include <asm/ebus.h>
-#include <asm/isa.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/starfire.h>
 #include <asm/smp.h>
 #include <asm/sections.h>
@@ -770,237 +767,106 @@ static int __init clock_model_matches(char *model)
         return 1;
 }
 
-static void __init __clock_assign_common(void __iomem *addr, char *model)
+static int __devinit clock_probe(struct of_device *op, const struct of_device_id *match)
 {
-        if (model[5] == '0' && model[6] == '2') {
-                mstk48t02_regs = addr;
-        } else if(model[5] == '0' && model[6] == '8') {
-                mstk48t08_regs = addr;
-                mstk48t02_regs = mstk48t08_regs + MOSTEK_48T08_48T02;
-        } else {
-                mstk48t59_regs = addr;
-                mstk48t02_regs = mstk48t59_regs + MOSTEK_48T59_48T02;
-        }
-}
-
-static void __init clock_assign_clk_reg(struct linux_prom_registers *clk_reg,
-                                        char *model)
-{
-        unsigned long addr;
-
-        addr = ((unsigned long) clk_reg[0].phys_addr |
-                (((unsigned long) clk_reg[0].which_io) << 32UL));
-
-        __clock_assign_common((void __iomem *) addr, model);
-}
-
-static int __init clock_probe_central(void)
-{
-        struct linux_prom_registers clk_reg[2], *pr;
-        struct device_node *dp;
-        char *model;
+        struct device_node *dp = op->node;
+        char *model = of_get_property(dp, "model", NULL);
+        unsigned long size, flags;
+        void __iomem *regs;
 
-        if (!central_bus)
-                return 0;
-
-        /* Get Central FHC's prom node.  */
-        dp = central_bus->child->prom_node;
-
-        /* Then get the first child device below it.  */
-        dp = dp->child;
-
-        while (dp) {
-                model = of_get_property(dp, "model", NULL);
-                if (!model || !clock_model_matches(model))
-                        goto next_sibling;
-
-                pr = of_get_property(dp, "reg", NULL);
-                memcpy(clk_reg, pr, sizeof(clk_reg));
-
-                apply_fhc_ranges(central_bus->child, clk_reg, 1);
-                apply_central_ranges(central_bus, clk_reg, 1);
-
-                clock_assign_clk_reg(clk_reg, model);
-                return 1;
+        if (!model || !clock_model_matches(model))
+                return -ENODEV;
 
-        next_sibling:
-                dp = dp->sibling;
-        }
+        /* On an Enterprise system there can be multiple mostek clocks.
+         * We should only match the one that is on the central FHC bus.
+         */
+        if (!strcmp(dp->parent->name, "fhc") &&
+            strcmp(dp->parent->parent->name, "central") != 0)
+                return -ENODEV;
 
-        return 0;
-}
+        size = (op->resource[0].end - op->resource[0].start) + 1;
+        regs = of_ioremap(&op->resource[0], 0, size, "clock");
+        if (!regs)
+                return -ENOMEM;
 
-#ifdef CONFIG_PCI
-static void __init clock_isa_ebus_assign_regs(struct resource *res, char *model)
-{
         if (!strcmp(model, "ds1287") ||
             !strcmp(model, "m5819") ||
             !strcmp(model, "m5819p") ||
             !strcmp(model, "m5823")) {
-                ds1287_regs = res->start;
+                ds1287_regs = (unsigned long) regs;
+        } else if (model[5] == '0' && model[6] == '2') {
+                mstk48t02_regs = regs;
+        } else if(model[5] == '0' && model[6] == '8') {
+                mstk48t08_regs = regs;
+                mstk48t02_regs = mstk48t08_regs + MOSTEK_48T08_48T02;
         } else {
-                mstk48t59_regs = (void __iomem *) res->start;
+                mstk48t59_regs = regs;
                 mstk48t02_regs = mstk48t59_regs + MOSTEK_48T59_48T02;
         }
-}
-
-static int __init clock_probe_one_ebus_dev(struct linux_ebus_device *edev)
-{
-        struct device_node *dp = edev->prom_node;
-        char *model;
-
-        model = of_get_property(dp, "model", NULL);
-        if (!clock_model_matches(model))
-                return 0;
 
-        clock_isa_ebus_assign_regs(&edev->resource[0], model);
+        printk(KERN_INFO "%s: Clock regs at %p\n", dp->full_name, regs);
 
-        return 1;
-}
-
-static int __init clock_probe_ebus(void)
-{
-        struct linux_ebus *ebus;
+        local_irq_save(flags);
 
-        for_each_ebus(ebus) {
-                struct linux_ebus_device *edev;
+        if (mstk48t02_regs != NULL) {
+                /* Report a low battery voltage condition. */
+                if (has_low_battery())
+                        prom_printf("NVRAM: Low battery voltage!\n");
 
-                for_each_ebusdev(edev, ebus) {
-                        if (clock_probe_one_ebus_dev(edev))
-                                return 1;
-                }
+                /* Kick start the clock if it is completely stopped. */
+                if (mostek_read(mstk48t02_regs + MOSTEK_SEC) & MSTK_STOP)
+                        kick_start_clock();
         }
 
-        return 0;
-}
-
-static int __init clock_probe_one_isa_dev(struct sparc_isa_device *idev)
-{
-        struct device_node *dp = idev->prom_node;
-        char *model;
-
-        model = of_get_property(dp, "model", NULL);
-        if (!clock_model_matches(model))
-                return 0;
-
-        clock_isa_ebus_assign_regs(&idev->resource, model);
-
-        return 1;
-}
-
-static int __init clock_probe_isa(void)
-{
-        struct sparc_isa_bridge *isa_br;
-
-        for_each_isa(isa_br) {
-                struct sparc_isa_device *isa_dev;
-
-                for_each_isadev(isa_dev, isa_br) {
-                        if (clock_probe_one_isa_dev(isa_dev))
-                                return 1;
-                }
-        }
+        set_system_time();
+        
+        local_irq_restore(flags);
 
         return 0;
 }
-#endif /* CONFIG_PCI */
-
-#ifdef CONFIG_SBUS
-static int __init clock_probe_one_sbus_dev(struct sbus_bus *sbus, struct sbus_dev *sdev)
-{
-        struct resource *res;
-        char model[64];
-        void __iomem *addr;
-
-        prom_getstring(sdev->prom_node, "model", model, sizeof(model));
-        if (!clock_model_matches(model))
-                return 0;
-
-        res = &sdev->resource[0];
-        addr = sbus_ioremap(res, 0, 0x800UL, "eeprom");
 
-        __clock_assign_common(addr, model);
-
-        return 1;
-}
-
-static int __init clock_probe_sbus(void)
-{
-        struct sbus_bus *sbus;
-
-        for_each_sbus(sbus) {
-                struct sbus_dev *sdev;
-
-                for_each_sbusdev(sdev, sbus) {
-                        if (clock_probe_one_sbus_dev(sbus, sdev))
-                                return 1;
-                }
-        }
+static struct of_device_id clock_match[] = {
+        {
+                .name = "eeprom",
+        },
+        {
+                .name = "rtc",
+        },
+        {},
+};
 
-        return 0;
-}
-#endif
+static struct of_platform_driver clock_driver = {
+        .name           = "clock",
+        .match_table    = clock_match,
+        .probe          = clock_probe,
+};
 
-void __init clock_probe(void)
+static int __init clock_init(void)
 {
-        static int invoked;
-        unsigned long flags;
-
-        if (invoked)
-                return;
-        invoked = 1;
-
         if (this_is_starfire) {
                 xtime.tv_sec = starfire_get_time();
                 xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
                 set_normalized_timespec(&wall_to_monotonic,
                                         -xtime.tv_sec, -xtime.tv_nsec);
-                return;
+                return 0;
         }
         if (tlb_type == hypervisor) {
                 xtime.tv_sec = hypervisor_get_time();
                 xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
                 set_normalized_timespec(&wall_to_monotonic,
                                         -xtime.tv_sec, -xtime.tv_nsec);
-                return;
-        }
-
-        /* Check FHC Central then EBUSs then ISA bridges then SBUSs.
-         * That way we handle the presence of multiple properly.
-         *
-         * As a special case, machines with Central must provide the
-         * timer chip there.
-         */
-        if (!clock_probe_central() &&
-#ifdef CONFIG_PCI
-            !clock_probe_ebus() &&
-            !clock_probe_isa() &&
-#endif
-#ifdef CONFIG_SBUS
-            !clock_probe_sbus()
-#endif
-                ) {
-                printk(KERN_WARNING "No clock chip found.\n");
-                return;
-        }
-
-        local_irq_save(flags);
-
-        if (mstk48t02_regs != NULL) {
-                /* Report a low battery voltage condition. */
-                if (has_low_battery())
-                        prom_printf("NVRAM: Low battery voltage!\n");
-
-                /* Kick start the clock if it is completely stopped. */
-                if (mostek_read(mstk48t02_regs + MOSTEK_SEC) & MSTK_STOP)
-                        kick_start_clock();
+                return 0;
         }
 
-        set_system_time();
-        
-        local_irq_restore(flags);
+        return of_register_driver(&clock_driver, &of_bus_type);
 }
 
+/* Must be after subsys_initcall() so that busses are probed.  Must
+ * be before device_initcall() because things like the RTC driver
+ * need to see the clock registers.
+ */
+fs_initcall(clock_init);
+
 /* This is gets the master TICK_INT timer going. */
 static unsigned long sparc64_init_timers(void)
 {
diff --git a/arch/sparc64/kernel/unaligned.c b/arch/sparc64/kernel/unaligned.c
index bb2d68577855..a9b765271b85 100644
--- a/arch/sparc64/kernel/unaligned.c
+++ b/arch/sparc64/kernel/unaligned.c
@@ -20,6 +20,7 @@
 #include <linux/smp.h>
 #include <linux/smp_lock.h>
 #include <linux/bitops.h>
+#include <linux/kallsyms.h>
 #include <asm/fpumacro.h>
 
 /* #define DEBUG_MNA */
@@ -291,7 +292,8 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
         if (count < 5) {
                 last_time = jiffies;
                 count++;
-                printk("Kernel unaligned access at TPC[%lx]\n", regs->tpc);
+                printk("Kernel unaligned access at TPC[%lx] ", regs->tpc);
+                print_symbol("%s\n", regs->tpc);
         }
 
         if (!ok_for_kernel(insn) || dir == both) {
diff --git a/arch/um/Makefile-x86_64 b/arch/um/Makefile-x86_64
index dfd88b652fbe..dffd1184c956 100644
--- a/arch/um/Makefile-x86_64
+++ b/arch/um/Makefile-x86_64
@@ -6,9 +6,11 @@ START := 0x60000000
 
 #We #undef __x86_64__ for kernelspace, not for userspace where
 #it's needed for headers to work!
-CFLAGS += -U__$(SUBARCH)__ -fno-builtin
-USER_CFLAGS += -fno-builtin
+CFLAGS += -U__$(SUBARCH)__ -fno-builtin -m64
+USER_CFLAGS += -fno-builtin -m64
 CHECKFLAGS  += -m64
+AFLAGS += -m64
+LDFLAGS += -m elf_x86_64
 
 ELF_ARCH := i386:x86-64
 ELF_FORMAT := elf64-x86-64
@@ -16,3 +18,4 @@ ELF_FORMAT := elf64-x86-64
 # Not on all 64-bit distros /lib is a symlink to /lib64. PLD is an example.
 
 LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64
+LINK-y += -m64
diff --git a/arch/um/drivers/stderr_console.c b/arch/um/drivers/stderr_console.c
index 429ae8e6c7e5..6d2cf32a9e8f 100644
--- a/arch/um/drivers/stderr_console.c
+++ b/arch/um/drivers/stderr_console.c
@@ -8,10 +8,7 @@
 
 /*
  * Don't register by default -- as this registeres very early in the
- * boot process it becomes the default console.  And as this isn't a
- * real tty driver init isn't able to open /dev/console then.
- *
- * In most cases this isn't what you want ...
+ * boot process it becomes the default console.
  */
 static int use_stderr_console = 0;
 
@@ -43,3 +40,20 @@ static int stderr_setup(char *str)
         return 1;
 }
 __setup("stderr=", stderr_setup);
+
+/* The previous behavior of not unregistering led to /dev/console being
+ * impossible to open.  My FC5 filesystem started having init die, and the
+ * system panicing because of this.  Unregistering causes the real
+ * console to become the default console, and /dev/console can then be
+ * opened.  Making this an initcall makes this happen late enough that
+ * there is no added value in dumping everything to stderr, and the
+ * normal console is good enough to show you all available output.
+ */
+static int __init unregister_stderr(void)
+{
+        unregister_console(&stderr_console);
+
+        return 0;
+}
+
+__initcall(unregister_stderr);
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index c5c9885a8297..624ca238d1fd 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -152,7 +152,7 @@ void destroy_context_skas(struct mm_struct *mm)
                 free_page(mmu->id.stack);
                 pte_lock_deinit(virt_to_page(mmu->last_page_table));
                 pte_free_kernel((pte_t *) mmu->last_page_table);
-                dec_page_state(nr_page_table_pages);
+                dec_zone_page_state(virt_to_page(mmu->last_page_table), NR_PAGETABLE);
 #ifdef CONFIG_3_LEVEL_PGTABLES
                 pmd_free((pmd_t *) mmu->last_pmd);
 #endif
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
deleted file mode 100644
index 8fa2ae7f3026..000000000000
--- a/arch/um/kernel/time.c
+++ /dev/null
@@ -1,172 +0,0 @@
-/* 
- * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
-#include <sys/time.h>
-#include <signal.h>
-#include <errno.h>
-#include "user_util.h"
-#include "kern_util.h"
-#include "user.h"
-#include "process.h"
-#include "time_user.h"
-#include "kern_constants.h"
-#include "os.h"
-
-/* XXX This really needs to be declared and initialized in a kernel file since
- * it's in <linux/time.h>
- */
-extern struct timespec wall_to_monotonic;
-
-extern struct timeval xtime;
-
-struct timeval local_offset = { 0, 0 };
-
-void timer(void)
-{
-        gettimeofday(&xtime, NULL);
-        timeradd(&xtime, &local_offset, &xtime);
-}
-
-static void set_interval(int timer_type)
-{
-        int usec = 1000000/hz();
-        struct itimerval interval = ((struct itimerval) { { 0, usec },
-                                                          { 0, usec } });
-
-        if(setitimer(timer_type, &interval, NULL) == -1)
-                panic("setitimer failed - errno = %d\n", errno);
-}
-
-void enable_timer(void)
-{
-        set_interval(ITIMER_VIRTUAL);
-}
-
-void prepare_timer(void * ptr)
-{
-        int usec = 1000000/hz();
-        *(struct itimerval *)ptr = ((struct itimerval) { { 0, usec },
-                                                         { 0, usec }});
-}
-
-void disable_timer(void)
-{
-        struct itimerval disable = ((struct itimerval) { { 0, 0 }, { 0, 0 }});
-        if((setitimer(ITIMER_VIRTUAL, &disable, NULL) < 0) ||
-           (setitimer(ITIMER_REAL, &disable, NULL) < 0))
-                printk("disnable_timer - setitimer failed, errno = %d\n",
-                       errno);
-        /* If there are signals already queued, after unblocking ignore them */
-        set_handler(SIGALRM, SIG_IGN, 0, -1);
-        set_handler(SIGVTALRM, SIG_IGN, 0, -1);
-}
-
-void switch_timers(int to_real)
-{
-        struct itimerval disable = ((struct itimerval) { { 0, 0 }, { 0, 0 }});
-        struct itimerval enable = ((struct itimerval) { { 0, 1000000/hz() },
-                                                        { 0, 1000000/hz() }});
-        int old, new;
-
-        if(to_real){
-                old = ITIMER_VIRTUAL;
-                new = ITIMER_REAL;
-        }
-        else {
-                old = ITIMER_REAL;
-                new = ITIMER_VIRTUAL;
-        }
-
-        if((setitimer(old, &disable, NULL) < 0) ||
-           (setitimer(new, &enable, NULL)))
-                printk("switch_timers - setitimer failed, errno = %d\n",
-                       errno);
-}
-
-void uml_idle_timer(void)
-{
-        if(signal(SIGVTALRM, SIG_IGN) == SIG_ERR)
-                panic("Couldn't unset SIGVTALRM handler");
-        
-        set_handler(SIGALRM, (__sighandler_t) alarm_handler, 
-                    SA_RESTART, SIGUSR1, SIGIO, SIGWINCH, SIGVTALRM, -1);
-        set_interval(ITIMER_REAL);
-}
-
-extern void ktime_get_ts(struct timespec *ts);
-#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
-
-void time_init(void)
-{
-        struct timespec now;
-
-        if(signal(SIGVTALRM, boot_timer_handler) == SIG_ERR)
-                panic("Couldn't set SIGVTALRM handler");
-        set_interval(ITIMER_VIRTUAL);
-
-        do_posix_clock_monotonic_gettime(&now);
-        wall_to_monotonic.tv_sec = -now.tv_sec;
-        wall_to_monotonic.tv_nsec = -now.tv_nsec;
-}
-
-/* Defined in linux/ktimer.h, which can't be included here */
-#define clock_was_set()         do { } while (0)
-
-void do_gettimeofday(struct timeval *tv)
-{
-        unsigned long flags;
-
-        flags = time_lock();
-        gettimeofday(tv, NULL);
-        timeradd(tv, &local_offset, tv);
-        time_unlock(flags);
-        clock_was_set();
-}
-
-int do_settimeofday(struct timespec *tv)
-{
-        struct timeval now;
-        unsigned long flags;
-        struct timeval tv_in;
-
-        if ((unsigned long) tv->tv_nsec >= UM_NSEC_PER_SEC)
-                return -EINVAL;
-
-        tv_in.tv_sec = tv->tv_sec;
-        tv_in.tv_usec = tv->tv_nsec / 1000;
-
-        flags = time_lock();
-        gettimeofday(&now, NULL);
-        timersub(&tv_in, &now, &local_offset);
-        time_unlock(flags);
-
-        return(0);
-}
-
-void idle_sleep(int secs)
-{
-        struct timespec ts;
-
-        ts.tv_sec = secs;
-        ts.tv_nsec = 0;
-        nanosleep(&ts, NULL);
-}
-
-/* XXX This partly duplicates init_irq_signals */
-
-void user_time_init(void)
-{
-        set_handler(SIGVTALRM, (__sighandler_t) alarm_handler,
-                    SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGWINCH,
-                    SIGALRM, SIGUSR2, -1);
-        set_handler(SIGALRM, (__sighandler_t) alarm_handler,
-                    SA_ONSTACK | SA_RESTART, SIGUSR1, SIGIO, SIGWINCH,
-                    SIGVTALRM, SIGUSR2, -1);
-        set_interval(ITIMER_VIRTUAL);
-}
diff --git a/arch/um/kernel/time_kern.c b/arch/um/kernel/time_kern.c
index 87cdbc560d36..820fa3615a3f 100644
--- a/arch/um/kernel/time_kern.c
+++ b/arch/um/kernel/time_kern.c
@@ -96,11 +96,15 @@ void time_init_kern(void)
 
 void do_boot_timer_handler(struct sigcontext * sc)
 {
+        unsigned long flags;
         struct pt_regs regs;
 
         CHOOSE_MODE((void) (UPT_SC(&regs.regs) = sc),
                     (void) (regs.regs.skas.is_user = 0));
+
+        write_seqlock_irqsave(&xtime_lock, flags);
         do_timer(&regs);
+        write_sequnlock_irqrestore(&xtime_lock, flags);
 }
 
 static DEFINE_SPINLOCK(timer_spinlock);
@@ -125,25 +129,17 @@ irqreturn_t um_timer(int irq, void *dev, struct pt_regs *regs)
         unsigned long long nsecs;
         unsigned long flags;
 
+        write_seqlock_irqsave(&xtime_lock, flags);
+
         do_timer(regs);
 
-        write_seqlock_irqsave(&xtime_lock, flags);
         nsecs = get_time() + local_offset;
         xtime.tv_sec = nsecs / NSEC_PER_SEC;
         xtime.tv_nsec = nsecs - xtime.tv_sec * NSEC_PER_SEC;
-        write_sequnlock_irqrestore(&xtime_lock, flags);
-
-        return(IRQ_HANDLED);
-}
 
-long um_time(int __user *tloc)
-{
-        long ret = get_time() / NSEC_PER_SEC;
-
-        if((tloc != NULL) && put_user(ret, tloc))
-                return -EFAULT;
+        write_sequnlock_irqrestore(&xtime_lock, flags);
 
-        return ret;
+        return IRQ_HANDLED;
 }
 
 void do_gettimeofday(struct timeval *tv)
@@ -174,18 +170,6 @@ static inline void set_time(unsigned long long nsecs)
         clock_was_set();
 }
 
-long um_stime(int __user *tptr)
-{
-        int value;
-
-        if (get_user(value, tptr))
-                return -EFAULT;
-
-        set_time((unsigned long long) value * NSEC_PER_SEC);
-
-        return 0;
-}
-
 int do_settimeofday(struct timespec *tv)
 {
         set_time((unsigned long long) tv->tv_sec * NSEC_PER_SEC + tv->tv_nsec);
diff --git a/arch/um/kernel/vmlinux.lds.S b/arch/um/kernel/vmlinux.lds.S
index 1660a769674b..0a7d50ff9a4c 100644
--- a/arch/um/kernel/vmlinux.lds.S
+++ b/arch/um/kernel/vmlinux.lds.S
@@ -1,4 +1,6 @@
 #include <linux/config.h>
+/* in case the preprocessor is a 32bit one */
+#undef i386
 #ifdef CONFIG_LD_SCRIPT_STATIC
 #include "uml.lds.S"
 #else
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index c6432e729241..560c8063c77c 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -55,7 +55,7 @@ static void __init find_tempdir(void)
  */
 static int next(int fd, char *buf, int size, char c)
 {
-        int n;
+        int n, len;
         char *ptr;
 
         while((ptr = strchr(buf, c)) == NULL){
@@ -69,7 +69,17 @@ static int next(int fd, char *buf, int size, char c)
         }
 
         ptr++;
-        memmove(buf, ptr, strlen(ptr) + 1);
+        len = strlen(ptr);
+        memmove(buf, ptr, len + 1);
+
+        /* Refill the buffer so that if there's a partial string that we care
+         * about, it will be completed, and we can recognize it.
+         */
+        n = read(fd, &buf[len], size - len - 1);
+        if(n < 0)
+                return -errno;
+
+        buf[len + n] = '\0';
         return 1;
 }
 
@@ -200,8 +210,11 @@ int create_tmp_file(unsigned long long len)
                 exit(1);
         }
 
-        if (lseek64(fd, len, SEEK_SET) < 0) {
-                perror("os_seek_file");
+        /* Seek to len - 1 because writing a character there will
+         * increase the file size by one byte, to the desired length.
+         */
+        if (lseek64(fd, len - 1, SEEK_SET) < 0) {
+                perror("os_seek_file");
                 exit(1);
         }
 
diff --git a/arch/um/sys-i386/sys_call_table.S b/arch/um/sys-i386/sys_call_table.S
index 1ff61474b25c..2497554b7b95 100644
--- a/arch/um/sys-i386/sys_call_table.S
+++ b/arch/um/sys-i386/sys_call_table.S
@@ -7,8 +7,6 @@
 #define sys_vm86old sys_ni_syscall
 #define sys_vm86 sys_ni_syscall
 
-#define sys_stime um_stime
-#define sys_time um_time
 #define old_mmap old_mmap_i386
 
 #include "../../i386/kernel/syscall_table.S"
diff --git a/arch/um/sys-x86_64/syscall_table.c b/arch/um/sys-x86_64/syscall_table.c
index 34b2e842864f..3c4318165de0 100644
--- a/arch/um/sys-x86_64/syscall_table.c
+++ b/arch/um/sys-x86_64/syscall_table.c
@@ -20,12 +20,6 @@
 /*#define sys_set_thread_area sys_ni_syscall
 #define sys_get_thread_area sys_ni_syscall*/
 
-/* For __NR_time. The x86-64 name hopefully will change from sys_time64 to
- * sys_time (since the current situation is bogus). I've sent a patch to cleanup
- * this. Remove below the obsoleted line. */
-#define sys_time64 um_time
-#define sys_time um_time
-
 /* On UML we call it this way ("old" means it's not mmap2) */
 #define sys_mmap old_mmap
 /* On x86-64 sys_uname is actually sys_newuname plus a compatibility trick.
diff --git a/arch/x86_64/kernel/functionlist b/arch/x86_64/kernel/functionlist
index 2bcebdc3eedb..01fa23580c85 100644
--- a/arch/x86_64/kernel/functionlist
+++ b/arch/x86_64/kernel/functionlist
@@ -384,7 +384,6 @@
 *(.text.__end_that_request_first)
 *(.text.wake_up_bit)
 *(.text.unuse_mm)
-*(.text.skb_release_data)
 *(.text.shrink_icache_memory)
 *(.text.sched_balance_self)
 *(.text.__pmd_alloc)
diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index eee03a3876a3..fb83547f563e 100644
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -3117,9 +3117,9 @@ void submit_bio(int rw, struct bio *bio)
         BIO_BUG_ON(!bio->bi_io_vec);
         bio->bi_rw |= rw;
         if (rw & WRITE)
-                mod_page_state(pgpgout, count);
+                count_vm_events(PGPGOUT, count);
         else
-                mod_page_state(pgpgin, count);
+                count_vm_events(PGPGIN, count);
 
         if (unlikely(block_dump)) {
                 char b[BDEVNAME_SIZE];
diff --git a/drivers/acorn/block/Kconfig b/drivers/acorn/block/Kconfig
index 073add35e66f..a0ff25ea439f 100644
--- a/drivers/acorn/block/Kconfig
+++ b/drivers/acorn/block/Kconfig
@@ -3,7 +3,7 @@
 #
 
 menu "Acorn-specific block devices"
-        depends on ARCH_ACORN
+        depends on ARCH_ARC || ARCH_A5K
 
 config BLK_DEV_FD1772
         tristate "Old Archimedes floppy (1772) support"
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index fde9334059af..a486eb1f1640 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -1018,7 +1018,7 @@ he_init_irq(struct he_dev *he_dev)
         return 0;
 }
 
-static int __init
+static int __devinit
 he_start(struct atm_dev *dev)
 {
         struct he_dev *he_dev;
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index 0aabfc2a59d9..325325afabec 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -358,7 +358,7 @@ static const struct atmphy_ops idt77105_ops = {
 };
 
 
-int idt77105_init(struct atm_dev *dev)
+int __devinit idt77105_init(struct atm_dev *dev)
 {
         dev->phy = &idt77105_ops;
         return 0;
diff --git a/drivers/atm/idt77105.h b/drivers/atm/idt77105.h
index 8ba8218aaefe..3fd2bc899761 100644
--- a/drivers/atm/idt77105.h
+++ b/drivers/atm/idt77105.h
@@ -76,7 +76,7 @@
 #define IDT77105_CTRSEL_RHEC    0x01    /* W, Rx HEC Error Counter */
 
 #ifdef __KERNEL__
-int idt77105_init(struct atm_dev *dev) __init;
+int idt77105_init(struct atm_dev *dev);
 #endif
 
 /*
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 2e2e50e1167a..333a7bc609d2 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -2284,7 +2284,7 @@ static int reset_sar(struct atm_dev *dev)
 }  
           
           
-static int __init ia_init(struct atm_dev *dev)
+static int __devinit ia_init(struct atm_dev *dev)
 {  
         IADEV *iadev;  
         unsigned long real_base;
@@ -2480,7 +2480,7 @@ static void ia_free_rx(IADEV *iadev)
                           iadev->rx_dle_dma);  
 }
 
-static int __init ia_start(struct atm_dev *dev)
+static int __devinit ia_start(struct atm_dev *dev)
 {  
         IADEV *iadev;  
         int error;  
diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c
index b1d063cc4fbe..f04f39c00833 100644
--- a/drivers/atm/suni.c
+++ b/drivers/atm/suni.c
@@ -289,7 +289,7 @@ static const struct atmphy_ops suni_ops = {
 };
 
 
-int suni_init(struct atm_dev *dev)
+int __devinit suni_init(struct atm_dev *dev)
 {
         unsigned char mri;
 
diff --git a/drivers/base/node.c b/drivers/base/node.c
index eae2bdc183bb..d7de1753e094 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -40,24 +40,13 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
         int n;
         int nid = dev->id;
         struct sysinfo i;
-        struct page_state ps;
         unsigned long inactive;
         unsigned long active;
         unsigned long free;
 
         si_meminfo_node(&i, nid);
-        get_page_state_node(&ps, nid);
         __get_zone_counts(&active, &inactive, &free, NODE_DATA(nid));
 
-        /* Check for negative values in these approximate counters */
-        if ((long)ps.nr_dirty < 0)
-                ps.nr_dirty = 0;
-        if ((long)ps.nr_writeback < 0)
-                ps.nr_writeback = 0;
-        if ((long)ps.nr_mapped < 0)
-                ps.nr_mapped = 0;
-        if ((long)ps.nr_slab < 0)
-                ps.nr_slab = 0;
 
         n = sprintf(buf, "\n"
                        "Node %d MemTotal:     %8lu kB\n"
@@ -71,7 +60,12 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
                        "Node %d LowFree:      %8lu kB\n"
                        "Node %d Dirty:        %8lu kB\n"
                        "Node %d Writeback:    %8lu kB\n"
+                       "Node %d FilePages:    %8lu kB\n"
                        "Node %d Mapped:       %8lu kB\n"
+                       "Node %d AnonPages:    %8lu kB\n"
+                       "Node %d PageTables:   %8lu kB\n"
+                       "Node %d NFS Unstable: %8lu kB\n"
+                       "Node %d Bounce:       %8lu kB\n"
                        "Node %d Slab:         %8lu kB\n",
                        nid, K(i.totalram),
                        nid, K(i.freeram),
@@ -82,10 +76,15 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
                        nid, K(i.freehigh),
                        nid, K(i.totalram - i.totalhigh),
                        nid, K(i.freeram - i.freehigh),
-                       nid, K(ps.nr_dirty),
-                       nid, K(ps.nr_writeback),
-                       nid, K(ps.nr_mapped),
-                       nid, K(ps.nr_slab));
+                       nid, K(node_page_state(nid, NR_FILE_DIRTY)),
+                       nid, K(node_page_state(nid, NR_WRITEBACK)),
+                       nid, K(node_page_state(nid, NR_FILE_PAGES)),
+                       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
+                       nid, K(node_page_state(nid, NR_ANON_PAGES)),
+                       nid, K(node_page_state(nid, NR_PAGETABLE)),
+                       nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
+                       nid, K(node_page_state(nid, NR_BOUNCE)),
+                       nid, K(node_page_state(nid, NR_SLAB)));
         n += hugetlb_report_node_meminfo(nid, buf + n);
         return n;
 }
@@ -95,28 +94,6 @@ static SYSDEV_ATTR(meminfo, S_IRUGO, node_read_meminfo, NULL);
 
 static ssize_t node_read_numastat(struct sys_device * dev, char * buf)
 {
-        unsigned long numa_hit, numa_miss, interleave_hit, numa_foreign;
-        unsigned long local_node, other_node;
-        int i, cpu;
-        pg_data_t *pg = NODE_DATA(dev->id);
-        numa_hit = 0;
-        numa_miss = 0;
-        interleave_hit = 0;
-        numa_foreign = 0;
-        local_node = 0;
-        other_node = 0;
-        for (i = 0; i < MAX_NR_ZONES; i++) {
-                struct zone *z = &pg->node_zones[i];
-                for_each_online_cpu(cpu) {
-                        struct per_cpu_pageset *ps = zone_pcp(z,cpu);
-                        numa_hit += ps->numa_hit;
-                        numa_miss += ps->numa_miss;
-                        numa_foreign += ps->numa_foreign;
-                        interleave_hit += ps->interleave_hit;
-                        local_node += ps->local_node;
-                        other_node += ps->other_node;
-                }
-        }
         return sprintf(buf,
                        "numa_hit %lu\n"
                        "numa_miss %lu\n"
@@ -124,12 +101,12 @@ static ssize_t node_read_numastat(struct sys_device * dev, char * buf)
                        "interleave_hit %lu\n"
                        "local_node %lu\n"
                        "other_node %lu\n",
-                       numa_hit,
-                       numa_miss,
-                       numa_foreign,
-                       interleave_hit,
-                       local_node,
-                       other_node);
+                       node_page_state(dev->id, NUMA_HIT),
+                       node_page_state(dev->id, NUMA_MISS),
+                       node_page_state(dev->id, NUMA_FOREIGN),
+                       node_page_state(dev->id, NUMA_INTERLEAVE_HIT),
+                       node_page_state(dev->id, NUMA_LOCAL),
+                       node_page_state(dev->id, NUMA_OTHER));
 }
 static SYSDEV_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
 
diff --git a/drivers/cdrom/cm206.c b/drivers/cdrom/cm206.c
index 4ee288688fed..9b05ddd23141 100644
--- a/drivers/cdrom/cm206.c
+++ b/drivers/cdrom/cm206.c
@@ -914,7 +914,7 @@ static void seek(int lba)
         cd->dsb = wait_dsb();
 }
 
-uch bcdbin(unsigned char bcd)
+static uch bcdbin(unsigned char bcd)
 {                               /* stolen from mcd.c! */
         return (bcd >> 4) * 10 + (bcd & 0xf);
 }
@@ -1532,7 +1532,7 @@ static void __init parse_options(void)
         }
 }
 
-static int __cm206_init(void)
+static int __init __cm206_init(void)
 {
         parse_options();
 #if !defined(AUTO_PROBE_MODULE)
@@ -1593,8 +1593,3 @@ __setup("cm206=", cm206_setup);
 #endif                          /* !MODULE */
 MODULE_ALIAS_BLOCKDEV_MAJOR(CM206_CDROM_MAJOR);
 
-/*
- * Local variables:
- * compile-command: "gcc -D__KERNEL__ -I/usr/src/linux/include -Wall -Wstrict-prototypes -O2 -fomit-frame-pointer -pipe -fno-strength-reduce -m486 -DMODULE -DMODVERSIONS -include /usr/src/linux/include/linux/modversions.h  -c -o cm206.o cm206.c"
- * End:
- */
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index c74e5660a9b7..18c0dcf894cd 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -282,7 +282,6 @@ static char	*stli_brdnames[] = {
 
 /*****************************************************************************/
 
-#ifdef MODULE
 /*
  *      Define some string labels for arguments passed from the module
  *      load line. These allow for easy board definitions, and easy
@@ -381,8 +380,6 @@ MODULE_PARM_DESC(board2, "Board 2 config -> name[,ioaddr[,memaddr]");
 module_param_array(board3, charp, NULL, 0);
 MODULE_PARM_DESC(board3, "Board 3 config -> name[,ioaddr[,memaddr]");
 
-#endif
-
 /*
  *      Set up a default memory address table for EISA board probing.
  *      The default addresses are all bellow 1Mbyte, which has to be the
@@ -643,14 +640,8 @@ static unsigned int	stli_baudrates[] = {
  *      Prototype all functions in this driver!
  */
 
-#ifdef MODULE
-static void     stli_argbrds(void);
 static int      stli_parsebrd(stlconf_t *confp, char **argp);
-
-static unsigned long    stli_atol(char *str);
-#endif
-
-int             stli_init(void);
+static int      stli_init(void);
 static int      stli_open(struct tty_struct *tty, struct file *filp);
 static void     stli_close(struct tty_struct *tty, struct file *filp);
 static int      stli_write(struct tty_struct *tty, const unsigned char *buf, int count);
@@ -786,8 +777,6 @@ static int	stli_timeron;
 
 static struct class *istallion_class;
 
-#ifdef MODULE
-
 /*
  *      Loadable module initialization stuff.
  */
@@ -954,8 +943,6 @@ static int stli_parsebrd(stlconf_t *confp, char **argp)
         return(1);
 }
 
-#endif
-
 /*****************************************************************************/
 
 static int stli_open(struct tty_struct *tty, struct file *filp)
@@ -4694,7 +4681,7 @@ static struct tty_operations stli_ops = {
 
 /*****************************************************************************/
 
-int __init stli_init(void)
+static int __init stli_init(void)
 {
         int i;
         printk(KERN_INFO "%s: version %s\n", stli_drvtitle, stli_drvversion);
diff --git a/drivers/char/pc8736x_gpio.c b/drivers/char/pc8736x_gpio.c
index 1c706ccfdbb3..c860de6a6fde 100644
--- a/drivers/char/pc8736x_gpio.c
+++ b/drivers/char/pc8736x_gpio.c
@@ -319,9 +319,10 @@ static int __init pc8736x_gpio_init(void)
         return 0;
 
 undo_platform_dev_add:
-        platform_device_put(pdev);
+        platform_device_del(pdev);
 undo_platform_dev_alloc:
-        kfree(pdev);
+        platform_device_put(pdev);
+
         return rc;
 }
 
diff --git a/drivers/char/scx200_gpio.c b/drivers/char/scx200_gpio.c
index 5a280a330401..45083e5dd23b 100644
--- a/drivers/char/scx200_gpio.c
+++ b/drivers/char/scx200_gpio.c
@@ -126,9 +126,10 @@ static int __init scx200_gpio_init(void)
 undo_chrdev_region:
         unregister_chrdev_region(dev, num_pins);
 undo_platform_device_add:
-        platform_device_put(pdev);
+        platform_device_del(pdev);
 undo_malloc:
-        kfree(pdev);
+        platform_device_put(pdev);
+
         return rc;
 }
 
@@ -136,7 +137,6 @@ static void __exit scx200_gpio_cleanup(void)
 {
         kfree(scx200_devices);
         unregister_chrdev_region(MKDEV(major, 0), num_pins);
-        platform_device_put(pdev);
         platform_device_unregister(pdev);
         /* kfree(pdev); */
 }
diff --git a/drivers/edac/amd76x_edac.c b/drivers/edac/amd76x_edac.c
index 53423ad6d4a3..702141c5501b 100644
--- a/drivers/edac/amd76x_edac.c
+++ b/drivers/edac/amd76x_edac.c
@@ -20,6 +20,9 @@
 #include <linux/slab.h>
 #include "edac_mc.h"
 
+#define AMD76X_REVISION " Ver: 2.0.0 "  __DATE__
+
+
 #define amd76x_printk(level, fmt, arg...) \
         edac_printk(level, "amd76x", fmt, ##arg)
 
@@ -102,15 +105,18 @@ static const struct amd76x_dev_info amd76x_devs[] = {
 static void amd76x_get_error_info(struct mem_ctl_info *mci,
                 struct amd76x_error_info *info)
 {
-        pci_read_config_dword(mci->pdev, AMD76X_ECC_MODE_STATUS,
+        struct pci_dev *pdev;
+
+        pdev = to_pci_dev(mci->dev);
+        pci_read_config_dword(pdev, AMD76X_ECC_MODE_STATUS,
                                 &info->ecc_mode_status);
 
         if (info->ecc_mode_status & BIT(8))
-                pci_write_bits32(mci->pdev, AMD76X_ECC_MODE_STATUS,
+                pci_write_bits32(pdev, AMD76X_ECC_MODE_STATUS,
                                 (u32) BIT(8), (u32) BIT(8));
 
         if (info->ecc_mode_status & BIT(9))
-                pci_write_bits32(mci->pdev, AMD76X_ECC_MODE_STATUS,
+                pci_write_bits32(pdev, AMD76X_ECC_MODE_STATUS,
                                 (u32) BIT(9), (u32) BIT(9));
 }
 
@@ -176,6 +182,38 @@ static void amd76x_check(struct mem_ctl_info *mci)
         amd76x_process_error_info(mci, &info, 1);
 }
 
+static void amd76x_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev,
+                enum edac_type edac_mode)
+{
+        struct csrow_info *csrow;
+        u32 mba, mba_base, mba_mask, dms;
+        int index;
+
+        for (index = 0; index < mci->nr_csrows; index++) {
+                csrow = &mci->csrows[index];
+
+                /* find the DRAM Chip Select Base address and mask */
+                pci_read_config_dword(pdev,
+                                      AMD76X_MEM_BASE_ADDR + (index * 4),
+                                      &mba);
+
+                if (!(mba & BIT(0)))
+                        continue;
+
+                mba_base = mba & 0xff800000UL;
+                mba_mask = ((mba & 0xff80) << 16) | 0x7fffffUL;
+                pci_read_config_dword(pdev, AMD76X_DRAM_MODE_STATUS, &dms);
+                csrow->first_page = mba_base >> PAGE_SHIFT;
+                csrow->nr_pages = (mba_mask + 1) >> PAGE_SHIFT;
+                csrow->last_page = csrow->first_page + csrow->nr_pages - 1;
+                csrow->page_mask = mba_mask >> PAGE_SHIFT;
+                csrow->grain = csrow->nr_pages << PAGE_SHIFT;
+                csrow->mtype = MEM_RDDR;
+                csrow->dtype = ((dms >> index) & 0x1) ? DEV_X4 : DEV_UNKNOWN;
+                csrow->edac_mode = edac_mode;
+        }
+}
+
 /**
  *      amd76x_probe1   -       Perform set up for detected device
  *      @pdev; PCI device detected
@@ -187,15 +225,13 @@ static void amd76x_check(struct mem_ctl_info *mci)
  */
 static int amd76x_probe1(struct pci_dev *pdev, int dev_idx)
 {
-        int rc = -ENODEV;
-        int index;
-        struct mem_ctl_info *mci = NULL;
-        enum edac_type ems_modes[] = {
+        static const enum edac_type ems_modes[] = {
                 EDAC_NONE,
                 EDAC_EC,
                 EDAC_SECDED,
                 EDAC_SECDED
         };
+        struct mem_ctl_info *mci = NULL;
         u32 ems;
         u32 ems_mode;
         struct amd76x_error_info discard;
@@ -206,53 +242,28 @@ static int amd76x_probe1(struct pci_dev *pdev, int dev_idx)
         mci = edac_mc_alloc(0, AMD76X_NR_CSROWS, AMD76X_NR_CHANS);
 
         if (mci == NULL) {
-                rc = -ENOMEM;
-                goto fail;
+                return -ENOMEM;
         }
 
         debugf0("%s(): mci = %p\n", __func__, mci);
-        mci->pdev = pdev;
+        mci->dev = &pdev->dev;
         mci->mtype_cap = MEM_FLAG_RDDR;
         mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_EC | EDAC_FLAG_SECDED;
         mci->edac_cap = ems_mode ?
                         (EDAC_FLAG_EC | EDAC_FLAG_SECDED) : EDAC_FLAG_NONE;
         mci->mod_name = EDAC_MOD_STR;
-        mci->mod_ver = "$Revision: 1.4.2.5 $";
+        mci->mod_ver = AMD76X_REVISION;
         mci->ctl_name = amd76x_devs[dev_idx].ctl_name;
         mci->edac_check = amd76x_check;
         mci->ctl_page_to_phys = NULL;
 
-        for (index = 0; index < mci->nr_csrows; index++) {
-                struct csrow_info *csrow = &mci->csrows[index];
-                u32 mba;
-                u32 mba_base;
-                u32 mba_mask;
-                u32 dms;
-
-                /* find the DRAM Chip Select Base address and mask */
-                pci_read_config_dword(mci->pdev,
-                                AMD76X_MEM_BASE_ADDR + (index * 4), &mba);
-
-                if (!(mba & BIT(0)))
-                        continue;
-
-                mba_base = mba & 0xff800000UL;
-                mba_mask = ((mba & 0xff80) << 16) | 0x7fffffUL;
-                pci_read_config_dword(mci->pdev, AMD76X_DRAM_MODE_STATUS,
-                                &dms);
-                csrow->first_page = mba_base >> PAGE_SHIFT;
-                csrow->nr_pages = (mba_mask + 1) >> PAGE_SHIFT;
-                csrow->last_page = csrow->first_page + csrow->nr_pages - 1;
-                csrow->page_mask = mba_mask >> PAGE_SHIFT;
-                csrow->grain = csrow->nr_pages << PAGE_SHIFT;
-                csrow->mtype = MEM_RDDR;
-                csrow->dtype = ((dms >> index) & 0x1) ? DEV_X4 : DEV_UNKNOWN;
-                csrow->edac_mode = ems_modes[ems_mode];
-        }
-
+        amd76x_init_csrows(mci, pdev, ems_modes[ems_mode]);
         amd76x_get_error_info(mci, &discard);  /* clear counters */
 
-        if (edac_mc_add_mc(mci)) {
+        /* Here we assume that we will never see multiple instances of this
+         * type of memory controller.  The ID is therefore hardcoded to 0.
+         */
+        if (edac_mc_add_mc(mci,0)) {
                 debugf3("%s(): failed edac_mc_add_mc()\n", __func__);
                 goto fail;
         }
@@ -262,9 +273,8 @@ static int amd76x_probe1(struct pci_dev *pdev, int dev_idx)
         return 0;
 
 fail:
-        if (mci != NULL)
-                edac_mc_free(mci);
-        return rc;
+        edac_mc_free(mci);
+        return -ENODEV;
 }
 
 /* returns count (>= 0), or negative on error */
@@ -291,7 +301,7 @@ static void __devexit amd76x_remove_one(struct pci_dev *pdev)
 
         debugf0("%s()\n", __func__);
 
-        if ((mci = edac_mc_del_mc(pdev)) == NULL)
+        if ((mci = edac_mc_del_mc(&pdev->dev)) == NULL)
                 return;
 
         edac_mc_free(mci);
diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c
index fce31936e6d7..5351a76739e5 100644
--- a/drivers/edac/e752x_edac.c
+++ b/drivers/edac/e752x_edac.c
@@ -25,6 +25,8 @@
 #include <linux/slab.h>
 #include "edac_mc.h"
 
+#define E752X_REVISION  " Ver: 2.0.0 " __DATE__
+
 static int force_function_unhide;
 
 #define e752x_printk(level, fmt, arg...) \
@@ -763,22 +765,174 @@ static void e752x_check(struct mem_ctl_info *mci)
         e752x_process_error_info(mci, &info, 1);
 }
 
-static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
+/* Return 1 if dual channel mode is active.  Else return 0. */
+static inline int dual_channel_active(u16 ddrcsr)
+{
+        return (((ddrcsr >> 12) & 3) == 3);
+}
+
+static void e752x_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev,
+                u16 ddrcsr)
+{
+        struct csrow_info *csrow;
+        unsigned long last_cumul_size;
+        int index, mem_dev, drc_chan;
+        int drc_drbg;  /* DRB granularity 0=64mb, 1=128mb */
+        int drc_ddim;  /* DRAM Data Integrity Mode 0=none, 2=edac */
+        u8 value;
+        u32 dra, drc, cumul_size;
+
+        pci_read_config_dword(pdev, E752X_DRA, &dra);
+        pci_read_config_dword(pdev, E752X_DRC, &drc);
+        drc_chan = dual_channel_active(ddrcsr);
+        drc_drbg = drc_chan + 1;  /* 128 in dual mode, 64 in single */
+        drc_ddim = (drc >> 20) & 0x3;
+
+        /* The dram row boundary (DRB) reg values are boundary address for
+         * each DRAM row with a granularity of 64 or 128MB (single/dual
+         * channel operation).  DRB regs are cumulative; therefore DRB7 will
+         * contain the total memory contained in all eight rows.
+         */
+        for (last_cumul_size = index = 0; index < mci->nr_csrows; index++) {
+                /* mem_dev 0=x8, 1=x4 */
+                mem_dev = (dra >> (index * 4 + 2)) & 0x3;
+                csrow = &mci->csrows[index];
+
+                mem_dev = (mem_dev == 2);
+                pci_read_config_byte(pdev, E752X_DRB + index, &value);
+                /* convert a 128 or 64 MiB DRB to a page size. */
+                cumul_size = value << (25 + drc_drbg - PAGE_SHIFT);
+                debugf3("%s(): (%d) cumul_size 0x%x\n", __func__, index,
+                        cumul_size);
+                if (cumul_size == last_cumul_size)
+                        continue;       /* not populated */
+
+                csrow->first_page = last_cumul_size;
+                csrow->last_page = cumul_size - 1;
+                csrow->nr_pages = cumul_size - last_cumul_size;
+                last_cumul_size = cumul_size;
+                csrow->grain = 1 << 12; /* 4KiB - resolution of CELOG */
+                csrow->mtype = MEM_RDDR;        /* only one type supported */
+                csrow->dtype = mem_dev ? DEV_X4 : DEV_X8;
+
+                /*
+                 * if single channel or x8 devices then SECDED
+                 * if dual channel and x4 then S4ECD4ED
+                 */
+                if (drc_ddim) {
+                        if (drc_chan && mem_dev) {
+                                csrow->edac_mode = EDAC_S4ECD4ED;
+                                mci->edac_cap |= EDAC_FLAG_S4ECD4ED;
+                        } else {
+                                csrow->edac_mode = EDAC_SECDED;
+                                mci->edac_cap |= EDAC_FLAG_SECDED;
+                        }
+                } else
+                        csrow->edac_mode = EDAC_NONE;
+        }
+}
+
+static void e752x_init_mem_map_table(struct pci_dev *pdev,
+                struct e752x_pvt *pvt)
 {
-        int rc = -ENODEV;
         int index;
+        u8 value, last, row, stat8;
+
+        last = 0;
+        row = 0;
+
+        for (index = 0; index < 8; index += 2) {
+                pci_read_config_byte(pdev, E752X_DRB + index, &value);
+                /* test if there is a dimm in this slot */
+                if (value == last) {
+                        /* no dimm in the slot, so flag it as empty */
+                        pvt->map[index] = 0xff;
+                        pvt->map[index + 1] = 0xff;
+                } else {        /* there is a dimm in the slot */
+                        pvt->map[index] = row;
+                        row++;
+                        last = value;
+                        /* test the next value to see if the dimm is double
+                         * sided
+                         */
+                        pci_read_config_byte(pdev, E752X_DRB + index + 1,
+                                             &value);
+                        pvt->map[index + 1] = (value == last) ?
+                            0xff :      /* the dimm is single sided,
+                                           so flag as empty */
+                            row;        /* this is a double sided dimm
+                                           to save the next row # */
+                        row++;
+                        last = value;
+                }
+        }
+
+        /* set the map type.  1 = normal, 0 = reversed */
+        pci_read_config_byte(pdev, E752X_DRM, &stat8);
+        pvt->map_type = ((stat8 & 0x0f) > ((stat8 >> 4) & 0x0f));
+}
+
+/* Return 0 on success or 1 on failure. */
+static int e752x_get_devs(struct pci_dev *pdev, int dev_idx,
+                struct e752x_pvt *pvt)
+{
+        struct pci_dev *dev;
+
+        pvt->bridge_ck = pci_get_device(PCI_VENDOR_ID_INTEL,
+                                        pvt->dev_info->err_dev,
+                                        pvt->bridge_ck);
+
+        if (pvt->bridge_ck == NULL)
+                pvt->bridge_ck = pci_scan_single_device(pdev->bus,
+                                                        PCI_DEVFN(0, 1));
+
+        if (pvt->bridge_ck == NULL) {
+                e752x_printk(KERN_ERR, "error reporting device not found:"
+                       "vendor %x device 0x%x (broken BIOS?)\n",
+                       PCI_VENDOR_ID_INTEL, e752x_devs[dev_idx].err_dev);
+                return 1;
+        }
+
+        dev = pci_get_device(PCI_VENDOR_ID_INTEL, e752x_devs[dev_idx].ctl_dev,
+                             NULL);
+
+        if (dev == NULL)
+                goto fail;
+
+        pvt->dev_d0f0 = dev;
+        pvt->dev_d0f1 = pci_dev_get(pvt->bridge_ck);
+
+        return 0;
+
+fail:
+        pci_dev_put(pvt->bridge_ck);
+        return 1;
+}
+
+static void e752x_init_error_reporting_regs(struct e752x_pvt *pvt)
+{
+        struct pci_dev *dev;
+
+        dev = pvt->dev_d0f1;
+        /* Turn off error disable & SMI in case the BIOS turned it on */
+        pci_write_config_byte(dev, E752X_HI_ERRMASK, 0x00);
+        pci_write_config_byte(dev, E752X_HI_SMICMD, 0x00);
+        pci_write_config_word(dev, E752X_SYSBUS_ERRMASK, 0x00);
+        pci_write_config_word(dev, E752X_SYSBUS_SMICMD, 0x00);
+        pci_write_config_byte(dev, E752X_BUF_ERRMASK, 0x00);
+        pci_write_config_byte(dev, E752X_BUF_SMICMD, 0x00);
+        pci_write_config_byte(dev, E752X_DRAM_ERRMASK, 0x00);
+        pci_write_config_byte(dev, E752X_DRAM_SMICMD, 0x00);
+}
+
+static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
+{
         u16 pci_data;
         u8 stat8;
-        struct mem_ctl_info *mci = NULL;
-        struct e752x_pvt *pvt = NULL;
+        struct mem_ctl_info *mci;
+        struct e752x_pvt *pvt;
         u16 ddrcsr;
-        u32 drc;
         int drc_chan;   /* Number of channels 0=1chan,1=2chan */
-        int drc_drbg;   /* DRB granularity 0=64mb, 1=128mb */
-        int drc_ddim;   /* DRAM Data Integrity Mode 0=none,2=edac */
-        u32 dra;
-        unsigned long last_cumul_size;
-        struct pci_dev *dev = NULL;
         struct e752x_error_info discard;
 
         debugf0("%s(): mci\n", __func__);
@@ -792,25 +946,20 @@ static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
         if (!force_function_unhide && !(stat8 & (1 << 5))) {
                 printk(KERN_INFO "Contact your BIOS vendor to see if the "
                         "E752x error registers can be safely un-hidden\n");
-                goto fail;
+                return -ENOMEM;
         }
         stat8 |= (1 << 5);
         pci_write_config_byte(pdev, E752X_DEVPRES1, stat8);
 
-        /* need to find out the number of channels */
-        pci_read_config_dword(pdev, E752X_DRC, &drc);
         pci_read_config_word(pdev, E752X_DDRCSR, &ddrcsr);
         /* FIXME: should check >>12 or 0xf, true for all? */
         /* Dual channel = 1, Single channel = 0 */
-        drc_chan = (((ddrcsr >> 12) & 3) == 3);
-        drc_drbg = drc_chan + 1;        /* 128 in dual mode, 64 in single */
-        drc_ddim = (drc >> 20) & 0x3;
+        drc_chan = dual_channel_active(ddrcsr);
 
         mci = edac_mc_alloc(sizeof(*pvt), E752X_NR_CSROWS, drc_chan + 1);
 
         if (mci == NULL) {
-                rc = -ENOMEM;
-                goto fail;
+                return -ENOMEM;
         }
 
         debugf3("%s(): init mci\n", __func__);
@@ -819,159 +968,54 @@ static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
             EDAC_FLAG_S4ECD4ED;
         /* FIXME - what if different memory types are in different csrows? */
         mci->mod_name = EDAC_MOD_STR;
-        mci->mod_ver = "$Revision: 1.5.2.11 $";
-        mci->pdev = pdev;
+        mci->mod_ver = E752X_REVISION;
+        mci->dev = &pdev->dev;
 
         debugf3("%s(): init pvt\n", __func__);
         pvt = (struct e752x_pvt *) mci->pvt_info;
         pvt->dev_info = &e752x_devs[dev_idx];
-        pvt->bridge_ck = pci_get_device(PCI_VENDOR_ID_INTEL,
-                                        pvt->dev_info->err_dev,
-                                        pvt->bridge_ck);
-
-        if (pvt->bridge_ck == NULL)
-                pvt->bridge_ck = pci_scan_single_device(pdev->bus,
-                                        PCI_DEVFN(0, 1));
+        pvt->mc_symmetric = ((ddrcsr & 0x10) != 0);
 
-        if (pvt->bridge_ck == NULL) {
-                e752x_printk(KERN_ERR, "error reporting device not found:"
-                        "vendor %x device 0x%x (broken BIOS?)\n",
-                        PCI_VENDOR_ID_INTEL, e752x_devs[dev_idx].err_dev);
-                goto fail;
+        if (e752x_get_devs(pdev, dev_idx, pvt)) {
+                edac_mc_free(mci);
+                return -ENODEV;
         }
 
-        pvt->mc_symmetric = ((ddrcsr & 0x10) != 0);
         debugf3("%s(): more mci init\n", __func__);
         mci->ctl_name = pvt->dev_info->ctl_name;
         mci->edac_check = e752x_check;
         mci->ctl_page_to_phys = ctl_page_to_phys;
 
-        /* find out the device types */
-        pci_read_config_dword(pdev, E752X_DRA, &dra);
-
-        /*
-         * The dram row boundary (DRB) reg values are boundary address for
-         * each DRAM row with a granularity of 64 or 128MB (single/dual
-         * channel operation).  DRB regs are cumulative; therefore DRB7 will
-         * contain the total memory contained in all eight rows.
-         */
-        for (last_cumul_size = index = 0; index < mci->nr_csrows; index++) {
-                u8 value;
-                u32 cumul_size;
-
-                /* mem_dev 0=x8, 1=x4 */
-                int mem_dev = (dra >> (index * 4 + 2)) & 0x3;
-                struct csrow_info *csrow = &mci->csrows[index];
-
-                mem_dev = (mem_dev == 2);
-                pci_read_config_byte(mci->pdev, E752X_DRB + index, &value);
-                /* convert a 128 or 64 MiB DRB to a page size. */
-                cumul_size = value << (25 + drc_drbg - PAGE_SHIFT);
-                debugf3("%s(): (%d) cumul_size 0x%x\n", __func__, index,
-                        cumul_size);
-
-                if (cumul_size == last_cumul_size)
-                        continue; /* not populated */
-
-                csrow->first_page = last_cumul_size;
-                csrow->last_page = cumul_size - 1;
-                csrow->nr_pages = cumul_size - last_cumul_size;
-                last_cumul_size = cumul_size;
-                csrow->grain = 1 << 12;  /* 4KiB - resolution of CELOG */
-                csrow->mtype = MEM_RDDR;  /* only one type supported */
-                csrow->dtype = mem_dev ? DEV_X4 : DEV_X8;
-
-                /*
-                 * if single channel or x8 devices then SECDED
-                 * if dual channel and x4 then S4ECD4ED
-                 */
-                if (drc_ddim) {
-                        if (drc_chan && mem_dev) {
-                                csrow->edac_mode = EDAC_S4ECD4ED;
-                                mci->edac_cap |= EDAC_FLAG_S4ECD4ED;
-                        } else {
-                                csrow->edac_mode = EDAC_SECDED;
-                                mci->edac_cap |= EDAC_FLAG_SECDED;
-                        }
-                } else
-                        csrow->edac_mode = EDAC_NONE;
-        }
-
-        /* Fill in the memory map table */
-        {
-                u8 value;
-                u8 last = 0;
-                u8 row = 0;
-
-                for (index = 0; index < 8; index += 2) {
-                        pci_read_config_byte(mci->pdev, E752X_DRB + index,
-                                        &value);
-
-                        /* test if there is a dimm in this slot */
-                        if (value == last) {
-                                /* no dimm in the slot, so flag it as empty */
-                                pvt->map[index] = 0xff;
-                                pvt->map[index + 1] = 0xff;
-                        } else { /* there is a dimm in the slot */
-                                pvt->map[index] = row;
-                                row++;
-                                last = value;
-                                /* test the next value to see if the dimm is
-                                   double sided */
-                                pci_read_config_byte(mci->pdev,
-                                                E752X_DRB + index + 1,
-                                                &value);
-                                pvt->map[index + 1] = (value == last) ?
-                                        0xff :  /* the dimm is single sided,
-                                                 * so flag as empty
-                                                 */
-                                        row;    /* this is a double sided dimm
-                                                 * to save the next row #
-                                                 */
-                                row++;
-                                last = value;
-                        }
-                }
-        }
+        e752x_init_csrows(mci, pdev, ddrcsr);
+        e752x_init_mem_map_table(pdev, pvt);
 
         /* set the map type.  1 = normal, 0 = reversed */
-        pci_read_config_byte(mci->pdev, E752X_DRM, &stat8);
+        pci_read_config_byte(pdev, E752X_DRM, &stat8);
         pvt->map_type = ((stat8 & 0x0f) > ((stat8 >> 4) & 0x0f));
 
         mci->edac_cap |= EDAC_FLAG_NONE;
         debugf3("%s(): tolm, remapbase, remaplimit\n", __func__);
 
         /* load the top of low memory, remap base, and remap limit vars */
-        pci_read_config_word(mci->pdev, E752X_TOLM, &pci_data);
+        pci_read_config_word(pdev, E752X_TOLM, &pci_data);
         pvt->tolm = ((u32) pci_data) << 4;
-        pci_read_config_word(mci->pdev, E752X_REMAPBASE, &pci_data);
+        pci_read_config_word(pdev, E752X_REMAPBASE, &pci_data);
         pvt->remapbase = ((u32) pci_data) << 14;
-        pci_read_config_word(mci->pdev, E752X_REMAPLIMIT, &pci_data);
+        pci_read_config_word(pdev, E752X_REMAPLIMIT, &pci_data);
         pvt->remaplimit = ((u32) pci_data) << 14;
         e752x_printk(KERN_INFO,
                 "tolm = %x, remapbase = %x, remaplimit = %x\n", pvt->tolm,
                 pvt->remapbase, pvt->remaplimit);
 
-        if (edac_mc_add_mc(mci)) {
+        /* Here we assume that we will never see multiple instances of this
+         * type of memory controller.  The ID is therefore hardcoded to 0.
+         */
+        if (edac_mc_add_mc(mci,0)) {
                 debugf3("%s(): failed edac_mc_add_mc()\n", __func__);
                 goto fail;
         }
 
-        dev = pci_get_device(PCI_VENDOR_ID_INTEL, e752x_devs[dev_idx].ctl_dev,
-                        NULL);
-        pvt->dev_d0f0 = dev;
-        /* find the error reporting device and clear errors */
-        dev = pvt->dev_d0f1 = pci_dev_get(pvt->bridge_ck);
-        /* Turn off error disable & SMI in case the BIOS turned it on */
-        pci_write_config_byte(dev, E752X_HI_ERRMASK, 0x00);
-        pci_write_config_byte(dev, E752X_HI_SMICMD, 0x00);
-        pci_write_config_word(dev, E752X_SYSBUS_ERRMASK, 0x00);
-        pci_write_config_word(dev, E752X_SYSBUS_SMICMD, 0x00);
-        pci_write_config_byte(dev, E752X_BUF_ERRMASK, 0x00);
-        pci_write_config_byte(dev, E752X_BUF_SMICMD, 0x00);
-        pci_write_config_byte(dev, E752X_DRAM_ERRMASK, 0x00);
-        pci_write_config_byte(dev, E752X_DRAM_SMICMD, 0x00);
-
+        e752x_init_error_reporting_regs(pvt);
         e752x_get_error_info(mci, &discard); /* clear other MCH errors */
 
         /* get this far and it's successful */
@@ -979,20 +1023,12 @@ static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
         return 0;
 
 fail:
-        if (mci) {
-                if (pvt->dev_d0f0)
-                        pci_dev_put(pvt->dev_d0f0);
-
-                if (pvt->dev_d0f1)
-                        pci_dev_put(pvt->dev_d0f1);
-
-                if (pvt->bridge_ck)
-                        pci_dev_put(pvt->bridge_ck);
-
-                edac_mc_free(mci);
-        }
+        pci_dev_put(pvt->dev_d0f0);
+        pci_dev_put(pvt->dev_d0f1);
+        pci_dev_put(pvt->bridge_ck);
+        edac_mc_free(mci);
 
-        return rc;
+        return -ENODEV;
 }
 
 /* returns count (>= 0), or negative on error */
@@ -1015,7 +1051,7 @@ static void __devexit e752x_remove_one(struct pci_dev *pdev)
 
         debugf0("%s()\n", __func__);
 
-        if ((mci = edac_mc_del_mc(pdev)) == NULL)
+        if ((mci = edac_mc_del_mc(&pdev->dev)) == NULL)
                 return;
 
         pvt = (struct e752x_pvt *) mci->pvt_info;
diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c
index a9518d3e4be4..9878379b4993 100644
--- a/drivers/edac/e7xxx_edac.c
+++ b/drivers/edac/e7xxx_edac.c
@@ -30,6 +30,8 @@
 #include <linux/slab.h>
 #include "edac_mc.h"
 
+#define E7XXX_REVISION " Ver: 2.0.0 " __DATE__
+
 #define e7xxx_printk(level, fmt, arg...) \
         edac_printk(level, "e7xxx", fmt, ##arg)
 
@@ -333,99 +335,61 @@ static void e7xxx_check(struct mem_ctl_info *mci)
         e7xxx_process_error_info(mci, &info, 1);
 }
 
-static int e7xxx_probe1(struct pci_dev *pdev, int dev_idx)
+/* Return 1 if dual channel mode is active.  Else return 0. */
+static inline int dual_channel_active(u32 drc, int dev_idx)
 {
-        int rc = -ENODEV;
-        int index;
-        u16 pci_data;
-        struct mem_ctl_info *mci = NULL;
-        struct e7xxx_pvt *pvt = NULL;
-        u32 drc;
-        int drc_chan = 1;       /* Number of channels 0=1chan,1=2chan */
-        int drc_drbg = 1;       /* DRB granularity 0=32mb,1=64mb */
-        int drc_ddim;           /* DRAM Data Integrity Mode 0=none,2=edac */
-        u32 dra;
-        unsigned long last_cumul_size;
-        struct e7xxx_error_info discard;
-
-        debugf0("%s(): mci\n", __func__);
+        return (dev_idx == E7501) ? ((drc >> 22) & 0x1) : 1;
+}
 
-        /* need to find out the number of channels */
-        pci_read_config_dword(pdev, E7XXX_DRC, &drc);
 
+/* Return DRB granularity (0=32mb, 1=64mb). */
+static inline int drb_granularity(u32 drc, int dev_idx)
+{
         /* only e7501 can be single channel */
-        if (dev_idx == E7501) {
-                drc_chan = ((drc >> 22) & 0x1);
-                drc_drbg = (drc >> 18) & 0x3;
-        }
-
-        drc_ddim = (drc >> 20) & 0x3;
-        mci = edac_mc_alloc(sizeof(*pvt), E7XXX_NR_CSROWS, drc_chan + 1);
-
-        if (mci == NULL) {
-                rc = -ENOMEM;
-                goto fail;
-        }
-
-        debugf3("%s(): init mci\n", __func__);
-        mci->mtype_cap = MEM_FLAG_RDDR;
-        mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED |
-                        EDAC_FLAG_S4ECD4ED;
-        /* FIXME - what if different memory types are in different csrows? */
-        mci->mod_name = EDAC_MOD_STR;
-        mci->mod_ver = "$Revision: 1.5.2.9 $";
-        mci->pdev = pdev;
+        return (dev_idx == E7501) ? ((drc >> 18) & 0x3) : 1;
+}
 
-        debugf3("%s(): init pvt\n", __func__);
-        pvt = (struct e7xxx_pvt *) mci->pvt_info;
-        pvt->dev_info = &e7xxx_devs[dev_idx];
-        pvt->bridge_ck = pci_get_device(PCI_VENDOR_ID_INTEL,
-                                        pvt->dev_info->err_dev,
-                                        pvt->bridge_ck);
 
-        if (!pvt->bridge_ck) {
-                e7xxx_printk(KERN_ERR, "error reporting device not found:"
-                        "vendor %x device 0x%x (broken BIOS?)\n",
-                        PCI_VENDOR_ID_INTEL, e7xxx_devs[dev_idx].err_dev);
-                goto fail;
-        }
-
-        debugf3("%s(): more mci init\n", __func__);
-        mci->ctl_name = pvt->dev_info->ctl_name;
-        mci->edac_check = e7xxx_check;
-        mci->ctl_page_to_phys = ctl_page_to_phys;
+static void e7xxx_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev,
+                int dev_idx, u32 drc)
+{
+        unsigned long last_cumul_size;
+        int index;
+        u8 value;
+        u32 dra, cumul_size;
+        int drc_chan, drc_drbg, drc_ddim, mem_dev;
+        struct csrow_info *csrow;
 
-        /* find out the device types */
         pci_read_config_dword(pdev, E7XXX_DRA, &dra);
+        drc_chan = dual_channel_active(drc, dev_idx);
+        drc_drbg = drb_granularity(drc, dev_idx);
+        drc_ddim = (drc >> 20) & 0x3;
+        last_cumul_size = 0;
 
-        /*
-         * The dram row boundary (DRB) reg values are boundary address
+        /* The dram row boundary (DRB) reg values are boundary address
          * for each DRAM row with a granularity of 32 or 64MB (single/dual
          * channel operation).  DRB regs are cumulative; therefore DRB7 will
          * contain the total memory contained in all eight rows.
          */
-        for (last_cumul_size = index = 0; index < mci->nr_csrows; index++) {
-                u8 value;
-                u32 cumul_size;
+        for (index = 0; index < mci->nr_csrows; index++) {
                 /* mem_dev 0=x8, 1=x4 */
-                int mem_dev = (dra >> (index * 4 + 3)) & 0x1;
-                struct csrow_info *csrow = &mci->csrows[index];
+                mem_dev = (dra >> (index * 4 + 3)) & 0x1;
+                csrow = &mci->csrows[index];
 
-                pci_read_config_byte(mci->pdev, E7XXX_DRB + index, &value);
+                pci_read_config_byte(pdev, E7XXX_DRB + index, &value);
                 /* convert a 64 or 32 MiB DRB to a page size. */
                 cumul_size = value << (25 + drc_drbg - PAGE_SHIFT);
                 debugf3("%s(): (%d) cumul_size 0x%x\n", __func__, index,
                         cumul_size);
-
                 if (cumul_size == last_cumul_size)
-                        continue;  /* not populated */
+                        continue;       /* not populated */
 
                 csrow->first_page = last_cumul_size;
                 csrow->last_page = cumul_size - 1;
                 csrow->nr_pages = cumul_size - last_cumul_size;
                 last_cumul_size = cumul_size;
-                csrow->grain = 1 << 12;  /* 4KiB - resolution of CELOG */
-                csrow->mtype = MEM_RDDR;  /* only one type supported */
+                csrow->grain = 1 << 12; /* 4KiB - resolution of CELOG */
+                csrow->mtype = MEM_RDDR;        /* only one type supported */
                 csrow->dtype = mem_dev ? DEV_X4 : DEV_X8;
 
                 /*
@@ -443,16 +407,61 @@ static int e7xxx_probe1(struct pci_dev *pdev, int dev_idx)
                 } else
                         csrow->edac_mode = EDAC_NONE;
         }
+}
 
-        mci->edac_cap |= EDAC_FLAG_NONE;
+static int e7xxx_probe1(struct pci_dev *pdev, int dev_idx)
+{
+        u16 pci_data;
+        struct mem_ctl_info *mci = NULL;
+        struct e7xxx_pvt *pvt = NULL;
+        u32 drc;
+        int drc_chan;
+        struct e7xxx_error_info discard;
+
+        debugf0("%s(): mci\n", __func__);
+        pci_read_config_dword(pdev, E7XXX_DRC, &drc);
+
+        drc_chan = dual_channel_active(drc, dev_idx);
+        mci = edac_mc_alloc(sizeof(*pvt), E7XXX_NR_CSROWS, drc_chan + 1);
+
+        if (mci == NULL)
+                return -ENOMEM;
+
+        debugf3("%s(): init mci\n", __func__);
+        mci->mtype_cap = MEM_FLAG_RDDR;
+        mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED |
+                        EDAC_FLAG_S4ECD4ED;
+        /* FIXME - what if different memory types are in different csrows? */
+        mci->mod_name = EDAC_MOD_STR;
+        mci->mod_ver = E7XXX_REVISION;
+        mci->dev = &pdev->dev;
+        debugf3("%s(): init pvt\n", __func__);
+        pvt = (struct e7xxx_pvt *) mci->pvt_info;
+        pvt->dev_info = &e7xxx_devs[dev_idx];
+        pvt->bridge_ck = pci_get_device(PCI_VENDOR_ID_INTEL,
+                                        pvt->dev_info->err_dev,
+                                        pvt->bridge_ck);
 
+        if (!pvt->bridge_ck) {
+                e7xxx_printk(KERN_ERR, "error reporting device not found:"
+                        "vendor %x device 0x%x (broken BIOS?)\n",
+                        PCI_VENDOR_ID_INTEL, e7xxx_devs[dev_idx].err_dev);
+                goto fail0;
+        }
+
+        debugf3("%s(): more mci init\n", __func__);
+        mci->ctl_name = pvt->dev_info->ctl_name;
+        mci->edac_check = e7xxx_check;
+        mci->ctl_page_to_phys = ctl_page_to_phys;
+        e7xxx_init_csrows(mci, pdev, dev_idx, drc);
+        mci->edac_cap |= EDAC_FLAG_NONE;
         debugf3("%s(): tolm, remapbase, remaplimit\n", __func__);
         /* load the top of low memory, remap base, and remap limit vars */
-        pci_read_config_word(mci->pdev, E7XXX_TOLM, &pci_data);
+        pci_read_config_word(pdev, E7XXX_TOLM, &pci_data);
         pvt->tolm = ((u32) pci_data) << 4;
-        pci_read_config_word(mci->pdev, E7XXX_REMAPBASE, &pci_data);
+        pci_read_config_word(pdev, E7XXX_REMAPBASE, &pci_data);
         pvt->remapbase = ((u32) pci_data) << 14;
-        pci_read_config_word(mci->pdev, E7XXX_REMAPLIMIT, &pci_data);
+        pci_read_config_word(pdev, E7XXX_REMAPLIMIT, &pci_data);
         pvt->remaplimit = ((u32) pci_data) << 14;
         e7xxx_printk(KERN_INFO,
                 "tolm = %x, remapbase = %x, remaplimit = %x\n", pvt->tolm,
@@ -461,23 +470,25 @@ static int e7xxx_probe1(struct pci_dev *pdev, int dev_idx)
         /* clear any pending errors, or initial state bits */
         e7xxx_get_error_info(mci, &discard);
 
-        if (edac_mc_add_mc(mci) != 0) {
+        /* Here we assume that we will never see multiple instances of this
+         * type of memory controller.  The ID is therefore hardcoded to 0.
+         */
+        if (edac_mc_add_mc(mci,0)) {
                 debugf3("%s(): failed edac_mc_add_mc()\n", __func__);
-                goto fail;
+                goto fail1;
         }
 
         /* get this far and it's successful */
         debugf3("%s(): success\n", __func__);
         return 0;
 
-fail:
-        if (mci != NULL) {
-                if(pvt != NULL && pvt->bridge_ck)
-                        pci_dev_put(pvt->bridge_ck);
-                edac_mc_free(mci);
-        }
+fail1:
+        pci_dev_put(pvt->bridge_ck);
+
+fail0:
+        edac_mc_free(mci);
 
-        return rc;
+        return -ENODEV;
 }
 
 /* returns count (>= 0), or negative on error */
@@ -498,7 +509,7 @@ static void __devexit e7xxx_remove_one(struct pci_dev *pdev)
 
         debugf0("%s()\n", __func__);
 
-        if ((mci = edac_mc_del_mc(pdev)) == NULL)
+        if ((mci = edac_mc_del_mc(&pdev->dev)) == NULL)
                 return;
 
         pvt = (struct e7xxx_pvt *) mci->pvt_info;
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index ea06e3a4dc35..357c95f30fc6 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -54,16 +54,17 @@ static int log_ce = 1;
 static int panic_on_ue;
 static int poll_msec = 1000;
 
-static int check_pci_parity = 0;        /* default YES check PCI parity */
-static int panic_on_pci_parity;         /* default no panic on PCI Parity */
-static atomic_t pci_parity_count = ATOMIC_INIT(0);
-
 /* lock to memory controller's control array */
 static DECLARE_MUTEX(mem_ctls_mutex);
 static struct list_head mc_devices = LIST_HEAD_INIT(mc_devices);
 
 static struct task_struct *edac_thread;
 
+#ifdef CONFIG_PCI
+static int check_pci_parity = 0;        /* default YES check PCI parity */
+static int panic_on_pci_parity;         /* default no panic on PCI Parity */
+static atomic_t pci_parity_count = ATOMIC_INIT(0);
+
 /* Structure of the whitelist and blacklist arrays */
 struct edac_pci_device_list {
         unsigned int  vendor;           /* Vendor ID */
@@ -80,6 +81,12 @@ static int pci_blacklist_count;
 static struct edac_pci_device_list pci_whitelist[MAX_LISTED_PCI_DEVICES];
 static int pci_whitelist_count ;
 
+#ifndef DISABLE_EDAC_SYSFS
+static struct kobject edac_pci_kobj; /* /sys/devices/system/edac/pci */
+static struct completion edac_pci_kobj_complete;
+#endif  /* DISABLE_EDAC_SYSFS */
+#endif  /* CONFIG_PCI */
+
 /*  START sysfs data and methods */
 
 #ifndef DISABLE_EDAC_SYSFS
@@ -127,18 +134,15 @@ static struct sysdev_class edac_class = {
         set_kset_name("edac"),
 };
 
-/* sysfs objects:
+/* sysfs object:
  *      /sys/devices/system/edac/mc
- *      /sys/devices/system/edac/pci
  */
 static struct kobject edac_memctrl_kobj;
-static struct kobject edac_pci_kobj;
 
 /* We use these to wait for the reference counts on edac_memctrl_kobj and
  * edac_pci_kobj to reach 0.
  */
 static struct completion edac_memctrl_kobj_complete;
-static struct completion edac_pci_kobj_complete;
 
 /*
  * /sys/devices/system/edac/mc;
@@ -324,6 +328,8 @@ static void edac_sysfs_memctrl_teardown(void)
 #endif  /* DISABLE_EDAC_SYSFS */
 }
 
+#ifdef CONFIG_PCI
+
 #ifndef DISABLE_EDAC_SYSFS
 
 /*
@@ -624,6 +630,252 @@ static void edac_sysfs_pci_teardown(void)
 #endif
 }
 
+
+static u16 get_pci_parity_status(struct pci_dev *dev, int secondary)
+{
+        int where;
+        u16 status;
+
+        where = secondary ? PCI_SEC_STATUS : PCI_STATUS;
+        pci_read_config_word(dev, where, &status);
+
+        /* If we get back 0xFFFF then we must suspect that the card has been
+         * pulled but the Linux PCI layer has not yet finished cleaning up.
+         * We don't want to report on such devices
+         */
+
+        if (status == 0xFFFF) {
+                u32 sanity;
+
+                pci_read_config_dword(dev, 0, &sanity);
+
+                if (sanity == 0xFFFFFFFF)
+                        return 0;
+        }
+
+        status &= PCI_STATUS_DETECTED_PARITY | PCI_STATUS_SIG_SYSTEM_ERROR |
+                PCI_STATUS_PARITY;
+
+        if (status)
+                /* reset only the bits we are interested in */
+                pci_write_config_word(dev, where, status);
+
+        return status;
+}
+
+typedef void (*pci_parity_check_fn_t) (struct pci_dev *dev);
+
+/* Clear any PCI parity errors logged by this device. */
+static void edac_pci_dev_parity_clear(struct pci_dev *dev)
+{
+        u8 header_type;
+
+        get_pci_parity_status(dev, 0);
+
+        /* read the device TYPE, looking for bridges */
+        pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
+
+        if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE)
+                get_pci_parity_status(dev, 1);
+}
+
+/*
+ *  PCI Parity polling
+ *
+ */
+static void edac_pci_dev_parity_test(struct pci_dev *dev)
+{
+        u16 status;
+        u8  header_type;
+
+        /* read the STATUS register on this device
+         */
+        status = get_pci_parity_status(dev, 0);
+
+        debugf2("PCI STATUS= 0x%04x %s\n", status, dev->dev.bus_id );
+
+        /* check the status reg for errors */
+        if (status) {
+                if (status & (PCI_STATUS_SIG_SYSTEM_ERROR))
+                        edac_printk(KERN_CRIT, EDAC_PCI,
+                                "Signaled System Error on %s\n",
+                                pci_name(dev));
+
+                if (status & (PCI_STATUS_PARITY)) {
+                        edac_printk(KERN_CRIT, EDAC_PCI,
+                                "Master Data Parity Error on %s\n",
+                                pci_name(dev));
+
+                        atomic_inc(&pci_parity_count);
+                }
+
+                if (status & (PCI_STATUS_DETECTED_PARITY)) {
+                        edac_printk(KERN_CRIT, EDAC_PCI,
+                                "Detected Parity Error on %s\n",
+                                pci_name(dev));
+
+                        atomic_inc(&pci_parity_count);
+                }
+        }
+
+        /* read the device TYPE, looking for bridges */
+        pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
+
+        debugf2("PCI HEADER TYPE= 0x%02x %s\n", header_type, dev->dev.bus_id );
+
+        if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+                /* On bridges, need to examine secondary status register  */
+                status = get_pci_parity_status(dev, 1);
+
+                debugf2("PCI SEC_STATUS= 0x%04x %s\n",
+                                status, dev->dev.bus_id );
+
+                /* check the secondary status reg for errors */
+                if (status) {
+                        if (status & (PCI_STATUS_SIG_SYSTEM_ERROR))
+                                edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
+                                        "Signaled System Error on %s\n",
+                                        pci_name(dev));
+
+                        if (status & (PCI_STATUS_PARITY)) {
+                                edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
+                                        "Master Data Parity Error on "
+                                        "%s\n", pci_name(dev));
+
+                                atomic_inc(&pci_parity_count);
+                        }
+
+                        if (status & (PCI_STATUS_DETECTED_PARITY)) {
+                                edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
+                                        "Detected Parity Error on %s\n",
+                                        pci_name(dev));
+
+                                atomic_inc(&pci_parity_count);
+                        }
+                }
+        }
+}
+
+/*
+ * check_dev_on_list: Scan for a PCI device on a white/black list
+ * @list:       an EDAC  &edac_pci_device_list  white/black list pointer
+ * @free_index: index of next free entry on the list
+ * @pci_dev:    PCI Device pointer
+ *
+ * see if list contains the device.
+ *
+ * Returns:     0 not found
+ *              1 found on list
+ */
+static int check_dev_on_list(struct edac_pci_device_list *list,
+                int free_index, struct pci_dev *dev)
+{
+        int i;
+        int rc = 0;     /* Assume not found */
+        unsigned short vendor=dev->vendor;
+        unsigned short device=dev->device;
+
+        /* Scan the list, looking for a vendor/device match */
+        for (i = 0; i < free_index; i++, list++ ) {
+                if ((list->vendor == vendor ) && (list->device == device )) {
+                        rc = 1;
+                        break;
+                }
+        }
+
+        return rc;
+}
+
+/*
+ * pci_dev parity list iterator
+ *      Scan the PCI device list for one iteration, looking for SERRORs
+ *      Master Parity ERRORS or Parity ERRORs on primary or secondary devices
+ */
+static inline void edac_pci_dev_parity_iterator(pci_parity_check_fn_t fn)
+{
+        struct pci_dev *dev = NULL;
+
+        /* request for kernel access to the next PCI device, if any,
+         * and while we are looking at it have its reference count
+         * bumped until we are done with it
+         */
+        while((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+                /* if whitelist exists then it has priority, so only scan
+                 * those devices on the whitelist
+                 */
+                if (pci_whitelist_count > 0 ) {
+                        if (check_dev_on_list(pci_whitelist,
+                                        pci_whitelist_count, dev))
+                                fn(dev);
+                } else {
+                        /*
+                         * if no whitelist, then check if this devices is
+                         * blacklisted
+                         */
+                        if (!check_dev_on_list(pci_blacklist,
+                                        pci_blacklist_count, dev))
+                                fn(dev);
+                }
+        }
+}
+
+static void do_pci_parity_check(void)
+{
+        unsigned long flags;
+        int before_count;
+
+        debugf3("%s()\n", __func__);
+
+        if (!check_pci_parity)
+                return;
+
+        before_count = atomic_read(&pci_parity_count);
+
+        /* scan all PCI devices looking for a Parity Error on devices and
+         * bridges
+         */
+        local_irq_save(flags);
+        edac_pci_dev_parity_iterator(edac_pci_dev_parity_test);
+        local_irq_restore(flags);
+
+        /* Only if operator has selected panic on PCI Error */
+        if (panic_on_pci_parity) {
+                /* If the count is different 'after' from 'before' */
+                if (before_count != atomic_read(&pci_parity_count))
+                        panic("EDAC: PCI Parity Error");
+        }
+}
+
+static inline void clear_pci_parity_errors(void)
+{
+        /* Clear any PCI bus parity errors that devices initially have logged
+         * in their registers.
+         */
+        edac_pci_dev_parity_iterator(edac_pci_dev_parity_clear);
+}
+
+#else   /* CONFIG_PCI */
+
+static inline void do_pci_parity_check(void)
+{
+        /* no-op */
+}
+
+static inline void clear_pci_parity_errors(void)
+{
+        /* no-op */
+}
+
+static void edac_sysfs_pci_teardown(void)
+{
+}
+
+static int edac_sysfs_pci_setup(void)
+{
+        return 0;
+}
+#endif  /* CONFIG_PCI */
+
 #ifndef DISABLE_EDAC_SYSFS
 
 /* EDAC sysfs CSROW data structures and methods */
@@ -1132,7 +1384,7 @@ static int edac_create_sysfs_mci_device(struct mem_ctl_info *mci)
                 return err;
 
         /* create a symlink for the device */
-        err = sysfs_create_link(edac_mci_kobj, &mci->pdev->dev.kobj,
+        err = sysfs_create_link(edac_mci_kobj, &mci->dev->kobj,
                                 EDAC_DEVICE_SYMLINK);
 
         if (err)
@@ -1238,7 +1490,7 @@ void edac_mc_dump_mci(struct mem_ctl_info *mci)
         debugf4("\tmci->edac_check = %p\n", mci->edac_check);
         debugf3("\tmci->nr_csrows = %d, csrows = %p\n",
                 mci->nr_csrows, mci->csrows);
-        debugf3("\tpdev = %p\n", mci->pdev);
+        debugf3("\tdev = %p\n", mci->dev);
         debugf3("\tmod_name:ctl_name = %s:%s\n",
                 mci->mod_name, mci->ctl_name);
         debugf3("\tpvt_info = %p\n\n", mci->pvt_info);
@@ -1363,7 +1615,7 @@ void edac_mc_free(struct mem_ctl_info *mci)
 }
 EXPORT_SYMBOL_GPL(edac_mc_free);
 
-static struct mem_ctl_info *find_mci_by_pdev(struct pci_dev *pdev)
+static struct mem_ctl_info *find_mci_by_dev(struct device *dev)
 {
         struct mem_ctl_info *mci;
         struct list_head *item;
@@ -1373,54 +1625,53 @@ static struct mem_ctl_info *find_mci_by_pdev(struct pci_dev *pdev)
         list_for_each(item, &mc_devices) {
                 mci = list_entry(item, struct mem_ctl_info, link);
 
-                if (mci->pdev == pdev)
+                if (mci->dev == dev)
                         return mci;
         }
 
         return NULL;
 }
 
-static int add_mc_to_global_list(struct mem_ctl_info *mci)
+/* Return 0 on success, 1 on failure.
+ * Before calling this function, caller must
+ * assign a unique value to mci->mc_idx.
+ */
+static int add_mc_to_global_list (struct mem_ctl_info *mci)
 {
         struct list_head *item, *insert_before;
         struct mem_ctl_info *p;
-        int i;
 
-        if (list_empty(&mc_devices)) {
-                mci->mc_idx = 0;
-                insert_before = &mc_devices;
-        } else {
-                if (find_mci_by_pdev(mci->pdev)) {
-                        edac_printk(KERN_WARNING, EDAC_MC,
-                                "%s (%s) %s %s already assigned %d\n",
-                                mci->pdev->dev.bus_id,
-                                pci_name(mci->pdev), mci->mod_name,
-                                mci->ctl_name, mci->mc_idx);
-                        return 1;
-                }
+        insert_before = &mc_devices;
 
-                insert_before = NULL;
-                i = 0;
+        if (unlikely((p = find_mci_by_dev(mci->dev)) != NULL))
+                goto fail0;
 
-                list_for_each(item, &mc_devices) {
-                        p = list_entry(item, struct mem_ctl_info, link);
+        list_for_each(item, &mc_devices) {
+                p = list_entry(item, struct mem_ctl_info, link);
 
-                        if (p->mc_idx != i) {
-                                insert_before = item;
-                                break;
-                        }
+                if (p->mc_idx >= mci->mc_idx) {
+                        if (unlikely(p->mc_idx == mci->mc_idx))
+                                goto fail1;
 
-                        i++;
+                        insert_before = item;
+                        break;
                 }
-
-                mci->mc_idx = i;
-
-                if (insert_before == NULL)
-                        insert_before = &mc_devices;
         }
 
         list_add_tail_rcu(&mci->link, insert_before);
         return 0;
+
+fail0:
+        edac_printk(KERN_WARNING, EDAC_MC,
+                    "%s (%s) %s %s already assigned %d\n", p->dev->bus_id,
+                    dev_name(p->dev), p->mod_name, p->ctl_name, p->mc_idx);
+        return 1;
+
+fail1:
+        edac_printk(KERN_WARNING, EDAC_MC,
+                    "bug in low-level driver: attempt to assign\n"
+                    "    duplicate mc_idx %d in %s()\n", p->mc_idx, __func__);
+        return 1;
 }
 
 static void complete_mc_list_del(struct rcu_head *head)
@@ -1444,6 +1695,7 @@ static void del_mc_from_global_list(struct mem_ctl_info *mci)
  * edac_mc_add_mc: Insert the 'mci' structure into the mci global list and
  *                 create sysfs entries associated with mci structure
  * @mci: pointer to the mci structure to be added to the list
+ * @mc_idx: A unique numeric identifier to be assigned to the 'mci' structure.
  *
  * Return:
  *      0       Success
@@ -1451,9 +1703,10 @@ static void del_mc_from_global_list(struct mem_ctl_info *mci)
  */
 
 /* FIXME - should a warning be printed if no error detection? correction? */
-int edac_mc_add_mc(struct mem_ctl_info *mci)
+int edac_mc_add_mc(struct mem_ctl_info *mci, int mc_idx)
 {
         debugf0("%s()\n", __func__);
+        mci->mc_idx = mc_idx;
 #ifdef CONFIG_EDAC_DEBUG
         if (edac_debug_level >= 3)
                 edac_mc_dump_mci(mci);
@@ -1486,8 +1739,8 @@ int edac_mc_add_mc(struct mem_ctl_info *mci)
         }
 
         /* Report action taken */
-        edac_mc_printk(mci, KERN_INFO, "Giving out device to %s %s: PCI %s\n",
-                mci->mod_name, mci->ctl_name, pci_name(mci->pdev));
+        edac_mc_printk(mci, KERN_INFO, "Giving out device to %s %s: DEV %s\n",
+                mci->mod_name, mci->ctl_name, dev_name(mci->dev));
 
         up(&mem_ctls_mutex);
         return 0;
@@ -1504,18 +1757,18 @@ EXPORT_SYMBOL_GPL(edac_mc_add_mc);
 /**
  * edac_mc_del_mc: Remove sysfs entries for specified mci structure and
  *                 remove mci structure from global list
- * @pdev: Pointer to 'struct pci_dev' representing mci structure to remove.
+ * @pdev: Pointer to 'struct device' representing mci structure to remove.
  *
  * Return pointer to removed mci structure, or NULL if device not found.
  */
-struct mem_ctl_info * edac_mc_del_mc(struct pci_dev *pdev)
+struct mem_ctl_info * edac_mc_del_mc(struct device *dev)
 {
         struct mem_ctl_info *mci;
 
         debugf0("MC: %s()\n", __func__);
         down(&mem_ctls_mutex);
 
-        if ((mci = find_mci_by_pdev(pdev)) == NULL) {
+        if ((mci = find_mci_by_dev(dev)) == NULL) {
                 up(&mem_ctls_mutex);
                 return NULL;
         }
@@ -1524,8 +1777,8 @@ struct mem_ctl_info * edac_mc_del_mc(struct pci_dev *pdev)
         del_mc_from_global_list(mci);
         up(&mem_ctls_mutex);
         edac_printk(KERN_INFO, EDAC_MC,
-                "Removed device %d for %s %s: PCI %s\n", mci->mc_idx,
-                mci->mod_name, mci->ctl_name, pci_name(mci->pdev));
+                "Removed device %d for %s %s: DEV %s\n", mci->mc_idx,
+                mci->mod_name, mci->ctl_name, dev_name(mci->dev));
         return mci;
 }
 EXPORT_SYMBOL_GPL(edac_mc_del_mc);
@@ -1739,244 +1992,6 @@ void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg)
 }
 EXPORT_SYMBOL_GPL(edac_mc_handle_ue_no_info);
 
-#ifdef CONFIG_PCI
-
-static u16 get_pci_parity_status(struct pci_dev *dev, int secondary)
-{
-        int where;
-        u16 status;
-
-        where = secondary ? PCI_SEC_STATUS : PCI_STATUS;
-        pci_read_config_word(dev, where, &status);
-
-        /* If we get back 0xFFFF then we must suspect that the card has been
-         * pulled but the Linux PCI layer has not yet finished cleaning up.
-         * We don't want to report on such devices
-         */
-
-        if (status == 0xFFFF) {
-                u32 sanity;
-
-                pci_read_config_dword(dev, 0, &sanity);
-
-                if (sanity == 0xFFFFFFFF)
-                        return 0;
-        }
-
-        status &= PCI_STATUS_DETECTED_PARITY | PCI_STATUS_SIG_SYSTEM_ERROR |
-                PCI_STATUS_PARITY;
-
-        if (status)
-                /* reset only the bits we are interested in */
-                pci_write_config_word(dev, where, status);
-
-        return status;
-}
-
-typedef void (*pci_parity_check_fn_t) (struct pci_dev *dev);
-
-/* Clear any PCI parity errors logged by this device. */
-static void edac_pci_dev_parity_clear(struct pci_dev *dev)
-{
-        u8 header_type;
-
-        get_pci_parity_status(dev, 0);
-
-        /* read the device TYPE, looking for bridges */
-        pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
-
-        if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE)
-                get_pci_parity_status(dev, 1);
-}
-
-/*
- *  PCI Parity polling
- *
- */
-static void edac_pci_dev_parity_test(struct pci_dev *dev)
-{
-        u16 status;
-        u8  header_type;
-
-        /* read the STATUS register on this device
-         */
-        status = get_pci_parity_status(dev, 0);
-
-        debugf2("PCI STATUS= 0x%04x %s\n", status, dev->dev.bus_id );
-
-        /* check the status reg for errors */
-        if (status) {
-                if (status & (PCI_STATUS_SIG_SYSTEM_ERROR))
-                        edac_printk(KERN_CRIT, EDAC_PCI,
-                                "Signaled System Error on %s\n",
-                                pci_name(dev));
-
-                if (status & (PCI_STATUS_PARITY)) {
-                        edac_printk(KERN_CRIT, EDAC_PCI,
-                                "Master Data Parity Error on %s\n",
-                                pci_name(dev));
-
-                        atomic_inc(&pci_parity_count);
-                }
-
-                if (status & (PCI_STATUS_DETECTED_PARITY)) {
-                        edac_printk(KERN_CRIT, EDAC_PCI,
-                                "Detected Parity Error on %s\n",
-                                pci_name(dev));
-
-                        atomic_inc(&pci_parity_count);
-                }
-        }
-
-        /* read the device TYPE, looking for bridges */
-        pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
-
-        debugf2("PCI HEADER TYPE= 0x%02x %s\n", header_type, dev->dev.bus_id );
-
-        if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
-                /* On bridges, need to examine secondary status register  */
-                status = get_pci_parity_status(dev, 1);
-
-                debugf2("PCI SEC_STATUS= 0x%04x %s\n",
-                                status, dev->dev.bus_id );
-
-                /* check the secondary status reg for errors */
-                if (status) {
-                        if (status & (PCI_STATUS_SIG_SYSTEM_ERROR))
-                                edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
-                                        "Signaled System Error on %s\n",
-                                        pci_name(dev));
-
-                        if (status & (PCI_STATUS_PARITY)) {
-                                edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
-                                        "Master Data Parity Error on "
-                                        "%s\n", pci_name(dev));
-
-                                atomic_inc(&pci_parity_count);
-                        }
-
-                        if (status & (PCI_STATUS_DETECTED_PARITY)) {
-                                edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
-                                        "Detected Parity Error on %s\n",
-                                        pci_name(dev));
-
-                                atomic_inc(&pci_parity_count);
-                        }
-                }
-        }
-}
-
-/*
- * check_dev_on_list: Scan for a PCI device on a white/black list
- * @list:       an EDAC  &edac_pci_device_list  white/black list pointer
- * @free_index: index of next free entry on the list
- * @pci_dev:    PCI Device pointer
- *
- * see if list contains the device.
- *
- * Returns:     0 not found
- *              1 found on list
- */
-static int check_dev_on_list(struct edac_pci_device_list *list,
-                int free_index, struct pci_dev *dev)
-{
-        int i;
-        int rc = 0;     /* Assume not found */
-        unsigned short vendor=dev->vendor;
-        unsigned short device=dev->device;
-
-        /* Scan the list, looking for a vendor/device match */
-        for (i = 0; i < free_index; i++, list++ ) {
-                if ((list->vendor == vendor ) && (list->device == device )) {
-                        rc = 1;
-                        break;
-                }
-        }
-
-        return rc;
-}
-
-/*
- * pci_dev parity list iterator
- *      Scan the PCI device list for one iteration, looking for SERRORs
- *      Master Parity ERRORS or Parity ERRORs on primary or secondary devices
- */
-static inline void edac_pci_dev_parity_iterator(pci_parity_check_fn_t fn)
-{
-        struct pci_dev *dev = NULL;
-
-        /* request for kernel access to the next PCI device, if any,
-         * and while we are looking at it have its reference count
-         * bumped until we are done with it
-         */
-        while((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
-                /* if whitelist exists then it has priority, so only scan
-                 * those devices on the whitelist
-                 */
-                if (pci_whitelist_count > 0 ) {
-                        if (check_dev_on_list(pci_whitelist,
-                                        pci_whitelist_count, dev))
-                                fn(dev);
-                } else {
-                        /*
-                         * if no whitelist, then check if this devices is
-                         * blacklisted
-                         */
-                        if (!check_dev_on_list(pci_blacklist,
-                                        pci_blacklist_count, dev))
-                                fn(dev);
-                }
-        }
-}
-
-static void do_pci_parity_check(void)
-{
-        unsigned long flags;
-        int before_count;
-
-        debugf3("%s()\n", __func__);
-
-        if (!check_pci_parity)
-                return;
-
-        before_count = atomic_read(&pci_parity_count);
-
-        /* scan all PCI devices looking for a Parity Error on devices and
-         * bridges
-         */
-        local_irq_save(flags);
-        edac_pci_dev_parity_iterator(edac_pci_dev_parity_test);
-        local_irq_restore(flags);
-
-        /* Only if operator has selected panic on PCI Error */
-        if (panic_on_pci_parity) {
-                /* If the count is different 'after' from 'before' */
-                if (before_count != atomic_read(&pci_parity_count))
-                        panic("EDAC: PCI Parity Error");
-        }
-}
-
-static inline void clear_pci_parity_errors(void)
-{
-        /* Clear any PCI bus parity errors that devices initially have logged
-         * in their registers.
-         */
-        edac_pci_dev_parity_iterator(edac_pci_dev_parity_clear);
-}
-
-#else  /* CONFIG_PCI */
-
-static inline void do_pci_parity_check(void)
-{
-        /* no-op */
-}
-
-static inline void clear_pci_parity_errors(void)
-{
-        /* no-op */
-}
-
-#endif  /* CONFIG_PCI */
 
 /*
  * Iterate over all MC instances and check for ECC, et al, errors
@@ -2096,10 +2111,12 @@ MODULE_DESCRIPTION("Core library routines for MC reporting");
 
 module_param(panic_on_ue, int, 0644);
 MODULE_PARM_DESC(panic_on_ue, "Panic on uncorrected error: 0=off 1=on");
+#ifdef CONFIG_PCI
 module_param(check_pci_parity, int, 0644);
 MODULE_PARM_DESC(check_pci_parity, "Check for PCI bus parity errors: 0=off 1=on");
 module_param(panic_on_pci_parity, int, 0644);
 MODULE_PARM_DESC(panic_on_pci_parity, "Panic on PCI Bus Parity error: 0=off 1=on");
+#endif
 module_param(log_ue, int, 0644);
 MODULE_PARM_DESC(log_ue, "Log uncorrectable error to console: 0=off 1=on");
 module_param(log_ce, int, 0644);
diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h
index 8d9e83909b9c..342979677d2f 100644
--- a/drivers/edac/edac_mc.h
+++ b/drivers/edac/edac_mc.h
@@ -88,6 +88,12 @@ extern int edac_debug_level;
 #define PCI_VEND_DEV(vend, dev) PCI_VENDOR_ID_ ## vend, \
         PCI_DEVICE_ID_ ## vend ## _ ## dev
 
+#if defined(CONFIG_X86) && defined(CONFIG_PCI)
+#define dev_name(dev) pci_name(to_pci_dev(dev))
+#else
+#define dev_name(dev) to_platform_device(dev)->name
+#endif
+
 /* memory devices */
 enum dev_type {
         DEV_UNKNOWN = 0,
@@ -327,10 +333,10 @@ struct mem_ctl_info {
         struct csrow_info *csrows;
         /*
          * FIXME - what about controllers on other busses? - IDs must be
-         * unique.  pdev pointer should be sufficiently unique, but
+         * unique.  dev pointer should be sufficiently unique, but
          * BUS:SLOT.FUNC numbers may not be unique.
          */
-        struct pci_dev *pdev;
+        struct device *dev;
         const char *mod_name;
         const char *mod_ver;
         const char *ctl_name;
@@ -353,6 +359,8 @@ struct mem_ctl_info {
         struct completion kobj_complete;
 };
 
+#ifdef CONFIG_PCI
+
 /* write all or some bits in a byte-register*/
 static inline void pci_write_bits8(struct pci_dev *pdev, int offset, u8 value,
                 u8 mask)
@@ -401,14 +409,16 @@ static inline void pci_write_bits32(struct pci_dev *pdev, int offset,
         pci_write_config_dword(pdev, offset, value);
 }
 
+#endif /* CONFIG_PCI */
+
 #ifdef CONFIG_EDAC_DEBUG
 void edac_mc_dump_channel(struct channel_info *chan);
 void edac_mc_dump_mci(struct mem_ctl_info *mci);
 void edac_mc_dump_csrow(struct csrow_info *csrow);
 #endif  /* CONFIG_EDAC_DEBUG */
 
-extern int edac_mc_add_mc(struct mem_ctl_info *mci);
-extern struct mem_ctl_info * edac_mc_del_mc(struct pci_dev *pdev);
+extern int edac_mc_add_mc(struct mem_ctl_info *mci,int mc_idx);
+extern struct mem_ctl_info * edac_mc_del_mc(struct device *dev);
 extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
                                         unsigned long page);
 extern void edac_mc_scrub_block(unsigned long page, unsigned long offset,
diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c
index fd342163cf97..d196dcc850a8 100644
--- a/drivers/edac/i82860_edac.c
+++ b/drivers/edac/i82860_edac.c
@@ -17,6 +17,8 @@
 #include <linux/slab.h>
 #include "edac_mc.h"
 
+#define  I82860_REVISION " Ver: 2.0.0 " __DATE__
+
 #define i82860_printk(level, fmt, arg...) \
         edac_printk(level, "i82860", fmt, ##arg)
 
@@ -63,17 +65,21 @@ static struct pci_dev *mci_pdev = NULL;	/* init dev: in case that AGP code
 static void i82860_get_error_info(struct mem_ctl_info *mci,
                 struct i82860_error_info *info)
 {
+        struct pci_dev *pdev;
+
+        pdev = to_pci_dev(mci->dev);
+
         /*
          * This is a mess because there is no atomic way to read all the
          * registers at once and the registers can transition from CE being
          * overwritten by UE.
          */
-        pci_read_config_word(mci->pdev, I82860_ERRSTS, &info->errsts);
-        pci_read_config_dword(mci->pdev, I82860_EAP, &info->eap);
-        pci_read_config_word(mci->pdev, I82860_DERRCTL_STS, &info->derrsyn);
-        pci_read_config_word(mci->pdev, I82860_ERRSTS, &info->errsts2);
+        pci_read_config_word(pdev, I82860_ERRSTS, &info->errsts);
+        pci_read_config_dword(pdev, I82860_EAP, &info->eap);
+        pci_read_config_word(pdev, I82860_DERRCTL_STS, &info->derrsyn);
+        pci_read_config_word(pdev, I82860_ERRSTS, &info->errsts2);
 
-        pci_write_bits16(mci->pdev, I82860_ERRSTS, 0x0003, 0x0003);
+        pci_write_bits16(pdev, I82860_ERRSTS, 0x0003, 0x0003);
 
         /*
          * If the error is the same for both reads then the first set of reads
@@ -84,8 +90,8 @@ static void i82860_get_error_info(struct mem_ctl_info *mci,
                 return;
 
         if ((info->errsts ^ info->errsts2) & 0x0003) {
-                pci_read_config_dword(mci->pdev, I82860_EAP, &info->eap);
-                pci_read_config_word(mci->pdev, I82860_DERRCTL_STS,
+                pci_read_config_dword(pdev, I82860_EAP, &info->eap);
+                pci_read_config_word(pdev, I82860_DERRCTL_STS,
                                 &info->derrsyn);
         }
 }
@@ -127,15 +133,50 @@ static void i82860_check(struct mem_ctl_info *mci)
         i82860_process_error_info(mci, &info, 1);
 }
 
-static int i82860_probe1(struct pci_dev *pdev, int dev_idx)
+static void i82860_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev)
 {
-        int rc = -ENODEV;
-        int index;
-        struct mem_ctl_info *mci = NULL;
         unsigned long last_cumul_size;
-        struct i82860_error_info discard;
+        u16 mchcfg_ddim;  /* DRAM Data Integrity Mode 0=none, 2=edac */
+        u16 value;
+        u32 cumul_size;
+        struct csrow_info *csrow;
+        int index;
+
+        pci_read_config_word(pdev, I82860_MCHCFG, &mchcfg_ddim);
+        mchcfg_ddim = mchcfg_ddim & 0x180;
+        last_cumul_size = 0;
+
+        /* The group row boundary (GRA) reg values are boundary address
+         * for each DRAM row with a granularity of 16MB.  GRA regs are
+         * cumulative; therefore GRA15 will contain the total memory contained
+         * in all eight rows.
+         */
+        for (index = 0; index < mci->nr_csrows; index++) {
+                csrow = &mci->csrows[index];
+                pci_read_config_word(pdev, I82860_GBA + index * 2, &value);
+                cumul_size = (value & I82860_GBA_MASK) <<
+                    (I82860_GBA_SHIFT - PAGE_SHIFT);
+                debugf3("%s(): (%d) cumul_size 0x%x\n", __func__, index,
+                        cumul_size);
 
-        u16 mchcfg_ddim;        /* DRAM Data Integrity Mode 0=none,2=edac */
+                if (cumul_size == last_cumul_size)
+                        continue;       /* not populated */
+
+                csrow->first_page = last_cumul_size;
+                csrow->last_page = cumul_size - 1;
+                csrow->nr_pages = cumul_size - last_cumul_size;
+                last_cumul_size = cumul_size;
+                csrow->grain = 1 << 12; /* I82860_EAP has 4KiB reolution */
+                csrow->mtype = MEM_RMBS;
+                csrow->dtype = DEV_UNKNOWN;
+                csrow->edac_mode = mchcfg_ddim ? EDAC_SECDED : EDAC_NONE;
+        }
+}
+
+static int i82860_probe1(struct pci_dev *pdev, int dev_idx)
+{
+        struct mem_ctl_info *mci;
+        struct i82860_error_info discard;
 
         /* RDRAM has channels but these don't map onto the abstractions that
            edac uses.
@@ -151,67 +192,35 @@ static int i82860_probe1(struct pci_dev *pdev, int dev_idx)
                 return -ENOMEM;
 
         debugf3("%s(): init mci\n", __func__);
-        mci->pdev = pdev;
+        mci->dev = &pdev->dev;
         mci->mtype_cap = MEM_FLAG_DDR;
-
         mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
         /* I"m not sure about this but I think that all RDRAM is SECDED */
         mci->edac_cap = EDAC_FLAG_SECDED;
-        /* adjust FLAGS */
-
         mci->mod_name = EDAC_MOD_STR;
-        mci->mod_ver = "$Revision: 1.1.2.6 $";
+        mci->mod_ver = I82860_REVISION;
         mci->ctl_name = i82860_devs[dev_idx].ctl_name;
         mci->edac_check = i82860_check;
         mci->ctl_page_to_phys = NULL;
+        i82860_init_csrows(mci, pdev);
+        i82860_get_error_info(mci, &discard);  /* clear counters */
 
-        pci_read_config_word(mci->pdev, I82860_MCHCFG, &mchcfg_ddim);
-        mchcfg_ddim = mchcfg_ddim & 0x180;
-
-        /*
-         * The group row boundary (GRA) reg values are boundary address
-         * for each DRAM row with a granularity of 16MB.  GRA regs are
-         * cumulative; therefore GRA15 will contain the total memory contained
-         * in all eight rows.
+        /* Here we assume that we will never see multiple instances of this
+         * type of memory controller.  The ID is therefore hardcoded to 0.
          */
-        for (last_cumul_size = index = 0; index < mci->nr_csrows; index++) {
-                u16 value;
-                u32 cumul_size;
-                struct csrow_info *csrow = &mci->csrows[index];
-
-                pci_read_config_word(mci->pdev, I82860_GBA + index * 2,
-                                &value);
-
-                cumul_size = (value & I82860_GBA_MASK) <<
-                    (I82860_GBA_SHIFT - PAGE_SHIFT);
-                debugf3("%s(): (%d) cumul_size 0x%x\n", __func__, index,
-                        cumul_size);
-
-                if (cumul_size == last_cumul_size)
-                        continue;       /* not populated */
-
-                csrow->first_page = last_cumul_size;
-                csrow->last_page = cumul_size - 1;
-                csrow->nr_pages = cumul_size - last_cumul_size;
-                last_cumul_size = cumul_size;
-                csrow->grain = 1 << 12;  /* I82860_EAP has 4KiB reolution */
-                csrow->mtype = MEM_RMBS;
-                csrow->dtype = DEV_UNKNOWN;
-                csrow->edac_mode = mchcfg_ddim ? EDAC_SECDED : EDAC_NONE;
+        if (edac_mc_add_mc(mci,0)) {
+                debugf3("%s(): failed edac_mc_add_mc()\n", __func__);
+                goto fail;
         }
 
-        i82860_get_error_info(mci, &discard);  /* clear counters */
+        /* get this far and it's successful */
+        debugf3("%s(): success\n", __func__);
 
-        if (edac_mc_add_mc(mci)) {
-                debugf3("%s(): failed edac_mc_add_mc()\n", __func__);
-                edac_mc_free(mci);
-        } else {
-                /* get this far and it's successful */
-                debugf3("%s(): success\n", __func__);
-                rc = 0;
-        }
+        return 0;
 
-        return rc;
+fail:
+        edac_mc_free(mci);
+        return -ENODEV;
 }
 
 /* returns count (>= 0), or negative on error */
@@ -240,7 +249,7 @@ static void __devexit i82860_remove_one(struct pci_dev *pdev)
 
         debugf0("%s()\n", __func__);
 
-        if ((mci = edac_mc_del_mc(pdev)) == NULL)
+        if ((mci = edac_mc_del_mc(&pdev->dev)) == NULL)
                 return;
 
         edac_mc_free(mci);
diff --git a/drivers/edac/i82875p_edac.c b/drivers/edac/i82875p_edac.c
index 0aec92698f17..6787403463a1 100644
--- a/drivers/edac/i82875p_edac.c
+++ b/drivers/edac/i82875p_edac.c
@@ -21,6 +21,8 @@
 #include <linux/slab.h>
 #include "edac_mc.h"
 
+#define I82875P_REVISION        " Ver: 2.0.0 " __DATE__
+
 #define i82875p_printk(level, fmt, arg...) \
         edac_printk(level, "i82875p", fmt, ##arg)
 
@@ -185,18 +187,22 @@ static int i82875p_registered = 1;
 static void i82875p_get_error_info(struct mem_ctl_info *mci,
                 struct i82875p_error_info *info)
 {
+        struct pci_dev *pdev;
+
+        pdev = to_pci_dev(mci->dev);
+
         /*
          * This is a mess because there is no atomic way to read all the
          * registers at once and the registers can transition from CE being
          * overwritten by UE.
          */
-        pci_read_config_word(mci->pdev, I82875P_ERRSTS, &info->errsts);
-        pci_read_config_dword(mci->pdev, I82875P_EAP, &info->eap);
-        pci_read_config_byte(mci->pdev, I82875P_DES, &info->des);
-        pci_read_config_byte(mci->pdev, I82875P_DERRSYN, &info->derrsyn);
-        pci_read_config_word(mci->pdev, I82875P_ERRSTS, &info->errsts2);
+        pci_read_config_word(pdev, I82875P_ERRSTS, &info->errsts);
+        pci_read_config_dword(pdev, I82875P_EAP, &info->eap);
+        pci_read_config_byte(pdev, I82875P_DES, &info->des);
+        pci_read_config_byte(pdev, I82875P_DERRSYN, &info->derrsyn);
+        pci_read_config_word(pdev, I82875P_ERRSTS, &info->errsts2);
 
-        pci_write_bits16(mci->pdev, I82875P_ERRSTS, 0x0081, 0x0081);
+        pci_write_bits16(pdev, I82875P_ERRSTS, 0x0081, 0x0081);
 
         /*
          * If the error is the same then we can for both reads then
@@ -208,9 +214,9 @@ static void i82875p_get_error_info(struct mem_ctl_info *mci,
                 return;
 
         if ((info->errsts ^ info->errsts2) & 0x0081) {
-                pci_read_config_dword(mci->pdev, I82875P_EAP, &info->eap);
-                pci_read_config_byte(mci->pdev, I82875P_DES, &info->des);
-                pci_read_config_byte(mci->pdev, I82875P_DERRSYN,
+                pci_read_config_dword(pdev, I82875P_EAP, &info->eap);
+                pci_read_config_byte(pdev, I82875P_DES, &info->des);
+                pci_read_config_byte(pdev, I82875P_DERRSYN,
                                 &info->derrsyn);
         }
 }
@@ -259,116 +265,109 @@ static void i82875p_check(struct mem_ctl_info *mci)
 extern int pci_proc_attach_device(struct pci_dev *);
 #endif
 
-static int i82875p_probe1(struct pci_dev *pdev, int dev_idx)
+/* Return 0 on success or 1 on failure. */
+static int i82875p_setup_overfl_dev(struct pci_dev *pdev,
+                struct pci_dev **ovrfl_pdev, void __iomem **ovrfl_window)
 {
-        int rc = -ENODEV;
-        int index;
-        struct mem_ctl_info *mci = NULL;
-        struct i82875p_pvt *pvt = NULL;
-        unsigned long last_cumul_size;
-        struct pci_dev *ovrfl_pdev;
-        void __iomem *ovrfl_window = NULL;
-        u32 drc;
-        u32 drc_chan;           /* Number of channels 0=1chan,1=2chan */
-        u32 nr_chans;
-        u32 drc_ddim;           /* DRAM Data Integrity Mode 0=none,2=edac */
-        struct i82875p_error_info discard;
+        struct pci_dev *dev;
+        void __iomem *window;
 
-        debugf0("%s()\n", __func__);
-        ovrfl_pdev = pci_get_device(PCI_VEND_DEV(INTEL, 82875_6), NULL);
+        *ovrfl_pdev = NULL;
+        *ovrfl_window = NULL;
+        dev = pci_get_device(PCI_VEND_DEV(INTEL, 82875_6), NULL);
 
-        if (!ovrfl_pdev) {
-                /*
-                 * Intel tells BIOS developers to hide device 6 which
+        if (dev == NULL) {
+                /* Intel tells BIOS developers to hide device 6 which
                  * configures the overflow device access containing
                  * the DRBs - this is where we expose device 6.
                  * http://www.x86-secret.com/articles/tweak/pat/patsecrets-2.htm
                  */
                 pci_write_bits8(pdev, 0xf4, 0x2, 0x2);
-                ovrfl_pdev =
-                        pci_scan_single_device(pdev->bus, PCI_DEVFN(6, 0));
+                dev = pci_scan_single_device(pdev->bus, PCI_DEVFN(6, 0));
 
-                if (!ovrfl_pdev)
-                        return -ENODEV;
+                if (dev == NULL)
+                        return 1;
         }
 
+        *ovrfl_pdev = dev;
+
 #ifdef CONFIG_PROC_FS
-        if (!ovrfl_pdev->procent && pci_proc_attach_device(ovrfl_pdev)) {
-                i82875p_printk(KERN_ERR,
-                        "%s(): Failed to attach overflow device\n", __func__);
-                return -ENODEV;
+        if ((dev->procent == NULL) && pci_proc_attach_device(dev)) {
+                i82875p_printk(KERN_ERR, "%s(): Failed to attach overflow "
+                               "device\n", __func__);
+                return 1;
         }
-#endif
-                                /* CONFIG_PROC_FS */
-        if (pci_enable_device(ovrfl_pdev)) {
-                i82875p_printk(KERN_ERR,
-                        "%s(): Failed to enable overflow device\n", __func__);
-                return -ENODEV;
+#endif  /* CONFIG_PROC_FS */
+        if (pci_enable_device(dev)) {
+                i82875p_printk(KERN_ERR, "%s(): Failed to enable overflow "
+                               "device\n", __func__);
+                return 1;
         }
 
-        if (pci_request_regions(ovrfl_pdev, pci_name(ovrfl_pdev))) {
+        if (pci_request_regions(dev, pci_name(dev))) {
 #ifdef CORRECT_BIOS
                 goto fail0;
 #endif
         }
 
         /* cache is irrelevant for PCI bus reads/writes */
-        ovrfl_window = ioremap_nocache(pci_resource_start(ovrfl_pdev, 0),
-                                pci_resource_len(ovrfl_pdev, 0));
+        window = ioremap_nocache(pci_resource_start(dev, 0),
+                                 pci_resource_len(dev, 0));
 
-        if (!ovrfl_window) {
+        if (window == NULL) {
                 i82875p_printk(KERN_ERR, "%s(): Failed to ioremap bar6\n",
-                        __func__);
+                               __func__);
                 goto fail1;
         }
 
-        /* need to find out the number of channels */
-        drc = readl(ovrfl_window + I82875P_DRC);
-        drc_chan = ((drc >> 21) & 0x1);
-        nr_chans = drc_chan + 1;
+        *ovrfl_window = window;
+        return 0;
 
-        drc_ddim = (drc >> 18) & 0x1;
-        mci = edac_mc_alloc(sizeof(*pvt), I82875P_NR_CSROWS(nr_chans),
-                                nr_chans);
+fail1:
+        pci_release_regions(dev);
 
-        if (!mci) {
-                rc = -ENOMEM;
-                goto fail2;
-        }
+#ifdef CORRECT_BIOS
+fail0:
+        pci_disable_device(dev);
+#endif
+        /* NOTE: the ovrfl proc entry and pci_dev are intentionally left */
+        return 1;
+}
 
-        debugf3("%s(): init mci\n", __func__);
-        mci->pdev = pdev;
-        mci->mtype_cap = MEM_FLAG_DDR;
-        mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
-        mci->edac_cap = EDAC_FLAG_UNKNOWN;
-        /* adjust FLAGS */
 
-        mci->mod_name = EDAC_MOD_STR;
-        mci->mod_ver = "$Revision: 1.5.2.11 $";
-        mci->ctl_name = i82875p_devs[dev_idx].ctl_name;
-        mci->edac_check = i82875p_check;
-        mci->ctl_page_to_phys = NULL;
-        debugf3("%s(): init pvt\n", __func__);
-        pvt = (struct i82875p_pvt *) mci->pvt_info;
-        pvt->ovrfl_pdev = ovrfl_pdev;
-        pvt->ovrfl_window = ovrfl_window;
+/* Return 1 if dual channel mode is active.  Else return 0. */
+static inline int dual_channel_active(u32 drc)
+{
+        return (drc >> 21) & 0x1;
+}
 
-        /*
-         * The dram row boundary (DRB) reg values are boundary address
+
+static void i82875p_init_csrows(struct mem_ctl_info *mci,
+                struct pci_dev *pdev, void __iomem *ovrfl_window, u32 drc)
+{
+        struct csrow_info *csrow;
+        unsigned long last_cumul_size;
+        u8 value;
+        u32 drc_ddim;  /* DRAM Data Integrity Mode 0=none,2=edac */
+        u32 cumul_size;
+        int index;
+
+        drc_ddim = (drc >> 18) & 0x1;
+        last_cumul_size = 0;
+
+        /* The dram row boundary (DRB) reg values are boundary address
          * for each DRAM row with a granularity of 32 or 64MB (single/dual
          * channel operation).  DRB regs are cumulative; therefore DRB7 will
          * contain the total memory contained in all eight rows.
          */
-        for (last_cumul_size = index = 0; index < mci->nr_csrows; index++) {
-                u8 value;
-                u32 cumul_size;
-                struct csrow_info *csrow = &mci->csrows[index];
+
+        for (index = 0; index < mci->nr_csrows; index++) {
+                csrow = &mci->csrows[index];
 
                 value = readb(ovrfl_window + I82875P_DRB + index);
                 cumul_size = value << (I82875P_DRB_SHIFT - PAGE_SHIFT);
                 debugf3("%s(): (%d) cumul_size 0x%x\n", __func__, index,
                         cumul_size);
-
                 if (cumul_size == last_cumul_size)
                         continue;       /* not populated */
 
@@ -376,35 +375,75 @@ static int i82875p_probe1(struct pci_dev *pdev, int dev_idx)
                 csrow->last_page = cumul_size - 1;
                 csrow->nr_pages = cumul_size - last_cumul_size;
                 last_cumul_size = cumul_size;
-                csrow->grain = 1 << 12;  /* I82875P_EAP has 4KiB reolution */
+                csrow->grain = 1 << 12; /* I82875P_EAP has 4KiB reolution */
                 csrow->mtype = MEM_DDR;
                 csrow->dtype = DEV_UNKNOWN;
                 csrow->edac_mode = drc_ddim ? EDAC_SECDED : EDAC_NONE;
         }
+}
+
+static int i82875p_probe1(struct pci_dev *pdev, int dev_idx)
+{
+        int rc = -ENODEV;
+        struct mem_ctl_info *mci;
+        struct i82875p_pvt *pvt;
+        struct pci_dev *ovrfl_pdev;
+        void __iomem *ovrfl_window;
+        u32 drc;
+        u32 nr_chans;
+        struct i82875p_error_info discard;
+
+        debugf0("%s()\n", __func__);
+        ovrfl_pdev = pci_get_device(PCI_VEND_DEV(INTEL, 82875_6), NULL);
+
+        if (i82875p_setup_overfl_dev(pdev, &ovrfl_pdev, &ovrfl_window))
+                return -ENODEV;
+        drc = readl(ovrfl_window + I82875P_DRC);
+        nr_chans = dual_channel_active(drc) + 1;
+        mci = edac_mc_alloc(sizeof(*pvt), I82875P_NR_CSROWS(nr_chans),
+                                nr_chans);
+
+        if (!mci) {
+                rc = -ENOMEM;
+                goto fail0;
+        }
 
+        debugf3("%s(): init mci\n", __func__);
+        mci->dev = &pdev->dev;
+        mci->mtype_cap = MEM_FLAG_DDR;
+        mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
+        mci->edac_cap = EDAC_FLAG_UNKNOWN;
+        mci->mod_name = EDAC_MOD_STR;
+        mci->mod_ver = I82875P_REVISION;
+        mci->ctl_name = i82875p_devs[dev_idx].ctl_name;
+        mci->edac_check = i82875p_check;
+        mci->ctl_page_to_phys = NULL;
+        debugf3("%s(): init pvt\n", __func__);
+        pvt = (struct i82875p_pvt *) mci->pvt_info;
+        pvt->ovrfl_pdev = ovrfl_pdev;
+        pvt->ovrfl_window = ovrfl_window;
+        i82875p_init_csrows(mci, pdev, ovrfl_window, drc);
         i82875p_get_error_info(mci, &discard);  /* clear counters */
 
-        if (edac_mc_add_mc(mci)) {
+        /* Here we assume that we will never see multiple instances of this
+         * type of memory controller.  The ID is therefore hardcoded to 0.
+         */
+        if (edac_mc_add_mc(mci,0)) {
                 debugf3("%s(): failed edac_mc_add_mc()\n", __func__);
-                goto fail3;
+                goto fail1;
         }
 
         /* get this far and it's successful */
         debugf3("%s(): success\n", __func__);
         return 0;
 
-fail3:
+fail1:
         edac_mc_free(mci);
 
-fail2:
+fail0:
         iounmap(ovrfl_window);
-
-fail1:
         pci_release_regions(ovrfl_pdev);
 
-#ifdef CORRECT_BIOS
-fail0:
-#endif
         pci_disable_device(ovrfl_pdev);
         /* NOTE: the ovrfl proc entry and pci_dev are intentionally left */
         return rc;
@@ -437,7 +476,7 @@ static void __devexit i82875p_remove_one(struct pci_dev *pdev)
 
         debugf0("%s()\n", __func__);
 
-        if ((mci = edac_mc_del_mc(pdev)) == NULL)
+        if ((mci = edac_mc_del_mc(&pdev->dev)) == NULL)
                 return;
 
         pvt = (struct i82875p_pvt *) mci->pvt_info;
diff --git a/drivers/edac/r82600_edac.c b/drivers/edac/r82600_edac.c
index 2c29fafe67c7..fecdb2c9ee28 100644
--- a/drivers/edac/r82600_edac.c
+++ b/drivers/edac/r82600_edac.c
@@ -23,6 +23,8 @@
 #include <linux/slab.h>
 #include "edac_mc.h"
 
+#define R82600_REVISION " Ver: 2.0.0 " __DATE__
+
 #define r82600_printk(level, fmt, arg...) \
         edac_printk(level, "r82600", fmt, ##arg)
 
@@ -134,17 +136,20 @@ static unsigned int disable_hardware_scrub = 0;
 static void r82600_get_error_info (struct mem_ctl_info *mci,
                 struct r82600_error_info *info)
 {
-        pci_read_config_dword(mci->pdev, R82600_EAP, &info->eapr);
+        struct pci_dev *pdev;
+
+        pdev = to_pci_dev(mci->dev);
+        pci_read_config_dword(pdev, R82600_EAP, &info->eapr);
 
         if (info->eapr & BIT(0))
                 /* Clear error to allow next error to be reported [p.62] */
-                pci_write_bits32(mci->pdev, R82600_EAP,
+                pci_write_bits32(pdev, R82600_EAP,
                                 ((u32) BIT(0) & (u32) BIT(1)),
                                 ((u32) BIT(0) & (u32) BIT(1)));
 
         if (info->eapr & BIT(1))
                 /* Clear error to allow next error to be reported [p.62] */
-                pci_write_bits32(mci->pdev, R82600_EAP,
+                pci_write_bits32(pdev, R82600_EAP,
                                 ((u32) BIT(0) & (u32) BIT(1)),
                                 ((u32) BIT(0) & (u32) BIT(1)));
 }
@@ -200,25 +205,72 @@ static void r82600_check(struct mem_ctl_info *mci)
         r82600_process_error_info(mci, &info, 1);
 }
 
-static int r82600_probe1(struct pci_dev *pdev, int dev_idx)
+static inline int ecc_enabled(u8 dramcr)
+{
+        return dramcr & BIT(5);
+}
+
+static void r82600_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev,
+                u8 dramcr)
 {
-        int rc = -ENODEV;
+        struct csrow_info *csrow;
         int index;
-        struct mem_ctl_info *mci = NULL;
+        u8 drbar;  /* SDRAM Row Boundry Address Register */
+        u32 row_high_limit, row_high_limit_last;
+        u32 reg_sdram, ecc_on, row_base;
+
+        ecc_on = ecc_enabled(dramcr);
+        reg_sdram = dramcr & BIT(4);
+        row_high_limit_last = 0;
+
+        for (index = 0; index < mci->nr_csrows; index++) {
+                csrow = &mci->csrows[index];
+
+                /* find the DRAM Chip Select Base address and mask */
+                pci_read_config_byte(pdev, R82600_DRBA + index, &drbar);
+
+                debugf1("%s() Row=%d DRBA = %#0x\n", __func__, index, drbar);
+
+                row_high_limit = ((u32) drbar << 24);
+/*              row_high_limit = ((u32)drbar << 24) | 0xffffffUL; */
+
+                debugf1("%s() Row=%d, Boundry Address=%#0x, Last = %#0x\n",
+                        __func__, index, row_high_limit, row_high_limit_last);
+
+                /* Empty row [p.57] */
+                if (row_high_limit == row_high_limit_last)
+                        continue;
+
+                row_base = row_high_limit_last;
+
+                csrow->first_page = row_base >> PAGE_SHIFT;
+                csrow->last_page = (row_high_limit >> PAGE_SHIFT) - 1;
+                csrow->nr_pages = csrow->last_page - csrow->first_page + 1;
+                /* Error address is top 19 bits - so granularity is      *
+                 * 14 bits                                               */
+                csrow->grain = 1 << 14;
+                csrow->mtype = reg_sdram ? MEM_RDDR : MEM_DDR;
+                /* FIXME - check that this is unknowable with this chipset */
+                csrow->dtype = DEV_UNKNOWN;
+
+                /* Mode is global on 82600 */
+                csrow->edac_mode = ecc_on ? EDAC_SECDED : EDAC_NONE;
+                row_high_limit_last = row_high_limit;
+        }
+}
+
+static int r82600_probe1(struct pci_dev *pdev, int dev_idx)
+{
+        struct mem_ctl_info *mci;
         u8 dramcr;
-        u32 ecc_on;
-        u32 reg_sdram;
         u32 eapr;
         u32 scrub_disabled;
         u32 sdram_refresh_rate;
-        u32 row_high_limit_last = 0;
         struct r82600_error_info discard;
 
         debugf0("%s()\n", __func__);
         pci_read_config_byte(pdev, R82600_DRAMC, &dramcr);
         pci_read_config_dword(pdev, R82600_EAP, &eapr);
-        ecc_on = dramcr & BIT(5);
-        reg_sdram = dramcr & BIT(4);
         scrub_disabled = eapr & BIT(31);
         sdram_refresh_rate = dramcr & (BIT(0) | BIT(1));
         debugf2("%s(): sdram refresh rate = %#0x\n", __func__,
@@ -226,13 +278,11 @@ static int r82600_probe1(struct pci_dev *pdev, int dev_idx)
         debugf2("%s(): DRAMC register = %#0x\n", __func__, dramcr);
         mci = edac_mc_alloc(0, R82600_NR_CSROWS, R82600_NR_CHANS);
 
-        if (mci == NULL) {
-                rc = -ENOMEM;
-                goto fail;
-        }
+        if (mci == NULL)
+                return -ENOMEM;
 
         debugf0("%s(): mci = %p\n", __func__, mci);
-        mci->pdev = pdev;
+        mci->dev = &pdev->dev;
         mci->mtype_cap = MEM_FLAG_RDDR | MEM_FLAG_DDR;
         mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_EC | EDAC_FLAG_SECDED;
         /* FIXME try to work out if the chip leads have been used for COM2
@@ -245,7 +295,7 @@ static int r82600_probe1(struct pci_dev *pdev, int dev_idx)
          * is possible.                                               */
         mci->edac_cap = EDAC_FLAG_NONE | EDAC_FLAG_EC | EDAC_FLAG_SECDED;
 
-        if (ecc_on) {
+        if (ecc_enabled(dramcr)) {
                 if (scrub_disabled)
                         debugf3("%s(): mci = %p - Scrubbing disabled! EAP: "
                                 "%#0x\n", __func__, mci, eapr);
@@ -253,53 +303,17 @@ static int r82600_probe1(struct pci_dev *pdev, int dev_idx)
                 mci->edac_cap = EDAC_FLAG_NONE;
 
         mci->mod_name = EDAC_MOD_STR;
-        mci->mod_ver = "$Revision: 1.1.2.6 $";
+        mci->mod_ver = R82600_REVISION;
         mci->ctl_name = "R82600";
         mci->edac_check = r82600_check;
         mci->ctl_page_to_phys = NULL;
-
-        for (index = 0; index < mci->nr_csrows; index++) {
-                struct csrow_info *csrow = &mci->csrows[index];
-                u8 drbar;       /* sDram Row Boundry Address Register */
-                u32 row_high_limit;
-                u32 row_base;
-
-                /* find the DRAM Chip Select Base address and mask */
-                pci_read_config_byte(mci->pdev, R82600_DRBA + index, &drbar);
-
-                debugf1("MC%d: %s() Row=%d DRBA = %#0x\n", mci->mc_idx,
-                        __func__, index, drbar);
-
-                row_high_limit = ((u32) drbar << 24);
-/*              row_high_limit = ((u32)drbar << 24) | 0xffffffUL; */
-
-                debugf1("MC%d: %s() Row=%d, Boundry Address=%#0x, Last = "
-                        "%#0x \n", mci->mc_idx, __func__, index,
-                        row_high_limit, row_high_limit_last);
-
-                /* Empty row [p.57] */
-                if (row_high_limit == row_high_limit_last)
-                        continue;
-
-                row_base = row_high_limit_last;
-                csrow->first_page = row_base >> PAGE_SHIFT;
-                csrow->last_page = (row_high_limit >> PAGE_SHIFT) - 1;
-                csrow->nr_pages = csrow->last_page - csrow->first_page + 1;
-                /* Error address is top 19 bits - so granularity is      *
-                 * 14 bits                                               */
-                csrow->grain = 1 << 14;
-                csrow->mtype = reg_sdram ? MEM_RDDR : MEM_DDR;
-                /* FIXME - check that this is unknowable with this chipset */
-                csrow->dtype = DEV_UNKNOWN;
-
-                /* Mode is global on 82600 */
-                csrow->edac_mode = ecc_on ? EDAC_SECDED : EDAC_NONE;
-                row_high_limit_last = row_high_limit;
-        }
-
+        r82600_init_csrows(mci, pdev, dramcr);
         r82600_get_error_info(mci, &discard);  /* clear counters */
 
-        if (edac_mc_add_mc(mci)) {
+        /* Here we assume that we will never see multiple instances of this
+         * type of memory controller.  The ID is therefore hardcoded to 0.
+         */
+        if (edac_mc_add_mc(mci,0)) {
                 debugf3("%s(): failed edac_mc_add_mc()\n", __func__);
                 goto fail;
         }
@@ -309,17 +323,15 @@ static int r82600_probe1(struct pci_dev *pdev, int dev_idx)
         if (disable_hardware_scrub) {
                 debugf3("%s(): Disabling Hardware Scrub (scrub on error)\n",
                         __func__);
-                pci_write_bits32(mci->pdev, R82600_EAP, BIT(31), BIT(31));
+                pci_write_bits32(pdev, R82600_EAP, BIT(31), BIT(31));
         }
 
         debugf3("%s(): success\n", __func__);
         return 0;
 
 fail:
-        if (mci)
-                edac_mc_free(mci);
-
-        return rc;
+        edac_mc_free(mci);
+        return -ENODEV;
 }
 
 /* returns count (>= 0), or negative on error */
@@ -338,7 +350,7 @@ static void __devexit r82600_remove_one(struct pci_dev *pdev)
 
         debugf0("%s()\n", __func__);
 
-        if ((mci = edac_mc_del_mc(pdev)) == NULL)
+        if ((mci = edac_mc_del_mc(&pdev->dev)) == NULL)
                 return;
 
         edac_mc_free(mci);
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 8b46ef7d9ff8..7be1d0a3e8f8 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -494,8 +494,8 @@ static int __devinit i801_probe(struct pci_dev *dev, const struct pci_device_id
         err = pci_request_region(dev, SMBBAR, i801_driver.name);
         if (err) {
                 dev_err(&dev->dev, "Failed to request SMBus region "
-                        "0x%lx-0x%lx\n", i801_smba,
-                        pci_resource_end(dev, SMBBAR));
+                        "0x%lx-0x%Lx\n", i801_smba,
+                        (unsigned long long)pci_resource_end(dev, SMBBAR));
                 goto exit;
         }
 
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 4c3f2de2a06e..b2c033edb03c 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -54,7 +54,6 @@
 #include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/ioctl.h>
-#include <linux/devfs_fs_kernel.h>
 #include <linux/cdev.h>
 #include <linux/in.h>
 #include <linux/net.h>
diff --git a/drivers/input/serio/i8042-sparcio.h b/drivers/input/serio/i8042-sparcio.h
index 6d66351805a2..9cad197a4e68 100644
--- a/drivers/input/serio/i8042-sparcio.h
+++ b/drivers/input/serio/i8042-sparcio.h
@@ -3,11 +3,9 @@
 
 #include <linux/config.h>
 #include <asm/io.h>
-
-#ifdef CONFIG_PCI
 #include <asm/oplib.h>
-#include <asm/ebus.h>
-#endif
+#include <asm/prom.h>
+#include <asm/of_device.h>
 
 static int i8042_kbd_irq = -1;
 static int i8042_aux_irq = -1;
@@ -48,54 +46,83 @@ static inline void i8042_write_command(int val)
 #define OBP_PS2MS_NAME1         "kdmouse"
 #define OBP_PS2MS_NAME2         "mouse"
 
+static int __devinit sparc_i8042_probe(struct of_device *op, const struct of_device_id *match)
+{
+        struct device_node *dp = op->node;
+
+        dp = dp->child;
+        while (dp) {
+                if (!strcmp(dp->name, OBP_PS2KBD_NAME1) ||
+                    !strcmp(dp->name, OBP_PS2KBD_NAME2)) {
+                        struct of_device *kbd = of_find_device_by_node(dp);
+                        unsigned int irq = kbd->irqs[0];
+                        if (irq == 0xffffffff)
+                                irq = op->irqs[0];
+                        i8042_kbd_irq = irq;
+                        kbd_iobase = of_ioremap(&kbd->resource[0],
+                                                0, 8, "kbd");
+                } else if (!strcmp(dp->name, OBP_PS2MS_NAME1) ||
+                           !strcmp(dp->name, OBP_PS2MS_NAME2)) {
+                        struct of_device *ms = of_find_device_by_node(dp);
+                        unsigned int irq = ms->irqs[0];
+                        if (irq == 0xffffffff)
+                                irq = op->irqs[0];
+                        i8042_aux_irq = irq;
+                }
+
+                dp = dp->sibling;
+        }
+
+        return 0;
+}
+
+static int __devexit sparc_i8042_remove(struct of_device *op)
+{
+        of_iounmap(kbd_iobase, 8);
+
+        return 0;
+}
+
+static struct of_device_id sparc_i8042_match[] = {
+        {
+                .name = "8042",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, i8042_match);
+
+static struct of_platform_driver sparc_i8042_driver = {
+        .name           = "i8042",
+        .match_table    = sparc_i8042_match,
+        .probe          = sparc_i8042_probe,
+        .remove         = __devexit_p(sparc_i8042_remove),
+};
+
 static int __init i8042_platform_init(void)
 {
 #ifndef CONFIG_PCI
         return -ENODEV;
 #else
-        char prop[128];
-        int len;
+        struct device_node *root = of_find_node_by_path("/");
 
-        len = prom_getproperty(prom_root_node, "name", prop, sizeof(prop));
-        if (len < 0) {
-                printk("i8042: Cannot get name property of root OBP node.\n");
-                return -ENODEV;
-        }
-        if (strncmp(prop, "SUNW,JavaStation-1", len) == 0) {
+        if (!strcmp(root->name, "SUNW,JavaStation-1")) {
                 /* Hardcoded values for MrCoffee.  */
                 i8042_kbd_irq = i8042_aux_irq = 13 | 0x20;
                 kbd_iobase = ioremap(0x71300060, 8);
                 if (!kbd_iobase)
                         return -ENODEV;
         } else {
-                struct linux_ebus *ebus;
-                struct linux_ebus_device *edev;
-                struct linux_ebus_child *child;
-
-                for_each_ebus(ebus) {
-                        for_each_ebusdev(edev, ebus) {
-                                if (!strcmp(edev->prom_node->name, "8042"))
-                                        goto edev_found;
-                        }
-                }
-                return -ENODEV;
-
-        edev_found:
-                for_each_edevchild(edev, child) {
-                        if (!strcmp(child->prom_node->name, OBP_PS2KBD_NAME1) ||
-                            !strcmp(child->prom_node->name, OBP_PS2KBD_NAME2)) {
-                                i8042_kbd_irq = child->irqs[0];
-                                kbd_iobase =
-                                        ioremap(child->resource[0].start, 8);
-                        }
-                        if (!strcmp(child->prom_node->name, OBP_PS2MS_NAME1) ||
-                            !strcmp(child->prom_node->name, OBP_PS2MS_NAME2))
-                                i8042_aux_irq = child->irqs[0];
-                }
+                int err = of_register_driver(&sparc_i8042_driver,
+                                             &of_bus_type);
+                if (err)
+                        return err;
+
                 if (i8042_kbd_irq == -1 ||
                     i8042_aux_irq == -1) {
-                        printk("i8042: Error, 8042 device lacks both kbd and "
-                               "mouse nodes.\n");
+                        if (kbd_iobase) {
+                                of_iounmap(kbd_iobase, 8);
+                                kbd_iobase = (void __iomem *) NULL;
+                        }
                         return -ENODEV;
                 }
         }
@@ -109,7 +136,10 @@ static int __init i8042_platform_init(void)
 static inline void i8042_platform_exit(void)
 {
 #ifdef CONFIG_PCI
-        iounmap(kbd_iobase);
+        struct device_node *root = of_find_node_by_path("/");
+
+        if (strcmp(root->name, "SUNW,JavaStation-1"))
+                of_unregister_driver(&sparc_i8042_driver);
 #endif
 }
 
diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index 7635736cc791..d55b0f7939a6 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -57,8 +57,8 @@
 
 #define DRV_MODULE_NAME         "bnx2"
 #define PFX DRV_MODULE_NAME     ": "
-#define DRV_MODULE_VERSION      "1.4.42"
-#define DRV_MODULE_RELDATE      "June 12, 2006"
+#define DRV_MODULE_VERSION      "1.4.43"
+#define DRV_MODULE_RELDATE      "June 28, 2006"
 
 #define RUN_AT(x) (jiffies + (x))
 
@@ -1676,7 +1676,7 @@ bnx2_tx_int(struct bnx2 *bp)
 
                 tx_free_bd += last + 1;
 
-                dev_kfree_skb_irq(skb);
+                dev_kfree_skb(skb);
 
                 hw_cons = bp->hw_tx_cons =
                         sblk->status_tx_quick_consumer_index0;
@@ -1824,7 +1824,7 @@ reuse_rx:
                 if ((len > (bp->dev->mtu + ETH_HLEN)) &&
                         (ntohs(skb->protocol) != 0x8100)) {
 
-                        dev_kfree_skb_irq(skb);
+                        dev_kfree_skb(skb);
                         goto next_rx;
 
                 }
@@ -3643,7 +3643,7 @@ bnx2_free_tx_skbs(struct bnx2 *bp)
                                 skb_shinfo(skb)->frags[j].size,
                                 PCI_DMA_TODEVICE);
                 }
-                dev_kfree_skb_any(skb);
+                dev_kfree_skb(skb);
                 i += j + 1;
         }
 
@@ -3669,7 +3669,7 @@ bnx2_free_rx_skbs(struct bnx2 *bp)
 
                 rx_buf->skb = NULL;
 
-                dev_kfree_skb_any(skb);
+                dev_kfree_skb(skb);
         }
 }
 
@@ -3999,7 +3999,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
         udelay(5);
 
         pci_unmap_single(bp->pdev, map, pkt_size, PCI_DMA_TODEVICE);
-        dev_kfree_skb_irq(skb);
+        dev_kfree_skb(skb);
 
         if (bp->status_blk->status_tx_quick_consumer_index0 != bp->tx_prod) {
                 goto loopback_test_done;
@@ -4541,7 +4541,7 @@ bnx2_close(struct net_device *dev)
         bnx2_netif_stop(bp);
         del_timer_sync(&bp->timer);
         if (bp->flags & NO_WOL_FLAG)
-                reset_code = BNX2_DRV_MSG_CODE_UNLOAD;
+                reset_code = BNX2_DRV_MSG_CODE_UNLOAD_LNK_DN;
         else if (bp->wol)
                 reset_code = BNX2_DRV_MSG_CODE_SUSPEND_WOL;
         else
@@ -5128,6 +5128,16 @@ bnx2_set_rx_csum(struct net_device *dev, u32 data)
         return 0;
 }
 
+static int
+bnx2_set_tso(struct net_device *dev, u32 data)
+{
+        if (data)
+                dev->features |= NETIF_F_TSO | NETIF_F_TSO_ECN;
+        else
+                dev->features &= ~(NETIF_F_TSO | NETIF_F_TSO_ECN);
+        return 0;
+}
+
 #define BNX2_NUM_STATS 46
 
 static struct {
@@ -5445,7 +5455,7 @@ static struct ethtool_ops bnx2_ethtool_ops = {
         .set_sg                 = ethtool_op_set_sg,
 #ifdef BCM_TSO
         .get_tso                = ethtool_op_get_tso,
-        .set_tso                = ethtool_op_set_tso,
+        .set_tso                = bnx2_set_tso,
 #endif
         .self_test_count        = bnx2_self_test_count,
         .self_test              = bnx2_self_test,
@@ -5926,7 +5936,7 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
         dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
 #endif
 #ifdef BCM_TSO
-        dev->features |= NETIF_F_TSO;
+        dev->features |= NETIF_F_TSO | NETIF_F_TSO_ECN;
 #endif
 
         netif_carrier_off(bp->dev);
@@ -5968,7 +5978,7 @@ bnx2_suspend(struct pci_dev *pdev, pm_message_t state)
         netif_device_detach(dev);
         del_timer_sync(&bp->timer);
         if (bp->flags & NO_WOL_FLAG)
-                reset_code = BNX2_DRV_MSG_CODE_UNLOAD;
+                reset_code = BNX2_DRV_MSG_CODE_UNLOAD_LNK_DN;
         else if (bp->wol)
                 reset_code = BNX2_DRV_MSG_CODE_SUSPEND_WOL;
         else
diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h
index 5845e334941b..658c5ee95c73 100644
--- a/drivers/net/bnx2.h
+++ b/drivers/net/bnx2.h
@@ -4174,6 +4174,7 @@ struct fw_info {
 #define BNX2_DRV_MSG_CODE_PULSE                  0x06000000
 #define BNX2_DRV_MSG_CODE_DIAG                   0x07000000
 #define BNX2_DRV_MSG_CODE_SUSPEND_NO_WOL         0x09000000
+#define BNX2_DRV_MSG_CODE_UNLOAD_LNK_DN          0x0b000000
 
 #define BNX2_DRV_MSG_DATA                        0x00ff0000
 #define BNX2_DRV_MSG_DATA_WAIT0                  0x00010000
diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig
index d2ce4896abff..e9e6d99a9add 100644
--- a/drivers/net/irda/Kconfig
+++ b/drivers/net/irda/Kconfig
@@ -350,7 +350,7 @@ config TOSHIBA_FIR
 
 config AU1000_FIR
         tristate "Alchemy Au1000 SIR/FIR"
-        depends on MIPS_AU1000 && IRDA
+        depends on SOC_AU1000 && IRDA
 
 config SMC_IRCC_FIR
         tristate "SMSC IrCC (EXPERIMENTAL)"
diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index 754297fc8f22..47f6f64d604c 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -101,7 +101,7 @@ static int transceiver_type = MCS_TSC_VISHAY;
 module_param(transceiver_type, int, 0444);
 MODULE_PARM_DESC(transceiver_type, "IR transceiver type, see mcs7780.h.");
 
-struct usb_driver mcs_driver = {
+static struct usb_driver mcs_driver = {
         .name = "mcs7780",
         .probe = mcs_probe,
         .disconnect = mcs_disconnect,
diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c
index c33ead3470db..9b246e44f756 100644
--- a/drivers/net/sunhme.c
+++ b/drivers/net/sunhme.c
@@ -2523,7 +2523,7 @@ static struct ethtool_ops hme_ethtool_ops = {
 static int hme_version_printed;
 
 #ifdef CONFIG_SBUS
-void __init quattro_get_ranges(struct quattro *qp)
+void __devinit quattro_get_ranges(struct quattro *qp)
 {
         struct sbus_dev *sdev = qp->quattro_dev;
         int err;
@@ -2539,7 +2539,7 @@ void __init quattro_get_ranges(struct quattro *qp)
         qp->nranges = (err / sizeof(struct linux_prom_ranges));
 }
 
-static void __init quattro_apply_ranges(struct quattro *qp, struct happy_meal *hp)
+static void __devinit quattro_apply_ranges(struct quattro *qp, struct happy_meal *hp)
 {
         struct sbus_dev *sdev = hp->happy_dev;
         int rng;
@@ -2566,7 +2566,7 @@ static void __init quattro_apply_ranges(struct quattro *qp, struct happy_meal *h
  *
  * Return NULL on failure.
  */
-static struct quattro * __init quattro_sbus_find(struct sbus_dev *goal_sdev)
+static struct quattro * __devinit quattro_sbus_find(struct sbus_dev *goal_sdev)
 {
         struct sbus_dev *sdev;
         struct quattro *qp;
@@ -2618,7 +2618,7 @@ static void __init quattro_sbus_register_irqs(void)
         }
 }
 
-static void __devexit quattro_sbus_free_irqs(void)
+static void quattro_sbus_free_irqs(void)
 {
         struct quattro *qp;
 
@@ -2662,7 +2662,7 @@ static struct quattro * __init quattro_pci_find(struct pci_dev *pdev)
 #endif /* CONFIG_PCI */
 
 #ifdef CONFIG_SBUS
-static int __init happy_meal_sbus_probe_one(struct sbus_dev *sdev, int is_qfe)
+static int __devinit happy_meal_sbus_probe_one(struct sbus_dev *sdev, int is_qfe)
 {
         struct device_node *dp = sdev->ofdev.node;
         struct quattro *qp = NULL;
diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c
index 298f2ddb2c17..d7024c7483bd 100644
--- a/drivers/parisc/led.c
+++ b/drivers/parisc/led.c
@@ -411,16 +411,17 @@ static __inline__ int led_get_net_activity(void)
 static __inline__ int led_get_diskio_activity(void)
 {       
         static unsigned long last_pgpgin, last_pgpgout;
-        struct page_state pgstat;
+        unsigned long events[NR_VM_EVENT_ITEMS];
         int changed;
 
-        get_full_page_state(&pgstat); /* get no of sectors in & out */
+        all_vm_events(events);
 
         /* Just use a very simple calculation here. Do not care about overflow,
            since we only want to know if there was activity or not. */
-        changed = (pgstat.pgpgin != last_pgpgin) || (pgstat.pgpgout != last_pgpgout);
-        last_pgpgin  = pgstat.pgpgin;
-        last_pgpgout = pgstat.pgpgout;
+        changed = (events[PGPGIN] != last_pgpgin) ||
+                  (events[PGPGOUT] != last_pgpgout);
+        last_pgpgin  = events[PGPGIN];
+        last_pgpgout = events[PGPGOUT];
 
         return (changed ? LED_DISK_IO : 0);
 }
diff --git a/drivers/serial/sunsab.c b/drivers/serial/sunsab.c
index 7da02d11c364..141fedbefbc4 100644
--- a/drivers/serial/sunsab.c
+++ b/drivers/serial/sunsab.c
@@ -1,7 +1,7 @@
 /* sunsab.c: ASYNC Driver for the SIEMENS SAB82532 DUSCC.
  *
  * Copyright (C) 1997  Eddie C. Dost  (ecd@skynet.be)
- * Copyright (C) 2002  David S. Miller (davem@redhat.com)
+ * Copyright (C) 2002, 2006  David S. Miller (davem@davemloft.net)
  *
  * Rewrote buffer handling to use CIRC(Circular Buffer) macros.
  *   Maxim Krasnyanskiy <maxk@qualcomm.com>
@@ -12,7 +12,7 @@
  *   Theodore Ts'o <tytso@mit.edu>, 2001-Oct-12
  *
  * Ported to new 2.5.x UART layer.
- *   David S. Miller <davem@redhat.com>
+ *   David S. Miller <davem@davemloft.net>
  */
 
 #include <linux/config.h>
@@ -37,8 +37,8 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/oplib.h>
-#include <asm/ebus.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 
 #if defined(CONFIG_SERIAL_SUNZILOG_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 #define SUPPORT_SYSRQ
@@ -976,199 +976,188 @@ static inline struct console *SUNSAB_CONSOLE(void)
 #define sunsab_console_init()   do { } while (0)
 #endif
 
-static void __init for_each_sab_edev(void (*callback)(struct linux_ebus_device *, void *), void *arg)
+static int __devinit sunsab_init_one(struct uart_sunsab_port *up,
+                                     struct of_device *op,
+                                     unsigned long offset,
+                                     int line)
 {
-        struct linux_ebus *ebus;
-        struct linux_ebus_device *edev = NULL;
-
-        for_each_ebus(ebus) {
-                for_each_ebusdev(edev, ebus) {
-                        if (!strcmp(edev->prom_node->name, "se")) {
-                                callback(edev, arg);
-                                continue;
-                        } else if (!strcmp(edev->prom_node->name, "serial")) {
-                                char *compat;
-                                int clen;
-
-                                /* On RIO this can be an SE, check it.  We could
-                                 * just check ebus->is_rio, but this is more portable.
-                                 */
-                                compat = of_get_property(edev->prom_node,
-                                                         "compatible", &clen);
-                                if (compat && clen > 0) {
-                                        if (strncmp(compat, "sab82532", 8) == 0) {
-                                                callback(edev, arg);
-                                                continue;
-                                        }
-                                }
-                        }
-                }
-        }
-}
+        up->port.line = line;
+        up->port.dev = &op->dev;
+
+        up->port.mapbase = op->resource[0].start + offset;
+        up->port.membase = of_ioremap(&op->resource[0], offset,
+                                      sizeof(union sab82532_async_regs),
+                                      "sab");
+        if (!up->port.membase)
+                return -ENOMEM;
+        up->regs = (union sab82532_async_regs __iomem *) up->port.membase;
 
-static void __init sab_count_callback(struct linux_ebus_device *edev, void *arg)
-{
-        int *count_p = arg;
+        up->port.irq = op->irqs[0];
 
-        (*count_p)++;
-}
+        up->port.fifosize = SAB82532_XMIT_FIFO_SIZE;
+        up->port.iotype = UPIO_MEM;
 
-static void __init sab_attach_callback(struct linux_ebus_device *edev, void *arg)
-{
-        int *instance_p = arg;
-        struct uart_sunsab_port *up;
-        unsigned long regs, offset;
-        int i;
+        writeb(SAB82532_IPC_IC_ACT_LOW, &up->regs->w.ipc);
 
-        /* Note: ports are located in reverse order */
-        regs = edev->resource[0].start;
-        offset = sizeof(union sab82532_async_regs);
-        for (i = 0; i < 2; i++) {
-                up = &sunsab_ports[(*instance_p * 2) + 1 - i];
+        up->port.ops = &sunsab_pops;
+        up->port.type = PORT_SUNSAB;
+        up->port.uartclk = SAB_BASE_BAUD;
 
-                memset(up, 0, sizeof(*up));
-                up->regs = ioremap(regs + offset, sizeof(union sab82532_async_regs));
-                up->port.irq = edev->irqs[0];
-                up->port.fifosize = SAB82532_XMIT_FIFO_SIZE;
-                up->port.mapbase = (unsigned long)up->regs;
-                up->port.iotype = UPIO_MEM;
+        up->type = readb(&up->regs->r.vstr) & 0x0f;
+        writeb(~((1 << 1) | (1 << 2) | (1 << 4)), &up->regs->w.pcr);
+        writeb(0xff, &up->regs->w.pim);
+        if ((up->port.line & 0x1) == 0) {
+                up->pvr_dsr_bit = (1 << 0);
+                up->pvr_dtr_bit = (1 << 1);
+        } else {
+                up->pvr_dsr_bit = (1 << 3);
+                up->pvr_dtr_bit = (1 << 2);
+        }
+        up->cached_pvr = (1 << 1) | (1 << 2) | (1 << 4);
+        writeb(up->cached_pvr, &up->regs->w.pvr);
+        up->cached_mode = readb(&up->regs->rw.mode);
+        up->cached_mode |= SAB82532_MODE_FRTS;
+        writeb(up->cached_mode, &up->regs->rw.mode);
+        up->cached_mode |= SAB82532_MODE_RTS;
+        writeb(up->cached_mode, &up->regs->rw.mode);
 
-                writeb(SAB82532_IPC_IC_ACT_LOW, &up->regs->w.ipc);
+        up->tec_timeout = SAB82532_MAX_TEC_TIMEOUT;
+        up->cec_timeout = SAB82532_MAX_CEC_TIMEOUT;
 
-                offset -= sizeof(union sab82532_async_regs);
+        if (!(up->port.line & 0x01)) {
+                int err;
+
+                err = request_irq(up->port.irq, sunsab_interrupt,
+                                  SA_SHIRQ, "sab", up);
+                if (err) {
+                        of_iounmap(up->port.membase,
+                                   sizeof(union sab82532_async_regs));
+                        return err;
+                }
         }
-        
-        (*instance_p)++;
+
+        return 0;
 }
 
-static int __init probe_for_sabs(void)
+static int __devinit sab_probe(struct of_device *op, const struct of_device_id *match)
 {
-        int this_sab = 0;
+        static int inst;
+        struct uart_sunsab_port *up;
+        int err;
+
+        up = &sunsab_ports[inst * 2];
+
+        err = sunsab_init_one(&up[0], op,
+                              sizeof(union sab82532_async_regs),
+                              (inst * 2) + 0);
+        if (err)
+                return err;
+
+        err = sunsab_init_one(&up[0], op, 0,
+                              (inst * 2) + 1);
+        if (err) {
+                of_iounmap(up[0].port.membase,
+                           sizeof(union sab82532_async_regs));
+                free_irq(up[0].port.irq, &up[0]);
+                return err;
+        }
 
-        /* Find device instances.  */
-        for_each_sab_edev(&sab_count_callback, &this_sab);
-        if (!this_sab)
-                return -ENODEV;
+        uart_add_one_port(&sunsab_reg, &up[0].port);
+        uart_add_one_port(&sunsab_reg, &up[1].port);
 
-        /* Allocate tables.  */
-        sunsab_ports = kmalloc(sizeof(struct uart_sunsab_port) * this_sab * 2,
-                               GFP_KERNEL);
-        if (!sunsab_ports)
-                return -ENOMEM;
+        dev_set_drvdata(&op->dev, &up[0]);
 
-        num_channels = this_sab * 2;
+        inst++;
 
-        this_sab = 0;
-        for_each_sab_edev(&sab_attach_callback, &this_sab);
         return 0;
 }
 
-static void __init sunsab_init_hw(void)
+static void __devexit sab_remove_one(struct uart_sunsab_port *up)
 {
-        int i;
-
-        for (i = 0; i < num_channels; i++) {
-                struct uart_sunsab_port *up = &sunsab_ports[i];
-
-                up->port.line = i;
-                up->port.ops = &sunsab_pops;
-                up->port.type = PORT_SUNSAB;
-                up->port.uartclk = SAB_BASE_BAUD;
-
-                up->type = readb(&up->regs->r.vstr) & 0x0f;
-                writeb(~((1 << 1) | (1 << 2) | (1 << 4)), &up->regs->w.pcr);
-                writeb(0xff, &up->regs->w.pim);
-                if (up->port.line == 0) {
-                        up->pvr_dsr_bit = (1 << 0);
-                        up->pvr_dtr_bit = (1 << 1);
-                } else {
-                        up->pvr_dsr_bit = (1 << 3);
-                        up->pvr_dtr_bit = (1 << 2);
-                }
-                up->cached_pvr = (1 << 1) | (1 << 2) | (1 << 4);
-                writeb(up->cached_pvr, &up->regs->w.pvr);
-                up->cached_mode = readb(&up->regs->rw.mode);
-                up->cached_mode |= SAB82532_MODE_FRTS;
-                writeb(up->cached_mode, &up->regs->rw.mode);
-                up->cached_mode |= SAB82532_MODE_RTS;
-                writeb(up->cached_mode, &up->regs->rw.mode);
-
-                up->tec_timeout = SAB82532_MAX_TEC_TIMEOUT;
-                up->cec_timeout = SAB82532_MAX_CEC_TIMEOUT;
-
-                if (!(up->port.line & 0x01)) {
-                        if (request_irq(up->port.irq, sunsab_interrupt,
-                                        SA_SHIRQ, "serial(sab82532)", up)) {
-                                printk("sunsab%d: can't get IRQ %x\n",
-                                       i, up->port.irq);
-                                continue;
-                        }
-                }
-        }
+        uart_remove_one_port(&sunsab_reg, &up->port);
+        if (!(up->port.line & 1))
+                free_irq(up->port.irq, up);
+        of_iounmap(up->port.membase,
+                   sizeof(union sab82532_async_regs));
 }
 
-static int __init sunsab_init(void)
+static int __devexit sab_remove(struct of_device *op)
 {
-        int ret = probe_for_sabs();
-        int i;
-
-        if (ret < 0)
-                return ret;
+        struct uart_sunsab_port *up = dev_get_drvdata(&op->dev);
 
-        sunsab_init_hw();
+        sab_remove_one(&up[0]);
+        sab_remove_one(&up[1]);
 
-        sunsab_reg.minor = sunserial_current_minor;
-        sunsab_reg.nr = num_channels;
+        dev_set_drvdata(&op->dev, NULL);
 
-        ret = uart_register_driver(&sunsab_reg);
-        if (ret < 0) {
-                int i;
+        return 0;
+}
 
-                for (i = 0; i < num_channels; i++) {
-                        struct uart_sunsab_port *up = &sunsab_ports[i];
+static struct of_device_id sab_match[] = {
+        {
+                .name = "se",
+        },
+        {
+                .name = "serial",
+                .compatible = "sab82532",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, sab_match);
 
-                        if (!(up->port.line & 0x01))
-                                free_irq(up->port.irq, up);
-                        iounmap(up->regs);
-                }
-                kfree(sunsab_ports);
-                sunsab_ports = NULL;
+static struct of_platform_driver sab_driver = {
+        .name           = "sab",
+        .match_table    = sab_match,
+        .probe          = sab_probe,
+        .remove         = __devexit_p(sab_remove),
+};
 
-                return ret;
+static int __init sunsab_init(void)
+{
+        struct device_node *dp;
+        int err;
+
+        num_channels = 0;
+        for_each_node_by_name(dp, "su")
+                num_channels += 2;
+        for_each_node_by_name(dp, "serial") {
+                if (of_device_is_compatible(dp, "sab82532"))
+                        num_channels += 2;
         }
 
-        sunsab_reg.tty_driver->name_base = sunsab_reg.minor - 64;
+        if (num_channels) {
+                sunsab_ports = kzalloc(sizeof(struct uart_sunsab_port) *
+                                       num_channels, GFP_KERNEL);
+                if (!sunsab_ports)
+                        return -ENOMEM;
 
-        sunsab_reg.cons = SUNSAB_CONSOLE();
+                sunsab_reg.minor = sunserial_current_minor;
+                sunsab_reg.nr = num_channels;
 
-        sunserial_current_minor += num_channels;
-        
-        for (i = 0; i < num_channels; i++) {
-                struct uart_sunsab_port *up = &sunsab_ports[i];
+                err = uart_register_driver(&sunsab_reg);
+                if (err) {
+                        kfree(sunsab_ports);
+                        sunsab_ports = NULL;
 
-                uart_add_one_port(&sunsab_reg, &up->port);
+                        return err;
+                }
+
+                sunsab_reg.tty_driver->name_base = sunsab_reg.minor - 64;
+                sunsab_reg.cons = SUNSAB_CONSOLE();
+                sunserial_current_minor += num_channels;
         }
 
-        return 0;
+        return of_register_driver(&sab_driver, &of_bus_type);
 }
 
 static void __exit sunsab_exit(void)
 {
-        int i;
-
-        for (i = 0; i < num_channels; i++) {
-                struct uart_sunsab_port *up = &sunsab_ports[i];
-
-                uart_remove_one_port(&sunsab_reg, &up->port);
-
-                if (!(up->port.line & 0x01))
-                        free_irq(up->port.irq, up);
-                iounmap(up->regs);
+        of_unregister_driver(&sab_driver);
+        if (num_channels) {
+                sunserial_current_minor -= num_channels;
+                uart_unregister_driver(&sunsab_reg);
         }
 
-        sunserial_current_minor -= num_channels;
-        uart_unregister_driver(&sunsab_reg);
-
         kfree(sunsab_ports);
         sunsab_ports = NULL;
 }
diff --git a/drivers/serial/sunsu.c b/drivers/serial/sunsu.c
index 6e28c25138cf..73a043b914ef 100644
--- a/drivers/serial/sunsu.c
+++ b/drivers/serial/sunsu.c
@@ -12,7 +12,7 @@
  *   Theodore Ts'o <tytso@mit.edu>, 2001-Oct-12
  *
  * Converted to new 2.5.x UART layer.
- *   David S. Miller (davem@redhat.com), 2002-Jul-29
+ *   David S. Miller (davem@davemloft.net), 2002-Jul-29
  */
 
 #include <linux/config.h>
@@ -40,11 +40,8 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/oplib.h>
-#include <asm/ebus.h>
-#ifdef CONFIG_SPARC64
-#include <asm/isa.h>
-#endif
+#include <asm/prom.h>
+#include <asm/of_device.h>
 
 #if defined(CONFIG_SERIAL_SUNSU_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 #define SUPPORT_SYSRQ
@@ -94,10 +91,10 @@ struct uart_sunsu_port {
         /* Probing information.  */
         enum su_type            su_type;
         unsigned int            type_probed;    /* XXX Stupid */
-        int                     port_node;
+        unsigned long           reg_size;
 
 #ifdef CONFIG_SERIO
-        struct serio            *serio;
+        struct serio            serio;
         int                     serio_open;
 #endif
 };
@@ -509,7 +506,7 @@ static void receive_kbd_ms_chars(struct uart_sunsu_port *up, struct pt_regs *reg
                 /* Stop-A is handled by drivers/char/keyboard.c now. */
                 if (up->su_type == SU_PORT_KBD) {
 #ifdef CONFIG_SERIO
-                        serio_interrupt(up->serio, ch, 0, regs);
+                        serio_interrupt(&up->serio, ch, 0, regs);
 #endif
                 } else if (up->su_type == SU_PORT_MS) {
                         int ret = suncore_mouse_baud_detection(ch, is_break);
@@ -523,7 +520,7 @@ static void receive_kbd_ms_chars(struct uart_sunsu_port *up, struct pt_regs *reg
 
                         case 0:
 #ifdef CONFIG_SERIO
-                                serio_interrupt(up->serio, ch, 0, regs);
+                                serio_interrupt(&up->serio, ch, 0, regs);
 #endif
                                 break;
                         };
@@ -1031,99 +1028,14 @@ static void sunsu_autoconfig(struct uart_sunsu_port *up)
 {
         unsigned char status1, status2, scratch, scratch2, scratch3;
         unsigned char save_lcr, save_mcr;
-        struct linux_ebus_device *dev = NULL;
-        struct linux_ebus *ebus;
-#ifdef CONFIG_SPARC64
-        struct sparc_isa_bridge *isa_br;
-        struct sparc_isa_device *isa_dev;
-#endif
-#ifndef CONFIG_SPARC64
-        struct linux_prom_registers reg0;
-#endif
         unsigned long flags;
 
-        if (!up->port_node || !up->su_type)
+        if (up->su_type == SU_PORT_NONE)
                 return;
 
         up->type_probed = PORT_UNKNOWN;
         up->port.iotype = UPIO_MEM;
 
-        /*
-         * First we look for Ebus-bases su's
-         */
-        for_each_ebus(ebus) {
-                for_each_ebusdev(dev, ebus) {
-                        if (dev->prom_node->node == up->port_node) {
-                                /*
-                                 * The EBus is broken on sparc; it delivers
-                                 * virtual addresses in resources. Oh well...
-                                 * This is correct on sparc64, though.
-                                 */
-                                up->port.membase = (char *) dev->resource[0].start;
-                                /*
-                                 * This is correct on both architectures.
-                                 */
-                                up->port.mapbase = dev->resource[0].start;
-                                up->port.irq = dev->irqs[0];
-                                goto ebus_done;
-                        }
-                }
-        }
-
-#ifdef CONFIG_SPARC64
-        for_each_isa(isa_br) {
-                for_each_isadev(isa_dev, isa_br) {
-                        if (isa_dev->prom_node->node == up->port_node) {
-                                /* Same on sparc64. Cool architecure... */
-                                up->port.membase = (char *) isa_dev->resource.start;
-                                up->port.mapbase = isa_dev->resource.start;
-                                up->port.irq = isa_dev->irq;
-                                goto ebus_done;
-                        }
-                }
-        }
-#endif
-
-#ifdef CONFIG_SPARC64
-        /*
-         * Not on Ebus, bailing.
-         */
-        return;
-#else
-        /*
-         * Not on Ebus, must be OBIO.
-         */
-        if (prom_getproperty(up->port_node, "reg",
-                             (char *)&reg0, sizeof(reg0)) == -1) {
-                prom_printf("sunsu: no \"reg\" property\n");
-                return;
-        }
-        prom_apply_obio_ranges(&reg0, 1);
-        if (reg0.which_io != 0) {       /* Just in case... */
-                prom_printf("sunsu: bus number nonzero: 0x%x:%x\n",
-                    reg0.which_io, reg0.phys_addr);
-                return;
-        }
-        up->port.mapbase = reg0.phys_addr;
-        if ((up->port.membase = ioremap(reg0.phys_addr, reg0.reg_size)) == 0) {
-                prom_printf("sunsu: Cannot map registers.\n");
-                return;
-        }
-
-        /*
-         * 0x20 is sun4m thing, Dave Redman heritage.
-         * See arch/sparc/kernel/irq.c.
-         */
-#define IRQ_4M(n)       ((n)|0x20)
-
-        /*
-         * There is no intr property on MrCoffee, so hardwire it.
-         */
-        up->port.irq = IRQ_4M(13);
-#endif
-
-ebus_done:
-
         spin_lock_irqsave(&up->port.lock, flags);
 
         if (!(up->port.flags & UPF_BUGGY_UART)) {
@@ -1269,18 +1181,13 @@ static struct uart_driver sunsu_reg = {
         .major                  = TTY_MAJOR,
 };
 
-static int __init sunsu_kbd_ms_init(struct uart_sunsu_port *up, int channel)
+static int __init sunsu_kbd_ms_init(struct uart_sunsu_port *up)
 {
         int quot, baud;
 #ifdef CONFIG_SERIO
         struct serio *serio;
 #endif
 
-        spin_lock_init(&up->port.lock);
-        up->port.line = channel;
-        up->port.type = PORT_UNKNOWN;
-        up->port.uartclk = (SU_BASE_BAUD * 16);
-
         if (up->su_type == SU_PORT_KBD) {
                 up->cflag = B1200 | CS8 | CLOCAL | CREAD;
                 baud = 1200;
@@ -1292,41 +1199,31 @@ static int __init sunsu_kbd_ms_init(struct uart_sunsu_port *up, int channel)
 
         sunsu_autoconfig(up);
         if (up->port.type == PORT_UNKNOWN)
-                return -1;
-
-        printk(KERN_INFO "su%d at 0x%p (irq = %d) is a %s\n",
-               channel,
-               up->port.membase, up->port.irq,
-               sunsu_type(&up->port));
+                return -ENODEV;
 
 #ifdef CONFIG_SERIO
-        up->serio = serio = kmalloc(sizeof(struct serio), GFP_KERNEL);
-        if (serio) {
-                memset(serio, 0, sizeof(*serio));
-
-                serio->port_data = up;
-
-                serio->id.type = SERIO_RS232;
-                if (up->su_type == SU_PORT_KBD) {
-                        serio->id.proto = SERIO_SUNKBD;
-                        strlcpy(serio->name, "sukbd", sizeof(serio->name));
-                } else {
-                        serio->id.proto = SERIO_SUN;
-                        serio->id.extra = 1;
-                        strlcpy(serio->name, "sums", sizeof(serio->name));
-                }
-                strlcpy(serio->phys, (channel == 0 ? "su/serio0" : "su/serio1"),
-                        sizeof(serio->phys));
-
-                serio->write = sunsu_serio_write;
-                serio->open = sunsu_serio_open;
-                serio->close = sunsu_serio_close;
+        serio = &up->serio;
+        serio->port_data = up;
 
-                serio_register_port(serio);
+        serio->id.type = SERIO_RS232;
+        if (up->su_type == SU_PORT_KBD) {
+                serio->id.proto = SERIO_SUNKBD;
+                strlcpy(serio->name, "sukbd", sizeof(serio->name));
         } else {
-                printk(KERN_WARNING "su%d: not enough memory for serio port\n",
-                        channel);
+                serio->id.proto = SERIO_SUN;
+                serio->id.extra = 1;
+                strlcpy(serio->name, "sums", sizeof(serio->name));
         }
+        strlcpy(serio->phys,
+                (!(up->port.line & 1) ? "su/serio0" : "su/serio1"),
+                sizeof(serio->phys));
+
+        serio->write = sunsu_serio_write;
+        serio->open = sunsu_serio_open;
+        serio->close = sunsu_serio_close;
+        serio->dev.parent = up->port.dev;
+
+        serio_register_port(serio);
 #endif
 
         sunsu_change_speed(&up->port, up->cflag, 0, quot);
@@ -1458,22 +1355,20 @@ static struct console sunsu_cons = {
  *      Register console.
  */
 
-static inline struct console *SUNSU_CONSOLE(void)
+static inline struct console *SUNSU_CONSOLE(int num_uart)
 {
         int i;
 
         if (con_is_present())
                 return NULL;
 
-        for (i = 0; i < UART_NR; i++) {
+        for (i = 0; i < num_uart; i++) {
                 int this_minor = sunsu_reg.minor + i;
 
                 if ((this_minor - 64) == (serial_console - 1))
                         break;
         }
-        if (i == UART_NR)
-                return NULL;
-        if (sunsu_ports[i].port_node == 0)
+        if (i == num_uart)
                 return NULL;
 
         sunsu_cons.index = i;
@@ -1481,252 +1376,184 @@ static inline struct console *SUNSU_CONSOLE(void)
         return &sunsu_cons;
 }
 #else
-#define SUNSU_CONSOLE()                 (NULL)
+#define SUNSU_CONSOLE(num_uart)         (NULL)
 #define sunsu_serial_console_init()     do { } while (0)
 #endif
 
-static int __init sunsu_serial_init(void)
+static enum su_type __devinit su_get_type(struct device_node *dp)
 {
-        int instance, ret, i;
+        struct device_node *ap = of_find_node_by_path("/aliases");
 
-        /* How many instances do we need?  */
-        instance = 0;
-        for (i = 0; i < UART_NR; i++) {
-                struct uart_sunsu_port *up = &sunsu_ports[i];
+        if (ap) {
+                char *keyb = of_get_property(ap, "keyboard", NULL);
+                char *ms = of_get_property(ap, "mouse", NULL);
 
-                if (up->su_type == SU_PORT_MS ||
-                    up->su_type == SU_PORT_KBD)
-                        continue;
-
-                spin_lock_init(&up->port.lock);
-                up->port.flags |= UPF_BOOT_AUTOCONF;
-                up->port.type = PORT_UNKNOWN;
-                up->port.uartclk = (SU_BASE_BAUD * 16);
+                if (keyb) {
+                        if (dp == of_find_node_by_path(keyb))
+                                return SU_PORT_KBD;
+                }
+                if (ms) {
+                        if (dp == of_find_node_by_path(ms))
+                                return SU_PORT_MS;
+                }
+        }
 
-                sunsu_autoconfig(up);
-                if (up->port.type == PORT_UNKNOWN)
-                        continue;
+        return SU_PORT_PORT;
+}
 
-                up->port.line = instance++;
-                up->port.ops = &sunsu_pops;
-        }
+static int __devinit su_probe(struct of_device *op, const struct of_device_id *match)
+{
+        static int inst;
+        struct device_node *dp = op->node;
+        struct uart_sunsu_port *up;
+        struct resource *rp;
+        int err;
 
-        sunsu_reg.minor = sunserial_current_minor;
+        if (inst >= UART_NR)
+                return -EINVAL;
 
-        sunsu_reg.nr = instance;
+        up = &sunsu_ports[inst];
+        up->port.line = inst;
 
-        ret = uart_register_driver(&sunsu_reg);
-        if (ret < 0)
-                return ret;
+        spin_lock_init(&up->port.lock);
 
-        sunsu_reg.tty_driver->name_base = sunsu_reg.minor - 64;
+        up->su_type = su_get_type(dp);
 
-        sunserial_current_minor += instance;
+        rp = &op->resource[0];
+        up->port.mapbase = op->resource[0].start;
 
-        sunsu_reg.cons = SUNSU_CONSOLE();
+        up->reg_size = (rp->end - rp->start) + 1;
+        up->port.membase = of_ioremap(rp, 0, up->reg_size, "su");
+        if (!up->port.membase)
+                return -ENOMEM;
 
-        for (i = 0; i < UART_NR; i++) {
-                struct uart_sunsu_port *up = &sunsu_ports[i];
+        up->port.irq = op->irqs[0];
 
-                /* Do not register Keyboard/Mouse lines with UART
-                 * layer.
-                 */
-                if (up->su_type == SU_PORT_MS ||
-                    up->su_type == SU_PORT_KBD)
-                        continue;
+        up->port.dev = &op->dev;
 
-                if (up->port.type == PORT_UNKNOWN)
-                        continue;
+        up->port.type = PORT_UNKNOWN;
+        up->port.uartclk = (SU_BASE_BAUD * 16);
 
-                uart_add_one_port(&sunsu_reg, &up->port);
+        err = 0;
+        if (up->su_type == SU_PORT_KBD || up->su_type == SU_PORT_MS) {
+                err = sunsu_kbd_ms_init(up);
+                if (err)
+                        goto out_unmap;
         }
 
-        return 0;
-}
+        up->port.flags |= UPF_BOOT_AUTOCONF;
 
-static int su_node_ok(int node, char *name, int namelen)
-{
-        if (strncmp(name, "su", namelen) == 0 ||
-            strncmp(name, "su_pnp", namelen) == 0)
-                return 1;
-
-        if (strncmp(name, "serial", namelen) == 0) {
-                char compat[32];
-                int clen;
-
-                /* Is it _really_ a 'su' device? */
-                clen = prom_getproperty(node, "compatible", compat, sizeof(compat));
-                if (clen > 0) {
-                        if (strncmp(compat, "sab82532", 8) == 0) {
-                                /* Nope, Siemens serial, not for us. */
-                                return 0;
-                        }
-                }
-                return 1;
-        }
+        sunsu_autoconfig(up);
 
-        return 0;
-}
+        err = -ENODEV;
+        if (up->port.type == PORT_UNKNOWN)
+                goto out_unmap;
 
-#define SU_PROPSIZE     128
+        up->port.ops = &sunsu_pops;
 
-/*
- * Scan status structure.
- * "prop" is a local variable but it eats stack to keep it in each
- * stack frame of a recursive procedure.
- */
-struct su_probe_scan {
-        int msnode, kbnode;     /* PROM nodes for mouse and keyboard */
-        int msx, kbx;           /* minors for mouse and keyboard */
-        int devices;            /* scan index */
-        char prop[SU_PROPSIZE];
-};
+        err = uart_add_one_port(&sunsu_reg, &up->port);
+        if (err)
+                goto out_unmap;
 
-/*
- * We have several platforms which present 'su' in different parts
- * of the device tree. 'su' may be found under obio, ebus, isa and pci.
- * We walk over the tree and find them wherever PROM hides them.
- */
-static void __init su_probe_any(struct su_probe_scan *t, int sunode)
-{
-        struct uart_sunsu_port *up;
-        int len;
+        dev_set_drvdata(&op->dev, up);
 
-        if (t->devices >= UART_NR)
-                return;
+        inst++;
 
-        for (; sunode != 0; sunode = prom_getsibling(sunode)) {
-                len = prom_getproperty(sunode, "name", t->prop, SU_PROPSIZE);
-                if (len <= 1)
-                        continue;               /* Broken PROM node */
-
-                if (su_node_ok(sunode, t->prop, len)) {
-                        up = &sunsu_ports[t->devices];
-                        if (t->kbnode != 0 && sunode == t->kbnode) {
-                                t->kbx = t->devices;
-                                up->su_type = SU_PORT_KBD;
-                        } else if (t->msnode != 0 && sunode == t->msnode) {
-                                t->msx = t->devices;
-                                up->su_type = SU_PORT_MS;
-                        } else {
-#ifdef CONFIG_SPARC64
-                                /*
-                                 * Do not attempt to use the truncated
-                                 * keyboard/mouse ports as serial ports
-                                 * on Ultras with PC keyboard attached.
-                                 */
-                                if (prom_getbool(sunode, "mouse"))
-                                        continue;
-                                if (prom_getbool(sunode, "keyboard"))
-                                        continue;
-#endif
-                                up->su_type = SU_PORT_PORT;
-                        }
-                        up->port_node = sunode;
-                        ++t->devices;
-                } else {
-                        su_probe_any(t, prom_getchild(sunode));
-                }
-        }
+        return 0;
+
+out_unmap:
+        of_iounmap(up->port.membase, up->reg_size);
+        return err;
 }
 
-static int __init sunsu_probe(void)
+static int __devexit su_remove(struct of_device *dev)
 {
-        int node;
-        int len;
-        struct su_probe_scan scan;
+        struct uart_sunsu_port *up = dev_get_drvdata(&dev->dev);;
 
-        /*
-         * First, we scan the tree.
-         */
-        scan.devices = 0;
-        scan.msx = -1;
-        scan.kbx = -1;
-        scan.kbnode = 0;
-        scan.msnode = 0;
+        if (up->su_type == SU_PORT_MS ||
+            up->su_type == SU_PORT_KBD) {
+#ifdef CONFIG_SERIO
+                serio_unregister_port(&up->serio);
+#endif
+        } else if (up->port.type != PORT_UNKNOWN)
+                uart_remove_one_port(&sunsu_reg, &up->port);
 
-        /*
-         * Get the nodes for keyboard and mouse from 'aliases'...
-         */
-        node = prom_getchild(prom_root_node);
-        node = prom_searchsiblings(node, "aliases");
-        if (node != 0) {
-                len = prom_getproperty(node, "keyboard", scan.prop, SU_PROPSIZE);
-                if (len > 0) {
-                        scan.prop[len] = 0;
-                        scan.kbnode = prom_finddevice(scan.prop);
-                }
+        return 0;
+}
 
-                len = prom_getproperty(node, "mouse", scan.prop, SU_PROPSIZE);
-                if (len > 0) {
-                        scan.prop[len] = 0;
-                        scan.msnode = prom_finddevice(scan.prop);
-                }
-        }
+static struct of_device_id su_match[] = {
+        {
+                .name = "su",
+        },
+        {
+                .name = "su_pnp",
+        },
+        {
+                .name = "serial",
+                .compatible = "su",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, su_match);
 
-        su_probe_any(&scan, prom_getchild(prom_root_node));
+static struct of_platform_driver su_driver = {
+        .name           = "su",
+        .match_table    = su_match,
+        .probe          = su_probe,
+        .remove         = __devexit_p(su_remove),
+};
 
-        /*
-         * Second, we process the special case of keyboard and mouse.
-         *
-         * Currently if we got keyboard and mouse hooked to "su" ports
-         * we do not use any possible remaining "su" as a serial port.
-         * Thus, we ignore values of .msx and .kbx, then compact ports.
-         */
-        if (scan.msx != -1 && scan.kbx != -1) {
-                sunsu_ports[0].su_type = SU_PORT_MS;
-                sunsu_ports[0].port_node = scan.msnode;
-                sunsu_kbd_ms_init(&sunsu_ports[0], 0);
+static int num_uart;
 
-                sunsu_ports[1].su_type = SU_PORT_KBD;
-                sunsu_ports[1].port_node = scan.kbnode;
-                sunsu_kbd_ms_init(&sunsu_ports[1], 1);
+static int __init sunsu_init(void)
+{
+        struct device_node *dp;
+        int err;
 
-                return 0;
+        num_uart = 0;
+        for_each_node_by_name(dp, "su") {
+                if (su_get_type(dp) == SU_PORT_PORT)
+                        num_uart++;
         }
-
-        if (scan.msx != -1 || scan.kbx != -1) {
-                printk("sunsu_probe: cannot match keyboard and mouse, confused\n");
-                return -ENODEV;
+        for_each_node_by_name(dp, "su_pnp") {
+                if (su_get_type(dp) == SU_PORT_PORT)
+                        num_uart++;
+        }
+        for_each_node_by_name(dp, "serial") {
+                if (of_device_is_compatible(dp, "su")) {
+                        if (su_get_type(dp) == SU_PORT_PORT)
+                                num_uart++;
+                }
         }
 
-        if (scan.devices == 0)
-                return -ENODEV;
+        if (num_uart) {
+                sunsu_reg.minor = sunserial_current_minor;
+                sunsu_reg.nr = num_uart;
+                err = uart_register_driver(&sunsu_reg);
+                if (err)
+                        return err;
+                sunsu_reg.tty_driver->name_base = sunsu_reg.minor - 64;
+                sunserial_current_minor += num_uart;
+                sunsu_reg.cons = SUNSU_CONSOLE(num_uart);
+        }
 
-        /*
-         * Console must be initiated after the generic initialization.
-         */
-        sunsu_serial_init();
+        err = of_register_driver(&su_driver, &of_bus_type);
+        if (err && num_uart)
+                uart_unregister_driver(&sunsu_reg);
 
-        return 0;
+        return err;
 }
 
 static void __exit sunsu_exit(void)
 {
-        int i, saw_uart;
-
-        saw_uart = 0;
-        for (i = 0; i < UART_NR; i++) {
-                struct uart_sunsu_port *up = &sunsu_ports[i];
-
-                if (up->su_type == SU_PORT_MS ||
-                    up->su_type == SU_PORT_KBD) {
-#ifdef CONFIG_SERIO
-                        if (up->serio) {
-                                serio_unregister_port(up->serio);
-                                up->serio = NULL;
-                        }
-#endif
-                } else if (up->port.type != PORT_UNKNOWN) {
-                        uart_remove_one_port(&sunsu_reg, &up->port);
-                        saw_uart++;
-                }
-        }
-
-        if (saw_uart)
+        if (num_uart)
                 uart_unregister_driver(&sunsu_reg);
 }
 
-module_init(sunsu_probe);
+module_init(sunsu_init);
 module_exit(sunsu_exit);
+
+MODULE_AUTHOR("Eddie C. Dost, Peter Zaitcev, and David S. Miller");
+MODULE_DESCRIPTION("Sun SU serial port driver");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/serial/sunzilog.c b/drivers/serial/sunzilog.c
index 9f42677287ad..1caa286a6be6 100644
--- a/drivers/serial/sunzilog.c
+++ b/drivers/serial/sunzilog.c
@@ -1,5 +1,4 @@
-/*
- * sunzilog.c
+/* sunzilog.c: Zilog serial driver for Sparc systems.
  *
  * Driver for Zilog serial chips found on Sun workstations and
  * servers.  This driver could actually be made more generic.
@@ -10,7 +9,7 @@
  * C. Dost, Pete Zaitcev, Ted Ts'o and Alex Buell for their
  * work there.
  *
- *  Copyright (C) 2002 David S. Miller (davem@redhat.com)
+ *  Copyright (C) 2002, 2006 David S. Miller (davem@davemloft.net)
  */
 
 #include <linux/config.h>
@@ -38,10 +37,8 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#ifdef CONFIG_SPARC64
-#include <asm/fhc.h>
-#endif
-#include <asm/sbus.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 
 #if defined(CONFIG_SERIAL_SUNZILOG_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
 #define SUPPORT_SYSRQ
@@ -65,7 +62,7 @@
 #define ZSDELAY()
 #define ZSDELAY_LONG()
 #define ZS_WSYNC(__channel) \
-        sbus_readb(&((__channel)->control))
+        readb(&((__channel)->control))
 #endif
 
 static int num_sunzilog;
@@ -107,7 +104,7 @@ struct uart_sunzilog_port {
         unsigned char                   prev_status;
 
 #ifdef CONFIG_SERIO
-        struct serio                    *serio;
+        struct serio                    serio;
         int                             serio_open;
 #endif
 };
@@ -138,9 +135,9 @@ static unsigned char read_zsreg(struct zilog_channel __iomem *channel,
 {
         unsigned char retval;
 
-        sbus_writeb(reg, &channel->control);
+        writeb(reg, &channel->control);
         ZSDELAY();
-        retval = sbus_readb(&channel->control);
+        retval = readb(&channel->control);
         ZSDELAY();
 
         return retval;
@@ -149,9 +146,9 @@ static unsigned char read_zsreg(struct zilog_channel __iomem *channel,
 static void write_zsreg(struct zilog_channel __iomem *channel,
                         unsigned char reg, unsigned char value)
 {
-        sbus_writeb(reg, &channel->control);
+        writeb(reg, &channel->control);
         ZSDELAY();
-        sbus_writeb(value, &channel->control);
+        writeb(value, &channel->control);
         ZSDELAY();
 }
 
@@ -162,17 +159,17 @@ static void sunzilog_clear_fifo(struct zilog_channel __iomem *channel)
         for (i = 0; i < 32; i++) {
                 unsigned char regval;
 
-                regval = sbus_readb(&channel->control);
+                regval = readb(&channel->control);
                 ZSDELAY();
                 if (regval & Rx_CH_AV)
                         break;
 
                 regval = read_zsreg(channel, R1);
-                sbus_readb(&channel->data);
+                readb(&channel->data);
                 ZSDELAY();
 
                 if (regval & (PAR_ERR | Rx_OVR | CRC_ERR)) {
-                        sbus_writeb(ERR_RES, &channel->control);
+                        writeb(ERR_RES, &channel->control);
                         ZSDELAY();
                         ZS_WSYNC(channel);
                 }
@@ -194,7 +191,7 @@ static void __load_zsregs(struct zilog_channel __iomem *channel, unsigned char *
                 udelay(100);
         }
 
-        sbus_writeb(ERR_RES, &channel->control);
+        writeb(ERR_RES, &channel->control);
         ZSDELAY();
         ZS_WSYNC(channel);
 
@@ -291,7 +288,7 @@ static void sunzilog_kbdms_receive_chars(struct uart_sunzilog_port *up,
                 /* Stop-A is handled by drivers/char/keyboard.c now. */
 #ifdef CONFIG_SERIO
                 if (up->serio_open)
-                        serio_interrupt(up->serio, ch, 0, regs);
+                        serio_interrupt(&up->serio, ch, 0, regs);
 #endif
         } else if (ZS_IS_MOUSE(up)) {
                 int ret = suncore_mouse_baud_detection(ch, is_break);
@@ -306,7 +303,7 @@ static void sunzilog_kbdms_receive_chars(struct uart_sunzilog_port *up,
                 case 0:
 #ifdef CONFIG_SERIO
                         if (up->serio_open)
-                                serio_interrupt(up->serio, ch, 0, regs);
+                                serio_interrupt(&up->serio, ch, 0, regs);
 #endif
                         break;
                 };
@@ -330,12 +327,12 @@ sunzilog_receive_chars(struct uart_sunzilog_port *up,
 
                 r1 = read_zsreg(channel, R1);
                 if (r1 & (PAR_ERR | Rx_OVR | CRC_ERR)) {
-                        sbus_writeb(ERR_RES, &channel->control);
+                        writeb(ERR_RES, &channel->control);
                         ZSDELAY();
                         ZS_WSYNC(channel);
                 }
 
-                ch = sbus_readb(&channel->control);
+                ch = readb(&channel->control);
                 ZSDELAY();
 
                 /* This funny hack depends upon BRK_ABRT not interfering
@@ -347,7 +344,7 @@ sunzilog_receive_chars(struct uart_sunzilog_port *up,
                 if (!(ch & Rx_CH_AV))
                         break;
 
-                ch = sbus_readb(&channel->data);
+                ch = readb(&channel->data);
                 ZSDELAY();
 
                 ch &= up->parity_mask;
@@ -406,10 +403,10 @@ static void sunzilog_status_handle(struct uart_sunzilog_port *up,
 {
         unsigned char status;
 
-        status = sbus_readb(&channel->control);
+        status = readb(&channel->control);
         ZSDELAY();
 
-        sbus_writeb(RES_EXT_INT, &channel->control);
+        writeb(RES_EXT_INT, &channel->control);
         ZSDELAY();
         ZS_WSYNC(channel);
 
@@ -421,7 +418,7 @@ static void sunzilog_status_handle(struct uart_sunzilog_port *up,
                          * confusing the PROM.
                          */
                         while (1) {
-                                status = sbus_readb(&channel->control);
+                                status = readb(&channel->control);
                                 ZSDELAY();
                                 if (!(status & BRK_ABRT))
                                         break;
@@ -458,7 +455,7 @@ static void sunzilog_transmit_chars(struct uart_sunzilog_port *up,
         struct circ_buf *xmit;
 
         if (ZS_IS_CONS(up)) {
-                unsigned char status = sbus_readb(&channel->control);
+                unsigned char status = readb(&channel->control);
                 ZSDELAY();
 
                 /* TX still busy?  Just wait for the next TX done interrupt.
@@ -487,7 +484,7 @@ static void sunzilog_transmit_chars(struct uart_sunzilog_port *up,
 
         if (up->port.x_char) {
                 up->flags |= SUNZILOG_FLAG_TX_ACTIVE;
-                sbus_writeb(up->port.x_char, &channel->data);
+                writeb(up->port.x_char, &channel->data);
                 ZSDELAY();
                 ZS_WSYNC(channel);
 
@@ -506,7 +503,7 @@ static void sunzilog_transmit_chars(struct uart_sunzilog_port *up,
                 goto ack_tx_int;
 
         up->flags |= SUNZILOG_FLAG_TX_ACTIVE;
-        sbus_writeb(xmit->buf[xmit->tail], &channel->data);
+        writeb(xmit->buf[xmit->tail], &channel->data);
         ZSDELAY();
         ZS_WSYNC(channel);
 
@@ -519,7 +516,7 @@ static void sunzilog_transmit_chars(struct uart_sunzilog_port *up,
         return;
 
 ack_tx_int:
-        sbus_writeb(RES_Tx_P, &channel->control);
+        writeb(RES_Tx_P, &channel->control);
         ZSDELAY();
         ZS_WSYNC(channel);
 }
@@ -540,7 +537,7 @@ static irqreturn_t sunzilog_interrupt(int irq, void *dev_id, struct pt_regs *reg
                 /* Channel A */
                 tty = NULL;
                 if (r3 & (CHAEXT | CHATxIP | CHARxIP)) {
-                        sbus_writeb(RES_H_IUS, &channel->control);
+                        writeb(RES_H_IUS, &channel->control);
                         ZSDELAY();
                         ZS_WSYNC(channel);
 
@@ -563,7 +560,7 @@ static irqreturn_t sunzilog_interrupt(int irq, void *dev_id, struct pt_regs *reg
                 spin_lock(&up->port.lock);
                 tty = NULL;
                 if (r3 & (CHBEXT | CHBTxIP | CHBRxIP)) {
-                        sbus_writeb(RES_H_IUS, &channel->control);
+                        writeb(RES_H_IUS, &channel->control);
                         ZSDELAY();
                         ZS_WSYNC(channel);
 
@@ -594,7 +591,7 @@ static __inline__ unsigned char sunzilog_read_channel_status(struct uart_port *p
         unsigned char status;
 
         channel = ZILOG_CHANNEL_FROM_PORT(port);
-        status = sbus_readb(&channel->control);
+        status = readb(&channel->control);
         ZSDELAY();
 
         return status;
@@ -682,7 +679,7 @@ static void sunzilog_start_tx(struct uart_port *port)
         up->flags |= SUNZILOG_FLAG_TX_ACTIVE;
         up->flags &= ~SUNZILOG_FLAG_TX_STOPPED;
 
-        status = sbus_readb(&channel->control);
+        status = readb(&channel->control);
         ZSDELAY();
 
         /* TX busy?  Just wait for the TX done interrupt.  */
@@ -693,7 +690,7 @@ static void sunzilog_start_tx(struct uart_port *port)
          * IRQ sending engine.
          */
         if (port->x_char) {
-                sbus_writeb(port->x_char, &channel->data);
+                writeb(port->x_char, &channel->data);
                 ZSDELAY();
                 ZS_WSYNC(channel);
 
@@ -702,7 +699,7 @@ static void sunzilog_start_tx(struct uart_port *port)
         } else {
                 struct circ_buf *xmit = &port->info->xmit;
 
-                sbus_writeb(xmit->buf[xmit->tail], &channel->data);
+                writeb(xmit->buf[xmit->tail], &channel->data);
                 ZSDELAY();
                 ZS_WSYNC(channel);
 
@@ -779,7 +776,7 @@ static void __sunzilog_startup(struct uart_sunzilog_port *up)
         struct zilog_channel __iomem *channel;
 
         channel = ZILOG_CHANNEL_FROM_PORT(&up->port);
-        up->prev_status = sbus_readb(&channel->control);
+        up->prev_status = readb(&channel->control);
 
         /* Enable receiver and transmitter.  */
         up->curregs[R3] |= RxENAB;
@@ -963,7 +960,7 @@ sunzilog_set_termios(struct uart_port *port, struct termios *termios,
 
 static const char *sunzilog_type(struct uart_port *port)
 {
-        return "SunZilog";
+        return "zs";
 }
 
 /* We do not request/release mappings of the registers here, this
@@ -1012,7 +1009,6 @@ static struct uart_sunzilog_port *sunzilog_port_table;
 static struct zilog_layout __iomem **sunzilog_chip_regs;
 
 static struct uart_sunzilog_port *sunzilog_irq_chain;
-static int zilog_irq = -1;
 
 static struct uart_driver sunzilog_reg = {
         .owner          =       THIS_MODULE,
@@ -1021,232 +1017,47 @@ static struct uart_driver sunzilog_reg = {
         .major          =       TTY_MAJOR,
 };
 
-static void * __init alloc_one_table(unsigned long size)
-{
-        void *ret;
-
-        ret = kmalloc(size, GFP_KERNEL);
-        if (ret != NULL)
-                memset(ret, 0, size);
-
-        return ret;
-}
-
-static void __init sunzilog_alloc_tables(void)
-{
-        sunzilog_port_table = 
-                alloc_one_table(NUM_CHANNELS * sizeof(struct uart_sunzilog_port));
-        sunzilog_chip_regs = 
-                alloc_one_table(NUM_SUNZILOG * sizeof(struct zilog_layout __iomem *));
-
-        if (sunzilog_port_table == NULL || sunzilog_chip_regs == NULL) {
-                prom_printf("SunZilog: Cannot allocate tables.\n");
-                prom_halt();
-        }
-}
-
-#ifdef CONFIG_SPARC64
-
-/* We used to attempt to use the address property of the Zilog device node
- * but that totally is not necessary on sparc64.
- */
-static struct zilog_layout __iomem * __init get_zs_sun4u(int chip, int zsnode)
+static int __init sunzilog_alloc_tables(void)
 {
-        void __iomem *mapped_addr;
-        unsigned int sun4u_ino;
-        struct sbus_bus *sbus = NULL;
-        struct sbus_dev *sdev = NULL;
-        int err;
-
-        if (central_bus == NULL) {
-                for_each_sbus(sbus) {
-                        for_each_sbusdev(sdev, sbus) {
-                                if (sdev->prom_node == zsnode)
-                                        goto found;
-                        }
-                }
-        }
- found:
-        if (sdev == NULL && central_bus == NULL) {
-                prom_printf("SunZilog: sdev&&central == NULL for "
-                            "Zilog %d in get_zs_sun4u.\n", chip);
-                prom_halt();
-        }
-        if (central_bus == NULL) {
-                mapped_addr =
-                        sbus_ioremap(&sdev->resource[0], 0,
-                                     PAGE_SIZE,
-                                     "Zilog Registers");
-        } else {
-                struct linux_prom_registers zsregs[1];
-
-                err = prom_getproperty(zsnode, "reg",
-                                       (char *) &zsregs[0],
-                                       sizeof(zsregs));
-                if (err == -1) {
-                        prom_printf("SunZilog: Cannot map "
-                                    "Zilog %d regs on "
-                                    "central bus.\n", chip);
-                        prom_halt();
-                }
-                apply_fhc_ranges(central_bus->child,
-                                 &zsregs[0], 1);
-                apply_central_ranges(central_bus, &zsregs[0], 1);
-                mapped_addr = (void __iomem *)
-                        ((((u64)zsregs[0].which_io)<<32UL) |
-                        ((u64)zsregs[0].phys_addr));
-        }
-
-        if (zilog_irq == -1) {
-                if (central_bus) {
-                        unsigned long iclr, imap;
-
-                        iclr = central_bus->child->fhc_regs.uregs
-                                + FHC_UREGS_ICLR;
-                        imap = central_bus->child->fhc_regs.uregs
-                                + FHC_UREGS_IMAP;
-                        zilog_irq = build_irq(0, iclr, imap);
-                } else {
-                        err = prom_getproperty(zsnode, "interrupts",
-                                               (char *) &sun4u_ino,
-                                               sizeof(sun4u_ino));
-                        zilog_irq = sbus_build_irq(sbus_root, sun4u_ino);
-                }
-        }
-
-        return (struct zilog_layout __iomem *) mapped_addr;
-}
-#else /* CONFIG_SPARC64 */
-
-/*
- * XXX The sun4d case is utterly screwed: it tries to re-walk the tree
- * (for the 3rd time) in order to find bootbus and cpu. Streamline it.
- */
-static struct zilog_layout __iomem * __init get_zs_sun4cmd(int chip, int node)
-{
-        struct linux_prom_irqs irq_info[2];
-        void __iomem *mapped_addr = NULL;
-        int zsnode, cpunode, bbnode;
-        struct linux_prom_registers zsreg[4];
-        struct resource res;
-
-        if (sparc_cpu_model == sun4d) {
-                int walk;
-
-                zsnode = 0;
-                bbnode = 0;
-                cpunode = 0;
-                for (walk = prom_getchild(prom_root_node);
-                     (walk = prom_searchsiblings(walk, "cpu-unit")) != 0;
-                     walk = prom_getsibling(walk)) {
-                        bbnode = prom_getchild(walk);
-                        if (bbnode &&
-                            (bbnode = prom_searchsiblings(bbnode, "bootbus"))) {
-                                if ((zsnode = prom_getchild(bbnode)) == node) {
-                                        cpunode = walk;
-                                        break;
-                                }
-                        }
-                }
-                if (!walk) {
-                        prom_printf("SunZilog: Cannot find the %d'th bootbus on sun4d.\n",
-                                    (chip / 2));
-                        prom_halt();
-                }
+        struct uart_sunzilog_port *up;
+        unsigned long size;
+        int i;
 
-                if (prom_getproperty(zsnode, "reg",
-                                     (char *) zsreg, sizeof(zsreg)) == -1) {
-                        prom_printf("SunZilog: Cannot map Zilog %d\n", chip);
-                        prom_halt();
-                }
-                /* XXX Looks like an off by one? */
-                prom_apply_generic_ranges(bbnode, cpunode, zsreg, 1);
-                res.start = zsreg[0].phys_addr;
-                res.end = res.start + (8 - 1);
-                res.flags = zsreg[0].which_io | IORESOURCE_IO;
-                mapped_addr = sbus_ioremap(&res, 0, 8, "Zilog Serial");
+        size = NUM_CHANNELS * sizeof(struct uart_sunzilog_port);
+        sunzilog_port_table = kzalloc(size, GFP_KERNEL);
+        if (!sunzilog_port_table)
+                return -ENOMEM;
 
-        } else {
-                zsnode = node;
+        for (i = 0; i < NUM_CHANNELS; i++) {
+                up = &sunzilog_port_table[i];
 
-#if 0 /* XXX When was this used? */
-                if (prom_getintdefault(zsnode, "slave", -1) != chipid) {
-                        zsnode = prom_getsibling(zsnode);
-                        continue;
-                }
-#endif
+                spin_lock_init(&up->port.lock);
 
-                /*
-                 * "address" is only present on ports that OBP opened
-                 * (from Mitch Bradley's "Hitchhiker's Guide to OBP").
-                 * We do not use it.
-                 */
+                if (i == 0)
+                        sunzilog_irq_chain = up;
 
-                if (prom_getproperty(zsnode, "reg",
-                                     (char *) zsreg, sizeof(zsreg)) == -1) {
-                        prom_printf("SunZilog: Cannot map Zilog %d\n", chip);
-                        prom_halt();
-                }
-                if (sparc_cpu_model == sun4m)   /* Crude. Pass parent. XXX */
-                        prom_apply_obio_ranges(zsreg, 1);
-                res.start = zsreg[0].phys_addr;
-                res.end = res.start + (8 - 1);
-                res.flags = zsreg[0].which_io | IORESOURCE_IO;
-                mapped_addr = sbus_ioremap(&res, 0, 8, "Zilog Serial");
+                if (i < NUM_CHANNELS - 1)
+                        up->next = up + 1;
+                else
+                        up->next = NULL;
         }
 
-        if (prom_getproperty(zsnode, "intr",
-                             (char *) irq_info, sizeof(irq_info))
-                    % sizeof(struct linux_prom_irqs)) {
-                prom_printf("SunZilog: Cannot get IRQ property for Zilog %d.\n",
-                            chip);
-                prom_halt();
-        }
-        if (zilog_irq == -1) {
-                zilog_irq = irq_info[0].pri;
-        } else if (zilog_irq != irq_info[0].pri) {
-                /* XXX. Dumb. Should handle per-chip IRQ, for add-ons. */
-                prom_printf("SunZilog: Inconsistent IRQ layout for Zilog %d.\n",
-                            chip);
-                prom_halt();
+        size = NUM_SUNZILOG * sizeof(struct zilog_layout __iomem *);
+        sunzilog_chip_regs = kzalloc(size, GFP_KERNEL);
+        if (!sunzilog_chip_regs) {
+                kfree(sunzilog_port_table);
+                sunzilog_irq_chain = NULL;
+                return -ENOMEM;
         }
 
-        return (struct zilog_layout __iomem *) mapped_addr;
+        return 0;
 }
-#endif /* !(CONFIG_SPARC64) */
 
-/* Get the address of the registers for SunZilog instance CHIP.  */
-static struct zilog_layout __iomem * __init get_zs(int chip, int node)
+static void sunzilog_free_tables(void)
 {
-        if (chip < 0 || chip >= NUM_SUNZILOG) {
-                prom_printf("SunZilog: Illegal chip number %d in get_zs.\n", chip);
-                prom_halt();
-        }
-
-#ifdef CONFIG_SPARC64
-        return get_zs_sun4u(chip, node);
-#else
-
-        if (sparc_cpu_model == sun4) {
-                struct resource res;
-
-                /* Not probe-able, hard code it. */
-                switch (chip) {
-                case 0:
-                        res.start = 0xf1000000;
-                        break;
-                case 1:
-                        res.start = 0xf0000000;
-                        break;
-                };
-                zilog_irq = 12;
-                res.end = (res.start + (8 - 1));
-                res.flags = IORESOURCE_IO;
-                return sbus_ioremap(&res, 0, 8, "SunZilog");
-        }
-
-        return get_zs_sun4cmd(chip, node);
-#endif
+        kfree(sunzilog_port_table);
+        sunzilog_irq_chain = NULL;
+        kfree(sunzilog_chip_regs);
 }
 
 #define ZS_PUT_CHAR_MAX_DELAY   2000    /* 10 ms */
@@ -1260,7 +1071,7 @@ static void sunzilog_putchar(struct uart_port *port, int ch)
          * udelay with ZSDELAY as that is a NOP on some platforms.  -DaveM
          */
         do {
-                unsigned char val = sbus_readb(&channel->control);
+                unsigned char val = readb(&channel->control);
                 if (val & Tx_BUF_EMP) {
                         ZSDELAY();
                         break;
@@ -1268,7 +1079,7 @@ static void sunzilog_putchar(struct uart_port *port, int ch)
                 udelay(5);
         } while (--loops);
 
-        sbus_writeb(ch, &channel->data);
+        writeb(ch, &channel->data);
         ZSDELAY();
         ZS_WSYNC(channel);
 }
@@ -1385,28 +1196,6 @@ static struct console sunzilog_console = {
         .data   =       &sunzilog_reg,
 };
 
-static int __init sunzilog_console_init(void)
-{
-        int i;
-
-        if (con_is_present())
-                return 0;
-
-        for (i = 0; i < NUM_CHANNELS; i++) {
-                int this_minor = sunzilog_reg.minor + i;
-
-                if ((this_minor - 64) == (serial_console - 1))
-                        break;
-        }
-        if (i == NUM_CHANNELS)
-                return 0;
-
-        sunzilog_console.index = i;
-        sunzilog_port_table[i].flags |= SUNZILOG_FLAG_IS_CONS;
-        register_console(&sunzilog_console);
-        return 0;
-}
-
 static inline struct console *SUNZILOG_CONSOLE(void)
 {
         int i;
@@ -1431,101 +1220,8 @@ static inline struct console *SUNZILOG_CONSOLE(void)
 
 #else
 #define SUNZILOG_CONSOLE()      (NULL)
-#define sunzilog_console_init() do { } while (0)
 #endif
 
-/*
- * We scan the PROM tree recursively. This is the most reliable way
- * to find Zilog nodes on various platforms. However, we face an extreme
- * shortage of kernel stack, so we must be very careful. To that end,
- * we scan only to a certain depth, and we use a common property buffer
- * in the scan structure.
- */
-#define ZS_PROPSIZE  128
-#define ZS_SCAN_DEPTH   5
-
-struct zs_probe_scan {
-        int depth;
-        void (*scanner)(struct zs_probe_scan *t, int node);
-
-        int devices;
-        char prop[ZS_PROPSIZE];
-};
-
-static int __inline__ sunzilog_node_ok(int node, const char *name, int len)
-{
-        if (strncmp(name, "zs", len) == 0)
-                return 1;
-        /* Don't fold this procedure just yet. Compare to su_node_ok(). */
-        return 0;
-}
-
-static void __init sunzilog_scan(struct zs_probe_scan *t, int node)
-{
-        int len;
-
-        for (; node != 0; node = prom_getsibling(node)) {
-                len = prom_getproperty(node, "name", t->prop, ZS_PROPSIZE);
-                if (len <= 1)
-                        continue;               /* Broken PROM node */
-                if (sunzilog_node_ok(node, t->prop, len)) {
-                        (*t->scanner)(t, node);
-                } else {
-                        if (t->depth < ZS_SCAN_DEPTH) {
-                                t->depth++;
-                                sunzilog_scan(t, prom_getchild(node));
-                                --t->depth;
-                        }
-                }
-        }
-}
-
-static void __init sunzilog_prepare(void)
-{
-        struct uart_sunzilog_port *up;
-        struct zilog_layout __iomem *rp;
-        int channel, chip;
-
-        /*
-         * Temporary fix.
-         */
-        for (channel = 0; channel < NUM_CHANNELS; channel++)
-                spin_lock_init(&sunzilog_port_table[channel].port.lock);
-
-        sunzilog_irq_chain = up = &sunzilog_port_table[0];
-        for (channel = 0; channel < NUM_CHANNELS - 1; channel++)
-                up[channel].next = &up[channel + 1];
-        up[channel].next = NULL;
-
-        for (chip = 0; chip < NUM_SUNZILOG; chip++) {
-                rp = sunzilog_chip_regs[chip];
-                up[(chip * 2) + 0].port.membase = (void __iomem *)&rp->channelA;
-                up[(chip * 2) + 1].port.membase = (void __iomem *)&rp->channelB;
-
-                /* Channel A */
-                up[(chip * 2) + 0].port.iotype = UPIO_MEM;
-                up[(chip * 2) + 0].port.irq = zilog_irq;
-                up[(chip * 2) + 0].port.uartclk = ZS_CLOCK;
-                up[(chip * 2) + 0].port.fifosize = 1;
-                up[(chip * 2) + 0].port.ops = &sunzilog_pops;
-                up[(chip * 2) + 0].port.type = PORT_SUNZILOG;
-                up[(chip * 2) + 0].port.flags = 0;
-                up[(chip * 2) + 0].port.line = (chip * 2) + 0;
-                up[(chip * 2) + 0].flags |= SUNZILOG_FLAG_IS_CHANNEL_A;
-
-                /* Channel B */
-                up[(chip * 2) + 1].port.iotype = UPIO_MEM;
-                up[(chip * 2) + 1].port.irq = zilog_irq;
-                up[(chip * 2) + 1].port.uartclk = ZS_CLOCK;
-                up[(chip * 2) + 1].port.fifosize = 1;
-                up[(chip * 2) + 1].port.ops = &sunzilog_pops;
-                up[(chip * 2) + 1].port.type = PORT_SUNZILOG;
-                up[(chip * 2) + 1].port.flags = 0;
-                up[(chip * 2) + 1].port.line = (chip * 2) + 1;
-                up[(chip * 2) + 1].flags |= 0;
-        }
-}
-
 static void __init sunzilog_init_kbdms(struct uart_sunzilog_port *up, int channel)
 {
         int baud, brg;
@@ -1539,8 +1235,6 @@ static void __init sunzilog_init_kbdms(struct uart_sunzilog_port *up, int channe
                 up->cflag = B4800 | CS8 | CLOCAL | CREAD;
                 baud = 4800;
         }
-        printk(KERN_INFO "zs%d at 0x%p (irq = %d) is a SunZilog\n",
-               channel, up->port.membase, zilog_irq);
 
         up->curregs[R15] = BRKIE;
         brg = BPS_TO_BRG(baud, ZS_CLOCK / ZS_CLOCK_DIVISOR);
@@ -1552,216 +1246,268 @@ static void __init sunzilog_init_kbdms(struct uart_sunzilog_port *up, int channe
 #ifdef CONFIG_SERIO
 static void __init sunzilog_register_serio(struct uart_sunzilog_port *up, int channel)
 {
-        struct serio *serio;
-
-        up->serio = serio = kmalloc(sizeof(struct serio), GFP_KERNEL);
-        if (serio) {
-                memset(serio, 0, sizeof(*serio));
-
-                serio->port_data = up;
-
-                serio->id.type = SERIO_RS232;
-                if (channel == KEYBOARD_LINE) {
-                        serio->id.proto = SERIO_SUNKBD;
-                        strlcpy(serio->name, "zskbd", sizeof(serio->name));
-                } else {
-                        serio->id.proto = SERIO_SUN;
-                        serio->id.extra = 1;
-                        strlcpy(serio->name, "zsms", sizeof(serio->name));
-                }
-                strlcpy(serio->phys,
-                        (channel == KEYBOARD_LINE ? "zs/serio0" : "zs/serio1"),
-                        sizeof(serio->phys));
+        struct serio *serio = &up->serio;
 
-                serio->write = sunzilog_serio_write;
-                serio->open = sunzilog_serio_open;
-                serio->close = sunzilog_serio_close;
+        serio->port_data = up;
 
-                serio_register_port(serio);
+        serio->id.type = SERIO_RS232;
+        if (channel == KEYBOARD_LINE) {
+                serio->id.proto = SERIO_SUNKBD;
+                strlcpy(serio->name, "zskbd", sizeof(serio->name));
         } else {
-                printk(KERN_WARNING "zs%d: not enough memory for serio port\n",
-                        channel);
+                serio->id.proto = SERIO_SUN;
+                serio->id.extra = 1;
+                strlcpy(serio->name, "zsms", sizeof(serio->name));
         }
+        strlcpy(serio->phys,
+                (channel == KEYBOARD_LINE ? "zs/serio0" : "zs/serio1"),
+                sizeof(serio->phys));
+
+        serio->write = sunzilog_serio_write;
+        serio->open = sunzilog_serio_open;
+        serio->close = sunzilog_serio_close;
+        serio->dev.parent = up->port.dev;
+
+        serio_register_port(serio);
 }
 #endif
 
-static void __init sunzilog_init_hw(void)
+static void __init sunzilog_init_hw(struct uart_sunzilog_port *up)
 {
-        int i;
-
-        for (i = 0; i < NUM_CHANNELS; i++) {
-                struct uart_sunzilog_port *up = &sunzilog_port_table[i];
-                struct zilog_channel __iomem *channel = ZILOG_CHANNEL_FROM_PORT(&up->port);
-                unsigned long flags;
-                int baud, brg;
+        struct zilog_channel __iomem *channel;
+        unsigned long flags;
+        int baud, brg;
 
-                spin_lock_irqsave(&up->port.lock, flags);
+        channel = ZILOG_CHANNEL_FROM_PORT(&up->port);
 
-                if (ZS_IS_CHANNEL_A(up)) {
-                        write_zsreg(channel, R9, FHWRES);
-                        ZSDELAY_LONG();
-                        (void) read_zsreg(channel, R0);
-                }
+        spin_lock_irqsave(&up->port.lock, flags);
+        if (ZS_IS_CHANNEL_A(up)) {
+                write_zsreg(channel, R9, FHWRES);
+                ZSDELAY_LONG();
+                (void) read_zsreg(channel, R0);
+        }
 
-                if (i == KEYBOARD_LINE || i == MOUSE_LINE) {
-                        sunzilog_init_kbdms(up, i);
-                        up->curregs[R9] |= (NV | MIE);
-                        write_zsreg(channel, R9, up->curregs[R9]);
-                } else {
-                        /* Normal serial TTY. */
-                        up->parity_mask = 0xff;
-                        up->curregs[R1] = EXT_INT_ENAB | INT_ALL_Rx | TxINT_ENAB;
-                        up->curregs[R4] = PAR_EVEN | X16CLK | SB1;
-                        up->curregs[R3] = RxENAB | Rx8;
-                        up->curregs[R5] = TxENAB | Tx8;
-                        up->curregs[R9] = NV | MIE;
-                        up->curregs[R10] = NRZ;
-                        up->curregs[R11] = TCBR | RCBR;
-                        baud = 9600;
-                        brg = BPS_TO_BRG(baud, ZS_CLOCK / ZS_CLOCK_DIVISOR);
-                        up->curregs[R12] = (brg & 0xff);
-                        up->curregs[R13] = (brg >> 8) & 0xff;
-                        up->curregs[R14] = BRSRC | BRENAB;
-                        __load_zsregs(channel, up->curregs);
-                        write_zsreg(channel, R9, up->curregs[R9]);
-                }
+        if (up->port.line == KEYBOARD_LINE ||
+            up->port.line == MOUSE_LINE) {
+                sunzilog_init_kbdms(up, up->port.line);
+                up->curregs[R9] |= (NV | MIE);
+                write_zsreg(channel, R9, up->curregs[R9]);
+        } else {
+                /* Normal serial TTY. */
+                up->parity_mask = 0xff;
+                up->curregs[R1] = EXT_INT_ENAB | INT_ALL_Rx | TxINT_ENAB;
+                up->curregs[R4] = PAR_EVEN | X16CLK | SB1;
+                up->curregs[R3] = RxENAB | Rx8;
+                up->curregs[R5] = TxENAB | Tx8;
+                up->curregs[R9] = NV | MIE;
+                up->curregs[R10] = NRZ;
+                up->curregs[R11] = TCBR | RCBR;
+                baud = 9600;
+                brg = BPS_TO_BRG(baud, ZS_CLOCK / ZS_CLOCK_DIVISOR);
+                up->curregs[R12] = (brg & 0xff);
+                up->curregs[R13] = (brg >> 8) & 0xff;
+                up->curregs[R14] = BRSRC | BRENAB;
+                __load_zsregs(channel, up->curregs);
+                write_zsreg(channel, R9, up->curregs[R9]);
+        }
 
-                spin_unlock_irqrestore(&up->port.lock, flags);
+        spin_unlock_irqrestore(&up->port.lock, flags);
 
 #ifdef CONFIG_SERIO
-                if (i == KEYBOARD_LINE || i == MOUSE_LINE)
-                        sunzilog_register_serio(up, i);
+        if (up->port.line == KEYBOARD_LINE || up->port.line == MOUSE_LINE)
+                sunzilog_register_serio(up, up->port.line);
 #endif
-        }
-}
-
-static struct zilog_layout __iomem * __init get_zs(int chip, int node);
-
-static void __init sunzilog_scan_probe(struct zs_probe_scan *t, int node)
-{
-        sunzilog_chip_regs[t->devices] = get_zs(t->devices, node);
-        t->devices++;
 }
 
-static int __init sunzilog_ports_init(void)
+static int __devinit zs_get_instance(struct device_node *dp)
 {
-        struct zs_probe_scan scan;
         int ret;
-        int uart_count;
-        int i;
-
-        printk(KERN_DEBUG "SunZilog: %d chips.\n", NUM_SUNZILOG);
-
-        scan.scanner = sunzilog_scan_probe;
-        scan.depth = 0;
-        scan.devices = 0;
-        sunzilog_scan(&scan, prom_getchild(prom_root_node));
-
-        sunzilog_prepare();
 
-        if (request_irq(zilog_irq, sunzilog_interrupt, SA_SHIRQ,
-                        "SunZilog", sunzilog_irq_chain)) {
-                prom_printf("SunZilog: Unable to register zs interrupt handler.\n");
-                prom_halt();
-        }
+        ret = of_getintprop_default(dp, "slave", -1);
+        if (ret != -1)
+                return ret;
 
-        sunzilog_init_hw();
+        if (of_find_property(dp, "keyboard", NULL))
+                ret = 1;
+        else
+                ret = 0;
 
-        /* We can only init this once we have probed the Zilogs
-         * in the system. Do not count channels assigned to keyboards
-         * or mice when we are deciding how many ports to register.
-         */
-        uart_count = 0;
-        for (i = 0; i < NUM_CHANNELS; i++) {
-                struct uart_sunzilog_port *up = &sunzilog_port_table[i];
+        return ret;
+}
 
-                if (ZS_IS_KEYB(up) || ZS_IS_MOUSE(up))
-                        continue;
+static int zilog_irq = -1;
 
-                uart_count++;
-        }
-                
-        sunzilog_reg.nr = uart_count;
-        sunzilog_reg.minor = sunserial_current_minor;
+static int __devinit zs_probe(struct of_device *dev, const struct of_device_id *match)
+{
+        struct of_device *op = to_of_device(&dev->dev);
+        struct uart_sunzilog_port *up;
+        struct zilog_layout __iomem *rp;
+        int inst = zs_get_instance(dev->node);
+        int err;
 
-        ret = uart_register_driver(&sunzilog_reg);
-        if (ret == 0) {
-                sunzilog_reg.tty_driver->name_base = sunzilog_reg.minor - 64;
-                sunzilog_reg.cons = SUNZILOG_CONSOLE();
+        sunzilog_chip_regs[inst] = of_ioremap(&op->resource[0], 0,
+                                              sizeof(struct zilog_layout),
+                                              "zs");
+        if (!sunzilog_chip_regs[inst])
+                return -ENOMEM;
 
-                sunserial_current_minor += uart_count;
+        rp = sunzilog_chip_regs[inst];
 
-                for (i = 0; i < NUM_CHANNELS; i++) {
-                        struct uart_sunzilog_port *up = &sunzilog_port_table[i];
+        if (zilog_irq == -1) {
+                zilog_irq = op->irqs[0];
+                err = request_irq(zilog_irq, sunzilog_interrupt, SA_SHIRQ,
+                                  "zs", sunzilog_irq_chain);
+                if (err) {
+                        of_iounmap(rp, sizeof(struct zilog_layout));
 
-                        if (ZS_IS_KEYB(up) || ZS_IS_MOUSE(up))
-                                continue;
+                        return err;
+                }
+        }
 
-                        if (uart_add_one_port(&sunzilog_reg, &up->port)) {
-                                printk(KERN_ERR
-                                    "SunZilog: failed to add port zs%d\n", i);
-                        }
+        up = &sunzilog_port_table[inst * 2];
+
+        /* Channel A */
+        up[0].port.mapbase = op->resource[0].start + 0x00;
+        up[0].port.membase = (void __iomem *) &rp->channelA;
+        up[0].port.iotype = UPIO_MEM;
+        up[0].port.irq = op->irqs[0];
+        up[0].port.uartclk = ZS_CLOCK;
+        up[0].port.fifosize = 1;
+        up[0].port.ops = &sunzilog_pops;
+        up[0].port.type = PORT_SUNZILOG;
+        up[0].port.flags = 0;
+        up[0].port.line = (inst * 2) + 0;
+        up[0].port.dev = &op->dev;
+        up[0].flags |= SUNZILOG_FLAG_IS_CHANNEL_A;
+        if (inst == 1)
+                up[0].flags |= SUNZILOG_FLAG_CONS_KEYB;
+        sunzilog_init_hw(&up[0]);
+
+        /* Channel B */
+        up[1].port.mapbase = op->resource[0].start + 0x04;
+        up[1].port.membase = (void __iomem *) &rp->channelB;
+        up[1].port.iotype = UPIO_MEM;
+        up[1].port.irq = op->irqs[0];
+        up[1].port.uartclk = ZS_CLOCK;
+        up[1].port.fifosize = 1;
+        up[1].port.ops = &sunzilog_pops;
+        up[1].port.type = PORT_SUNZILOG;
+        up[1].port.flags = 0;
+        up[1].port.line = (inst * 2) + 1;
+        up[1].port.dev = &op->dev;
+        up[1].flags |= 0;
+        if (inst == 1)
+                up[1].flags |= SUNZILOG_FLAG_CONS_MOUSE;
+        sunzilog_init_hw(&up[1]);
+
+        if (inst != 1) {
+                err = uart_add_one_port(&sunzilog_reg, &up[0].port);
+                if (err) {
+                        of_iounmap(rp, sizeof(struct zilog_layout));
+                        return err;
+                }
+                err = uart_add_one_port(&sunzilog_reg, &up[1].port);
+                if (err) {
+                        uart_remove_one_port(&sunzilog_reg, &up[0].port);
+                        of_iounmap(rp, sizeof(struct zilog_layout));
+                        return err;
                 }
         }
 
-        return ret;
+        dev_set_drvdata(&dev->dev, &up[0]);
+
+        return 0;
 }
 
-static void __init sunzilog_scan_count(struct zs_probe_scan *t, int node)
+static void __devexit zs_remove_one(struct uart_sunzilog_port *up)
 {
-        t->devices++;
+        if (ZS_IS_KEYB(up) || ZS_IS_MOUSE(up)) {
+#ifdef CONFIG_SERIO
+                serio_unregister_port(&up->serio);
+#endif
+        } else
+                uart_remove_one_port(&sunzilog_reg, &up->port);
 }
 
-static int __init sunzilog_ports_count(void)
+static int __devexit zs_remove(struct of_device *dev)
 {
-        struct zs_probe_scan scan;
+        struct uart_sunzilog_port *up = dev_get_drvdata(&dev->dev);
+        struct zilog_layout __iomem *regs;
 
-        /* Sun4 Zilog setup is hard coded, no probing to do.  */
-        if (sparc_cpu_model == sun4)
-                return 2;
+        zs_remove_one(&up[0]);
+        zs_remove_one(&up[1]);
 
-        scan.scanner = sunzilog_scan_count;
-        scan.depth = 0;
-        scan.devices = 0;
+        regs = sunzilog_chip_regs[up[0].port.line / 2];
+        of_iounmap(regs, sizeof(struct zilog_layout));
 
-        sunzilog_scan(&scan, prom_getchild(prom_root_node));
+        dev_set_drvdata(&dev->dev, NULL);
 
-        return scan.devices;
+        return 0;
 }
 
+static struct of_device_id zs_match[] = {
+        {
+                .name = "zs",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, zs_match);
+
+static struct of_platform_driver zs_driver = {
+        .name           = "zs",
+        .match_table    = zs_match,
+        .probe          = zs_probe,
+        .remove         = __devexit_p(zs_remove),
+};
+
 static int __init sunzilog_init(void)
 {
+        struct device_node *dp;
+        int err;
 
-        NUM_SUNZILOG = sunzilog_ports_count();
-        if (NUM_SUNZILOG == 0)
-                return -ENODEV;
+        NUM_SUNZILOG = 0;
+        for_each_node_by_name(dp, "zs")
+                NUM_SUNZILOG++;
 
-        sunzilog_alloc_tables();
+        if (NUM_SUNZILOG) {
+                int uart_count;
 
-        sunzilog_ports_init();
+                err = sunzilog_alloc_tables();
+                if (err)
+                        return err;
 
-        return 0;
+                /* Subtract 1 for keyboard, 1 for mouse.  */
+                uart_count = (NUM_SUNZILOG * 2) - 2;
+
+                sunzilog_reg.nr = uart_count;
+                sunzilog_reg.minor = sunserial_current_minor;
+                err = uart_register_driver(&sunzilog_reg);
+                if (err) {
+                        sunzilog_free_tables();
+                        return err;
+                }
+                sunzilog_reg.tty_driver->name_base = sunzilog_reg.minor - 64;
+                sunzilog_reg.cons = SUNZILOG_CONSOLE();
+
+                sunserial_current_minor += uart_count;
+        }
+
+        return of_register_driver(&zs_driver, &of_bus_type);
 }
 
 static void __exit sunzilog_exit(void)
 {
-        int i;
+        of_unregister_driver(&zs_driver);
 
-        for (i = 0; i < NUM_CHANNELS; i++) {
-                struct uart_sunzilog_port *up = &sunzilog_port_table[i];
-
-                if (ZS_IS_KEYB(up) || ZS_IS_MOUSE(up)) {
-#ifdef CONFIG_SERIO
-                        if (up->serio) {
-                                serio_unregister_port(up->serio);
-                                up->serio = NULL;
-                        }
-#endif
-                } else
-                        uart_remove_one_port(&sunzilog_reg, &up->port);
+        if (zilog_irq != -1) {
+                free_irq(zilog_irq, sunzilog_irq_chain);
+                zilog_irq = -1;
         }
 
-        uart_unregister_driver(&sunzilog_reg);
+        if (NUM_SUNZILOG) {
+                uart_unregister_driver(&sunzilog_reg);
+                sunzilog_free_tables();
+        }
 }
 
 module_init(sunzilog_init);
@@ -1769,4 +1515,5 @@ module_exit(sunzilog_exit);
 
 MODULE_AUTHOR("David S. Miller");
 MODULE_DESCRIPTION("Sun Zilog serial port driver");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index bcbeaf7101d1..f7bdd94b3aa8 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -47,6 +47,7 @@
 #include <linux/usbdevice_fs.h>
 #include <linux/cdev.h>
 #include <linux/notifier.h>
+#include <linux/security.h>
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
 #include <linux/moduleparam.h>
@@ -68,6 +69,7 @@ struct async {
         void __user *userbuffer;
         void __user *userurb;
         struct urb *urb;
+        u32 secid;
 };
 
 static int usbfs_snoop = 0;
@@ -312,7 +314,7 @@ static void async_completed(struct urb *urb, struct pt_regs *regs)
                 sinfo.si_code = SI_ASYNCIO;
                 sinfo.si_addr = as->userurb;
                 kill_proc_info_as_uid(as->signr, &sinfo, as->pid, as->uid, 
-                                      as->euid);
+                                      as->euid, as->secid);
         }
         snoop(&urb->dev->dev, "urb complete\n");
         snoop_urb(urb, as->userurb);
@@ -572,6 +574,7 @@ static int usbdev_open(struct inode *inode, struct file *file)
         ps->disc_euid = current->euid;
         ps->disccontext = NULL;
         ps->ifclaimed = 0;
+        security_task_getsecid(current, &ps->secid);
         wmb();
         list_add_tail(&ps->list, &dev->filelist);
         file->private_data = ps;
@@ -1053,6 +1056,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
         as->pid = current->pid;
         as->uid = current->uid;
         as->euid = current->euid;
+        security_task_getsecid(current, &as->secid);
         if (!(uurb->endpoint & USB_DIR_IN)) {
                 if (copy_from_user(as->urb->transfer_buffer, uurb->buffer, as->urb->transfer_buffer_length)) {
                         free_async(as);
diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index bfc9b28a7242..d0a208de32cf 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -700,7 +700,7 @@ static void usbfs_remove_device(struct usb_device *dev)
                         sinfo.si_errno = EPIPE;
                         sinfo.si_code = SI_ASYNCIO;
                         sinfo.si_addr = ds->disccontext;
-                        kill_proc_info_as_uid(ds->discsignr, &sinfo, ds->disc_pid, ds->disc_uid, ds->disc_euid);
+                        kill_proc_info_as_uid(ds->discsignr, &sinfo, ds->disc_pid, ds->disc_uid, ds->disc_euid, ds->secid);
                 }
         }
 }
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 7a650c763a62..49f69236b420 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -80,6 +80,7 @@ struct dev_state {
         uid_t disc_uid, disc_euid;
         void __user *disccontext;
         unsigned long ifclaimed;
+        u32 secid;
 };
 
 /* internal notify stuff */
diff --git a/drivers/video/bw2.c b/drivers/video/bw2.c
index 6577fdfdfc16..c66e3d52cbf3 100644
--- a/drivers/video/bw2.c
+++ b/drivers/video/bw2.c
@@ -1,6 +1,6 @@
 /* bw2.c: BWTWO frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1996,1998 Jakub Jelinek (jj@ultra.linux.cz)
  * Copyright (C) 1996 Miguel de Icaza (miguel@nuclecu.unam.mx)
  * Copyright (C) 1997 Eddie C. Dost (ecd@skynet.be)
@@ -19,14 +19,11 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/sbus.h>
 #include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
-#ifdef CONFIG_SPARC32
-#include <asm/sun4paddr.h>
-#endif
-
 #include "sbuslib.h"
 
 /*
@@ -59,30 +56,30 @@ static struct fb_ops bw2_ops = {
 #define BWTWO_REGISTER_OFFSET 0x400000
 
 struct bt_regs {
-        volatile u32 addr;
-        volatile u32 color_map;
-        volatile u32 control;
-        volatile u32 cursor;
+        u32 addr;
+        u32 color_map;
+        u32 control;
+        u32 cursor;
 };
 
 struct bw2_regs {
         struct bt_regs  cmap;
-        volatile u8     control;
-        volatile u8     status;
-        volatile u8     cursor_start;
-        volatile u8     cursor_end;
-        volatile u8     h_blank_start;
-        volatile u8     h_blank_end;
-        volatile u8     h_sync_start;
-        volatile u8     h_sync_end;
-        volatile u8     comp_sync_end;
-        volatile u8     v_blank_start_high;
-        volatile u8     v_blank_start_low;
-        volatile u8     v_blank_end;
-        volatile u8     v_sync_start;
-        volatile u8     v_sync_end;
-        volatile u8     xfer_holdoff_start;
-        volatile u8     xfer_holdoff_end;
+        u8      control;
+        u8      status;
+        u8      cursor_start;
+        u8      cursor_end;
+        u8      h_blank_start;
+        u8      h_blank_end;
+        u8      h_sync_start;
+        u8      h_sync_end;
+        u8      comp_sync_end;
+        u8      v_blank_start_high;
+        u8      v_blank_start_low;
+        u8      v_blank_end;
+        u8      v_sync_start;
+        u8      v_sync_end;
+        u8      xfer_holdoff_start;
+        u8      xfer_holdoff_end;
 };
 
 /* Status Register Constants */
@@ -117,9 +114,8 @@ struct bw2_par {
 #define BW2_FLAG_BLANKED        0x00000001
 
         unsigned long           physbase;
+        unsigned long           which_io;
         unsigned long           fbsize;
-
-        struct sbus_dev         *sdev;
 };
 
 /**
@@ -174,9 +170,7 @@ static int bw2_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
         return sbusfb_mmap_helper(bw2_mmap_map,
                                   par->physbase, par->fbsize,
-                                  (par->sdev ?
-                                   par->sdev->reg_addrs[0].which_io :
-                                   0),
+                                  par->which_io,
                                   vma);
 }
 
@@ -288,139 +282,124 @@ static void bw2_do_default_mode(struct bw2_par *par, struct fb_info *info,
 struct all_info {
         struct fb_info info;
         struct bw2_par par;
-        struct list_head list;
 };
-static LIST_HEAD(bw2_list);
 
-static void bw2_init_one(struct sbus_dev *sdev)
+static int __devinit bw2_init_one(struct of_device *op)
 {
+        struct device_node *dp = op->node;
         struct all_info *all;
-        struct resource *resp;
-#ifdef CONFIG_SUN4
-        struct resource res;
-#endif
-        int linebytes;
+        int linebytes, err;
 
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "bw2: Cannot allocate memory.\n");
-                return;
-        }
-        memset(all, 0, sizeof(*all));
-
-        INIT_LIST_HEAD(&all->list);
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
         spin_lock_init(&all->par.lock);
-        all->par.sdev = sdev;
-
-#ifdef CONFIG_SUN4
-        if (!sdev) {
-                all->par.physbase = sun4_bwtwo_physaddr;
-                res.start = sun4_bwtwo_physaddr;
-                res.end = res.start + BWTWO_REGISTER_OFFSET + sizeof(struct bw2_regs) - 1;
-                res.flags = IORESOURCE_IO;
-                resp = &res;
-                all->info.var.xres = all->info.var.xres_virtual = 1152;
-                all->info.var.yres = all->info.var.yres_virtual = 900;
-                all->info.var.bits_per_pixel = 1;
-                linebytes = 1152 / 8;
-        } else
-#else
-        {
-                BUG_ON(!sdev);
-                all->par.physbase = sdev->reg_addrs[0].phys_addr;
-                resp = &sdev->resource[0];
-                sbusfb_fill_var(&all->info.var, (sdev ? sdev->prom_node : 0), 1);
-                linebytes = prom_getintdefault(sdev->prom_node, "linebytes",
-                                               all->info.var.xres);
-        }
-#endif
+
+        all->par.physbase = op->resource[0].start;
+        all->par.which_io = op->resource[0].flags & IORESOURCE_BITS;
+
+        sbusfb_fill_var(&all->info.var, dp->node, 1);
+        linebytes = of_getintprop_default(dp, "linebytes",
+                                          all->info.var.xres);
+
         all->info.var.red.length = all->info.var.green.length =
                 all->info.var.blue.length = all->info.var.bits_per_pixel;
         all->info.var.red.offset = all->info.var.green.offset =
                 all->info.var.blue.offset = 0;
 
-        all->par.regs = sbus_ioremap(resp, BWTWO_REGISTER_OFFSET,
-                             sizeof(struct bw2_regs), "bw2 regs");
+        all->par.regs = of_ioremap(&op->resource[0], BWTWO_REGISTER_OFFSET,
+                                   sizeof(struct bw2_regs), "bw2 regs");
 
-        if (sdev && !prom_getbool(sdev->prom_node, "width"))
+        if (!of_find_property(dp, "width", NULL))
                 bw2_do_default_mode(&all->par, &all->info, &linebytes);
 
         all->par.fbsize = PAGE_ALIGN(linebytes * all->info.var.yres);
 
         all->info.flags = FBINFO_DEFAULT;
         all->info.fbops = &bw2_ops;
-#if defined(CONFIG_SPARC32)
-        if (sdev)
-                all->info.screen_base = (char __iomem *)
-                        prom_getintdefault(sdev->prom_node, "address", 0);
-#endif
-        if (!all->info.screen_base)
-                all->info.screen_base =
-                        sbus_ioremap(resp, 0, all->par.fbsize, "bw2 ram");
+
+        all->info.screen_base =
+                sbus_ioremap(&op->resource[0], 0, all->par.fbsize, "bw2 ram");
         all->info.par = &all->par;
 
         bw2_blank(0, &all->info);
 
         bw2_init_fix(&all->info, linebytes);
 
-        if (register_framebuffer(&all->info) < 0) {
-                printk(KERN_ERR "bw2: Could not register framebuffer.\n");
+        err= register_framebuffer(&all->info);
+        if (err < 0) {
+                of_iounmap(all->par.regs, sizeof(struct bw2_regs));
+                of_iounmap(all->info.screen_base, all->par.fbsize);
                 kfree(all);
-                return;
+                return err;
         }
 
-        list_add(&all->list, &bw2_list);
+        dev_set_drvdata(&op->dev, all);
+
+        printk("%s: bwtwo at %lx:%lx\n",
+               dp->full_name,
+               all->par.which_io, all->par.physbase);
 
-        printk("bw2: bwtwo at %lx:%lx\n",
-               (long) (sdev ? sdev->reg_addrs[0].which_io : 0),
-               (long) all->par.physbase);
+        return 0;
 }
 
-int __init bw2_init(void)
+static int __devinit bw2_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_bus *sbus;
-        struct sbus_dev *sdev;
+        struct of_device *op = to_of_device(&dev->dev);
 
-        if (fb_get_options("bw2fb", NULL))
-                return -ENODEV;
+        return bw2_init_one(op);
+}
 
-#ifdef CONFIG_SUN4
-        bw2_init_one(NULL);
-#endif
-        for_all_sbusdev(sdev, sbus) {
-                if (!strcmp(sdev->prom_name, "bwtwo"))
-                        bw2_init_one(sdev);
-        }
+static int __devexit bw2_remove(struct of_device *dev)
+{
+        struct all_info *all = dev_get_drvdata(&dev->dev);
+
+        unregister_framebuffer(&all->info);
+
+        of_iounmap(all->par.regs, sizeof(struct bw2_regs));
+        of_iounmap(all->info.screen_base, all->par.fbsize);
+
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit bw2_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id bw2_match[] = {
+        {
+                .name = "bwtwo",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, bw2_match);
 
-        list_for_each_safe(pos, tmp, &bw2_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+static struct of_platform_driver bw2_driver = {
+        .name           = "bw2",
+        .match_table    = bw2_match,
+        .probe          = bw2_probe,
+        .remove         = __devexit_p(bw2_remove),
+};
 
-                unregister_framebuffer(&all->info);
-                kfree(all);
-        }
+static int __init bw2_init(void)
+{
+        if (fb_get_options("bw2fb", NULL))
+                return -ENODEV;
+
+        return of_register_driver(&bw2_driver, &of_bus_type);
 }
 
-int __init
-bw2_setup(char *arg)
+static void __exit bw2_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        return of_unregister_driver(&bw2_driver);
 }
 
-module_init(bw2_init);
 
-#ifdef MODULE
+module_init(bw2_init);
 module_exit(bw2_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for BWTWO chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/cg14.c b/drivers/video/cg14.c
index 63b6c79c8a0a..7f926c619b61 100644
--- a/drivers/video/cg14.c
+++ b/drivers/video/cg14.c
@@ -1,6 +1,6 @@
 /* cg14.c: CGFOURTEEN frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1996,1998 Jakub Jelinek (jj@ultra.linux.cz)
  * Copyright (C) 1995 Miguel de Icaza (miguel@nuclecu.unam.mx)
  *
@@ -18,8 +18,8 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/sbus.h>
-#include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
 #include "sbuslib.h"
@@ -99,73 +99,73 @@ static struct fb_ops cg14_ops = {
 #define CG14_MCR_PIXMODE_32             3
 
 struct cg14_regs{
-        volatile u8 mcr;        /* Master Control Reg */
-        volatile u8 ppr;        /* Packed Pixel Reg */
-        volatile u8 tms[2];     /* Test Mode Status Regs */
-        volatile u8 msr;        /* Master Status Reg */
-        volatile u8 fsr;        /* Fault Status Reg */
-        volatile u8 rev;        /* Revision & Impl */
-        volatile u8 ccr;        /* Clock Control Reg */
-        volatile u32 tmr;       /* Test Mode Read Back */
-        volatile u8 mod;        /* Monitor Operation Data Reg */
-        volatile u8 acr;        /* Aux Control */
+        u8 mcr; /* Master Control Reg */
+        u8 ppr; /* Packed Pixel Reg */
+        u8 tms[2];      /* Test Mode Status Regs */
+        u8 msr; /* Master Status Reg */
+        u8 fsr; /* Fault Status Reg */
+        u8 rev; /* Revision & Impl */
+        u8 ccr; /* Clock Control Reg */
+        u32 tmr;        /* Test Mode Read Back */
+        u8 mod; /* Monitor Operation Data Reg */
+        u8 acr; /* Aux Control */
         u8 xxx0[6];
-        volatile u16 hct;       /* Hor Counter */
-        volatile u16 vct;       /* Vert Counter */
-        volatile u16 hbs;       /* Hor Blank Start */
-        volatile u16 hbc;       /* Hor Blank Clear */
-        volatile u16 hss;       /* Hor Sync Start */
-        volatile u16 hsc;       /* Hor Sync Clear */
-        volatile u16 csc;       /* Composite Sync Clear */
-        volatile u16 vbs;       /* Vert Blank Start */
-        volatile u16 vbc;       /* Vert Blank Clear */
-        volatile u16 vss;       /* Vert Sync Start */
-        volatile u16 vsc;       /* Vert Sync Clear */
-        volatile u16 xcs;
-        volatile u16 xcc;
-        volatile u16 fsa;       /* Fault Status Address */
-        volatile u16 adr;       /* Address Registers */
+        u16 hct;        /* Hor Counter */
+        u16 vct;        /* Vert Counter */
+        u16 hbs;        /* Hor Blank Start */
+        u16 hbc;        /* Hor Blank Clear */
+        u16 hss;        /* Hor Sync Start */
+        u16 hsc;        /* Hor Sync Clear */
+        u16 csc;        /* Composite Sync Clear */
+        u16 vbs;        /* Vert Blank Start */
+        u16 vbc;        /* Vert Blank Clear */
+        u16 vss;        /* Vert Sync Start */
+        u16 vsc;        /* Vert Sync Clear */
+        u16 xcs;
+        u16 xcc;
+        u16 fsa;        /* Fault Status Address */
+        u16 adr;        /* Address Registers */
         u8 xxx1[0xce];
-        volatile u8 pcg[0x100]; /* Pixel Clock Generator */
-        volatile u32 vbr;       /* Frame Base Row */
-        volatile u32 vmcr;      /* VBC Master Control */
-        volatile u32 vcr;       /* VBC refresh */
-        volatile u32 vca;       /* VBC Config */
+        u8 pcg[0x100]; /* Pixel Clock Generator */
+        u32 vbr;        /* Frame Base Row */
+        u32 vmcr;       /* VBC Master Control */
+        u32 vcr;        /* VBC refresh */
+        u32 vca;        /* VBC Config */
 };
 
 #define CG14_CCR_ENABLE 0x04
 #define CG14_CCR_SELECT 0x02    /* HW/Full screen */
 
 struct cg14_cursor {
-        volatile u32 cpl0[32];  /* Enable plane 0 */
-        volatile u32 cpl1[32];  /* Color selection plane */
-        volatile u8 ccr;        /* Cursor Control Reg */
+        u32 cpl0[32];   /* Enable plane 0 */
+        u32 cpl1[32];  /* Color selection plane */
+        u8 ccr; /* Cursor Control Reg */
         u8 xxx0[3];
-        volatile u16 cursx;     /* Cursor x,y position */
-        volatile u16 cursy;     /* Cursor x,y position */
-        volatile u32 color0;
-        volatile u32 color1;
+        u16 cursx;      /* Cursor x,y position */
+        u16 cursy;      /* Cursor x,y position */
+        u32 color0;
+        u32 color1;
         u32 xxx1[0x1bc];
-        volatile u32 cpl0i[32]; /* Enable plane 0 autoinc */
-        volatile u32 cpl1i[32]; /* Color selection autoinc */
+        u32 cpl0i[32];  /* Enable plane 0 autoinc */
+        u32 cpl1i[32]; /* Color selection autoinc */
 };
 
 struct cg14_dac {
-        volatile u8 addr;       /* Address Register */
+        u8 addr;        /* Address Register */
         u8 xxx0[255];
-        volatile u8 glut;       /* Gamma table */
+        u8 glut;        /* Gamma table */
         u8 xxx1[255];
-        volatile u8 select;     /* Register Select */
+        u8 select;      /* Register Select */
         u8 xxx2[255];
-        volatile u8 mode;       /* Mode Register */
+        u8 mode;        /* Mode Register */
 };
 
 struct cg14_xlut{
-        volatile u8 x_xlut [256];
-        volatile u8 x_xlutd [256];
+        u8 x_xlut [256];
+        u8 x_xlutd [256];
         u8 xxx0[0x600];
-        volatile u8 x_xlut_inc [256];
-        volatile u8 x_xlutd_inc [256];
+        u8 x_xlut_inc [256];
+        u8 x_xlutd_inc [256];
 };
 
 /* Color look up table (clut) */
@@ -204,7 +204,6 @@ struct cg14_par {
 
         int                     mode;
         int                     ramsize;
-        struct sbus_dev         *sdev;
 };
 
 static void __cg14_reset(struct cg14_par *par)
@@ -355,14 +354,9 @@ static int cg14_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
  *  Initialisation
  */
 
-static void cg14_init_fix(struct fb_info *info, int linebytes)
+static void cg14_init_fix(struct fb_info *info, int linebytes, struct device_node *dp)
 {
-        struct cg14_par *par = (struct cg14_par *)info->par;
-        const char *name;
-
-        name = "cgfourteen";
-        if (par->sdev)
-                name = par->sdev->prom_name;
+        const char *name = dp->name;
 
         strlcpy(info->fix.id, name, sizeof(info->fix.id));
 
@@ -456,98 +450,81 @@ static struct sbus_mmap_map __cg14_mmap_map[CG14_MMAP_ENTRIES] __initdata = {
 struct all_info {
         struct fb_info info;
         struct cg14_par par;
-        struct list_head list;
 };
-static LIST_HEAD(cg14_list);
 
-static void cg14_init_one(struct sbus_dev *sdev, int node, int parent_node)
+static void cg14_unmap_regs(struct all_info *all)
 {
-        struct all_info *all;
-        unsigned long phys, rphys;
-        u32 bases[6];
-        int is_8mb, linebytes, i;
-
-        if (!sdev) {
-                if (prom_getproperty(node, "address",
-                                     (char *) &bases[0], sizeof(bases)) <= 0
-                    || !bases[0]) {
-                        printk(KERN_ERR "cg14: Device is not mapped.\n");
-                        return;
-                }
-                if (__get_iospace(bases[0]) != __get_iospace(bases[1])) {
-                        printk(KERN_ERR "cg14: I/O spaces don't match.\n");
-                        return;
-                }
-        }
+        if (all->par.regs)
+                of_iounmap(all->par.regs, sizeof(struct cg14_regs));
+        if (all->par.clut)
+                of_iounmap(all->par.clut, sizeof(struct cg14_clut));
+        if (all->par.cursor)
+                of_iounmap(all->par.cursor, sizeof(struct cg14_cursor));
+        if (all->info.screen_base)
+                of_iounmap(all->info.screen_base, all->par.fbsize);
+}
 
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "cg14: Cannot allocate memory.\n");
-                return;
-        }
-        memset(all, 0, sizeof(*all));
+static int __devinit cg14_init_one(struct of_device *op)
+{
+        struct device_node *dp = op->node;
+        struct all_info *all;
+        int is_8mb, linebytes, i, err;
 
-        INIT_LIST_HEAD(&all->list);
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
         spin_lock_init(&all->par.lock);
 
-        sbusfb_fill_var(&all->info.var, node, 8);
+        sbusfb_fill_var(&all->info.var, dp->node, 8);
         all->info.var.red.length = 8;
         all->info.var.green.length = 8;
         all->info.var.blue.length = 8;
 
-        linebytes = prom_getintdefault(node, "linebytes",
-                                       all->info.var.xres);
+        linebytes = of_getintprop_default(dp, "linebytes",
+                                          all->info.var.xres);
         all->par.fbsize = PAGE_ALIGN(linebytes * all->info.var.yres);
 
-        all->par.sdev = sdev;
-        if (sdev) {
-                rphys = sdev->reg_addrs[0].phys_addr;
-                all->par.physbase = phys = sdev->reg_addrs[1].phys_addr;
-                all->par.iospace = sdev->reg_addrs[0].which_io;
-
-                all->par.regs = sbus_ioremap(&sdev->resource[0], 0,
-                                     sizeof(struct cg14_regs),
-                                     "cg14 regs");
-                all->par.clut = sbus_ioremap(&sdev->resource[0], CG14_CLUT1,
-                                     sizeof(struct cg14_clut),
-                                     "cg14 clut");
-                all->par.cursor = sbus_ioremap(&sdev->resource[0], CG14_CURSORREGS,
-                                     sizeof(struct cg14_cursor),
-                                     "cg14 cursor");
-                all->info.screen_base = sbus_ioremap(&sdev->resource[1], 0,
-                                     all->par.fbsize, "cg14 ram");
+        if (!strcmp(dp->parent->name, "sbus") ||
+            !strcmp(dp->parent->name, "sbi")) {
+                all->par.physbase = op->resource[0].start;
+                all->par.iospace = op->resource[0].flags & IORESOURCE_BITS;
         } else {
-                rphys = __get_phys(bases[0]);
-                all->par.physbase = phys = __get_phys(bases[1]);
-                all->par.iospace = __get_iospace(bases[0]);
-                all->par.regs = (struct cg14_regs __iomem *)(unsigned long)bases[0];
-                all->par.clut = (struct cg14_clut __iomem *)((unsigned long)bases[0] +
-                                                     CG14_CLUT1);
-                all->par.cursor =
-                        (struct cg14_cursor __iomem *)((unsigned long)bases[0] +
-                                               CG14_CURSORREGS);
-
-                all->info.screen_base = (char __iomem *)(unsigned long)bases[1];
+                all->par.physbase = op->resource[1].start;
+                all->par.iospace = op->resource[0].flags & IORESOURCE_BITS;
         }
 
-        prom_getproperty(node, "reg", (char *) &bases[0], sizeof(bases));
-        is_8mb = (bases[5] == 0x800000);
+        all->par.regs = of_ioremap(&op->resource[0], 0,
+                                   sizeof(struct cg14_regs), "cg14 regs");
+        all->par.clut = of_ioremap(&op->resource[0], CG14_CLUT1,
+                                   sizeof(struct cg14_clut), "cg14 clut");
+        all->par.cursor = of_ioremap(&op->resource[0], CG14_CURSORREGS,
+                                   sizeof(struct cg14_cursor), "cg14 cursor");
 
-        if (sizeof(all->par.mmap_map) != sizeof(__cg14_mmap_map)) {
-                extern void __cg14_mmap_sized_wrongly(void);
+        all->info.screen_base = of_ioremap(&op->resource[1], 0,
+                                           all->par.fbsize, "cg14 ram");
 
-                __cg14_mmap_sized_wrongly();
-        }
+        if (!all->par.regs || !all->par.clut || !all->par.cursor ||
+            !all->info.screen_base)
+                cg14_unmap_regs(all);
+
+        is_8mb = (((op->resource[1].end - op->resource[1].start) + 1) ==
+                  (8 * 1024 * 1024));
+
+        BUILD_BUG_ON(sizeof(all->par.mmap_map) != sizeof(__cg14_mmap_map));
                 
-        memcpy(&all->par.mmap_map, &__cg14_mmap_map, sizeof(all->par.mmap_map));
+        memcpy(&all->par.mmap_map, &__cg14_mmap_map,
+               sizeof(all->par.mmap_map));
+
         for (i = 0; i < CG14_MMAP_ENTRIES; i++) {
                 struct sbus_mmap_map *map = &all->par.mmap_map[i];
 
                 if (!map->size)
                         break;
                 if (map->poff & 0x80000000)
-                        map->poff = (map->poff & 0x7fffffff) + rphys - phys;
+                        map->poff = (map->poff & 0x7fffffff) +
+                                (op->resource[0].start -
+                                 op->resource[1].start);
                 if (is_8mb &&
                     map->size >= 0x100000 &&
                     map->size <= 0x400000)
@@ -564,84 +541,87 @@ static void cg14_init_one(struct sbus_dev *sdev, int node, int parent_node)
         __cg14_reset(&all->par);
 
         if (fb_alloc_cmap(&all->info.cmap, 256, 0)) {
-                printk(KERN_ERR "cg14: Could not allocate color map.\n");
+                cg14_unmap_regs(all);
                 kfree(all);
-                return;
+                return -ENOMEM;
         }
         fb_set_cmap(&all->info.cmap, &all->info);
 
-        cg14_init_fix(&all->info, linebytes);
+        cg14_init_fix(&all->info, linebytes, dp);
 
-        if (register_framebuffer(&all->info) < 0) {
-                printk(KERN_ERR "cg14: Could not register framebuffer.\n");
+        err = register_framebuffer(&all->info);
+        if (err < 0) {
                 fb_dealloc_cmap(&all->info.cmap);
+                cg14_unmap_regs(all);
                 kfree(all);
-                return;
+                return err;
         }
 
-        list_add(&all->list, &cg14_list);
+        dev_set_drvdata(&op->dev, all);
 
-        printk("cg14: cgfourteen at %lx:%lx, %dMB\n",
-               all->par.iospace, all->par.physbase, all->par.ramsize >> 20);
+        printk("%s: cgfourteen at %lx:%lx, %dMB\n",
+               dp->full_name,
+               all->par.iospace, all->par.physbase,
+               all->par.ramsize >> 20);
 
+        return 0;
 }
 
-int __init cg14_init(void)
+static int __devinit cg14_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_bus *sbus;
-        struct sbus_dev *sdev;
+        struct of_device *op = to_of_device(&dev->dev);
 
-        if (fb_get_options("cg14fb", NULL))
-                return -ENODEV;
+        return cg14_init_one(op);
+}
 
-#ifdef CONFIG_SPARC32
-        {
-                int root, node;
-
-                root = prom_getchild(prom_root_node);
-                root = prom_searchsiblings(root, "obio");
-                if (root) {
-                        node = prom_searchsiblings(prom_getchild(root),
-                                                   "cgfourteen");
-                        if (node)
-                                cg14_init_one(NULL, node, root);
-                }
-        }
-#endif
-        for_all_sbusdev(sdev, sbus) {
-                if (!strcmp(sdev->prom_name, "cgfourteen"))
-                        cg14_init_one(sdev, sdev->prom_node, sbus->prom_node);
-        }
+static int __devexit cg14_remove(struct of_device *dev)
+{
+        struct all_info *all = dev_get_drvdata(&dev->dev);
+
+        unregister_framebuffer(&all->info);
+        fb_dealloc_cmap(&all->info.cmap);
+
+        cg14_unmap_regs(all);
+
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit cg14_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id cg14_match[] = {
+        {
+                .name = "cgfourteen",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, cg14_match);
 
-        list_for_each_safe(pos, tmp, &cg14_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+static struct of_platform_driver cg14_driver = {
+        .name           = "cg14",
+        .match_table    = cg14_match,
+        .probe          = cg14_probe,
+        .remove         = __devexit_p(cg14_remove),
+};
 
-                unregister_framebuffer(&all->info);
-                fb_dealloc_cmap(&all->info.cmap);
-                kfree(all);
-        }
+int __init cg14_init(void)
+{
+        if (fb_get_options("cg14fb", NULL))
+                return -ENODEV;
+
+        return of_register_driver(&cg14_driver, &of_bus_type);
 }
 
-int __init
-cg14_setup(char *arg)
+void __exit cg14_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        of_unregister_driver(&cg14_driver);
 }
 
 module_init(cg14_init);
-
-#ifdef MODULE
 module_exit(cg14_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for CGfourteen chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/cg3.c b/drivers/video/cg3.c
index 3de6e1b5ab2f..9c8c753ef454 100644
--- a/drivers/video/cg3.c
+++ b/drivers/video/cg3.c
@@ -1,6 +1,6 @@
 /* cg3.c: CGTHREE frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1996,1998 Jakub Jelinek (jj@ultra.linux.cz)
  * Copyright (C) 1996 Miguel de Icaza (miguel@nuclecu.unam.mx)
  * Copyright (C) 1997 Eddie C. Dost (ecd@skynet.be)
@@ -19,8 +19,9 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/sbus.h>
 #include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
 #include "sbuslib.h"
@@ -80,30 +81,30 @@ enum cg3_type {
 };
 
 struct bt_regs {
-        volatile u32 addr;
-        volatile u32 color_map;
-        volatile u32 control;
-        volatile u32 cursor;
+        u32 addr;
+        u32 color_map;
+        u32 control;
+        u32 cursor;
 };
 
 struct cg3_regs {
         struct bt_regs  cmap;
-        volatile u8     control;
-        volatile u8     status;
-        volatile u8     cursor_start;
-        volatile u8     cursor_end;
-        volatile u8     h_blank_start;
-        volatile u8     h_blank_end;
-        volatile u8     h_sync_start;
-        volatile u8     h_sync_end;
-        volatile u8     comp_sync_end;
-        volatile u8     v_blank_start_high;
-        volatile u8     v_blank_start_low;
-        volatile u8     v_blank_end;
-        volatile u8     v_sync_start;
-        volatile u8     v_sync_end;
-        volatile u8     xfer_holdoff_start;
-        volatile u8     xfer_holdoff_end;
+        u8      control;
+        u8      status;
+        u8      cursor_start;
+        u8      cursor_end;
+        u8      h_blank_start;
+        u8      h_blank_end;
+        u8      h_sync_start;
+        u8      h_sync_end;
+        u8      comp_sync_end;
+        u8      v_blank_start_high;
+        u8      v_blank_start_low;
+        u8      v_blank_end;
+        u8      v_sync_start;
+        u8      v_sync_end;
+        u8      xfer_holdoff_start;
+        u8      xfer_holdoff_end;
 };
 
 /* Offset of interesting structures in the OBIO space */
@@ -120,9 +121,8 @@ struct cg3_par {
 #define CG3_FLAG_RDI            0x00000002
 
         unsigned long           physbase;
+        unsigned long           which_io;
         unsigned long           fbsize;
-
-        struct sbus_dev         *sdev;
 };
 
 /**
@@ -235,7 +235,7 @@ static int cg3_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
         return sbusfb_mmap_helper(cg3_mmap_map,
                                   par->physbase, par->fbsize,
-                                  par->sdev->reg_addrs[0].which_io,
+                                  par->which_io,
                                   vma);
 }
 
@@ -252,11 +252,9 @@ static int cg3_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
  */
 
 static void
-cg3_init_fix(struct fb_info *info, int linebytes)
+cg3_init_fix(struct fb_info *info, int linebytes, struct device_node *dp)
 {
-        struct cg3_par *par = (struct cg3_par *)info->par;
-
-        strlcpy(info->fix.id, par->sdev->prom_name, sizeof(info->fix.id));
+        strlcpy(info->fix.id, dp->name, sizeof(info->fix.id));
 
         info->fix.type = FB_TYPE_PACKED_PIXELS;
         info->fix.visual = FB_VISUAL_PSEUDOCOLOR;
@@ -267,16 +265,15 @@ cg3_init_fix(struct fb_info *info, int linebytes)
 }
 
 static void cg3_rdi_maybe_fixup_var(struct fb_var_screeninfo *var,
-                                    struct sbus_dev *sdev)
+                                    struct device_node *dp)
 {
-        char buffer[40];
+        char *params;
         char *p;
         int ww, hh;
 
-        *buffer = 0;
-        prom_getstring(sdev->prom_node, "params", buffer, sizeof(buffer));
-        if (*buffer) {
-                ww = simple_strtoul(buffer, &p, 10);
+        params = of_get_property(dp, "params", NULL);
+        if (params) {
+                ww = simple_strtoul(params, &p, 10);
                 if (ww && *p == 'x') {
                         hh = simple_strtoul(p + 1, &p, 10);
                         if (hh && *p == '-') {
@@ -348,11 +345,11 @@ static void cg3_do_default_mode(struct cg3_par *par)
                 sbus_writeb(p[1], regp);
         }
         for (p = cg3_dacvals; *p; p += 2) {
-                volatile u8 __iomem *regp;
+                u8 __iomem *regp;
 
-                regp = (volatile u8 __iomem *)&par->regs->cmap.addr;
+                regp = (u8 __iomem *)&par->regs->cmap.addr;
                 sbus_writeb(p[0], regp);
-                regp = (volatile u8 __iomem *)&par->regs->cmap.control;
+                regp = (u8 __iomem *)&par->regs->cmap.control;
                 sbus_writeb(p[1], regp);
         }
 }
@@ -360,129 +357,137 @@ static void cg3_do_default_mode(struct cg3_par *par)
 struct all_info {
         struct fb_info info;
         struct cg3_par par;
-        struct list_head list;
 };
-static LIST_HEAD(cg3_list);
 
-static void cg3_init_one(struct sbus_dev *sdev)
+static int __devinit cg3_init_one(struct of_device *op)
 {
+        struct device_node *dp = op->node;
         struct all_info *all;
-        int linebytes;
-
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "cg3: Cannot allocate memory.\n");
-                return;
-        }
-        memset(all, 0, sizeof(*all));
+        int linebytes, err;
 
-        INIT_LIST_HEAD(&all->list);
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
         spin_lock_init(&all->par.lock);
-        all->par.sdev = sdev;
 
-        all->par.physbase = sdev->reg_addrs[0].phys_addr;
+        all->par.physbase = op->resource[0].start;
+        all->par.which_io = op->resource[0].flags & IORESOURCE_BITS;
 
-        sbusfb_fill_var(&all->info.var, sdev->prom_node, 8);
+        sbusfb_fill_var(&all->info.var, dp->node, 8);
         all->info.var.red.length = 8;
         all->info.var.green.length = 8;
         all->info.var.blue.length = 8;
-        if (!strcmp(sdev->prom_name, "cgRDI"))
+        if (!strcmp(dp->name, "cgRDI"))
                 all->par.flags |= CG3_FLAG_RDI;
         if (all->par.flags & CG3_FLAG_RDI)
-                cg3_rdi_maybe_fixup_var(&all->info.var, sdev);
+                cg3_rdi_maybe_fixup_var(&all->info.var, dp);
 
-        linebytes = prom_getintdefault(sdev->prom_node, "linebytes",
-                                       all->info.var.xres);
+        linebytes = of_getintprop_default(dp, "linebytes",
+                                          all->info.var.xres);
         all->par.fbsize = PAGE_ALIGN(linebytes * all->info.var.yres);
 
-        all->par.regs = sbus_ioremap(&sdev->resource[0], CG3_REGS_OFFSET,
-                             sizeof(struct cg3_regs), "cg3 regs");
+        all->par.regs = of_ioremap(&op->resource[0], CG3_REGS_OFFSET,
+                                   sizeof(struct cg3_regs), "cg3 regs");
 
         all->info.flags = FBINFO_DEFAULT;
         all->info.fbops = &cg3_ops;
-#ifdef CONFIG_SPARC32
-        all->info.screen_base = (char __iomem *)
-                prom_getintdefault(sdev->prom_node, "address", 0);
-#endif
-        if (!all->info.screen_base)
-                all->info.screen_base =
-                        sbus_ioremap(&sdev->resource[0], CG3_RAM_OFFSET,
-                                     all->par.fbsize, "cg3 ram");
+        all->info.screen_base =
+                of_ioremap(&op->resource[0], CG3_RAM_OFFSET,
+                           all->par.fbsize, "cg3 ram");
         all->info.par = &all->par;
 
         cg3_blank(0, &all->info);
 
-        if (!prom_getbool(sdev->prom_node, "width"))
+        if (!of_find_property(dp, "width", NULL))
                 cg3_do_default_mode(&all->par);
 
         if (fb_alloc_cmap(&all->info.cmap, 256, 0)) {
-                printk(KERN_ERR "cg3: Could not allocate color map.\n");
+                of_iounmap(all->par.regs, sizeof(struct cg3_regs));
+                of_iounmap(all->info.screen_base, all->par.fbsize);
                 kfree(all);
-                return;
+                return -ENOMEM;
         }
         fb_set_cmap(&all->info.cmap, &all->info);
 
-        cg3_init_fix(&all->info, linebytes);
+        cg3_init_fix(&all->info, linebytes, dp);
 
-        if (register_framebuffer(&all->info) < 0) {
-                printk(KERN_ERR "cg3: Could not register framebuffer.\n");
+        err = register_framebuffer(&all->info);
+        if (err < 0) {
                 fb_dealloc_cmap(&all->info.cmap);
+                of_iounmap(all->par.regs, sizeof(struct cg3_regs));
+                of_iounmap(all->info.screen_base, all->par.fbsize);
                 kfree(all);
-                return;
+                return err;
         }
 
-        list_add(&all->list, &cg3_list);
+        dev_set_drvdata(&op->dev, all);
+
+        printk("%s: cg3 at %lx:%lx\n",
+               dp->full_name, all->par.which_io, all->par.physbase);
 
-        printk("cg3: %s at %lx:%lx\n",
-               sdev->prom_name,
-               (long) sdev->reg_addrs[0].which_io,
-               (long) sdev->reg_addrs[0].phys_addr);
+        return 0;
 }
 
-int __init cg3_init(void)
+static int __devinit cg3_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_bus *sbus;
-        struct sbus_dev *sdev;
+        struct of_device *op = to_of_device(&dev->dev);
 
-        if (fb_get_options("cg3fb", NULL))
-                return -ENODEV;
+        return cg3_init_one(op);
+}
 
-        for_all_sbusdev(sdev, sbus) {
-                if (!strcmp(sdev->prom_name, "cgthree") ||
-                    !strcmp(sdev->prom_name, "cgRDI"))
-                        cg3_init_one(sdev);
-        }
+static int __devexit cg3_remove(struct of_device *dev)
+{
+        struct all_info *all = dev_get_drvdata(&dev->dev);
+
+        unregister_framebuffer(&all->info);
+        fb_dealloc_cmap(&all->info.cmap);
+
+        of_iounmap(all->par.regs, sizeof(struct cg3_regs));
+        of_iounmap(all->info.screen_base, all->par.fbsize);
+
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit cg3_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id cg3_match[] = {
+        {
+                .name = "cgthree",
+        },
+        {
+                .name = "cgRDI",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, cg3_match);
 
-        list_for_each_safe(pos, tmp, &cg3_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+static struct of_platform_driver cg3_driver = {
+        .name           = "cg3",
+        .match_table    = cg3_match,
+        .probe          = cg3_probe,
+        .remove         = __devexit_p(cg3_remove),
+};
 
-                unregister_framebuffer(&all->info);
-                fb_dealloc_cmap(&all->info.cmap);
-                kfree(all);
-        }
+static int __init cg3_init(void)
+{
+        if (fb_get_options("cg3fb", NULL))
+                return -ENODEV;
+
+        return of_register_driver(&cg3_driver, &of_bus_type);
 }
 
-int __init
-cg3_setup(char *arg)
+static void __exit cg3_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        of_unregister_driver(&cg3_driver);
 }
 
 module_init(cg3_init);
-
-#ifdef MODULE
 module_exit(cg3_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for CGthree chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/cg6.c b/drivers/video/cg6.c
index 7aab91ead681..64146be2eeb0 100644
--- a/drivers/video/cg6.c
+++ b/drivers/video/cg6.c
@@ -1,6 +1,6 @@
 /* cg6.c: CGSIX (GX, GXplus, TGX) frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1996,1998 Jakub Jelinek (jj@ultra.linux.cz)
  * Copyright (C) 1996 Miguel de Icaza (miguel@nuclecu.unam.mx)
  * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
@@ -19,8 +19,8 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/sbus.h>
-#include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
 #include "sbuslib.h"
@@ -164,89 +164,89 @@ static struct fb_ops cg6_ops = {
 
 /* The contents are unknown */
 struct cg6_tec {
-        volatile int tec_matrix;
-        volatile int tec_clip;
-        volatile int tec_vdc;
+        int tec_matrix;
+        int tec_clip;
+        int tec_vdc;
 };
 
 struct cg6_thc {
-        uint thc_pad0[512];
-        volatile uint thc_hs;           /* hsync timing */
-        volatile uint thc_hsdvs;
-        volatile uint thc_hd;
-        volatile uint thc_vs;           /* vsync timing */
-        volatile uint thc_vd;
-        volatile uint thc_refresh;
-        volatile uint thc_misc;
-        uint thc_pad1[56];
-        volatile uint thc_cursxy;       /* cursor x,y position (16 bits each) */
-        volatile uint thc_cursmask[32]; /* cursor mask bits */
-        volatile uint thc_cursbits[32]; /* what to show where mask enabled */
+        u32 thc_pad0[512];
+        u32 thc_hs;             /* hsync timing */
+        u32 thc_hsdvs;
+        u32 thc_hd;
+        u32 thc_vs;             /* vsync timing */
+        u32 thc_vd;
+        u32 thc_refresh;
+        u32 thc_misc;
+        u32 thc_pad1[56];
+        u32 thc_cursxy; /* cursor x,y position (16 bits each) */
+        u32 thc_cursmask[32];   /* cursor mask bits */
+        u32 thc_cursbits[32];   /* what to show where mask enabled */
 };
 
 struct cg6_fbc {
-        u32             xxx0[1];
-        volatile u32    mode;
-        volatile u32    clip;
-        u32             xxx1[1];            
-        volatile u32    s;
-        volatile u32    draw;
-        volatile u32    blit;
-        volatile u32    font;
-        u32             xxx2[24];
-        volatile u32    x0, y0, z0, color0;
-        volatile u32    x1, y1, z1, color1;
-        volatile u32    x2, y2, z2, color2;
-        volatile u32    x3, y3, z3, color3;
-        volatile u32    offx, offy;
-        u32             xxx3[2];
-        volatile u32    incx, incy;
-        u32             xxx4[2];
-        volatile u32    clipminx, clipminy;
-        u32             xxx5[2];
-        volatile u32    clipmaxx, clipmaxy;
-        u32             xxx6[2];
-        volatile u32    fg;
-        volatile u32    bg;
-        volatile u32    alu;
-        volatile u32    pm;
-        volatile u32    pixelm;
-        u32             xxx7[2];
-        volatile u32    patalign;
-        volatile u32    pattern[8];
-        u32             xxx8[432];
-        volatile u32    apointx, apointy, apointz;
-        u32             xxx9[1];
-        volatile u32    rpointx, rpointy, rpointz;
-        u32             xxx10[5];
-        volatile u32    pointr, pointg, pointb, pointa;
-        volatile u32    alinex, aliney, alinez;
-        u32             xxx11[1];
-        volatile u32    rlinex, rliney, rlinez;
-        u32             xxx12[5];
-        volatile u32    liner, lineg, lineb, linea;
-        volatile u32    atrix, atriy, atriz;
-        u32             xxx13[1];
-        volatile u32    rtrix, rtriy, rtriz;
-        u32             xxx14[5];
-        volatile u32    trir, trig, trib, tria;
-        volatile u32    aquadx, aquady, aquadz;
-        u32             xxx15[1];
-        volatile u32    rquadx, rquady, rquadz;
-        u32             xxx16[5];
-        volatile u32    quadr, quadg, quadb, quada;
-        volatile u32    arectx, arecty, arectz;
-        u32             xxx17[1];
-        volatile u32    rrectx, rrecty, rrectz;
-        u32             xxx18[5];
-        volatile u32    rectr, rectg, rectb, recta;
+        u32     xxx0[1];
+        u32     mode;
+        u32     clip;
+        u32     xxx1[1];            
+        u32     s;
+        u32     draw;
+        u32     blit;
+        u32     font;
+        u32     xxx2[24];
+        u32     x0, y0, z0, color0;
+        u32     x1, y1, z1, color1;
+        u32     x2, y2, z2, color2;
+        u32     x3, y3, z3, color3;
+        u32     offx, offy;
+        u32     xxx3[2];
+        u32     incx, incy;
+        u32     xxx4[2];
+        u32     clipminx, clipminy;
+        u32     xxx5[2];
+        u32     clipmaxx, clipmaxy;
+        u32     xxx6[2];
+        u32     fg;
+        u32     bg;
+        u32     alu;
+        u32     pm;
+        u32     pixelm;
+        u32     xxx7[2];
+        u32     patalign;
+        u32     pattern[8];
+        u32     xxx8[432];
+        u32     apointx, apointy, apointz;
+        u32     xxx9[1];
+        u32     rpointx, rpointy, rpointz;
+        u32     xxx10[5];
+        u32     pointr, pointg, pointb, pointa;
+        u32     alinex, aliney, alinez;
+        u32     xxx11[1];
+        u32     rlinex, rliney, rlinez;
+        u32     xxx12[5];
+        u32     liner, lineg, lineb, linea;
+        u32     atrix, atriy, atriz;
+        u32     xxx13[1];
+        u32     rtrix, rtriy, rtriz;
+        u32     xxx14[5];
+        u32     trir, trig, trib, tria;
+        u32     aquadx, aquady, aquadz;
+        u32     xxx15[1];
+        u32     rquadx, rquady, rquadz;
+        u32     xxx16[5];
+        u32     quadr, quadg, quadb, quada;
+        u32     arectx, arecty, arectz;
+        u32     xxx17[1];
+        u32     rrectx, rrecty, rrectz;
+        u32     xxx18[5];
+        u32     rectr, rectg, rectb, recta;
 };
 
 struct bt_regs {
-        volatile u32 addr;
-        volatile u32 color_map;
-        volatile u32 control;
-        volatile u32 cursor;
+        u32 addr;
+        u32 color_map;
+        u32 control;
+        u32 cursor;
 };
 
 struct cg6_par {
@@ -255,15 +255,14 @@ struct cg6_par {
         struct cg6_fbc          __iomem *fbc;
         struct cg6_thc          __iomem *thc;
         struct cg6_tec          __iomem *tec;
-        volatile u32            __iomem *fhc;
+        u32                     __iomem *fhc;
 
         u32                     flags;
 #define CG6_FLAG_BLANKED        0x00000001
 
         unsigned long           physbase;
+        unsigned long           which_io;
         unsigned long           fbsize;
-
-        struct sbus_dev         *sdev;
 };
 
 static int cg6_sync(struct fb_info *info)
@@ -529,8 +528,7 @@ static int cg6_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
         return sbusfb_mmap_helper(cg6_mmap_map,
                                   par->physbase, par->fbsize,
-                                  par->sdev->reg_addrs[0].which_io,
-                                  vma);
+                                  par->which_io, vma);
 }
 
 static int cg6_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
@@ -658,62 +656,75 @@ static void cg6_chip_init(struct fb_info *info)
 struct all_info {
         struct fb_info info;
         struct cg6_par par;
-        struct list_head list;
 };
-static LIST_HEAD(cg6_list);
 
-static void cg6_init_one(struct sbus_dev *sdev)
+static void cg6_unmap_regs(struct all_info *all)
 {
-        struct all_info *all;
-        int linebytes;
+        if (all->par.fbc)
+                of_iounmap(all->par.fbc, 4096);
+        if (all->par.tec)
+                of_iounmap(all->par.tec, sizeof(struct cg6_tec));
+        if (all->par.thc)
+                of_iounmap(all->par.thc, sizeof(struct cg6_thc));
+        if (all->par.bt)
+                of_iounmap(all->par.bt, sizeof(struct bt_regs));
+        if (all->par.fhc)
+                of_iounmap(all->par.fhc, sizeof(u32));
+
+        if (all->info.screen_base)
+                of_iounmap(all->info.screen_base, all->par.fbsize);
+}
 
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "cg6: Cannot allocate memory.\n");
-                return;
-        }
-        memset(all, 0, sizeof(*all));
+static int __devinit cg6_init_one(struct of_device *op)
+{
+        struct device_node *dp = op->node;
+        struct all_info *all;
+        int linebytes, err;
 
-        INIT_LIST_HEAD(&all->list);
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
         spin_lock_init(&all->par.lock);
-        all->par.sdev = sdev;
 
-        all->par.physbase = sdev->reg_addrs[0].phys_addr;
+        all->par.physbase = op->resource[0].start;
+        all->par.which_io = op->resource[0].flags & IORESOURCE_BITS;
 
-        sbusfb_fill_var(&all->info.var, sdev->prom_node, 8);
+        sbusfb_fill_var(&all->info.var, dp->node, 8);
         all->info.var.red.length = 8;
         all->info.var.green.length = 8;
         all->info.var.blue.length = 8;
 
-        linebytes = prom_getintdefault(sdev->prom_node, "linebytes",
-                                       all->info.var.xres);
+        linebytes = of_getintprop_default(dp, "linebytes",
+                                          all->info.var.xres);
         all->par.fbsize = PAGE_ALIGN(linebytes * all->info.var.yres);
-        if (prom_getbool(sdev->prom_node, "dblbuf"))
+        if (of_find_property(dp, "dblbuf", NULL))
                 all->par.fbsize *= 4;
 
-        all->par.fbc = sbus_ioremap(&sdev->resource[0], CG6_FBC_OFFSET,
-                             4096, "cgsix fbc");
-        all->par.tec = sbus_ioremap(&sdev->resource[0], CG6_TEC_OFFSET,
-                             sizeof(struct cg6_tec), "cgsix tec");
-        all->par.thc = sbus_ioremap(&sdev->resource[0], CG6_THC_OFFSET,
-                             sizeof(struct cg6_thc), "cgsix thc");
-        all->par.bt = sbus_ioremap(&sdev->resource[0], CG6_BROOKTREE_OFFSET,
-                             sizeof(struct bt_regs), "cgsix dac");
-        all->par.fhc = sbus_ioremap(&sdev->resource[0], CG6_FHC_OFFSET,
-                             sizeof(u32), "cgsix fhc");
+        all->par.fbc = of_ioremap(&op->resource[0], CG6_FBC_OFFSET,
+                                  4096, "cgsix fbc");
+        all->par.tec = of_ioremap(&op->resource[0], CG6_TEC_OFFSET,
+                                  sizeof(struct cg6_tec), "cgsix tec");
+        all->par.thc = of_ioremap(&op->resource[0], CG6_THC_OFFSET,
+                                  sizeof(struct cg6_thc), "cgsix thc");
+        all->par.bt = of_ioremap(&op->resource[0], CG6_BROOKTREE_OFFSET,
+                                 sizeof(struct bt_regs), "cgsix dac");
+        all->par.fhc = of_ioremap(&op->resource[0], CG6_FHC_OFFSET,
+                                  sizeof(u32), "cgsix fhc");
 
         all->info.flags = FBINFO_DEFAULT | FBINFO_HWACCEL_IMAGEBLIT |
                           FBINFO_HWACCEL_COPYAREA | FBINFO_HWACCEL_FILLRECT;
         all->info.fbops = &cg6_ops;
-#ifdef CONFIG_SPARC32
-        all->info.screen_base = (char __iomem *)
-                prom_getintdefault(sdev->prom_node, "address", 0);
-#endif
-        if (!all->info.screen_base)
-                all->info.screen_base = 
-                        sbus_ioremap(&sdev->resource[0], CG6_RAM_OFFSET,
-                                     all->par.fbsize, "cgsix ram");
+
+        all->info.screen_base =  of_ioremap(&op->resource[0], CG6_RAM_OFFSET,
+                                            all->par.fbsize, "cgsix ram");
+        if (!all->par.fbc || !all->par.tec || !all->par.thc ||
+            !all->par.bt || !all->par.fhc || !all->info.screen_base) {
+                cg6_unmap_regs(all);
+                kfree(all);
+                return -ENOMEM;
+        }
+
         all->info.par = &all->par;
 
         all->info.var.accel_flags = FB_ACCELF_TEXT;
@@ -723,72 +734,90 @@ static void cg6_init_one(struct sbus_dev *sdev)
         cg6_blank(0, &all->info);
 
         if (fb_alloc_cmap(&all->info.cmap, 256, 0)) {
-                printk(KERN_ERR "cg6: Could not allocate color map.\n");
+                cg6_unmap_regs(all);
                 kfree(all);
-                return;
+                return -ENOMEM;
         }
 
         fb_set_cmap(&all->info.cmap, &all->info);
         cg6_init_fix(&all->info, linebytes);
 
-        if (register_framebuffer(&all->info) < 0) {
-                printk(KERN_ERR "cg6: Could not register framebuffer.\n");
+        err = register_framebuffer(&all->info);
+        if (err < 0) {
+                cg6_unmap_regs(all);
                 fb_dealloc_cmap(&all->info.cmap);
                 kfree(all);
-                return;
+                return err;
         }
 
-        list_add(&all->list, &cg6_list);
+        dev_set_drvdata(&op->dev, all);
 
-        printk("cg6: CGsix [%s] at %lx:%lx\n",
+        printk("%s: CGsix [%s] at %lx:%lx\n",
+               dp->full_name,
                all->info.fix.id,
-               (long) sdev->reg_addrs[0].which_io,
-               (long) sdev->reg_addrs[0].phys_addr);
+               all->par.which_io, all->par.physbase);
+
+        return 0;
 }
 
-int __init cg6_init(void)
+static int __devinit cg6_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_bus *sbus;
-        struct sbus_dev *sdev;
+        struct of_device *op = to_of_device(&dev->dev);
 
-        if (fb_get_options("cg6fb", NULL))
-                return -ENODEV;
+        return cg6_init_one(op);
+}
 
-        for_all_sbusdev(sdev, sbus) {
-                if (!strcmp(sdev->prom_name, "cgsix") ||
-                    !strcmp(sdev->prom_name, "cgthree+"))
-                        cg6_init_one(sdev);
-        }
+static int __devexit cg6_remove(struct of_device *dev)
+{
+        struct all_info *all = dev_get_drvdata(&dev->dev);
+
+        unregister_framebuffer(&all->info);
+        fb_dealloc_cmap(&all->info.cmap);
+
+        cg6_unmap_regs(all);
+
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit cg6_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id cg6_match[] = {
+        {
+                .name = "cgsix",
+        },
+        {
+                .name = "cgthree+",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, cg6_match);
 
-        list_for_each_safe(pos, tmp, &cg6_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+static struct of_platform_driver cg6_driver = {
+        .name           = "cg6",
+        .match_table    = cg6_match,
+        .probe          = cg6_probe,
+        .remove         = __devexit_p(cg6_remove),
+};
 
-                unregister_framebuffer(&all->info);
-                fb_dealloc_cmap(&all->info.cmap);
-                kfree(all);
-        }
+static int __init cg6_init(void)
+{
+        if (fb_get_options("cg6fb", NULL))
+                return -ENODEV;
+
+        return of_register_driver(&cg6_driver, &of_bus_type);
 }
 
-int __init
-cg6_setup(char *arg)
+static void __exit cg6_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        of_unregister_driver(&cg6_driver);
 }
 
 module_init(cg6_init);
-
-#ifdef MODULE
 module_exit(cg6_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for CGsix chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/ffb.c b/drivers/video/ffb.c
index 7633e41adda1..2a0e8210d398 100644
--- a/drivers/video/ffb.c
+++ b/drivers/video/ffb.c
@@ -1,6 +1,6 @@
 /* ffb.c: Creator/Elite3D frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1997,1998,1999 Jakub Jelinek (jj@ultra.linux.cz)
  *
  * Driver layout based loosely on tgafb.c, see that file for credits.
@@ -19,7 +19,8 @@
 
 #include <asm/io.h>
 #include <asm/upa.h>
-#include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
 #include "sbuslib.h"
@@ -184,161 +185,161 @@ static struct fb_ops ffb_ops = {
 
 struct ffb_fbc {
         /* Next vertex registers */
-        u32             xxx1[3];
-        volatile u32    alpha;
-        volatile u32    red;
-        volatile u32    green;
-        volatile u32    blue;
-        volatile u32    depth;
-        volatile u32    y;
-        volatile u32    x;
-        u32             xxx2[2];
-        volatile u32    ryf;
-        volatile u32    rxf;
-        u32             xxx3[2];
+        u32     xxx1[3];
+        u32     alpha;
+        u32     red;
+        u32     green;
+        u32     blue;
+        u32     depth;
+        u32     y;
+        u32     x;
+        u32     xxx2[2];
+        u32     ryf;
+        u32     rxf;
+        u32     xxx3[2];
         
-        volatile u32    dmyf;
-        volatile u32    dmxf;
-        u32             xxx4[2];
-        volatile u32    ebyi;
-        volatile u32    ebxi;
-        u32             xxx5[2];
-        volatile u32    by;
-        volatile u32    bx;
-        u32             dy;
-        u32             dx;
-        volatile u32    bh;
-        volatile u32    bw;
-        u32             xxx6[2];
+        u32     dmyf;
+        u32     dmxf;
+        u32     xxx4[2];
+        u32     ebyi;
+        u32     ebxi;
+        u32     xxx5[2];
+        u32     by;
+        u32     bx;
+        u32     dy;
+        u32     dx;
+        u32     bh;
+        u32     bw;
+        u32     xxx6[2];
         
-        u32             xxx7[32];
+        u32     xxx7[32];
         
         /* Setup unit vertex state register */
-        volatile u32    suvtx;
-        u32             xxx8[63];
+        u32     suvtx;
+        u32     xxx8[63];
         
         /* Control registers */
-        volatile u32    ppc;
-        volatile u32    wid;
-        volatile u32    fg;
-        volatile u32    bg;
-        volatile u32    consty;
-        volatile u32    constz;
-        volatile u32    xclip;
-        volatile u32    dcss;
-        volatile u32    vclipmin;
-        volatile u32    vclipmax;
-        volatile u32    vclipzmin;
-        volatile u32    vclipzmax;
-        volatile u32    dcsf;
-        volatile u32    dcsb;
-        volatile u32    dczf;
-        volatile u32    dczb;
+        u32     ppc;
+        u32     wid;
+        u32     fg;
+        u32     bg;
+        u32     consty;
+        u32     constz;
+        u32     xclip;
+        u32     dcss;
+        u32     vclipmin;
+        u32     vclipmax;
+        u32     vclipzmin;
+        u32     vclipzmax;
+        u32     dcsf;
+        u32     dcsb;
+        u32     dczf;
+        u32     dczb;
         
-        u32             xxx9;
-        volatile u32    blendc;
-        volatile u32    blendc1;
-        volatile u32    blendc2;
-        volatile u32    fbramitc;
-        volatile u32    fbc;
-        volatile u32    rop;
-        volatile u32    cmp;
-        volatile u32    matchab;
-        volatile u32    matchc;
-        volatile u32    magnab;
-        volatile u32    magnc;
-        volatile u32    fbcfg0;
-        volatile u32    fbcfg1;
-        volatile u32    fbcfg2;
-        volatile u32    fbcfg3;
+        u32     xxx9;
+        u32     blendc;
+        u32     blendc1;
+        u32     blendc2;
+        u32     fbramitc;
+        u32     fbc;
+        u32     rop;
+        u32     cmp;
+        u32     matchab;
+        u32     matchc;
+        u32     magnab;
+        u32     magnc;
+        u32     fbcfg0;
+        u32     fbcfg1;
+        u32     fbcfg2;
+        u32     fbcfg3;
         
-        u32             ppcfg;
-        volatile u32    pick;
-        volatile u32    fillmode;
-        volatile u32    fbramwac;
-        volatile u32    pmask;
-        volatile u32    xpmask;
-        volatile u32    ypmask;
-        volatile u32    zpmask;
-        volatile u32    clip0min;
-        volatile u32    clip0max;
-        volatile u32    clip1min;
-        volatile u32    clip1max;
-        volatile u32    clip2min;
-        volatile u32    clip2max;
-        volatile u32    clip3min;
-        volatile u32    clip3max;
+        u32     ppcfg;
+        u32     pick;
+        u32     fillmode;
+        u32     fbramwac;
+        u32     pmask;
+        u32     xpmask;
+        u32     ypmask;
+        u32     zpmask;
+        u32     clip0min;
+        u32     clip0max;
+        u32     clip1min;
+        u32     clip1max;
+        u32     clip2min;
+        u32     clip2max;
+        u32     clip3min;
+        u32     clip3max;
         
         /* New 3dRAM III support regs */
-        volatile u32    rawblend2;
-        volatile u32    rawpreblend;
-        volatile u32    rawstencil;
-        volatile u32    rawstencilctl;
-        volatile u32    threedram1;
-        volatile u32    threedram2;
-        volatile u32    passin;
-        volatile u32    rawclrdepth;
-        volatile u32    rawpmask;
-        volatile u32    rawcsrc;
-        volatile u32    rawmatch;
-        volatile u32    rawmagn;
-        volatile u32    rawropblend;
-        volatile u32    rawcmp;
-        volatile u32    rawwac;
-        volatile u32    fbramid;
+        u32     rawblend2;
+        u32     rawpreblend;
+        u32     rawstencil;
+        u32     rawstencilctl;
+        u32     threedram1;
+        u32     threedram2;
+        u32     passin;
+        u32     rawclrdepth;
+        u32     rawpmask;
+        u32     rawcsrc;
+        u32     rawmatch;
+        u32     rawmagn;
+        u32     rawropblend;
+        u32     rawcmp;
+        u32     rawwac;
+        u32     fbramid;
         
-        volatile u32    drawop;
-        u32             xxx10[2];
-        volatile u32    fontlpat;
-        u32             xxx11;
-        volatile u32    fontxy;
-        volatile u32    fontw;
-        volatile u32    fontinc;
-        volatile u32    font;
-        u32             xxx12[3];
-        volatile u32    blend2;
-        volatile u32    preblend;
-        volatile u32    stencil;
-        volatile u32    stencilctl;
-
-        u32             xxx13[4];       
-        volatile u32    dcss1;
-        volatile u32    dcss2;
-        volatile u32    dcss3;
-        volatile u32    widpmask;
-        volatile u32    dcs2;
-        volatile u32    dcs3;
-        volatile u32    dcs4;
-        u32             xxx14;
-        volatile u32    dcd2;
-        volatile u32    dcd3;
-        volatile u32    dcd4;
-        u32             xxx15;
+        u32     drawop;
+        u32     xxx10[2];
+        u32     fontlpat;
+        u32     xxx11;
+        u32     fontxy;
+        u32     fontw;
+        u32     fontinc;
+        u32     font;
+        u32     xxx12[3];
+        u32     blend2;
+        u32     preblend;
+        u32     stencil;
+        u32     stencilctl;
+
+        u32     xxx13[4];       
+        u32     dcss1;
+        u32     dcss2;
+        u32     dcss3;
+        u32     widpmask;
+        u32     dcs2;
+        u32     dcs3;
+        u32     dcs4;
+        u32     xxx14;
+        u32     dcd2;
+        u32     dcd3;
+        u32     dcd4;
+        u32     xxx15;
         
-        volatile u32    pattern[32];
+        u32     pattern[32];
         
-        u32             xxx16[256];
+        u32     xxx16[256];
         
-        volatile u32    devid;
-        u32             xxx17[63];
+        u32     devid;
+        u32     xxx17[63];
         
-        volatile u32    ucsr;
-        u32             xxx18[31];
+        u32     ucsr;
+        u32     xxx18[31];
         
-        volatile u32    mer;
+        u32     mer;
 };
 
 struct ffb_dac {
-        volatile u32    type;
-        volatile u32    value;
-        volatile u32    type2;
-        volatile u32    value2;
+        u32     type;
+        u32     value;
+        u32     type2;
+        u32     value2;
 };
 
 struct ffb_par {
         spinlock_t              lock;
-        struct ffb_fbc          *fbc;
-        struct ffb_dac          *dac;
+        struct ffb_fbc __iomem  *fbc;
+        struct ffb_dac __iomem  *dac;
 
         u32                     flags;
 #define FFB_FLAG_AFB            0x00000001
@@ -353,16 +354,13 @@ struct ffb_par {
         unsigned long           physbase;
         unsigned long           fbsize;
 
-        char                    name[64];
-        int                     prom_node;
-        int                     prom_parent_node;
         int                     dac_rev;
         int                     board_type;
 };
 
 static void FFBFifo(struct ffb_par *par, int n)
 {
-        struct ffb_fbc *fbc;
+        struct ffb_fbc __iomem *fbc;
         int cache = par->fifo_cache;
 
         if (cache - n < 0) {
@@ -375,7 +373,7 @@ static void FFBFifo(struct ffb_par *par, int n)
 
 static void FFBWait(struct ffb_par *par)
 {
-        struct ffb_fbc *fbc;
+        struct ffb_fbc __iomem *fbc;
         int limit = 10000;
 
         fbc = par->fbc;
@@ -408,8 +406,8 @@ static __inline__ void ffb_rop(struct ffb_par *par, u32 rop)
 
 static void ffb_switch_from_graph(struct ffb_par *par)
 {
-        struct ffb_fbc *fbc = par->fbc;
-        struct ffb_dac *dac = par->dac;
+        struct ffb_fbc __iomem *fbc = par->fbc;
+        struct ffb_dac __iomem *dac = par->dac;
         unsigned long flags;
 
         spin_lock_irqsave(&par->lock, flags);
@@ -462,7 +460,7 @@ static int ffb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
 static void ffb_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
 {
         struct ffb_par *par = (struct ffb_par *) info->par;
-        struct ffb_fbc *fbc = par->fbc;
+        struct ffb_fbc __iomem *fbc = par->fbc;
         unsigned long flags;
         u32 fg;
 
@@ -505,7 +503,7 @@ static void
 ffb_copyarea(struct fb_info *info, const struct fb_copyarea *area) 
 {
         struct ffb_par *par = (struct ffb_par *) info->par;
-        struct ffb_fbc *fbc = par->fbc;
+        struct ffb_fbc __iomem *fbc = par->fbc;
         unsigned long flags;
 
         if (area->dx != area->sx ||
@@ -541,7 +539,7 @@ ffb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
 static void ffb_imageblit(struct fb_info *info, const struct fb_image *image)
 {
         struct ffb_par *par = (struct ffb_par *) info->par;
-        struct ffb_fbc *fbc = par->fbc;
+        struct ffb_fbc __iomem *fbc = par->fbc;
         const u8 *data = image->data;
         unsigned long flags;
         u32 fg, bg, xy;
@@ -664,7 +662,7 @@ static int
 ffb_blank(int blank, struct fb_info *info)
 {
         struct ffb_par *par = (struct ffb_par *) info->par;
-        struct ffb_dac *dac = par->dac;
+        struct ffb_dac __iomem *dac = par->dac;
         unsigned long flags;
         u32 tmp;
 
@@ -883,78 +881,42 @@ ffb_init_fix(struct fb_info *info)
         info->fix.accel = FB_ACCEL_SUN_CREATOR;
 }
 
-static int ffb_apply_upa_parent_ranges(int parent,
-                                       struct linux_prom64_registers *regs)
-{
-        struct linux_prom64_ranges ranges[PROMREG_MAX];
-        char name[128];
-        int len, i;
-
-        prom_getproperty(parent, "name", name, sizeof(name));
-        if (strcmp(name, "upa") != 0)
-                return 0;
-
-        len = prom_getproperty(parent, "ranges", (void *) ranges, sizeof(ranges));
-        if (len <= 0)
-                return 1;
-
-        len /= sizeof(struct linux_prom64_ranges);
-        for (i = 0; i < len; i++) {
-                struct linux_prom64_ranges *rng = &ranges[i];
-                u64 phys_addr = regs->phys_addr;
-
-                if (phys_addr >= rng->ot_child_base &&
-                    phys_addr < (rng->ot_child_base + rng->or_size)) {
-                        regs->phys_addr -= rng->ot_child_base;
-                        regs->phys_addr += rng->ot_parent_base;
-                        return 0;
-                }
-        }
-
-        return 1;
-}
-
 struct all_info {
         struct fb_info info;
         struct ffb_par par;
         u32 pseudo_palette[256];
-        struct list_head list;
 };
-static LIST_HEAD(ffb_list);
 
-static void ffb_init_one(int node, int parent)
+static int ffb_init_one(struct of_device *op)
 {
-        struct linux_prom64_registers regs[2*PROMREG_MAX];
-        struct ffb_fbc *fbc;
-        struct ffb_dac *dac;
+        struct device_node *dp = op->node;
+        struct ffb_fbc __iomem *fbc;
+        struct ffb_dac __iomem *dac;
         struct all_info *all;
+        int err;
 
-        if (prom_getproperty(node, "reg", (void *) regs, sizeof(regs)) <= 0) {
-                printk("ffb: Cannot get reg device node property.\n");
-                return;
-        }
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
-        if (ffb_apply_upa_parent_ranges(parent, &regs[0])) {
-                printk("ffb: Cannot apply parent ranges to regs.\n");
-                return;
+        spin_lock_init(&all->par.lock);
+        all->par.fbc = of_ioremap(&op->resource[2], 0,
+                                  sizeof(struct ffb_fbc), "ffb fbc");
+        if (!all->par.fbc) {
+                kfree(all);
+                return -ENOMEM;
         }
 
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "ffb: Cannot allocate memory.\n");
-                return;
+        all->par.dac = of_ioremap(&op->resource[1], 0,
+                                  sizeof(struct ffb_dac), "ffb dac");
+        if (!all->par.dac) {
+                of_iounmap(all->par.fbc, sizeof(struct ffb_fbc));
+                kfree(all);
+                return -ENOMEM;
         }
-        memset(all, 0, sizeof(*all));
-
-        INIT_LIST_HEAD(&all->list);     
 
-        spin_lock_init(&all->par.lock);
-        all->par.fbc = (struct ffb_fbc *)(regs[0].phys_addr + FFB_FBC_REGS_POFF);
-        all->par.dac = (struct ffb_dac *)(regs[0].phys_addr + FFB_DAC_POFF);
         all->par.rop_cache = FFB_ROP_NEW;
-        all->par.physbase = regs[0].phys_addr;
-        all->par.prom_node = node;
-        all->par.prom_parent_node = parent;
+        all->par.physbase = op->resource[0].start;
 
         /* Don't mention copyarea, so SCROLL_REDRAW is always
          * used.  It is the fastest on this chip.
@@ -968,7 +930,7 @@ static void ffb_init_one(int node, int parent)
         all->info.par = &all->par;
         all->info.pseudo_palette = all->pseudo_palette;
 
-        sbusfb_fill_var(&all->info.var, all->par.prom_node, 32);
+        sbusfb_fill_var(&all->info.var, dp->node, 32);
         all->par.fbsize = PAGE_ALIGN(all->info.var.xres *
                                      all->info.var.yres *
                                      4);
@@ -976,14 +938,13 @@ static void ffb_init_one(int node, int parent)
 
         all->info.var.accel_flags = FB_ACCELF_TEXT;
 
-        prom_getstring(node, "name", all->par.name, sizeof(all->par.name));
-        if (!strcmp(all->par.name, "SUNW,afb"))
+        if (!strcmp(dp->name, "SUNW,afb"))
                 all->par.flags |= FFB_FLAG_AFB;
 
-        all->par.board_type = prom_getintdefault(node, "board_type", 0);
+        all->par.board_type = of_getintprop_default(dp, "board_type", 0);
 
         fbc = all->par.fbc;
-        if((upa_readl(&fbc->ucsr) & FFB_UCSR_ALL_ERRORS) != 0)
+        if ((upa_readl(&fbc->ucsr) & FFB_UCSR_ALL_ERRORS) != 0)
                 upa_writel(FFB_UCSR_ALL_ERRORS, &fbc->ucsr);
 
         ffb_switch_from_graph(&all->par);
@@ -1008,81 +969,88 @@ static void ffb_init_one(int node, int parent)
         if (fb_alloc_cmap(&all->info.cmap, 256, 0)) {
                 printk(KERN_ERR "ffb: Could not allocate color map.\n");
                 kfree(all);
-                return;
+                return -ENOMEM;
         }
 
         ffb_init_fix(&all->info);
 
-        if (register_framebuffer(&all->info) < 0) {
+        err = register_framebuffer(&all->info);
+        if (err < 0) {
                 printk(KERN_ERR "ffb: Could not register framebuffer.\n");
                 fb_dealloc_cmap(&all->info.cmap);
                 kfree(all);
-                return;
+                return err;
         }
 
-        list_add(&all->list, &ffb_list);
+        dev_set_drvdata(&op->dev, all);
 
-        printk("ffb: %s at %016lx type %d DAC %d\n",
+        printk("%s: %s at %016lx, type %d, DAC revision %d\n",
+               dp->full_name,
                ((all->par.flags & FFB_FLAG_AFB) ? "AFB" : "FFB"),
-               regs[0].phys_addr, all->par.board_type, all->par.dac_rev);
+               all->par.physbase, all->par.board_type, all->par.dac_rev);
+
+        return 0;
 }
 
-static void ffb_scan_siblings(int root)
+static int __devinit ffb_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        int node, child;
-
-        child = prom_getchild(root);
-        for (node = prom_searchsiblings(child, "SUNW,ffb"); node;
-             node = prom_searchsiblings(prom_getsibling(node), "SUNW,ffb"))
-                ffb_init_one(node, root);
-        for (node = prom_searchsiblings(child, "SUNW,afb"); node;
-             node = prom_searchsiblings(prom_getsibling(node), "SUNW,afb"))
-                ffb_init_one(node, root);
+        struct of_device *op = to_of_device(&dev->dev);
+
+        return ffb_init_one(op);
 }
 
-int __init ffb_init(void)
+static int __devexit ffb_remove(struct of_device *dev)
 {
-        int root;
+        struct all_info *all = dev_get_drvdata(&dev->dev);
 
-        if (fb_get_options("ffb", NULL))
-                return -ENODEV;
+        unregister_framebuffer(&all->info);
+        fb_dealloc_cmap(&all->info.cmap);
 
-        ffb_scan_siblings(prom_root_node);
+        of_iounmap(all->par.fbc, sizeof(struct ffb_fbc));
+        of_iounmap(all->par.dac, sizeof(struct ffb_dac));
 
-        root = prom_getchild(prom_root_node);
-        for (root = prom_searchsiblings(root, "upa"); root;
-             root = prom_searchsiblings(prom_getsibling(root), "upa"))
-                ffb_scan_siblings(root);
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit ffb_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id ffb_match[] = {
+        {
+                .name = "SUNW,ffb",
+        },
+        {
+                .name = "SUNW,afb",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, ffb_match);
+
+static struct of_platform_driver ffb_driver = {
+        .name           = "ffb",
+        .match_table    = ffb_match,
+        .probe          = ffb_probe,
+        .remove         = __devexit_p(ffb_remove),
+};
 
-        list_for_each_safe(pos, tmp, &ffb_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+int __init ffb_init(void)
+{
+        if (fb_get_options("ffb", NULL))
+                return -ENODEV;
 
-                unregister_framebuffer(&all->info);
-                fb_dealloc_cmap(&all->info.cmap);
-                kfree(all);
-        }
+        return of_register_driver(&ffb_driver, &of_bus_type);
 }
 
-int __init
-ffb_setup(char *arg)
+void __exit ffb_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        of_unregister_driver(&ffb_driver);
 }
 
 module_init(ffb_init);
-
-#ifdef MODULE
 module_exit(ffb_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for Creator/Elite3D chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/imacfb.c b/drivers/video/imacfb.c
index 7b1c168c834d..cdbae173d69a 100644
--- a/drivers/video/imacfb.c
+++ b/drivers/video/imacfb.c
@@ -207,10 +207,6 @@ static int __init imacfb_probe(struct platform_device *dev)
                 size_remap = size_total;
         imacfb_fix.smem_len = size_remap;
 
-#ifndef __i386__
-        screen_info.imacpm_seg = 0;
-#endif
-
         if (!request_mem_region(imacfb_fix.smem_start, size_total, "imacfb")) {
                 printk(KERN_WARNING
                        "imacfb: cannot reserve video memory at 0x%lx\n",
diff --git a/drivers/video/leo.c b/drivers/video/leo.c
index a23cfdb9d826..f3a24338d9ac 100644
--- a/drivers/video/leo.c
+++ b/drivers/video/leo.c
@@ -1,6 +1,6 @@
 /* leo.c: LEO frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1996-1999 Jakub Jelinek (jj@ultra.linux.cz)
  * Copyright (C) 1997 Michal Rehacek (Michal.Rehacek@st.mff.cuni.cz)
  *
@@ -18,8 +18,8 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/sbus.h>
-#include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
 #include "sbuslib.h"
@@ -80,10 +80,10 @@ static struct fb_ops leo_ops = {
 
 struct leo_cursor {
         u8              xxx0[16];
-        volatile u32    cur_type;
-        volatile u32    cur_misc;
-        volatile u32    cur_cursxy;
-        volatile u32    cur_data;
+        u32     cur_type;
+        u32     cur_misc;
+        u32     cur_cursxy;
+        u32     cur_data;
 };
 
 #define LEO_KRN_TYPE_CLUT0      0x00001000
@@ -99,27 +99,27 @@ struct leo_cursor {
 #define LEO_KRN_CSR_UNK2        0x00000001
 
 struct leo_lx_krn {
-        volatile u32    krn_type;
-        volatile u32    krn_csr;
-        volatile u32    krn_value;
+        u32     krn_type;
+        u32     krn_csr;
+        u32     krn_value;
 };
 
 struct leo_lc_ss0_krn {
-        volatile u32    misc;
+        u32     misc;
         u8              xxx0[0x800-4];
-        volatile u32    rev;
+        u32     rev;
 };
 
 struct leo_lc_ss0_usr {
-        volatile u32    csr;
-        volatile u32    addrspace;
-        volatile u32    fontmsk;
-        volatile u32    fontt;
-        volatile u32    extent;
-        volatile u32    src;
+        u32     csr;
+        u32     addrspace;
+        u32     fontmsk;
+        u32     fontt;
+        u32     extent;
+        u32     src;
         u32             dst;
-        volatile u32    copy;
-        volatile u32    fill;
+        u32     copy;
+        u32     fill;
 };
 
 struct leo_lc_ss1_krn {
@@ -132,47 +132,47 @@ struct leo_lc_ss1_usr {
 
 struct leo_ld {
         u8              xxx0[0xe00];
-        volatile u32    csr;
-        volatile u32    wid;
-        volatile u32    wmask;
-        volatile u32    widclip;
-        volatile u32    vclipmin;
-        volatile u32    vclipmax;
-        volatile u32    pickmin;        /* SS1 only */
-        volatile u32    pickmax;        /* SS1 only */
-        volatile u32    fg;
-        volatile u32    bg;
-        volatile u32    src;            /* Copy/Scroll (SS0 only) */
-        volatile u32    dst;            /* Copy/Scroll/Fill (SS0 only) */
-        volatile u32    extent;         /* Copy/Scroll/Fill size (SS0 only) */
+        u32     csr;
+        u32     wid;
+        u32     wmask;
+        u32     widclip;
+        u32     vclipmin;
+        u32     vclipmax;
+        u32     pickmin;        /* SS1 only */
+        u32     pickmax;        /* SS1 only */
+        u32     fg;
+        u32     bg;
+        u32     src;            /* Copy/Scroll (SS0 only) */
+        u32     dst;            /* Copy/Scroll/Fill (SS0 only) */
+        u32     extent;         /* Copy/Scroll/Fill size (SS0 only) */
         u32             xxx1[3];
-        volatile u32    setsem;         /* SS1 only */
-        volatile u32    clrsem;         /* SS1 only */
-        volatile u32    clrpick;        /* SS1 only */
-        volatile u32    clrdat;         /* SS1 only */
-        volatile u32    alpha;          /* SS1 only */
+        u32     setsem;         /* SS1 only */
+        u32     clrsem;         /* SS1 only */
+        u32     clrpick;        /* SS1 only */
+        u32     clrdat;         /* SS1 only */
+        u32     alpha;          /* SS1 only */
         u8              xxx2[0x2c];
-        volatile u32    winbg;
-        volatile u32    planemask;
-        volatile u32    rop;
-        volatile u32    z;
-        volatile u32    dczf;           /* SS1 only */
-        volatile u32    dczb;           /* SS1 only */
-        volatile u32    dcs;            /* SS1 only */
-        volatile u32    dczs;           /* SS1 only */
-        volatile u32    pickfb;         /* SS1 only */
-        volatile u32    pickbb;         /* SS1 only */
-        volatile u32    dcfc;           /* SS1 only */
-        volatile u32    forcecol;       /* SS1 only */
-        volatile u32    door[8];        /* SS1 only */
-        volatile u32    pick[5];        /* SS1 only */
+        u32     winbg;
+        u32     planemask;
+        u32     rop;
+        u32     z;
+        u32     dczf;           /* SS1 only */
+        u32     dczb;           /* SS1 only */
+        u32     dcs;            /* SS1 only */
+        u32     dczs;           /* SS1 only */
+        u32     pickfb;         /* SS1 only */
+        u32     pickbb;         /* SS1 only */
+        u32     dcfc;           /* SS1 only */
+        u32     forcecol;       /* SS1 only */
+        u32     door[8];        /* SS1 only */
+        u32     pick[5];        /* SS1 only */
 };
 
 #define LEO_SS1_MISC_ENABLE     0x00000001
 #define LEO_SS1_MISC_STEREO     0x00000002
 struct leo_ld_ss1 {
-        u8              xxx0[0xef4];
-        volatile u32    ss1_misc;
+        u8      xxx0[0xef4];
+        u32     ss1_misc;
 };
 
 struct leo_ld_gbl {
@@ -193,9 +193,8 @@ struct leo_par {
 #define LEO_FLAG_BLANKED        0x00000001
 
         unsigned long           physbase;
+        unsigned long           which_io;
         unsigned long           fbsize;
-
-        struct sbus_dev         *sdev;
 };
 
 static void leo_wait(struct leo_lx_krn __iomem *lx_krn)
@@ -368,8 +367,7 @@ static int leo_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
         return sbusfb_mmap_helper(leo_mmap_map,
                                   par->physbase, par->fbsize,
-                                  par->sdev->reg_addrs[0].which_io,
-                                  vma);
+                                  par->which_io, vma);
 }
 
 static int leo_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
@@ -385,11 +383,9 @@ static int leo_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
  */
 
 static void
-leo_init_fix(struct fb_info *info)
+leo_init_fix(struct fb_info *info, struct device_node *dp)
 {
-        struct leo_par *par = (struct leo_par *)info->par;
-
-        strlcpy(info->fix.id, par->sdev->prom_name, sizeof(info->fix.id));
+        strlcpy(info->fix.id, dp->name, sizeof(info->fix.id));
 
         info->fix.type = FB_TYPE_PACKED_PIXELS;
         info->fix.visual = FB_VISUAL_TRUECOLOR;
@@ -532,60 +528,74 @@ static void leo_fixup_var_rgb(struct fb_var_screeninfo *var)
 struct all_info {
         struct fb_info info;
         struct leo_par par;
-        struct list_head list;
 };
-static LIST_HEAD(leo_list);
 
-static void leo_init_one(struct sbus_dev *sdev)
+static void leo_unmap_regs(struct all_info *all)
 {
-        struct all_info *all;
-        int linebytes;
+        if (all->par.lc_ss0_usr)
+                of_iounmap(all->par.lc_ss0_usr, 0x1000);
+        if (all->par.ld_ss0)
+                of_iounmap(all->par.ld_ss0, 0x1000);
+        if (all->par.ld_ss1)
+                of_iounmap(all->par.ld_ss1, 0x1000);
+        if (all->par.lx_krn)
+                of_iounmap(all->par.lx_krn, 0x1000);
+        if (all->par.cursor)
+                of_iounmap(all->par.cursor, sizeof(struct leo_cursor));
+        if (all->info.screen_base)
+                of_iounmap(all->info.screen_base, 0x800000);
+}
 
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "leo: Cannot allocate memory.\n");
-                return;
-        }
-        memset(all, 0, sizeof(*all));
+static int __devinit leo_init_one(struct of_device *op)
+{
+        struct device_node *dp = op->node;
+        struct all_info *all;
+        int linebytes, err;
 
-        INIT_LIST_HEAD(&all->list);
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
         spin_lock_init(&all->par.lock);
-        all->par.sdev = sdev;
 
-        all->par.physbase = sdev->reg_addrs[0].phys_addr;
+        all->par.physbase = op->resource[0].start;
+        all->par.which_io = op->resource[0].flags & IORESOURCE_BITS;
 
-        sbusfb_fill_var(&all->info.var, sdev->prom_node, 32);
+        sbusfb_fill_var(&all->info.var, dp->node, 32);
         leo_fixup_var_rgb(&all->info.var);
 
-        linebytes = prom_getintdefault(sdev->prom_node, "linebytes",
-                                       all->info.var.xres);
+        linebytes = of_getintprop_default(dp, "linebytes",
+                                          all->info.var.xres);
         all->par.fbsize = PAGE_ALIGN(linebytes * all->info.var.yres);
 
-#ifdef CONFIG_SPARC32
-        all->info.screen_base = (char __iomem *)
-                prom_getintdefault(sdev->prom_node, "address", 0);
-#endif
-        if (!all->info.screen_base)
-                all->info.screen_base = 
-                        sbus_ioremap(&sdev->resource[0], LEO_OFF_SS0,
-                                     0x800000, "leo ram");
-
         all->par.lc_ss0_usr =
-                sbus_ioremap(&sdev->resource[0], LEO_OFF_LC_SS0_USR,
-                             0x1000, "leolc ss0usr");
+                of_ioremap(&op->resource[0], LEO_OFF_LC_SS0_USR,
+                           0x1000, "leolc ss0usr");
         all->par.ld_ss0 =
-                sbus_ioremap(&sdev->resource[0], LEO_OFF_LD_SS0,
-                             0x1000, "leold ss0");
+                of_ioremap(&op->resource[0], LEO_OFF_LD_SS0,
+                           0x1000, "leold ss0");
         all->par.ld_ss1 =
-                sbus_ioremap(&sdev->resource[0], LEO_OFF_LD_SS1,
-                             0x1000, "leold ss1");
+                of_ioremap(&op->resource[0], LEO_OFF_LD_SS1,
+                           0x1000, "leold ss1");
         all->par.lx_krn =
-                sbus_ioremap(&sdev->resource[0], LEO_OFF_LX_KRN,
-                             0x1000, "leolx krn");
+                of_ioremap(&op->resource[0], LEO_OFF_LX_KRN,
+                           0x1000, "leolx krn");
         all->par.cursor =
-                sbus_ioremap(&sdev->resource[0], LEO_OFF_LX_CURSOR,
-                             sizeof(struct leo_cursor), "leolx cursor");
+                of_ioremap(&op->resource[0], LEO_OFF_LX_CURSOR,
+                           sizeof(struct leo_cursor), "leolx cursor");
+        all->info.screen_base = 
+                of_ioremap(&op->resource[0], LEO_OFF_SS0,
+                           0x800000, "leo ram");
+        if (!all->par.lc_ss0_usr ||
+            !all->par.ld_ss0 ||
+            !all->par.ld_ss1 ||
+            !all->par.lx_krn ||
+            !all->par.cursor ||
+            !all->info.screen_base) {
+                leo_unmap_regs(all);
+                kfree(all);
+                return -ENOMEM;
+        }
 
         all->info.flags = FBINFO_DEFAULT | FBINFO_HWACCEL_YPAN;
         all->info.fbops = &leo_ops;
@@ -597,69 +607,85 @@ static void leo_init_one(struct sbus_dev *sdev)
         leo_blank(0, &all->info);
 
         if (fb_alloc_cmap(&all->info.cmap, 256, 0)) {
-                printk(KERN_ERR "leo: Could not allocate color map.\n");
+                leo_unmap_regs(all);
                 kfree(all);
-                return;
+                return -ENOMEM;;
         }
 
-        leo_init_fix(&all->info);
+        leo_init_fix(&all->info, dp);
 
-        if (register_framebuffer(&all->info) < 0) {
-                printk(KERN_ERR "leo: Could not register framebuffer.\n");
+        err = register_framebuffer(&all->info);
+        if (err < 0) {
                 fb_dealloc_cmap(&all->info.cmap);
+                leo_unmap_regs(all);
                 kfree(all);
-                return;
+                return err;
         }
 
-        list_add(&all->list, &leo_list);
+        dev_set_drvdata(&op->dev, all);
+
+        printk("%s: leo at %lx:%lx\n",
+               dp->full_name,
+               all->par.which_io, all->par.physbase);
 
-        printk("leo: %s at %lx:%lx\n",
-               sdev->prom_name,
-               (long) sdev->reg_addrs[0].which_io,
-               (long) sdev->reg_addrs[0].phys_addr);
+        return 0;
 }
 
-int __init leo_init(void)
+static int __devinit leo_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_bus *sbus;
-        struct sbus_dev *sdev;
+        struct of_device *op = to_of_device(&dev->dev);
 
-        if (fb_get_options("leofb", NULL))
-                return -ENODEV;
+        return leo_init_one(op);
+}
 
-        for_all_sbusdev(sdev, sbus) {
-                if (!strcmp(sdev->prom_name, "leo"))
-                        leo_init_one(sdev);
-        }
+static int __devexit leo_remove(struct of_device *dev)
+{
+        struct all_info *all = dev_get_drvdata(&dev->dev);
+
+        unregister_framebuffer(&all->info);
+        fb_dealloc_cmap(&all->info.cmap);
+
+        leo_unmap_regs(all);
+
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit leo_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id leo_match[] = {
+        {
+                .name = "leo",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, leo_match);
+
+static struct of_platform_driver leo_driver = {
+        .name           = "leo",
+        .match_table    = leo_match,
+        .probe          = leo_probe,
+        .remove         = __devexit_p(leo_remove),
+};
 
-        list_for_each_safe(pos, tmp, &leo_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+static int __init leo_init(void)
+{
+        if (fb_get_options("leofb", NULL))
+                return -ENODEV;
 
-                unregister_framebuffer(&all->info);
-                fb_dealloc_cmap(&all->info.cmap);
-                kfree(all);
-        }
+        return of_register_driver(&leo_driver, &of_bus_type);
 }
 
-int __init
-leo_setup(char *arg)
+static void __exit leo_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        of_unregister_driver(&leo_driver);
 }
 
 module_init(leo_init);
-#ifdef MODULE
 module_exit(leo_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for LEO chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/p9100.c b/drivers/video/p9100.c
index 0d1957505359..56ac51d6a7f3 100644
--- a/drivers/video/p9100.c
+++ b/drivers/video/p9100.c
@@ -1,6 +1,6 @@
 /* p9100.c: P9100 frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright 1999 Derrick J Brashear (shadow@dementia.org)
  *
  * Driver layout based loosely on tgafb.c, see that file for credits.
@@ -17,8 +17,8 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/sbus.h>
-#include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
 #include "sbuslib.h"
@@ -72,60 +72,60 @@ static struct fb_ops p9100_ops = {
 
 struct p9100_regs {
         /* Registers for the system control */
-        volatile u32 sys_base;
-        volatile u32 sys_config;
-        volatile u32 sys_intr;
-        volatile u32 sys_int_ena;
-        volatile u32 sys_alt_rd;
-        volatile u32 sys_alt_wr;
-        volatile u32 sys_xxx[58];
+        u32 sys_base;
+        u32 sys_config;
+        u32 sys_intr;
+        u32 sys_int_ena;
+        u32 sys_alt_rd;
+        u32 sys_alt_wr;
+        u32 sys_xxx[58];
 
         /* Registers for the video control */
-        volatile u32 vid_base;
-        volatile u32 vid_hcnt;
-        volatile u32 vid_htotal;
-        volatile u32 vid_hsync_rise;
-        volatile u32 vid_hblank_rise;
-        volatile u32 vid_hblank_fall;
-        volatile u32 vid_hcnt_preload;
-        volatile u32 vid_vcnt;
-        volatile u32 vid_vlen;
-        volatile u32 vid_vsync_rise;
-        volatile u32 vid_vblank_rise;
-        volatile u32 vid_vblank_fall;
-        volatile u32 vid_vcnt_preload;
-        volatile u32 vid_screenpaint_addr;
-        volatile u32 vid_screenpaint_timectl1;
-        volatile u32 vid_screenpaint_qsfcnt;
-        volatile u32 vid_screenpaint_timectl2;
-        volatile u32 vid_xxx[15];
+        u32 vid_base;
+        u32 vid_hcnt;
+        u32 vid_htotal;
+        u32 vid_hsync_rise;
+        u32 vid_hblank_rise;
+        u32 vid_hblank_fall;
+        u32 vid_hcnt_preload;
+        u32 vid_vcnt;
+        u32 vid_vlen;
+        u32 vid_vsync_rise;
+        u32 vid_vblank_rise;
+        u32 vid_vblank_fall;
+        u32 vid_vcnt_preload;
+        u32 vid_screenpaint_addr;
+        u32 vid_screenpaint_timectl1;
+        u32 vid_screenpaint_qsfcnt;
+        u32 vid_screenpaint_timectl2;
+        u32 vid_xxx[15];
 
         /* Registers for the video control */
-        volatile u32 vram_base;
-        volatile u32 vram_memcfg;
-        volatile u32 vram_refresh_pd;
-        volatile u32 vram_refresh_cnt;
-        volatile u32 vram_raslo_max;
-        volatile u32 vram_raslo_cur;
-        volatile u32 pwrup_cfg;
-        volatile u32 vram_xxx[25];
+        u32 vram_base;
+        u32 vram_memcfg;
+        u32 vram_refresh_pd;
+        u32 vram_refresh_cnt;
+        u32 vram_raslo_max;
+        u32 vram_raslo_cur;
+        u32 pwrup_cfg;
+        u32 vram_xxx[25];
 
         /* Registers for IBM RGB528 Palette */
-        volatile u32 ramdac_cmap_wridx; 
-        volatile u32 ramdac_palette_data;
-        volatile u32 ramdac_pixel_mask;
-        volatile u32 ramdac_palette_rdaddr;
-        volatile u32 ramdac_idx_lo;
-        volatile u32 ramdac_idx_hi;
-        volatile u32 ramdac_idx_data;
-        volatile u32 ramdac_idx_ctl;
-        volatile u32 ramdac_xxx[1784];
+        u32 ramdac_cmap_wridx; 
+        u32 ramdac_palette_data;
+        u32 ramdac_pixel_mask;
+        u32 ramdac_palette_rdaddr;
+        u32 ramdac_idx_lo;
+        u32 ramdac_idx_hi;
+        u32 ramdac_idx_data;
+        u32 ramdac_idx_ctl;
+        u32 ramdac_xxx[1784];
 };
 
 struct p9100_cmd_parameng {
-        volatile u32 parameng_status;
-        volatile u32 parameng_bltcmd;
-        volatile u32 parameng_quadcmd;
+        u32 parameng_status;
+        u32 parameng_bltcmd;
+        u32 parameng_quadcmd;
 };
 
 struct p9100_par {
@@ -136,9 +136,8 @@ struct p9100_par {
 #define P9100_FLAG_BLANKED      0x00000001
 
         unsigned long           physbase;
+        unsigned long           which_io;
         unsigned long           fbsize;
-
-        struct sbus_dev         *sdev;
 };
 
 /**
@@ -227,8 +226,7 @@ static int p9100_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
         return sbusfb_mmap_helper(p9100_mmap_map,
                                   par->physbase, par->fbsize,
-                                  par->sdev->reg_addrs[0].which_io,
-                                  vma);
+                                  par->which_io, vma);
 }
 
 static int p9100_ioctl(struct fb_info *info, unsigned int cmd,
@@ -245,12 +243,9 @@ static int p9100_ioctl(struct fb_info *info, unsigned int cmd,
  *  Initialisation
  */
 
-static void
-p9100_init_fix(struct fb_info *info, int linebytes)
+static void p9100_init_fix(struct fb_info *info, int linebytes, struct device_node *dp)
 {
-        struct p9100_par *par = (struct p9100_par *)info->par;
-
-        strlcpy(info->fix.id, par->sdev->prom_name, sizeof(info->fix.id));
+        strlcpy(info->fix.id, dp->name, sizeof(info->fix.id));
 
         info->fix.type = FB_TYPE_PACKED_PIXELS;
         info->fix.visual = FB_VISUAL_PSEUDOCOLOR;
@@ -263,121 +258,137 @@ p9100_init_fix(struct fb_info *info, int linebytes)
 struct all_info {
         struct fb_info info;
         struct p9100_par par;
-        struct list_head list;
 };
-static LIST_HEAD(p9100_list);
 
-static void p9100_init_one(struct sbus_dev *sdev)
+static int __devinit p9100_init_one(struct of_device *op)
 {
+        struct device_node *dp = op->node;
         struct all_info *all;
-        int linebytes;
-
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "p9100: Cannot allocate memory.\n");
-                return;
-        }
-        memset(all, 0, sizeof(*all));
+        int linebytes, err;
 
-        INIT_LIST_HEAD(&all->list);
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
         spin_lock_init(&all->par.lock);
-        all->par.sdev = sdev;
 
         /* This is the framebuffer and the only resource apps can mmap.  */
-        all->par.physbase = sdev->reg_addrs[2].phys_addr;
+        all->par.physbase = op->resource[2].start;
+        all->par.which_io = op->resource[2].flags & IORESOURCE_BITS;
 
-        sbusfb_fill_var(&all->info.var, sdev->prom_node, 8);
+        sbusfb_fill_var(&all->info.var, dp->node, 8);
         all->info.var.red.length = 8;
         all->info.var.green.length = 8;
         all->info.var.blue.length = 8;
 
-        linebytes = prom_getintdefault(sdev->prom_node, "linebytes",
-                                       all->info.var.xres);
+        linebytes = of_getintprop_default(dp, "linebytes",
+                                          all->info.var.xres);
         all->par.fbsize = PAGE_ALIGN(linebytes * all->info.var.yres);
 
-        all->par.regs = sbus_ioremap(&sdev->resource[0], 0,
-                             sizeof(struct p9100_regs), "p9100 regs");
+        all->par.regs = of_ioremap(&op->resource[0], 0,
+                                   sizeof(struct p9100_regs), "p9100 regs");
+        if (!all->par.regs) {
+                kfree(all);
+                return -ENOMEM;
+        }
 
         all->info.flags = FBINFO_DEFAULT;
         all->info.fbops = &p9100_ops;
-#ifdef CONFIG_SPARC32
-        all->info.screen_base = (char __iomem *)
-                prom_getintdefault(sdev->prom_node, "address", 0);
-#endif
-        if (!all->info.screen_base)
-                all->info.screen_base = sbus_ioremap(&sdev->resource[2], 0,
-                                     all->par.fbsize, "p9100 ram");
+        all->info.screen_base = of_ioremap(&op->resource[2], 0,
+                                           all->par.fbsize, "p9100 ram");
+        if (!all->info.screen_base) {
+                of_iounmap(all->par.regs, sizeof(struct p9100_regs));
+                kfree(all);
+                return -ENOMEM;
+        }
         all->info.par = &all->par;
 
         p9100_blank(0, &all->info);
 
         if (fb_alloc_cmap(&all->info.cmap, 256, 0)) {
-                printk(KERN_ERR "p9100: Could not allocate color map.\n");
+                of_iounmap(all->par.regs, sizeof(struct p9100_regs));
+                of_iounmap(all->info.screen_base, all->par.fbsize);
                 kfree(all);
-                return;
+                return -ENOMEM;
         }
 
-        p9100_init_fix(&all->info, linebytes);
+        p9100_init_fix(&all->info, linebytes, dp);
 
-        if (register_framebuffer(&all->info) < 0) {
-                printk(KERN_ERR "p9100: Could not register framebuffer.\n");
+        err = register_framebuffer(&all->info);
+        if (err < 0) {
                 fb_dealloc_cmap(&all->info.cmap);
+                of_iounmap(all->par.regs, sizeof(struct p9100_regs));
+                of_iounmap(all->info.screen_base, all->par.fbsize);
                 kfree(all);
-                return;
+                return err;
         }
         fb_set_cmap(&all->info.cmap, &all->info);
 
-        list_add(&all->list, &p9100_list);
+        dev_set_drvdata(&op->dev, all);
+
+        printk("%s: p9100 at %lx:%lx\n",
+               dp->full_name,
+               all->par.which_io, all->par.physbase);
 
-        printk("p9100: %s at %lx:%lx\n",
-               sdev->prom_name,
-               (long) sdev->reg_addrs[0].which_io,
-               (long) sdev->reg_addrs[0].phys_addr);
+        return 0;
 }
 
-int __init p9100_init(void)
+static int __devinit p9100_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_bus *sbus;
-        struct sbus_dev *sdev;
+        struct of_device *op = to_of_device(&dev->dev);
 
-        if (fb_get_options("p9100fb", NULL))
-                return -ENODEV;
+        return p9100_init_one(op);
+}
 
-        for_all_sbusdev(sdev, sbus) {
-                if (!strcmp(sdev->prom_name, "p9100"))
-                        p9100_init_one(sdev);
-        }
+static int __devexit p9100_remove(struct of_device *dev)
+{
+        struct all_info *all = dev_get_drvdata(&dev->dev);
+
+        unregister_framebuffer(&all->info);
+        fb_dealloc_cmap(&all->info.cmap);
+
+        of_iounmap(all->par.regs, sizeof(struct p9100_regs));
+        of_iounmap(all->info.screen_base, all->par.fbsize);
+
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit p9100_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id p9100_match[] = {
+        {
+                .name = "p9100",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, p9100_match);
 
-        list_for_each_safe(pos, tmp, &p9100_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+static struct of_platform_driver p9100_driver = {
+        .name           = "p9100",
+        .match_table    = p9100_match,
+        .probe          = p9100_probe,
+        .remove         = __devexit_p(p9100_remove),
+};
 
-                unregister_framebuffer(&all->info);
-                fb_dealloc_cmap(&all->info.cmap);
-                kfree(all);
-        }
+static int __init p9100_init(void)
+{
+        if (fb_get_options("p9100fb", NULL))
+                return -ENODEV;
+
+        return of_register_driver(&p9100_driver, &of_bus_type);
 }
 
-int __init
-p9100_setup(char *arg)
+static void __exit p9100_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        of_unregister_driver(&p9100_driver);
 }
 
 module_init(p9100_init);
-
-#ifdef MODULE
 module_exit(p9100_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for P9100 chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/tcx.c b/drivers/video/tcx.c
index 95b918229d9b..6990ab11cd06 100644
--- a/drivers/video/tcx.c
+++ b/drivers/video/tcx.c
@@ -1,6 +1,6 @@
 /* tcx.c: TCX frame buffer driver
  *
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2003, 2006 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1996,1998 Jakub Jelinek (jj@ultra.linux.cz)
  * Copyright (C) 1996 Miguel de Icaza (miguel@nuclecu.unam.mx)
  * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
@@ -19,8 +19,8 @@
 #include <linux/mm.h>
 
 #include <asm/io.h>
-#include <asm/sbus.h>
-#include <asm/oplib.h>
+#include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/fbio.h>
 
 #include "sbuslib.h"
@@ -77,32 +77,32 @@ static struct fb_ops tcx_ops = {
 
 /* The contents are unknown */
 struct tcx_tec {
-        volatile u32 tec_matrix;
-        volatile u32 tec_clip;
-        volatile u32 tec_vdc;
+        u32 tec_matrix;
+        u32 tec_clip;
+        u32 tec_vdc;
 };
 
 struct tcx_thc {
-        volatile u32 thc_rev;
+        u32 thc_rev;
         u32 thc_pad0[511];
-        volatile u32 thc_hs;            /* hsync timing */
-        volatile u32 thc_hsdvs;
-        volatile u32 thc_hd;
-        volatile u32 thc_vs;            /* vsync timing */
-        volatile u32 thc_vd;
-        volatile u32 thc_refresh;
-        volatile u32 thc_misc;
+        u32 thc_hs;             /* hsync timing */
+        u32 thc_hsdvs;
+        u32 thc_hd;
+        u32 thc_vs;             /* vsync timing */
+        u32 thc_vd;
+        u32 thc_refresh;
+        u32 thc_misc;
         u32 thc_pad1[56];
-        volatile u32 thc_cursxy;        /* cursor x,y position (16 bits each) */
-        volatile u32 thc_cursmask[32];  /* cursor mask bits */
-        volatile u32 thc_cursbits[32];  /* what to show where mask enabled */
+        u32 thc_cursxy; /* cursor x,y position (16 bits each) */
+        u32 thc_cursmask[32];   /* cursor mask bits */
+        u32 thc_cursbits[32];   /* what to show where mask enabled */
 };
 
 struct bt_regs {
-        volatile u32 addr;
-        volatile u32 color_map;
-        volatile u32 control;
-        volatile u32 cursor;
+        u32 addr;
+        u32 color_map;
+        u32 control;
+        u32 cursor;
 };
 
 #define TCX_MMAP_ENTRIES 14
@@ -112,24 +112,23 @@ struct tcx_par {
         struct bt_regs          __iomem *bt;
         struct tcx_thc          __iomem *thc;
         struct tcx_tec          __iomem *tec;
-        volatile u32            __iomem *cplane;
+        u32                     __iomem *cplane;
 
         u32                     flags;
 #define TCX_FLAG_BLANKED        0x00000001
 
         unsigned long           physbase;
+        unsigned long           which_io;
         unsigned long           fbsize;
 
         struct sbus_mmap_map    mmap_map[TCX_MMAP_ENTRIES];
         int                     lowdepth;
-
-        struct sbus_dev         *sdev;
 };
 
 /* Reset control plane so that WID is 8-bit plane. */
 static void __tcx_set_control_plane (struct tcx_par *par)
 {
-        volatile u32 __iomem *p, *pend;
+        u32 __iomem *p, *pend;
         
         if (par->lowdepth)
                 return;
@@ -307,8 +306,7 @@ static int tcx_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
         return sbusfb_mmap_helper(par->mmap_map,
                                   par->physbase, par->fbsize,
-                                  par->sdev->reg_addrs[0].which_io,
-                                  vma);
+                                  par->which_io, vma);
 }
 
 static int tcx_ioctl(struct fb_info *info, unsigned int cmd,
@@ -350,48 +348,71 @@ tcx_init_fix(struct fb_info *info, int linebytes)
 struct all_info {
         struct fb_info info;
         struct tcx_par par;
-        struct list_head list;
 };
-static LIST_HEAD(tcx_list);
 
-static void tcx_init_one(struct sbus_dev *sdev)
+static void tcx_unmap_regs(struct all_info *all)
 {
-        struct all_info *all;
-        int linebytes, i;
+        if (all->par.tec)
+                of_iounmap(all->par.tec, sizeof(struct tcx_tec));
+        if (all->par.thc)
+                of_iounmap(all->par.thc, sizeof(struct tcx_thc));
+        if (all->par.bt)
+                of_iounmap(all->par.bt, sizeof(struct bt_regs));
+        if (all->par.cplane)
+                of_iounmap(all->par.cplane, all->par.fbsize * sizeof(u32));
+        if (all->info.screen_base)
+                of_iounmap(all->info.screen_base, all->par.fbsize);
+}
 
-        all = kmalloc(sizeof(*all), GFP_KERNEL);
-        if (!all) {
-                printk(KERN_ERR "tcx: Cannot allocate memory.\n");
-                return;
-        }
-        memset(all, 0, sizeof(*all));
+static int __devinit tcx_init_one(struct of_device *op)
+{
+        struct device_node *dp = op->node;
+        struct all_info *all;
+        int linebytes, i, err;
 
-        INIT_LIST_HEAD(&all->list);
+        all = kzalloc(sizeof(*all), GFP_KERNEL);
+        if (!all)
+                return -ENOMEM;
 
         spin_lock_init(&all->par.lock);
-        all->par.sdev = sdev;
 
-        all->par.lowdepth = prom_getbool(sdev->prom_node, "tcx-8-bit");
+        all->par.lowdepth =
+                (of_find_property(dp, "tcx-8-bit", NULL) != NULL);
 
-        sbusfb_fill_var(&all->info.var, sdev->prom_node, 8);
+        sbusfb_fill_var(&all->info.var, dp->node, 8);
         all->info.var.red.length = 8;
         all->info.var.green.length = 8;
         all->info.var.blue.length = 8;
 
-        linebytes = prom_getintdefault(sdev->prom_node, "linebytes",
-                                       all->info.var.xres);
+        linebytes = of_getintprop_default(dp, "linebytes",
+                                          all->info.var.xres);
         all->par.fbsize = PAGE_ALIGN(linebytes * all->info.var.yres);
 
-        all->par.tec = sbus_ioremap(&sdev->resource[7], 0,
-                             sizeof(struct tcx_tec), "tcx tec");
-        all->par.thc = sbus_ioremap(&sdev->resource[9], 0,
-                             sizeof(struct tcx_thc), "tcx thc");
-        all->par.bt = sbus_ioremap(&sdev->resource[8], 0,
-                             sizeof(struct bt_regs), "tcx dac");
+        all->par.tec = of_ioremap(&op->resource[7], 0,
+                                  sizeof(struct tcx_tec), "tcx tec");
+        all->par.thc = of_ioremap(&op->resource[9], 0,
+                                  sizeof(struct tcx_thc), "tcx thc");
+        all->par.bt = of_ioremap(&op->resource[8], 0,
+                                 sizeof(struct bt_regs), "tcx dac");
+        all->info.screen_base = of_ioremap(&op->resource[0], 0,
+                                           all->par.fbsize, "tcx ram");
+        if (!all->par.tec || !all->par.thc ||
+            !all->par.bt || !all->info.screen_base) {
+                tcx_unmap_regs(all);
+                kfree(all);
+                return -ENOMEM;
+        }
+
         memcpy(&all->par.mmap_map, &__tcx_mmap_map, sizeof(all->par.mmap_map));
         if (!all->par.lowdepth) {
-                all->par.cplane = sbus_ioremap(&sdev->resource[4], 0,
-                                     all->par.fbsize * sizeof(u32), "tcx cplane");
+                all->par.cplane = of_ioremap(&op->resource[4], 0,
+                                             all->par.fbsize * sizeof(u32),
+                                             "tcx cplane");
+                if (!all->par.cplane) {
+                        tcx_unmap_regs(all);
+                        kfree(all);
+                        return -ENOMEM;
+                }
         } else {
                 all->par.mmap_map[1].size = SBUS_MMAP_EMPTY;
                 all->par.mmap_map[4].size = SBUS_MMAP_EMPTY;
@@ -400,6 +421,8 @@ static void tcx_init_one(struct sbus_dev *sdev)
         }
 
         all->par.physbase = 0;
+        all->par.which_io = op->resource[0].flags & IORESOURCE_BITS;
+
         for (i = 0; i < TCX_MMAP_ENTRIES; i++) {
                 int j;
 
@@ -416,18 +439,11 @@ static void tcx_init_one(struct sbus_dev *sdev)
                         j = i;
                         break;
                 };
-                all->par.mmap_map[i].poff = sdev->reg_addrs[j].phys_addr;
+                all->par.mmap_map[i].poff = op->resource[j].start;
         }
 
         all->info.flags = FBINFO_DEFAULT;
         all->info.fbops = &tcx_ops;
-#ifdef CONFIG_SPARC32
-        all->info.screen_base = (char __iomem *)
-                prom_getintdefault(sdev->prom_node, "address", 0);
-#endif
-        if (!all->info.screen_base)
-                all->info.screen_base = sbus_ioremap(&sdev->resource[0], 0,
-                                     all->par.fbsize, "tcx ram");
         all->info.par = &all->par;
 
         /* Initialize brooktree DAC. */
@@ -445,72 +461,88 @@ static void tcx_init_one(struct sbus_dev *sdev)
         tcx_blank(FB_BLANK_UNBLANK, &all->info);
 
         if (fb_alloc_cmap(&all->info.cmap, 256, 0)) {
-                printk(KERN_ERR "tcx: Could not allocate color map.\n");
+                tcx_unmap_regs(all);
                 kfree(all);
-                return;
+                return -ENOMEM;
         }
 
         fb_set_cmap(&all->info.cmap, &all->info);
         tcx_init_fix(&all->info, linebytes);
 
-        if (register_framebuffer(&all->info) < 0) {
-                printk(KERN_ERR "tcx: Could not register framebuffer.\n");
+        err = register_framebuffer(&all->info);
+        if (err < 0) {
                 fb_dealloc_cmap(&all->info.cmap);
+                tcx_unmap_regs(all);
                 kfree(all);
-                return;
+                return err;
         }
 
-        list_add(&all->list, &tcx_list);
+        dev_set_drvdata(&op->dev, all);
 
-        printk("tcx: %s at %lx:%lx, %s\n",
-               sdev->prom_name,
-               (long) sdev->reg_addrs[0].which_io,
-               (long) sdev->reg_addrs[0].phys_addr,
+        printk("%s: TCX at %lx:%lx, %s\n",
+               dp->full_name,
+               all->par.which_io,
+               op->resource[0].start,
                all->par.lowdepth ? "8-bit only" : "24-bit depth");
+
+        return 0;
 }
 
-int __init tcx_init(void)
+static int __devinit tcx_probe(struct of_device *dev, const struct of_device_id *match)
 {
-        struct sbus_bus *sbus;
-        struct sbus_dev *sdev;
+        struct of_device *op = to_of_device(&dev->dev);
 
-        if (fb_get_options("tcxfb", NULL))
-                return -ENODEV;
+        return tcx_init_one(op);
+}
 
-        for_all_sbusdev(sdev, sbus) {
-                if (!strcmp(sdev->prom_name, "SUNW,tcx"))
-                        tcx_init_one(sdev);
-        }
+static int __devexit tcx_remove(struct of_device *dev)
+{
+        struct all_info *all = dev_get_drvdata(&dev->dev);
+
+        unregister_framebuffer(&all->info);
+        fb_dealloc_cmap(&all->info.cmap);
+
+        tcx_unmap_regs(all);
+
+        kfree(all);
+
+        dev_set_drvdata(&dev->dev, NULL);
 
         return 0;
 }
 
-void __exit tcx_exit(void)
-{
-        struct list_head *pos, *tmp;
+static struct of_device_id tcx_match[] = {
+        {
+                .name = "SUNW,tcx",
+        },
+        {},
+};
+MODULE_DEVICE_TABLE(of, tcx_match);
 
-        list_for_each_safe(pos, tmp, &tcx_list) {
-                struct all_info *all = list_entry(pos, typeof(*all), list);
+static struct of_platform_driver tcx_driver = {
+        .name           = "tcx",
+        .match_table    = tcx_match,
+        .probe          = tcx_probe,
+        .remove         = __devexit_p(tcx_remove),
+};
 
-                unregister_framebuffer(&all->info);
-                fb_dealloc_cmap(&all->info.cmap);
-                kfree(all);
-        }
+int __init tcx_init(void)
+{
+        if (fb_get_options("tcxfb", NULL))
+                return -ENODEV;
+
+        return of_register_driver(&tcx_driver, &of_bus_type);
 }
 
-int __init
-tcx_setup(char *arg)
+void __exit tcx_exit(void)
 {
-        /* No cmdline options yet... */
-        return 0;
+        of_unregister_driver(&tcx_driver);
 }
 
 module_init(tcx_init);
-
-#ifdef MODULE
 module_exit(tcx_exit);
-#endif
 
 MODULE_DESCRIPTION("framebuffer driver for TCX chipsets");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
+MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
+MODULE_VERSION("2.0");
 MODULE_LICENSE("GPL");
diff --git a/fs/Kconfig b/fs/Kconfig
index 6dc8cfd6d80c..53f5c6d61121 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -326,7 +326,7 @@ source "fs/xfs/Kconfig"
 
 config OCFS2_FS
         tristate "OCFS2 file system support (EXPERIMENTAL)"
-        depends on NET && EXPERIMENTAL
+        depends on NET && SYSFS && EXPERIMENTAL
         select CONFIGFS_FS
         select JBD
         select CRC32
@@ -356,6 +356,16 @@ config OCFS2_FS
                   - POSIX ACLs
                   - readpages / writepages (not user visible)
 
+config OCFS2_DEBUG_MASKLOG
+        bool "OCFS2 logging support"
+        depends on OCFS2_FS
+        default y
+        help
+          The ocfs2 filesystem has an extensive logging system.  The system
+          allows selection of events to log via files in /sys/o2cb/logmask/.
+          This option will enlarge your kernel, but it allows debugging of
+          ocfs2 filesystem issues.
+
 config MINIX_FS
         tristate "Minix fs support"
         help
diff --git a/fs/buffer.c b/fs/buffer.c
index e9994722f4a3..90e52e677209 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -852,7 +852,7 @@ int __set_page_dirty_buffers(struct page *page)
                 write_lock_irq(&mapping->tree_lock);
                 if (page->mapping) {    /* Race with truncate? */
                         if (mapping_cap_account_dirty(mapping))
-                                inc_page_state(nr_dirty);
+                                __inc_zone_page_state(page, NR_FILE_DIRTY);
                         radix_tree_tag_set(&mapping->page_tree,
                                                 page_index(page),
                                                 PAGECACHE_TAG_DIRTY);
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 207f8006fd6c..df025453dd97 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -211,7 +211,7 @@ static void remove_dir(struct dentry * d)
         struct configfs_dirent * sd;
 
         sd = d->d_fsdata;
-        list_del_init(&sd->s_sibling);
+        list_del_init(&sd->s_sibling);
         configfs_put(sd);
         if (d->d_inode)
                 simple_rmdir(parent->d_inode,d);
@@ -330,7 +330,7 @@ static int configfs_detach_prep(struct dentry *dentry)
 
                         ret = configfs_detach_prep(sd->s_dentry);
                         if (!ret)
-                                continue;
+                                continue;
                 } else
                         ret = -ENOTEMPTY;
 
@@ -931,7 +931,7 @@ int configfs_rename_dir(struct config_item * item, const char *new_name)
 
         new_dentry = lookup_one_len(new_name, parent, strlen(new_name));
         if (!IS_ERR(new_dentry)) {
-                if (!new_dentry->d_inode) {
+                if (!new_dentry->d_inode) {
                         error = config_item_set_name(item, "%s", new_name);
                         if (!error) {
                                 d_add(new_dentry, NULL);
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index e5512e295cf2..fb65e0800a86 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -66,7 +66,7 @@ static void fill_item_path(struct config_item * item, char * buffer, int length)
 }
 
 static int create_link(struct config_item *parent_item,
-                       struct config_item *item,
+                       struct config_item *item,
                        struct dentry *dentry)
 {
         struct configfs_dirent *target_sd = item->ci_dentry->d_fsdata;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 031b27a4bc9a..892643dc9af1 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -464,8 +464,8 @@ void sync_inodes_sb(struct super_block *sb, int wait)
                 .range_start    = 0,
                 .range_end      = LLONG_MAX,
         };
-        unsigned long nr_dirty = read_page_state(nr_dirty);
-        unsigned long nr_unstable = read_page_state(nr_unstable);
+        unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+        unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 
         wbc.nr_to_write = nr_dirty + nr_unstable +
                         (inodes_stat.nr_inodes - inodes_stat.nr_unused) +
diff --git a/fs/inode.c b/fs/inode.c
index f42961eb983b..14a6c4147e4e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -452,15 +452,14 @@ static void prune_icache(int nr_to_scan)
                 nr_pruned++;
         }
         inodes_stat.nr_unused -= nr_pruned;
+        if (current_is_kswapd())
+                __count_vm_events(KSWAPD_INODESTEAL, reap);
+        else
+                __count_vm_events(PGINODESTEAL, reap);
         spin_unlock(&inode_lock);
 
         dispose_list(&freeable);
         mutex_unlock(&iprune_mutex);
-
-        if (current_is_kswapd())
-                mod_page_state(kswapd_inodesteal, reap);
-        else
-                mod_page_state(pginodesteal, reap);
 }
 
 /*
diff --git a/fs/ioprio.c b/fs/ioprio.c
index 7fa76ed53c10..93aa5715f224 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -125,11 +125,24 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
         return ret;
 }
 
+static int get_task_ioprio(struct task_struct *p)
+{
+        int ret;
+
+        ret = security_task_getioprio(p);
+        if (ret)
+                goto out;
+        ret = p->ioprio;
+out:
+        return ret;
+}
+
 asmlinkage long sys_ioprio_get(int which, int who)
 {
         struct task_struct *g, *p;
         struct user_struct *user;
         int ret = -ESRCH;
+        int tmpio;
 
         read_lock_irq(&tasklist_lock);
         switch (which) {
@@ -139,16 +152,19 @@ asmlinkage long sys_ioprio_get(int which, int who)
                         else
                                 p = find_task_by_pid(who);
                         if (p)
-                                ret = p->ioprio;
+                                ret = get_task_ioprio(p);
                         break;
                 case IOPRIO_WHO_PGRP:
                         if (!who)
                                 who = process_group(current);
                         do_each_task_pid(who, PIDTYPE_PGID, p) {
+                                tmpio = get_task_ioprio(p);
+                                if (tmpio < 0)
+                                        continue;
                                 if (ret == -ESRCH)
-                                        ret = p->ioprio;
+                                        ret = tmpio;
                                 else
-                                        ret = ioprio_best(ret, p->ioprio);
+                                        ret = ioprio_best(ret, tmpio);
                         } while_each_task_pid(who, PIDTYPE_PGID, p);
                         break;
                 case IOPRIO_WHO_USER:
@@ -163,10 +179,13 @@ asmlinkage long sys_ioprio_get(int which, int who)
                         do_each_thread(g, p) {
                                 if (p->uid != user->uid)
                                         continue;
+                                tmpio = get_task_ioprio(p);
+                                if (tmpio < 0)
+                                        continue;
                                 if (ret == -ESRCH)
-                                        ret = p->ioprio;
+                                        ret = tmpio;
                                 else
-                                        ret = ioprio_best(ret, p->ioprio);
+                                        ret = ioprio_best(ret, tmpio);
                         } while_each_thread(g, p);
 
                         if (who)
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 52d60c3d8996..e7d5a3097fe6 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -93,7 +93,7 @@ static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
          */
         if (type)
                 *type = VM_FAULT_MAJOR;
-        inc_page_state(pgmajfault);
+        count_vm_event(PGMAJFAULT);
         return page;
 }
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index d89f6fb3b3a3..26b1fe909377 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -315,6 +315,7 @@ nfs_scan_lock_dirty(struct nfs_inode *nfsi, struct list_head *dst,
                                                 req->wb_index, NFS_PAGE_TAG_DIRTY);
                                 nfs_list_remove_request(req);
                                 nfs_list_add_request(req, dst);
+                                dec_zone_page_state(req->wb_page, NR_FILE_DIRTY);
                                 res++;
                         }
                 }
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 8fccb9cb173b..f21e268705c0 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -497,7 +497,7 @@ nfs_mark_request_dirty(struct nfs_page *req)
         nfs_list_add_request(req, &nfsi->dirty);
         nfsi->ndirty++;
         spin_unlock(&nfsi->req_lock);
-        inc_page_state(nr_dirty);
+        inc_zone_page_state(req->wb_page, NR_FILE_DIRTY);
         mark_inode_dirty(inode);
 }
 
@@ -525,7 +525,7 @@ nfs_mark_request_commit(struct nfs_page *req)
         nfs_list_add_request(req, &nfsi->commit);
         nfsi->ncommit++;
         spin_unlock(&nfsi->req_lock);
-        inc_page_state(nr_unstable);
+        inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
         mark_inode_dirty(inode);
 }
 #endif
@@ -609,7 +609,6 @@ nfs_scan_dirty(struct inode *inode, struct list_head *dst, unsigned long idx_sta
         if (nfsi->ndirty != 0) {
                 res = nfs_scan_lock_dirty(nfsi, dst, idx_start, npages);
                 nfsi->ndirty -= res;
-                sub_page_state(nr_dirty,res);
                 if ((nfsi->ndirty == 0) != list_empty(&nfsi->dirty))
                         printk(KERN_ERR "NFS: desynchronized value of nfs_i.ndirty.\n");
         }
@@ -1394,7 +1393,6 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
 {
         struct nfs_write_data   *data = calldata;
         struct nfs_page         *req;
-        int res = 0;
 
         dprintk("NFS: %4d nfs_commit_done (status %d)\n",
                                 task->tk_pid, task->tk_status);
@@ -1406,6 +1404,7 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
         while (!list_empty(&data->pages)) {
                 req = nfs_list_entry(data->pages.next);
                 nfs_list_remove_request(req);
+                dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
 
                 dprintk("NFS: commit (%s/%Ld %d@%Ld)",
                         req->wb_context->dentry->d_inode->i_sb->s_id,
@@ -1432,9 +1431,7 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
                 nfs_mark_request_dirty(req);
         next:
                 nfs_clear_page_writeback(req);
-                res++;
         }
-        sub_page_state(nr_unstable,res);
 }
 
 static const struct rpc_call_ops nfs_commit_ops = {
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 3eec30000f3f..01bc68c628ad 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -126,7 +126,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
         if (*ep)
                 goto out;
         dprintk("found fsidtype %d\n", fsidtype);
-        if (fsidtype > 2)
+        if (key_len(fsidtype)==0) /* invalid type */
                 goto out;
         if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0)
                 goto out;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7c7d01672d35..9daa0b9feb8d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1237,8 +1237,15 @@ find_file(struct inode *ino)
         return NULL;
 }
 
-#define TEST_ACCESS(x) ((x > 0 || x < 4)?1:0)
-#define TEST_DENY(x) ((x >= 0 || x < 5)?1:0)
+static int access_valid(u32 x)
+{
+        return (x > 0 && x < 4);
+}
+
+static int deny_valid(u32 x)
+{
+        return (x >= 0 && x < 5);
+}
 
 static void
 set_access(unsigned int *access, unsigned long bmap) {
@@ -1745,7 +1752,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
         int status;
 
         status = nfserr_inval;
-        if (!TEST_ACCESS(open->op_share_access) || !TEST_DENY(open->op_share_deny))
+        if (!access_valid(open->op_share_access)
+                        || !deny_valid(open->op_share_deny))
                 goto out;
         /*
          * Lookup file; if found, lookup stateid and check open request,
@@ -1782,10 +1790,10 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
         } else {
                 /* Stateid was not found, this is a new OPEN */
                 int flags = 0;
+                if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
+                        flags |= MAY_READ;
                 if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
-                        flags = MAY_WRITE;
-                else
-                        flags = MAY_READ;
+                        flags |= MAY_WRITE;
                 status = nfs4_new_open(rqstp, &stp, dp, current_fh, flags);
                 if (status)
                         goto out;
@@ -2070,16 +2078,12 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl
         if (!stateid->si_fileid) { /* delegation stateid */
                 if(!(dp = find_delegation_stateid(ino, stateid))) {
                         dprintk("NFSD: delegation stateid not found\n");
-                        if (nfs4_in_grace())
-                                status = nfserr_grace;
                         goto out;
                 }
                 stidp = &dp->dl_stateid;
         } else { /* open or lock stateid */
                 if (!(stp = find_stateid(stateid, flags))) {
                         dprintk("NFSD: open or lock stateid not found\n");
-                        if (nfs4_in_grace())
-                                status = nfserr_grace;
                         goto out;
                 }
                 if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp))
@@ -2252,8 +2256,9 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
                         (int)current_fh->fh_dentry->d_name.len,
                         current_fh->fh_dentry->d_name.name);
 
-        if ((status = fh_verify(rqstp, current_fh, S_IFREG, 0)))
-                goto out;
+        status = fh_verify(rqstp, current_fh, S_IFREG, 0);
+        if (status)
+                return status;
 
         nfs4_lock_state();
 
@@ -2320,7 +2325,8 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct n
                         (int)current_fh->fh_dentry->d_name.len,
                         current_fh->fh_dentry->d_name.name);
 
-        if (!TEST_ACCESS(od->od_share_access) || !TEST_DENY(od->od_share_deny))
+        if (!access_valid(od->od_share_access)
+                        || !deny_valid(od->od_share_deny))
                 return nfserr_inval;
 
         nfs4_lock_state();
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 3f2ec2e6d06c..ecc439d2565f 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -187,13 +187,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
                         goto out;
                 }
 
-                /* Set user creds for this exportpoint */
-                error = nfsd_setuser(rqstp, exp);
-                if (error) {
-                        error = nfserrno(error);
-                        goto out;
-                }
-
                 /*
                  * Look up the dentry using the NFS file handle.
                  */
@@ -251,6 +244,14 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
         }
         cache_get(&exp->h);
 
+        /* Set user creds for this exportpoint; necessary even in the "just
+         * checking" case because this may be a filehandle that was created by
+         * fh_compose, and that is about to be used in another nfsv4 compound
+         * operation */
+        error = nfserrno(nfsd_setuser(rqstp, exp));
+        if (error)
+                goto out;
+
         error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type);
         if (error)
                 goto out;
@@ -312,8 +313,8 @@ int
 fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, struct svc_fh *ref_fh)
 {
         /* ref_fh is a reference file handle.
-         * if it is non-null, then we should compose a filehandle which is
-         * of the same version, where possible.
+         * if it is non-null and for the same filesystem, then we should compose
+         * a filehandle which is of the same version, where possible.
          * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
          * Then create a 32byte filehandle using nfs_fhbase_old
          *
@@ -332,7 +333,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, st
                 parent->d_name.name, dentry->d_name.name,
                 (inode ? inode->i_ino : 0));
 
-        if (ref_fh) {
+        if (ref_fh && ref_fh->fh_export == exp) {
                 ref_fh_version = ref_fh->fh_handle.fh_version;
                 if (ref_fh_version == 0xca)
                         ref_fh_fsid_type = 0;
@@ -461,7 +462,7 @@ fh_update(struct svc_fh *fhp)
         } else {
                 int size;
                 if (fhp->fh_handle.fh_fileid_type != 0)
-                        goto out_uptodate;
+                        goto out;
                 datap = fhp->fh_handle.fh_auth+
                         fhp->fh_handle.fh_size/4 -1;
                 size = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4;
@@ -481,10 +482,6 @@ out_negative:
         printk(KERN_ERR "fh_update: %s/%s still negative!\n",
                 dentry->d_parent->d_name.name, dentry->d_name.name);
         goto out;
-out_uptodate:
-        printk(KERN_ERR "fh_update: %s/%s already up-to-date!\n",
-                dentry->d_parent->d_name.name, dentry->d_name.name);
-        goto out;
 }
 
 /*
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 245eaa1fb59b..e170030d45da 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -673,7 +673,10 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
                 goto out_nfserr;
 
         if (access & MAY_WRITE) {
-                flags = O_WRONLY|O_LARGEFILE;
+                if (access & MAY_READ)
+                        flags = O_RDWR|O_LARGEFILE;
+                else
+                        flags = O_WRONLY|O_LARGEFILE;
 
                 DQUOT_INIT(inode);
         }
@@ -834,7 +837,7 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
         if (ra && ra->p_set)
                 file->f_ra = ra->p_ra;
 
-        if (file->f_op->sendfile) {
+        if (file->f_op->sendfile && rqstp->rq_sendfile_ok) {
                 svc_pushback_unused_pages(rqstp);
                 err = file->f_op->sendfile(file, &offset, *count,
                                                  nfsd_read_actor, rqstp);
@@ -1517,14 +1520,15 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
                         err = nfserrno(err);
         }
 
-        fh_unlock(ffhp);
         dput(dnew);
+out_unlock:
+        fh_unlock(ffhp);
 out:
         return err;
 
 out_nfserr:
         err = nfserrno(err);
-        goto out;
+        goto out_unlock;
 }
 
 /*
@@ -1553,7 +1557,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
         tdir = tdentry->d_inode;
 
         err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
-        if (fdir->i_sb != tdir->i_sb)
+        if (ffhp->fh_export != tfhp->fh_export)
                 goto out;
 
         err = nfserr_perm;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index cca71317b6d6..f1d1c342ce01 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -558,16 +558,9 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
         u64 vbo_max; /* file offset, max_blocks from iblock */
         u64 p_blkno;
         int contig_blocks;
-        unsigned char blocksize_bits;
+        unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
         unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
 
-        if (!inode || !bh_result) {
-                mlog(ML_ERROR, "inode or bh_result is null\n");
-                return -EIO;
-        }
-
-        blocksize_bits = inode->i_sb->s_blocksize_bits;
-
         /* This function won't even be called if the request isn't all
          * nicely aligned and of the right size, so there's no need
          * for us to check any of that. */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 1d26cfcd9f84..504595d6cf65 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -517,6 +517,7 @@ static inline void o2hb_prepare_block(struct o2hb_region *reg,
         hb_block->hb_seq = cpu_to_le64(cputime);
         hb_block->hb_node = node_num;
         hb_block->hb_generation = cpu_to_le64(generation);
+        hb_block->hb_dead_ms = cpu_to_le32(o2hb_dead_threshold * O2HB_REGION_TIMEOUT_MS);
 
         /* This step must always happen last! */
         hb_block->hb_cksum = cpu_to_le32(o2hb_compute_block_crc_le(reg,
@@ -645,6 +646,8 @@ static int o2hb_check_slot(struct o2hb_region *reg,
         struct o2nm_node *node;
         struct o2hb_disk_heartbeat_block *hb_block = reg->hr_tmp_block;
         u64 cputime;
+        unsigned int dead_ms = o2hb_dead_threshold * O2HB_REGION_TIMEOUT_MS;
+        unsigned int slot_dead_ms;
 
         memcpy(hb_block, slot->ds_raw_block, reg->hr_block_bytes);
 
@@ -733,6 +736,23 @@ fire_callbacks:
                               &o2hb_live_slots[slot->ds_node_num]);
 
                 slot->ds_equal_samples = 0;
+
+                /* We want to be sure that all nodes agree on the
+                 * number of milliseconds before a node will be
+                 * considered dead. The self-fencing timeout is
+                 * computed from this value, and a discrepancy might
+                 * result in heartbeat calling a node dead when it
+                 * hasn't self-fenced yet. */
+                slot_dead_ms = le32_to_cpu(hb_block->hb_dead_ms);
+                if (slot_dead_ms && slot_dead_ms != dead_ms) {
+                        /* TODO: Perhaps we can fail the region here. */
+                        mlog(ML_ERROR, "Node %d on device %s has a dead count "
+                             "of %u ms, but our count is %u ms.\n"
+                             "Please double check your configuration values "
+                             "for 'O2CB_HEARTBEAT_THRESHOLD'\n",
+                             slot->ds_node_num, reg->hr_dev_name, slot_dead_ms,
+                             dead_ms);
+                }
                 goto out;
         }
 
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index 73edad782537..a42628ba9ddf 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -123,6 +123,17 @@
 #define MLOG_MASK_PREFIX 0
 #endif
 
+/*
+ * When logging is disabled, force the bit test to 0 for anything other
+ * than errors and notices, allowing gcc to remove the code completely.
+ * When enabled, allow all masks.
+ */
+#if defined(CONFIG_OCFS2_DEBUG_MASKLOG)
+#define ML_ALLOWED_BITS ~0
+#else
+#define ML_ALLOWED_BITS (ML_ERROR|ML_NOTICE)
+#endif
+
 #define MLOG_MAX_BITS 64
 
 struct mlog_bits {
@@ -187,7 +198,8 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 
 #define mlog(mask, fmt, args...) do {                                   \
         u64 __m = MLOG_MASK_PREFIX | (mask);                            \
-        if (__mlog_test_u64(__m, mlog_and_bits) &&                      \
+        if ((__m & ML_ALLOWED_BITS) &&                                  \
+            __mlog_test_u64(__m, mlog_and_bits) &&                      \
             !__mlog_test_u64(__m, mlog_not_bits)) {                     \
                 if (__m & ML_ERROR)                                     \
                         __mlog_printk(KERN_ERR, "ERROR: "fmt , ##args); \
@@ -204,6 +216,7 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
                 mlog(ML_ERROR, "status = %lld\n", (long long)_st);      \
 } while (0)
 
+#if defined(CONFIG_OCFS2_DEBUG_MASKLOG)
 #define mlog_entry(fmt, args...) do {                                   \
         mlog(ML_ENTRY, "ENTRY:" fmt , ##args);                          \
 } while (0)
@@ -247,6 +260,13 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 #define mlog_exit_void() do {                                           \
         mlog(ML_EXIT, "EXIT\n");                                        \
 } while (0)
+#else
+#define mlog_entry(...)  do { } while (0)
+#define mlog_entry_void(...)  do { } while (0)
+#define mlog_exit(...)  do { } while (0)
+#define mlog_exit_ptr(...)  do { } while (0)
+#define mlog_exit_void(...)  do { } while (0)
+#endif  /* defined(CONFIG_OCFS2_DEBUG_MASKLOG) */
 
 #define mlog_bug_on_msg(cond, fmt, args...) do {                        \
         if (cond) {                                                     \
diff --git a/fs/ocfs2/cluster/ocfs2_heartbeat.h b/fs/ocfs2/cluster/ocfs2_heartbeat.h
index 94096069cb43..3f4151da9709 100644
--- a/fs/ocfs2/cluster/ocfs2_heartbeat.h
+++ b/fs/ocfs2/cluster/ocfs2_heartbeat.h
@@ -32,6 +32,7 @@ struct o2hb_disk_heartbeat_block {
         __u8  hb_pad1[3];
         __le32 hb_cksum;
         __le64 hb_generation;
+        __le32 hb_dead_ms;
 };
 
 #endif /* _OCFS2_HEARTBEAT_H */
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 1591eb37a723..b650efa8c8be 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -396,8 +396,8 @@ static void o2net_set_nn_state(struct o2net_node *nn,
         }
 
         if (was_valid && !valid) {
-                mlog(ML_NOTICE, "no longer connected to " SC_NODEF_FMT "\n",
-                     SC_NODEF_ARGS(old_sc));
+                printk(KERN_INFO "o2net: no longer connected to "
+                       SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc));
                 o2net_complete_nodes_nsw(nn);
         }
 
@@ -409,10 +409,10 @@ static void o2net_set_nn_state(struct o2net_node *nn,
                  * the only way to start connecting again is to down
                  * heartbeat and bring it back up. */
                 cancel_delayed_work(&nn->nn_connect_expired);
-                mlog(ML_NOTICE, "%s " SC_NODEF_FMT "\n", 
-                     o2nm_this_node() > sc->sc_node->nd_num ?
-                        "connected to" : "accepted connection from",
-                     SC_NODEF_ARGS(sc));
+                printk(KERN_INFO "o2net: %s " SC_NODEF_FMT "\n",
+                       o2nm_this_node() > sc->sc_node->nd_num ?
+                                "connected to" : "accepted connection from",
+                       SC_NODEF_ARGS(sc));
         }
 
         /* trigger the connecting worker func as long as we're not valid,
@@ -1280,7 +1280,7 @@ static void o2net_idle_timer(unsigned long data)
 
         do_gettimeofday(&now);
 
-        mlog(ML_NOTICE, "connection to " SC_NODEF_FMT " has been idle for 10 "
+        printk(KERN_INFO "o2net: connection to " SC_NODEF_FMT " has been idle for 10 "
              "seconds, shutting it down.\n", SC_NODEF_ARGS(sc));
         mlog(ML_NOTICE, "here are some times that might help debug the "
              "situation: (tmr %ld.%ld now %ld.%ld dr %ld.%ld adv "
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index ae47f450792f..3d494d1a5f36 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -213,11 +213,9 @@ int ocfs2_find_files_on_disk(const char *name,
                              struct ocfs2_dir_entry **dirent)
 {
         int status = -ENOENT;
-        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-        mlog_entry("(osb=%p, parent=%llu, name='%.*s', blkno=%p, inode=%p)\n",
-                   osb, (unsigned long long)OCFS2_I(inode)->ip_blkno,
-                   namelen, name, blkno, inode);
+        mlog_entry("(name=%.*s, blkno=%p, inode=%p, dirent_bh=%p, dirent=%p)\n",
+                   namelen, name, blkno, inode, dirent_bh, dirent);
 
         *dirent_bh = ocfs2_find_entry(name, namelen, inode, dirent);
         if (!*dirent_bh || !*dirent) {
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 9bdc9cf65991..14530ee7e11d 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -822,8 +822,6 @@ int dlm_begin_reco_handler(struct o2net_msg *msg, u32 len, void *data);
 int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data);
 int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
                           u8 nodenum, u8 *real_master);
-int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
-                               struct dlm_lock_resource *res, u8 *real_master);
 
 
 int dlm_dispatch_assert_master(struct dlm_ctxt *dlm,
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index b8c23f7ba67e..8d1065f8b3bd 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -408,12 +408,13 @@ static void __dlm_print_nodes(struct dlm_ctxt *dlm)
 
         assert_spin_locked(&dlm->spinlock);
 
-        mlog(ML_NOTICE, "Nodes in my domain (\"%s\"):\n", dlm->name);
+        printk(KERN_INFO "ocfs2_dlm: Nodes in domain (\"%s\"): ", dlm->name);
 
         while ((node = find_next_bit(dlm->domain_map, O2NM_MAX_NODES,
                                      node + 1)) < O2NM_MAX_NODES) {
-                mlog(ML_NOTICE, " node %d\n", node);
+                printk("%d ", node);
         }
+        printk("\n");
 }
 
 static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data)
@@ -429,7 +430,7 @@ static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data)
 
         node = exit_msg->node_idx;
 
-        mlog(0, "Node %u leaves domain %s\n", node, dlm->name);
+        printk(KERN_INFO "ocfs2_dlm: Node %u leaves domain %s\n", node, dlm->name);
 
         spin_lock(&dlm->spinlock);
         clear_bit(node, dlm->domain_map);
@@ -678,6 +679,8 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data)
                 set_bit(assert->node_idx, dlm->domain_map);
                 __dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
 
+                printk(KERN_INFO "ocfs2_dlm: Node %u joins domain %s\n",
+                       assert->node_idx, dlm->name);
                 __dlm_print_nodes(dlm);
 
                 /* notify anything attached to the heartbeat events */
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 29b2845f370d..594745fab0b5 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -95,6 +95,9 @@ static void dlm_reco_unlock_ast(void *astdata, enum dlm_status st);
 static void dlm_request_all_locks_worker(struct dlm_work_item *item,
                                          void *data);
 static void dlm_mig_lockres_worker(struct dlm_work_item *item, void *data);
+static int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
+                                      struct dlm_lock_resource *res,
+                                      u8 *real_master);
 
 static u64 dlm_get_next_mig_cookie(void);
 
@@ -1484,8 +1487,9 @@ leave:
 
 
 
-int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
-                               struct dlm_lock_resource *res, u8 *real_master)
+static int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
+                                      struct dlm_lock_resource *res,
+                                      u8 *real_master)
 {
         struct dlm_node_iter iter;
         int nodenum;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 4acd37286bdd..762eb1fbb34d 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2071,8 +2071,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
         }
 
         /* launch vote thread */
-        osb->vote_task = kthread_run(ocfs2_vote_thread, osb, "ocfs2vote-%d",
-                                     osb->osb_id);
+        osb->vote_task = kthread_run(ocfs2_vote_thread, osb, "ocfs2vote");
         if (IS_ERR(osb->vote_task)) {
                 status = PTR_ERR(osb->vote_task);
                 osb->vote_task = NULL;
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 1a5c69071df6..fcd4475d1f89 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -298,7 +298,7 @@ static int ocfs2_extent_map_find_leaf(struct inode *inode,
 
                 ret = ocfs2_extent_map_insert(inode, rec,
                                               le16_to_cpu(el->l_tree_depth));
-                if (ret) {
+                if (ret && (ret != -EEXIST)) {
                         mlog_errno(ret);
                         goto out_free;
                 }
@@ -427,6 +427,11 @@ static int ocfs2_extent_map_insert_entry(struct ocfs2_extent_map *em,
 /*
  * Simple rule: on any return code other than -EAGAIN, anything left
  * in the insert_context will be freed.
+ *
+ * Simple rule #2: A return code of -EEXIST from this function or
+ * its calls to ocfs2_extent_map_insert_entry() signifies that another
+ * thread beat us to the insert.  It is not an actual error, but it
+ * tells the caller we have no more work to do.
  */
 static int ocfs2_extent_map_try_insert(struct inode *inode,
                                        struct ocfs2_extent_rec *rec,
@@ -448,22 +453,32 @@ static int ocfs2_extent_map_try_insert(struct inode *inode,
                 goto out_unlock;
         }
 
+        /* Since insert_entry failed, the map MUST have old_ent */
         old_ent = ocfs2_extent_map_lookup(em, le32_to_cpu(rec->e_cpos),
-                                          le32_to_cpu(rec->e_clusters), NULL,
-                                          NULL);
+                                          le32_to_cpu(rec->e_clusters),
+                                          NULL, NULL);
 
         BUG_ON(!old_ent);
 
-        ret = -EEXIST;
-        if (old_ent->e_tree_depth < tree_depth)
+        if (old_ent->e_tree_depth < tree_depth) {
+                /* Another thread beat us to the lower tree_depth */
+                ret = -EEXIST;
                 goto out_unlock;
+        }
 
         if (old_ent->e_tree_depth == tree_depth) {
+                /*
+                 * Another thread beat us to this tree_depth.
+                 * Let's make sure we agree with that thread (the
+                 * extent_rec should be identical).
+                 */
                 if (!memcmp(rec, &old_ent->e_rec,
                             sizeof(struct ocfs2_extent_rec)))
                         ret = 0;
+                else
+                        /* FIXME: Should this be ESRCH/EBADR??? */
+                        ret = -EEXIST;
 
-                /* FIXME: Should this be ESRCH/EBADR??? */
                 goto out_unlock;
         }
 
@@ -599,7 +614,7 @@ static int ocfs2_extent_map_insert(struct inode *inode,
                                                   tree_depth, &ctxt);
         } while (ret == -EAGAIN);
 
-        if (ret < 0)
+        if ((ret < 0) && (ret != -EEXIST))
                 mlog_errno(ret);
 
         if (ctxt.left_ent)
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 910a601b2e98..f92bf1dd379a 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -784,8 +784,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal)
         }
 
         /* Launch the commit thread */
-        osb->commit_task = kthread_run(ocfs2_commit_thread, osb, "ocfs2cmt-%d",
-                                       osb->osb_id);
+        osb->commit_task = kthread_run(ocfs2_commit_thread, osb, "ocfs2cmt");
         if (IS_ERR(osb->commit_task)) {
                 status = PTR_ERR(osb->commit_task);
                 osb->commit_task = NULL;
@@ -1118,7 +1117,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
                 goto out;
 
         osb->recovery_thread_task =  kthread_run(__ocfs2_recovery_thread, osb,
-                                                 "ocfs2rec-%d", osb->osb_id);
+                                                 "ocfs2rec");
         if (IS_ERR(osb->recovery_thread_task)) {
                 mlog_errno((int)PTR_ERR(osb->recovery_thread_task));
                 osb->recovery_thread_task = NULL;
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 843cf9ddefe8..83934e33e5b0 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -46,12 +46,12 @@ static struct page *ocfs2_nopage(struct vm_area_struct * area,
                                  unsigned long address,
                                  int *type)
 {
-        struct inode *inode = area->vm_file->f_dentry->d_inode;
         struct page *page = NOPAGE_SIGBUS;
         sigset_t blocked, oldset;
         int ret;
 
-        mlog_entry("(inode %lu, address %lu)\n", inode->i_ino, address);
+        mlog_entry("(area=%p, address=%lu, type=%p)\n", area, address,
+                   type);
 
         /* The best way to deal with signals in this path is
          * to block them upfront, rather than allowing the
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index da1093039c01..cd4a6f253d13 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -184,7 +184,6 @@ struct ocfs2_journal;
 struct ocfs2_journal_handle;
 struct ocfs2_super
 {
-        u32 osb_id;             /* id used by the proc interface */
         struct task_struct *commit_task;
         struct super_block *sb;
         struct inode *root_inode;
@@ -222,13 +221,11 @@ struct ocfs2_super
         unsigned long s_mount_opt;
 
         u16 max_slots;
-        u16 num_nodes;
         s16 node_num;
         s16 slot_num;
         int s_sectsize_bits;
         int s_clustersize;
         int s_clustersize_bits;
-        struct proc_dir_entry *proc_sub_dir; /* points to /proc/fs/ocfs2/<maj_min> */
 
         atomic_t vol_state;
         struct mutex recovery_lock;
@@ -294,7 +291,6 @@ struct ocfs2_super
 };
 
 #define OCFS2_SB(sb)        ((struct ocfs2_super *)(sb)->s_fs_info)
-#define OCFS2_MAX_OSB_ID             65536
 
 static inline int ocfs2_should_order_data(struct inode *inode)
 {
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 871627961d6d..aa6f5aadedc4 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -264,7 +264,7 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
         osb->slot_num = slot;
         spin_unlock(&si->si_lock);
 
-        mlog(ML_NOTICE, "taking node slot %d\n", osb->slot_num);
+        mlog(0, "taking node slot %d\n", osb->slot_num);
 
         status = ocfs2_update_disk_slots(osb, si);
         if (status < 0)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index cdf73393f094..382706a67ffd 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -68,13 +68,6 @@
 
 #include "buffer_head_io.h"
 
-/*
- * Globals
- */
-static spinlock_t ocfs2_globals_lock = SPIN_LOCK_UNLOCKED;
-
-static u32 osb_id;             /* Keeps track of next available OSB Id */
-
 static kmem_cache_t *ocfs2_inode_cachep = NULL;
 
 kmem_cache_t *ocfs2_lock_cache = NULL;
@@ -642,10 +635,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
         ocfs2_complete_mount_recovery(osb);
 
-        printk("ocfs2: Mounting device (%u,%u) on (node %d, slot %d) with %s "
-               "data mode.\n",
-               MAJOR(sb->s_dev), MINOR(sb->s_dev), osb->node_num,
-               osb->slot_num,
+        printk(KERN_INFO "ocfs2: Mounting device (%s) on (node %d, slot %d) "
+               "with %s data mode.\n",
+               osb->dev_str, osb->node_num, osb->slot_num,
                osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
                "ordered");
 
@@ -800,10 +792,6 @@ static int __init ocfs2_init(void)
                 goto leave;
         }
 
-        spin_lock(&ocfs2_globals_lock);
-        osb_id = 0;
-        spin_unlock(&ocfs2_globals_lock);
-
         ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
         if (!ocfs2_debugfs_root) {
                 status = -EFAULT;
@@ -1020,7 +1008,7 @@ static int ocfs2_fill_local_node_info(struct ocfs2_super *osb)
                 goto bail;
         }
 
-        mlog(ML_NOTICE, "I am node %d\n", osb->node_num);
+        mlog(0, "I am node %d\n", osb->node_num);
 
         status = 0;
 bail:
@@ -1191,8 +1179,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
         atomic_set(&osb->vol_state, VOLUME_DISMOUNTED);
 
-        printk("ocfs2: Unmounting device (%u,%u) on (node %d)\n",
-               MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev), osb->node_num);
+        printk(KERN_INFO "ocfs2: Unmounting device (%s) on (node %d)\n",
+               osb->dev_str, osb->node_num);
 
         ocfs2_delete_osb(osb);
         kfree(osb);
@@ -1212,8 +1200,6 @@ static int ocfs2_setup_osb_uuid(struct ocfs2_super *osb, const unsigned char *uu
         if (osb->uuid_str == NULL)
                 return -ENOMEM;
 
-        memcpy(osb->uuid, uuid, OCFS2_VOL_UUID_LEN);
-
         for (i = 0, ptr = osb->uuid_str; i < OCFS2_VOL_UUID_LEN; i++) {
                 /* print with null */
                 ret = snprintf(ptr, 3, "%02X", uuid[i]);
@@ -1311,13 +1297,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
                 goto bail;
         }
 
-        osb->uuid = kmalloc(OCFS2_VOL_UUID_LEN, GFP_KERNEL);
-        if (!osb->uuid) {
-                mlog(ML_ERROR, "unable to alloc uuid\n");
-                status = -ENOMEM;
-                goto bail;
-        }
-
         di = (struct ocfs2_dinode *)bh->b_data;
 
         osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
@@ -1327,7 +1306,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
                 status = -EINVAL;
                 goto bail;
         }
-        mlog(ML_NOTICE, "max_slots for this device: %u\n", osb->max_slots);
+        mlog(0, "max_slots for this device: %u\n", osb->max_slots);
 
         init_waitqueue_head(&osb->osb_wipe_event);
         osb->osb_orphan_wipes = kcalloc(osb->max_slots,
@@ -1418,7 +1397,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
                 goto bail;
         }
 
-        memcpy(&uuid_net_key, &osb->uuid[i], sizeof(osb->net_key));
+        memcpy(&uuid_net_key, di->id2.i_super.s_uuid, sizeof(uuid_net_key));
         osb->net_key = le32_to_cpu(uuid_net_key);
 
         strncpy(osb->vol_label, di->id2.i_super.s_label, 63);
@@ -1484,18 +1463,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
                 goto bail;
         }
 
-        /*  Link this osb onto the global linked list of all osb structures. */
-        /*  The Global Link List is mainted for the whole driver . */
-        spin_lock(&ocfs2_globals_lock);
-        osb->osb_id = osb_id;
-        if (osb_id < OCFS2_MAX_OSB_ID)
-                osb_id++;
-        else {
-                mlog(ML_ERROR, "Too many volumes mounted\n");
-                status = -ENOMEM;
-        }
-        spin_unlock(&ocfs2_globals_lock);
-
 bail:
         mlog_exit(status);
         return status;
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index 0c8a1294ec96..c0f68aa6c175 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -154,7 +154,7 @@ static void *ocfs2_follow_link(struct dentry *dentry,
         }
 
         status = vfs_follow_link(nd, link);
-        if (status)
+        if (status && status != -ENOENT)
                 mlog_errno(status);
 bail:
         if (page) {
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 5c10ea157425..6aa2aa779a09 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -120,7 +120,6 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 {
         struct sysinfo i;
         int len;
-        struct page_state ps;
         unsigned long inactive;
         unsigned long active;
         unsigned long free;
@@ -129,7 +128,6 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
         struct vmalloc_info vmi;
         long cached;
 
-        get_page_state(&ps);
         get_zone_counts(&active, &inactive, &free);
 
 /*
@@ -142,7 +140,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
         allowed = ((totalram_pages - hugetlb_total_pages())
                 * sysctl_overcommit_ratio / 100) + total_swap_pages;
 
-        cached = get_page_cache_size() - total_swapcache_pages - i.bufferram;
+        cached = global_page_state(NR_FILE_PAGES) -
+                        total_swapcache_pages - i.bufferram;
         if (cached < 0)
                 cached = 0;
 
@@ -167,11 +166,14 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
                 "SwapFree:     %8lu kB\n"
                 "Dirty:        %8lu kB\n"
                 "Writeback:    %8lu kB\n"
+                "AnonPages:    %8lu kB\n"
                 "Mapped:       %8lu kB\n"
                 "Slab:         %8lu kB\n"
+                "PageTables:   %8lu kB\n"
+                "NFS Unstable: %8lu kB\n"
+                "Bounce:       %8lu kB\n"
                 "CommitLimit:  %8lu kB\n"
                 "Committed_AS: %8lu kB\n"
-                "PageTables:   %8lu kB\n"
                 "VmallocTotal: %8lu kB\n"
                 "VmallocUsed:  %8lu kB\n"
                 "VmallocChunk: %8lu kB\n",
@@ -188,13 +190,16 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
                 K(i.freeram-i.freehigh),
                 K(i.totalswap),
                 K(i.freeswap),
-                K(ps.nr_dirty),
-                K(ps.nr_writeback),
-                K(ps.nr_mapped),
-                K(ps.nr_slab),
+                K(global_page_state(NR_FILE_DIRTY)),
+                K(global_page_state(NR_WRITEBACK)),
+                K(global_page_state(NR_ANON_PAGES)),
+                K(global_page_state(NR_FILE_MAPPED)),
+                K(global_page_state(NR_SLAB)),
+                K(global_page_state(NR_PAGETABLE)),
+                K(global_page_state(NR_UNSTABLE_NFS)),
+                K(global_page_state(NR_BOUNCE)),
                 K(allowed),
                 K(committed),
-                K(ps.nr_page_table_pages),
                 (unsigned long)VMALLOC_TOTAL >> 10,
                 vmi.used >> 10,
                 vmi.largest_chunk >> 10
diff --git a/include/asm-alpha/socket.h b/include/asm-alpha/socket.h
index b5193229132a..d22ab97ea72e 100644
--- a/include/asm-alpha/socket.h
+++ b/include/asm-alpha/socket.h
@@ -51,6 +51,7 @@
 #define SCM_TIMESTAMP           SO_TIMESTAMP
 
 #define SO_PEERSEC              30
+#define SO_PASSSEC              34
 
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION              19
diff --git a/include/asm-arm/socket.h b/include/asm-arm/socket.h
index 3c51da6438c9..19f7df702b06 100644
--- a/include/asm-arm/socket.h
+++ b/include/asm-arm/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-arm26/socket.h b/include/asm-arm26/socket.h
index 3c51da6438c9..19f7df702b06 100644
--- a/include/asm-arm26/socket.h
+++ b/include/asm-arm26/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-cris/socket.h b/include/asm-cris/socket.h
index 8b1da3e58c55..01cfdf1d6d33 100644
--- a/include/asm-cris/socket.h
+++ b/include/asm-cris/socket.h
@@ -50,6 +50,7 @@
 #define SO_ACCEPTCONN          30
 
 #define SO_PEERSEC             31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
 
diff --git a/include/asm-frv/socket.h b/include/asm-frv/socket.h
index 7177f8b9817c..31db18fc871f 100644
--- a/include/asm-frv/socket.h
+++ b/include/asm-frv/socket.h
@@ -48,6 +48,7 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
 
diff --git a/include/asm-h8300/socket.h b/include/asm-h8300/socket.h
index d98cf85bafc1..ebc830fee0d0 100644
--- a/include/asm-h8300/socket.h
+++ b/include/asm-h8300/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-i386/socket.h b/include/asm-i386/socket.h
index 802ae76195b7..5755d57c4e95 100644
--- a/include/asm-i386/socket.h
+++ b/include/asm-i386/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-ia64/socket.h b/include/asm-ia64/socket.h
index a255006fb7b5..d638ef3d50c3 100644
--- a/include/asm-ia64/socket.h
+++ b/include/asm-ia64/socket.h
@@ -57,5 +57,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC             31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/include/asm-m32r/socket.h b/include/asm-m32r/socket.h
index 8b6680f223c0..acdf748fcdc8 100644
--- a/include/asm-m32r/socket.h
+++ b/include/asm-m32r/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/include/asm-m68k/socket.h b/include/asm-m68k/socket.h
index f578ca4b776a..a5966ec005ae 100644
--- a/include/asm-m68k/socket.h
+++ b/include/asm-m68k/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC             31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-mips/socket.h b/include/asm-mips/socket.h
index 0bb31e5aaca6..36ebe4e186a7 100644
--- a/include/asm-mips/socket.h
+++ b/include/asm-mips/socket.h
@@ -69,6 +69,7 @@ To add: #define SO_REUSEPORT 0x0200	/* Allow local address and port reuse.  */
 #define SO_PEERSEC              30
 #define SO_SNDBUFFORCE          31
 #define SO_RCVBUFFORCE          33
+#define SO_PASSSEC              34
 
 #ifdef __KERNEL__
 
diff --git a/include/asm-parisc/socket.h b/include/asm-parisc/socket.h
index 1bf54dc53c10..ce2eae1708b5 100644
--- a/include/asm-parisc/socket.h
+++ b/include/asm-parisc/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           0x401c
 
 #define SO_PEERSEC              0x401d
+#define SO_PASSSEC              0x401e
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-powerpc/socket.h b/include/asm-powerpc/socket.h
index e4b8177d4acc..c8b1da50e72d 100644
--- a/include/asm-powerpc/socket.h
+++ b/include/asm-powerpc/socket.h
@@ -55,5 +55,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif  /* _ASM_POWERPC_SOCKET_H */
diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h
index 859b5e969826..24312387fa24 100644
--- a/include/asm-s390/pgtable.h
+++ b/include/asm-s390/pgtable.h
@@ -657,13 +657,6 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
         __pte;                                                            \
 })
 
-#define SetPageUptodate(_page) \
-        do {                                                                  \
-                struct page *__page = (_page);                                \
-                if (!test_and_set_bit(PG_uptodate, &__page->flags))           \
-                        page_test_and_clear_dirty(_page);                     \
-        } while (0)
-
 #ifdef __s390x__
 
 #define pfn_pmd(pfn, pgprot)                                              \
diff --git a/include/asm-s390/socket.h b/include/asm-s390/socket.h
index 15a5298c8744..1778a49a74c5 100644
--- a/include/asm-s390/socket.h
+++ b/include/asm-s390/socket.h
@@ -56,5 +56,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-sh/socket.h b/include/asm-sh/socket.h
index 553904ff9336..ca70362eb563 100644
--- a/include/asm-sh/socket.h
+++ b/include/asm-sh/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* __ASM_SH_SOCKET_H */
diff --git a/include/asm-sparc/of_device.h b/include/asm-sparc/of_device.h
index 4816d102f918..80ea31f6e17f 100644
--- a/include/asm-sparc/of_device.h
+++ b/include/asm-sparc/of_device.h
@@ -4,10 +4,12 @@
 
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
+#include <asm/openprom.h>
 #include <asm/prom.h>
 
 extern struct bus_type ebus_bus_type;
 extern struct bus_type sbus_bus_type;
+extern struct bus_type of_bus_type;
 
 /*
  * The of_device is a kind of "base class" that is a superset of
@@ -16,11 +18,25 @@ extern struct bus_type sbus_bus_type;
  */
 struct of_device
 {
-        struct device_node      *node;          /* OF device node */
-        struct device           dev;            /* Generic device interface */
+        struct device_node              *node;
+        struct device                   dev;
+        struct resource                 resource[PROMREG_MAX];
+        unsigned int                    irqs[PROMINTR_MAX];
+        int                             num_irqs;
+
+        void                            *sysdata;
+
+        int                             slot;
+        int                             portid;
+        int                             clock_freq;
 };
 #define to_of_device(d) container_of(d, struct of_device, dev)
 
+extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name);
+extern void of_iounmap(void __iomem *base, unsigned long size);
+
+extern struct of_device *of_find_device_by_node(struct device_node *);
+
 extern const struct of_device_id *of_match_device(
         const struct of_device_id *matches, const struct of_device *dev);
 
diff --git a/include/asm-sparc/prom.h b/include/asm-sparc/prom.h
index f9cf44c07164..86c13dccea3d 100644
--- a/include/asm-sparc/prom.h
+++ b/include/asm-sparc/prom.h
@@ -25,11 +25,6 @@
 typedef u32 phandle;
 typedef u32 ihandle;
 
-struct interrupt_info {
-        int     line;
-        int     sense;          /* +ve/-ve logic, edge or level, etc. */
-};
-
 struct property {
         char    *name;
         int     length;
@@ -43,9 +38,6 @@ struct device_node {
         char    *name;
         char    *type;
         phandle node;
-        phandle linux_phandle;
-        int     n_intrs;
-        struct  interrupt_info *intrs;
         char    *path_component_name;
         char    *full_name;
 
@@ -69,6 +61,8 @@ struct device_node {
 #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags)
 #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags)
 
+#define OF_BAD_ADDR     ((u64)-1)
+
 static inline void set_node_proc_entry(struct device_node *dn, struct proc_dir_entry *de)
 {
         dn->pde = de;
@@ -101,6 +95,8 @@ extern int of_set_property(struct device_node *node, const char *name, void *val
 extern int of_getintprop_default(struct device_node *np,
                                  const char *name,
                                  int def);
+extern int of_n_addr_cells(struct device_node *np);
+extern int of_n_size_cells(struct device_node *np);
 
 extern void prom_build_devicetree(void);
 
diff --git a/include/asm-sparc/socket.h b/include/asm-sparc/socket.h
index 4e0ce3a35ea9..f6c4e5baf3f7 100644
--- a/include/asm-sparc/socket.h
+++ b/include/asm-sparc/socket.h
@@ -48,6 +48,7 @@
 #define SCM_TIMESTAMP           SO_TIMESTAMP
 
 #define SO_PEERSEC              0x001e
+#define SO_PASSSEC              0x001f
 
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION              0x5001
diff --git a/include/asm-sparc64/of_device.h b/include/asm-sparc64/of_device.h
index 024088ef9d27..a62c7b997d66 100644
--- a/include/asm-sparc64/of_device.h
+++ b/include/asm-sparc64/of_device.h
@@ -4,11 +4,13 @@
 
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
+#include <asm/openprom.h>
 #include <asm/prom.h>
 
 extern struct bus_type isa_bus_type;
 extern struct bus_type ebus_bus_type;
 extern struct bus_type sbus_bus_type;
+extern struct bus_type of_bus_type;
 
 /*
  * The of_device is a kind of "base class" that is a superset of
@@ -17,11 +19,25 @@ extern struct bus_type sbus_bus_type;
  */
 struct of_device
 {
-        struct device_node      *node;          /* OF device node */
-        struct device           dev;            /* Generic device interface */
+        struct device_node              *node;
+        struct device                   dev;
+        struct resource                 resource[PROMREG_MAX];
+        unsigned int                    irqs[PROMINTR_MAX];
+        int                             num_irqs;
+
+        void                            *sysdata;
+
+        int                             slot;
+        int                             portid;
+        int                             clock_freq;
 };
 #define to_of_device(d) container_of(d, struct of_device, dev)
 
+extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name);
+extern void of_iounmap(void __iomem *base, unsigned long size);
+
+extern struct of_device *of_find_device_by_node(struct device_node *);
+
 extern const struct of_device_id *of_match_device(
         const struct of_device_id *matches, const struct of_device *dev);
 
diff --git a/include/asm-sparc64/pbm.h b/include/asm-sparc64/pbm.h
index cebe80b1da6c..dcfa7629358c 100644
--- a/include/asm-sparc64/pbm.h
+++ b/include/asm-sparc64/pbm.h
@@ -16,6 +16,7 @@
 #include <asm/page.h>
 #include <asm/oplib.h>
 #include <asm/prom.h>
+#include <asm/of_device.h>
 #include <asm/iommu.h>
 
 /* The abstraction used here is that there are PCI controllers,
@@ -209,7 +210,6 @@ struct pci_controller_info {
 
         /* Operations which are controller specific. */
         void (*scan_bus)(struct pci_controller_info *);
-        unsigned int (*irq_build)(struct pci_pbm_info *, struct pci_dev *, unsigned int);
         void (*base_address_update)(struct pci_dev *, int);
         void (*resource_adjust)(struct pci_dev *, struct resource *, struct resource *);
 
@@ -217,8 +217,6 @@ struct pci_controller_info {
         struct pci_ops                  *pci_ops;
         unsigned int                    pci_first_busno;
         unsigned int                    pci_last_busno;
-
-        void                            *starfire_cookie;
 };
 
 /* PCI devices which are not bridges have this placed in their pci_dev
@@ -228,6 +226,7 @@ struct pci_controller_info {
 struct pcidev_cookie {
         struct pci_pbm_info             *pbm;
         struct device_node              *prom_node;
+        struct of_device                *op;
         struct linux_prom_pci_registers prom_regs[PROMREG_MAX];
         int num_prom_regs;
         struct linux_prom_pci_registers prom_assignments[PROMREG_MAX];
diff --git a/include/asm-sparc64/prom.h b/include/asm-sparc64/prom.h
index 265614d497c4..99671ed6625d 100644
--- a/include/asm-sparc64/prom.h
+++ b/include/asm-sparc64/prom.h
@@ -25,11 +25,6 @@
 typedef u32 phandle;
 typedef u32 ihandle;
 
-struct interrupt_info {
-        int     line;
-        int     sense;          /* +ve/-ve logic, edge or level, etc. */
-};
-
 struct property {
         char    *name;
         int     length;
@@ -39,13 +34,11 @@ struct property {
         unsigned int unique_id;
 };
 
+struct of_irq_controller;
 struct device_node {
         char    *name;
         char    *type;
         phandle node;
-        phandle linux_phandle;
-        int     n_intrs;
-        struct  interrupt_info *intrs;
         char    *path_component_name;
         char    *full_name;
 
@@ -61,6 +54,13 @@ struct device_node {
         unsigned long _flags;
         void    *data;
         unsigned int unique_id;
+
+        struct of_irq_controller *irq_trans;
+};
+
+struct of_irq_controller {
+        unsigned int    (*irq_build)(struct device_node *, unsigned int, void *);
+        void            *data;
 };
 
 /* flag descriptions */
@@ -69,6 +69,8 @@ struct device_node {
 #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags)
 #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags)
 
+#define OF_BAD_ADDR     ((u64)-1)
+
 static inline void set_node_proc_entry(struct device_node *dn, struct proc_dir_entry *de)
 {
         dn->pde = de;
@@ -101,6 +103,8 @@ extern int of_set_property(struct device_node *node, const char *name, void *val
 extern int of_getintprop_default(struct device_node *np,
                                  const char *name,
                                  int def);
+extern int of_n_addr_cells(struct device_node *np);
+extern int of_n_size_cells(struct device_node *np);
 
 extern void prom_build_devicetree(void);
 
diff --git a/include/asm-sparc64/sbus.h b/include/asm-sparc64/sbus.h
index 56ee985e4605..7efd49d31bb8 100644
--- a/include/asm-sparc64/sbus.h
+++ b/include/asm-sparc64/sbus.h
@@ -80,7 +80,6 @@ struct sbus_bus {
         int num_sbus_ranges;
 
         int portid;
-        void *starfire_cookie;
 };
 #define to_sbus(d) container_of(d, struct sbus_bus, ofdev.dev)
 
diff --git a/include/asm-sparc64/socket.h b/include/asm-sparc64/socket.h
index 59987dad3359..754d46a50af3 100644
--- a/include/asm-sparc64/socket.h
+++ b/include/asm-sparc64/socket.h
@@ -48,6 +48,7 @@
 #define SCM_TIMESTAMP           SO_TIMESTAMP
 
 #define SO_PEERSEC              0x001e
+#define SO_PASSSEC              0x001f
 
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION              0x5001
diff --git a/include/asm-sparc64/starfire.h b/include/asm-sparc64/starfire.h
index b606cb2b32a8..48b50b5e35b0 100644
--- a/include/asm-sparc64/starfire.h
+++ b/include/asm-sparc64/starfire.h
@@ -14,7 +14,7 @@ extern int this_is_starfire;
 extern void check_if_starfire(void);
 extern void starfire_cpu_setup(void);
 extern int starfire_hard_smp_processor_id(void);
-extern void *starfire_hookup(int);
+extern void starfire_hookup(int);
 extern unsigned int starfire_translate(unsigned long imap, unsigned int upaid);
 
 #endif
diff --git a/include/asm-um/io.h b/include/asm-um/io.h
index 1934d9340e2c..44e8b8c772ae 100644
--- a/include/asm-um/io.h
+++ b/include/asm-um/io.h
@@ -45,8 +45,13 @@ static inline void writel(unsigned int b, volatile void __iomem *addr)
 {
         *(volatile unsigned int __force *) addr = b;
 }
+static inline void writeq(unsigned int b, volatile void __iomem *addr)
+{
+        *(volatile unsigned long long __force *) addr = b;
+}
 #define __raw_writeb writeb
 #define __raw_writew writew
 #define __raw_writel writel
+#define __raw_writeq writeq
 
 #endif
diff --git a/include/asm-v850/socket.h b/include/asm-v850/socket.h
index 0240d366a0a4..0dfe55ac2ef2 100644
--- a/include/asm-v850/socket.h
+++ b/include/asm-v850/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif /* __V850_SOCKET_H__ */
diff --git a/include/asm-x86_64/socket.h b/include/asm-x86_64/socket.h
index f2cdbeae5d5b..b46702607933 100644
--- a/include/asm-x86_64/socket.h
+++ b/include/asm-x86_64/socket.h
@@ -48,5 +48,6 @@
 #define SO_ACCEPTCONN           30
 
 #define SO_PEERSEC             31
+#define SO_PASSSEC              34
 
 #endif /* _ASM_SOCKET_H */
diff --git a/include/asm-xtensa/socket.h b/include/asm-xtensa/socket.h
index 00f83f3a6d72..971d231be60e 100644
--- a/include/asm-xtensa/socket.h
+++ b/include/asm-xtensa/socket.h
@@ -59,5 +59,6 @@
 
 #define SO_ACCEPTCONN           30
 #define SO_PEERSEC              31
+#define SO_PASSSEC              34
 
 #endif  /* _XTENSA_SOCKET_H */
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 1eb238affb12..41788a31c438 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -7,6 +7,7 @@
 #define LINUX_ATMDEV_H
 
 
+#include <linux/device.h>
 #include <linux/atmapi.h>
 #include <linux/atm.h>
 #include <linux/atmioc.h>
@@ -358,6 +359,7 @@ struct atm_dev {
         struct proc_dir_entry *proc_entry; /* proc entry */
         char *proc_name;                /* proc entry name */
 #endif
+        struct class_device class_dev;  /* sysfs class device */
         struct list_head dev_list;      /* linkage */
 };
 
@@ -459,7 +461,7 @@ static inline void atm_dev_put(struct atm_dev *dev)
                 BUG_ON(!test_bit(ATM_DF_REMOVED, &dev->flags));
                 if (dev->ops->dev_close)
                         dev->ops->dev_close(dev);
-                kfree(dev);
+                class_device_put(&dev->class_dev);
         }
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c41a1299b8cf..75179529e399 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -36,7 +36,6 @@ extern int sysctl_legacy_va_layout;
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/atomic.h>
 
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
@@ -515,6 +514,11 @@ static inline void set_page_links(struct page *page, unsigned long zone,
         set_page_section(page, pfn_to_section_nr(pfn));
 }
 
+/*
+ * Some inline functions in vmstat.h depend on page_zone()
+ */
+#include <linux/vmstat.h>
+
 #ifndef CONFIG_DISCONTIGMEM
 /* The array of struct pages - for discontigmem use pgdat->lmem_map */
 extern struct page *mem_map;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d6120fa69116..27e748eb72b0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -46,6 +46,27 @@ struct zone_padding {
 #define ZONE_PADDING(name)
 #endif
 
+enum zone_stat_item {
+        NR_ANON_PAGES,  /* Mapped anonymous pages */
+        NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
+                           only modified from process context */
+        NR_FILE_PAGES,
+        NR_SLAB,        /* Pages used by slab allocator */
+        NR_PAGETABLE,   /* used for pagetables */
+        NR_FILE_DIRTY,
+        NR_WRITEBACK,
+        NR_UNSTABLE_NFS,        /* NFS unstable pages */
+        NR_BOUNCE,
+#ifdef CONFIG_NUMA
+        NUMA_HIT,               /* allocated in intended node */
+        NUMA_MISS,              /* allocated in non intended node */
+        NUMA_FOREIGN,           /* was intended here, hit elsewhere */
+        NUMA_INTERLEAVE_HIT,    /* interleaver preferred this zone */
+        NUMA_LOCAL,             /* allocation from local node */
+        NUMA_OTHER,             /* allocation from other node */
+#endif
+        NR_VM_ZONE_STAT_ITEMS };
+
 struct per_cpu_pages {
         int count;              /* number of pages in the list */
         int high;               /* high watermark, emptying needed */
@@ -55,13 +76,8 @@ struct per_cpu_pages {
 
 struct per_cpu_pageset {
         struct per_cpu_pages pcp[2];    /* 0: hot.  1: cold */
-#ifdef CONFIG_NUMA
-        unsigned long numa_hit;         /* allocated in intended node */
-        unsigned long numa_miss;        /* allocated in non intended node */
-        unsigned long numa_foreign;     /* was intended here, hit elsewhere */
-        unsigned long interleave_hit;   /* interleaver prefered this zone */
-        unsigned long local_node;       /* allocation from local node */
-        unsigned long other_node;       /* allocation from other node */
+#ifdef CONFIG_SMP
+        s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
 #endif
 } ____cacheline_aligned_in_smp;
 
@@ -165,12 +181,8 @@ struct zone {
         /* A count of how many reclaimers are scanning this zone */
         atomic_t                reclaim_in_progress;
 
-        /*
-         * timestamp (in jiffies) of the last zone reclaim that did not
-         * result in freeing of pages. This is used to avoid repeated scans
-         * if all memory in the zone is in use.
-         */
-        unsigned long           last_unsuccessful_zone_reclaim;
+        /* Zone statistics */
+        atomic_long_t           vm_stat[NR_VM_ZONE_STAT_ITEMS];
 
         /*
          * prev_priority holds the scanning priority for this zone.  It is
diff --git a/include/linux/net.h b/include/linux/net.h
index 385e68f5bd93..b20c53c74413 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -61,6 +61,7 @@ typedef enum {
 #define SOCK_ASYNC_WAITDATA     1
 #define SOCK_NOSPACE            2
 #define SOCK_PASSCRED           3
+#define SOCK_PASSSEC            4
 
 #ifndef ARCH_HAS_SOCKET_TYPES
 /**
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 03cd7551a7a1..aa2d3c12c4d8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -315,6 +315,8 @@ struct net_device
 #define NETIF_F_GSO_SHIFT       16
 #define NETIF_F_TSO             (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
 #define NETIF_F_UFO             (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)
+#define NETIF_F_GSO_ROBUST      (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
+#define NETIF_F_TSO_ECN         (SKB_GSO_TCPV4_ECN << NETIF_F_GSO_SHIFT)
 
 #define NETIF_F_GEN_CSUM        (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
 #define NETIF_F_ALL_CSUM        (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)
@@ -543,7 +545,8 @@ struct packet_type {
                                          struct net_device *,
                                          struct packet_type *,
                                          struct net_device *);
-        struct sk_buff          *(*gso_segment)(struct sk_buff *skb, int sg);
+        struct sk_buff          *(*gso_segment)(struct sk_buff *skb,
+                                                int features);
         void                    *af_packet_priv;
         struct list_head        list;
 };
@@ -968,7 +971,7 @@ extern int		netdev_max_backlog;
 extern int              weight_p;
 extern int              netdev_set_master(struct net_device *dev, struct net_device *master);
 extern int skb_checksum_help(struct sk_buff *skb, int inward);
-extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg);
+extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features);
 #ifdef CONFIG_BUG
 extern void netdev_rx_csum_fault(struct net_device *dev);
 #else
@@ -988,11 +991,16 @@ extern void dev_seq_stop(struct seq_file *seq, void *v);
 
 extern void linkwatch_run_queue(void);
 
+static inline int skb_gso_ok(struct sk_buff *skb, int features)
+{
+        int feature = skb_shinfo(skb)->gso_size ?
+                      skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT : 0;
+        return (features & feature) == feature;
+}
+
 static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
 {
-        int feature = skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT;
-        return skb_shinfo(skb)->gso_size &&
-               (dev->features & feature) != feature;
+        return !skb_gso_ok(skb, dev->features);
 }
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 0c076d58c676..5748642e9f36 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -5,12 +5,8 @@
 #ifndef PAGE_FLAGS_H
 #define PAGE_FLAGS_H
 
-#include <linux/percpu.h>
-#include <linux/cache.h>
 #include <linux/types.h>
 
-#include <asm/pgtable.h>
-
 /*
  * Various page->flags bits:
  *
@@ -103,134 +99,6 @@
 #endif
 
 /*
- * Global page accounting.  One instance per CPU.  Only unsigned longs are
- * allowed.
- *
- * - Fields can be modified with xxx_page_state and xxx_page_state_zone at
- * any time safely (which protects the instance from modification by
- * interrupt.
- * - The __xxx_page_state variants can be used safely when interrupts are
- * disabled.
- * - The __xxx_page_state variants can be used if the field is only
- * modified from process context and protected from preemption, or only
- * modified from interrupt context.  In this case, the field should be
- * commented here.
- */
-struct page_state {
-        unsigned long nr_dirty;         /* Dirty writeable pages */
-        unsigned long nr_writeback;     /* Pages under writeback */
-        unsigned long nr_unstable;      /* NFS unstable pages */
-        unsigned long nr_page_table_pages;/* Pages used for pagetables */
-        unsigned long nr_mapped;        /* mapped into pagetables.
-                                         * only modified from process context */
-        unsigned long nr_slab;          /* In slab */
-#define GET_PAGE_STATE_LAST nr_slab
-
-        /*
-         * The below are zeroed by get_page_state().  Use get_full_page_state()
-         * to add up all these.
-         */
-        unsigned long pgpgin;           /* Disk reads */
-        unsigned long pgpgout;          /* Disk writes */
-        unsigned long pswpin;           /* swap reads */
-        unsigned long pswpout;          /* swap writes */
-
-        unsigned long pgalloc_high;     /* page allocations */
-        unsigned long pgalloc_normal;
-        unsigned long pgalloc_dma32;
-        unsigned long pgalloc_dma;
-
-        unsigned long pgfree;           /* page freeings */
-        unsigned long pgactivate;       /* pages moved inactive->active */
-        unsigned long pgdeactivate;     /* pages moved active->inactive */
-
-        unsigned long pgfault;          /* faults (major+minor) */
-        unsigned long pgmajfault;       /* faults (major only) */
-
-        unsigned long pgrefill_high;    /* inspected in refill_inactive_zone */
-        unsigned long pgrefill_normal;
-        unsigned long pgrefill_dma32;
-        unsigned long pgrefill_dma;
-
-        unsigned long pgsteal_high;     /* total highmem pages reclaimed */
-        unsigned long pgsteal_normal;
-        unsigned long pgsteal_dma32;
-        unsigned long pgsteal_dma;
-
-        unsigned long pgscan_kswapd_high;/* total highmem pages scanned */
-        unsigned long pgscan_kswapd_normal;
-        unsigned long pgscan_kswapd_dma32;
-        unsigned long pgscan_kswapd_dma;
-
-        unsigned long pgscan_direct_high;/* total highmem pages scanned */
-        unsigned long pgscan_direct_normal;
-        unsigned long pgscan_direct_dma32;
-        unsigned long pgscan_direct_dma;
-
-        unsigned long pginodesteal;     /* pages reclaimed via inode freeing */
-        unsigned long slabs_scanned;    /* slab objects scanned */
-        unsigned long kswapd_steal;     /* pages reclaimed by kswapd */
-        unsigned long kswapd_inodesteal;/* reclaimed via kswapd inode freeing */
-        unsigned long pageoutrun;       /* kswapd's calls to page reclaim */
-        unsigned long allocstall;       /* direct reclaim calls */
-
-        unsigned long pgrotated;        /* pages rotated to tail of the LRU */
-        unsigned long nr_bounce;        /* pages for bounce buffers */
-};
-
-extern void get_page_state(struct page_state *ret);
-extern void get_page_state_node(struct page_state *ret, int node);
-extern void get_full_page_state(struct page_state *ret);
-extern unsigned long read_page_state_offset(unsigned long offset);
-extern void mod_page_state_offset(unsigned long offset, unsigned long delta);
-extern void __mod_page_state_offset(unsigned long offset, unsigned long delta);
-
-#define read_page_state(member) \
-        read_page_state_offset(offsetof(struct page_state, member))
-
-#define mod_page_state(member, delta)   \
-        mod_page_state_offset(offsetof(struct page_state, member), (delta))
-
-#define __mod_page_state(member, delta) \
-        __mod_page_state_offset(offsetof(struct page_state, member), (delta))
-
-#define inc_page_state(member)          mod_page_state(member, 1UL)
-#define dec_page_state(member)          mod_page_state(member, 0UL - 1)
-#define add_page_state(member,delta)    mod_page_state(member, (delta))
-#define sub_page_state(member,delta)    mod_page_state(member, 0UL - (delta))
-
-#define __inc_page_state(member)        __mod_page_state(member, 1UL)
-#define __dec_page_state(member)        __mod_page_state(member, 0UL - 1)
-#define __add_page_state(member,delta)  __mod_page_state(member, (delta))
-#define __sub_page_state(member,delta)  __mod_page_state(member, 0UL - (delta))
-
-#define page_state(member) (*__page_state(offsetof(struct page_state, member)))
-
-#define state_zone_offset(zone, member)                                 \
-({                                                                      \
-        unsigned offset;                                                \
-        if (is_highmem(zone))                                           \
-                offset = offsetof(struct page_state, member##_high);    \
-        else if (is_normal(zone))                                       \
-                offset = offsetof(struct page_state, member##_normal);  \
-        else if (is_dma32(zone))                                        \
-                offset = offsetof(struct page_state, member##_dma32);   \
-        else                                                            \
-                offset = offsetof(struct page_state, member##_dma);     \
-        offset;                                                         \
-})
-
-#define __mod_page_state_zone(zone, member, delta)                      \
- do {                                                                   \
-        __mod_page_state_offset(state_zone_offset(zone, member), (delta)); \
- } while (0)
-
-#define mod_page_state_zone(zone, member, delta)                        \
- do {                                                                   \
-        mod_page_state_offset(state_zone_offset(zone, member), (delta)); \
- } while (0)
-
-/*
  * Manipulation of page state flags
  */
 #define PageLocked(page)                \
@@ -254,7 +122,14 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta);
 #define TestClearPageReferenced(page) test_and_clear_bit(PG_referenced, &(page)->flags)
 
 #define PageUptodate(page)      test_bit(PG_uptodate, &(page)->flags)
-#ifndef SetPageUptodate
+#ifdef CONFIG_S390
+#define SetPageUptodate(_page) \
+        do {                                                                  \
+                struct page *__page = (_page);                                \
+                if (!test_and_set_bit(PG_uptodate, &__page->flags))           \
+                        page_test_and_clear_dirty(_page);                     \
+        } while (0)
+#else
 #define SetPageUptodate(page)   set_bit(PG_uptodate, &(page)->flags)
 #endif
 #define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags)
@@ -306,7 +181,7 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta);
         do {                                                            \
                 if (!test_and_set_bit(PG_writeback,                     \
                                 &(page)->flags))                        \
-                        inc_page_state(nr_writeback);                   \
+                        inc_zone_page_state(page, NR_WRITEBACK);        \
         } while (0)
 #define TestSetPageWriteback(page)                                      \
         ({                                                              \
@@ -314,14 +189,14 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta);
                 ret = test_and_set_bit(PG_writeback,                    \
                                         &(page)->flags);                \
                 if (!ret)                                               \
-                        inc_page_state(nr_writeback);                   \
+                        inc_zone_page_state(page, NR_WRITEBACK);        \
                 ret;                                                    \
         })
 #define ClearPageWriteback(page)                                        \
         do {                                                            \
                 if (test_and_clear_bit(PG_writeback,                    \
                                 &(page)->flags))                        \
-                        dec_page_state(nr_writeback);                   \
+                        dec_zone_page_state(page, NR_WRITEBACK);        \
         } while (0)
 #define TestClearPageWriteback(page)                                    \
         ({                                                              \
@@ -329,7 +204,7 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta);
                 ret = test_and_clear_bit(PG_writeback,                  \
                                 &(page)->flags);                        \
                 if (ret)                                                \
-                        dec_page_state(nr_writeback);                   \
+                        dec_zone_page_state(page, NR_WRITEBACK);        \
                 ret;                                                    \
         })
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 1245df7141aa..0a2f5d27f60e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -113,51 +113,6 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 extern void remove_from_page_cache(struct page *page);
 extern void __remove_from_page_cache(struct page *page);
 
-extern atomic_t nr_pagecache;
-
-#ifdef CONFIG_SMP
-
-#define PAGECACHE_ACCT_THRESHOLD        max(16, NR_CPUS * 2)
-DECLARE_PER_CPU(long, nr_pagecache_local);
-
-/*
- * pagecache_acct implements approximate accounting for pagecache.
- * vm_enough_memory() do not need high accuracy. Writers will keep
- * an offset in their per-cpu arena and will spill that into the
- * global count whenever the absolute value of the local count
- * exceeds the counter's threshold.
- *
- * MUST be protected from preemption.
- * current protection is mapping->page_lock.
- */
-static inline void pagecache_acct(int count)
-{
-        long *local;
-
-        local = &__get_cpu_var(nr_pagecache_local);
-        *local += count;
-        if (*local > PAGECACHE_ACCT_THRESHOLD || *local < -PAGECACHE_ACCT_THRESHOLD) {
-                atomic_add(*local, &nr_pagecache);
-                *local = 0;
-        }
-}
-
-#else
-
-static inline void pagecache_acct(int count)
-{
-        atomic_add(count, &nr_pagecache);
-}
-#endif
-
-static inline unsigned long get_page_cache_size(void)
-{
-        int ret = atomic_read(&nr_pagecache);
-        if (unlikely(ret < 0))
-                ret = 0;
-        return ret;
-}
-
 /*
  * Return byte-offset into filesystem object for page.
  */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 48dfe00070c7..b4ca73d65891 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -163,14 +163,22 @@ extern int rcu_needs_cpu(int cpu);
  *
  * It is illegal to block while in an RCU read-side critical section.
  */
-#define rcu_read_lock()         preempt_disable()
+#define rcu_read_lock() \
+        do { \
+                preempt_disable(); \
+                __acquire(RCU); \
+        } while(0)
 
 /**
  * rcu_read_unlock - marks the end of an RCU read-side critical section.
  *
  * See rcu_read_lock() for more information.
  */
-#define rcu_read_unlock()       preempt_enable()
+#define rcu_read_unlock() \
+        do { \
+                __release(RCU); \
+                preempt_enable(); \
+        } while(0)
 
 /*
  * So where is rcu_write_lock()?  It does not exist, as there is no
@@ -193,14 +201,22 @@ extern int rcu_needs_cpu(int cpu);
  * can use just rcu_read_lock().
  *
  */
-#define rcu_read_lock_bh()      local_bh_disable()
+#define rcu_read_lock_bh() \
+        do { \
+                local_bh_disable(); \
+                __acquire(RCU_BH); \
+        } while(0)
 
 /*
  * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
  *
  * See rcu_read_lock_bh() for more information.
  */
-#define rcu_read_unlock_bh()    local_bh_enable()
+#define rcu_read_unlock_bh() \
+        do { \
+                __release(RCU_BH); \
+                local_bh_enable(); \
+        } while(0)
 
 /**
  * rcu_dereference - fetch an RCU-protected pointer in an
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 36e2bf4b4315..5371e4e74595 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -34,8 +34,8 @@ struct rtc_time {
  * alarm API.
  */
 struct rtc_wkalrm {
-        unsigned char enabled;  /* 0 = alarm disable, 1 = alarm disabled */
-        unsigned char pending;  /* 0 = alarm pending, 1 = alarm not pending */
+        unsigned char enabled;  /* 0 = alarm disabled, 1 = alarm enabled */
+        unsigned char pending;  /* 0 = alarm not pending, 1 = alarm pending */
         struct rtc_time time;   /* time the alarm is set to */
 };
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 821f0481ebe1..aaf723308ed4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1153,7 +1153,7 @@ extern int force_sig_info(int, struct siginfo *, struct task_struct *);
 extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp);
 extern int kill_pg_info(int, struct siginfo *, pid_t);
 extern int kill_proc_info(int, struct siginfo *, pid_t);
-extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t);
+extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t, u32);
 extern void do_notify_parent(struct task_struct *, int);
 extern void force_sig(int, struct task_struct *);
 extern void force_sig_specific(int, struct task_struct *);
diff --git a/include/linux/security.h b/include/linux/security.h
index 51805806f974..f75303831d09 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -67,7 +67,7 @@ struct xfrm_state;
 struct xfrm_user_sec_ctx;
 
 extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb);
-extern int cap_netlink_recv(struct sk_buff *skb);
+extern int cap_netlink_recv(struct sk_buff *skb, int cap);
 
 /*
  * Values used in the task_security_ops calls
@@ -567,6 +567,9 @@ struct swap_info_struct;
  *      @p.
  *      @p contains the task_struct for the process.
  *      Return 0 if permission is granted.
+ * @task_getsecid:
+ *      Retrieve the security identifier of the process @p.
+ *      @p contains the task_struct for the process and place is into @secid.
  * @task_setgroups:
  *      Check permission before setting the supplementary group set of the
  *      current process.
@@ -582,6 +585,10 @@ struct swap_info_struct;
  *      @p contains the task_struct of process.
  *      @ioprio contains the new ioprio value
  *      Return 0 if permission is granted.
+ * @task_getioprio
+ *      Check permission before getting the ioprio value of @p.
+ *      @p contains the task_struct of process.
+ *      Return 0 if permission is granted.
  * @task_setrlimit:
  *      Check permission before setting the resource limits of the current
  *      process for @resource to @new_rlim.  The old resource limit values can
@@ -615,6 +622,7 @@ struct swap_info_struct;
  *      @p contains the task_struct for process.
  *      @info contains the signal information.
  *      @sig contains the signal value.
+ *      @secid contains the sid of the process where the signal originated
  *      Return 0 if permission is granted.
  * @task_wait:
  *      Check permission before allowing a process to reap a child process @p
@@ -656,6 +664,7 @@ struct swap_info_struct;
  *      Check permission before processing the received netlink message in
  *      @skb.
  *      @skb contains the sk_buff structure for the netlink message.
+ *      @cap indicates the capability required
  *      Return 0 if permission is granted.
  *
  * Security hooks for Unix domain networking.
@@ -1218,16 +1227,18 @@ struct security_operations {
         int (*task_setpgid) (struct task_struct * p, pid_t pgid);
         int (*task_getpgid) (struct task_struct * p);
         int (*task_getsid) (struct task_struct * p);
+        void (*task_getsecid) (struct task_struct * p, u32 * secid);
         int (*task_setgroups) (struct group_info *group_info);
         int (*task_setnice) (struct task_struct * p, int nice);
         int (*task_setioprio) (struct task_struct * p, int ioprio);
+        int (*task_getioprio) (struct task_struct * p);
         int (*task_setrlimit) (unsigned int resource, struct rlimit * new_rlim);
         int (*task_setscheduler) (struct task_struct * p, int policy,
                                   struct sched_param * lp);
         int (*task_getscheduler) (struct task_struct * p);
         int (*task_movememory) (struct task_struct * p);
         int (*task_kill) (struct task_struct * p,
-                          struct siginfo * info, int sig);
+                          struct siginfo * info, int sig, u32 secid);
         int (*task_wait) (struct task_struct * p);
         int (*task_prctl) (int option, unsigned long arg2,
                            unsigned long arg3, unsigned long arg4,
@@ -1266,7 +1277,7 @@ struct security_operations {
                           struct sembuf * sops, unsigned nsops, int alter);
 
         int (*netlink_send) (struct sock * sk, struct sk_buff * skb);
-        int (*netlink_recv) (struct sk_buff * skb);
+        int (*netlink_recv) (struct sk_buff * skb, int cap);
 
         /* allow module stacking */
         int (*register_security) (const char *name,
@@ -1838,6 +1849,11 @@ static inline int security_task_getsid (struct task_struct *p)
         return security_ops->task_getsid (p);
 }
 
+static inline void security_task_getsecid (struct task_struct *p, u32 *secid)
+{
+        security_ops->task_getsecid (p, secid);
+}
+
 static inline int security_task_setgroups (struct group_info *group_info)
 {
         return security_ops->task_setgroups (group_info);
@@ -1853,6 +1869,11 @@ static inline int security_task_setioprio (struct task_struct *p, int ioprio)
         return security_ops->task_setioprio (p, ioprio);
 }
 
+static inline int security_task_getioprio (struct task_struct *p)
+{
+        return security_ops->task_getioprio (p);
+}
+
 static inline int security_task_setrlimit (unsigned int resource,
                                            struct rlimit *new_rlim)
 {
@@ -1877,9 +1898,10 @@ static inline int security_task_movememory (struct task_struct *p)
 }
 
 static inline int security_task_kill (struct task_struct *p,
-                                      struct siginfo *info, int sig)
+                                      struct siginfo *info, int sig,
+                                      u32 secid)
 {
-        return security_ops->task_kill (p, info, sig);
+        return security_ops->task_kill (p, info, sig, secid);
 }
 
 static inline int security_task_wait (struct task_struct *p)
@@ -2032,9 +2054,9 @@ static inline int security_netlink_send(struct sock *sk, struct sk_buff * skb)
         return security_ops->netlink_send(sk, skb);
 }
 
-static inline int security_netlink_recv(struct sk_buff * skb)
+static inline int security_netlink_recv(struct sk_buff * skb, int cap)
 {
-        return security_ops->netlink_recv(skb);
+        return security_ops->netlink_recv(skb, cap);
 }
 
 /* prototypes */
@@ -2490,6 +2512,9 @@ static inline int security_task_getsid (struct task_struct *p)
         return 0;
 }
 
+static inline void security_task_getsecid (struct task_struct *p, u32 *secid)
+{ }
+
 static inline int security_task_setgroups (struct group_info *group_info)
 {
         return 0;
@@ -2505,6 +2530,11 @@ static inline int security_task_setioprio (struct task_struct *p, int ioprio)
         return 0;
 }
 
+static inline int security_task_getioprio (struct task_struct *p)
+{
+        return 0;
+}
+
 static inline int security_task_setrlimit (unsigned int resource,
                                            struct rlimit *new_rlim)
 {
@@ -2529,7 +2559,8 @@ static inline int security_task_movememory (struct task_struct *p)
 }
 
 static inline int security_task_kill (struct task_struct *p,
-                                      struct siginfo *info, int sig)
+                                      struct siginfo *info, int sig,
+                                      u32 secid)
 {
         return 0;
 }
@@ -2670,9 +2701,9 @@ static inline int security_netlink_send (struct sock *sk, struct sk_buff *skb)
         return cap_netlink_send (sk, skb);
 }
 
-static inline int security_netlink_recv (struct sk_buff *skb)
+static inline int security_netlink_recv (struct sk_buff *skb, int cap)
 {
-        return cap_netlink_recv (skb);
+        return cap_netlink_recv (skb, cap);
 }
 
 static inline struct dentry *securityfs_create_dir(const char *name,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 16eef03ce0eb..59918be91d0a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -172,6 +172,12 @@ enum {
 enum {
         SKB_GSO_TCPV4 = 1 << 0,
         SKB_GSO_UDPV4 = 1 << 1,
+
+        /* This indicates the skb is from an untrusted source. */
+        SKB_GSO_DODGY = 1 << 2,
+
+        /* This indicates the tcp segment has CWR set. */
+        SKB_GSO_TCPV4_ECN = 1 << 3,
 };
 
 /** 
@@ -1298,8 +1304,7 @@ extern void	       skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 extern void            skb_split(struct sk_buff *skb,
                                  struct sk_buff *skb1, const u32 len);
 
-extern void            skb_release_data(struct sk_buff *skb);
-extern struct sk_buff *skb_segment(struct sk_buff *skb, int sg);
+extern struct sk_buff *skb_segment(struct sk_buff *skb, int features);
 
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
                                        int len, void *buffer)
diff --git a/include/linux/smp.h b/include/linux/smp.h
index c93c3fe4308c..837e8bce1349 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -125,4 +125,6 @@ static inline void smp_send_reschedule(int cpu) { }
 #define put_cpu()               preempt_enable()
 #define put_cpu_no_resched()    preempt_enable_no_resched()
 
+void smp_setup_processor_id(void);
+
 #endif /* __LINUX_SMP_H */
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 503564384545..7b27c09b5604 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -159,7 +159,9 @@ struct svc_rqst {
                                                  * determine what device number
                                                  * to report (real or virtual)
                                                  */
-
+        int                     rq_sendfile_ok; /* turned off in gss privacy
+                                                 * to prevent encrypting page
+                                                 * cache pages */
         wait_queue_head_t       rq_wait;        /* synchronization */
 };
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c41e2d6d1acc..cf6ca6e377bd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -189,7 +189,6 @@ extern long vm_total_pages;
 
 #ifdef CONFIG_NUMA
 extern int zone_reclaim_mode;
-extern int zone_reclaim_interval;
 extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
 #else
 #define zone_reclaim_mode 0
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
new file mode 100644
index 000000000000..3e0daf54133e
--- /dev/null
+++ b/include/linux/vmstat.h
@@ -0,0 +1,215 @@
+#ifndef _LINUX_VMSTAT_H
+#define _LINUX_VMSTAT_H
+
+#include <linux/types.h>
+#include <linux/percpu.h>
+#include <linux/config.h>
+#include <linux/mmzone.h>
+#include <asm/atomic.h>
+
+#ifdef CONFIG_VM_EVENT_COUNTERS
+/*
+ * Light weight per cpu counter implementation.
+ *
+ * Counters should only be incremented and no critical kernel component
+ * should rely on the counter values.
+ *
+ * Counters are handled completely inline. On many platforms the code
+ * generated will simply be the increment of a global address.
+ */
+
+#define FOR_ALL_ZONES(x) x##_DMA, x##_DMA32, x##_NORMAL, x##_HIGH
+
+enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
+                FOR_ALL_ZONES(PGALLOC),
+                PGFREE, PGACTIVATE, PGDEACTIVATE,
+                PGFAULT, PGMAJFAULT,
+                FOR_ALL_ZONES(PGREFILL),
+                FOR_ALL_ZONES(PGSTEAL),
+                FOR_ALL_ZONES(PGSCAN_KSWAPD),
+                FOR_ALL_ZONES(PGSCAN_DIRECT),
+                PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL,
+                PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+                NR_VM_EVENT_ITEMS
+};
+
+struct vm_event_state {
+        unsigned long event[NR_VM_EVENT_ITEMS];
+};
+
+DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
+
+static inline void __count_vm_event(enum vm_event_item item)
+{
+        __get_cpu_var(vm_event_states.event[item])++;
+}
+
+static inline void count_vm_event(enum vm_event_item item)
+{
+        get_cpu_var(vm_event_states.event[item])++;
+        put_cpu();
+}
+
+static inline void __count_vm_events(enum vm_event_item item, long delta)
+{
+        __get_cpu_var(vm_event_states.event[item]) += delta;
+}
+
+static inline void count_vm_events(enum vm_event_item item, long delta)
+{
+        get_cpu_var(vm_event_states.event[item])++;
+        put_cpu();
+}
+
+extern void all_vm_events(unsigned long *);
+extern void vm_events_fold_cpu(int cpu);
+
+#else
+
+/* Disable counters */
+#define get_cpu_vm_events(e)    0L
+#define count_vm_event(e)       do { } while (0)
+#define count_vm_events(e,d)    do { } while (0)
+#define __count_vm_event(e)     do { } while (0)
+#define __count_vm_events(e,d)  do { } while (0)
+#define vm_events_fold_cpu(x)   do { } while (0)
+
+#endif /* CONFIG_VM_EVENT_COUNTERS */
+
+#define __count_zone_vm_events(item, zone, delta) \
+                        __count_vm_events(item##_DMA + zone_idx(zone), delta)
+
+/*
+ * Zone based page accounting with per cpu differentials.
+ */
+extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+
+static inline void zone_page_state_add(long x, struct zone *zone,
+                                 enum zone_stat_item item)
+{
+        atomic_long_add(x, &zone->vm_stat[item]);
+        atomic_long_add(x, &vm_stat[item]);
+}
+
+static inline unsigned long global_page_state(enum zone_stat_item item)
+{
+        long x = atomic_long_read(&vm_stat[item]);
+#ifdef CONFIG_SMP
+        if (x < 0)
+                x = 0;
+#endif
+        return x;
+}
+
+static inline unsigned long zone_page_state(struct zone *zone,
+                                        enum zone_stat_item item)
+{
+        long x = atomic_long_read(&zone->vm_stat[item]);
+#ifdef CONFIG_SMP
+        if (x < 0)
+                x = 0;
+#endif
+        return x;
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * Determine the per node value of a stat item. This function
+ * is called frequently in a NUMA machine, so try to be as
+ * frugal as possible.
+ */
+static inline unsigned long node_page_state(int node,
+                                 enum zone_stat_item item)
+{
+        struct zone *zones = NODE_DATA(node)->node_zones;
+
+        return
+#ifndef CONFIG_DMA_IS_NORMAL
+#if !defined(CONFIG_DMA_IS_DMA32) && BITS_PER_LONG >= 64
+                zone_page_state(&zones[ZONE_DMA32], item) +
+#endif
+                zone_page_state(&zones[ZONE_NORMAL], item) +
+#endif
+#ifdef CONFIG_HIGHMEM
+                zone_page_state(&zones[ZONE_HIGHMEM], item) +
+#endif
+                zone_page_state(&zones[ZONE_DMA], item);
+}
+
+extern void zone_statistics(struct zonelist *, struct zone *);
+
+#else
+
+#define node_page_state(node, item) global_page_state(item)
+#define zone_statistics(_zl,_z) do { } while (0)
+
+#endif /* CONFIG_NUMA */
+
+#define __add_zone_page_state(__z, __i, __d)    \
+                __mod_zone_page_state(__z, __i, __d)
+#define __sub_zone_page_state(__z, __i, __d)    \
+                __mod_zone_page_state(__z, __i,-(__d))
+
+#define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
+#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
+
+static inline void zap_zone_vm_stats(struct zone *zone)
+{
+        memset(zone->vm_stat, 0, sizeof(zone->vm_stat));
+}
+
+extern void inc_zone_state(struct zone *, enum zone_stat_item);
+
+#ifdef CONFIG_SMP
+void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
+void __inc_zone_page_state(struct page *, enum zone_stat_item);
+void __dec_zone_page_state(struct page *, enum zone_stat_item);
+
+void mod_zone_page_state(struct zone *, enum zone_stat_item, int);
+void inc_zone_page_state(struct page *, enum zone_stat_item);
+void dec_zone_page_state(struct page *, enum zone_stat_item);
+
+extern void inc_zone_state(struct zone *, enum zone_stat_item);
+
+void refresh_cpu_vm_stats(int);
+void refresh_vm_stats(void);
+
+#else /* CONFIG_SMP */
+
+/*
+ * We do not maintain differentials in a single processor configuration.
+ * The functions directly modify the zone and global counters.
+ */
+static inline void __mod_zone_page_state(struct zone *zone,
+                        enum zone_stat_item item, int delta)
+{
+        zone_page_state_add(delta, zone, item);
+}
+
+static inline void __inc_zone_page_state(struct page *page,
+                        enum zone_stat_item item)
+{
+        atomic_long_inc(&page_zone(page)->vm_stat[item]);
+        atomic_long_inc(&vm_stat[item]);
+}
+
+static inline void __dec_zone_page_state(struct page *page,
+                        enum zone_stat_item item)
+{
+        atomic_long_dec(&page_zone(page)->vm_stat[item]);
+        atomic_long_dec(&vm_stat[item]);
+}
+
+/*
+ * We only use atomic operations to update counters. So there is no need to
+ * disable interrupts.
+ */
+#define inc_zone_page_state __inc_zone_page_state
+#define dec_zone_page_state __dec_zone_page_state
+#define mod_zone_page_state __mod_zone_page_state
+
+static inline void refresh_cpu_vm_stats(int cpu) { }
+static inline void refresh_vm_stats(void) { }
+#endif
+
+#endif /* _LINUX_VMSTAT_H */
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 795f81f9ec7f..5ba72d95280c 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -53,10 +53,16 @@ struct unix_address {
 struct unix_skb_parms {
         struct ucred            creds;          /* Skb credentials      */
         struct scm_fp_list      *fp;            /* Passed files         */
+#ifdef CONFIG_SECURITY_NETWORK
+        char                    *secdata;       /* Security context     */
+        u32                     seclen;         /* Security length      */
+#endif
 };
 
 #define UNIXCB(skb)     (*(struct unix_skb_parms*)&((skb)->cb))
 #define UNIXCREDS(skb)  (&UNIXCB((skb)).creds)
+#define UNIXSECDATA(skb)        (&UNIXCB((skb)).secdata)
+#define UNIXSECLEN(skb)         (&UNIXCB((skb)).seclen)
 
 #define unix_state_rlock(s)     spin_lock(&unix_sk(s)->lock)
 #define unix_state_runlock(s)   spin_unlock(&unix_sk(s)->lock)
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 75b5b9333fc7..1925c65e617b 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -169,17 +169,23 @@ psched_tod_diff(int delta_sec, int bound)
 
 #define PSCHED_TADD2(tv, delta, tv_res) \
 ({ \
-           int __delta = (tv).tv_usec + (delta); \
-           (tv_res).tv_sec = (tv).tv_sec; \
-           if (__delta > USEC_PER_SEC) { (tv_res).tv_sec++; __delta -= USEC_PER_SEC; } \
+           int __delta = (delta); \
+           (tv_res) = (tv); \
+           while(__delta >= USEC_PER_SEC){ \
+                 (tv_res).tv_sec++; \
+                 __delta -= USEC_PER_SEC; \
+           } \
            (tv_res).tv_usec = __delta; \
 })
 
 #define PSCHED_TADD(tv, delta) \
 ({ \
-           (tv).tv_usec += (delta); \
-           if ((tv).tv_usec > USEC_PER_SEC) { (tv).tv_sec++; \
-                 (tv).tv_usec -= USEC_PER_SEC; } \
+           int __delta = (delta); \
+           while(__delta >= USEC_PER_SEC){ \
+                 (tv).tv_sec++; \
+                 __delta -= USEC_PER_SEC; \
+           } \
+           (tv).tv_usec = __delta; \
 })
 
 /* Set/check that time is in the "past perfect";
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 3b6dc15c68a5..40b6b9c9973f 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -36,7 +36,8 @@
 struct net_protocol {
         int                     (*handler)(struct sk_buff *skb);
         void                    (*err_handler)(struct sk_buff *skb, u32 info);
-        struct sk_buff         *(*gso_segment)(struct sk_buff *skb, int sg);
+        struct sk_buff         *(*gso_segment)(struct sk_buff *skb,
+                                               int features);
         int                     no_policy;
 };
 
diff --git a/include/net/scm.h b/include/net/scm.h
index 540619cb7160..02daa097cdcd 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -19,6 +19,10 @@ struct scm_cookie
 {
         struct ucred            creds;          /* Skb credentials      */
         struct scm_fp_list      *fp;            /* Passed files         */
+#ifdef CONFIG_SECURITY_NETWORK
+        char                    *secdata;       /* Security context     */
+        u32                     seclen;         /* Security length      */
+#endif
         unsigned long           seq;            /* Connection seqno     */
 };
 
@@ -48,6 +52,17 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg,
         return __scm_send(sock, msg, scm);
 }
 
+#ifdef CONFIG_SECURITY_NETWORK
+static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm)
+{
+        if (test_bit(SOCK_PASSSEC, &sock->flags) && scm->secdata != NULL)
+                put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, scm->seclen, scm->secdata);
+}
+#else
+static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm)
+{ }
+#endif /* CONFIG_SECURITY_NETWORK */
+
 static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg,
                                 struct scm_cookie *scm, int flags)
 {
@@ -62,6 +77,8 @@ static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg,
         if (test_bit(SOCK_PASSCRED, &sock->flags))
                 put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(scm->creds), &scm->creds);
 
+        scm_passec(sock, msg, scm);
+
         if (!scm->fp)
                 return;
         
diff --git a/include/net/sock.h b/include/net/sock.h
index 2d8d6adf1616..7136bae48c2f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -383,7 +383,6 @@ enum sock_flags {
         SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
         SOCK_DBG, /* %SO_DEBUG setting */
         SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
-        SOCK_NO_LARGESEND, /* whether to sent large segments or not */
         SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
         SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
 };
@@ -1033,7 +1032,7 @@ static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
         if (sk->sk_route_caps & NETIF_F_GSO)
                 sk->sk_route_caps |= NETIF_F_TSO;
         if (sk->sk_route_caps & NETIF_F_TSO) {
-                if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len)
+                if (dst->header_len)
                         sk->sk_route_caps &= ~NETIF_F_TSO;
                 else 
                         sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ca3d38dfc00b..624921e76332 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1086,7 +1086,7 @@ extern struct request_sock_ops tcp_request_sock_ops;
 
 extern int tcp_v4_destroy_sock(struct sock *sk);
 
-extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg);
+extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
 
 #ifdef CONFIG_PROC_FS
 extern int  tcp4_proc_init(void);
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h
index c6b84397448d..7bb366f70934 100644
--- a/include/net/tcp_ecn.h
+++ b/include/net/tcp_ecn.h
@@ -31,10 +31,9 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct tcp_sock *tp,
                                     struct sk_buff *skb)
 {
         tp->ecn_flags = 0;
-        if (sysctl_tcp_ecn && !(sk->sk_route_caps & NETIF_F_TSO)) {
+        if (sysctl_tcp_ecn) {
                 TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE|TCPCB_FLAG_CWR;
                 tp->ecn_flags = TCP_ECN_OK;
-                sock_set_flag(sk, SOCK_NO_LARGESEND);
         }
 }
 
@@ -56,6 +55,9 @@ static inline void TCP_ECN_send(struct sock *sk, struct tcp_sock *tp,
                         if (tp->ecn_flags&TCP_ECN_QUEUE_CWR) {
                                 tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
                                 skb->h.th->cwr = 1;
+                                if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+                                        skb_shinfo(skb)->gso_type |=
+                                                SKB_GSO_TCPV4_ECN;
                         }
                 } else {
                         /* ACK or retransmitted segment: clear ECT|CE */
diff --git a/init/Kconfig b/init/Kconfig
index f70f2fd273c2..a5b073a103e7 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -54,8 +54,8 @@ config LOCK_KERNEL
 
 config INIT_ENV_ARG_LIMIT
         int
-        default 32 if !USERMODE
-        default 128 if USERMODE
+        default 32 if !UML
+        default 128 if UML
         help
           Maximum of each of the number of arguments and environment
           variables passed to init from the kernel command line.
@@ -379,6 +379,15 @@ config SLAB
           SLOB is more space efficient but does not scale well and is
           more susceptible to fragmentation.
 
+config VM_EVENT_COUNTERS
+        default y
+        bool "Enable VM event counters for /proc/vmstat" if EMBEDDED
+        help
+          VM event counters are only needed to for event counts to be
+          shown. They have no function for the kernel itself. This
+          option allows the disabling of the VM event counters.
+          /proc/vmstat will only show page counts.
+
 endmenu         # General setup
 
 config TINY_SHMEM
diff --git a/init/main.c b/init/main.c
index bce0eb7f4f8f..ae04eb78a93a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -446,10 +446,17 @@ static void __init boot_cpu_init(void)
         cpu_set(cpu, cpu_possible_map);
 }
 
+void __init __attribute__((weak)) smp_setup_processor_id(void)
+{
+}
+
 asmlinkage void __init start_kernel(void)
 {
         char * command_line;
         extern struct kernel_param __start___param[], __stop___param[];
+
+        smp_setup_processor_id();
+
 /*
  * Interrupts are still disabled. Do necessary setups, then
  * enable them
diff --git a/kernel/audit.c b/kernel/audit.c
index 82443fb433ef..d417ca1db79b 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -445,7 +445,7 @@ void audit_send_reply(int pid, int seq, int type, int done, int multi,
  * Check for appropriate CAP_AUDIT_ capabilities on incoming audit
  * control messages.
  */
-static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type)
+static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 {
         int err = 0;
 
@@ -459,13 +459,13 @@ static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type)
         case AUDIT_DEL:
         case AUDIT_DEL_RULE:
         case AUDIT_SIGNAL_INFO:
-                if (!cap_raised(eff_cap, CAP_AUDIT_CONTROL))
+                if (security_netlink_recv(skb, CAP_AUDIT_CONTROL))
                         err = -EPERM;
                 break;
         case AUDIT_USER:
         case AUDIT_FIRST_USER_MSG...AUDIT_LAST_USER_MSG:
         case AUDIT_FIRST_USER_MSG2...AUDIT_LAST_USER_MSG2:
-                if (!cap_raised(eff_cap, CAP_AUDIT_WRITE))
+                if (security_netlink_recv(skb, CAP_AUDIT_WRITE))
                         err = -EPERM;
                 break;
         default:  /* bad msg */
@@ -488,7 +488,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
         char                    *ctx;
         u32                     len;
 
-        err = audit_netlink_ok(NETLINK_CB(skb).eff_cap, msg_type);
+        err = audit_netlink_ok(skb, msg_type);
         if (err)
                 return err;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 2629c1711fd6..d5e37072ea54 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4386,7 +4386,16 @@ asmlinkage long sys_sched_yield(void)
         return 0;
 }
 
-static inline void __cond_resched(void)
+static inline int __resched_legal(void)
+{
+        if (unlikely(preempt_count()))
+                return 0;
+        if (unlikely(system_state != SYSTEM_RUNNING))
+                return 0;
+        return 1;
+}
+
+static void __cond_resched(void)
 {
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
         __might_sleep(__FILE__, __LINE__);
@@ -4396,10 +4405,6 @@ static inline void __cond_resched(void)
          * PREEMPT_ACTIVE, which could trigger a second
          * cond_resched() call.
          */
-        if (unlikely(preempt_count()))
-                return;
-        if (unlikely(system_state != SYSTEM_RUNNING))
-                return;
         do {
                 add_preempt_count(PREEMPT_ACTIVE);
                 schedule();
@@ -4409,13 +4414,12 @@ static inline void __cond_resched(void)
 
 int __sched cond_resched(void)
 {
-        if (need_resched()) {
+        if (need_resched() && __resched_legal()) {
                 __cond_resched();
                 return 1;
         }
         return 0;
 }
-
 EXPORT_SYMBOL(cond_resched);
 
 /*
@@ -4436,7 +4440,7 @@ int cond_resched_lock(spinlock_t *lock)
                 ret = 1;
                 spin_lock(lock);
         }
-        if (need_resched()) {
+        if (need_resched() && __resched_legal()) {
                 _raw_spin_unlock(lock);
                 preempt_enable_no_resched();
                 __cond_resched();
@@ -4445,14 +4449,13 @@ int cond_resched_lock(spinlock_t *lock)
         }
         return ret;
 }
-
 EXPORT_SYMBOL(cond_resched_lock);
 
 int __sched cond_resched_softirq(void)
 {
         BUG_ON(!in_softirq());
 
-        if (need_resched()) {
+        if (need_resched() && __resched_legal()) {
                 __local_bh_enable();
                 __cond_resched();
                 local_bh_disable();
@@ -4460,10 +4463,8 @@ int __sched cond_resched_softirq(void)
         }
         return 0;
 }
-
 EXPORT_SYMBOL(cond_resched_softirq);
 
-
 /**
  * yield - yield the current processor to other threads.
  *
diff --git a/kernel/signal.c b/kernel/signal.c
index 52adf53929f6..477d11adf3d1 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -584,7 +584,7 @@ static int check_kill_permission(int sig, struct siginfo *info,
             && !capable(CAP_KILL))
                 return error;
 
-        error = security_task_kill(t, info, sig);
+        error = security_task_kill(t, info, sig, 0);
         if (!error)
                 audit_signal_info(sig, t); /* Let audit system see the signal */
         return error;
@@ -1107,7 +1107,7 @@ kill_proc_info(int sig, struct siginfo *info, pid_t pid)
 
 /* like kill_proc_info(), but doesn't use uid/euid of "current" */
 int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
-                      uid_t uid, uid_t euid)
+                      uid_t uid, uid_t euid, u32 secid)
 {
         int ret = -EINVAL;
         struct task_struct *p;
@@ -1127,6 +1127,9 @@ int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
                 ret = -EPERM;
                 goto out_unlock;
         }
+        ret = security_task_kill(p, info, sig, secid);
+        if (ret)
+                goto out_unlock;
         if (sig && p->sighand) {
                 unsigned long flags;
                 spin_lock_irqsave(&p->sighand->siglock, flags);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 93a2c5398648..ee0db45e2438 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -933,15 +933,6 @@ static ctl_table vm_table[] = {
                 .strategy       = &sysctl_intvec,
                 .extra1         = &zero,
         },
-        {
-                .ctl_name       = VM_ZONE_RECLAIM_INTERVAL,
-                .procname       = "zone_reclaim_interval",
-                .data           = &zone_reclaim_interval,
-                .maxlen         = sizeof(zone_reclaim_interval),
-                .mode           = 0644,
-                .proc_handler   = &proc_dointvec_jiffies,
-                .strategy       = &sysctl_jiffies,
-        },
 #endif
 #ifdef CONFIG_X86_32
         {
diff --git a/mm/Makefile b/mm/Makefile
index 0b8f73f2ed16..9dd824c11eeb 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -10,7 +10,7 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 obj-y                   := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
                            page_alloc.o page-writeback.o pdflush.o \
                            readahead.o swap.o truncate.o vmscan.o \
-                           prio_tree.o util.o mmzone.o $(mmu-y)
+                           prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
 
 obj-$(CONFIG_SWAP)      += page_io.o swap_state.o swapfile.o thrash.o
 obj-$(CONFIG_HUGETLBFS) += hugetlb.o
diff --git a/mm/filemap.c b/mm/filemap.c
index 648f2c0c8e18..796a5471b495 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -120,7 +120,7 @@ void __remove_from_page_cache(struct page *page)
         radix_tree_delete(&mapping->page_tree, page->index);
         page->mapping = NULL;
         mapping->nrpages--;
-        pagecache_acct(-1);
+        __dec_zone_page_state(page, NR_FILE_PAGES);
 }
 
 void remove_from_page_cache(struct page *page)
@@ -449,7 +449,7 @@ int add_to_page_cache(struct page *page, struct address_space *mapping,
                         page->mapping = mapping;
                         page->index = offset;
                         mapping->nrpages++;
-                        pagecache_acct(1);
+                        __inc_zone_page_state(page, NR_FILE_PAGES);
                 }
                 write_unlock_irq(&mapping->tree_lock);
                 radix_tree_preload_end();
@@ -1416,7 +1416,7 @@ retry_find:
                  */
                 if (!did_readaround) {
                         majmin = VM_FAULT_MAJOR;
-                        inc_page_state(pgmajfault);
+                        count_vm_event(PGMAJFAULT);
                 }
                 did_readaround = 1;
                 ra_pages = max_sane_readahead(file->f_ra.ra_pages);
@@ -1487,7 +1487,7 @@ no_cached_page:
 page_not_uptodate:
         if (!did_readaround) {
                 majmin = VM_FAULT_MAJOR;
-                inc_page_state(pgmajfault);
+                count_vm_event(PGMAJFAULT);
         }
         lock_page(page);
 
diff --git a/mm/highmem.c b/mm/highmem.c
index 9b274fdf9d08..9b2a5403c447 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -315,8 +315,8 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
                 if (bvec->bv_page == org_vec->bv_page)
                         continue;
 
-                mempool_free(bvec->bv_page, pool);      
-                dec_page_state(nr_bounce);
+                dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
+                mempool_free(bvec->bv_page, pool);
         }
 
         bio_endio(bio_orig, bio_orig->bi_size, err);
@@ -397,7 +397,7 @@ static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
                 to->bv_page = mempool_alloc(pool, q->bounce_gfp);
                 to->bv_len = from->bv_len;
                 to->bv_offset = from->bv_offset;
-                inc_page_state(nr_bounce);
+                inc_zone_page_state(to->bv_page, NR_BOUNCE);
 
                 if (rw == WRITE) {
                         char *vto, *vfrom;
diff --git a/mm/memory.c b/mm/memory.c
index 247b5c312b9b..7e2a4b1580e3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -126,7 +126,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
         pmd_clear(pmd);
         pte_lock_deinit(page);
         pte_free_tlb(tlb, page);
-        dec_page_state(nr_page_table_pages);
+        dec_zone_page_state(page, NR_PAGETABLE);
         tlb->mm->nr_ptes--;
 }
 
@@ -311,7 +311,7 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
                 pte_free(new);
         } else {
                 mm->nr_ptes++;
-                inc_page_state(nr_page_table_pages);
+                inc_zone_page_state(new, NR_PAGETABLE);
                 pmd_populate(mm, pmd, new);
         }
         spin_unlock(&mm->page_table_lock);
@@ -1951,7 +1951,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
                 /* Had to read the page from swap area: Major fault */
                 ret = VM_FAULT_MAJOR;
-                inc_page_state(pgmajfault);
+                count_vm_event(PGMAJFAULT);
                 grab_swap_token();
         }
 
@@ -2324,7 +2324,7 @@ int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
         __set_current_state(TASK_RUNNING);
 
-        inc_page_state(pgfault);
+        count_vm_event(PGFAULT);
 
         if (unlikely(is_vm_hugetlb_page(vma)))
                 return hugetlb_fault(mm, vma, address, write_access);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 6b9740bbf4c0..e07e27e846a2 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1209,10 +1209,8 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 
         zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
         page = __alloc_pages(gfp, order, zl);
-        if (page && page_zone(page) == zl->zones[0]) {
-                zone_pcp(zl->zones[0],get_cpu())->interleave_hit++;
-                put_cpu();
-        }
+        if (page && page_zone(page) == zl->zones[0])
+                inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
         return page;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 6446c6134b04..c1868ecdbc5f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -96,7 +96,7 @@ int __vm_enough_memory(long pages, int cap_sys_admin)
         if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
                 unsigned long n;
 
-                free = get_page_cache_size();
+                free = global_page_state(NR_FILE_PAGES);
                 free += nr_swap_pages;
 
                 /*
diff --git a/mm/nommu.c b/mm/nommu.c
index 029fadac0fb5..5151c44a8257 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1122,7 +1122,7 @@ int __vm_enough_memory(long pages, int cap_sys_admin)
         if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
                 unsigned long n;
 
-                free = get_page_cache_size();
+                free = global_page_state(NR_FILE_PAGES);
                 free += nr_swap_pages;
 
                 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4ec7026c7bab..e630188ccc40 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -99,22 +99,6 @@ EXPORT_SYMBOL(laptop_mode);
 
 static void background_writeout(unsigned long _min_pages);
 
-struct writeback_state
-{
-        unsigned long nr_dirty;
-        unsigned long nr_unstable;
-        unsigned long nr_mapped;
-        unsigned long nr_writeback;
-};
-
-static void get_writeback_state(struct writeback_state *wbs)
-{
-        wbs->nr_dirty = read_page_state(nr_dirty);
-        wbs->nr_unstable = read_page_state(nr_unstable);
-        wbs->nr_mapped = read_page_state(nr_mapped);
-        wbs->nr_writeback = read_page_state(nr_writeback);
-}
-
 /*
  * Work out the current dirty-memory clamping and background writeout
  * thresholds.
@@ -133,8 +117,8 @@ static void get_writeback_state(struct writeback_state *wbs)
  * clamping level.
  */
 static void
-get_dirty_limits(struct writeback_state *wbs, long *pbackground, long *pdirty,
-                struct address_space *mapping)
+get_dirty_limits(long *pbackground, long *pdirty,
+                                        struct address_space *mapping)
 {
         int background_ratio;           /* Percentages */
         int dirty_ratio;
@@ -144,8 +128,6 @@ get_dirty_limits(struct writeback_state *wbs, long *pbackground, long *pdirty,
         unsigned long available_memory = total_pages;
         struct task_struct *tsk;
 
-        get_writeback_state(wbs);
-
 #ifdef CONFIG_HIGHMEM
         /*
          * If this mapping can only allocate from low memory,
@@ -156,7 +138,9 @@ get_dirty_limits(struct writeback_state *wbs, long *pbackground, long *pdirty,
 #endif
 
 
-        unmapped_ratio = 100 - (wbs->nr_mapped * 100) / total_pages;
+        unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
+                                global_page_state(NR_ANON_PAGES)) * 100) /
+                                        total_pages;
 
         dirty_ratio = vm_dirty_ratio;
         if (dirty_ratio > unmapped_ratio / 2)
@@ -189,7 +173,6 @@ get_dirty_limits(struct writeback_state *wbs, long *pbackground, long *pdirty,
  */
 static void balance_dirty_pages(struct address_space *mapping)
 {
-        struct writeback_state wbs;
         long nr_reclaimable;
         long background_thresh;
         long dirty_thresh;
@@ -207,11 +190,12 @@ static void balance_dirty_pages(struct address_space *mapping)
                         .range_cyclic   = 1,
                 };
 
-                get_dirty_limits(&wbs, &background_thresh,
-                                        &dirty_thresh, mapping);
-                nr_reclaimable = wbs.nr_dirty + wbs.nr_unstable;
-                if (nr_reclaimable + wbs.nr_writeback <= dirty_thresh)
-                        break;
+                get_dirty_limits(&background_thresh, &dirty_thresh, mapping);
+                nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
+                                        global_page_state(NR_UNSTABLE_NFS);
+                if (nr_reclaimable + global_page_state(NR_WRITEBACK) <=
+                        dirty_thresh)
+                                break;
 
                 if (!dirty_exceeded)
                         dirty_exceeded = 1;
@@ -224,11 +208,14 @@ static void balance_dirty_pages(struct address_space *mapping)
                  */
                 if (nr_reclaimable) {
                         writeback_inodes(&wbc);
-                        get_dirty_limits(&wbs, &background_thresh,
-                                        &dirty_thresh, mapping);
-                        nr_reclaimable = wbs.nr_dirty + wbs.nr_unstable;
-                        if (nr_reclaimable + wbs.nr_writeback <= dirty_thresh)
-                                break;
+                        get_dirty_limits(&background_thresh,
+                                                &dirty_thresh, mapping);
+                        nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
+                                        global_page_state(NR_UNSTABLE_NFS);
+                        if (nr_reclaimable +
+                                global_page_state(NR_WRITEBACK)
+                                        <= dirty_thresh)
+                                                break;
                         pages_written += write_chunk - wbc.nr_to_write;
                         if (pages_written >= write_chunk)
                                 break;          /* We've done our duty */
@@ -236,8 +223,9 @@ static void balance_dirty_pages(struct address_space *mapping)
                 blk_congestion_wait(WRITE, HZ/10);
         }
 
-        if (nr_reclaimable + wbs.nr_writeback <= dirty_thresh && dirty_exceeded)
-                dirty_exceeded = 0;
+        if (nr_reclaimable + global_page_state(NR_WRITEBACK)
+                <= dirty_thresh && dirty_exceeded)
+                        dirty_exceeded = 0;
 
         if (writeback_in_progress(bdi))
                 return;         /* pdflush is already working this queue */
@@ -299,12 +287,11 @@ EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
 void throttle_vm_writeout(void)
 {
-        struct writeback_state wbs;
         long background_thresh;
         long dirty_thresh;
 
         for ( ; ; ) {
-                get_dirty_limits(&wbs, &background_thresh, &dirty_thresh, NULL);
+                get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
 
                 /*
                  * Boost the allowable dirty threshold a bit for page
@@ -312,8 +299,9 @@ void throttle_vm_writeout(void)
                  */
                 dirty_thresh += dirty_thresh / 10;      /* wheeee... */
 
-                if (wbs.nr_unstable + wbs.nr_writeback <= dirty_thresh)
-                        break;
+                if (global_page_state(NR_UNSTABLE_NFS) +
+                        global_page_state(NR_WRITEBACK) <= dirty_thresh)
+                                break;
                 blk_congestion_wait(WRITE, HZ/10);
         }
 }
@@ -336,12 +324,12 @@ static void background_writeout(unsigned long _min_pages)
         };
 
         for ( ; ; ) {
-                struct writeback_state wbs;
                 long background_thresh;
                 long dirty_thresh;
 
-                get_dirty_limits(&wbs, &background_thresh, &dirty_thresh, NULL);
-                if (wbs.nr_dirty + wbs.nr_unstable < background_thresh
+                get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
+                if (global_page_state(NR_FILE_DIRTY) +
+                        global_page_state(NR_UNSTABLE_NFS) < background_thresh
                                 && min_pages <= 0)
                         break;
                 wbc.encountered_congestion = 0;
@@ -365,12 +353,9 @@ static void background_writeout(unsigned long _min_pages)
  */
 int wakeup_pdflush(long nr_pages)
 {
-        if (nr_pages == 0) {
-                struct writeback_state wbs;
-
-                get_writeback_state(&wbs);
-                nr_pages = wbs.nr_dirty + wbs.nr_unstable;
-        }
+        if (nr_pages == 0)
+                nr_pages = global_page_state(NR_FILE_DIRTY) +
+                                global_page_state(NR_UNSTABLE_NFS);
         return pdflush_operation(background_writeout, nr_pages);
 }
 
@@ -401,7 +386,6 @@ static void wb_kupdate(unsigned long arg)
         unsigned long start_jif;
         unsigned long next_jif;
         long nr_to_write;
-        struct writeback_state wbs;
         struct writeback_control wbc = {
                 .bdi            = NULL,
                 .sync_mode      = WB_SYNC_NONE,
@@ -414,11 +398,11 @@ static void wb_kupdate(unsigned long arg)
 
         sync_supers();
 
-        get_writeback_state(&wbs);
         oldest_jif = jiffies - dirty_expire_interval;
         start_jif = jiffies;
         next_jif = start_jif + dirty_writeback_interval;
-        nr_to_write = wbs.nr_dirty + wbs.nr_unstable +
+        nr_to_write = global_page_state(NR_FILE_DIRTY) +
+                        global_page_state(NR_UNSTABLE_NFS) +
                         (inodes_stat.nr_inodes - inodes_stat.nr_unused);
         while (nr_to_write > 0) {
                 wbc.encountered_congestion = 0;
@@ -640,7 +624,8 @@ int __set_page_dirty_nobuffers(struct page *page)
                         if (mapping2) { /* Race with truncate? */
                                 BUG_ON(mapping2 != mapping);
                                 if (mapping_cap_account_dirty(mapping))
-                                        inc_page_state(nr_dirty);
+                                        __inc_zone_page_state(page,
+                                                                NR_FILE_DIRTY);
                                 radix_tree_tag_set(&mapping->page_tree,
                                         page_index(page), PAGECACHE_TAG_DIRTY);
                         }
@@ -727,9 +712,9 @@ int test_clear_page_dirty(struct page *page)
                         radix_tree_tag_clear(&mapping->page_tree,
                                                 page_index(page),
                                                 PAGECACHE_TAG_DIRTY);
-                        write_unlock_irqrestore(&mapping->tree_lock, flags);
                         if (mapping_cap_account_dirty(mapping))
-                                dec_page_state(nr_dirty);
+                                __dec_zone_page_state(page, NR_FILE_DIRTY);
+                        write_unlock_irqrestore(&mapping->tree_lock, flags);
                         return 1;
                 }
                 write_unlock_irqrestore(&mapping->tree_lock, flags);
@@ -760,7 +745,7 @@ int clear_page_dirty_for_io(struct page *page)
         if (mapping) {
                 if (TestClearPageDirty(page)) {
                         if (mapping_cap_account_dirty(mapping))
-                                dec_page_state(nr_dirty);
+                                dec_zone_page_state(page, NR_FILE_DIRTY);
                         return 1;
                 }
                 return 0;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 084a2de7e52a..30b0b97ad023 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -456,7 +456,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 
         kernel_map_pages(page, 1 << order, 0);
         local_irq_save(flags);
-        __mod_page_state(pgfree, 1 << order);
+        __count_vm_events(PGFREE, 1 << order);
         free_one_page(page_zone(page), page, order);
         local_irq_restore(flags);
 }
@@ -709,27 +709,6 @@ void drain_local_pages(void)
 }
 #endif /* CONFIG_PM */
 
-static void zone_statistics(struct zonelist *zonelist, struct zone *z, int cpu)
-{
-#ifdef CONFIG_NUMA
-        pg_data_t *pg = z->zone_pgdat;
-        pg_data_t *orig = zonelist->zones[0]->zone_pgdat;
-        struct per_cpu_pageset *p;
-
-        p = zone_pcp(z, cpu);
-        if (pg == orig) {
-                p->numa_hit++;
-        } else {
-                p->numa_miss++;
-                zone_pcp(zonelist->zones[0], cpu)->numa_foreign++;
-        }
-        if (pg == NODE_DATA(numa_node_id()))
-                p->local_node++;
-        else
-                p->other_node++;
-#endif
-}
-
 /*
  * Free a 0-order page
  */
@@ -750,7 +729,7 @@ static void fastcall free_hot_cold_page(struct page *page, int cold)
 
         pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
         local_irq_save(flags);
-        __inc_page_state(pgfree);
+        __count_vm_event(PGFREE);
         list_add(&page->lru, &pcp->list);
         pcp->count++;
         if (pcp->count >= pcp->high) {
@@ -826,8 +805,8 @@ again:
                         goto failed;
         }
 
-        __mod_page_state_zone(zone, pgalloc, 1 << order);
-        zone_statistics(zonelist, zone, cpu);
+        __count_zone_vm_events(PGALLOC, zone, 1 << order);
+        zone_statistics(zonelist, zone);
         local_irq_restore(flags);
         put_cpu();
 
@@ -1231,141 +1210,6 @@ static void show_node(struct zone *zone)
 #define show_node(zone) do { } while (0)
 #endif
 
-/*
- * Accumulate the page_state information across all CPUs.
- * The result is unavoidably approximate - it can change
- * during and after execution of this function.
- */
-static DEFINE_PER_CPU(struct page_state, page_states) = {0};
-
-atomic_t nr_pagecache = ATOMIC_INIT(0);
-EXPORT_SYMBOL(nr_pagecache);
-#ifdef CONFIG_SMP
-DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
-#endif
-
-static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
-{
-        unsigned cpu;
-
-        memset(ret, 0, nr * sizeof(unsigned long));
-        cpus_and(*cpumask, *cpumask, cpu_online_map);
-
-        for_each_cpu_mask(cpu, *cpumask) {
-                unsigned long *in;
-                unsigned long *out;
-                unsigned off;
-                unsigned next_cpu;
-
-                in = (unsigned long *)&per_cpu(page_states, cpu);
-
-                next_cpu = next_cpu(cpu, *cpumask);
-                if (likely(next_cpu < NR_CPUS))
-                        prefetch(&per_cpu(page_states, next_cpu));
-
-                out = (unsigned long *)ret;
-                for (off = 0; off < nr; off++)
-                        *out++ += *in++;
-        }
-}
-
-void get_page_state_node(struct page_state *ret, int node)
-{
-        int nr;
-        cpumask_t mask = node_to_cpumask(node);
-
-        nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-        nr /= sizeof(unsigned long);
-
-        __get_page_state(ret, nr+1, &mask);
-}
-
-void get_page_state(struct page_state *ret)
-{
-        int nr;
-        cpumask_t mask = CPU_MASK_ALL;
-
-        nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-        nr /= sizeof(unsigned long);
-
-        __get_page_state(ret, nr + 1, &mask);
-}
-
-void get_full_page_state(struct page_state *ret)
-{
-        cpumask_t mask = CPU_MASK_ALL;
-
-        __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
-}
-
-unsigned long read_page_state_offset(unsigned long offset)
-{
-        unsigned long ret = 0;
-        int cpu;
-
-        for_each_online_cpu(cpu) {
-                unsigned long in;
-
-                in = (unsigned long)&per_cpu(page_states, cpu) + offset;
-                ret += *((unsigned long *)in);
-        }
-        return ret;
-}
-
-void __mod_page_state_offset(unsigned long offset, unsigned long delta)
-{
-        void *ptr;
-
-        ptr = &__get_cpu_var(page_states);
-        *(unsigned long *)(ptr + offset) += delta;
-}
-EXPORT_SYMBOL(__mod_page_state_offset);
-
-void mod_page_state_offset(unsigned long offset, unsigned long delta)
-{
-        unsigned long flags;
-        void *ptr;
-
-        local_irq_save(flags);
-        ptr = &__get_cpu_var(page_states);
-        *(unsigned long *)(ptr + offset) += delta;
-        local_irq_restore(flags);
-}
-EXPORT_SYMBOL(mod_page_state_offset);
-
-void __get_zone_counts(unsigned long *active, unsigned long *inactive,
-                        unsigned long *free, struct pglist_data *pgdat)
-{
-        struct zone *zones = pgdat->node_zones;
-        int i;
-
-        *active = 0;
-        *inactive = 0;
-        *free = 0;
-        for (i = 0; i < MAX_NR_ZONES; i++) {
-                *active += zones[i].nr_active;
-                *inactive += zones[i].nr_inactive;
-                *free += zones[i].free_pages;
-        }
-}
-
-void get_zone_counts(unsigned long *active,
-                unsigned long *inactive, unsigned long *free)
-{
-        struct pglist_data *pgdat;
-
-        *active = 0;
-        *inactive = 0;
-        *free = 0;
-        for_each_online_pgdat(pgdat) {
-                unsigned long l, m, n;
-                __get_zone_counts(&l, &m, &n, pgdat);
-                *active += l;
-                *inactive += m;
-                *free += n;
-        }
-}
-
 void si_meminfo(struct sysinfo *val)
 {
         val->totalram = totalram_pages;
@@ -1406,7 +1250,6 @@ void si_meminfo_node(struct sysinfo *val, int nid)
  */
 void show_free_areas(void)
 {
-        struct page_state ps;
         int cpu, temperature;
         unsigned long active;
         unsigned long inactive;
@@ -1438,7 +1281,6 @@ void show_free_areas(void)
                 }
         }
 
-        get_page_state(&ps);
         get_zone_counts(&active, &inactive, &free);
 
         printk("Free pages: %11ukB (%ukB HighMem)\n",
@@ -1449,13 +1291,13 @@ void show_free_areas(void)
                 "unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
                 active,
                 inactive,
-                ps.nr_dirty,
-                ps.nr_writeback,
-                ps.nr_unstable,
+                global_page_state(NR_FILE_DIRTY),
+                global_page_state(NR_WRITEBACK),
+                global_page_state(NR_UNSTABLE_NFS),
                 nr_free_pages(),
-                ps.nr_slab,
-                ps.nr_mapped,
-                ps.nr_page_table_pages);
+                global_page_state(NR_SLAB),
+                global_page_state(NR_FILE_MAPPED),
+                global_page_state(NR_PAGETABLE));
 
         for_each_zone(zone) {
                 int i;
@@ -2180,6 +2022,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
                 zone->nr_scan_inactive = 0;
                 zone->nr_active = 0;
                 zone->nr_inactive = 0;
+                zap_zone_vm_stats(zone);
                 atomic_set(&zone->reclaim_in_progress, 0);
                 if (!size)
                         continue;
@@ -2253,307 +2096,18 @@ void __init free_area_init(unsigned long *zones_size)
                         __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
 }
 
-#ifdef CONFIG_PROC_FS
-
-#include <linux/seq_file.h>
-
-static void *frag_start(struct seq_file *m, loff_t *pos)
-{
-        pg_data_t *pgdat;
-        loff_t node = *pos;
-        for (pgdat = first_online_pgdat();
-             pgdat && node;
-             pgdat = next_online_pgdat(pgdat))
-                --node;
-
-        return pgdat;
-}
-
-static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
-{
-        pg_data_t *pgdat = (pg_data_t *)arg;
-
-        (*pos)++;
-        return next_online_pgdat(pgdat);
-}
-
-static void frag_stop(struct seq_file *m, void *arg)
-{
-}
-
-/* 
- * This walks the free areas for each zone.
- */
-static int frag_show(struct seq_file *m, void *arg)
-{
-        pg_data_t *pgdat = (pg_data_t *)arg;
-        struct zone *zone;
-        struct zone *node_zones = pgdat->node_zones;
-        unsigned long flags;
-        int order;
-
-        for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
-                if (!populated_zone(zone))
-                        continue;
-
-                spin_lock_irqsave(&zone->lock, flags);
-                seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
-                for (order = 0; order < MAX_ORDER; ++order)
-                        seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
-                spin_unlock_irqrestore(&zone->lock, flags);
-                seq_putc(m, '\n');
-        }
-        return 0;
-}
-
-struct seq_operations fragmentation_op = {
-        .start  = frag_start,
-        .next   = frag_next,
-        .stop   = frag_stop,
-        .show   = frag_show,
-};
-
-/*
- * Output information about zones in @pgdat.
- */
-static int zoneinfo_show(struct seq_file *m, void *arg)
-{
-        pg_data_t *pgdat = arg;
-        struct zone *zone;
-        struct zone *node_zones = pgdat->node_zones;
-        unsigned long flags;
-
-        for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
-                int i;
-
-                if (!populated_zone(zone))
-                        continue;
-
-                spin_lock_irqsave(&zone->lock, flags);
-                seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
-                seq_printf(m,
-                           "\n  pages free     %lu"
-                           "\n        min      %lu"
-                           "\n        low      %lu"
-                           "\n        high     %lu"
-                           "\n        active   %lu"
-                           "\n        inactive %lu"
-                           "\n        scanned  %lu (a: %lu i: %lu)"
-                           "\n        spanned  %lu"
-                           "\n        present  %lu",
-                           zone->free_pages,
-                           zone->pages_min,
-                           zone->pages_low,
-                           zone->pages_high,
-                           zone->nr_active,
-                           zone->nr_inactive,
-                           zone->pages_scanned,
-                           zone->nr_scan_active, zone->nr_scan_inactive,
-                           zone->spanned_pages,
-                           zone->present_pages);
-                seq_printf(m,
-                           "\n        protection: (%lu",
-                           zone->lowmem_reserve[0]);
-                for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
-                        seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
-                seq_printf(m,
-                           ")"
-                           "\n  pagesets");
-                for_each_online_cpu(i) {
-                        struct per_cpu_pageset *pageset;
-                        int j;
-
-                        pageset = zone_pcp(zone, i);
-                        for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
-                                if (pageset->pcp[j].count)
-                                        break;
-                        }
-                        if (j == ARRAY_SIZE(pageset->pcp))
-                                continue;
-                        for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
-                                seq_printf(m,
-                                           "\n    cpu: %i pcp: %i"
-                                           "\n              count: %i"
-                                           "\n              high:  %i"
-                                           "\n              batch: %i",
-                                           i, j,
-                                           pageset->pcp[j].count,
-                                           pageset->pcp[j].high,
-                                           pageset->pcp[j].batch);
-                        }
-#ifdef CONFIG_NUMA
-                        seq_printf(m,
-                                   "\n            numa_hit:       %lu"
-                                   "\n            numa_miss:      %lu"
-                                   "\n            numa_foreign:   %lu"
-                                   "\n            interleave_hit: %lu"
-                                   "\n            local_node:     %lu"
-                                   "\n            other_node:     %lu",
-                                   pageset->numa_hit,
-                                   pageset->numa_miss,
-                                   pageset->numa_foreign,
-                                   pageset->interleave_hit,
-                                   pageset->local_node,
-                                   pageset->other_node);
-#endif
-                }
-                seq_printf(m,
-                           "\n  all_unreclaimable: %u"
-                           "\n  prev_priority:     %i"
-                           "\n  temp_priority:     %i"
-                           "\n  start_pfn:         %lu",
-                           zone->all_unreclaimable,
-                           zone->prev_priority,
-                           zone->temp_priority,
-                           zone->zone_start_pfn);
-                spin_unlock_irqrestore(&zone->lock, flags);
-                seq_putc(m, '\n');
-        }
-        return 0;
-}
-
-struct seq_operations zoneinfo_op = {
-        .start  = frag_start, /* iterate over all zones. The same as in
-                               * fragmentation. */
-        .next   = frag_next,
-        .stop   = frag_stop,
-        .show   = zoneinfo_show,
-};
-
-static char *vmstat_text[] = {
-        "nr_dirty",
-        "nr_writeback",
-        "nr_unstable",
-        "nr_page_table_pages",
-        "nr_mapped",
-        "nr_slab",
-
-        "pgpgin",
-        "pgpgout",
-        "pswpin",
-        "pswpout",
-
-        "pgalloc_high",
-        "pgalloc_normal",
-        "pgalloc_dma32",
-        "pgalloc_dma",
-
-        "pgfree",
-        "pgactivate",
-        "pgdeactivate",
-
-        "pgfault",
-        "pgmajfault",
-
-        "pgrefill_high",
-        "pgrefill_normal",
-        "pgrefill_dma32",
-        "pgrefill_dma",
-
-        "pgsteal_high",
-        "pgsteal_normal",
-        "pgsteal_dma32",
-        "pgsteal_dma",
-
-        "pgscan_kswapd_high",
-        "pgscan_kswapd_normal",
-        "pgscan_kswapd_dma32",
-        "pgscan_kswapd_dma",
-
-        "pgscan_direct_high",
-        "pgscan_direct_normal",
-        "pgscan_direct_dma32",
-        "pgscan_direct_dma",
-
-        "pginodesteal",
-        "slabs_scanned",
-        "kswapd_steal",
-        "kswapd_inodesteal",
-        "pageoutrun",
-        "allocstall",
-
-        "pgrotated",
-        "nr_bounce",
-};
-
-static void *vmstat_start(struct seq_file *m, loff_t *pos)
-{
-        struct page_state *ps;
-
-        if (*pos >= ARRAY_SIZE(vmstat_text))
-                return NULL;
-
-        ps = kmalloc(sizeof(*ps), GFP_KERNEL);
-        m->private = ps;
-        if (!ps)
-                return ERR_PTR(-ENOMEM);
-        get_full_page_state(ps);
-        ps->pgpgin /= 2;                /* sectors -> kbytes */
-        ps->pgpgout /= 2;
-        return (unsigned long *)ps + *pos;
-}
-
-static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
-{
-        (*pos)++;
-        if (*pos >= ARRAY_SIZE(vmstat_text))
-                return NULL;
-        return (unsigned long *)m->private + *pos;
-}
-
-static int vmstat_show(struct seq_file *m, void *arg)
-{
-        unsigned long *l = arg;
-        unsigned long off = l - (unsigned long *)m->private;
-
-        seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
-        return 0;
-}
-
-static void vmstat_stop(struct seq_file *m, void *arg)
-{
-        kfree(m->private);
-        m->private = NULL;
-}
-
-struct seq_operations vmstat_op = {
-        .start  = vmstat_start,
-        .next   = vmstat_next,
-        .stop   = vmstat_stop,
-        .show   = vmstat_show,
-};
-
-#endif /* CONFIG_PROC_FS */
-
 #ifdef CONFIG_HOTPLUG_CPU
 static int page_alloc_cpu_notify(struct notifier_block *self,
                                  unsigned long action, void *hcpu)
 {
         int cpu = (unsigned long)hcpu;
-        long *count;
-        unsigned long *src, *dest;
 
         if (action == CPU_DEAD) {
-                int i;
-
-                /* Drain local pagecache count. */
-                count = &per_cpu(nr_pagecache_local, cpu);
-                atomic_add(*count, &nr_pagecache);
-                *count = 0;
                 local_irq_disable();
                 __drain_pages(cpu);
-
-                /* Add dead cpu's page_states to our own. */
-                dest = (unsigned long *)&__get_cpu_var(page_states);
-                src = (unsigned long *)&per_cpu(page_states, cpu);
-
-                for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long);
-                                i++) {
-                        dest[i] += src[i];
-                        src[i] = 0;
-                }
-
+                vm_events_fold_cpu(cpu);
                 local_irq_enable();
+                refresh_cpu_vm_stats(cpu);
         }
         return NOTIFY_OK;
 }
diff --git a/mm/page_io.c b/mm/page_io.c
index bb2b0d53889c..88029948d00a 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -101,7 +101,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
         }
         if (wbc->sync_mode == WB_SYNC_ALL)
                 rw |= (1 << BIO_RW_SYNC);
-        inc_page_state(pswpout);
+        count_vm_event(PSWPOUT);
         set_page_writeback(page);
         unlock_page(page);
         submit_bio(rw, bio);
@@ -123,7 +123,7 @@ int swap_readpage(struct file *file, struct page *page)
                 ret = -ENOMEM;
                 goto out;
         }
-        inc_page_state(pswpin);
+        count_vm_event(PSWPIN);
         submit_bio(READ, bio);
 out:
         return ret;
diff --git a/mm/rmap.c b/mm/rmap.c
index e76909e880ca..40158b59729e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -455,7 +455,7 @@ static void __page_set_anon_rmap(struct page *page,
          * nr_mapped state can be updated without turning off
          * interrupts because it is not modified via interrupt.
          */
-        __inc_page_state(nr_mapped);
+        __inc_zone_page_state(page, NR_ANON_PAGES);
 }
 
 /**
@@ -499,7 +499,7 @@ void page_add_new_anon_rmap(struct page *page,
 void page_add_file_rmap(struct page *page)
 {
         if (atomic_inc_and_test(&page->_mapcount))
-                __inc_page_state(nr_mapped);
+                __inc_zone_page_state(page, NR_FILE_MAPPED);
 }
 
 /**
@@ -531,7 +531,8 @@ void page_remove_rmap(struct page *page)
                  */
                 if (page_test_and_clear_dirty(page))
                         set_page_dirty(page);
-                __dec_page_state(nr_mapped);
+                __dec_zone_page_state(page,
+                                PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
         }
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index b14ff817d162..a9c09e0ba709 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1045,12 +1045,12 @@ repeat:
                 swappage = lookup_swap_cache(swap);
                 if (!swappage) {
                         shmem_swp_unmap(entry);
-                        spin_unlock(&info->lock);
                         /* here we actually do the io */
                         if (type && *type == VM_FAULT_MINOR) {
-                                inc_page_state(pgmajfault);
+                                __count_vm_event(PGMAJFAULT);
                                 *type = VM_FAULT_MAJOR;
                         }
+                        spin_unlock(&info->lock);
                         swappage = shmem_swapin(info, swap, idx);
                         if (!swappage) {
                                 spin_lock(&info->lock);
diff --git a/mm/slab.c b/mm/slab.c
index 233e39d14caf..3936af344542 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -309,6 +309,13 @@ struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
 #define SIZE_AC 1
 #define SIZE_L3 (1 + MAX_NUMNODES)
 
+static int drain_freelist(struct kmem_cache *cache,
+                        struct kmem_list3 *l3, int tofree);
+static void free_block(struct kmem_cache *cachep, void **objpp, int len,
+                        int node);
+static void enable_cpucache(struct kmem_cache *cachep);
+static void cache_reap(void *unused);
+
 /*
  * This function must be completely optimized away if a constant is passed to
  * it.  Mostly the same as what is in linux/slab.h except it returns an index.
@@ -456,7 +463,7 @@ struct kmem_cache {
 #define STATS_DEC_ACTIVE(x)     ((x)->num_active--)
 #define STATS_INC_ALLOCED(x)    ((x)->num_allocations++)
 #define STATS_INC_GROWN(x)      ((x)->grown++)
-#define STATS_INC_REAPED(x)     ((x)->reaped++)
+#define STATS_ADD_REAPED(x,y)   ((x)->reaped += (y))
 #define STATS_SET_HIGH(x)                                               \
         do {                                                            \
                 if ((x)->num_active > (x)->high_mark)                   \
@@ -480,7 +487,7 @@ struct kmem_cache {
 #define STATS_DEC_ACTIVE(x)     do { } while (0)
 #define STATS_INC_ALLOCED(x)    do { } while (0)
 #define STATS_INC_GROWN(x)      do { } while (0)
-#define STATS_INC_REAPED(x)     do { } while (0)
+#define STATS_ADD_REAPED(x,y)   do { } while (0)
 #define STATS_SET_HIGH(x)       do { } while (0)
 #define STATS_INC_ERR(x)        do { } while (0)
 #define STATS_INC_NODEALLOCS(x) do { } while (0)
@@ -700,12 +707,6 @@ int slab_is_available(void)
 
 static DEFINE_PER_CPU(struct work_struct, reap_work);
 
-static void free_block(struct kmem_cache *cachep, void **objpp, int len,
-                        int node);
-static void enable_cpucache(struct kmem_cache *cachep);
-static void cache_reap(void *unused);
-static int __node_shrink(struct kmem_cache *cachep, int node);
-
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
         return cachep->array[smp_processor_id()];
@@ -1241,10 +1242,7 @@ free_array_cache:
                         l3 = cachep->nodelists[node];
                         if (!l3)
                                 continue;
-                        spin_lock_irq(&l3->list_lock);
-                        /* free slabs belonging to this node */
-                        __node_shrink(cachep, node);
-                        spin_unlock_irq(&l3->list_lock);
+                        drain_freelist(cachep, l3, l3->free_objects);
                 }
                 mutex_unlock(&cache_chain_mutex);
                 break;
@@ -1507,7 +1505,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
         nr_pages = (1 << cachep->gfporder);
         if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
                 atomic_add(nr_pages, &slab_reclaim_pages);
-        add_page_state(nr_slab, nr_pages);
+        add_zone_page_state(page_zone(page), NR_SLAB, nr_pages);
         for (i = 0; i < nr_pages; i++)
                 __SetPageSlab(page + i);
         return page_address(page);
@@ -1522,12 +1520,12 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
         struct page *page = virt_to_page(addr);
         const unsigned long nr_freed = i;
 
+        sub_zone_page_state(page_zone(page), NR_SLAB, nr_freed);
         while (i--) {
                 BUG_ON(!PageSlab(page));
                 __ClearPageSlab(page);
                 page++;
         }
-        sub_page_state(nr_slab, nr_freed);
         if (current->reclaim_state)
                 current->reclaim_state->reclaimed_slab += nr_freed;
         free_pages((unsigned long)addr, cachep->gfporder);
@@ -2248,32 +2246,45 @@ static void drain_cpu_caches(struct kmem_cache *cachep)
         }
 }
 
-static int __node_shrink(struct kmem_cache *cachep, int node)
+/*
+ * Remove slabs from the list of free slabs.
+ * Specify the number of slabs to drain in tofree.
+ *
+ * Returns the actual number of slabs released.
+ */
+static int drain_freelist(struct kmem_cache *cache,
+                        struct kmem_list3 *l3, int tofree)
 {
+        struct list_head *p;
+        int nr_freed;
         struct slab *slabp;
-        struct kmem_list3 *l3 = cachep->nodelists[node];
-        int ret;
 
-        for (;;) {
-                struct list_head *p;
+        nr_freed = 0;
+        while (nr_freed < tofree && !list_empty(&l3->slabs_free)) {
 
+                spin_lock_irq(&l3->list_lock);
                 p = l3->slabs_free.prev;
-                if (p == &l3->slabs_free)
-                        break;
+                if (p == &l3->slabs_free) {
+                        spin_unlock_irq(&l3->list_lock);
+                        goto out;
+                }
 
-                slabp = list_entry(l3->slabs_free.prev, struct slab, list);
+                slabp = list_entry(p, struct slab, list);
 #if DEBUG
                 BUG_ON(slabp->inuse);
 #endif
                 list_del(&slabp->list);
-
-                l3->free_objects -= cachep->num;
+                /*
+                 * Safe to drop the lock. The slab is no longer linked
+                 * to the cache.
+                 */
+                l3->free_objects -= cache->num;
                 spin_unlock_irq(&l3->list_lock);
-                slab_destroy(cachep, slabp);
-                spin_lock_irq(&l3->list_lock);
+                slab_destroy(cache, slabp);
+                nr_freed++;
         }
-        ret = !list_empty(&l3->slabs_full) || !list_empty(&l3->slabs_partial);
-        return ret;
+out:
+        return nr_freed;
 }
 
 static int __cache_shrink(struct kmem_cache *cachep)
@@ -2286,11 +2297,13 @@ static int __cache_shrink(struct kmem_cache *cachep)
         check_irq_on();
         for_each_online_node(i) {
                 l3 = cachep->nodelists[i];
-                if (l3) {
-                        spin_lock_irq(&l3->list_lock);
-                        ret += __node_shrink(cachep, i);
-                        spin_unlock_irq(&l3->list_lock);
-                }
+                if (!l3)
+                        continue;
+
+                drain_freelist(cachep, l3, l3->free_objects);
+
+                ret += !list_empty(&l3->slabs_full) ||
+                        !list_empty(&l3->slabs_partial);
         }
         return (ret ? 1 : 0);
 }
@@ -3694,10 +3707,6 @@ static void cache_reap(void *unused)
         }
 
         list_for_each_entry(searchp, &cache_chain, next) {
-                struct list_head *p;
-                int tofree;
-                struct slab *slabp;
-
                 check_irq_on();
 
                 /*
@@ -3722,47 +3731,22 @@ static void cache_reap(void *unused)
 
                 drain_array(searchp, l3, l3->shared, 0, node);
 
-                if (l3->free_touched) {
+                if (l3->free_touched)
                         l3->free_touched = 0;
-                        goto next;
-                }
-
-                tofree = (l3->free_limit + 5 * searchp->num - 1) /
-                                (5 * searchp->num);
-                do {
-                        /*
-                         * Do not lock if there are no free blocks.
-                         */
-                        if (list_empty(&l3->slabs_free))
-                                break;
-
-                        spin_lock_irq(&l3->list_lock);
-                        p = l3->slabs_free.next;
-                        if (p == &(l3->slabs_free)) {
-                                spin_unlock_irq(&l3->list_lock);
-                                break;
-                        }
+                else {
+                        int freed;
 
-                        slabp = list_entry(p, struct slab, list);
-                        BUG_ON(slabp->inuse);
-                        list_del(&slabp->list);
-                        STATS_INC_REAPED(searchp);
-
-                        /*
-                         * Safe to drop the lock. The slab is no longer linked
-                         * to the cache. searchp cannot disappear, we hold
-                         * cache_chain_lock
-                         */
-                        l3->free_objects -= searchp->num;
-                        spin_unlock_irq(&l3->list_lock);
-                        slab_destroy(searchp, slabp);
-                } while (--tofree > 0);
+                        freed = drain_freelist(searchp, l3, (l3->free_limit +
+                                5 * searchp->num - 1) / (5 * searchp->num));
+                        STATS_ADD_REAPED(searchp, freed);
+                }
 next:
                 cond_resched();
         }
         check_irq_on();
         mutex_unlock(&cache_chain_mutex);
         next_reap_node();
+        refresh_cpu_vm_stats(smp_processor_id());
         /* Set up the next iteration */
         schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
 }
diff --git a/mm/swap.c b/mm/swap.c
index 990868afc1c6..8fd095c4ae51 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -87,7 +87,7 @@ int rotate_reclaimable_page(struct page *page)
         spin_lock_irqsave(&zone->lru_lock, flags);
         if (PageLRU(page) && !PageActive(page)) {
                 list_move_tail(&page->lru, &zone->inactive_list);
-                inc_page_state(pgrotated);
+                __count_vm_event(PGROTATED);
         }
         if (!test_clear_page_writeback(page))
                 BUG();
@@ -107,7 +107,7 @@ void fastcall activate_page(struct page *page)
                 del_page_from_inactive_list(zone, page);
                 SetPageActive(page);
                 add_page_to_active_list(zone, page);
-                inc_page_state(pgactivate);
+                __count_vm_event(PGACTIVATE);
         }
         spin_unlock_irq(&zone->lru_lock);
 }
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 7535211bb495..fccbd9bba77b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -87,7 +87,7 @@ static int __add_to_swap_cache(struct page *page, swp_entry_t entry,
                         SetPageSwapCache(page);
                         set_page_private(page, entry.val);
                         total_swapcache_pages++;
-                        pagecache_acct(1);
+                        __inc_zone_page_state(page, NR_FILE_PAGES);
                 }
                 write_unlock_irq(&swapper_space.tree_lock);
                 radix_tree_preload_end();
@@ -132,7 +132,7 @@ void __delete_from_swap_cache(struct page *page)
         set_page_private(page, 0);
         ClearPageSwapCache(page);
         total_swapcache_pages--;
-        pagecache_acct(-1);
+        __dec_zone_page_state(page, NR_FILE_PAGES);
         INC_CACHE_INFO(del_total);
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eeacb0d695c3..ff2ebe9458a3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -47,8 +47,6 @@ struct scan_control {
         /* Incremented by the number of inactive pages that were scanned */
         unsigned long nr_scanned;
 
-        unsigned long nr_mapped;        /* From page_state */
-
         /* This context's GFP mask */
         gfp_t gfp_mask;
 
@@ -217,7 +215,7 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
                                 break;
                         if (shrink_ret < nr_before)
                                 ret += nr_before - shrink_ret;
-                        mod_page_state(slabs_scanned, this_scan);
+                        count_vm_events(SLABS_SCANNED, this_scan);
                         total_scan -= this_scan;
 
                         cond_resched();
@@ -571,7 +569,7 @@ keep:
         list_splice(&ret_pages, page_list);
         if (pagevec_count(&freed_pvec))
                 __pagevec_release_nonlru(&freed_pvec);
-        mod_page_state(pgactivate, pgactivate);
+        count_vm_events(PGACTIVATE, pgactivate);
         return nr_reclaimed;
 }
 
@@ -661,11 +659,11 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
                 nr_reclaimed += nr_freed;
                 local_irq_disable();
                 if (current_is_kswapd()) {
-                        __mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
-                        __mod_page_state(kswapd_steal, nr_freed);
+                        __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
+                        __count_vm_events(KSWAPD_STEAL, nr_freed);
                 } else
-                        __mod_page_state_zone(zone, pgscan_direct, nr_scan);
-                __mod_page_state_zone(zone, pgsteal, nr_freed);
+                        __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
+                __count_vm_events(PGACTIVATE, nr_freed);
 
                 if (nr_taken == 0)
                         goto done;
@@ -744,7 +742,9 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
                  * how much memory
                  * is mapped.
                  */
-                mapped_ratio = (sc->nr_mapped * 100) / vm_total_pages;
+                mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
+                                global_page_state(NR_ANON_PAGES)) * 100) /
+                                        vm_total_pages;
 
                 /*
                  * Now decide how much we really want to unmap some pages.  The
@@ -841,11 +841,10 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
                 }
         }
         zone->nr_active += pgmoved;
-        spin_unlock(&zone->lru_lock);
 
-        __mod_page_state_zone(zone, pgrefill, pgscanned);
-        __mod_page_state(pgdeactivate, pgdeactivate);
-        local_irq_enable();
+        __count_zone_vm_events(PGREFILL, zone, pgscanned);
+        __count_vm_events(PGDEACTIVATE, pgdeactivate);
+        spin_unlock_irq(&zone->lru_lock);
 
         pagevec_release(&pvec);
 }
@@ -977,7 +976,7 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
                 .swappiness = vm_swappiness,
         };
 
-        inc_page_state(allocstall);
+        count_vm_event(ALLOCSTALL);
 
         for (i = 0; zones[i] != NULL; i++) {
                 struct zone *zone = zones[i];
@@ -990,7 +989,6 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
         }
 
         for (priority = DEF_PRIORITY; priority >= 0; priority--) {
-                sc.nr_mapped = read_page_state(nr_mapped);
                 sc.nr_scanned = 0;
                 if (!priority)
                         disable_swap_token();
@@ -1075,9 +1073,7 @@ loop_again:
         total_scanned = 0;
         nr_reclaimed = 0;
         sc.may_writepage = !laptop_mode;
-        sc.nr_mapped = read_page_state(nr_mapped);
-
-        inc_page_state(pageoutrun);
+        count_vm_event(PAGEOUTRUN);
 
         for (i = 0; i < pgdat->nr_zones; i++) {
                 struct zone *zone = pgdat->node_zones + i;
@@ -1365,7 +1361,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
         for_each_zone(zone)
                 lru_pages += zone->nr_active + zone->nr_inactive;
 
-        nr_slab = read_page_state(nr_slab);
+        nr_slab = global_page_state(NR_SLAB);
         /* If slab caches are huge, it's better to hit them first */
         while (nr_slab >= lru_pages) {
                 reclaim_state.reclaimed_slab = 0;
@@ -1407,9 +1403,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
                 for (prio = DEF_PRIORITY; prio >= 0; prio--) {
                         unsigned long nr_to_scan = nr_pages - ret;
 
-                        sc.nr_mapped = read_page_state(nr_mapped);
                         sc.nr_scanned = 0;
-
                         ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
                         if (ret >= nr_pages)
                                 goto out;
@@ -1523,11 +1517,6 @@ int zone_reclaim_mode __read_mostly;
 #define RECLAIM_SLAB (1<<3)     /* Do a global slab shrink if the zone is out of memory */
 
 /*
- * Mininum time between zone reclaim scans
- */
-int zone_reclaim_interval __read_mostly = 30*HZ;
-
-/*
  * Priority for ZONE_RECLAIM. This determines the fraction of pages
  * of a node considered for each zone_reclaim. 4 scans 1/16th of
  * a zone.
@@ -1548,7 +1537,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
         struct scan_control sc = {
                 .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
                 .may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
-                .nr_mapped = read_page_state(nr_mapped),
                 .swap_cluster_max = max_t(unsigned long, nr_pages,
                                         SWAP_CLUSTER_MAX),
                 .gfp_mask = gfp_mask,
@@ -1593,16 +1581,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 
         p->reclaim_state = NULL;
         current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
-
-        if (nr_reclaimed == 0) {
-                /*
-                 * We were unable to reclaim enough pages to stay on node.  We
-                 * now allow off node accesses for a certain time period before
-                 * trying again to reclaim pages from the local zone.
-                 */
-                zone->last_unsuccessful_zone_reclaim = jiffies;
-        }
-
         return nr_reclaimed >= nr_pages;
 }
 
@@ -1612,13 +1590,17 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
         int node_id;
 
         /*
-         * Do not reclaim if there was a recent unsuccessful attempt at zone
-         * reclaim.  In that case we let allocations go off node for the
-         * zone_reclaim_interval.  Otherwise we would scan for each off-node
-         * page allocation.
+         * Do not reclaim if there are not enough reclaimable pages in this
+         * zone that would satify this allocations.
+         *
+         * All unmapped pagecache pages are reclaimable.
+         *
+         * Both counters may be temporarily off a bit so we use
+         * SWAP_CLUSTER_MAX as the boundary. It may also be good to
+         * leave a few frequently used unmapped pagecache pages around.
          */
-        if (time_before(jiffies,
-                zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
+        if (zone_page_state(zone, NR_FILE_PAGES) -
+                zone_page_state(zone, NR_FILE_MAPPED) < SWAP_CLUSTER_MAX)
                         return 0;
 
         /*
diff --git a/mm/vmstat.c b/mm/vmstat.c
new file mode 100644
index 000000000000..73b83d67bab6
--- /dev/null
+++ b/mm/vmstat.c
@@ -0,0 +1,614 @@
+/*
+ *  linux/mm/vmstat.c
+ *
+ *  Manages VM statistics
+ *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  zoned VM statistics
+ *  Copyright (C) 2006 Silicon Graphics, Inc.,
+ *              Christoph Lameter <christoph@lameter.com>
+ */
+
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+
+void __get_zone_counts(unsigned long *active, unsigned long *inactive,
+                        unsigned long *free, struct pglist_data *pgdat)
+{
+        struct zone *zones = pgdat->node_zones;
+        int i;
+
+        *active = 0;
+        *inactive = 0;
+        *free = 0;
+        for (i = 0; i < MAX_NR_ZONES; i++) {
+                *active += zones[i].nr_active;
+                *inactive += zones[i].nr_inactive;
+                *free += zones[i].free_pages;
+        }
+}
+
+void get_zone_counts(unsigned long *active,
+                unsigned long *inactive, unsigned long *free)
+{
+        struct pglist_data *pgdat;
+
+        *active = 0;
+        *inactive = 0;
+        *free = 0;
+        for_each_online_pgdat(pgdat) {
+                unsigned long l, m, n;
+                __get_zone_counts(&l, &m, &n, pgdat);
+                *active += l;
+                *inactive += m;
+                *free += n;
+        }
+}
+
+#ifdef CONFIG_VM_EVENT_COUNTERS
+DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
+EXPORT_PER_CPU_SYMBOL(vm_event_states);
+
+static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask)
+{
+        int cpu = 0;
+        int i;
+
+        memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long));
+
+        cpu = first_cpu(*cpumask);
+        while (cpu < NR_CPUS) {
+                struct vm_event_state *this = &per_cpu(vm_event_states, cpu);
+
+                cpu = next_cpu(cpu, *cpumask);
+
+                if (cpu < NR_CPUS)
+                        prefetch(&per_cpu(vm_event_states, cpu));
+
+
+                for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+                        ret[i] += this->event[i];
+        }
+}
+
+/*
+ * Accumulate the vm event counters across all CPUs.
+ * The result is unavoidably approximate - it can change
+ * during and after execution of this function.
+*/
+void all_vm_events(unsigned long *ret)
+{
+        sum_vm_events(ret, &cpu_online_map);
+}
+
+#ifdef CONFIG_HOTPLUG
+/*
+ * Fold the foreign cpu events into our own.
+ *
+ * This is adding to the events on one processor
+ * but keeps the global counts constant.
+ */
+void vm_events_fold_cpu(int cpu)
+{
+        struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu);
+        int i;
+
+        for (i = 0; i < NR_VM_EVENT_ITEMS; i++) {
+                count_vm_events(i, fold_state->event[i]);
+                fold_state->event[i] = 0;
+        }
+}
+#endif /* CONFIG_HOTPLUG */
+
+#endif /* CONFIG_VM_EVENT_COUNTERS */
+
+/*
+ * Manage combined zone based / global counters
+ *
+ * vm_stat contains the global counters
+ */
+atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+EXPORT_SYMBOL(vm_stat);
+
+#ifdef CONFIG_SMP
+
+#define STAT_THRESHOLD 32
+
+/*
+ * Determine pointer to currently valid differential byte given a zone and
+ * the item number.
+ *
+ * Preemption must be off
+ */
+static inline s8 *diff_pointer(struct zone *zone, enum zone_stat_item item)
+{
+        return &zone_pcp(zone, smp_processor_id())->vm_stat_diff[item];
+}
+
+/*
+ * For use when we know that interrupts are disabled.
+ */
+void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+                                int delta)
+{
+        s8 *p;
+        long x;
+
+        p = diff_pointer(zone, item);
+        x = delta + *p;
+
+        if (unlikely(x > STAT_THRESHOLD || x < -STAT_THRESHOLD)) {
+                zone_page_state_add(x, zone, item);
+                x = 0;
+        }
+
+        *p = x;
+}
+EXPORT_SYMBOL(__mod_zone_page_state);
+
+/*
+ * For an unknown interrupt state
+ */
+void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+                                        int delta)
+{
+        unsigned long flags;
+
+        local_irq_save(flags);
+        __mod_zone_page_state(zone, item, delta);
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_zone_page_state);
+
+/*
+ * Optimized increment and decrement functions.
+ *
+ * These are only for a single page and therefore can take a struct page *
+ * argument instead of struct zone *. This allows the inclusion of the code
+ * generated for page_zone(page) into the optimized functions.
+ *
+ * No overflow check is necessary and therefore the differential can be
+ * incremented or decremented in place which may allow the compilers to
+ * generate better code.
+ *
+ * The increment or decrement is known and therefore one boundary check can
+ * be omitted.
+ *
+ * Some processors have inc/dec instructions that are atomic vs an interrupt.
+ * However, the code must first determine the differential location in a zone
+ * based on the processor number and then inc/dec the counter. There is no
+ * guarantee without disabling preemption that the processor will not change
+ * in between and therefore the atomicity vs. interrupt cannot be exploited
+ * in a useful way here.
+ */
+static void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
+{
+        s8 *p = diff_pointer(zone, item);
+
+        (*p)++;
+
+        if (unlikely(*p > STAT_THRESHOLD)) {
+                zone_page_state_add(*p, zone, item);
+                *p = 0;
+        }
+}
+
+void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+        __inc_zone_state(page_zone(page), item);
+}
+EXPORT_SYMBOL(__inc_zone_page_state);
+
+void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+        struct zone *zone = page_zone(page);
+        s8 *p = diff_pointer(zone, item);
+
+        (*p)--;
+
+        if (unlikely(*p < -STAT_THRESHOLD)) {
+                zone_page_state_add(*p, zone, item);
+                *p = 0;
+        }
+}
+EXPORT_SYMBOL(__dec_zone_page_state);
+
+void inc_zone_state(struct zone *zone, enum zone_stat_item item)
+{
+        unsigned long flags;
+
+        local_irq_save(flags);
+        __inc_zone_state(zone, item);
+        local_irq_restore(flags);
+}
+
+void inc_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+        unsigned long flags;
+        struct zone *zone;
+
+        zone = page_zone(page);
+        local_irq_save(flags);
+        __inc_zone_state(zone, item);
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL(inc_zone_page_state);
+
+void dec_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+        unsigned long flags;
+        struct zone *zone;
+        s8 *p;
+
+        zone = page_zone(page);
+        local_irq_save(flags);
+        p = diff_pointer(zone, item);
+
+        (*p)--;
+
+        if (unlikely(*p < -STAT_THRESHOLD)) {
+                zone_page_state_add(*p, zone, item);
+                *p = 0;
+        }
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL(dec_zone_page_state);
+
+/*
+ * Update the zone counters for one cpu.
+ */
+void refresh_cpu_vm_stats(int cpu)
+{
+        struct zone *zone;
+        int i;
+        unsigned long flags;
+
+        for_each_zone(zone) {
+                struct per_cpu_pageset *pcp;
+
+                pcp = zone_pcp(zone, cpu);
+
+                for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+                        if (pcp->vm_stat_diff[i]) {
+                                local_irq_save(flags);
+                                zone_page_state_add(pcp->vm_stat_diff[i],
+                                        zone, i);
+                                pcp->vm_stat_diff[i] = 0;
+                                local_irq_restore(flags);
+                        }
+        }
+}
+
+static void __refresh_cpu_vm_stats(void *dummy)
+{
+        refresh_cpu_vm_stats(smp_processor_id());
+}
+
+/*
+ * Consolidate all counters.
+ *
+ * Note that the result is less inaccurate but still inaccurate
+ * if concurrent processes are allowed to run.
+ */
+void refresh_vm_stats(void)
+{
+        on_each_cpu(__refresh_cpu_vm_stats, NULL, 0, 1);
+}
+EXPORT_SYMBOL(refresh_vm_stats);
+
+#endif
+
+#ifdef CONFIG_NUMA
+/*
+ * zonelist = the list of zones passed to the allocator
+ * z        = the zone from which the allocation occurred.
+ *
+ * Must be called with interrupts disabled.
+ */
+void zone_statistics(struct zonelist *zonelist, struct zone *z)
+{
+        if (z->zone_pgdat == zonelist->zones[0]->zone_pgdat) {
+                __inc_zone_state(z, NUMA_HIT);
+        } else {
+                __inc_zone_state(z, NUMA_MISS);
+                __inc_zone_state(zonelist->zones[0], NUMA_FOREIGN);
+        }
+        if (z->zone_pgdat == NODE_DATA(numa_node_id()))
+                __inc_zone_state(z, NUMA_LOCAL);
+        else
+                __inc_zone_state(z, NUMA_OTHER);
+}
+#endif
+
+#ifdef CONFIG_PROC_FS
+
+#include <linux/seq_file.h>
+
+static void *frag_start(struct seq_file *m, loff_t *pos)
+{
+        pg_data_t *pgdat;
+        loff_t node = *pos;
+        for (pgdat = first_online_pgdat();
+             pgdat && node;
+             pgdat = next_online_pgdat(pgdat))
+                --node;
+
+        return pgdat;
+}
+
+static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+        pg_data_t *pgdat = (pg_data_t *)arg;
+
+        (*pos)++;
+        return next_online_pgdat(pgdat);
+}
+
+static void frag_stop(struct seq_file *m, void *arg)
+{
+}
+
+/*
+ * This walks the free areas for each zone.
+ */
+static int frag_show(struct seq_file *m, void *arg)
+{
+        pg_data_t *pgdat = (pg_data_t *)arg;
+        struct zone *zone;
+        struct zone *node_zones = pgdat->node_zones;
+        unsigned long flags;
+        int order;
+
+        for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
+                if (!populated_zone(zone))
+                        continue;
+
+                spin_lock_irqsave(&zone->lock, flags);
+                seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
+                for (order = 0; order < MAX_ORDER; ++order)
+                        seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
+                spin_unlock_irqrestore(&zone->lock, flags);
+                seq_putc(m, '\n');
+        }
+        return 0;
+}
+
+struct seq_operations fragmentation_op = {
+        .start  = frag_start,
+        .next   = frag_next,
+        .stop   = frag_stop,
+        .show   = frag_show,
+};
+
+static char *vmstat_text[] = {
+        /* Zoned VM counters */
+        "nr_anon_pages",
+        "nr_mapped",
+        "nr_file_pages",
+        "nr_slab",
+        "nr_page_table_pages",
+        "nr_dirty",
+        "nr_writeback",
+        "nr_unstable",
+        "nr_bounce",
+
+#ifdef CONFIG_NUMA
+        "numa_hit",
+        "numa_miss",
+        "numa_foreign",
+        "numa_interleave",
+        "numa_local",
+        "numa_other",
+#endif
+
+#ifdef CONFIG_VM_EVENT_COUNTERS
+        "pgpgin",
+        "pgpgout",
+        "pswpin",
+        "pswpout",
+
+        "pgalloc_dma",
+        "pgalloc_dma32",
+        "pgalloc_normal",
+        "pgalloc_high",
+
+        "pgfree",
+        "pgactivate",
+        "pgdeactivate",
+
+        "pgfault",
+        "pgmajfault",
+
+        "pgrefill_dma",
+        "pgrefill_dma32",
+        "pgrefill_normal",
+        "pgrefill_high",
+
+        "pgsteal_dma",
+        "pgsteal_dma32",
+        "pgsteal_normal",
+        "pgsteal_high",
+
+        "pgscan_kswapd_dma",
+        "pgscan_kswapd_dma32",
+        "pgscan_kswapd_normal",
+        "pgscan_kswapd_high",
+
+        "pgscan_direct_dma",
+        "pgscan_direct_dma32",
+        "pgscan_direct_normal",
+        "pgscan_direct_high",
+
+        "pginodesteal",
+        "slabs_scanned",
+        "kswapd_steal",
+        "kswapd_inodesteal",
+        "pageoutrun",
+        "allocstall",
+
+        "pgrotated",
+#endif
+};
+
+/*
+ * Output information about zones in @pgdat.
+ */
+static int zoneinfo_show(struct seq_file *m, void *arg)
+{
+        pg_data_t *pgdat = arg;
+        struct zone *zone;
+        struct zone *node_zones = pgdat->node_zones;
+        unsigned long flags;
+
+        for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
+                int i;
+
+                if (!populated_zone(zone))
+                        continue;
+
+                spin_lock_irqsave(&zone->lock, flags);
+                seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
+                seq_printf(m,
+                           "\n  pages free     %lu"
+                           "\n        min      %lu"
+                           "\n        low      %lu"
+                           "\n        high     %lu"
+                           "\n        active   %lu"
+                           "\n        inactive %lu"
+                           "\n        scanned  %lu (a: %lu i: %lu)"
+                           "\n        spanned  %lu"
+                           "\n        present  %lu",
+                           zone->free_pages,
+                           zone->pages_min,
+                           zone->pages_low,
+                           zone->pages_high,
+                           zone->nr_active,
+                           zone->nr_inactive,
+                           zone->pages_scanned,
+                           zone->nr_scan_active, zone->nr_scan_inactive,
+                           zone->spanned_pages,
+                           zone->present_pages);
+
+                for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+                        seq_printf(m, "\n    %-12s %lu", vmstat_text[i],
+                                        zone_page_state(zone, i));
+
+                seq_printf(m,
+                           "\n        protection: (%lu",
+                           zone->lowmem_reserve[0]);
+                for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
+                        seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
+                seq_printf(m,
+                           ")"
+                           "\n  pagesets");
+                for_each_online_cpu(i) {
+                        struct per_cpu_pageset *pageset;
+                        int j;
+
+                        pageset = zone_pcp(zone, i);
+                        for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
+                                if (pageset->pcp[j].count)
+                                        break;
+                        }
+                        if (j == ARRAY_SIZE(pageset->pcp))
+                                continue;
+                        for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
+                                seq_printf(m,
+                                           "\n    cpu: %i pcp: %i"
+                                           "\n              count: %i"
+                                           "\n              high:  %i"
+                                           "\n              batch: %i",
+                                           i, j,
+                                           pageset->pcp[j].count,
+                                           pageset->pcp[j].high,
+                                           pageset->pcp[j].batch);
+                        }
+                }
+                seq_printf(m,
+                           "\n  all_unreclaimable: %u"
+                           "\n  prev_priority:     %i"
+                           "\n  temp_priority:     %i"
+                           "\n  start_pfn:         %lu",
+                           zone->all_unreclaimable,
+                           zone->prev_priority,
+                           zone->temp_priority,
+                           zone->zone_start_pfn);
+                spin_unlock_irqrestore(&zone->lock, flags);
+                seq_putc(m, '\n');
+        }
+        return 0;
+}
+
+struct seq_operations zoneinfo_op = {
+        .start  = frag_start, /* iterate over all zones. The same as in
+                               * fragmentation. */
+        .next   = frag_next,
+        .stop   = frag_stop,
+        .show   = zoneinfo_show,
+};
+
+static void *vmstat_start(struct seq_file *m, loff_t *pos)
+{
+        unsigned long *v;
+#ifdef CONFIG_VM_EVENT_COUNTERS
+        unsigned long *e;
+#endif
+        int i;
+
+        if (*pos >= ARRAY_SIZE(vmstat_text))
+                return NULL;
+
+#ifdef CONFIG_VM_EVENT_COUNTERS
+        v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long)
+                        + sizeof(struct vm_event_state), GFP_KERNEL);
+#else
+        v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long),
+                        GFP_KERNEL);
+#endif
+        m->private = v;
+        if (!v)
+                return ERR_PTR(-ENOMEM);
+        for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+                v[i] = global_page_state(i);
+#ifdef CONFIG_VM_EVENT_COUNTERS
+        e = v + NR_VM_ZONE_STAT_ITEMS;
+        all_vm_events(e);
+        e[PGPGIN] /= 2;         /* sectors -> kbytes */
+        e[PGPGOUT] /= 2;
+#endif
+        return v + *pos;
+}
+
+static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+        (*pos)++;
+        if (*pos >= ARRAY_SIZE(vmstat_text))
+                return NULL;
+        return (unsigned long *)m->private + *pos;
+}
+
+static int vmstat_show(struct seq_file *m, void *arg)
+{
+        unsigned long *l = arg;
+        unsigned long off = l - (unsigned long *)m->private;
+
+        seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
+        return 0;
+}
+
+static void vmstat_stop(struct seq_file *m, void *arg)
+{
+        kfree(m->private);
+        m->private = NULL;
+}
+
+struct seq_operations vmstat_op = {
+        .start  = vmstat_start,
+        .next   = vmstat_next,
+        .stop   = vmstat_stop,
+        .show   = vmstat_show,
+};
+
+#endif /* CONFIG_PROC_FS */
+
diff --git a/net/atm/Makefile b/net/atm/Makefile
index d5818751f6ba..89656d6c0b90 100644
--- a/net/atm/Makefile
+++ b/net/atm/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the ATM Protocol Families.
 #
 
-atm-y           := addr.o pvc.o signaling.o svc.o ioctl.o common.o atm_misc.o raw.o resources.o
+atm-y           := addr.o pvc.o signaling.o svc.o ioctl.o common.o atm_misc.o raw.o resources.o atm_sysfs.o
 mpoa-objs       := mpc.o mpoa_caches.o mpoa_proc.o
 
 obj-$(CONFIG_ATM) += atm.o
diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c
new file mode 100644
index 000000000000..5df4b9a068bb
--- /dev/null
+++ b/net/atm/atm_sysfs.c
@@ -0,0 +1,176 @@
+/* ATM driver model support. */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/kobject.h>
+#include <linux/atmdev.h>
+#include "common.h"
+#include "resources.h"
+
+#define to_atm_dev(cldev) container_of(cldev, struct atm_dev, class_dev)
+
+static ssize_t show_type(struct class_device *cdev, char *buf)
+{
+        struct atm_dev *adev = to_atm_dev(cdev);
+        return sprintf(buf, "%s\n", adev->type);
+}
+
+static ssize_t show_address(struct class_device *cdev, char *buf)
+{
+        char *pos = buf;
+        struct atm_dev *adev = to_atm_dev(cdev);
+        int i;
+
+        for (i = 0; i < (ESI_LEN - 1); i++)
+                pos += sprintf(pos, "%02x:", adev->esi[i]);
+        pos += sprintf(pos, "%02x\n", adev->esi[i]);
+
+        return pos - buf;
+}
+
+static ssize_t show_atmaddress(struct class_device *cdev, char *buf)
+{
+        unsigned long flags;
+        char *pos = buf;
+        struct atm_dev *adev = to_atm_dev(cdev);
+        struct atm_dev_addr *aaddr;
+        int bin[] = { 1, 2, 10, 6, 1 }, *fmt = bin;
+        int i, j;
+
+        spin_lock_irqsave(&adev->lock, flags);
+        list_for_each_entry(aaddr, &adev->local, entry) {
+                for(i = 0, j = 0; i < ATM_ESA_LEN; ++i, ++j) {
+                        if (j == *fmt) {
+                                pos += sprintf(pos, ".");
+                                ++fmt;
+                                j = 0;
+                        }
+                        pos += sprintf(pos, "%02x", aaddr->addr.sas_addr.prv[i]);
+                }
+                pos += sprintf(pos, "\n");
+        }
+        spin_unlock_irqrestore(&adev->lock, flags);
+
+        return pos - buf;
+}
+
+static ssize_t show_carrier(struct class_device *cdev, char *buf)
+{
+        char *pos = buf;
+        struct atm_dev *adev = to_atm_dev(cdev);
+
+        pos += sprintf(pos, "%d\n",
+                       adev->signal == ATM_PHY_SIG_LOST ? 0 : 1);
+                
+        return pos - buf;
+}
+
+static ssize_t show_link_rate(struct class_device *cdev, char *buf)
+{
+        char *pos = buf;
+        struct atm_dev *adev = to_atm_dev(cdev);
+        int link_rate;
+
+        /* show the link rate, not the data rate */
+        switch (adev->link_rate) {
+                case ATM_OC3_PCR:
+                        link_rate = 155520000;
+                        break;
+                case ATM_OC12_PCR:
+                        link_rate = 622080000;
+                        break;
+                case ATM_25_PCR:
+                        link_rate = 25600000;
+                        break;
+                default:
+                        link_rate = adev->link_rate * 8 * 53;
+        }
+        pos += sprintf(pos, "%d\n", link_rate);
+                
+        return pos - buf;
+}
+
+static CLASS_DEVICE_ATTR(address, S_IRUGO, show_address, NULL);
+static CLASS_DEVICE_ATTR(atmaddress, S_IRUGO, show_atmaddress, NULL);
+static CLASS_DEVICE_ATTR(carrier, S_IRUGO, show_carrier, NULL);
+static CLASS_DEVICE_ATTR(type, S_IRUGO, show_type, NULL);
+static CLASS_DEVICE_ATTR(link_rate, S_IRUGO, show_link_rate, NULL);
+
+static struct class_device_attribute *atm_attrs[] = {
+        &class_device_attr_atmaddress,
+        &class_device_attr_address,
+        &class_device_attr_carrier,
+        &class_device_attr_type,
+        &class_device_attr_link_rate,
+        NULL
+};
+
+static int atm_uevent(struct class_device *cdev, char **envp, int num_envp, char *buf, int size)
+{
+        struct atm_dev *adev;
+        int i = 0, len = 0;
+
+        if (!cdev)
+                return -ENODEV;
+
+        adev = to_atm_dev(cdev);
+        if (!adev)
+                return -ENODEV;
+
+        if (add_uevent_var(envp, num_envp, &i, buf, size, &len,
+                           "NAME=%s%d", adev->type, adev->number))
+                return -ENOMEM;
+
+        envp[i] = NULL;
+        return 0;
+}
+
+static void atm_release(struct class_device *cdev)
+{
+        struct atm_dev *adev = to_atm_dev(cdev);
+
+        kfree(adev);
+}
+
+static struct class atm_class = {
+        .name           = "atm",
+        .release        = atm_release,
+        .uevent         = atm_uevent,
+};
+
+int atm_register_sysfs(struct atm_dev *adev)
+{
+        struct class_device *cdev = &adev->class_dev;
+        int i, err;
+
+        cdev->class = &atm_class;
+        class_set_devdata(cdev, adev);
+
+        snprintf(cdev->class_id, BUS_ID_SIZE, "%s%d", adev->type, adev->number);
+        err = class_device_register(cdev);
+        if (err < 0)
+                return err;
+
+        for (i = 0; atm_attrs[i]; i++)
+                class_device_create_file(cdev, atm_attrs[i]);
+
+        return 0;
+}
+
+void atm_unregister_sysfs(struct atm_dev *adev)
+{
+        struct class_device *cdev = &adev->class_dev;
+
+        class_device_del(cdev);
+}
+
+int __init atm_sysfs_init(void)
+{
+        return class_register(&atm_class);
+}
+
+void __exit atm_sysfs_exit(void)
+{
+        class_unregister(&atm_class);
+}
diff --git a/net/atm/common.c b/net/atm/common.c
index ae002220fa99..35ab1a61e831 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -791,8 +791,14 @@ static int __init atm_init(void)
                 printk(KERN_ERR "atm_proc_init() failed with %d\n",error);
                 goto out_atmsvc_exit;
         }
+        if ((error = atm_sysfs_init()) < 0) {
+                printk(KERN_ERR "atm_sysfs_init() failed with %d\n",error);
+                goto out_atmproc_exit;
+        }
 out:
         return error;
+out_atmproc_exit:
+        atm_proc_exit();
 out_atmsvc_exit:
         atmsvc_exit();
 out_atmpvc_exit:
@@ -805,6 +811,7 @@ out_unregister_vcc_proto:
 static void __exit atm_exit(void)
 {
         atm_proc_exit();
+        atm_sysfs_exit();
         atmsvc_exit();
         atmpvc_exit();
         proto_unregister(&vcc_proto);
diff --git a/net/atm/common.h b/net/atm/common.h
index 4887c317cefe..a422da7788fb 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -28,6 +28,8 @@ int atmpvc_init(void);
 void atmpvc_exit(void);
 int atmsvc_init(void);
 void atmsvc_exit(void);
+int atm_sysfs_init(void);
+void atm_sysfs_exit(void);
 
 #ifdef CONFIG_PROC_FS
 int atm_proc_init(void);
diff --git a/net/atm/resources.c b/net/atm/resources.c
index 18ac80698f83..534baf704056 100644
--- a/net/atm/resources.c
+++ b/net/atm/resources.c
@@ -114,14 +114,27 @@ struct atm_dev *atm_dev_register(const char *type, const struct atmdev_ops *ops,
                 printk(KERN_ERR "atm_dev_register: "
                        "atm_proc_dev_register failed for dev %s\n",
                        type);
-                mutex_unlock(&atm_dev_mutex);
-                kfree(dev);
-                return NULL;
+                goto out_fail;
+        }
+
+        if (atm_register_sysfs(dev) < 0) {
+                printk(KERN_ERR "atm_dev_register: "
+                       "atm_register_sysfs failed for dev %s\n",
+                       type);
+                atm_proc_dev_deregister(dev);
+                goto out_fail;
         }
+
         list_add_tail(&dev->dev_list, &atm_devs);
-        mutex_unlock(&atm_dev_mutex);
 
+out:
+        mutex_unlock(&atm_dev_mutex);
         return dev;
+
+out_fail:
+        kfree(dev);
+        dev = NULL;
+        goto out;
 }
 
 
@@ -140,6 +153,7 @@ void atm_dev_deregister(struct atm_dev *dev)
         mutex_unlock(&atm_dev_mutex);
 
         atm_dev_release_vccs(dev);
+        atm_unregister_sysfs(dev);
         atm_proc_dev_deregister(dev);
 
         atm_dev_put(dev);
diff --git a/net/atm/resources.h b/net/atm/resources.h
index ac7222fee7a8..644989980c37 100644
--- a/net/atm/resources.h
+++ b/net/atm/resources.h
@@ -43,4 +43,6 @@ static inline void atm_proc_dev_deregister(struct atm_dev *dev)
 
 #endif /* CONFIG_PROC_FS */
 
+int atm_register_sysfs(struct atm_dev *adev);
+void atm_unregister_sysfs(struct atm_dev *adev);
 #endif
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 2afdc7c0736c..f8dbcee80eba 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -184,6 +184,6 @@ void br_dev_setup(struct net_device *dev)
         dev->set_mac_address = br_set_mac_address;
         dev->priv_flags = IFF_EBRIDGE;
 
-        dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
-                | NETIF_F_HIGHDMA | NETIF_F_TSO | NETIF_F_NO_CSUM;
+        dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
+                        NETIF_F_TSO | NETIF_F_NO_CSUM | NETIF_F_GSO_ROBUST;
 }
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 07956ecf545e..f55ef682ef84 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -392,7 +392,8 @@ void br_features_recompute(struct net_bridge *br)
                 features &= feature;
         }
 
-        br->dev->features = features | checksum | NETIF_F_LLTX;
+        br->dev->features = features | checksum | NETIF_F_LLTX |
+                            NETIF_F_GSO_ROBUST;
 }
 
 /* called with RTNL */
diff --git a/net/core/dev.c b/net/core/dev.c
index f1c52cbd6ef7..08976b08df5b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1190,11 +1190,14 @@ out:
 /**
  *      skb_gso_segment - Perform segmentation on skb.
  *      @skb: buffer to segment
- *      @sg: whether scatter-gather is supported on the target.
+ *      @features: features for the output path (see dev->features)
  *
  *      This function segments the given skb and returns a list of segments.
+ *
+ *      It may return NULL if the skb requires no segmentation.  This is
+ *      only possible when GSO is used for verifying header integrity.
  */
-struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
+struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
         struct packet_type *ptype;
@@ -1210,12 +1213,14 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
         rcu_read_lock();
         list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
                 if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
-                        segs = ptype->gso_segment(skb, sg);
+                        segs = ptype->gso_segment(skb, features);
                         break;
                 }
         }
         rcu_read_unlock();
 
+        __skb_push(skb, skb->data - skb->mac.raw);
+
         return segs;
 }
 
@@ -1234,7 +1239,6 @@ void netdev_rx_csum_fault(struct net_device *dev)
 EXPORT_SYMBOL(netdev_rx_csum_fault);
 #endif
 
-#ifdef CONFIG_HIGHMEM
 /* Actually, we should eliminate this check as soon as we know, that:
  * 1. IOMMU is present and allows to map all the memory.
  * 2. No high memory really exists on this machine.
@@ -1242,6 +1246,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
 
 static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 {
+#ifdef CONFIG_HIGHMEM
         int i;
 
         if (dev->features & NETIF_F_HIGHDMA)
@@ -1251,11 +1256,9 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
                 if (PageHighMem(skb_shinfo(skb)->frags[i].page))
                         return 1;
 
+#endif
         return 0;
 }
-#else
-#define illegal_highdma(dev, skb)       (0)
-#endif
 
 struct dev_gso_cb {
         void (*destructor)(struct sk_buff *skb);
@@ -1291,9 +1294,15 @@ static int dev_gso_segment(struct sk_buff *skb)
 {
         struct net_device *dev = skb->dev;
         struct sk_buff *segs;
+        int features = dev->features & ~(illegal_highdma(dev, skb) ?
+                                         NETIF_F_SG : 0);
+
+        segs = skb_gso_segment(skb, features);
+
+        /* Verifying header integrity only. */
+        if (!segs)
+                return 0;
 
-        segs = skb_gso_segment(skb, dev->features & NETIF_F_SG &&
-                                    !illegal_highdma(dev, skb));
         if (unlikely(IS_ERR(segs)))
                 return PTR_ERR(segs);
 
@@ -1310,13 +1319,17 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
                 if (netdev_nit)
                         dev_queue_xmit_nit(skb, dev);
 
-                if (!netif_needs_gso(dev, skb))
-                        return dev->hard_start_xmit(skb, dev);
+                if (netif_needs_gso(dev, skb)) {
+                        if (unlikely(dev_gso_segment(skb)))
+                                goto out_kfree_skb;
+                        if (skb->next)
+                                goto gso;
+                }
 
-                if (unlikely(dev_gso_segment(skb)))
-                        goto out_kfree_skb;
+                return dev->hard_start_xmit(skb, dev);
         }
 
+gso:
         do {
                 struct sk_buff *nskb = skb->next;
                 int rc;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 3fcfa9c59e1f..f25aac17497a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -663,7 +663,7 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp)
         sz_idx = type>>2;
         kind = type&3;
 
-        if (kind != 2 && security_netlink_recv(skb)) {
+        if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN)) {
                 *errp = -EPERM;
                 return -1;
         }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6edbb90cbcec..a1c9ecf4f1e0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -272,7 +272,7 @@ static void skb_clone_fraglist(struct sk_buff *skb)
                 skb_get(list);
 }
 
-void skb_release_data(struct sk_buff *skb)
+static void skb_release_data(struct sk_buff *skb)
 {
         if (!skb->cloned ||
             !atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
@@ -1848,13 +1848,13 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 /**
  *      skb_segment - Perform protocol segmentation on skb.
  *      @skb: buffer to segment
- *      @sg: whether scatter-gather can be used for generated segments
+ *      @features: features for the output path (see dev->features)
  *
  *      This function performs segmentation on the given skb.  It returns
  *      the segment at the given position.  It returns NULL if there are
  *      no more segments to generate, or when an error is encountered.
  */
-struct sk_buff *skb_segment(struct sk_buff *skb, int sg)
+struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = NULL;
         struct sk_buff *tail = NULL;
@@ -1863,6 +1863,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int sg)
         unsigned int offset = doffset;
         unsigned int headroom;
         unsigned int len;
+        int sg = features & NETIF_F_SG;
         int nfrags = skb_shinfo(skb)->nr_frags;
         int err = -ENOMEM;
         int i = 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 5d820c376653..204a8dec65cc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -565,6 +565,13 @@ set_rcvbuf:
                         ret = -ENONET;
                         break;
 
+                case SO_PASSSEC:
+                        if (valbool)
+                                set_bit(SOCK_PASSSEC, &sock->flags);
+                        else
+                                clear_bit(SOCK_PASSSEC, &sock->flags);
+                        break;
+
                 /* We implement the SO_SNDLOWAT etc to
                    not be settable (1003.1g 5.3) */
                 default:
@@ -723,6 +730,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
                         v.val = sk->sk_state == TCP_LISTEN;
                         break;
 
+                case SO_PASSSEC:
+                        v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0;
+                        break;
+
                 case SO_PEERSEC:
                         return security_socket_getpeersec_stream(sock, optval, optlen, len);
 
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 74133ecd7700..8b99bd33540d 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
         if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
                 return;
 
-        if (!cap_raised(NETLINK_CB(skb).eff_cap, CAP_NET_ADMIN))
+        if (security_netlink_recv(skb, CAP_NET_ADMIN))
                 RCV_SKB_FAIL(-EPERM);
 
         /* Eventually we might send routing messages too */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 461216b47948..8d157157bf8e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1097,7 +1097,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = ERR_PTR(-EINVAL);
         struct iphdr *iph;
@@ -1126,10 +1126,10 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg)
         rcu_read_lock();
         ops = rcu_dereference(inet_protos[proto]);
         if (ops && ops->gso_segment)
-                segs = ops->gso_segment(skb, sg);
+                segs = ops->gso_segment(skb, features);
         rcu_read_unlock();
 
-        if (IS_ERR(segs))
+        if (!segs || unlikely(IS_ERR(segs)))
                 goto out;
 
         skb = segs;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index e1d7f5fbc526..ef0b5aac5838 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -332,7 +332,7 @@ config IP_NF_MATCH_HASHLIMIT
         help
           This option adds a new iptables `hashlimit' match.  
 
-          As opposed to `limit', this match dynamically crates a hash table
+          As opposed to `limit', this match dynamically creates a hash table
           of limit buckets, based on your selection of source/destination
           ip addresses and/or ports.
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index d0d19192026d..ad39bf640567 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1120,7 +1120,8 @@ int arpt_register_table(struct arpt_table *table,
                 return ret;
         }
 
-        if (xt_register_table(table, &bootstrap, newinfo) != 0) {
+        ret = xt_register_table(table, &bootstrap, newinfo);
+        if (ret != 0) {
                 xt_free_table_info(newinfo);
                 return ret;
         }
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index b93f0494362f..198ac36db861 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -457,11 +457,19 @@ dev_cmp(struct ipq_queue_entry *entry, unsigned long ifindex)
         if (entry->info->indev)
                 if (entry->info->indev->ifindex == ifindex)
                         return 1;
-                        
         if (entry->info->outdev)
                 if (entry->info->outdev->ifindex == ifindex)
                         return 1;
-
+#ifdef CONFIG_BRIDGE_NETFILTER
+        if (entry->skb->nf_bridge) {
+                if (entry->skb->nf_bridge->physindev &&
+                    entry->skb->nf_bridge->physindev->ifindex == ifindex)
+                        return 1;
+                if (entry->skb->nf_bridge->physoutdev &&
+                    entry->skb->nf_bridge->physoutdev->ifindex == ifindex)
+                        return 1;
+        }
+#endif
         return 0;
 }
 
@@ -507,7 +515,7 @@ ipq_rcv_skb(struct sk_buff *skb)
         if (type <= IPQM_BASE)
                 return;
                 
-        if (security_netlink_recv(skb))
+        if (security_netlink_recv(skb, CAP_NET_ADMIN))
                 RCV_SKB_FAIL(-EPERM);
         
         write_lock_bh(&queue_lock);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 706c0025ec5e..7aaaf92efb59 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -2113,7 +2113,8 @@ int ipt_register_table(struct xt_table *table, const struct ipt_replace *repl)
                 return ret;
         }
 
-        if (xt_register_table(table, &bootstrap, newinfo) != 0) {
+        ret = xt_register_table(table, &bootstrap, newinfo);
+        if (ret != 0) {
                 xt_free_table_info(newinfo);
                 return ret;
         }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c04176be7ed1..0336422c88a0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2145,7 +2145,7 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg)
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
 {
         struct sk_buff *segs = ERR_PTR(-EINVAL);
         struct tcphdr *th;
@@ -2166,10 +2166,14 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg)
         if (!pskb_may_pull(skb, thlen))
                 goto out;
 
+        segs = NULL;
+        if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST))
+                goto out;
+
         oldlen = (u16)~skb->len;
         __skb_pull(skb, thlen);
 
-        segs = skb_segment(skb, sg);
+        segs = skb_segment(skb, features);
         if (IS_ERR(segs))
                 goto out;
 
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index c148c1081880..b56399c7cc12 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,7 +26,10 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
         const struct tcp_sock *tp = tcp_sk(sk);
         struct tcp_info *info = _info;
 
-        r->idiag_rqueue = tp->rcv_nxt - tp->copied_seq;
+        if (sk->sk_state == TCP_LISTEN)
+                r->idiag_rqueue = sk->sk_ack_backlog;
+        else
+                r->idiag_rqueue = tp->rcv_nxt - tp->copied_seq;
         r->idiag_wqueue = tp->write_seq - tp->snd_una;
         if (info != NULL)
                 tcp_get_info(sk, info);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 94fe5b1f9dcb..7fa0b4a8a389 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4178,8 +4178,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
                  */
 
                 TCP_ECN_rcv_synack(tp, th);
-                if (tp->ecn_flags&TCP_ECN_OK)
-                        sock_set_flag(sk, SOCK_NO_LARGESEND);
 
                 tp->snd_wl1 = TCP_SKB_CB(skb)->seq;
                 tcp_ack(sk, skb, FLAG_SLOWPATH);
@@ -4322,8 +4320,6 @@ discard:
                 tp->max_window = tp->snd_wnd;
 
                 TCP_ECN_rcv_syn(tp, th);
-                if (tp->ecn_flags&TCP_ECN_OK)
-                        sock_set_flag(sk, SOCK_NO_LARGESEND);
 
                 tcp_mtup_init(sk);
                 tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 25ecc6e2478b..4c6ef47eb1c3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1726,7 +1726,8 @@ static void get_tcp4_sock(struct sock *sp, char *tmpbuf, int i)
         sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
                         "%08X %5d %8d %lu %d %p %u %u %u %u %d",
                 i, src, srcp, dest, destp, sp->sk_state,
-                tp->write_seq - tp->snd_una, tp->rcv_nxt - tp->copied_seq,
+                tp->write_seq - tp->snd_una,
+                (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq),
                 timer_active,
                 jiffies_to_clock_t(timer_expires - jiffies),
                 icsk->icsk_retransmits,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2b9b7f6c7f7c..54b2ef7d3efe 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -440,8 +440,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
                         newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
                 newtp->rx_opt.mss_clamp = req->mss;
                 TCP_ECN_openreq_child(newtp, req);
-                if (newtp->ecn_flags&TCP_ECN_OK)
-                        sock_set_flag(newsk, SOCK_NO_LARGESEND);
 
                 TCP_INC_STATS_BH(TCP_MIB_PASSIVEOPENS);
         }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bdd71db8bf90..5a7cb4a9c867 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2044,8 +2044,6 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
         memset(th, 0, sizeof(struct tcphdr));
         th->syn = 1;
         th->ack = 1;
-        if (dst->dev->features&NETIF_F_TSO)
-                ireq->ecn_ok = 0;
         TCP_ECN_make_synack(req, th);
         th->source = inet_sk(sk)->sport;
         th->dest = ireq->rmt_port;
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index b4b7d441af25..968a14be0d05 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -505,7 +505,7 @@ ipq_rcv_skb(struct sk_buff *skb)
         if (type <= IPQM_BASE)
                 return;
         
-        if (security_netlink_recv(skb))
+        if (security_netlink_recv(skb, CAP_NET_ADMIN))
                 RCV_SKB_FAIL(-EPERM);   
 
         write_lock_bh(&queue_lock);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 2e72f89a7019..0b5bd5587a3e 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1281,7 +1281,8 @@ int ip6t_register_table(struct xt_table *table,
                 return ret;
         }
 
-        if (xt_register_table(table, &bootstrap, newinfo) != 0) {
+        ret = xt_register_table(table, &bootstrap, newinfo);
+        if (ret != 0) {
                 xt_free_table_info(newinfo);
                 return ret;
         }
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a50eb306e9e2..b36d5b2e7c30 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1469,7 +1469,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
                    dest->s6_addr32[0], dest->s6_addr32[1],
                    dest->s6_addr32[2], dest->s6_addr32[3], destp,
                    sp->sk_state, 
-                   tp->write_seq-tp->snd_una, tp->rcv_nxt-tp->copied_seq,
+                   tp->write_seq-tp->snd_una,
+                   (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq),
                    timer_active,
                    jiffies_to_clock_t(timer_expires - jiffies),
                    icsk->icsk_retransmits,
diff --git a/net/irda/irlan/irlan_client.c b/net/irda/irlan/irlan_client.c
index f8e6cb0db04b..95cf1234ea17 100644
--- a/net/irda/irlan/irlan_client.c
+++ b/net/irda/irlan/irlan_client.c
@@ -173,13 +173,14 @@ void irlan_client_discovery_indication(discinfo_t *discovery,
         rcu_read_lock();
         self = irlan_get_any();
         if (self) {
-                IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
+                IRDA_ASSERT(self->magic == IRLAN_MAGIC, goto out;);
 
                 IRDA_DEBUG(1, "%s(), Found instance (%08x)!\n", __FUNCTION__ ,
                       daddr);
                 
                 irlan_client_wakeup(self, saddr, daddr);
         }
+IRDA_ASSERT_LABEL(out:)
         rcu_read_unlock();
 }
         
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index b1622b7de1cf..42a178aa30f9 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -411,7 +411,10 @@ config NETFILTER_XT_MATCH_STATISTIC
         tristate '"statistic" match support'
         depends on NETFILTER_XTABLES
         help
-          statistic module
+          This option adds a `statistic' match, which allows you to match
+          on packets periodically or randomly with a given percentage.
+
+          To compile it as a module, choose M here.  If unsure, say N.
 
 config NETFILTER_XT_MATCH_STRING
         tristate  '"string" match support'
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index b8c7c567c9df..af4845971f70 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -29,6 +29,7 @@
 #include <linux/errno.h>
 #include <linux/netlink.h>
 #include <linux/spinlock.h>
+#include <linux/interrupt.h>
 #include <linux/notifier.h>
 
 #include <linux/netfilter.h>
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 0c6da496cfa9..0839b701b930 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -28,6 +28,8 @@
 #include <linux/sctp.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_protocol.h>
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index b88e82a1a987..ec9f0efea6bb 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -229,7 +229,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb,
                  NFNL_SUBSYS_ID(nlh->nlmsg_type),
                  NFNL_MSG_TYPE(nlh->nlmsg_type));
 
-        if (!cap_raised(NETLINK_CB(skb).eff_cap, CAP_NET_ADMIN)) {
+        if (security_netlink_recv(skb, CAP_NET_ADMIN)) {
                 DEBUGP("missing CAP_NET_ADMIN\n");
                 *errp = -EPERM;
                 return -1;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 86a4ac33de34..49ef41e34c48 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -680,11 +680,19 @@ dev_cmp(struct nfqnl_queue_entry *entry, unsigned long ifindex)
         if (entinf->indev)
                 if (entinf->indev->ifindex == ifindex)
                         return 1;
-                        
         if (entinf->outdev)
                 if (entinf->outdev->ifindex == ifindex)
                         return 1;
-
+#ifdef CONFIG_BRIDGE_NETFILTER
+        if (entry->skb->nf_bridge) {
+                if (entry->skb->nf_bridge->physindev &&
+                    entry->skb->nf_bridge->physindev->ifindex == ifindex)
+                        return 1;
+                if (entry->skb->nf_bridge->physoutdev &&
+                    entry->skb->nf_bridge->physoutdev->ifindex == ifindex)
+                        return 1;
+        }
+#endif
         return 0;
 }
 
diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c
index 9316c753692f..843383e01d41 100644
--- a/net/netfilter/xt_sctp.c
+++ b/net/netfilter/xt_sctp.c
@@ -151,7 +151,7 @@ match(const struct sk_buff *skb,
                 && SCCHECK(((ntohs(sh->dest) >= info->dpts[0]) 
                         && (ntohs(sh->dest) <= info->dpts[1])), 
                         XT_SCTP_DEST_PORTS, info->flags, info->invflags)
-                && SCCHECK(match_packet(skb, protoff,
+                && SCCHECK(match_packet(skb, protoff + sizeof (sctp_sctphdr_t),
                                         info->chunkmap, info->chunk_match_type,
                                         info->flag_info, info->flag_count, 
                                         hotdrop),
diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c
index 1b61dac9c873..a9a63aa68936 100644
--- a/net/netfilter/xt_tcpudp.c
+++ b/net/netfilter/xt_tcpudp.c
@@ -260,7 +260,7 @@ static int __init xt_tcpudp_init(void)
         return ret;
 
 out_unreg_udp:
-        xt_unregister_match(&tcp_matchstruct);
+        xt_unregister_match(&udp_matchstruct);
 out_unreg_tcp6:
         xt_unregister_match(&tcp6_matchstruct);
 out_unreg_tcp:
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index f329b72578f5..edf084becd5e 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -320,7 +320,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
                 goto errout;
         }
 
-        if ((ops->flags & GENL_ADMIN_PERM) && security_netlink_recv(skb)) {
+        if ((ops->flags & GENL_ADMIN_PERM) && security_netlink_recv(skb, CAP_NET_ADMIN)) {
                 err = -EPERM;
                 goto errout;
         }
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index f8bac6ccd524..d88468d21c37 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -224,7 +224,8 @@ EXPORT_SYMBOL(gss_service_to_auth_domain_name);
 void
 gss_mech_put(struct gss_api_mech * gm)
 {
-        module_put(gm->gm_owner);
+        if (gm)
+                module_put(gm->gm_owner);
 }
 
 EXPORT_SYMBOL(gss_mech_put);
@@ -307,8 +308,7 @@ gss_delete_sec_context(struct gss_ctx	**context_handle)
                 (*context_handle)->mech_type->gm_ops
                         ->gss_delete_sec_context((*context_handle)
                                                         ->internal_ctx_id);
-        if ((*context_handle)->mech_type)
-                gss_mech_put((*context_handle)->mech_type);
+        gss_mech_put((*context_handle)->mech_type);
         kfree(*context_handle);
         *context_handle=NULL;
         return GSS_S_COMPLETE;
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index d51e316c5821..94217ec9e2dd 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -425,6 +425,7 @@ static int rsc_parse(struct cache_detail *cd,
         struct rsc rsci, *rscp = NULL;
         time_t expiry;
         int status = -EINVAL;
+        struct gss_api_mech *gm = NULL;
 
         memset(&rsci, 0, sizeof(rsci));
         /* context handle */
@@ -453,7 +454,6 @@ static int rsc_parse(struct cache_detail *cd,
                 set_bit(CACHE_NEGATIVE, &rsci.h.flags);
         else {
                 int N, i;
-                struct gss_api_mech *gm;
 
                 /* gid */
                 if (get_int(&mesg, &rsci.cred.cr_gid))
@@ -488,21 +488,17 @@ static int rsc_parse(struct cache_detail *cd,
                 status = -EINVAL;
                 /* mech-specific data: */
                 len = qword_get(&mesg, buf, mlen);
-                if (len < 0) {
-                        gss_mech_put(gm);
+                if (len < 0)
                         goto out;
-                }
                 status = gss_import_sec_context(buf, len, gm, &rsci.mechctx);
-                if (status) {
-                        gss_mech_put(gm);
+                if (status)
                         goto out;
-                }
-                gss_mech_put(gm);
         }
         rsci.h.expiry_time = expiry;
         rscp = rsc_update(&rsci, rscp);
         status = 0;
 out:
+        gss_mech_put(gm);
         rsc_free(&rsci);
         if (rscp)
                 cache_put(&rscp->h, &rsc_cache);
@@ -836,6 +832,74 @@ out:
         return stat;
 }
 
+static inline int
+total_buf_len(struct xdr_buf *buf)
+{
+        return buf->head[0].iov_len + buf->page_len + buf->tail[0].iov_len;
+}
+
+static void
+fix_priv_head(struct xdr_buf *buf, int pad)
+{
+        if (buf->page_len == 0) {
+                /* We need to adjust head and buf->len in tandem in this
+                 * case to make svc_defer() work--it finds the original
+                 * buffer start using buf->len - buf->head[0].iov_len. */
+                buf->head[0].iov_len -= pad;
+        }
+}
+
+static int
+unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx)
+{
+        u32 priv_len, maj_stat;
+        int pad, saved_len, remaining_len, offset;
+
+        rqstp->rq_sendfile_ok = 0;
+
+        priv_len = ntohl(svc_getu32(&buf->head[0]));
+        if (rqstp->rq_deferred) {
+                /* Already decrypted last time through! The sequence number
+                 * check at out_seq is unnecessary but harmless: */
+                goto out_seq;
+        }
+        /* buf->len is the number of bytes from the original start of the
+         * request to the end, where head[0].iov_len is just the bytes
+         * not yet read from the head, so these two values are different: */
+        remaining_len = total_buf_len(buf);
+        if (priv_len > remaining_len)
+                return -EINVAL;
+        pad = remaining_len - priv_len;
+        buf->len -= pad;
+        fix_priv_head(buf, pad);
+
+        /* Maybe it would be better to give gss_unwrap a length parameter: */
+        saved_len = buf->len;
+        buf->len = priv_len;
+        maj_stat = gss_unwrap(ctx, 0, buf);
+        pad = priv_len - buf->len;
+        buf->len = saved_len;
+        buf->len -= pad;
+        /* The upper layers assume the buffer is aligned on 4-byte boundaries.
+         * In the krb5p case, at least, the data ends up offset, so we need to
+         * move it around. */
+        /* XXX: This is very inefficient.  It would be better to either do
+         * this while we encrypt, or maybe in the receive code, if we can peak
+         * ahead and work out the service and mechanism there. */
+        offset = buf->head[0].iov_len % 4;
+        if (offset) {
+                buf->buflen = RPCSVC_MAXPAYLOAD;
+                xdr_shift_buf(buf, offset);
+                fix_priv_head(buf, pad);
+        }
+        if (maj_stat != GSS_S_COMPLETE)
+                return -EINVAL;
+out_seq:
+        if (ntohl(svc_getu32(&buf->head[0])) != seq)
+                return -EINVAL;
+        return 0;
+}
+
 struct gss_svc_data {
         /* decoded gss client cred: */
         struct rpc_gss_wire_cred        clcred;
@@ -1051,7 +1115,14 @@ svcauth_gss_accept(struct svc_rqst *rqstp, u32 *authp)
                         svc_putu32(resv, 0);
                         break;
                 case RPC_GSS_SVC_PRIVACY:
-                        /* currently unsupported */
+                        if (unwrap_priv_data(rqstp, &rqstp->rq_arg,
+                                        gc->gc_seq, rsci->mechctx))
+                                goto auth_err;
+                        /* placeholders for length and seq. number: */
+                        svcdata->body_start = resv->iov_base + resv->iov_len;
+                        svc_putu32(resv, 0);
+                        svc_putu32(resv, 0);
+                        break;
                 default:
                         goto auth_err;
                 }
@@ -1076,8 +1147,8 @@ out:
         return ret;
 }
 
-static int
-svcauth_gss_release(struct svc_rqst *rqstp)
+static inline int
+svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp)
 {
         struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data;
         struct rpc_gss_wire_cred *gc = &gsd->clcred;
@@ -1089,69 +1160,147 @@ svcauth_gss_release(struct svc_rqst *rqstp)
         int integ_offset, integ_len;
         int stat = -EINVAL;
 
+        p = gsd->body_start;
+        gsd->body_start = NULL;
+        /* move accept_stat to right place: */
+        memcpy(p, p + 2, 4);
+        /* Don't wrap in failure case: */
+        /* Counting on not getting here if call was not even accepted! */
+        if (*p != rpc_success) {
+                resbuf->head[0].iov_len -= 2 * 4;
+                goto out;
+        }
+        p++;
+        integ_offset = (u8 *)(p + 1) - (u8 *)resbuf->head[0].iov_base;
+        integ_len = resbuf->len - integ_offset;
+        BUG_ON(integ_len % 4);
+        *p++ = htonl(integ_len);
+        *p++ = htonl(gc->gc_seq);
+        if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset,
+                                integ_len))
+                BUG();
+        if (resbuf->page_len == 0
+                        && resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE
+                        < PAGE_SIZE) {
+                BUG_ON(resbuf->tail[0].iov_len);
+                /* Use head for everything */
+                resv = &resbuf->head[0];
+        } else if (resbuf->tail[0].iov_base == NULL) {
+                if (resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE > PAGE_SIZE)
+                        goto out_err;
+                resbuf->tail[0].iov_base = resbuf->head[0].iov_base
+                                                + resbuf->head[0].iov_len;
+                resbuf->tail[0].iov_len = 0;
+                rqstp->rq_restailpage = 0;
+                resv = &resbuf->tail[0];
+        } else {
+                resv = &resbuf->tail[0];
+        }
+        mic.data = (u8 *)resv->iov_base + resv->iov_len + 4;
+        if (gss_get_mic(gsd->rsci->mechctx, &integ_buf, &mic))
+                goto out_err;
+        svc_putu32(resv, htonl(mic.len));
+        memset(mic.data + mic.len, 0,
+                        round_up_to_quad(mic.len) - mic.len);
+        resv->iov_len += XDR_QUADLEN(mic.len) << 2;
+        /* not strictly required: */
+        resbuf->len += XDR_QUADLEN(mic.len) << 2;
+        BUG_ON(resv->iov_len > PAGE_SIZE);
+out:
+        stat = 0;
+out_err:
+        return stat;
+}
+
+static inline int
+svcauth_gss_wrap_resp_priv(struct svc_rqst *rqstp)
+{
+        struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data;
+        struct rpc_gss_wire_cred *gc = &gsd->clcred;
+        struct xdr_buf *resbuf = &rqstp->rq_res;
+        struct page **inpages = NULL;
+        u32 *p;
+        int offset, *len;
+        int pad;
+
+        p = gsd->body_start;
+        gsd->body_start = NULL;
+        /* move accept_stat to right place: */
+        memcpy(p, p + 2, 4);
+        /* Don't wrap in failure case: */
+        /* Counting on not getting here if call was not even accepted! */
+        if (*p != rpc_success) {
+                resbuf->head[0].iov_len -= 2 * 4;
+                return 0;
+        }
+        p++;
+        len = p++;
+        offset = (u8 *)p - (u8 *)resbuf->head[0].iov_base;
+        *p++ = htonl(gc->gc_seq);
+        inpages = resbuf->pages;
+        /* XXX: Would be better to write some xdr helper functions for
+         * nfs{2,3,4}xdr.c that place the data right, instead of copying: */
+        if (resbuf->tail[0].iov_base && rqstp->rq_restailpage == 0) {
+                BUG_ON(resbuf->tail[0].iov_base >= resbuf->head[0].iov_base
+                                                        + PAGE_SIZE);
+                BUG_ON(resbuf->tail[0].iov_base < resbuf->head[0].iov_base);
+                if (resbuf->tail[0].iov_len + resbuf->head[0].iov_len
+                                + 2 * RPC_MAX_AUTH_SIZE > PAGE_SIZE)
+                        return -ENOMEM;
+                memmove(resbuf->tail[0].iov_base + RPC_MAX_AUTH_SIZE,
+                        resbuf->tail[0].iov_base,
+                        resbuf->tail[0].iov_len);
+                resbuf->tail[0].iov_base += RPC_MAX_AUTH_SIZE;
+        }
+        if (resbuf->tail[0].iov_base == NULL) {
+                if (resbuf->head[0].iov_len + 2*RPC_MAX_AUTH_SIZE > PAGE_SIZE)
+                        return -ENOMEM;
+                resbuf->tail[0].iov_base = resbuf->head[0].iov_base
+                        + resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE;
+                resbuf->tail[0].iov_len = 0;
+                rqstp->rq_restailpage = 0;
+        }
+        if (gss_wrap(gsd->rsci->mechctx, offset, resbuf, inpages))
+                return -ENOMEM;
+        *len = htonl(resbuf->len - offset);
+        pad = 3 - ((resbuf->len - offset - 1)&3);
+        p = (u32 *)(resbuf->tail[0].iov_base + resbuf->tail[0].iov_len);
+        memset(p, 0, pad);
+        resbuf->tail[0].iov_len += pad;
+        resbuf->len += pad;
+        return 0;
+}
+
+static int
+svcauth_gss_release(struct svc_rqst *rqstp)
+{
+        struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data;
+        struct rpc_gss_wire_cred *gc = &gsd->clcred;
+        struct xdr_buf *resbuf = &rqstp->rq_res;
+        int stat = -EINVAL;
+
         if (gc->gc_proc != RPC_GSS_PROC_DATA)
                 goto out;
         /* Release can be called twice, but we only wrap once. */
         if (gsd->body_start == NULL)
                 goto out;
         /* normally not set till svc_send, but we need it here: */
-        resbuf->len = resbuf->head[0].iov_len
-                + resbuf->page_len + resbuf->tail[0].iov_len;
+        /* XXX: what for?  Do we mess it up the moment we call svc_putu32
+         * or whatever? */
+        resbuf->len = total_buf_len(resbuf);
         switch (gc->gc_svc) {
         case RPC_GSS_SVC_NONE:
                 break;
         case RPC_GSS_SVC_INTEGRITY:
-                p = gsd->body_start;
-                gsd->body_start = NULL;
-                /* move accept_stat to right place: */
-                memcpy(p, p + 2, 4);
-                /* don't wrap in failure case: */
-                /* Note: counting on not getting here if call was not even
-                 * accepted! */
-                if (*p != rpc_success) {
-                        resbuf->head[0].iov_len -= 2 * 4;
-                        goto out;
-                }
-                p++;
-                integ_offset = (u8 *)(p + 1) - (u8 *)resbuf->head[0].iov_base;
-                integ_len = resbuf->len - integ_offset;
-                BUG_ON(integ_len % 4);
-                *p++ = htonl(integ_len);
-                *p++ = htonl(gc->gc_seq);
-                if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset,
-                                        integ_len))
-                        BUG();
-                if (resbuf->page_len == 0
-                        && resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE
-                                < PAGE_SIZE) {
-                        BUG_ON(resbuf->tail[0].iov_len);
-                        /* Use head for everything */
-                        resv = &resbuf->head[0];
-                } else if (resbuf->tail[0].iov_base == NULL) {
-                        if (resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE
-                                        > PAGE_SIZE)
-                                goto out_err;
-                        resbuf->tail[0].iov_base =
-                                resbuf->head[0].iov_base
-                                + resbuf->head[0].iov_len;
-                        resbuf->tail[0].iov_len = 0;
-                        rqstp->rq_restailpage = 0;
-                        resv = &resbuf->tail[0];
-                } else {
-                        resv = &resbuf->tail[0];
-                }
-                mic.data = (u8 *)resv->iov_base + resv->iov_len + 4;
-                if (gss_get_mic(gsd->rsci->mechctx, &integ_buf, &mic))
+                stat = svcauth_gss_wrap_resp_integ(rqstp);
+                if (stat)
                         goto out_err;
-                svc_putu32(resv, htonl(mic.len));
-                memset(mic.data + mic.len, 0,
-                                round_up_to_quad(mic.len) - mic.len);
-                resv->iov_len += XDR_QUADLEN(mic.len) << 2;
-                /* not strictly required: */
-                resbuf->len += XDR_QUADLEN(mic.len) << 2;
-                BUG_ON(resv->iov_len > PAGE_SIZE);
                 break;
         case RPC_GSS_SVC_PRIVACY:
+                stat = svcauth_gss_wrap_resp_priv(rqstp);
+                if (stat)
+                        goto out_err;
+                break;
         default:
                 goto out_err;
         }
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index b08419e1fc68..01ba60a49572 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -280,7 +280,10 @@ svc_process(struct svc_serv *serv, struct svc_rqst *rqstp)
         rqstp->rq_res.page_base = 0;
         rqstp->rq_res.page_len = 0;
         rqstp->rq_res.buflen = PAGE_SIZE;
+        rqstp->rq_res.tail[0].iov_base = NULL;
         rqstp->rq_res.tail[0].iov_len = 0;
+        /* Will be turned off only in gss privacy case: */
+        rqstp->rq_sendfile_ok = 1;
         /* tcp needs a space for the record length... */
         if (rqstp->rq_prot == IPPROTO_TCP)
                 svc_putu32(resv, 0);
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 5003acb15919..0539a8362858 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -191,7 +191,8 @@ static int __init tipc_init(void)
         int res;
 
         tipc_log_reinit(CONFIG_TIPC_LOG);
-        info("Activated (compiled " __DATE__ " " __TIME__ ")\n");
+        info("Activated (version " TIPC_MOD_VER 
+             " compiled " __DATE__ " " __TIME__ ")\n");
 
         tipc_own_addr = 0;
         tipc_remote_management = 1;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index d64658053746..c6831c75cfa4 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2,7 +2,7 @@
  * net/tipc/link.c: TIPC link code
  * 
  * Copyright (c) 1996-2006, Ericsson AB
- * Copyright (c) 2004-2005, Wind River Systems
+ * Copyright (c) 2004-2006, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -988,17 +988,18 @@ static int link_bundle_buf(struct link *l_ptr,
         struct tipc_msg *bundler_msg = buf_msg(bundler);
         struct tipc_msg *msg = buf_msg(buf);
         u32 size = msg_size(msg);
-        u32 to_pos = align(msg_size(bundler_msg));
-        u32 rest = link_max_pkt(l_ptr) - to_pos;
+        u32 bundle_size = msg_size(bundler_msg);
+        u32 to_pos = align(bundle_size);
+        u32 pad = to_pos - bundle_size;
 
         if (msg_user(bundler_msg) != MSG_BUNDLER)
                 return 0;
         if (msg_type(bundler_msg) != OPEN_MSG)
                 return 0;
-        if (rest < align(size))
+        if (skb_tailroom(bundler) < (pad + size))
                 return 0;
 
-        skb_put(bundler, (to_pos - msg_size(bundler_msg)) + size);
+        skb_put(bundler, pad + size);
         memcpy(bundler->data + to_pos, buf->data, size);
         msg_set_size(bundler_msg, to_pos + size);
         msg_set_msgcnt(bundler_msg, msg_msgcnt(bundler_msg) + 1);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 861322b935da..fc6d09630ccd 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2,7 +2,7 @@
  * net/tipc/node.c: TIPC node management routines
  * 
  * Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2005, Wind River Systems
+ * Copyright (c) 2005-2006, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -592,6 +592,7 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space)
         struct sk_buff *buf;
         struct node *n_ptr;
         struct tipc_node_info node_info;
+        u32 payload_size;
 
         if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR))
                 return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
@@ -608,8 +609,11 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space)
         /* For now, get space for all other nodes 
            (will need to modify this when slave nodes are supported */
 
-        buf = tipc_cfg_reply_alloc(TLV_SPACE(sizeof(node_info)) *
-                                   (tipc_max_nodes - 1));
+        payload_size = TLV_SPACE(sizeof(node_info)) * (tipc_max_nodes - 1);
+        if (payload_size > 32768u)
+                return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
+                                                   " (too many nodes)");
+        buf = tipc_cfg_reply_alloc(payload_size);
         if (!buf)
                 return NULL;
 
@@ -633,6 +637,7 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
         struct sk_buff *buf;
         struct node *n_ptr;
         struct tipc_link_info link_info;
+        u32 payload_size;
 
         if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR))
                 return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
@@ -645,12 +650,15 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
 
         if (!tipc_nodes)
                 return tipc_cfg_reply_none();
-
-        /* For now, get space for 2 links to all other nodes + bcast link 
-           (will need to modify this when slave nodes are supported */
-
-        buf = tipc_cfg_reply_alloc(TLV_SPACE(sizeof(link_info)) *
-                                   (2 * (tipc_max_nodes - 1) + 1));
+        
+        /* Get space for all unicast links + multicast link */
+
+        payload_size = TLV_SPACE(sizeof(link_info)) *
+                (tipc_net.zones[tipc_zone(tipc_own_addr)]->links + 1);
+        if (payload_size > 32768u)
+                return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
+                                                   " (too many links)");
+        buf = tipc_cfg_reply_alloc(payload_size);
         if (!buf)
                 return NULL;
 
diff --git a/net/tipc/zone.h b/net/tipc/zone.h
index 267999c5a240..5ab3d08602e2 100644
--- a/net/tipc/zone.h
+++ b/net/tipc/zone.h
@@ -2,7 +2,7 @@
  * net/tipc/zone.h: Include file for TIPC zone management routines
  * 
  * Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2005, Wind River Systems
+ * Copyright (c) 2005-2006, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -45,7 +45,7 @@
  * struct _zone - TIPC zone structure
  * @addr: network address of zone
  * @clusters: array of pointers to all clusters within zone
- * @links: (used for inter-zone communication)
+ * @links: number of (unicast) links to zone
  */
  
 struct _zone {
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d901465ce013..fd11d4048b52 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -128,6 +128,30 @@ static atomic_t unix_nr_socks = ATOMIC_INIT(0);
 
 #define UNIX_ABSTRACT(sk)       (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)
 
+#ifdef CONFIG_SECURITY_NETWORK
+static void unix_get_peersec_dgram(struct sk_buff *skb)
+{
+        int err;
+
+        err = security_socket_getpeersec_dgram(skb, UNIXSECDATA(skb),
+                                               UNIXSECLEN(skb));
+        if (err)
+                *(UNIXSECDATA(skb)) = NULL;
+}
+
+static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
+{
+        scm->secdata = *UNIXSECDATA(skb);
+        scm->seclen = *UNIXSECLEN(skb);
+}
+#else
+static void unix_get_peersec_dgram(struct sk_buff *skb)
+{ }
+
+static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
+{ }
+#endif /* CONFIG_SECURITY_NETWORK */
+
 /*
  *  SMP locking strategy:
  *    hash table is protected with spinlock unix_table_lock
@@ -1291,6 +1315,8 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
         if (siocb->scm->fp)
                 unix_attach_fds(siocb->scm, skb);
 
+        unix_get_peersec_dgram(skb);
+
         skb->h.raw = skb->data;
         err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
         if (err)
@@ -1570,6 +1596,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
                 memset(&tmp_scm, 0, sizeof(tmp_scm));
         }
         siocb->scm->creds = *UNIXCREDS(skb);
+        unix_set_secdata(siocb->scm, skb);
 
         if (!(flags & MSG_PEEK))
         {
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 17b29ec3c417..43f00fc28a3d 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1164,8 +1164,6 @@ int xfrm_state_mtu(struct xfrm_state *x, int mtu)
         return res;
 }
 
-EXPORT_SYMBOL(xfrm_state_mtu);
-
 int xfrm_init_state(struct xfrm_state *x)
 {
         struct xfrm_state_afinfo *afinfo;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index c21dc26141ea..3e6a722d072e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1435,7 +1435,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *err
         link = &xfrm_dispatch[type];
 
         /* All operations require privileges, even GET */
-        if (security_netlink_recv(skb)) {
+        if (security_netlink_recv(skb, CAP_NET_ADMIN)) {
                 *errp = -EPERM;
                 return -1;
         }
diff --git a/security/commoncap.c b/security/commoncap.c
index 841eb4e5c62b..57673ee07ceb 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -33,9 +33,9 @@ int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
 
 EXPORT_SYMBOL(cap_netlink_send);
 
-int cap_netlink_recv(struct sk_buff *skb)
+int cap_netlink_recv(struct sk_buff *skb, int cap)
 {
-        if (!cap_raised(NETLINK_CB(skb).eff_cap, CAP_NET_ADMIN))
+        if (!cap_raised(NETLINK_CB(skb).eff_cap, cap))
                 return -EPERM;
         return 0;
 }
diff --git a/security/dummy.c b/security/dummy.c
index 310fcdf7b749..d417936562db 100644
--- a/security/dummy.c
+++ b/security/dummy.c
@@ -506,6 +506,9 @@ static int dummy_task_getsid (struct task_struct *p)
         return 0;
 }
 
+static void dummy_task_getsecid (struct task_struct *p, u32 *secid)
+{ }
+
 static int dummy_task_setgroups (struct group_info *group_info)
 {
         return 0;
@@ -521,6 +524,11 @@ static int dummy_task_setioprio (struct task_struct *p, int ioprio)
         return 0;
 }
 
+static int dummy_task_getioprio (struct task_struct *p)
+{
+        return 0;
+}
+
 static int dummy_task_setrlimit (unsigned int resource, struct rlimit *new_rlim)
 {
         return 0;
@@ -548,7 +556,7 @@ static int dummy_task_wait (struct task_struct *p)
 }
 
 static int dummy_task_kill (struct task_struct *p, struct siginfo *info,
-                            int sig)
+                            int sig, u32 secid)
 {
         return 0;
 }
@@ -675,9 +683,9 @@ static int dummy_netlink_send (struct sock *sk, struct sk_buff *skb)
         return 0;
 }
 
-static int dummy_netlink_recv (struct sk_buff *skb)
+static int dummy_netlink_recv (struct sk_buff *skb, int cap)
 {
-        if (!cap_raised (NETLINK_CB (skb).eff_cap, CAP_NET_ADMIN))
+        if (!cap_raised (NETLINK_CB (skb).eff_cap, cap))
                 return -EPERM;
         return 0;
 }
@@ -981,9 +989,11 @@ void security_fixup_ops (struct security_operations *ops)
         set_to_dummy_if_null(ops, task_setpgid);
         set_to_dummy_if_null(ops, task_getpgid);
         set_to_dummy_if_null(ops, task_getsid);
+        set_to_dummy_if_null(ops, task_getsecid);
         set_to_dummy_if_null(ops, task_setgroups);
         set_to_dummy_if_null(ops, task_setnice);
         set_to_dummy_if_null(ops, task_setioprio);
+        set_to_dummy_if_null(ops, task_getioprio);
         set_to_dummy_if_null(ops, task_setrlimit);
         set_to_dummy_if_null(ops, task_setscheduler);
         set_to_dummy_if_null(ops, task_getscheduler);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 28832e689800..51bec4c88f19 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -69,6 +69,7 @@
 #include <linux/sysctl.h>
 #include <linux/audit.h>
 #include <linux/string.h>
+#include <linux/selinux.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -2643,6 +2644,11 @@ static int selinux_task_getsid(struct task_struct *p)
         return task_has_perm(current, p, PROCESS__GETSESSION);
 }
 
+static void selinux_task_getsecid(struct task_struct *p, u32 *secid)
+{
+        selinux_get_task_sid(p, secid);
+}
+
 static int selinux_task_setgroups(struct group_info *group_info)
 {
         /* See the comment for setuid above. */
@@ -2665,6 +2671,11 @@ static int selinux_task_setioprio(struct task_struct *p, int ioprio)
         return task_has_perm(current, p, PROCESS__SETSCHED);
 }
 
+static int selinux_task_getioprio(struct task_struct *p)
+{
+        return task_has_perm(current, p, PROCESS__GETSCHED);
+}
+
 static int selinux_task_setrlimit(unsigned int resource, struct rlimit *new_rlim)
 {
         struct rlimit *old_rlim = current->signal->rlim + resource;
@@ -2699,12 +2710,14 @@ static int selinux_task_movememory(struct task_struct *p)
         return task_has_perm(current, p, PROCESS__SETSCHED);
 }
 
-static int selinux_task_kill(struct task_struct *p, struct siginfo *info, int sig)
+static int selinux_task_kill(struct task_struct *p, struct siginfo *info,
+                                int sig, u32 secid)
 {
         u32 perm;
         int rc;
+        struct task_security_struct *tsec;
 
-        rc = secondary_ops->task_kill(p, info, sig);
+        rc = secondary_ops->task_kill(p, info, sig, secid);
         if (rc)
                 return rc;
 
@@ -2715,8 +2728,12 @@ static int selinux_task_kill(struct task_struct *p, struct siginfo *info, int si
                 perm = PROCESS__SIGNULL; /* null signal; existence test */
         else
                 perm = signal_to_av(sig);
-
-        return task_has_perm(current, p, perm);
+        tsec = p->security;
+        if (secid)
+                rc = avc_has_perm(secid, tsec->sid, SECCLASS_PROCESS, perm, NULL);
+        else
+                rc = task_has_perm(current, p, perm);
+        return rc;
 }
 
 static int selinux_task_prctl(int option,
@@ -3420,7 +3437,13 @@ out:
 static int selinux_socket_getpeersec_dgram(struct sk_buff *skb, char **secdata, u32 *seclen)
 {
         int err = 0;
-        u32 peer_sid = selinux_socket_getpeer_dgram(skb);
+        u32 peer_sid;
+
+        if (skb->sk->sk_family == PF_UNIX)
+                selinux_get_inode_sid(SOCK_INODE(skb->sk->sk_socket),
+                                      &peer_sid);
+        else
+                peer_sid = selinux_socket_getpeer_dgram(skb);
 
         if (peer_sid == SECSID_NULL)
                 return -EINVAL;
@@ -3432,8 +3455,6 @@ static int selinux_socket_getpeersec_dgram(struct sk_buff *skb, char **secdata,
         return 0;
 }
 
-
-
 static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority)
 {
         return sk_alloc_security(sk, family, priority);
@@ -3641,32 +3662,32 @@ static unsigned int selinux_ipv6_postroute_last(unsigned int hooknum,
 
 static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-        struct task_security_struct *tsec;
-        struct av_decision avd;
         int err;
 
         err = secondary_ops->netlink_send(sk, skb);
         if (err)
                 return err;
 
-        tsec = current->security;
-
-        avd.allowed = 0;
-        avc_has_perm_noaudit(tsec->sid, tsec->sid,
-                                SECCLASS_CAPABILITY, ~0, &avd);
-        cap_mask(NETLINK_CB(skb).eff_cap, avd.allowed);
-
         if (policydb_loaded_version >= POLICYDB_VERSION_NLCLASS)
                 err = selinux_nlmsg_perm(sk, skb);
 
         return err;
 }
 
-static int selinux_netlink_recv(struct sk_buff *skb)
+static int selinux_netlink_recv(struct sk_buff *skb, int capability)
 {
-        if (!cap_raised(NETLINK_CB(skb).eff_cap, CAP_NET_ADMIN))
-                return -EPERM;
-        return 0;
+        int err;
+        struct avc_audit_data ad;
+
+        err = secondary_ops->netlink_recv(skb, capability);
+        if (err)
+                return err;
+
+        AVC_AUDIT_DATA_INIT(&ad, CAP);
+        ad.u.cap = capability;
+
+        return avc_has_perm(NETLINK_CB(skb).sid, NETLINK_CB(skb).sid,
+                            SECCLASS_CAPABILITY, CAP_TO_MASK(capability), &ad);
 }
 
 static int ipc_alloc_security(struct task_struct *task,
@@ -4429,9 +4450,11 @@ static struct security_operations selinux_ops = {
         .task_setpgid =                 selinux_task_setpgid,
         .task_getpgid =                 selinux_task_getpgid,
         .task_getsid =                  selinux_task_getsid,
+        .task_getsecid =                selinux_task_getsecid,
         .task_setgroups =               selinux_task_setgroups,
         .task_setnice =                 selinux_task_setnice,
         .task_setioprio =               selinux_task_setioprio,
+        .task_getioprio =               selinux_task_getioprio,
         .task_setrlimit =               selinux_task_setrlimit,
         .task_setscheduler =            selinux_task_setscheduler,
         .task_getscheduler =            selinux_task_getscheduler,